diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2026-01-22 20:13:25 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-01-22 20:14:36 -0800 |
| commit | 9abf22075da98c615be2f608ec1167329a71eafd (patch) | |
| tree | 8b2da9cc0b7f9410e3619223a679467d40391004 | |
| parent | 0b87bbf65d7d33754fd12df5984b9741e886dc69 (diff) | |
| parent | 0a80e38d0fe1fe7b59c1e93ad908c4148a15926a (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR (net-6.19-rc7).
Conflicts:
drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
b35a6fd37a00 ("hinic3: Add adaptive IRQ coalescing with DIM")
fb2bb2a1ebf7 ("hinic3: Fix netif_queue_set_napi queue_index input parameter error")
https://lore.kernel.org/fc0a7fdf08789a52653e8ad05281a0a849e79206.1768915707.git.zhuyikai1@h-partners.com
drivers/net/wireless/ath/ath12k/mac.c
drivers/net/wireless/ath/ath12k/wifi7/hw.c
31707572108d ("wifi: ath12k: Fix wrong P2P device link id issue")
c26f294fef2a ("wifi: ath12k: Move ieee80211_ops callback to the arch specific module")
https://lore.kernel.org/20260114123751.6a208818@canb.auug.org.au
Adjacent changes:
drivers/net/wireless/ath/ath12k/mac.c
8b8d6ee53dfd ("wifi: ath12k: Fix scan state stuck in ABORTING after cancel_remain_on_channel")
914c890d3b90 ("wifi: ath12k: Add framework for hardware specific ieee80211_ops registration")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
425 files changed, 4715 insertions, 2343 deletions
@@ -12,6 +12,7 @@ # Aaron Durbin <adurbin@google.com> Abel Vesa <abelvesa@kernel.org> <abel.vesa@nxp.com> +Abel Vesa <abelvesa@kernel.org> <abel.vesa@linaro.org> Abel Vesa <abelvesa@kernel.org> <abelvesa@gmail.com> Abhijeet Dharmapurikar <quic_adharmap@quicinc.com> <adharmap@codeaurora.org> Abhinav Kumar <quic_abhinavk@quicinc.com> <abhinavk@codeaurora.org> @@ -207,6 +208,7 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch> Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com> +Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org> Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com> David Brownell <david-b@pacbell.net> David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org> @@ -794,6 +796,7 @@ Sven Eckelmann <sven@narfation.org> <sven.eckelmann@open-mesh.com> Sven Eckelmann <sven@narfation.org> <sven.eckelmann@openmesh.com> Sven Eckelmann <sven@narfation.org> <sven@open-mesh.com> Sven Peter <sven@kernel.org> <sven@svenpeter.dev> +Szymon Wilczek <swilczek.lx@gmail.com> <szymonwilczek@gmx.com> Takashi YOSHII <takashi.yoshii.zj@renesas.com> Tamizh Chelvam Raja <quic_tamizhr@quicinc.com> <tamizhr@codeaurora.org> Taniya Das <quic_tdas@quicinc.com> <tdas@codeaurora.org> @@ -876,6 +879,8 @@ Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn> Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com> +Yixun Lan <dlan@kernel.org> <dlan@gentoo.org> +Yixun Lan <dlan@kernel.org> <yixun.lan@amlogic.com> Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com> Yu-Chun Lin <eleanor.lin@realtek.com> <eleanor15x@gmail.com> Yusuke Goda <goda.yusuke@renesas.com> @@ -2231,6 +2231,10 @@ S: Markham, Ontario S: L3R 8B2 S: Canada +N: Krzysztof Kozlowski +E: krzk@kernel.org +D: NFC network subsystem and drivers maintainer + N: Christian Krafft D: PowerPC Cell support diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a8d0afde7f85..1058f2a6d6a8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2917,6 +2917,41 @@ Kernel parameters for Movable pages. "nn[KMGTPE]", "nn%", and "mirror" are exclusive, so you cannot specify multiple forms. + kfence.burst= [MM,KFENCE] The number of additional successive + allocations to be attempted through KFENCE for each + sample interval. + Format: <unsigned integer> + Default: 0 + + kfence.check_on_panic= + [MM,KFENCE] Whether to check all KFENCE-managed objects' + canaries on panic. + Format: <bool> + Default: false + + kfence.deferrable= + [MM,KFENCE] Whether to use a deferrable timer to trigger + allocations. This avoids forcing CPU wake-ups if the + system is idle, at the risk of a less predictable + sample interval. + Format: <bool> + Default: CONFIG_KFENCE_DEFERRABLE + + kfence.sample_interval= + [MM,KFENCE] KFENCE's sample interval in milliseconds. + Format: <unsigned integer> + 0 - Disable KFENCE. + >0 - Enabled KFENCE with given sample interval. + Default: CONFIG_KFENCE_SAMPLE_INTERVAL + + kfence.skip_covered_thresh= + [MM,KFENCE] If pool utilization reaches this threshold + (pool usage%), KFENCE limits currently covered + allocations of the same source from further filling + up the pool. + Format: <unsigned integer> + Default: 75 + kgdbdbgp= [KGDB,HW,EARLY] kgdb over EHCI usb debug port. Format: <Controller#>[,poll interval] The controller # is the number of the ehci usb debug diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 4d71211fdad8..245bf6394935 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -494,6 +494,10 @@ memory allocations. The default value depends on CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT. +When CONFIG_MEM_ALLOC_PROFILING_DEBUG=y, this control is read-only to avoid +warnings produced by allocations made while profiling is disabled and freed +when it's enabled. + memory_failure_early_kill ========================= diff --git a/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml b/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml index 2aa75b7add7b..daa70a8500e9 100644 --- a/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/brcm,iproc-i2c.yaml @@ -16,7 +16,8 @@ properties: - brcm,iproc-nic-i2c reg: - maxItems: 1 + minItems: 1 + maxItems: 2 clock-frequency: enum: [ 100000, 400000 ] @@ -41,8 +42,15 @@ allOf: contains: const: brcm,iproc-nic-i2c then: + properties: + reg: + minItems: 2 required: - brcm,ape-hsls-addr-mask + else: + properties: + reg: + maxItems: 1 unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index 48bd11410e8c..f5068df20cfe 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -56,7 +56,7 @@ properties: clocks: minItems: 5 - maxItems: 7 + maxItems: 6 clock-names: minItems: 5 @@ -67,7 +67,6 @@ properties: - enum: [rchng, refgen] - const: pipe - const: pipediv2 - - const: phy_aux power-domains: maxItems: 1 @@ -180,6 +179,7 @@ allOf: contains: enum: - qcom,glymur-qmp-gen5x4-pcie-phy + - qcom,qcs8300-qmp-gen4x2-pcie-phy - qcom,sa8775p-qmp-gen4x2-pcie-phy - qcom,sa8775p-qmp-gen4x4-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy @@ -202,19 +202,6 @@ allOf: compatible: contains: enum: - - qcom,qcs8300-qmp-gen4x2-pcie-phy - then: - properties: - clocks: - minItems: 7 - clock-names: - minItems: 7 - - - if: - properties: - compatible: - contains: - enum: - qcom,glymur-qmp-gen5x4-pcie-phy - qcom,sm8550-qmp-gen4x2-pcie-phy - qcom,sm8650-qmp-gen4x2-pcie-phy diff --git a/Documentation/devicetree/bindings/sound/everest,es8316.yaml b/Documentation/devicetree/bindings/sound/everest,es8316.yaml index 81a0215050e0..fe5d938ca310 100644 --- a/Documentation/devicetree/bindings/sound/everest,es8316.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es8316.yaml @@ -49,6 +49,10 @@ properties: items: - const: mclk + interrupts: + maxItems: 1 + description: Headphone detect interrupt + port: $ref: audio-graph-port.yaml# unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml index 3f4f59287c1c..2eb631950963 100644 --- a/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml +++ b/Documentation/devicetree/bindings/sound/realtek,rt5640.yaml @@ -47,6 +47,12 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 1 + + clock-names: + const: mclk + interrupts: maxItems: 1 description: The CODEC's interrupt output. @@ -98,6 +104,7 @@ properties: - 4 # Use GPIO2 for jack-detect - 5 # Use GPIO3 for jack-detect - 6 # Use GPIO4 for jack-detect + - 7 # Use HDA header for jack-detect realtek,jack-detect-not-inverted: description: @@ -121,6 +128,10 @@ properties: - 2 # Scale current by 1.0 - 3 # Scale current by 1.5 + port: + $ref: audio-graph-port.yaml# + unevaluatedProperties: false + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml index 32dea7392e8d..56c755c22945 100644 --- a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml +++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml @@ -70,6 +70,9 @@ properties: "#sound-dai-cells": const: 0 + port: + $ref: /schemas/graph.yaml#/properties/port + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml index a792434c59db..a7f58114c02e 100644 --- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml @@ -406,7 +406,6 @@ allOf: compatible: contains: enum: - - qcom,ipq5018-dwc3 - qcom,ipq6018-dwc3 - qcom,ipq8074-dwc3 - qcom,msm8953-dwc3 @@ -428,6 +427,7 @@ allOf: compatible: contains: enum: + - qcom,msm8994-dwc3 - qcom,msm8996-dwc3 - qcom,qcs404-dwc3 - qcom,sdm660-dwc3 @@ -451,6 +451,7 @@ allOf: compatible: contains: enum: + - qcom,ipq5018-dwc3 - qcom,ipq5332-dwc3 then: properties: @@ -488,7 +489,6 @@ allOf: enum: - qcom,ipq4019-dwc3 - qcom,ipq8064-dwc3 - - qcom,msm8994-dwc3 - qcom,qcs615-dwc3 - qcom,qcs8300-dwc3 - qcom,qdu1000-dwc3 diff --git a/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml index 8cee7c5582f2..7d784a648b7d 100644 --- a/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml @@ -420,7 +420,6 @@ allOf: compatible: contains: enum: - - qcom,ipq5018-dwc3 - qcom,ipq6018-dwc3 - qcom,ipq8074-dwc3 - qcom,msm8953-dwc3 @@ -443,6 +442,7 @@ allOf: compatible: contains: enum: + - qcom,msm8994-dwc3 - qcom,msm8996-dwc3 - qcom,qcs404-dwc3 - qcom,sdm660-dwc3 @@ -467,6 +467,7 @@ allOf: compatible: contains: enum: + - qcom,ipq5018-dwc3 - qcom,ipq5332-dwc3 then: properties: @@ -509,7 +510,6 @@ allOf: - qcom,ipq4019-dwc3 - qcom,ipq8064-dwc3 - qcom,kaanapali-dwc3 - - qcom,msm8994-dwc3 - qcom,qcs615-dwc3 - qcom,qcs8300-dwc3 - qcom,qdu1000-dwc3 diff --git a/Documentation/mm/allocation-profiling.rst b/Documentation/mm/allocation-profiling.rst index 316311240e6a..5389d241176a 100644 --- a/Documentation/mm/allocation-profiling.rst +++ b/Documentation/mm/allocation-profiling.rst @@ -33,6 +33,16 @@ Boot parameter: sysctl: /proc/sys/vm/mem_profiling + 1: Enable memory profiling. + + 0: Disable memory profiling. + + The default value depends on CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT. + + When CONFIG_MEM_ALLOC_PROFILING_DEBUG=y, this control is read-only to avoid + warnings produced by allocations made while profiling is disabled and freed + when it's enabled. + Runtime info: /proc/allocinfo diff --git a/Documentation/netlink/specs/dev-energymodel.yaml b/Documentation/netlink/specs/dev-energymodel.yaml new file mode 100644 index 000000000000..11faabfdfbe8 --- /dev/null +++ b/Documentation/netlink/specs/dev-energymodel.yaml @@ -0,0 +1,175 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +# +# Copyright (c) 2025 Valve Corporation. +# +--- +name: dev-energymodel + +doc: | + Energy model netlink interface to notify its changes. + +protocol: genetlink + +uapi-header: linux/dev_energymodel.h + +definitions: + - + type: flags + name: perf-state-flags + entries: + - + name: perf-state-inefficient + doc: >- + The performance state is inefficient. There is in this perf-domain, + another performance state with a higher frequency but a lower or + equal power cost. + - + type: flags + name: perf-domain-flags + entries: + - + name: perf-domain-microwatts + doc: >- + The power values are in micro-Watts or some other scale. + - + name: perf-domain-skip-inefficiencies + doc: >- + Skip inefficient states when estimating energy consumption. + - + name: perf-domain-artificial + doc: >- + The power values are artificial and might be created by platform + missing real power information. + +attribute-sets: + - + name: perf-domain + doc: >- + Information on a single performance domains. + attributes: + - + name: pad + type: pad + - + name: perf-domain-id + type: u32 + doc: >- + A unique ID number for each performance domain. + - + name: flags + type: u64 + doc: >- + Bitmask of performance domain flags. + enum: perf-domain-flags + - + name: cpus + type: u64 + multi-attr: true + doc: >- + CPUs that belong to this performance domain. + - + name: perf-table + doc: >- + Performance states table. + attributes: + - + name: perf-domain-id + type: u32 + doc: >- + A unique ID number for each performance domain. + - + name: perf-state + type: nest + nested-attributes: perf-state + multi-attr: true + - + name: perf-state + doc: >- + Performance state of a performance domain. + attributes: + - + name: pad + type: pad + - + name: performance + type: u64 + doc: >- + CPU performance (capacity) at a given frequency. + - + name: frequency + type: u64 + doc: >- + The frequency in KHz, for consistency with CPUFreq. + - + name: power + type: u64 + doc: >- + The power consumed at this level (by 1 CPU or by a registered + device). It can be a total power: static and dynamic. + - + name: cost + type: u64 + doc: >- + The cost coefficient associated with this level, used during energy + calculation. Equal to: power * max_frequency / frequency. + - + name: flags + type: u64 + doc: >- + Bitmask of performance state flags. + enum: perf-state-flags + +operations: + list: + - + name: get-perf-domains + attribute-set: perf-domain + doc: Get the list of information for all performance domains. + do: + request: + attributes: + - perf-domain-id + reply: + attributes: &perf-domain-attrs + - pad + - perf-domain-id + - flags + - cpus + dump: + reply: + attributes: *perf-domain-attrs + - + name: get-perf-table + attribute-set: perf-table + doc: Get the energy model table of a performance domain. + do: + request: + attributes: + - perf-domain-id + reply: + attributes: + - perf-domain-id + - perf-state + - + name: perf-domain-created + doc: A performance domain is created. + notify: get-perf-table + mcgrp: event + - + name: perf-domain-updated + doc: A performance domain is updated. + notify: get-perf-table + mcgrp: event + - + name: perf-domain-deleted + doc: A performance domain is deleted. + attribute-set: perf-table + event: + attributes: + - perf-domain-id + mcgrp: event + +mcast-groups: + list: + - + name: event diff --git a/Documentation/netlink/specs/em.yaml b/Documentation/netlink/specs/em.yaml deleted file mode 100644 index 9905ca482325..000000000000 --- a/Documentation/netlink/specs/em.yaml +++ /dev/null @@ -1,113 +0,0 @@ -# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) - -name: em - -doc: | - Energy model netlink interface to notify its changes. - -protocol: genetlink - -uapi-header: linux/energy_model.h - -attribute-sets: - - - name: pds - attributes: - - - name: pd - type: nest - nested-attributes: pd - multi-attr: true - - - name: pd - attributes: - - - name: pad - type: pad - - - name: pd-id - type: u32 - - - name: flags - type: u64 - - - name: cpus - type: string - - - name: pd-table - attributes: - - - name: pd-id - type: u32 - - - name: ps - type: nest - nested-attributes: ps - multi-attr: true - - - name: ps - attributes: - - - name: pad - type: pad - - - name: performance - type: u64 - - - name: frequency - type: u64 - - - name: power - type: u64 - - - name: cost - type: u64 - - - name: flags - type: u64 - -operations: - list: - - - name: get-pds - attribute-set: pds - doc: Get the list of information for all performance domains. - do: - reply: - attributes: - - pd - - - name: get-pd-table - attribute-set: pd-table - doc: Get the energy model table of a performance domain. - do: - request: - attributes: - - pd-id - reply: - attributes: - - pd-id - - ps - - - name: pd-created - doc: A performance domain is created. - notify: get-pd-table - mcgrp: event - - - name: pd-updated - doc: A performance domain is updated. - notify: get-pd-table - mcgrp: event - - - name: pd-deleted - doc: A performance domain is deleted. - attribute-set: pd-table - event: - attributes: - - pd-id - mcgrp: event - -mcast-groups: - list: - - - name: event diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml index 8e7974ec453f..331f1b342b3a 100644 --- a/Documentation/netlink/specs/fou.yaml +++ b/Documentation/netlink/specs/fou.yaml @@ -39,6 +39,8 @@ attribute-sets: - name: ipproto type: u8 + checks: + min: 1 - name: type type: u8 diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 989192421cc9..6bce4507d5d3 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -363,6 +363,18 @@ just do it. As a result, a sequence of smaller series gets merged quicker and with better review coverage. Re-posting large series also increases the mailing list traffic. +Limit patches outstanding on mailing list +----------------------------------------- + +Avoid having more than 15 patches, across all series, outstanding for +review on the mailing list for a single tree. In other words, a maximum of +15 patches under review on net, and a maximum of 15 patches under review on +net-next. + +This limit is intended to focus developer effort on testing patches before +upstream review. Aiding the quality of upstream submissions, and easing the +load on reviewers. + .. _rcs: Local variable ordering ("reverse xmas tree", "RCS") diff --git a/MAINTAINERS b/MAINTAINERS index 92768bceb929..ed816ef6e57c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -314,6 +314,7 @@ R: Mauro Carvalho Chehab <mchehab@kernel.org> R: Shuai Xue <xueshuai@linux.alibaba.com> L: linux-acpi@vger.kernel.org F: drivers/acpi/apei/ +F: drivers/firmware/efi/cper* ACPI COMPONENT ARCHITECTURE (ACPICA) M: "Rafael J. Wysocki" <rafael@kernel.org> @@ -3131,6 +3132,7 @@ F: drivers/*/*ma35* K: ma35d1 ARM/NUVOTON NPCM ARCHITECTURE +M: Andrew Jeffery <andrew@codeconstruct.com.au> M: Avi Fishman <avifishman70@gmail.com> M: Tomer Maimon <tmaimon77@gmail.com> M: Tali Perry <tali.perry1@gmail.com> @@ -3139,6 +3141,7 @@ R: Nancy Yuen <yuenn@google.com> R: Benjamin Fair <benjaminfair@google.com> L: openbmc@lists.ozlabs.org (moderated for non-subscribers) S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/bmc/linux.git F: Documentation/devicetree/bindings/*/*/*npcm* F: Documentation/devicetree/bindings/*/*npcm* F: Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml @@ -6420,6 +6423,7 @@ F: include/linux/blk-cgroup.h CONTROL GROUP - CPUSET M: Waiman Long <longman@redhat.com> +R: Chen Ridong <chenridong@huaweicloud.com> L: cgroups@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git @@ -9303,12 +9307,12 @@ M: Lukasz Luba <lukasz.luba@arm.com> M: "Rafael J. Wysocki" <rafael@kernel.org> L: linux-pm@vger.kernel.org S: Maintained -F: kernel/power/energy_model.c -F: include/linux/energy_model.h +F: Documentation/netlink/specs/dev-energymodel.yaml F: Documentation/power/energy-model.rst -F: Documentation/netlink/specs/em.yaml -F: include/uapi/linux/energy_model.h +F: include/linux/energy_model.h +F: include/uapi/linux/dev_energymodel.h F: kernel/power/em_netlink*.* +F: kernel/power/energy_model.c EPAPR HYPERVISOR BYTE CHANNEL DEVICE DRIVER M: Laurentiu Tudor <laurentiu.tudor@nxp.com> @@ -9519,6 +9523,7 @@ F: arch/arm/boot/compressed/efi-header.S F: arch/x86/platform/efi/ F: drivers/firmware/efi/ F: include/linux/efi*.h +X: drivers/firmware/efi/cper* EXTERNAL CONNECTOR SUBSYSTEM (EXTCON) M: MyungJoo Ham <myungjoo.ham@samsung.com> @@ -18490,9 +18495,8 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzk@kernel.org> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/net/nfc/ @@ -21119,6 +21123,10 @@ S: Maintained F: rust/helpers/pwm.c F: rust/kernel/pwm.rs +PWM SUBSYSTEM DRIVERS [RUST] +R: Michal Wilczynski <m.wilczynski@samsung.com> +F: drivers/pwm/*.rs + PXA GPIO DRIVER M: Robert Jarzmik <robert.jarzmik@free.fr> L: linux-gpio@vger.kernel.org @@ -22548,7 +22556,7 @@ F: drivers/mailbox/riscv-sbi-mpxy-mbox.c F: include/linux/mailbox/riscv-rpmi-message.h RISC-V SPACEMIT SoC Support -M: Yixun Lan <dlan@gentoo.org> +M: Yixun Lan <dlan@kernel.org> L: linux-riscv@lists.infradead.org L: spacemit@lists.linux.dev S: Maintained @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts b/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts index 3b7577e48b46..50bd29572f3e 100644 --- a/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts +++ b/arch/arm/boot/dts/microchip/lan966x-pcb8290.dts @@ -54,6 +54,7 @@ &mdio0 { pinctrl-0 = <&miim_a_pins>; pinctrl-names = "default"; + reset-gpios = <&gpio 53 GPIO_ACTIVE_LOW>; status = "okay"; ext_phy0: ethernet-phy@7 { diff --git a/arch/arm/boot/dts/microchip/sama7d65.dtsi b/arch/arm/boot/dts/microchip/sama7d65.dtsi index cd2cf9a6f40b..868045c650a7 100644 --- a/arch/arm/boot/dts/microchip/sama7d65.dtsi +++ b/arch/arm/boot/dts/microchip/sama7d65.dtsi @@ -527,7 +527,7 @@ interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; clocks = <&pmc PMC_TYPE_PERIPHERAL 37>; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; dmas = <&dma0 AT91_XDMAC_DT_PERID(12)>, <&dma0 AT91_XDMAC_DT_PERID(11)>; dma-names = "tx", "rx"; @@ -676,7 +676,7 @@ flx9: flexcom@e2820000 { compatible = "microchip,sama7d65-flexcom", "atmel,sama5d2-flexcom"; reg = <0xe2820000 0x200>; - ranges = <0x0 0xe281c000 0x800>; + ranges = <0x0 0xe2820000 0x800>; clocks = <&pmc PMC_TYPE_PERIPHERAL 43>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/mach-npcm/Kconfig b/arch/arm/mach-npcm/Kconfig index 63b42a19d1b8..d933e8abb50f 100644 --- a/arch/arm/mach-npcm/Kconfig +++ b/arch/arm/mach-npcm/Kconfig @@ -30,7 +30,6 @@ config ARCH_NPCM7XX select ARM_ERRATA_764369 if SMP select ARM_ERRATA_720789 select ARM_ERRATA_754322 - select ARM_ERRATA_794072 select PL310_ERRATA_588369 select PL310_ERRATA_727915 select MFD_SYSCON diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 709da31d5785..137aa8375257 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -202,19 +202,6 @@ nvidia,outputs = <&dsia &dsib &sor0 &sor1>; nvidia,head = <0>; - - interconnects = <&mc TEGRA210_MC_DISPLAY0A &emc>, - <&mc TEGRA210_MC_DISPLAY0B &emc>, - <&mc TEGRA210_MC_DISPLAY0C &emc>, - <&mc TEGRA210_MC_DISPLAYHC &emc>, - <&mc TEGRA210_MC_DISPLAYD &emc>, - <&mc TEGRA210_MC_DISPLAYT &emc>; - interconnect-names = "wina", - "winb", - "winc", - "cursor", - "wind", - "wint"; }; dc@54240000 { @@ -230,15 +217,6 @@ nvidia,outputs = <&dsia &dsib &sor0 &sor1>; nvidia,head = <1>; - - interconnects = <&mc TEGRA210_MC_DISPLAY0AB &emc>, - <&mc TEGRA210_MC_DISPLAY0BB &emc>, - <&mc TEGRA210_MC_DISPLAY0CB &emc>, - <&mc TEGRA210_MC_DISPLAYHCB &emc>; - interconnect-names = "wina", - "winb", - "winc", - "cursor"; }; dsia: dsi@54300000 { @@ -1052,7 +1030,6 @@ #iommu-cells = <1>; #reset-cells = <1>; - #interconnect-cells = <1>; }; emc: external-memory-controller@7001b000 { @@ -1066,7 +1043,6 @@ nvidia,memory-controller = <&mc>; operating-points-v2 = <&emc_icc_dvfs_opp_table>; - #interconnect-cells = <0>; #cooling-cells = <2>; }; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 5334adebf278..b9e0d9c7c065 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -5788,8 +5788,12 @@ clocks = <&rpmhcc RPMH_CXO_CLK>; clock-names = "xo"; - power-domains = <&rpmhpd SC8280XP_NSP>; - power-domain-names = "nsp"; + power-domains = <&rpmhpd SC8280XP_NSP>, + <&rpmhpd SC8280XP_CX>, + <&rpmhpd SC8280XP_MXC>; + power-domain-names = "nsp", + "cx", + "mxc"; memory-region = <&pil_nsp0_mem>; @@ -5919,8 +5923,12 @@ clocks = <&rpmhcc RPMH_CXO_CLK>; clock-names = "xo"; - power-domains = <&rpmhpd SC8280XP_NSP>; - power-domain-names = "nsp"; + power-domains = <&rpmhpd SC8280XP_NSP>, + <&rpmhpd SC8280XP_CX>, + <&rpmhpd SC8280XP_MXC>; + power-domain-names = "nsp", + "cx", + "mxc"; memory-region = <&pil_nsp1_mem>; diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts b/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts index a259eb9d45ae..8aead6dc25e0 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-enchilada.dts @@ -31,9 +31,9 @@ }; &display_panel { - status = "okay"; + compatible = "samsung,sofef00-ams628nw01", "samsung,sofef00"; - compatible = "samsung,sofef00"; + status = "okay"; }; &bq27441_fg { diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 2ca9e50ef599..e3f93f4f412d 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -4133,8 +4133,6 @@ usb_1: usb@a600000 { compatible = "qcom,sm8550-dwc3", "qcom,snps-dwc3"; reg = <0x0 0x0a600000 0x0 0xfc100>; - #address-cells = <1>; - #size-cells = <0>; clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>, <&gcc GCC_USB30_PRIM_MASTER_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 07ae74851621..f8e1950a74ac 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -5150,9 +5150,6 @@ dma-coherent; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/qcom/talos.dtsi b/arch/arm64/boot/dts/qcom/talos.dtsi index d1dbfa3bd81c..95d26e313622 100644 --- a/arch/arm64/boot/dts/qcom/talos.dtsi +++ b/arch/arm64/boot/dts/qcom/talos.dtsi @@ -1399,10 +1399,10 @@ <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>, <&gcc GCC_UFS_PHY_AHB_CLK>, <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>, - <&gcc GCC_UFS_PHY_ICE_CORE_CLK>, <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>, - <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>; + <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>, + <&gcc GCC_UFS_PHY_ICE_CORE_CLK>; clock-names = "core_clk", "bus_aggr_clk", "iface_clk", diff --git a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts index e5e6b800c2d1..3473db08b9b2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts @@ -199,7 +199,7 @@ compatible = "brcm,bcm43455-fmac", "brcm,bcm4329-fmac"; reg = <1>; interrupt-parent = <&gpio0>; - interrupts = <RK_PA3 GPIO_ACTIVE_HIGH>; + interrupts = <RK_PA3 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "host-wake"; pinctrl-names = "default"; pinctrl-0 = <&wifi_host_wake>; diff --git a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts index 35bbaf559ca3..6b0563cb4d3a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts +++ b/arch/arm64/boot/dts/rockchip/rk3326-odroid-go3.dts @@ -14,7 +14,8 @@ joystick_mux_controller: mux-controller { compatible = "gpio-mux"; - pinctrl = <&mux_en_pins>; + pinctrl-0 = <&mux_en_pins>; + pinctrl-names = "default"; #mux-control-cells = <0>; mux-gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>, diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts index e7d4a2f9a95e..b2de018a7d36 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts @@ -424,9 +424,7 @@ &pcie0 { ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; - max-link-speed = <2>; num-lanes = <2>; - pinctrl-names = "default"; status = "okay"; vpcie12v-supply = <&vcc12v_dcin>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi index 8d94d9f91a5c..3a9a10f531bd 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi @@ -71,7 +71,6 @@ }; &pcie0 { - max-link-speed = <1>; num-lanes = <1>; vpcie3v3-supply = <&vcc3v3_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index eaaca08a7601..810ab6ff4e67 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -969,7 +969,6 @@ }; &spi1 { - max-freq = <10000000>; status = "okay"; spiflash: flash@0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts index 2dca1dca20b8..5de964d369b0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts @@ -40,13 +40,13 @@ button-up { label = "Volume Up"; linux,code = <KEY_VOLUMEUP>; - press-threshold-microvolt = <100000>; + press-threshold-microvolt = <2000>; }; button-down { label = "Volume Down"; linux,code = <KEY_VOLUMEDOWN>; - press-threshold-microvolt = <600000>; + press-threshold-microvolt = <300000>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 587e89d7fc5e..8299e9d10c7c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -483,7 +483,7 @@ pinctrl-names = "default"; pinctrl-0 = <&q7_thermal_pin &bios_disable_override_hog_pin>; - gpios { + gpio-pins { bios_disable_override_hog_pin: bios-disable-override-hog-pin { rockchip,pins = <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_down>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts index 74160cf89188..6d52e3723a4e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-4c-plus.dts @@ -529,11 +529,11 @@ rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>; }; - vsel1_gpio: vsel1-gpio { + vsel1_gpio: vsel1-gpio-pin { rockchip,pins = <1 RK_PC1 RK_FUNC_GPIO &pcfg_pull_down>; }; - vsel2_gpio: vsel2-gpio { + vsel2_gpio: vsel2-gpio-pin { rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_down>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso b/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso index 70c23e1bf14b..d1a906031912 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso +++ b/arch/arm64/boot/dts/rockchip/rk3568-wolfvision-pf5-display-vz.dtso @@ -11,7 +11,6 @@ #include "rk3568-wolfvision-pf5-display.dtsi" &st7789 { - compatible = "jasonic,jt240mhqs-hwt-ek-e3", - "sitronix,st7789v"; + compatible = "jasonic,jt240mhqs-hwt-ek-e3"; rotation = <270>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts b/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts index cce34c541f7c..bb2cc2814b83 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-nanopi-m5.dts @@ -201,6 +201,7 @@ pinctrl-names = "default"; pinctrl-0 = <&hp_det_l>; + simple-audio-card,bitclock-master = <&masterdai>; simple-audio-card,format = "i2s"; simple-audio-card,hp-det-gpios = <&gpio2 RK_PD6 GPIO_ACTIVE_LOW>; simple-audio-card,mclk-fs = <256>; @@ -211,15 +212,16 @@ "Headphones", "HPOR", "IN1P", "Microphone Jack"; simple-audio-card,widgets = - "Headphone", "Headphone Jack", + "Headphone", "Headphones", "Microphone", "Microphone Jack"; simple-audio-card,codec { sound-dai = <&rt5616>; }; - simple-audio-card,cpu { + masterdai: simple-audio-card,cpu { sound-dai = <&sai2>; + system-clock-frequency = <12288000>; }; }; }; @@ -727,10 +729,12 @@ rt5616: audio-codec@1b { compatible = "realtek,rt5616"; reg = <0x1b>; - assigned-clocks = <&cru CLK_SAI2_MCLKOUT>; + assigned-clocks = <&cru CLK_SAI2_MCLKOUT_TO_IO>; assigned-clock-rates = <12288000>; - clocks = <&cru CLK_SAI2_MCLKOUT>; + clocks = <&cru CLK_SAI2_MCLKOUT_TO_IO>; clock-names = "mclk"; + pinctrl-0 = <&sai2m0_mclk>; + pinctrl-names = "default"; #sound-dai-cells = <0>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index a86fc6b4e8c4..c72343e7a045 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -1261,7 +1261,7 @@ gpu: gpu@27800000 { compatible = "rockchip,rk3576-mali", "arm,mali-bifrost"; - reg = <0x0 0x27800000 0x0 0x200000>; + reg = <0x0 0x27800000 0x0 0x20000>; assigned-clocks = <&scmi_clk SCMI_CLK_GPU>; assigned-clock-rates = <198000000>; clocks = <&cru CLK_GPU>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi index 2a7921793020..7ab12d1054a7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi @@ -1200,7 +1200,7 @@ status = "disabled"; }; - rknn_mmu_1: iommu@fdac9000 { + rknn_mmu_1: iommu@fdaca000 { compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu"; reg = <0x0 0xfdaca000 0x0 0x100>; interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH 0>; @@ -1230,7 +1230,7 @@ status = "disabled"; }; - rknn_mmu_2: iommu@fdad9000 { + rknn_mmu_2: iommu@fdada000 { compatible = "rockchip,rk3588-iommu", "rockchip,rk3568-iommu"; reg = <0x0 0xfdada000 0x0 0x100>; interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH 0>; diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi index 357de4ca7555..e759fae77dcf 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -131,6 +131,7 @@ reg-names = "main", "isr0"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -149,6 +150,7 @@ reg-names = "main", "isr0"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <4>; @@ -164,6 +166,7 @@ compatible = "loongson,ls2k0500-eiointc"; reg = <0x0 0x1fe11600 0x0 0xea00>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <1>; interrupt-parent = <&cpuintc>; interrupts = <3>; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index 60ab425f793f..be4f7d119660 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -46,7 +46,7 @@ }; /* i2c of the dvi eeprom edid */ - i2c-gpio-0 { + i2c-0 { compatible = "i2c-gpio"; scl-gpios = <&gpio0 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; sda-gpios = <&gpio0 1 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -57,7 +57,7 @@ }; /* i2c of the eeprom edid */ - i2c-gpio-1 { + i2c-1 { compatible = "i2c-gpio"; scl-gpios = <&gpio0 33 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; sda-gpios = <&gpio0 32 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; @@ -114,6 +114,7 @@ <0x0 0x1fe01140 0x0 0x8>; reg-names = "main", "isr0", "isr1"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -131,6 +132,7 @@ <0x0 0x1fe01148 0x0 0x8>; reg-names = "main", "isr0", "isr1"; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <3>; @@ -437,54 +439,47 @@ gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, - <13 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 12 IRQ_TYPE_LEVEL_HIGH>, + <&liointc0 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, - <15 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 14 IRQ_TYPE_LEVEL_HIGH>, + <&liointc0 15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; status = "disabled"; }; ehci0: usb@4,1 { reg = <0x2100 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc1>; - interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc1 18 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; ohci0: usb@4,2 { reg = <0x2200 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc1>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc1 19 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; display@6,0 { reg = <0x3000 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 28 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; hda@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 4 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; sata: sata@8,0 { reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupt-parent = <&liointc0>; - interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&liointc0 19 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index 6c77b86ee06c..3678c084adf7 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -126,6 +126,7 @@ reg = <0x0 0x1fe01400 0x0 0x64>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; interrupt-parent = <&cpuintc>; interrupts = <2>; @@ -140,6 +141,7 @@ compatible = "loongson,ls2k2000-eiointc"; reg = <0x0 0x1fe01600 0x0 0xea00>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <1>; interrupt-parent = <&cpuintc>; interrupts = <3>; @@ -149,6 +151,7 @@ compatible = "loongson,pch-pic-1.0"; reg = <0x0 0x10000000 0x0 0x400>; interrupt-controller; + #address-cells = <0>; #interrupt-cells = <2>; loongson,pic-base-vec = <0>; interrupt-parent = <&eiointc>; @@ -291,65 +294,57 @@ gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, - <13 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 12 IRQ_TYPE_LEVEL_HIGH>, + <&pic 13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, - <15 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 14 IRQ_TYPE_LEVEL_HIGH>, + <&pic 15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; gmac2: ethernet@3,2 { reg = <0x1a00 0x0 0x0 0x0 0x0>; - interrupts = <17 IRQ_TYPE_LEVEL_HIGH>, - <18 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 17 IRQ_TYPE_LEVEL_HIGH>, + <&pic 18 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; - interrupt-parent = <&pic>; status = "disabled"; }; xhci0: usb@4,0 { reg = <0x2000 0x0 0x0 0x0 0x0>; - interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 48 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; xhci1: usb@19,0 { reg = <0xc800 0x0 0x0 0x0 0x0>; - interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 22 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; display@6,1 { reg = <0x3100 0x0 0x0 0x0 0x0>; - interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 28 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; i2s@7,0 { reg = <0x3800 0x0 0x0 0x0 0x0>; - interrupts = <78 IRQ_TYPE_LEVEL_HIGH>, - <79 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&pic 78 IRQ_TYPE_LEVEL_HIGH>, + <&pic 79 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "tx", "rx"; - interrupt-parent = <&pic>; status = "disabled"; }; sata: sata@8,0 { reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; - interrupt-parent = <&pic>; + interrupts-extended = <&pic 16 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 7f288e89573b..4eed7bc312a8 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -126,14 +126,6 @@ SYM_CODE_START(smpboot_entry) LONG_LI t1, CSR_STFILL csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1 #endif - /* Enable PG */ - li.w t0, 0xb0 # PLV=0, IE=0, PG=1 - csrwr t0, LOONGARCH_CSR_CRMD - li.w t0, 0x04 # PLV=0, PIE=1, PWE=0 - csrwr t0, LOONGARCH_CSR_PRMD - li.w t0, 0x00 # FPE=0, SXE=0, ASXE=0, BTE=0 - csrwr t0, LOONGARCH_CSR_EUEN - la.pcrel t0, cpuboot_data ld.d sp, t0, CPU_BOOT_STACK ld.d tp, t0, CPU_BOOT_TINFO diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 9d257c8519c9..e34a6fb33e11 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -626,6 +626,18 @@ static const struct loongarch_perf_event *loongarch_pmu_map_cache_event(u64 conf return pev; } +static inline bool loongarch_pmu_event_requires_counter(const struct perf_event *event) +{ + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + case PERF_TYPE_RAW: + return true; + default: + return false; + } +} + static int validate_group(struct perf_event *event) { struct cpu_hw_events fake_cpuc; @@ -633,15 +645,18 @@ static int validate_group(struct perf_event *event) memset(&fake_cpuc, 0, sizeof(fake_cpuc)); - if (loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0) + if (loongarch_pmu_event_requires_counter(leader) && + loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0) return -EINVAL; for_each_sibling_event(sibling, leader) { - if (loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0) + if (loongarch_pmu_event_requires_counter(sibling) && + loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0) return -EINVAL; } - if (loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0) + if (loongarch_pmu_event_requires_counter(event) && + loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0) return -EINVAL; return 0; diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index 29886876143f..dfaf6ccfdd8b 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -679,6 +679,7 @@ static void kvm_eiointc_destroy(struct kvm_device *dev) kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device); kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &eiointc->device_vext); kfree(eiointc); + kfree(dev); } static struct kvm_device_ops kvm_eiointc_dev_ops = { diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index 05cefd29282e..1058c13dba7f 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -459,6 +459,7 @@ static void kvm_ipi_destroy(struct kvm_device *dev) ipi = kvm->arch.ipi; kvm_io_bus_unregister_dev(kvm, KVM_IOCSR_BUS, &ipi->device); kfree(ipi); + kfree(dev); } static struct kvm_device_ops kvm_ipi_dev_ops = { diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index a698a73de399..4addb34bf432 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -475,6 +475,7 @@ static void kvm_pch_pic_destroy(struct kvm_device *dev) /* unregister pch pic device and free it's memory */ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &s->device); kfree(s); + kfree(dev); } static struct kvm_device_ops kvm_pch_pic_dev_ops = { diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index a673d3d68254..8986048f9b11 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -425,6 +425,28 @@ void __init paging_init(void) static struct kcore_list kcore_kseg0; #endif +static inline void __init highmem_init(void) +{ +#ifdef CONFIG_HIGHMEM + unsigned long tmp; + + /* + * If CPU cannot support HIGHMEM discard the memory above highstart_pfn + */ + if (cpu_has_dc_aliases) { + memblock_remove(PFN_PHYS(highstart_pfn), -1); + return; + } + + for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { + struct page *page = pfn_to_page(tmp); + + if (!memblock_is_memory(PFN_PHYS(tmp))) + SetPageReserved(page); + } +#endif +} + void __init arch_mm_preinit(void) { /* @@ -435,6 +457,7 @@ void __init arch_mm_preinit(void) maar_init(); setup_zero_pages(); /* Setup zeroed pages. */ + highmem_init(); #ifdef CONFIG_64BIT if ((unsigned long) &_text > (unsigned long) CKSEG0) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2429cb1c7baa..764001deb060 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/processor.h> #include <linux/smp.h> +#include <linux/sys_info.h> #include <asm/interrupt.h> #include <asm/paca.h> @@ -235,7 +236,11 @@ static void watchdog_smp_panic(int cpu) pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", cpu, tb, last_reset, tb_to_ns(tb - last_reset) / 1000000); - if (!sysctl_hardlockup_all_cpu_backtrace) { + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) { + trigger_allbutcpu_cpu_backtrace(cpu); + cpumask_clear(&wd_smp_cpus_ipi); + } else { /* * Try to trigger the stuck CPUs, unless we are going to * get a backtrace on all of them anyway. @@ -244,11 +249,9 @@ static void watchdog_smp_panic(int cpu) smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } - } else { - trigger_allbutcpu_cpu_backtrace(cpu); - cpumask_clear(&wd_smp_cpus_ipi); } + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); @@ -415,9 +418,11 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi - if (sysctl_hardlockup_all_cpu_backtrace) + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) trigger_allbutcpu_cpu_backtrace(cpu); + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index ff5c7134a37a..acf9ffa1a171 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -42,10 +42,34 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { unsigned int level; pte_t *pte = lookup_address(addr, &level); + pteval_t val; if (WARN_ON(!pte || level != PG_LEVEL_4K)) return false; + val = pte_val(*pte); + + /* + * protect requires making the page not-present. If the PTE is + * already in the right state, there's nothing to do. + */ + if (protect != !!(val & _PAGE_PRESENT)) + return true; + + /* + * Otherwise, invert the entire PTE. This avoids writing out an + * L1TF-vulnerable PTE (not present, without the high address bits + * set). + */ + set_pte(pte, __pte(~val)); + + /* + * If the page was protected (non-present) and we're making it + * present, there is no need to flush the TLB at all. + */ + if (!protect) + return true; + /* * We need to avoid IPIs, as we may get KFENCE allocations or faults * with interrupts disabled. Therefore, the below is best-effort, and @@ -53,11 +77,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) * lazy fault handling takes care of faults after the page is PRESENT. */ - if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - else - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - /* * Flush this CPU's TLB, assuming whoever did the allocation/free is * likely to continue running on this CPU. diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 3792ab4819dc..6ebff44a3f75 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -825,7 +825,8 @@ static __init bool get_mem_config(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) return __get_mem_config_intel(&hw_res->r_resctrl); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) return __rdt_get_mem_config_amd(&hw_res->r_resctrl); return false; @@ -987,7 +988,8 @@ static __init void rdt_init_res_defs(void) { if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) rdt_init_res_defs_intel(); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) rdt_init_res_defs_amd(); } @@ -1019,8 +1021,19 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_occ_scale = ebx; c->x86_cache_mbm_width_offset = eax & 0xff; - if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) - c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + if (!c->x86_cache_mbm_width_offset) { + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + break; + case X86_VENDOR_HYGON: + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_HYGON; + break; + default: + /* Leave c->x86_cache_mbm_width_offset as 0 */ + break; + } + } } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 4a916c84a322..79c18657ede0 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -14,6 +14,9 @@ #define MBM_CNTR_WIDTH_OFFSET_AMD 20 +/* Hygon MBM counter width as an offset from MBM_CNTR_WIDTH_BASE */ +#define MBM_CNTR_WIDTH_OFFSET_HYGON 8 + #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 3c306de52fd4..834641c6049a 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -115,12 +115,12 @@ void __init kernel_randomize_memory(void) /* * Adapt physical memory region size based on available memory, - * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the - * device BAR space assuming the direct map space is large enough - * for creating a ZONE_DEVICE mapping in the direct map corresponding - * to the physical BAR address. + * except when CONFIG_ZONE_DEVICE is enabled. ZONE_DEVICE wants to map + * any physical address into the direct-map. KASLR wants to reliably + * steal some physical address bits. Those design choices are in direct + * conflict. */ - if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb)) + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) && (memory_tb < kaslr_regions[0].size_tb)) kaslr_regions[0].size_tb = memory_tb; /* diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c index 9850c338548d..cff025b06be1 100644 --- a/block/bio-integrity-auto.c +++ b/block/bio-integrity-auto.c @@ -140,7 +140,7 @@ bool bio_integrity_prep(struct bio *bio) return true; set_flags = false; gfp |= __GFP_ZERO; - } else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) + } else if (bi->metadata_size > bi->pi_tuple_size) gfp |= __GFP_ZERO; break; default: diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 6d4d06236f61..cc3c83e4cc23 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -28,6 +28,10 @@ static bool sleep_no_lps0 __read_mostly; module_param(sleep_no_lps0, bool, 0644); MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface"); +static bool check_lps0_constraints __read_mostly; +module_param(check_lps0_constraints, bool, 0644); +MODULE_PARM_DESC(check_lps0_constraints, "Check LPS0 device constraints"); + static const struct acpi_device_id lps0_device_ids[] = { {"PNP0D80", }, {"", }, @@ -515,7 +519,8 @@ static struct acpi_scan_handler lps0_handler = { static int acpi_s2idle_begin_lps0(void) { - if (pm_debug_messages_on && !lpi_constraints_table) { + if (lps0_device_handle && !sleep_no_lps0 && check_lps0_constraints && + !lpi_constraints_table) { if (acpi_s2idle_vendor_amd()) lpi_device_get_constraints_amd(); else @@ -539,7 +544,7 @@ static int acpi_s2idle_prepare_late_lps0(void) if (!lps0_device_handle || sleep_no_lps0) return 0; - if (pm_debug_messages_on) + if (check_lps0_constraints) lpi_check_constraints(); /* Screen off */ diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 7a7f88b3fa2b..931d0081169b 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -2094,13 +2094,13 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ap->flags & ATA_FLAG_EM) ap->em_message_type = hpriv->em_msg_type; - ahci_mark_external_port(ap); - - ahci_update_initial_lpm_policy(ap); - /* disabled/not-implemented port */ - if (!(hpriv->port_map & (1 << i))) + if (!(hpriv->port_map & (1 << i))) { ap->ops = &ata_dummy_port_ops; + } else { + ahci_mark_external_port(ap); + ahci_update_initial_lpm_policy(ap); + } } /* apply workaround for ASUS P5W DH Deluxe mainboard */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 09d8c035fcdf..ddf9a7b28a59 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2872,7 +2872,8 @@ static void ata_dev_config_lpm(struct ata_device *dev) static void ata_dev_print_features(struct ata_device *dev) { - if (!(dev->flags & ATA_DFLAG_FEATURES_MASK)) + if (!(dev->flags & ATA_DFLAG_FEATURES_MASK) && !dev->cpr_log && + !ata_id_has_hipm(dev->id) && !ata_id_has_dipm(dev->id)) return; ata_dev_info(dev, @@ -3116,6 +3117,11 @@ int ata_dev_configure(struct ata_device *dev) ata_mode_string(xfer_mask), cdb_intr_string, atapi_an_string, dma_dir_string); + + ata_dev_config_lpm(dev); + + if (print_info) + ata_dev_print_features(dev); } /* determine max_sectors */ diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index b2817a2995d6..04e1e774645e 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -909,7 +909,7 @@ static bool ata_scsi_lpm_supported(struct ata_port *ap) struct ata_link *link; struct ata_device *dev; - if (ap->flags & ATA_FLAG_NO_LPM) + if ((ap->flags & ATA_FLAG_NO_LPM) || !ap->ops->set_lpm) return false; ata_for_each_link(link, ap, EDGE) { diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index c7c0fb79a6bf..4c0632ab4e1b 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -665,12 +665,22 @@ static void nullb_add_fault_config(struct nullb_device *dev) configfs_add_default_group(&dev->init_hctx_fault_config.group, &dev->group); } +static void nullb_del_fault_config(struct nullb_device *dev) +{ + config_item_put(&dev->init_hctx_fault_config.group.cg_item); + config_item_put(&dev->requeue_config.group.cg_item); + config_item_put(&dev->timeout_config.group.cg_item); +} + #else static void nullb_add_fault_config(struct nullb_device *dev) { } +static void nullb_del_fault_config(struct nullb_device *dev) +{ +} #endif static struct @@ -702,7 +712,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item) null_del_dev(dev->nullb); mutex_unlock(&lock); } - + nullb_del_fault_config(dev); config_item_put(item); } diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index d1c354636315..8194a970f002 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1662,7 +1662,6 @@ static void destroy_sysfs(struct rnbd_clt_dev *dev, /* To avoid deadlock firstly remove itself */ sysfs_remove_file_self(&dev->kobj, sysfs_self); kobject_del(&dev->kobj); - kobject_put(&dev->kobj); } } diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 77ac940e3013..49bba2b9a3c4 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -75,9 +75,16 @@ EXPORT_SYMBOL_FOR_MODULES(cxl_do_xormap_calc, "cxl_translate"); static u64 cxl_apply_xor_maps(struct cxl_root_decoder *cxlrd, u64 addr) { - struct cxl_cxims_data *cximsd = cxlrd->platform_data; + int hbiw = cxlrd->cxlsd.nr_targets; + struct cxl_cxims_data *cximsd; + + /* No xormaps for host bridge interleave ways of 1 or 3 */ + if (hbiw == 1 || hbiw == 3) + return addr; + + cximsd = cxlrd->platform_data; - return cxl_do_xormap_calc(cximsd, addr, cxlrd->cxlsd.nr_targets); + return cxl_do_xormap_calc(cximsd, addr, hbiw); } struct cxl_cxims_context { diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 1c5d2022c87a..eb5a3a7640c6 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -403,7 +403,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, * is not set. */ if (cxled->part < 0) - for (int i = 0; cxlds->nr_partitions; i++) + for (int i = 0; i < cxlds->nr_partitions; i++) if (resource_contains(&cxlds->part[i].res, res)) { cxled->part = i; break; @@ -530,7 +530,7 @@ resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled) resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { - resource_size_t base = -1; + resource_size_t base = RESOURCE_SIZE_MAX; lockdep_assert_held(&cxl_rwsem.dpa); if (cxled->dpa_res) diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index fef3aa0c6680..3310dbfae9d6 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1590,7 +1590,7 @@ static int update_decoder_targets(struct device *dev, void *data) cxlsd->target[i] = dport; dev_dbg(dev, "dport%d found in target list, index %d\n", dport->port_id, i); - return 1; + return 0; } } diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index ae899f68551f..5bd1213737fa 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -759,7 +759,7 @@ static ssize_t extended_linear_cache_size_show(struct device *dev, ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; - return sysfs_emit(buf, "%#llx\n", p->cache_size); + return sysfs_emit(buf, "%pap\n", &p->cache_size); } static DEVICE_ATTR_RO(extended_linear_cache_size); @@ -3118,7 +3118,7 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_region_params *p = &cxlr->params; struct cxl_endpoint_decoder *cxled = NULL; - u64 dpa_offset, hpa_offset, hpa; + u64 base, dpa_offset, hpa_offset, hpa; u16 eig = 0; u8 eiw = 0; int pos; @@ -3136,8 +3136,14 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, ways_to_eiw(p->interleave_ways, &eiw); granularity_to_eig(p->interleave_granularity, &eig); - dpa_offset = dpa - cxl_dpa_resource_start(cxled); + base = cxl_dpa_resource_start(cxled); + if (base == RESOURCE_SIZE_MAX) + return ULLONG_MAX; + + dpa_offset = dpa - base; hpa_offset = cxl_calculate_hpa_offset(dpa_offset, pos, eiw, eig); + if (hpa_offset == ULLONG_MAX) + return ULLONG_MAX; /* Apply the hpa_offset to the region base address */ hpa = hpa_offset + p->res->start + p->cache_size; @@ -3146,6 +3152,9 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd, if (cxlrd->ops.hpa_to_spa) hpa = cxlrd->ops.hpa_to_spa(cxlrd, hpa); + if (hpa == ULLONG_MAX) + return ULLONG_MAX; + if (!cxl_resource_contains_addr(p->res, hpa)) { dev_dbg(&cxlr->dev, "Addr trans fail: hpa 0x%llx not in region\n", hpa); @@ -3170,7 +3179,8 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset, struct cxl_region_params *p = &cxlr->params; struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent); struct cxl_endpoint_decoder *cxled; - u64 hpa, hpa_offset, dpa_offset; + u64 hpa_offset = offset; + u64 dpa, dpa_offset; u16 eig = 0; u8 eiw = 0; int pos; @@ -3187,10 +3197,13 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset, * CXL HPA is assumed to equal SPA. */ if (cxlrd->ops.spa_to_hpa) { - hpa = cxlrd->ops.spa_to_hpa(cxlrd, p->res->start + offset); - hpa_offset = hpa - p->res->start; - } else { - hpa_offset = offset; + hpa_offset = cxlrd->ops.spa_to_hpa(cxlrd, p->res->start + offset); + if (hpa_offset == ULLONG_MAX) { + dev_dbg(&cxlr->dev, "HPA not found for %pr offset %#llx\n", + p->res, offset); + return -ENXIO; + } + hpa_offset -= p->res->start; } pos = cxl_calculate_position(hpa_offset, eiw, eig); @@ -3207,8 +3220,13 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset, cxled = p->targets[i]; if (cxled->pos != pos) continue; + + dpa = cxl_dpa_resource_start(cxled); + if (dpa != RESOURCE_SIZE_MAX) + dpa += dpa_offset; + result->cxlmd = cxled_to_memdev(cxled); - result->dpa = cxl_dpa_resource_start(cxled) + dpa_offset; + result->dpa = dpa; return 0; } diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 0867115aeef2..c6ae27c982f4 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -67,14 +67,16 @@ struct dev_dax_range { /** * struct dev_dax - instance data for a subdivision of a dax region, and * data while the device is activated in the driver. - * @region - parent region - * @dax_dev - core dax functionality + * @region: parent region + * @dax_dev: core dax functionality + * @align: alignment of this instance * @target_node: effective numa node if dev_dax memory range is onlined * @dyn_id: is this a dynamic or statically created instance * @id: ida allocated id when the dax_region is not static * @ida: mapping id allocator - * @dev - device core - * @pgmap - pgmap for memmap setup / lifetime (driver owned) + * @dev: device core + * @pgmap: pgmap for memmap setup / lifetime (driver owned) + * @memmap_on_memory: allow kmem to put the memmap in the memory * @nr_range: size of @ranges * @ranges: range tuples of memory used */ diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index bd49f0374291..04bbd774b3b4 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -936,6 +936,7 @@ static void admac_remove(struct platform_device *pdev) } static const struct of_device_id admac_of_match[] = { + { .compatible = "apple,t8103-admac", }, { .compatible = "apple,admac", }, { } }; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 7d226453961f..22bb604a3f97 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -1765,6 +1765,7 @@ static int atc_alloc_chan_resources(struct dma_chan *chan) static void atc_free_chan_resources(struct dma_chan *chan) { struct at_dma_chan *atchan = to_at_dma_chan(chan); + struct at_dma_slave *atslave; BUG_ON(atc_chan_is_enabled(atchan)); @@ -1774,8 +1775,12 @@ static void atc_free_chan_resources(struct dma_chan *chan) /* * Free atslave allocated in at_dma_xlate() */ - kfree(chan->private); - chan->private = NULL; + atslave = chan->private; + if (atslave) { + put_device(atslave->dma_dev); + kfree(atslave); + chan->private = NULL; + } dev_vdbg(chan2dev(chan), "free_chan_resources: done\n"); } diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c index 7f0e76439ce5..ed037fa883f6 100644 --- a/drivers/dma/bcm-sba-raid.c +++ b/drivers/dma/bcm-sba-raid.c @@ -1699,7 +1699,7 @@ static int sba_probe(struct platform_device *pdev) /* Prealloc channel resource */ ret = sba_prealloc_channel_resources(sba); if (ret) - goto fail_free_mchan; + goto fail_put_mbox; /* Check availability of debugfs */ if (!debugfs_initialized()) @@ -1729,6 +1729,8 @@ skip_debugfs: fail_free_resources: debugfs_remove_recursive(sba->root); sba_freeup_channel_resources(sba); +fail_put_mbox: + put_device(sba->mbox_dev); fail_free_mchan: mbox_free_channel(sba->mchan); return ret; @@ -1744,6 +1746,8 @@ static void sba_remove(struct platform_device *pdev) sba_freeup_channel_resources(sba); + put_device(sba->mbox_dev); + mbox_free_channel(sba->mchan); } diff --git a/drivers/dma/cv1800b-dmamux.c b/drivers/dma/cv1800b-dmamux.c index e900d6595617..f7a952fcbc7d 100644 --- a/drivers/dma/cv1800b-dmamux.c +++ b/drivers/dma/cv1800b-dmamux.c @@ -102,11 +102,11 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, struct llist_node *node; unsigned long flags; unsigned int chid, devid, cpuid; - int ret; + int ret = -EINVAL; if (dma_spec->args_count != DMAMUX_NCELLS) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } devid = dma_spec->args[0]; @@ -115,18 +115,18 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (devid > MAX_DMA_MAPPING_ID) { dev_err(&pdev->dev, "invalid device id: %u\n", devid); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (cpuid > MAX_DMA_CPU_ID) { dev_err(&pdev->dev, "invalid cpu id: %u\n", cpuid); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -136,8 +136,6 @@ static void *cv1800_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (map->peripheral == devid && map->cpu == cpuid) goto found; } - - ret = -EINVAL; goto failed; } else { node = llist_del_first(&dmamux->free_maps); @@ -171,12 +169,17 @@ found: dev_dbg(&pdev->dev, "register channel %u for req %u (cpu %u)\n", chid, devid, cpuid); + put_device(&pdev->dev); + return map; failed: spin_unlock_irqrestore(&dmamux->lock, flags); of_node_put(dma_spec->np); dev_err(&pdev->dev, "errno %d\n", ret); +err_put_pdev: + put_device(&pdev->dev); + return ERR_PTR(ret); } diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c index deadf135681b..cbec277af4dd 100644 --- a/drivers/dma/dw/rzn1-dmamux.c +++ b/drivers/dma/dw/rzn1-dmamux.c @@ -90,7 +90,7 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (test_and_set_bit(map->req_idx, dmamux->used_chans)) { ret = -EBUSY; - goto free_map; + goto put_dma_spec_np; } mask = BIT(map->req_idx); @@ -103,6 +103,8 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, clear_bitmap: clear_bit(map->req_idx, dmamux->used_chans); +put_dma_spec_np: + of_node_put(dma_spec->np); free_map: kfree(map); put_device: diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index a59212758029..7137f51ff6a0 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -873,6 +873,7 @@ err_errirq: free_irq(fsl_chan->txirq, fsl_chan); err_txirq: dma_pool_destroy(fsl_chan->tcd_pool); + clk_disable_unprepare(fsl_chan->clk); return ret; } diff --git a/drivers/dma/idxd/compat.c b/drivers/dma/idxd/compat.c index eff9943f1a42..95b8ef958633 100644 --- a/drivers/dma/idxd/compat.c +++ b/drivers/dma/idxd/compat.c @@ -20,11 +20,16 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t c int rc = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); - if (dev && dev->driver) { + if (!dev) + return -ENODEV; + + if (dev->driver) { device_driver_detach(dev); rc = count; } + put_device(dev); + return rc; } static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store); @@ -38,9 +43,12 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t cou struct idxd_dev *idxd_dev; dev = bus_find_device_by_name(bus, NULL, buf); - if (!dev || dev->driver || drv != &dsa_drv.drv) + if (!dev) return -ENODEV; + if (dev->driver || drv != &dsa_drv.drv) + goto err_put_dev; + idxd_dev = confdev_to_idxd_dev(dev); if (is_idxd_dev(idxd_dev)) { alt_drv = driver_find("idxd", bus); @@ -53,13 +61,20 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t cou alt_drv = driver_find("user", bus); } if (!alt_drv) - return -ENODEV; + goto err_put_dev; rc = device_driver_attach(alt_drv, dev); if (rc < 0) - return rc; + goto err_put_dev; + + put_device(dev); return count; + +err_put_dev: + put_device(dev); + + return rc; } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, 0200, NULL, bind_store); diff --git a/drivers/dma/lpc18xx-dmamux.c b/drivers/dma/lpc18xx-dmamux.c index 2b6436f4b193..d3ff521951b8 100644 --- a/drivers/dma/lpc18xx-dmamux.c +++ b/drivers/dma/lpc18xx-dmamux.c @@ -57,30 +57,31 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, struct lpc18xx_dmamux_data *dmamux = platform_get_drvdata(pdev); unsigned long flags; unsigned mux; + int ret = -EINVAL; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } mux = dma_spec->args[0]; if (mux >= dmamux->dma_master_requests) { dev_err(&pdev->dev, "invalid mux number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[1] > LPC18XX_DMAMUX_MAX_VAL) { dev_err(&pdev->dev, "invalid dma mux value: %d\n", dma_spec->args[1]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -89,7 +90,8 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_err(&pdev->dev, "dma request %u busy with %u.