diff options
550 files changed, 5537 insertions, 3311 deletions
@@ -377,6 +377,7 @@ Matthew Wilcox <willy@infradead.org> <willy@debian.org> Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com> Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org> Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu> +Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net> Matthieu CASTET <castet.matthieu@free.fr> Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com> Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting> diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 5f502bf68fbc..ff456871bf4b 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -92,6 +92,13 @@ Brief summary of control files. memory.oom_control set/show oom controls. memory.numa_stat show the number of memory usage per numa node + memory.kmem.limit_in_bytes Deprecated knob to set and read the kernel + memory hard limit. Kernel hard limit is not + supported since 5.16. Writing any value to + do file will not have any effect same as if + nokmem kernel parameter was specified. + Kernel memory is still charged and reported + by memory.kmem.usage_in_bytes. memory.kmem.usage_in_bytes show current kernel memory allocation memory.kmem.failcnt show the number of kernel memory usage hits limits diff --git a/Documentation/arch/arm64/cpu-feature-registers.rst b/Documentation/arch/arm64/cpu-feature-registers.rst index 4e4625f2455f..de6d8a4790e2 100644 --- a/Documentation/arch/arm64/cpu-feature-registers.rst +++ b/Documentation/arch/arm64/cpu-feature-registers.rst @@ -175,6 +175,8 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | SME | [27-24] | y | + +------------------------------+---------+---------+ | MTE | [11-8] | y | +------------------------------+---------+---------+ | SSBS | [7-4] | y | @@ -288,8 +290,18 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | CSSC | [55-52] | y | + +------------------------------+---------+---------+ + | RPRFM | [51-48] | y | + +------------------------------+---------+---------+ + | BC | [23-20] | y | + +------------------------------+---------+---------+ | MOPS | [19-16] | y | +------------------------------+---------+---------+ + | APA3 | [15-12] | y | + +------------------------------+---------+---------+ + | GPA3 | [11-8] | y | + +------------------------------+---------+---------+ | RPRES | [7-4] | y | +------------------------------+---------+---------+ | WFXT | [3-0] | y | diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 8c8addb4194c..76ff9d7398fd 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -305,6 +305,9 @@ HWCAP2_SMEF16F16 HWCAP2_MOPS Functionality implied by ID_AA64ISAR2_EL1.MOPS == 0b0001. +HWCAP2_HBC + Functionality implied by ID_AA64ISAR2_EL1.BC == 0b0001. + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arch/loongarch/introduction.rst b/Documentation/arch/loongarch/introduction.rst index 49135d451ced..8c568cfc2107 100644 --- a/Documentation/arch/loongarch/introduction.rst +++ b/Documentation/arch/loongarch/introduction.rst @@ -381,9 +381,9 @@ Documentation of LoongArch ISA: Documentation of LoongArch ELF psABI: - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-CN.pdf (in Chinese) + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-CN.pdf (in Chinese) - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-EN.pdf (in English) + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-EN.pdf (in English) Linux kernel repository of Loongson and LoongArch: diff --git a/Documentation/devicetree/bindings/ata/pata-common.yaml b/Documentation/devicetree/bindings/ata/pata-common.yaml index 337ddf1113c4..4e867dd4d402 100644 --- a/Documentation/devicetree/bindings/ata/pata-common.yaml +++ b/Documentation/devicetree/bindings/ata/pata-common.yaml @@ -38,6 +38,7 @@ patternProperties: ID number 0 and the slave drive will have ID number 1. The PATA port nodes will be named "ide-port". type: object + additionalProperties: false properties: reg: diff --git a/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml b/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml index 839648e753d4..42b6f80613f3 100644 --- a/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml +++ b/Documentation/devicetree/bindings/clock/renesas,5p35023.yaml @@ -37,6 +37,9 @@ properties: maxItems: 1 '#clock-cells': + description: + The index in the assigned-clocks is mapped to the output clock as below + 0 - REF, 1 - SE1, 2 - SE2, 3 - SE3, 4 - DIFF1, 5 - DIFF2. const: 1 clocks: @@ -68,7 +71,7 @@ examples: reg = <0x68>; #clock-cells = <1>; - clocks = <&x1_x2>; + clocks = <&x1>; renesas,settings = [ 80 00 11 19 4c 02 23 7f 83 19 08 a9 5f 25 24 bf @@ -79,8 +82,8 @@ examples: assigned-clocks = <&versa3 0>, <&versa3 1>, <&versa3 2>, <&versa3 3>, <&versa3 4>, <&versa3 5>; - assigned-clock-rates = <12288000>, <25000000>, - <12000000>, <11289600>, - <11289600>, <24000000>; + assigned-clock-rates = <24000000>, <11289600>, + <11289600>, <12000000>, + <25000000>, <12288000>; }; }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml index 21ae7bce038e..171a41407241 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml @@ -9,6 +9,9 @@ title: Freescale MXS Inter IC (I2C) Controller maintainers: - Shawn Guo <shawnguo@kernel.org> +allOf: + - $ref: /schemas/i2c/i2c-controller.yaml# + properties: compatible: enum: @@ -37,7 +40,7 @@ required: - dmas - dma-names -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index cf29ab10501c..b1b2cf81b42f 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -270,6 +270,7 @@ allOf: contains: enum: - qcom,msm8998-smmu-v2 + - qcom,sdm630-smmu-v2 then: anyOf: - properties: @@ -311,7 +312,6 @@ allOf: compatible: contains: enum: - - qcom,sdm630-smmu-v2 - qcom,sm6375-smmu-v2 then: anyOf: diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml index 9804d13de648..6a6f222b868f 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml @@ -31,10 +31,6 @@ properties: charger: $ref: /schemas/power/supply/maxim,max77693.yaml - connector: - $ref: /schemas/connector/usb-connector.yaml# - unevaluatedProperties: false - led: $ref: /schemas/leds/maxim,max77693.yaml diff --git a/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml b/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml index da2dcfeebf12..510f6cb0f084 100644 --- a/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml +++ b/Documentation/devicetree/bindings/soc/loongson/loongson,ls2k-pmc.yaml @@ -11,11 +11,16 @@ maintainers: properties: compatible: - items: - - enum: - - loongson,ls2k0500-pmc - - loongson,ls2k1000-pmc - - const: syscon + oneOf: + - items: + - const: loongson,ls2k0500-pmc + - const: syscon + - items: + - enum: + - loongson,ls2k1000-pmc + - loongson,ls2k2000-pmc + - const: loongson,ls2k0500-pmc + - const: syscon reg: maxItems: 1 @@ -32,6 +37,18 @@ properties: addition, the PM need according to it to indicate that current SoC whether support Suspend To RAM. + syscon-poweroff: + $ref: /schemas/power/reset/syscon-poweroff.yaml# + type: object + description: + Node for power off method + + syscon-reboot: + $ref: /schemas/power/reset/syscon-reboot.yaml# + type: object + description: + Node for reboot method + required: - compatible - reg @@ -44,9 +61,23 @@ examples: #include <dt-bindings/interrupt-controller/irq.h> power-management@1fe27000 { - compatible = "loongson,ls2k1000-pmc", "syscon"; + compatible = "loongson,ls2k1000-pmc", "loongson,ls2k0500-pmc", "syscon"; reg = <0x1fe27000 0x58>; interrupt-parent = <&liointc1>; interrupts = <11 IRQ_TYPE_LEVEL_LOW>; loongson,suspend-address = <0x0 0x1c000500>; + + syscon-reboot { + compatible = "syscon-reboot"; + offset = <0x30>; + mask = <0x1>; + }; + + syscon-poweroff { + compatible = "syscon-poweroff"; + regmap = <&pmc>; + offset = <0x14>; + mask = <0x3c00>; + value = <0x3c00>; + }; }; diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml index 2f593c7225e5..14cac0e6e0a1 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml @@ -23,6 +23,13 @@ properties: - const: fsl,imx51-ecspi - const: fsl,imx53-ecspi - items: + - enum: + - fsl,imx25-cspi + - fsl,imx50-cspi + - fsl,imx51-cspi + - fsl,imx53-cspi + - const: fsl,imx35-cspi + - items: - const: fsl,imx8mp-ecspi - const: fsl,imx6ul-ecspi - items: diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index deac4e973ddc..4d05b9862451 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -949,3 +949,99 @@ mmap_lock held. All in-tree users have been audited and do not seem to depend on the mmap_lock being held, but out of tree users should verify for themselves. If they do need it, they can return VM_FAULT_RETRY to be called with the mmap_lock held. + +--- + +**mandatory** + +The order of opening block devices and matching or creating superblocks has +changed. + +The old logic opened block devices first and then tried to find a +suitable superblock to reuse based on the block device pointer. + +The new logic tries to find a suitable superblock first based on the device +number, and opening the block device afterwards. + +Since opening block devices cannot happen under s_umount because of lock +ordering requirements s_umount is now dropped while opening block devices and +reacquired before calling fill_super(). + +In the old logic concurrent mounters would find the superblock on the list of +superblocks for the filesystem type. Since the first opener of the block device +would hold s_umount they would wait until the superblock became either born or +was discarded due to initialization failure. + +Since the new logic drops s_umount concurrent mounters could grab s_umount and +would spin. Instead they are now made to wait using an explicit wait-wake +mechanism without having to hold s_umount. + +--- + +**mandatory** + +The holder of a block device is now the superblock. + +The holder of a block device used to be the file_system_type which wasn't +particularly useful. It wasn't possible to go from block device to owning +superblock without matching on the device pointer stored in the superblock. +This mechanism would only work for a single device so the block layer couldn't +find the owning superblock of any additional devices. + +In the old mechanism reusing or creating a superblock for a racing mount(2) and +umount(2) relied on the file_system_type as the holder. This was severly +underdocumented however: + +(1) Any concurrent mounter that managed to grab an active reference on an + existing superblock was made to wait until the superblock either became + ready or until the superblock was removed from the list of superblocks of + the filesystem type. If the superblock is ready the caller would simple + reuse it. + +(2) If the mounter came after deactivate_locked_super() but before + the superblock had been removed from the list of superblocks of the + filesystem type the mounter would wait until the superblock was shutdown, + reuse the block device and allocate a new superblock. + +(3) If the mounter came after deactivate_locked_super() and after + the superblock had been removed from the list of superblocks of the + filesystem type the mounter would reuse the block device and allocate a new + superblock (the bd_holder point may still be set to the filesystem type). + +Because the holder of the block device was the file_system_type any concurrent +mounter could open the block devices of any superblock of the same +file_system_type without risking seeing EBUSY because the block device was +still in use by another superblock. + +Making the superblock the owner of the block device changes this as the holder +is now a unique superblock and thus block devices associated with it cannot be +reused by concurrent mounters. So a concurrent mounter in (2) could suddenly +see EBUSY when trying to open a block device whose holder was a different +superblock. + +The new logic thus waits until the superblock and the devices are shutdown in +->kill_sb(). Removal of the superblock from the list of superblocks of the +filesystem type is now moved to a later point when the devices are closed: + +(1) Any concurrent mounter managing to grab an active reference on an existing + superblock is made to wait until the superblock is either ready or until + the superblock and all devices are shutdown in ->kill_sb(). If the + superblock is ready the caller will simply reuse it. + +(2) If the mounter comes after deactivate_locked_super() but before + the superblock has been removed from the list of superblocks of the + filesystem type the mounter is made to wait until the superblock and the + devices are shut down in ->kill_sb() and the superblock is removed from the + list of superblocks of the filesystem type. The mounter will allocate a new + superblock and grab ownership of the block device (the bd_holder pointer of + the block device will be set to the newly allocated superblock). + +(3) This case is now collapsed into (2) as the superblock is left on the list + of superblocks of the filesystem type until all devices are shutdown in + ->kill_sb(). In other words, if the superblock isn't on the list of + superblock of the filesystem type anymore then it has given up ownership of + all associated block devices (the bd_holder pointer is NULL). + +As this is a VFS level change it has no practical consequences for filesystems +other than that all of them must use one of the provided kill_litter_super(), +kill_anon_super(), or kill_block_super() helpers. diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst index 858ed5d80def..0135905c0aa3 100644 --- a/Documentation/kbuild/kconfig-language.rst +++ b/Documentation/kbuild/kconfig-language.rst @@ -573,6 +573,32 @@ above, leading to: bool "Support for foo hardware" depends on ARCH_FOO_VENDOR || COMPILE_TEST +Optional dependencies +~~~~~~~~~~~~~~~~~~~~~ + +Some drivers are able to optionally use a feature from another module +or build cleanly with that module disabled, but cause a link failure +when trying to use that loadable module from a built-in driver. + +The most common way to express this optional dependency in Kconfig logic +uses the slightly counterintuitive:: + + config FOO + tristate "Support for foo hardware" + depends on BAR || !BAR + +This means that there is either a dependency on BAR that disallows +the combination of FOO=y with BAR=m, or BAR is completely disabled. +For a more formalized approach if there are multiple drivers that have +the same dependency, a helper symbol can be used, like:: + + config FOO + tristate "Support for foo hardware" + depends on BAR_OPTIONAL + + config BAR_OPTIONAL + def_tristate BAR || !BAR + Kconfig recursive dependency limitations ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/tools/rtla/rtla-timerlat-hist.rst b/Documentation/tools/rtla/rtla-timerlat-hist.rst index 057db78d4095..03b7f3deb069 100644 --- a/Documentation/tools/rtla/rtla-timerlat-hist.rst +++ b/Documentation/tools/rtla/rtla-timerlat-hist.rst @@ -36,11 +36,11 @@ EXAMPLE In the example below, **rtla timerlat hist** is set to run for *10* minutes, in the cpus *0-4*, *skipping zero* only lines. Moreover, **rtla timerlat hist** will change the priority of the *timerlat* threads to run under -*SCHED_DEADLINE* priority, with a *10us* runtime every *1ms* period. The +*SCHED_DEADLINE* priority, with a *100us* runtime every *1ms* period. The *1ms* period is also passed to the *timerlat* tracer. Auto-analysis is disabled to reduce overhead :: - [root@alien ~]# timerlat hist -d 10m -c 0-4 -P d:100us:1ms -p 1ms --no-aa + [root@alien ~]# timerlat hist -d 10m -c 0-4 -P d:100us:1ms -p 1000 --no-aa # RTLA timerlat histogram # Time unit is microseconds (us) # Duration: 0 00:10:00 diff --git a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst index cba04befc950..59d6bf33050c 100644 --- a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst +++ b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst @@ -344,9 +344,9 @@ LoongArch指令集架构的文档： LoongArch的ELF psABI文档： - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-CN.pdf （中文版） + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-CN.pdf （中文版） - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-EN.pdf （英文版） + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-EN.pdf （英文版） Loongson与LoongArch的Linux内核源码仓库： diff --git a/MAINTAINERS b/MAINTAINERS index 03011d7ee087..d9f6abd77fc7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -470,7 +470,6 @@ F: drivers/hwmon/adm1029.c ADM8211 WIRELESS DRIVER L: linux-wireless@vger.kernel.org S: Orphan -W: https://wireless.wiki.kernel.org/ F: drivers/net/wireless/admtek/adm8211.* ADP1653 FLASH CONTROLLER DRIVER @@ -1662,7 +1661,7 @@ F: arch/arm*/include/asm/perf_event.h F: arch/arm*/kernel/hw_breakpoint.c F: arch/arm*/kernel/perf_* F: drivers/perf/ -F: include/linux/perf/arm_pmu.h +F: include/linux/perf/arm_pmu*.h ARM PORT M: Russell King <linux@armlinux.org.uk> @@ -1963,12 +1962,12 @@ F: drivers/irqchip/irq-aspeed-i2c-ic.c ARM/ASPEED MACHINE SUPPORT M: Joel Stanley <joel@jms.id.au> -R: Andrew Jeffery <andrew@aj.id.au> +R: Andrew Jeffery <andrew@codeconstruct.com.au> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) S: Supported Q: https://patchwork.ozlabs.org/project/linux-aspeed/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/joel/aspeed.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/joel/bmc.git F: Documentation/devicetree/bindings/arm/aspeed/ F: arch/arm/boot/dts/aspeed/ F: arch/arm/mach-aspeed/ @@ -3058,7 +3057,7 @@ F: Documentation/devicetree/bindings/peci/peci-aspeed.yaml F: drivers/peci/controller/peci-aspeed.c ASPEED PINCTRL DRIVERS -M: Andrew Jeffery <andrew@aj.id.au> +M: Andrew Jeffery <andrew@codeconstruct.com.au> L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) L: openbmc@lists.ozlabs.org (moderated for non-subscribers) L: linux-gpio@vger.kernel.org @@ -3075,7 +3074,7 @@ F: drivers/irqchip/irq-aspeed-scu-ic.c F: include/dt-bindings/interrupt-controller/aspeed-scu-ic.h ASPEED SD/MMC DRIVER -M: Andrew Jeffery <andrew@aj.id.au> +M: Andrew Jeffery <andrew@codeconstruct.com.au> L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) L: openbmc@lists.ozlabs.org (moderated for non-subscribers) L: linux-mmc@vger.kernel.org @@ -4083,7 +4082,7 @@ F: drivers/net/wireless/broadcom/brcm80211/ BROADCOM BRCMSTB GPIO DRIVER M: Doug Berger <opendmb@gmail.com> -M: Florian Fainelli <florian.fainelli@broadcom> +M: Florian Fainelli <florian.fainelli@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml @@ -6656,9 +6655,9 @@ F: Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml F: drivers/gpu/drm/panel/panel-novatek-nt36672a.c DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS -M: Ben Skeggs <bskeggs@redhat.com> M: Karol Herbst <kherbst@redhat.com> M: Lyude Paul <lyude@redhat.com> +M: Danilo Krummrich <dakr@redhat.com> L: dri-devel@lists.freedesktop.org L: nouveau@lists.freedesktop.org S: Supported @@ -8885,7 +8884,7 @@ F: drivers/gpio/gpio-mockup.c F: tools/testing/selftests/gpio/ GPIO REGMAP -R: Michael Walle <michael@walle.cc> +M: Michael Walle <michael@walle.cc> S: Maintained F: drivers/gpio/gpio-regmap.c F: include/linux/gpio/regmap.h @@ -9542,10 +9541,8 @@ F: Documentation/devicetree/bindings/iio/pressure/honeywell,mprls0025pa.yaml F: drivers/iio/pressure/mprls0025pa.c HOST AP DRIVER -M: Jouni Malinen <j@w1.fi> L: linux-wireless@vger.kernel.org S: Obsolete -W: http://w1.fi/hostap-driver.html F: drivers/net/wireless/intersil/hostap/ HP BIOSCFG DRIVER @@ -13627,6 +13624,7 @@ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT M: Hans de Goede <hdegoede@redhat.com> +M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> M: Mark Gross <markgross@kernel.org> M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org @@ -14221,6 +14219,7 @@ F: drivers/platform/surface/surface_gpe.c MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT M: Hans de Goede <hdegoede@redhat.com> +M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> M: Mark Gross <markgross@kernel.org> M: Maximilian Luz <luzmaximilian@gmail.com> L: platform-driver-x86@vger.kernel.org @@ -14958,7 +14957,7 @@ K: macsec K: \bmdo_ NETWORKING [MPTCP] -M: Matthieu Baerts <matthieu.baerts@tessares.net> +M: Matthieu Baerts <matttbe@kernel.org> M: Mat Martineau <martineau@kernel.org> L: netdev@vger.kernel.org L: mptcp@lists.linux.dev @@ -17613,6 +17612,7 @@ M: Kalle Valo <kvalo@kernel.org> M: Jeff Johnson <quic_jjohnson@quicinc.com> L: ath12k@lists.infradead.org S: Supported +W: https://wireless.wiki.kernel.org/en/users/Drivers/ath12k T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git F: drivers/net/wireless/ath/ath12k/ @@ -18143,8 +18143,6 @@ REALTEK WIRELESS DRIVER (rtlwifi family) M: Ping-Ke Shih <pkshih@realtek.com> L: linux-wireless@vger.kernel.org S: Maintained -W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtlwifi/ REALTEK WIRELESS DRIVER (rtw88) @@ -18672,7 +18670,6 @@ F: drivers/media/dvb-frontends/rtl2832_sdr* RTL8180 WIRELESS DRIVER L: linux-wireless@vger.kernel.org S: Orphan -W: https://wireless.wiki.kernel.org/ F: drivers/net/wireless/realtek/rtl818x/rtl8180/ RTL8187 WIRELESS DRIVER @@ -18680,14 +18677,12 @@ M: Hin-Tak Leung <hintak.leung@gmail.com> M: Larry Finger <Larry.Finger@lwfinger.net> L: linux-wireless@vger.kernel.org S: Maintained -W: https://wireless.wiki.kernel.org/ F: drivers/net/wireless/realtek/rtl818x/rtl8187/ RTL8XXXU WIRELESS DRIVER (rtl8xxxu) M: Jes Sorensen <Jes.Sorensen@gmail.com> L: linux-wireless@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jes/linux.git rtl8xxxu-devel F: drivers/net/wireless/realtek/rtl8xxxu/ RTRS TRANSPORT DRIVERS @@ -21669,7 +21664,6 @@ L: linux-wireless@vger.kernel.org S: Orphan W: https://wireless.wiki.kernel.org/en/users/Drivers/wl12xx W: https://wireless.wiki.kernel.org/en/users/Drivers/wl1251 -T: git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git F: drivers/net/wireless/ti/ TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER @@ -23436,9 +23430,11 @@ F: drivers/platform/x86/x86-android-tablets/ X86 PLATFORM DRIVERS M: Hans de Goede <hdegoede@redhat.com> +M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> M: Mark Gross <markgross@kernel.org> L: platform-driver-x86@vger.kernel.org S: Maintained +Q: https://patchwork.kernel.org/project/platform-driver-x86/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git F: drivers/platform/olpc/ F: drivers/platform/x86/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc4 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi index 091ba310053e..d2d516d113ba 100644 --- a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi @@ -614,12 +614,12 @@ /* Configure pwm clock source for timers 8 & 9 */ &timer8 { assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>; - assigned-clock-parents = <&sys_clkin_ck>; + assigned-clock-parents = <&sys_32k_ck>; }; &timer9 { assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>; - assigned-clock-parents = <&sys_clkin_ck>; + assigned-clock-parents = <&sys_32k_ck>; }; /* @@ -640,6 +640,7 @@ &uart3 { interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH &omap4_pmx_core 0x17c>; + overrun-throttle-ms = <500>; }; &uart4 { diff --git a/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi b/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi index 0da759f8e2c2..7dd2340bc5e4 100644 --- a/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi +++ b/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi @@ -12,8 +12,7 @@ cpu_thermal: cpu-thermal { polling-delay = <1000>; /* milliseconds */ coefficients = <0 20000>; - /* sensor ID */ - thermal-sensors = <&bandgap 0>; + thermal-sensors = <&bandgap>; cpu_trips: trips { cpu_alert0: cpu_alert { diff --git a/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi b/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi index 801b4f10350c..d484ec1e4fd8 100644 --- a/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi +++ b/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi @@ -12,7 +12,10 @@ cpu_thermal: cpu_thermal { polling-delay-passive = <250>; /* milliseconds */ polling-delay = <1000>; /* milliseconds */ - /* sensor ID */ + /* + * See 44xx files for single sensor addressing, omap5 and dra7 need + * also sensor ID for addressing. + */ thermal-sensors = <&bandgap 0>; cpu_trips: trips { diff --git a/arch/arm/boot/dts/ti/omap/omap443x.dtsi b/arch/arm/boot/dts/ti/omap/omap443x.dtsi index 238aceb799f8..2104170fe2cd 100644 --- a/arch/arm/boot/dts/ti/omap/omap443x.dtsi +++ b/arch/arm/boot/dts/ti/omap/omap443x.dtsi @@ -69,6 +69,7 @@ }; &cpu_thermal { + thermal-sensors = <&bandgap>; coefficients = <0 20000>; }; diff --git a/arch/arm/boot/dts/ti/omap/omap4460.dtsi b/arch/arm/boot/dts/ti/omap/omap4460.dtsi index 1b27a862ae81..a6764750d447 100644 --- a/arch/arm/boot/dts/ti/omap/omap4460.dtsi +++ b/arch/arm/boot/dts/ti/omap/omap4460.dtsi @@ -79,6 +79,7 @@ }; &cpu_thermal { + thermal-sensors = <&bandgap>; coefficients = <348 (-9301)>; }; diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h index 246a3de25931..aaaedafef7cc 100644 --- a/arch/arm/include/asm/hardware/locomo.h +++ b/arch/arm/include/asm/hardware/locomo.h @@ -195,7 +195,7 @@ struct locomo_driver { #define LOCOMO_DRIVER_NAME(_ldev) ((_ldev)->dev.driver->name) -void locomo_lcd_power(struct locomo_dev *, int, unsigned int); +extern void locomolcd_power(int on); int locomo_driver_register(struct locomo_driver *); void locomo_driver_unregister(struct locomo_driver *); diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c index f57802f3ee3a..37b168119fe4 100644 --- a/arch/arm/mach-omap2/pm44xx.c +++ b/arch/arm/mach-omap2/pm44xx.c @@ -99,7 +99,7 @@ static int omap4_pm_suspend(void) * possible causes. * http://www.spinics.net/lists/arm-kernel/msg218641.html */ - pr_warn("A possible cause could be an old bootloader - try u-boot >= v2012.07\n"); + pr_debug("A possible cause could be an old bootloader - try u-boot >= v2012.07\n"); } else { pr_info("Successfully put all powerdomains to target state\n"); } @@ -257,7 +257,7 @@ int __init omap4_pm_init(void) * http://www.spinics.net/lists/arm-kernel/msg218641.html */ if (cpu_is_omap44xx()) - pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n"); + pr_debug("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n"); ret = pwrdm_for_each(pwrdms_setup, NULL); if (ret) { diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h index b7bc23ffd3c6..c95273c9567b 100644 --- a/arch/arm/mach-sa1100/include/mach/collie.h +++ b/arch/arm/mach-sa1100/include/mach/collie.h @@ -16,8 +16,6 @@ #include "hardware.h" /* Gives GPIO_MAX */ -extern void locomolcd_power(int on); - #define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1) #define COLLIE_GPIO_CHARGE_ON (COLLIE_SCOOP_GPIO_BASE + 0) #define COLLIE_SCP_DIAG_BOOT1 SCOOP_GPCR_PA12 diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c index ff2881458504..84a2f17ff32d 100644 --- a/arch/arm/mm/cache-uniphier.c +++ b/arch/arm/mm/cache-uniphier.c @@ -58,11 +58,13 @@ ((op & UNIPHIER_SSCOQM_S_MASK) == UNIPHIER_SSCOQM_S_RANGE) /** - * uniphier_cache_data - UniPhier outer cache specific data + * struct uniphier_cache_data - UniPhier outer cache specific data * * @ctrl_base: virtual base address of control registers * @rev_base: virtual base address of revision registers * @op_base: virtual base address of operation registers + * @way_ctrl_base: virtual address of the way control registers for this + * SoC revision * @way_mask: each bit specifies if the way is present * @nsets: number of associativity sets * @line_size: line size in bytes diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile index c6872b7e9471..89aee6c92576 100644 --- a/arch/arm64/boot/dts/freescale/Makefile +++ b/arch/arm64/boot/dts/freescale/Makefile @@ -66,6 +66,7 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-mx8menlo.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-nitrogen-r2.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-phg.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-rdk.dtb +dtb-$(CONFIG_ARCH_MXC) += imx8mm-prt8mm.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-tqma8mqml-mba8mx.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-var-som-symphony.dtb dtb-$(CONFIG_ARCH_MXC) += imx8mm-venice-gw71xx-0x.dtb diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index e31ab8b4f54f..a882c86ec313 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -26,7 +26,7 @@ port { hdmi_connector_in: endpoint { - remote-endpoint = <&adv7533_out>; + remote-endpoint = <&adv7535_out>; }; }; }; @@ -72,6 +72,13 @@ enable-active-high; }; + reg_vddext_3v3: regulator-vddext-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VDDEXT_3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + backlight: backlight { compatible = "pwm-backlight"; pwms = <&pwm1 0 5000000 0>; @@ -317,15 +324,16 @@ hdmi@3d { compatible = "adi,adv7535"; - reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>; - reg-names = "main", "cec", "edid", "packet"; + reg = <0x3d>; + interrupt-parent = <&gpio1>; + interrupts = <9 IRQ_TYPE_EDGE_FALLING>; adi,dsi-lanes = <4>; - - adi,input-depth = <8>; - adi,input-colorspace = "rgb"; - adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; + avdd-supply = <&buck5_reg>; + dvdd-supply = <&buck5_reg>; + pvdd-supply = <&buck5_reg>; + a2vdd-supply = <&buck5_reg>; + v3p3-supply = <®_vddext_3v3>; + v1p2-supply = <&buck5_reg>; ports { #address-cells = <1>; @@ -334,7 +342,7 @@ port@0 { reg = <0>; - adv7533_in: endpoint { + adv7535_in: endpoint { remote-endpoint = <&dsi_out>; }; }; @@ -342,7 +350,7 @@ port@1 { reg = <1>; - adv7533_out: endpoint { + adv7535_out: endpoint { remote-endpoint = <&hdmi_connector_in>; }; }; @@ -448,7 +456,7 @@ reg = <1>; dsi_out: endpoint { - remote-endpoint = <&adv7533_in>; + remote-endpoint = <&adv7535_in>; data-lanes = <1 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts index 06e91297fb16..acd265d8b58e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts @@ -381,9 +381,10 @@ &sai3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sai3>; - assigned-clocks = <&clk IMX8MP_CLK_SAI3>; + assigned-clocks = <&clk IMX8MP_CLK_SAI3>, + <&clk IMX8MP_AUDIO_PLL2> ; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; - assigned-clock-rates = <12288000>; + assigned-clock-rates = <12288000>, <361267200>; fsl,sai-mclk-direction-output; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 6f2f50e1639c..83d907294fbc 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -790,6 +790,12 @@ reg = <IMX8MP_POWER_DOMAIN_AUDIOMIX>; clocks = <&clk IMX8MP_CLK_AUDIO_ROOT>, <&clk IMX8MP_CLK_AUDIO_AXI>; + assigned-clocks = <&clk IMX8MP_CLK_AUDIO_AHB>, + <&clk IMX8MP_CLK_AUDIO_AXI_SRC>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_SYS_PLL1_800M>; + assigned-clock-rates = <400000000>, + <600000000>; }; pgc_gpu2d: power-domain@6 { diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi index 1c71c08becde..f6e422dc2663 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi @@ -81,7 +81,7 @@ &gpio1 { pmic-irq-hog { gpio-hog; - gpios = <2 GPIO_ACTIVE_LOW>; + gpios = <3 GPIO_ACTIVE_LOW>; input; line-name = "PMIC_IRQ#"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 4dbbf8fdab75..a9e52b50c8c4 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -2957,7 +2957,7 @@ clock-names = "merge","merge_async"; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xc000 0x1000>; - mediatek,merge-mute = <1>; + mediatek,merge-mute; resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE0_DL_ASYNC>; }; @@ -2970,7 +2970,7 @@ clock-names = "merge","merge_async"; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xd000 0x1000>; - mediatek,merge-mute = <1>; + mediatek,merge-mute; resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE1_DL_ASYNC>; }; @@ -2983,7 +2983,7 @@ clock-names = "merge","merge_async"; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xe000 0x1000>; - mediatek,merge-mute = <1>; + mediatek,merge-mute; resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE2_DL_ASYNC>; }; @@ -2996,7 +2996,7 @@ clock-names = "merge","merge_async"; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xf000 0x1000>; - mediatek,merge-mute = <1>; + mediatek,merge-mute; resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE3_DL_ASYNC>; }; @@ -3009,7 +3009,7 @@ clock-names = "merge","merge_async"; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; mediatek,gce-client-reg = <&gce0 SUBSYS_1c11XXXX 0x0000 0x1000>; - mediatek,merge-fifo-en = <1>; + mediatek,merge-fifo-en; resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE4_DL_ASYNC>; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 5315789f4868..a789119e6483 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -636,6 +636,7 @@ CONFIG_POWER_RESET_MSM=y CONFIG_POWER_RESET_QCOM_PON=m CONFIG_POWER_RESET_XGENE=y CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y CONFIG_SYSCON_REBOOT_MODE=y CONFIG_NVMEM_REBOOT_MODE=m CONFIG_BATTERY_SBS=m @@ -1175,7 +1176,6 @@ CONFIG_COMMON_CLK_S2MPS11=y CONFIG_COMMON_CLK_PWM=y CONFIG_COMMON_CLK_RS9_PCIE=y CONFIG_COMMON_CLK_VC5=y -CONFIG_COMMON_CLK_NPCM8XX=y CONFIG_COMMON_CLK_BD718XX=m CONFIG_CLK_RASPBERRYPI=m CONFIG_CLK_IMX8MM=y diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 96e50227f940..5bba39376055 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -663,7 +663,7 @@ static inline bool supports_clearbhb(int scope) isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); return cpuid_feature_extract_unsigned_field(isar2, - ID_AA64ISAR2_EL1_BC_SHIFT); + ID_AA64ISAR2_EL1_CLRBHB_SHIFT); } const struct cpumask *system_32bit_el0_cpumask(void); diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index f43a38ac1779..2ddc33d93b13 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -28,7 +28,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); + pte_t *ptep, pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index b7238c72a04c..66efd67ea7e8 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -118,7 +118,7 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu); u64 __guest_enter(struct kvm_vcpu *vcpu); -bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt); +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); #ifdef __KVM_NVHE_HYPERVISOR__ void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index b018ae12ff5f..444a73c2e638 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -222,7 +222,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h index 1becb10ecd80..d9fd5e6c7d3c 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h +++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h @@ -12,6 +12,6 @@ #define FFA_MAX_FUNC_NUM 0x7F int hyp_ffa_init(void *pages); -bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt); +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); #endif /* __KVM_HYP_FFA_H */ diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index ab4f5d160c58..6e4dba9eadef 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -634,9 +634,8 @@ out_handled: return true; } -bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt) +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - DECLARE_REG(u64, func_id, host_ctxt, 0); struct arm_smccc_res res; /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 90fade1b032e..1cc06e6797bd 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -57,6 +57,7 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc + bic x0, x0, #ARM_SMCCC_CALL_HINTS mov x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) cmp x0, x3 b.eq 1f diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 857d9bc04fd4..2385fd03ed87 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -368,6 +368,7 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) if (static_branch_unlikely(&kvm_protected_mode_initialized)) hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize; + id &= ~ARM_SMCCC_CALL_HINTS; id -= KVM_HOST_SMCCC_ID(0); if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall))) @@ -392,11 +393,14 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) static void handle_host_smc(struct kvm_cpu_context *host_ctxt) { + DECLARE_REG(u64, func_id, host_ctxt, 0); bool handled; - handled = kvm_host_psci_handler(host_ctxt); + func_id &= ~ARM_SMCCC_CALL_HINTS; + + handled = kvm_host_psci_handler(host_ctxt, func_id); if (!handled) - handled = kvm_host_ffa_handler(host_ctxt); + handled = kvm_host_ffa_handler(host_ctxt, func_id); if (!handled) default_host_smc_handler(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index 24543d2a3490..d57bcb6ab94d 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -273,9 +273,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ } } -bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt) +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - DECLARE_REG(u64, func_id, host_ctxt, 0); unsigned long ret; switch (kvm_host_psci_config.version) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 587a104f66c3..482280fe22d7 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -652,6 +652,9 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) mutex_unlock(&kvm_hyp_pgd_mutex); + if (!ret) + *haddr = base; + return ret; } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 9c52718ea750..13fd592228b1 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -241,15 +241,8 @@ static void clear_flush(struct mm_struct *mm, flush_tlb_range(&vma, saddr, addr); } -static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry) -{ - VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry)); - - return page_folio(pfn_to_page(swp_offset_pfn(entry))); -} - void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { size_t pgsize; int i; @@ -257,13 +250,10 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, unsigned long pfn, dpfn; pgprot_t hugeprot; - if (!pte_present(pte)) { - struct folio *folio; - - folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte)); - ncontig = num_contig_ptes(folio_size(folio), &pgsize); + ncontig = num_contig_ptes(sz, &pgsize); - for (i = 0; i < ncontig; i++, ptep++) + if (!pte_present(pte)) { + for (i = 0; i < ncontig; i++, ptep++, addr += pgsize) set_pte_at(mm, addr, ptep, pte); return; } @@ -273,7 +263,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, return; } - ncontig = find_num_contig(mm, addr, ptep, &pgsize); pfn = pte_pfn(pte); dpfn = pgsize >> PAGE_SHIFT; hugeprot = pte_pgprot(pte); @@ -571,5 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 2517ef7c21cf..76ce150e7347 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1347,7 +1347,11 @@ UnsignedEnum 51:48 RPRFM 0b0000 NI 0b0001 IMP EndEnum -Res0 47:28 +Res0 47:32 +UnsignedEnum 31:28 CLRBHB + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 27:24 PAC_frac 0b0000 NI 0b0001 IMP diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 15f6cfddcc08..41e8fe55cd98 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -907,3 +907,7 @@ EXPORT_SYMBOL(acpi_unregister_ioapic); * TBD when IA64 starts to support suspend... */ int acpi_suspend_lowlevel(void) { return 0; } + +void acpi_proc_quirk_mwait_check(void) +{ +} diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index 5c9c03bdf915..b24437e28c6e 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -19,7 +19,7 @@ */ #ifndef __ASSEMBLY__ #ifndef PHYS_OFFSET -#define PHYS_OFFSET _AC(0, UL) +#define PHYS_OFFSET _UL(0) #endif extern unsigned long vm_map_base; #endif /* __ASSEMBLY__ */ @@ -43,7 +43,7 @@ extern unsigned long vm_map_base; * Memory above this physical address will be considered highmem. */ #ifndef HIGHMEM_START -#define HIGHMEM_START (_AC(1, UL) << _AC(DMW_PABITS, UL)) +#define HIGHMEM_START (_UL(1) << _UL(DMW_PABITS)) #endif #define TO_PHYS(x) ( ((x) & TO_PHYS_MASK)) @@ -65,16 +65,16 @@ extern unsigned long vm_map_base; #define _ATYPE_ #define _ATYPE32_ #define _ATYPE64_ -#define _CONST64_(x) x #else #define _ATYPE_ __PTRDIFF_TYPE__ #define _ATYPE32_ int #define _ATYPE64_ __s64 +#endif + #ifdef CONFIG_64BIT -#define _CONST64_(x) x ## UL +#define _CONST64_(x) _UL(x) #else -#define _CONST64_(x) x ## ULL -#endif +#define _CONST64_(x) _ULL(x) #endif /* diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h index 7af0cebf28d7..b9a4ab54285c 100644 --- a/arch/loongarch/include/asm/elf.h +++ b/arch/loongarch/include/asm/elf.h @@ -111,6 +111,15 @@ #define R_LARCH_TLS_GD_HI20 98 #define R_LARCH_32_PCREL 99 #define R_LARCH_RELAX 100 +#define R_LARCH_DELETE 101 +#define R_LARCH_ALIGN 102 +#define R_LARCH_PCREL20_S2 103 +#define R_LARCH_CFA 104 +#define R_LARCH_ADD6 105 +#define R_LARCH_SUB6 106 +#define R_LARCH_ADD_ULEB128 107 +#define R_LARCH_SUB_ULEB128 108 +#define R_LARCH_64_PCREL 109 #ifndef ELF_ARCH diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h new file mode 100644 index 000000000000..af74a3fdcad1 --- /dev/null +++ b/arch/loongarch/include/asm/exception.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_EXCEPTION_H +#define __ASM_EXCEPTION_H + +#include <asm/ptrace.h> +#include <linux/kprobes.h> + +void show_registers(struct pt_regs *regs); + +asmlinkage void cache_parity_error(void); +asmlinkage void noinstr do_ade(struct pt_regs *regs); +asmlinkage void noinstr do_ale(struct pt_regs *regs); +asmlinkage void noinstr do_bce(struct pt_regs *regs); +asmlinkage void noinstr do_bp(struct pt_regs *regs); +asmlinkage void noinstr do_ri(struct pt_regs *regs); +asmlinkage void noinstr do_fpu(struct pt_regs *regs); +asmlinkage void noinstr do_fpe(struct pt_regs *regs, unsigned long fcsr); +asmlinkage void noinstr do_lsx(struct pt_regs *regs); +asmlinkage void noinstr do_lasx(struct pt_regs *regs); +asmlinkage void noinstr do_lbt(struct pt_regs *regs); +asmlinkage void noinstr do_watch(struct pt_regs *regs); +asmlinkage void noinstr do_syscall(struct pt_regs *regs); +asmlinkage void noinstr do_reserved(struct pt_regs *regs); +asmlinkage void noinstr do_vint(struct pt_regs *regs, unsigned long sp); +asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long write, unsigned long address); + +asmlinkage void handle_ade(void); +asmlinkage void handle_ale(void); +asmlinkage void handle_bce(void); +asmlinkage void handle_sys(void); +asmlinkage void handle_bp(void); +asmlinkage void handle_ri(void); +asmlinkage void handle_fpu(void); +asmlinkage void handle_fpe(void); +asmlinkage void handle_lsx(void); +asmlinkage void handle_lasx(void); +asmlinkage void handle_lbt(void); +asmlinkage void handle_watch(void); +asmlinkage void handle_reserved(void); +asmlinkage void handle_vint(void); +asmlinkage void noinstr handle_loongarch_irq(struct pt_regs *regs); + +#endif /* __ASM_EXCEPTION_H */ diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index deeff8158f45..cd6084f4e153 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -10,8 +10,6 @@ #include <asm/io.h> #include <asm/pgtable.h> -#define __HAVE_ARCH_SHADOW_MAP - #define KASAN_SHADOW_SCALE_SHIFT 3 #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) @@ -62,61 +60,22 @@ extern bool kasan_early_stage; extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; +#define kasan_mem_to_shadow kasan_mem_to_shadow +void *kasan_mem_to_shadow(const void *addr); + +#define kasan_shadow_to_mem kasan_shadow_to_mem +const void *kasan_shadow_to_mem(const void *shadow_addr); + #define kasan_arch_is_ready kasan_arch_is_ready static __always_inline bool kasan_arch_is_ready(void) { return !kasan_early_stage; } -static inline void *kasan_mem_to_shadow(const void *addr) -{ - if (!kasan_arch_is_ready()) { - return (void *)(kasan_early_shadow_page); - } else { - unsigned long maddr = (unsigned long)addr; - unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; - unsigned long offset = 0; - - maddr &= XRANGE_SHADOW_MASK; - switch (xrange) { - case XKPRANGE_CC_SEG: - offset = XKPRANGE_CC_SHADOW_OFFSET; - break; - case XKPRANGE_UC_SEG: - offset = XKPRANGE_UC_SHADOW_OFFSET; - break; - case XKVRANGE_VC_SEG: - offset = XKVRANGE_VC_SHADOW_OFFSET; - break; - default: - WARN_ON(1); - return NULL; - } - - return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset); - } -} - -static inline const void *kasan_shadow_to_mem(const void *shadow_addr) +#define addr_has_metadata addr_has_metadata +static __always_inline bool addr_has_metadata(const void *addr) { - unsigned long addr = (unsigned long)shadow_addr; - - if (unlikely(addr > KASAN_SHADOW_END) || - unlikely(addr < KASAN_SHADOW_START)) { - WARN_ON(1); - return NULL; - } - - if (addr >= XKVRANGE_VC_SHADOW_OFFSET) - return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START); - else if (addr >= XKPRANGE_UC_SHADOW_OFFSET) - return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START); - else if (addr >= XKPRANGE_CC_SHADOW_OFFSET) - return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START); - else { - WARN_ON(1); - return NULL; - } + return (kasan_mem_to_shadow((void *)addr) != NULL); } void kasan_init(void); diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 66ecb480c894..f81e5f01d619 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -70,6 +70,7 @@ struct secondary_data { extern struct secondary_data cpuboot_data; extern asmlinkage void smpboot_entry(void); +extern asmlinkage void start_secondary(void); extern void calculate_cpu_foreign_map(void); diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index c56ea0b75448..4fcc168f0732 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -19,6 +19,10 @@ obj-$(CONFIG_CPU_HAS_LBT) += lbt.o obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o +CFLAGS_module.