%u\n", mux, mux, dmamux->muxes[mux].value); of_node_put(dma_spec->np); - return ERR_PTR(-EBUSY); + ret = -EBUSY; + goto err_put_pdev; } dmamux->muxes[mux].busy = true; @@ -106,7 +108,14 @@ static void *lpc18xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "mapping dmamux %u.%u to dma request %u\n", mux, dmamux->muxes[mux].value, mux); + put_device(&pdev->dev); + return &dmamux->muxes[mux]; + +err_put_pdev: + put_device(&pdev->dev); + + return ERR_PTR(ret); } static int lpc18xx_dmamux_probe(struct platform_device *pdev) diff --git a/drivers/dma/lpc32xx-dmamux.c b/drivers/dma/lpc32xx-dmamux.c index 351d7e23e615..33be714740dd 100644 --- a/drivers/dma/lpc32xx-dmamux.c +++ b/drivers/dma/lpc32xx-dmamux.c @@ -95,11 +95,12 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, struct lpc32xx_dmamux_data *dmamux = platform_get_drvdata(pdev); unsigned long flags; struct lpc32xx_dmamux *mux = NULL; + int ret = -EINVAL; int i; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } for (i = 0; i < ARRAY_SIZE(lpc32xx_muxes); i++) { @@ -111,20 +112,20 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, if (!mux) { dev_err(&pdev->dev, "invalid mux request number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[2] > 1) { dev_err(&pdev->dev, "invalid dma mux value: %d\n", dma_spec->args[1]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } spin_lock_irqsave(&dmamux->lock, flags); @@ -133,7 +134,8 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_err(dev, "dma request signal %d busy, routed to %s\n", mux->signal, mux->muxval ? mux->name_sel1 : mux->name_sel1); of_node_put(dma_spec->np); - return ERR_PTR(-EBUSY); + ret = -EBUSY; + goto err_put_pdev; } mux->busy = true; @@ -148,7 +150,14 @@ static void *lpc32xx_dmamux_reserve(struct of_phandle_args *dma_spec, dev_dbg(dev, "dma request signal %d routed to %s\n", mux->signal, mux->muxval ? mux->name_sel1 : mux->name_sel1); + put_device(&pdev->dev); + return mux; + +err_put_pdev: + put_device(&pdev->dev); + + return ERR_PTR(ret); } static int lpc32xx_dmamux_probe(struct platform_device *pdev) diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index d07229a74886..d12e729ee12c 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -152,8 +152,8 @@ struct mmp_pdma_phy { * * Controller Configuration: * @run_bits: Control bits in DCSR register for channel start/stop - * @dma_mask: DMA addressing capability of controller. 0 to use OF/platform - * settings, or explicit mask like DMA_BIT_MASK(32/64) + * @dma_width: DMA addressing width in bits (32 or 64). Determines the + * DMA mask capability of the controller hardware. */ struct mmp_pdma_ops { /* Hardware Register Operations */ @@ -173,7 +173,7 @@ struct mmp_pdma_ops { /* Controller Configuration */ u32 run_bits; - u64 dma_mask; + u32 dma_width; }; struct mmp_pdma_device { @@ -928,6 +928,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, { struct mmp_pdma_desc_sw *sw; struct mmp_pdma_device *pdev = to_mmp_pdma_dev(chan->chan.device); + unsigned long flags; u64 curr; u32 residue = 0; bool passed = false; @@ -945,6 +946,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, else curr = pdev->ops->read_src_addr(chan->phy); + spin_lock_irqsave(&chan->desc_lock, flags); + list_for_each_entry(sw, &chan->chain_running, node) { u64 start, end; u32 len; @@ -989,6 +992,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, continue; if (sw->async_tx.cookie == cookie) { + spin_unlock_irqrestore(&chan->desc_lock, flags); return residue; } else { residue = 0; @@ -996,6 +1000,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, } } + spin_unlock_irqrestore(&chan->desc_lock, flags); + /* We should only get here in case of cyclic transactions */ return residue; } @@ -1172,7 +1178,7 @@ static const struct mmp_pdma_ops marvell_pdma_v1_ops = { .get_desc_src_addr = get_desc_src_addr_32, .get_desc_dst_addr = get_desc_dst_addr_32, .run_bits = (DCSR_RUN), - .dma_mask = 0, /* let OF/platform set DMA mask */ + .dma_width = 32, }; static const struct mmp_pdma_ops spacemit_k1_pdma_ops = { @@ -1185,7 +1191,7 @@ static const struct mmp_pdma_ops spacemit_k1_pdma_ops = { .get_desc_src_addr = get_desc_src_addr_64, .get_desc_dst_addr = get_desc_dst_addr_64, .run_bits = (DCSR_RUN | DCSR_LPAEEN), - .dma_mask = DMA_BIT_MASK(64), /* force 64-bit DMA addr capability */ + .dma_width = 64, }; static const struct of_device_id mmp_pdma_dt_ids[] = { @@ -1314,13 +1320,9 @@ static int mmp_pdma_probe(struct platform_device *op) pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; - /* Set DMA mask based on ops->dma_mask, or OF/platform */ - if (pdev->ops->dma_mask) - dma_set_mask(pdev->dev, pdev->ops->dma_mask); - else if (pdev->dev->coherent_dma_mask) - dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask); - else - dma_set_mask(pdev->dev, DMA_BIT_MASK(64)); + /* Set DMA mask based on controller hardware capabilities */ + dma_set_mask_and_coherent(pdev->dev, + DMA_BIT_MASK(pdev->ops->dma_width)); ret = dma_async_device_register(&pdev->device); if (ret) { diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 66bfea1f156d..6e30f3aa401e 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -1605,14 +1605,16 @@ static int gpi_peripheral_config(struct dma_chan *chan, struct dma_slave_config *config) { struct gchan *gchan = to_gchan(chan); + void *new_config; if (!config->peripheral_config) return -EINVAL; - gchan->config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT); - if (!gchan->config) + new_config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT); + if (!new_config) return -ENOMEM; + gchan->config = new_config; memcpy(gchan->config, config->peripheral_config, config->peripheral_size); return 0; diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 1f687b08d6b8..9e5f088355e2 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -557,11 +557,16 @@ rz_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, static int rz_dmac_terminate_all(struct dma_chan *chan) { struct rz_dmac_chan *channel = to_rz_dmac_chan(chan); + struct rz_lmdesc *lmdesc = channel->lmdesc.base; unsigned long flags; + unsigned int i; LIST_HEAD(head); rz_dmac_disable_hw(channel); spin_lock_irqsave(&channel->vc.lock, flags); + for (i = 0; i < DMAC_NR_LMDESC; i++) + lmdesc[i].header = 0; + list_splice_tail_init(&channel->ld_active, &channel->ld_free); list_splice_tail_init(&channel->ld_queue, &channel->ld_free); vchan_get_all_descriptors(&channel->vc, &head); @@ -854,6 +859,13 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac, return 0; } +static void rz_dmac_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac) { struct device_node *np = dev->of_node; @@ -876,6 +888,10 @@ static int rz_dmac_parse_of_icu(struct device *dev, struct rz_dmac *dmac) return -ENODEV; } + ret = devm_add_action_or_reset(dev, rz_dmac_put_device, &dmac->icu.pdev->dev); + if (ret) + return ret; + dmac_index = args.args[0]; if (dmac_index > RZV2H_MAX_DMAC_INDEX) { dev_err(dev, "DMAC index %u invalid.\n", dmac_index); @@ -1055,8 +1071,6 @@ static void rz_dmac_remove(struct platform_device *pdev) reset_control_assert(dmac->rstc); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); - - platform_device_put(dmac->icu.pdev); } static const struct of_device_id of_rz_dmac_match[] = { diff --git a/drivers/dma/stm32/stm32-dmamux.c b/drivers/dma/stm32/stm32-dmamux.c index 8d77e2a7939a..db13498b9c9f 100644 --- a/drivers/dma/stm32/stm32-dmamux.c +++ b/drivers/dma/stm32/stm32-dmamux.c @@ -90,23 +90,25 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, struct stm32_dmamux_data *dmamux = platform_get_drvdata(pdev); struct stm32_dmamux *mux; u32 i, min, max; - int ret; + int ret = -EINVAL; unsigned long flags; if (dma_spec->args_count != 3) { dev_err(&pdev->dev, "invalid number of dma mux args\n"); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } if (dma_spec->args[0] > dmamux->dmamux_requests) { dev_err(&pdev->dev, "invalid mux request number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto err_put_pdev; } mux = kzalloc(sizeof(*mux), GFP_KERNEL); - if (!mux) - return ERR_PTR(-ENOMEM); + if (!mux) { + ret = -ENOMEM; + goto err_put_pdev; + } spin_lock_irqsave(&dmamux->lock, flags); mux->chan_id = find_first_zero_bit(dmamux->dma_inuse, @@ -116,7 +118,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, spin_unlock_irqrestore(&dmamux->lock, flags); dev_err(&pdev->dev, "Run out of free DMA requests\n"); ret = -ENOMEM; - goto error_chan_id; + goto err_free_mux; } set_bit(mux->chan_id, dmamux->dma_inuse); spin_unlock_irqrestore(&dmamux->lock, flags); @@ -133,8 +135,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", i - 1); if (!dma_spec->np) { dev_err(&pdev->dev, "can't get dma master\n"); - ret = -EINVAL; - goto error; + goto err_clear_inuse; } /* Set dma request */ @@ -142,7 +143,7 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { spin_unlock_irqrestore(&dmamux->lock, flags); - goto error; + goto err_put_dma_spec_np; } spin_unlock_irqrestore(&dmamux->lock, flags); @@ -160,13 +161,19 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, dev_dbg(&pdev->dev, "Mapping DMAMUX(%u) to DMA%u(%u)\n", mux->request, mux->master, mux->chan_id); + put_device(&pdev->dev); + return mux; -error: +err_put_dma_spec_np: + of_node_put(dma_spec->np); +err_clear_inuse: clear_bit(mux->chan_id, dmamux->dma_inuse); - -error_chan_id: +err_free_mux: kfree(mux); +err_put_pdev: + put_device(&pdev->dev); + return ERR_PTR(ret); } diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index d0e8bb27a03b..215bfef37ec6 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -429,10 +429,17 @@ static void tegra_adma_stop(struct tegra_adma_chan *tdc) return; } - kfree(tdc->desc); + vchan_terminate_vdesc(&tdc->desc->vd); tdc->desc = NULL; } +static void tegra_adma_synchronize(struct dma_chan *dc) +{ + struct tegra_adma_chan *tdc = to_tegra_adma_chan(dc); + + vchan_synchronize(&tdc->vc); +} + static void tegra_adma_start(struct tegra_adma_chan *tdc) { struct virt_dma_desc *vd = vchan_next_desc(&tdc->vc); @@ -1155,6 +1162,7 @@ static int tegra_adma_probe(struct platform_device *pdev) tdma->dma_dev.device_config = tegra_adma_slave_config; tdma->dma_dev.device_tx_status = tegra_adma_tx_status; tdma->dma_dev.device_terminate_all = tegra_adma_terminate_all; + tdma->dma_dev.device_synchronize = tegra_adma_synchronize; tdma->dma_dev.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); tdma->dma_dev.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); tdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); diff --git a/drivers/dma/ti/dma-crossbar.c b/drivers/dma/ti/dma-crossbar.c index 7f17ee87a6dc..e04077d542d2 100644 --- a/drivers/dma/ti/dma-crossbar.c +++ b/drivers/dma/ti/dma-crossbar.c @@ -79,34 +79,35 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, { struct platform_device *pdev = of_find_device_by_node(ofdma->of_node); struct ti_am335x_xbar_data *xbar = platform_get_drvdata(pdev); - struct ti_am335x_xbar_map *map; + struct ti_am335x_xbar_map *map = ERR_PTR(-EINVAL); if (dma_spec->args_count != 3) - return ERR_PTR(-EINVAL); + goto out_put_pdev; if (dma_spec->args[2] >= xbar->xbar_events) { dev_err(&pdev->dev, "Invalid XBAR event number: %d\n", dma_spec->args[2]); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } if (dma_spec->args[0] >= xbar->dma_requests) { dev_err(&pdev->dev, "Invalid DMA request line number: %d\n", dma_spec->args[0]); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "Can't get DMA master\n"); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) { of_node_put(dma_spec->np); - return ERR_PTR(-ENOMEM); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } map->dma_line = (u16)dma_spec->args[0]; @@ -120,6 +121,9 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, ti_am335x_xbar_write(xbar->iomem, map->dma_line, map->mux_val); +out_put_pdev: + put_device(&pdev->dev); + return map; } @@ -241,28 +245,26 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, { struct platform_device *pdev = of_find_device_by_node(ofdma->of_node); struct ti_dra7_xbar_data *xbar = platform_get_drvdata(pdev); - struct ti_dra7_xbar_map *map; + struct ti_dra7_xbar_map *map = ERR_PTR(-EINVAL); if (dma_spec->args[0] >= xbar->xbar_requests) { dev_err(&pdev->dev, "Invalid XBAR request number: %d\n", dma_spec->args[0]); - put_device(&pdev->dev); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } /* The of_node_put() will be done in the core for the node */ dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0); if (!dma_spec->np) { dev_err(&pdev->dev, "Can't get DMA master\n"); - put_device(&pdev->dev); - return ERR_PTR(-EINVAL); + goto out_put_pdev; } map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) { of_node_put(dma_spec->np); - put_device(&pdev->dev); - return ERR_PTR(-ENOMEM); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } mutex_lock(&xbar->mutex); @@ -273,8 +275,8 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, dev_err(&pdev->dev, "Run out of free DMA requests\n"); kfree(map); of_node_put(dma_spec->np); - put_device(&pdev->dev); - return ERR_PTR(-ENOMEM); + map = ERR_PTR(-ENOMEM); + goto out_put_pdev; } set_bit(map->xbar_out, xbar->dma_inuse); mutex_unlock(&xbar->mutex); @@ -288,6 +290,9 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec, ti_dra7_xbar_write(xbar->iomem, map->xbar_out, map->xbar_in); +out_put_pdev: + put_device(&pdev->dev); + return map; } diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index 05228bf00033..624360423ef1 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -42,9 +42,9 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property) } ud = platform_get_drvdata(pdev); + put_device(&pdev->dev); if (!ud) { pr_debug("UDMA has not been probed\n"); - put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); } diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index 8c023c6e623a..73ed4b794630 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1808,6 +1808,8 @@ static int omap_dma_probe(struct platform_device *pdev) if (rc) { pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n", rc); + if (od->ll123_supported) + dma_pool_destroy(od->desc_pool); omap_dma_free(od); return rc; } @@ -1823,6 +1825,8 @@ static int omap_dma_probe(struct platform_device *pdev) if (rc) { pr_warn("OMAP-DMA: failed to register DMA controller\n"); dma_async_device_unregister(&od->ddev); + if (od->ll123_supported) + dma_pool_destroy(od->desc_pool); omap_dma_free(od); } } diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h index 6ad08878e938..70bca92621aa 100644 --- a/drivers/dma/xilinx/xdma-regs.h +++ b/drivers/dma/xilinx/xdma-regs.h @@ -9,6 +9,7 @@ /* The length of register space exposed to host */ #define XDMA_REG_SPACE_LEN 65536 +#define XDMA_MAX_REG_OFFSET (XDMA_REG_SPACE_LEN - 4) /* * maximum number of DMA channels for each direction: diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 0d88b1a670e1..5ecf8223c112 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -38,7 +38,7 @@ static const struct regmap_config xdma_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = XDMA_REG_SPACE_LEN, + .max_register = XDMA_MAX_REG_OFFSET, }; /** diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index fabff602065f..89a8254d9cdc 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -131,6 +131,7 @@ #define XILINX_MCDMA_MAX_CHANS_PER_DEVICE 0x20 #define XILINX_DMA_MAX_CHANS_PER_DEVICE 0x2 #define XILINX_CDMA_MAX_CHANS_PER_DEVICE 0x1 +#define XILINX_DMA_DFAULT_ADDRWIDTH 0x20 #define XILINX_DMA_DMAXR_ALL_IRQ_MASK \ (XILINX_DMA_DMASR_FRM_CNT_IRQ | \ @@ -3159,7 +3160,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; struct xilinx_dma_device *xdev; struct device_node *child, *np = pdev->dev.of_node; - u32 num_frames, addr_width, len_width; + u32 num_frames, addr_width = XILINX_DMA_DFAULT_ADDRWIDTH, len_width; int i, err; /* Allocate and initialize the DMA engine structure */ @@ -3235,7 +3236,9 @@ static int xilinx_dma_probe(struct platform_device *pdev) err = of_property_read_u32(node, "xlnx,addrwidth", &addr_width); if (err < 0) - dev_warn(xdev->dev, "missing xlnx,addrwidth property\n"); + dev_warn(xdev->dev, + "missing xlnx,addrwidth property, using default value %d\n", + XILINX_DMA_DFAULT_ADDRWIDTH); if (addr_width > 32) xdev->ext_addr = true; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index a461095efd8a..8879a7235156 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -83,10 +83,8 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, if (ref->pin != pin) continue; reg = dpll_pin_registration_find(ref, ops, priv, cookie); - if (reg) { - refcount_inc(&ref->refcount); - return 0; - } + if (reg) + return -EEXIST; ref_exists = true; break; } @@ -164,10 +162,8 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, if (ref->dpll != dpll) continue; reg = dpll_pin_registration_find(ref, ops, priv, cookie); - if (reg) { - refcount_inc(&ref->refcount); - return 0; - } + if (reg) + return -EEXIST; ref_exists = true; break; } diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index afccdebf5ac1..6cade6d7ceff 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -358,10 +358,11 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) layers[1].type = EDAC_MC_LAYER_CHANNEL; layers[1].size = nr_channels; layers[1].is_virt_csrow = false; - mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, - sizeof(struct i3200_priv)); + + rc = -ENOMEM; + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(struct i3200_priv)); if (!mci) - return -ENOMEM; + goto unmap; edac_dbg(3, "MC: init mci\n"); @@ -421,9 +422,9 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) return 0; fail: + edac_mc_free(mci); +unmap: iounmap(window); - if (mci) - edac_mc_free(mci); return rc; } diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c index 49ab5721aab2..292dda754c23 100644 --- a/drivers/edac/x38_edac.c +++ b/drivers/edac/x38_edac.c @@ -341,9 +341,12 @@ static int x38_probe1(struct pci_dev *pdev, int dev_idx) layers[1].type = EDAC_MC_LAYER_CHANNEL; layers[1].size = x38_channel_num; layers[1].is_virt_csrow = false; + + + rc = -ENOMEM; mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, 0); if (!mci) - return -ENOMEM; + goto unmap; edac_dbg(3, "MC: init mci\n"); @@ -403,9 +406,9 @@ static int x38_probe1(struct pci_dev *pdev, int dev_idx) return 0; fail: + edac_mc_free(mci); +unmap: iounmap(window); - if (mci) - edac_mc_free(mci); return rc; } diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 0232bd040f61..bd99802cb0ca 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -162,7 +162,7 @@ int cper_bits_to_str(char *buf, int buf_size, unsigned long bits, len -= size; str += size; } - return len - buf_size; + return buf_size - len; } EXPORT_SYMBOL_GPL(cper_bits_to_str); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 55452e61af31..17b5f3415465 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -74,10 +74,10 @@ struct mm_struct efi_mm = { .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), .user_ns = &init_user_ns, - .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, #ifdef CONFIG_SCHED_MM_CID .mm_cid.lock = __RAW_SPIN_LOCK_UNLOCKED(efi_mm.mm_cid.lock), #endif + .flexible_array = MM_STRUCT_FLEXIBLE_ARRAY_INIT, }; struct workqueue_struct *efi_rts_wq; @@ -819,6 +819,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, if (tbl) { phys_initrd_start = tbl->base; phys_initrd_size = tbl->size; + tbl->base = tbl->size = 0; early_memunmap(tbl, sizeof(*tbl)); } } diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 538f27209ce7..97780f27ce5b 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -6,6 +6,7 @@ * Copyright (c) 2007, MontaVista Software, Inc. <source@mvista.com> */ +#include <linux/cleanup.h> #include <linux/gpio/driver.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -109,6 +110,22 @@ davinci_direction_out(struct gpio_chip *chip, unsigned offset, int value) return __davinci_direction(chip, offset, true, value); } +static int davinci_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + struct davinci_gpio_controller *d = gpiochip_get_data(chip); + struct davinci_gpio_regs __iomem *g; + u32 mask = __gpio_mask(offset), val; + int bank = offset / 32; + + g = d->regs[bank]; + + guard(spinlock_irqsave)(&d->lock); + + val = readl_relaxed(&g->dir); + + return (val & mask) ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT; +} + /* * Read the pin's value (works even if it's set up as output); * returns zero/nonzero. @@ -203,6 +220,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.get = davinci_gpio_get; chips->chip.direction_output = davinci_direction_out; chips->chip.set = davinci_gpio_set; + chips->chip.get_direction = davinci_get_direction; chips->chip.ngpio = ngpio; chips->chip.base = -1; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index dcf427d3cf43..fe2d107b0a84 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -468,9 +468,6 @@ int gpiod_get_direction(struct gpio_desc *desc) test_bit(GPIOD_FLAG_IS_OUT, &flags)) return 0; - if (!guard.gc->get_direction) - return -ENOTSUPP; - ret = gpiochip_get_direction(guard.gc, offset); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9f9774f58ce1..b20a06abb65d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -274,6 +274,8 @@ extern int amdgpu_rebar; extern int amdgpu_wbrf; extern int amdgpu_user_queue; +extern uint amdgpu_hdmi_hpd_debounce_delay_ms; + #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d5c44bd34d45..d2c3885de711 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5063,6 +5063,14 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_ttm_set_buffer_funcs_status(adev, false); + /* + * device went through surprise hotplug; we need to destroy topology + * before ip_fini_early to prevent kfd locking refcount issues by calling + * amdgpu_amdkfd_suspend() + */ + if (drm_dev_is_unplugged(adev_to_drm(adev))) + amdgpu_amdkfd_device_fini_sw(adev); + amdgpu_device_ip_fini_early(adev); amdgpu_irq_fini_hw(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index b5d34797d606..52bc04452812 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1880,7 +1880,12 @@ int amdgpu_display_get_scanout_buffer(struct drm_plane *plane, struct drm_scanout_buffer *sb) { struct amdgpu_bo *abo; - struct drm_framebuffer *fb = plane->state->fb; + struct drm_framebuffer *fb; + + if (drm_drv_uses_atomic_modeset(plane->dev)) + fb = plane->state->fb; + else + fb = plane->fb; if (!fb) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e22cfa7c6d32..c1461317eb29 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -95,18 +95,6 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) attach->peer2peer = false; - /* - * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+. - * Such buffers cannot be safely accessed over P2P due to device-local - * compression metadata. Fallback to system-memory path instead. - * Device supports GFX12 (GC 12.x or newer) - * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag - * - */ - if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) && - bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) - attach->peer2peer = false; - if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) && pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 848e6b7db482..6ccb80e2d7c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -247,6 +247,7 @@ int amdgpu_damage_clips = -1; /* auto */ int amdgpu_umsch_mm_fwlog; int amdgpu_rebar = -1; /* auto */ int amdgpu_user_queue = -1; +uint amdgpu_hdmi_hpd_debounce_delay_ms; DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", @@ -1123,6 +1124,16 @@ module_param_named(rebar, amdgpu_rebar, int, 0444); MODULE_PARM_DESC(user_queue, "Enable user queues (-1 = auto (default), 0 = disable, 1 = enable, 2 = enable UQs and disable KQs)"); module_param_named(user_queue, amdgpu_user_queue, int, 0444); +/* + * DOC: hdmi_hpd_debounce_delay_ms (uint) + * HDMI HPD disconnect debounce delay in milliseconds. + * + * Used to filter short disconnect->reconnect HPD toggles some HDMI sinks + * generate while entering/leaving power save. Set to 0 to disable by default. + */ +MODULE_PARM_DESC(hdmi_hpd_debounce_delay_ms, "HDMI HPD disconnect debounce delay in milliseconds (0 to disable (by default), 1500 is common)"); +module_param_named(hdmi_hpd_debounce_delay_ms, amdgpu_hdmi_hpd_debounce_delay_ms, uint, 0644); + /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index d2237ce9da70..1485f4789440 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -375,7 +375,7 @@ void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset, * @start_page: first page to map in the GART aperture * @num_pages: number of pages to be mapped * @flags: page table entry flags - * @dst: CPU address of the GART table + * @dst: valid CPU address of GART table, cannot be null * * Binds a BO that is allocated in VRAM to the GART page table * (all ASICs). @@ -396,7 +396,7 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa, return; for (i = 0; i < num_pages; ++i) { - amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr, + amdgpu_gmc_set_pte_pde(adev, dst, start_page + i, pa + AMDGPU_GPU_PAGE_SIZE * i, flags); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 869bceb0fe2c..8924380086c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -732,6 +732,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, return 0; if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { + + if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) + return 0; + if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c index 9a969175900e..58b26c78b642 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c @@ -885,12 +885,28 @@ static int amdgpu_userq_input_args_validate(struct drm_device *dev, return 0; } +bool amdgpu_userq_enabled(struct drm_device *dev) +{ + struct amdgpu_device *adev = drm_to_adev(dev); + int i; + + for (i = 0; i < AMDGPU_HW_IP_NUM; i++) { + if (adev->userq_funcs[i]) + return true; + } + + return false; +} + int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { union drm_amdgpu_userq *args = data; int r; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + if (amdgpu_userq_input_args_validate(dev, args, filp) < 0) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h index c37444427a14..b48b3bc293fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h @@ -141,6 +141,7 @@ uint64_t amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr, struct drm_file *filp); u32 amdgpu_userq_get_supported_ip_mask(struct amdgpu_device *adev); +bool amdgpu_userq_enabled(struct drm_device *dev); int amdgpu_userq_suspend(struct amdgpu_device *adev); int amdgpu_userq_resume(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index eba9fb359047..85e9edc1cb6f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -141,6 +141,8 @@ static void amdgpu_userq_walk_and_drop_fence_drv(struct xarray *xa) void amdgpu_userq_fence_driver_free(struct amdgpu_usermode_queue *userq) { + dma_fence_put(userq->last_fence); + amdgpu_userq_walk_and_drop_fence_drv(&userq->fence_drv_xa); xa_destroy(&userq->fence_drv_xa); /* Drop the fence_drv reference held by user queue */ @@ -471,6 +473,9 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, struct drm_exec exec; u64 wptr; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_syncobj_handles = args->num_syncobj_handles; syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles), size_mul(sizeof(u32), num_syncobj_handles)); @@ -653,6 +658,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, int r, i, rentry, wentry, cnt; struct drm_exec exec; + if (!amdgpu_userq_enabled(dev)) + return -ENOTSUPP; + num_read_bo_handles = wait_info->num_bo_read_handles; bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles), size_mul(sizeof(u32), num_read_bo_handles)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c362d4dfb5bb..a67285118c37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1069,9 +1069,7 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked && - /* SI doesn't support pasid or KIQ/MES */ - params->adev->family > AMDGPU_FAMILY_SI) { + if (!params->unlocked) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 8ad7519f7b58..f1ee3921d970 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1235,16 +1235,16 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_NC); break; case AMDGPU_VM_MTYPE_WC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC); break; case AMDGPU_VM_MTYPE_RW: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW); break; case AMDGPU_VM_MTYPE_CC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC); break; case AMDGPU_VM_MTYPE_UC: - *flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); + *flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC); break; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index d7a2e7178ea9..625ea8ab7a74 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1209,14 +1209,8 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, pr_debug_ratelimited("Evicting process pid %d queues\n", pdd->process->lead_thread->pid); - if (dqm->dev->kfd->shared_resources.enable_mes) { + if (dqm->dev->kfd->shared_resources.enable_mes) pdd->last_evict_timestamp = get_jiffies_64(); - retval = suspend_all_queues_mes(dqm); - if (retval) { - dev_err(dev, "Suspending all queues failed"); - goto out; - } - } /* Mark all queues as evicted. Deactivate all active queues on * the qpd. @@ -1246,10 +1240,6 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD); - } else { - retval = resume_all_queues_mes(dqm); - if (retval) - dev_err(dev, "Resuming all queues failed"); } out: @@ -2919,6 +2909,14 @@ static int allocate_hiq_sdma_mqd(struct device_queue_manager *dqm) return retval; } +static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, + struct kfd_mem_obj *mqd) +{ + WARN(!mqd, "No hiq sdma mqd trunk to free"); + + amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); +} + struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) { struct device_queue_manager *dqm; @@ -3042,19 +3040,14 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_node *dev) return dqm; } + if (!dev->kfd->shared_resources.enable_mes) + deallocate_hiq_sdma_mqd(dev, &dqm->hiq_sdma_mqd); + out_free: kfree(dqm); return NULL; } -static void deallocate_hiq_sdma_mqd(struct kfd_node *dev, - struct kfd_mem_obj *mqd) -{ - WARN(!mqd, "No hiq sdma mqd trunk to free"); - - amdgpu_amdkfd_free_gtt_mem(dev->adev, &mqd->gtt_mem); -} - void device_queue_manager_uninit(struct device_queue_manager *dqm) { dqm->ops.stop(dqm); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 740711ac1037..1ea5a250440f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5266,6 +5266,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) struct amdgpu_dm_backlight_caps *caps; char bl_name[16]; int min, max; + int real_brightness; + int init_brightness; if (aconnector->bl_idx == -1) return; @@ -5290,6 +5292,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL; + init_brightness = props.brightness; + if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) { drm_info(drm, "Using custom brightness curve\n"); props.scale = BACKLIGHT_SCALE_NON_LINEAR; @@ -5308,8 +5312,20 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) if (IS_ERR(dm->backlight_dev[aconnector->bl_idx])) { drm_err(drm, "DM: Backlight registration failed!\n"); dm->backlight_dev[aconnector->bl_idx] = NULL; - } else + } else { + /* + * dm->brightness[x] can be inconsistent just after startup until + * ops.get_brightness is called. + */ + real_brightness = + amdgpu_dm_backlight_ops.get_brightness(dm->backlight_dev[aconnector->bl_idx]); + + if (real_brightness != init_brightness) { + dm->actual_brightness[aconnector->bl_idx] = real_brightness; + dm->brightness[aconnector->bl_idx] = real_brightness; + } drm_dbg_driver(drm, "DM: Registered Backlight device: %s\n", bl_name); + } } static int initialize_plane(struct amdgpu_display_manager *dm, @@ -5626,7 +5642,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (psr_feature_enabled) { amdgpu_dm_set_psr_caps(link); - drm_info(adev_to_drm(adev), "PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + drm_info(adev_to_drm(adev), "%s: PSR support %d, DC PSR ver %d, sink PSR ver %d DPCD caps 0x%x su_y_granularity %d\n", + aconnector->base.name, link->psr_settings.psr_feature_enabled, link->psr_settings.psr_version, link->dpcd_caps.psr_info.psr_version, @@ -8930,9 +8947,18 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, mutex_init(&aconnector->hpd_lock); mutex_init(&aconnector->handle_mst_msg_ready); - aconnector->hdmi_hpd_debounce_delay_ms = AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS; - INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); - aconnector->hdmi_prev_sink = NULL; + /* + * If HDMI HPD debounce delay is set, use the minimum between selected + * value and AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS + */ + if (amdgpu_hdmi_hpd_debounce_delay_ms) { + aconnector->hdmi_hpd_debounce_delay_ms = min(amdgpu_hdmi_hpd_debounce_delay_ms, + AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS); + INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); + aconnector->hdmi_prev_sink = NULL; + } else { + aconnector->hdmi_hpd_debounce_delay_ms = 0; + } /* * configure support HPD hot plug connector_>polled default value is 0 diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index bd0403005f37..beb0d04d3e68 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -59,7 +59,10 @@ #define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL) -#define AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS 1500 +/* + * Maximum HDMI HPD debounce delay in milliseconds + */ +#define AMDGPU_DM_MAX_HDMI_HPD_DEBOUNCE_MS 5000 /* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" diff --git a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h index b015e80672ec..fcd3ab4b0045 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hdmi_types.h @@ -41,7 +41,7 @@ /* kHZ*/ #define DP_ADAPTOR_DVI_MAX_TMDS_CLK 165000 /* kHZ*/ -#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 165000 +#define DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK 340000 struct dp_hdmi_dongle_signature_data { int8_t id[15];/* "DP-HDMI ADAPTOR"*/ diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index e1940b8e5bc3..7fa6bc97a919 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -336,7 +336,7 @@ static void query_dp_dual_mode_adaptor( /* Assume we have no valid DP passive dongle connected */ *dongle = DISPLAY_DONGLE_NONE; - sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK; /* Read DP-HDMI dongle I2c (no response interpreted as DP-DVI dongle)*/ if (!i2c_read( @@ -392,6 +392,8 @@ static void query_dp_dual_mode_adaptor( } } + if (is_valid_hdmi_signature) + sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_HDMI_SAFE_MAX_TMDS_CLK; if (is_type2_dongle) { uint32_t max_tmds_clk = diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 33c3cd2e1e24..d7642d388bc3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1702,8 +1702,9 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; CustomSkuTable_t *skutable = &pptable->CustomSkuTable; - uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; + int16_t od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; + uint32_t power_limit; if (smu_v14_0_get_current_power_limit(smu, &power_limit)) power_limit = smu->adev->pm.ac_power ? diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c index fe4c026280f0..60166919c5b5 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c @@ -163,6 +163,7 @@ struct dw_hdmi_qp { unsigned long ref_clk_rate; struct regmap *regm; + int main_irq; unsigned long tmds_char_rate; }; @@ -1271,6 +1272,7 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, dw_hdmi_qp_init_hw(hdmi); + hdmi->main_irq = plat_data->main_irq; ret = devm_request_threaded_irq(dev, plat_data->main_irq, dw_hdmi_qp_main_hardirq, NULL, IRQF_SHARED, dev_name(dev), hdmi); @@ -1331,9 +1333,16 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, } EXPORT_SYMBOL_GPL(dw_hdmi_qp_bind); +void dw_hdmi_qp_suspend(struct device *dev, struct dw_hdmi_qp *hdmi) +{ + disable_irq(hdmi->main_irq); +} +EXPORT_SYMBOL_GPL(dw_hdmi_qp_suspend); + void dw_hdmi_qp_resume(struct device *dev, struct dw_hdmi_qp *hdmi) { dw_hdmi_qp_init_hw(hdmi); + enable_irq(hdmi->main_irq); } EXPORT_SYMBOL_GPL(dw_hdmi_qp_resume); diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index 8a06d296561d..0de47e83d84d 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -1602,14 +1602,48 @@ drm_gpuvm_bo_create(struct drm_gpuvm *gpuvm, } EXPORT_SYMBOL_GPL(drm_gpuvm_bo_create); +/* + * drm_gpuvm_bo_destroy_not_in_lists() - final part of drm_gpuvm_bo cleanup + * @vm_bo: the &drm_gpuvm_bo to destroy + * + * It is illegal to call this method if the @vm_bo is present in the GEMs gpuva + * list, the extobj list, or the evicted list. + * + * Note that this puts a refcount on the GEM object, which may destroy the GEM + * object if the refcount reaches zero. It's illegal for this to happen if the + * caller holds the GEMs gpuva mutex because it would free the mutex. + */ +static void +drm_gpuvm_bo_destroy_not_in_lists(struct drm_gpuvm_bo *vm_bo) +{ + struct drm_gpuvm *gpuvm = vm_bo->vm; + const struct drm_gpuvm_ops *ops = gpuvm->ops; + struct drm_gem_object *obj = vm_bo->obj; + + if (ops && ops->vm_bo_free) + ops->vm_bo_free(vm_bo); + else + kfree(vm_bo); + + drm_gpuvm_put(gpuvm); + drm_gem_object_put(obj); +} + +static void +drm_gpuvm_bo_destroy_not_in_lists_kref(struct kref *kref) +{ + struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo, + kref); + + drm_gpuvm_bo_destroy_not_in_lists(vm_bo); +} + static void drm_gpuvm_bo_destroy(struct kref *kref) { struct drm_gpuvm_bo *vm_bo = container_of(kref, struct drm_gpuvm_bo, kref); struct drm_gpuvm *gpuvm = vm_bo->vm; - const struct drm_gpuvm_ops *ops = gpuvm->ops; - struct drm_gem_object *obj = vm_bo->obj; bool lock = !drm_gpuvm_resv_protected(gpuvm); if (!lock) @@ -1618,16 +1652,10 @@ drm_gpuvm_bo_destroy(struct kref *kref) drm_gpuvm_bo_list_del(vm_bo, extobj, lock); drm_gpuvm_bo_list_del(vm_bo, evict, lock); - drm_gem_gpuva_assert_lock_held(gpuvm, obj); + drm_gem_gpuva_assert_lock_held(gpuvm, vm_bo->obj); list_del(&vm_bo->list.entry.gem); - if (ops && ops->vm_bo_free) - ops->vm_bo_free(vm_bo); - else - kfree(vm_bo); - - drm_gpuvm_put(gpuvm); - drm_gem_object_put(obj); + drm_gpuvm_bo_destroy_not_in_lists(vm_bo); } /** @@ -1745,9 +1773,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_put_deferred); void drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm) { - const struct drm_gpuvm_ops *ops = gpuvm->ops; struct drm_gpuvm_bo *vm_bo; - struct drm_gem_object *obj; struct llist_node *bo_defer; bo_defer = llist_del_all(&gpuvm->bo_defer); @@ -1766,14 +1792,7 @@ drm_gpuvm_bo_deferred_cleanup(struct drm_gpuvm *gpuvm) while (bo_defer) { vm_bo = llist_entry(bo_defer, struct drm_gpuvm_bo, list.entry.bo_defer); bo_defer = bo_defer->next; - obj = vm_bo->obj; - if (ops && ops->vm_bo_free) - ops->vm_bo_free(vm_bo); - else - kfree(vm_bo); - - drm_gpuvm_put(gpuvm); - drm_gem_object_put(obj); + drm_gpuvm_bo_destroy_not_in_lists(vm_bo); } } EXPORT_SYMBOL_GPL(drm_gpuvm_bo_deferred_cleanup); @@ -1861,6 +1880,9 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain); * count is decreased. If not found @__vm_bo is returned without further * increase of the reference count. * + * The provided @__vm_bo must not already be in the gpuva, evict, or extobj + * lists prior to calling this method. + * * A new &drm_gpuvm_bo is added to the GEMs gpuva list. * * Returns: a pointer to the found &drm_gpuvm_bo or @__vm_bo if no existing @@ -1873,14 +1895,19 @@ drm_gpuvm_bo_obtain_prealloc(struct drm_gpuvm_bo *__vm_bo) struct drm_gem_object *obj = __vm_bo->obj; struct drm_gpuvm_bo *vm_bo; + drm_WARN_ON(gpuvm->drm, !drm_gpuvm_immediate_mode(gpuvm)); + + mutex_lock(&obj->gpuva.lock); vm_bo = drm_gpuvm_bo_find(gpuvm, obj); if (vm_bo) { - drm_gpuvm_bo_put(__vm_bo); + mutex_unlock(&obj->gpuva.lock); + kref_put(&__vm_bo->kref, drm_gpuvm_bo_destroy_not_in_lists_kref); return vm_bo; } drm_gem_gpuva_assert_lock_held(gpuvm, obj); list_add_tail(&__vm_bo->list.entry.gem, &obj->gpuva.list); + mutex_unlock(&obj->gpuva.lock); return __vm_bo; } diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 76d77a736d84..4b77be94348d 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -457,27 +457,20 @@ int gud_plane_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); struct drm_crtc *crtc = new_plane_state->crtc; - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; const struct drm_display_mode *mode; struct drm_framebuffer *old_fb = old_plane_state->fb; struct drm_connector_state *connector_state = NULL; struct drm_framebuffer *fb = new_plane_state->fb; - const struct drm_format_info *format = fb->format; + const struct drm_format_info *format; struct drm_connector *connector; unsigned int i, num_properties; struct gud_state_req *req; int idx, ret; size_t len; - if (drm_WARN_ON_ONCE(plane->dev, !fb)) - return -EINVAL; - - if (drm_WARN_ON_ONCE(plane->dev, !crtc)) - return -EINVAL; - - crtc_state = drm_atomic_get_new_crtc_state(state, crtc); - - mode = &crtc_state->mode; + if (crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state, DRM_PLANE_NO_SCALING, @@ -492,6 +485,9 @@ int gud_plane_atomic_check(struct drm_plane *plane, if (old_plane_state->rotation != new_plane_state->rotation) crtc_state->mode_changed = true; + mode = &crtc_state->mode; + format = fb->format; + if (old_fb && old_fb->format != format) crtc_state->mode_changed = true; @@ -598,7 +594,7 @@ void gud_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_helper_damage_iter iter; int ret, idx; - if (crtc->state->mode_changed || !crtc->state->enable) { + if (!crtc || crtc->state->mode_changed || !crtc->state->enable) { cancel_work_sync(&gdrm->work); mutex_lock(&gdrm->damage_lock); if (gdrm->fb) { diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 7582ef34bf3f..303d8d9b7775 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -686,7 +686,7 @@ static void err_print_guc_ctb(struct drm_i915_error_state_buf *m, } /* This list includes registers that are useful in debugging GuC hangs. */ -const struct { +static const struct { u32 start; u32 count; } guc_hw_reg_state[] = { diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c index a95ee5dcc2e3..1a889139cb05 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/curs507a.c +++ b/drivers/gpu/drm/nouveau/dispnv50/curs507a.c @@ -84,6 +84,7 @@ curs507a_prepare(struct nv50_wndw *wndw, struct nv50_head_atom *asyh, asyh->curs.handle = handle; asyh->curs.offset = offset; asyh->set.curs = asyh->curs.visible; + nv50_atom(asyh->state.state)->lock_core = true; } } diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 3dd742b4f823..e32ed1db6c56 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -43,6 +43,9 @@ nv50_head_flush_clr(struct nv50_head *head, union nv50_head_atom_mask clr = { .mask = asyh->clr.mask & ~(flush ? 0 : asyh->set.mask), }; + + lockdep_assert_held(&head->disp->mutex); + if (clr.crc) nv50_crc_atomic_clr(head); if (clr.olut) head->func->olut_clr(head); if (clr.core) head->func->core_clr(head); @@ -65,6 +68,8 @@ nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh) void nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh) { + lockdep_assert_held(&head->disp->mutex); + if (asyh->set.view ) head->func->view (head, asyh); if (asyh->set.mode ) head->func->mode (head, asyh); if (asyh->set.core ) head->func->core_set(head, asyh); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b26b682826bc..162cc58c7b8f 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -623,49 +623,6 @@ static struct panel_simple *panel_simple_probe(struct device *dev) if (IS_ERR(desc)) return ERR_CAST(desc); - panel = devm_drm_panel_alloc(dev, struct panel_simple, base, - &panel_simple_funcs, desc->connector_type); - if (IS_ERR(panel)) - return ERR_CAST(panel); - - panel->desc = desc; - - panel->supply = devm_regulator_get(dev, "power"); - if (IS_ERR(panel->supply)) - return ERR_CAST(panel->supply); - - panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", - GPIOD_OUT_LOW); - if (IS_ERR(panel->enable_gpio)) - return dev_err_cast_probe(dev, panel->enable_gpio, - "failed to request GPIO\n"); - - err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); - if (err) { - dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); - return ERR_PTR(err); - } - - ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); - if (ddc) { - panel->ddc = of_find_i2c_adapter_by_node(ddc); - of_node_put(ddc); - - if (!panel->ddc) - return ERR_PTR(-EPROBE_DEFER); - } - - if (!of_device_is_compatible(dev->of_node, "panel-dpi") && - !of_get_display_timing(dev->of_node, "panel-timing", &dt)) - panel_simple_parse_panel_timing_node(dev, panel, &dt); - - if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { - /* Optional data-mapping property for overriding bus format */ - err = panel_simple_override_nondefault_lvds_datamapping(dev, panel); - if (err) - goto free_ddc; - } - connector_type = desc->connector_type; /* Catch common mistakes for panels. */ switch (connector_type) { @@ -690,8 +647,7 @@ static struct panel_simple *panel_simple_probe(struct device *dev) break; case DRM_MODE_CONNECTOR_eDP: dev_warn(dev, "eDP panels moved to panel-edp\n"); - err = -EINVAL; - goto free_ddc; + return ERR_PTR(-EINVAL); case DRM_MODE_CONNECTOR_DSI: if (desc->bpc != 6 && desc->bpc != 8) dev_warn(dev, "Expected bpc in {6,8} but got: %u\n", desc->bpc); @@ -720,6 +676,49 @@ static struct panel_simple *panel_simple_probe(struct device *dev) break; } + panel = devm_drm_panel_alloc(dev, struct panel_simple, base, + &panel_simple_funcs, connector_type); + if (IS_ERR(panel)) + return ERR_CAST(panel); + + panel->desc = desc; + + panel->supply = devm_regulator_get(dev, "power"); + if (IS_ERR(panel->supply)) + return ERR_CAST(panel->supply); + + panel->enable_gpio = devm_gpiod_get_optional(dev, "enable", + GPIOD_OUT_LOW); + if (IS_ERR(panel->enable_gpio)) + return dev_err_cast_probe(dev, panel->enable_gpio, + "failed to request GPIO\n"); + + err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation); + if (err) { + dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err); + return ERR_PTR(err); + } + + ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0); + if (ddc) { + panel->ddc = of_find_i2c_adapter_by_node(ddc); + of_node_put(ddc); + + if (!panel->ddc) + return ERR_PTR(-EPROBE_DEFER); + } + + if (!of_device_is_compatible(dev->of_node, "panel-dpi") && + !of_get_display_timing(dev->of_node, "panel-timing", &dt)) + panel_simple_parse_panel_timing_node(dev, panel, &dt); + + if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) { + /* Optional data-mapping property for overriding bus format */ + err = panel_simple_override_nondefault_lvds_datamapping(dev, panel); + if (err) + goto free_ddc; + } + dev_set_drvdata(dev, panel); /* @@ -1900,6 +1899,7 @@ static const struct panel_desc dataimage_scf0700c48ggu18 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct display_timing dlc_dlc0700yzg_1_timing = { diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index d4839d282689..f6339963e496 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -1252,17 +1252,7 @@ static int panthor_vm_prepare_map_op_ctx(struct panthor_vm_op_ctx *op_ctx, goto err_cleanup; } - /* drm_gpuvm_bo_obtain_prealloc() will call drm_gpuvm_bo_put() on our - * pre-allocated BO if the <BO,VM> association exists. Given we - * only have one ref on preallocated_vm_bo, drm_gpuvm_bo_destroy() will - * be called immediately, and we have to hold the VM resv lock when - * calling this function. - */ - dma_resv_lock(panthor_vm_resv(vm), NULL); - mutex_lock(&bo->base.base.gpuva.lock); op_ctx->map.vm_bo = drm_gpuvm_bo_obtain_prealloc(preallocated_vm_bo); - mutex_unlock(&bo->base.base.gpuva.lock); - dma_resv_unlock(panthor_vm_resv(vm)); op_ctx->map.bo_offset = offset; diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c index c9fe6aa3e3e3..8604342f9943 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c @@ -121,7 +121,7 @@ static void dw_hdmi_qp_rockchip_encoder_enable(struct drm_encoder *encoder) struct drm_crtc *crtc = encoder->crtc; /* Unconditionally switch to TMDS as FRL is not yet supported */ - gpiod_set_value(hdmi->frl_enable_gpio, 0); + gpiod_set_value_cansleep(hdmi->frl_enable_gpio, 0); if (!crtc || !crtc->state) return; @@ -640,6 +640,15 @@ static void dw_hdmi_qp_rockchip_remove(struct platform_device *pdev) component_del(&pdev->dev, &dw_hdmi_qp_rockchip_ops); } +static int __maybe_unused dw_hdmi_qp_rockchip_suspend(struct device *dev) +{ + struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev); + + dw_hdmi_qp_suspend(dev, hdmi->hdmi); + + return 0; +} + static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev) { struct rockchip_hdmi_qp *hdmi = dev_get_drvdata(dev); @@ -655,7 +664,8 @@ static int __maybe_unused dw_hdmi_qp_rockchip_resume(struct device *dev) } static const struct dev_pm_ops dw_hdmi_qp_rockchip_pm = { - SET_SYSTEM_SLEEP_PM_OPS(NULL, dw_hdmi_qp_rockchip_resume) + SET_SYSTEM_SLEEP_PM_OPS(dw_hdmi_qp_rockchip_suspend, + dw_hdmi_qp_rockchip_resume) }; struct platform_driver dw_hdmi_qp_rockchip_pltfm_driver = { diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c index cd8380f0eddc..f3950e8476a7 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c @@ -2104,7 +2104,7 @@ static void rk3568_vop2_wait_for_port_mux_done(struct vop2 *vop2) * Spin until the previous port_mux figuration is done. */ ret = readx_poll_timeout_atomic(rk3568_vop2_read_port_mux, vop2, port_mux_sel, - port_mux_sel == vop2->old_port_sel, 0, 50 * 1000); + port_mux_sel == vop2->old_port_sel, 10, 50 * 1000); if (ret) DRM_DEV_ERROR(vop2->dev, "wait port_mux done timeout: 0x%x--0x%x\n", port_mux_sel, vop2->old_port_sel); @@ -2124,7 +2124,7 @@ static void rk3568_vop2_wait_for_layer_cfg_done(struct vop2 *vop2, u32 cfg) * Spin until the previous layer configuration is done. */ ret = readx_poll_timeout_atomic(rk3568_vop2_read_layer_cfg, vop2, atv_layer_cfg, - atv_layer_cfg == cfg, 0, 50 * 1000); + atv_layer_cfg == cfg, 10, 50 * 1000); if (ret) DRM_DEV_ERROR(vop2->dev, "wait layer cfg done timeout: 0x%x--0x%x\n", atv_layer_cfg, cfg); @@ -2144,6 +2144,7 @@ static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) u8 layer_sel_id; unsigned int ofs; u32 ovl_ctrl; + u32 cfg_done; int i; struct vop2_video_port *vp0 = &vop2->vps[0]; struct vop2_video_port *vp1 = &vop2->vps[1]; @@ -2298,8 +2299,16 @@ static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) rk3568_vop2_wait_for_port_mux_done(vop2); } - if (layer_sel != old_layer_sel && atv_layer_sel != old_layer_sel) - rk3568_vop2_wait_for_layer_cfg_done(vop2, vop2->old_layer_sel); + if (layer_sel != old_layer_sel && atv_layer_sel != old_layer_sel) { + cfg_done = vop2_readl(vop2, RK3568_REG_CFG_DONE); + cfg_done &= (BIT(vop2->data->nr_vps) - 1); + cfg_done &= ~BIT(vp->id); + /* + * Changes of other VPs' overlays have not taken effect + */ + if (cfg_done) + rk3568_vop2_wait_for_layer_cfg_done(vop2, vop2->old_layer_sel); + } vop2_writel(vop2, RK3568_OVL_LAYER_SEL, layer_sel); mutex_unlock(&vop2->ovl_lock); diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h index da670d7eeb2e..de96bfe7562c 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h +++ b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h @@ -55,15 +55,6 @@ const struct drm_format_info *drm_sysfb_get_format_si(struct drm_device *dev, #endif /* - * Input parsing - */ - -int drm_sysfb_get_validated_int(struct drm_device *dev, const char *name, - u64 value, u32 max); -int drm_sysfb_get_validated_int0(struct drm_device *dev, const char *name, - u64 value, u32 max); - -/* * Display modes */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index