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,) +CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,) + ifdef CONFIG_FUNCTION_TRACER ifndef CONFIG_DYNAMIC_FTRACE obj-y += mcount.o ftrace.o diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 9450e09073eb..8e00a754e548 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -281,7 +281,6 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pr_info("SRAT: PXM %u -> CPU 0x%02x -> Node %u\n", pxm, pa->apic_id, node); } -void __init acpi_numa_arch_fixup(void) {} #endif void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c index 4a4107a6a965..aed901c57fb4 100644 --- a/arch/loongarch/kernel/mem.c +++ b/arch/loongarch/kernel/mem.c @@ -50,7 +50,6 @@ void __init memblock_init(void) } memblock_set_current_limit(PFN_PHYS(max_low_pfn)); - memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); /* Reserve the first 2MB */ memblock_reserve(PHYS_OFFSET, 0x200000); @@ -58,4 +57,7 @@ void __init memblock_init(void) /* Reserve the kernel text/data/bss */ memblock_reserve(__pa_symbol(&_text), __pa_symbol(&_end) - __pa_symbol(&_text)); + + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.reserved, 0); } diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c index d4dbcda1c4b0..e2f30ff9afde 100644 --- a/arch/loongarch/kernel/module-sections.c +++ b/arch/loongarch/kernel/module-sections.c @@ -6,6 +6,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/moduleloader.h> #include <linux/ftrace.h> Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val) diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c index b8b86088b2dd..b13b2858fe39 100644 --- a/arch/loongarch/kernel/module.c +++ b/arch/loongarch/kernel/module.c @@ -367,6 +367,24 @@ static int apply_r_larch_got_pc(struct module *mod, return apply_r_larch_pcala(mod, location, got, rela_stack, rela_stack_top, type); } +static int apply_r_larch_32_pcrel(struct module *mod, u32 *location, Elf_Addr v, + s64 *rela_stack, size_t *rela_stack_top, unsigned int type) +{ + ptrdiff_t offset = (void *)v - (void *)location; + + *(u32 *)location = offset; + return 0; +} + +static int apply_r_larch_64_pcrel(struct module *mod, u32 *location, Elf_Addr v, + s64 *rela_stack, size_t *rela_stack_top, unsigned int type) +{ + ptrdiff_t offset = (void *)v - (void *)location; + + *(u64 *)location = offset; + return 0; +} + /* * reloc_handlers_rela() - Apply a particular relocation to a module * @mod: the module to apply the reloc to @@ -382,7 +400,7 @@ typedef int (*reloc_rela_handler)(struct module *mod, u32 *location, Elf_Addr v, /* The handlers for known reloc types */ static reloc_rela_handler reloc_rela_handlers[] = { - [R_LARCH_NONE ... R_LARCH_RELAX] = apply_r_larch_error, + [R_LARCH_NONE ... R_LARCH_64_PCREL] = apply_r_larch_error, [R_LARCH_NONE] = apply_r_larch_none, [R_LARCH_32] = apply_r_larch_32, @@ -396,6 +414,8 @@ static reloc_rela_handler reloc_rela_handlers[] = { [R_LARCH_SOP_POP_32_S_10_5 ... R_LARCH_SOP_POP_32_U] = apply_r_larch_sop_imm_field, [R_LARCH_ADD32 ... R_LARCH_SUB64] = apply_r_larch_add_sub, [R_LARCH_PCALA_HI20...R_LARCH_PCALA64_HI12] = apply_r_larch_pcala, + [R_LARCH_32_PCREL] = apply_r_larch_32_pcrel, + [R_LARCH_64_PCREL] = apply_r_larch_64_pcrel, }; int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index c7d33c489e04..6e65ff12d5c7 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -436,7 +436,7 @@ void __init paging_init(void) void __init mem_init(void) { - high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); + high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 3cb082e0c992..767d94cce0de 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -37,6 +37,7 @@ #include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/elf.h> +#include <asm/exec.h> #include <asm/fpu.h> #include <asm/lbt.h> #include <asm/io.h> diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S index d13252553a7c..f49f6b053763 100644 --- a/arch/loongarch/kernel/relocate_kernel.S +++ b/arch/loongarch/kernel/relocate_kernel.S @@ -72,7 +72,6 @@ copy_word: LONG_ADDI s5, s5, -1 beqz s5, process_entry b copy_word - b process_entry done: ibar 0 diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c index 504fdfe85203..4a3686d13349 100644 --- a/arch/loongarch/kernel/signal.c +++ b/arch/loongarch/kernel/signal.c @@ -13,6 +13,7 @@ #include <linux/audit.h> #include <linux/cache.h> #include <linux/context_tracking.h> +#include <linux/entry-common.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/mm.h> @@ -891,8 +892,8 @@ static unsigned long setup_extcontext(struct extctx_layout *extctx, unsigned lon return new_sp; } -void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, - struct extctx_layout *extctx) +static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, + struct extctx_layout *extctx) { unsigned long sp; @@ -922,7 +923,7 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, * Atomically swap in the new signal mask, and wait for a signal. */ -asmlinkage long sys_rt_sigreturn(void) +SYSCALL_DEFINE0(rt_sigreturn) { int sig; sigset_t set; diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 6667b0a90f81..ef35c871244f 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -13,6 +13,7 @@ #include <linux/cpumask.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/profile.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/threads.h> @@ -556,10 +557,12 @@ void smp_send_stop(void) smp_call_function(stop_this_cpu, NULL, 0); } +#ifdef CONFIG_PROFILING int setup_profiling_timer(unsigned int multiplier) { return 0; } +#endif static void flush_tlb_all_ipi(void *info) { diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index 3fc4211db989..b4c5acd7aa3b 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -13,6 +13,7 @@ #include <linux/unistd.h> #include <asm/asm.h> +#include <asm/exception.h> #include <asm/signal.h> #include <asm/switch_to.h> #include <asm-generic/syscalls.h> diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index c189e03cd5da..3064af94db9c 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -29,7 +29,7 @@ static void constant_event_handler(struct clock_event_device *dev) { } -irqreturn_t constant_timer_interrupt(int irq, void *data) +static irqreturn_t constant_timer_interrupt(int irq, void *data) { int cpu = smp_processor_id(); struct clock_event_device *cd; diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c index caa7cd859078..3fd166006698 100644 --- a/arch/loongarch/kernel/topology.c +++ b/arch/loongarch/kernel/topology.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/acpi.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/init.h> @@ -7,6 +8,8 @@ #include <linux/percpu.h> #include <asm/bootinfo.h> +#include <acpi/processor.h> + static DEFINE_PER_CPU(struct cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 65214774ef7c..aebfc3733a76 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -25,7 +25,6 @@ #include <linux/ptrace.h> #include <linux/kgdb.h> #include <linux/kdebug.h> -#include <linux/kprobes.h> #include <linux/notifier.h> #include <linux/irq.h> #include <linux/perf_event.h> @@ -35,6 +34,7 @@ #include <asm/branch.h> #include <asm/break.h> #include <asm/cpu.h> +#include <asm/exception.h> #include <asm/fpu.h> #include <asm/lbt.h> #include <asm/inst.h> @@ -53,21 +53,6 @@ #include "access-helper.h" -extern asmlinkage void handle_ade(void); -extern asmlinkage void handle_ale(void); -extern asmlinkage void handle_bce(void); -extern asmlinkage void handle_sys(void); -extern asmlinkage void handle_bp(void); -extern asmlinkage void handle_ri(void); -extern asmlinkage void handle_fpu(void); -extern asmlinkage void handle_fpe(void); -extern asmlinkage void handle_lbt(void); -extern asmlinkage void handle_lsx(void); -extern asmlinkage void handle_lasx(void); -extern asmlinkage void handle_reserved(void); -extern asmlinkage void handle_watch(void); -extern asmlinkage void handle_vint(void); - static void show_backtrace(struct task_struct *task, const struct pt_regs *regs, const char *loglvl, bool user) { @@ -439,8 +424,8 @@ static inline void setup_vint_size(unsigned int size) * happen together with Overflow or Underflow, and `ptrace' can set * any bits. */ -void force_fcsr_sig(unsigned long fcsr, void __user *fault_addr, - struct task_struct *tsk) +static void force_fcsr_sig(unsigned long fcsr, + void __user *fault_addr, struct task_struct *tsk) { int si_code = FPE_FLTUNK; @@ -458,7 +443,7 @@ void force_fcsr_sig(unsigned long fcsr, void __user *fault_addr, force_sig_fault(SIGFPE, si_code, fault_addr); } -int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcsr) +static int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcsr) { int si_code; @@ -824,7 +809,7 @@ out: asmlinkage void noinstr do_ri(struct pt_regs *regs) { int status = SIGILL; - unsigned int opcode = 0; + unsigned int __maybe_unused opcode; unsigned int __user *era = (unsigned int __user *)exception_era(regs); irqentry_state_t state = irqentry_enter(regs); diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index b1686afcf876..bb2ec86f37a8 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -53,33 +53,6 @@ SECTIONS . = ALIGN(PECOFF_SEGMENT_ALIGN); _etext = .; - /* - * struct alt_inst entries. From the header (alternative.h): - * "Alternative instructions for different CPU types or capabilities" - * Think locking instructions on spinlocks. - */ - . = ALIGN(4); - .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { - __alt_instructions = .; - *(.altinstructions) - __alt_instructions_end = .; - } - -#ifdef CONFIG_RELOCATABLE - . = ALIGN(8); - .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) { - __la_abs_begin = .; - *(.la_abs) - __la_abs_end = .; - } -#endif - - .got : ALIGN(16) { *(.got) } - .plt : ALIGN(16) { *(.plt) } - .got.plt : ALIGN(16) { *(.got.plt) } - - .data.rel : { *(.data.rel*) } - . = ALIGN(PECOFF_SEGMENT_ALIGN); __init_begin = .; __inittext_begin = .; @@ -94,6 +67,18 @@ SECTIONS __initdata_begin = .; + /* + * struct alt_inst entries. From the header (alternative.h): + * "Alternative instructions for different CPU types or capabilities" + * Think locking instructions on spinlocks. + */ + . = ALIGN(4); + .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { + __alt_instructions = .; + *(.altinstructions) + __alt_instructions_end = .; + } + INIT_DATA_SECTION(16) .exit.data : { EXIT_DATA @@ -113,6 +98,11 @@ SECTIONS _sdata = .; RO_DATA(4096) + + .got : ALIGN(16) { *(.got) } + .plt : ALIGN(16) { *(.plt) } + .got.plt : ALIGN(16) { *(.got.plt) } + RW_DATA(1 << CONFIG_L1_CACHE_SHIFT, PAGE_SIZE, THREAD_SIZE) .rela.dyn : ALIGN(8) { @@ -121,6 +111,17 @@ SECTIONS __rela_dyn_end = .; } + .data.rel : { *(.data.rel*) } + +#ifdef CONFIG_RELOCATABLE + . = ALIGN(8); + .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) { + __la_abs_begin = .; + *(.la_abs) + __la_abs_end = .; + } +#endif + .sdata : { *(.sdata) } diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index e6376e3dce86..1fc2f6813ea0 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -20,12 +20,12 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kdebug.h> -#include <linux/kprobes.h> #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/kfence.h> #include <asm/branch.h> +#include <asm/exception.h> #include <asm/mmu_context.h> #include <asm/ptrace.h> diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index ba138117b124..1e76fcb83093 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -50,18 +50,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return (pte_t *) pmd; } -/* - * This function checks for proper alignment of input addr and len parameters. - */ -int is_aligned_hugepage_range(unsigned long addr, unsigned long len) -{ - if (len & ~HPAGE_MASK) - return -EINVAL; - if (addr & ~HPAGE_MASK) - return -EINVAL; - return 0; -} - int pmd_huge(pmd_t pmd) { return (pmd_val(pmd) & _PAGE_HUGE) != 0; diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c index 73b0980ab6f5..70ca73019811 100644 --- a/arch/loongarch/mm/ioremap.c +++ b/arch/loongarch/mm/ioremap.c @@ -4,6 +4,7 @@ */ #include <asm/io.h> +#include <asm-generic/early_ioremap.h> void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size) { diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index da68bc1a4643..cc3e81fe0186 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -35,6 +35,57 @@ static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); bool kasan_early_stage = true; +void *kasan_mem_to_shadow(const void *addr) +{ + if (!kasan_arch_is_ready()) { + return (void *)(kasan_early_shadow_page); + } else { + unsigned long maddr = (unsigned long)addr; + unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; + unsigned long offset = 0; + + maddr &= XRANGE_SHADOW_MASK; + switch (xrange) { + case XKPRANGE_CC_SEG: + offset = XKPRANGE_CC_SHADOW_OFFSET; + break; + case XKPRANGE_UC_SEG: + offset = XKPRANGE_UC_SHADOW_OFFSET; + break; + case XKVRANGE_VC_SEG: + offset = XKVRANGE_VC_SHADOW_OFFSET; + break; + default: + WARN_ON(1); + return NULL; + } + + return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset); + } +} + +const void *kasan_shadow_to_mem(const void *shadow_addr) +{ + unsigned long addr = (unsigned long)shadow_addr; + + if (unlikely(addr > KASAN_SHADOW_END) || + unlikely(addr < KASAN_SHADOW_START)) { + WARN_ON(1); + return NULL; + } + + if (addr >= XKVRANGE_VC_SHADOW_OFFSET) + return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START); + else if (addr >= XKPRANGE_UC_SHADOW_OFFSET) + return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START); + else if (addr >= XKPRANGE_CC_SHADOW_OFFSET) + return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START); + else { + WARN_ON(1); + return NULL; + } +} + /* * Alloc memory for shadow memory page table. */ diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index eb8572e201ea..2c0a411f23aa 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -261,7 +261,7 @@ unsigned long pcpu_handlers[NR_CPUS]; #endif extern long exception_handlers[VECSIZE * 128 / sizeof(long)]; -void setup_tlb_handler(int cpu) +static void setup_tlb_handler(int cpu) { setup_ptwalker(); local_flush_tlb_all(); diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index 012da042d0a4..7b9f91db227f 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -164,6 +164,7 @@ static struct platform_device db1x00_audio_dev = { /******************************************************************************/ +#ifdef CONFIG_MMC_AU1X static irqreturn_t db1100_mmc_cd(int irq, void *ptr) { mmc_detect_change(ptr, msecs_to_jiffies(500)); @@ -369,6 +370,7 @@ static struct platform_device db1100_mmc1_dev = { .num_resources = ARRAY_SIZE(au1100_mmc1_res), .resource = au1100_mmc1_res, }; +#endif /* CONFIG_MMC_AU1X */ /******************************************************************************/ @@ -440,8 +442,10 @@ static struct platform_device *db1x00_devs[] = { static struct platform_device *db1100_devs[] = { &au1100_lcd_device, +#ifdef CONFIG_MMC_AU1X &db1100_mmc0_dev, &db1100_mmc1_dev, +#endif }; int __init db1000_dev_setup(void) diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c index 76080c71a2a7..f521874ebb07 100644 --- a/arch/mips/alchemy/devboards/db1200.c +++ b/arch/mips/alchemy/devboards/db1200.c @@ -326,6 +326,7 @@ static struct platform_device db1200_ide_dev = { /**********************************************************************/ +#ifdef CONFIG_MMC_AU1X /* SD carddetects: they're supposed to be edge-triggered, but ack * doesn't seem to work (CPLD Rev 2). Instead, the screaming one * is disabled and its counterpart enabled. The 200ms timeout is @@ -584,6 +585,7 @@ static struct platform_device pb1200_mmc1_dev = { .num_resources = ARRAY_SIZE(au1200_mmc1_res), .resource = au1200_mmc1_res, }; +#endif /* CONFIG_MMC_AU1X */ /**********************************************************************/ @@ -751,7 +753,9 @@ static struct platform_device db1200_audiodma_dev = { static struct platform_device *db1200_devs[] __initdata = { NULL, /* PSC0, selected by S6.8 */ &db1200_ide_dev, +#ifdef CONFIG_MMC_AU1X &db1200_mmc0_dev, +#endif &au1200_lcd_dev, &db1200_eth_dev, &db1200_nand_dev, @@ -762,7 +766,9 @@ static struct platform_device *db1200_devs[] __initdata = { }; static struct platform_device *pb1200_devs[] __initdata = { +#ifdef CONFIG_MMC_AU1X &pb1200_mmc1_dev, +#endif }; /* Some peripheral base addresses differ on the PB1200 */ diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c index ff61901329c6..d377e043b49f 100644 --- a/arch/mips/alchemy/devboards/db1300.c +++ b/arch/mips/alchemy/devboards/db1300.c @@ -450,6 +450,7 @@ static struct platform_device db1300_ide_dev = { /**********************************************************************/ +#ifdef CONFIG_MMC_AU1X static irqreturn_t db1300_mmc_cd(int irq, void *ptr) { disable_irq_nosync(irq); @@ -632,6 +633,7 @@ static struct platform_device db1300_sd0_dev = { .resource = au1300_sd0_res, .num_resources = ARRAY_SIZE(au1300_sd0_res), }; +#endif /* CONFIG_MMC_AU1X */ /**********************************************************************/ @@ -767,8 +769,10 @@ static struct platform_device *db1300_dev[] __initdata = { &db1300_5waysw_dev, &db1300_nand_dev, &db1300_ide_dev, +#ifdef CONFIG_MMC_AU1X &db1300_sd0_dev, &db1300_sd1_dev, +#endif &db1300_lcd_dev, &db1300_ac97_dev, &db1300_i2s_dev, diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index f7f078c2872c..72daacc472a0 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -6,7 +6,7 @@ #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); + pte_t *ptep, pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index a8a1a7c1e16e..a9f7e21f6656 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -140,7 +140,7 @@ static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t entry) + pte_t *ptep, pte_t entry, unsigned long sz) { __set_huge_pte_at(mm, addr, ptep, entry); } diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index de092b04ee1a..92df40c6cc6b 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift) } #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index b15f15dcacb5..e6a958a5da27 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -73,29 +73,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum bool firstframe; stack_end = stack_page + THREAD_SIZE; - if (!is_idle_task(task)) { - /* - * For user tasks, this is the SP value loaded on - * kernel entry, see "PACAKSAVE(r13)" in _switch() and - * system_call_common(). - * - * Likewise for non-swapper kernel threads, - * this also happens to be the top of the stack - * as setup by copy_thread(). - * - * Note that stack backlinks are not properly setup by - * copy_thread() and thus, a forked task() will have - * an unreliable stack trace until it's been - * _switch()'ed to for the first time. - */ - stack_end -= STACK_USER_INT_FRAME_SIZE; - } else { - /* - * idle tasks have a custom stack layout, - * c.f. cpu_idle_thread_init(). - */ + + // See copy_thread() for details. + if (task->flags & PF_KTHREAD) stack_end -= STACK_FRAME_MIN_SIZE; - } + else + stack_end -= STACK_USER_INT_FRAME_SIZE; if (task == current) sp = current_stack_frame(); diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c index 3bc0eb21b2a0..5a2e512e96db 100644 --- a/arch/powerpc/mm/book3s64/hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hugetlbpage.c @@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { + unsigned long psize; if (radix_enabled()) return radix__huge_ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + + psize = huge_page_size(hstate_vma(vma)); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } void __init hugetlbpage_init_defaultsize(void) diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index 17075c78d4bc..35fd2a95be24 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, pte_t old_pte, pte_t pte) { struct mm_struct *mm = vma->vm_mm; + unsigned long psize = huge_page_size(hstate_vma(vma)); /* * POWER9 NMMU must flush the TLB after clearing the PTE before @@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, atomic_read(&mm->context.copros) > 0) radix__flush_hugetlb_page(vma, addr); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index dbbfe897455d..a642a7929892 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -91,7 +91,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa, if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot))) return -EINVAL; - set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot))); + set_huge_pte_at(&init_mm, va, ptep, + pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize); return 0; } diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 3f86fd217690..3ba9fe411604 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -288,7 +288,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, } #if defined(CONFIG_PPC_8xx) -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz) { pmd_t *pmd = pmd_off(mm, addr); pte_basic_t val; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi index d79f94432b27..12ebe9792356 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -262,7 +262,7 @@ reg = <0x100000 0x400000>; }; reserved-data@600000 { - reg = <0x600000 0x1000000>; + reg = <0x600000 0xa00000>; }; }; }; @@ -440,30 +440,6 @@ }; }; - uart0_pins: uart0-0 { - tx-pins { - pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX, - GPOEN_ENABLE, - GPI_NONE)>; - bias-disable; - drive-strength = <12>; - input-disable; - input-schmitt-disable; - slew-rate = <0>; - }; - - rx-pins { - pinmux = <GPIOMUX(6, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_UART0_RX)>; - bias-disable; /* external pull-up */ - drive-strength = <2>; - input-enable; - input-schmitt-enable; - slew-rate = <0>; - }; - }; - tdm_pins: tdm-0 { tx-pins { pinmux = <GPIOMUX(44, GPOUT_SYS_TDM_TXD, @@ -497,6 +473,30 @@ input-enable; }; }; + + uart0_pins: uart0-0 { + tx-pins { + pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX, + GPOEN_ENABLE, + GPI_NONE)>; + bias-disable; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pinmux = <GPIOMUX(6, GPOUT_LOW, + GPOEN_DISABLE, + GPI_SYS_UART0_RX)>; + bias-disable; /* external pull-up */ + drive-strength = <2>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; }; &tdm { @@ -513,6 +513,7 @@ &usb0 { dr_mode = "peripheral"; + status = "okay"; }; &U74_1 { diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 34e24f078cc1..4c5b0e929890 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -18,7 +18,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr, #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pte_t pte); + unsigned long addr, pte_t *ptep, pte_t pte, + unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR pte_t huge_ptep_get_and_clear(struct mm_struct *mm, diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index 1b7e9fa265cb..b7e0e03c69b1 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -460,8 +460,11 @@ static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu, reg_num >= ARRAY_SIZE(kvm_isa_ext_arr)) return -ENOENT; - *reg_val = 0; host_isa_ext = kvm_isa_ext_arr[reg_num]; + if (!__riscv_isa_extension_available(NULL, host_isa_ext)) + return -ENOENT; + + *reg_val = 0; if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext)) *reg_val = 1; /* Mark the given extension as available */ @@ -842,7 +845,7 @@ static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu, u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i; isa_ext = kvm_isa_ext_arr[i]; - if (!__riscv_isa_extension_available(vcpu->arch.isa, isa_ext)) + if (!__riscv_isa_extension_available(NULL, isa_ext)) continue; if (uindices) { diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 96225a8533ad..e4a2ace92dbe 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -180,7 +180,8 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte) + pte_t pte, + unsigned long sz) { int i, pte_num; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index af2fbe48e16c..438cd92e6080 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -40,23 +40,25 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_ZEC12=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_SIG=y +CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m -CONFIG_CRASH_DUMP=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y +CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m @@ -434,6 +436,7 @@ CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y +# CONFIG_MD_BITMAP_FILE is not set CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m @@ -577,6 +580,7 @@ CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m # CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y +# CONFIG_FB_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID_SUPPORT is not set @@ -647,6 +651,7 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y +CONFIG_TMPFS_QUOTA=y CONFIG_HUGETLBFS=y CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m @@ -703,6 +708,7 @@ CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_INIT_STACK_NONE=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m @@ -825,9 +831,9 @@ CONFIG_LOCK_STAT=y CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_IRQFLAGS=y +CONFIG_DEBUG_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y -CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 3f263b767a4c..1b8150e50f6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -38,23 +38,25 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_ZEC12=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_SIG=y +CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m -CONFIG_CRASH_DUMP=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y +CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m @@ -424,6 +426,7 @@ CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y +# CONFIG_MD_BITMAP_FILE is not set CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m @@ -566,6 +569,7 @@ CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m CONFIG_FB=y +# CONFIG_FB_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID_SUPPORT is not set @@ -632,6 +636,7 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y +CONFIG_TMPFS_QUOTA=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -687,6 +692,7 @@ CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_INIT_STACK_NONE=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -781,7 +787,6 @@ CONFIG_PTDUMP_DEBUGFS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y CONFIG_TEST_LOCKUP=m -CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index e62fb2015102..b831083b4edd 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_CRASH_DUMP=y CONFIG_MARCH_ZEC12=y CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set @@ -15,9 +16,8 @@ CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set -CONFIG_CRASH_DUMP=y # CONFIG_PFAULT is not set -# CONFIG_S390_HYPFS_FS is not set +# CONFIG_S390_HYPFS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index f07267875a19..deb198a61039 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -16,6 +16,8 @@ #define hugepages_supported() (MACHINE_HAS_EDAT1) void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz); +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, @@ -65,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(huge_ptep_get(ptep), pte); if (changed) { huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); } return changed; } @@ -74,7 +76,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep); - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); } static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c index 3986a044eb36..554447768bdd 100644 --- a/arch/s390/kernel/cert_store.c +++ b/arch/s390/kernel/cert_store.c @@ -432,15 +432,16 @@ static char *get_key_description(struct vcssb *vcssb, const struct vce *vce) char *desc; cs_token = vcssb->cs_token; - /* Description string contains "%64s:%04u:%08u\0". */ + /* Description string contains "%64s:%05u:%010u\0". */ name_len = sizeof(vce->vce_hdr.vc_name); - len = name_len + 1 + 4 + 1 + 8 + 1; + len = name_len + 1 + 5 + 1 + 10 + 1; desc = kmalloc(len, GFP_KERNEL); if (!desc) return NULL; memcpy(desc, vce->vce_hdr.vc_name, name_len); - sprintf(desc + name_len, ":%04u:%08u", vce->vce_hdr.vc_index, cs_token); + snprintf(desc + name_len, len - name_len, ":%05u:%010u", + vce->vce_hdr.vc_index, cs_token); return desc; } diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c718f2a0de94..297a6d897d5a 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -142,7 +142,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) __storage_key_init_range(paddr, paddr + size - 1); } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { unsigned long rste; @@ -163,6 +163,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, __pte(rste)); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz) +{ + __set_huge_pte_at(mm, addr, ptep, pte); +} + pte_t huge_ptep_get(pte_t *ptep) { return __rste_to_pte(pte_val(*ptep)); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index eeb42e5cd7d6..e6a643f63ebf 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2513,7 +2513,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, return -E2BIG; } - return ret; + return tjit.common.prg; } bool bpf_jit_supports_subprog_tailcalls(void) diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c index c33b3daa4ad1..33d20f34560f 100644 --- a/arch/sh/mm/ioremap.c +++ b/arch/sh/mm/ioremap.c @@ -72,8 +72,8 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot) #define __ioremap_29bit(offset, size, prot) NULL #endif /* CONFIG_29BIT */ -void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) +void __iomem __ref *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { void __iomem *mapped; pgprot_t pgprot = __pgprot(prot); diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 0a26cca24232..c714ca6a05aa 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -14,6 +14,8 @@ extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end; #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz); +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR @@ -32,7 +34,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t old_pte = *ptep; - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); } #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS @@ -42,7 +44,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, { int changed = !pte_same(*ptep, pte); if (changed) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); flush_tlb_page(vma, addr); } return changed; diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index d7018823206c..b432500c13a5 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -328,7 +328,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte_offset_huge(pmd, addr); } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { unsigned int nptes, orig_shift, shift; @@ -364,6 +364,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, orig_shift); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry, unsigned long sz) +{ + __set_huge_pte_at(mm, addr, ptep, entry); +} + pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index abadd5f23425..e24976593a29 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu) /* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */ wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0); - /* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */ - wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask); + /* + * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze + * and PerfCntrGLobalStatus.PerfCntrOvfl + */ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, + GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask); } static int amd_pmu_cpu_prepare(int cpu) @@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu) int i, nb_id; cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; + amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; - - amd_pmu_cpu_reset(cpu); } static void amd_pmu_cpu_dead(int cpu) @@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; + amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw->amd_nb = NULL; } - - amd_pmu_cpu_reset(cpu); } static inline void amd_pmu_set_global_ctl(u64 ctl) @@ -884,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) struct hw_perf_event *hwc; struct perf_event *event; int handled = 0, idx; - u64 status, mask; + u64 reserved, status, mask; bool pmu_enabled; /* @@ -909,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) status &= ~GLOBAL_STATUS_LBRS_FROZEN; } + reserved = status & ~amd_pmu_global_cntr_mask; + if (reserved) + pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n", + reserved); + + /* Clear any reserved bits set by buggy microcode */ + status &= amd_pmu_global_cntr_mask; + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1a4def36d5bb..17715cb8731d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1419,7 +1419,6 @@ struct kvm_arch { * the thread holds the MMU lock in write mode. */ spinlock_t tdp_mmu_pages_lock; - struct workqueue_struct *tdp_mmu_zap_wq; #endif /* CONFIG_X86_64 */ /* @@ -1835,7 +1834,7 @@ void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -int kvm_mmu_init_vm(struct kvm *kvm); +void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 5ff49fd67732..571fe4d2d232 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -105,6 +105,13 @@ CFI_POST_PADDING \ SYM_FUNC_END(__cfi_##name) +/* UML needs to be able to override memcpy() and friends for KASAN. */ +#ifdef CONFIG_UML +# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS_WEAK +#else +# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS +#endif + /* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ #define SYM_TYPED_FUNC_START(name) \ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 416901d406f8..8dac45a2c7fc 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -186,8 +186,7 @@ do { \ #else #define deactivate_mm(tsk, mm) \ do { \ - if (!tsk->vfork_done) \ - shstk_free(tsk); \ + shstk_free(tsk); \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d6ad98ca1288..e02b179ec659 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -955,6 +955,14 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } +static inline pte_t pte_next_pfn(pte_t pte) +{ + if (__pte_needs_invert(pte_val(pte))) + return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT)); + return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); +} +#define pte_next_pfn pte_next_pfn + static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 0086920cda06..a3669a7774ed 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -683,13 +683,11 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); -extern bool cpu_has_ibpb_brtype_microcode(void); extern void amd_clear_divider(void); extern void amd_check_microcode(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } -static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } static inline void amd_clear_divider(void) { } static inline void amd_check_microcode(void) { } #endif diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a5ead6a6d233..517ee01503be 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -720,13 +720,8 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { s32 *s; - /* - * Do not patch out the default return thunks if those needed are the - * ones generated by the compiler. - */ - if (cpu_feature_enabled(X86_FEATURE_RETHUNK) && - (x86_return_thunk == __x86_return_thunk)) - return; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + static_call_force_reinit(); for (s = start; s < end; s++) { void *dest = NULL, *addr = (void *)s + *s; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index c06bfc086565..faa9f2299848 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -272,7 +272,6 @@ void __init callthunks_patch_builtin_calls(void) pr_info("Setting up call depth tracking\n"); mutex_lock(&text_mutex); callthunks_setup(&cs, &builtin_coretext); - static_call_force_reinit(); thunks_initialized = true; mutex_unlock(&text_mutex); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dd8379d84445..03ef962a6992 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -766,6 +766,15 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_TOPOEXT)) smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) { + if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB)) + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + setup_force_cpu_cap(X86_FEATURE_SBPB); + } + } } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -1301,25 +1310,6 @@ void amd_check_microcode(void) on_each_cpu(zenbleed_check_cpu, NULL, 1); } -bool cpu_has_ibpb_brtype_microcode(void) -{ - switch (boot_cpu_data.x86) { - /* Zen1/2 IBPB flushes branch type predictions too. */ - case 0x17: - return boot_cpu_has(X86_FEATURE_AMD_IBPB); - case 0x19: - /* Poke the MSR bit on Zen3/4 to check its presence. */ - if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { - setup_force_cpu_cap(X86_FEATURE_SBPB); - return true; - } else { - return false; - } - default: - return false; - } -} - /* * Issue a DIV 0/1 insn to clear any division data from previous DIV * operations. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f081d26616ac..10499bcd4e39 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2404,27 +2404,16 @@ early_param("spec_rstack_overflow", srso_parse_cmdline); static void __init srso_select_mitigation(void) { - bool has_microcode; + bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE); if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) goto pred_cmd; - /* - * The first check is for the kernel running as a guest in order - * for guests to verify whether IBPB is a viable mitigation. - */ - has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); if (!has_microcode) { pr_warn("IBPB-extending microcode not applied!\n"); pr_warn(SRSO_NOTICE); } else { /* - * Enable the synthetic (even if in a real CPUID leaf) - * flags for guests. - */ - setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); - - /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. */ @@ -2444,7 +2433,7 @@ static void __init srso_select_mitigation(void) switch (srso_cmd) { case SRSO_CMD_OFF: - return; + goto pred_cmd; case SRSO_CMD_MICROCODE: if (has_microcode) { @@ -2717,7 +2706,7 @@ static ssize_t srso_show_state(char *buf) return sysfs_emit(buf, "%s%s\n", srso_strings[srso_mitigation], - (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); + boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode"); } static ssize_t gds_show_state(char *buf) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 382d4e6b848d..4e5ffc8b0e46 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1303,7 +1303,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), - VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), VULNBL_AMD(0x19, SRSO), {} }; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 91fa70e51004..279148e72459 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -235,6 +235,21 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page, return epc_page; } +/* + * Ensure the SECS page is not swapped out. Must be called with encl->lock + * to protect the enclave states including SECS and ensure the SECS page is + * not swapped out again while being used. + */ +static struct sgx_epc_page *sgx_encl_load_secs(struct sgx_encl *encl) +{ + struct sgx_epc_page *epc_page = encl->secs.epc_page; + + if (!epc_page) + epc_page = sgx_encl_eldu(&encl->secs, NULL); + + return epc_page; +} + static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, struct sgx_encl_page *entry) { @@ -248,11 +263,9 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, return entry; } - if (!(encl->secs.epc_page)) { - epc_page = sgx_encl_eldu(&encl->secs, NULL); - if (IS_ERR(epc_page)) - return ERR_CAST(epc_page); - } + epc_page = sgx_encl_load_secs(encl); + if (IS_ERR(epc_page)) + return ERR_CAST(epc_page); epc_page = sgx_encl_eldu(entry, encl->secs.epc_page); if (IS_ERR(epc_page)) @@ -339,6 +352,13 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, mutex_lock(&encl->lock); + epc_page = sgx_encl_load_secs(encl); + if (IS_ERR(epc_page)) { + if (PTR_ERR(epc_page) == -EBUSY) + vmret = VM_FAULT_NOPAGE; + goto err_out_unlock; + } + epc_page = sgx_alloc_epc_page(encl_page, false); if (IS_ERR(epc_page)) { if (PTR_ERR(epc_page) == -EBUSY) diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 3a43a2dee658..9c9faa1634fb 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -695,7 +695,6 @@ void kgdb_arch_exit(void) } /** - * * kgdb_skipexception - Bail out of KGDB when we've been triggered. * @exception: Exception vector number * @regs: Current &struct pt_regs. diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9f0909142a0a..b6f4e8399fca 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -257,13 +257,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP))) io_bitmap_share(p); - /* - * If copy_thread() if failing, don't leak the shadow stack possibly - * allocated in shstk_alloc_thread_stack() above. - */ - if (ret) - shstk_free(p); - return ret; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b9145a63da77..b098b1fa2470 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -358,15 +358,11 @@ static void __init add_early_ima_buffer(u64 phys_addr) #if defined(CONFIG_HAVE_IMA_KEXEC) && !defined(CONFIG_OF_FLATTREE) int __init ima_free_kexec_buffer(void) { - int rc; - if (!ima_kexec_buffer_size) return -ENOENT; - rc = memblock_phys_free(ima_kexec_buffer_phys, - ima_kexec_buffer_size); - if (rc) - return rc; + memblock_free_late(ima_kexec_buffer_phys, + ima_kexec_buffer_size); ima_kexec_buffer_phys = 0; ima_kexec_buffer_size = 0; diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index fd689921a1db..59e15dd8d0f8 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -205,10 +205,21 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long cl return 0; /* - * For CLONE_VM, except vfork, the child needs a separate shadow + * For CLONE_VFORK the child will share the parents shadow stack. + * Make sure to clear the internal tracking of the thread shadow + * stack so the freeing logic run for child knows to leave it alone. + */ + if (clone_flags & CLONE_VFORK) { + shstk->base = 0; + shstk->size = 0; + return 0; + } + + /* + * For !CLONE_VM the child will use a copy of the parents shadow * stack. */ - if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) + if (!