f031a312c783..b22887e8c881 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -32,9 +32,15 @@ #include <drm/ttm/ttm_placement.h> -static void vmw_bo_release(struct vmw_bo *vbo) +/** + * vmw_bo_free - vmw_bo destructor + * + * @bo: Pointer to the embedded struct ttm_buffer_object + */ +static void vmw_bo_free(struct ttm_buffer_object *bo) { struct vmw_resource *res; + struct vmw_bo *vbo = to_vmw_bo(&bo->base); WARN_ON(kref_read(&vbo->tbo.base.refcount) != 0); vmw_bo_unmap(vbo); @@ -62,20 +68,8 @@ static void vmw_bo_release(struct vmw_bo *vbo) } vmw_surface_unreference(&vbo->dumb_surface); } - drm_gem_object_release(&vbo->tbo.base); -} - -/** - * vmw_bo_free - vmw_bo destructor - * - * @bo: Pointer to the embedded struct ttm_buffer_object - */ -static void vmw_bo_free(struct ttm_buffer_object *bo) -{ - struct vmw_bo *vbo = to_vmw_bo(&bo->base); - WARN_ON(!RB_EMPTY_ROOT(&vbo->res_tree)); - vmw_bo_release(vbo); + drm_gem_object_release(&vbo->tbo.base); WARN_ON(vbo->dirty); kfree(vbo); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 00be92da5509..85795082fef9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -515,12 +515,12 @@ int vmw_fence_obj_unref_ioctl(struct drm_device *dev, void *data, /** * vmw_event_fence_action_seq_passed * - * @action: The struct vmw_fence_action embedded in a struct - * vmw_event_fence_action. + * @f: The struct dma_fence which provides timestamp for the action event + * @cb: The struct dma_fence_cb callback for the action event. * - * This function is called when the seqno of the fence where @action is - * attached has passed. It queues the event on the submitter's event list. - * This function is always called from atomic context. + * This function is called when the seqno of the fence has passed + * and it is always called from atomic context. + * It queues the event on the submitter's event list. */ static void vmw_event_fence_action_seq_passed(struct dma_fence *f, struct dma_fence_cb *cb) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index d32ce1cb579e..bc51b5d55e38 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -766,13 +766,15 @@ err_out: return ERR_PTR(ret); } - ttm_bo_reserve(&bo->tbo, false, false, NULL); - ret = vmw_bo_dirty_add(bo); - if (!ret && surface && surface->res.func->dirty_alloc) { - surface->res.coherent = true; - ret = surface->res.func->dirty_alloc(&surface->res); + if (bo) { + ttm_bo_reserve(&bo->tbo, false, false, NULL); + ret = vmw_bo_dirty_add(bo); + if (!ret && surface && surface->res.func->dirty_alloc) { + surface->res.coherent = true; + ret = surface->res.func->dirty_alloc(&surface->res); + } + ttm_bo_unreserve(&bo->tbo); } - ttm_bo_unreserve(&bo->tbo); return &vfb->base; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 69dfe69ce0f8..a8c8c9375d29 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -923,8 +923,10 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, ttm_bo_unreserve(&buf->tbo); res = vmw_shader_alloc(dev_priv, buf, size, 0, shader_type); - if (unlikely(ret != 0)) + if (IS_ERR(res)) { + ret = PTR_ERR(res); goto no_reserve; + } ret = vmw_cmdbuf_res_add(man, vmw_cmdbuf_res_shader, vmw_shader_key(user_key, shader_type), diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 0a3ab7efed46..f1c17fb60dc1 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -195,13 +195,15 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, /* * Write dump contents to the page. No need to synchronize; panic should - * be single-threaded. + * be single-threaded. Ignore failures from kmsg_dump_get_buffer() since + * panic notification should be done even if there is no message data. + * Don't assume bytes_written is set in case of failure, so initialize it. */ kmsg_dump_rewind(&iter); - kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, + bytes_written = 0; + (void)kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, &bytes_written); - if (!bytes_written) - return; + /* * P3 to contain the physical address of the panic page & P4 to * contain the size of the panic data in that page. Rest of the @@ -210,7 +212,7 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, hv_set_msr(HV_MSR_CRASH_P0, 0); hv_set_msr(HV_MSR_CRASH_P1, 0); hv_set_msr(HV_MSR_CRASH_P2, 0); - hv_set_msr(HV_MSR_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_msr(HV_MSR_CRASH_P3, bytes_written ? virt_to_phys(hv_panic_page) : 0); hv_set_msr(HV_MSR_CRASH_P4, bytes_written); /* diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index b2862e0a317a..cdbc5f5c3215 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -375,7 +375,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) return; /* - * The cmxchg() above does an implicit memory barrier to + * The cmpxchg() above does an implicit memory barrier to * ensure the write to MessageType (ie set to * HVMSG_NONE) happens before we read the * MessagePending and EOMing. Otherwise, the EOMing diff --git a/drivers/hv/mshv_eventfd.c b/drivers/hv/mshv_eventfd.c index d93a18f09c76..0b75ff1edb73 100644 --- a/drivers/hv/mshv_eventfd.c +++ b/drivers/hv/mshv_eventfd.c @@ -388,7 +388,7 @@ static int mshv_irqfd_assign(struct mshv_partition *pt, { struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL; struct mshv_irqfd *irqfd, *tmp; - unsigned int events; + __poll_t events; int ret; int idx; diff --git a/drivers/hv/mshv_regions.c b/drivers/hv/mshv_regions.c index 30bacba6aec3..adba3564d9f1 100644 --- a/drivers/hv/mshv_regions.c +++ b/drivers/hv/mshv_regions.c @@ -20,6 +20,41 @@ #define MSHV_MAP_FAULT_IN_PAGES PTRS_PER_PMD /** + * mshv_chunk_stride - Compute stride for mapping guest memory + * @page : The page to check for huge page backing + * @gfn : Guest frame number for the mapping + * @page_count: Total number of pages in the mapping + * + * Determines the appropriate stride (in pages) for mapping guest memory. + * Uses huge page stride if the backing page is huge and the guest mapping + * is properly aligned; otherwise falls back to single page stride. + * + * Return: Stride in pages, or -EINVAL if page order is unsupported. + */ +static int mshv_chunk_stride(struct page *page, + u64 gfn, u64 page_count) +{ + unsigned int page_order; + + /* + * Use single page stride by default. For huge page stride, the + * page must be compound and point to the head of the compound + * page, and both gfn and page_count must be huge-page aligned. + */ + if (!PageCompound(page) || !PageHead(page) || + !IS_ALIGNED(gfn, PTRS_PER_PMD) || + !IS_ALIGNED(page_count, PTRS_PER_PMD)) + return 1; + + page_order = folio_order(page_folio(page)); + /* The hypervisor only supports 2M huge page */ + if (page_order != PMD_ORDER) + return -EINVAL; + + return 1 << page_order; +} + +/** * mshv_region_process_chunk - Processes a contiguous chunk of memory pages * in a region. * @region : Pointer to the memory region structure. @@ -45,25 +80,23 @@ static long mshv_region_process_chunk(struct mshv_mem_region *region, int (*handler)(struct mshv_mem_region *region, u32 flags, u64 page_offset, - u64 page_count)) + u64 page_count, + bool huge_page)) { - u64 count, stride; - unsigned int page_order; + u64 gfn = region->start_gfn + page_offset; + u64 count; struct page *page; - int ret; + int stride, ret; page = region->pages[page_offset]; if (!page) return -EINVAL; - page_order = folio_order(page_folio(page)); - /* The hypervisor only supports 4K and 2M page sizes */ - if (page_order && page_order != PMD_ORDER) - return -EINVAL; + stride = mshv_chunk_stride(page, gfn, page_count); + if (stride < 0) + return stride; - stride = 1 << page_order; - - /* Start at stride since the first page is validated */ + /* Start at stride since the first stride is validated */ for (count = stride; count < page_count; count += stride) { page = region->pages[page_offset + count]; @@ -71,12 +104,13 @@ static long mshv_region_process_chunk(struct mshv_mem_region *region, if (!page) break; - /* Break if page size changes */ - if (page_order != folio_order(page_folio(page))) + /* Break if stride size changes */ + if (stride != mshv_chunk_stride(page, gfn + count, + page_count - count)) break; } - ret = handler(region, flags, page_offset, count); + ret = handler(region, flags, page_offset, count, stride > 1); if (ret) return ret; @@ -108,7 +142,8 @@ static int mshv_region_process_range(struct mshv_mem_region *region, int (*handler)(struct mshv_mem_region *region, u32 flags, u64 page_offset, - u64 page_count)) + u64 page_count, + bool huge_page)) { long ret; @@ -162,11 +197,10 @@ struct mshv_mem_region *mshv_region_create(u64 guest_pfn, u64 nr_pages, static int mshv_region_chunk_share(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_MODIFY_SPA_PAGE_HOST_ACCESS_LARGE_PAGE; return hv_call_modify_spa_host_access(region->partition->pt_id, @@ -188,11 +222,10 @@ int mshv_region_share(struct mshv_mem_region *region) static int mshv_region_chunk_unshare(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_MODIFY_SPA_PAGE_HOST_ACCESS_LARGE_PAGE; return hv_call_modify_spa_host_access(region->partition->pt_id, @@ -212,11 +245,10 @@ int mshv_region_unshare(struct mshv_mem_region *region) static int mshv_region_chunk_remap(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_MAP_GPA_LARGE_PAGE; return hv_call_map_gpa_pages(region->partition->pt_id, @@ -295,11 +327,10 @@ release_pages: static int mshv_region_chunk_unmap(struct mshv_mem_region *region, u32 flags, - u64 page_offset, u64 page_count) + u64 page_offset, u64 page_count, + bool huge_page) { - struct page *page = region->pages[page_offset]; - - if (PageHuge(page) || PageTransCompound(page)) + if (huge_page) flags |= HV_UNMAP_GPA_LARGE_PAGE; return hv_call_unmap_gpa_pages(region->partition->pt_id, diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c index 1134a82c7881..681b58154d5e 100644 --- a/drivers/hv/mshv_root_main.c +++ b/drivers/hv/mshv_root_main.c @@ -611,7 +611,6 @@ mshv_partition_region_by_gfn(struct mshv_partition *partition, u64 gfn) return NULL; } -#ifdef CONFIG_X86_64 static struct mshv_mem_region * mshv_partition_region_by_gfn_get(struct mshv_partition *p, u64 gfn) { @@ -643,12 +642,17 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) { struct mshv_partition *p = vp->vp_partition; struct mshv_mem_region *region; - struct hv_x64_memory_intercept_message *msg; bool ret; u64 gfn; - - msg = (struct hv_x64_memory_intercept_message *) +#if defined(CONFIG_X86_64) + struct hv_x64_memory_intercept_message *msg = + (struct hv_x64_memory_intercept_message *) + vp->vp_intercept_msg_page->u.payload; +#elif defined(CONFIG_ARM64) + struct hv_arm64_memory_intercept_message *msg = + (struct hv_arm64_memory_intercept_message *) vp->vp_intercept_msg_page->u.payload; +#endif gfn = HVPFN_DOWN(msg->guest_physical_address); @@ -666,9 +670,6 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) return ret; } -#else /* CONFIG_X86_64 */ -static bool mshv_handle_gpa_intercept(struct mshv_vp *vp) { return false; } -#endif /* CONFIG_X86_64 */ static bool mshv_vp_handle_intercept(struct mshv_vp *vp) { @@ -1280,7 +1281,7 @@ mshv_map_user_memory(struct mshv_partition *partition, long ret; if (mem.flags & BIT(MSHV_SET_MEM_BIT_UNMAP) || - !access_ok((const void *)mem.userspace_addr, mem.size)) + !access_ok((const void __user *)mem.userspace_addr, mem.size)) return -EINVAL; mmap_read_lock(current->mm); diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 2a0962a0b441..d882126c1778 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -593,6 +593,13 @@ static bool is_use_dma(struct lpi2c_imx_struct *lpi2c_imx, struct i2c_msg *msg) return false; /* + * A system-wide suspend or resume transition is in progress. LPI2C should use PIO to + * transfer data to avoid issue caused by no ready DMA HW resource. + */ + if (pm_suspend_in_progress()) + return false; + + /* * When the length of data is less than I2C_DMA_THRESHOLD, * cpu mode is used directly to avoid low performance. */ diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 3a04016db2c3..ae609bdd2ec4 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -116,6 +116,7 @@ struct geni_i2c_dev { dma_addr_t dma_addr; struct dma_chan *tx_c; struct dma_chan *rx_c; + bool no_dma; bool gpi_mode; bool abort_done; bool is_tx_multi_desc_xfer; @@ -447,7 +448,7 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, size_t len = msg->len; struct i2c_msg *cur; - dma_buf = i2c_get_dma_safe_msg_buf(msg, 32); + dma_buf = gi2c->no_dma ? NULL : i2c_get_dma_safe_msg_buf(msg, 32); if (dma_buf) geni_se_select_mode(se, GENI_SE_DMA); else @@ -486,7 +487,7 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, size_t len = msg->len; struct i2c_msg *cur; - dma_buf = i2c_get_dma_safe_msg_buf(msg, 32); + dma_buf = gi2c->no_dma ? NULL : i2c_get_dma_safe_msg_buf(msg, 32); if (dma_buf) geni_se_select_mode(se, GENI_SE_DMA); else @@ -1080,10 +1081,12 @@ static int geni_i2c_probe(struct platform_device *pdev) goto err_resources; } - if (desc && desc->no_dma_support) + if (desc && desc->no_dma_support) { fifo_disable = false; - else + gi2c->no_dma = true; + } else { fifo_disable = readl_relaxed(gi2c->se.base + GENI_IF_DISABLE_RO) & FIFO_IF_DISABLE; + } if (fifo_disable) { /* FIFO is disabled, so we can only use GPI DMA */ diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index 3e8f126cb7f7..9e3595b3623e 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -670,12 +670,39 @@ static const struct riic_of_data riic_rz_t2h_info = { static int riic_i2c_suspend(struct device *dev) { - struct riic_dev *riic = dev_get_drvdata(dev); - int ret; + /* + * Some I2C devices may need the I2C controller to remain active + * during resume_noirq() or suspend_noirq(). If the controller is + * autosuspended, there is no way to wake it up once runtime PM is + * disabled (in suspend_late()). + * + * During system resume, the I2C controller will be available only + * after runtime PM is re-enabled (in resume_early()). However, this + * may be too late for some devices. + * + * Wake up the controller in the suspend() callback while runtime PM + * is still enabled. The I2C controller will remain available until + * the suspend_noirq() callback (pm_runtime_force_suspend()) is + * called. During resume, the I2C controller can be restored by the + * resume_noirq() callback (pm_runtime_force_resume()). + * + * Finally, the resume() callback re-enables autosuspend, ensuring + * the I2C controller remains available until the system enters + * suspend_noirq() and from resume_noirq(). + */ + return pm_runtime_resume_and_get(dev); +} - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; +static int riic_i2c_resume(struct device *dev) +{ + pm_runtime_put_autosuspend(dev); + + return 0; +} + +static int riic_i2c_suspend_noirq(struct device *dev) +{ + struct riic_dev *riic = dev_get_drvdata(dev); i2c_mark_adapter_suspended(&riic->adapter); @@ -683,12 +710,12 @@ static int riic_i2c_suspend(struct device *dev) riic_clear_set_bit(riic, ICCR1_ICE, 0, RIIC_ICCR1); pm_runtime_mark_last_busy(dev); - pm_runtime_put_sync(dev); + pm_runtime_force_suspend(dev); return reset_control_assert(riic->rstc); } -static int riic_i2c_resume(struct device *dev) +static int riic_i2c_resume_noirq(struct device *dev) { struct riic_dev *riic = dev_get_drvdata(dev); int ret; @@ -697,6 +724,10 @@ static int riic_i2c_resume(struct device *dev) if (ret) return ret; + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + ret = riic_init_hw(riic); if (ret) { /* @@ -714,6 +745,7 @@ static int riic_i2c_resume(struct device *dev) } static const struct dev_pm_ops riic_i2c_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(riic_i2c_suspend_noirq, riic_i2c_resume_noirq) SYSTEM_SLEEP_PM_OPS(riic_i2c_suspend, riic_i2c_resume) }; diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index d236aef80a8d..e1e63c2be82b 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -3,6 +3,7 @@ * Helpers for IOMMU drivers implementing SVA */ #include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> #include <linux/mutex.h> #include <linux/sched/mm.h> #include <linux/iommu.h> diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c index 7228a33f6c37..643c8e459611 100644 --- a/drivers/irqchip/irq-riscv-imsic-platform.c +++ b/drivers/irqchip/irq-riscv-imsic-platform.c @@ -158,11 +158,11 @@ static int imsic_irq_set_affinity(struct irq_data *d, const struct cpumask *mask tmp_vec.local_id = new_vec->local_id; /* Point device to the temporary vector */ - imsic_msi_update_msg(d, &tmp_vec); + imsic_msi_update_msg(irq_get_irq_data(d->irq), &tmp_vec); } /* Point device to the new vector */ - imsic_msi_update_msg(d, new_vec); + imsic_msi_update_msg(irq_get_irq_data(d->irq), new_vec); /* Update irq descriptors with the new vector */ d->chip_data = new_vec; diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index df98144a9539..33521c328a82 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -109,14 +109,14 @@ mISDN_read(struct file *filep, char __user *buf, size_t count, loff_t *off) spin_unlock_irq(&dev->lock); if (filep->f_flags & O_NONBLOCK) return -EAGAIN; - wait_event_interruptible(dev->wait, (dev->work || + wait_event_interruptible(dev->wait, (READ_ONCE(dev->work) || !list_empty(list))); if (signal_pending(current)) return -ERESTARTSYS; spin_lock_irq(&dev->lock); } if (dev->work) - dev->work = 0; + WRITE_ONCE(dev->work, 0); if (!list_empty(list)) { timer = list_first_entry(list, struct mISDNtimer, list); list_del(&timer->list); @@ -141,13 +141,16 @@ mISDN_poll(struct file *filep, poll_table *wait) if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s(%p, %p)\n", __func__, filep, wait); if (dev) { + u32 work; + poll_wait(filep, &dev->wait, wait); mask = 0; - if (dev->work || !list_empty(&dev->expired)) + work = READ_ONCE(dev->work); + if (work || !list_empty(&dev->expired)) mask |= (EPOLLIN | EPOLLRDNORM); if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s work(%d) empty(%d)\n", __func__, - dev->work, list_empty(&dev->expired)); + work, list_empty(&dev->expired)); } return mask; } @@ -172,7 +175,7 @@ misdn_add_timer(struct mISDNtimerdev *dev, int timeout) struct mISDNtimer *timer; if (!timeout) { - dev->work = 1; + WRITE_ONCE(dev->work, 1); wake_up_interruptible(&dev->wait); id = 0; } else { diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 885399ed0776..d34a19453560 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -560,11 +560,6 @@ int led_classdev_register_ext(struct device *parent, #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED led_cdev->brightness_hw_changed = -1; #endif - /* add to the list of leds */ - down_write(&leds_list_lock); - list_add_tail(&led_cdev->node, &leds_list); - up_write(&leds_list_lock); - if (!led_cdev->max_brightness) led_cdev->max_brightness = LED_FULL; @@ -574,6 +569,11 @@ int led_classdev_register_ext(struct device *parent, led_init_core(led_cdev); + /* add to the list of leds */ + down_write(&leds_list_lock); + list_add_tail(&led_cdev->node, &leds_list); + up_write(&leds_list_lock); + #ifdef CONFIG_LEDS_TRIGGERS led_trigger_set_default(led_cdev); #endif diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b7923d052a8d..7d685b01862e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1895,6 +1895,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { + if (slave_dev->type != ARPHRD_ETHER && + BOND_MODE(bond) == BOND_MODE_8023AD) { + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "8023AD mode requires Ethernet devices"); + return -EINVAL; + } slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", bond_dev->type, slave_dev->type); @@ -4113,8 +4119,9 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); - return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, - fk, data, l2_proto, nhoff, hlen, 0); + return __skb_flow_dissect(dev_net(bond->dev), skb, + &flow_keys_bonding, fk, data, + l2_proto, nhoff, hlen, 0); default: break; } diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 7ab9578f5b89..769745e22a3c 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -332,6 +332,7 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, can_ml = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); can_set_ml_priv(dev, can_ml); + can_set_cap(dev, CAN_CAP_CC); if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index de8e212a1366..4c219a5b139b 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -486,11 +486,17 @@ resubmit_urb: urb->transfer_buffer, RX_BUFFER_SIZE, ems_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 08da507faef4..8cc924c47042 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -541,13 +541,20 @@ resubmit_urb: urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + err = usb_submit_urb(urb, GFP_ATOMIC); + if (!err) + return; + + usb_unanchor_urb(urb); + if (err == -ENODEV) { for (i = 0; i < dev->net_count; i++) { if (dev->nets[i]) netif_device_detach(dev->nets[i]->netdev); } - } else if (err) { + } else { dev_err(dev->udev->dev.parent, "failed resubmitting read bulk urb: %pe\n", ERR_PTR(err)); } diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index d093babbc320..192338b481f2 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -754,6 +754,10 @@ resubmit_urb: usb_anchor_urb(urb, &parent->rx_submitted); rc = usb_submit_urb(urb, GFP_ATOMIC); + if (!rc) + return; + + usb_unanchor_urb(urb); /* USB failure take down all interfaces */ if (rc == -ENODEV) { @@ -762,6 +766,9 @@ device_detach: if (parent->canch[rc]) netif_device_detach(parent->canch[rc]->netdev); } + } else if (rc != -ESHUTDOWN && net_ratelimit()) { + netdev_info(netdev, "failed to re-submit IN URB: %pe\n", + ERR_PTR(urb->status)); } } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 62701ec34272..d0a2a2a33c1c 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -361,7 +361,14 @@ resubmit_urb: urb->transfer_buffer, KVASER_USB_RX_BUFFER_SIZE, kvaser_usb_read_bulk_callback, dev); + usb_anchor_urb(urb, &dev->rx_submitted); + err = usb_submit_urb(urb, GFP_ATOMIC); + if (!err) + return; + + usb_unanchor_urb(urb); + if (err == -ENODEV) { for (i = 0; i < dev->nchannels; i++) { struct kvaser_usb_net_priv *priv; @@ -372,7 +379,7 @@ resubmit_urb: netif_device_detach(priv->netdev); } - } else if (err) { + } else { dev_err(&dev->intf->dev, "Failed resubmitting read bulk urb: %d\n", err); } diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 41c0a1c399bf..04170326dc7e 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -608,11 +608,17 @@ resubmit_urb: urb->transfer_buffer, MCBA_USB_RX_BUFF_SIZE, mcba_usb_read_bulk_callback, priv); + usb_anchor_urb(urb, &priv->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 7449328f7cd7..3125cf59d002 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -541,11 +541,17 @@ resubmit_urb: urb->transfer_buffer, RX_BUFFER_SIZE, usb_8dev_read_bulk_callback, priv); + usb_anchor_urb(urb, &priv->rx_submitted); + retval = usb_submit_urb(urb, GFP_ATOMIC); + if (!retval) + return; + + usb_unanchor_urb(urb); if (retval == -ENODEV) netif_device_detach(netdev); - else if (retval) + else netdev_err(netdev, "failed resubmitting read bulk urb: %d\n", retval); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 3ddd896d6987..b5a60a048896 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1837,7 +1837,7 @@ static void xgbe_get_stats64(struct net_device *netdev, s->multicast = pstats->rxmulticastframes_g; s->rx_length_errors = pstats->rxlengtherror; s->rx_crc_errors = pstats->rxcrcerror; - s->rx_fifo_errors = pstats->rxfifooverflow; + s->rx_over_errors = pstats->rxfifooverflow; s->tx_packets = pstats->txframecount_gb; s->tx_bytes = pstats->txoctetcount_gb; @@ -2292,9 +2292,6 @@ read_again: goto read_again; if (error || packet->errors) { - if (packet->errors) - netif_err(pdata, rx_err, netdev, - "error in received packet\n"); dev_kfree_skb(skb); goto next_packet; } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index fd35f4b4dc50..014340f33345 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -156,7 +156,7 @@ static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv, ASP_RX_FILTER_NET_OFFSET_L4(32), ASP_RX_FILTER_NET_OFFSET(nfilt->hw_index + 1)); - rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) | + rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->ch) | ASP_RX_FILTER_NET_CFG_EN | ASP_RX_FILTER_NET_CFG_L2_EN | ASP_RX_FILTER_NET_CFG_L3_EN | @@ -166,7 +166,7 @@ static void bcmasp_netfilt_hw_en_wake(struct bcmasp_priv *priv, ASP_RX_FILTER_NET_CFG_UMC(nfilt->port), ASP_RX_FILTER_NET_CFG(nfilt->hw_index)); - rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->port + 8) | + rx_filter_core_wl(priv, ASP_RX_FILTER_NET_CFG_CH(nfilt->ch) | ASP_RX_FILTER_NET_CFG_EN | ASP_RX_FILTER_NET_CFG_L2_EN | ASP_RX_FILTER_NET_CFG_L3_EN | @@ -714,6 +714,7 @@ struct bcmasp_net_filter *bcmasp_netfilt_get_init(struct bcmasp_intf *intf, nfilter = &priv->net_filters[open_index]; nfilter->claimed = true; nfilter->port = intf->port; + nfilter->ch = intf->channel + priv->tx_chan_offset; nfilter->hw_index = open_index; } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h index 74adfdb50e11..e238507be40a 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h @@ -348,6 +348,7 @@ struct bcmasp_net_filter { bool wake_filter; int port; + int ch; unsigned int hw_index; }; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 3a032d4ac598..eab81e073e1e 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -3801,6 +3801,7 @@ int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) { int status; bool pmac_valid = false; + u32 pmac_id; eth_zero_addr(mac); @@ -3813,7 +3814,7 @@ int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) adapter->if_handle, 0); } else { status = be_cmd_get_mac_from_list(adapter, mac, &pmac_valid, - NULL, adapter->if_handle, 0); + &pmac_id, adapter->if_handle, 0); } return status; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b633c6e2bab7..52e10467b3e4 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2141,7 +2141,7 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) struct be_aic_obj *aic; struct be_rx_obj *rxo; struct be_tx_obj *txo; - u64 rx_pkts = 0, tx_pkts = 0; + u64 rx_pkts = 0, tx_pkts = 0, pkts; ulong now; u32 pps, delta; int i; @@ -2157,15 +2157,17 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) for_all_rx_queues_on_eq(adapter, eqo, rxo, i) { do { start = u64_stats_fetch_begin(&rxo->stats.sync); - rx_pkts += rxo->stats.rx_pkts; + pkts = rxo->stats.rx_pkts; } while (u64_stats_fetch_retry(&rxo->stats.sync, start)); + rx_pkts += pkts; } for_all_tx_queues_on_eq(adapter, eqo, txo, i) { do { start = u64_stats_fetch_begin(&txo->stats.sync); - tx_pkts += txo->stats.tx_reqs; + pkts = txo->stats.tx_reqs; } while (u64_stats_fetch_retry(&txo->stats.sync, start)); + tx_pkts += pkts; } /* Skip, if wrapped around or first calculation */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index cfb56bf0e361..a1405c928525 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1150,7 +1150,7 @@ fec_restart(struct net_device *ndev) u32 rcntl = FEC_RCR_MII; if (OPT_ARCH_HAS_MAX_FL) - rcntl |= (fep->netdev->mtu + ETH_HLEN + ETH_FCS_LEN) << 16; + rcntl |= (fep->netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN) << 16; if (fep->bufdesc_ex) fec_ptp_save_state(fep); @@ -1285,12 +1285,13 @@ fec_restart(struct net_device *ndev) /* When Jumbo Frame is enabled, the FIFO may not be large enough * to hold an entire frame. In such cases, if the MTU exceeds - * (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN), configure the interface - * to operate in cut-through mode, triggered by the FIFO threshold. + * (PKT_MAXBUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN), configure + * the interface to operate in cut-through mode, triggered by + * the FIFO threshold. * Otherwise, enable the ENET store-and-forward mode. */ if ((fep->quirks & FEC_QUIRK_JUMBO_FRAME) && - (ndev->mtu > (PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN))) + (ndev->mtu > (PKT_MAXBUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN))) writel(0xF, fep->hwp + FEC_X_WMRK); else writel(FEC_TXWMRK_STRFWD, fep->hwp + FEC_X_WMRK); @@ -4039,7 +4040,7 @@ static int fec_change_mtu(struct net_device *ndev, int new_mtu) if (netif_running(ndev)) return -EBUSY; - order = get_order(new_mtu + ETH_HLEN + ETH_FCS_LEN + order = get_order(new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN + FEC_DRV_RESERVE_SPACE); fep->rx_frame_size = (PAGE_SIZE << order) - FEC_DRV_RESERVE_SPACE; fep->pagepool_order = order; @@ -4590,7 +4591,7 @@ fec_probe(struct platform_device *pdev) else fep->max_buf_size = PKT_MAXBUF_SIZE; - ndev->max_mtu = fep->max_buf_size - ETH_HLEN - ETH_FCS_LEN; + ndev->max_mtu = fep->max_buf_size - VLAN_ETH_HLEN - ETH_FCS_LEN; ret = register_netdev(ndev); if (ret) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index affd5a6c44e7..131d1210dc4a 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1602,8 +1602,10 @@ static void ugeth_mac_config(struct phylink_config *config, unsigned int mode, pr_warn("TBI mode requires that the device tree specify a tbi-handle\n"); tbiphy = of_phy_find_device(ug_info->tbi_node); - if (!tbiphy) + if (!tbiphy) { pr_warn("Could not get TBI device\n"); + return; + } value = phy_read(tbiphy, ENET_TBI_MII_CR); value &= ~0x1000; /* Turn off autonegotiation */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 7b9269f6fdfc..a47464a22751 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2530,44 +2530,47 @@ static netdev_features_t hns3_features_check(struct sk_buff *skb, static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, struct hns3_enet_ring *ring, bool is_tx) { + struct ring_stats ring_stats; unsigned int start; do { start = u64_stats_fetch_begin(&ring->syncp); - if (is_tx) { - stats->tx_bytes += ring->stats.tx_bytes; - stats->tx_packets += ring->stats.tx_pkts; - stats->tx_dropped += ring->stats.sw_err_cnt; - stats->tx_dropped += ring->stats.tx_vlan_err; - stats->tx_dropped += ring->stats.tx_l4_proto_err; - stats->tx_dropped += ring->stats.tx_l2l3l4_err; - stats->tx_dropped += ring->stats.tx_tso_err; - stats->tx_dropped += ring->stats.over_max_recursion; - stats->tx_dropped += ring->stats.hw_limitation; - stats->tx_dropped += ring->stats.copy_bits_err; - stats->tx_dropped += ring->stats.skb2sgl_err; - stats->tx_dropped += ring->stats.map_sg_err; - stats->tx_errors += ring->stats.sw_err_cnt; - stats->tx_errors += ring->stats.tx_vlan_err; - stats->tx_errors += ring->stats.tx_l4_proto_err; - stats->tx_errors += ring->stats.tx_l2l3l4_err; - stats->tx_errors += ring->stats.tx_tso_err; - stats->tx_errors += ring->stats.over_max_recursion; - stats->tx_errors += ring->stats.hw_limitation; - stats->tx_errors += ring->stats.copy_bits_err; - stats->tx_errors += ring->stats.skb2sgl_err; - stats->tx_errors += ring->stats.map_sg_err; - } else { - stats->rx_bytes += ring->stats.rx_bytes; - stats->rx_packets += ring->stats.rx_pkts; - stats->rx_dropped += ring->stats.l2_err; - stats->rx_errors += ring->stats.l2_err; - stats->rx_errors += ring->stats.l3l4_csum_err; - stats->rx_crc_errors += ring->stats.l2_err; - stats->multicast += ring->stats.rx_multicast; - stats->rx_length_errors += ring->stats.err_pkt_len; - } + ring_stats = ring->stats; } while (u64_stats_fetch_retry(&ring->syncp, start)); + + if (is_tx) { + stats->tx_bytes += ring_stats.tx_bytes; + stats->tx_packets += ring_stats.tx_pkts; + stats->tx_dropped += ring_stats.sw_err_cnt; + stats->tx_dropped += ring_stats.tx_vlan_err; + stats->tx_dropped += ring_stats.tx_l4_proto_err; + stats->tx_dropped += ring_stats.tx_l2l3l4_err; + stats->tx_dropped += ring_stats.tx_tso_err; + stats->tx_dropped += ring_stats.over_max_recursion; + stats->tx_dropped += ring_stats.hw_limitation; + stats->tx_dropped += ring_stats.copy_bits_err; + stats->tx_dropped += ring_stats.skb2sgl_err; + stats->tx_dropped += ring_stats.map_sg_err; + stats->tx_errors += ring_stats.sw_err_cnt; + stats->tx_errors += ring_stats.tx_vlan_err; + stats->tx_errors += ring_stats.tx_l4_proto_err; + stats->tx_errors += ring_stats.tx_l2l3l4_err; + stats->tx_errors += ring_stats.tx_tso_err; + stats->tx_errors += ring_stats.over_max_recursion; + stats->tx_errors += ring_stats.hw_limitation; + stats->tx_errors += ring_stats.copy_bits_err; + stats->tx_errors += ring_stats.skb2sgl_err; + stats->tx_errors += ring_stats.map_sg_err; + } else { + stats->rx_bytes += ring_stats.rx_bytes; + stats->rx_packets += ring_stats.rx_pkts; + stats->rx_dropped += ring_stats.l2_err; + stats->rx_errors += ring_stats.l2_err; + stats->rx_errors += ring_stats.l3l4_csum_err; + stats->rx_crc_errors += ring_stats.l2_err; + stats->multicast += ring_stats.rx_multicast; + stats->rx_length_errors += ring_stats.err_pkt_len; + } } static void hns3_nic_get_stats64(struct net_device *netdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 9bb708fa42f2..416e02e7b995 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -731,7 +731,7 @@ struct hclge_fd_tcam_config_3_cmd { #define HCLGE_FD_AD_QID_M GENMASK(11, 2) #define HCLGE_FD_AD_USE_COUNTER_B 12 #define HCLGE_FD_AD_COUNTER_NUM_S 13 -#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(20, 13) +#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(19, 13) #define HCLGE_FD_AD_NXT_STEP_B 20 #define HCLGE_FD_AD_NXT_KEY_S 21 #define HCLGE_FD_AD_NXT_KEY_M GENMASK(25, 21) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c589baea7c77..b8e2aa19f9e6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5690,7 +5690,7 @@ static int hclge_fd_ad_config(struct hclge_dev *hdev, u8 stage, int loc, HCLGE_FD_AD_COUNTER_NUM_S, action->counter_id); hnae3_set_bit(ad_data, HCLGE_FD_AD_NXT_STEP_B, action->use_next_stage); hnae3_set_field(ad_data, HCLGE_FD_AD_NXT_KEY_M, HCLGE_FD_AD_NXT_KEY_S, - action->counter_id); + action->next_input_key); req->ad_data = cpu_to_le64(ad_data); ret = hclge_cmd_send(&hdev->hw, &desc, 1); diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c index 6950ee4d037b..e7d6c2033b45 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c @@ -63,21 +63,12 @@ static void qp_add_napi(struct hinic3_irq_cfg *irq_cfg) struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev); netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi); napi_enable(&irq_cfg->napi); } static void qp_del_napi(struct hinic3_irq_cfg *irq_cfg) { napi_disable(&irq_cfg->napi); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_RX, NULL); - netif_queue_set_napi(irq_cfg->netdev, irq_cfg->irq_id, - NETDEV_QUEUE_TYPE_TX, NULL); - netif_stop_subqueue(irq_cfg->netdev, irq_cfg->irq_id); netif_napi_del(&irq_cfg->napi); } @@ -240,6 +231,11 @@ int hinic3_qps_irq_init(struct net_device *netdev) INIT_WORK(&irq_cfg->rxq->dim.work, hinic3_rx_dim_work); irq_cfg->rxq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE; + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, &irq_cfg->napi); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, &irq_cfg->napi); + hinic3_set_msix_auto_mask_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_SET_MSIX_AUTO_MASK); @@ -254,6 +250,10 @@ err_release_irqs: q_id--; irq_cfg = &nic_dev->q_params.irq_cfg[q_id]; qp_del_napi(irq_cfg); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, NULL); hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_MSIX_DISABLE); @@ -276,6 +276,10 @@ void hinic3_qps_irq_uninit(struct net_device *netdev) for (q_id = 0; q_id < nic_dev->q_params.num_qps; q_id++) { irq_cfg = &nic_dev->q_params.irq_cfg[q_id]; qp_del_napi(irq_cfg); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_RX, NULL); + netif_queue_set_napi(irq_cfg->netdev, q_id, + NETDEV_QUEUE_TYPE_TX, NULL); hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx, HINIC3_MSIX_DISABLE); hinic3_set_msix_auto_mask_state(nic_dev->hwdev, diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index d88b7f3fd1f9..2ef39cc70c21 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -460,6 +460,7 @@ static void ice_devlink_reinit_down(struct ice_pf *pf) ice_vsi_decfg(ice_get_main_vsi(pf)); rtnl_unlock(); ice_deinit_pf(pf); + ice_deinit_hw(&pf->hw); ice_deinit_dev(pf); } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 147aaee192a7..00f75d87c73f 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -979,6 +979,7 @@ void ice_map_xdp_rings(struct ice_vsi *vsi); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size); int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index c0a19f232538..64e798b8f18f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2214,7 +2214,7 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) /* there are some rare cases when trying to release the resource * results in an admin queue timeout, so handle them correctly */ - timeout = jiffies + 10 * ICE_CTL_Q_SQ_CMD_TIMEOUT; + timeout = jiffies + 10 * usecs_to_jiffies(ICE_CTL_Q_SQ_CMD_TIMEOUT); do { status = ice_aq_release_res(hw, res, 0, NULL); if (status != -EIO) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 969d4f8f9c02..3565a5d96c6d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3626,11 +3626,7 @@ ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) if (!lut) return -ENOMEM; - err = ice_get_rss_key(vsi, rxfh->key); - if (err) - goto out; - - err = ice_get_rss_lut(vsi, lut, vsi->rss_table_size); + err = ice_get_rss(vsi, rxfh->key, lut, vsi->rss_table_size); if (err) goto out; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 44f3c2bab308..6dabac51e1f9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -400,6 +400,8 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; + u64_stats_init(&ring_stats->syncp); + WRITE_ONCE(tx_ring_stats[i], ring_stats); } @@ -419,6 +421,8 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) if (!ring_stats) goto err_out; + u64_stats_init(&ring_stats->syncp); + WRITE_ONCE(rx_ring_stats[i], ring_stats); } @@ -3809,22 +3813,31 @@ int ice_vsi_add_vlan_zero(struct ice_vsi *vsi) int ice_vsi_del_vlan_zero(struct ice_vsi *vsi) { struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_pf *pf = vsi->back; struct ice_vlan vlan; int err; - vlan = ICE_VLAN(0, 0, 0); - err = vlan_ops->del_vlan(vsi, &vlan); - if (err && err != -EEXIST) - return err; + if (pf->lag && pf->lag->primary) { + dev_dbg(ice_pf_to_dev(pf), "Interface is primary in aggregate - not deleting prune list\n"); + } else { + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + } /* in SVM both VLAN 0 filters are identical */ if (!ice_is_dvm_ena(&vsi->back->hw)) return 0; - vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); - err = vlan_ops->del_vlan(vsi, &vlan); - if (err && err != -EEXIST) - return err; + if (pf->lag && pf->lag->primary) { + dev_dbg(ice_pf_to_dev(pf), "Interface is primary in aggregate - not deleting QinQ prune list\n"); + } else { + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + } /* when deleting the last VLAN filter, make sure to disable the VLAN * promisc mode so the filter isn't left by accident diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4bb68e7a00f5..de488185cd4a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4836,6 +4836,7 @@ static void ice_deinit_features(struct ice_pf *pf) ice_dpll_deinit(pf); if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) xa_destroy(&pf->eswitch.reprs); + ice_hwmon_exit(pf); } static void ice_init_wakeup(struct ice_pf *pf) @@ -5437,8 +5438,6 @@ static void ice_remove(struct pci_dev *pdev) ice_free_vfs(pf); } - ice_hwmon_exit(pf); - if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); @@ -7989,6 +7988,34 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) } /** + * ice_get_rss - Get RSS LUT and/or key + * @vsi: Pointer to VSI structure + * @seed: Buffer to store the key in + * @lut: Buffer to store the lookup table entries + * @lut_size: Size of buffer to store the lookup table entries + * + * Return: 0 on success, negative on failure + */ +int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) +{ + int err; + + if (seed) { + err = ice_get_rss_key(vsi, seed); + if (err) + return err; + } + + if (lut) { + err = ice_get_rss_lut(vsi, lut, lut_size); + if (err) + return err; + } + + return 0; +} + +/** * ice_set_rss_hfunc - Set RSS HASH function * @vsi: Pointer to VSI structure * @hfunc: hash function (ICE_AQ_VSI_Q_OPT_RSS_*) diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index 3e1052d070cf..0a8b50350b86 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -108,11 +108,11 @@ static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter, ptp_read_system_prets(sts); idpf_ptp_enable_shtime(adapter); + lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); /* Read the system timestamp post PHC read */ ptp_read_system_postts(sts); - lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); hi = readl(ptp->dev_clk_regs.dev_clk_ns_h); spin_unlock(&ptp->read_dev_clk_lock); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 97a5fe766b6b..66ba645e8b90 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3956,7 +3956,7 @@ static void idpf_update_dim_sample(struct idpf_q_vector *q_vector, static void idpf_net_dim(struct idpf_q_vector *q_vector) { struct dim_sample dim_sample = { }; - u64 packets, bytes; + u64 packets, bytes, pkts, bts; u32 i; if (!IDPF_ITR_IS_DYNAMIC(q_vector->tx_intr_mode)) @@ -3968,9 +3968,12 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector) do { start = u64_stats_fetch_begin(&txq->stats_sync); - packets += u64_stats_read(&txq->q_stats.packets); - bytes += u64_stats_read(&txq->q_stats.bytes); + pkts = u64_stats_read(&txq->q_stats.packets); + bts = u64_stats_read(&txq->q_stats.bytes); } while (u64_stats_fetch_retry(&txq->stats_sync, start)); + + packets += pkts; + bytes += bts; } idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->tx_dim, @@ -3987,9 +3990,12 @@ check_rx_itr: do { start = u64_stats_fetch_begin(&rxq->stats_sync); - packets += u64_stats_read(&rxq->q_stats.packets); - bytes += u64_stats_read(&rxq->q_stats.bytes); + pkts = u64_stats_read(&rxq->q_stats.packets); + bts = u64_stats_read(&rxq->q_stats.bytes); } while (u64_stats_fetch_retry(&rxq->stats_sync, start)); + + packets += pkts; + bytes += bts; } idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->rx_dim, diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 498ba1522ca4..9482ab11f050 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -443,9 +443,10 @@ #define IGC_TXPBSIZE_DEFAULT ( \ IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \ IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4)) +/* TSN value following I225/I226 SW User Manual Section 7.5.4 */ #define IGC_TXPBSIZE_TSN ( \ - IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \ - IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4)) + IGC_TXPB0SIZE(5) | IGC_TXPB1SIZE(5) | IGC_TXPB2SIZE(5) | \ + IGC_TXPB3SIZE(5) | IGC_OS2BMCPBSIZE(4)) #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index e94c1922b97a..3172cdbca9cc 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1565,8 +1565,8 @@ static int igc_ethtool_set_channels(struct net_device *netdev, if (ch->other_count != NON_Q_VECTORS) return -EINVAL; - /* Do not allow channel reconfiguration when mqprio is enabled */ - if (adapter->strict_priority_enable) + /* Do not allow channel reconfiguration when any TSN qdisc is enabled */ + if (adapter->flags & IGC_FLAG_TSN_ANY_ENABLED) return -EINVAL; /* Verify the number of channels doesn't exceed hw limits */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7aafa60ba0c8..89a321a344d2 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7759,6 +7759,11 @@ int igc_reinit_queues(struct igc_adapter *adapter) if (netif_running(netdev)) err = igc_open(netdev); + if (!err) { + /* Restore default IEEE 802.1Qbv schedule after queue reinit */ + igc_tsn_clear_schedule(adapter); + } + return err; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index b7b46d863bee..7aae83c108fd 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -774,36 +774,43 @@ static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter, static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + u32 txstmpl_old; u64 regval; u32 mask; int i; + /* Establish baseline of TXSTMPL_0 before checking TXTT_0. + * This baseline is used to detect if a new timestamp arrives in + * register 0 during the hardware bug workaround below. + */ + txstmpl_old = rd32(IGC_TXSTMPL); + mask = rd32(IGC_TSYNCTXCTL) & IGC_TSYNCTXCTL_TXTT_ANY; if (mask & IGC_TSYNCTXCTL_TXTT_0) { regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; } else { - /* There's a bug in the hardware that could cause - * missing interrupts for TX timestamping. The issue - * is that for new interrupts to be triggered, the - * IGC_TXSTMPH_0 register must be read. + /* TXTT_0 not set - register 0 has no new timestamp initially. + * + * Hardware bug: Future timestamp interrupts won't fire unless + * TXSTMPH_0 is read, even if the timestamp was captured in + * registers 1-3. * - * To avoid discarding a valid timestamp that just - * happened at the "wrong" time, we need to confirm - * that there was no timestamp captured, we do that by - * assuming that no two timestamps in sequence have - * the same nanosecond value. + * Workaround: Read TXSTMPH_0 here to enable future interrupts. + * However, this read clears TXTT_0. If a timestamp arrives in + * register 0 after checking TXTT_0 but before this read, it + * would be lost. * - * So, we read the "low" register, read the "high" - * register (to latch a new timestamp) and read the - * "low" register again, if "old" and "new" versions - * of the "low" register are different, a valid - * timestamp was captured, we can read the "high" - * register again. + * To detect this race: We saved a baseline read of TXSTMPL_0 + * before TXTT_0 check. After performing the workaround read of + * TXSTMPH_0, we read TXSTMPL_0 again. Since consecutive + * timestamps never share the same nanosecond value, a change + * between the baseline and new TXSTMPL_0 indicates a timestamp + * arrived during the race window. If so, read the complete + * timestamp. */ - u32 txstmpl_old, txstmpl_new; + u32 txstmpl_new; - txstmpl_old = rd32(IGC_TXSTMPL); rd32(IGC_TXSTMPH); txstmpl_new = rd32(IGC_TXSTMPL); @@ -818,7 +825,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) done: /* Now that the problematic first register was handled, we can - * use retrieve the timestamps from the other registers + * retrieve the timestamps from the other registers * (starting from '1') with less complications. */ for (i = 1; i < IGC_MAX_TX_TSTAMP_REGS; i++) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 2d78e08f985f..747fbdf2a908 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1551,8 +1551,8 @@ static int rvu_get_attach_blkaddr(struct rvu *rvu, int blktype, return -ENODEV; } -static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, - int num_lfs, struct rsrc_attach *attach) +static int rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, + int num_lfs, struct rsrc_attach *attach) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct rvu_hwinfo *hw = rvu->hw; @@ -1562,21 +1562,21 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, u64 cfg; if (!num_lfs) - return; + return -EINVAL; blkaddr = rvu_get_attach_blkaddr(rvu, blktype, pcifunc, attach); if (blkaddr < 0) - return; + return -EFAULT; block = &hw->block[blkaddr]; if (!block->lf.bmap) - return; + return -ESRCH; for (slot = 0; slot < num_lfs; slot++) { /* Allocate the resource */ lf = rvu_alloc_rsrc(&block->lf); if (lf < 0) - return; + return -EFAULT; cfg = (1ULL << 63) | (pcifunc << 8) | slot; rvu_write64(rvu, blkaddr, block->lfcfg_reg | @@ -1587,6 +1587,8 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, /* Set start MSIX vector for this LF within this PF/VF */ rvu_set_msix_offset(rvu, pfvf, block, lf); } + + return 0; } static int rvu_check_rsrc_availability(struct rvu *rvu, @@ -1724,22 +1726,31 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, int err; /* If first request, detach all existing attached resources */ - if (!attach->modify) - rvu_detach_rsrcs(rvu, NULL, pcifunc); + if (!attach->modify) { + err = rvu_detach_rsrcs(rvu, NULL, pcifunc); + if (err) + return err; + } mutex_lock(&rvu->rsrc_lock); /* Check if the request can be accommodated */ err = rvu_check_rsrc_availability(rvu, attach, pcifunc); if (err) - goto exit; + goto fail1; /* Now attach the requested resources */ - if (attach->npalf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); + if (attach->npalf) { + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); + if (err) + goto fail1; + } - if (attach->nixlf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); + if (attach->nixlf) { + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); + if (err) + goto fail2; + } if (attach->sso) { /* RVU func doesn't know which exact LF or slot is attached @@ -1749,33 +1760,64 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, */ if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, - attach->sso, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, + attach->sso, attach); + if (err) + goto fail3; } if (attach->ssow) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, - attach->ssow, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, + attach->ssow, attach); + if (err) + goto fail4; } if (attach->timlfs) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); - rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, - attach->timlfs, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, + attach->timlfs, attach); + if (err) + goto fail5; } if (attach->cptlfs) { if (attach->modify && rvu_attach_from_same_block(rvu, BLKTYPE_CPT, attach)) rvu_detach_block(rvu, pcifunc, BLKTYPE_CPT); - rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, - attach->cptlfs, attach); + err = rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, + attach->cptlfs, attach); + if (err) + goto fail6; } -exit: + mutex_unlock(&rvu->rsrc_lock); + return 0; + +fail6: + if (attach->timlfs) + rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); + +fail5: + if (attach->ssow) + rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); + +fail4: + if (attach->sso) + rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); + +fail3: + if (attach->nixlf) + rvu_detach_block(rvu, pcifunc, BLKTYPE_NIX); + +fail2: + if (attach->npalf) + rvu_detach_block(rvu, pcifunc, BLKTYPE_NPA); + +fail1: mutex_unlock(&rvu->rsrc_lock); return err; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 3abd750a4bd7..3d91a34f8b57 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -1222,6 +1222,9 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu, u8 cgx_idx, lmac; void *cgxd; + if (!rvu->fwdata) + return LMAC_AF_ERR_FIRMWARE_DATA_NOT_MAPPED; + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) return -EPERM; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index e4a5f9fa6fd4..bbfd8231aed5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -56,7 +56,7 @@ int rvu_sdp_init(struct rvu *rvu) struct rvu_pfvf *pfvf; u32 i = 0; - if (rvu->fwdata->channel_data.valid) { + if (rvu->fwdata && rvu->fwdata->channel_data.valid) { sdp_pf_num[0] = 0; pfvf = &rvu->pf[sdp_pf_num[0]]; pfvf->sdp_info = &rvu->fwdata->channel_data.info; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 4c7e0f345cb5..060c715ebad0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -328,7 +328,7 @@ static int cn10k_mcs_write_rx_flowid(struct otx2_nic *pfvf, req->data[0] = FIELD_PREP(MCS_TCAM0_MAC_DA_MASK, mac_da); req->mask[0] = ~0ULL; - req->mask[0] = ~MCS_TCAM0_MAC_DA_MASK; + req->mask[0] &= ~MCS_TCAM0_MAC_DA_MASK; req->data[1] = FIELD_PREP(MCS_TCAM1_ETYPE_MASK, ETH_P_MACSEC); req->mask[1] = ~0ULL; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index e616a727a3a9..8cdfc36d79d2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -940,13 +940,8 @@ static inline dma_addr_t otx2_dma_map_page(struct otx2_nic *pfvf, size_t offset, size_t size, enum dma_data_direction dir) { - dma_addr_t iova; - - iova = dma_map_page_attrs(pfvf->dev, page, + return dma_map_page_attrs(pfvf->dev, page, offset, size, dir, DMA_ATTR_SKIP_CPU_SYNC); - if (unlikely(dma_mapping_error(pfvf->dev, iova))) - return (dma_addr_t)NULL; - return iova; } static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index a7feb4c392b3..6b2d8559f0eb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -3249,7 +3249,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->watchdog_timeo = OTX2_TX_TIMEOUT; netdev->netdev_ops = &otx2_netdev_ops; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(pf); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 59e5fb2e7e05..347a0078f622 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4365,11 +4365,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int first_entry, tx_packets; struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; + bool set_ic, is_last_segment; u32 pay_len, mss, queue; int i, first_tx, nfrags; u8 proto_hdr_len, hdr; dma_addr_t des; - bool set_ic; /* Always insert VLAN tag to SKB payload for TSO frames. * @@ -4557,10 +4557,16 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) stmmac_enable_tx_timestamp(priv, first); } + /* If we only have one entry used, then the first entry is the last + * segment. + */ + is_last_segment = ((tx_q->cur_tx - first_entry) & + (priv->dma_conf.dma_tx_size - 1)) == 1; + /* Complete the first descriptor before granting the DMA */ stmmac_prepare_tso_tx_desc(priv, first, 1, proto_hdr_len, 0, 1, - tx_q->tx_skbuff_dma[first_entry].last_segment, - hdr / 4, (skb->len - proto_hdr_len)); + is_last_segment, hdr / 4, + skb->len - proto_hdr_len); /* If context desc is used to change MSS */ if (mss_desc) { diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index 62d7f47d4f8d..f0514251d4f3 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -70,7 +70,7 @@ int txgbe_test_hostif(struct wx *wx) buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), - WX_HI_COMMAND_TIMEOUT, true); + WX_HI_COMMAND_TIMEOUT, false); } int txgbe_read_eeprom_hostif(struct wx *wx, @@ -148,7 +148,7 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int buffer.duplex = duplex; return wx_host_interface_command(wx, (u32 *)&buffer, sizeof(buffer), - WX_HI_COMMAND_TIMEOUT, true); + WX_HI_COMMAND_TIMEOUT, false); } static void txgbe_get_link_capabilities(struct wx *wx, int *speed, diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 50de3ee204db..80f84fc87008 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -69,7 +69,6 @@ struct ipvl_dev { DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; - spinlock_t addrs_lock; }; struct ipvl_addr { @@ -90,6 +89,7 @@ struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; + spinlock_t addrs_lock; /* guards hash-table and addrs */ struct list_head ipvlans; u16 mode; u16 flags; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2efa3ba148aa..bdb3a46b327c 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -107,17 +107,15 @@ void ipvlan_ht_addr_del(struct ipvl_addr *addr) struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6) { - struct ipvl_addr *addr, *ret = NULL; + struct ipvl_addr *addr; - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) { - if (addr_equal(is_v6, addr, iaddr)) { - ret = addr; - break; - } + assert_spin_locked(&ipvlan->port->addrs_lock); + + list_for_each_entry(addr, &ipvlan->addrs, anode) { + if (addr_equal(is_v6, addr, iaddr)) + return addr; } - rcu_read_unlock(); - return ret; + return NULL; } bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 660f3db11766..baccdad695fd 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -75,6 +75,7 @@ static int ipvlan_port_create(struct net_device *dev) for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); + spin_lock_init(&port->addrs_lock); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); @@ -181,6 +182,7 @@ static void ipvlan_uninit(struct net_device *dev) static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); + struct ipvl_port *port = ipvlan->port; struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || @@ -189,10 +191,10 @@ static int ipvlan_open(struct net_device *dev) else dev->flags &= ~IFF_NOARP; - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) + spin_lock_bh(&port->addrs_lock); + list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); - rcu_read_unlock(); + spin_unlock_bh(&port->addrs_lock); return 0; } @@ -206,10 +208,10 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); - rcu_read_lock(); - list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) + spin_lock_bh(&ipvlan->port->addrs_lock); + list_for_each_entry(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); - rcu_read_unlock(); + spin_unlock_bh(&ipvlan->port->addrs_lock); return 0; } @@ -579,7 +581,6 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); - spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing @@ -657,13 +658,13 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head) struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); @@ -817,6 +818,8 @@ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; + assert_spin_locked(&ipvlan->port->addrs_lock); + addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; @@ -847,16 +850,16 @@ static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); kfree_rcu(addr, rcu); } @@ -878,14 +881,14 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return ret; } @@ -924,21 +927,24 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); + int ret = NOTIFY_OK; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); - return notifier_from_errno(-EADDRINUSE); + ret = notifier_from_errno(-EADDRINUSE); } + spin_unlock_bh(&ipvlan->port->addrs_lock); break; } - return NOTIFY_OK; + return ret; } #endif @@ -946,14 +952,14 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; - spin_lock_bh(&ipvlan->addrs_lock); + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); - spin_unlock_bh(&ipvlan->addrs_lock); + spin_unlock_bh(&ipvlan->port->addrs_lock); return ret; } @@ -995,21 +1001,24 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused, struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); + int ret = NOTIFY_OK; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: + spin_lock_bh(&ipvlan->port->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); - return notifier_from_errno(-EADDRINUSE); + ret = notifier_from_errno(-EADDRINUSE); } + spin_unlock_bh(&ipvlan->port->addrs_lock); break; } - return NOTIFY_OK; + return ret; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 49537d3c4120..5f17f68f3c08 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -244,7 +244,9 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, &state->state, &nsim_bpf_string_fops); debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded); + mutex_lock(&nsim_dev->progs_list_lock); list_add_tail(&state->l, &nsim_dev->bpf_bound_progs); + mutex_unlock(&nsim_dev->progs_list_lock); prog->aux->offload->dev_priv = state; @@ -273,12 +275,16 @@ static int nsim_bpf_translate(struct bpf_prog *prog) static void nsim_bpf_destroy_prog(struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state; + struct nsim_dev *nsim_dev; state = prog->aux->offload->dev_priv; + nsim_dev = state->nsim_dev; WARN(state->is_loaded, "offload state destroyed while program still bound"); debugfs_remove_recursive(state->ddir); + mutex_lock(&nsim_dev->progs_list_lock); list_del(&state->l); + mutex_unlock(&nsim_dev->progs_list_lock); kfree(state); } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 2683a989873e..dfd571b22107 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1647,6 +1647,7 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; nsim_dev->test2 = NSIM_DEV_TEST2_DEFAULT; spin_lock_init(&nsim_dev->fa_cookie_lock); + mutex_init(&nsim_dev->progs_list_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); @@ -1785,6 +1786,7 @@ void nsim_drv_remove(struct nsim_bus_dev *nsim_bus_dev) devl_unregister(devlink); kfree(nsim_dev->vfconfigs); kfree(nsim_dev->fa_cookie); + mutex_destroy(&nsim_dev->progs_list_lock); devl_unlock(devlink); devlink_free(devlink); dev_set_drvdata(&nsim_bus_dev->dev, NULL); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index d1a941e2b18f..46c67983c517 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -324,6 +324,7 @@ struct nsim_dev { u32 prog_id_gen; struct list_head bpf_bound_progs; struct list_head bpf_bound_maps; + struct mutex progs_list_lock; struct netdev_phys_item_id switch_id; struct list_head port_list; bool fw_update_status; diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index 74dbce205f71..44006bb6ac0b 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -96,12 +96,10 @@ static unsigned int mtk_pcs_lynxi_inband_caps(struct phylink_pcs *pcs, { switch (interface) { case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: case PHY_INTERFACE_MODE_SGMII: return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; - case PHY_INTERFACE_MODE_2500BASEX: - return LINK_INBAND_DISABLE; - default: return 0; } diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index 9766dd99afaa..12ff4c1f285d 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -277,7 +277,7 @@ static int xway_gphy_init_leds(struct phy_device *phydev) static int xway_gphy_config_init(struct phy_device *phydev) { - struct device_node *np = phydev->mdio.dev.of_node; + struct device_node *np; int err; /* Mask all interrupts */ @@ -286,7 +286,10 @@ static int xway_gphy_config_init(struct phy_device *phydev) return err; /* Use default LED configuration if 'leds' node isn't defined */ - if (!of_get_child_by_name(np, "leds")) + np = of_get_child_by_name(phydev->mdio.dev.of_node, "leds"); + if (np) + of_node_put(np); + else xway_gphy_init_leds(phydev); /* Clear all pending interrupts */ diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 84bef5099dda..47f095bd91ce 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -519,6 +519,8 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_F("HALNy", "HL-GSFP", sfp_fixup_halny_gsfp), + SFP_QUIRK_F("H-COM", "SPP425H-GAB4", sfp_fixup_potron), + // HG MXPD-483II-F 2.5G supports 2500Base-X, but incorrectly reports // 2600MBd in their EERPOM SFP_QUIRK_S("HG GENUINE", "MXPD-483II", sfp_quirk_2500basex), diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 8b6d6a1b3c2e..2b4716ccf0c5 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -604,10 +604,6 @@ static const struct usb_device_id products[] = { .driver_info = (unsigned long)&dm9601_info, }, { - USB_DEVICE(0x0fe6, 0x9700), /* DM9601 USB to Fast Ethernet Adapter */ - .driver_info = (unsigned long)&dm9601_info, - }, - { USB_DEVICE(0x0a46, 0x9000), /* DM9000E */ .driver_info = (unsigned long)&dm9601_info, }, diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 36742e64cff7..9280ef544bbb 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1821,9 +1821,12 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_NOARP) != 0) net->flags |= IFF_NOARP; - /* maybe the remote can't receive an Ethernet MTU */ - if (net->mtu > (dev->hard_mtu - net->hard_header_len)) - net->mtu = dev->hard_mtu - net->hard_header_len; + if (net->max_mtu > (dev->hard_mtu - net->hard_header_len)) + net->max_mtu = dev->hard_mtu - net->hard_header_len; + + if (net->mtu > net->max_mtu) + net->mtu = net->max_mtu; + } else if (!info->in || !info->out) status = usbnet_get_endpoints(dev, udev); else { @@ -1984,6 +1987,7 @@ int usbnet_resume(struct usb_interface *intf) } else { netif_trans_update(dev->net); __skb_queue_tail(&dev->txq, skb); + netdev_sent_queue(dev->net, skb->len); } } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 14e6f2a2fb77..9982412fd7f2 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -228,16 +228,20 @@ static void veth_get_ethtool_stats(struct net_device *dev, const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats; const void *base = (void *)&rq_stats->vs; unsigned int start, tx_idx = idx; + u64 buf[VETH_TQ_STATS_LEN]; size_t offset; - tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_TQ_STATS_LEN; j++) { offset = veth_tq_stats_desc[j].offset; - data[tx_idx + j] += *(u64 *)(base + offset); + buf[j] = *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); + + tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; + for (j = 0; j < VETH_TQ_STATS_LEN; j++) + data[tx_idx + j] += buf[j]; } pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c index 7bbda46cfd93..82f120ee1c66 100644 --- a/drivers/net/wireless/ath/ath10k/ce.c +++ b/drivers/net/wireless/ath/ath10k/ce.c @@ -1727,8 +1727,8 @@ static void _ath10k_ce_free_pipe(struct ath10k *ar, int ce_id) (ce_state->src_ring->nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), - ce_state->src_ring->base_addr_owner_space, - ce_state->src_ring->base_addr_ce_space); + ce_state->src_ring->base_addr_owner_space_unaligned, + ce_state->src_ring->base_addr_ce_space_unaligned); kfree(ce_state->src_ring); } @@ -1737,8 +1737,8 @@ static void _ath10k_ce_free_pipe(struct ath10k *ar, int ce_id) (ce_state->dest_ring->nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), - ce_state->dest_ring->base_addr_owner_space, - ce_state->dest_ring->base_addr_ce_space); + ce_state->dest_ring->base_addr_owner_space_unaligned, + ce_state->dest_ring->base_addr_ce_space_unaligned); kfree(ce_state->dest_ring); } @@ -1758,8 +1758,8 @@ static void _ath10k_ce_free_pipe_64(struct ath10k *ar, int ce_id) (ce_state->src_ring->nentries * sizeof(struct ce_desc_64) + CE_DESC_RING_ALIGN), - ce_state->src_ring->base_addr_owner_space, - ce_state->src_ring->base_addr_ce_space); + ce_state->src_ring->base_addr_owner_space_unaligned, + ce_state->src_ring->base_addr_ce_space_unaligned); kfree(ce_state->src_ring); } @@ -1768,8 +1768,8 @@ static void _ath10k_ce_free_pipe_64(struct ath10k *ar, int ce_id) (ce_state->dest_ring->nentries * sizeof(struct ce_desc_64) + CE_DESC_RING_ALIGN), - ce_state->dest_ring->base_addr_owner_space, - ce_state->dest_ring->base_addr_ce_space); + ce_state->dest_ring->base_addr_owner_space_unaligned, + ce_state->dest_ring->base_addr_ce_space_unaligned); kfree(ce_state->dest_ring); } diff --git a/drivers/net/wireless/ath/ath12k/ce.c b/drivers/net/wireless/ath/ath12k/ce.c index 9f9d2f2477c7..f13b260c5c96 100644 --- a/drivers/net/wireless/ath/ath12k/ce.c +++ b/drivers/net/wireless/ath/ath12k/ce.c @@ -686,8 +686,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->src_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->src_ring->base_addr_owner_space, - pipe->src_ring->base_addr_ce_space); + pipe->src_ring->base_addr_owner_space_unaligned, + pipe->src_ring->base_addr_ce_space_unaligned); kfree(pipe->src_ring); pipe->src_ring = NULL; } @@ -698,8 +698,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->dest_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->dest_ring->base_addr_owner_space, - pipe->dest_ring->base_addr_ce_space); + pipe->dest_ring->base_addr_owner_space_unaligned, + pipe->dest_ring->base_addr_ce_space_unaligned); kfree(pipe->dest_ring); pipe->dest_ring = NULL; } @@ -711,8 +711,8 @@ void ath12k_ce_free_pipes(struct ath12k_base *ab) dma_free_coherent(ab->dev, pipe->status_ring->nentries * desc_sz + CE_DESC_RING_ALIGN, - pipe->status_ring->base_addr_owner_space, - pipe->status_ring->base_addr_ce_space); + pipe->status_ring->base_addr_owner_space_unaligned, + pipe->status_ring->base_addr_ce_space_unaligned); kfree(pipe->status_ring); pipe->status_ring = NULL; } diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index 2f4daee9e2f0..5cd10752b22e 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -5606,7 +5606,8 @@ void ath12k_mac_op_cancel_hw_scan(struct ieee80211_hw *hw, for_each_set_bit(link_id, &links_map, ATH12K_NUM_MAX_LINKS) { arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); - if (!arvif || arvif->is_started) + if (!arvif || !arvif->is_created || + arvif->ar->scan.arvif != arvif) continue; ar = arvif->ar; @@ -12214,6 +12215,9 @@ void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, if (drop) return; + for_each_ar(ah, ar, i) + wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); + /* vif can be NULL when flush() is considered for hw */ if (!vif) { for_each_ar(ah, ar, i) @@ -12221,9 +12225,6 @@ void ath12k_mac_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return; } - for_each_ar(ah, ar, i) - wiphy_work_flush(hw->wiphy, &ar->wmi_mgmt_tx_work); - ahvif = ath12k_vif_to_ahvif(vif); links = ahvif->links_map; for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { @@ -13448,7 +13449,7 @@ int ath12k_mac_op_cancel_remain_on_channel(struct ieee80211_hw *hw, ath12k_scan_abort(ar); cancel_delayed_work_sync(&ar->scan.timeout); - wiphy_work_cancel(hw->wiphy, &ar->scan.vdev_clean_wk); + wiphy_work_flush(hw->wiphy, &ar->scan.vdev_clean_wk); return 0; } diff --git a/drivers/net/wireless/ath/ath12k/wifi7/hw.c b/drivers/net/wireless/ath/ath12k/wifi7/hw.c index 1f5dda73230d..8ac06b2fc18f 100644 --- a/drivers/net/wireless/ath/ath12k/wifi7/hw.c +++ b/drivers/net/wireless/ath/ath12k/wifi7/hw.c @@ -705,7 +705,10 @@ static void ath12k_wifi7_mac_op_tx(struct ieee80211_hw *hw, return; } } else { - link_id = 0; + if (vif->type == NL80211_IFTYPE_P2P_DEVICE) + link_id = ATH12K_FIRST_SCAN_LINK; + else + link_id = 0; } arvif = rcu_dereference(ahvif->link[link_id]); diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 150b04d0a21c..17ffc4822741 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -6479,16 +6479,9 @@ static int freq_to_idx(struct ath12k *ar, int freq) if (!sband) continue; - for (ch = 0; ch < sband->n_channels; ch++, idx++) { - if (sband->channels[ch].center_freq < - KHZ_TO_MHZ(ar->freq_range.start_freq) || - sband->channels[ch].center_freq > - KHZ_TO_MHZ(ar->freq_range.end_freq)) - continue; - + for (ch = 0; ch < sband->n_channels; ch++, idx++) if (sband->channels[ch].center_freq == freq) goto exit; - } } exit: diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index 354c5ce66045..f3397dc6c422 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -825,7 +825,7 @@ void mwifiex_update_rxreor_flags(struct mwifiex_adapter *adapter, u8 flags) static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter, bool coex_flag) { - u8 i; + u8 i, j; u32 rx_win_size; struct mwifiex_private *priv; @@ -863,8 +863,8 @@ static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter, if (rx_win_size != priv->add_ba_param.rx_win_size) { if (!priv->media_connected) continue; - for (i = 0; i < MAX_NUM_TID; i++) - mwifiex_11n_delba(priv, i); + for (j = 0; j < MAX_NUM_TID; j++) + mwifiex_11n_delba(priv, j); } } } diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index f3a853edfc11..8c8e074a3a70 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -2035,6 +2035,7 @@ int rsi_mac80211_attach(struct rsi_common *common) hw->queues = MAX_HW_QUEUES; hw->extra_tx_headroom = RSI_NEEDED_HEADROOM; + hw->vif_data_size = sizeof(struct vif_priv); hw->max_rates = 1; hw->max_rate_tries = MAX_RETRIES; diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index cf6d3e2a007b..1d7e3ad900c1 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -78,9 +78,8 @@ struct mhi_mbim_context { struct mbim_tx_hdr { struct usb_cdc_ncm_nth16 nth16; - - /* Must be last as it ends in a flexible-array member. */ struct usb_cdc_ncm_ndp16 ndp16; + struct usb_cdc_ncm_dpe16 dpe16[2]; } __packed; static struct mhi_mbim_link *mhi_mbim_get_link_rcu(struct mhi_mbim_context *mbim, @@ -109,20 +108,20 @@ static int mhi_mbim_get_link_mux_id(struct mhi_controller *cntrl) static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session, u16 tx_seq) { - DEFINE_RAW_FLEX(struct mbim_tx_hdr, mbim_hdr, ndp16.dpe16, 2); unsigned int dgram_size = skb->len; struct usb_cdc_ncm_nth16 *nth16; struct usb_cdc_ncm_ndp16 *ndp16; + struct mbim_tx_hdr *mbim_hdr; /* Only one NDP is sent, containing the IP packet (no aggregation) */ /* Ensure we have enough headroom for crafting MBIM header */ - if (skb_cow_head(skb, __struct_size(mbim_hdr))) { + if (skb_cow_head(skb, sizeof(struct mbim_tx_hdr))) { dev_kfree_skb_any(skb); return NULL; } - mbim_hdr = skb_push(skb, __struct_size(mbim_hdr)); + mbim_hdr = skb_push(skb, sizeof(struct mbim_tx_hdr)); /* Fill NTB header */ nth16 = &mbim_hdr->nth16; @@ -135,11 +134,12 @@ static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session, /* Fill the unique NDP */ ndp16 = &mbim_hdr->ndp16; ndp16->dwSignature = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN | (session << 24)); - ndp16->wLength = cpu_to_le16(struct_size(ndp16, dpe16, 2)); + ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) + + sizeof(struct usb_cdc_ncm_dpe16) * 2); ndp16->wNextNdpIndex = 0; /* Datagram follows the mbim header */ - ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(__struct_size(mbim_hdr)); + ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(sizeof(struct mbim_tx_hdr)); ndp16->dpe16[0].wDatagramLength = cpu_to_le16(dgram_size); /* null termination */ @@ -585,8 +585,7 @@ static void mhi_mbim_setup(struct net_device *ndev) { ndev->header_ops = NULL; /* No header */ ndev->type = ARPHRD_RAWIP; - ndev->needed_headroom = - struct_size_t(struct mbim_tx_hdr, ndp16.dpe16, 2); + ndev->needed_headroom = sizeof(struct mbim_tx_hdr); ndev->hard_header_len = 0; ndev->addr_len = 0; ndev->flags = IFF_POINTOPOINT | IFF_NOARP; diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 9ef8ef2d4363..b957fce83b7c 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -125,10 +125,6 @@ static ssize_t virtual_ncidev_write(struct file *file, kfree_skb(skb); return -EFAULT; } - if (strnlen(skb->data, count) != count) { - kfree_skb(skb); - return -EINVAL; - } nci_recv_frame(vdev->ndev, skb); return count; diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 15b3d07f8ccd..ed61b97fde59 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1704,6 +1704,7 @@ static const struct apple_nvme_hw apple_nvme_t8103_hw = { static const struct of_device_id apple_nvme_of_match[] = { { .compatible = "apple,t8015-nvme-ans2", .data = &apple_nvme_t8015_hw }, + { .compatible = "apple,t8103-nvme-ans2", .data = &apple_nvme_t8103_hw }, { .compatible = "apple,nvme-ans2", .data = &apple_nvme_t8103_hw }, {}, }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index bc455fa98246..6948de3f438a 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3587,6 +3587,8 @@ fail_ctrl: ctrl->ctrl.opts = NULL; + if (ctrl->ctrl.admin_tagset) + nvme_remove_admin_tag_set(&ctrl->ctrl); /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0e4caeab739c..58f3097888a7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1532,7 +1532,10 @@ static int nvme_pci_subsystem_reset(struct nvme_ctrl *ctrl) } writel(NVME_SUBSYS_RESET, dev->bar + NVME_REG_NSSR); - nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE); + + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) + goto unlock; /* * Read controller status to flush the previous write and trigger a @@ -3999,6 +4002,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1fa0, 0x2283), /* Wodposit WPBSNM8-256GTP */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 96648ec2fadb..67c423a8b052 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -150,7 +150,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req) * code path with duplicate ctrl subsysnqn. In order to prevent that we * mask the passthru-ctrl subsysnqn with the target ctrl subsysnqn. */ - memcpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); + strscpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); /* use fabric id-ctrl values */ id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) + diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 15416ff0eac4..549a4786d1c3 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -982,6 +982,18 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len); goto err_proto; } + /* + * Ensure command data structures are initialized. We must check both + * cmd->req.sg and cmd->iov because they can have different NULL states: + * - Uninitialized commands: both NULL + * - READ commands: cmd->req.sg allocated, cmd->iov NULL + * - WRITE commands: both allocated + */ + if (unlikely(!cmd->req.sg || !cmd->iov)) { + pr_err("queue %d: H2CData PDU received for invalid command state (ttag %u)\n", + queue->idx, data->ttag); + goto err_proto; + } cmd->pdu_recv = 0; nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; @@ -1992,14 +2004,13 @@ static void nvmet_tcp_listen_data_ready(struct sock *sk) trace_sk_data_ready(sk); + if (sk->sk_state != TCP_LISTEN) + return; + read_lock_bh(&sk->sk_callback_lock); port = sk->sk_user_data; - if (!port) - goto out; - - if (sk->sk_state == TCP_LISTEN) + if (port) queue_work(nvmet_wq, &port->accept_work); -out: read_unlock_bh(&sk->sk_callback_lock); } diff --git a/drivers/of/base.c b/drivers/of/base.c index 0b65039ece53..57420806c1a2 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1942,13 +1942,17 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) end--; len = end - start; - if (kstrtoint(end, 10, &id) < 0) + if (kstrtoint(end, 10, &id) < 0) { + of_node_put(np); continue; + } /* Allocate an alias_prop with enough space for the stem */ ap = dt_alloc(sizeof(*ap) + len + 1, __alignof__(*ap)); - if (!ap) + if (!ap) { + of_node_put(np); continue; + } memset(ap, 0, sizeof(*ap) + len + 1); ap->alias = start; of_alias_add(ap, np, id, start, len); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index f77cb19973a5..a6dca3a005aa 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -569,7 +569,7 @@ static int __init of_platform_default_populate_init(void) node = of_find_node_by_path("/firmware"); if (node) { - of_platform_populate(node, NULL, NULL, NULL); + of_platform_default_populate(node, NULL, NULL); of_node_put(node); } diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 00b0210e1f1d..e3f848ffb52a 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -225,12 +225,6 @@ config PCI_P2PDMA P2P DMA transactions must be between devices behind the same root port. - Enabling this option will reduce the entropy of x86 KASLR memory - regions. For example - on a 46 bit system, the entropy goes down - from 16 bits to 15 bits. The actual reduction in entropy depends - on the physical address bits, on processor features, kernel config - (5 level page table) and physical memory present on the system. - If unsure, say N. config PCI_LABEL diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb3.c b/drivers/phy/broadcom/phy-bcm-ns-usb3.c index 9f995e156f75..6e56498d0644 100644 --- a/drivers/phy/broadcom/phy-bcm-ns-usb3.c +++ b/drivers/phy/broadcom/phy-bcm-ns-usb3.c @@ -203,7 +203,7 @@ static int bcm_ns_usb3_mdio_probe(struct mdio_device *mdiodev) usb3->dev = dev; usb3->mdiodev = mdiodev; - usb3->family = (enum bcm_ns_family)device_get_match_data(dev); + usb3->family = (unsigned long)device_get_match_data(dev); syscon_np = of_parse_phandle(dev->of_node, "usb3-dmp-syscon", 0); err = of_address_to_resource(syscon_np, 0, &res); diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index 68fcc8114d75..7f5600103a00 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -89,7 +89,8 @@ static int imx8_pcie_phy_power_on(struct phy *phy) writel(imx8_phy->tx_deemph_gen2, imx8_phy->base + PCIE_PHY_TRSV_REG6); break; - case IMX8MP: /* Do nothing. */ + case IMX8MP: + reset_control_assert(imx8_phy->reset); break; } diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c index ad8a55012e42..91b3e62743d3 100644 --- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c +++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c @@ -126,8 +126,6 @@ struct imx8mq_usb_phy { static void tca_blk_orientation_set(struct tca_blk *tca, enum typec_orientation orientation); -#ifdef CONFIG_TYPEC - static int tca_blk_typec_switch_set(struct typec_switch_dev *sw, enum typec_orientation orientation) { @@ -175,18 +173,6 @@ static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) typec_switch_unregister(sw); } -#else - -static struct typec_switch_dev *tca_blk_get_typec_switch(struct platform_device *pdev, - struct imx8mq_usb_phy *imx_phy) -{ - return NULL; -} - -static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) {} - -#endif /* CONFIG_TYPEC */ - static void tca_blk_orientation_set(struct tca_blk *tca, enum typec_orientation orientation) { @@ -504,6 +490,7 @@ static void imx8m_phy_tune(struct imx8mq_usb_phy *imx_phy) if (imx_phy->pcs_tx_swing_full != PHY_TUNE_DEFAULT) { value = readl(imx_phy->base + PHY_CTRL5); + value &= ~PHY_CTRL5_PCS_TX_SWING_FULL_MASK; value |= FIELD_PREP(PHY_CTRL5_PCS_TX_SWING_FULL_MASK, imx_phy->pcs_tx_swing_full); writel(value, imx_phy->base + PHY_CTRL5); diff --git a/drivers/phy/microchip/Kconfig b/drivers/phy/microchip/Kconfig index 2f0045e874ac..2e6d1224711e 100644 --- a/drivers/phy/microchip/Kconfig +++ b/drivers/phy/microchip/Kconfig @@ -6,7 +6,7 @@ config PHY_SPARX5_SERDES tristate "Microchip Sparx5 SerDes PHY driver" select GENERIC_PHY - depends on ARCH_SPARX5 || COMPILE_TEST + depends on ARCH_SPARX5 || ARCH_LAN969X || COMPILE_TEST depends on OF depends on HAS_IOMEM help diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index b5514a32ff8f..eb93015be841 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -1093,29 +1093,29 @@ static int qusb2_phy_probe(struct platform_device *pdev) or->hsdisc_trim.override = true; } - pm_runtime_set_active(dev); - pm_runtime_enable(dev); + dev_set_drvdata(dev, qphy); + /* - * Prevent runtime pm from being ON by default. Users can enable - * it using power/control in sysfs. + * Enable runtime PM support, but forbid it by default. + * Users can allow it again via the power/control attribute in sysfs. */ + pm_runtime_set_active(dev); pm_runtime_forbid(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; generic_phy = devm_phy_create(dev, NULL, &qusb2_phy_gen_ops); if (IS_ERR(generic_phy)) { ret = PTR_ERR(generic_phy); dev_err(dev, "failed to create phy, %d\n", ret); - pm_runtime_disable(dev); return ret; } qphy->phy = generic_phy; - dev_set_drvdata(dev, qphy); phy_set_drvdata(generic_phy, qphy); phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - pm_runtime_disable(dev); return PTR_ERR_OR_ZERO(phy_provider); } diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index b0f23690ec30..8f4c08e599aa 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -821,17 +821,20 @@ static void rockchip_chg_detect_work(struct work_struct *work) container_of(work, struct rockchip_usb2phy_port, chg_work.work); struct rockchip_usb2phy *rphy = dev_get_drvdata(rport->phy->dev.parent); struct regmap *base = get_reg_base(rphy); - bool is_dcd, tmout, vout; + bool is_dcd, tmout, vout, vbus_attach; unsigned long delay; + vbus_attach = property_enabled(rphy->grf, &rport->port_cfg->utmi_bvalid); + dev_dbg(&rport->phy->dev, "chg detection work state = %d\n", rphy->chg_state); switch (rphy->chg_state) { case USB_CHG_STATE_UNDEFINED: - if (!rport->suspended) + if (!rport->suspended && !vbus_attach) rockchip_usb2phy_power_off(rport->phy); /* put the controller in non-driving mode */ - property_enable(base, &rphy->phy_cfg->chg_det.opmode, false); + if (!vbus_attach) + property_enable(base, &rphy->phy_cfg->chg_det.opmode, false); /* Start DCD processing stage 1 */ rockchip_chg_enable_dcd(rphy, true); rphy->chg_state = USB_CHG_STATE_WAIT_FOR_DCD; @@ -894,7 +897,8 @@ static void rockchip_chg_detect_work(struct work_struct *work) fallthrough; case USB_CHG_STATE_DETECTED: /* put the controller in normal mode */ - property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); + if (!vbus_attach) + property_enable(base, &rphy->phy_cfg->chg_det.opmode, true); rockchip_usb2phy_otg_sm_work(&rport->otg_sm_work.work); dev_dbg(&rport->phy->dev, "charger = %s\n", chg_to_string(rphy->chg_type)); @@ -1491,7 +1495,7 @@ next_child: rphy); if (ret) { dev_err_probe(rphy->dev, ret, "failed to request usb2phy irq handle\n"); - goto put_child; + return ret; } } diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 27fe92f73f33..b44afbff8616 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -712,7 +712,7 @@ static int stm32_usbphyc_probe(struct platform_device *pdev) } ret = of_property_read_u32(child, "reg", &index); - if (ret || index > usbphyc->nphys) { + if (ret || index >= usbphyc->nphys) { dev_err(&phy->dev, "invalid reg property: %d\n", ret); if (!ret) ret = -EINVAL; diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index e818f6c3980e..bec9616c4a2e 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -84,6 +84,7 @@ #define XUSB_PADCTL_USB2_BIAS_PAD_CTL0 0x284 #define BIAS_PAD_PD BIT(11) #define HS_SQUELCH_LEVEL(x) (((x) & 0x7) << 0) +#define HS_DISCON_LEVEL(x) (((x) & 0x7) << 3) #define XUSB_PADCTL_USB2_BIAS_PAD_CTL1 0x288 #define USB2_TRK_START_TIMER(x) (((x) & 0x7f) << 12) @@ -623,6 +624,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) value &= ~BIAS_PAD_PD; value &= ~HS_SQUELCH_LEVEL(~0); value |= HS_SQUELCH_LEVEL(priv->calib.hs_squelch); + value &= ~HS_DISCON_LEVEL(~0); + value |= HS_DISCON_LEVEL(0x7); padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL0); udelay(1); diff --git a/drivers/phy/ti/phy-da8xx-usb.c b/drivers/phy/ti/phy-da8xx-usb.c index 1d81a1e6ec6b..62fa6f89c0e6 100644 --- a/drivers/phy/ti/phy-da8xx-usb.c +++ b/drivers/phy/ti/phy-da8xx-usb.c @@ -180,6 +180,7 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) struct da8xx_usb_phy_platform_data *pdata = dev->platform_data; struct device_node *node = dev->of_node; struct da8xx_usb_phy *d_phy; + int ret; d_phy = devm_kzalloc(dev, sizeof(*d_phy), GFP_KERNEL); if (!d_phy) @@ -233,8 +234,6 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) return PTR_ERR(d_phy->phy_provider); } } else { - int ret; - ret = phy_create_lookup(d_phy->usb11_phy, "usb-phy", "ohci-da8xx"); if (ret) @@ -249,7 +248,9 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) PHY_INIT_BITS, PHY_INIT_BITS); pm_runtime_set_active(dev); - devm_pm_runtime_enable(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; /* * Prevent runtime pm from being ON by default. Users can enable * it using power/control in sysfs. diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index 6cfe2538d15b..6213c2b6005a 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -512,7 +512,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(base), "failed to get base memory resource\n"); - priv->regmap = regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg); + priv->regmap = devm_regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg); if (IS_ERR(priv->regmap)) return dev_err_probe(dev, PTR_ERR(priv->regmap), "Failed to get syscon\n"); diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index a8b37037c6fe..19849703be4a 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -246,6 +246,8 @@ static struct rpmhpd *sa8540p_rpmhpds[] = { [SC8280XP_MMCX_AO] = &mmcx_ao, [SC8280XP_MX] = &mx, [SC8280XP_MX_AO] = &mx_ao, + [SC8280XP_MXC] = &mxc, + [SC8280XP_MXC_AO] = &mxc_ao, [SC8280XP_NSP] = &nsp, }; @@ -700,6 +702,8 @@ static struct rpmhpd *sc8280xp_rpmhpds[] = { [SC8280XP_MMCX_AO] = &mmcx_ao, [SC8280XP_MX] = &mx, [SC8280XP_MX_AO] = &mx_ao, + [SC8280XP_MXC] = &mxc, + [SC8280XP_MXC_AO] = &mxc_ao, [SC8280XP_NSP] = &nsp, [SC8280XP_QPHY] = &qphy, }; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index cd06229db394..ec8731515333 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -2295,8 +2295,9 @@ static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long ar .duty_offset_ns = wf.duty_offset_ns, }; - return copy_to_user((struct pwmchip_waveform __user *)arg, - &cwf, sizeof(cwf)); + ret = copy_to_user((struct pwmchip_waveform __user *)arg, + &cwf, sizeof(cwf)); + return ret ? -EFAULT : 0; } case PWM_IOCTL_GETWF: @@ -2329,8 +2330,9 @@ static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long ar .duty_offset_ns = wf.duty_offset_ns, }; - return copy_to_user((struct pwmchip_waveform __user *)arg, - &cwf, sizeof(cwf)); + ret = copy_to_user((struct pwmchip_waveform __user *)arg, + &cwf, sizeof(cwf)); + return ret ? -EFAULT : 0; } case PWM_IOCTL_SETROUNDEDWF: diff --git a/drivers/pwm/pwm-max7360.c b/drivers/pwm/pwm-max7360.c index 16261958ce7f..732969303dd7 100644 --- a/drivers/pwm/pwm-max7360.c +++ b/drivers/pwm/pwm-max7360.c @@ -153,6 +153,7 @@ static int max7360_pwm_read_waveform(struct pwm_chip *chip, } static const struct pwm_ops max7360_pwm_ops = { + .sizeof_wfhw = sizeof(struct max7360_pwm_waveform), .request = max7360_pwm_request, .round_waveform_tohw = max7360_pwm_round_waveform_tohw, .round_waveform_fromhw = max7360_pwm_round_waveform_fromhw, diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h index e79c3c47259c..e8971842b124 100644 --- a/drivers/resctrl/mpam_internal.h +++ b/drivers/resctrl/mpam_internal.h @@ -12,7 +12,6 @@ #include <linux/jump_label.h> #include <linux/llist.h> #include <linux/mutex.h> -#include <linux/srcu.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/types.h> @@ -201,8 +200,12 @@ struct mpam_props { } PACKED_FOR_KUNIT; #define mpam_has_feature(_feat, x) test_bit(_feat, (x)->features) -#define mpam_set_feature(_feat, x) set_bit(_feat, (x)->features) -#define mpam_clear_feature(_feat, x) clear_bit(_feat, (x)->features) +/* + * The non-atomic get/set operations are used because if struct mpam_props is + * packed, the alignment requirements for atomics aren't met. + */ +#define mpam_set_feature(_feat, x) __set_bit(_feat, (x)->features) +#define mpam_clear_feature(_feat, x) __clear_bit(_feat, (x)->features) /* The values for MSMON_CFG_MBWU_FLT.RWBW */ enum mon_filter_options { diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 91e70cb46fb5..5c67c13e5735 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -105,7 +105,7 @@ static int sdw_drv_probe(struct device *dev) if (ret) return ret; - ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES, GFP_KERNEL); + ret = ida_alloc_max(&slave->bus->slave_ida, SDW_FW_MAX_DEVICES - 1, GFP_KERNEL); if (ret < 0) { dev_err(dev, "Failed to allocated ID: %d\n", ret); return ret; diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index 3d4d00188c26..d933cebad52b 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -23,6 +23,7 @@ const struct device_type sdw_slave_type = { .release = sdw_slave_release, .uevent = sdw_slave_uevent, }; +EXPORT_SYMBOL_GPL(sdw_slave_type); int sdw_slave_add(struct sdw_bus *bus, struct sdw_slave_id *id, struct fwnode_handle *fwnode) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index baf5bc844b6f..2bb1ceb9d621 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -1040,6 +1040,11 @@ int usb_get_bos_descriptor(struct usb_device *dev) __u8 cap_type; int ret; + if (dev->quirks & USB_QUIRK_NO_BOS) { + dev_dbg(ddev, "skipping BOS descriptor\n"); + return -ENOMSG; + } + bos = kzalloc(sizeof(*bos), GFP_KERNEL); if (!bos) return -ENOMEM; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 47f589c4104a..c4d85089d19b 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -450,6 +450,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0c45, 0x7056), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Elgato 4K X - BOS descriptor fetch hangs at SuperSpeed Plus */ + { USB_DEVICE(0x0fd9, 0x009b), .driver_info = USB_QUIRK_NO_BOS }, + /* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */ { USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index ec8407972b9d..93fd5fdf95cb 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -993,6 +993,8 @@ static bool dwc3_core_is_valid(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_GSNPSID); dwc->ip = DWC3_GSNPS_ID(reg); + if (dwc->ip == DWC4_IP) + dwc->ip = DWC32_IP; /* This should read as U3 followed by revision number */ if (DWC3_IP_IS(DWC3)) { diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index a5fc92c4ffa3..45757169b672 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1265,6 +1265,7 @@ struct dwc3 { #define DWC3_IP 0x5533 #define DWC31_IP 0x3331 #define DWC32_IP 0x3332 +#define DWC4_IP 0x3430 u32 revision; diff --git a/drivers/usb/dwc3/dwc3-apple.c b/drivers/usb/dwc3/dwc3-apple.c index cc47cad232e3..40c3ccfddb67 100644 --- a/drivers/usb/dwc3/dwc3-apple.c +++ b/drivers/usb/dwc3/dwc3-apple.c @@ -218,25 +218,31 @@ static int dwc3_apple_core_init(struct dwc3_apple *appledwc) return ret; } -static void dwc3_apple_phy_set_mode(struct dwc3_apple *appledwc, enum phy_mode mode) -{ - lockdep_assert_held(&appledwc->lock); - - /* - * This platform requires SUSPHY to be enabled here already in order to properly configure - * the PHY and switch dwc3's PIPE interface to USB3 PHY. - */ - dwc3_enable_susphy(&appledwc->dwc, true); - phy_set_mode(appledwc->dwc.usb2_generic_phy[0], mode); - phy_set_mode(appledwc->dwc.usb3_generic_phy[0], mode); -} - static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state state) { int ret, ret_reset; lockdep_assert_held(&appledwc->lock); + /* + * The USB2 PHY on this platform must be configured for host or device mode while it is + * still powered off and before dwc3 tries to access it. Otherwise, the new configuration + * will sometimes only take affect after the *next* time dwc3 is brought up which causes + * the connected device to just not work. + * The USB3 PHY must be configured later after dwc3 has already been initialized. + */ + switch (state) { + case DWC3_APPLE_HOST: + phy_set_mode(appledwc->dwc.usb2_generic_phy[0], PHY_MODE_USB_HOST); + break; + case DWC3_APPLE_DEVICE: + phy_set_mode(appledwc->dwc.usb2_generic_phy[0], PHY_MODE_USB_DEVICE); + break; + default: + /* Unreachable unless there's a bug in this driver */ + return -EINVAL; + } + ret = reset_control_deassert(appledwc->reset); if (ret) { dev_err(appledwc->dev, "Failed to deassert reset, err=%d\n", ret); @@ -257,7 +263,13 @@ static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state st case DWC3_APPLE_HOST: appledwc->dwc.dr_mode = USB_DR_MODE_HOST; dwc3_apple_set_ptrcap(appledwc, DWC3_GCTL_PRTCAP_HOST); - dwc3_apple_phy_set_mode(appledwc, PHY_MODE_USB_HOST); + /* + * This platform requires SUSPHY to be enabled here already in order to properly + * configure the PHY and switch dwc3's PIPE interface to USB3 PHY. The USB2 PHY + * has already been configured to the correct mode earlier. + */ + dwc3_enable_susphy(&appledwc->dwc, true); + phy_set_mode(appledwc->dwc.usb3_generic_phy[0], PHY_MODE_USB_HOST); ret = dwc3_host_init(&appledwc->dwc); if (ret) { dev_err(appledwc->dev, "Failed to initialize host, ret=%d\n", ret); @@ -268,7 +280,13 @@ static int dwc3_apple_init(struct dwc3_apple *appledwc, enum dwc3_apple_state st case DWC3_APPLE_DEVICE: appledwc->dwc.dr_mode = USB_DR_MODE_PERIPHERAL; dwc3_apple_set_ptrcap(appledwc, DWC3_GCTL_PRTCAP_DEVICE); - dwc3_apple_phy_set_mode(appledwc, PHY_MODE_USB_DEVICE); + /* + * This platform requires SUSPHY to be enabled here already in order to properly + * configure the PHY and switch dwc3's PIPE interface to USB3 PHY. The USB2 PHY + * has already been configured to the correct mode earlier. + */ + dwc3_enable_susphy(&appledwc->dwc, true); + phy_set_mode(appledwc->dwc.usb3_generic_phy[0], PHY_MODE_USB_DEVICE); ret = dwc3_gadget_init(&appledwc->dwc); if (ret) { dev_err(appledwc->dev, "Failed to initialize gadget, ret=%d\n", ret); @@ -340,6 +358,22 @@ static int dwc3_usb_role_switch_set(struct usb_role_switch *sw, enum usb_role ro guard(mutex)(&appledwc->lock); /* + * Skip role switches if appledwc is already in the desired state. The + * USB-C port controller on M2 and M1/M2 Pro/Max/Ultra devices issues + * additional interrupts which results in usb_role_switch_set_role() + * calls with the current role. + * Ignore those calls here to ensure the USB-C port controller and + * appledwc are in a consistent state. + * This matches the behaviour in __dwc3_set_mode(). + * Do no handle USB_ROLE_NONE for DWC3_APPLE_NO_CABLE and + * DWC3_APPLE_PROBE_PENDING since that is no-op anyway. + */ + if (appledwc->state == DWC3_APPLE_HOST && role == USB_ROLE_HOST) + return 0; + if (appledwc->state == DWC3_APPLE_DEVICE && role == USB_ROLE_DEVICE) + return 0; + + /* * We need to tear all of dwc3 down and re-initialize it every time a cable is * connected or disconnected or when the mode changes. See the documentation for enum * dwc3_apple_state for details. diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index aa6ab666741a..a96476507d2f 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -362,6 +362,10 @@ uvc_function_set_alt(struct usb_function *f, unsigned interface, unsigned alt) return ret; usb_ep_enable(uvc->video.ep); + uvc->video.max_req_size = uvc->video.ep->maxpacket + * max_t(unsigned int, uvc->video.ep->maxburst, 1) + * (uvc->video.ep->mult); + memset(&v4l2_event, 0, sizeof(v4l2_event)); v4l2_event.type = UVC_EVENT_STREAMON; v4l2_event_queue(&uvc->vdev, &v4l2_event); diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h index 9e79cbe50715..676419a04976 100644 --- a/drivers/usb/gadget/function/uvc.h +++ b/drivers/usb/gadget/function/uvc.h @@ -107,7 +107,7 @@ struct uvc_video { unsigned int width; unsigned int height; unsigned int imagesize; - unsigned int interval; + unsigned int interval; /* in 100ns units */ struct mutex mutex; /* protects frame parameters */ unsigned int uvc_num_requests; @@ -117,6 +117,7 @@ struct uvc_video { /* Requests */ bool is_enabled; /* tracks whether video stream is enabled */ unsigned int req_size; + unsigned int max_req_size; struct list_head ureqs; /* all uvc_requests allocated by uvc_video */ /* USB requests that the video pump thread can encode into */ diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c index 9a1bbd79ff5a..586e5524c171 100644 --- a/drivers/usb/gadget/function/uvc_queue.c +++ b/drivers/usb/gadget/function/uvc_queue.c @@ -86,10 +86,17 @@ static int uvc_buffer_prepare(struct vb2_buffer *vb) buf->bytesused = 0; } else { buf->bytesused = vb2_get_plane_payload(vb, 0); - buf->req_payload_size = - DIV_ROUND_UP(buf->bytesused + - (video->reqs_per_frame * UVCG_REQUEST_HEADER_LEN), - video->reqs_per_frame); + + if (video->reqs_per_frame != 0) { + buf->req_payload_size = + DIV_ROUND_UP(buf->bytesused + + (video->reqs_per_frame * UVCG_REQUEST_HEADER_LEN), + video->reqs_per_frame); + if (buf->req_payload_size > video->req_size) + buf->req_payload_size = video->req_size; + } else { + buf->req_payload_size = video->max_req_size; + } } return 0; @@ -175,7 +182,15 @@ int uvcg_alloc_buffers(struct uvc_video_queue *queue, { int ret; +retry: ret = vb2_reqbufs(&queue->queue, rb); + if (ret < 0 && queue->use_sg) { + uvc_trace(UVC_TRACE_IOCTL, + "failed to alloc buffer with sg enabled, try non-sg mode\n"); + queue->use_sg = 0; + queue->queue.mem_ops = &vb2_vmalloc_memops; + goto retry; + } return ret ? ret : rb->count; } diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index fb77b0b21790..f568dee08b3b 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -499,13 +499,11 @@ uvc_video_prep_requests(struct uvc_video *video) { struct uvc_device *uvc = container_of(video, struct uvc_device, video); struct usb_composite_dev *cdev = uvc->func.config->cdev; - unsigned int interval_duration = video->ep->desc->bInterval * 1250; + unsigned int interval_duration; unsigned int max_req_size, req_size, header_size; unsigned int nreq; - max_req_size = video->ep->maxpacket - * max_t(unsigned int, video->ep->maxburst, 1) - * (video->ep->mult); + max_req_size = video->max_req_size; if (!usb_endpoint_xfer_isoc(video->ep->desc)) { video->req_size = max_req_size; @@ -515,8 +513,11 @@ uvc_video_prep_requests(struct uvc_video *video) return; } + interval_duration = 2 << (video->ep->desc->bInterval - 1); if (cdev->gadget->speed < USB_SPEED_HIGH) - interval_duration = video->ep->desc->bInterval * 10000; + interval_duration *= 10000; + else + interval_duration *= 1250; nreq = DIV_ROUND_UP(video->interval, interval_duration); @@ -837,7 +838,6 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) video->interval = 666666; /* Initialize the video buffers queue. */ - uvcg_queue_init(&video->queue, uvc->v4l2_dev.dev->parent, + return uvcg_queue_init(&video->queue, uvc->v4l2_dev.dev->parent, V4L2_BUF_TYPE_VIDEO_OUTPUT, &video->mutex); - return 0; } diff --git a/drivers/usb/host/ohci-platform.c b/drivers/usb/host/ohci-platform.c index 2e4bb5cc2165..c801527d5bd2 100644 --- a/drivers/usb/host/ohci-platform.c +++ b/drivers/usb/host/ohci-platform.c @@ -392,3 +392,4 @@ MODULE_DESCRIPTION(DRIVER_DESC); MODULE_AUTHOR("Hauke Mehrtens"); MODULE_AUTHOR("Alan Stern"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: ehci_platform"); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index 5e02f2ceafb6..f4419d4526c4 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -211,3 +211,4 @@ static struct platform_driver uhci_platform_driver = { .of_match_table = platform_uhci_ids, }, }; +MODULE_SOFTDEP("pre: ehci_platform"); diff --git a/drivers/usb/host/xhci-sideband.c b/drivers/usb/host/xhci-sideband.c index a85f62a73313..2bd77255032b 100644 --- a/drivers/usb/host/xhci-sideband.c +++ b/drivers/usb/host/xhci-sideband.c @@ -210,7 +210,6 @@ xhci_sideband_remove_endpoint(struct xhci_sideband *sb, return -ENODEV; __xhci_sideband_remove_endpoint(sb, ep); - xhci_initialize_ring_info(ep->ring); return 0; } diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 31ccced5125e..8b492871d21d 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1563,7 +1563,7 @@ static int tegra_xusb_setup_wakeup(struct platform_device *pdev, struct tegra_xu for (i = 0; i < tegra->soc->max_num_wakes; i++) { struct irq_data *data; - tegra->wake_irqs[i] = platform_get_irq(pdev, i + WAKE_IRQ_START_INDEX); + tegra->wake_irqs[i] = platform_get_irq_optional(pdev, i + WAKE_IRQ_START_INDEX); if (tegra->wake_irqs[i] < 0) break; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 02c9bfe21ae2..b3ba16b9718c 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2898,16 +2898,25 @@ int xhci_stop_endpoint_sync(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, int gfp_t gfp_flags) { struct xhci_command *command; + struct xhci_ep_ctx *ep_ctx; unsigned long flags; - int ret; + int ret = -ENODEV; command = xhci_alloc_command(xhci, true, gfp_flags); if (!command) return -ENOMEM; spin_lock_irqsave(&xhci->lock, flags); - ret = xhci_queue_stop_endpoint(xhci, command, ep->vdev->slot_id, - ep->ep_index, suspend); + + /* make sure endpoint exists and is running before stopping it */ + if (ep->ring) { + ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); + if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_RUNNING) + ret = xhci_queue_stop_endpoint(xhci, command, + ep->vdev->slot_id, + ep->ep_index, suspend); + } + if (ret < 0) { spin_unlock_irqrestore(&xhci->lock, flags); goto out; diff --git a/drivers/usb/serial/f81232.c b/drivers/usb/serial/f81232.c index 530b77fc2f78..9262a2ac97f5 100644 --- a/drivers/usb/serial/f81232.c +++ b/drivers/usb/serial/f81232.c @@ -70,7 +70,6 @@ MODULE_DEVICE_TABLE(usb, combined_id_table); #define F81232_REGISTER_REQUEST 0xa0 #define F81232_GET_REGISTER 0xc0 #define F81232_SET_REGISTER 0x40 -#define F81534A_ACCESS_REG_RETRY 2 #define SERIAL_BASE_ADDRESS 0x0120 #define RECEIVE_BUFFER_REGISTER (0x00 + SERIAL_BASE_ADDRESS) @@ -824,36 +823,31 @@ static void f81232_lsr_worker(struct work_struct *work) static int f81534a_ctrl_set_register(struct usb_interface *intf, u16 reg, u16 size, void *val) { - struct usb_device *dev = interface_to_usbdev(intf); - int retry = F81534A_ACCESS_REG_RETRY; - int status; - - while (retry--) { - status = usb_control_msg_send(dev, - 0, - F81232_REGISTER_REQUEST, - F81232_SET_REGISTER, - reg, - 0, - val, - size, - USB_CTRL_SET_TIMEOUT, - GFP_KERNEL); - if (status) { - status = usb_translate_errors(status); - if (status == -EIO) - continue; - } - - break; - } - - if (status) { - dev_err(&intf->dev, "failed to set register 0x%x: %d\n", - reg, status); - } + return usb_control_msg_send(interface_to_usbdev(intf), + 0, + F81232_REGISTER_REQUEST, + F81232_SET_REGISTER, + reg, + 0, + val, + size, + USB_CTRL_SET_TIMEOUT, + GFP_KERNEL); +} - return status; +static int f81534a_ctrl_get_register(struct usb_interface *intf, u16 reg, + u16 size, void *val) +{ + return usb_control_msg_recv(interface_to_usbdev(intf), + 0, + F81232_REGISTER_REQUEST, + F81232_GET_REGISTER, + reg, + 0, + val, + size, + USB_CTRL_GET_TIMEOUT, + GFP_KERNEL); } static int f81534a_ctrl_enable_all_ports(struct usb_interface *intf, bool en) @@ -869,6 +863,29 @@ static int f81534a_ctrl_enable_all_ports(struct usb_interface *intf, bool en) * bit 0~11 : Serial port enable bit. */ if (en) { + /* + * The Fintek F81532A/534A/535/536 family relies on the + * F81534A_CTRL_CMD_ENABLE_PORT (116h) register during + * initialization to both determine serial port status and + * control port creation. + * + * If the driver experiences fast load/unload cycles, the + * device state may becomes unstable, resulting in the + * incomplete generation of serial ports. + * + * Performing a dummy read operation on the register prior + * to the initial write command resolves the issue. + * + * This clears the device's stale internal state. Subsequent + * write operations will correctly generate all serial ports. + */ + status = f81534a_ctrl_get_register(intf, + F81534A_CTRL_CMD_ENABLE_PORT, + sizeof(enable), + enable); + if (status) + return status; + enable[0] = 0xff; enable[1] = 0x8f; } diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index fe2f21d85737..acb48b1c83f7 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -848,6 +848,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_DEVEL_BOARD_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_EVAL_BOARD_PID, 1) }, { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, LMI_LM3S_ICDI_BOARD_PID, 1) }, + { USB_DEVICE(FTDI_VID, FTDI_AXE027_PID) }, { USB_DEVICE_INTERFACE_NUMBER(FTDI_VID, FTDI_TURTELIZER_PID, 1) }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 2539b9e2f712..6c76cfebfd0e 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -96,6 +96,8 @@ #define LMI_LM3S_EVAL_BOARD_PID 0xbcd9 #define LMI_LM3S_ICDI_BOARD_PID 0xbcda +#define FTDI_AXE027_PID 0xBD90 /* PICAXE AXE027 USB download cable */ + #define FTDI_TURTELIZER_PID 0xBDC8 /* JTAG/RS-232 adapter by egnite GmbH */ /* OpenDCC (www.opendcc.de) product id */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 4c0e5a3ab557..9f2cc5fb9f45 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1505,6 +1505,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x1250, 0xff, 0x00, 0x00) }, /* Telit LE910Cx (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1252, 0xff) }, /* Telit LE910Cx (MBIM) */ { USB_DEVICE(TELIT_VENDOR_ID, 0x1260), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1261), diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 4ca2746ce16b..be49a976428f 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -7890,7 +7890,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) port->partner_desc.identity = &port->partner_ident; port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode); - if (!port->role_sw) + if (IS_ERR_OR_NULL(port->role_sw)) port->role_sw = usb_role_switch_get(port->dev); if (IS_ERR(port->role_sw)) { err = PTR_ERR(port->role_sw); diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 4438637c8900..6d6fc85835d4 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -115,6 +115,10 @@ config BTRFS_EXPERIMENTAL - extent tree v2 - complex rework of extent tracking - - large folio support + - large folio and block size (> page size) support + + - shutdown ioctl and auto-degradation support + + - asynchronous checksum generation for data writes If unsure, say N. diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index d8ca5b6e88e0..89022e9f393b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1661,7 +1661,7 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); - if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { + if (!btrfs_fs_incompat(info, EXTENT_TREE_V2)) { struct btrfs_root *extent_root = btrfs_extent_root(info, 0); struct btrfs_root *csum_root = btrfs_csum_root(info, 0); @@ -3255,6 +3255,15 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) return 0; } +static bool fs_is_full_ro(const struct btrfs_fs_info *fs_info) +{ + if (!sb_rdonly(fs_info->sb)) + return false; + if (unlikely(fs_info->mount_opt & BTRFS_MOUNT_FULL_RO_MASK)) + return true; + return false; +} + int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices) { u32 sectorsize; @@ -3363,6 +3372,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) WRITE_ONCE(fs_info->fs_error, -EUCLEAN); + /* If the fs has any rescue options, no transaction is allowed. */ + if (fs_is_full_ro(fs_info)) + WRITE_ONCE(fs_info->fs_error, -EROFS); + /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); @@ -3489,6 +3502,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->generation == btrfs_super_uuid_tree_generation(disk_super)) set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); + if (unlikely(btrfs_verify_dev_items(fs_info))) { + ret = -EUCLEAN; + goto fail_block_groups; + } ret = btrfs_verify_dev_extents(fs_info); if (ret) { btrfs_err(fs_info, diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 0f7e1ef27891..8ffbc40ebe45 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -264,6 +264,14 @@ enum { BTRFS_MOUNT_REF_TRACKER = (1ULL << 33), }; +/* These mount options require a full read-only fs, no new transaction is allowed. */ +#define BTRFS_MOUNT_FULL_RO_MASK \ + (BTRFS_MOUNT_NOLOGREPLAY | \ + BTRFS_MOUNT_IGNOREBADROOTS | \ + BTRFS_MOUNT_IGNOREDATACSUMS | \ + BTRFS_MOUNT_IGNOREMETACSUMS | \ + BTRFS_MOUNT_IGNORESUPERFLAGS) + /* * Compat flags that we support. If any incompat flags are set other than the * ones specified below then we will fail to mount diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d2b302ac6af9..a2b5b440637e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4180,6 +4180,15 @@ cache_acl: return 0; out: + /* + * We may have a read locked leaf and iget_failed() triggers inode + * eviction which needs to release the delayed inode and that needs + * to lock the delayed inode's mutex. This can cause a ABBA deadlock + * with a task running delayed items, as that require first locking + * the delayed inode's mutex and then modifying its subvolume btree. + * So release the path before iget_failed(). + */ + btrfs_release_path(path); iget_failed(vfs_inode); return ret; } diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index b5fe95baf92e..58dc3e5057ce 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -705,7 +705,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, struct inode *src = file_inode(file_src); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); int ret; - int wb_ret; u64 len = olen; u64 bs = fs_info->sectorsize; u64 end; @@ -750,25 +749,29 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, btrfs_lock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); btrfs_unlock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); + if (ret < 0) + return ret; /* * We may have copied an inline extent into a page of the destination - * range, so wait for writeback to complete before truncating pages + * range, so wait for writeback to complete before invalidating pages * from the page cache. This is a rare case. */ - wb_ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); - ret = ret ? ret : wb_ret; + ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); + if (ret < 0) + return ret; + /* - * Truncate page cache pages so that future reads will see the cloned - * data immediately and not the previous data. + * Invalidate page cache so that future reads will see the cloned data + * immediately and not the previous data. */ - truncate_inode_pages_range(&inode->i_data, - round_down(destoff, PAGE_SIZE), - round_up(destoff + len, PAGE_SIZE) - 1); + ret = filemap_invalidate_inode(inode, false, destoff, end); + if (ret < 0) + return ret; btrfs_btree_balance_dirty(fs_info); - return ret; + return 0; } static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 2522faa97478..d8127a7120c2 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6383,6 +6383,8 @@ static int range_is_hole_in_parent(struct send_ctx *sctx, extent_end = btrfs_file_extent_end(path); if (extent_end <= start) goto next; + if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) + return 0; if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) { search_start = extent_end; goto next; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 6babbe333741..3f08e450f796 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -306,18 +306,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) 0); if (ret) - return ret; + goto out_free; } ret = btrfs_sysfs_add_space_info_type(space_info); if (ret) - return ret; + goto out_free; list_add(&space_info->list, &info->space_info); if (flags & BTRFS_BLOCK_GROUP_DATA) info->data_sinfo = space_info; return ret; + +out_free: + kfree(space_info); + return ret; } int btrfs_init_space_info(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 1f64c132b387..4b3c2acac51a 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -26,7 +26,6 @@ #include "misc.h" #include "fs.h" #include "accessors.h" -#include "zoned.h" /* * Structure name Path @@ -1189,56 +1188,6 @@ static ssize_t btrfs_commit_stats_store(struct kobject *kobj, } BTRFS_ATTR_RW(, commit_stats, btrfs_commit_stats_show, btrfs_commit_stats_store); -static ssize_t btrfs_zoned_stats_show(struct kobject *kobj, - struct kobj_attribute *a, char *buf) -{ - struct btrfs_fs_info *fs_info = to_fs_info(kobj); - struct btrfs_block_group *bg; - size_t ret = 0; - - - if (!btrfs_is_zoned(fs_info)) - return ret; - - spin_lock(&fs_info->zone_active_bgs_lock); - ret += sysfs_emit_at(buf, ret, "active