(clone_flags & CLONE_VM)) return 0; size = adjust_shstk_size(stack_size); @@ -408,7 +419,25 @@ void shstk_free(struct task_struct *tsk) if (!tsk->mm || tsk->mm != current->mm) return; + /* + * If shstk->base is NULL, then this task is not managing its + * own shadow stack (CLONE_VFORK). So skip freeing it. + */ + if (!shstk->base) + return; + + /* + * shstk->base is NULL for CLONE_VFORK child tasks, and so is + * normal. But size = 0 on a shstk->base is not normal and + * indicated an attempt to free the thread shadow stack twice. + * Warn about it. + */ + if (WARN_ON(!shstk->size)) + return; + unmap_shadow_stack(shstk->base, shstk->size); + + shstk->size = 0; } static int wrss_control(bool enable) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e1d011c67cc6..f7901cb4d2fa 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6167,20 +6167,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -int kvm_mmu_init_vm(struct kvm *kvm) +void kvm_mmu_init_vm(struct kvm *kvm) { - int r; - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (tdp_mmu_enabled) { - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; - } + if (tdp_mmu_enabled) + kvm_mmu_init_tdp_mmu(kvm); kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; @@ -6189,8 +6184,6 @@ int kvm_mmu_init_vm(struct kvm *kvm) kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; - - return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) @@ -6246,7 +6239,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; - int i; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; @@ -6257,11 +6249,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (tdp_mmu_enabled) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, true, flush); - } + if (tdp_mmu_enabled) + flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b102014e2c60..decc1f153669 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -58,7 +58,12 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; - u8 mmu_valid_gen; + union { + u8 mmu_valid_gen; + + /* Only accessed under slots_lock. */ + bool tdp_mmu_scheduled_root_to_zap; + }; /* * The shadow page can't be replaced by an equivalent huge page @@ -100,13 +105,7 @@ struct kvm_mmu_page { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; }; - union { - DECLARE_BITMAP(unsync_child_bitmap, 512); - struct { - struct work_struct tdp_mmu_async_work; - void *tdp_mmu_async_data; - }; - }; + DECLARE_BITMAP(unsync_child_bitmap, 512); /* * Tracks shadow pages that, if zapped, would allow KVM to create an NX diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6c63f2d1675f..6cd4dd631a2f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -12,18 +12,10 @@ #include <trace/events/kvm.h> /* Initializes the TDP MMU for the VM, if enabled. */ -int kvm_mmu_init_tdp_mmu(struct kvm *kvm) +void kvm_mmu_init_tdp_mmu(struct kvm *kvm) { - struct workqueue_struct *wq; - - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); - if (!wq) - return -ENOMEM; - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - kvm->arch.tdp_mmu_zap_wq = wq; - return 1; } /* Arbitrarily returns true so that this may be used in if statements. */ @@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * ultimately frees all roots. */ kvm_tdp_mmu_invalidate_all_roots(kvm); - - /* - * Destroying a workqueue also first flushes the workqueue, i.e. no - * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). - */ - destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); + kvm_tdp_mmu_zap_invalidated_roots(kvm); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* * Ensure that all the outstanding RCU callbacks to free shadow pages - * can run before the VM is torn down. Work items on tdp_mmu_zap_wq - * can call kvm_tdp_mmu_put_root and create new callbacks. + * can run before the VM is torn down. Putting the last reference to + * zapped roots will create new callbacks. */ rcu_barrier(); } @@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); - -static void tdp_mmu_zap_root_work(struct work_struct *work) -{ - struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page, - tdp_mmu_async_work); - struct kvm *kvm = root->tdp_mmu_async_data; - - read_lock(&kvm->mmu_lock); - - /* - * A TLB flush is not necessary as KVM performs a local TLB flush when - * allocating a new root (see kvm_mmu_load()), and when migrating vCPU - * to a different pCPU. Note, the local TLB flush on reuse also - * invalidates any paging-structure-cache entries, i.e. TLB entries for - * intermediate paging structures, that may be zapped, as such entries - * are associated with the ASID on both VMX and SVM. - */ - tdp_mmu_zap_root(kvm, root, true); - - /* - * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for - * avoiding an infinite loop. By design, the root is reachable while - * it's being asynchronously zapped, thus a different task can put its - * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an - * asynchronously zapped root is unavoidable. - */ - kvm_tdp_mmu_put_root(kvm, root, true); - - read_unlock(&kvm->mmu_lock); -} - -static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root) -{ - root->tdp_mmu_async_data = kvm; - INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work); - queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false) +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \ + _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \ + if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \ + } else /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * by a memslot update or by the destruction of the VM. Initialize the * refcount to two; one reference for the vCPU, and one reference for * the TDP MMU itself, which is held until the root is invalidated and - * is ultimately put by tdp_mmu_zap_root_work(). + * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); @@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or * more SPTEs were zapped since the MMU lock was last acquired. */ -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool can_yield, bool flush) +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); + for_each_tdp_mmu_root_yield_safe(kvm, root, false) + flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; } @@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *root; - int i; /* * Zap all roots, including invalid roots, as all SPTEs must be dropped @@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - for_each_tdp_mmu_root_yield_safe(kvm, root, i) - tdp_mmu_zap_root(kvm, root, false); - } + for_each_tdp_mmu_root_yield_safe(kvm, root, false) + tdp_mmu_zap_root(kvm, root, false); } /* @@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + struct kvm_mmu_page *root; + + read_lock(&kvm->mmu_lock); + + for_each_tdp_mmu_root_yield_safe(kvm, root, true) { + if (!root->tdp_mmu_scheduled_root_to_zap) + continue; + + root->tdp_mmu_scheduled_root_to_zap = false; + KVM_BUG_ON(!root->role.invalid, kvm); + + /* + * A TLB flush is not necessary as KVM performs a local TLB + * flush when allocating a new root (see kvm_mmu_load()), and + * when migrating a vCPU to a different pCPU. Note, the local + * TLB flush on reuse also invalidates paging-structure-cache + * entries, i.e. TLB entries for intermediate paging structures, + * that may be zapped, as such entries are associated with the + * ASID on both VMX and SVM. + */ + tdp_mmu_zap_root(kvm, root, true); + + /* + * The referenced needs to be put *after* zapping the root, as + * the root must be reachable by mmu_notifiers while it's being + * zapped + */ + kvm_tdp_mmu_put_root(kvm, root, true); + } + + read_unlock(&kvm->mmu_lock); } /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously. Using a separate workqueue makes it - * easy to ensure that the destruction is performed before the "fast zap" - * completes, without keeping a separate list of invalidated roots; the list is - * effectively the list of work items in the workqueue. + * zapping is done separately so that it happens with mmu_lock with read, + * whereas invalidating roots must be done with mmu_lock held for write (unless + * the VM is being destroyed). * - * Note, the asynchronous worker is gifted the TDP MMU's reference. + * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) @@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) /* * As above, mmu_lock isn't held when destroying the VM! There can't * be other references to @kvm, i.e. nothing else can invalidate roots - * or be consuming roots, but walking the list of roots does need to be - * guarded against roots being deleted by the asynchronous zap worker. + * or get/put references to roots. */ - rcu_read_lock(); - - list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + /* + * Note, invalid roots can outlive a memslot update! Invalid + * roots must be *zapped* before the memslot update completes, + * but a different task can acquire a reference and keep the + * root alive after its been zapped. + */ if (!root->role.invalid) { + root->tdp_mmu_scheduled_root_to_zap = true; root->role.invalid = true; - tdp_mmu_schedule_zap_root(kvm, root); } } - - rcu_read_unlock(); } /* @@ -1146,8 +1123,13 @@ retry: bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + struct kvm_mmu_page *root; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) + flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, + range->may_block, flush); + + return flush; } typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 0a63b1afabd3..733a3aef3a96 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,7 +7,7 @@ #include "spte.h" -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); @@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index b9a0a939d59f..4900c078045a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } +} + +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_cpuid_entry2 *best; + + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); + if (best) + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_vcpu_after_set_cpuid(svm); +} + static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); - - if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && - (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) { - set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); - if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP)) - svm_clr_intercept(svm, INTERCEPT_RDTSCP); - } } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f283eb47f6ac..9507df93f410 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -683,6 +683,21 @@ static int svm_hardware_enable(void) amd_pmu_enable_virt(); + /* + * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type + * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests. + * Since Linux does not change the value of TSC_AUX once set, prime the + * TSC_AUX field now to avoid a RDMSR on every vCPU run. + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + struct sev_es_save_area *hostsa; + u32 msr_hi; + + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); + + rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi); + } + return 0; } @@ -1532,7 +1547,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); - if (likely(tsc_aux_uret_slot >= 0)) + /* + * TSC_AUX is always virtualized for SEV-ES guests when the feature is + * available. The user return MSR support is not required in this case + * because TSC_AUX is restored on #VMEXIT from the host save area + * (which has been initialized in svm_hardware_enable()). + */ + if (likely(tsc_aux_uret_slot >= 0) && + (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; @@ -3087,6 +3109,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_TSC_AUX: /* + * TSC_AUX is always virtualized for SEV-ES guests when the + * feature is available. The user return MSR support is not + * required in this case because TSC_AUX is restored on #VMEXIT + * from the host save area (which has been initialized in + * svm_hardware_enable()). + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) + break; + + /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the * guest via direct_access_msrs, and switch it via user return. @@ -4284,7 +4316,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_cpuid_entry2 *best; /* * SVM doesn't provide a way to disable just XSAVES in the guest, KVM @@ -4328,12 +4359,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); - /* For sev guests, the memory encryption bit is not reserved in CR3. */ - if (sev_guest(vcpu->kvm)) { - best = kvm_find_cpuid_entry(vcpu, 0x8000001F); - if (best) - vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); - } + if (sev_guest(vcpu->kvm)) + sev_vcpu_after_set_cpuid(svm); init_vmcb_after_set_cpuid(vcpu); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f41253958357..be67ab7fdd10 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -684,6 +684,7 @@ void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c9c81e82e65..9f18b06bbda6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12308,9 +12308,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out; - ret = kvm_mmu_init_vm(kvm); - if (ret) - goto out_page_track; + kvm_mmu_init_vm(kvm); ret = static_call(kvm_x86_vm_init)(kvm); if (ret) @@ -12355,7 +12353,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) out_uninit_mmu: kvm_mmu_uninit_vm(kvm); -out_page_track: kvm_page_track_cleanup(kvm); out: return ret; diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 8f95fb267caa..76697df8dfd5 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -40,7 +40,7 @@ SYM_TYPED_FUNC_START(__memcpy) SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) -SYM_FUNC_ALIAS(memcpy, __memcpy) +SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_START_LOCAL(memcpy_orig) diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 0559b206fb11..ccdf3a597045 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -212,5 +212,5 @@ SYM_FUNC_START(__memmove) SYM_FUNC_END(__memmove) EXPORT_SYMBOL(__memmove) -SYM_FUNC_ALIAS(memmove, __memmove) +SYM_FUNC_ALIAS_MEMFUNC(memmove, __memmove) EXPORT_SYMBOL(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 7c59a704c458..3d818b849ec6 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -40,7 +40,7 @@ SYM_FUNC_START(__memset) SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) -SYM_FUNC_ALIAS(memset, __memset) +SYM_FUNC_ALIAS_MEMFUNC(memset, __memset) EXPORT_SYMBOL(memset) SYM_FUNC_START_LOCAL(memset_orig) diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile index a65b7a9ebff2..d8b0fadf429a 100644 --- a/arch/xtensa/boot/Makefile +++ b/arch/xtensa/boot/Makefile @@ -9,8 +9,7 @@ # KBUILD_CFLAGS used when building rest of boot (takes effect recursively) -KBUILD_CFLAGS += -fno-builtin -Iarch/$(ARCH)/boot/include -HOSTFLAGS += -Iarch/$(ARCH)/boot/include +KBUILD_CFLAGS += -fno-builtin subdir-y := lib targets += vmlinux.bin vmlinux.bin.gz diff --git a/arch/xtensa/boot/lib/zmem.c b/arch/xtensa/boot/lib/zmem.c index e3ecd743c515..b89189355122 100644 --- a/arch/xtensa/boot/lib/zmem.c +++ b/arch/xtensa/boot/lib/zmem.c @@ -4,13 +4,14 @@ /* bits taken from ppc */ extern void *avail_ram, *end_avail; +void gunzip(void *dst, int dstlen, unsigned char *src, int *lenp); -void exit (void) +static void exit(void) { for (;;); } -void *zalloc(unsigned size) +static void *zalloc(unsigned int size) { void *p = avail_ram; diff --git a/arch/xtensa/include/asm/core.h b/arch/xtensa/include/asm/core.h index 3f5ffae89b58..6f02f6f21890 100644 --- a/arch/xtensa/include/asm/core.h +++ b/arch/xtensa/include/asm/core.h @@ -6,6 +6,10 @@ #include <variant/core.h> +#ifndef XCHAL_HAVE_DIV32 +#define XCHAL_HAVE_DIV32 0 +#endif + #ifndef XCHAL_HAVE_EXCLUSIVE #define XCHAL_HAVE_EXCLUSIVE 0 #endif diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h index 9f119c1ca0b5..9ec86f440a48 100644 --- a/arch/xtensa/include/asm/hw_breakpoint.h +++ b/arch/xtensa/include/asm/hw_breakpoint.h @@ -48,6 +48,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp); void hw_breakpoint_pmu_read(struct perf_event *bp); int check_hw_breakpoint(struct pt_regs *regs); void clear_ptrace_hw_breakpoint(struct task_struct *tsk); +void restore_dbreak(void); #else diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index a6d09fe04831..d008a153a2b9 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -14,6 +14,8 @@ #include <linux/compiler.h> #include <linux/stringify.h> + +#include <asm/bootparam.h> #include <asm/ptrace.h> #include <asm/types.h> #include <asm/regs.h> @@ -217,6 +219,9 @@ struct mm_struct; extern unsigned long __get_wchan(struct task_struct *p); +void init_arch(bp_tag_t *bp_start); +void do_notify_resume(struct pt_regs *regs); + #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1]) diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h index 308f209a4740..a270467556dc 100644 --- a/arch/xtensa/include/asm/ptrace.h +++ b/arch/xtensa/include/asm/ptrace.h @@ -106,6 +106,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->areg[2]; } +int do_syscall_trace_enter(struct pt_regs *regs); +void do_syscall_trace_leave(struct pt_regs *regs); + #else /* __ASSEMBLY__ */ # include <asm/asm-offsets.h> diff --git a/arch/xtensa/include/asm/smp.h b/arch/xtensa/include/asm/smp.h index 5dc5bf8cdd77..e446e6fc4557 100644 --- a/arch/xtensa/include/asm/smp.h +++ b/arch/xtensa/include/asm/smp.h @@ -23,6 +23,7 @@ struct cpumask; void arch_send_call_function_ipi_mask(const struct cpumask *mask); void arch_send_call_function_single_ipi(int cpu); +void secondary_start_kernel(void); void smp_init_cpus(void); void secondary_init_irq(void); void ipi_init(void); diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h index 50889935138a..8c3ceb427018 100644 --- a/arch/xtensa/include/asm/tlb.h +++ b/arch/xtensa/include/asm/tlb.h @@ -18,4 +18,6 @@ #define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte) +void check_tlb_sanity(void); + #endif /* _XTENSA_TLB_H */ diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c index 285fb2942b06..1eeecd58eb0c 100644 --- a/arch/xtensa/kernel/hw_breakpoint.c +++ b/arch/xtensa/kernel/hw_breakpoint.c @@ -13,6 +13,7 @@ #include <linux/percpu.h> #include <linux/perf_event.h> #include <asm/core.h> +#include <asm/hw_breakpoint.h> /* Breakpoint currently in use for each IBREAKA. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[XCHAL_NUM_IBREAK]); diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c index 42f106004400..b1e410f6b5ab 100644 --- a/arch/xtensa/kernel/irq.c +++ b/arch/xtensa/kernel/irq.c @@ -28,6 +28,7 @@ #include <asm/mxregs.h> #include <linux/uaccess.h> #include <asm/platform.h> +#include <asm/traps.h> DECLARE_PER_CPU(unsigned long, nmi_count); diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index f29477162ede..9056cd1a8302 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -541,7 +541,6 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -void do_syscall_trace_leave(struct pt_regs *regs); int do_syscall_trace_enter(struct pt_regs *regs) { if (regs->syscall == NO_SYSCALL) diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 5c01d7e70d90..81f0b106cfc1 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -26,6 +26,8 @@ #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/coprocessor.h> +#include <asm/processor.h> +#include <asm/syscall.h> #include <asm/unistd.h> extern struct task_struct *coproc_owners[]; diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 07dd6baf18cf..94a23f100726 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -21,6 +21,7 @@ #include <linux/irq.h> #include <linux/kdebug.h> #include <linux/module.h> +#include <linux/profile.h> #include <linux/sched/mm.h> #include <linux/sched/hotplug.h> #include <linux/sched/task_stack.h> diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c index f643ea5e36da..831ffb648bda 100644 --- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -12,6 +12,7 @@ #include <linux/sched.h> #include <linux/stacktrace.h> +#include <asm/ftrace.h> #include <asm/stacktrace.h> #include <asm/traps.h> #include <linux/uaccess.h> diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 427c125a137a..38092d21acf8 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -23,6 +23,7 @@ * for more details. */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> diff --git a/arch/xtensa/lib/umulsidi3.S b/arch/xtensa/lib/umulsidi3.S index 8c7a94a0c5d0..5da501b57813 100644 --- a/arch/xtensa/lib/umulsidi3.S +++ b/arch/xtensa/lib/umulsidi3.S @@ -3,7 +3,9 @@ #include <asm/asmmacro.h> #include <asm/core.h> -#if !XCHAL_HAVE_MUL16 && !XCHAL_HAVE_MUL32 && !XCHAL_HAVE_MAC16 +#if XCHAL_HAVE_MUL16 || XCHAL_HAVE_MUL32 || XCHAL_HAVE_MAC16 +#define XCHAL_NO_MUL 0 +#else #define XCHAL_NO_MUL 1 #endif diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index d1eb8d6c5b82..16e11b6f6f78 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -20,6 +20,7 @@ #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/hardirq.h> +#include <asm/traps.h> void bad_page_fault(struct pt_regs*, unsigned long, int); diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 0a11fc5f185b..4f974b74883c 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -17,6 +17,7 @@ #include <linux/mm.h> #include <asm/processor.h> #include <asm/mmu_context.h> +#include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 85c82cd42188..e89f27f2bb18 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -201,7 +201,7 @@ static int tuntap_write(struct iss_net_private *lp, struct sk_buff **skb) return simc_write(lp->tp.info.tuntap.fd, (*skb)->data, (*skb)->len); } -unsigned short tuntap_protocol(struct sk_buff *skb) +static unsigned short tuntap_protocol(struct sk_buff *skb) { return eth_type_trans(skb, skb->dev); } @@ -441,7 +441,7 @@ static int iss_net_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } -void iss_net_user_timer_expire(struct timer_list *unused) +static void iss_net_user_timer_expire(struct timer_list *unused) { } diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 167be74df4ee..dd7310c94713 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -270,7 +270,7 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, finish_wait(&rqw->wait, &data.wq); /* - * We raced with wbt_wake_function() getting a token, + * We raced with rq_qos_wake_function() getting a token, * which means we now have two. Put our local token * and wake anyone else potentially waiting for one. */ diff --git a/block/disk-events.c b/block/disk-events.c index 422db8292d09..13c3372c465a 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -290,7 +290,6 @@ EXPORT_SYMBOL(disk_check_media_change); /** * disk_force_media_change - force a media change event * @disk: the disk which will raise the event - * @events: the events to raise * * Should be called when the media changes for @disk. Generates a uevent * and attempts to free all dentries and inodes and invalidates all block diff --git a/crypto/sm2.c b/crypto/sm2.c index 285b3cb7c0bc..5ab120d74c59 100644 --- a/crypto/sm2.c +++ b/crypto/sm2.c @@ -278,10 +278,14 @@ int sm2_compute_z_digest(struct shash_desc *desc, if (!ec) return -ENOMEM; - err = __sm2_set_pub_key(ec, key, keylen); + err = sm2_ec_ctx_init(ec); if (err) goto out_free_ec; + err = __sm2_set_pub_key(ec, key, keylen); + if (err) + goto out_deinit_ec; + bits_len = SM2_DEFAULT_USERID_LEN * 8; entl[0] = bits_len >> 8; entl[1] = bits_len & 0xff; diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index ba79f397c9e8..467a60235370 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -327,7 +327,7 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev) } if (!ret) - ivpu_info(vdev, "VPU ready message received successfully\n"); + ivpu_dbg(vdev, PM, "VPU ready message received successfully\n"); else ivpu_hw_diagnose_failure(vdev); @@ -634,6 +634,7 @@ static void ivpu_dev_fini(struct ivpu_device *vdev) static struct pci_device_id ivpu_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_ARL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_LNL) }, { } }; diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 9e8c075fe9ef..03b3d6532fb6 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -23,6 +23,7 @@ #define DRIVER_DATE "20230117" #define PCI_DEVICE_ID_MTL 0x7d1d +#define PCI_DEVICE_ID_ARL 0xad1d #define PCI_DEVICE_ID_LNL 0x643e #define IVPU_HW_37XX 37 @@ -165,6 +166,7 @@ static inline int ivpu_hw_gen(struct ivpu_device *vdev) { switch (ivpu_device_id(vdev)) { case PCI_DEVICE_ID_MTL: + case PCI_DEVICE_ID_ARL: return IVPU_HW_37XX; case PCI_DEVICE_ID_LNL: return IVPU_HW_40XX; diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index 9827ea4d7b83..0191cf8e5964 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -220,7 +220,8 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev) if (ret) return ret; - fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size, DRM_IVPU_BO_WC); + fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size, + DRM_IVPU_BO_CACHED | DRM_IVPU_BO_NOSNOOP); if (!fw->mem) { ivpu_err(vdev, "Failed to allocate firmware runtime memory\n"); return -ENOMEM; @@ -330,7 +331,7 @@ int ivpu_fw_load(struct ivpu_device *vdev) memset(start, 0, size); } - wmb(); /* Flush WC buffers after writing fw->mem */ + clflush_cache_range(fw->mem->kvaddr, fw->mem->base.size); return 0; } @@ -432,6 +433,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params if (!ivpu_fw_is_cold_boot(vdev)) { boot_params->save_restore_ret_address = 0; vdev->pm->is_warmboot = true; + clflush_cache_range(vdev->fw->mem->kvaddr, SZ_4K); return; } @@ -493,7 +495,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev); boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev); - wmb(); /* Flush WC buffers after writing bootparams */ + clflush_cache_range(vdev->fw->mem->kvaddr, SZ_4K); ivpu_fw_boot_params_print(vdev, boot_params); } diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index 6b0ceda5f253..f4130586ff1b 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -8,6 +8,8 @@ #include <drm/drm_gem.h> #include <drm/drm_mm.h> +#define DRM_IVPU_BO_NOSNOOP 0x10000000 + struct dma_buf; struct ivpu_bo_ops; struct ivpu_file_priv; @@ -83,6 +85,9 @@ static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo) static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo) { + if (bo->flags & DRM_IVPU_BO_NOSNOOP) + return false; + return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED; } diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 34626d66fa10..8bdb59a45da6 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -57,8 +57,7 @@ #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK) -#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \ - (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ +#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI0_ERR)) | \ (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, CFI1_ERR)) | \ (REG_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, IMR0_ERR)) | \ @@ -196,6 +195,14 @@ static int ivpu_pll_wait_for_status_ready(struct ivpu_device *vdev) return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, READY, 1, PLL_TIMEOUT_US); } +static int ivpu_wait_for_clock_own_resource_ack(struct ivpu_device *vdev) +{ + if (ivpu_is_simics(vdev)) + return 0; + + return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, CLOCK_RESOURCE_OWN_ACK, 1, TIMEOUT_US); +} + static void ivpu_pll_init_frequency_ratios(struct ivpu_device *vdev) { struct ivpu_hw_info *hw = vdev->hw; @@ -556,6 +563,12 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev) { int ret; + ret = ivpu_wait_for_clock_own_resource_ack(vdev); + if (ret) { + ivpu_err(vdev, "Timed out waiting for clock own resource ACK\n"); + return ret; + } + ivpu_boot_pwr_island_trickle_drive(vdev, true); ivpu_boot_pwr_island_drive(vdev, true); @@ -1046,8 +1059,6 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq) if (status == 0) return IRQ_NONE; - REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status); - if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status)) ivpu_dbg(vdev, IRQ, "FREQ_CHANGE"); @@ -1092,6 +1103,9 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq) schedule_recovery = true; } + /* This must be done after interrupts are cleared at the source. */ + REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status); + if (schedule_recovery) ivpu_pm_schedule_recovery(vdev); @@ -1103,9 +1117,14 @@ static irqreturn_t ivpu_hw_40xx_irq_handler(int irq, void *ptr) struct ivpu_device *vdev = ptr; irqreturn_t ret = IRQ_NONE; + REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1); + ret |= ivpu_hw_40xx_irqv_handler(vdev, irq); ret |= ivpu_hw_40xx_irqb_handler(vdev, irq); + /* Re-enable global interrupts to re-trigger MSI for pending interrupts */ + REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0); + if (ret & IRQ_WAKE_THREAD) return IRQ_WAKE_THREAD; diff --git a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h index 5139cfe88532..ff4a5d4f5821 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx_reg.h +++ b/drivers/accel/ivpu/ivpu_hw_40xx_reg.h @@ -70,6 +70,8 @@ #define VPU_40XX_BUTTRESS_VPU_STATUS_READY_MASK BIT_MASK(0) #define VPU_40XX_BUTTRESS_VPU_STATUS_IDLE_MASK BIT_MASK(1) #define VPU_40XX_BUTTRESS_VPU_STATUS_DUP_IDLE_MASK BIT_MASK(2) +#define VPU_40XX_BUTTRESS_VPU_STATUS_CLOCK_RESOURCE_OWN_ACK_MASK BIT_MASK(6) +#define VPU_40XX_BUTTRESS_VPU_STATUS_POWER_RESOURCE_OWN_ACK_MASK BIT_MASK(7) #define VPU_40XX_BUTTRESS_VPU_STATUS_PERF_CLK_MASK BIT_MASK(11) #define VPU_40XX_BUTTRESS_VPU_STATUS_DISABLE_CLK_RELINQUISH_MASK BIT_MASK(12) diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index fa0af59e39ab..295c0d7b5039 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -209,10 +209,10 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, struct ivpu_ipc_rx_msg *rx_msg; int wait_ret, ret = 0; - wait_ret = wait_event_interruptible_timeout(cons->rx_msg_wq, - (IS_KTHREAD() && kthread_should_stop()) || - !list_empty(&cons->rx_msg_list), - msecs_to_jiffies(timeout_ms)); + wait_ret = wait_event_timeout(cons->rx_msg_wq, + (IS_KTHREAD() && kthread_should_stop()) || + !list_empty(&cons->rx_msg_list), + msecs_to_jiffies(timeout_ms)); if (IS_KTHREAD() && kthread_should_stop()) return -EINTR; @@ -220,9 +220,6 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, if (wait_ret == 0) return -ETIMEDOUT; - if (wait_ret < 0) - return -ERESTARTSYS; - spin_lock_irq(&cons->rx_msg_lock); rx_msg = list_first_entry_or_null(&cons->rx_msg_list, struct ivpu_ipc_rx_msg, link); if (!rx_msg) { diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 948e31f7ce6e..b411948594ff 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -2057,7 +2057,9 @@ static int acpi_video_bus_add(struct acpi_device *device) !auto_detect) acpi_video_bus_register_backlight(video); - acpi_video_bus_add_notify_handler(video); + error = acpi_video_bus_add_notify_handler(video); + if (error) + goto err_del; error = acpi_dev_install_notify_handler(device, ACPI_DEVICE_NOTIFY, acpi_video_bus_notify); @@ -2067,10 +2069,11 @@ static int acpi_video_bus_add(struct acpi_device *device) return 0; err_remove: + acpi_video_bus_remove_notify_handler(video); +err_del: mutex_lock(&video_list_lock); list_del(&video->entry); mutex_unlock(&video_list_lock); - acpi_video_bus_remove_notify_handler(video); acpi_video_bus_unregister_backlight(video); err_put_video: acpi_video_bus_put_devices(video); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index f0e6738ae3c9..f96bf32cd368 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -855,7 +855,7 @@ static size_t sizeof_idt(struct acpi_nfit_interleave *idt) { if (idt->header.length < sizeof(*idt)) return 0; - return sizeof(*idt) + sizeof(u32) * (idt->line_count - 1); + return sizeof(*idt) + sizeof(u32) * idt->line_count; } static bool add_idt(struct acpi_nfit_desc *acpi_desc, diff --git a/drivers/acpi/processor_pdc.c b/drivers/acpi/processor_pdc.c index 1a8591e9a9bf..994091bd52de 100644 --- a/drivers/acpi/processor_pdc.c +++ b/drivers/acpi/processor_pdc.c @@ -19,6 +19,7 @@ static void acpi_set_pdc_bits(u32 *buf) { buf[0] = ACPI_PDC_REVISION_ID; buf[1] = 1; + buf[2] = 0; /* Twiddle arch-specific bits needed for _PDC */ arch_acpi_set_proc_cap_bits(&buf[2]); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 0072e0f9ad39..d8cc1e27a125 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1973,6 +1973,96 @@ retry: } /** + * ata_dev_power_set_standby - Set a device power mode to standby + * @dev: target device + * + * Issue a STANDBY IMMEDIATE command to set a device power mode to standby. + * For an HDD device, this spins down the disks. + * + * LOCKING: + * Kernel thread context (may sleep). + */ +void ata_dev_power_set_standby(struct ata_device *dev) +{ + unsigned long ap_flags = dev->link->ap->flags; + struct ata_taskfile tf; + unsigned int err_mask; + + /* Issue STANDBY IMMEDIATE command only if supported by the device */ + if (dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) + return; + + /* + * Some odd clown BIOSes issue spindown on power off (ACPI S4 or S5) + * causing some drives to spin up and down again. For these, do nothing + * if we are being called on shutdown. + */ + if ((ap_flags & ATA_FLAG_NO_POWEROFF_SPINDOWN) && + system_state == SYSTEM_POWER_OFF) + return; + + if ((ap_flags & ATA_FLAG_NO_HIBERNATE_SPINDOWN) && + system_entering_hibernation()) + return; + + ata_tf_init(dev, &tf); + tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; + tf.protocol = ATA_PROT_NODATA; + tf.command = ATA_CMD_STANDBYNOW1; + + ata_dev_notice(dev, "Entering standby power mode\n"); + + err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); + if (err_mask) + ata_dev_err(dev, "STANDBY IMMEDIATE failed (err_mask=0x%x)\n", + err_mask); +} + +/** + * ata_dev_power_set_active - Set a device power mode to active + * @dev: target device + * + * Issue a VERIFY command to enter to ensure that the device is in the + * active power mode. For a spun-down HDD (standby or idle power mode), + * the VERIFY command will complete after the disk spins up. + * + * LOCKING: + * Kernel thread context (may sleep). + */ +void ata_dev_power_set_active(struct ata_device *dev) +{ + struct ata_taskfile tf; + unsigned int err_mask; + + /* + * Issue READ VERIFY SECTORS command for 1 sector at lba=0 only + * if supported by the device. + */ + if (dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) + return; + + ata_tf_init(dev, &tf); + tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; + tf.protocol = ATA_PROT_NODATA; + tf.command = ATA_CMD_VERIFY; + tf.nsect = 1; + if (dev->flags & ATA_DFLAG_LBA) { + tf.flags |= ATA_TFLAG_LBA; + tf.device |= ATA_LBA; + } else { + /* CHS */ + tf.lbal = 0x1; /* sect */ + } + + ata_dev_notice(dev, "Entering active power mode\n"); + + err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); + if (err_mask) + ata_dev_err(dev, "VERIFY failed (err_mask=0x%x)\n", + err_mask); +} + +/** * ata_read_log_page - read a specific log page * @dev: target device * @log: log to read @@ -2529,7 +2619,7 @@ static int ata_dev_config_lba(struct ata_device *dev) { const u16 *id = dev->id; const char *lba_desc; - char ncq_desc[24]; + char ncq_desc[32]; int ret; dev->flags |= ATA_DFLAG_LBA; @@ -5037,17 +5127,19 @@ static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg, struct ata_link *link; unsigned long flags; - /* Previous resume operation might still be in - * progress. Wait for PM_PENDING to clear. + spin_lock_irqsave(ap->lock, flags); + + /* + * A previous PM operation might still be in progress. Wait for + * ATA_PFLAG_PM_PENDING to clear. */ if (ap->pflags & ATA_PFLAG_PM_PENDING) { + spin_unlock_irqrestore(ap->lock, flags); ata_port_wait_eh(ap); - WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); + spin_lock_irqsave(ap->lock, flags); } - /* request PM ops to EH */ - spin_lock_irqsave(ap->lock, flags); - + /* Request PM operation to EH */ ap->pm_mesg = mesg; ap->pflags |= ATA_PFLAG_PM_PENDING; ata_for_each_link(link, ap, HOST_FIRST) { @@ -5059,10 +5151,8 @@ static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg, spin_unlock_irqrestore(ap->lock, flags); - if (!async) { + if (!async) ata_port_wait_eh(ap); - WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); - } } /* @@ -5078,11 +5168,27 @@ static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg) { + /* + * We are about to suspend the port, so we do not care about + * scsi_rescan_device() calls scheduled by previous resume operations. + * The next resume will schedule the rescan again. So cancel any rescan + * that is not done yet. + */ + cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false); } static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg) { + /* + * We are about to suspend the port, so we do not care about + * scsi_rescan_device() calls scheduled by previous resume operations. + * The next resume will schedule the rescan again. So cancel any rescan + * that is not done yet. + */ + cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true); } @@ -5229,7 +5335,7 @@ EXPORT_SYMBOL_GPL(ata_host_resume); #endif const struct device_type ata_port_type = { - .name = "ata_port", + .name = ATA_PORT_TYPE_NAME, #ifdef CONFIG_PM .pm = &ata_port_pm_ops, #endif @@ -5948,11 +6054,30 @@ static void ata_port_detach(struct ata_port *ap) struct ata_link *link; struct ata_device *dev; - /* tell EH we're leaving & flush EH */ + /* Wait for any ongoing EH */ + ata_port_wait_eh(ap); + + mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); + + /* Remove scsi devices */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ALL) { + if (dev->sdev) { + spin_unlock_irqrestore(ap->lock, flags); + scsi_remove_device(dev->sdev); + spin_lock_irqsave(ap->lock, flags); + dev->sdev = NULL; + } + } + } + + /* Tell EH to disable all devices */ ap->pflags |= ATA_PFLAG_UNLOADING; ata_port_schedule_eh(ap); + spin_unlock_irqrestore(ap->lock, flags); + mutex_unlock(&ap->scsi_scan_mutex); /* wait till EH commits suicide */ ata_port_wait_eh(ap); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 4cf4f57e57b8..5686353e442c 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -147,6 +147,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { .timeouts = ata_eh_other_timeouts, }, { .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT), .timeouts = ata_eh_flush_timeouts }, + { .commands = CMDS(ATA_CMD_VERIFY), + .timeouts = ata_eh_reset_timeouts }, }; #undef CMDS @@ -498,7 +500,19 @@ static void ata_eh_unload(struct ata_port *ap) struct ata_device *dev; unsigned long flags; - /* Restore SControl IPM and SPD for the next driver and + /* + * Unless we are restarting, transition all enabled devices to + * standby power mode. + */ + if (system_state != SYSTEM_RESTART) { + ata_for_each_link(link, ap, PMP_FIRST) { + ata_for_each_dev(dev, link, ENABLED) + ata_dev_power_set_standby(dev); + } + } + + /* + * Restore SControl IPM and SPD for the next driver and * disable attached devices. */ ata_for_each_link(link, ap, PMP_FIRST) { @@ -684,6 +698,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ehc->saved_xfer_mode[devno] = dev->xfer_mode; if (ata_ncq_enabled(dev)) ehc->saved_ncq_enabled |= 1 << devno; + + /* If we are resuming, wake up the device */ + if (ap->pflags & ATA_PFLAG_RESUMING) + ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE; } } @@ -743,6 +761,8 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) /* clean up */ spin_lock_irqsave(ap->lock, flags); + ap->pflags &= ~ATA_PFLAG_RESUMING; + if (ap->pflags & ATA_PFLAG_LOADING) ap->pflags &= ~ATA_PFLAG_LOADING; else if ((ap->pflags & ATA_PFLAG_SCSI_HOTPLUG) && @@ -1218,6 +1238,13 @@ void ata_eh_detach_dev(struct ata_device *dev) struct ata_eh_context *ehc = &link->eh_context; unsigned long flags; + /* + * If the device is still enabled, transition it to standby power mode + * (i.e. spin down HDDs). + */ + if (ata_dev_enabled(dev)) + ata_dev_power_set_standby(dev); + ata_dev_disable(dev); spin_lock_irqsave(ap->lock, flags); @@ -2305,7 +2332,7 @@ static void ata_eh_link_report(struct ata_link *link) struct ata_eh_context *ehc = &link->eh_context; struct ata_queued_cmd *qc; const char *frozen, *desc; - char tries_buf[6] = ""; + char tries_buf[16] = ""; int tag, nr_failed = 0; if (ehc->i.flags & ATA_EHI_QUIET) @@ -3016,6 +3043,15 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, if (ehc->i.flags & ATA_EHI_DID_RESET) readid_flags |= ATA_READID_POSTRESET; + /* + * When resuming, before executing any command, make sure to + * transition the device to the active power mode. + */ + if ((action & ATA_EH_SET_ACTIVE) && ata_dev_enabled(dev)) { + ata_dev_power_set_active(dev); + ata_eh_done(link, dev, ATA_EH_SET_ACTIVE); + } + if ((action & ATA_EH_REVALIDATE) && ata_dev_enabled(dev)) { WARN_ON(dev->class == ATA_DEV_PMP); @@ -3989,6 +4025,7 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) unsigned long flags; int rc = 0; struct ata_device *dev; + struct ata_link *link; /* are we suspending? */ spin_lock_irqsave(ap->lock, flags); @@ -4001,6 +4038,12 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED); + /* Set all devices attached to the port in standby mode */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ENABLED) + ata_dev_power_set_standby(dev); + } + /* * If we have a ZPODD attached, check its zero * power ready status before the port is frozen. @@ -4083,6 +4126,7 @@ static void ata_eh_handle_port_resume(struct ata_port *ap) /* update the flags */ spin_lock_irqsave(ap->lock, flags); ap->pflags &= ~(ATA_PFLAG_PM_PENDING | ATA_PFLAG_SUSPENDED); + ap->pflags |= ATA_PFLAG_RESUMING; spin_unlock_irqrestore(ap->lock, flags); } #endif /* CONFIG_PM */ diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d3f28b82c97b..a371b497035e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1050,14 +1050,13 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) } } else { sdev->sector_size = ata_id_logical_sector_size(dev->id); + /* - * Stop the drive on suspend but do not issue START STOP UNIT - * on resume as this is not necessary and may fail: the device - * will be woken up by ata_port_pm_resume() with a port reset - * and device revalidation. + * Ask the sd driver to issue START STOP UNIT on runtime suspend + * and resume only. For system level suspend/resume, devices + * power state is handled directly by libata EH. */ - sdev->manage_start_stop = 1; - sdev->no_start_on_resume = 1; + sdev->manage_runtime_start_stop = true; } /* @@ -1090,6 +1089,42 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) } /** + * ata_scsi_slave_alloc - Early setup of SCSI device + * @sdev: SCSI device to examine + * + * This is called from scsi_alloc_sdev() when the scsi device + * associated with an ATA device is scanned on a port. + * + * LOCKING: + * Defined by SCSI layer. We don't really care. + */ + +int ata_scsi_slave_alloc(struct scsi_device *sdev) +{ + struct ata_port *ap = ata_shost_to_port(sdev->host); + struct device_link *link; + + ata_scsi_sdev_config(sdev); + + /* + * Create a link from the ata_port device to the scsi device to ensure + * that PM does suspend/resume in the correct order: the scsi device is + * consumer (child) and the ata port the supplier (parent). + */ + link = device_link_add(&sdev->sdev_gendev, &ap->tdev, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); + if (!link) { + ata_port_err(ap, "Failed to create link to scsi device %s\n", + dev_name(&sdev->sdev_gendev)); + return -ENODEV; + } + + return 0; +} +EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc); + +/** * ata_scsi_slave_config - Set SCSI device attributes * @sdev: SCSI device to examine * @@ -1105,14 +1140,11 @@ int ata_scsi_slave_config(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = __ata_scsi_find_dev(ap, sdev); - int rc = 0; - - ata_scsi_sdev_config(sdev); if (dev) - rc = ata_scsi_dev_config(sdev, dev); + return ata_scsi_dev_config(sdev, dev); - return rc; + return 0; } EXPORT_SYMBOL_GPL(ata_scsi_slave_config); @@ -1136,6 +1168,8 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev) unsigned long flags; struct ata_device *dev; + device_link_remove(&sdev->sdev_gendev, &ap->tdev); + spin_lock_irqsave(ap->lock, flags); dev = __ata_scsi_find_dev(ap, sdev); if (dev && dev->sdev) { @@ -1195,7 +1229,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) } if (cdb[4] & 0x1) { - tf->nsect = 1; /* 1 sector, lba=0 */ + tf->nsect = 1; /* 1 sector, lba=0 */ if (qc->dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; @@ -1211,7 +1245,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) tf->lbah = 0x0; /* cyl high */ } - tf->command = ATA_CMD_VERIFY; /* READ VERIFY */ + tf->command = ATA_CMD_VERIFY; /* READ VERIFY */ } else { /* Some odd clown BIOSen issue spindown on power off (ACPI S4 * or S5) causing some drives to spin up and down again. @@ -1221,7 +1255,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) goto skip; if ((qc->ap->flags & ATA_FLAG_NO_HIBERNATE_SPINDOWN) && - system_entering_hibernation()) + system_entering_hibernation()) goto skip; /* Issue ATA STANDBY IMMEDIATE command */ @@ -1835,6 +1869,9 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) hdr[2] = 0x7; /* claim SPC-5 version compatibility */ } + if (args->dev->flags & ATA_DFLAG_CDL) + hdr[2] = 0xd; /* claim SPC-6 version compatibility */ + memcpy(rbuf, hdr, sizeof(hdr)); memcpy(&rbuf[8], "ATA ", 8); ata_id_string(args->id, &rbuf[16], ATA_ID_PROD, 16); @@ -4312,7 +4349,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) break; case MAINTENANCE_IN: - if (scsicmd[1] == MI_REPORT_SUPPORTED_OPERATION_CODES) + if ((scsicmd[1] & 0x1f) == MI_REPORT_SUPPORTED_OPERATION_CODES) ata_scsi_rbuf_fill(&args, ata_scsiop_maint_in); else ata_scsi_set_invalid_field(dev, cmd, 1, 0xff); @@ -4722,7 +4759,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) struct ata_link *link; struct ata_device *dev; unsigned long flags; - bool delay_rescan = false; + int ret = 0; mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); @@ -4731,37 +4768,34 @@ void ata_scsi_dev_rescan(struct work_struct *work) ata_for_each_dev(dev, link, ENABLED) { struct scsi_device *sdev = dev->sdev; + /* + * If the port was suspended before this was scheduled, + * bail out. + */ + if (ap->pflags & ATA_PFLAG_SUSPENDED) + goto unlock; + if (!sdev) continue; if (scsi_device_get(sdev)) continue; - /* - * If the rescan work was scheduled because of a resume - * event, the port is already fully resumed, but the - * SCSI device may not yet be fully resumed. In such - * case, executing scsi_rescan_device() may cause a - * deadlock with the PM code on device_lock(). Prevent - * this by giving up and retrying rescan after a short - * delay. - */ - delay_rescan = sdev->sdev_gendev.power.is_suspended; - if (delay_rescan) { - scsi_device_put(sdev); - break; - } - spin_unlock_irqrestore(ap->lock, flags); - scsi_rescan_device(sdev); + ret = scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); + + if (ret) + goto unlock; } } +unlock: spin_unlock_irqrestore(ap->lock, flags); mutex_unlock(&ap->scsi_scan_mutex); - if (delay_rescan) + /* Reschedule with a delay if scsi_rescan_device() returned an error */ + if (ret) schedule_delayed_work(&ap->scsi_rescan_task, msecs_to_jiffies(5)); } diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index e4fb9d1b9b39..3e49a877500e 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -266,6 +266,10 @@ void ata_tport_delete(struct ata_port *ap) put_device(dev); } +static const struct device_type ata_port_sas_type = { + .name = ATA_PORT_TYPE_NAME, +}; + /** ata_tport_add - initialize a transport ATA port structure * * @parent: parent device @@ -283,7 +287,10 @@ int ata_tport_add(struct device *parent, struct device *dev = &ap->tdev; device_initialize(dev); - dev->type = &ata_port_type; + if (ap->flags & ATA_FLAG_SAS_HOST) + dev->type = &ata_port_sas_type; + else + dev->type = &ata_port_type; dev->parent = parent; ata_host_get(ap->host); diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 6e7d352803bd..05ac80da8ebc 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -30,6 +30,8 @@ enum { ATA_DNXFER_QUIET = (1 << 31), }; +#define ATA_PORT_TYPE_NAME "ata_port" + extern atomic_t ata_print_id; extern int atapi_passthru16; extern int libata_fua; @@ -60,6 +62,8 @@ extern int ata_dev_reread_id(struct ata_device *dev, unsigned int readid_flags); extern int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, unsigned int readid_flags); extern int ata_dev_configure(struct ata_device *dev); +extern void ata_dev_power_set_standby(struct ata_device *dev); +extern void ata_dev_power_set_active(struct ata_device *dev); extern int sata_down_spd_limit(struct ata_link *link, u32 spd_limit); extern int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel); extern unsigned int ata_dev_set_feature(struct ata_device *dev, diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index db716ffd083e..3db88bbcae0f 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -453,7 +453,8 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg, if (!rbnode) return -ENOMEM; regcache_rbtree_set_register(map, rbnode, - reg - rbnode->base_reg, value); + (reg - rbnode->base_reg) / map->reg_stride, + value); regcache_rbtree_insert(map, &rbtree_ctx->root, rbnode); rbtree_ctx->cached_rbnode = rbnode; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 3de11f077144..a999b698b131 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -632,9 +632,8 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...) static void rbd_dev_remove_parent(struct rbd_device *rbd_dev); static int rbd_dev_refresh(struct rbd_device *rbd_dev); -static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev); -static int rbd_dev_header_info(struct rbd_device *rbd_dev); -static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev); +static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev, + struct rbd_image_header *header); static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev, u64 snap_id); static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, @@ -995,15 +994,24 @@ static void rbd_init_layout(struct rbd_device *rbd_dev) RCU_INIT_POINTER(rbd_dev->layout.pool_ns, NULL); } +static void rbd_image_header_cleanup(struct rbd_image_header *header) +{ + kfree(header->object_prefix); + ceph_put_snap_context(header->snapc); + kfree(header->snap_sizes); + kfree(header->snap_names); + + memset(header, 0, sizeof(*header)); +} + /* * Fill an rbd image header with information from the given format 1 * on-disk header. */ -static int rbd_header_from_disk(struct rbd_device *rbd_dev, - struct rbd_image_header_ondisk *ondisk) +static int rbd_header_from_disk(struct rbd_image_header *header, + struct rbd_image_header_ondisk *ondisk, + bool first_time) { - struct rbd_image_header *header = &rbd_dev->header; - bool first_time = header->object_prefix == NULL; struct ceph_snap_context *snapc; char *object_prefix = NULL; char *snap_names = NULL; @@ -1070,11 +1078,6 @@ static int rbd_header_from_disk(struct rbd_device *rbd_dev, if (first_time) { header->object_prefix = object_prefix; header->obj_order = ondisk->options.order; - rbd_init_layout(rbd_dev); - } else { - ceph_put_snap_context(header->snapc); - kfree(header->snap_names); - kfree(header->snap_sizes); } /* The remaining fields always get updated (when we refresh) */ @@ -4859,7 +4862,9 @@ out_req: * return, the rbd_dev->header field will contain up-to-date * information about the image. */ -static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev) +static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev, + struct rbd_image_header *header, + bool first_time) { struct rbd_image_header_ondisk *ondisk = NULL; u32 snap_count = 0; @@ -4907,7 +4912,7 @@ static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev) snap_count = le32_to_cpu(ondisk->snap_count); } while (snap_count != want_count); - ret = rbd_header_from_disk(rbd_dev, ondisk); + ret = rbd_header_from_disk(header, ondisk, first_time); out: kfree(ondisk); @@ -4931,39 +4936,6 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev) } } -static int rbd_dev_refresh(struct rbd_device *rbd_dev) -{ - u64 mapping_size; - int ret; - - down_write(&rbd_dev->header_rwsem); - mapping_size = rbd_dev->mapping.size; - - ret = rbd_dev_header_info(rbd_dev); - if (ret) - goto out; - - /* - * If there is a parent, see if it has disappeared due to the - * mapped image getting flattened. - */ - if (rbd_dev->parent) { - ret = rbd_dev_v2_parent_info(rbd_dev); - if (ret) - goto out; - } - - rbd_assert(!rbd_is_snap(rbd_dev)); - rbd_dev->mapping.size = rbd_dev->header.image_size; - -out: - up_write(&rbd_dev->header_rwsem); - if (!ret && mapping_size != rbd_dev->mapping.size) - rbd_dev_update_size(rbd_dev); - - return ret; -} - static const struct blk_mq_ops rbd_mq_ops = { .queue_rq = rbd_queue_rq, }; @@ -5503,17 +5475,12 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, return 0; } -static int rbd_dev_v2_image_size(struct rbd_device *rbd_dev) -{ - return _rbd_dev_v2_snap_size(rbd_dev, CEPH_NOSNAP, - &rbd_dev->header.obj_order, - &rbd_dev->header.image_size); -} - -static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev) +static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev, + char **pobject_prefix) { size_t size; void *reply_buf; + char *object_prefix; int ret; void *p; @@ -5531,16 +5498,16 @@ static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev) goto out; p = reply_buf; - rbd_dev->header.object_prefix = ceph_extract_encoded_string(&p, - p + ret, NULL, GFP_NOIO); + object_prefix = ceph_extract_encoded_string(&p, p + ret, NULL, + GFP_NOIO); + if (IS_ERR(object_prefix)) { + ret = PTR_ERR(object_prefix); + goto out; + } ret = 0; - if (IS_ERR(rbd_dev->header.object_prefix)) { - ret = PTR_ERR(rbd_dev->header.object_prefix); - rbd_dev->header.object_prefix = NULL; - } else { - dout(" object_prefix = %s\n", rbd_dev->header.object_prefix); - } + *pobject_prefix = object_prefix; + dout(" object_prefix = %s\n", object_prefix); out: kfree(reply_buf); @@ -5591,13 +5558,6 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, return 0; } -static int rbd_dev_v2_features(struct rbd_device *rbd_dev) -{ - return _rbd_dev_v2_snap_features(rbd_dev, CEPH_NOSNAP, - rbd_is_ro(rbd_dev), - &rbd_dev->header.features); -} - /* * These are generic image flags, but since they are used only for * object map, store them in rbd_dev->object_map_flags. @@ -5634,6 +5594,14 @@ struct parent_image_info { u64 overlap; }; +static void rbd_parent_info_cleanup(struct parent_image_info *pii) +{ + kfree(pii->pool_ns); + kfree(pii->image_id); + + memset(pii, 0, sizeof(*pii)); +} + /* * The caller is responsible for @pii. */ @@ -5703,6 +5671,9 @@ static int __get_parent_info(struct rbd_device *rbd_dev, if (pii->has_overlap) ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii->pool_id, pii->pool_ns, pii->image_id, pii->snap_id, + pii->has_overlap, pii->overlap); return 0; e_inval: @@ -5741,14 +5712,17 @@ static int __get_parent_info_legacy(struct rbd_device *rbd_dev, pii->has_overlap = true; ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii->pool_id, pii->pool_ns, pii->image_id, pii->snap_id, + pii->has_overlap, pii->overlap); return 0; e_inval: return -EINVAL; } -static int get_parent_info(struct rbd_device *rbd_dev, - struct parent_image_info *pii) +static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev, + struct parent_image_info *pii) { struct page *req_page, *reply_page; void *p; @@ -5776,7 +5750,7 @@ static int get_parent_info(struct rbd_device *rbd_dev, return ret; } -static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) +static int rbd_dev_setup_parent(struct rbd_device *rbd_dev) { struct rbd_spec *parent_spec; struct parent_image_info pii = { 0 }; @@ -5786,37 +5760,12 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) if (!parent_spec) return -ENOMEM; - ret = get_parent_info(rbd_dev, &pii); + ret = rbd_dev_v2_parent_info(rbd_dev, &pii); if (ret) goto out_err; - dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", - __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id, - pii.has_overlap, pii.overlap); - - if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) { - /* - * Either the parent never existed, or we have - * record of it but the image got flattened so it no - * longer has a parent. When the parent of a - * layered image disappears we immediately set the - * overlap to 0. The effect of this is that all new - * requests will be treated as if the image had no - * parent. - * - * If !pii.has_overlap, the parent image spec is not - * applicable. It's there to avoid duplication in each - * snapshot record. - */ - if (rbd_dev->parent_overlap) { - rbd_dev->parent_overlap = 0; - rbd_dev_parent_put(rbd_dev); - pr_info("%s: clone image has been flattened\n", - rbd_dev->disk->disk_name); - } - + if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) goto out; /* No parent? No problem. */ - } /* The ceph file layout needs to fit pool id in 32 bits */ @@ -5828,58 +5777,46 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) } /* - * The parent won't change (except when the clone is - * flattened, already handled that). So we only need to - * record the parent spec we have not already done so. + * The parent won't change except when the clone is flattened, + * so we only need to record the parent image spec once. */ - if (!rbd_dev->parent_spec) { - parent_spec->pool_id = pii.pool_id; - if (pii.pool_ns && *pii.pool_ns) { - parent_spec->pool_ns = pii.pool_ns; - pii.pool_ns = NULL; - } - parent_spec->image_id = pii.image_id; - pii.image_id = NULL; - parent_spec->snap_id = pii.snap_id; - - rbd_dev->parent_spec = parent_spec; - parent_spec = NULL; /* rbd_dev now owns this */ + parent_spec->pool_id = pii.pool_id; + if (pii.pool_ns && *pii.pool_ns) { + parent_spec->pool_ns = pii.pool_ns; + pii.pool_ns = NULL; } + parent_spec->image_id = pii.image_id; + pii.image_id = NULL; + parent_spec->snap_id = pii.snap_id; + + rbd_assert(!rbd_dev->parent_spec); + rbd_dev->parent_spec = parent_spec; + parent_spec = NULL; /* rbd_dev now owns this */ /* - * We always update the parent overlap. If it's zero we issue - * a warning, as we will proceed as if there was no parent. + * Record the parent overlap. If it's zero, issue a warning as + * we will proceed as if there is no parent. */ - if (!pii.overlap) { - if (parent_spec) { - /* refresh, careful to warn just once */ - if (rbd_dev->parent_overlap) - rbd_warn(rbd_dev, - "clone now standalone (overlap became 0)"); - } else { - /* initial probe */ - rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); - } - } + if (!pii.overlap) + rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); rbd_dev->parent_overlap = pii.overlap; out: ret = 0; out_err: - kfree(pii.pool_ns); - kfree(pii.image_id); + rbd_parent_info_cleanup(&pii); rbd_spec_put(parent_spec); return ret; } -static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev) +static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev, + u64 *stripe_unit, u64 *stripe_count) { struct { __le64 stripe_unit; __le64 stripe_count; } __attribute__ ((packed)) striping_info_buf = { 0 }; size_t size = sizeof (striping_info_buf); - void *p; int ret; ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, @@ -5891,27 +5828,33 @@ static int rbd_dev_v2_striping_info(struct rbd_device *rbd_dev) if (ret < size) return -ERANGE; - p = &striping_info_buf; - rbd_dev->header.stripe_unit = ceph_decode_64(&p); - rbd_dev->header.stripe_count = ceph_decode_64(&p); + *stripe_unit = le64_to_cpu(striping_info_buf.stripe_unit); + *stripe_count = le64_to_cpu(striping_info_buf.stripe_count); + dout(" stripe_unit = %llu stripe_count = %llu\n", *stripe_unit, + *stripe_count); + return 0; } -static int rbd_dev_v2_data_pool(struct rbd_device *rbd_dev) +static int rbd_dev_v2_data_pool(struct rbd_device *rbd_dev, s64 *data_pool_id) { - __le64 data_pool_id; + __le64 data_pool_buf; int ret; ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, &rbd_dev->header_oloc, "get_data_pool", - NULL, 0, &data_pool_id, sizeof(data_pool_id)); + NULL, 0, &data_pool_buf, + sizeof(data_pool_buf)); + dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret); if (ret < 0) return ret; - if (ret < sizeof(data_pool_id)) + if (ret < sizeof(data_pool_buf)) return -EBADMSG; - rbd_dev->header.data_pool_id = le64_to_cpu(data_pool_id); - WARN_ON(rbd_dev->header.data_pool_id == CEPH_NOPOOL); + *data_pool_id = le64_to_cpu(data_pool_buf); + dout(" data_pool_id = %lld\n", *data_pool_id); + WARN_ON(*data_pool_id == CEPH_NOPOOL); + return 0; } @@ -6103,7 +6046,8 @@ out_err: return ret; } -static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev) +static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev, + struct ceph_snap_context **psnapc) { size_t size; int ret; @@ -6164,9 +6108,7 @@ static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev) for (i = 0; i < snap_count; i++) snapc->snaps[i] = ceph_decode_64(&p); - ceph_put_snap_context(rbd_dev->header.snapc); - rbd_dev->header.snapc = snapc; - + *psnapc = snapc; dout(" snap context seq = %llu, snap_count = %u\n", (unsigned long long)seq, (unsigned int)snap_count); out: @@ -6215,38 +6157,42 @@ out: return snap_name; } -static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev) +static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev, + struct rbd_image_header *header, + bool first_time) { - bool first_time = rbd_dev->header.object_prefix == NULL; int ret; - ret = rbd_dev_v2_image_size(rbd_dev); + ret = _rbd_dev_v2_snap_size(rbd_dev, CEPH_NOSNAP, + first_time ? &header->obj_order : NULL, + &header->image_size); if (ret) return ret; if (first_time) { - ret = rbd_dev_v2_header_onetime(rbd_dev); + ret = rbd_dev_v2_header_onetime(rbd_dev, header); if (ret) return ret; } - ret = rbd_dev_v2_snap_context(rbd_dev); - if (ret && first_time) { - kfree(rbd_dev->header.object_prefix); - rbd_dev->header.object_prefix = NULL; - } + ret = rbd_dev_v2_snap_context(rbd_dev, &header->snapc); + if (ret) + return ret; - return ret; + return 0; } -static int rbd_dev_header_info(struct rbd_device *rbd_dev) +static int rbd_dev_header_info(struct rbd_device *rbd_dev, + struct rbd_image_header *header, + bool first_time) { rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); + rbd_assert(!header->object_prefix && !header->snapc); if (rbd_dev->image_format == 1) - return rbd_dev_v1_header_info(rbd_dev); + return rbd_dev_v1_header_info(rbd_dev, header, first_time); - return rbd_dev_v2_header_info(rbd_dev); + return rbd_dev_v2_header_info(rbd_dev, header, first_time); } /* @@ -6734,60 +6680,49 @@ out: */ static void rbd_dev_unprobe(struct rbd_device *rbd_dev) { - struct rbd_image_header *header; - rbd_dev_parent_put(rbd_dev); rbd_object_map_free(rbd_dev); rbd_dev_mapping_clear(rbd_dev); /* Free dynamic fields from the header, then zero it out */ - header = &rbd_dev->header; - ceph_put_snap_context(header->snapc); - kfree(header->snap_sizes); - kfree(header->snap_names); - kfree(header->object_prefix); - memset(header, 0, sizeof (*header)); + rbd_image_header_cleanup(&rbd_dev->header); } -static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev) +static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev, + struct rbd_image_header *header) { int ret; - ret = rbd_dev_v2_object_prefix(rbd_dev); + ret = rbd_dev_v2_object_prefix(rbd_dev, &header->object_prefix); if (ret) - goto out_err; + return ret; /* * Get the and check features for the image. Currently the * features are assumed to never change. */ - ret = rbd_dev_v2_features(rbd_dev); + ret = _rbd_dev_v2_snap_features(rbd_dev, CEPH_NOSNAP, + rbd_is_ro(rbd_dev), &header->features); if (ret) - goto out_err; + return ret; /* If the image supports fancy striping, get its parameters */ - if (rbd_dev->header.features & RBD_FEATURE_STRIPINGV2) { - ret = rbd_dev_v2_striping_info(rbd_dev); - if (ret < 0) - goto out_err; + if (header->features & RBD_FEATURE_STRIPINGV2) { + ret = rbd_dev_v2_striping_info(rbd_dev, &header->stripe_unit, + &header->stripe_count); + if (ret) + return ret; } - if (rbd_dev->header.features & RBD_FEATURE_DATA_POOL) { - ret = rbd_dev_v2_data_pool(rbd_dev); + if (header->features & RBD_FEATURE_DATA_POOL) { + ret = rbd_dev_v2_data_pool(rbd_dev, &header->data_pool_id); if (ret) - goto out_err; + return ret; } - rbd_init_layout(rbd_dev); return 0; - -out_err: - rbd_dev->header.features = 0; - kfree(rbd_dev->header.object_prefix); - rbd_dev->header.object_prefix = NULL; - return ret; } /* @@ -6982,13 +6917,15 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) if (!depth) down_write(&rbd_dev->header_rwsem); - ret = rbd_dev_header_info(rbd_dev); + ret = rbd_dev_header_info(rbd_dev, &rbd_dev->header, true); if (ret) { if (ret == -ENOENT && !need_watch) rbd_print_dne(rbd_dev, false); goto err_out_probe; } + rbd_init_layout(rbd_dev); + /* * If this image is the one being mapped, we have pool name and * id, image name and id, and snap name - need to fill snap id. @@ -7017,7 +6954,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) } if (rbd_dev->header.features & RBD_FEATURE_LAYERING) { - ret = rbd_dev_v2_parent_info(rbd_dev); + ret = rbd_dev_setup_parent(rbd_dev); if (ret) goto err_out_probe; } @@ -7043,6 +6980,107 @@ err_out_format: return ret; } +static void rbd_dev_update_header(struct rbd_device *rbd_dev, + struct rbd_image_header *header) +{ + rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); + rbd_assert(rbd_dev->header.object_prefix); /* !first_time */ + + if (rbd_dev->header.image_size != header->image_size) { + rbd_dev->header.image_size = header->image_size; + + if (!rbd_is_snap(rbd_dev)) { + rbd_dev->mapping.size = header->image_size; + rbd_dev_update_size(rbd_dev); + } + } + + ceph_put_snap_context(rbd_dev->header.snapc); + rbd_dev->header.snapc = header->snapc; + header->snapc = NULL; + + if (rbd_dev->image_format == 1) { + kfree(rbd_dev->header.snap_names); + rbd_dev->header.snap_names = header->snap_names; + header->snap_names = NULL; + + kfree(rbd_dev->header.snap_sizes); + rbd_dev->header.snap_sizes = header->snap_sizes; + header->snap_sizes = NULL; + } +} + +static void rbd_dev_update_parent(struct rbd_device *rbd_dev, + struct parent_image_info *pii) +{ + if (pii->pool_id == CEPH_NOPOOL || !pii->has_overlap) { + /* + * Either the parent never existed, or we have + * record of it but the image got flattened so it no + * longer has a parent. When the parent of a + * layered image disappears we immediately set the + * overlap to 0. The effect of this is that all new + * requests will be treated as if the image had no + * parent. + * + * If !pii.has_overlap, the parent image spec is not + * applicable. It's there to avoid duplication in each + * snapshot record. + */ + if (rbd_dev->parent_overlap) { + rbd_dev->parent_overlap = 0; + rbd_dev_parent_put(rbd_dev); + pr_info("%s: clone has been flattened\n", + rbd_dev->disk->disk_name); + } + } else { + rbd_assert(rbd_dev->parent_spec); + + /* + * Update the parent overlap. If it became zero, issue + * a warning as we will proceed as if there is no parent. + */ + if (!pii->overlap && rbd_dev->parent_overlap) + rbd_warn(rbd_dev, + "clone has become standalone (overlap 0)"); + rbd_dev->parent_overlap = pii->overlap; + } +} + +static int rbd_dev_refresh(struct rbd_device *rbd_dev) +{ + struct rbd_image_header header = { 0 }; + struct parent_image_info pii = { 0 }; + int ret; + + dout("%s rbd_dev %p\n", __func__, rbd_dev); + + ret = rbd_dev_header_info(rbd_dev, &header, false); + if (ret) + goto out; + + /* + * If there is a parent, see if it has disappeared due to the + * mapped image getting flattened. + */ + if (rbd_dev->parent) { + ret = rbd_dev_v2_parent_info(rbd_dev, &pii); + if (ret) + goto out; + } + + down_write(&rbd_dev->header_rwsem); + rbd_dev_update_header(rbd_dev, &header); + if (rbd_dev->parent) + rbd_dev_update_parent(rbd_dev, &pii); + up_write(&rbd_dev->header_rwsem); + +out: + rbd_parent_info_cleanup(&pii); + rbd_image_header_cleanup(&header); + return ret; +} + static ssize_t do_rbd_add(const char *buf, size_t count) { struct rbd_device *rbd_dev = NULL; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 82597ab4f747..499f4809fcdf 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4419,6 +4419,7 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_QCA_ROME) { data->setup_on_usb = btusb_setup_qca; + hdev->shutdown = btusb_shutdown_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; hdev->cmd_timeout = btusb_qca_cmd_timeout; set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index eb4e7bee1e20..d57bc066dce6 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -38,6 +38,7 @@ enum sysc_soc { SOC_2420, SOC_2430, SOC_3430, + SOC_AM35, SOC_3630, SOC_4430, SOC_4460, @@ -1097,6 +1098,11 @@ static int sysc_enable_module(struct device *dev) if (ddata->cfg.quirks & (SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_SIDLE_ACT)) { best_mode = SYSC_IDLE_NO; + + /* Clear WAKEUP */ + if (regbits->enwkup_shift >= 0 && + ddata->cfg.sysc_val & BIT(regbits->enwkup_shift)) + reg &= ~BIT(regbits->enwkup_shift); } else { best_mode = fls(ddata->cfg.sidlemodes) - 1; if (best_mode > SYSC_IDLE_MASK) { @@ -1224,6 +1230,13 @@ set_sidle: } } + if (ddata->cfg.quirks & SYSC_QUIRK_SWSUP_SIDLE_ACT) { + /* Set WAKEUP */ + if (regbits->enwkup_shift >= 0 && + ddata->cfg.sysc_val & BIT(regbits->enwkup_shift)) + reg |= BIT(regbits->enwkup_shift); + } + reg &= ~(SYSC_IDLE_MASK << regbits->sidle_shift); reg |= best_mode << regbits->sidle_shift; if (regbits->autoidle_shift >= 0 && @@ -1518,16 +1531,16 @@ struct sysc_revision_quirk { static const struct sysc_revision_quirk sysc_revision_quirks[] = { /* These drivers need to be fixed to not use pm_runtime_irq_safe() */ SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000046, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000052, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), /* Uarts on omap4 and later */ SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffff00ff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47422e03, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x47424e03, 0xffffffff, - SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK_SWSUP_SIDLE_ACT | SYSC_QUIRK_LEGACY_IDLE), /* Quirks that need to be set based on the module address */ SYSC_QUIRK("mcpdm", 0x40132000, 0, 0x10, -ENODEV, 0x50000800, 0xffffffff, @@ -1862,7 +1875,7 @@ static void sysc_pre_reset_quirk_dss(struct sysc *ddata) dev_warn(ddata->dev, "%s: timed out %08x !+ %08x\n", __func__, val, irq_mask); - if (sysc_soc->soc == SOC_3430) { + if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35) { /* Clear DSS_SDI_CONTROL */ sysc_write(ddata, 0x44, 0); @@ -2150,8 +2163,7 @@ static int sysc_reset(struct sysc *ddata) } if (ddata->cfg.srst_udelay) - usleep_range(ddata->cfg.srst_udelay, - ddata->cfg.srst_udelay * 2); + fsleep(ddata->cfg.srst_udelay); if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); @@ -3025,6 +3037,7 @@ static void ti_sysc_idle(struct work_struct *work) static const struct soc_device_attribute sysc_soc_match[] = { SOC_FLAG("OMAP242*", SOC_2420), SOC_FLAG("OMAP243*", SOC_2430), + SOC_FLAG("AM35*", SOC_AM35), SOC_FLAG("OMAP3[45]*", SOC_3430), SOC_FLAG("OMAP3[67]*", SOC_3630), SOC_FLAG("OMAP443*", SOC_4430), @@ -3229,7 +3242,7 @@ static int sysc_check_active_timer(struct sysc *ddata) * can be dropped if we stop supporting old beagleboard revisions * A to B4 at some point. */ - if (sysc_soc->soc == SOC_3430) + if (sysc_soc->soc == SOC_3430 || sysc_soc->soc == SOC_AM35) error = -ENXIO; else error = -EBUSY; diff --git a/drivers/clk/clk-si521xx.c b/drivers/clk/clk-si521xx.c index 4eaf1b53f06b..ef4ba467e747 100644 --- a/drivers/clk/clk-si521xx.c +++ b/drivers/clk/clk-si521xx.c @@ -96,7 +96,7 @@ static int si521xx_regmap_i2c_write(void *context, unsigned int reg, unsigned int val) { struct i2c_client *i2c = context; - const u8 data[3] = { reg, 1, val }; + const u8 data[2] = { reg, val }; const int count = ARRAY_SIZE(data); int ret; @@ -146,7 +146,7 @@ static int si521xx_regmap_i2c_read(void *context, unsigned int reg, static const struct regmap_config si521xx_regmap_config = { .reg_bits = 8, .val_bits = 8, - .cache_type = REGCACHE_NONE, + .cache_type = REGCACHE_FLAT, .max_register = SI521XX_REG_DA, .rd_table = &si521xx_readable_table, .wr_table = &si521xx_writeable_table, @@ -281,9 +281,10 @@ static int si521xx_probe(struct i2c_client *client) { const u16 chip_info = (u16)(uintptr_t)device_get_match_data(&client->dev); const struct clk_parent_data clk_parent_data = { .index = 0 }; - struct si521xx *si; + const u8 data[3] = { SI521XX_REG_BC, 1, 1 }; unsigned char name[6] = "DIFF0"; struct clk_init_data init = {}; + struct si521xx *si; int i, ret; if (!chip_info) @@ -308,7 +309,7 @@ static int si521xx_probe(struct i2c_client *client) "Failed to allocate register map\n"); /* Always read back 1 Byte via I2C */ - ret = regmap_write(si->regmap, SI521XX_REG_BC, 1); + ret = i2c_master_send(client, data, ARRAY_SIZE(data)); if (ret < 0) return ret; diff --git a/drivers/clk/clk-versaclock3.c b/drivers/clk/clk-versaclock3.c index 7ab2447bd203..3d7de355f8f6 100644 --- a/drivers/clk/clk-versaclock3.c +++ b/drivers/clk/clk-versaclock3.c @@ -118,21 +118,21 @@ enum vc3_div { VC3_DIV5, }; -enum vc3_clk_mux { - VC3_DIFF2_MUX, - VC3_DIFF1_MUX, - VC3_SE3_MUX, - VC3_SE2_MUX, - VC3_SE1_MUX, -}; - enum vc3_clk { - VC3_DIFF2, - VC3_DIFF1, - VC3_SE3, - VC3_SE2, - VC3_SE1, VC3_REF, + VC3_SE1, + VC3_SE2, + VC3_SE3, + VC3_DIFF1, + VC3_DIFF2, +}; + +enum vc3_clk_mux { + VC3_SE1_MUX = VC3_SE1 - 1, + VC3_SE2_MUX = VC3_SE2 - 1, + VC3_SE3_MUX = VC3_SE3 - 1, + VC3_DIFF1_MUX = VC3_DIFF1 - 1, + VC3_DIFF2_MUX = VC3_DIFF2 - 1, }; struct vc3_clk_data { @@ -401,11 +401,10 @@ static long vc3_pll_round_rate(struct clk_hw *hw, unsigned long rate, /* Determine best fractional part, which is 16 bit wide */ div_frc = rate % *parent_rate; div_frc *= BIT(16) - 1; - do_div(div_frc, *parent_rate); - vc3->div_frc = (u32)div_frc; + vc3->div_frc = min_t(u64, div64_ul(div_frc, *parent_rate), U16_MAX); rate = (*parent_rate * - (vc3->div_int * VC3_2_POW_16 + div_frc) / VC3_2_POW_16); + (vc3->div_int * VC3_2_POW_16 + vc3->div_frc) / VC3_2_POW_16); } else { rate = *parent_rate * vc3->div_int; } @@ -897,33 +896,33 @@ static struct vc3_hw_data clk_div[] = { }; static struct vc3_hw_data clk_mux[] = { - [VC3_DIFF2_MUX] = { + [VC3_SE1_MUX] = { .data = &(struct vc3_clk_data) { - .offs = VC3_DIFF2_CTRL_REG, - .bitmsk = VC3_DIFF2_CTRL_REG_DIFF2_CLK_SEL + .offs = VC3_SE1_DIV4_CTRL, + .bitmsk = VC3_SE1_DIV4_CTRL_SE1_CLK_SEL }, .hw.init = &(struct clk_init_data){ - .name = "diff2_mux", + .name = "se1_mux", .ops = &vc3_clk_mux_ops, .parent_hws = (const struct clk_hw *[]) { - &clk_div[VC3_DIV1].hw, - &clk_div[VC3_DIV3].hw + &clk_div[VC3_DIV5].hw, + &clk_div[VC3_DIV4].hw }, .num_parents = 2, .flags = CLK_SET_RATE_PARENT } }, - [VC3_DIFF1_MUX] = { + [VC3_SE2_MUX] = { .data = &(struct vc3_clk_data) { - .offs = VC3_DIFF1_CTRL_REG, - .bitmsk = VC3_DIFF1_CTRL_REG_DIFF1_CLK_SEL + .offs = VC3_SE2_CTRL_REG0, + .bitmsk = VC3_SE2_CTRL_REG0_SE2_CLK_SEL }, .hw.init = &(struct clk_init_data){ - .name = "diff1_mux", + .name = "se2_mux", .ops = &vc3_clk_mux_ops, .parent_hws = (const struct clk_hw *[]) { - &clk_div[VC3_DIV1].hw, - &clk_div[VC3_DIV3].hw + &clk_div[VC3_DIV5].hw, + &clk_div[VC3_DIV4].hw }, .num_parents = 2, .flags = CLK_SET_RATE_PARENT @@ -945,33 +944,33 @@ static struct vc3_hw_data clk_mux[] = { .flags = CLK_SET_RATE_PARENT } }, - [VC3_SE2_MUX] = { + [VC3_DIFF1_MUX] = { .data = &(struct vc3_clk_data) { - .offs = VC3_SE2_CTRL_REG0, - .bitmsk = VC3_SE2_CTRL_REG0_SE2_CLK_SEL + .offs = VC3_DIFF1_CTRL_REG, + .bitmsk = VC3_DIFF1_CTRL_REG_DIFF1_CLK_SEL }, .hw.init = &(struct clk_init_data){ - .name = "se2_mux", + .name = "diff1_mux", .ops = &vc3_clk_mux_ops, .parent_hws = (const struct clk_hw *[]) { - &clk_div[VC3_DIV5].hw, - &clk_div[VC3_DIV4].hw + &clk_div[VC3_DIV1].hw, + &clk_div[VC3_DIV3].hw }, .num_parents = 2, .flags = CLK_SET_RATE_PARENT } }, - [VC3_SE1_MUX] = { + [VC3_DIFF2_MUX] = { .data = &(struct vc3_clk_data) { - .offs = VC3_SE1_DIV4_CTRL, - .bitmsk = VC3_SE1_DIV4_CTRL_SE1_CLK_SEL + .offs = VC3_DIFF2_CTRL_REG, + .bitmsk = VC3_DIFF2_CTRL_REG_DIFF2_CLK_SEL }, .hw.init = &(struct clk_init_data){ - .name = "se1_mux", + .name = "diff2_mux", .ops = &vc3_clk_mux_ops, .parent_hws = (const struct clk_hw *[]) { - &clk_div[VC3_DIV5].hw, - &clk_div[VC3_DIV4].hw + &clk_div[VC3_DIV1].hw, + &clk_div[VC3_DIV3].hw }, .num_parents = 2, .flags = CLK_SET_RATE_PARENT @@ -1110,7 +1109,7 @@ static int vc3_probe(struct i2c_client *client) name, 0, CLK_SET_RATE_PARENT, 1, 1); else clk_out[i] = devm_clk_hw_register_fixed_factor_parent_hw(dev, - name, &clk_mux[i].hw, CLK_SET_RATE_PARENT, 1, 1); + name, &clk_mux[i - 1].hw, CLK_SET_RATE_PARENT, 1, 1); if (IS_ERR(clk_out[i])) return PTR_ERR(clk_out[i]); diff --git a/drivers/clk/sprd/ums512-clk.c b/drivers/clk/sprd/ums512-clk.c index 8f4441dd572b..9384ecc6c741 100644 --- a/drivers/clk/sprd/ums512-clk.c +++ b/drivers/clk/sprd/ums512-clk.c @@ -800,7 +800,7 @@ static SPRD_MUX_CLK_DATA(uart1_clk, "uart1-clk", uart_parents, 0x250, 0, 3, UMS512_MUX_FLAG); static const struct clk_parent_data thm_parents[] = { - { .fw_name = "ext-32m" }, + { .fw_name = "ext-32k" }, { .hw = &clk_250k.hw }, }; static SPRD_MUX_CLK_DATA(thm0_clk, "thm0-clk", thm_parents, diff --git a/drivers/clk/tegra/clk-bpmp.c b/drivers/clk/tegra/clk-bpmp.c index a9f3fb448de6..7bfba0afd778 100644 --- a/drivers/clk/tegra/clk-bpmp.c +++ b/drivers/clk/tegra/clk-bpmp.c @@ -159,7 +159,7 @@ static unsigned long tegra_bpmp_clk_recalc_rate(struct clk_hw *hw, err = tegra_bpmp_clk_transfer(clk->bpmp, &msg); if (err < 0) - return err; + return 0; return response.rate; } diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index d1c559879dcc..40d055560e52 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -14,7 +14,7 @@ struct cxl_cxims_data { int nr_maps; - u64 xormaps[]; + u64 xormaps[] __counted_by(nr_maps); }; /* @@ -112,9 +112,9 @@ static int cxl_parse_cxims(union acpi_subtable_headers *header, void *arg, GFP_KERNEL); if (!cximsd) return -ENOMEM; + cximsd->nr_maps = nr_maps; memcpy(cximsd->xormaps, cxims->xormap_list, nr_maps * sizeof(*cximsd->xormaps)); - cximsd->nr_maps = nr_maps; cxlrd->platform_data = cximsd; return 0; diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index ca60bb8114f2..4df4f614f490 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -715,24 +715,25 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel) for (i = 0; i < cel_entries; i++) { u16 opcode = le16_to_cpu(cel_entry[i].opcode); struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + int enabled = 0; - if (!cmd && (!cxl_is_poison_command(opcode) || - !cxl_is_security_command(opcode))) { - dev_dbg(dev, - "Opcode 0x%04x unsupported by driver\n", opcode); - continue; - } - - if (cmd) + if (cmd) { set_bit(cmd->info.id, mds->enabled_cmds); + enabled++; + } - if (cxl_is_poison_command(opcode)) + if (cxl_is_poison_command(opcode)) { cxl_set_poison_cmd_enabled(&mds->poison, opcode); + enabled++; + } - if (cxl_is_security_command(opcode)) + if (cxl_is_security_command(opcode)) { cxl_set_security_cmd_enabled(&mds->security, opcode); + enabled++; + } - dev_dbg(dev, "Opcode 0x%04x enabled\n", opcode); + dev_dbg(dev, "Opcode 0x%04x %s\n", opcode, + enabled ? "enabled" : "unsupported by driver"); } } diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 724be8448eb4..7ca01a834e18 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include <linux/platform_device.h> #include <linux/memregion.h> #include <linux/workqueue.h> #include <linux/debugfs.h> @@ -706,16 +707,20 @@ static int cxl_setup_comp_regs(struct device *dev, struct cxl_register_map *map, return cxl_setup_regs(map); } -static inline int cxl_port_setup_regs(struct cxl_port *port, - resource_size_t component_reg_phys) +static int cxl_port_setup_regs(struct cxl_port *port, + resource_size_t component_reg_phys) { + if (dev_is_platform(port->uport_dev)) + return 0; return cxl_setup_comp_regs(&port->dev, &port->comp_map, component_reg_phys); } -static inline int cxl_dport_setup_regs(struct cxl_dport *dport, - resource_size_t component_reg_phys) +static int cxl_dport_setup_regs(struct cxl_dport *dport, + resource_size_t component_reg_phys) { + if (dev_is_platform(dport->dport_dev)) + return 0; return cxl_setup_comp_regs(dport->dport_dev, &dport->comp_map, component_reg_phys); } diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index e115ba382e04..6d63b8798c29 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -717,13 +717,35 @@ static int match_free_decoder(struct device *dev, void *data) return 0; } +static int match_auto_decoder(struct device *dev, void *data) +{ + struct cxl_region_params *p = data; + struct cxl_decoder *cxld; + struct range *r; + + if (!is_switch_decoder(dev)) + return 0; + + cxld = to_cxl_decoder(dev); + r = &cxld->hpa_range; + + if (p->res && p->res->start == r->start && p->res->end == r->end) + return 1; + + return 0; +} + static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port, struct cxl_region *cxlr) { struct device *dev; int id = 0; - dev = device_find_child(&port->dev, &id, match_free_decoder); + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) + dev = device_find_child(&port->dev, &cxlr->params, + match_auto_decoder); + else + dev = device_find_child(&port->dev, &id, match_free_decoder); if (!dev) return NULL; /* @@ -1154,16 +1176,15 @@ static int cxl_port_setup_targets(struct cxl_port *port, } /* - * If @parent_port is masking address bits, pick the next unused address - * bit to route @port's targets. + * Interleave granularity is a multiple of @parent_port granularity. + * Multiplier is the parent port interleave ways. */ - if (parent_iw > 1 && cxl_rr->nr_targets > 1) { - u32 address_bit = max(peig + peiw, eiw + peig); - - eig = address_bit - eiw + 1; - } else { - eiw = peiw; - eig = peig; + rc = granularity_to_eig(parent_ig * parent_iw, &eig); + if (rc) { + dev_dbg(&cxlr->dev, + "%s: invalid granularity calculation (%d * %d)\n", + dev_name(&parent_port->dev), parent_ig, parent_iw); + return rc; } rc = eig_to_granularity(eig, &ig); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 1cb1494c28fe..44a21ab7add5 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -529,7 +529,6 @@ static int cxl_pci_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type, static int cxl_pci_ras_unmask(struct pci_dev *pdev) { - struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus); struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); void __iomem *addr; u32 orig_val, val, mask; @@ -541,9 +540,9 @@ static int cxl_pci_ras_unmask(struct pci_dev *pdev) return 0; } - /* BIOS has CXL error control */ - if (!host_bridge->native_cxl_error) - return -ENXIO; + /* BIOS has PCIe AER error control */ + if (!pcie_aer_is_native(pdev)) + return 0; rc = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &cap); if (rc) diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c index 789193ed0386..c278d5facf7d 100644 --- a/drivers/dma/ti/k3-udma-glue.c +++ b/drivers/dma/ti/k3-udma-glue.c @@ -558,6 +558,9 @@ int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn) tx_chn->virq = k3_ringacc_get_ring_irq_num(tx_chn->ringtxcq); } + if (!tx_chn->virq) + return -ENXIO; + return tx_chn->virq; } EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_irq); diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 26db5b8dfc1e..749868b9e80d 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -81,7 +81,8 @@ MODULE_PARM_DESC(exclusive_login, "Exclusive login to sbp2 device " * * - power condition * Set the power condition field in the START STOP UNIT commands sent by - * sd_mod on suspend, resume, and shutdown (if manage_start_stop is on). + * sd_mod on suspend, resume, and shutdown (if manage_system_start_stop or + * manage_runtime_start_stop is on). * Some disks need this to spin down or to resume properly. * * - override internal blacklist @@ -1517,8 +1518,10 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->use_10_for_rw = 1; - if (sbp2_param_exclusive_login) - sdev->manage_start_stop = 1; + if (sbp2_param_exclusive_login) { + sdev->manage_system_start_stop = true; + sdev->manage_runtime_start_stop = true; + } if (sdev->type == TYPE_ROM) sdev->use_10_for_ms = 1; diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 2109cd178ff7..121f4fc903cd 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -397,6 +397,19 @@ static u32 ffa_get_num_pages_sg(struct scatterlist *sg) return num_pages; } +static u8 ffa_memory_attributes_get(u32 func_id) +{ + /* + * For the memory lend or donate operation, if the receiver is a PE or + * a proxy endpoint, the owner/sender must not specify the attributes + */ + if (func_id == FFA_FN_NATIVE(MEM_LEND) || + func_id == FFA_MEM_LEND) + return 0; + + return FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | FFA_MEM_INNER_SHAREABLE; +} + static int ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, struct ffa_mem_ops_args *args) @@ -413,8 +426,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, mem_region->tag = args->tag; mem_region->flags = args->flags; mem_region->sender_id = drv_info->vm_id; - mem_region->attributes = FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | - FFA_MEM_INNER_SHAREABLE; + mem_region->attributes = ffa_memory_attributes_get(func_id); ep_mem_access = &mem_region->ep_mem_access[0]; for (idx = 0; idx < args->nattrs; idx++, ep_mem_access++) { diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index c0cd556fbaae..30dedd6ebfde 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -1080,6 +1080,8 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph) if (!pinfo) return -ENOMEM; + pinfo->version = version; + ret = scmi_perf_attributes_get(ph, pinfo); if (ret) return ret; @@ -1104,8 +1106,6 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph) if (ret) return ret; - pinfo->version = version; - return ph->set_priv(ph, pinfo); } diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 1599f1176842..ce20a60676f0 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -623,6 +623,34 @@ static __init int match_config_table(const efi_guid_t *guid, return 0; } +/** + * reserve_unaccepted - Map and reserve unaccepted configuration table + * @unaccepted: Pointer to unaccepted memory table + * + * memblock_add() makes sure that the table is mapped in direct mapping. During + * normal boot it happens automatically because the table is allocated from + * usable memory. But during crashkernel boot only memory specifically reserved + * for crash scenario is mapped. memblock_add() forces the table to be mapped + * in crashkernel case. + * + * Align the range to the nearest page borders. Ranges smaller than page size + * are not going to be mapped. + * + * memblock_reserve() makes sure that future allocations will not touch the + * table. + */ + +static __init void reserve_unaccepted(struct efi_unaccepted_memory *unaccepted) +{ + phys_addr_t start, size; + + start = PAGE_ALIGN_DOWN(efi.unaccepted); + size = PAGE_ALIGN(sizeof(*unaccepted) + unaccepted->size); + + memblock_add(start, size); + memblock_reserve(start, size); +} + int __init efi_config_parse_tables(const efi_config_table_t *config_tables, int count, const efi_config_table_type_t *arch_tables) @@ -751,11 +779,9 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, unaccepted = early_memremap(efi.unaccepted, sizeof(*unaccepted)); if (unaccepted) { - unsigned long size; if (unaccepted->version == 1) { - size = sizeof(*unaccepted) + unaccepted->size; - memblock_reserve(efi.unaccepted, size); + reserve_unaccepted(unaccepted); } else { efi.unaccepted = EFI_INVALID_TABLE_ADDR; } diff --git a/drivers/firmware/imx/imx-dsp.c b/drivers/firmware/imx/imx-dsp.c index 3dba590a2a95..508eab346fc6 100644 --- a/drivers/firmware/imx/imx-dsp.c +++ b/drivers/firmware/imx/imx-dsp.c @@ -114,6 +114,7 @@ static int imx_dsp_setup_channels(struct imx_dsp_ipc *dsp_ipc) dsp_chan->idx = i % 2; dsp_chan->ch = mbox_request_channel_byname(cl, chan_name); if (IS_ERR(dsp_chan->ch)) { + kfree(dsp_chan->name); ret = PTR_ERR(dsp_chan->ch); if (ret != -EPROBE_DEFER) dev_err(dev, "Failed to request mbox chan %s ret %d\n", diff --git a/drivers/gpio/gpio-pmic-eic-sprd.c b/drivers/gpio/gpio-pmic-eic-sprd.c index 2b9b7be9b8fd..01c0fd0a9d8c 100644 --- a/drivers/gpio/gpio-pmic-eic-sprd.c +++ b/drivers/gpio/gpio-pmic-eic-sprd.c @@ -352,6 +352,7 @@ static int sprd_pmic_eic_probe(struct platform_device *pdev) pmic_eic->chip.set_config = sprd_pmic_eic_set_config; pmic_eic->chip.set = sprd_pmic_eic_set; pmic_eic->chip.get = sprd_pmic_eic_get; + pmic_eic->chip.can_sleep = true; irq = &pmic_eic->chip.irq; gpio_irq_chip_set_chip(irq, &pmic_eic_irq_chip); diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 271db3639a78..44bf1709a648 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -19,6 +19,7 @@ #include <linux/irq.h> #include <linux/irq_sim.h> #include <linux/list.h> +#include <linux/minmax.h> #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/mutex.h> @@ -685,52 +686,32 @@ gpio_sim_device_config_live_show(struct config_item *item, char *page) return sprintf(page, "%c\n", live ? '1' : '0'); } -static char **gpio_sim_make_line_names(struct gpio_sim_bank *bank, - unsigned int *line_names_size) +static unsigned int gpio_sim_get_line_names_size(struct gpio_sim_bank *bank) { - unsigned int max_offset = 0; - bool has_line_names = false; struct gpio_sim_line *line; - char **line_names; + unsigned int size = 0; list_for_each_entry(line, &bank->line_list, siblings) { - if (line->offset >= bank->num_lines) + if (!line->name || (line->offset >= bank->num_lines)) continue; - if (line->name) { - if (line->offset > max_offset) - max_offset = line->offset; - - /* - * max_offset can stay at 0 so it's not an indicator - * of whether line names were configured at all. - */ - has_line_names = true; - } + size = max(size, line->offset + 1); } - if (!has_line_names) - /* - * This is not an error - NULL means, there are no line - * names configured. - */ - return NULL; - - *line_names_size = max_offset + 1; + return size; +} - line_names = kcalloc(*line_names_size, sizeof(*line_names), GFP_KERNEL); - if (!line_names) - return ERR_PTR(-ENOMEM); +static void +gpio_sim_set_line_names(struct gpio_sim_bank *bank, char **line_names) +{ + struct gpio_sim_line *line; list_for_each_entry(line, &bank->line_list, siblings) { - if (line->offset >= bank->num_lines) + if (!line->name || (line->offset >= bank->num_lines)) continue; - if (line->name && (line->offset <= max_offset)) - line_names[line->offset] = line->name; + line_names[line->offset] = line->name; } - - return line_names; } static void gpio_sim_remove_hogs(struct gpio_sim_device *dev) @@ -834,7 +815,7 @@ gpio_sim_make_bank_swnode(struct gpio_sim_bank *bank, struct fwnode_handle *parent) { struct property_entry properties[GPIO_SIM_PROP_MAX]; - unsigned int prop_idx = 0, line_names_size = 0; + unsigned int prop_idx = 0, line_names_size; char **line_names __free(kfree) = NULL; memset(properties, 0, sizeof(properties)); @@ -845,14 +826,19 @@ gpio_sim_make_bank_swnode(struct gpio_sim_bank *bank, properties[prop_idx++] = PROPERTY_ENTRY_STRING("gpio-sim,label", bank->label); - line_names = gpio_sim_make_line_names(bank, &line_names_size); - if (IS_ERR(line_names)) - return ERR_CAST(line_names); + line_names_size = gpio_sim_get_line_names_size(bank); + if (line_names_size) { + line_names = kcalloc(line_names_size, sizeof(*line_names), + GFP_KERNEL); + if (!line_names) + return ERR_PTR(-ENOMEM); + + gpio_sim_set_line_names(bank, line_names); - if (line_names) properties[prop_idx++] = PROPERTY_ENTRY_STRING_ARRAY_LEN( "gpio-line-names", line_names, line_names_size); + } return fwnode_create_software_node(properties, parent); } diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c index 78f8790168ae..f96d260a4a19 100644 --- a/drivers/gpio/gpio-tb10x.c +++ b/drivers/gpio/gpio-tb10x.c @@ -195,7 +195,7 @@ static int tb10x_gpio_probe(struct platform_device *pdev) handle_edge_irq, IRQ_NOREQUEST, IRQ_NOPROBE, IRQ_GC_INIT_MASK_CACHE); if (ret) - return ret; + goto err_remove_domain; gc = tb10x_gpio->domain->gc->gc[0]; gc->reg_base = tb10x_gpio->base; @@ -209,6 +209,10 @@ static int tb10x_gpio_probe(struct platform_device *pdev) } return 0; + +err_remove_domain: + irq_domain_remove(tb10x_gpio->domain); + return ret; } static int tb10x_gpio_remove(struct platform_device *pdev) diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c index bbd9e9191199..fad979797486 100644 --- a/drivers/gpio/gpio-timberdale.c +++ b/drivers/gpio/gpio-timberdale.c @@ -43,9 +43,10 @@ static int timbgpio_update_bit(struct gpio_chip *gpio, unsigned index, unsigned offset, bool enabled) { struct timbgpio *tgpio = gpiochip_get_data(gpio); + unsigned long flags; u32 reg; - spin_lock(&tgpio->lock); + spin_lock_irqsave(&tgpio->lock, flags); reg = ioread32(tgpio->membase + offset); if (enabled) @@ -54,7 +55,7 @@ static int timbgpio_update_bit(struct gpio_chip *gpio, unsigned index, reg &= ~(1 << index); iowrite32(reg, tgpio->membase + offset); - spin_unlock(&tgpio->lock); + spin_unlock_irqrestore(&tgpio->lock, flags); return 0; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index ab9ef1c20349..3caa020391c7 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -136,7 +136,7 @@ config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" depends on DRM select FRAMEBUFFER_CONSOLE_DETECT_PRIMARY if FRAMEBUFFER_CONSOLE - default y + default FB help Choose this option if you have a need for the legacy fbdev support. Note that this support also provides the linux console diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 73ee14f7a9a4..dce9e7d5e4ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -1776,7 +1776,7 @@ static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct atom_context *ctx = adev->mode_info.atom_context; - return sysfs_emit(buf, "%s\n", ctx->vbios_ver_str); + return sysfs_emit(buf, "%s\n", ctx->vbios_pn); } static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 937c54fc7174..163445baa4fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -801,6 +801,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, enable ? "enable":"disable", get_ras_block_str(head), amdgpu_ras_is_poison_mode_supported(adev), ret); + kfree(info); return ret; } 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 8a6cb41444a4..0d3d538b64eb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -216,7 +216,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (q->wptr_bo) { wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1); - queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off; + queue_input.wptr_mc_addr = amdgpu_bo_gpu_offset(q->wptr_bo) + wptr_addr_off; } queue_input.is_kfd_process = 1; 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 c6fd34bab358..868946dd7ef1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6098,8 +6098,6 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) drm_mode_set_crtcinfo(&saved_mode, 0); - else if (!old_stream) - drm_mode_set_crtcinfo(&mode, 0); /* * If scaling is enabled and refresh rate didn't change @@ -6661,6 +6659,8 @@ enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connec goto fail; } + drm_mode_set_crtcinfo(mode, 0); + stream = create_validate_stream_for_sink(aconnector, mode, to_dm_connector_state(connector->state), NULL); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 478281f2a5ba..2a6157555fd1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1178,12 +1178,15 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) dto_params.otg_inst = tg->inst; dto_params.timing = &pipe_ctx->stream->timing; dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; - dccg->funcs->set_dtbclk_dto(dccg, &dto_params); - dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst); - dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst); - } else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST && dccg->funcs->disable_symclk_se) + if (dccg) { + dccg->funcs->set_dtbclk_dto(dccg, &dto_params); + dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst); + dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst); + } + } else if (dccg && dccg->funcs->disable_symclk_se) { dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst, link_enc->transmitter - TRANSMITTER_UNIPHY_A); + } if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { /* TODO: This looks like a bug to me as we are disabling HPO IO when @@ -2658,11 +2661,11 @@ void dce110_prepare_bandwidth( struct clk_mgr *dccg = dc->clk_mgr; dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool); - - dccg->funcs->update_clocks( - dccg, - context, - false); + if (dccg) + dccg->funcs->update_clocks( + dccg, + context, + false); } void dce110_optimize_bandwidth( @@ -2673,10 +2676,11 @@ void dce110_optimize_bandwidth( dce110_set_displaymarks(dc, context); - dccg->funcs->update_clocks( - dccg, - context, - true); + if (dccg) + dccg->funcs->update_clocks( + dccg, + context, + true); } static void dce110_program_front_end_for_pipe( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index e72f15ac0048..aeadc587433f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2692,8 +2692,6 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) struct dce_hwseq *hws = dc->hwseq; unsigned int k1_div = PIXEL_RATE_DIV_NA; unsigned int k2_div = PIXEL_RATE_DIV_NA; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); - struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { if (dc->hwseq->funcs.setup_hpo_hw_control) @@ -2713,10 +2711,8 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) dto_params.timing = &pipe_ctx->stream->timing; dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr); dccg->funcs->set_dtbclk_dto(dccg, &dto_params); - } else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST && dccg->funcs->enable_symclk_se) - dccg->funcs->enable_symclk_se(dccg, - stream_enc->stream_enc_inst, link_enc->transmitter - TRANSMITTER_UNIPHY_A); - + } else { + } if (hws->funcs.calculate_dccg_k1_k2_values && dc->res_pool->dccg->funcs->set_pixel_rate_div) { hws->funcs.calculate_dccg_k1_k2_values(pipe_ctx, &k1_div, &k2_div); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c index 3082da04a63d..1d052f08aff5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c @@ -75,7 +75,7 @@ void mpc32_power_on_blnd_lut( if (power_on) { REG_UPDATE(MPCC_MCM_MEM_PWR_CTRL[mpcc_id], MPCC_MCM_1DLUT_MEM_PWR_FORCE, 0); REG_WAIT(MPCC_MCM_MEM_PWR_CTRL[mpcc_id], MPCC_MCM_1DLUT_MEM_PWR_STATE, 0, 1, 5); - } else { + } else if (!mpc->ctx->dc->debug.disable_mem_low_power) { ASSERT(false); /* TODO: change to mpc * dpp_base->ctx->dc->optimized_required = true; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 8f1633c3fb93..73a4a4eb29e0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -100,6 +100,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, st->nents = 0; for (i = 0; i < page_count; i++) { struct folio *folio; + unsigned long nr_pages; const unsigned int shrink[] = { I915_SHRINK_BOUND | I915_SHRINK_UNBOUND, 0, @@ -150,6 +151,8 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, } } while (1); + nr_pages = min_t(unsigned long, + folio_nr_pages(folio), page_count - i); if (!i || sg->length >= max_segment || folio_pfn(folio) != next_pfn) { @@ -157,13 +160,13 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, sg = sg_next(sg); st->nents++; - sg_set_folio(sg, folio, folio_size(folio), 0); + sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0); } else { /* XXX: could overflow? */ - sg->length += folio_size(folio); + sg->length += nr_pages * PAGE_SIZE; } - next_pfn = folio_pfn(folio) + folio_nr_pages(folio); - i += folio_nr_pages(folio) - 1; + next_pfn = folio_pfn(folio) + nr_pages; + i += nr_pages - 1; /* Check that the i965g/gm workaround works. */ GEM_BUG_ON(gfp & __GFP_DMA32 && next_pfn >= 0x00100000UL); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index ee15486fed0d..e85d70a62123 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -558,7 +558,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, DRIVER_CAPS(i915)->has_logical_contexts = true; ewma__engine_latency_init(&engine->latency); - seqcount_init(&engine->stats.execlists.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 8a641bcf777c..3292524469d5 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3550,6 +3550,8 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) logical_ring_default_vfuncs(engine); logical_ring_default_irqs(engine); + seqcount_init(&engine->stats.execlists.lock); + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) rcs_submission_override(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index dd0ed941441a..da21f2786b5d 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -511,20 +511,31 @@ void intel_ggtt_unbind_vma(struct i915_address_space *vm, vm->clear_range(vm, vma_res->start, vma_res->vma_size); } +/* + * Reserve the top of the GuC address space for firmware images. Addresses + * beyond GUC_GGTT_TOP in the GuC address space are inaccessible by GuC, + * which makes for a suitable range to hold GuC/HuC firmware images if the + * size of the GGTT is 4G. However, on a 32-bit platform the size of the GGTT + * is limited to 2G, which is less than GUC_GGTT_TOP, but we reserve a chunk + * of the same size anyway, which is far more than needed, to keep the logic + * in uc_fw_ggtt_offset() simple. + */ +#define GUC_TOP_RESERVE_SIZE (SZ_4G - GUC_GGTT_TOP) + static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt) { - u64 size; + u64 offset; int ret; if (!intel_uc_uses_guc(&ggtt->vm.gt->uc)) return 0; - GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP); - size = ggtt->vm.total - GUC_GGTT_TOP; + GEM_BUG_ON(ggtt->vm.total <= GUC_TOP_RESERVE_SIZE); + offset = ggtt->vm.total - GUC_TOP_RESERVE_SIZE; - ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, size, - GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE, - PIN_NOEVICT); + ret = i915_gem_gtt_reserve(&ggtt->vm, NULL, &ggtt->uc_fw, + GUC_TOP_RESERVE_SIZE, offset, + I915_COLOR_UNEVICTABLE, PIN_NOEVICT); if (ret) drm_dbg(&ggtt->vm.i915->drm, "Failed to reserve top of GGTT for GuC\n"); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 957d0aeb0c02..c378cc7c953c 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1094,6 +1094,9 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) I915_BO_ALLOC_PM_VOLATILE); if (IS_ERR(obj)) { obj = i915_gem_object_create_shmem(engine->i915, context_size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + /* * Wa_22016122933: For Media version 13.0, all Media GT shared * memory needs to be mapped as WC on CPU side and UC (PAT @@ -1102,8 +1105,6 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) if (intel_gt_needs_wa_22016122933(engine->gt)) i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE); } - if (IS_ERR(obj)) - return ERR_CAST(obj); vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL); if (IS_ERR(vma)) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index b5b7f2fe8c78..dc7b40e06e38 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1433,6 +1433,36 @@ static void guc_timestamp_ping(struct work_struct *wrk) int srcu, ret; /* + * Ideally the busyness worker should take a gt pm wakeref because the + * worker only needs to be active while gt is awake. However, the + * gt_park path cancels the worker synchronously and this complicates + * the flow if the worker is also running at the same time. The cancel + * waits for the worker and when the worker releases the wakeref, that + * would call gt_park and would lead to a deadlock. + * + * The resolution is to take the global pm wakeref if runtime pm is + * already active. If not, we don't need to update the busyness stats as + * the stats would already be updated when the gt was parked. + * + * Note: + * - We do not requeue the worker if we cannot take a reference to runtime + * pm since intel_guc_busyness_unpark would requeue the worker in the + * resume path. + * + * - If the gt was parked longer than time taken for GT timestamp to roll + * over, we ignore those rollovers since we don't care about tracking + * the exact GT time. We only care about roll overs when the gt is + * active and running workloads. + * + * - There is a window of time between gt_park and runtime suspend, + * where the worker may run. This is acceptable since the worker will + * not find any new data to update busyness. + */ + wakeref = intel_runtime_pm_get_if_active(>->i915->runtime_pm); + if (!wakeref) + return; + + /* * Synchronize with gt reset to make sure the worker does not * corrupt the engine/guc stats. NB: can't actually block waiting * for a reset to complete as the reset requires flushing out @@ -1440,10 +1470,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) */ ret = intel_gt_reset_trylock(gt, &srcu); if (ret) - return; + goto err_trylock; - with_intel_runtime_pm(>->i915->runtime_pm, wakeref) - __update_guc_busyness_stats(guc); + __update_guc_busyness_stats(guc); /* adjust context stats for overflow */ xa_for_each(&guc->context_lookup, index, ce) @@ -1452,6 +1481,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) intel_gt_reset_unlock(gt, srcu); guc_enable_busyness_worker(guc); + +err_trylock: + intel_runtime_pm_put(>->i915->runtime_pm, wakeref); } static int guc_action_enable_usage_stats(struct intel_guc *guc) diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 9913971fa5d2..25ea76558690 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -334,6 +334,8 @@ static void meson_encoder_hdmi_hpd_notify(struct drm_bridge *bridge, return; cec_notifier_set_phys_addr_from_edid(encoder_hdmi->cec_notifier, edid); + + kfree(edid); } else cec_notifier_phys_addr_invalidate(encoder_hdmi->cec_notifier); } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 1fe17ff95f5e..e73a233c6572 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -189,21 +189,12 @@ u_free(void *addr) static inline void * u_memcpya(uint64_t user, unsigned int nmemb, unsigned int size) { - void *mem; - void __user *userptr = (void __force __user *)(uintptr_t)user; + void __user *userptr = u64_to_user_ptr(user); + size_t bytes; - size *= nmemb; - - mem = kvmalloc(size, GFP_KERNEL); - if (!mem) - return ERR_PTR(-ENOMEM); - - if (copy_from_user(mem, userptr, size)) { - u_free(mem); - return ERR_PTR(-EFAULT); - } - - return mem; + if (unlikely(check_mul_overflow(nmemb, size, &bytes))) + return ERR_PTR(-EOVERFLOW); + return vmemdup_user(userptr, bytes); } #include <nvif/object.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index 19024ce21fbb..5dda94e1318c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -213,7 +213,7 @@ nouveau_exec_job_timeout(struct nouveau_job *job) nouveau_sched_entity_fini(job->entity); - return DRM_GPU_SCHED_STAT_ENODEV; + return DRM_GPU_SCHED_STAT_NOMINAL; } static struct nouveau_job_ops nouveau_exec_job_ops = { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 61d9e70da9fd..ca762ea55413 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -207,7 +207,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha int nouveau_fence_emit(struct nouveau_fence *fence) { - struct nouveau_channel *chan = fence->channel; + struct nouveau_channel *chan = unrcu_pointer(fence->channel); struct nouveau_fence_chan *fctx = chan->fence; struct nouveau_fence_priv *priv = (void*)chan->drm->fence; int ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 88217185e0f3..3b7ea5221226 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -375,14 +375,20 @@ nouveau_sched_run_job(struct drm_sched_job *sched_job) static enum drm_gpu_sched_stat nouveau_sched_timedout_job(struct drm_sched_job *sched_job) { + struct drm_gpu_scheduler *sched = sched_job->sched; struct nouveau_job *job = to_nouveau_job(sched_job); + enum drm_gpu_sched_stat stat = DRM_GPU_SCHED_STAT_NOMINAL; - NV_PRINTK(warn, job->cli, "Job timed out.\n"); + drm_sched_stop(sched, sched_job); if (job->ops->timeout) - return job->ops->timeout(job); + stat = job->ops->timeout(job); + else + NV_PRINTK(warn, job->cli, "Generic job timeout.\n"); + + drm_sched_start(sched, true); - return DRM_GPU_SCHED_STAT_ENODEV; + return stat; } static void diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 186b28dc7038..05d5e7af6d25 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -939,7 +939,7 @@ static void drm_test_mm_insert_range(struct kunit *test) KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, 0, max - 1)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, 0, max / 2)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, - max / 2, max / 2)); + max / 2, max)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, max / 4 + 1, 3 * max / 4 - 1)); diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c index 3c00135ead45..5c514946bbad 100644 --- a/drivers/gpu/drm/virtio/virtgpu_submit.c +++ b/drivers/gpu/drm/virtio/virtgpu_submit.c @@ -361,7 +361,6 @@ static void virtio_gpu_complete_submit(struct virtio_gpu_submit *submit) submit->buf = NULL; submit->buflist = NULL; submit->sync_file = NULL; - submit->out_fence = NULL; submit->out_fence_fd = -1; } diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index cdd8c67d9129..affcfb243f0f 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -441,8 +441,25 @@ err_release_lock: void __i2c_dw_disable(struct dw_i2c_dev *dev) { + unsigned int raw_intr_stats; + unsigned int enable; int timeout = 100; + bool abort_needed; unsigned int status; + int ret; + + regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_intr_stats); + regmap_read(dev->map, DW_IC_ENABLE, &enable); + + abort_needed = raw_intr_stats & DW_IC_INTR_MST_ON_HOLD; + if (abort_needed) { + regmap_write(dev->map, DW_IC_ENABLE, enable | DW_IC_ENABLE_ABORT); + ret = regmap_read_poll_timeout(dev->map, DW_IC_ENABLE, enable, + !(enable & DW_IC_ENABLE_ABORT), 10, + 100); + if (ret) + dev_err(dev->dev, "timeout while trying to abort current transfer\n"); + } do { __i2c_dw_disable_nowait(dev); diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index cf4f684f5356..a7f6f3eafad7 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -98,6 +98,7 @@ #define DW_IC_INTR_START_DET BIT(10) #define DW_IC_INTR_GEN_CALL BIT(11) #define DW_IC_INTR_RESTART_DET BIT(12) +#define DW_IC_INTR_MST_ON_HOLD BIT(13) #define DW_IC_INTR_DEFAULT_MASK (DW_IC_INTR_RX_FULL | \ DW_IC_INTR_TX_ABRT | \ @@ -108,6 +109,8 @@ DW_IC_INTR_RX_UNDER | \ DW_IC_INTR_RD_REQ) +#define DW_IC_ENABLE_ABORT BIT(1) + #define DW_IC_STATUS_ACTIVITY BIT(0) #define DW_IC_STATUS_TFE BIT(2) #define DW_IC_STATUS_RFNE BIT(3) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 73ae06432133..1d855258a45d 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1754,6 +1754,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) "SMBus I801 adapter at %04lx", priv->smba); err = i2c_add_adapter(&priv->adapter); if (err) { + platform_device_unregister(priv->tco_pdev); i801_acpi_remove(priv); return err; } diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 495a8b5f6a2b..ae4bae63ad4f 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -694,6 +694,7 @@ static void npcm_i2c_callback(struct npcm_i2c *bus, { struct i2c_msg *msgs; int msgs_num; + bool do_complete = false; msgs = bus->msgs; msgs_num = bus->msgs_num; @@ -722,23 +723,17 @@ static void npcm_i2c_callback(struct npcm_i2c *bus, msgs[1].flags & I2C_M_RD) msgs[1].len = info; } - if (completion_done(&bus->cmd_complete) == false) - complete(&bus->cmd_complete); - break; - + do_complete = true; + break; case I2C_NACK_IND: /* MASTER transmit got a NACK before tx all bytes */ bus->cmd_err = -ENXIO; - if (bus->master_or_slave == I2C_MASTER) - complete(&bus->cmd_complete); - + do_complete = true; break; case I2C_BUS_ERR_IND: /* Bus error */ bus->cmd_err = -EAGAIN; - if (bus->master_or_slave == I2C_MASTER) - complete(&bus->cmd_complete); - + do_complete = true; break; case I2C_WAKE_UP_IND: /* I2C wake up */ @@ -752,6 +747,8 @@ static void npcm_i2c_callback(struct npcm_i2c *bus, if (bus->slave) bus->master_or_slave = I2C_SLAVE; #endif + if (do_complete) + complete(&bus->cmd_complete); } static u8 npcm_i2c_fifo_usage(struct npcm_i2c *bus) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index b3bb97762c85..71391b590ada 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -710,7 +710,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) * reset the IP instead of just flush fifos */ ret = xiic_reinit(i2c); - if (!ret) + if (ret < 0) dev_dbg(i2c->adap.dev.parent, "reinit failed\n"); if (i2c->rx_msg) { diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 313904be5f3b..57ff09f18c37 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -341,7 +341,7 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, priv->adap.lock_ops = &i2c_parent_lock_ops; /* Sanity check on class */ - if (i2c_mux_parent_classes(parent) & class) + if (i2c_mux_parent_classes(parent) & class & ~I2C_CLASS_DEPRECATED) dev_err(&parent->dev, "Segment %d behind mux can't share classes with ancestors\n", chan_id); diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index a3a122fae71e..22f2280eab7f 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -243,6 +243,10 @@ static int i2c_demux_pinctrl_probe(struct platform_device *pdev) props[i].name = devm_kstrdup(&pdev->dev, "status", GFP_KERNEL); props[i].value = devm_kstrdup(&pdev->dev, "ok", GFP_KERNEL); + if (!props[i].name || !props[i].value) { + err = -ENOMEM; + goto err_rollback; + } props[i].length = 3; of_changeset_init(&priv->chan[i].chgset); diff --git a/drivers/i2c/muxes/i2c-mux-gpio.c b/drivers/i2c/muxes/i2c-mux-gpio.c index 5d5cbe0130cd..5ca03bd34c8d 100644 --- a/drivers/i2c/muxes/i2c-mux-gpio.c +++ b/drivers/i2c/muxes/i2c-mux-gpio.c @@ -105,8 +105,10 @@ static int i2c_mux_gpio_probe_fw(struct gpiomux *mux, } else if (is_acpi_node(child)) { rc = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), values + i); - if (rc) + if (rc) { + fwnode_handle_put(child); return dev_err_probe(dev, rc, "Cannot get address\n"); + } } i++; diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 2082081402d3..0b8927508427 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -671,8 +671,7 @@ static int apple_dart_attach_dev(struct iommu_domain *domain, return ret; switch (domain->type) { - case IOMMU_DOMAIN_DMA: - case IOMMU_DOMAIN_UNMANAGED: + default: ret = apple_dart_domain_add_streams(dart_domain, cfg); if (ret) return ret; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 4d83edc2be99..8a16cd3ef487 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -186,6 +186,15 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd) } } +/* + * Cloned from the MAX_TLBI_OPS in arch/arm64/include/asm/tlbflush.h, this + * is used as a threshold to replace per-page TLBI commands to issue in the + * command queue with an address-space TLBI command, when SMMU w/o a range + * invalidation feature handles too many per-page TLBI commands, which will + * otherwise result in a soft lockup. + */ +#define CMDQ_MAX_TLBI_OPS (1 << (PAGE_SHIFT - 3)) + static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, @@ -201,8 +210,13 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn, * range. So do a simple translation here by calculating size correctly. */ size = end - start; - if (size == ULONG_MAX) - size = 0; + if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_RANGE_INV)) { + if (size >= CMDQ_MAX_TLBI_OPS * PAGE_SIZE) + size = 0; + } else { + if (size == ULONG_MAX) + size = 0; + } if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) { if (!size) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index e82bf1c449a3..bd0a596f9863 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1895,18 +1895,23 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd, /* Get the leaf page size */ tg = __ffs(smmu_domain->domain.pgsize_bitmap); + num_pages = size >> tg; + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ cmd->tlbi.tg = (tg - 10) / 2; /* - * Determine what level the granule is at. For non-leaf, io-pgtable - * assumes .tlb_flush_walk can invalidate multiple levels at once, - * so ignore the nominal last-level granule and leave TTL=0. + * Determine what level the granule is at. For non-leaf, both + * io-pgtable and SVA pass a nominal last-level granule because + * they don't know what level(s) actually apply, so ignore that + * and leave TTL=0. However for various errata reasons we still + * want to use a range command, so avoid the SVA corner case + * where both scale and num could be 0 as well. */ if (cmd->tlbi.leaf) cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); - - num_pages = size >> tg; + else if ((num_pages & CMDQ_TLBI_RANGE_NUM_MAX) == 1) + num_pages++; } cmds.num = 0; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 5db283c17e0d..3685ba90ec88 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2998,13 +2998,6 @@ static int iommu_suspend(void) struct intel_iommu *iommu = NULL; unsigned long flag; - for_each_active_iommu(iommu, drhd) { - iommu->iommu_state = kcalloc(MAX_SR_DMAR_REGS, sizeof(u32), - GFP_KERNEL); - if (!iommu->iommu_state) - goto nomem; - } - iommu_flush_all(); for_each_active_iommu(iommu, drhd) { @@ -3024,12 +3017,6 @@ static int iommu_suspend(void) raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } return 0; - -nomem: - for_each_active_iommu(iommu, drhd) - kfree(iommu->iommu_state); - - return -ENOMEM; } static void iommu_resume(void) @@ -3061,9 +3048,6 @@ static void iommu_resume(void) raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } - - for_each_active_iommu(iommu, drhd) - kfree(iommu->iommu_state); } static struct syscore_ops iommu_syscore_ops = { diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index c18fb699c87a..7dac94f62b4e 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -681,7 +681,7 @@ struct intel_iommu { struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; struct q_inval *qi; /* Queued invalidation info */ - u32 *iommu_state; /* Store iommu states between suspend and resume.*/ + u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/ #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 640275873a27..fab6c347ce57 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -262,7 +262,7 @@ struct mtk_iommu_data { struct device *smicomm_dev; struct mtk_iommu_bank_data *bank; - struct mtk_iommu_domain *share_dom; /* For 2 HWs share pgtable */ + struct mtk_iommu_domain *share_dom; struct regmap *pericfg; struct mutex mutex; /* Protect m4u_group/m4u_dom above */ @@ -643,8 +643,8 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom, struct mtk_iommu_domain *share_dom = data->share_dom; const struct mtk_iommu_iova_region *region; - /* Always use share domain in sharing pgtable case */ - if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE) && share_dom) { + /* Share pgtable when 2 MM IOMMU share the pgtable or one IOMMU use multiple iova ranges */ + if (share_dom) { dom->iop = share_dom->iop; dom->cfg = share_dom->cfg; dom->domain.pgsize_bitmap = share_dom->cfg.pgsize_bitmap; @@ -677,8 +677,7 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom, /* Update our support page sizes bitmap */ dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap; - if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) - data->share_dom = dom; + data->share_dom = dom; update_iova_region: /* Update the iova region for this domain */ diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index 8c581c985aa7..7f314e58f3ce 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -12,6 +12,7 @@ #include <linux/irqdomain.h> #include <linux/irq.h> #include <linux/irqchip.h> +#include <linux/irqchip/xtensa-mx.h> #include <linux/of.h> #include <asm/mxregs.h> diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index 04f9ea675f2c..214ed81eb0e9 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -479,10 +479,6 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data, led_parse_fwnode_props(dev, fwnode, &props); - /* We want to label LEDs that can produce full range of colors - * as RGB, not multicolor */ - BUG_ON(props.color == LED_COLOR_ID_MULTI); - if (props.label) { /* * If init_data.devicename is NULL, then it indicates that diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index aea95745c73f..90ce58fd629e 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -241,6 +241,7 @@ config MFD_CS42L43 tristate select MFD_CORE select REGMAP + select REGMAP_IRQ config MFD_CS42L43_I2C tristate "Cirrus Logic CS42L43 (I2C)" diff --git a/drivers/mfd/cs42l43.c b/drivers/mfd/cs42l43.c index 37b23e9bae82..7b6d07cbe6fc 100644 --- a/drivers/mfd/cs42l43.c +++ b/drivers/mfd/cs42l43.c @@ -1178,8 +1178,8 @@ err: } EXPORT_NS_GPL_DEV_PM_OPS(cs42l43_pm_ops, MFD_CS42L43) = { - SET_SYSTEM_SLEEP_PM_OPS(cs42l43_suspend, cs42l43_resume) - SET_RUNTIME_PM_OPS(cs42l43_runtime_suspend, cs42l43_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(cs42l43_suspend, cs42l43_resume) + RUNTIME_PM_OPS(cs42l43_runtime_suspend, cs42l43_runtime_resume, NULL) }; MODULE_DESCRIPTION("CS42L43 Core Driver"); diff --git a/drivers/misc/cardreader/rts5227.c b/drivers/misc/cardreader/rts5227.c index 3dae5e3a1697..cd512284bfb3 100644 --- a/drivers/misc/cardreader/rts5227.c +++ b/drivers/misc/cardreader/rts5227.c @@ -83,63 +83,20 @@ static void rts5227_fetch_vendor_settings(struct rtsx_pcr *pcr) static void rts5227_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; - u32 lval; struct rtsx_cr_option *option = &pcr->option; - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - if (CHK_PCI_PID(pcr, 0x522A)) { - if (0 == (lval & 0x0F)) - rtsx_pci_enable_oobs_polling(pcr); - else + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) rtsx_pci_disable_oobs_polling(pcr); + else + rtsx_pci_enable_oobs_polling(pcr); } - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_2_EN); - if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; - } static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) @@ -195,7 +152,7 @@ static int rts5227_extra_init_hw(struct rtsx_pcr *pcr) } } - if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) + if (option->force_clkreq_0) rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5228.c b/drivers/misc/cardreader/rts5228.c index f4ab09439da7..0c7f10bcf6f1 100644 --- a/drivers/misc/cardreader/rts5228.c +++ b/drivers/misc/cardreader/rts5228.c @@ -386,59 +386,25 @@ static void rts5228_process_ocp(struct rtsx_pcr *pcr) static void rts5228_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; - u32 lval; struct rtsx_cr_option *option = &pcr->option; - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - - if (0 == (lval & 0x0F)) - rtsx_pci_enable_oobs_polling(pcr); - else + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) rtsx_pci_disable_oobs_polling(pcr); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); else - rtsx_clear_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_2_EN); + rtsx_pci_enable_oobs_polling(pcr); rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0); - if (option->ltr_en) { - u16 val; - pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_en) { + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) { + struct rtsx_cr_option *option = &pcr->option; rtsx_pci_write_register(pcr, RTS5228_AUTOLOAD_CFG1, CD_RESUME_EN_MASK, CD_RESUME_EN_MASK); @@ -469,6 +435,17 @@ static int rts5228_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c index 47ab72a43256..6c81040e18be 100644 --- a/drivers/misc/cardreader/rts5249.c +++ b/drivers/misc/cardreader/rts5249.c @@ -86,64 +86,22 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr) static void rts5249_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; struct rtsx_cr_option *option = &(pcr->option); - u32 lval; - - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A)) { - if (0 == (lval & 0x0F)) - rtsx_pci_enable_oobs_polling(pcr); - else + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) rtsx_pci_disable_oobs_polling(pcr); + else + rtsx_pci_enable_oobs_polling(pcr); } - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } -static int rts5249_init_from_hw(struct rtsx_pcr *pcr) -{ - struct rtsx_cr_option *option = &(pcr->option); - - if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN - | PM_L1_1_EN | PM_L1_2_EN)) - option->force_clkreq_0 = false; - else - option->force_clkreq_0 = true; - - return 0; -} - static void rts52xa_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime) { /* Set relink_time to 0 */ @@ -276,7 +234,6 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) struct rtsx_cr_option *option = &(pcr->option); rts5249_init_from_cfg(pcr); - rts5249_init_from_hw(pcr); rtsx_pci_init_cmd(pcr); @@ -327,11 +284,12 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr) } } + /* * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced * to drive low, and we forcibly request clock. */ - if (option->force_clkreq_0 && pcr->aspm_mode == ASPM_MODE_CFG) + if (option->force_clkreq_0) rtsx_pci_write_register(pcr, PETXCFG, FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); else diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index 79b18f6f73a8..d2d3a6ccb8f7 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -480,47 +480,19 @@ static void rts5260_pwr_saving_setting(struct rtsx_pcr *pcr) static void rts5260_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; struct rtsx_cr_option *option = &pcr->option; - u32 lval; - - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); rts5260_pwr_saving_setting(pcr); if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) { + struct rtsx_cr_option *option = &pcr->option; /* Set mcu_cnt to 7 to ensure data can be sampled properly */ rtsx_pci_write_register(pcr, 0xFC03, 0x7F, 0x07); @@ -539,6 +511,17 @@ static int rts5260_extra_init_hw(struct rtsx_pcr *pcr) rts5260_init_hw(pcr); + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00); return 0; diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c index 94af6bf8a25a..67252512a132 100644 --- a/drivers/misc/cardreader/rts5261.c +++ b/drivers/misc/cardreader/rts5261.c @@ -454,54 +454,17 @@ static void rts5261_init_from_hw(struct rtsx_pcr *pcr) static void rts5261_init_from_cfg(struct rtsx_pcr *pcr) { - struct pci_dev *pdev = pcr->pci; - int l1ss; - u32 lval; struct rtsx_cr_option *option = &pcr->option; - l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); - if (!l1ss) - return; - - pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, &lval); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_1) - rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_ASPM_L1_2) - rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) - rtsx_set_dev_flag(pcr, PM_L1_1_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_1_EN); - - if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) - rtsx_set_dev_flag(pcr, PM_L1_2_EN); - else - rtsx_clear_dev_flag(pcr, PM_L1_2_EN); - - rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0); if (option->ltr_en) { - u16 val; - - pcie_capability_read_word(pdev, PCI_EXP_DEVCTL2, &val); - if (val & PCI_EXP_DEVCTL2_LTR_EN) { - option->ltr_enabled = true; - option->ltr_active = true; + if (option->ltr_enabled) rtsx_set_ltr_latency(pcr, option->ltr_active_latency); - } else { - option->ltr_enabled = false; - } } } static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) { + struct rtsx_cr_option *option = &pcr->option; u32 val; rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1, @@ -547,6 +510,17 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) else rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00); + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFB); if (pcr->rtd3_en) { diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index a3f4b52bb159..a30751ad3733 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1326,11 +1326,8 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) return err; } - if (pcr->aspm_mode == ASPM_MODE_REG) { + if (pcr->aspm_mode == ASPM_MODE_REG) rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0x30, 0x30); - rtsx_pci_write_register(pcr, PETXCFG, - FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); - } /* No CD interrupt if probing driver with card inserted. * So we need to initialize pcr->card_exist here. @@ -1345,7 +1342,9 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) { - int err; + struct rtsx_cr_option *option = &(pcr->option); + int err, l1ss; + u32 lval; u16 cfg_val; u8 val; @@ -1430,6 +1429,48 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) pcr->aspm_enabled = true; } + l1ss = pci_find_ext_capability(pcr->pci, PCI_EXT_CAP_ID_L1SS); + if (l1ss) { + pci_read_config_dword(pcr->pci, l1ss + PCI_L1SS_CTL1, &lval); + + if (lval & PCI_L1SS_CTL1_ASPM_L1_1) + rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); + else + rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); + + if (lval & PCI_L1SS_CTL1_ASPM_L1_2) + rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); + else + rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); + + if (lval & PCI_L1SS_CTL1_PCIPM_L1_1) + rtsx_set_dev_flag(pcr, PM_L1_1_EN); + else + rtsx_clear_dev_flag(pcr, PM_L1_1_EN); + + if (lval & PCI_L1SS_CTL1_PCIPM_L1_2) + rtsx_set_dev_flag(pcr, PM_L1_2_EN); + else + rtsx_clear_dev_flag(pcr, PM_L1_2_EN); + + pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &cfg_val); + if (cfg_val & PCI_EXP_DEVCTL2_LTR_EN) { + option->ltr_enabled = true; + option->ltr_active = true; + } else { + option->ltr_enabled = false; + } + + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) + option->force_clkreq_0 = false; + else + option->force_clkreq_0 = true; + } else { + option->ltr_enabled = false; + option->force_clkreq_0 = true; + } + if (pcr->ops->fetch_vendor_settings) pcr->ops->fetch_vendor_settings(pcr); diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 8b91a55ec0d2..8ee51e49fced 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -894,6 +894,13 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, return -EINVAL; } + /* UBI cannot work on flashes with zero erasesize. */ + if (!mtd->erasesize) { + pr_err("ubi: refuse attaching mtd%d - zero erasesize flash is not supported\n", + mtd->index); + return -EINVAL; + } + if (ubi_num == UBI_DEV_NUM_AUTO) { /* Search for an empty slot in the @ubi_devices array */ for (ubi_num = 0; ubi_num < UBI_MAX_DEVICES; ubi_num++) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 52a99d8bada0..ab434a77b059 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2958,14 +2958,16 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) * from the wrong location resulting in the switch booting * to wrong mode and inoperable. */ - mv88e6xxx_g1_wait_eeprom_done(chip); + if (chip->info->ops->get_eeprom) + mv88e6xxx_g2_eeprom_wait(chip); gpiod_set_value_cansleep(gpiod, 1); usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); usleep_range(10000, 20000); - mv88e6xxx_g1_wait_eeprom_done(chip); + if (chip->info->ops->get_eeprom) + mv88e6xxx_g2_eeprom_wait(chip); } } diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 2fa55a643591..174c773b38c2 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -75,37 +75,6 @@ static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } -void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip) -{ - const unsigned long timeout = jiffies + 1 * HZ; - u16 val; - int err; - - /* Wait up to 1 second for the switch to finish reading the - * EEPROM. - */ - while (time_before(jiffies, timeout)) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); - if (err) { - dev_err(chip->dev, "Error reading status"); - return; - } - - /* If the switch is still resetting, it may not - * respond on the bus, and so MDIO read returns - * 0xffff. Differentiate between that, and waiting for - * the EEPROM to be done by bit 0 being set. - */ - if (val != 0xffff && - val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE)) - return; - - usleep_range(1000, 2000); - } - - dev_err(chip->dev, "Timeout waiting for EEPROM done"); -} - /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 * Offset 0x02: Switch MAC Address Register Bytes 2 & 3 * Offset 0x03: Switch MAC Address Register Bytes 4 & 5 diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index c99ddd117fe6..1095261f5b49 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -282,7 +282,6 @@ int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip); -void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 937a01f2ba75..b2b5f6ba438f 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -340,7 +340,7 @@ int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) * Offset 0x15: EEPROM Addr (for 8-bit data access) */ -static int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) +int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) { int bit = __bf_shf(MV88E6XXX_G2_EEPROM_CMD_BUSY); int err; diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index 7e091965582b..d9434f7cae53 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -365,6 +365,7 @@ int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip); int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, int port); +int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip); extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6250_watchdog_ops; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 832a2ae01950..a8d79ee350f8 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1303,24 +1303,23 @@ static void ibmveth_rx_csum_helper(struct sk_buff *skb, * the user space for finding a flow. During this process, OVS computes * checksum on the first packet when CHECKSUM_PARTIAL flag is set. * - * So, re-compute TCP pseudo header checksum when configured for - * trunk mode. + * So, re-compute TCP pseudo header checksum. */ + if (iph_proto == IPPROTO_TCP) { struct tcphdr *tcph = (struct tcphdr *)(skb->data + iphlen); + if (tcph->check == 0x0000) { /* Recompute TCP pseudo header checksum */ - if (adapter->is_active_trunk) { - tcphdrlen = skb->len - iphlen; - if (skb_proto == ETH_P_IP) - tcph->check = - ~csum_tcpudp_magic(iph->saddr, - iph->daddr, tcphdrlen, iph_proto, 0); - else if (skb_proto == ETH_P_IPV6) - tcph->check = - ~csum_ipv6_magic(&iph6->saddr, - &iph6->daddr, tcphdrlen, iph_proto, 0); - } + tcphdrlen = skb->len - iphlen; + if (skb_proto == ETH_P_IP) + tcph->check = + ~csum_tcpudp_magic(iph->saddr, + iph->daddr, tcphdrlen, iph_proto, 0); + else if (skb_proto == ETH_P_IPV6) + tcph->check = + ~csum_ipv6_magic(&iph6->saddr, + &iph6->daddr, tcphdrlen, iph_proto, 0); /* Setup SKB fields for checksum offload */ skb_partial_csum_set(skb, iphlen, offsetof(struct tcphdr, check)); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index cad237dd8894..01e88b6e43a1 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -2655,12 +2655,14 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - /* Read flexiflag registers to determine whether the - * corresponding RXDID is configured and supported or not. - * Since Legacy 16byte descriptor format is not supported, - * start from Legacy 32byte descriptor. + /* RXDIDs supported by DDP package can be read from the register + * to get the supported RXDID bitmap. But the legacy 32byte RXDID + * is not listed in DDP package, add it in the bitmap manually. + * Legacy 16byte descriptor is not supported. */ - for (i = ICE_RXDID_LEGACY_1; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + rxdid->supported_rxdids |= BIT(ICE_RXDID_LEGACY_1); + + for (i = ICE_RXDID_FLEX_NIC; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) diff --git a/drivers/net/ethernet/marvell/sky2.h b/drivers/net/ethernet/marvell/sky2.h index ddec1627f1a7..8d0bacf4e49c 100644 --- a/drivers/net/ethernet/marvell/sky2.h +++ b/drivers/net/ethernet/marvell/sky2.h @@ -2195,7 +2195,7 @@ struct rx_ring_info { struct sk_buff *skb; dma_addr_t data_addr; DEFINE_DMA_UNMAP_LEN(data_size); - dma_addr_t frag_addr[ETH_JUMBO_MTU >> PAGE_SHIFT]; + dma_addr_t frag_addr[ETH_JUMBO_MTU >> PAGE_SHIFT ?: 1]; }; enum flow_control { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index b9c4ad69eec9..60d49b0f595f 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3172,8 +3172,8 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth) eth->rx_events++; if (likely(napi_schedule_prep(ð->rx_napi))) { - __napi_schedule(ð->rx_napi); mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + __napi_schedule(ð->rx_napi); } return IRQ_HANDLED; @@ -3185,8 +3185,8 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth) eth->tx_events++; if (likely(napi_schedule_prep(ð->tx_napi))) { - __napi_schedule(ð->tx_napi); mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); + __napi_schedule(ð->tx_napi); } return IRQ_HANDLED; diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index 329e374b9539..43ba71e82260 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -46,6 +46,7 @@ config LAN743X tristate "LAN743x support" depends on PCI depends on PTP_1588_CLOCK_OPTIONAL + select PHYLIB select FIXED_PHY select CRC16 select CRC32 diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 4a16ebff3d1d..48ea4aeeea5d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -91,63 +91,137 @@ static unsigned int mana_checksum_info(struct sk_buff *skb) return 0; } +static void mana_add_sge(struct mana_tx_package *tp, struct mana_skb_head *ash, + int sg_i, dma_addr_t da, int sge_len, u32 gpa_mkey) +{ + ash->dma_handle[sg_i] = da; + ash->size[sg_i] = sge_len; + + tp->wqe_req.sgl[sg_i].address = da; + tp->wqe_req.sgl[sg_i].mem_key = gpa_mkey; + tp->wqe_req.sgl[sg_i].size = sge_len; +} + static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc, - struct mana_tx_package *tp) + struct mana_tx_package *tp, int gso_hs) { struct mana_skb_head *ash = (struct mana_skb_head *)skb->head; + int hsg = 1; /* num of SGEs of linear part */ struct gdma_dev *gd = apc->ac->gdma_dev; + int skb_hlen = skb_headlen(skb); + int sge0_len, sge1_len = 0; struct gdma_context *gc; struct device *dev; skb_frag_t *frag; dma_addr_t da; + int sg_i; int i; gc = gd->gdma_context; dev = gc->dev; - da = dma_map_single(dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); + if (gso_hs && gso_hs < skb_hlen) { + sge0_len = gso_hs; + sge1_len = skb_hlen - gso_hs; + } else { + sge0_len = skb_hlen; + } + + da = dma_map_single(dev, skb->data, sge0_len, DMA_TO_DEVICE); if (dma_mapping_error(dev, da)) return -ENOMEM; - ash->dma_handle[0] = da; - ash->size[0] = skb_headlen(skb); + mana_add_sge(tp, ash, 0, da, sge0_len, gd->gpa_mkey); - tp->wqe_req.sgl[0].address = ash->dma_handle[0]; - tp->wqe_req.sgl[0].mem_key = gd->gpa_mkey; - tp->wqe_req.sgl[0].size = ash->size[0]; + if (sge1_len) { + sg_i = 1; + da = dma_map_single(dev, skb->data + sge0_len, sge1_len, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, da)) + goto frag_err; + + mana_add_sge(tp, ash, sg_i, da, sge1_len, gd->gpa_mkey); + hsg = 2; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + sg_i = hsg + i; + frag = &skb_shinfo(skb)->frags[i]; da = skb_frag_dma_map(dev, frag, 0, skb_frag_size(frag), DMA_TO_DEVICE); - if (dma_mapping_error(dev, da)) goto frag_err; - ash->dma_handle[i + 1] = da; - ash->size[i + 1] = skb_frag_size(frag); - - tp->wqe_req.sgl[i + 1].address = ash->dma_handle[i + 1]; - tp->wqe_req.sgl[i + 1].mem_key = gd->gpa_mkey; - tp->wqe_req.sgl[i + 1].size = ash->size[i + 1]; + mana_add_sge(tp, ash, sg_i, da, skb_frag_size(frag), + gd->gpa_mkey); } return 0; frag_err: - for (i = i - 1; i >= 0; i--) - dma_unmap_page(dev, ash->dma_handle[i + 1], ash->size[i + 1], + for (i = sg_i - 1; i >= hsg; i--) + dma_unmap_page(dev, ash->dma_handle[i], ash->size[i], DMA_TO_DEVICE); - dma_unmap_single(dev, ash->dma_handle[0], ash->size[0], DMA_TO_DEVICE); + for (i = hsg - 1; i >= 0; i--) + dma_unmap_single(dev, ash->dma_handle[i], ash->size[i], + DMA_TO_DEVICE); return -ENOMEM; } +/* Handle the case when GSO SKB linear length is too large. + * MANA NIC requires GSO packets to put only the packet header to SGE0. + * So, we need 2 SGEs for the skb linear part which contains more than the + * header. + * Return a positive value for the number of SGEs, or a negative value + * for an error. + */ +static int mana_fix_skb_head(struct net_device *ndev, struct sk_buff *skb, + int gso_hs) +{ + int num_sge = 1 + skb_shinfo(skb)->nr_frags; + int skb_hlen = skb_headlen(skb); + + if (gso_hs < skb_hlen) { + num_sge++; + } else if (gso_hs > skb_hlen) { + if (net_ratelimit()) + netdev_err(ndev, + "TX nonlinear head: hs:%d, skb_hlen:%d\n", + gso_hs, skb_hlen); + + return -EINVAL; + } + + return num_sge; +} + +/* Get the GSO packet's header size */ +static int mana_get_gso_hs(struct sk_buff *skb) +{ + int gso_hs; + + if (skb->encapsulation) { + gso_hs = skb_inner_tcp_all_headers(skb); + } else { + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + gso_hs = skb_transport_offset(skb) + + sizeof(struct udphdr); + } else { + gso_hs = skb_tcp_all_headers(skb); + } + } + + return gso_hs; +} + netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) { enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT; struct mana_port_context *apc = netdev_priv(ndev); + int gso_hs = 0; /* zero for non-GSO pkts */ u16 txq_idx = skb_get_queue_mapping(skb); struct gdma_dev *gd = apc->ac->gdma_dev; bool ipv4 = false, ipv6 = false; @@ -159,7 +233,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct mana_txq *txq; struct mana_cq *cq; int err, len; - u16 ihs; if (unlikely(!apc->port_is_up)) goto tx_drop; @@ -209,19 +282,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit = 0; pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; - WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); - - if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { - pkg.wqe_req.sgl = pkg.sgl_array; - } else { - pkg.sgl_ptr = kmalloc_array(pkg.wqe_req.num_sge, - sizeof(struct gdma_sge), - GFP_ATOMIC); - if (!pkg.sgl_ptr) - goto tx_drop_count; - - pkg.wqe_req.sgl = pkg.sgl_ptr; - } if (skb->protocol == htons(ETH_P_IP)) ipv4 = true; @@ -229,6 +289,26 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) ipv6 = true; if (skb_is_gso(skb)) { + int num_sge; + + gso_hs = mana_get_gso_hs(skb); + + num_sge = mana_fix_skb_head(ndev, skb, gso_hs); + if (num_sge > 0) + pkg.wqe_req.num_sge = num_sge; + else + goto tx_drop_count; + + u64_stats_update_begin(&tx_stats->syncp); + if (skb->encapsulation) { + tx_stats->tso_inner_packets++; + tx_stats->tso_inner_bytes += skb->len - gso_hs; + } else { + tx_stats->tso_packets++; + tx_stats->tso_bytes += skb->len - gso_hs; + } + u64_stats_update_end(&tx_stats->syncp); + pkg.tx_oob.s_oob.is_outer_ipv4 = ipv4; pkg.tx_oob.s_oob.is_outer_ipv6 = ipv6; @@ -252,28 +332,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); } - - if (skb->encapsulation) { - ihs = skb_inner_tcp_all_headers(skb); - u64_stats_update_begin(&tx_stats->syncp); - tx_stats->tso_inner_packets++; - tx_stats->tso_inner_bytes += skb->len - ihs; - u64_stats_update_end(&tx_stats->syncp); - } else { - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { - ihs = skb_transport_offset(skb) + sizeof(struct udphdr); - } else { - ihs = skb_tcp_all_headers(skb); - if (ipv6_has_hopopt_jumbo(skb)) - ihs -= sizeof(struct hop_jumbo_hdr); - } - - u64_stats_update_begin(&tx_stats->syncp); - tx_stats->tso_packets++; - tx_stats->tso_bytes += skb->len - ihs; - u64_stats_update_end(&tx_stats->syncp); - } - } else if (skb->ip_summed == CHECKSUM_PARTIAL) { csum_type = mana_checksum_info(skb); @@ -296,11 +354,25 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) } else { /* Can't do offload of this type of checksum */ if (skb_checksum_help(skb)) - goto free_sgl_ptr; + goto tx_drop_count; } } - if (mana_map_skb(skb, apc, &pkg)) { + WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); + + if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { + pkg.wqe_req.sgl = pkg.sgl_array; + } else { + pkg.sgl_ptr = kmalloc_array(pkg.wqe_req.num_sge, + sizeof(struct gdma_sge), + GFP_ATOMIC); + if (!pkg.sgl_ptr) + goto tx_drop_count; + + pkg.wqe_req.sgl = pkg.sgl_ptr; + } + + if (mana_map_skb(skb, apc, &pkg, gso_hs)) { u64_stats_update_begin(&tx_stats->syncp); tx_stats->mana_map_err++; u64_stats_update_end(&tx_stats->syncp); @@ -1258,11 +1330,16 @@ static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc) struct mana_skb_head *ash = (struct mana_skb_head *)skb->head; struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; struct device *dev = gc->dev; - int i; + int hsg, i; - dma_unmap_single(dev, ash->dma_handle[0], ash->size[0], DMA_TO_DEVICE); + /* Number of SGEs of linear part */ + hsg = (skb_is_gso(skb) && skb_headlen(skb) > ash->size[0]) ? 