block-groups: %zu\n", - list_count_nodes(&fs_info->zone_active_bgs)); - spin_unlock(&fs_info->zone_active_bgs_lock); - - mutex_lock(&fs_info->reclaim_bgs_lock); - spin_lock(&fs_info->unused_bgs_lock); - ret += sysfs_emit_at(buf, ret, "\treclaimable: %zu\n", - list_count_nodes(&fs_info->reclaim_bgs)); - ret += sysfs_emit_at(buf, ret, "\tunused: %zu\n", - list_count_nodes(&fs_info->unused_bgs)); - spin_unlock(&fs_info->unused_bgs_lock); - mutex_unlock(&fs_info->reclaim_bgs_lock); - - ret += sysfs_emit_at(buf, ret, "\tneed reclaim: %s\n", - str_true_false(btrfs_zoned_should_reclaim(fs_info))); - - if (fs_info->data_reloc_bg) - ret += sysfs_emit_at(buf, ret, - "data relocation block-group: %llu\n", - fs_info->data_reloc_bg); - if (fs_info->treelog_bg) - ret += sysfs_emit_at(buf, ret, - "tree-log block-group: %llu\n", - fs_info->treelog_bg); - - spin_lock(&fs_info->zone_active_bgs_lock); - ret += sysfs_emit_at(buf, ret, "active zones:\n"); - list_for_each_entry(bg, &fs_info->zone_active_bgs, active_bg_list) { - ret += sysfs_emit_at(buf, ret, - "\tstart: %llu, wp: %llu used: %llu, reserved: %llu, unusable: %llu\n", - bg->start, bg->alloc_offset, bg->used, - bg->reserved, bg->zone_unusable); - } - spin_unlock(&fs_info->zone_active_bgs_lock); - return ret; -} -BTRFS_ATTR(, zoned_stats, btrfs_zoned_stats_show); - static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { @@ -1651,7 +1600,6 @@ static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, bg_reclaim_threshold), BTRFS_ATTR_PTR(, commit_stats), BTRFS_ATTR_PTR(, temp_fsid), - BTRFS_ATTR_PTR(, zoned_stats), #ifdef CONFIG_BTRFS_EXPERIMENTAL BTRFS_ATTR_PTR(, offload_csum), #endif diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 0b9f25dd1a68..aabf825e8d7b 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -1059,6 +1059,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, if (out_stripe_len != BTRFS_STRIPE_LEN) { test_err("calculated stripe length doesn't match"); + ret = -EINVAL; goto out; } @@ -1066,12 +1067,14 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, for (i = 0; i < out_ndaddrs; i++) test_msg("mapped %llu", logical[i]); test_err("unexpected number of mapped addresses: %d", out_ndaddrs); + ret = -EINVAL; goto out; } for (i = 0; i < out_ndaddrs; i++) { if (logical[i] != test->mapped_logical[i]) { test_err("unexpected logical address mapped"); + ret = -EINVAL; goto out; } } diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index e9124605974b..0fcc31beeffe 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -517,11 +517,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID; root->fs_info->fs_root = tmp_root; ret = btrfs_insert_fs_root(root->fs_info, tmp_root); + btrfs_put_root(tmp_root); if (ret) { test_err("couldn't insert fs root %d", ret); goto out; } - btrfs_put_root(tmp_root); tmp_root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(tmp_root)) { @@ -532,11 +532,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID; ret = btrfs_insert_fs_root(root->fs_info, tmp_root); + btrfs_put_root(tmp_root); if (ret) { - test_err("couldn't insert fs root %d", ret); + test_err("couldn't insert subvolume root %d", ret); goto out; } - btrfs_put_root(tmp_root); test_msg("running qgroup tests"); ret = test_no_shared_qgroup(root, sectorsize, nodesize); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2d9d38b82daa..6cffcf0c3e7a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2798,7 +2798,7 @@ static int replay_one_buffer(struct extent_buffer *eb, nritems = btrfs_header_nritems(eb); for (wc->log_slot = 0; wc->log_slot < nritems; wc->log_slot++) { - struct btrfs_inode_item *inode_item; + struct btrfs_inode_item *inode_item = NULL; btrfs_item_key_to_cpu(eb, &wc->log_key, wc->log_slot); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 13c514684cfb..8a08412f3529 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1364,7 +1364,9 @@ struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev, (bytenr + BTRFS_SUPER_INFO_SIZE) >> PAGE_SHIFT); } + filemap_invalidate_lock(mapping); page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); + filemap_invalidate_unlock(mapping); if (IS_ERR(page)) return ERR_CAST(page); @@ -7257,6 +7259,7 @@ static int read_one_dev(struct extent_buffer *leaf, return -EINVAL; } } + set_bit(BTRFS_DEV_STATE_ITEM_FOUND, &device->dev_state); set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { @@ -8083,6 +8086,45 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info) } /* + * Ensure that all devices registered in the fs have their device items in the + * chunk tree. + * + * Return true if unexpected device is found. + * Return false otherwise. + */ +bool btrfs_verify_dev_items(const struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *seed_devs; + struct btrfs_device *dev; + bool ret = false; + + mutex_lock(&uuid_mutex); + list_for_each_entry(dev, &fs_info->fs_devices->devices, dev_list) { + if (!test_bit(BTRFS_DEV_STATE_ITEM_FOUND, &dev->dev_state)) { + btrfs_err(fs_info, + "devid %llu path %s is registered but not found in chunk tree", + dev->devid, btrfs_dev_name(dev)); + ret = true; + } + } + list_for_each_entry(seed_devs, &fs_info->fs_devices->seed_list, seed_list) { + list_for_each_entry(dev, &seed_devs->devices, dev_list) { + if (!test_bit(BTRFS_DEV_STATE_ITEM_FOUND, &dev->dev_state)) { + btrfs_err(fs_info, + "devid %llu path %s is registered but not found in chunk tree", + dev->devid, btrfs_dev_name(dev)); + ret = true; + } + } + } + mutex_unlock(&uuid_mutex); + if (ret) + btrfs_err(fs_info, +"remove the above devices or use 'btrfs device scan --forget <dev>' to unregister them before mount"); + return ret; +} + +/* * Check whether the given block group or device is pinned by any inode being * used as a swapfile. */ diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 34b854c1a303..f20abeb16bce 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -100,6 +100,9 @@ enum btrfs_raid_types { #define BTRFS_DEV_STATE_FLUSH_SENT (4) #define BTRFS_DEV_STATE_NO_READA (5) +/* Set when the device item is found in chunk tree, used to catch unexpected registered device. */ +#define BTRFS_DEV_STATE_ITEM_FOUND (7) + /* Special value encoding failure to write primary super block. */ #define BTRFS_SUPER_PRIMARY_WRITE_ERROR (INT_MAX / 2) @@ -893,6 +896,7 @@ enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); +bool btrfs_verify_dev_items(const struct btrfs_fs_info *fs_info); bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 0550fd30fd10..635fb8a52e0c 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -393,9 +393,11 @@ out: repair_branches: ret2 = 0; + ext4_double_down_write_data_sem(orig_inode, donor_inode); r_len = ext4_swap_extents(handle, donor_inode, orig_inode, mext->donor_lblk, orig_map->m_lblk, *m_len, 0, &ret2); + ext4_double_up_write_data_sem(orig_inode, donor_inode); if (ret2 || r_len != *m_len) { ext4_error_inode_block(orig_inode, (sector_t)(orig_map->m_lblk), EIO, "Unable to copy data block, data will be lost!"); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 2e02efbddaac..4ed8ddf2a60b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1037,6 +1037,7 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, ext4_error_inode(ea_inode, __func__, __LINE__, 0, "EA inode %lu ref wraparound: ref_count=%lld ref_change=%d", ea_inode->i_ino, ref_count, ref_change); + brelse(iloc.bh); ret = -EFSCORRUPTED; goto out; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6800886c4d10..baa2f2141146 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2750,8 +2750,13 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. + * + * If the mapping does not have data integrity semantics, + * there's no need to wait for the writeout to complete, as the + * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || + mapping_no_data_integrity(mapping)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 01bc894e9c2b..3b2a171e652f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3200,8 +3200,10 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) + if (fc->writeback_cache) { mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); + mapping_set_no_data_integrity(&inode->i_data); + } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index ab76120705e2..134d7f760a33 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -417,8 +417,10 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; - if (d->len == 0) - return -ENODEV; + if (d->len == 0) { + error = -ENODEV; + goto out_blkdev_put; + } ops = bdev->bd_disk->fops->pr_ops; if (!ops) { diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2248e3ad089a..8a3857a49d84 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -149,7 +149,7 @@ static int nfs4_do_check_delegation(struct inode *inode, fmode_t type, int nfs4_have_delegation(struct inode *inode, fmode_t type, int flags) { if (S_ISDIR(inode->i_mode) && !directory_delegations) - nfs_inode_evict_delegation(inode); + nfs4_inode_set_return_delegation_on_close(inode); return nfs4_do_check_delegation(inode, type, flags, true); } @@ -581,6 +581,10 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation if (delegation == NULL) return 0; + /* Directory delegations don't require any state recovery */ + if (!S_ISREG(inode->i_mode)) + goto out_return; + if (!issync) mode |= O_NONBLOCK; /* Recall of any remaining application leases */ @@ -604,6 +608,7 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation goto out; } +out_return: err = nfs_do_return_delegation(inode, delegation, issync); out: /* Refcount matched in nfs_start_delegation_return_locked() */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 23a78a742b61..8f9ea79b7882 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1440,7 +1440,8 @@ static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) if (!dir || !nfs_verify_change_attribute(dir, verf)) return; - if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + if (NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0) || + (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0))) nfs_set_verifier_delegated(&verf); dentry->d_time = verf; } @@ -1465,6 +1466,49 @@ void nfs_set_verifier(struct dentry *dentry, unsigned long verf) EXPORT_SYMBOL_GPL(nfs_set_verifier); #if IS_ENABLED(CONFIG_NFS_V4) +static void nfs_clear_verifier_file(struct inode *inode) +{ + struct dentry *alias; + struct inode *dir; + + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + spin_lock(&alias->d_lock); + dir = d_inode_rcu(alias->d_parent); + if (!dir || + !NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0)) + nfs_unset_verifier_delegated(&alias->d_time); + spin_unlock(&alias->d_lock); + } +} + +static void nfs_clear_verifier_directory(struct inode *dir) +{ + struct dentry *this_parent; + struct dentry *dentry; + struct inode *inode; + + if (hlist_empty(&dir->i_dentry)) + return; + this_parent = + hlist_entry(dir->i_dentry.first, struct dentry, d_u.d_alias); + + spin_lock(&this_parent->d_lock); + nfs_unset_verifier_delegated(&this_parent->d_time); + dentry = d_first_child(this_parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) + continue; + inode = d_inode_rcu(dentry); + if (inode && + NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + nfs_unset_verifier_delegated(&dentry->d_time); + spin_unlock(&dentry->d_lock); + } + spin_unlock(&this_parent->d_lock); +} + /** * nfs_clear_verifier_delegated - clear the dir verifier delegation tag * @inode: pointer to inode @@ -1477,16 +1521,13 @@ EXPORT_SYMBOL_GPL(nfs_set_verifier); */ void nfs_clear_verifier_delegated(struct inode *inode) { - struct dentry *alias; - if (!inode) return; spin_lock(&inode->i_lock); - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - spin_lock(&alias->d_lock); - nfs_unset_verifier_delegated(&alias->d_time); - spin_unlock(&alias->d_lock); - } + if (S_ISREG(inode->i_mode)) + nfs_clear_verifier_file(inode); + else if (S_ISDIR(inode->i_mode)) + nfs_clear_verifier_directory(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); @@ -1516,14 +1557,6 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (!nfs_dentry_verify_change(dir, dentry)) return 0; - /* - * If we have a directory delegation then we don't need to revalidate - * the directory. The delegation will either get recalled or we will - * receive a notification when it changes. - */ - if (nfs_have_directory_delegation(dir)) - return 0; - /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { if (rcu_walk) @@ -2217,13 +2250,6 @@ no_open: EXPORT_SYMBOL_GPL(nfs_atomic_open); static int -nfs_lookup_revalidate_delegated_parent(struct inode *dir, struct dentry *dentry, - struct inode *inode) -{ - return nfs_lookup_revalidate_done(dir, dentry, inode, 1); -} - -static int nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { @@ -2247,12 +2273,10 @@ nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, if (inode == NULL) goto full_reval; - if (nfs_verifier_is_delegated(dentry)) + if (nfs_verifier_is_delegated(dentry) || + nfs_have_directory_delegation(inode)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); - if (nfs_have_directory_delegation(dir)) - return nfs_lookup_revalidate_delegated_parent(dir, dentry, inode); - /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto full_reval; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d020aab40c64..d1c138a416cf 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -511,7 +511,8 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || current_is_kswapd() || current_is_kcompactd()) return false; - if (nfs_wb_folio(folio->mapping->host, folio) < 0) + if (nfs_wb_folio_reclaim(folio->mapping->host, folio) < 0 || + folio_test_private(folio)) return false; } return nfs_fscache_release_folio(folio, gfp); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index c55ea8fa3bfa..c2d8a13a9dbd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -103,7 +103,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, sizeof(struct nfs4_ff_ds_version), gfp_flags); if (!ds_versions) - goto out_scratch; + goto out_err_drain_dsaddrs; for (i = 0; i < version_count; i++) { /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 84049f3cd340..de2cce1d08f4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,7 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int error = 0; kuid_t task_uid = current_fsuid(); kuid_t owner_uid = inode->i_uid; @@ -727,6 +727,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; + if (S_ISREG(inode->i_mode)) + nfs_file_block_o_direct(NFS_I(inode)); + + oldsize = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); @@ -774,10 +778,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) { - nfs_file_block_o_direct(NFS_I(inode)); + if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { diff --git a/fs/nfs/io.c b/fs/nfs/io.c index d275b0a250bf..8337f0ae852d 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -84,6 +84,7 @@ nfs_start_io_write(struct inode *inode) nfs_file_block_o_direct(NFS_I(inode)); return err; } +EXPORT_SYMBOL_GPL(nfs_start_io_write); /** * nfs_end_io_write - declare that the buffered write operation is done @@ -97,6 +98,7 @@ nfs_end_io_write(struct inode *inode) { up_write(&inode->i_rwsem); } +EXPORT_SYMBOL_GPL(nfs_end_io_write); /* Call with exclusively locked inode->i_rwsem */ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index a113bfdacfd6..41fbcb3f9167 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -461,6 +461,8 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) v = 0; total = hdr->args.count; base = hdr->args.pgbase; + pagevec += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; while (total && v < hdr->page_array.npages) { len = min_t(size_t, total, PAGE_SIZE - base); bvec_set_page(&iocb->bvec[v], *pagevec, len, base); @@ -618,7 +620,6 @@ static void nfs_local_call_read(struct work_struct *work) struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; - bool force_done = false; ssize_t status; int n_iters; @@ -637,13 +638,13 @@ static void nfs_local_call_read(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial read */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_read_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short reads */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_read_iocb_done(iocb); + break; } } } @@ -821,7 +822,6 @@ static void nfs_local_call_write(struct work_struct *work) container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; unsigned long old_flags = current->flags; - bool force_done = false; ssize_t status; int n_iters; @@ -843,13 +843,13 @@ static void nfs_local_call_write(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial write */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_write_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short writes */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_write_iocb_done(iocb); + break; } } file_end_write(filp); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d537fb0c230e..c08520828708 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,7 +114,6 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; - nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -138,13 +137,17 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); @@ -155,7 +158,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -170,7 +173,9 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) @@ -179,7 +184,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -189,14 +194,17 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) { nfs_truncate_last_folio(inode->i_mapping, oldsize, @@ -205,7 +213,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -416,7 +424,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; - loff_t oldsize_dst = i_size_read(dst_inode); + loff_t oldsize_dst; size_t count = args->count; ssize_t status; @@ -461,6 +469,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); + oldsize_dst = i_size_read(dst_inode); status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ec1ce593dea2..a0885ae55abc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3894,8 +3894,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - calldata->lr.roc = pnfs_roc(state->inode, - &calldata->lr.arg, &calldata->lr.res, msg.rpc_cred); + calldata->lr.roc = pnfs_roc(state->inode, &calldata->lr.arg, + &calldata->lr.res, msg.rpc_cred, wait); if (calldata->lr.roc) { calldata->arg.lr_args = &calldata->lr.arg; calldata->res.lr_res = &calldata->lr.res; @@ -4494,6 +4494,25 @@ static bool should_request_dir_deleg(struct inode *inode) } #endif /* CONFIG_NFS_V4_1 */ +static void nfs4_call_getattr_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_setup_sequence(data->seq_server->nfs_client, data->seq_args, + data->seq_res, task); +} + +static void nfs4_call_getattr_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + + nfs4_sequence_process(task, data->seq_res); +} + +static const struct rpc_call_ops nfs4_call_getattr_ops = { + .rpc_call_prepare = nfs4_call_getattr_prepare, + .rpc_call_done = nfs4_call_getattr_done, +}; + static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode) { @@ -4511,16 +4530,26 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_argp = &args, .rpc_resp = &res, }; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_call_getattr_ops, + .callback_data = &data, + }; struct nfs4_gdd_res gdd_res; - unsigned short task_flags = 0; int status; if (nfs4_has_session(server->nfs_client)) - task_flags = RPC_TASK_MOVEABLE; + task_setup.flags = RPC_TASK_MOVEABLE; /* Is this is an attribute revalidation, subject to softreval? */ if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) - task_flags |= RPC_TASK_TIMEOUT; + task_setup.flags |= RPC_TASK_TIMEOUT; args.get_dir_deleg = should_request_dir_deleg(inode); if (args.get_dir_deleg) @@ -4530,22 +4559,24 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, nfs_fattr_init(fattr); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); - status = nfs4_do_call_sync(server->client, server, &msg, - &args.seq_args, &res.seq_res, task_flags); + status = nfs4_call_sync_custom(&task_setup); + if (args.get_dir_deleg) { switch (status) { case 0: if (gdd_res.status != GDD4_OK) break; - status = nfs_inode_set_delegation( - inode, current_cred(), FMODE_READ, - &gdd_res.deleg, 0, NFS4_OPEN_DELEGATE_READ); + nfs_inode_set_delegation(inode, current_cred(), + FMODE_READ, &gdd_res.deleg, 0, + NFS4_OPEN_DELEGATE_READ); break; case -ENOTSUPP: case -EOPNOTSUPP: server->caps &= ~NFS_CAP_DIR_DELEG; } } + + nfs4_sequence_free_slot(&res.seq_res); return status; } @@ -7005,7 +7036,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->inode = nfs_igrab_and_active(inode); if (data->inode || issync) { data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, - cred); + cred, issync); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 01179f7de322..dba51c622cf3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1445,6 +1445,8 @@ void nfs_inode_find_state_and_recover(struct inode *inode, struct nfs4_state *state; bool found = false; + if (!S_ISREG(inode->i_mode)) + goto out; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; @@ -1466,7 +1468,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode, found = true; } rcu_read_unlock(); - +out: nfs_inode_find_delegation_state_and_recover(inode, stateid); if (found) nfs4_schedule_state_manager(clp); @@ -1478,6 +1480,8 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; + if (!S_ISREG(inode->i_mode)) + return; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { if (ctx->state != state) diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 6ce55e8e6b67..9f9ce4a565ea 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1062,6 +1062,9 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done, DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); +DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio_reclaim); +DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_reclaim_done); + DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b72d7cc36766..cff225721d1c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1533,10 +1533,9 @@ static int pnfs_layout_return_on_reboot(struct pnfs_layout_hdr *lo) PNFS_FL_LAYOUTRETURN_PRIVILEGED); } -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1547,7 +1546,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; - bool skip_read = false; + bool skip_read; if (!nfs_have_layout(ino)) return false; @@ -1560,20 +1559,14 @@ retry: lo = NULL; goto out_noroc; } - pnfs_get_layout_hdr(lo); - if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - rcu_read_unlock(); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, - TASK_UNINTERRUPTIBLE); - pnfs_put_layout_hdr(lo); - goto retry; - } /* no roc if we hold a delegation */ + skip_read = false; if (nfs4_check_delegation(ino, FMODE_READ)) { - if (nfs4_check_delegation(ino, FMODE_WRITE)) + if (nfs4_check_delegation(ino, FMODE_WRITE)) { + lo = NULL; goto out_noroc; + } skip_read = true; } @@ -1582,12 +1575,43 @@ retry: if (state == NULL) continue; /* Don't return layout if there is open file state */ - if (state->state & FMODE_WRITE) + if (state->state & FMODE_WRITE) { + lo = NULL; goto out_noroc; + } if (state->state & FMODE_READ) skip_read = true; } + if (skip_read) { + bool writes = false; + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (lseg->pls_range.iomode != IOMODE_READ) { + writes = true; + break; + } + } + if (!writes) { + lo = NULL; + goto out_noroc; + } + } + + pnfs_get_layout_hdr(lo); + if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { + if (!sync) { + pnfs_set_plh_return_info( + lo, skip_read ? IOMODE_RW : IOMODE_ANY, 0); + goto out_noroc; + } + spin_unlock(&ino->i_lock); + rcu_read_unlock(); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto retry; + } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { if (skip_read && lseg->pls_range.iomode == IOMODE_READ) @@ -1627,7 +1651,7 @@ retry: out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); - pnfs_layoutcommit_inode(ino, true); + pnfs_layoutcommit_inode(ino, sync); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 91ff877185c8..3db8f13d8fe4 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -303,10 +303,9 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq); int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list); -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred); +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync); int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, @@ -773,12 +772,10 @@ pnfs_layoutcommit_outstanding(struct inode *inode) return false; } - -static inline bool -pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +static inline bool pnfs_roc(struct inode *ino, + struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, + const struct cred *cred, bool sync) { return false; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 336c510f3750..bf412455e8ed 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2025,6 +2025,39 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) } /** + * nfs_wb_folio_reclaim - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller + */ +int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio) +{ + loff_t range_start = folio_pos(folio); + size_t len = folio_size(folio); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_start + len - 1, + .for_sync = 1, + }; + int ret; + + if (folio_test_writeback(folio)) + return -EBUSY; + if (folio_clear_dirty_for_io(folio)) { + trace_nfs_writeback_folio_reclaim(inode, range_start, len); + ret = nfs_writepage_locked(folio, &wbc); + trace_nfs_writeback_folio_reclaim_done(inode, range_start, len, + ret); + return ret; + } + nfs_commit_inode(inode, 0); + return 0; +} + +/** * nfs_wb_folio - Write back all requests on one page * @inode: pointer to page * @folio: pointer to folio diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d97295eaebe6..c19d6d713780 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -848,15 +848,16 @@ sparse_alloc: * invalid inode records, such as records that start at agbno 0 * or extend beyond the AG. * - * Set min agbno to the first aligned, non-zero agbno and max to - * the last aligned agbno that is at least one full chunk from - * the end of the AG. + * Set min agbno to the first chunk aligned, non-zero agbno and + * max to one less than the last chunk aligned agbno from the + * end of the AG. We subtract 1 from max so that the cluster + * allocation alignment takes over and allows allocation within + * the last full inode chunk in the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(xfs_ag_block_count(args.mp, pag_agno(pag)), - args.mp->m_sb.sb_inoalignmt) - - igeo->ialloc_blks; + args.mp->m_sb.sb_inoalignmt) - 1; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 9186c58e83d5..be16efaa6925 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -48,6 +48,31 @@ xfs_rtgroup_min_block( return 0; } +/* Compute the number of rt extents in this realtime group. */ +static xfs_rtxnum_t +__xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + ASSERT(rgno < rgcount); + if (rgno == rgcount - 1) + return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); + + ASSERT(xfs_has_rtgroups(mp)); + return mp->m_sb.sb_rgextents; +} + +xfs_rtxnum_t +xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, + mp->m_sb.sb_rextents); +} + /* Precompute this group's geometry */ void xfs_rtgroup_calc_geometry( @@ -58,7 +83,8 @@ xfs_rtgroup_calc_geometry( xfs_rtbxlen_t rextents) { rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents); - rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; + rtg_group(rtg)->xg_block_count = + rtg->rtg_extents * mp->m_sb.sb_rextsize; rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno); } @@ -136,31 +162,6 @@ out_unwind_new_rtgs: return error; } -/* Compute the number of rt extents in this realtime group. */ -xfs_rtxnum_t -__xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, - xfs_rtbxlen_t rextents) -{ - ASSERT(rgno < rgcount); - if (rgno == rgcount - 1) - return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); - - ASSERT(xfs_has_rtgroups(mp)); - return mp->m_sb.sb_rgextents; -} - -xfs_rtxnum_t -xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno) -{ - return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, - mp->m_sb.sb_rextents); -} - /* * Update the rt extent count of the previous tail rtgroup if it changed during * recovery (i.e. recovery of a growfs). diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 03f1e2493334..73cace4d25c7 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -285,8 +285,6 @@ void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents); -xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents); xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno); void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a311385b23d8..d4544ccafea5 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1180,9 +1180,11 @@ xfs_log_cover( int error = 0; bool need_covered; - ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && - !xfs_ail_min_lsn(mp->m_log->l_ailp)) || - xlog_is_shutdown(mp->m_log)); + if (!xlog_is_shutdown(mp->m_log)) { + ASSERT(xlog_cil_empty(mp->m_log)); + ASSERT(xlog_iclogs_empty(mp->m_log)); + ASSERT(!xfs_ail_min_lsn(mp->m_log->l_ailp)); + } if (!xfs_log_writable(mp)) return 0; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index e063f4f2f2e6..a12ffed12391 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -126,7 +126,7 @@ xfs_rtcopy_summary( error = 0; out: xfs_rtbuf_cache_relse(oargs); - return 0; + return error; } /* * Mark an extent specified by start and len allocated. @@ -1265,7 +1265,7 @@ xfs_growfs_check_rtgeom( uint32_t rem; if (rextsize != 1) - return -EINVAL; + goto out_inval; div_u64_rem(nmp->m_sb.sb_rblocks, gblocks, &rem); if (rem) { xfs_warn(mp, @@ -1326,7 +1326,7 @@ xfs_grow_last_rtg( return true; if (mp->m_sb.sb_rgcount == 0) return false; - return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <= + return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) < mp->m_sb.sb_rgextents; } diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1fff717cae51..4d679d2a206b 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -46,7 +46,8 @@ * * The mmu_gather API consists of: * - * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() + * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / + * tlb_finish_mmu() * * start and finish a mmu_gather * @@ -364,6 +365,20 @@ struct mmu_gather { unsigned int vma_huge : 1; unsigned int vma_pfn : 1; + /* + * Did we unshare (unmap) any shared page tables? For now only + * used for hugetlb PMD table sharing. + */ + unsigned int unshared_tables : 1; + + /* + * Did we unshare any page tables such that they are now exclusive + * and could get reused+modified by the new owner? When setting this + * flag, "unshared_tables" will be set as well. For now only used + * for hugetlb PMD table sharing. + */ + unsigned int fully_unshared_tables : 1; + unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER @@ -400,6 +415,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an @@ -484,7 +500,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || - tlb->cleared_puds || tlb->cleared_p4ds)) + tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); @@ -773,6 +789,63 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #endif +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, + unsigned long addr) +{ + /* + * The caller must make sure that concurrent unsharing + exclusive + * reuse is impossible until tlb_flush_unshared_tables() was called. + */ + VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); + ptdesc_pmd_pts_dec(pt); + + /* Clearing a PUD pointing at a PMD table with PMD leaves. */ + tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); + + /* + * If the page table is now exclusively owned, we fully unshared + * a page table. + */ + if (!ptdesc_pmd_is_shared(pt)) + tlb->fully_unshared_tables = true; + tlb->unshared_tables = true; +} + +static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) +{ + /* + * As soon as the caller drops locks to allow for reuse of + * previously-shared tables, these tables could get modified and + * even reused outside of hugetlb context, so we have to make sure that + * any page table walkers (incl. TLB, GUP-fast) are aware of that + * change. + * + * Even if we are not fully unsharing a PMD table, we must + * flush the TLB for the unsharer now. + */ + if (tlb->unshared_tables) + tlb_flush_mmu_tlbonly(tlb); + + /* + * Similarly, we must make sure that concurrent GUP-fast will not + * walk previously-shared page tables that are getting modified+reused + * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. + * + * We only perform this when we are the last sharer of a page table, + * as the IPI will reach all CPUs: any GUP-fast. + * + * Note that on configs where tlb_remove_table_sync_one() is a NOP, + * the expectation is that the tlb_flush_mmu_tlbonly() would have issued + * required IPIs already for us. + */ + if (tlb->fully_unshared_tables) { + tlb_remove_table_sync_one(); + tlb->fully_unshared_tables = false; + } +} +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/drm/bridge/dw_hdmi_qp.h b/include/drm/bridge/dw_hdmi_qp.h index 3f461f6b9bbf..3af12f82da2c 100644 --- a/include/drm/bridge/dw_hdmi_qp.h +++ b/include/drm/bridge/dw_hdmi_qp.h @@ -34,5 +34,6 @@ struct dw_hdmi_qp_plat_data { struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, struct drm_encoder *encoder, const struct dw_hdmi_qp_plat_data *plat_data); +void dw_hdmi_qp_suspend(struct device *dev, struct dw_hdmi_qp *hdmi); void dw_hdmi_qp_resume(struct device *dev, struct dw_hdmi_qp *hdmi); #endif /* __DW_HDMI_QP__ */ diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index df2f24b950e4..14d2859f0bda 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -552,6 +552,22 @@ ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size); /** + * drm_dp_dpcd_readb() - read a single byte from the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to read + * @valuep: location where the value of the register will be stored + * + * Returns the number of bytes transferred (1) on success, or a negative + * error code on failure. In most of the cases you should be using + * drm_dp_dpcd_read_byte() instead. + */ +static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, + unsigned int offset, u8 *valuep) +{ + return drm_dp_dpcd_read(aux, offset, valuep, 1); +} + +/** * drm_dp_dpcd_read_data() - read a series of bytes from the DPCD * @aux: DisplayPort AUX channel (SST or MST) * @offset: address of the (first) register to read @@ -570,12 +586,29 @@ static inline int drm_dp_dpcd_read_data(struct drm_dp_aux *aux, void *buffer, size_t size) { int ret; + size_t i; + u8 *buf = buffer; ret = drm_dp_dpcd_read(aux, offset, buffer, size); - if (ret < 0) - return ret; - if (ret < size) - return -EPROTO; + if (ret >= 0) { + if (ret < size) + return -EPROTO; + return 0; + } + + /* + * Workaround for USB-C hubs/adapters with buggy firmware that fail + * multi-byte AUX reads but work with single-byte reads. + * Known affected devices: + * - Lenovo USB-C to VGA adapter (VIA VL817, idVendor=17ef, idProduct=7217) + * - Dell DA310 USB-C hub (idVendor=413c, idProduct=c010) + * Attempt byte-by-byte reading as a fallback. + */ + for (i = 0; i < size; i++) { + ret = drm_dp_dpcd_readb(aux, offset + i, &buf[i]); + if (ret < 0) + return ret; + } return 0; } @@ -610,22 +643,6 @@ static inline int drm_dp_dpcd_write_data(struct drm_dp_aux *aux, } /** - * drm_dp_dpcd_readb() - read a single byte from the DPCD - * @aux: DisplayPort AUX channel - * @offset: address of the register to read - * @valuep: location where the value of the register will be stored - * - * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. In most of the cases you should be using - * drm_dp_dpcd_read_byte() instead. - */ -static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, - unsigned int offset, u8 *valuep) -{ - return drm_dp_dpcd_read(aux, offset, valuep, 1); -} - -/** * drm_dp_dpcd_writeb() - write a single byte to the DPCD * @aux: DisplayPort AUX channel * @offset: address of the register to write diff --git a/include/dt-bindings/power/qcom,rpmhpd.h b/include/dt-bindings/power/qcom,rpmhpd.h index 50e7c886709d..06851363ae0e 100644 --- a/include/dt-bindings/power/qcom,rpmhpd.h +++ b/include/dt-bindings/power/qcom,rpmhpd.h @@ -264,5 +264,6 @@ #define SC8280XP_NSP 13 #define SC8280XP_QPHY 14 #define SC8280XP_XO 15 +#define SC8280XP_MXC_AO 16 #endif diff --git a/include/hyperv/hvhdk.h b/include/hyperv/hvhdk.h index 469186df7826..08965970c17d 100644 --- a/include/hyperv/hvhdk.h +++ b/include/hyperv/hvhdk.h @@ -800,6 +800,53 @@ struct hv_x64_memory_intercept_message { u8 instruction_bytes[16]; } __packed; +#if IS_ENABLED(CONFIG_ARM64) +union hv_arm64_vp_execution_state { + u16 as_uint16; + struct { + u16 cpl:2; /* Exception Level (EL) */ + u16 debug_active:1; + u16 interruption_pending:1; + u16 vtl:4; + u16 virtualization_fault_active:1; + u16 reserved:7; + } __packed; +}; + +struct hv_arm64_intercept_message_header { + u32 vp_index; + u8 instruction_length; + u8 intercept_access_type; + union hv_arm64_vp_execution_state execution_state; + u64 pc; + u64 cpsr; +} __packed; + +union hv_arm64_memory_access_info { + u8 as_uint8; + struct { + u8 gva_valid:1; + u8 gva_gpa_valid:1; + u8 hypercall_output_pending:1; + u8 reserved:5; + } __packed; +}; + +struct hv_arm64_memory_intercept_message { + struct hv_arm64_intercept_message_header header; + u32 cache_type; /* enum hv_cache_type */ + u8 instruction_byte_count; + union hv_arm64_memory_access_info memory_access_info; + u16 reserved1; + u8 instruction_bytes[4]; + u32 reserved2; + u64 guest_virtual_address; + u64 guest_physical_address; + u64 syndrome; +} __packed; + +#endif /* CONFIG_ARM64 */ + /* * Dispatch state for the VP communicated by the hypervisor to the * VP-dispatching thread in the root on return from HVCALL_DISPATCH_VP. diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 43aa6153dc57..e7497f804644 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -18,7 +18,7 @@ * @power: The power consumed at this level (by 1 CPU or by a registered * device). It can be a total power: static and dynamic. * @cost: The cost coefficient associated with this level, used during - * energy calculation. Equal to: power * max_frequency / frequency + * energy calculation. Equal to: 10 * power * max_frequency / frequency * @flags: see "em_perf_state flags" description below. */ struct em_perf_state { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 019a1c5281e4..e51b8ef0cebd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -240,8 +240,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); @@ -300,13 +301,17 @@ static inline struct address_space *hugetlb_folio_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline int huge_pmd_unshare(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } +static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, + struct vm_area_struct *vma) +{ +} + static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) @@ -1326,7 +1331,7 @@ static inline __init void hugetlb_cma_reserve(int order) #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { - return page_count(virt_to_page(pte)) > 1; + return ptdesc_pmd_is_shared(virt_to_ptdesc(pte)); } #else static inline bool hugetlb_pmd_shared(pte_t *pte) diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 0ad1ddbb8b99..e5822f6e7f27 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -211,6 +211,7 @@ struct kmem_obj_info; * __kfence_obj_info() - fill kmem_obj_info struct * @kpp: kmem_obj_info to be filled * @object: the object + * @slab: the slab * * Return: * * false - not a KFENCE object diff --git a/include/linux/mm.h b/include/linux/mm.h index 6f959d8ca4b4..f0d5be9dc736 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -608,7 +608,11 @@ enum { /* * Flags which should result in page tables being copied on fork. These are * flags which indicate that the VMA maps page tables which cannot be - * reconsistuted upon page fault, so necessitate page table copying upon + * reconsistuted upon page fault, so necessitate page table copying upon fork. + * + * Note that these flags should be compared with the DESTINATION VMA not the + * source, as VM_UFFD_WP may not be propagated to destination, while all other + * flags will be. * * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be * reasonably reconstructed on page fault. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 42af2292951d..78950eb8926d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1329,7 +1329,7 @@ struct mm_struct { * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ - unsigned long cpu_bitmap[]; + char flexible_array[] __aligned(__alignof__(unsigned long)); }; /* Copy value to the first system word of mm flags, non-atomically. */ @@ -1366,19 +1366,24 @@ static inline void __mm_flags_set_mask_bits_word(struct mm_struct *mm, MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; +#define MM_STRUCT_FLEXIBLE_ARRAY_INIT \ +{ \ + [0 ... sizeof(cpumask_t) + MM_CID_STATIC_SIZE - 1] = 0 \ +} + /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; - cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); + cpu_bitmap += offsetof(struct mm_struct, flexible_array); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { - return (struct cpumask *)&mm->cpu_bitmap; + return (struct cpumask *)&mm->flexible_array; } #ifdef CONFIG_LRU_GEN @@ -1469,7 +1474,7 @@ static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) { unsigned long bitmap = (unsigned long)mm; - bitmap += offsetof(struct mm_struct, cpu_bitmap); + bitmap += offsetof(struct mm_struct, flexible_array); /* Skip cpu_bitmap */ bitmap += cpumask_size(); return (struct cpumask *)bitmap; @@ -1495,7 +1500,7 @@ static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct * mm_init_cid(mm, p); return 0; } -#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) +# define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { @@ -1509,6 +1514,8 @@ static inline unsigned int mm_cid_size(void) return cpumask_size() + bitmap_size(num_possible_cpus()); } +/* Use 2 * NR_CPUS as worse case for static allocation. */ +# define MM_CID_STATIC_SIZE (2 * sizeof(cpumask_t)) #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } @@ -1517,11 +1524,13 @@ static inline unsigned int mm_cid_size(void) { return 0; } +# define MM_CID_STATIC_SIZE 0 #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 75ef7c9f9307..fc5d6c88d2f0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1648,14 +1648,15 @@ static inline int is_highmem(const struct zone *zone) return is_highmem_idx(zone_idx(zone)); } -#ifdef CONFIG_ZONE_DMA -bool has_managed_dma(void); -#else +bool has_managed_zone(enum zone_type zone); static inline bool has_managed_dma(void) { +#ifdef CONFIG_ZONE_DMA + return has_managed_zone(ZONE_DMA); +#else return false; -} #endif +} #ifndef CONFIG_NUMA diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a6624edb7226..8dd79a3f3d66 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -637,6 +637,7 @@ extern int nfs_update_folio(struct file *file, struct folio *folio, extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); +extern int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index cf3c6ab408aa..207156f2143c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -83,6 +83,7 @@ static inline void reset_hung_task_detector(void) { } #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); extern unsigned int hardlockup_panic; +extern unsigned long hardlockup_si_mask; #else static inline void hardlockup_detector_disable(void) {} #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 31a848485ad9..ec442af3f886 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,6 +210,7 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ + AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -345,6 +346,16 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } +static inline void mapping_set_no_data_integrity(struct address_space *mapping) +{ + set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); +} + +static inline bool mapping_no_data_integrity(const struct address_space *mapping) +{ + return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; diff --git a/include/linux/pci.h b/include/linux/pci.h index 864775651c6f..b5cc0c2b9906 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2210,6 +2210,10 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { return -ENOSPC; } + +static inline void pci_free_irq_vectors(struct pci_dev *dev) +{ +} #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ diff --git a/include/linux/sched.h b/include/linux/sched.h index d395f2810fac..da0133524d08 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1874,7 +1874,6 @@ static inline int task_nice(const struct task_struct *p) extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0e1d73955fa5..95d0040df584 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -325,6 +325,7 @@ static inline void might_alloc(gfp_t gfp_mask) /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value + * @flags: Flags to add. * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 6673e4d4ac2e..4933777404d6 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -35,6 +35,7 @@ struct ts_state * @get_pattern: return head of pattern * @get_pattern_len: return length of pattern * @owner: module reference to algorithm + * @list: list to search */ struct ts_ops { diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 59409c1fc3de..2f7bd2fdc616 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -75,4 +75,7 @@ /* short SET_ADDRESS request timeout */ #define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT BIT(16) +/* skip BOS descriptor request */ +#define USB_QUIRK_NO_BOS BIT(17) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cbccedf32228..6c11aa0e103b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3221,8 +3221,6 @@ struct cfg80211_auth_request { * if this is %NULL for a link, that link is not requested * @elems: extra elements for the per-STA profile for this link * @elems_len: length of the elements - * @disabled: If set this link should be included during association etc. but it - * should not be used until enabled by the AP MLD. * @error: per-link error code, must be <= 0. If there is an error, then the * operation as a whole must fail. */ @@ -3230,7 +3228,6 @@ struct cfg80211_assoc_link { struct cfg80211_bss *bss; const u8 *elems; size_t elems_len; - bool disabled; int error; }; diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 58fd6e84f961..a7860c047503 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1402,7 +1402,7 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index de6f6d25767c..869f97c9bf73 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,6 +322,7 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_recvmsg_peek_nowait, "PUT peek-nwt") \ EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ @@ -340,6 +341,9 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_notify_released, "SEE nfy-rlsd") \ EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_call_see_recvmsg_requeue, "SEE recv-rqu") \ + EM(rxrpc_call_see_recvmsg_requeue_first, "SEE recv-rqF") \ + EM(rxrpc_call_see_recvmsg_requeue_move, "SEE recv-rqM") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/include/uapi/linux/dev_energymodel.h b/include/uapi/linux/dev_energymodel.h new file mode 100644 index 000000000000..355d8885c9a0 --- /dev/null +++ b/include/uapi/linux/dev_energymodel.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_DEV_ENERGYMODEL_H +#define _UAPI_LINUX_DEV_ENERGYMODEL_H + +#define DEV_ENERGYMODEL_FAMILY_NAME "dev-energymodel" +#define DEV_ENERGYMODEL_FAMILY_VERSION 1 + +/** + * enum dev_energymodel_perf_state_flags + * @DEV_ENERGYMODEL_PERF_STATE_FLAGS_PERF_STATE_INEFFICIENT: The performance + * state is inefficient. There is in this perf-domain, another performance + * state with a higher frequency but a lower or equal power cost. + */ +enum dev_energymodel_perf_state_flags { + DEV_ENERGYMODEL_PERF_STATE_FLAGS_PERF_STATE_INEFFICIENT = 1, +}; + +/** + * enum dev_energymodel_perf_domain_flags + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_MICROWATTS: The power values + * are in micro-Watts or some other scale. + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip + * inefficient states when estimating energy consumption. + * @DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL: The power values + * are artificial and might be created by platform missing real power + * information. + */ +enum dev_energymodel_perf_domain_flags { + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_MICROWATTS = 1, + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_SKIP_INEFFICIENCIES = 2, + DEV_ENERGYMODEL_PERF_DOMAIN_FLAGS_PERF_DOMAIN_ARTIFICIAL = 4, +}; + +enum { + DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD = 1, + DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS, + DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS, + + __DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX, + DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX = (__DEV_ENERGYMODEL_A_PERF_DOMAIN_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID = 1, + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE, + + __DEV_ENERGYMODEL_A_PERF_TABLE_MAX, + DEV_ENERGYMODEL_A_PERF_TABLE_MAX = (__DEV_ENERGYMODEL_A_PERF_TABLE_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_A_PERF_STATE_PAD = 1, + DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE, + DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY, + DEV_ENERGYMODEL_A_PERF_STATE_POWER, + DEV_ENERGYMODEL_A_PERF_STATE_COST, + DEV_ENERGYMODEL_A_PERF_STATE_FLAGS, + + __DEV_ENERGYMODEL_A_PERF_STATE_MAX, + DEV_ENERGYMODEL_A_PERF_STATE_MAX = (__DEV_ENERGYMODEL_A_PERF_STATE_MAX - 1) +}; + +enum { + DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS = 1, + DEV_ENERGYMODEL_CMD_GET_PERF_TABLE, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_CREATED, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_UPDATED, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_DELETED, + + __DEV_ENERGYMODEL_CMD_MAX, + DEV_ENERGYMODEL_CMD_MAX = (__DEV_ENERGYMODEL_CMD_MAX - 1) +}; + +#define DEV_ENERGYMODEL_MCGRP_EVENT "event" + +#endif /* _UAPI_LINUX_DEV_ENERGYMODEL_H */ diff --git a/include/uapi/linux/energy_model.h b/include/uapi/linux/energy_model.h deleted file mode 100644 index 0bcad967854f..000000000000 --- a/include/uapi/linux/energy_model.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ -/* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ -/* YNL-GEN uapi header */ -/* To regenerate run: tools/net/ynl/ynl-regen.sh */ - -#ifndef _UAPI_LINUX_ENERGY_MODEL_H -#define _UAPI_LINUX_ENERGY_MODEL_H - -#define EM_FAMILY_NAME "em" -#define EM_FAMILY_VERSION 1 - -enum { - EM_A_PDS_PD = 1, - - __EM_A_PDS_MAX, - EM_A_PDS_MAX = (__EM_A_PDS_MAX - 1) -}; - -enum { - EM_A_PD_PAD = 1, - EM_A_PD_PD_ID, - EM_A_PD_FLAGS, - EM_A_PD_CPUS, - - __EM_A_PD_MAX, - EM_A_PD_MAX = (__EM_A_PD_MAX - 1) -}; - -enum { - EM_A_PD_TABLE_PD_ID = 1, - EM_A_PD_TABLE_PS, - - __EM_A_PD_TABLE_MAX, - EM_A_PD_TABLE_MAX = (__EM_A_PD_TABLE_MAX - 1) -}; - -enum { - EM_A_PS_PAD = 1, - EM_A_PS_PERFORMANCE, - EM_A_PS_FREQUENCY, - EM_A_PS_POWER, - EM_A_PS_COST, - EM_A_PS_FLAGS, - - __EM_A_PS_MAX, - EM_A_PS_MAX = (__EM_A_PS_MAX - 1) -}; - -enum { - EM_CMD_GET_PDS = 1, - EM_CMD_GET_PD_TABLE, - EM_CMD_PD_CREATED, - EM_CMD_PD_UPDATED, - EM_CMD_PD_DELETED, - - __EM_CMD_MAX, - EM_CMD_MAX = (__EM_CMD_MAX - 1) -}; - -#define EM_MCGRP_EVENT "event" - -#endif /* _UAPI_LINUX_ENERGY_MODEL_H */ diff --git a/include/uapi/linux/ext4.h b/include/uapi/linux/ext4.h index 411dcc1e4a35..9c683991c32f 100644 --- a/include/uapi/linux/ext4.h +++ b/include/uapi/linux/ext4.h @@ -139,7 +139,7 @@ struct ext4_tune_sb_params { __u32 clear_feature_incompat_mask; __u32 clear_feature_ro_compat_mask; __u8 mount_opts[64]; - __u8 pad[64]; + __u8 pad[68]; }; #define EXT4_TUNE_FL_ERRORS_BEHAVIOR 0x00000001 diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index f030adc462ee..75fd7f5e6cc3 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -216,6 +216,23 @@ struct landlock_net_port_attr { * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with * ``O_TRUNC``. This access right is available since the third version of the * Landlock ABI. + * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened + * character or block device. + * + * This access right applies to all `ioctl(2)` commands implemented by device + * drivers. However, the following common IOCTL commands continue to be + * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: + * + * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), + * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), + * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, + * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) + * * Some IOCTL commands which do not make sense when used with devices, but + * whose implementations are safe and return the right error codes + * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) + * + * This access right is available since the fifth version of the Landlock + * ABI. * * Whether an opened file can be truncated with :manpage:`ftruncate(2)` or used * with `ioctl(2)` is determined during :manpage:`open(2)`, in the same way as @@ -275,26 +292,6 @@ struct landlock_net_port_attr { * If multiple requirements are not met, the ``EACCES`` error code takes * precedence over ``EXDEV``. * - * The following access right applies both to files and directories: - * - * - %LANDLOCK_ACCESS_FS_IOCTL_DEV: Invoke :manpage:`ioctl(2)` commands on an opened - * character or block device. - * - * This access right applies to all `ioctl(2)` commands implemented by device - * drivers. However, the following common IOCTL commands continue to be - * invokable independent of the %LANDLOCK_ACCESS_FS_IOCTL_DEV right: - * - * * IOCTL commands targeting file descriptors (``FIOCLEX``, ``FIONCLEX``), - * * IOCTL commands targeting file descriptions (``FIONBIO``, ``FIOASYNC``), - * * IOCTL commands targeting file systems (``FIFREEZE``, ``FITHAW``, - * ``FIGETBSZ``, ``FS_IOC_GETFSUUID``, ``FS_IOC_GETFSSYSFSPATH``) - * * Some IOCTL commands which do not make sense when used with devices, but - * whose implementations are safe and return the right error codes - * (``FS_IOC_FIEMAP``, ``FICLONE``, ``FICLONERANGE``, ``FIDEDUPERANGE``) - * - * This access right is available since the fifth version of the Landlock - * ABI. - * * .. warning:: * * It is currently not possible to restrict some file-related actions diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 964e1c779cdd..7c12badf85dc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2880,8 +2880,9 @@ enum nl80211_commands { * index. If the userspace includes more RNR elements than number of * MBSSID elements then these will be added in every EMA beacon. * - * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is - * disabled. + * @NL80211_ATTR_MLO_LINK_DISABLED: Unused. It was used to indicate that a link + * is disabled during association. However, the AP will send the + * information by including a TTLM in the association response. * * @NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA: Include BSS usage data, i.e. * include BSSes that can only be used in restricted scenarios and/or diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 87a87396e940..b7a077c11c21 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3003,12 +3003,12 @@ static __cold void io_ring_exit_work(struct work_struct *work) mutex_unlock(&ctx->uring_lock); } - if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) - io_move_task_work_from_local(ctx); - /* The SQPOLL thread never reaches this path */ - while (io_uring_try_cancel_requests(ctx, NULL, true, false)) + do { + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + io_move_task_work_from_local(ctx); cond_resched(); + } while (io_uring_try_cancel_requests(ctx, NULL, true, false)); if (ctx->sq_data) { struct io_sq_data *sqd = ctx->sq_data; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 554a02ee298b..5f0d33b04910 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic process-grouping system. * @@ -20,10 +21,6 @@ * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 3e8cc34d8d50..c06e2e96f79d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kernel/cpuset.c * @@ -16,10 +17,6 @@ * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. */ #include "cpuset-internal.h" diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 915b02f65980..817c33450fee 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -1,17 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * cgroup_freezer.c - control group freezer subsystem * * Copyright IBM Corporation, 2007 * * Author : Cedric Le Goater <clg@fr.ibm.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of version 2.1 of the GNU Lesser General Public License - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. */ #include <linux/export.h> diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 26392badc36b..c5da29ad010c 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -184,6 +184,12 @@ static __init struct gen_pool *__dma_atomic_pool_init(size_t pool_size, return pool; } +#ifdef CONFIG_ZONE_DMA32 +#define has_managed_dma32 has_managed_zone(ZONE_DMA32) +#else +#define has_managed_dma32 false +#endif + static int __init dma_atomic_pool_init(void) { int ret = 0; @@ -199,17 +205,20 @@ static int __init dma_atomic_pool_init(void) } INIT_WORK(&atomic_pool_work, atomic_pool_work_fn); - atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size, + /* All memory might be in the DMA zone(s) to begin with */ + if (has_managed_zone(ZONE_NORMAL)) { + atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL); - if (!atomic_pool_kernel) - ret = -ENOMEM; + if (!atomic_pool_kernel) + ret = -ENOMEM; + } if (has_managed_dma()) { atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL | GFP_DMA); if (!atomic_pool_dma) ret = -ENOMEM; } - if (IS_ENABLED(CONFIG_ZONE_DMA32)) { + if (has_managed_dma32) { atomic_pool_dma32 = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL | GFP_DMA32); if (!atomic_pool_dma32) @@ -224,11 +233,11 @@ postcore_initcall(dma_atomic_pool_init); static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) { if (prev == NULL) { - if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) - return atomic_pool_dma32; - if (atomic_pool_dma && (gfp & GFP_DMA)) - return atomic_pool_dma; - return atomic_pool_kernel; + if (gfp & GFP_DMA) + return atomic_pool_dma ?: atomic_pool_dma32 ?: atomic_pool_kernel; + if (gfp & GFP_DMA32) + return atomic_pool_dma32 ?: atomic_pool_dma ?: atomic_pool_kernel; + return atomic_pool_kernel ?: atomic_pool_dma32 ?: atomic_pool_dma; } if (prev == atomic_pool_kernel) return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 9dc51fab604f..d4482b6e3cae 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -460,27 +460,23 @@ static void __init deserialize_bitmap(unsigned int order, } } -/* Return true if memory was deserizlied */ -static bool __init kho_mem_deserialize(const void *fdt) +/* Returns physical address of the preserved memory map from FDT */ +static phys_addr_t __init kho_get_mem_map_phys(const void *fdt) { - struct khoser_mem_chunk *chunk; const void *mem_ptr; - u64 mem; int len; mem_ptr = fdt_getprop(fdt, 0, PROP_PRESERVED_MEMORY_MAP, &len); if (!mem_ptr || len != sizeof(u64)) { pr_err("failed to get preserved memory bitmaps\n"); - return false; + return 0; } - mem = get_unaligned((const u64 *)mem_ptr); - chunk = mem ? phys_to_virt(mem) : NULL; - - /* No preserved physical pages were passed, no deserialization */ - if (!chunk) - return false; + return get_unaligned((const u64 *)mem_ptr); +} +static void __init kho_mem_deserialize(struct khoser_mem_chunk *chunk) +{ while (chunk) { unsigned int i; @@ -489,8 +485,6 @@ static bool __init kho_mem_deserialize(const void *fdt) &chunk->bitmaps[i]); chunk = KHOSER_LOAD_PTR(chunk->hdr.next); } - - return true; } /* @@ -1253,6 +1247,7 @@ bool kho_finalized(void) struct kho_in { phys_addr_t fdt_phys; phys_addr_t scratch_phys; + phys_addr_t mem_map_phys; struct kho_debugfs dbg; }; @@ -1434,12 +1429,10 @@ static void __init kho_release_scratch(void) void __init kho_memory_init(void) { - if (kho_in.scratch_phys) { + if (kho_in.mem_map_phys) { kho_scratch = phys_to_virt(kho_in.scratch_phys); kho_release_scratch(); - - if (!kho_mem_deserialize(kho_get_fdt())) - kho_in.fdt_phys = 0; + kho_mem_deserialize(phys_to_virt(kho_in.mem_map_phys)); } else { kho_reserve_scratch(); } @@ -1448,8 +1441,9 @@ void __init kho_memory_init(void) void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys, u64 scratch_len) { - void *fdt = NULL; struct kho_scratch *scratch = NULL; + phys_addr_t mem_map_phys; + void *fdt = NULL; int err = 0; unsigned int scratch_cnt = scratch_len / sizeof(*kho_scratch); @@ -1475,6 +1469,12 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, goto out; } + mem_map_phys = kho_get_mem_map_phys(fdt); + if (!mem_map_phys) { + err = -ENOENT; + goto out; + } + scratch = early_memremap(scratch_phys, scratch_len); if (!scratch) { pr_warn("setup: failed to memremap scratch (phys=0x%llx, len=%lld)\n", @@ -1515,6 +1515,7 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, kho_in.fdt_phys = fdt_phys; kho_in.scratch_phys = scratch_phys; + kho_in.mem_map_phys = mem_map_phys; kho_scratch_cnt = scratch_cnt; pr_info("found kexec handover data.\n"); diff --git a/kernel/module/kmod.c b/kernel/module/kmod.c index 25f253812512..a25dccdf7aa7 100644 --- a/kernel/module/kmod.c +++ b/kernel/module/kmod.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kmod - the kernel module loader * diff --git a/kernel/panic.c b/kernel/panic.c index 0d52210a9e2b..0c20fcaae98a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -131,7 +131,8 @@ static int proc_taint(const struct ctl_table *table, int write, static int sysctl_panic_print_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - panic_print_deprecated(); + if (write) + panic_print_deprecated(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } @@ -1014,7 +1015,6 @@ static int panic_print_set(const char *val, const struct kernel_param *kp) static int panic_print_get(char *val, const struct kernel_param *kp) { - panic_print_deprecated(); return param_get_ulong(val, kp); } diff --git a/kernel/power/em_netlink.c b/kernel/power/em_netlink.c index 4b85da138a06..5a611d3950fd 100644 --- a/kernel/power/em_netlink.c +++ b/kernel/power/em_netlink.c @@ -12,27 +12,35 @@ #include <linux/energy_model.h> #include <net/sock.h> #include <net/genetlink.h> -#include <uapi/linux/energy_model.h> +#include <uapi/linux/dev_energymodel.h> #include "em_netlink.h" #include "em_netlink_autogen.h" -#define EM_A_PD_CPUS_LEN 256 - /*************************** Command encoding ********************************/ +struct dump_ctx { + int idx; + int start; + struct sk_buff *skb; + struct netlink_callback *cb; +}; + static int __em_nl_get_pd_size(struct em_perf_domain *pd, void *data) { - char cpus_buf[EM_A_PD_CPUS_LEN]; + int nr_cpus, msg_sz, cpus_sz; int *tot_msg_sz = data; - int msg_sz, cpus_sz; - cpus_sz = snprintf(cpus_buf, sizeof(cpus_buf), "%*pb", - cpumask_pr_args(to_cpumask(pd->cpus))); + nr_cpus = cpumask_weight(to_cpumask(pd->cpus)); + cpus_sz = nla_total_size_64bit(sizeof(u64)) * nr_cpus; - msg_sz = nla_total_size(0) + /* EM_A_PDS_PD */ - nla_total_size(sizeof(u32)) + /* EM_A_PD_PD_ID */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PD_FLAGS */ - nla_total_size(cpus_sz); /* EM_A_PD_CPUS */ + msg_sz = nla_total_size(0) + + /* DEV_ENERGYMODEL_A_PERF_DOMAINS_PERF_DOMAIN */ + nla_total_size(sizeof(u32)) + + /* DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS */ + nla_total_size(cpus_sz); + /* DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS */ *tot_msg_sz += nlmsg_total_size(genlmsg_msg_size(msg_sz)); return 0; @@ -40,56 +48,80 @@ static int __em_nl_get_pd_size(struct em_perf_domain *pd, void *data) static int __em_nl_get_pd(struct em_perf_domain *pd, void *data) { - char cpus_buf[EM_A_PD_CPUS_LEN]; struct sk_buff *msg = data; - struct nlattr *entry; - - entry = nla_nest_start(msg, EM_A_PDS_PD); - if (!entry) - goto out_cancel_nest; + struct cpumask *cpumask; + int cpu; - if (nla_put_u32(msg, EM_A_PD_PD_ID, pd->id)) + if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + pd->id)) goto out_cancel_nest; - if (nla_put_u64_64bit(msg, EM_A_PD_FLAGS, pd->flags, EM_A_PD_PAD)) + if (nla_put_u64_64bit(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS, + pd->flags, DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD)) goto out_cancel_nest; - snprintf(cpus_buf, sizeof(cpus_buf), "%*pb", - cpumask_pr_args(to_cpumask(pd->cpus))); - if (nla_put_string(msg, EM_A_PD_CPUS, cpus_buf)) - goto out_cancel_nest; - - nla_nest_end(msg, entry); + cpumask = to_cpumask(pd->cpus); + for_each_cpu(cpu, cpumask) { + if (nla_put_u64_64bit(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS, + cpu, DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD)) + goto out_cancel_nest; + } return 0; out_cancel_nest: - nla_nest_cancel(msg, entry); - return -EMSGSIZE; } -int em_nl_get_pds_doit(struct sk_buff *skb, struct genl_info *info) +static int __em_nl_get_pd_for_dump(struct em_perf_domain *pd, void *data) { - struct sk_buff *msg; + const struct genl_info *info; + struct dump_ctx *ctx = data; void *hdr; + int ret; + + if (ctx->idx++ < ctx->start) + return 0; + + info = genl_info_dump(ctx->cb); + hdr = genlmsg_iput(ctx->skb, info); + if (!hdr) { + genlmsg_cancel(ctx->skb, hdr); + return -EMSGSIZE; + } + + ret = __em_nl_get_pd(pd, ctx->skb); + genlmsg_end(ctx->skb, hdr); + return ret; +} + +int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb, + struct genl_info *info) +{ + int id, ret = -EMSGSIZE, msg_sz = 0; int cmd = info->genlhdr->cmd; - int ret = -EMSGSIZE, msg_sz = 0; + struct em_perf_domain *pd; + struct sk_buff *msg; + void *hdr; + + if (!info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID]) + return -EINVAL; - for_each_em_perf_domain(__em_nl_get_pd_size, &msg_sz); + id = nla_get_u32(info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID]); + pd = em_perf_domain_get_by_id(id); + __em_nl_get_pd_size(pd, &msg_sz); msg = genlmsg_new(msg_sz, GFP_KERNEL); if (!msg) return -ENOMEM; - hdr = genlmsg_put_reply(msg, info, &em_nl_family, 0, cmd); + hdr = genlmsg_put_reply(msg, info, &dev_energymodel_nl_family, 0, cmd); if (!hdr) goto out_free_msg; - ret = for_each_em_perf_domain(__em_nl_get_pd, msg); + ret = __em_nl_get_pd(pd, msg); if (ret) goto out_cancel_msg; - genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -98,19 +130,31 @@ out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); - return ret; } +int dev_energymodel_nl_get_perf_domains_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct dump_ctx ctx = { + .idx = 0, + .start = cb->args[0], + .skb = skb, + .cb = cb, + }; + + return for_each_em_perf_domain(__em_nl_get_pd_for_dump, &ctx); +} + static struct em_perf_domain *__em_nl_get_pd_table_id(struct nlattr **attrs) { struct em_perf_domain *pd; int id; - if (!attrs[EM_A_PD_TABLE_PD_ID]) + if (!attrs[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID]) return NULL; - id = nla_get_u32(attrs[EM_A_PD_TABLE_PD_ID]); + id = nla_get_u32(attrs[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID]); pd = em_perf_domain_get_by_id(id); return pd; } @@ -119,25 +163,34 @@ static int __em_nl_get_pd_table_size(const struct em_perf_domain *pd) { int id_sz, ps_sz; - id_sz = nla_total_size(sizeof(u32)); /* EM_A_PD_TABLE_PD_ID */ - ps_sz = nla_total_size(0) + /* EM_A_PD_TABLE_PS */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_PERFORMANCE */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_FREQUENCY */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_POWER */ - nla_total_size_64bit(sizeof(u64)) + /* EM_A_PS_COST */ - nla_total_size_64bit(sizeof(u64)); /* EM_A_PS_FLAGS */ + id_sz = nla_total_size(sizeof(u32)); + /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID */ + ps_sz = nla_total_size(0) + + /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_POWER */ + nla_total_size_64bit(sizeof(u64)) + + /* DEV_ENERGYMODEL_A_PERF_STATE_COST */ + nla_total_size_64bit(sizeof(u64)); + /* DEV_ENERGYMODEL_A_PERF_STATE_FLAGS */ ps_sz *= pd->nr_perf_states; return nlmsg_total_size(genlmsg_msg_size(id_sz + ps_sz)); } -static int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain *pd) +static +int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain *pd) { struct em_perf_state *table, *ps; struct nlattr *entry; int i; - if (nla_put_u32(msg, EM_A_PD_TABLE_PD_ID, pd->id)) + if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID, + pd->id)) goto out_err; rcu_read_lock(); @@ -146,24 +199,35 @@ static int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain for (i = 0; i < pd->nr_perf_states; i++) { ps = &table[i]; - entry = nla_nest_start(msg, EM_A_PD_TABLE_PS); + entry = nla_nest_start(msg, + DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE); if (!entry) goto out_unlock_ps; - if (nla_put_u64_64bit(msg, EM_A_PS_PERFORMANCE, - ps->performance, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE, + ps->performance, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_FREQUENCY, - ps->frequency, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY, + ps->frequency, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_POWER, - ps->power, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_POWER, + ps->power, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_COST, - ps->cost, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_COST, + ps->cost, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; - if (nla_put_u64_64bit(msg, EM_A_PS_FLAGS, - ps->flags, EM_A_PS_PAD)) + if (nla_put_u64_64bit(msg, + DEV_ENERGYMODEL_A_PERF_STATE_FLAGS, + ps->flags, + DEV_ENERGYMODEL_A_PERF_STATE_PAD)) goto out_cancel_ps_nest; nla_nest_end(msg, entry); @@ -179,7 +243,8 @@ out_err: return -EMSGSIZE; } -int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info) +int dev_energymodel_nl_get_perf_table_doit(struct sk_buff *skb, + struct genl_info *info) { int cmd = info->genlhdr->cmd; int msg_sz, ret = -EMSGSIZE; @@ -197,7 +262,7 @@ int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = genlmsg_put_reply(msg, info, &em_nl_family, 0, cmd); + hdr = genlmsg_put_reply(msg, info, &dev_energymodel_nl_family, 0, cmd); if (!hdr) goto out_free_msg; @@ -221,7 +286,7 @@ static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type) int msg_sz, ret = -EMSGSIZE; void *hdr; - if (!genl_has_listeners(&em_nl_family, &init_net, EM_NLGRP_EVENT)) + if (!genl_has_listeners(&dev_energymodel_nl_family, &init_net, DEV_ENERGYMODEL_NLGRP_EVENT)) return; msg_sz = __em_nl_get_pd_table_size(pd); @@ -230,7 +295,7 @@ static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type) if (!msg) return; - hdr = genlmsg_put(msg, 0, 0, &em_nl_family, 0, ntf_type); + hdr = genlmsg_put(msg, 0, 0, &dev_energymodel_nl_family, 0, ntf_type); if (!hdr) goto out_free_msg; @@ -240,28 +305,28 @@ static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type) genlmsg_end(msg, hdr); - genlmsg_multicast(&em_nl_family, msg, 0, EM_NLGRP_EVENT, GFP_KERNEL); + genlmsg_multicast(&dev_energymodel_nl_family, msg, 0, + DEV_ENERGYMODEL_NLGRP_EVENT, GFP_KERNEL); return; out_free_msg: nlmsg_free(msg); - return; } void em_notify_pd_created(const struct em_perf_domain *pd) { - __em_notify_pd_table(pd, EM_CMD_PD_CREATED); + __em_notify_pd_table(pd, DEV_ENERGYMODEL_CMD_PERF_DOMAIN_CREATED); } void em_notify_pd_updated(const struct em_perf_domain *pd) { - __em_notify_pd_table(pd, EM_CMD_PD_UPDATED); + __em_notify_pd_table(pd, DEV_ENERGYMODEL_CMD_PERF_DOMAIN_UPDATED); } static int __em_notify_pd_deleted_size(const struct em_perf_domain *pd) { - int id_sz = nla_total_size(sizeof(u32)); /* EM_A_PD_TABLE_PD_ID */ + int id_sz = nla_total_size(sizeof(u32)); /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID */ return nlmsg_total_size(genlmsg_msg_size(id_sz)); } @@ -272,7 +337,8 @@ void em_notify_pd_deleted(const struct em_perf_domain *pd) void *hdr; int msg_sz; - if (!genl_has_listeners(&em_nl_family, &init_net, EM_NLGRP_EVENT)) + if (!genl_has_listeners(&dev_energymodel_nl_family, &init_net, + DEV_ENERGYMODEL_NLGRP_EVENT)) return; msg_sz = __em_notify_pd_deleted_size(pd); @@ -281,28 +347,29 @@ void em_notify_pd_deleted(const struct em_perf_domain *pd) if (!msg) return; - hdr = genlmsg_put(msg, 0, 0, &em_nl_family, 0, EM_CMD_PD_DELETED); + hdr = genlmsg_put(msg, 0, 0, &dev_energymodel_nl_family, 0, + DEV_ENERGYMODEL_CMD_PERF_DOMAIN_DELETED); if (!hdr) goto out_free_msg; - if (nla_put_u32(msg, EM_A_PD_TABLE_PD_ID, pd->id)) { + if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID, + pd->id)) goto out_free_msg; - } genlmsg_end(msg, hdr); - genlmsg_multicast(&em_nl_family, msg, 0, EM_NLGRP_EVENT, GFP_KERNEL); + genlmsg_multicast(&dev_energymodel_nl_family, msg, 0, + DEV_ENERGYMODEL_NLGRP_EVENT, GFP_KERNEL); return; out_free_msg: nlmsg_free(msg); - return; } /**************************** Initialization *********************************/ static int __init em_netlink_init(void) { - return genl_register_family(&em_nl_family); + return genl_register_family(&dev_energymodel_nl_family); } postcore_initcall(em_netlink_init); diff --git a/kernel/power/em_netlink_autogen.c b/kernel/power/em_netlink_autogen.c index ceb3b2bb6ebe..fedd473e4244 100644 --- a/kernel/power/em_netlink_autogen.c +++ b/kernel/power/em_netlink_autogen.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ /* YNL-GEN kernel source */ /* To regenerate run: tools/net/ynl/ynl-regen.sh */ @@ -9,41 +9,53 @@ #include "em_netlink_autogen.h" -#include <uapi/linux/energy_model.h> +#include <uapi/linux/dev_energymodel.h> -/* EM_CMD_GET_PD_TABLE - do */ -static const struct nla_policy em_get_pd_table_nl_policy[EM_A_PD_TABLE_PD_ID + 1] = { - [EM_A_PD_TABLE_PD_ID] = { .type = NLA_U32, }, +/* DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS - do */ +static const struct nla_policy dev_energymodel_get_perf_domains_nl_policy[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID + 1] = { + [DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID] = { .type = NLA_U32, }, }; -/* Ops table for em */ -static const struct genl_split_ops em_nl_ops[] = { +/* DEV_ENERGYMODEL_CMD_GET_PERF_TABLE - do */ +static const struct nla_policy dev_energymodel_get_perf_table_nl_policy[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID + 1] = { + [DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID] = { .type = NLA_U32, }, +}; + +/* Ops table for dev_energymodel */ +static const struct genl_split_ops dev_energymodel_nl_ops[] = { + { + .cmd = DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS, + .doit = dev_energymodel_nl_get_perf_domains_doit, + .policy = dev_energymodel_get_perf_domains_nl_policy, + .maxattr = DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID, + .flags = GENL_CMD_CAP_DO, + }, { - .cmd = EM_CMD_GET_PDS, - .doit = em_nl_get_pds_doit, - .flags = GENL_CMD_CAP_DO, + .cmd = DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS, + .dumpit = dev_energymodel_nl_get_perf_domains_dumpit, + .flags = GENL_CMD_CAP_DUMP, }, { - .cmd = EM_CMD_GET_PD_TABLE, - .doit = em_nl_get_pd_table_doit, - .policy = em_get_pd_table_nl_policy, - .maxattr = EM_A_PD_TABLE_PD_ID, + .cmd = DEV_ENERGYMODEL_CMD_GET_PERF_TABLE, + .doit = dev_energymodel_nl_get_perf_table_doit, + .policy = dev_energymodel_get_perf_table_nl_policy, + .maxattr = DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID, .flags = GENL_CMD_CAP_DO, }, }; -static const struct genl_multicast_group em_nl_mcgrps[] = { - [EM_NLGRP_EVENT] = { "event", }, +static const struct genl_multicast_group dev_energymodel_nl_mcgrps[] = { + [DEV_ENERGYMODEL_NLGRP_EVENT] = { "event", }, }; -struct genl_family em_nl_family __ro_after_init = { - .name = EM_FAMILY_NAME, - .version = EM_FAMILY_VERSION, +struct genl_family dev_energymodel_nl_family __ro_after_init = { + .name = DEV_ENERGYMODEL_FAMILY_NAME, + .version = DEV_ENERGYMODEL_FAMILY_VERSION, .netnsok = true, .parallel_ops = true, .module = THIS_MODULE, - .split_ops = em_nl_ops, - .n_split_ops = ARRAY_SIZE(em_nl_ops), - .mcgrps = em_nl_mcgrps, - .n_mcgrps = ARRAY_SIZE(em_nl_mcgrps), + .split_ops = dev_energymodel_nl_ops, + .n_split_ops = ARRAY_SIZE(dev_energymodel_nl_ops), + .mcgrps = dev_energymodel_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(dev_energymodel_nl_mcgrps), }; diff --git a/kernel/power/em_netlink_autogen.h b/kernel/power/em_netlink_autogen.h index 140ab548103c..5caf2f7e18a5 100644 --- a/kernel/power/em_netlink_autogen.h +++ b/kernel/power/em_netlink_autogen.h @@ -1,24 +1,28 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/em.yaml */ +/* Documentation/netlink/specs/dev-energymodel.yaml */ /* YNL-GEN kernel header */ /* To regenerate run: tools/net/ynl/ynl-regen.sh */ -#ifndef _LINUX_EM_GEN_H -#define _LINUX_EM_GEN_H +#ifndef _LINUX_DEV_ENERGYMODEL_GEN_H +#define _LINUX_DEV_ENERGYMODEL_GEN_H #include <net/netlink.h> #include <net/genetlink.h> -#include <uapi/linux/energy_model.h> +#include <uapi/linux/dev_energymodel.h> -int em_nl_get_pds_doit(struct sk_buff *skb, struct genl_info *info); -int em_nl_get_pd_table_doit(struct sk_buff *skb, struct genl_info *info); +int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb, + struct genl_info *info); +int dev_energymodel_nl_get_perf_domains_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int dev_energymodel_nl_get_perf_table_doit(struct sk_buff *skb, + struct genl_info *info); enum { - EM_NLGRP_EVENT, + DEV_ENERGYMODEL_NLGRP_EVENT, }; -extern struct genl_family em_nl_family; +extern struct genl_family dev_energymodel_nl_family; -#endif /* _LINUX_EM_GEN_H */ +#endif /* _LINUX_DEV_ENERGYMODEL_GEN_H */ diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 11af9f64aa82..5b055cbe5341 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -449,8 +449,10 @@ static int em_create_pd(struct device *dev, int nr_states, INIT_LIST_HEAD(&pd->node); id = ida_alloc(&em_pd_ida, GFP_KERNEL); - if (id < 0) - return -ENOMEM; + if (id < 0) { + kfree(pd); + return id; + } pd->id = id; em_table = em_table_alloc(pd); diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index 3fa403f9831f..32fc12e53675 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -1557,18 +1557,27 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) ctxt->allow_unsafe_takeover = nbcon_allow_unsafe_takeover(); while (nbcon_seq_read(con) < stop_seq) { - if (!nbcon_context_try_acquire(ctxt, false)) - return -EPERM; - /* - * nbcon_emit_next_record() returns false when the console was - * handed over or taken over. In both cases the context is no - * longer valid. + * Atomic flushing does not use console driver synchronization + * (i.e. it does not hold the port lock for uart consoles). + * Therefore IRQs must be disabled to avoid being interrupted + * and then calling into a driver that will deadlock trying + * to acquire console ownership. */ - if (!nbcon_emit_next_record(&wctxt, true)) - return -EAGAIN; + scoped_guard(irqsave) { + if (!nbcon_context_try_acquire(ctxt, false)) + return -EPERM; - nbcon_context_release(ctxt); + /* + * nbcon_emit_next_record() returns false when + * the console was handed over or taken over. + * In both cases the context is no longer valid. + */ + if (!nbcon_emit_next_record(&wctxt, true)) + return -EAGAIN; + + nbcon_context_release(ctxt); + } if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ @@ -1595,22 +1604,11 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) { struct console_flush_type ft; - unsigned long flags; int err; again: - /* - * Atomic flushing does not use console driver synchronization (i.e. - * it does not hold the port lock for uart consoles). Therefore IRQs - * must be disabled to avoid being interrupted and then calling into - * a driver that will deadlock trying to acquire console ownership. - */ - local_irq_save(flags); - err = __nbcon_atomic_flush_pending_con(con, stop_seq); - local_irq_restore(flags); - /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 60afadb6eede..045f83ad261e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4950,9 +4950,13 @@ struct balance_callback *splice_balance_callbacks(struct rq *rq) return __splice_balance_callbacks(rq, true); } -static void __balance_callbacks(struct rq *rq) +void __balance_callbacks(struct rq *rq, struct rq_flags *rf) { + if (rf) + rq_unpin_lock(rq, rf); do_balance_callbacks(rq, __splice_balance_callbacks(rq, false)); + if (rf) + rq_repin_lock(rq, rf); } void balance_callbacks(struct rq *rq, struct balance_callback *head) @@ -4991,7 +4995,7 @@ static inline void finish_lock_switch(struct rq *rq) * prev into current: */ spin_acquire(&__rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_); - __balance_callbacks(rq); + __balance_callbacks(rq, NULL); raw_spin_rq_unlock_irq(rq); } @@ -6867,7 +6871,7 @@ keep_resched: proxy_tag_curr(rq, next); rq_unpin_lock(rq, &rf); - __balance_callbacks(rq); + __balance_callbacks(rq, NULL); raw_spin_rq_unlock_irq(rq); } trace_sched_exit_tp(is_switch); @@ -7316,7 +7320,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) trace_sched_pi_setprio(p, pi_task); oldprio = p->prio; - if (oldprio == prio) + if (oldprio == prio && !dl_prio(prio)) queue_flag &= ~DEQUEUE_MOVE; prev_class = p->sched_class; @@ -7362,9 +7366,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) out_unlock: /* Caller holds task_struct::pi_lock, IRQs are still disabled */ - rq_unpin_lock(rq, &rf); - __balance_callbacks(rq); - rq_repin_lock(rq, &rf); + __balance_callbacks(rq, &rf); __task_rq_unlock(rq, p, &rf); } #endif /* CONFIG_RT_MUTEXES */ @@ -9124,6 +9126,8 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup) if (resched) resched_curr(rq); + + __balance_callbacks(rq, &rq_guard.rf); } static struct cgroup_subsys_state * diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 319439fe1870..c509f2e7d69d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -752,8 +752,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - update_rq_clock(rq); - WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); @@ -1420,7 +1418,7 @@ update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se, int static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec) { - bool idle = rq->curr == rq->idle; + bool idle = idle_rq(rq); s64 scaled_delta_exec; if (unlikely(delta_exec <= 0)) { @@ -1603,8 +1601,8 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * | 8 | B:zero_laxity-wait | | | * | | | <---+ | * | +--------------------------------+ | - * | | ^ ^ 2 | - * | | 7 | 2 +--------------------+ + * | | ^ ^ 2 | + * | | 7 | 2, 1 +----------------+ * | v | * | +-------------+ | * +-- | C:idle-wait | -+ @@ -1649,8 +1647,11 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * dl_defer_idle = 0 * * - * [1] A->B, A->D + * [1] A->B, A->D, C->B * dl_server_start() + * dl_defer_idle = 0; + * if (dl_server_active) + * return; // [B] * dl_server_active = 1; * enqueue_dl_entity() * update_dl_entity(WAKEUP) @@ -1759,6 +1760,7 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec) * "B:zero_laxity-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"] * "B:zero_laxity-wait" -> "D:running" [label="3:dl_server_timer"] * "C:idle-wait" -> "A:init" [label="8:dl_server_timer"] + * "C:idle-wait" -> "B:zero_laxity-wait" [label="1:dl_server_start"] * "C:idle-wait" -> "B:zero_laxity-wait" [label="2:dl_server_update"] * "C:idle-wait" -> "C:idle-wait" [label="7:dl_server_update_idle"] * "D:running" -> "A:init" [label="4:pick_task_dl"] @@ -1784,6 +1786,7 @@ void dl_server_start(struct sched_dl_entity *dl_se) { struct rq *rq = dl_se->rq; + dl_se->dl_defer_idle = 0; if (!dl_server(dl_se) || dl_se->dl_server_active) return; @@ -1834,6 +1837,7 @@ void sched_init_dl_servers(void) rq = cpu_rq(cpu); guard(rq_lock_irq)(rq); + update_rq_clock(rq); dl_se = &rq->fair_server; @@ -2210,7 +2214,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { replenish_dl_entity(dl_se); - } else if ((flags & ENQUEUE_RESTORE) && + } else if ((flags & ENQUEUE_MOVE) && !is_dl_boosted(dl_se) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) { setup_new_dl_entity(dl_se); @@ -3154,7 +3158,7 @@ void dl_add_task_root_domain(struct task_struct *p) struct rq *rq; struct dl_bw *dl_b; unsigned int cpu; - struct cpumask *msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl); + struct cpumask *msk; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); if (!dl_task(p) || dl_entity_is_special(&p->dl)) { @@ -3162,20 +3166,12 @@ void dl_add_task_root_domain(struct task_struct *p) return; } - /* - * Get an active rq, whose rq->rd traces the correct root - * domain. - * Ideally this would be under cpuset reader lock until rq->rd is - * fetched. However, sleepable locks cannot nest inside pi_lock, so we - * rely on the caller of dl_add_task_root_domain() holds 'cpuset_mutex' - * to guarantee the CPU stays in the cpuset. - */ + msk = this_cpu_cpumask_var_ptr(local_cpu_mask_dl); dl_get_task_effective_cpus(p, msk); cpu = cpumask_first_and(cpu_active_mask, msk); BUG_ON(cpu >= nr_cpu_ids); rq = cpu_rq(cpu); dl_b = &rq->rd->dl_bw; - /* End of fetching rd */ raw_spin_lock(&dl_b->lock); __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); @@ -3299,6 +3295,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) static u64 get_prio_dl(struct rq *rq, struct task_struct *p) { + /* + * Make sure to update current so we don't return a stale value. + */ + if (task_current_donor(rq, p)) + update_curr_dl(rq); + return p->dl.deadline; } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 8f6d8d7f895c..afe28c04d5aa 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -545,6 +545,7 @@ static void scx_task_iter_start(struct scx_task_iter *iter) static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter) { if (iter->locked_task) { + __balance_callbacks(iter->rq, &iter->rf); task_rq_unlock(iter->rq, iter->locked_task, &iter->rf); iter->locked_task = NULL; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d30cca6870f5..93fce4bbff5e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1364,6 +1364,28 @@ static inline u32 sched_rng(void) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +static inline bool idle_rq(struct rq *rq) +{ + return rq->curr == rq->idle && !rq->nr_running && !rq->ttwu_pending; +} + +/** + * available_idle_cpu - is a given CPU idle for enqueuing work. + * @cpu: the CPU in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +static inline bool available_idle_cpu(int cpu) +{ + if (!idle_rq(cpu_rq(cpu))) + return 0; + + if (vcpu_is_preempted(cpu)) + return 0; + + return 1; +} + #ifdef CONFIG_SCHED_PROXY_EXEC static inline void rq_set_donor(struct rq *rq, struct task_struct *t) { @@ -2366,7 +2388,8 @@ extern const u32 sched_prio_to_wmult[40]; * should preserve as much state as possible. * * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location - * in the runqueue. + * in the runqueue. IOW the priority is allowed to change. Callers + * must expect to deal with balance callbacks. * * NOCLOCK - skip the update_rq_clock() (avoids double updates) * @@ -3947,6 +3970,8 @@ extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags); extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags); extern struct balance_callback *splice_balance_callbacks(struct rq *rq); + +extern void __balance_callbacks(struct rq *rq, struct rq_flags *rf); extern void balance_callbacks(struct rq *rq, struct balance_callback *head); /* diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 0496dc29ed0f..6f10db3646e7 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -180,35 +180,7 @@ int task_prio(const struct task_struct *p) */ int idle_cpu(int cpu) { - struct rq *rq = cpu_rq(cpu); - - if (rq->curr != rq->idle) - return 0; - - if (rq->nr_running) - return 0; - - if (rq->ttwu_pending) - return 0; - - return 1; -} - -/** - * available_idle_cpu - is a given CPU idle for enqueuing work. - * @cpu: the CPU in question. - * - * Return: 1 if the CPU is currently idle. 0 otherwise. - */ -int available_idle_cpu(int cpu) -{ - if (!idle_cpu(cpu)) - return 0; - - if (vcpu_is_preempted(cpu)) - return 0; - - return 1; + return idle_rq(cpu_rq(cpu)); } /** @@ -667,7 +639,7 @@ change: * itself. */ newprio = rt_effective_prio(p, newprio); - if (newprio == oldprio) + if (newprio == oldprio && !dl_prio(newprio)) queue_flags &= ~DEQUEUE_MOVE; } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index bdb30cc5e873..0e4bc1ca15ff 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -913,7 +913,7 @@ static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, return true; /* Extra check for softirq clock bases */ - if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) + if (base->index < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ef2d5dca6f70..aa758efc3731 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1148,7 +1148,6 @@ struct ftrace_page { }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) -#define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; @@ -3834,7 +3833,8 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) return 0; } -static int ftrace_allocate_records(struct ftrace_page *pg, int count) +static int ftrace_allocate_records(struct ftrace_page *pg, int count, + unsigned long *num_pages) { int order; int pages; @@ -3844,7 +3844,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return -EINVAL; /* We want to fill as much as possible, with no empty pages */ - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); + pages = DIV_ROUND_UP(count * ENTRY_SIZE, PAGE_SIZE); order = fls(pages) - 1; again: @@ -3859,6 +3859,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) } ftrace_number_of_pages += 1 << order; + *num_pages += 1 << order; ftrace_number_of_groups++; cnt = (PAGE_SIZE << order) / ENTRY_SIZE; @@ -3887,12 +3888,14 @@ static void ftrace_free_pages(struct ftrace_page *pages) } static struct ftrace_page * -ftrace_allocate_pages(unsigned long num_to_init) +ftrace_allocate_pages(unsigned long num_to_init, unsigned long *num_pages) { struct ftrace_page *start_pg; struct ftrace_page *pg; int cnt; + *num_pages = 0; + if (!num_to_init) return NULL; @@ -3906,7 +3909,7 @@ ftrace_allocate_pages(unsigned long num_to_init) * waste as little space as possible. */ for (;;) { - cnt = ftrace_allocate_records(pg, num_to_init); + cnt = ftrace_allocate_records(pg, num_to_init, num_pages); if (cnt < 0) goto free_pages; @@ -7192,8 +7195,6 @@ static int ftrace_process_locs(struct module *mod, if (!count) return 0; - pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); - /* * Sorting mcount in vmlinux at build time depend on * CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in @@ -7206,7 +7207,7 @@ static int ftrace_process_locs(struct module *mod, test_is_sorted(start, count); } - start_pg = ftrace_allocate_pages(count); + start_pg = ftrace_allocate_pages(count, &pages); if (!start_pg) return -ENOMEM; @@ -7305,27 +7306,27 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { unsigned long pg_remaining, remaining = 0; - unsigned long skip; + long skip; /* Count the number of entries unused and compare it to skipped. */ - pg_remaining = (ENTRIES_PER_PAGE << pg->order) - pg->index; + pg_remaining = (PAGE_SIZE << pg->order) / ENTRY_SIZE - pg->index; if (!WARN(skipped < pg_remaining, "Extra allocated pages for ftrace")) { skip = skipped - pg_remaining; - for (pg = pg_unuse; pg; pg = pg->next) + for (pg = pg_unuse; pg && skip > 0; pg = pg->next) { remaining += 1 << pg->order; + skip -= (PAGE_SIZE << pg->order) / ENTRY_SIZE; + } pages -= remaining; - skip = DIV_ROUND_UP(skip, ENTRIES_PER_PAGE); - /* * Check to see if the number of pages remaining would * just fit the number of entries skipped. */ - WARN(skip != remaining, "Extra allocated pages for ftrace: %lu with %lu skipped", + WARN(pg || skip > 0, "Extra allocated pages for ftrace: %lu with %lu skipped", remaining, skipped); } /* Need to synchronize with ftrace_location_range() */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 0685e3a8aa0a..366122f4a0f8 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -71,7 +71,7 @@ unsigned int __read_mostly hardlockup_panic = * hard lockup is detected, it could be task, memory, lock etc. * Refer include/linux/sys_info.h for detailed bit definition. */ -static unsigned long hardlockup_si_mask; +unsigned long hardlockup_si_mask; #ifdef CONFIG_SYSFS diff --git a/lib/buildid.c b/lib/buildid.c index aaf61dfc0919..818331051afe 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -5,6 +5,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/pagemap.h> +#include <linux/fs.h> #include <linux/secretmem.h> #define BUILD_ID 3 @@ -46,20 +47,9 @@ static int freader_get_folio(struct freader *r, loff_t file_off) freader_put_folio(r); - /* reject secretmem folios created with memfd_secret() */ - if (secretmem_mapping(r->file->f_mapping)) - return -EFAULT; - + /* only use page cache lookup - fail if not already cached */ r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT); - /* if sleeping is allowed, wait for the page, if necessary */ - if (r->may_fault && (IS_ERR(r->folio) || !folio_test_uptodate(r->folio))) { - filemap_invalidate_lock_shared(r->file->f_mapping); - r->folio = read_cache_folio(r->file->f_mapping, file_off >> PAGE_SHIFT, - NULL, r->file); - filemap_invalidate_unlock_shared(r->file->f_mapping); - } - if (IS_ERR(r->folio) || !folio_test_uptodate(r->folio)) { if (!IS_ERR(r->folio)) folio_put(r->folio); @@ -97,6 +87,24 @@ const void *freader_fetch(struct freader *r, loff_t file_off, size_t sz) return r->data + file_off; } + /* reject secretmem folios created with memfd_secret() */ + if (secretmem_mapping(r->file->f_mapping)) { + r->err = -EFAULT; + return NULL; + } + + /* use __kernel_read() for sleepable context */ + if (r->may_fault) { + ssize_t ret; + + ret = __kernel_read(r->file, r->buf, sz, &file_off); + if (ret != sz) { + r->err = (ret < 0) ? ret : -EIO; + return NULL; + } + return r->buf; + } + /* fetch or reuse folio for given file offset */ r->err = freader_get_folio(r, file_off); if (r->err) diff --git a/mm/Kconfig b/mm/Kconfig index bd0ea5454af8..a992f2203eb9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1220,10 +1220,14 @@ config ZONE_DEVICE Device memory hotplug support allows for establishing pmem, or other device driver discovered memory regions, in the memmap. This allows pfn_to_page() lookups of otherwise - "device-physical" addresses which is needed for using a DAX - mapping in an O_DIRECT operation, among other things. - - If FS_DAX is enabled, then say Y. + "device-physical" addresses which is needed for DAX, PCI_P2PDMA, and + DEVICE_PRIVATE features among others. + + Enabling this option will reduce the entropy of x86 KASLR memory + regions. For example - on a 46 bit system, the entropy goes down + from 16 bits to 15 bits. The actual reduction in entropy depends + on the physical address bits, on processor features, kernel config + (5 level page table) and physical memory present on the system. # # Helpers to mirror range of the CPU page tables of a process into device page diff --git a/mm/damon/core.c b/mm/damon/core.c index f9fc0375890a..84f80a20f233 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1431,6 +1431,35 @@ bool damon_is_running(struct damon_ctx *ctx) return running; } +/* + * damon_call_handle_inactive_ctx() - handle DAMON call request that added to + * an inactive context. + * @ctx: The inactive DAMON context. + * @control: Control variable of the call request. + * + * This function is called in a case that @control is added to @ctx but @ctx is + * not running (inactive). See if @ctx handled @control or not, and cleanup + * @control if it was not handled. + * + * Returns 0 if @control was handled by @ctx, negative error code otherwise. + */ +static int damon_call_handle_inactive_ctx( + struct damon_ctx *ctx, struct damon_call_control *control) +{ + struct damon_call_control *c; + + mutex_lock(&ctx->call_controls_lock); + list_for_each_entry(c, &ctx->call_controls, list) { + if (c == control) { + list_del(&control->list); + mutex_unlock(&ctx->call_controls_lock); + return -EINVAL; + } + } + mutex_unlock(&ctx->call_controls_lock); + return 0; +} + /** * damon_call() - Invoke a given function on DAMON worker thread (kdamond). * @ctx: DAMON context to call the function for. @@ -1461,7 +1490,7 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control) list_add_tail(&control->list, &ctx->call_controls); mutex_unlock(&ctx->call_controls_lock); if (!damon_is_running(ctx)) - return -EINVAL; + return damon_call_handle_inactive_ctx(ctx, control); if (control->repeat) return 0; wait_for_completion(&control->completion); @@ -2051,13 +2080,15 @@ static unsigned long damos_get_node_memcg_used_bp( rcu_read_lock(); memcg = mem_cgroup_from_id(goal->memcg_id); - rcu_read_unlock(); - if (!memcg) { + if (!memcg || !mem_cgroup_tryget(memcg)) { + rcu_read_unlock(); if (goal->metric == DAMOS_QUOTA_NODE_MEMCG_USED_BP) return 0; else /* DAMOS_QUOTA_NODE_MEMCG_FREE_BP */ return 10000; } + rcu_read_unlock(); + mem_cgroup_flush_stats(memcg); lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(goal->nid)); used_pages = lruvec_page_state(lruvec, NR_ACTIVE_ANON); @@ -2065,6 +2096,8 @@ static unsigned long damos_get_node_memcg_used_bp( used_pages += lruvec_page_state(lruvec, NR_ACTIVE_FILE); used_pages += lruvec_page_state(lruvec, NR_INACTIVE_FILE); + mem_cgroup_put(memcg); + si_meminfo_node(&i, goal->nid); if (goal->metric == DAMOS_QUOTA_NODE_MEMCG_USED_BP) numerator = used_pages; @@ -2751,13 +2784,13 @@ done: if (ctx->ops.cleanup) ctx->ops.cleanup(ctx); kfree(ctx->regions_score_histogram); + kdamond_call(ctx, true); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); ctx->kdamond = NULL; mutex_unlock(&ctx->kdamond_lock); - kdamond_call(ctx, true); damos_walk_cancel(ctx); mutex_lock(&damon_lock); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 30d20f5b3192..3a699dcd5a7f 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2152,13 +2152,13 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) return err; err = damos_sysfs_set_dests(scheme); if (err) - goto put_access_pattern_out; + goto rmdir_put_access_pattern_out; err = damon_sysfs_scheme_set_quotas(scheme); if (err) goto put_dests_out; err = damon_sysfs_scheme_set_watermarks(scheme); if (err) - goto put_quotas_access_pattern_out; + goto rmdir_put_quotas_access_pattern_out; err = damos_sysfs_set_filter_dirs(scheme); if (err) goto put_watermarks_quotas_access_pattern_out; @@ -2183,13 +2183,15 @@ put_filters_watermarks_quotas_access_pattern_out: put_watermarks_quotas_access_pattern_out: kobject_put(&scheme->watermarks->kobj); scheme->watermarks = NULL; -put_quotas_access_pattern_out: +rmdir_put_quotas_access_pattern_out: + damon_sysfs_quotas_rm_dirs(scheme->quotas); kobject_put(&scheme->quotas->kobj); scheme->quotas = NULL; put_dests_out: kobject_put(&scheme->dests->kobj); scheme->dests = NULL; -put_access_pattern_out: +rmdir_put_access_pattern_out: + damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern); kobject_put(&scheme->access_pattern->kobj); scheme->access_pattern = NULL; return err; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index e2bd2d7becdd..95fd9375a7d8 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -792,7 +792,7 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) nr_regions_range = damon_sysfs_ul_range_alloc(10, 1000); if (!nr_regions_range) { err = -ENOMEM; - goto put_intervals_out; + goto rmdir_put_intervals_out; } err = kobject_init_and_add(&nr_regions_range->kobj, @@ -806,6 +806,8 @@ static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) put_nr_regions_intervals_out: kobject_put(&nr_regions_range->kobj); attrs->nr_regions_range = NULL; +rmdir_put_intervals_out: + damon_sysfs_intervals_rm_dirs(intervals); put_intervals_out: kobject_put(&intervals->kobj); attrs->intervals = NULL; @@ -948,7 +950,7 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) err = damon_sysfs_context_set_targets(context); if (err) - goto put_attrs_out; + goto rmdir_put_attrs_out; err = damon_sysfs_context_set_schemes(context); if (err) @@ -958,7 +960,8 @@ static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) put_targets_attrs_out: kobject_put(&context->targets->kobj); context->targets = NULL; -put_attrs_out: +rmdir_put_attrs_out: + damon_sysfs_attrs_rm_dirs(context->attrs); kobject_put(&context->attrs->kobj); context->attrs = NULL; return err; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 51273baec9e5..a1832da0f623 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4286,6 +4286,11 @@ static int __init hugepages_setup(char *s) unsigned long tmp; char *p = s; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring hugepages=%s cmdline\n", s); + return 0; + } + if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; @@ -4366,6 +4371,11 @@ static int __init hugepagesz_setup(char *s) unsigned long size; struct hstate *h; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring hugepagesz=%s cmdline\n", s); + return 0; + } + parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); @@ -4414,6 +4424,12 @@ static int __init default_hugepagesz_setup(char *s) unsigned long size; int i; + if (!hugepages_supported()) { + pr_warn("HugeTLB: hugepages unsupported, ignoring default_hugepagesz=%s cmdline\n", + s); + return 0; + } + parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); @@ -5096,7 +5112,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; - bool shared_pmd = false; + struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); @@ -5106,6 +5122,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, * range. */ flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); @@ -5122,8 +5139,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; - if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { - shared_pmd = true; + if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; @@ -5134,15 +5150,16 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); + tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); } - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, old_end - len, old_end); + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); return len + old_addr - old_end; } @@ -5161,7 +5178,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; - bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -5184,10 +5200,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); - tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); - force_flush = true; address |= last_addr_mask; continue; } @@ -5303,21 +5317,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } tlb_end_vma(tlb, vma); - /* - * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We - * could defer the flush until now, since by holding i_mmap_rwsem we - * guaranteed that the last reference would not be dropped. But we must - * do the flushing before we return, as otherwise i_mmap_rwsem will be - * dropped and the last reference to the shared PMDs page might be - * dropped as well. - * - * In theory we could defer the freeing of the PMD pages as well, but - * huge_pmd_unshare() relies on the exact page_count for the PMD page to - * detect sharing, so we cannot defer the release of the page either. - * Instead, do flush now. - */ - if (force_flush) - tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, @@ -6416,11 +6416,11 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); - bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6433,6 +6433,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); @@ -6459,7 +6460,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(&tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -6468,7 +6469,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); - shared_pmd = true; address |= last_addr_mask; continue; } @@ -6529,23 +6529,16 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } next: spin_unlock(ptl); cond_resched(); } - /* - * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare - * may have cleared our pud entry and done put_page on the page table: - * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. If we actually - * did unshare a page of pmds, flush the range corresponding to the pud. - */ - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, start, end); + + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new @@ -6556,6 +6549,7 @@ next: i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); return pages > 0 ? (pages << h->order) : pages; } @@ -6912,18 +6906,27 @@ out: return pte; } -/* - * unmap huge page backed by shared pte. +/** + * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * @addr: the address we are trying to unshare. + * @ptep: pointer into the (pmd) page table. * - * Called with page table lock held. + * Called with the page table lock held, the i_mmap_rwsem held in write mode + * and the hugetlb vma lock held in write mode. * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user + * Note: The caller must call huge_pmd_unshare_flush() before dropping the + * i_mmap_rwsem. + * + * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it + * was not a shared PMD table. */ -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); @@ -6935,18 +6938,36 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); - /* - * Once our caller drops the rmap lock, some other process might be - * using this page table as a normal, non-hugetlb page table. - * Wait for pending gup_fast() in other threads to finish before letting - * that happen. - */ - tlb_remove_table_sync_one(); - ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); + + tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); + mm_dec_nr_pmds(mm); return 1; } +/* + * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * + * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table + * unsharing with concurrent page table walkers. + * + * This function must be called after a sequence of huge_pmd_unshare() + * calls while still holding the i_mmap_rwsem. + */ +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * We must synchronize page table unsharing such that nobody will + * try reusing a previously-shared page table while it might still + * be in use by previous sharers (TLB, GUP_fast). + */ + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + + tlb_flush_unshared_tables(tlb); +} + #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, @@ -6955,12 +6976,16 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ +} + void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { @@ -7227,6 +7252,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; + struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; @@ -7238,6 +7264,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, return; flush_cache_range(vma, start, end); + tlb_gather_mmu_vma(&tlb, vma); + /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -7256,10 +7284,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - huge_pmd_unshare(mm, vma, address, ptep); + huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } - flush_hugetlb_tlb_range(vma, start, end); + huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); @@ -7269,6 +7297,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); } /* diff --git a/mm/init-mm.c b/mm/init-mm.c index 4600e7605cab..c5556bb9d5f0 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -44,7 +44,10 @@ struct mm_struct init_mm = { .mm_lock_seq = SEQCNT_ZERO(init_mm.mm_lock_seq), #endif .user_ns = &init_user_ns, - .cpu_bitmap = CPU_BITS_NONE, +#ifdef CONFIG_SCHED_MM_CID + .mm_cid.lock = __RAW_SPIN_LOCK_UNLOCKED(init_mm.mm_cid.lock), +#endif + .flexible_array = MM_STRUCT_FLEXIBLE_ARRAY_INIT, INIT_MM_CONTEXT(init_mm) }; diff --git a/mm/internal.h b/mm/internal.h index e430da900430..f35dbcf99a86 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -538,16 +538,8 @@ extern unsigned long highest_memmap_pfn; bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); -#ifdef CONFIG_NUMA int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat); -#else -static inline int user_proactive_reclaim(char *buf, - struct mem_cgroup *memcg, pg_data_t *pgdat) -{ - return 0; -} -#endif /* * in mm/rmap.c: diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 577a1699c553..da0f5b6f5744 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -823,6 +823,9 @@ static struct notifier_block kfence_check_canary_notifier = { static struct delayed_work kfence_timer; #ifdef CONFIG_KFENCE_STATIC_KEYS +/* Wait queue to wake up allocation-gate timer task. */ +static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); + static int kfence_reboot_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -832,7 +835,12 @@ static int kfence_reboot_callback(struct notifier_block *nb, */ WRITE_ONCE(kfence_enabled, false); /* Cancel any pending timer work */ - cancel_delayed_work_sync(&kfence_timer); + cancel_delayed_work(&kfence_timer); + /* + * Wake up any blocked toggle_allocation_gate() so it can complete + * early while the system is still able to handle IPIs. + */ + wake_up(&allocation_wait); return NOTIFY_OK; } @@ -842,9 +850,6 @@ static struct notifier_block kfence_reboot_notifier = { .priority = INT_MAX, /* Run early to stop timers ASAP */ }; -/* Wait queue to wake up allocation-gate timer task. */ -static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); - static void wake_up_kfence_timer(struct irq_work *work) { wake_up(&allocation_wait); @@ -873,7 +878,9 @@ static void toggle_allocation_gate(struct work_struct *work) /* Enable static key, and await allocation to happen. */ static_branch_enable(&kfence_allocation_key); - wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate) > 0); + wait_event_idle(allocation_wait, + atomic_read(&kfence_allocation_gate) > 0 || + !READ_ONCE(kfence_enabled)); /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c index e7f554a31bb4..9e1c5f2b7a41 100644 --- a/mm/kmsan/shadow.c +++ b/mm/kmsan/shadow.c @@ -207,7 +207,7 @@ void kmsan_free_page(struct page *page, unsigned int order) if (!kmsan_enabled || kmsan_in_runtime()) return; kmsan_enter_runtime(); - kmsan_internal_poison_memory(page_address(page), page_size(page), + kmsan_internal_poison_memory(page_address(page), PAGE_SIZE << order, GFP_KERNEL & ~(__GFP_RECLAIM), KMSAN_POISON_CHECK | KMSAN_POISON_FREE); kmsan_leave_runtime(); diff --git a/mm/memory.c b/mm/memory.c index 2a55edc48a65..da360a6eb8a4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1465,7 +1465,11 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, static bool vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { - if (src_vma->vm_flags & VM_COPY_ON_FORK) + /* + * We check against dst_vma as while sane VMA flags will have been + * copied, VM_UFFD_WP may be set only on dst_vma. + */ + if (dst_vma->vm_flags & VM_COPY_ON_FORK) return true; /* * The presence of an anon_vma indicates an anonymous VMA has page @@ -1963,10 +1967,9 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb, do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud)) { - if (next - addr != HPAGE_PUD_SIZE) { - mmap_assert_locked(tlb->mm); + if (next - addr != HPAGE_PUD_SIZE) split_huge_pud(vma, pud, addr); - } else if (zap_huge_pud(tlb, vma, pud, addr)) + else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } diff --git a/mm/migrate.c b/mm/migrate.c index 5169f9717f60..4688b9e38cd2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1458,6 +1458,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; + enum ttu_flags ttu = 0; if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ @@ -1498,8 +1499,6 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, goto put_anon; if (folio_mapped(src)) { - enum ttu_flags ttu = 0; - if (!folio_test_anon(src)) { /* * In shared mappings, try_to_unmap could potentially @@ -1516,16 +1515,17 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, try_to_migrate(src, ttu); page_was_mapped = 1; - - if (ttu & TTU_RMAP_LOCKED) - i_mmap_unlock_write(mapping); } if (!folio_mapped(src)) rc = move_to_new_folio(dst, src, mode); if (page_was_mapped) - remove_migration_ptes(src, !rc ? dst : src, 0); + remove_migration_ptes(src, !rc ? dst : src, + ttu ? RMP_LOCKED : 0); + + if (ttu & TTU_RMAP_LOCKED) + i_mmap_unlock_write(mapping); unlock_put_anon: folio_unlock(dst); diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 247e3f9db6c7..7468ec388455 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -10,6 +10,7 @@ #include <linux/swap.h> #include <linux/rmap.h> #include <linux/pgalloc.h> +#include <linux/hugetlb.h> #include <asm/tlb.h> @@ -426,6 +427,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, #endif tlb->vma_pfn = 0; + tlb->fully_unshared_tables = 0; __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } @@ -460,6 +462,31 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) } /** + * tlb_gather_mmu_vma - initialize an mmu_gather structure for operating on a + * single VMA + * @tlb: the mmu_gather structure to initialize + * @vma: the vm_area_struct + * + * Called to initialize an (on-stack) mmu_gather structure for operating on + * a single VMA. In contrast to tlb_gather_mmu(), calling