2 : 1; - for (i = 1; i < skb_shinfo(skb)->nr_frags + 1; i++) + for (i = 0; i < hsg; i++) + dma_unmap_single(dev, ash->dma_handle[i], ash->size[i], + DMA_TO_DEVICE); + + for (i = hsg; i < skb_shinfo(skb)->nr_frags + hsg; i++) dma_unmap_page(dev, ash->dma_handle[i], ash->size[i], DMA_TO_DEVICE); } @@ -1317,19 +1394,23 @@ static void mana_poll_tx_cq(struct mana_cq *cq) case CQE_TX_VPORT_IDX_OUT_OF_RANGE: case CQE_TX_VPORT_DISABLED: case CQE_TX_VLAN_TAGGING_VIOLATION: - WARN_ONCE(1, "TX: CQE error %d: ignored.\n", - cqe_oob->cqe_hdr.cqe_type); + if (net_ratelimit()) + netdev_err(ndev, "TX: CQE error %d\n", + cqe_oob->cqe_hdr.cqe_type); + apc->eth_stats.tx_cqe_err++; break; default: - /* If the CQE type is unexpected, log an error, assert, - * and go through the error path. + /* If the CQE type is unknown, log an error, + * and still free the SKB, update tail, etc. */ - WARN_ONCE(1, "TX: Unexpected CQE type %d: HW BUG?\n", - cqe_oob->cqe_hdr.cqe_type); + if (net_ratelimit()) + netdev_err(ndev, "TX: unknown CQE type %d\n", + cqe_oob->cqe_hdr.cqe_type); + apc->eth_stats.tx_cqe_unknown_type++; - return; + break; } if (WARN_ON_ONCE(txq->gdma_txq_id != completions[i].wq_num)) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index 0bfc375161ed..a174c6fc626a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -110,9 +110,9 @@ struct qed_ll2_info { enum core_tx_dest tx_dest; u8 tx_stats_en; bool main_func_queue; + struct qed_ll2_cbs cbs; struct qed_ll2_rx_queue rx_queue; struct qed_ll2_tx_queue tx_queue; - struct qed_ll2_cbs cbs; }; extern const struct qed_ll2_ops qed_ll2_ops_pass; diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 3c165b15709f..0023ff254915 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -4,6 +4,7 @@ * Copyright (C) 2022 Renesas Electronics Corporation */ +#include <linux/clk.h> #include <linux/dma-mapping.h> #include <linux/err.h> #include <linux/etherdevice.h> @@ -1049,7 +1050,7 @@ static void rswitch_rmac_setting(struct rswitch_etha *etha, const u8 *mac) static void rswitch_etha_enable_mii(struct rswitch_etha *etha) { rswitch_modify(etha->addr, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, - MPIC_PSMCS(0x05) | MPIC_PSMHT(0x06)); + MPIC_PSMCS(etha->psmcs) | MPIC_PSMHT(0x06)); rswitch_modify(etha->addr, MPSM, 0, MPSM_MFF_C45); } @@ -1693,6 +1694,12 @@ static void rswitch_etha_init(struct rswitch_private *priv, int index) etha->index = index; etha->addr = priv->addr + RSWITCH_ETHA_OFFSET + index * RSWITCH_ETHA_SIZE; etha->coma_addr = priv->addr; + + /* MPIC.PSMCS = (clk [MHz] / (MDC frequency [MHz] * 2) - 1. + * Calculating PSMCS value as MDC frequency = 2.5MHz. So, multiply + * both the numerator and the denominator by 10. + */ + etha->psmcs = clk_get_rate(priv->clk) / 100000 / (25 * 2) - 1; } static int rswitch_device_alloc(struct rswitch_private *priv, int index) @@ -1900,6 +1907,10 @@ static int renesas_eth_sw_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&priv->lock); + priv->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + attr = soc_device_match(rswitch_soc_no_speed_change); if (attr) priv->etha_no_runtime_change = true; diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index f0c16a37ea55..04f49a7a5843 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -915,6 +915,7 @@ struct rswitch_etha { bool external_phy; struct mii_bus *mii; phy_interface_t phy_interface; + u32 psmcs; u8 mac_addr[MAX_ADDR_LEN]; int link; int speed; @@ -1012,6 +1013,7 @@ struct rswitch_private { struct rswitch_mfwd mfwd; spinlock_t lock; /* lock interrupt registers' control */ + struct clk *clk; bool etha_no_runtime_change; bool gwca_halt; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index ab4324ed46da..d8d3c729f219 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -104,6 +104,7 @@ struct stm32_ops { int (*parse_data)(struct stm32_dwmac *dwmac, struct device *dev); u32 syscfg_eth_mask; + bool clk_rx_enable_in_suspend; }; static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat) @@ -121,7 +122,8 @@ static int stm32_dwmac_init(struct plat_stmmacenet_data *plat_dat) if (ret) return ret; - if (!dwmac->dev->power.is_suspended) { + if (!dwmac->ops->clk_rx_enable_in_suspend || + !dwmac->dev->power.is_suspended) { ret = clk_prepare_enable(dwmac->clk_rx); if (ret) { clk_disable_unprepare(dwmac->clk_tx); @@ -508,7 +510,8 @@ static struct stm32_ops stm32mp1_dwmac_data = { .suspend = stm32mp1_suspend, .resume = stm32mp1_resume, .parse_data = stm32mp1_parse_data, - .syscfg_eth_mask = SYSCFG_MP1_ETH_MASK + .syscfg_eth_mask = SYSCFG_MP1_ETH_MASK, + .clk_rx_enable_in_suspend = true }; static const struct of_device_id stm32_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 81b6f3ecdf92..bb1dbf4c9f6c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6012,33 +6012,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data) return IRQ_HANDLED; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/* Polling receive - used by NETCONSOLE and other diagnostic tools - * to allow network I/O with interrupts disabled. - */ -static void stmmac_poll_controller(struct net_device *dev) -{ - struct stmmac_priv *priv = netdev_priv(dev); - int i; - - /* If adapter is down, do nothing */ - if (test_bit(STMMAC_DOWN, &priv->state)) - return; - - if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN) { - for (i = 0; i < priv->plat->rx_queues_to_use; i++) - stmmac_msi_intr_rx(0, &priv->dma_conf.rx_queue[i]); - - for (i = 0; i < priv->plat->tx_queues_to_use; i++) - stmmac_msi_intr_tx(0, &priv->dma_conf.tx_queue[i]); - } else { - disable_irq(dev->irq); - stmmac_interrupt(dev->irq, dev); - enable_irq(dev->irq); - } -} -#endif - /** * stmmac_ioctl - Entry point for the Ioctl * @dev: Device pointer. @@ -6999,9 +6972,6 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_get_stats64 = stmmac_get_stats64, .ndo_setup_tc = stmmac_setup_tc, .ndo_select_queue = stmmac_select_queue, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = stmmac_poll_controller, -#endif .ndo_set_mac_address = stmmac_set_mac_address, .ndo_vlan_rx_add_vid = stmmac_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = stmmac_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 843bd8804bfa..1ffde555da47 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -874,7 +874,7 @@ static int __maybe_unused stmmac_pltfr_resume(struct device *dev) struct platform_device *pdev = to_platform_device(dev); int ret; - ret = stmmac_pltfr_init(pdev, priv->plat->bsp_priv); + ret = stmmac_pltfr_init(pdev, priv->plat); if (ret) return ret; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index bea6fc0f324c..24120605502f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1747,9 +1747,10 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) } tx_chn->irq = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); - if (tx_chn->irq <= 0) { + if (tx_chn->irq < 0) { dev_err(dev, "Failed to get tx dma irq %d\n", tx_chn->irq); + ret = tx_chn->irq; goto err; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 6635b28bc672..482ae82a99c1 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -316,12 +316,12 @@ static int prueth_init_tx_chns(struct prueth_emac *emac) goto fail; } - tx_chn->irq = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); - if (tx_chn->irq <= 0) { - ret = -EINVAL; + ret = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); + if (ret < 0) { netdev_err(ndev, "failed to get tx irq\n"); goto fail; } + tx_chn->irq = ret; snprintf(tx_chn->name, sizeof(tx_chn->name), "%s-tx%d", dev_name(dev), tx_chn->id); diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 5d6454fedb3f..78ad2da3ee29 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -90,7 +90,9 @@ static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index, ret = fn(dev, USB_VENDOR_REQUEST_READ_REGISTER, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, &buf, 4); - if (unlikely(ret < 0)) { + if (unlikely(ret < 4)) { + ret = ret < 0 ? ret : -ENODATA; + netdev_warn(dev->net, "Failed to read reg index 0x%08x: %d\n", index, ret); return ret; diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 47c2ad7a3e42..fd50bb313b92 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -34,6 +34,8 @@ #define TDM_PPPOHT_SLIC_MAXIN #define RX_BD_ERRORS (R_CD_S | R_OV_S | R_CR_S | R_AB_S | R_NO_S | R_LG_S) +static int uhdlc_close(struct net_device *dev); + static struct ucc_tdm_info utdm_primary_info = { .uf_info = { .tsa = 0, @@ -708,6 +710,7 @@ static int uhdlc_open(struct net_device *dev) hdlc_device *hdlc = dev_to_hdlc(dev); struct ucc_hdlc_private *priv = hdlc->priv; struct ucc_tdm *utdm = priv->utdm; + int rc = 0; if (priv->hdlc_busy != 1) { if (request_irq(priv->ut_info->uf_info.irq, @@ -731,10 +734,13 @@ static int uhdlc_open(struct net_device *dev) napi_enable(&priv->napi); netdev_reset_queue(dev); netif_start_queue(dev); - hdlc_open(dev); + + rc = hdlc_open(dev); + if (rc) + uhdlc_close(dev); } - return 0; + return rc; } static void uhdlc_memclean(struct ucc_hdlc_private *priv) @@ -824,6 +830,8 @@ static int uhdlc_close(struct net_device *dev) netdev_reset_queue(dev); priv->hdlc_busy = 0; + hdlc_close(dev); + return 0; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index bece26741d3a..611d1a6aabb9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -442,7 +442,12 @@ struct brcmf_scan_params_v2_le { * fixed parameter portion is assumed, otherwise * ssid in the fixed portion is ignored */ - __le16 channel_list[1]; /* list of chanspecs */ + union { + __le16 padding; /* Reserve space for at least 1 entry for abort + * which uses an on stack brcmf_scan_params_v2_le + */ + DECLARE_FLEX_ARRAY(__le16, channel_list); /* chanspecs */ + }; }; struct brcmf_scan_results { @@ -702,7 +707,7 @@ struct brcmf_sta_info_le { struct brcmf_chanspec_list { __le32 count; /* # of entries */ - __le32 element[1]; /* variable length uint32 list */ + __le32 element[]; /* variable length uint32 list */ }; /* diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h index f5e08988dc7b..06d6f7f66430 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h @@ -310,9 +310,9 @@ struct iwl_fw_ini_fifo_hdr { struct iwl_fw_ini_error_dump_range { __le32 range_data_size; union { - __le32 internal_base_addr; - __le64 dram_base_addr; - __le32 page_num; + __le32 internal_base_addr __packed; + __le64 dram_base_addr __packed; + __le32 page_num __packed; struct iwl_fw_ini_fifo_hdr fifo_hdr; struct iwl_cmd_header fw_pkt_hdr; }; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 1f5db65a088d..1d5ee4330f29 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -802,7 +802,7 @@ out: mvm->nvm_data->bands[0].n_channels = 1; mvm->nvm_data->bands[0].n_bitrates = 1; mvm->nvm_data->bands[0].bitrates = - (void *)((u8 *)mvm->nvm_data->channels + 1); + (void *)(mvm->nvm_data->channels + 1); mvm->nvm_data->bands[0].bitrates->hw_value = 10; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index 8b6c641772ee..b719843e9457 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -731,73 +731,78 @@ static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm, mvmvif->associated = vif->cfg.assoc; - if (!(changes & BSS_CHANGED_ASSOC)) - return; - - if (vif->cfg.assoc) { - /* clear statistics to get clean beacon counter */ - iwl_mvm_request_statistics(mvm, true); - iwl_mvm_sf_update(mvm, vif, false); - iwl_mvm_power_vif_assoc(mvm, vif); - - for_each_mvm_vif_valid_link(mvmvif, i) { - memset(&mvmvif->link[i]->beacon_stats, 0, - sizeof(mvmvif->link[i]->beacon_stats)); + if (changes & BSS_CHANGED_ASSOC) { + if (vif->cfg.assoc) { + /* clear statistics to get clean beacon counter */ + iwl_mvm_request_statistics(mvm, true); + iwl_mvm_sf_update(mvm, vif, false); + iwl_mvm_power_vif_assoc(mvm, vif); + + for_each_mvm_vif_valid_link(mvmvif, i) { + memset(&mvmvif->link[i]->beacon_stats, 0, + sizeof(mvmvif->link[i]->beacon_stats)); + + if (vif->p2p) { + iwl_mvm_update_smps(mvm, vif, + IWL_MVM_SMPS_REQ_PROT, + IEEE80211_SMPS_DYNAMIC, i); + } + + rcu_read_lock(); + link_conf = rcu_dereference(vif->link_conf[i]); + if (link_conf && !link_conf->dtim_period) + protect = true; + rcu_read_unlock(); + } - if (vif->p2p) { - iwl_mvm_update_smps(mvm, vif, - IWL_MVM_SMPS_REQ_PROT, - IEEE80211_SMPS_DYNAMIC, i); + if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) && + protect) { + /* If we're not restarting and still haven't + * heard a beacon (dtim period unknown) then + * make sure we still have enough minimum time + * remaining in the time event, since the auth + * might actually have taken quite a while + * (especially for SAE) and so the remaining + * time could be small without us having heard + * a beacon yet. + */ + iwl_mvm_protect_assoc(mvm, vif, 0); } - rcu_read_lock(); - link_conf = rcu_dereference(vif->link_conf[i]); - if (link_conf && !link_conf->dtim_period) - protect = true; - rcu_read_unlock(); - } + iwl_mvm_sf_update(mvm, vif, false); + + /* FIXME: need to decide about misbehaving AP handling */ + iwl_mvm_power_vif_assoc(mvm, vif); + } else if (iwl_mvm_mld_vif_have_valid_ap_sta(mvmvif)) { + iwl_mvm_mei_host_disassociated(mvm); - if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) && - protect) { - /* If we're not restarting and still haven't - * heard a beacon (dtim period unknown) then - * make sure we still have enough minimum time - * remaining in the time event, since the auth - * might actually have taken quite a while - * (especially for SAE) and so the remaining - * time could be small without us having heard - * a beacon yet. + /* If update fails - SF might be running in associated + * mode while disassociated - which is forbidden. */ - iwl_mvm_protect_assoc(mvm, vif, 0); + ret = iwl_mvm_sf_update(mvm, vif, false); + WARN_ONCE(ret && + !test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, + &mvm->status), + "Failed to update SF upon disassociation\n"); + + /* If we get an assert during the connection (after the + * station has been added, but before the vif is set + * to associated), mac80211 will re-add the station and + * then configure the vif. Since the vif is not + * associated, we would remove the station here and + * this would fail the recovery. + */ + iwl_mvm_mld_vif_delete_all_stas(mvm, vif); } - iwl_mvm_sf_update(mvm, vif, false); - - /* FIXME: need to decide about misbehaving AP handling */ - iwl_mvm_power_vif_assoc(mvm, vif); - } else if (iwl_mvm_mld_vif_have_valid_ap_sta(mvmvif)) { - iwl_mvm_mei_host_disassociated(mvm); - - /* If update fails - SF might be running in associated - * mode while disassociated - which is forbidden. - */ - ret = iwl_mvm_sf_update(mvm, vif, false); - WARN_ONCE(ret && - !test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, - &mvm->status), - "Failed to update SF upon disassociation\n"); - - /* If we get an assert during the connection (after the - * station has been added, but before the vif is set - * to associated), mac80211 will re-add the station and - * then configure the vif. Since the vif is not - * associated, we would remove the station here and - * this would fail the recovery. - */ - iwl_mvm_mld_vif_delete_all_stas(mvm, vif); + iwl_mvm_bss_info_changed_station_assoc(mvm, vif, changes); } - iwl_mvm_bss_info_changed_station_assoc(mvm, vif, changes); + if (changes & BSS_CHANGED_PS) { + ret = iwl_mvm_power_update_mac(mvm); + if (ret) + IWL_ERR(mvm, "failed to update power mode\n"); + } } static void diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index c1d9ce753468..3cbe2c0b8d6b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -2342,7 +2342,7 @@ iwl_mvm_scan_umac_fill_general_p_v12(struct iwl_mvm *mvm, if (gen_flags & IWL_UMAC_SCAN_GEN_FLAGS_V2_FRAGMENTED_LMAC2) gp->num_of_fragments[SCAN_HB_LMAC_IDX] = IWL_SCAN_NUM_OF_FRAGS; - if (version < 12) { + if (version < 16) { gp->scan_start_mac_or_link_id = scan_vif->id; } else { struct iwl_mvm_vif_link_info *link_info; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 36d70d589aed..898dca393643 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1612,6 +1612,7 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm, iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]); memset(&info->status, 0, sizeof(info->status)); + info->flags &= ~(IEEE80211_TX_STAT_ACK | IEEE80211_TX_STAT_TX_FILTERED); /* inform mac80211 about what happened with the frame */ switch (status & TX_STATUS_MSK) { @@ -1964,6 +1965,8 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid, */ if (!is_flush) info->flags |= IEEE80211_TX_STAT_ACK; + else + info->flags &= ~IEEE80211_TX_STAT_ACK; } /* diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index 391793a16adc..10690e82358b 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -918,9 +918,17 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv, mwifiex_dbg_dump(priv->adapter, EVT_D, "RXBA_SYNC event:", event_buf, len); - while (tlv_buf_left >= sizeof(*tlv_rxba)) { + while (tlv_buf_left > sizeof(*tlv_rxba)) { tlv_type = le16_to_cpu(tlv_rxba->header.type); tlv_len = le16_to_cpu(tlv_rxba->header.len); + if (size_add(sizeof(tlv_rxba->header), tlv_len) > tlv_buf_left) { + mwifiex_dbg(priv->adapter, WARN, + "TLV size (%zu) overflows event_buf buf_left=%d\n", + size_add(sizeof(tlv_rxba->header), tlv_len), + tlv_buf_left); + return; + } + if (tlv_type != TLV_TYPE_RXBA_SYNC) { mwifiex_dbg(priv->adapter, ERROR, "Wrong TLV id=0x%x\n", tlv_type); @@ -929,6 +937,14 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv, tlv_seq_num = le16_to_cpu(tlv_rxba->seq_num); tlv_bitmap_len = le16_to_cpu(tlv_rxba->bitmap_len); + if (size_add(sizeof(*tlv_rxba), tlv_bitmap_len) > tlv_buf_left) { + mwifiex_dbg(priv->adapter, WARN, + "TLV size (%zu) overflows event_buf buf_left=%d\n", + size_add(sizeof(*tlv_rxba), tlv_bitmap_len), + tlv_buf_left); + return; + } + mwifiex_dbg(priv->adapter, INFO, "%pM tid=%d seq_num=%d bitmap_len=%d\n", tlv_rxba->mac, tlv_rxba->tid, tlv_seq_num, @@ -965,8 +981,8 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv, } } - tlv_buf_left -= (sizeof(*tlv_rxba) + tlv_len); - tmp = (u8 *)tlv_rxba + tlv_len + sizeof(*tlv_rxba); + tlv_buf_left -= (sizeof(tlv_rxba->header) + tlv_len); + tmp = (u8 *)tlv_rxba + sizeof(tlv_rxba->header) + tlv_len; tlv_rxba = (struct mwifiex_ie_types_rxba_sync *)tmp; } } diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index f2168fac95ed..8e6db904e5b2 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -779,7 +779,7 @@ struct mwifiex_ie_types_rxba_sync { u8 reserved; __le16 seq_num; __le16 bitmap_len; - u8 bitmap[1]; + u8 bitmap[]; } __packed; struct chan_band_param_set { diff --git a/drivers/net/wireless/marvell/mwifiex/sta_rx.c b/drivers/net/wireless/marvell/mwifiex/sta_rx.c index 65420ad67416..257737137cd7 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_rx.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_rx.c @@ -86,7 +86,8 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv, rx_pkt_len = le16_to_cpu(local_rx_pd->rx_pkt_length); rx_pkt_hdr = (void *)local_rx_pd + rx_pkt_off; - if (sizeof(*rx_pkt_hdr) + rx_pkt_off > skb->len) { + if (sizeof(rx_pkt_hdr->eth803_hdr) + sizeof(rfc1042_header) + + rx_pkt_off > skb->len) { mwifiex_dbg(priv->adapter, ERROR, "wrong rx packet offset: len=%d, rx_pkt_off=%d\n", skb->len, rx_pkt_off); @@ -95,12 +96,13 @@ int mwifiex_process_rx_packet(struct mwifiex_private *priv, return -1; } - if ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, - sizeof(bridge_tunnel_header))) || - (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header, - sizeof(rfc1042_header)) && - ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_AARP && - ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_IPX)) { + if (sizeof(*rx_pkt_hdr) + rx_pkt_off <= skb->len && + ((!memcmp(&rx_pkt_hdr->rfc1042_hdr, bridge_tunnel_header, + sizeof(bridge_tunnel_header))) || + (!memcmp(&rx_pkt_hdr->rfc1042_hdr, rfc1042_header, + sizeof(rfc1042_header)) && + ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_AARP && + ntohs(rx_pkt_hdr->rfc1042_hdr.snap_type) != ETH_P_IPX))) { /* * Replace the 803 header and rfc1042 header (llc/snap) with an * EthernetII header, keep the src/dst and snap_type diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 05d9ab3ce819..dc8f4e157eb2 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -93,13 +93,13 @@ __mt76_get_rxwi(struct mt76_dev *dev) { struct mt76_txwi_cache *t = NULL; - spin_lock(&dev->wed_lock); + spin_lock_bh(&dev->wed_lock); if (!list_empty(&dev->rxwi_cache)) { t = list_first_entry(&dev->rxwi_cache, struct mt76_txwi_cache, list); list_del(&t->list); } - spin_unlock(&dev->wed_lock); + spin_unlock_bh(&dev->wed_lock); return t; } @@ -145,9 +145,9 @@ mt76_put_rxwi(struct mt76_dev *dev, struct mt76_txwi_cache *t) if (!t) return; - spin_lock(&dev->wed_lock); + spin_lock_bh(&dev->wed_lock); list_add(&t->list, &dev->rxwi_cache); - spin_unlock(&dev->wed_lock); + spin_unlock_bh(&dev->wed_lock); } EXPORT_SYMBOL_GPL(mt76_put_rxwi); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c index 0acabba2d1a5..5d402cf2951c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_eeprom.c @@ -131,15 +131,8 @@ u8 mt76x02_get_lna_gain(struct mt76x02_dev *dev, s8 *lna_2g, s8 *lna_5g, struct ieee80211_channel *chan) { - u16 val; u8 lna; - val = mt76x02_eeprom_get(dev, MT_EE_NIC_CONF_1); - if (val & MT_EE_NIC_CONF_1_LNA_EXT_2G) - *lna_2g = 0; - if (val & MT_EE_NIC_CONF_1_LNA_EXT_5G) - memset(lna_5g, 0, sizeof(s8) * 3); - if (chan->band == NL80211_BAND_2GHZ) lna = *lna_2g; else if (chan->hw_value <= 64) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c index d5809408d1d3..8c01855885ce 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c @@ -256,7 +256,8 @@ void mt76x2_read_rx_gain(struct mt76x02_dev *dev) struct ieee80211_channel *chan = dev->mphy.chandef.chan; int channel = chan->hw_value; s8 lna_5g[3], lna_2g; - u8 lna; + bool use_lna; + u8 lna = 0; u16 val; if (chan->band == NL80211_BAND_2GHZ) @@ -275,7 +276,15 @@ void mt76x2_read_rx_gain(struct mt76x02_dev *dev) dev->cal.rx.mcu_gain |= (lna_5g[1] & 0xff) << 16; dev->cal.rx.mcu_gain |= (lna_5g[2] & 0xff) << 24; - lna = mt76x02_get_lna_gain(dev, &lna_2g, lna_5g, chan); + val = mt76x02_eeprom_get(dev, MT_EE_NIC_CONF_1); + if (chan->band == NL80211_BAND_2GHZ) + use_lna = !(val & MT_EE_NIC_CONF_1_LNA_EXT_2G); + else + use_lna = !(val & MT_EE_NIC_CONF_1_LNA_EXT_5G); + + if (use_lna) + lna = mt76x02_get_lna_gain(dev, &lna_2g, lna_5g, chan); + dev->cal.rx.lna_gain = mt76x02_sign_extend(lna, 8); } EXPORT_SYMBOL_GPL(mt76x2_read_rx_gain); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723d.h b/drivers/net/wireless/realtek/rtw88/rtw8723d.h index 3642a2c7f80c..2434e2480cbe 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8723d.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8723d.h @@ -46,6 +46,7 @@ struct rtw8723du_efuse { u8 vender_id[2]; /* 0x100 */ u8 product_id[2]; /* 0x102 */ u8 usb_option; /* 0x104 */ + u8 res5[2]; /* 0x105 */ u8 mac_addr[ETH_ALEN]; /* 0x107 */ }; diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index e85ff946e8c8..9c8fd69ae5ad 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -229,6 +229,7 @@ int pcie_aer_is_native(struct pci_dev *dev) return pcie_ports_native || host->native_aer; } +EXPORT_SYMBOL_NS_GPL(pcie_aer_is_native, CXL); static int pci_enable_pcie_error_reporting(struct pci_dev *dev) { diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index 58a2b1a1cae4..1f3803bde7ee 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -29,10 +29,8 @@ extern bool pcie_ports_dpc_native; #ifdef CONFIG_PCIEAER int pcie_aer_init(void); -int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pcie_aer_init(void) { return 0; } -static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif #ifdef CONFIG_HOTPLUG_PCI_PCIE diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 6851d10d6582..a68df4133403 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/module.h> #include <linux/slab.h> @@ -231,19 +232,15 @@ static inline u32 ipc_data_readl(struct intel_scu_ipc_dev *scu, u32 offset) /* Wait till scu status is busy */ static inline int busy_loop(struct intel_scu_ipc_dev *scu) { - unsigned long end = jiffies + IPC_TIMEOUT; - - do { - u32 status; - - status = ipc_read_status(scu); - if (!(status & IPC_STATUS_BUSY)) - return (status & IPC_STATUS_ERR) ? -EIO : 0; + u8 status; + int err; - usleep_range(50, 100); - } while (time_before(jiffies, end)); + err = readx_poll_timeout(ipc_read_status, scu, status, !(status & IPC_STATUS_BUSY), + 100, jiffies_to_usecs(IPC_TIMEOUT)); + if (err) + return err; - return -ETIMEDOUT; + return (status & IPC_STATUS_ERR) ? -EIO : 0; } /* Wait till ipc ioc interrupt is received or timeout in 10 HZ */ @@ -251,10 +248,12 @@ static inline int ipc_wait_for_interrupt(struct intel_scu_ipc_dev *scu) { int status; - if (!wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT)) - return -ETIMEDOUT; + wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT); status = ipc_read_status(scu); + if (status & IPC_STATUS_BUSY) + return -ETIMEDOUT; + if (status & IPC_STATUS_ERR) return -EIO; @@ -266,6 +265,24 @@ static int intel_scu_ipc_check_status(struct intel_scu_ipc_dev *scu) return scu->irq > 0 ? ipc_wait_for_interrupt(scu) : busy_loop(scu); } +static struct intel_scu_ipc_dev *intel_scu_ipc_get(struct intel_scu_ipc_dev *scu) +{ + u8 status; + + if (!scu) + scu = ipcdev; + if (!scu) + return ERR_PTR(-ENODEV); + + status = ipc_read_status(scu); + if (status & IPC_STATUS_BUSY) { + dev_dbg(&scu->dev, "device is busy\n"); + return ERR_PTR(-EBUSY); + } + + return scu; +} + /* Read/Write power control(PMIC in Langwell, MSIC in PenWell) registers */ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, u32 count, u32 op, u32 id) @@ -279,11 +296,10 @@ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, memset(cbuf, 0, sizeof(cbuf)); mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } for (nc = 0; nc < count; nc++, offset += 2) { @@ -438,13 +454,12 @@ int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, int err; mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } - scu = ipcdev; + cmdval = sub << 12 | cmd; ipc_command(scu, cmdval); err = intel_scu_ipc_check_status(scu); @@ -484,11 +499,10 @@ int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, return -EINVAL; mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } memcpy(inbuf, in, inlen); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index d70c89d32534..41584427dc32 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4116,9 +4116,11 @@ static void hotkey_resume(void) { tpacpi_disable_brightness_delay(); + mutex_lock(&hotkey_mutex); if (hotkey_status_set(true) < 0 || hotkey_mask_set(hotkey_acpi_mask) < 0) pr_err("error while attempting to reset the event firmware interface\n"); + mutex_unlock(&hotkey_mutex); tpacpi_send_radiosw_update(); tpacpi_input_send_tabletsw(); diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig index 59e1ebb7842e..411e00b255d6 100644 --- a/drivers/power/reset/Kconfig +++ b/drivers/power/reset/Kconfig @@ -300,7 +300,7 @@ config NVMEM_REBOOT_MODE config POWER_MLXBF tristate "Mellanox BlueField power handling driver" - depends on (GPIO_MLXBF2 && ACPI) + depends on (GPIO_MLXBF2 || GPIO_MLXBF3) && ACPI help This driver supports reset or low power mode handling for Mellanox BlueField. diff --git a/drivers/power/reset/pwr-mlxbf.c b/drivers/power/reset/pwr-mlxbf.c index 12dedf841a44..de35d24bb7ef 100644 --- a/drivers/power/reset/pwr-mlxbf.c +++ b/drivers/power/reset/pwr-mlxbf.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only or BSD-3-Clause +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause /* * Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. diff --git a/drivers/power/reset/vexpress-poweroff.c b/drivers/power/reset/vexpress-poweroff.c index 447ffdacddf9..17064d7b19f6 100644 --- a/drivers/power/reset/vexpress-poweroff.c +++ b/drivers/power/reset/vexpress-poweroff.c @@ -121,7 +121,7 @@ static int vexpress_reset_probe(struct platform_device *pdev) return PTR_ERR(regmap); dev_set_drvdata(&pdev->dev, regmap); - switch ((enum vexpress_reset_func)match->data) { + switch ((uintptr_t)match->data) { case FUNC_SHUTDOWN: vexpress_power_off_device = &pdev->dev; pm_power_off = vexpress_power_off; diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index 663a1c423806..a61bb1283e19 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -769,6 +769,7 @@ config BATTERY_RT5033 config CHARGER_RT5033 tristate "RT5033 battery charger support" depends on MFD_RT5033 + depends on EXTCON || !EXTCON help This adds support for battery charger in Richtek RT5033 PMIC. The device supports pre-charge mode, fast charge mode and diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 6f83e99d2eb7..ce36d6ca3422 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -115,7 +115,6 @@ struct ab8500_btemp { static enum power_supply_property ab8500_btemp_props[] = { POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_ONLINE, - POWER_SUPPLY_PROP_TECHNOLOGY, POWER_SUPPLY_PROP_TEMP, }; @@ -532,12 +531,6 @@ static int ab8500_btemp_get_property(struct power_supply *psy, else val->intval = 1; break; - case POWER_SUPPLY_PROP_TECHNOLOGY: - if (di->bm->bi) - val->intval = di->bm->bi->technology; - else - val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN; - break; case POWER_SUPPLY_PROP_TEMP: val->intval = ab8500_btemp_get_temp(di); break; @@ -662,7 +655,7 @@ static char *supply_interface[] = { static const struct power_supply_desc ab8500_btemp_desc = { .name = "ab8500_btemp", - .type = POWER_SUPPLY_TYPE_BATTERY, + .type = POWER_SUPPLY_TYPE_UNKNOWN, .properties = ab8500_btemp_props, .num_properties = ARRAY_SIZE(ab8500_btemp_props), .get_property = ab8500_btemp_get_property, diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c index ea4ad61d4c7e..2205ea0834a6 100644 --- a/drivers/power/supply/ab8500_chargalg.c +++ b/drivers/power/supply/ab8500_chargalg.c @@ -1720,7 +1720,7 @@ static char *supply_interface[] = { static const struct power_supply_desc ab8500_chargalg_desc = { .name = "ab8500_chargalg", - .type = POWER_SUPPLY_TYPE_BATTERY, + .type = POWER_SUPPLY_TYPE_UNKNOWN, .properties = ab8500_chargalg_props, .num_properties = ARRAY_SIZE(ab8500_chargalg_props), .get_property = ab8500_chargalg_get_property, diff --git a/drivers/power/supply/mt6370-charger.c b/drivers/power/supply/mt6370-charger.c index f27dae5043f5..a9641bd3d8cf 100644 --- a/drivers/power/supply/mt6370-charger.c +++ b/drivers/power/supply/mt6370-charger.c @@ -324,7 +324,7 @@ static int mt6370_chg_toggle_cfo(struct mt6370_priv *priv) if (fl_strobe) { dev_err(priv->dev, "Flash led is still in strobe mode\n"); - return ret; + return -EINVAL; } /* cfo off */ diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index 06e5b6b0e255..d483a81560ab 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -482,6 +482,13 @@ int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env) if (ret) return ret; + /* + * Kernel generates KOBJ_REMOVE uevent in device removal path, after + * resources have been freed. Exit early to avoid use-after-free. + */ + if (psy->removing) + return 0; + prop_buf = (char *)get_zeroed_page(GFP_KERNEL); if (!prop_buf) return -ENOMEM; diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index 8328bcea1a29..f64daf5a41d9 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -1045,6 +1045,13 @@ static void rk817_charging_monitor(struct work_struct *work) queue_delayed_work(system_wq, &charger->work, msecs_to_jiffies(8000)); } +static void rk817_cleanup_node(void *data) +{ + struct device_node *node = data; + + of_node_put(node); +} + static int rk817_charger_probe(struct platform_device *pdev) { struct rk808 *rk808 = dev_get_drvdata(pdev->dev.parent); @@ -1061,11 +1068,13 @@ static int rk817_charger_probe(struct platform_device *pdev) if (!node) return -ENODEV; + ret = devm_add_action_or_reset(&pdev->dev, rk817_cleanup_node, node); + if (ret) + return ret; + charger = devm_kzalloc(&pdev->dev, sizeof(*charger), GFP_KERNEL); - if (!charger) { - of_node_put(node); + if (!charger) return -ENOMEM; - } charger->rk808 = rk808; @@ -1211,3 +1220,4 @@ MODULE_DESCRIPTION("Battery power supply driver for RK817 PMIC"); MODULE_AUTHOR("Maya Matuszczyk <maccraft123mc@gmail.com>"); MODULE_AUTHOR("Chris Morgan <macromorgan@hotmail.com>"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:rk817-charger"); diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c index 683adb18253d..fdfdc83ab045 100644 --- a/drivers/power/supply/rt9467-charger.c +++ b/drivers/power/supply/rt9467-charger.c @@ -598,8 +598,8 @@ static int rt9467_run_aicl(struct rt9467_chg_data *data) reinit_completion(&data->aicl_done); ret = wait_for_completion_timeout(&data->aicl_done, msecs_to_jiffies(3500)); - if (ret) - return ret; + if (ret == 0) + return -ETIMEDOUT; ret = rt9467_get_value_from_ranges(data, F_IAICR, RT9467_RANGE_IAICR, &aicr_get); if (ret) { diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c index 954feba6600b..7970843a4f48 100644 --- a/drivers/power/supply/ucs1002_power.c +++ b/drivers/power/supply/ucs1002_power.c @@ -384,7 +384,8 @@ static int ucs1002_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_USB_TYPE: return ucs1002_get_usb_type(info, val); case POWER_SUPPLY_PROP_HEALTH: - return val->intval = info->health; + val->intval = info->health; + return 0; case POWER_SUPPLY_PROP_PRESENT: val->intval = info->present; return 0; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 6835ffe88d43..4021d3d325f9 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4046,7 +4046,6 @@ ptp_ocp_device_init(struct ptp_ocp *bp, struct pci_dev *pdev) return 0; out: - ptp_ocp_dev_release(&bp->dev); put_device(&bp->dev); return err; } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index d8e1caaf207e..3137e40fcd3e 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5542,6 +5542,8 @@ regulator_register(struct device *dev, goto rinse; } device_initialize(&rdev->dev); + dev_set_drvdata(&rdev->dev, rdev); + rdev->dev.class = ®ulator_class; spin_lock_init(&rdev->err_lock); /* @@ -5603,11 +5605,9 @@ regulator_register(struct device *dev, rdev->supply_name = regulator_desc->supply_name; /* register with sysfs */ - rdev->dev.class = ®ulator_class; rdev->dev.parent = config->dev; dev_set_name(&rdev->dev, "regulator.%lu", (unsigned long) atomic_inc_return(®ulator_no)); - dev_set_drvdata(&rdev->dev, rdev); /* set regulator constraints */ if (init_data) @@ -5724,15 +5724,11 @@ wash: mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); mutex_unlock(®ulator_list_mutex); - put_device(&rdev->dev); - rdev = NULL; clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); - if (rdev && rdev->dev.of_node) - of_node_put(rdev->dev.of_node); - kfree(rdev); kfree(config); + put_device(&rdev->dev); rinse: if (dangling_cfg_gpiod) gpiod_put(cfg->ena_gpiod); diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c index b9cda2210c33..65fbd95f1dbb 100644 --- a/drivers/regulator/mt6358-regulator.c +++ b/drivers/regulator/mt6358-regulator.c @@ -43,7 +43,7 @@ struct mt6358_regulator_info { .desc = { \ .name = #vreg, \ .of_match = of_match_ptr(match), \ - .ops = &mt6358_volt_range_ops, \ + .ops = &mt6358_buck_ops, \ .type = REGULATOR_VOLTAGE, \ .id = MT6358_ID_##vreg, \ .owner = THIS_MODULE, \ @@ -139,7 +139,7 @@ struct mt6358_regulator_info { .desc = { \ .name = #vreg, \ .of_match = of_match_ptr(match), \ - .ops = &mt6358_volt_range_ops, \ + .ops = &mt6358_buck_ops, \ .type = REGULATOR_VOLTAGE, \ .id = MT6366_ID_##vreg, \ .owner = THIS_MODULE, \ @@ -450,7 +450,7 @@ static unsigned int mt6358_regulator_get_mode(struct regulator_dev *rdev) } } -static const struct regulator_ops mt6358_volt_range_ops = { +static const struct regulator_ops mt6358_buck_ops = { .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, .set_voltage_sel = regulator_set_voltage_sel_regmap, @@ -464,6 +464,18 @@ static const struct regulator_ops mt6358_volt_range_ops = { .get_mode = mt6358_regulator_get_mode, }; +static const struct regulator_ops mt6358_volt_range_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = mt6358_get_buck_voltage_sel, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6358_get_status, +}; + static const struct regulator_ops mt6358_volt_table_ops = { .list_voltage = regulator_list_voltage_table, .map_voltage = regulator_map_voltage_iterate, diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index df782646e856..ab2f35bc294d 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -518,12 +518,12 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, if (port) { put_device(&port->dev); retval = -EEXIST; - goto err_out; + goto err_put; } port = kzalloc(sizeof(struct zfcp_port), GFP_KERNEL); if (!port) - goto err_out; + goto err_put; rwlock_init(&port->unit_list_lock); INIT_LIST_HEAD(&port->unit_list); @@ -546,7 +546,7 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, if (dev_set_name(&port->dev, "0x%016llx", (unsigned long long)wwpn)) { kfree(port); - goto err_out; + goto err_put; } retval = -EINVAL; @@ -563,7 +563,8 @@ struct zfcp_port *zfcp_port_enqueue(struct zfcp_adapter *adapter, u64 wwpn, return port; -err_out: +err_put: zfcp_ccw_adapter_put(adapter); +err_out: return ERR_PTR(retval); } diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index 93c68931a593..22cef283b2b9 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -27,7 +27,7 @@ #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.6.0.56" +#define DRV_VERSION "1.6.0.57" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " @@ -237,6 +237,8 @@ struct fnic { unsigned int cq_count; struct mutex sgreset_mutex; + spinlock_t sgreset_lock; /* lock for sgreset */ + struct scsi_cmnd *sgreset_sc; struct dentry *fnic_stats_debugfs_host; struct dentry *fnic_stats_debugfs_file; struct dentry *fnic_reset_debugfs_file; diff --git a/drivers/scsi/fnic/fnic_io.h b/drivers/scsi/fnic/fnic_io.h index f4c8769df312..5895ead20e14 100644 --- a/drivers/scsi/fnic/fnic_io.h +++ b/drivers/scsi/fnic/fnic_io.h @@ -52,6 +52,8 @@ struct fnic_io_req { unsigned long start_time; /* in jiffies */ struct completion *abts_done; /* completion for abts */ struct completion *dr_done; /* completion for device reset */ + unsigned int tag; + struct scsi_cmnd *sc; /* midlayer's cmd pointer */ }; enum fnic_port_speeds { diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c index 984bc5fc55e2..f27f9319e0b2 100644 --- a/drivers/scsi/fnic/fnic_main.c +++ b/drivers/scsi/fnic/fnic_main.c @@ -754,6 +754,8 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) for (i = 0; i < FNIC_IO_LOCKS; i++) spin_lock_init(&fnic->io_req_lock[i]); + spin_lock_init(&fnic->sgreset_lock); + err = -ENOMEM; fnic->io_req_pool = mempool_create_slab_pool(2, fnic_io_req_cache); if (!fnic->io_req_pool) diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 9761b2c9db48..416d81954819 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -1047,9 +1047,9 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, { u8 type; u8 hdr_status; - struct fcpio_tag tag; + struct fcpio_tag ftag; u32 id; - struct scsi_cmnd *sc; + struct scsi_cmnd *sc = NULL; struct fnic_io_req *io_req; struct fnic_stats *fnic_stats = &fnic->fnic_stats; struct abort_stats *abts_stats = &fnic->fnic_stats.abts_stats; @@ -1058,27 +1058,43 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned long flags; spinlock_t *io_lock; unsigned long start_time; + unsigned int tag; - fcpio_header_dec(&desc->hdr, &type, &hdr_status, &tag); - fcpio_tag_id_dec(&tag, &id); + fcpio_header_dec(&desc->hdr, &type, &hdr_status, &ftag); + fcpio_tag_id_dec(&ftag, &id); - if ((id & FNIC_TAG_MASK) >= fnic->fnic_max_tag_id) { + tag = id & FNIC_TAG_MASK; + if (tag == fnic->fnic_max_tag_id) { + if (!(id & FNIC_TAG_DEV_RST)) { + shost_printk(KERN_ERR, fnic->lport->host, + "Tag out of range id 0x%x hdr status = %s\n", + id, fnic_fcpio_status_to_str(hdr_status)); + return; + } + } else if (tag > fnic->fnic_max_tag_id) { shost_printk(KERN_ERR, fnic->lport->host, - "Tag out of range tag %x hdr status = %s\n", - id, fnic_fcpio_status_to_str(hdr_status)); + "Tag out of range tag 0x%x hdr status = %s\n", + tag, fnic_fcpio_status_to_str(hdr_status)); return; } - sc = scsi_host_find_tag(fnic->lport->host, id & FNIC_TAG_MASK); + if ((tag == fnic->fnic_max_tag_id) && (id & FNIC_TAG_DEV_RST)) { + sc = fnic->sgreset_sc; + io_lock = &fnic->sgreset_lock; + } else { + sc = scsi_host_find_tag(fnic->lport->host, id & FNIC_TAG_MASK); + io_lock = fnic_io_lock_hash(fnic, sc); + } + WARN_ON_ONCE(!sc); if (!sc) { atomic64_inc(&fnic_stats->io_stats.sc_null); shost_printk(KERN_ERR, fnic->lport->host, "itmf_cmpl sc is null - hdr status = %s tag = 0x%x\n", - fnic_fcpio_status_to_str(hdr_status), id); + fnic_fcpio_status_to_str(hdr_status), tag); return; } - io_lock = fnic_io_lock_hash(fnic, sc); + spin_lock_irqsave(io_lock, flags); io_req = fnic_priv(sc)->io_req; WARN_ON_ONCE(!io_req); @@ -1089,7 +1105,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, shost_printk(KERN_ERR, fnic->lport->host, "itmf_cmpl io_req is null - " "hdr status = %s tag = 0x%x sc 0x%p\n", - fnic_fcpio_status_to_str(hdr_status), id, sc); + fnic_fcpio_status_to_str(hdr_status), tag, sc); return; } start_time = io_req->start_time; @@ -1938,6 +1954,10 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic, struct scsi_lun fc_lun; int ret = 0; unsigned long intr_flags; + unsigned int tag = scsi_cmd_to_rq(sc)->tag; + + if (tag == SCSI_NO_TAG) + tag = io_req->tag; spin_lock_irqsave(host->host_lock, intr_flags); if (unlikely(fnic_chk_state_flags_locked(fnic, @@ -1964,7 +1984,8 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic, /* fill in the lun info */ int_to_scsilun(sc->device->lun, &fc_lun); - fnic_queue_wq_copy_desc_itmf(wq, scsi_cmd_to_rq(sc)->tag | FNIC_TAG_DEV_RST, + tag |= FNIC_TAG_DEV_RST; + fnic_queue_wq_copy_desc_itmf(wq, tag, 0, FCPIO_ITMF_LUN_RESET, SCSI_NO_TAG, fc_lun.scsi_lun, io_req->port_id, fnic->config.ra_tov, fnic->config.ed_tov); @@ -2146,8 +2167,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic, .ret = SUCCESS, }; - if (new_sc) - iter_data.lr_sc = lr_sc; + iter_data.lr_sc = lr_sc; scsi_host_busy_iter(fnic->lport->host, fnic_pending_aborts_iter, &iter_data); @@ -2230,8 +2250,14 @@ int fnic_device_reset(struct scsi_cmnd *sc) mutex_lock(&fnic->sgreset_mutex); tag = fnic->fnic_max_tag_id; new_sc = 1; - } - io_lock = fnic_io_lock_hash(fnic, sc); + fnic->sgreset_sc = sc; + io_lock = &fnic->sgreset_lock; + FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, + "fcid: 0x%x lun: 0x%llx flags: 0x%x tag: 0x%x Issuing sgreset\n", + rport->port_id, sc->device->lun, fnic_priv(sc)->flags, tag); + } else + io_lock = fnic_io_lock_hash(fnic, sc); + spin_lock_irqsave(io_lock, flags); io_req = fnic_priv(sc)->io_req; @@ -2247,6 +2273,8 @@ int fnic_device_reset(struct scsi_cmnd *sc) } memset(io_req, 0, sizeof(*io_req)); io_req->port_id = rport->port_id; + io_req->tag = tag; + io_req->sc = sc; fnic_priv(sc)->io_req = io_req; } io_req->dr_done = &tm_done; @@ -2400,8 +2428,10 @@ fnic_device_reset_end: (u64)sc->cmnd[4] << 8 | sc->cmnd[5]), fnic_flags_and_state(sc)); - if (new_sc) + if (new_sc) { + fnic->sgreset_sc = NULL; mutex_unlock(&fnic->sgreset_mutex); + } FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, "Returning from device reset %s\n", diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index d0911bc28663..89367c4bf0ef 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -613,6 +613,17 @@ void scsi_cdl_check(struct scsi_device *sdev) bool cdl_supported; unsigned char *buf; + /* + * Support for CDL was defined in SPC-5. Ignore devices reporting an + * lower SPC version. This also avoids problems with old drives choking + * on MAINTENANCE_IN / MI_REPORT_SUPPORTED_OPERATION_CODES with a + * service action specified, as done in scsi_cdl_check_cmd(). + */ + if (sdev->scsi_level < SCSI_SPC_5) { + sdev->cdl_supported = 0; + return; + } + buf = kmalloc(SCSI_CDL_CHECK_BUF_LEN, GFP_KERNEL); if (!buf) { sdev->cdl_supported = 0; diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 52014b2d39e1..902655d75947 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -822,7 +822,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result, * device is attached at LUN 0 (SCSI_SCAN_TARGET_PRESENT) so * non-zero LUNs can be scanned. */ - sdev->scsi_level = inq_result[2] & 0x07; + sdev->scsi_level = inq_result[2] & 0x0f; if (sdev->scsi_level >= 2 || (sdev->scsi_level == 1 && (inq_result[3] & 0x0f) == 1)) sdev->scsi_level++; @@ -1619,12 +1619,24 @@ int scsi_add_device(struct Scsi_Host *host, uint channel, } EXPORT_SYMBOL(scsi_add_device); -void scsi_rescan_device(struct scsi_device *sdev) +int scsi_rescan_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; + int ret = 0; device_lock(dev); + /* + * Bail out if the device is not running. Otherwise, the rescan may + * block waiting for commands to be executed, with us holding the + * device lock. This can result in a potential deadlock in the power + * management core code when system resume is on-going. + */ + if (sdev->sdev_state != SDEV_RUNNING) { + ret = -EWOULDBLOCK; + goto unlock; + } + scsi_attach_vpd(sdev); scsi_cdl_check(sdev); @@ -1638,7 +1650,11 @@ void scsi_rescan_device(struct scsi_device *sdev) drv->rescan(dev); module_put(dev->driver->owner); } + +unlock: device_unlock(dev); + + return ret; } EXPORT_SYMBOL(scsi_rescan_device); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index c92a317ba547..83b6a3f3863b 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -201,18 +201,32 @@ cache_type_store(struct device *dev, struct device_attribute *attr, } static ssize_t -manage_start_stop_show(struct device *dev, struct device_attribute *attr, - char *buf) +manage_start_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; - return sprintf(buf, "%u\n", sdp->manage_start_stop); + return sysfs_emit(buf, "%u\n", + sdp->manage_system_start_stop && + sdp->manage_runtime_start_stop); } +static DEVICE_ATTR_RO(manage_start_stop); static ssize_t -manage_start_stop_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +manage_system_start_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + return sysfs_emit(buf, "%u\n", sdp->manage_system_start_stop); +} + +static ssize_t +manage_system_start_stop_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; @@ -224,11 +238,42 @@ manage_start_stop_store(struct device *dev, struct device_attribute *attr, if (kstrtobool(buf, &v)) return -EINVAL; - sdp->manage_start_stop = v; + sdp->manage_system_start_stop = v; return count; } -static DEVICE_ATTR_RW(manage_start_stop); +static DEVICE_ATTR_RW(manage_system_start_stop); + +static ssize_t +manage_runtime_start_stop_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + return sysfs_emit(buf, "%u\n", sdp->manage_runtime_start_stop); +} + +static ssize_t +manage_runtime_start_stop_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + bool v; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->manage_runtime_start_stop = v; + + return count; +} +static DEVICE_ATTR_RW(manage_runtime_start_stop); static ssize_t allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -560,6 +605,8 @@ static struct attribute *sd_disk_attrs[] = { &dev_attr_FUA.attr, &dev_attr_allow_restart.attr, &dev_attr_manage_start_stop.attr, + &dev_attr_manage_system_start_stop.attr, + &dev_attr_manage_runtime_start_stop.attr, &dev_attr_protection_type.attr, &dev_attr_protection_mode.attr, &dev_attr_app_tag_own.attr, @@ -3694,7 +3741,8 @@ static int sd_remove(struct device *dev) device_del(&sdkp->disk_dev); del_gendisk(sdkp->disk); - sd_shutdown(dev); + if (!sdkp->suspended) + sd_shutdown(dev); put_disk(sdkp->disk); return 0; @@ -3771,13 +3819,20 @@ static void sd_shutdown(struct device *dev) sd_sync_cache(sdkp, NULL); } - if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) { + if (system_state != SYSTEM_RESTART && + sdkp->device->manage_system_start_stop) { sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } } -static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) +static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime) +{ + return (sdev->manage_system_start_stop && !runtime) || + (sdev->manage_runtime_start_stop && runtime); +} + +static int sd_suspend_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); struct scsi_sense_hdr sshdr; @@ -3809,15 +3864,18 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) } } - if (sdkp->device->manage_start_stop) { + if (sd_do_start_stop(sdkp->device, runtime)) { if (!sdkp->device->silence_suspend) sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); /* an error is not worth aborting a system sleep */ ret = sd_start_stop_device(sdkp, 0); - if (ignore_stop_errors) + if (!runtime) ret = 0; } + if (!ret) + sdkp->suspended = true; + return ret; } @@ -3826,15 +3884,15 @@ static int sd_suspend_system(struct device *dev) if (pm_runtime_suspended(dev)) return 0; - return sd_suspend_common(dev, true); + return sd_suspend_common(dev, false); } static int sd_suspend_runtime(struct device *dev) { - return sd_suspend_common(dev, false); + return sd_suspend_common(dev, true); } -static int sd_resume(struct device *dev) +static int sd_resume(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; @@ -3842,16 +3900,21 @@ static int sd_resume(struct device *dev) if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; - if (!sdkp->device->manage_start_stop) + if (!sd_do_start_stop(sdkp->device, runtime)) { + sdkp->suspended = false; return 0; + } if (!sdkp->device->no_start_on_resume) { sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); } - if (!ret) + if (!ret) { opal_unlock_from_suspend(sdkp->opal_dev); + sdkp->suspended = false; + } + return ret; } @@ -3860,7 +3923,7 @@ static int sd_resume_system(struct device *dev) if (pm_runtime_suspended(dev)) return 0; - return sd_resume(dev); + return sd_resume(dev, false); } static int sd_resume_runtime(struct device *dev) @@ -3887,7 +3950,7 @@ static int sd_resume_runtime(struct device *dev) "Failed to clear sense data\n"); } - return sd_resume(dev); + return sd_resume(dev, true); } static const struct dev_pm_ops sd_pm_ops = { diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 5eea762f84d1..409dda5350d1 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -131,6 +131,7 @@ struct scsi_disk { u8 provisioning_mode; u8 zeroing_mode; u8 nr_actuators; /* Number of actuators */ + bool suspended; /* Disk is suspended (stopped) */ unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c index 1dcd243df567..ec87d9d878f3 100644 --- a/drivers/soc/imx/soc-imx8m.c +++ b/drivers/soc/imx/soc-imx8m.c @@ -100,6 +100,7 @@ static void __init imx8mm_soc_uid(void) { void __iomem *ocotp_base; struct device_node *np; + struct clk *clk; u32 offset = of_machine_is_compatible("fsl,imx8mp") ? IMX8MP_OCOTP_UID_OFFSET : 0; @@ -109,11 +110,20 @@ static void __init imx8mm_soc_uid(void) ocotp_base = of_iomap(np, 0); WARN_ON(!ocotp_base); + clk = of_clk_get_by_name(np, NULL); + if (IS_ERR(clk)) { + WARN_ON(IS_ERR(clk)); + return; + } + + clk_prepare_enable(clk); soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH + offset); soc_uid <<= 32; soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW + offset); + clk_disable_unprepare(clk); + clk_put(clk); iounmap(ocotp_base); of_node_put(np); } diff --git a/drivers/soc/loongson/Kconfig b/drivers/soc/loongson/Kconfig index 314e13bb3e01..368344943a93 100644 --- a/drivers/soc/loongson/Kconfig +++ b/drivers/soc/loongson/Kconfig @@ -20,6 +20,7 @@ config LOONGSON2_GUTS config LOONGSON2_PM bool "Loongson-2 SoC Power Management Controller Driver" depends on LOONGARCH && OF + depends on INPUT=y help The Loongson-2's power management controller was ACPI, supports ACPI S2Idle (Suspend To Idle), ACPI S3 (Suspend To RAM), ACPI S4 (Suspend To diff --git a/drivers/soc/loongson/loongson2_guts.c b/drivers/soc/loongson/loongson2_guts.c index bace4bc8e03b..9a469779eea7 100644 --- a/drivers/soc/loongson/loongson2_guts.c +++ b/drivers/soc/loongson/loongson2_guts.c @@ -70,7 +70,7 @@ static const struct loongson2_soc_die_attr *loongson2_soc_die_match( if (matches->svr == (svr & matches->mask)) return matches; matches++; - }; + } return NULL; } @@ -94,7 +94,6 @@ static int loongson2_guts_probe(struct platform_device *pdev) { struct device_node *root, *np = pdev->dev.of_node; struct device *dev = &pdev->dev; - struct resource *res; const struct loongson2_soc_die_attr *soc_die; const char *machine; u32 svr; @@ -106,8 +105,7 @@ static int loongson2_guts_probe(struct platform_device *pdev) guts->little_endian = of_property_read_bool(np, "little-endian"); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - guts->regs = ioremap(res->start, res->end - res->start + 1); + guts->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(guts->regs)) return PTR_ERR(guts->regs); diff --git a/drivers/soc/loongson/loongson2_pm.c b/drivers/soc/loongson/loongson2_pm.c index 796add6e8b63..b8e5e1e3528a 100644 --- a/drivers/soc/loongson/loongson2_pm.c +++ b/drivers/soc/loongson/loongson2_pm.c @@ -11,6 +11,7 @@ #include <linux/input.h> #include <linux/suspend.h> #include <linux/interrupt.h> +#include <linux/of_platform.h> #include <linux/pm_wakeirq.h> #include <linux/platform_device.h> #include <asm/bootinfo.h> @@ -192,12 +193,16 @@ static int loongson2_pm_probe(struct platform_device *pdev) if (loongson_sysconf.suspend_addr) suspend_set_ops(&loongson2_suspend_ops); + /* Populate children */ + retval = devm_of_platform_populate(dev); + if (retval) + dev_err(dev, "Error populating children, reboot and poweroff might not work properly\n"); + return 0; } static const struct of_device_id loongson2_pm_match[] = { { .compatible = "loongson,ls2k0500-pmc", }, - { .compatible = "loongson,ls2k1000-pmc", }, {}, }; diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c index 453a9b37ce78..d239fc5a49cc 100644 --- a/drivers/spi/spi-cs42l43.c +++ b/drivers/spi/spi-cs42l43.c @@ -256,7 +256,6 @@ static int cs42l43_spi_probe(struct platform_device *pdev) ret = devm_spi_register_controller(priv->dev, priv->ctlr); if (ret) { - pm_runtime_disable(priv->dev); dev_err(priv->dev, "Failed to register SPI controller: %d\n", ret); } diff --git a/drivers/spi/spi-gxp.c b/drivers/spi/spi-gxp.c index fd2fac236bbd..3aff5a166c94 100644 --- a/drivers/spi/spi-gxp.c +++ b/drivers/spi/spi-gxp.c @@ -194,7 +194,7 @@ static ssize_t gxp_spi_write(struct gxp_spi_chip *chip, const struct spi_mem_op return ret; } - return write_len; + return 0; } static int do_gxp_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index b7ac60f4a219..b6523d4b9259 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -843,7 +843,6 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb) EXPORT_SYMBOL(target_to_linux_sector); struct devices_idr_iter { - struct config_item *prev_item; int (*fn)(struct se_device *dev, void *data); void *data; }; @@ -853,11 +852,9 @@ static int target_devices_idr_iter(int id, void *p, void *data) { struct devices_idr_iter *iter = data; struct se_device *dev = p; + struct config_item *item; int ret; - config_item_put(iter->prev_item); - iter->prev_item = NULL; - /* * We add the device early to the idr, so it can be used * by backend modules during configuration. We do not want @@ -867,12 +864,13 @@ static int target_devices_idr_iter(int id, void *p, void *data) if (!target_dev_configured(dev)) return 0; - iter->prev_item = config_item_get_unless_zero(&dev->dev_group.cg_item); - if (!iter->prev_item) + item = config_item_get_unless_zero(&dev->dev_group.cg_item); + if (!item) return 0; mutex_unlock(&device_mutex); ret = iter->fn(dev, iter->data); + config_item_put(item); mutex_lock(&device_mutex); return ret; @@ -895,7 +893,6 @@ int target_for_each_device(int (*fn)(struct se_device *dev, void *data), mutex_lock(&device_mutex); ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter); mutex_unlock(&device_mutex); - config_item_put(iter.prev_item); return ret; } diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h index 72685ee0d53f..6bb5cae09688 100644 --- a/drivers/tee/optee/optee_private.h +++ b/drivers/tee/optee/optee_private.h @@ -238,8 +238,6 @@ int optee_notif_send(struct optee *optee, u_int key); u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params, struct tee_param *param); -int optee_supp_read(struct tee_context *ctx, void __user *buf, size_t len); -int optee_supp_write(struct tee_context *ctx, void __user *buf, size_t len); void optee_supp_init(struct optee_supp *supp); void optee_supp_uninit(struct optee_supp *supp); void optee_supp_release(struct optee_supp *supp); diff --git a/drivers/tee/tee_private.h b/drivers/tee/tee_private.h index 409cadcc1cff..754e11dcb240 100644 --- a/drivers/tee/tee_private.h +++ b/drivers/tee/tee_private.h @@ -47,8 +47,6 @@ struct tee_device { struct tee_shm_pool *pool; }; -int tee_shm_init(void); - int tee_shm_get_fd(struct tee_shm *shm); bool tee_device_get(struct tee_device *teedev); diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index 6c20c9f90a05..4e6a97db894e 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -185,9 +185,6 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr, if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1) return -EINVAL; - if (kstrtoint(buf, 10, &trip.hysteresis)) - return -EINVAL; - mutex_lock(&tz->lock); if (!device_is_registered(dev)) { @@ -198,7 +195,11 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr, ret = __thermal_zone_get_trip(tz, trip_id, &trip); if (ret) goto unlock; - + + ret = kstrtoint(buf, 10, &trip.hysteresis); + if (ret) + goto unlock; + ret = thermal_zone_set_trip(tz, trip_id, &trip); unlock: mutex_unlock(&tz->lock); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index b3550ff9c494..1f3aba607cd5 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3097,10 +3097,8 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) gsm->has_devices = false; } for (i = NUM_DLCI - 1; i >= 0; i--) - if (gsm->dlci[i]) { + if (gsm->dlci[i]) gsm_dlci_release(gsm->dlci[i]); - gsm->dlci[i] = NULL; - } mutex_unlock(&gsm->mutex); /* Now wipe the queues */ tty_ldisc_flush(gsm->tty); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fb891b67968f..141627370aab 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1936,7 +1936,10 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { - if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) + struct irq_data *d; + + d = irq_get_irq_data(port->irq); + if (d && irqd_is_wakeup_set(d)) pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c index e4490639d383..9d2738e10c0b 100644 --- a/drivers/vfio/mdev/mdev_sysfs.c +++ b/drivers/vfio/mdev/mdev_sysfs.c @@ -233,7 +233,8 @@ int parent_create_sysfs_files(struct mdev_parent *parent) out_err: while (--i >= 0) mdev_type_remove(parent->types[i]); - return 0; + kset_unregister(parent->mdev_types_kset); + return ret; } static ssize_t remove_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/vfio/pci/pds/Kconfig b/drivers/vfio/pci/pds/Kconfig index 407b3fd32733..6eceef7b028a 100644 --- a/drivers/vfio/pci/pds/Kconfig +++ b/drivers/vfio/pci/pds/Kconfig @@ -3,7 +3,7 @@ config PDS_VFIO_PCI tristate "VFIO support for PDS PCI devices" - depends on PDS_CORE + depends on PDS_CORE && PCI_IOV select VFIO_PCI_CORE help This provides generic PCI support for PDS devices using the VFIO diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c index b46174f5eb09..649b18ee394b 100644 --- a/drivers/vfio/pci/pds/vfio_dev.c +++ b/drivers/vfio/pci/pds/vfio_dev.c @@ -162,7 +162,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev) pci_id = PCI_DEVID(pdev->bus->number, pdev->devfn); dev_dbg(&pdev->dev, "%s: PF %#04x VF %#04x vf_id %d domain %d pds_vfio %p\n", - __func__, pci_dev_id(pdev->physfn), pci_id, vf_id, + __func__, pci_dev_id(pci_physfn(pdev)), pci_id, vf_id, pci_domain_nr(pdev->bus), pds_vfio); return 0; diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 955d938eb663..7b8fd977f71c 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -123,8 +123,18 @@ static inline ssize_t vringh_iov_xfer(struct vringh *vrh, done += partlen; len -= partlen; ptr += partlen; + iov->consumed += partlen; + iov->iov[iov->i].iov_len -= partlen; + iov->iov[iov->i].iov_base += partlen; - vringh_kiov_advance(iov, partlen); + if (!iov->iov[iov->i].iov_len) { + /* Fix up old iov element then increment. */ + iov->iov[iov->i].iov_len = iov->consumed; + iov->iov[iov->i].iov_base -= iov->consumed; + + iov->consumed = 0; + iov->i++; + } } return done; } diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig index 1b5a319971ed..30577b1d3de5 100644 --- a/drivers/video/console/Kconfig +++ b/drivers/video/console/Kconfig @@ -73,6 +73,7 @@ config DUMMY_CONSOLE_ROWS config FRAMEBUFFER_CONSOLE bool "Framebuffer Console support" depends on FB_CORE && !UML + default DRM_FBDEV_EMULATION select VT_HW_CONSOLE_BINDING select CRC32 select FONT_SUPPORT diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index eac0ba39581e..c29754b65c0e 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -1762,7 +1762,7 @@ config FB_COBALT config FB_SH7760 bool "SH7760/SH7763/SH7720/SH7721 LCDC support" - depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ + depends on FB=y && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ || CPU_SUBTYPE_SH7720 || CPU_SUBTYPE_SH7721) select FB_IOMEM_HELPERS help diff --git a/drivers/video/fbdev/core/Kconfig b/drivers/video/fbdev/core/Kconfig index baf7e852c75b..5ac1b0637531 100644 --- a/drivers/video/fbdev/core/Kconfig +++ b/drivers/video/fbdev/core/Kconfig @@ -28,7 +28,7 @@ config FIRMWARE_EDID config FB_DEVICE bool "Provide legacy /dev/fb* device" depends on FB_CORE - default y + default FB help Say Y here if you want the legacy /dev/fb* device file and interfaces within sysfs anc procfs. It is only required if you @@ -80,7 +80,7 @@ struct aio_ring { struct kioctx_table { struct rcu_head rcu; unsigned nr; - struct kioctx __rcu *table[]; + struct kioctx __rcu *table[] __counted_by(nr); }; struct kioctx_cpu { diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 43b2a2851ba3..206812ce544a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -345,10 +345,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ + SET_PERSONALITY(exec_params.hdr); if (elf_check_fdpic(&exec_params.hdr)) - set_personality(PER_LINUX_FDPIC); - else - set_personality(PER_LINUX); + current->personality |= PER_LINUX_FDPIC; if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 6a13cf00218b..9fe4ccca50a0 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -103,24 +103,17 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) * Transfer bytes to our delayed refs rsv. * * @fs_info: the filesystem - * @src: source block rsv to transfer from * @num_bytes: number of bytes to transfer * - * This transfers up to the num_bytes amount from the src rsv to the + * This transfers up to the num_bytes amount, previously reserved, to the * delayed_refs_rsv. Any extra bytes are returned to the space info. */ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *src, u64 num_bytes) { struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv; u64 to_free = 0; - spin_lock(&src->lock); - src->reserved -= num_bytes; - src->size -= num_bytes; - spin_unlock(&src->lock); - spin_lock(&delayed_refs_rsv->lock); if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) { u64 delta = delayed_refs_rsv->size - @@ -163,6 +156,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv; u64 limit = btrfs_calc_delayed_ref_bytes(fs_info, 1); u64 num_bytes = 0; + u64 refilled_bytes; + u64 to_free; int ret = -ENOSPC; spin_lock(&block_rsv->lock); @@ -178,9 +173,38 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, num_bytes, flush); if (ret) return ret; - btrfs_block_rsv_add_bytes(block_rsv, num_bytes, false); - trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", - 0, num_bytes, 1); + + /* + * We may have raced with someone else, so check again if we the block + * reserve is still not full and release any excess space. + */ + spin_lock(&block_rsv->lock); + if (block_rsv->reserved < block_rsv->size) { + u64 needed = block_rsv->size - block_rsv->reserved; + + if (num_bytes >= needed) { + block_rsv->reserved += needed; + block_rsv->full = true; + to_free = num_bytes - needed; + refilled_bytes = needed; + } else { + block_rsv->reserved += num_bytes; + to_free = 0; + refilled_bytes = num_bytes; + } + } else { + to_free = num_bytes; + refilled_bytes = 0; + } + spin_unlock(&block_rsv->lock); + + if (to_free > 0) + btrfs_space_info_free_bytes_may_use(fs_info, block_rsv->space_info, + to_free); + + if (refilled_bytes > 0) + trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, + refilled_bytes, 1); return 0; } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index b8e14b0ba5f1..fd9bf2b709c0 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -407,7 +407,6 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans); int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *src, u64 num_bytes); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f356f08b55cb..fc313fce5bbd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1514,15 +1514,14 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_release_path(path); /* now insert the actual backref */ - if (owner < BTRFS_FIRST_FREE_OBJECTID) { - BUG_ON(refs_to_add != 1); + if (owner < BTRFS_FIRST_FREE_OBJECTID) ret = insert_tree_block_ref(trans, path, bytenr, parent, root_objectid); - } else { + else ret = insert_extent_data_ref(trans, path, bytenr, parent, root_objectid, owner, offset, refs_to_add); - } + if (ret) btrfs_abort_transaction(trans, ret); out: @@ -1656,7 +1655,10 @@ again: goto again; } } else { - err = -EIO; + err = -EUCLEAN; + btrfs_err(fs_info, + "missing extent item for extent %llu num_bytes %llu level %d", + head->bytenr, head->num_bytes, extent_op->level); goto out; } } @@ -1699,12 +1701,12 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent = ref->parent; ref_root = ref->root; - if (node->ref_mod != 1) { + if (unlikely(node->ref_mod != 1)) { btrfs_err(trans->fs_info, - "btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu", + "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu", node->bytenr, node->ref_mod, node->action, ref_root, parent); - return -EIO; + return -EUCLEAN; } if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { BUG_ON(!extent_op || !extent_op->update_flags); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6954ae763b86..caccd0376342 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3995,8 +3995,14 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, char *dst = (char *)dstv; unsigned long i = get_eb_page_index(start); - if (check_eb_range(eb, start, len)) + if (check_eb_range(eb, start, len)) { + /* + * Invalid range hit, reset the memory, so callers won't get + * some random garbage for their uninitialzed memory. + */ + memset(dstv, 0, len); return; + } offset = get_eb_offset_in_page(eb, start); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cffdd6f7f8e8..1a093ec0f7e3 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2117,7 +2117,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * calculated f_bavail. */ if (!mixed && block_rsv->space_info->full && - total_free_meta - thresh < block_rsv->size) + (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size)) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 0bf42dccb041..c780d3729463 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -631,14 +631,14 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, reloc_reserved = true; } - ret = btrfs_block_rsv_add(fs_info, rsv, num_bytes, flush); + ret = btrfs_reserve_metadata_bytes(fs_info, rsv, num_bytes, flush); if (ret) goto reserve_fail; if (delayed_refs_bytes) { - btrfs_migrate_to_delayed_refs_rsv(fs_info, rsv, - delayed_refs_bytes); + btrfs_migrate_to_delayed_refs_rsv(fs_info, delayed_refs_bytes); num_bytes -= delayed_refs_bytes; } + btrfs_block_rsv_add_bytes(rsv, num_bytes, true); if (rsv->space_info->force_alloc) do_chunk_alloc = true; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d1e46b839519..cbb17b542131 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4722,7 +4722,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int slot; int ins_nr = 0; - int start_slot; + int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9621455edebc..5a5a8d488a7b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1594,7 +1594,7 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 search_start; u64 hole_size; u64 max_hole_start; - u64 max_hole_size; + u64 max_hole_size = 0; u64 extent_end; u64 search_end = device->total_bytes; int ret; @@ -1602,17 +1602,16 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, struct extent_buffer *l; search_start = dev_extent_search_start(device); + max_hole_start = search_start; WARN_ON(device->zone_info && !IS_ALIGNED(num_bytes, device->zone_info->zone_size)); path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - max_hole_start = search_start; - max_hole_size = 0; - + if (!path) { + ret = -ENOMEM; + goto out; + } again: if (search_start >= search_end || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { diff --git a/fs/buffer.c b/fs/buffer.c index 2379564e5aea..12e9a71c693d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2011,7 +2011,7 @@ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) } EXPORT_SYMBOL(folio_zero_new_buffers); -static void +static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { @@ -2025,7 +2025,8 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, * current block, then do not map the buffer and let the caller * handle it. */ - BUG_ON(offset >= iomap->offset + iomap->length); + if (offset >= iomap->offset + iomap->length) + return -EIO; switch (iomap->type) { case IOMAP_HOLE: @@ -2037,7 +2038,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); - break; + return 0; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) @@ -2045,7 +2046,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); - break; + return 0; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions @@ -2057,12 +2058,24 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || - offset >= i_size_read(inode)) + offset >= i_size_read(inode)) { + /* + * This can happen if truncating the block device races + * with the check in the caller as i_size updates on + * block devices aren't synchronized by i_rwsem for + * block devices. + */ + if (S_ISBLK(inode->i_mode)) + return -EIO; set_buffer_new(bh); + } bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); - break; + return 0; + default: + WARN_ON_ONCE(1); + return -EIO; } } @@ -2103,13 +2116,12 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); - if (get_block) { + if (get_block) err = get_block(inode, block, bh, 1); - if (err) - break; - } else { - iomap_to_bh(inode, block, bh, iomap); - } + else + err = iomap_to_bh(inode, block, bh, iomap); + if (err) + break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index e4d5cd56a80b..e1f31b86fd48 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -249,11 +249,9 @@ static struct inode *parse_longname(const struct inode *parent, if (!dir) { /* This can happen if we're not mounting cephfs on the root */ dir = ceph_get_inode(parent->i_sb, vino, NULL); - if (!dir) - dir = ERR_PTR(-ENOENT); + if (IS_ERR(dir)) + dout("Can't find inode %s (%s)\n", inode_number, name); } - if (IS_ERR(dir)) - dout("Can't find inode %s (%s)\n", inode_number, name); out: kfree(inode_number); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 969ce991b0b0..c1af01b2c42d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1535,10 +1535,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, if (wbc->pages_skipped) { /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. + * Writeback is not making progress due to locked buffers. + * Skip this inode for now. Although having skipped pages + * is odd for clean inodes, it can happen for some + * filesystems so handle that gracefully. */ - redirty_tail_locked(inode, wb); + if (inode->i_state & I_DIRTY_ALL) + redirty_tail_locked(inode, wb); + else + inode_cgwb_move_to_attached(inode, wb); return; } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index ae8673ce08b1..5db54ca29a35 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -640,11 +640,13 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, size_t poff, plen; /* - * If the write completely overlaps the current folio, then + * If the write or zeroing completely overlaps the current folio, then * entire folio will be dirtied so there is no need for * per-block state tracking structures to be attached to this folio. + * For the unshare case, we must read in the ondisk contents because we + * are not changing pagecache contents. */ - if (pos <= folio_pos(folio) && + if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) && pos + len >= folio_pos(folio) + folio_size(folio)) return 0; @@ -1047,7 +1049,7 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, /* * Scan the data range passed to us for dirty page cache folios. If we find a - * dirty folio, punch out the preceeding range and update the offset from which + * dirty folio, punch out the preceding range and update the offset from which * the next punch will start from. * * We can punch out storage reservations under clean pages because they either @@ -1261,7 +1263,6 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); - long status = 0; loff_t written = 0; /* don't bother with blocks that are not shared to start with */ @@ -1272,28 +1273,33 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) return length; do { - unsigned long offset = offset_in_page(pos); - unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length); struct folio *folio; + int status; + size_t offset; + size_t bytes = min_t(u64, SIZE_MAX, length); status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) return status; - if (iter->iomap.flags & IOMAP_F_STALE) + if (iomap->flags & IOMAP_F_STALE) break; - status = iomap_write_end(iter, pos, bytes, bytes, folio); - if (WARN_ON_ONCE(status == 0)) + offset = offset_in_folio(folio, pos); + if (bytes > folio_size(folio) - offset) + bytes = folio_size(folio) - offset; + + bytes = iomap_write_end(iter, pos, bytes, bytes, folio); + if (WARN_ON_ONCE(bytes == 0)) return -EIO; cond_resched(); - pos += status; - written += status; - length -= status; + pos += bytes; + written += bytes; + length -= bytes; balance_dirty_pages_ratelimited(iter->inode->i_mapping); - } while (length); + } while (length > 0); return written; } diff --git a/fs/libfs.c b/fs/libfs.c index a4eb12757886..37f2d34ee090 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1903,6 +1903,7 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ + iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3508d8238826..7016eaadf555 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10622,7 +10622,9 @@ static void nfs4_disable_swap(struct inode *inode) */ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + wake_up_var(&clp->cl_state); } static const struct inode_operations nfs4_dir_inode_operations = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e079987af4a3..9a5d911a7edc 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *clnt = clp->cl_rpcclient; + bool swapon = false; - if (clp->cl_rpcclient->cl_shutdown) + if (clnt->cl_shutdown) return; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { - wake_up_var(&clp->cl_state); - return; + + if (atomic_read(&clnt->cl_swapper)) { + swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, + &clp->cl_state); + if (!swapon) { + wake_up_var(&clp->cl_state); + return; + } } - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) __func__, PTR_ERR(task)); if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); + if (swapon) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs4_clear_state_manager_bit(clp); - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2703,6 +2714,13 @@ static void nfs4_state_manager(struct nfs_client *clp) nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); + if (test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, + &clp->cl_state)) { + memflags = memalloc_nofs_save(); + continue; + } + if (!test_and_set_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state)) { if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) { nfs_client_return_marked_delegations(clp); @@ -2741,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); again: - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); - if (atomic_read(&cl->cl_swapper)) { + + if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) && + !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) { wait_var_event_interruptible(&clp->cl_state, test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)); - if (atomic_read(&cl->cl_swapper) && - test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + if (!atomic_read(&cl->cl_swapper)) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; /* Either no longer a swapper, or were signalled */ + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); } - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); if (refcount_read(&clp->cl_count) > 1 && !signalled() && test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && - !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; nfs_put_client(clp); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 8c1ee1a1a28f..7720b5e43014 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -802,8 +802,8 @@ static void nfs_inode_remove_request(struct nfs_page *req) } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { - nfs_release_request(req); atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests); + nfs_release_request(req); } } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2e40c74d2f72..92c7dde148a4 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4113,6 +4113,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, struct file *file, unsigned long maxcount) { struct xdr_stream *xdr = resp->xdr; + unsigned int base = xdr->buf->page_len & ~PAGE_MASK; unsigned int starting_len = xdr->buf->len; __be32 zero = xdr_zero; __be32 nfserr; @@ -4121,8 +4122,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, return nfserr_resource; nfserr = nfsd_iter_read(resp->rqstp, read->rd_fhp, file, - read->rd_offset, &maxcount, - xdr->buf->page_len & ~PAGE_MASK, + read->rd_offset, &maxcount, base, &read->rd_eof); read->rd_length = maxcount; if (nfserr) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 48fe71d309cb..8beb2730929d 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, struct the_nilfs *nilfs = inode->i_sb->s_fs_info; err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn); - if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */ - brelse(bh); + if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */ goto failed; - } } lock_buffer(bh); @@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, failed: unlock_page(bh->b_page); put_page(bh->b_page); + if (unlikely(err)) + brelse(bh); return err; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index cfec5e0c7f66..5661a363005e 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1562,6 +1562,7 @@ load_root: put_inode_out: iput(inode); out: + ntfs3_put_sbi(sbi); kfree(boot2); return err; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index d1761ec5866a..ada3fcc9c6d5 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -337,7 +337,7 @@ static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry, { struct iattr attr = { .ia_valid = - ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index c8c8588bd98c..26b782c53910 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -188,7 +188,7 @@ static int ovl_check_encode_origin(struct dentry *dentry) /* Lower file handle for non-upper non-decodable */ if (!ovl_dentry_upper(dentry) && !decodable) - return 0; + return 1; /* Upper file handle for pure upper */ if (!ovl_dentry_lower(dentry)) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4193633c4c7a..8be4dc050d1e 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -341,7 +341,6 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (!aio_req) goto out; - real.flags = 0; aio_req->orig_iocb = iocb; kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_complete = ovl_aio_rw_complete; @@ -391,6 +390,12 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); + /* + * Overlayfs doesn't support deferred completions, don't copy + * this property in case it is set by the issuer. + */ + ifl &= ~IOCB_DIO_CALLER_COMP; + old_cred = ovl_override_creds(file_inode(file)->i_sb); if (is_sync_kiocb(iocb)) { file_start_write(real.file); @@ -407,7 +412,6 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (!aio_req) goto out; - real.flags = 0; aio_req->orig_iocb = iocb; kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_flags = ifl; diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index e9539f98e86a..d82d2a043da2 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -8,6 +8,7 @@ struct ovl_config { char *upperdir; char *workdir; + char **lowerdirs; bool default_permissions; int redirect_mode; int verity_mode; @@ -39,17 +40,8 @@ struct ovl_layer { int idx; /* One fsid per unique underlying sb (upper fsid == 0) */ int fsid; - char *name; }; -/* - * ovl_free_fs() relies on @mnt being the first member when unmounting - * the private mounts created for each layer. Let's check both the - * offset and type. - */ -static_assert(offsetof(struct ovl_layer, mnt) == 0); -static_assert(__same_type(typeof_member(struct ovl_layer, mnt), struct vfsmount *)); - struct ovl_path { const struct ovl_layer *layer; struct dentry *dentry; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index b9355bb6d75a..95b751507ac8 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -752,12 +752,12 @@ void ovl_free_fs(struct ovl_fs *ofs) if (ofs->upperdir_locked) ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root); - /* Hack! Reuse ofs->layers as a vfsmount array before freeing it */ - mounts = (struct vfsmount **) ofs->layers; + /* Reuse ofs->config.lowerdirs as a vfsmount array before freeing it */ + mounts = (struct vfsmount **) ofs->config.lowerdirs; for (i = 0; i < ofs->numlayer; i++) { iput(ofs->layers[i].trap); + kfree(ofs->config.lowerdirs[i]); mounts[i] = ofs->layers[i].mnt; - kfree(ofs->layers[i].name); } kern_unmount_array(mounts, ofs->numlayer); kfree(ofs->layers); @@ -765,6 +765,7 @@ void ovl_free_fs(struct ovl_fs *ofs) free_anon_bdev(ofs->fs[i].pseudo_dev); kfree(ofs->fs); + kfree(ofs->config.lowerdirs); kfree(ofs->config.upperdir); kfree(ofs->config.workdir); if (ofs->creator_cred) @@ -949,16 +950,16 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) struct super_block *sb = dentry->d_sb; struct ovl_fs *ofs = OVL_FS(sb); size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer; - const struct ovl_layer *data_layers = &ofs->layers[nr_merged_lower]; + char **lowerdatadirs = &ofs->config.lowerdirs[nr_merged_lower]; - /* ofs->layers[0] is the upper layer */ - seq_printf(m, ",lowerdir=%s", ofs->layers[1].name); + /* lowerdirs[] starts from offset 1 */ + seq_printf(m, ",lowerdir=%s", ofs->config.lowerdirs[1]); /* dump regular lower layers */ for (nr = 2; nr < nr_merged_lower; nr++) - seq_printf(m, ":%s", ofs->layers[nr].name); + seq_printf(m, ":%s", ofs->config.lowerdirs[nr]); /* dump data lower layers */ for (nr = 0; nr < ofs->numdatalayer; nr++) - seq_printf(m, "::%s", data_layers[nr].name); + seq_printf(m, "::%s", lowerdatadirs[nr]); if (ofs->config.upperdir) { seq_show_option(m, "upperdir", ofs->config.upperdir); seq_show_option(m, "workdir", ofs->config.workdir); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index def266b5e2a3..3fa2416264a4 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -104,8 +104,8 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak) static int ovl_dentry_revalidate_common(struct dentry *dentry, unsigned int flags, bool weak) { - struct ovl_entry *oe = OVL_E(dentry); - struct ovl_path *lowerstack = ovl_lowerstack(oe); + struct ovl_entry *oe; + struct ovl_path *lowerstack; struct inode *inode = d_inode_rcu(dentry); struct dentry *upper; unsigned int i; @@ -115,6 +115,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, if (!inode) return -ECHILD; + oe = OVL_I_E(inode); + lowerstack = ovl_lowerstack(oe); upper = ovl_i_dentry_upper(inode); if (upper) ret = ovl_revalidate_real(upper, flags, weak); @@ -167,6 +169,7 @@ static void ovl_free_inode(struct inode *inode) struct ovl_inode *oi = OVL_I(inode); kfree(oi->redirect); + kfree(oi->oe); mutex_destroy(&oi->lock); kmem_cache_free(ovl_inode_cachep, oi); } @@ -176,7 +179,7 @@ static void ovl_destroy_inode(struct inode *inode) struct ovl_inode *oi = OVL_I(inode); dput(oi->__upperdentry); - ovl_free_entry(oi->oe); + ovl_stack_put(ovl_lowerstack(oi->oe), ovl_numlower(oi->oe)); if (S_ISDIR(inode->i_mode)) ovl_dir_cache_free(inode); else @@ -569,11 +572,6 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs, upper_layer->idx = 0; upper_layer->fsid = 0; - err = -ENOMEM; - upper_layer->name = kstrdup(ofs->config.upperdir, GFP_KERNEL); - if (!upper_layer->name) - goto out; - /* * Inherit SB_NOSEC flag from upperdir. * @@ -1122,7 +1120,8 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, layers[ofs->numlayer].idx = ofs->numlayer; layers[ofs->numlayer].fsid = fsid; layers[ofs->numlayer].fs = &ofs->fs[fsid]; - layers[ofs->numlayer].name = l->name; + /* Store for printing lowerdir=... in ovl_show_options() */ + ofs->config.lowerdirs[ofs->numlayer] = l->name; l->name = NULL; ofs->numlayer++; ofs->fs[fsid].is_lower = true; @@ -1367,8 +1366,16 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) if (!layers) goto out_err; + ofs->config.lowerdirs = kcalloc(ctx->nr + 1, sizeof(char *), GFP_KERNEL); + if (!ofs->config.lowerdirs) { + kfree(layers); + goto out_err; + } ofs->layers = layers; - /* Layer 0 is reserved for upper even if there's no upper */ + /* + * Layer 0 is reserved for upper even if there's no upper. + * For consistency, config.lowerdirs[0] is NULL. + */ ofs->numlayer = 1; sb->s_stack_depth = 0; diff --git a/fs/pipe.c b/fs/pipe.c index 6c1a9b1db907..139190165a1c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -537,7 +537,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) break; } ret += copied; - buf->offset = 0; buf->len = copied; if (!iov_iter_count(from)) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 9dda7e54b2d0..9a8f32f21ff5 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -289,9 +289,7 @@ struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; -#ifdef CONFIG_MMU struct vma_iterator iter; -#endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a8ac0dd8041e..7cebd397cc26 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -175,15 +175,28 @@ static int show_map(struct seq_file *m, void *_p) return nommu_vma_show(m, _p); } -static void *m_start(struct seq_file *m, loff_t *pos) +static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, + loff_t *ppos) +{ + struct vm_area_struct *vma = vma_next(&priv->iter); + + if (vma) { + *ppos = vma->vm_start; + } else { + *ppos = -1UL; + } + + return vma; +} + +static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; + unsigned long last_addr = *ppos; struct mm_struct *mm; - struct vm_area_struct *vma; - unsigned long addr = *pos; - /* See m_next(). Zero at the start or after lseek. */ - if (addr == -1UL) + /* See proc_get_vma(). Zero at the start or after lseek. */ + if (last_addr == -1UL) return NULL; /* pin the task and mm whilst we play with them */ @@ -192,44 +205,41 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } - /* start the next element from addr */ - vma = find_vma(mm, addr); - if (vma) - return vma; + vma_iter_init(&priv->iter, mm, last_addr); - mmap_read_unlock(mm); - mmput(mm); - return NULL; + return proc_get_vma(priv, ppos); } -static void m_stop(struct seq_file *m, void *_vml) +static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(_vml)) { - mmap_read_unlock(priv->mm); - mmput(priv->mm); - } - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } -static void *m_next(struct seq_file *m, void *_p, loff_t *pos) +static void *m_next(struct seq_file *m, void *_p, loff_t *ppos) { - struct vm_area_struct *vma = _p; - - *pos = vma->vm_end; - return find_vma(vma->vm_mm, vma->vm_end); + return proc_get_vma(m->private, ppos); } static const struct seq_operations proc_pid_maps_ops = { diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index b81749492ef9..7d12b8c5b2fa 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -2699,7 +2699,7 @@ struct reiserfs_iget_args { #define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12) #define journal_trans_half(blocksize) \ - ((blocksize - sizeof (struct reiserfs_journal_desc) + sizeof (__u32) - 12) / sizeof (__u32)) + ((blocksize - sizeof(struct reiserfs_journal_desc) - 12) / sizeof(__u32)) /* journal.c see journal.c for all the comments here */ @@ -2711,7 +2711,7 @@ struct reiserfs_journal_desc { __le32 j_len; __le32 j_mount_id; /* mount id of this trans */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_desc_trans_id(d) le32_to_cpu((d)->j_trans_id) @@ -2726,7 +2726,7 @@ struct reiserfs_journal_desc { struct reiserfs_journal_commit { __le32 j_trans_id; /* must match j_trans_id from the desc block */ __le32 j_len; /* ditto */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_commit_trans_id(c) le32_to_cpu((c)->j_trans_id) diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index b17f067e4ada..e2be8aedb26e 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -452,6 +452,9 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) struct cached_fid *cfid, *q; LIST_HEAD(entry); + if (cfids == NULL) + return; + spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { list_move(&cfid->entry, &entry); @@ -651,6 +654,9 @@ void free_cached_dirs(struct cached_fids *cfids) struct cached_fid *cfid, *q; LIST_HEAD(entry); + if (cfids == NULL) + return; + if (cfids->laundromat) { kthread_stop(cfids->laundromat); cfids->laundromat = NULL; diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 032d8716f671..02082621d8e0 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1807,6 +1807,7 @@ static inline bool is_retryable_error(int error) #define MID_RETRY_NEEDED 8 /* session closed while this request out */ #define MID_RESPONSE_MALFORMED 0x10 #define MID_SHUTDOWN 0x20 +#define MID_RESPONSE_READY 0x40 /* ready for other process handle the rsp */ /* Flags */ #define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ @@ -1943,7 +1944,7 @@ require use of the stronger protocol */ * cifsInodeInfo->lock_sem cifsInodeInfo->llist cifs_init_once * ->can_cache_brlcks * cifsInodeInfo->deferred_lock cifsInodeInfo->deferred_closes cifsInodeInfo_alloc - * cached_fid->fid_mutex cifs_tcon->crfid tconInfoAlloc + * cached_fid->fid_mutex cifs_tcon->crfid tcon_info_alloc * cifsFileInfo->fh_mutex cifsFileInfo cifs_new_fileinfo * cifsFileInfo->file_info_lock cifsFileInfo->count cifs_new_fileinfo * ->invalidHandle initiate_cifs_search diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 7d8035846680..0c37eefa18a5 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -512,7 +512,7 @@ extern int CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses); extern struct cifs_ses *sesInfoAlloc(void); extern void sesInfoFree(struct cifs_ses *); -extern struct cifs_tcon *tconInfoAlloc(void); +extern struct cifs_tcon *tcon_info_alloc(bool dir_leases_enabled); extern void tconInfoFree(struct cifs_tcon *); extern int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server, diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 687754791bf0..3902e90dca6b 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1882,7 +1882,8 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) } } - tcon = tconInfoAlloc(); + /* no need to setup directory caching on IPC share, so pass in false */ + tcon = tcon_info_alloc(false); if (tcon == NULL) return -ENOMEM; @@ -2492,7 +2493,10 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) goto out_fail; } - tcon = tconInfoAlloc(); + if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) + tcon = tcon_info_alloc(true); + else + tcon = tcon_info_alloc(false); if (tcon == NULL) { rc = -ENOMEM; goto out_fail; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index e45ce31bbda7..a3493da12ad1 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1541,6 +1541,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_parse_mount_err: kfree_sensitive(ctx->password); + ctx->password = NULL; return -EINVAL; } diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 366b755ca913..35b176457bbe 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -113,18 +113,22 @@ sesInfoFree(struct cifs_ses *buf_to_free) } struct cifs_tcon * -tconInfoAlloc(void) +tcon_info_alloc(bool dir_leases_enabled) { struct cifs_tcon *ret_buf; ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL); if (!ret_buf) return NULL; - ret_buf->cfids = init_cached_dirs(); - if (!ret_buf->cfids) { - kfree(ret_buf); - return NULL; + + if (dir_leases_enabled == true) { + ret_buf->cfids = init_cached_dirs(); + if (!ret_buf->cfids) { + kfree(ret_buf); + return NULL; + } } + /* else ret_buf->cfids is already set to NULL above */ atomic_inc(&tconInfoAllocCount); ret_buf->status = TID_NEW; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index b41e2e872b22..0b89f7008ac0 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -539,6 +539,9 @@ static int parse_create_response(struct cifs_open_info_data *data, int rc = 0; switch (rsp->hdr.Status) { + case STATUS_IO_REPARSE_TAG_NOT_HANDLED: + reparse_point = true; + break; case STATUS_STOPPED_ON_SYMLINK: rc = smb2_parse_symlink_response(cifs_sb, iov, &data->symlink_target); diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index 194799ddd382..1a90dd78b238 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -877,8 +877,6 @@ static const struct status_to_posix_error smb2_error_map_table[] = { "STATUS_IO_REPARSE_TAG_MISMATCH"}, {STATUS_IO_REPARSE_DATA_INVALID, -EIO, "STATUS_IO_REPARSE_DATA_INVALID"}, - {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EIO, - "STATUS_IO_REPARSE_TAG_NOT_HANDLED"}, {STATUS_REPARSE_POINT_NOT_RESOLVED, -EIO, "STATUS_REPARSE_POINT_NOT_RESOLVED"}, {STATUS_DIRECTORY_IS_A_REPARSE_POINT, -EIO, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 44d4943e9c56..c75a80bb6d9e 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -848,7 +848,7 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) iov[num].iov_base = create_posix_buf(mode); if (mode == ACL_NO_MODE) - cifs_dbg(FYI, "Invalid mode\n"); + cifs_dbg(FYI, "%s: no mode\n", __func__); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_posix); @@ -3878,7 +3878,7 @@ void smb2_reconnect_server(struct work_struct *work) goto done; /* allocate a dummy tcon struct used for reconnect */ - tcon = tconInfoAlloc(); + tcon = tcon_info_alloc(false); if (!tcon) { resched = true; list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) { diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 2a2aec8c6112..94df9eec3d8d 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1401,10 +1401,13 @@ create_conn: server->smbd_conn = smbd_get_connection( server, (struct sockaddr *) &server->dstaddr); - if (server->smbd_conn) + if (server->smbd_conn) { cifs_dbg(VFS, "RDMA transport re-established\n"); - - return server->smbd_conn ? 