this function will + * not require another call to tlb_start_vma(). In contrast to tlb_start_vma(), + * this function will *not* call flush_cache_range(). + * + * For hugetlb VMAs, this function will also initialize the mmu_gather + * page_size accordingly, not requiring a separate call to + * tlb_change_page_size(). + * + */ +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + tlb_gather_mmu(tlb, vma->vm_mm); + tlb_update_vma_flags(tlb, vma); + if (is_vm_hugetlb_page(vma)) + /* All entries have the same size. */ + tlb_change_page_size(tlb, huge_page_size(hstate_vma(vma))); +} + +/** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish * @@ -469,6 +496,12 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) void tlb_finish_mmu(struct mmu_gather *tlb) { /* + * We expect an earlier huge_pmd_unshare_flush() call to sort this out, + * due to complicated locking requirements with page table unsharing. + */ + VM_WARN_ON_ONCE(tlb->fully_unshared_tables); + + /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB * flush by batching, one thread may end up seeing inconsistent PTEs diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index 5b009a9cd8b4..8f5735fda0a2 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -7,6 +7,8 @@ #include <linux/numa.h> #include <linux/numa_memblks.h> +#include <asm/numa.h> + int numa_distance_cnt; static u8 *numa_distance; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c380f063e8b7..cbf758e27aa2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -167,6 +167,33 @@ static inline void __pcp_trylock_noop(unsigned long *flags) { } pcp_trylock_finish(UP_flags); \ }) +/* + * With the UP spinlock implementation, when we spin_lock(&pcp->lock) (for i.e. + * a potentially remote cpu drain) and get interrupted by an operation that + * attempts pcp_spin_trylock(), we can't rely on the trylock failure due to UP + * spinlock assumptions making the trylock a no-op. So we have to turn that + * spin_lock() to a spin_lock_irqsave(). This works because on UP there are no + * remote cpu's so we can only be locking the only existing local one. + */ +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +static inline void __flags_noop(unsigned long *flags) { } +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ +({ \ + __flags_noop(&(flags)); \ + spin_lock(&(ptr)->lock); \ +}) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ +({ \ + spin_unlock(&(ptr)->lock); \ + __flags_noop(&(flags)); \ +}) +#else +#define pcp_spin_lock_maybe_irqsave(ptr, flags) \ + spin_lock_irqsave(&(ptr)->lock, flags) +#define pcp_spin_unlock_maybe_irqrestore(ptr, flags) \ + spin_unlock_irqrestore(&(ptr)->lock, flags) +#endif + #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -2556,6 +2583,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) { int high_min, to_drain, to_drain_batched, batch; + unsigned long UP_flags; bool todo = false; high_min = READ_ONCE(pcp->high_min); @@ -2575,9 +2603,9 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) to_drain = pcp->count - pcp->high; while (to_drain > 0) { to_drain_batched = min(to_drain, batch); - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain_batched, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); todo = true; to_drain -= to_drain_batched; @@ -2594,14 +2622,15 @@ bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp) */ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { + unsigned long UP_flags; int to_drain, batch; batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); free_pcppages_bulk(zone, to_drain, pcp, 0); - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } } #endif @@ -2612,10 +2641,11 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + unsigned long UP_flags; int count; do { - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); count = pcp->count; if (count) { int to_drain = min(count, @@ -2624,7 +2654,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone) free_pcppages_bulk(zone, to_drain, pcp, 0); count -= to_drain; } - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } while (count); } @@ -6109,6 +6139,7 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) { struct per_cpu_pages *pcp; struct cpu_cacheinfo *cci; + unsigned long UP_flags; pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); cci = get_cpu_cacheinfo(cpu); @@ -6119,12 +6150,12 @@ static void zone_pcp_update_cacheinfo(struct zone *zone, unsigned int cpu) * This can reduce zone lock contention without hurting * cache-hot pages sharing. */ - spin_lock(&pcp->lock); + pcp_spin_lock_maybe_irqsave(pcp, UP_flags); if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch) pcp->flags |= PCPF_FREE_HIGH_BATCH; else pcp->flags &= ~PCPF_FREE_HIGH_BATCH; - spin_unlock(&pcp->lock); + pcp_spin_unlock_maybe_irqrestore(pcp, UP_flags); } void setup_pcp_cacheinfo(unsigned int cpu) @@ -6667,11 +6698,19 @@ static int percpu_pagelist_high_fraction_sysctl_handler(const struct ctl_table * int old_percpu_pagelist_high_fraction; int ret; + /* + * Avoid using pcp_batch_high_lock for reads as the value is read + * atomically and a race with offlining is harmless. + */ + + if (!write) + return proc_dointvec_minmax(table, write, buffer, length, ppos); + mutex_lock(&pcp_batch_high_lock); old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); - if (!write || ret < 0) + if (ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ @@ -7418,20 +7457,16 @@ bool put_page_back_buddy(struct page *page) } #endif -#ifdef CONFIG_ZONE_DMA -bool has_managed_dma(void) +bool has_managed_zone(enum zone_type zone) { struct pglist_data *pgdat; for_each_online_pgdat(pgdat) { - struct zone *zone = &pgdat->node_zones[ZONE_DMA]; - - if (managed_zone(zone)) + if (managed_zone(&pgdat->node_zones[zone])) return true; } return false; } -#endif /* CONFIG_ZONE_DMA */ #ifdef CONFIG_UNACCEPTED_MEMORY diff --git a/mm/rmap.c b/mm/rmap.c index f955f02d570e..7b9879ef442d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -76,7 +76,7 @@ #include <linux/mm_inline.h> #include <linux/oom.h> -#include <asm/tlbflush.h> +#include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> @@ -2008,26 +2008,25 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* - * The ref count of the PMD page was - * dropped which is part of the way map - * counting is done for shared PMDs. - * Return 'true' here. When there is - * no other sharing, huge_pmd_unshare - * returns false and we will unmap the - * actual page and drop map count - * to zero. + * The PMD table was unmapped, + * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) @@ -2404,31 +2403,29 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * fail if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { - hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { + hugetlb_vma_unlock_write(vma); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* - * The ref count of the PMD page was - * dropped which is part of the way map - * counting is done for shared PMDs. - * Return 'true' here. When there is - * no other sharing, huge_pmd_unshare - * returns false and we will unmap the - * actual page and drop map count - * to zero. + * The PMD table was unmapped, + * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); diff --git a/mm/slub.c b/mm/slub.c index 861592ac5425..f77b7407c51b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5694,8 +5694,12 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node) if (unlikely(!size)) return ZERO_SIZE_PTR; - if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq())) - /* kmalloc_nolock() in PREEMPT_RT is not supported from irq */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) + /* + * kmalloc_nolock() in PREEMPT_RT is not supported from + * non-preemptible context because local_lock becomes a + * sleeping lock on RT. + */ return NULL; retry: if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) @@ -37,6 +37,8 @@ struct mmap_state { bool check_ksm_early :1; /* If we map new, hold the file rmap lock on mapping. */ bool hold_file_rmap_lock :1; + /* If .mmap_prepare changed the file, we don't need to pin. */ + bool file_doesnt_need_get :1; }; #define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vm_flags_, file_) \ @@ -67,18 +69,13 @@ struct mmap_state { .state = VMA_MERGE_START, \ } -/* - * If, at any point, the VMA had unCoW'd mappings from parents, it will maintain - * more than one anon_vma_chain connecting it to more than one anon_vma. A merge - * would mean a wider range of folios sharing the root anon_vma lock, and thus - * potential lock contention, we do not wish to encourage merging such that this - * scales to a problem. - */ -static bool vma_had_uncowed_parents(struct vm_area_struct *vma) +/* Was this VMA ever forked from a parent, i.e. maybe contains CoW mappings? */ +static bool vma_is_fork_child(struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from - * parents. This can improve scalability caused by anon_vma lock. + * parents. This can improve scalability caused by the anon_vma root + * lock. */ return vma && vma->anon_vma && !list_is_singular(&vma->anon_vma_chain); } @@ -115,11 +112,19 @@ static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) VM_WARN_ON(src && src_anon != src->anon_vma); /* Case 1 - we will dup_anon_vma() from src into tgt. */ - if (!tgt_anon && src_anon) - return !vma_had_uncowed_parents(src); + if (!tgt_anon && src_anon) { + struct vm_area_struct *copied_from = vmg->copied_from; + + if (vma_is_fork_child(src)) + return false; + if (vma_is_fork_child(copied_from)) + return false; + + return true; + } /* Case 2 - we will simply use tgt's anon_vma. */ if (tgt_anon && !src_anon) - return !vma_had_uncowed_parents(tgt); + return !vma_is_fork_child(tgt); /* Case 3 - the anon_vma's are already shared. */ return src_anon == tgt_anon; } @@ -829,6 +834,8 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( VM_WARN_ON_VMG(middle && !(vma_iter_addr(vmg->vmi) >= middle->vm_start && vma_iter_addr(vmg->vmi) < middle->vm_end), vmg); + /* An existing merge can never be used by the mremap() logic. */ + VM_WARN_ON_VMG(vmg->copied_from, vmg); vmg->state = VMA_MERGE_NOMERGE; @@ -1099,6 +1106,33 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) } /* + * vma_merge_copied_range - Attempt to merge a VMA that is being copied by + * mremap() + * + * @vmg: Describes the VMA we are adding, in the copied-to range @vmg->start to + * @vmg->end (exclusive), which we try to merge with any adjacent VMAs if + * possible. + * + * vmg->prev, next, start, end, pgoff should all be relative to the COPIED TO + * range, i.e. the target range for the VMA. + * + * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer + * to the VMA we expanded. + * + * ASSUMPTIONS: Same as vma_merge_new_range(), except vmg->middle must contain + * the copied-from VMA. + */ +static struct vm_area_struct *vma_merge_copied_range(struct vma_merge_struct *vmg) +{ + /* We must have a copied-from VMA. */ + VM_WARN_ON_VMG(!vmg->middle, vmg); + + vmg->copied_from = vmg->middle; + vmg->middle = NULL; + return vma_merge_new_range(vmg); +} + +/* * vma_expand - Expand an existing VMA * * @vmg: Describes a VMA expansion operation. @@ -1117,46 +1151,52 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) int vma_expand(struct vma_merge_struct *vmg) { struct vm_area_struct *anon_dup = NULL; - bool remove_next = false; struct vm_area_struct *target = vmg->target; struct vm_area_struct *next = vmg->next; + bool remove_next = false; vm_flags_t sticky_flags; - - sticky_flags = vmg->vm_flags & VM_STICKY; - sticky_flags |= target->vm_flags & VM_STICKY; - - VM_WARN_ON_VMG(!target, vmg); + int ret = 0; mmap_assert_write_locked(vmg->mm); - vma_start_write(target); - if (next && (target != next) && (vmg->end == next->vm_end)) { - int ret; - sticky_flags |= next->vm_flags & VM_STICKY; + if (next && target != next && vmg->end == next->vm_end) remove_next = true; - /* This should already have been checked by this point. */ - VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg); - vma_start_write(next); - /* - * In this case we don't report OOM, so vmg->give_up_on_mm is - * safe. - */ - ret = dup_anon_vma(target, next, &anon_dup); - if (ret) - return ret; - } + /* We must have a target. */ + VM_WARN_ON_VMG(!target, vmg); + /* This should have already been checked by this point. */ + VM_WARN_ON_VMG(remove_next && !can_merge_remove_vma(next), vmg); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON_VMG(next && !remove_next && next != target && vmg->end > next->vm_start, vmg); - /* Only handles expanding */ + /* Only handles expanding. */ VM_WARN_ON_VMG(target->vm_start < vmg->start || target->vm_end > vmg->end, vmg); + sticky_flags = vmg->vm_flags & VM_STICKY; + sticky_flags |= target->vm_flags & VM_STICKY; if (remove_next) - vmg->__remove_next = true; + sticky_flags |= next->vm_flags & VM_STICKY; + + /* + * If we are removing the next VMA or copying from a VMA + * (e.g. mremap()'ing), we must propagate anon_vma state. + * + * Note that, by convention, callers ignore OOM for this case, so + * we don't need to account for vmg->give_up_on_mm here. + */ + if (remove_next) + ret = dup_anon_vma(target, next, &anon_dup); + if (!ret && vmg->copied_from) + ret = dup_anon_vma(target, vmg->copied_from, &anon_dup); + if (ret) + return ret; + if (remove_next) { + vma_start_write(next); + vmg->__remove_next = true; + } if (commit_merge(vmg)) goto nomem; @@ -1828,10 +1868,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - vmg.middle = NULL; /* New VMA range. */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); - new_vma = vma_merge_new_range(&vmg); + new_vma = vma_merge_copied_range(&vmg); if (new_vma) { /* @@ -2413,7 +2452,9 @@ static int __mmap_new_file_vma(struct mmap_state *map, struct vma_iterator *vmi = map->vmi; int error; - vma->vm_file = get_file(map->file); + vma->vm_file = map->file; + if (!map->file_doesnt_need_get) + get_file(map->file); if (!map->file->f_op->mmap) return 0; @@ -2601,7 +2642,10 @@ static int call_mmap_prepare(struct mmap_state *map, /* Update fields permitted to be changed. */ map->pgoff = desc->pgoff; - map->file = desc->vm_file; + if (desc->vm_file != map->file) { + map->file_doesnt_need_get = true; + map->file = desc->vm_file; + } map->vm_flags = desc->vm_flags; map->page_prot = desc->page_prot; /* User-defined fields. */ @@ -106,6 +106,9 @@ struct vma_merge_struct { struct anon_vma_name *anon_name; enum vma_merge_state state; + /* If copied from (i.e. mremap()'d) the VMA from which we are copying. */ + struct vm_area_struct *copied_from; + /* Flags which callers can use to modify merge behaviour: */ /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 41dd01e8430c..628f96e83b11 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4248,7 +4248,7 @@ void *vzalloc_node_noprof(unsigned long size, int node) EXPORT_SYMBOL(vzalloc_node_noprof); /** - * vrealloc_node_align_noprof - reallocate virtually contiguous memory; contents + * vrealloc_node_align - reallocate virtually contiguous memory; contents * remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate diff --git a/mm/vmscan.c b/mm/vmscan.c index 670fe9fae5ba..614ccf39fe3f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -7707,6 +7707,17 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) return ret; } +#else + +static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, + unsigned long nr_pages, + struct scan_control *sc) +{ + return 0; +} + +#endif + enum { MEMORY_RECLAIM_SWAPPINESS = 0, MEMORY_RECLAIM_SWAPPINESS_MAX, @@ -7814,8 +7825,6 @@ int user_proactive_reclaim(char *buf, return 0; } -#endif - /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list diff --git a/mm/zswap.c b/mm/zswap.c index 5d0f8b13a958..ac9b7a60736b 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -787,7 +787,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) return 0; fail: - if (acomp) + if (!IS_ERR_OR_NULL(acomp)) crypto_free_acomp(acomp); kfree(buffer); return ret; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c57c806edba8..1a84c5a3c446 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1332,14 +1332,15 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); - printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n" - "mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" + printk("%sskb len=%u data_len=%u headroom=%u headlen=%u tailroom=%u\n" + "end-tail=%u mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n" "priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n" "encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n", - level, skb->len, headroom, skb_headlen(skb), tailroom, + level, skb->len, skb->data_len, headroom, skb_headlen(skb), + tailroom, skb->end - skb->tail, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->mac_len, diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 99ede37698ac..35ce3941fae3 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -158,7 +158,7 @@ unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, DSA_MAX_NUM_OFFLOADING_BRIDGES, 1); - if (bridge_num >= max) + if (bridge_num > max) return 0; set_bit(bridge_num, &dsa_fwd_offloading_bridges); diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 3970b6b7ace5..ab8f309f8925 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -215,6 +215,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) return gue_control_message(skb, guehdr); proto_ctype = guehdr->proto_ctype; + if (unlikely(!proto_ctype)) + goto drop; + __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 7a99639204b1..309d5ba983d0 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -15,7 +15,7 @@ const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1] = { [FOU_ATTR_PORT] = { .type = NLA_BE16, }, [FOU_ATTR_AF] = { .type = NLA_U8, }, - [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, + [FOU_ATTR_IPPROTO] = NLA_POLICY_MIN(NLA_U8, 1), [FOU_ATTR_TYPE] = { .type = NLA_U8, }, [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 59d17b6f06bf..f6a5d8c73af9 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1555,8 +1555,8 @@ skip_routeinfo: memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); - if (in6_dev->ra_mtu != mtu) { - in6_dev->ra_mtu = mtu; + if (READ_ONCE(in6_dev->ra_mtu) != mtu) { + WRITE_ONCE(in6_dev->ra_mtu, mtu); send_ifinfo_notify = true; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 687c1366a4d0..f9b0f666600f 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1086,8 +1086,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel = session->tunnel; /* Check protocol version */ - if (version != tunnel->version) + if (version != tunnel->version) { + l2tp_session_put(session); goto invalid; + } if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { @@ -1414,8 +1416,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); - struct sock *sk = tunnel->sock; - struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); @@ -1423,6 +1423,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work) * the sk API to release it here. */ if (tunnel->fd < 0) { + struct socket *sock = tunnel->sock->sk_socket; + if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 649ea9d2ae9b..5bc7eb2342bb 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -451,8 +451,6 @@ struct ieee80211_mgd_assoc_data { struct ieee80211_conn_settings conn; u16 status; - - bool disabled; } link[IEEE80211_MLD_MAX_NUM_LINKS]; u8 ap_addr[ETH_ALEN] __aligned(2); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7b0aa24c1f97..515384ca2f8f 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -350,6 +350,8 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee80211_sdata_running(nsdata)) { + struct ieee80211_link_data *link; + /* * Only OCB and monitor mode may coexist */ @@ -376,8 +378,10 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, * will not add another interface while any channel * switch is active. */ - if (nsdata->vif.bss_conf.csa_active) - return -EBUSY; + for_each_link_data(nsdata, link) { + if (link->conf->csa_active) + return -EBUSY; + } /* * The remaining checks are only performed for interfaces diff --git a/net/mac80211/key.c b/net/mac80211/key.c index d5da7ccea66e..04c8809173d7 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -987,7 +987,8 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) if (ieee80211_sdata_running(sdata)) { list_for_each_entry(key, &sdata->key_list, list) { - increment_tailroom_need_count(sdata); + if (!(key->flags & KEY_FLAG_TAINTED)) + increment_tailroom_need_count(sdata); ieee80211_key_enable_hw_accel(key); } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ddff090e7dce..82a08f49f498 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -6161,6 +6161,98 @@ static bool ieee80211_get_dtim(const struct cfg80211_bss_ies *ies, return true; } +static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) +{ + if (bm_size == 1) + return *data; + + return get_unaligned_le16(data); +} + +static int +ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata, + const struct ieee80211_ttlm_elem *ttlm, + struct ieee80211_adv_ttlm_info *ttlm_info) +{ + /* The element size was already validated in + * ieee80211_tid_to_link_map_size_ok() + */ + u8 control, link_map_presence, map_size, tid; + u8 *pos; + + memset(ttlm_info, 0, sizeof(*ttlm_info)); + pos = (void *)ttlm->optional; + control = ttlm->control; + + if ((control & IEEE80211_TTLM_CONTROL_DIRECTION) != + IEEE80211_TTLM_DIRECTION_BOTH) { + sdata_info(sdata, "Invalid advertised T2L map direction\n"); + return -EINVAL; + } + + link_map_presence = *pos; + pos++; + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) { + ttlm_info->switch_time = get_unaligned_le16(pos); + + /* Since ttlm_info->switch_time == 0 means no switch time, bump + * it by 1. + */ + if (!ttlm_info->switch_time) + ttlm_info->switch_time = 1; + + pos += 2; + } + + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) { + ttlm_info->duration = pos[0] | pos[1] << 8 | pos[2] << 16; + pos += 3; + } + + if (control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) { + ttlm_info->map = 0xffff; + return 0; + } + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + map_size = 1; + else + map_size = 2; + + /* According to Draft P802.11be_D3.0 clause 35.3.7.1.7, an AP MLD shall + * not advertise a TID-to-link mapping that does not map all TIDs to the + * same link set, reject frame if not all links have mapping + */ + if (link_map_presence != 0xff) { + sdata_info(sdata, + "Invalid advertised T2L mapping presence indicator\n"); + return -EINVAL; + } + + ttlm_info->map = ieee80211_get_ttlm(map_size, pos); + if (!ttlm_info->map) { + sdata_info(sdata, + "Invalid advertised T2L map for TID 0\n"); + return -EINVAL; + } + + pos += map_size; + + for (tid = 1; tid < 8; tid++) { + u16 map = ieee80211_get_ttlm(map_size, pos); + + if (map != ttlm_info->map) { + sdata_info(sdata, "Invalid advertised T2L map for tid %d\n", + tid); + return -EINVAL; + } + + pos += map_size; + } + return 0; +} + static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, struct ieee802_11_elems *elems, @@ -6192,8 +6284,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, continue; valid_links |= BIT(link_id); - if (assoc_data->link[link_id].disabled) - dormant_links |= BIT(link_id); if (link_id != assoc_data->assoc_link_id) { err = ieee80211_sta_allocate_link(sta, link_id); @@ -6202,6 +6292,33 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } } + /* + * We do not support setting a negotiated TTLM during + * association. As such, we can assume that if there is a TTLM, + * then it is the currently active advertised TTLM. + * In that case, there must be exactly one TTLM that does not + * have a switch time set. This mapping should also leave us + * with at least one usable link. + */ + if (elems->ttlm_num > 1) { + sdata_info(sdata, + "More than one advertised TTLM in association response\n"); + goto out_err; + } else if (elems->ttlm_num == 1) { + if (ieee80211_parse_adv_t2l(sdata, elems->ttlm[0], + &sdata->u.mgd.ttlm_info) || + sdata->u.mgd.ttlm_info.switch_time != 0 || + !(valid_links & sdata->u.mgd.ttlm_info.map)) { + sdata_info(sdata, + "Invalid advertised TTLM in association response\n"); + goto out_err; + } + + sdata->u.mgd.ttlm_info.active = true; + dormant_links = + valid_links & ~sdata->u.mgd.ttlm_info.map; + } + ieee80211_vif_set_links(sdata, valid_links, dormant_links); } @@ -6992,95 +7109,6 @@ static void ieee80211_tid_to_link_map_work(struct wiphy *wiphy, sdata->u.mgd.ttlm_info.switch_time = 0; } -static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) -{ - if (bm_size == 1) - return *data; - else - return get_unaligned_le16(data); -} - -static int -ieee80211_parse_adv_t2l(struct ieee80211_sub_if_data *sdata, - const struct ieee80211_ttlm_elem *ttlm, - struct ieee80211_adv_ttlm_info *ttlm_info) -{ - /* The element size was already validated in - * ieee80211_tid_to_link_map_size_ok() - */ - u8 control, link_map_presence, map_size, tid; - u8 *pos; - - memset(ttlm_info, 0, sizeof(*ttlm_info)); - pos = (void *)ttlm->optional; - control = ttlm->control; - - if ((control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) || - !(control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT)) - return 0; - - if ((control & IEEE80211_TTLM_CONTROL_DIRECTION) != - IEEE80211_TTLM_DIRECTION_BOTH) { - sdata_info(sdata, "Invalid advertised T2L map direction\n"); - return -EINVAL; - } - - link_map_presence = *pos; - pos++; - - ttlm_info->switch_time = get_unaligned_le16(pos); - - /* Since ttlm_info->switch_time == 0 means no switch time, bump it - * by 1. - */ - if (!ttlm_info->switch_time) - ttlm_info->switch_time = 1; - - pos += 2; - - if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) { - ttlm_info->duration = pos[0] | pos[1] << 8 | pos[2] << 16; - pos += 3; - } - - if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) - map_size = 1; - else - map_size = 2; - - /* According to Draft P802.11be_D3.0 clause 35.3.7.1.7, an AP MLD shall - * not advertise a TID-to-link mapping that does not map all TIDs to the - * same link set, reject frame if not all links have mapping - */ - if (link_map_presence != 0xff) { - sdata_info(sdata, - "Invalid advertised T2L mapping presence indicator\n"); - return -EINVAL; - } - - ttlm_info->map = ieee80211_get_ttlm(map_size, pos); - if (!ttlm_info->map) { - sdata_info(sdata, - "Invalid advertised T2L map for TID 0\n"); - return -EINVAL; - } - - pos += map_size; - - for (tid = 1; tid < 8; tid++) { - u16 map = ieee80211_get_ttlm(map_size, pos); - - if (map != ttlm_info->map) { - sdata_info(sdata, "Invalid advertised T2L map for tid %d\n", - tid); - return -EINVAL; - } - - pos += map_size; - } - return 0; -} - static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, u64 beacon_ts) @@ -9737,7 +9765,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, req, true, i, &assoc_data->link[i].conn); assoc_data->link[i].bss = link_cbss; - assoc_data->link[i].disabled = req->links[i].disabled; if (!bss->uapsd_supported) uapsd_supported = false; @@ -10719,8 +10746,6 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata, &data->link[link_id].conn); data->link[link_id].bss = link_cbss; - data->link[link_id].disabled = - req->add_links[link_id].disabled; data->link[link_id].elems = (u8 *)req->add_links[link_id].elems; data->link[link_id].elems_len = diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 5ef315ed3b0f..4823c8d45639 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -347,8 +347,13 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) mgmt->da)) return; } else { - /* Beacons are expected only with broadcast address */ - if (!is_broadcast_ether_addr(mgmt->da)) + /* + * Non-S1G beacons are expected only with broadcast address. + * S1G beacons only carry the SA so no DA check is required + * nor possible. + */ + if (!ieee80211_is_s1g_beacon(mgmt->frame_control) && + !is_broadcast_ether_addr(mgmt->da)) return; } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index b94cb2ffbaf8..9cc29ae85b06 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -752,7 +752,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) unsigned char *dptr; ax25_cb *ax25s; int ret; - struct sk_buff *skbn; + struct sk_buff *nskb, *oskb; /* * Reject malformed packets early. Check that it contains at least 2 @@ -811,14 +811,16 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) /* We are going to change the netrom headers so we should get our own skb, we also did not know until now how much header space we had to reserve... - RXQ */ - if ((skbn=skb_copy_expand(skb, dev->hard_header_len, 0, GFP_ATOMIC)) == NULL) { + nskb = skb_copy_expand(skb, dev->hard_header_len, 0, GFP_ATOMIC); + + if (!nskb) { nr_node_unlock(nr_node); nr_node_put(nr_node); dev_put(dev); return 0; } - kfree_skb(skb); - skb=skbn; + oskb = skb; + skb = nskb; skb->data[14]--; dptr = skb_push(skb, 1); @@ -837,6 +839,9 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) nr_node_unlock(nr_node); nr_node_put(nr_node); + if (ret) + kfree_skb(oskb); + return ret; } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 6bbbc16ab778..f0ce8ce1dce0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -310,22 +310,23 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) */ int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb) { + u64 tx_success = 0, tx_fail = 0; struct nlattr *nla; int i; - __u64 tx_success = 0; - __u64 tx_fail = 0; - for_each_possible_cpu(i) { const struct vport_upcall_stats_percpu *stats; + u64 n_success, n_fail; unsigned int start; stats = per_cpu_ptr(vport->upcall_stats, i); do { start = u64_stats_fetch_begin(&stats->syncp); - tx_success += u64_stats_read(&stats->n_success); - tx_fail += u64_stats_read(&stats->n_fail); + n_success = u64_stats_read(&stats->n_success); + n_fail = u64_stats_read(&stats->n_fail); } while (u64_stats_fetch_retry(&stats->syncp, start)); + tx_success += n_success; + tx_fail += n_fail; } nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5b7342d43486..36d6ca0d1089 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -387,7 +387,7 @@ struct rxrpc_peer { struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ unsigned long app_data; /* Application data (e.g. afs_server) */ - time64_t last_tx_at; /* Last time packet sent here */ + unsigned int last_tx_at; /* Last time packet sent here (time64_t LSW) */ seqlock_t service_conn_lock; spinlock_t lock; /* access lock */ int debug_id; /* debug ID for printks */ @@ -1379,6 +1379,13 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t acked_serial, bool sendmsg_fail); +/* Update the last transmission time on a peer for keepalive purposes. */ +static inline void rxrpc_peer_mark_tx(struct rxrpc_peer *peer) +{ + /* To avoid tearing on 32-bit systems, we only keep the LSW. */ + WRITE_ONCE(peer->last_tx_at, ktime_get_seconds()); +} + /* * peer_object.c */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 232b6986da83..98ad9b51ca2c 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -194,7 +194,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret < 0) trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret, rxrpc_tx_point_call_final_resend); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 8b5903b6e481..d70db367e358 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -275,7 +275,7 @@ static void rxrpc_send_ack_packet(struct rxrpc_call *call, int nr_kv, size_t len rxrpc_local_dont_fragment(conn->local, why == rxrpc_propose_ack_ping_for_mtu_probe); ret = do_udp_sendmsg(conn->local->socket, &msg, len); - call->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(call->peer); if (ret < 0) { trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); @@ -411,7 +411,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt)); ret = do_udp_sendmsg(conn->local->socket, &msg, sizeof(pkt)); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_abort); @@ -698,7 +698,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req ret = 0; trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, rxrpc_txdata_inject_loss); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); goto done; } } @@ -711,7 +711,7 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req */ rxrpc_inc_stat(call->rxnet, stat_tx_data_send); ret = do_udp_sendmsg(conn->local->socket, &msg, len); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); if (ret == -EMSGSIZE) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_msgsize); @@ -797,7 +797,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn) trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); } /* @@ -917,7 +917,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) trace_rxrpc_tx_packet(peer->debug_id, &whdr, rxrpc_tx_point_version_keepalive); - peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(peer); _leave(""); } @@ -973,7 +973,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response if (ret < 0) goto fail; - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); return; fail: diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 7f4729234957..9d02448ac062 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -238,6 +238,21 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, struct sk_buff *skb, } /* + * Reconstruct the last transmission time. The difference calculated should be + * valid provided no more than ~68 years elapsed since the last transmission. + */ +static time64_t rxrpc_peer_get_tx_mark(const struct rxrpc_peer *peer, time64_t base) +{ + s32 last_tx_at = READ_ONCE(peer->last_tx_at); + s32 base_lsw = base; + s32 diff = last_tx_at - base_lsw; + + diff = clamp(diff, -RXRPC_KEEPALIVE_TIME, RXRPC_KEEPALIVE_TIME); + + return diff + base; +} + +/* * Perform keep-alive pings. */ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, @@ -265,7 +280,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_unlock_bh(&rxnet->peer_hash_lock); if (use) { - keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; + keepalive_at = rxrpc_peer_get_tx_mark(peer, base) + RXRPC_KEEPALIVE_TIME; slot = keepalive_at - base; _debug("%02x peer %u t=%d {%pISp}", cursor, peer->debug_id, slot, &peer->srx.transport); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index d803562ca0ac..59292f7f9205 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -296,13 +296,13 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) now = ktime_get_seconds(); seq_printf(seq, - "UDP %-47.47s %-47.47s %3u %4u %5u %6llus %8d %8d\n", + "UDP %-47.47s %-47.47s %3u %4u %5u %6ds %8d %8d\n", lbuff, rbuff, refcount_read(&peer->ref), peer->cong_ssthresh, peer->max_data, - now - peer->last_tx_at, + (s32)now - (s32)READ_ONCE(peer->last_tx_at), READ_ONCE(peer->recent_srtt_us), READ_ONCE(peer->recent_rto_us)); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7fa7e77f6bb9..e1f7513a46db 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -518,7 +518,8 @@ try_again: if (rxrpc_call_has_failed(call)) goto call_failed; - if (!skb_queue_empty(&call->recvmsg_queue)) + if (!(flags & MSG_PEEK) && + !skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); goto not_yet_complete; @@ -549,11 +550,21 @@ error_unlock_call: error_requeue_call: if (!(flags & MSG_PEEK)) { spin_lock_irq(&rx->recvmsg_lock); - list_add(&call->recvmsg_link, &rx->recvmsg_q); - spin_unlock_irq(&rx->recvmsg_lock); + if (list_empty(&call->recvmsg_link)) { + list_add(&call->recvmsg_link, &rx->recvmsg_q); + rxrpc_see_call(call, rxrpc_call_see_recvmsg_requeue); + spin_unlock_irq(&rx->recvmsg_lock); + } else if (list_is_first(&call->recvmsg_link, &rx->recvmsg_q)) { + spin_unlock_irq(&rx->recvmsg_lock); + rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_first); + } else { + list_move(&call->recvmsg_link, &rx->recvmsg_q); + spin_unlock_irq(&rx->recvmsg_lock); + rxrpc_put_call(call, rxrpc_call_see_recvmsg_requeue_move); + } trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0); } else { - rxrpc_put_call(call, rxrpc_call_put_recvmsg); + rxrpc_put_call(call, rxrpc_call_put_recvmsg_peek_nowait); } error_no_call: release_sock(&rx->sk); diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index dce5a3d8a964..43cbf9efd89f 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -678,7 +678,7 @@ static int rxgk_issue_challenge(struct rxrpc_connection *conn) ret = do_udp_sendmsg(conn->local->socket, &msg, len); if (ret > 0) - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); __free_page(page); if (ret < 0) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 3657c0661cdc..a756855a0a62 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -694,7 +694,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) return -EAGAIN; } - conn->peer->last_tx_at = ktime_get_seconds(); + rxrpc_peer_mark_tx(conn->peer); trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_rxkad_challenge); _leave(" = 0"); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 1dfdda6c2d4c..8e8f6af731d5 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -821,6 +821,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { +drop: qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -829,6 +830,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, skb_push(skb, skb->dev->hard_header_len); ife_meta = ife_encode(skb, metalen); + if (!ife_meta) + goto drop; spin_lock(&ife->tcf_lock); @@ -844,8 +847,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, if (err < 0) { /* too corrupt to keep around if overwritten */ spin_unlock(&ife->tcf_lock); - qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); - return TC_ACT_SHOT; + goto drop; } skboff += err; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 9d59090bbe93..e7778413e72f 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -373,7 +373,7 @@ static void qfq_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) /* Deschedule class and remove it from its parent aggregate. */ static void qfq_deact_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) { - if (cl->qdisc->q.qlen > 0) /* class is active */ + if (cl_is_active(cl)) /* class is active */ qfq_deactivate_class(q, cl); qfq_rm_from_agg(q, cl); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 8badec6d82a2..6e4bdaa876ed 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -178,6 +178,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt, if (m->dev == dev) return -ELOOP; + if (sch->parent != TC_H_ROOT) { + NL_SET_ERR_MSG_MOD(extack, "teql can only be used as root"); + return -EOPNOTSUPP; + } + q->m = m; skb_queue_head_init(&q->q); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3755ba079d07..7b823d759141 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -603,6 +603,11 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_PEER_INIT, SCTP_PEER_INIT(initchunk)); + /* SCTP-AUTH: generate the association shared keys so that + * we can potentially sign the COOKIE-ECHO. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); + /* Reset init error count upon receipt of INIT-ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); @@ -617,11 +622,6 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_ECHOED)); - /* SCTP-AUTH: generate the association shared keys so that - * we can potentially sign the COOKIE-ECHO. - */ - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); - /* 5.1 C) "A" shall then send the State Cookie received in the * INIT ACK chunk in a COOKIE ECHO chunk, ... */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index dcc8a1d5851e..d3e26025ef58 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -28,6 +28,7 @@ static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, bool cancel_timeout); +static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs); static const struct virtio_transport * virtio_transport_get_ops(struct vsock_sock *vsk) @@ -499,9 +500,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) return 0; spin_lock_bh(&vvs->tx_lock); - ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); - if (ret > credit) - ret = credit; + ret = min_t(u32, credit, virtio_transport_has_space(vvs)); vvs->tx_cnt += ret; vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); @@ -822,6 +821,15 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); +static u32 virtio_transport_tx_buf_size(struct virtio_vsock_sock *vvs) +{ + /* The peer advertises its receive buffer via peer_buf_alloc, but we + * cap it to our local buf_alloc so a remote peer cannot force us to + * queue more data than our own buffer configuration allows. + */ + return min(vvs->peer_buf_alloc, vvs->buf_alloc); +} + int virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, struct msghdr *msg, @@ -831,7 +839,7 @@ virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, spin_lock_bh(&vvs->tx_lock); - if (len > vvs->peer_buf_alloc) { + if (len > virtio_transport_tx_buf_size(vvs)) { spin_unlock_bh(&vvs->tx_lock); return -EMSGSIZE; } @@ -877,12 +885,16 @@ u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); -static s64 virtio_transport_has_space(struct vsock_sock *vsk) +static s64 virtio_transport_has_space(struct virtio_vsock_sock *vvs) { - struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + /* Use s64 arithmetic so if the peer shrinks peer_buf_alloc while + * we have bytes in flight (tx_cnt - peer_fwd_cnt), the subtraction + * does not underflow. + */ + bytes = (s64)virtio_transport_tx_buf_size(vvs) - + (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; @@ -895,7 +907,7 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) s64 bytes; spin_lock_bh(&vvs->tx_lock); - bytes = virtio_transport_has_space(vsk); + bytes = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return bytes; @@ -1359,9 +1371,11 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small - * payload. + * payload. Skip non-linear (e.g. zerocopy) skbs; these carry payload + * in skb_shinfo. */ - if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue)) { + if (len <= GOOD_COPY_LEN && !skb_queue_empty(&vvs->rx_queue) && + !skb_is_nonlinear(skb)) { struct virtio_vsock_hdr *last_hdr; struct sk_buff *last_skb; @@ -1490,7 +1504,7 @@ static bool virtio_transport_space_update(struct sock *sk, spin_lock_bh(&vvs->tx_lock); vvs->peer_buf_alloc = le32_to_cpu(hdr->buf_alloc); vvs->peer_fwd_cnt = le32_to_cpu(hdr->fwd_cnt); - space_available = virtio_transport_has_space(vsk); + space_available = virtio_transport_has_space(vvs); spin_unlock_bh(&vvs->tx_lock); return space_available; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 225580507a4b..bf3a1a617cc0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12244,9 +12244,6 @@ static int nl80211_process_links(struct cfg80211_registered_device *rdev, return -EINVAL; } } - - links[link_id].disabled = - nla_get_flag(attrs[NL80211_ATTR_MLO_LINK_DISABLED]); } return 0; @@ -12426,13 +12423,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } - if (req.links[req.link_id].disabled) { - GENL_SET_ERR_MSG(info, - "cannot have assoc link disabled"); - err = -EINVAL; - goto free; - } - if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]) req.ext_mld_capa_ops = nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]); diff --git a/net/wireless/util.c b/net/wireless/util.c index cc55b759694e..08c525835518 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1562,12 +1562,14 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); - result = tmp; /* and take NSS, DCM into account */ - result = (result * rate->nss) / 8; + tmp *= rate->nss; + do_div(tmp, 8); if (rate->he_dcm) - result /= 2; + do_div(tmp, 2); + + result = tmp; return result / 10000; } diff --git a/security/landlock/audit.c b/security/landlock/audit.c index c52d079cdb77..e899995f1fd5 100644 --- a/security/landlock/audit.c +++ b/security/landlock/audit.c @@ -191,7 +191,7 @@ static size_t get_denied_layer(const struct landlock_ruleset *const domain, long youngest_layer = -1; for_each_set_bit(access_bit, &access_req, layer_masks_size) { - const access_mask_t mask = (*layer_masks)[access_bit]; + const layer_mask_t mask = (*layer_masks)[access_bit]; long layer; if (!mask) diff --git a/security/landlock/domain.h b/security/landlock/domain.h index 7fb70b25f85a..621f054c9a2b 100644 --- a/security/landlock/domain.h +++ b/security/landlock/domain.h @@ -97,7 +97,7 @@ struct landlock_hierarchy { */ atomic64_t num_denials; /** - * @id: Landlock domain ID, sets once at domain creation time. + * @id: Landlock domain ID, set once at domain creation time. */ u64 id; /** diff --git a/security/landlock/errata/abi-6.h b/security/landlock/errata/abi-6.h index df7bc0e1fdf4..5113a829f87e 100644 --- a/security/landlock/errata/abi-6.h +++ b/security/landlock/errata/abi-6.h @@ -9,7 +9,7 @@ * This fix addresses an issue where signal scoping was overly restrictive, * preventing sandboxed threads from signaling other threads within the same * process if they belonged to different domains. Because threads are not - * security boundaries, user space might assume that any thread within the same + * security boundaries, user space might assume that all threads within the same * process can send signals between themselves (see :manpage:`nptl(7)` and * :manpage:`libpsx(3)`). Consistent with :manpage:`ptrace(2)` behavior, direct * interaction between threads of the same process should always be allowed. diff --git a/security/landlock/fs.c b/security/landlock/fs.c index fe794875ad46..8205673c8b1c 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -939,7 +939,12 @@ jump_up: } path_put(&walker_path); - if (!allowed_parent1) { + /* + * Check CONFIG_AUDIT to enable elision of log_request_parent* and + * associated caller's stack variables thanks to dead code elimination. + */ +#ifdef CONFIG_AUDIT + if (!allowed_parent1 && log_request_parent1) { log_request_parent1->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent1->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent1->audit.u.path = *path; @@ -949,7 +954,7 @@ jump_up: ARRAY_SIZE(*layer_masks_parent1); } - if (!allowed_parent2) { + if (!allowed_parent2 && log_request_parent2) { log_request_parent2->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent2->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent2->audit.u.path = *path; @@ -958,6 +963,8 @@ jump_up: log_request_parent2->layer_masks_size = ARRAY_SIZE(*layer_masks_parent2); } +#endif /* CONFIG_AUDIT */ + return allowed_parent1 && allowed_parent2; } @@ -1314,7 +1321,8 @@ static void hook_sb_delete(struct super_block *const sb) * second call to iput() for the same Landlock object. Also * checks I_NEW because such inode cannot be tied to an object. */ - if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { + if (inode_state_read(inode) & + (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } diff --git a/security/landlock/net.c b/security/landlock/net.c index 1f3915a90a80..e6367e30e5b0 100644 --- a/security/landlock/net.c +++ b/security/landlock/net.c @@ -71,6 +71,61 @@ static int current_check_access_socket(struct socket *const sock, switch (address->sa_family) { case AF_UNSPEC: + if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) { + /* + * Connecting to an address with AF_UNSPEC dissolves + * the TCP association, which have the same effect as + * closing the connection while retaining the socket + * object (i.e., the file descriptor). As for dropping + * privileges, closing connections is always allowed. + * + * For a TCP access control system, this request is + * legitimate. Let the network stack handle potential + * inconsistencies and return -EINVAL if needed. + */ + return 0; + } else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { + /* + * Binding to an AF_UNSPEC address is treated + * differently by IPv4 and IPv6 sockets. The socket's + * family may change under our feet due to + * setsockopt(IPV6_ADDRFORM), but that's ok: we either + * reject entirely or require + * %LANDLOCK_ACCESS_NET_BIND_TCP for the given port, so + * it cannot be used to bypass the policy. + * + * IPv4 sockets map AF_UNSPEC to AF_INET for + * retrocompatibility for bind accesses, only if the + * address is INADDR_ANY (cf. __inet_bind). IPv6 + * sockets always reject it. + * + * Checking the address is required to not wrongfully + * return -EACCES instead of -EAFNOSUPPORT or -EINVAL. + * We could return 0 and let the network stack handle + * these checks, but it is safer to return a proper + * error and test consistency thanks to kselftest. + */ + if (sock->sk->__sk_common.skc_family == AF_INET) { + const struct sockaddr_in *const sockaddr = + (struct sockaddr_in *)address; + + if (addrlen < sizeof(struct sockaddr_in)) + return -EINVAL; + + if (sockaddr->sin_addr.s_addr != + htonl(INADDR_ANY)) + return -EAFNOSUPPORT; + } else { + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + else + return -EAFNOSUPPORT; + } + } else { + WARN_ON_ONCE(1); + } + /* Only for bind(AF_UNSPEC+INADDR_ANY) on IPv4 socket. */ + fallthrough; case AF_INET: { const struct sockaddr_in *addr4; @@ -119,57 +174,18 @@ static int current_check_access_socket(struct socket *const sock, return 0; } - /* Specific AF_UNSPEC handling. */ - if (address->sa_family == AF_UNSPEC) { - /* - * Connecting to an address with AF_UNSPEC dissolves the TCP - * association, which have the same effect as closing the - * connection while retaining the socket object (i.e., the file - * descriptor). As for dropping privileges, closing - * connections is always allowed. - * - * For a TCP access control system, this request is legitimate. - * Let the network stack handle potential inconsistencies and - * return -EINVAL if needed. - */ - if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP) - return 0; - - /* - * For compatibility reason, accept AF_UNSPEC for bind - * accesses (mapped to AF_INET) only if the address is - * INADDR_ANY (cf. __inet_bind). Checking the address is - * required to not wrongfully return -EACCES instead of - * -EAFNOSUPPORT. - * - * We could return 0 and let the network stack handle these - * checks, but it is safer to return a proper error and test - * consistency thanks to kselftest. - */ - if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP) { - /* addrlen has already been checked for AF_UNSPEC. */ - const struct sockaddr_in *const sockaddr = - (struct sockaddr_in *)address; - - if (sock->sk->__sk_common.skc_family != AF_INET) - return -EINVAL; - - if (sockaddr->sin_addr.s_addr != htonl(INADDR_ANY)) - return -EAFNOSUPPORT; - } - } else { - /* - * Checks sa_family consistency to not wrongfully return - * -EACCES instead of -EINVAL. Valid sa_family changes are - * only (from AF_INET or AF_INET6) to AF_UNSPEC. - * - * We could return 0 and let the network stack handle this - * check, but it is safer to return a proper error and test - * consistency thanks to kselftest. - */ - if (address->sa_family != sock->sk->__sk_common.skc_family) - return -EINVAL; - } + /* + * Checks sa_family consistency to not wrongfully return + * -EACCES instead of -EINVAL. Valid sa_family changes are + * only (from AF_INET or AF_INET6) to AF_UNSPEC. + * + * We could return 0 and let the network stack handle this + * check, but it is safer to return a proper error and test + * consistency thanks to kselftest. + */ + if (address->sa_family != sock->sk->__sk_common.skc_family && + address->sa_family != AF_UNSPEC) + return -EINVAL; id.key.data = (__force uintptr_t)port; BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data)); diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c index dfcdc19ea268..0a5b0c76b3f7 100644 --- a/security/landlock/ruleset.c +++ b/security/landlock/ruleset.c @@ -23,7 +23,6 @@ #include <linux/workqueue.h> #include "access.h" -#include "audit.h" #include "domain.h" #include "limits.h" #include "object.h" diff --git a/security/landlock/task.c b/security/landlock/task.c index 2385017418ca..833bc0cfe5c9 100644 --- a/security/landlock/task.c +++ b/security/landlock/task.c @@ -86,7 +86,6 @@ static int hook_ptrace_access_check(struct task_struct *const child, const unsigned int mode) { const struct landlock_cred_security *parent_subject; - const struct landlock_ruleset *child_dom; int err; /* Quick return for non-landlocked tasks. */ @@ -96,7 +95,8 @@ static int hook_ptrace_access_check(struct task_struct *const child, scoped_guard(rcu) { - child_dom = landlock_get_task_domain(child); + const struct landlock_ruleset *const child_dom = + landlock_get_task_domain(child); err = domain_ptrace(parent_subject->domain, child_dom); } @@ -166,15 +166,15 @@ static int hook_ptrace_traceme(struct task_struct *const parent) } /** - * domain_is_scoped - Checks if the client domain is scoped in the same - * domain as the server. + * domain_is_scoped - Check if an interaction from a client/sender to a + * server/receiver should be restricted based on scope controls. * * @client: IPC sender domain. * @server: IPC receiver domain. * @scope: The scope restriction criteria. * - * Returns: True if the @client domain is scoped to access the @server, - * unless the @server is also scoped in the same domain as @client. + * Returns: True if @server is in a different domain from @client, and @client + * is scoped to access @server (i.e. access should be denied). */ static bool domain_is_scoped(const struct landlock_ruleset *const client, const struct landlock_ruleset *const server, diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index a82dd155e1d3..b12df5b5ddfc 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1074,7 +1074,9 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) runtime->oss.params = 0; runtime->oss.prepare = 1; runtime->oss.buffer_used = 0; - snd_pcm_runtime_buffer_set_silence(runtime); + err = snd_pcm_runtime_buffer_set_silence(runtime); + if (err < 0) + goto failure; runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 68bee40c9ada..932a9bf98cbc 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -730,13 +730,18 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) } /* fill the PCM buffer with the current silence format; called from pcm_oss.c */ -void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) +int snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) { - snd_pcm_buffer_access_lock(runtime); + int err; + + err = snd_pcm_buffer_access_lock(runtime); + if (err < 0) + return err; if (runtime->dma_area) snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); snd_pcm_buffer_access_unlock(runtime); + return 0; } EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 61c7372e6307..29469e549791 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6613,6 +6613,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a2e, "HP Envy 16", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -6817,6 +6818,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8f42, "HP ZBook 8 G2a 14W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8f57, "HP Trekker G7JC", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8f62, "HP ZBook 8 G2a 16W", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), + SND_PCI_QUIRK(0x1043, 0x1024, "ASUS Zephyrus G14 2025", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), diff --git a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c index 3cca750857b6..dc35932b6b22 100644 --- a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c +++ b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c @@ -103,6 +103,7 @@ static int cirrus_scodec_test_gpio_probe(struct platform_device *pdev) /* GPIO core modifies our struct gpio_chip so use a copy */ gpio_priv->chip = cirrus_scodec_test_gpio_chip; + gpio_priv->chip.parent = &pdev->dev; ret = devm_gpiochip_add_data(&pdev->dev, &gpio_priv->chip, gpio_priv); if (ret) return dev_err_probe(&pdev->dev, ret, "Failed to add gpiochip\n"); @@ -319,7 +320,7 @@ static struct kunit_case cirrus_scodec_test_cases[] = { }; static struct kunit_suite cirrus_scodec_test_suite = { - .name = "snd-hda-scodec-cs35l56-test", + .name = "snd-hda-cirrus-scodec-test", .init = cirrus_scodec_test_case_init, .test_cases = cirrus_scodec_test_cases, }; diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index f7a7f216d586..624a822341bb 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -2,7 +2,7 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 - 2025 Texas Instruments, Inc. +// Copyright 2023 - 2026 Texas Instruments, Inc. // // Author: Shenghao Ding <shenghao-ding@ti.com> // Current maintainer: Baojun Xu <baojun.xu@ti.com> @@ -60,6 +60,7 @@ struct tas2781_hda_i2c_priv { int (*save_calibration)(struct tas2781_hda *h); int hda_chip_id; + bool skip_calibration; }; static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) @@ -491,7 +492,8 @@ static void tasdevice_dspfw_init(void *context) /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - hda_priv->save_calibration(tas_hda); + if (!hda_priv->skip_calibration) + hda_priv->save_calibration(tas_hda); } static void tasdev_fw_ready(const struct firmware *fmw, void *context) @@ -548,6 +550,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, void *master_data) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv; struct hda_component_parent *parent = master_data; struct hda_component *comp; struct hda_codec *codec; @@ -568,11 +571,22 @@ static int tas2781_hda_bind(struct device *dev, struct device *master, case 0x1028: tas_hda->catlog_id = DELL; break; + case 0x103C: + tas_hda->catlog_id = HP; + break; default: tas_hda->catlog_id = LENOVO; break; } + /* + * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data + * causes audio dropouts during playback, use fallback data + * from DSP firmware as a workaround. + */ + if (codec->core.subsystem_id == 0x10431384) + hda_priv->skip_calibration = true; + pm_runtime_get_sync(dev); comp->dev = dev; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index bf4d9d336561..0294177acc66 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -420,6 +420,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6500RE"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "M6501RM"), } }, diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index 443cf59cb71a..fdf4a9add852 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -23,7 +23,6 @@ #include "tlv320adcx140.h" struct adcx140_priv { - struct snd_soc_component *component; struct regulator *supply_areg; struct gpio_desc *gpio_reset; struct regmap *regmap; @@ -338,7 +337,7 @@ static const struct snd_kcontrol_new adcx140_dapm_ch4_dre_en_switch = SOC_DAPM_SINGLE("Switch", ADCX140_CH4_CFG0, 0, 1, 0); static const struct snd_kcontrol_new adcx140_dapm_dre_en_switch = - SOC_DAPM_SINGLE("Switch", ADCX140_DSP_CFG1, 3, 1, 0); + SOC_DAPM_SINGLE("Switch", ADCX140_DSP_CFG1, 3, 1, 1); /* Output Mixer */ static const struct snd_kcontrol_new adcx140_output_mixer_controls[] = { @@ -699,7 +698,6 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) { int pwr_ctrl = 0; int ret = 0; - struct snd_soc_component *component = adcx140->component; if (power_state) pwr_ctrl = ADCX140_PWR_CFG_ADC_PDZ | ADCX140_PWR_CFG_PLL_PDZ; @@ -711,7 +709,7 @@ static void adcx140_pwr_ctrl(struct adcx140_priv *adcx140, bool power_state) ret = regmap_write(adcx140->regmap, ADCX140_PHASE_CALIB, adcx140->phase_calib_on ? 0x00 : 0x40); if (ret) - dev_err(component->dev, "%s: register write error %d\n", + dev_err(adcx140->dev, "%s: register write error %d\n", __func__, ret); } @@ -727,7 +725,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, struct adcx140_priv *adcx140 = snd_soc_component_get_drvdata(component); u8 data = 0; - switch (params_width(params)) { + switch (params_physical_width(params)) { case 16: data = ADCX140_16_BIT_WORD; break; @@ -742,7 +740,7 @@ static int adcx140_hw_params(struct snd_pcm_substream *substream, break; default: dev_err(component->dev, "%s: Unsupported width %d\n", - __func__, params_width(params)); + __func__, params_physical_width(params)); return -EINVAL; } @@ -1156,6 +1154,9 @@ static int adcx140_i2c_probe(struct i2c_client *i2c) adcx140->gpio_reset = devm_gpiod_get_optional(adcx140->dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(adcx140->gpio_reset)) + return dev_err_probe(&i2c->dev, PTR_ERR(adcx140->gpio_reset), + "Failed to get Reset GPIO\n"); + if (!adcx140->gpio_reset) dev_info(&i2c->dev, "Reset GPIO not defined\n"); adcx140->supply_areg = devm_regulator_get_optional(adcx140->dev, diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index d7aca6567c2d..2fc234adca5f 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -678,6 +678,7 @@ struct wsa881x_priv { */ unsigned int sd_n_val; int active_ports; + bool hw_init; bool port_prepared[WSA881X_MAX_SWR_PORTS]; bool port_enable[WSA881X_MAX_SWR_PORTS]; }; @@ -687,6 +688,9 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) struct regmap *rm = wsa881x->regmap; unsigned int val = 0; + if (wsa881x->hw_init) + return; + regmap_register_patch(wsa881x->regmap, wsa881x_rev_2_0, ARRAY_SIZE(wsa881x_rev_2_0)); @@ -724,6 +728,8 @@ static void wsa881x_init(struct wsa881x_priv *wsa881x) regmap_update_bits(rm, WSA881X_OTP_REG_28, 0x3F, 0x3A); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG1, 0xFF, 0xB2); regmap_update_bits(rm, WSA881X_BONGO_RESRV_REG2, 0xFF, 0x05); + + wsa881x->hw_init = true; } static int wsa881x_component_probe(struct snd_soc_component *comp) @@ -1067,6 +1073,9 @@ static int wsa881x_update_status(struct sdw_slave *slave, { struct wsa881x_priv *wsa881x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa881x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) wsa881x_init(wsa881x); diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index c3046e260cb9..468d2b38a22a 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -475,6 +475,7 @@ struct wsa883x_priv { int active_ports; int dev_mode; int comp_offset; + bool hw_init; /* * Protects temperature reading code (related to speaker protection) and * fields: temperature and pa_on. @@ -1043,6 +1044,9 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) struct regmap *regmap = wsa883x->regmap; int variant, version, ret; + if (wsa883x->hw_init) + return 0; + ret = regmap_read(regmap, WSA883X_OTP_REG_0, &variant); if (ret) return ret; @@ -1054,22 +1058,23 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) switch (variant) { case WSA8830: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8830\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8830\n", + version); break; case WSA8835: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835\n", + version); break; case WSA8832: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8832\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8832\n", + version); break; case WSA8835_V2: - dev_info(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835_V2\n", - version); + dev_dbg(wsa883x->dev, "WSA883X Version 1_%d, Variant: WSA8835_V2\n", + version); break; default: + dev_warn(wsa883x->dev, "unknown variant: %d\n", variant); break; } @@ -1085,6 +1090,8 @@ static int wsa883x_init(struct wsa883x_priv *wsa883x) wsa883x->comp_offset); } + wsa883x->hw_init = true; + return 0; } @@ -1093,6 +1100,9 @@ static int wsa883x_update_status(struct sdw_slave *slave, { struct wsa883x_priv *wsa883x = dev_get_drvdata(&slave->dev); + if (status == SDW_SLAVE_UNATTACHED) + wsa883x->hw_init = false; + if (status == SDW_SLAVE_ATTACHED && slave->dev_num > 0) return wsa883x_init(wsa883x); diff --git a/sound/soc/codecs/wsa884x.c b/sound/soc/codecs/wsa884x.c index 887edd2be705..6c6b497657d0 100644 --- a/sound/soc/codecs/wsa884x.c +++ b/sound/soc/codecs/wsa884x.c @@ -1534,7 +1534,7 @@ static void wsa884x_init(struct wsa884x_priv *wsa884x) wsa884x_set_gain_parameters(wsa884x); - wsa884x->hw_init = false; + wsa884x->hw_init = true; } static int wsa884x_update_status(struct sdw_slave *slave, @@ -2109,7 +2109,6 @@ static int wsa884x_probe(struct sdw_slave *pdev, /* Start in cache-only until device is enumerated */ regcache_cache_only(wsa884x->regmap, true); - wsa884x->hw_init = true; if (IS_REACHABLE(CONFIG_HWMON)) { struct device *hwmon; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 355f7ec8943c..bdc02e85b089 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1179,9 +1179,9 @@ void graph_util_parse_link_direction(struct device_node *np, bool is_playback_only = of_property_read_bool(np, "playback-only"); bool is_capture_only = of_property_read_bool(np, "capture-only"); - if (playback_only) + if (np && playback_only) *playback_only = is_playback_only; - if (capture_only) + if (np && capture_only) *capture_only = is_capture_only; } EXPORT_SYMBOL_GPL(graph_util_parse_link_direction); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 2c1001148d54..8721a098d53f 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -767,6 +767,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { { .callback = sof_sdw_quirk_cb, .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0DD6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_ptlrvp"), }, .driver_data = (void *)(SOC_SDW_PCH_DMIC), diff --git a/sound/soc/sdw_utils/soc_sdw_cs42l43.c b/sound/soc/sdw_utils/soc_sdw_cs42l43.c index 4c954501e500..2685ff4f0932 100644 --- a/sound/soc/sdw_utils/soc_sdw_cs42l43.c +++ b/sound/soc/sdw_utils/soc_sdw_cs42l43.c @@ -44,7 +44,7 @@ static const struct snd_soc_dapm_route cs42l43_dmic_map[] = { static struct snd_soc_jack_pin soc_jack_pins[] = { { .pin = "Headphone", - .mask = SND_JACK_HEADPHONE, + .mask = SND_JACK_HEADPHONE | SND_JACK_LINEOUT, }, { .pin = "Headset Mic", diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index bf382aa07e92..ccf149f949e8 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -841,6 +841,19 @@ struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_part(const u64 adr) } EXPORT_SYMBOL_NS(asoc_sdw_find_codec_info_part, "SND_SOC_SDW_UTILS"); +static struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_sdw_id(const struct sdw_slave_id *id) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(codec_info_list); i++) + if (id->part_id == codec_info_list[i].part_id && + (!codec_info_list[i].version_id || + id->sdw_version == codec_info_list[i].version_id)) + return &codec_info_list[i]; + + return NULL; +} + struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_acpi(const u8 *acpi_id) { int i; @@ -873,22 +886,46 @@ struct asoc_sdw_codec_info *asoc_sdw_find_codec_info_dai(const char *dai_name, i } EXPORT_SYMBOL_NS(asoc_sdw_find_codec_info_dai, "SND_SOC_SDW_UTILS"); +static int asoc_sdw_find_codec_info_dai_index(const struct asoc_sdw_codec_info *codec_info, + const char *dai_name) +{ + int i; + + for (i = 0; i < codec_info->dai_num; i++) { + if (!strcmp(codec_info->dais[i].dai_name, dai_name)) + return i; + } + + return -ENOENT; +} + int asoc_sdw_rtd_init(struct snd_soc_pcm_runtime *rtd) { struct snd_soc_card *card = rtd->card; struct snd_soc_dapm_context *dapm = snd_soc_card_to_dapm(card); struct asoc_sdw_codec_info *codec_info; struct snd_soc_dai *dai; + struct sdw_slave *sdw_peripheral; const char *spk_components=""; int dai_index; int ret; int i; for_each_rtd_codec_dais(rtd, i, dai) { - codec_info = asoc_sdw_find_codec_info_dai(dai->name, &dai_index); + if (is_sdw_slave(dai->component->dev)) + sdw_peripheral = dev_to_sdw_dev(dai->component->dev); + else if (dai->component->dev->parent && is_sdw_slave(dai->component->dev->parent)) + sdw_peripheral = dev_to_sdw_dev(dai->component->dev->parent); + else + continue; + + codec_info = asoc_sdw_find_codec_info_sdw_id(&sdw_peripheral->id); if (!codec_info) return -EINVAL; + dai_index = asoc_sdw_find_codec_info_dai_index(codec_info, dai->name); + WARN_ON(dai_index < 0); + /* * A codec dai can be connected to different dai links for capture and playback, * but we only need to call the rtd_init function once. @@ -898,6 +935,10 @@ int asoc_sdw_rtd_init(struct snd_soc_pcm_runtime *rtd) if (codec_info->dais[dai_index].rtd_init_done) continue; + dev_dbg(card->dev, "%#x/%s initializing for %s/%s\n", + codec_info->part_id, codec_info->dais[dai_index].dai_name, + dai->component->name, dai->name); + /* * Add card controls and dapm widgets for the first codec dai. * The controls and widgets will be used for all codec dais. diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 624e9269fc25..ba42939d5f01 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -543,11 +543,11 @@ int snd_soc_bytes_get(struct snd_kcontrol *kcontrol, ucontrol->value.bytes.data[0] &= ~params->mask; break; case 2: - ((u16 *)(&ucontrol->value.bytes.data))[0] + ((__be16 *)(&ucontrol->value.bytes.data))[0] &= cpu_to_be16(~params->mask); break; case 4: - ((u32 *)(&ucontrol->value.bytes.data))[0] + ((__be32 *)(&ucontrol->value.bytes.data))[0] &= cpu_to_be32(~params->mask); break; default: diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 261d9067d27b..e795907a3963 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -2077,7 +2077,7 @@ static const struct regmap_config tegra210_ahub_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = TEGRA210_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct regmap_config tegra186_ahub_regmap_config = { @@ -2085,7 +2085,7 @@ static const struct regmap_config tegra186_ahub_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = TEGRA186_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct regmap_config tegra264_ahub_regmap_config = { @@ -2094,7 +2094,7 @@ static const struct regmap_config tegra264_ahub_regmap_config = { .reg_stride = 4, .writeable_reg = tegra264_ahub_wr_reg, .max_register = TEGRA264_MAX_REGISTER_ADDR, - .cache_type = REGCACHE_FLAT_S, + .cache_type = REGCACHE_FLAT, }; static const struct tegra_ahub_soc_data soc_data_tegra210 = { diff --git a/sound/soc/ti/davinci-evm.c b/sound/soc/ti/davinci-evm.c index 3848766d96c3..ad514c2e5a25 100644 --- a/sound/soc/ti/davinci-evm.c +++ b/sound/soc/ti/davinci-evm.c @@ -194,27 +194,32 @@ static int davinci_evm_probe(struct platform_device *pdev) return -EINVAL; dai->cpus->of_node = of_parse_phandle(np, "ti,mcasp-controller", 0); - if (!dai->cpus->of_node) - return -EINVAL; + if (!dai->cpus->of_node) { + ret = -EINVAL; + goto err_put; + } dai->platforms->of_node = dai->cpus->of_node; evm_soc_card.dev = &pdev->dev; ret = snd_soc_of_parse_card_name(&evm_soc_card, "ti,model"); if (ret) - return ret; + goto err_put; mclk = devm_clk_get(&pdev->dev, "mclk"); if (PTR_ERR(mclk) == -EPROBE_DEFER) { - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto err_put; } else if (IS_ERR(mclk)) { dev_dbg(&pdev->dev, "mclk not found.\n"); mclk = NULL; } drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; + if (!drvdata) { + ret = -ENOMEM; + goto err_put; + } drvdata->mclk = mclk; @@ -224,7 +229,8 @@ static int davinci_evm_probe(struct platform_device *pdev) if (!drvdata->mclk) { dev_err(&pdev->dev, "No clock or clock rate defined.\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put; } drvdata->sysclk = clk_get_rate(drvdata->mclk); } else if (drvdata->mclk) { @@ -240,8 +246,25 @@ static int davinci_evm_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(&evm_soc_card, drvdata); ret = devm_snd_soc_register_card(&pdev->dev, &evm_soc_card); - if (ret) + if (ret) { dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret); + goto err_put; + } + + return ret; + +err_put: + dai->platforms->of_node = NULL; + + if (dai->cpus->of_node) { + of_node_put(dai->cpus->of_node); + dai->cpus->of_node = NULL; + } + + if (dai->codecs->of_node) { + of_node_put(dai->codecs->of_node); + dai->codecs->of_node = NULL; + } return ret; } diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 54d01dfd820f..263abb36bb2d 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1553,7 +1553,7 @@ static int prepare_playback_urb(struct snd_usb_substream *subs, for (i = 0; i < ctx->packets; i++) { counts = snd_usb_endpoint_next_packet_size(ep, ctx, i, avail); - if (counts < 0) + if (counts < 0 || frames + counts >= ep->max_urb_frames) break; /* set up descriptor */ urb->iso_frame_desc[i].offset = frames * stride; diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index c2f3e8b3f2ac..9b692f368be7 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -41,7 +41,7 @@ clean distclean: rm -rf pyynl.egg-info rm -rf build -install: libynl.a lib/*.h +install: libynl.a lib/*.h ynltool @echo -e "\tINSTALL libynl.a" @$(INSTALL) -d $(DESTDIR)$(libdir) @$(INSTALL) -m 0644 libynl.a $(DESTDIR)$(libdir)/libynl.a @@ -51,6 +51,7 @@ install: libynl.a lib/*.h @echo -e "\tINSTALL pyynl" @pip install --prefix=$(DESTDIR)$(prefix) . @make -C generated install + @make -C ynltool install run_tests: @$(MAKE) -C tests run_tests diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 81b4ecd89100..d9809276db98 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -21,7 +21,7 @@ files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode - params=( $(git grep -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) + params=( $(git grep --no-line-number -B1 -h '/\* YNL-GEN' $f | sed 's@/\*\(.*\)\*/@\1@') ) args=$(sed -n 's@/\* YNL-ARG \(.*\) \*/@\1@p' $f) if [ $f -nt ${params[0]} -a -z "$force" ]; then diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index ad6e1ec706ce..9b4503113ce5 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -72,23 +72,27 @@ HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" # # To support disassembly, objtool needs libopcodes which is provided -# with libbdf (binutils-dev or binutils-devel package). +# with libbfd (binutils-dev or binutils-devel package). # -FEATURE_USER = .objtool -FEATURE_TESTS = libbfd disassembler-init-styled -FEATURE_DISPLAY = -include $(srctree)/tools/build/Makefile.feature +# We check using HOSTCC directly rather than the shared feature framework +# because objtool is a host tool that links against host libraries. +# +HAVE_LIBOPCODES := $(shell echo 'int main(void) { return 0; }' | \ + $(HOSTCC) -xc - -o /dev/null -lopcodes 2>/dev/null && echo y) -ifeq ($(feature-disassembler-init-styled), 1) - OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED -endif +# Styled disassembler support requires binutils >= 2.39 +HAVE_DISASM_STYLED := $(shell echo '$(pound)include <dis-asm.h>' | \ + $(HOSTCC) -E -xc - 2>/dev/null | grep -q disassembler_style && echo y) BUILD_DISAS := n -ifeq ($(feature-libbfd),1) +ifeq ($(HAVE_LIBOPCODES),y) BUILD_DISAS := y - OBJTOOL_CFLAGS += -DDISAS -DPACKAGE="objtool" + OBJTOOL_CFLAGS += -DDISAS -DPACKAGE='"objtool"' OBJTOOL_LDFLAGS += -lopcodes +ifeq ($(HAVE_DISASM_STYLED),y) + OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED +endif endif export BUILD_DISAS diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index 25ff7942b4d5..2b27b54096b8 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -152,8 +152,8 @@ static inline void unindent(int *unused) { indent--; } if (unlikely(insn->sym && insn->sym->pfunc && \ insn->sym->pfunc->debug_checksum)) { \ char *insn_off = offstr(insn->sec, insn->offset); \ - __dbg("checksum: %s %s %016lx", \ - func->name, insn_off, checksum); \ + __dbg("checksum: %s %s %016llx", \ + func->name, insn_off, (unsigned long long)checksum);\ free(insn_off); \ } \ }) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 17c1c36a7bf9..000c89a1e50d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -251,8 +251,11 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); - if (!evsel) - goto out_err; + if (!evsel) { + perf_cpu_map__put(cpus); + perf_cpu_map__put(pmu_cpus); + return NULL; + } if (name) { evsel->name = strdup(name); diff --git a/tools/testing/cxl/test/cxl_translate.c b/tools/testing/cxl/test/cxl_translate.c index 2200ae21795c..16328b2112b2 100644 --- a/tools/testing/cxl/test/cxl_translate.c +++ b/tools/testing/cxl/test/cxl_translate.c @@ -68,6 +68,8 @@ static u64 to_hpa(u64 dpa_offset, int pos, u8 r_eiw, u16 r_eig, u8 hb_ways, /* Calculate base HPA offset from DPA and position */ hpa_offset = cxl_calculate_hpa_offset(dpa_offset, pos, r_eiw, r_eig); + if (hpa_offset == ULLONG_MAX) + return ULLONG_MAX; if (math == XOR_MATH) { cximsd->nr_maps = hbiw_to_nr_maps[hb_ways]; @@ -258,19 +260,23 @@ static int test_random_params(void) pos = get_random_u32() % ways; dpa = get_random_u64() >> 12; + reverse_dpa = ULLONG_MAX; + reverse_pos = -1; + hpa = cxl_calculate_hpa_offset(dpa, pos, eiw, eig); - reverse_dpa = cxl_calculate_dpa_offset(hpa, eiw, eig); - reverse_pos = cxl_calculate_position(hpa, eiw, eig); - - if (reverse_dpa != dpa || reverse_pos != pos) { - pr_err("test random iter %d FAIL hpa=%llu, dpa=%llu reverse_dpa=%llu, pos=%d reverse_pos=%d eiw=%u eig=%u\n", - i, hpa, dpa, reverse_dpa, pos, reverse_pos, eiw, - eig); - - if (failures++ > 10) { - pr_err("test random too many failures, stop\n"); - break; - } + if (hpa != ULLONG_MAX) { + reverse_dpa = cxl_calculate_dpa_offset(hpa, eiw, eig); + reverse_pos = cxl_calculate_position(hpa, eiw, eig); + if (reverse_dpa == dpa && reverse_pos == pos) + continue; + } + + pr_err("test random iter %d FAIL hpa=%llu, dpa=%llu reverse_dpa=%llu, pos=%d reverse_pos=%d eiw=%u eig=%u\n", + i, hpa, dpa, reverse_dpa, pos, reverse_pos, eiw, eig); + + if (failures++ > 10) { + pr_err("test random too many failures, stop\n"); + break; } } pr_info("..... test random: PASS %d FAIL %d\n", i - failures, failures); diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 230b75f6015b..90551650299c 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -237,6 +237,7 @@ struct service_fixture { struct sockaddr_un unix_addr; socklen_t unix_addr_len; }; + struct sockaddr_storage _largest; }; }; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index eee814e09dd7..968a91c927a4 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -4362,22 +4362,24 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) { const char *const path = file1_s1d1; int srv_fd, cli_fd, ruleset_fd; - socklen_t size; - struct sockaddr_un srv_un, cli_un; + struct sockaddr_un srv_un = { + .sun_family = AF_UNIX, + }; + struct sockaddr_un cli_un = { + .sun_family = AF_UNIX, + }; const struct landlock_ruleset_attr attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_IOCTL_DEV, }; /* Sets up a server */ - srv_un.sun_family = AF_UNIX; - strncpy(srv_un.sun_path, path, sizeof(srv_un.sun_path)); - ASSERT_EQ(0, unlink(path)); srv_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, srv_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(srv_un.sun_path); - ASSERT_EQ(0, bind(srv_fd, (struct sockaddr *)&srv_un, size)); + strncpy(srv_un.sun_path, path, sizeof(srv_un.sun_path)); + ASSERT_EQ(0, bind(srv_fd, (struct sockaddr *)&srv_un, sizeof(srv_un))); + ASSERT_EQ(0, listen(srv_fd, 10 /* qlen */)); /* Enables Landlock. */ @@ -4387,24 +4389,18 @@ TEST_F_FORK(layout1, named_unix_domain_socket_ioctl) ASSERT_EQ(0, close(ruleset_fd)); /* Sets up a client connection to it */ - cli_un.sun_family = AF_UNIX; cli_fd = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, cli_fd); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - ASSERT_EQ(0, bind(cli_fd, (struct sockaddr *)&cli_un, size)); - - bzero(&cli_un, sizeof(cli_un)); - cli_un.sun_family = AF_UNIX; strncpy(cli_un.sun_path, path, sizeof(cli_un.sun_path)); - size = offsetof(struct sockaddr_un, sun_path) + strlen(cli_un.sun_path); - - ASSERT_EQ(0, connect(cli_fd, (struct sockaddr *)&cli_un, size)); + ASSERT_EQ(0, + connect(cli_fd, (struct sockaddr *)&cli_un, sizeof(cli_un))); /* FIONREAD and other IOCTLs should not be forbidden. */ EXPECT_EQ(0, test_fionread_ioctl(cli_fd)); - ASSERT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(cli_fd)); + EXPECT_EQ(0, close(srv_fd)); } /* clang-format off */ @@ -7074,8 +7070,8 @@ static int matches_log_fs_extra(struct __test_metadata *const _metadata, return -E2BIG; /* - * It is assume that absolute_path does not contain control characters nor - * spaces, see audit_string_contains_control(). + * It is assumed that absolute_path does not contain control + * characters nor spaces, see audit_string_contains_control(). */ absolute_path = realpath(path, NULL); if (!absolute_path) diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 2a45208551e6..b34b139b3f89 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -121,6 +121,10 @@ static socklen_t get_addrlen(const struct service_fixture *const srv, { switch (srv->protocol.domain) { case AF_UNSPEC: + if (minimal) + return sizeof(sa_family_t); + return sizeof(struct sockaddr_storage); + case AF_INET: return sizeof(srv->ipv4_addr); @@ -758,6 +762,11 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); + /* Tries to bind with too small addrlen. */ + EXPECT_EQ(-EINVAL, bind_variant_addrlen( + bind_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + /* Allowed bind on AF_UNSPEC/INADDR_ANY. */ ret = bind_variant(bind_fd, &self->unspec_any0); if (variant->prot.domain == AF_INET) { @@ -766,6 +775,8 @@ TEST_F(protocol, bind_unspec) TH_LOG("Failed to bind to unspec/any socket: %s", strerror(errno)); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -792,6 +803,8 @@ TEST_F(protocol, bind_unspec) } else { EXPECT_EQ(0, ret); } + } else if (variant->prot.domain == AF_INET6) { + EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret); } @@ -801,7 +814,8 @@ TEST_F(protocol, bind_unspec) bind_fd = socket_variant(&self->srv0); ASSERT_LE(0, bind_fd); ret = bind_variant(bind_fd, &self->unspec_srv0); - if (variant->prot.domain == AF_INET) { + if (variant->prot.domain == AF_INET || + variant->prot.domain == AF_INET6) { EXPECT_EQ(-EAFNOSUPPORT, ret); } else { EXPECT_EQ(-EINVAL, ret) @@ -892,7 +906,19 @@ TEST_F(protocol, connect_unspec) EXPECT_EQ(0, close(ruleset_fd)); } - ret = connect_variant(connect_fd, &self->unspec_any0); + /* Try to re-disconnect with a truncated address struct. */ + EXPECT_EQ(-EINVAL, + connect_variant_addrlen( + connect_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, true) - 1)); + + /* + * Re-disconnect, with a minimal sockaddr struct (just a + * bare af_family=AF_UNSPEC field). + */ + ret = connect_variant_addrlen(connect_fd, &self->unspec_any0, + get_addrlen(&self->unspec_any0, + true)); if (self->srv0.protocol.domain == AF_UNIX && self->srv0.protocol.type == SOCK_STREAM) { EXPECT_EQ(-EINVAL, ret); diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index 4e356334ecb7..4f64c90583cd 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -86,16 +86,9 @@ static int get_yama_ptrace_scope(void) } /* clang-format off */ -FIXTURE(hierarchy) {}; +FIXTURE(scoped_domains) {}; /* clang-format on */ -FIXTURE_VARIANT(hierarchy) -{ - const bool domain_both; - const bool domain_parent; - const bool domain_child; -}; - /* * Test multiple tracing combinations between a parent process P1 and a child * process P2. @@ -104,155 +97,18 @@ FIXTURE_VARIANT(hierarchy) * restriction is enforced in addition to any Landlock check, which means that * all P2 requests to trace P1 would be denied. */ +#include "scoped_base_variants.h" -/* - * No domain - * - * P1-. P1 -> P2 : allow - * \ P2 -> P1 : allow - * 'P2 - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = false, - .domain_child = false, -}; - -/* - * Child domain - * - * P1--. P1 -> P2 : allow - * \ P2 -> P1 : deny - * .'-----. - * | P2 | - * '------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = false, - .domain_child = true, -}; - -/* - * Parent domain - * .------. - * | P1 --. P1 -> P2 : deny - * '------' \ P2 -> P1 : allow - * ' - * P2 - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = true, - .domain_child = false, -}; - -/* - * Parent + child domain (siblings) - * .------. - * | P1 ---. P1 -> P2 : deny - * '------' \ P2 -> P1 : deny - * .---'--. - * | P2 | - * '------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) { - /* clang-format on */ - .domain_both = false, - .domain_parent = true, - .domain_child = true, -}; - -/* - * Same domain (inherited) - * .-------------. - * | P1----. | P1 -> P2 : allow - * | \ | P2 -> P1 : allow - * | ' | - * | P2 | - * '-------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = false, - .domain_child = false, -}; - -/* - * Inherited + child domain - * .-----------------. - * | P1----. | P1 -> P2 : allow - * | \ | P2 -> P1 : deny - * | .-'----. | - * | | P2 | | - * | '------' | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = false, - .domain_child = true, -}; - -/* - * Inherited + parent domain - * .-----------------. - * |.------. | P1 -> P2 : deny - * || P1 ----. | P2 -> P1 : allow - * |'------' \ | - * | ' | - * | P2 | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = true, - .domain_child = false, -}; - -/* - * Inherited + parent and child domain (siblings) - * .-----------------. - * | .------. | P1 -> P2 : deny - * | | P1 . | P2 -> P1 : deny - * | '------'\ | - * | \ | - * | .--'---. | - * | | P2 | | - * | '------' | - * '-----------------' - */ -/* clang-format off */ -FIXTURE_VARIANT_ADD(hierarchy, deny_with_forked_domain) { - /* clang-format on */ - .domain_both = true, - .domain_parent = true, - .domain_child = true, -}; - -FIXTURE_SETUP(hierarchy) +FIXTURE_SETUP(scoped_domains) { } -FIXTURE_TEARDOWN(hierarchy) +FIXTURE_TEARDOWN(scoped_domains) { } /* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */ -TEST_F(hierarchy, trace) +TEST_F(scoped_domains, trace) { pid_t child, parent; int status, err_proc_read; diff --git a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c index 6825082c079c..72f97648d4a7 100644 --- a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c +++ b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c @@ -543,7 +543,7 @@ TEST_F(scoped_vs_unscoped, unix_scoping) ASSERT_EQ(1, write(pipe_child[1], ".", 1)); ASSERT_EQ(grand_child, waitpid(grand_child, &status, 0)); - EXPECT_EQ(0, close(stream_server_child)) + EXPECT_EQ(0, close(stream_server_child)); EXPECT_EQ(0, close(dgram_server_child)); return; } @@ -779,7 +779,6 @@ FIXTURE_TEARDOWN(various_address_sockets) TEST_F(various_address_sockets, scoped_pathname_sockets) { - socklen_t size_stream, size_dgram; pid_t child; int status; char buf_child, buf_parent; @@ -798,12 +797,8 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) /* Pathname address. */ snprintf(stream_pathname_addr.sun_path, sizeof(stream_pathname_addr.sun_path), "%s", stream_path); - size_stream = offsetof(struct sockaddr_un, sun_path) + - strlen(stream_pathname_addr.sun_path); snprintf(dgram_pathname_addr.sun_path, sizeof(dgram_pathname_addr.sun_path), "%s", dgram_path); - size_dgram = offsetof(struct sockaddr_un, sun_path) + - strlen(dgram_pathname_addr.sun_path); /* Abstract address. */ memset(&stream_abstract_addr, 0, sizeof(stream_abstract_addr)); @@ -841,8 +836,9 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) /* Connects with pathname sockets. */ stream_pathname_socket = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, stream_pathname_socket); - ASSERT_EQ(0, connect(stream_pathname_socket, - &stream_pathname_addr, size_stream)); + ASSERT_EQ(0, + connect(stream_pathname_socket, &stream_pathname_addr, + sizeof(stream_pathname_addr))); ASSERT_EQ(1, write(stream_pathname_socket, "b", 1)); EXPECT_EQ(0, close(stream_pathname_socket)); @@ -850,12 +846,13 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) dgram_pathname_socket = socket(AF_UNIX, SOCK_DGRAM, 0); ASSERT_LE(0, dgram_pathname_socket); err = sendto(dgram_pathname_socket, "c", 1, 0, - &dgram_pathname_addr, size_dgram); + &dgram_pathname_addr, sizeof(dgram_pathname_addr)); EXPECT_EQ(1, err); /* Sends with connection. */ - ASSERT_EQ(0, connect(dgram_pathname_socket, - &dgram_pathname_addr, size_dgram)); + ASSERT_EQ(0, + connect(dgram_pathname_socket, &dgram_pathname_addr, + sizeof(dgram_pathname_addr))); ASSERT_EQ(1, write(dgram_pathname_socket, "d", 1)); EXPECT_EQ(0, close(dgram_pathname_socket)); @@ -910,13 +907,13 @@ TEST_F(various_address_sockets, scoped_pathname_sockets) stream_pathname_socket = socket(AF_UNIX, SOCK_STREAM, 0); ASSERT_LE(0, stream_pathname_socket); ASSERT_EQ(0, bind(stream_pathname_socket, &stream_pathname_addr, - size_stream)); + sizeof(stream_pathname_addr))); ASSERT_EQ(0, listen(stream_pathname_socket, backlog)); dgram_pathname_socket = socket(AF_UNIX, SOCK_DGRAM, 0); ASSERT_LE(0, dgram_pathname_socket); ASSERT_EQ(0, bind(dgram_pathname_socket, &dgram_pathname_addr, - size_dgram)); + sizeof(dgram_pathname_addr))); /* Sets up abstract servers. */ stream_abstract_socket = socket(AF_UNIX, SOCK_STREAM, 0); diff --git a/tools/testing/selftests/landlock/scoped_base_variants.h b/tools/testing/selftests/landlock/scoped_base_variants.h index d3b1fa8a584e..7116728ebc68 100644 --- a/tools/testing/selftests/landlock/scoped_base_variants.h +++ b/tools/testing/selftests/landlock/scoped_base_variants.h @@ -1,8 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Landlock scoped_domains variants + * Landlock scoped_domains test variant definition. * - * See the hierarchy variants from ptrace_test.c + * This file defines a fixture variant "scoped_domains" that has all + * permutations of parent/child process being in separate or shared + * Landlock domain, or not being in a Landlock domain at all. + * + * Scoped access tests can include this file to avoid repeating these + * combinations. * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2019-2020 ANSSI diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 6279893a0adc..f61150d28eb2 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -179,7 +179,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared) if (rw && shared && fs_is_unknown(fs_type)) { ksft_print_msg("Unknown filesystem\n"); result = KSFT_SKIP; - return; + break; } /* * R/O pinning or pinning in a private mapping is always diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index 363c1033cc7d..10b686102b79 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -22,12 +22,37 @@ FIXTURE(merge) struct procmap_fd procmap; }; +static char *map_carveout(unsigned int page_size) +{ + return mmap(NULL, 30 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); +} + +static pid_t do_fork(struct procmap_fd *procmap) +{ + pid_t pid = fork(); + + if (pid == -1) + return -1; + if (pid != 0) { + wait(NULL); + return pid; + } + + /* Reopen for child. */ + if (close_procmap(procmap)) + return -1; + if (open_self_procmap(procmap)) + return -1; + + return 0; +} + FIXTURE_SETUP(merge) { self->page_size = psize(); /* Carve out PROT_NONE region to map over. */ - self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, - MAP_ANON | MAP_PRIVATE, -1, 0); + self->carveout = map_carveout(self->page_size); ASSERT_NE(self->carveout, MAP_FAILED); /* Setup PROCMAP_QUERY interface. */ ASSERT_EQ(open_self_procmap(&self->procmap), 0); @@ -36,7 +61,8 @@ FIXTURE_SETUP(merge) FIXTURE_TEARDOWN(merge) { ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); - ASSERT_EQ(close_procmap(&self->procmap), 0); + /* May fail for parent of forked process. */ + close_procmap(&self->procmap); /* * Clear unconditionally, as some tests set this. It is no issue if this * fails (KSM may be disabled for instance). @@ -44,6 +70,44 @@ FIXTURE_TEARDOWN(merge) prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); } +FIXTURE(merge_with_fork) +{ + unsigned int page_size; + char *carveout; + struct procmap_fd procmap; +}; + +FIXTURE_VARIANT(merge_with_fork) +{ + bool forked; +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, forked) +{ + .forked = true, +}; + +FIXTURE_VARIANT_ADD(merge_with_fork, unforked) +{ + .forked = false, +}; + +FIXTURE_SETUP(merge_with_fork) +{ + self->page_size = psize(); + self->carveout = map_carveout(self->page_size); + ASSERT_NE(self->carveout, MAP_FAILED); + ASSERT_EQ(open_self_procmap(&self->procmap), 0); +} + +FIXTURE_TEARDOWN(merge_with_fork) +{ + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); + ASSERT_EQ(close_procmap(&self->procmap), 0); + /* See above. */ + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); +} + TEST_F(merge, mprotect_unfaulted_left) { unsigned int page_size = self->page_size; @@ -322,8 +386,8 @@ TEST_F(merge, forked_target_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -344,19 +408,10 @@ TEST_F(merge, forked_target_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -386,8 +441,8 @@ TEST_F(merge, forked_source_vma) unsigned int page_size = self->page_size; char *carveout = self->carveout; struct procmap_fd *procmap = &self->procmap; - pid_t pid; char *ptr, *ptr2; + pid_t pid; int i; /* @@ -408,19 +463,10 @@ TEST_F(merge, forked_source_vma) */ ptr[0] = 'x'; - pid = fork(); + pid = do_fork(&self->procmap); ASSERT_NE(pid, -1); - - if (pid != 0) { - wait(NULL); + if (pid != 0) return; - } - - /* Child process below: */ - - /* Reopen for child. */ - ASSERT_EQ(close_procmap(&self->procmap), 0); - ASSERT_EQ(open_self_procmap(&self->procmap), 0); /* unCOWing everything does not cause the AVC to go away. */ for (i = 0; i < 5 * page_size; i += page_size) @@ -1171,4 +1217,288 @@ TEST_F(merge, mremap_correct_placed_faulted) ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); } +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |------------| + * | \ | + * |-----------| | / |---------| + * | unfaulted | v \ | faulted | + * |-----------| / |---------| + * B \ A + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b; + + /* + * mremap() such that A and B merge: + * + * |---------------------------| + * | \ | + * | |-----------| / |---------| + * v | unfaulted | \ | faulted | + * |-----------| / |---------| + * B \ A + * + * Then unmap VMA A to trigger the bug. + */ + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + /* Fault it in. */ + ptr_a[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMA B in position, + * unfaulted. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* + * Now move VMA A into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_a = mremap(ptr_a, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size]); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 6 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_unfaulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + unsigned long offset; + char *ptr_a, *ptr_b, *ptr_c; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | unfaulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* Map VMA B into place. */ + ptr_b = mmap(&self->carveout[page_size + 3 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_b, MAP_FAILED); + /* Fault it in. */ + ptr_b[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move it out of the way so we can place VMAs A, C in position, + * unfaulted. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* Map VMA C into place. */ + ptr_c = mmap(&self->carveout[page_size + 3 * page_size + 3 * page_size], + 3 * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_c, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged, if not forked. */ + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + offset = variant->forked ? 3 * page_size : 9 * page_size; + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + offset); + + /* If forked, B and C should also not have merged. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 3 * page_size); + } +} + +TEST_F(merge_with_fork, mremap_faulted_to_unfaulted_prev_faulted_next) +{ + struct procmap_fd *procmap = &self->procmap; + unsigned int page_size = self->page_size; + char *ptr_a, *ptr_b, *ptr_bc; + + /* + * mremap() with MREMAP_DONTUNMAP such that A, B and C merge: + * + * |---------------------------| + * | \ | + * |-----------| | |-----------| / |---------| + * | unfaulted | v | faulted | \ | faulted | + * |-----------| |-----------| / |---------| + * A C \ B + */ + + /* + * Map VMA B and C into place. We have to map them together so their + * anon_vma is the same and the vma->vm_pgoff's are correctly aligned. + */ + ptr_bc = mmap(&self->carveout[page_size + 3 * page_size], + 3 * page_size + 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_bc, MAP_FAILED); + + /* Fault it in. */ + ptr_bc[0] = 'x'; + + if (variant->forked) { + pid_t pid = do_fork(&self->procmap); + + ASSERT_NE(pid, -1); + if (pid != 0) + return; + } + + /* + * Now move VMA B out the way (splitting VMA BC) so we can place VMA A + * in position, unfaulted, and leave the remainder of the VMA we just + * moved in place, faulted, as VMA C. + */ + ptr_b = mremap(ptr_bc, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE, &self->carveout[20 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* Map VMA A into place. */ + ptr_a = mmap(&self->carveout[page_size], 3 * page_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0); + ASSERT_NE(ptr_a, MAP_FAILED); + + /* + * Now move VMA B into position with MREMAP_DONTUNMAP to catch incorrect + * anon_vma propagation. + */ + ptr_b = mremap(ptr_b, 3 * page_size, 3 * page_size, + MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + &self->carveout[page_size + 3 * page_size]); + ASSERT_NE(ptr_b, MAP_FAILED); + + /* The VMAs should have merged. A,B,C if unforked, B, C if forked. */ + if (variant->forked) { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_b)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_b); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_b + 6 * page_size); + } else { + ASSERT_TRUE(find_vma_procmap(procmap, ptr_a)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr_a); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr_a + 9 * page_size); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index fe7937dc5f45..ce9699092f50 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -48,6 +48,7 @@ TEST_PROGS := \ ipv6_flowlabel.sh \ ipv6_force_forwarding.sh \ ipv6_route_update_soft_lockup.sh \ + ipvtap_test.sh \ l2_tos_ttl_inherit.sh \ l2tp.sh \ link_netns.py \ diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 3ef209cacb8e..663744305e52 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -73,6 +73,8 @@ # +------------------------+ #============================================================================== +source lib.sh + readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) @@ -246,14 +248,15 @@ test_ipv6_forward() send_mcast4() { - sleep 2 + sleep 5 + wait_local_port_listen ${LISTENER} 4000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' & } send_mcast6() { - sleep 2 + wait_local_port_listen ${LISTENER} 6000 udp ip netns exec "${SOURCE}" bash -c \ 'printf "%s %128s" 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' & } diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 1e1f253118f5..b84362b9b508 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,6 +48,7 @@ CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SIT=y CONFIG_IPV6_VTI=y CONFIG_IPVLAN=m +CONFIG_IPVTAP=m CONFIG_KALLSYMS=y CONFIG_L2TP=m CONFIG_L2TP_ETH=m @@ -116,6 +117,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_PSAMPLE=m CONFIG_RPS=y CONFIG_SYSFS=y +CONFIG_TAP=m CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_TEST_BPF=m diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh index b5773ac8847d..e0d45292a298 100755 --- a/tools/testing/selftests/net/fib-onlink-tests.sh +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -121,7 +121,7 @@ log_subsection() run_cmd() { - local cmd="$*" + local cmd="$1" local out local rc @@ -146,7 +146,7 @@ get_linklocal() local pfx local addr - addr=$(${pfx} ip -6 -br addr show dev ${dev} | \ + addr=$(${pfx} ${IP} -6 -br addr show dev ${dev} | \ awk '{ for (i = 3; i <= NF; ++i) { if ($i ~ /^fe80/) @@ -174,58 +174,48 @@ setup() set -e - # create namespace - setup_ns PEER_NS + # create namespaces + setup_ns ns1 + IP="ip -netns $ns1" + setup_ns ns2 # add vrf table - ip li add ${VRF} type vrf table ${VRF_TABLE} - ip li set ${VRF} up - ip ro add table ${VRF_TABLE} unreachable default metric 8192 - ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} li add ${VRF} type vrf table ${VRF_TABLE} + ${IP} li set ${VRF} up + ${IP} ro add table ${VRF_TABLE} unreachable default metric 8192 + ${IP} -6 ro add table ${VRF_TABLE} unreachable default metric 8192 # create test interfaces - ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} - ip li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} - ip li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} - ip li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} + ${IP} li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} + ${IP} li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} + ${IP} li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} + ${IP} li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} # enslave vrf interfaces for n in 5 7; do - ip li set ${NETIFS[p${n}]} vrf ${VRF} + ${IP} li set ${NETIFS[p${n}]} vrf ${VRF} done # add addresses for n in 1 3 5 7; do - ip li set ${NETIFS[p${n}]} up - ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} up + ${IP} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ${IP} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done # move peer interfaces to namespace and add addresses for n in 2 4 6 8; do - ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up - ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} - ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad + ${IP} li set ${NETIFS[p${n}]} netns ${ns2} up + ip -netns $ns2 addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip -netns $ns2 addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad done - ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} - ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} + ${IP} -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64} + ${IP} -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64} set +e } -cleanup() -{ - # make sure we start from a clean slate - cleanup_ns ${PEER_NS} 2>/dev/null - for n in 1 3 5 7; do - ip link del ${NETIFS[p${n}]} 2>/dev/null - done - ip link del ${VRF} 2>/dev/null - ip ro flush table ${VRF_TABLE} - ip -6 ro flush table ${VRF_TABLE} -} - ################################################################################ # IPv4 tests # @@ -242,7 +232,7 @@ run_ip() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 via "${gw}" "${dev}" onlink + run_cmd "${IP} ro add table ${table} ${prefix}/32 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -258,8 +248,8 @@ run_ip_mpath() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip ro add table "${table}" "${prefix}"/32 \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} ro add table ${table} ${prefix}/32 \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -342,7 +332,7 @@ run_ip6() # dev arg may be empty [ -n "${dev}" ] && dev="dev ${dev}" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 via "${gw}" "${dev}" onlink + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 via ${gw} ${dev} onlink" log_test $? ${exp_rc} "${desc}" } @@ -356,8 +346,8 @@ run_ip6_mpath() local exp_rc="$6" local desc="$7" - run_cmd ip -6 ro add table "${table}" "${prefix}"/128 "${opts}" \ - nexthop via ${nh1} nexthop via ${nh2} + run_cmd "${IP} -6 ro add table ${table} ${prefix}/128 ${opts} \ + nexthop via ${nh1} nexthop via ${nh2}" log_test $? ${exp_rc} "${desc}" } @@ -491,10 +481,9 @@ do esac done -cleanup setup run_onlink_tests -cleanup +cleanup_ns ${ns1} ${ns2} if [ "$TESTS" != "none" ]; then printf "\nTests passed: %3d\n" ${nsuccess} diff --git a/tools/testing/selftests/net/ipvtap_test.sh b/tools/testing/selftests/net/ipvtap_test.sh new file mode 100755 index 000000000000..354ca7ce8584 --- /dev/null +++ b/tools/testing/selftests/net/ipvtap_test.sh @@ -0,0 +1,168 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Simple tests for ipvtap + + +# +# The testing environment looks this way: +# +# |------HNS-------| |------PHY-------| +# | veth<----------------->veth | +# |------|--|------| |----------------| +# | | +# | | |-----TST0-------| +# | |------------|----ipvlan | +# | |----------------| +# | +# | |-----TST1-------| +# |---------------|----ipvlan | +# |----------------| +# + +ALL_TESTS=" + test_ip_set +" + +source lib.sh + +DEBUG=0 + +VETH_HOST=vethtst.h +VETH_PHY=vethtst.p + +NS_COUNT=32 +IP_ITERATIONS=1024 +IPSET_TIMEOUT="60s" + +ns_run() { + ns=$1 + shift + if [[ "$ns" == "global" ]]; then + "$@" >/dev/null + else + ip netns exec "$ns" "$@" >/dev/null + fi +} + +test_ip_setup_env() { + setup_ns NS_PHY + setup_ns HST_NS + + # setup simulated other-host (phy) and host itself + ns_run "$HST_NS" ip link add $VETH_HOST type veth peer name $VETH_PHY \ + netns "$NS_PHY" >/dev/null + ns_run "$HST_NS" ip link set $VETH_HOST up + ns_run "$NS_PHY" ip link set $VETH_PHY up + + for ((i=0; i<NS_COUNT; i++)); do + setup_ns ipvlan_ns_$i + ns="ipvlan_ns_$i" + if [ "$DEBUG" = "1" ]; then + echo "created NS ${!ns}" + fi + if ! ns_run "$HST_NS" ip link add netns ${!ns} ipvlan0 \ + link $VETH_HOST \ + type ipvtap mode l2 bridge; then + exit_error "FAIL: Failed to configure ipvlan link." + fi + done +} + +test_ip_cleanup_env() { + ns_run "$HST_NS" ip link del $VETH_HOST + cleanup_all_ns +} + +exit_error() { + echo "$1" + exit $ksft_fail +} + +rnd() { + echo $(( RANDOM % 32 + 16 )) +} + +test_ip_set_thread() { + # Here we are trying to create some IP conflicts between namespaces. + # If just add/remove IP, nothing interesting will happen. + # But if add random IP and then remove random IP, + # eventually conflicts start to apear. + ip link set ipvlan0 up + for ((i=0; i<IP_ITERATIONS; i++)); do + v=$(rnd) + ip a a "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a a "fc00::$v/64" dev ipvlan0 2>/dev/null + v=$(rnd) + ip a d "172.25.0.$v/24" dev ipvlan0 2>/dev/null + ip a d "fc00::$v/64" dev ipvlan0 2>/dev/null + done +} + +test_ip_set() { + RET=0 + + trap test_ip_cleanup_env EXIT + + test_ip_setup_env + + declare -A ns_pids + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ns_run ${!ns} timeout "$IPSET_TIMEOUT" \ + bash -c "$0 test_ip_set_thread"& + ns_pids[$i]=$! + done + + for ((i=0; i<NS_COUNT; i++)); do + wait "${ns_pids[$i]}" + done + + declare -A all_ips + for ((i=0; i<NS_COUNT; i++)); do + ns="ipvlan_ns_$i" + ip_output=$(ip netns exec ${!ns} ip a l dev ipvlan0 | grep inet) + while IFS= read -r nsip_out; do + if [[ -z $nsip_out ]]; then + continue; + fi + nsip=$(awk '{print $2}' <<< "$nsip_out") + if [[ -v all_ips[$nsip] ]]; then + RET=$ksft_fail + log_test "conflict for $nsip" + return "$RET" + else + all_ips[$nsip]=$i + fi + done <<< "$ip_output" + done + + if [ "$DEBUG" = "1" ]; then + for key in "${!all_ips[@]}"; do + echo "$key: ${all_ips[$key]}" + done + fi + + trap - EXIT + test_ip_cleanup_env + + log_test "test multithreaded ip set" +} + +if [[ "$1" == "-d" ]]; then + DEBUG=1 + shift +fi + +if [[ "$1" == "-t" ]]; then + shift + TESTS="$*" +fi + +if [[ "$1" == "test_ip_set_thread" ]]; then + test_ip_set_thread +else + require_command ip + + tests_run +fi diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json index e5cc31f265f8..0179c57104ad 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/teql.json @@ -81,5 +81,30 @@ "$TC qdisc del dev $DUMMY handle 1: root", "$IP link del dev $DUMMY" ] + }, + { + "id": "124e", + "name": "Try to add teql as a child qdisc", + "category": [ + "qdisc", + "ets", + "tbf" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: qfq", + "$TC class add dev $DUMMY parent 1: classid 1:1 qfq weight 15 maxpkt 16384" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1:1 handle 2:1 teql0", + "expExitCode": "2", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:1", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1:" + ] } ] diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 83148875a12c..434065215d12 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -36,6 +36,7 @@ BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall $(KHDR_INCLUDES) +CFLAGS += -I $(top_srcdir)/tools/testing/selftests/ # call32_from_64 in thunks.S uses absolute addresses. ifeq ($(CAN_BUILD_WITH_NOPIE),1) diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index 142c02a6834a..bf633cde82b0 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -25,7 +25,7 @@ enum transport { }; static const char * const transport_ksyms[] = { - #define x(name, symbol) "d " symbol "_transport", + #define x(name, symbol) " " symbol "_transport", KNOWN_TRANSPORTS(x) #undef x }; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index bbe3723babdc..5bd20ccd9335 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -347,10 +347,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) } #define SOCK_BUF_SIZE (2 * 1024 * 1024) +#define SOCK_BUF_SIZE_SMALL (64 * 1024) #define MAX_MSG_PAGES 4 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { + unsigned long long sock_buf_size; unsigned long curr_hash; size_t max_msg_size; int page_size; @@ -363,6 +365,16 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + /* Wait, until receiver sets buffer size. */ control_expectln("SRVREADY"); @@ -2219,6 +2231,101 @@ static void test_stream_accepted_setsockopt_server(const struct test_opts *opts) close(fd); } +static void test_stream_tx_credit_bounds_client(const struct test_opts *opts) +{ + unsigned long long sock_buf_size; + size_t total = 0; + char buf[4096]; + int fd; + + memset(buf, 'A', sizeof(buf)); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + sock_buf_size = SOCK_BUF_SIZE_SMALL; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + + if (fcntl(fd, F_SETFL, fcntl(fd, F_GETFL, 0) | O_NONBLOCK) < 0) { + perror("fcntl(F_SETFL)"); + exit(EXIT_FAILURE); + } + + control_expectln("SRVREADY"); + + for (;;) { + ssize_t sent = send(fd, buf, sizeof(buf), 0); + + if (sent == 0) { + fprintf(stderr, "unexpected EOF while sending bytes\n"); + exit(EXIT_FAILURE); + } + + if (sent < 0) { + if (errno == EINTR) + continue; + + if (errno == EAGAIN || errno == EWOULDBLOCK) + break; + + perror("send"); + exit(EXIT_FAILURE); + } + + total += sent; + } + + control_writeln("CLIDONE"); + close(fd); + + /* We should not be able to send more bytes than the value set as + * local buffer size. + */ + if (total > sock_buf_size) { + fprintf(stderr, + "TX credit too large: queued %zu bytes (expected <= %llu)\n", + total, sock_buf_size); + exit(EXIT_FAILURE); + } +} + +static void test_stream_tx_credit_bounds_server(const struct test_opts *opts) +{ + unsigned long long sock_buf_size; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + sock_buf_size = SOCK_BUF_SIZE; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); + + control_writeln("SRVREADY"); + control_expectln("CLIDONE"); + + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -2403,6 +2510,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_accepted_setsockopt_client, .run_server = test_stream_accepted_setsockopt_server, }, + { + .name = "SOCK_STREAM virtio MSG_ZEROCOPY coalescence corruption", + .run_client = test_stream_msgzcopy_mangle_client, + .run_server = test_stream_msgzcopy_mangle_server, + }, + { + .name = "SOCK_STREAM TX credit bounds", + .run_client = test_stream_tx_credit_bounds_client, + .run_server = test_stream_tx_credit_bounds_server, + }, {}, }; diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c index 9d9a6cb9614a..a31ddfc1cd0c 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.c +++ b/tools/testing/vsock/vsock_test_zerocopy.c @@ -9,14 +9,18 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <unistd.h> #include <poll.h> #include <linux/errqueue.h> #include <linux/kernel.h> +#include <linux/sockios.h> +#include <linux/time64.h> #include <errno.h> #include "control.h" +#include "timeout.h" #include "vsock_test_zerocopy.h" #include "msg_zerocopy_common.h" @@ -356,3 +360,73 @@ void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts) control_expectln("DONE"); close(fd); } + +#define GOOD_COPY_LEN 128 /* net/vmw_vsock/virtio_transport_common.c */ + +void test_stream_msgzcopy_mangle_client(const struct test_opts *opts) +{ + char sbuf1[PAGE_SIZE + 1], sbuf2[GOOD_COPY_LEN]; + unsigned long hash; + struct pollfd fds; + int fd, i; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + + memset(sbuf1, 'x', sizeof(sbuf1)); + send_buf(fd, sbuf1, sizeof(sbuf1), 0, sizeof(sbuf1)); + + for (i = 0; i < sizeof(sbuf2); i++) + sbuf2[i] = rand() & 0xff; + + send_buf(fd, sbuf2, sizeof(sbuf2), MSG_ZEROCOPY, sizeof(sbuf2)); + + hash = hash_djb2(sbuf2, sizeof(sbuf2)); + control_writeulong(hash); + + fds.fd = fd; + fds.events = 0; + + if (poll(&fds, 1, TIMEOUT * MSEC_PER_SEC) != 1 || + !(fds.revents & POLLERR)) { + perror("poll"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +void test_stream_msgzcopy_mangle_server(const struct test_opts *opts) +{ + unsigned long local_hash, remote_hash; + char rbuf[PAGE_SIZE + 1]; + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Wait, don't race the (buggy) skbs coalescence. */ + vsock_ioctl_int(fd, SIOCINQ, PAGE_SIZE + 1 + GOOD_COPY_LEN); + + /* Discard the first packet. */ + recv_buf(fd, rbuf, PAGE_SIZE + 1, 0, PAGE_SIZE + 1); + + recv_buf(fd, rbuf, GOOD_COPY_LEN, 0, GOOD_COPY_LEN); + remote_hash = control_readulong(); + local_hash = hash_djb2(rbuf, GOOD_COPY_LEN); + + if (local_hash != remote_hash) { + fprintf(stderr, "Data received corrupted\n"); + exit(EXIT_FAILURE); + } + + close(fd); +} diff --git a/tools/testing/vsock/vsock_test_zerocopy.h b/tools/testing/vsock/vsock_test_zerocopy.h index 3ef2579e024d..d46c91a69f16 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.h +++ b/tools/testing/vsock/vsock_test_zerocopy.h @@ -12,4 +12,7 @@ void test_seqpacket_msgzcopy_server(const struct test_opts *opts); void test_stream_msgzcopy_empty_errq_client(const struct test_opts *opts); void test_stream_msgzcopy_empty_errq_server(const struct test_opts *opts); +void test_stream_msgzcopy_mangle_client(const struct test_opts *opts); +void test_stream_msgzcopy_mangle_server(const struct test_opts *opts); + #endif /* VSOCK_TEST_ZEROCOPY_H */ |