0 : -ENOENT; + trace_smb3_smbd_connect_done(server->hostname, server->conn_id, &server->dstaddr); + return 0; + } + trace_smb3_smbd_connect_err(server->hostname, server->conn_id, &server->dstaddr); + return -ENOENT; } static void destroy_caches_and_workqueue(struct smbd_connection *info) diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index a7e4755bed0f..de199ec9f726 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -935,6 +935,8 @@ DEFINE_EVENT(smb3_connect_class, smb3_##name, \ TP_ARGS(hostname, conn_id, addr)) DEFINE_SMB3_CONNECT_EVENT(connect_done); +DEFINE_SMB3_CONNECT_EVENT(smbd_connect_done); +DEFINE_SMB3_CONNECT_EVENT(smbd_connect_err); DECLARE_EVENT_CLASS(smb3_connect_err_class, TP_PROTO(char *hostname, __u64 conn_id, diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index d52057a511ee..14710afdc2a3 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -35,6 +35,8 @@ void cifs_wake_up_task(struct mid_q_entry *mid) { + if (mid->mid_state == MID_RESPONSE_RECEIVED) + mid->mid_state = MID_RESPONSE_READY; wake_up_process(mid->callback_data); } @@ -87,7 +89,8 @@ static void __release_mid(struct kref *refcount) struct TCP_Server_Info *server = midEntry->server; if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) && - midEntry->mid_state == MID_RESPONSE_RECEIVED && + (midEntry->mid_state == MID_RESPONSE_RECEIVED || + midEntry->mid_state == MID_RESPONSE_READY) && server->ops->handle_cancelled_mid) server->ops->handle_cancelled_mid(midEntry, server); @@ -737,7 +740,8 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ) int error; error = wait_event_state(server->response_q, - midQ->mid_state != MID_REQUEST_SUBMITTED, + midQ->mid_state != MID_REQUEST_SUBMITTED && + midQ->mid_state != MID_RESPONSE_RECEIVED, (TASK_KILLABLE|TASK_FREEZABLE_UNSAFE)); if (error < 0) return -ERESTARTSYS; @@ -890,7 +894,7 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) spin_lock(&server->mid_lock); switch (mid->mid_state) { - case MID_RESPONSE_RECEIVED: + case MID_RESPONSE_READY: spin_unlock(&server->mid_lock); return rc; case MID_RETRY_NEEDED: @@ -989,6 +993,9 @@ cifs_compound_callback(struct mid_q_entry *mid) credits.instance = server->reconnect_instance; add_credits(server, &credits, mid->optype); + + if (mid->mid_state == MID_RESPONSE_RECEIVED) + mid->mid_state = MID_RESPONSE_READY; } static void @@ -1209,7 +1216,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, send_cancel(server, &rqst[i], midQ[i]); spin_lock(&server->mid_lock); midQ[i]->mid_flags |= MID_WAIT_CANCELLED; - if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED || + midQ[i]->mid_state == MID_RESPONSE_RECEIVED) { midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; @@ -1230,7 +1238,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, } if (!midQ[i]->resp_buf || - midQ[i]->mid_state != MID_RESPONSE_RECEIVED) { + midQ[i]->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_dbg(FYI, "Bad MID state?\n"); goto out; @@ -1417,7 +1425,8 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, if (rc != 0) { send_cancel(server, &rqst, midQ); spin_lock(&server->mid_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; spin_unlock(&server->mid_lock); @@ -1434,7 +1443,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, } if (!midQ->resp_buf || !out_buf || - midQ->mid_state != MID_RESPONSE_RECEIVED) { + midQ->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_server_dbg(VFS, "Bad MID state?\n"); goto out; @@ -1558,14 +1567,16 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, /* Wait for a reply - allow signals to interrupt. */ rc = wait_event_interruptible(server->response_q, - (!(midQ->mid_state == MID_REQUEST_SUBMITTED)) || + (!(midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED)) || ((server->tcpStatus != CifsGood) && (server->tcpStatus != CifsNew))); /* Were we interrupted by a signal ? */ spin_lock(&server->srv_lock); if ((rc == -ERESTARTSYS) && - (midQ->mid_state == MID_REQUEST_SUBMITTED) && + (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) && ((server->tcpStatus == CifsGood) || (server->tcpStatus == CifsNew))) { spin_unlock(&server->srv_lock); @@ -1596,7 +1607,8 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, if (rc) { send_cancel(server, &rqst, midQ); spin_lock(&server->mid_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; spin_unlock(&server->mid_lock); @@ -1616,7 +1628,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, return rc; /* rcvd frame is ok */ - if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_RECEIVED) { + if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_tcon_dbg(VFS, "Bad MID state?\n"); goto out; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 0d990c2f33cd..db7fa704a3f6 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -197,6 +197,9 @@ int ksmbd_conn_write(struct ksmbd_work *work) if (work->send_no_response) return 0; + if (!work->iov_idx) + return -EINVAL; + ksmbd_conn_lock(conn); sent = conn->transport->ops->writev(conn->transport, work->iov, work->iov_cnt, diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 5ab2f52f9b35..32347fec33c4 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -115,8 +115,10 @@ static int __process_request(struct ksmbd_work *work, struct ksmbd_conn *conn, if (check_conn_state(work)) return SERVER_HANDLER_CONTINUE; - if (ksmbd_verify_smb_message(work)) + if (ksmbd_verify_smb_message(work)) { + conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); return SERVER_HANDLER_ABORT; + } command = conn->ops->get_cmd_val(work); *cmd = command; diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index e881df1d10cb..23bd3d1209df 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -440,10 +440,8 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) validate_credit: if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && - smb2_validate_credit_charge(work->conn, hdr)) { - work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); + smb2_validate_credit_charge(work->conn, hdr)) return 1; - } return 0; } diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 9f64e7332796..8c8d64e76103 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -70,6 +70,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); static int dcache_dir_open_wrapper(struct inode *inode, struct file *file); +static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx); static int eventfs_release(struct inode *inode, struct file *file); static const struct inode_operations eventfs_root_dir_inode_operations = { @@ -79,7 +80,7 @@ static const struct inode_operations eventfs_root_dir_inode_operations = { static const struct file_operations eventfs_file_operations = { .open = dcache_dir_open_wrapper, .read = generic_read_dir, - .iterate_shared = dcache_readdir, + .iterate_shared = dcache_readdir_wrapper, .llseek = generic_file_llseek, .release = eventfs_release, }; @@ -396,6 +397,11 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, return ret; } +struct dentry_list { + void *cursor; + struct dentry **dentries; +}; + /** * eventfs_release - called to release eventfs file/dir * @inode: inode to be released @@ -404,26 +410,25 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, static int eventfs_release(struct inode *inode, struct file *file) { struct tracefs_inode *ti; - struct eventfs_inode *ei; - struct eventfs_file *ef; - struct dentry *dentry; - int idx; + struct dentry_list *dlist = file->private_data; + void *cursor; + int i; ti = get_tracefs(inode); if (!(ti->flags & TRACEFS_EVENT_INODE)) return -EINVAL; - ei = ti->private; - idx = srcu_read_lock(&eventfs_srcu); - list_for_each_entry_srcu(ef, &ei->e_top_files, list, - srcu_read_lock_held(&eventfs_srcu)) { - mutex_lock(&eventfs_mutex); - dentry = ef->dentry; - mutex_unlock(&eventfs_mutex); - if (dentry) - dput(dentry); + if (WARN_ON_ONCE(!dlist)) + return -EINVAL; + + for (i = 0; dlist->dentries && dlist->dentries[i]; i++) { + dput(dlist->dentries[i]); } - srcu_read_unlock(&eventfs_srcu, idx); + + cursor = dlist->cursor; + kfree(dlist->dentries); + kfree(dlist); + file->private_data = cursor; return dcache_dir_close(inode, file); } @@ -442,22 +447,70 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file) struct tracefs_inode *ti; struct eventfs_inode *ei; struct eventfs_file *ef; + struct dentry_list *dlist; + struct dentry **dentries = NULL; struct dentry *dentry = file_dentry(file); + struct dentry *d; struct inode *f_inode = file_inode(file); + int cnt = 0; int idx; + int ret; ti = get_tracefs(f_inode); if (!(ti->flags & TRACEFS_EVENT_INODE)) return -EINVAL; + if (WARN_ON_ONCE(file->private_data)) + return -EINVAL; + + dlist = kmalloc(sizeof(*dlist), GFP_KERNEL); + if (!dlist) + return -ENOMEM; + ei = ti->private; idx = srcu_read_lock(&eventfs_srcu); list_for_each_entry_srcu(ef, &ei->e_top_files, list, srcu_read_lock_held(&eventfs_srcu)) { - create_dentry(ef, dentry, false); + d = create_dentry(ef, dentry, false); + if (d) { + struct dentry **tmp; + + tmp = krealloc(dentries, sizeof(d) * (cnt + 2), GFP_KERNEL); + if (!tmp) + break; + tmp[cnt] = d; + tmp[cnt + 1] = NULL; + cnt++; + dentries = tmp; + } } srcu_read_unlock(&eventfs_srcu, idx); - return dcache_dir_open(inode, file); + ret = dcache_dir_open(inode, file); + + /* + * dcache_dir_open() sets file->private_data to a dentry cursor. + * Need to save that but also save all the dentries that were + * opened by this function. + */ + dlist->cursor = file->private_data; + dlist->dentries = dentries; + file->private_data = dlist; + return ret; +} + +/* + * This just sets the file->private_data back to the cursor and back. + */ +static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx) +{ + struct dentry_list *dlist = file->private_data; + int ret; + + file->private_data = dlist->cursor; + ret = dcache_readdir(file, ctx); + dlist->cursor = file->private_data; + file->private_data = dlist; + return ret; } /** diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index c9d653168ad0..ed0bc8cbc703 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS bool "XFS online metadata check usage data collection" default y depends on XFS_ONLINE_SCRUB - select FS_DEBUG + select XFS_DEBUG help If you say Y here, the kernel will gather usage data about the online metadata check subsystem. This includes the number diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 2420865f3007..a5100a11faf9 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -131,4 +131,26 @@ void xlog_check_buf_cancel_table(struct xlog *log); #define xlog_check_buf_cancel_table(log) do { } while (0) #endif +/* + * Transform a regular reservation into one suitable for recovery of a log + * intent item. + * + * Intent recovery only runs a single step of the transaction chain and defers + * the rest to a separate transaction. Therefore, we reduce logcount to 1 here + * to avoid livelocks if the log grant space is nearly exhausted due to the + * recovered intent pinning the tail. Keep the same logflags to avoid tripping + * asserts elsewhere. Struct copies abound below. + */ +static inline struct xfs_trans_res +xlog_recover_resv(const struct xfs_trans_res *r) +{ + struct xfs_trans_res ret = { + .tr_logres = r->tr_logres, + .tr_logcount = 1, + .tr_logflags = r->tr_logflags, + }; + + return ret; +} + #endif /* __XFS_LOG_RECOVER_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 5e174685a77c..6264daaab37b 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -266,7 +266,8 @@ xfs_validate_sb_write( return -EFSCORRUPTED; } - if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { + if (!xfs_is_readonly(mp) && + xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 7d3aa14d81b5..4849efcaa33a 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -588,6 +588,8 @@ out_nofix: out_teardown: error = xchk_teardown(sc, error); out_sc: + if (error != -ENOENT) + xchk_stats_merge(mp, sm, &run); kfree(sc); out: trace_xchk_done(XFS_I(file_inode(file)), sm, error); @@ -595,8 +597,6 @@ out: sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; error = 0; } - if (error != -ENOENT) - xchk_stats_merge(mp, sm, &run); return error; need_drain: error = xchk_teardown(sc, 0); diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index aeb92624176b..cd91db4a5548 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -185,7 +185,10 @@ xchk_stats_merge_one( { struct xchk_scrub_stats *css; - ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); + if (sm->sm_type >= XFS_SCRUB_TYPE_NR) { + ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); + return; + } css = &cs->cs_stats[sm->sm_type]; spin_lock(&css->css_lock); diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 5db87b34fb6e..89c7a9f4f930 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -333,7 +333,6 @@ xfs_attr_inactive( int error = 0; mp = dp->i_mount; - ASSERT(! XFS_NOT_DQATTACHED(mp, dp)); xfs_ilock(dp, lock_mode); if (!xfs_inode_has_attr_fork(dp)) diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index 2788a6f2edcd..36fe2abb16e6 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -547,7 +547,7 @@ xfs_attri_item_recover( struct xfs_inode *ip; struct xfs_da_args *args; struct xfs_trans *tp; - struct xfs_trans_res tres; + struct xfs_trans_res resv; struct xfs_attri_log_format *attrp; struct xfs_attri_log_nameval *nv = attrip->attri_nameval; int error; @@ -618,8 +618,9 @@ xfs_attri_item_recover( goto out; } - xfs_init_attr_trans(args, &tres, &total); - error = xfs_trans_alloc(mp, &tres, total, 0, XFS_TRANS_RESERVE, &tp); + xfs_init_attr_trans(args, &resv, &total); + resv = xlog_recover_resv(&resv); + error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp); if (error) goto out; diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 7551c3ec4ea5..e736a0844c89 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -490,6 +490,7 @@ xfs_bui_item_recover( struct list_head *capture_list) { struct xfs_bmap_intent fake = { }; + struct xfs_trans_res resv; struct xfs_bui_log_item *buip = BUI_ITEM(lip); struct xfs_trans *tp; struct xfs_inode *ip = NULL; @@ -515,7 +516,8 @@ xfs_bui_item_recover( return error; /* Allocate transaction and do the work. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp); if (error) goto err_rele; diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index 1064c2342876..7cd09c3a82cb 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -146,6 +146,20 @@ xfs_nfs_get_inode( return ERR_PTR(error); } + /* + * Reload the incore unlinked list to avoid failure in inodegc. + * Use an unlocked check here because unrecovered unlinked inodes + * should be somewhat rare. + */ + if (xfs_inode_unlinked_incomplete(ip)) { + error = xfs_inode_reload_unlinked(ip); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + xfs_irele(ip); + return ERR_PTR(error); + } + } + if (VFS_I(ip)->i_generation != generation) { xfs_irele(ip); return ERR_PTR(-ESTALE); diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index f1a5ecf099aa..3fa8789820ad 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -660,6 +660,7 @@ xfs_efi_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_efi_log_item *efip = EFI_ITEM(lip); struct xfs_mount *mp = lip->li_log->l_mp; struct xfs_efd_log_item *efdp; @@ -683,7 +684,8 @@ xfs_efi_item_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp); if (error) return error; efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents); diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 10403ba9b58f..736e5545f584 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -565,6 +565,19 @@ err: } #endif /* CONFIG_XFS_RT */ +static inline bool +rmap_not_shareable(struct xfs_mount *mp, const struct xfs_rmap_irec *r) +{ + if (!xfs_has_reflink(mp)) + return true; + if (XFS_RMAP_NON_INODE_OWNER(r->rm_owner)) + return true; + if (r->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK | + XFS_RMAP_UNWRITTEN)) + return true; + return false; +} + /* Execute a getfsmap query against the regular data device. */ STATIC int __xfs_getfsmap_datadev( @@ -598,7 +611,6 @@ __xfs_getfsmap_datadev( * low to the fsmap low key and max out the high key to the end * of the AG. */ - info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb); info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); if (error) @@ -608,12 +620,9 @@ __xfs_getfsmap_datadev( /* Adjust the low key if we are continuing from where we left off. */ if (info->low.rm_blockcount == 0) { - /* empty */ - } else if (XFS_RMAP_NON_INODE_OWNER(info->low.rm_owner) || - (info->low.rm_flags & (XFS_RMAP_ATTR_FORK | - XFS_RMAP_BMBT_BLOCK | - XFS_RMAP_UNWRITTEN))) { - info->low.rm_startblock += info->low.rm_blockcount; + /* No previous record from which to continue */ + } else if (rmap_not_shareable(mp, &info->low)) { + /* Last record seen was an unshareable extent */ info->low.rm_owner = 0; info->low.rm_offset = 0; @@ -621,8 +630,10 @@ __xfs_getfsmap_datadev( if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs) return 0; } else { + /* Last record seen was a shareable file data extent */ info->low.rm_offset += info->low.rm_blockcount; } + info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb); info->high.rm_startblock = -1U; info->high.rm_owner = ULLONG_MAX; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e541f5c0bc25..3c210ac83713 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -113,7 +113,7 @@ xfs_inode_alloc( INIT_LIST_HEAD(&ip->i_ioend_list); spin_lock_init(&ip->i_ioend_lock); ip->i_next_unlinked = NULLAGINO; - ip->i_prev_unlinked = NULLAGINO; + ip->i_prev_unlinked = 0; return ip; } @@ -443,7 +443,7 @@ xfs_inodegc_queue_all( int cpu; bool ret = false; - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); @@ -463,7 +463,7 @@ xfs_inodegc_wait_all( int error = 0; flush_workqueue(mp->m_inodegc_wq); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { struct xfs_inodegc *gc; gc = per_cpu_ptr(mp->m_inodegc, cpu); @@ -1845,9 +1845,17 @@ xfs_inodegc_worker( struct xfs_inodegc, work); struct llist_node *node = llist_del_all(&gc->list); struct xfs_inode *ip, *n; + struct xfs_mount *mp = gc->mp; unsigned int nofs_flag; - ASSERT(gc->cpu == smp_processor_id()); + /* + * Clear the cpu mask bit and ensure that we have seen the latest + * update of the gc structure associated with this CPU. This matches + * with the release semantics used when setting the cpumask bit in + * xfs_inodegc_queue. + */ + cpumask_clear_cpu(gc->cpu, &mp->m_inodegc_cpumask); + smp_mb__after_atomic(); WRITE_ONCE(gc->items, 0); @@ -1862,7 +1870,7 @@ xfs_inodegc_worker( nofs_flag = memalloc_nofs_save(); ip = llist_entry(node, struct xfs_inode, i_gclist); - trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits)); + trace_xfs_inodegc_worker(mp, READ_ONCE(gc->shrinker_hits)); WRITE_ONCE(gc->shrinker_hits, 0); llist_for_each_entry_safe(ip, n, node, i_gclist) { @@ -2057,6 +2065,7 @@ xfs_inodegc_queue( struct xfs_inodegc *gc; int items; unsigned int shrinker_hits; + unsigned int cpu_nr; unsigned long queue_delay = 1; trace_xfs_inode_set_need_inactive(ip); @@ -2064,18 +2073,28 @@ xfs_inodegc_queue( ip->i_flags |= XFS_NEED_INACTIVE; spin_unlock(&ip->i_flags_lock); - gc = get_cpu_ptr(mp->m_inodegc); + cpu_nr = get_cpu(); + gc = this_cpu_ptr(mp->m_inodegc); llist_add(&ip->i_gclist, &gc->list); items = READ_ONCE(gc->items); WRITE_ONCE(gc->items, items + 1); shrinker_hits = READ_ONCE(gc->shrinker_hits); /* + * Ensure the list add is always seen by anyone who finds the cpumask + * bit set. This effectively gives the cpumask bit set operation + * release ordering semantics. + */ + smp_mb__before_atomic(); + if (!cpumask_test_cpu(cpu_nr, &mp->m_inodegc_cpumask)) + cpumask_test_and_set_cpu(cpu_nr, &mp->m_inodegc_cpumask); + + /* * We queue the work while holding the current CPU so that the work * is scheduled to run on this CPU. */ if (!xfs_is_inodegc_enabled(mp)) { - put_cpu_ptr(gc); + put_cpu(); return; } @@ -2085,7 +2104,7 @@ xfs_inodegc_queue( trace_xfs_inodegc_queue(mp, __return_address); mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, queue_delay); - put_cpu_ptr(gc); + put_cpu(); if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) { trace_xfs_inodegc_throttle(mp, __return_address); @@ -2094,47 +2113,6 @@ xfs_inodegc_queue( } /* - * Fold the dead CPU inodegc queue into the current CPUs queue. - */ -void -xfs_inodegc_cpu_dead( - struct xfs_mount *mp, - unsigned int dead_cpu) -{ - struct xfs_inodegc *dead_gc, *gc; - struct llist_node *first, *last; - unsigned int count = 0; - - dead_gc = per_cpu_ptr(mp->m_inodegc, dead_cpu); - cancel_delayed_work_sync(&dead_gc->work); - - if (llist_empty(&dead_gc->list)) - return; - - first = dead_gc->list.first; - last = first; - while (last->next) { - last = last->next; - count++; - } - dead_gc->list.first = NULL; - dead_gc->items = 0; - - /* Add pending work to current CPU */ - gc = get_cpu_ptr(mp->m_inodegc); - llist_add_batch(first, last, &gc->list); - count += READ_ONCE(gc->items); - WRITE_ONCE(gc->items, count); - - if (xfs_is_inodegc_enabled(mp)) { - trace_xfs_inodegc_queue(mp, __return_address); - mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, - 0); - } - put_cpu_ptr(gc); -} - -/* * We set the inode flag atomically with the radix tree tag. Once we get tag * lookups on the radix tree, this inode flag can go away. * @@ -2195,7 +2173,7 @@ xfs_inodegc_shrinker_count( if (!xfs_is_inodegc_enabled(mp)) return 0; - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) return XFS_INODEGC_SHRINKER_COUNT; @@ -2220,7 +2198,7 @@ xfs_inodegc_shrinker_scan( trace_xfs_inodegc_shrinker_scan(mp, sc, __return_address); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { unsigned int h = READ_ONCE(gc->shrinker_hits); diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 2fa6f2e09d07..905944dafbe5 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -79,7 +79,6 @@ void xfs_inodegc_push(struct xfs_mount *mp); int xfs_inodegc_flush(struct xfs_mount *mp); void xfs_inodegc_stop(struct xfs_mount *mp); void xfs_inodegc_start(struct xfs_mount *mp); -void xfs_inodegc_cpu_dead(struct xfs_mount *mp, unsigned int cpu); int xfs_inodegc_register_shrinker(struct xfs_mount *mp); #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 360fe83a334f..4d55f58d99b7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1642,8 +1642,11 @@ xfs_inode_needs_inactive( if (VFS_I(ip)->i_mode == 0) return false; - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) return false; /* If the log isn't running, push inodes straight to reclaim. */ @@ -1703,8 +1706,11 @@ xfs_inactive( mp = ip->i_mount; ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY)); - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) goto out; /* Metadata inodes require explicit resource cleanup. */ @@ -1736,9 +1742,21 @@ xfs_inactive( ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0)) truncate = 1; - error = xfs_qm_dqattach(ip); - if (error) - goto out; + if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { + /* + * If this inode is being inactivated during a quotacheck and + * has not yet been scanned by quotacheck, we /must/ remove + * the dquots from the inode before inactivation changes the + * block and inode counts. Most probably this is a result of + * reloading the incore iunlinked list to purge unrecovered + * unlinked inodes. + */ + xfs_qm_dqdetach(ip); + } else { + error = xfs_qm_dqattach(ip); + if (error) + goto out; + } if (S_ISLNK(VFS_I(ip)->i_mode)) error = xfs_inactive_symlink(ip); @@ -1822,12 +1840,17 @@ xfs_iunlink_lookup( rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, agino); + if (!ip) { + /* Caller can handle inode not being in memory. */ + rcu_read_unlock(); + return NULL; + } /* - * Inode not in memory or in RCU freeing limbo should not happen. - * Warn about this and let the caller handle the failure. + * Inode in RCU freeing limbo should not happen. Warn about this and + * let the caller handle the failure. */ - if (WARN_ON_ONCE(!ip || !ip->i_ino)) { + if (WARN_ON_ONCE(!ip->i_ino)) { rcu_read_unlock(); return NULL; } @@ -1836,7 +1859,10 @@ xfs_iunlink_lookup( return ip; } -/* Update the prev pointer of the next agino. */ +/* + * Update the prev pointer of the next agino. Returns -ENOLINK if the inode + * is not in cache. + */ static int xfs_iunlink_update_backref( struct xfs_perag *pag, @@ -1851,7 +1877,8 @@ xfs_iunlink_update_backref( ip = xfs_iunlink_lookup(pag, next_agino); if (!ip) - return -EFSCORRUPTED; + return -ENOLINK; + ip->i_prev_unlinked = prev_agino; return 0; } @@ -1895,6 +1922,64 @@ xfs_iunlink_update_bucket( return 0; } +/* + * Load the inode @next_agino into the cache and set its prev_unlinked pointer + * to @prev_agino. Caller must hold the AGI to synchronize with other changes + * to the unlinked list. + */ +STATIC int +xfs_iunlink_reload_next( + struct xfs_trans *tp, + struct xfs_buf *agibp, + xfs_agino_t prev_agino, + xfs_agino_t next_agino) +{ + struct xfs_perag *pag = agibp->b_pag; + struct xfs_mount *mp = pag->pag_mount; + struct xfs_inode *next_ip = NULL; + xfs_ino_t ino; + int error; + + ASSERT(next_agino != NULLAGINO); + +#ifdef DEBUG + rcu_read_lock(); + next_ip = radix_tree_lookup(&pag->pag_ici_root, next_agino); + ASSERT(next_ip == NULL); + rcu_read_unlock(); +#endif + + xfs_info_ratelimited(mp, + "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating recovery.", + next_agino, pag->pag_agno); + + /* + * Use an untrusted lookup just to be cautious in case the AGI has been + * corrupted and now points at a free inode. That shouldn't happen, + * but we'd rather shut down now since we're already running in a weird + * situation. + */ + ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino); + error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip); + if (error) + return error; + + /* If this is not an unlinked inode, something is very wrong. */ + if (VFS_I(next_ip)->i_nlink != 0) { + error = -EFSCORRUPTED; + goto rele; + } + + next_ip->i_prev_unlinked = prev_agino; + trace_xfs_iunlink_reload_next(next_ip); +rele: + ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE)); + if (xfs_is_quotacheck_running(mp) && next_ip) + xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED); + xfs_irele(next_ip); + return error; +} + static int xfs_iunlink_insert_inode( struct xfs_trans *tp, @@ -1926,6 +2011,8 @@ xfs_iunlink_insert_inode( * inode. */ error = xfs_iunlink_update_backref(pag, agino, next_agino); + if (error == -ENOLINK) + error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino); if (error) return error; @@ -1941,6 +2028,7 @@ xfs_iunlink_insert_inode( } /* Point the head of the list to point to this inode. */ + ip->i_prev_unlinked = NULLAGINO; return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); } @@ -2020,6 +2108,9 @@ xfs_iunlink_remove_inode( */ error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked, ip->i_next_unlinked); + if (error == -ENOLINK) + error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked, + ip->i_next_unlinked); if (error) return error; @@ -2040,7 +2131,7 @@ xfs_iunlink_remove_inode( } ip->i_next_unlinked = NULLAGINO; - ip->i_prev_unlinked = NULLAGINO; + ip->i_prev_unlinked = 0; return error; } @@ -3529,3 +3620,117 @@ xfs_iunlock2_io_mmap( if (ip1 != ip2) inode_unlock(VFS_I(ip1)); } + +/* + * Reload the incore inode list for this inode. Caller should ensure that + * the link count cannot change, either by taking ILOCK_SHARED or otherwise + * preventing other threads from executing. + */ +int +xfs_inode_reload_unlinked_bucket( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_buf *agibp; + struct xfs_agi *agi; + struct xfs_perag *pag; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino); + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + xfs_agino_t prev_agino, next_agino; + unsigned int bucket; + bool foundit = false; + int error; + + /* Grab the first inode in the list */ + pag = xfs_perag_get(mp, agno); + error = xfs_ialloc_read_agi(pag, tp, &agibp); + xfs_perag_put(pag); + if (error) + return error; + + /* + * We've taken ILOCK_SHARED and the AGI buffer lock to stabilize the + * incore unlinked list pointers for this inode. Check once more to + * see if we raced with anyone else to reload the unlinked list. + */ + if (!xfs_inode_unlinked_incomplete(ip)) { + foundit = true; + goto out_agibp; + } + + bucket = agino % XFS_AGI_UNLINKED_BUCKETS; + agi = agibp->b_addr; + + trace_xfs_inode_reload_unlinked_bucket(ip); + + xfs_info_ratelimited(mp, + "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating list recovery.", + agino, agno); + + prev_agino = NULLAGINO; + next_agino = be32_to_cpu(agi->agi_unlinked[bucket]); + while (next_agino != NULLAGINO) { + struct xfs_inode *next_ip = NULL; + + /* Found this caller's inode, set its backlink. */ + if (next_agino == agino) { + next_ip = ip; + next_ip->i_prev_unlinked = prev_agino; + foundit = true; + goto next_inode; + } + + /* Try in-memory lookup first. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); + if (next_ip) + goto next_inode; + + /* Inode not in memory, try reloading it. */ + error = xfs_iunlink_reload_next(tp, agibp, prev_agino, + next_agino); + if (error) + break; + + /* Grab the reloaded inode. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); + if (!next_ip) { + /* No incore inode at all? We reloaded it... */ + ASSERT(next_ip != NULL); + error = -EFSCORRUPTED; + break; + } + +next_inode: + prev_agino = next_agino; + next_agino = next_ip->i_next_unlinked; + } + +out_agibp: + xfs_trans_brelse(tp, agibp); + /* Should have found this inode somewhere in the iunlinked bucket. */ + if (!error && !foundit) + error = -EFSCORRUPTED; + return error; +} + +/* Decide if this inode is missing its unlinked list and reload it. */ +int +xfs_inode_reload_unlinked( + struct xfs_inode *ip) +{ + struct xfs_trans *tp; + int error; + + error = xfs_trans_alloc_empty(ip->i_mount, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + if (xfs_inode_unlinked_incomplete(ip)) + error = xfs_inode_reload_unlinked_bucket(tp, ip); + xfs_iunlock(ip, XFS_ILOCK_SHARED); + xfs_trans_cancel(tp); + + return error; +} diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 7547caf2f2ab..0c5bdb91152e 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -68,8 +68,21 @@ typedef struct xfs_inode { uint64_t i_diflags2; /* XFS_DIFLAG2_... */ struct timespec64 i_crtime; /* time created */ - /* unlinked list pointers */ + /* + * Unlinked list pointers. These point to the next and previous inodes + * in the AGI unlinked bucket list, respectively. These fields can + * only be updated with the AGI locked. + * + * i_next_unlinked caches di_next_unlinked. + */ xfs_agino_t i_next_unlinked; + + /* + * If the inode is not on an unlinked list, this field is zero. If the + * inode is the first element in an unlinked list, this field is + * NULLAGINO. Otherwise, i_prev_unlinked points to the previous inode + * in the unlinked list. + */ xfs_agino_t i_prev_unlinked; /* VFS inode */ @@ -81,6 +94,11 @@ typedef struct xfs_inode { struct list_head i_ioend_list; } xfs_inode_t; +static inline bool xfs_inode_on_unlinked_list(const struct xfs_inode *ip) +{ + return ip->i_prev_unlinked != 0; +} + static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip) { return ip->i_forkoff > 0; @@ -326,6 +344,9 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip) */ #define XFS_INACTIVATING (1 << 13) +/* Quotacheck is running but inode has not been added to quota counts. */ +#define XFS_IQUOTAUNCHECKED (1 << 14) + /* All inode state flags related to inode reclaim. */ #define XFS_ALL_IRECLAIM_FLAGS (XFS_IRECLAIMABLE | \ XFS_IRECLAIM | \ @@ -340,7 +361,7 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip) #define XFS_IRECLAIM_RESET_FLAGS \ (XFS_IRECLAIMABLE | XFS_IRECLAIM | \ XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | XFS_NEED_INACTIVE | \ - XFS_INACTIVATING) + XFS_INACTIVATING | XFS_IQUOTAUNCHECKED) /* * Flags for inode locking. @@ -575,4 +596,13 @@ void xfs_end_io(struct work_struct *work); int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); +static inline bool +xfs_inode_unlinked_incomplete( + struct xfs_inode *ip) +{ + return VFS_I(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip); +} +int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip); +int xfs_inode_reload_unlinked(struct xfs_inode *ip); + #endif /* __XFS_INODE_H__ */ diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index c2093cb56092..f5377ba5967a 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -80,6 +80,17 @@ xfs_bulkstat_one_int( if (error) goto out; + /* Reload the incore unlinked list to avoid failure in inodegc. */ + if (xfs_inode_unlinked_incomplete(ip)) { + error = xfs_inode_reload_unlinked_bucket(tp, ip); + if (error) { + xfs_iunlock(ip, XFS_ILOCK_SHARED); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + xfs_irele(ip); + return error; + } + } + ASSERT(ip != NULL); ASSERT(ip->i_imap.im_blkno != 0); inode = VFS_I(ip); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 79004d193e54..51c100c86177 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -715,15 +715,7 @@ xfs_log_mount( * just worked. */ if (!xfs_has_norecovery(mp)) { - /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - bool readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, - &mp->m_opstate); error = xlog_recover(log); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); if (error) { xfs_warn(mp, "log mount/recovery failed: error %d", error); @@ -772,7 +764,6 @@ xfs_log_mount_finish( struct xfs_mount *mp) { struct xlog *log = mp->m_log; - bool readonly; int error = 0; if (xfs_has_norecovery(mp)) { @@ -781,12 +772,6 @@ xfs_log_mount_finish( } /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); - - /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. * xfs_fs_drop_inode needs to be able to prevent the deletion @@ -835,8 +820,6 @@ xfs_log_mount_finish( xfs_buftarg_drain(mp->m_ddev_targp); clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); /* Make sure the log is dead if we're returning failure. */ ASSERT(!error || xlog_is_shutdown(log)); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index eccbfb99e894..ebc70aaa299c 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -124,7 +124,7 @@ xlog_cil_push_pcp_aggregate( struct xlog_cil_pcp *cilpcp; int cpu; - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &ctx->cil_pcpmask) { cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); ctx->ticket->t_curr_res += cilpcp->space_reserved; @@ -165,7 +165,13 @@ xlog_cil_insert_pcp_aggregate( if (!test_and_clear_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) return; - for_each_online_cpu(cpu) { + /* + * We can race with other cpus setting cil_pcpmask. However, we've + * atomically cleared PCP_SPACE which forces other threads to add to + * the global space used count. cil_pcpmask is a superset of cilpcp + * structures that could have a nonzero space_used. + */ + for_each_cpu(cpu, &ctx->cil_pcpmask) { int old, prev; cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); @@ -554,6 +560,7 @@ xlog_cil_insert_items( int iovhdr_res = 0, split_res = 0, ctx_res = 0; int space_used; int order; + unsigned int cpu_nr; struct xlog_cil_pcp *cilpcp; ASSERT(tp); @@ -577,7 +584,12 @@ xlog_cil_insert_items( * can't be scheduled away between split sample/update operations that * are done without outside locking to serialise them. */ - cilpcp = get_cpu_ptr(cil->xc_pcp); + cpu_nr = get_cpu(); + cilpcp = this_cpu_ptr(cil->xc_pcp); + + /* Tell the future push that there was work added by this CPU. */ + if (!cpumask_test_cpu(cpu_nr, &ctx->cil_pcpmask)) + cpumask_test_and_set_cpu(cpu_nr, &ctx->cil_pcpmask); /* * We need to take the CIL checkpoint unit reservation on the first @@ -663,7 +675,7 @@ xlog_cil_insert_items( continue; list_add_tail(&lip->li_cil, &cilpcp->log_items); } - put_cpu_ptr(cilpcp); + put_cpu(); /* * If we've overrun the reservation, dump the tx details before we move @@ -1791,38 +1803,6 @@ out_shutdown: } /* - * Move dead percpu state to the relevant CIL context structures. - * - * We have to lock the CIL context here to ensure that nothing is modifying - * the percpu state, either addition or removal. Both of these are done under - * the CIL context lock, so grabbing that exclusively here will ensure we can - * safely drain the cilpcp for the CPU that is dying. - */ -void -xlog_cil_pcp_dead( - struct xlog *log, - unsigned int cpu) -{ - struct xfs_cil *cil = log->l_cilp; - struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); - struct xfs_cil_ctx *ctx; - - down_write(&cil->xc_ctx_lock); - ctx = cil->xc_ctx; - if (ctx->ticket) - ctx->ticket->t_curr_res += cilpcp->space_reserved; - cilpcp->space_reserved = 0; - - if (!list_empty(&cilpcp->log_items)) - list_splice_init(&cilpcp->log_items, &ctx->log_items); - if (!list_empty(&cilpcp->busy_extents)) - list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents); - atomic_add(cilpcp->space_used, &ctx->space_used); - cilpcp->space_used = 0; - up_write(&cil->xc_ctx_lock); -} - -/* * Perform initial CIL structure initialisation. */ int diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 1bd2963e8fbd..af87648331d5 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -231,6 +231,12 @@ struct xfs_cil_ctx { struct work_struct discard_endio_work; struct work_struct push_work; atomic_t order_id; + + /* + * CPUs that could have added items to the percpu CIL data. Access is + * coordinated with xc_ctx_lock. + */ + struct cpumask cil_pcpmask; }; /* @@ -278,9 +284,6 @@ struct xfs_cil { wait_queue_head_t xc_push_wait; /* background push throttle */ void __percpu *xc_pcp; /* percpu CIL structures */ -#ifdef CONFIG_HOTPLUG_CPU - struct list_head xc_pcp_list; -#endif } ____cacheline_aligned_in_smp; /* xc_flags bit values */ @@ -705,9 +708,4 @@ xlog_kvmalloc( return p; } -/* - * CIL CPU dead notifier - */ -void xlog_cil_pcp_dead(struct xlog *log, unsigned int cpu); - #endif /* __XFS_LOG_PRIV_H__ */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 82c81d20459d..13b94d2e605b 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -329,7 +329,7 @@ xlog_find_verify_cycle( * try a smaller size. We need to be able to read at least * a log sector, or we're out of luck. */ - bufblks = 1 << ffs(nbblks); + bufblks = roundup_pow_of_two(nbblks); while (bufblks > log->l_logBBsize) bufblks >>= 1; while (!(buffer = xlog_alloc_buffer(log, bufblks))) { @@ -1528,7 +1528,7 @@ xlog_write_log_records( * a smaller size. We need to be able to write at least a * log sector, or we're out of luck. */ - bufblks = 1 << ffs(blocks); + bufblks = roundup_pow_of_two(blocks); while (bufblks > log->l_logBBsize) bufblks >>= 1; while (!(buffer = xlog_alloc_buffer(log, bufblks))) { diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index a25eece3be2b..d19cca099bc3 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -60,6 +60,7 @@ struct xfs_error_cfg { * Per-cpu deferred inode inactivation GC lists. */ struct xfs_inodegc { + struct xfs_mount *mp; struct llist_head list; struct delayed_work work; int error; @@ -67,9 +68,7 @@ struct xfs_inodegc { /* approximate count of inodes in the list */ unsigned int items; unsigned int shrinker_hits; -#if defined(DEBUG) || defined(XFS_WARN) unsigned int cpu; -#endif }; /* @@ -98,7 +97,6 @@ typedef struct xfs_mount { xfs_buftarg_t *m_ddev_targp; /* saves taking the address */ xfs_buftarg_t *m_logdev_targp;/* ptr to log device */ xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */ - struct list_head m_mount_list; /* global mount list */ void __percpu *m_inodegc; /* percpu inodegc structures */ /* @@ -249,6 +247,9 @@ typedef struct xfs_mount { unsigned int *m_errortag; struct xfs_kobj m_errortag_kobj; #endif + + /* cpus that have inodes queued for inactivation */ + struct cpumask m_inodegc_cpumask; } xfs_mount_t; #define M_IGEO(mp) (&(mp)->m_ino_geo) @@ -404,6 +405,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID) #define XFS_OPSTATE_WARNED_SHRINK 8 /* Kernel has logged a warning about logged xattr updates being used. */ #define XFS_OPSTATE_WARNED_LARP 9 +/* Mount time quotacheck is running */ +#define XFS_OPSTATE_QUOTACHECK_RUNNING 10 #define __XFS_IS_OPSTATE(name, NAME) \ static inline bool xfs_is_ ## name (struct xfs_mount *mp) \ @@ -426,6 +429,11 @@ __XFS_IS_OPSTATE(inode32, INODE32) __XFS_IS_OPSTATE(readonly, READONLY) __XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED) __XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED) +#ifdef CONFIG_XFS_QUOTA +__XFS_IS_OPSTATE(quotacheck_running, QUOTACHECK_RUNNING) +#else +# define xfs_is_quotacheck_running(mp) (false) +#endif static inline bool xfs_should_warn(struct xfs_mount *mp, long nr) @@ -443,7 +451,8 @@ xfs_should_warn(struct xfs_mount *mp, long nr) { (1UL << XFS_OPSTATE_BLOCKGC_ENABLED), "blockgc" }, \ { (1UL << XFS_OPSTATE_WARNED_SCRUB), "wscrub" }, \ { (1UL << XFS_OPSTATE_WARNED_SHRINK), "wshrink" }, \ - { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" } + { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" }, \ + { (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING), "quotacheck" } /* * Max and min values for mount-option defined I/O diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6abcc34fafd8..086e78a6143a 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1160,6 +1160,19 @@ xfs_qm_dqusage_adjust( if (error) return error; + /* + * Reload the incore unlinked list to avoid failure in inodegc. + * Use an unlocked check here because unrecovered unlinked inodes + * should be somewhat rare. + */ + if (xfs_inode_unlinked_incomplete(ip)) { + error = xfs_inode_reload_unlinked(ip); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + goto error0; + } + } + ASSERT(ip->i_delayed_blks == 0); if (XFS_IS_REALTIME_INODE(ip)) { @@ -1173,6 +1186,7 @@ xfs_qm_dqusage_adjust( } nblks = (xfs_qcnt_t)ip->i_nblocks - rtblks; + xfs_iflags_clear(ip, XFS_IQUOTAUNCHECKED); /* * Add the (disk blocks and inode) resources occupied by this @@ -1319,8 +1333,10 @@ xfs_qm_quotacheck( flags |= XFS_PQUOTA_CHKD; } + xfs_set_quotacheck_running(mp); error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true, NULL); + xfs_clear_quotacheck_running(mp); /* * On error, the inode walk may have partially populated the dquot diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index edd8587658d5..2d4444d61e98 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -477,6 +477,7 @@ xfs_cui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_cui_log_item *cuip = CUI_ITEM(lip); struct xfs_cud_log_item *cudp; struct xfs_trans *tp; @@ -514,8 +515,9 @@ xfs_cui_item_recover( * doesn't fit. We need to reserve enough blocks to handle a * full btree split on either end of the refcount range. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, mp->m_refc_maxlevels * 2, 0, + XFS_TRANS_RESERVE, &tp); if (error) return error; diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 520c7ebdfed8..0e0e747028da 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -507,6 +507,7 @@ xfs_rui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_rui_log_item *ruip = RUI_ITEM(lip); struct xfs_rud_log_item *rudp; struct xfs_trans *tp; @@ -530,8 +531,9 @@ xfs_rui_item_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, mp->m_rmap_maxlevels, 0, + XFS_TRANS_RESERVE, &tp); if (error) return error; rudp = xfs_trans_get_rud(tp, ruip); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index b5c202f5d96c..819a3568b28f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -56,28 +56,6 @@ static struct kset *xfs_kset; /* top-level xfs sysfs dir */ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #endif -#ifdef CONFIG_HOTPLUG_CPU -static LIST_HEAD(xfs_mount_list); -static DEFINE_SPINLOCK(xfs_mount_list_lock); - -static inline void xfs_mount_list_add(struct xfs_mount *mp) -{ - spin_lock(&xfs_mount_list_lock); - list_add(&mp->m_mount_list, &xfs_mount_list); - spin_unlock(&xfs_mount_list_lock); -} - -static inline void xfs_mount_list_del(struct xfs_mount *mp) -{ - spin_lock(&xfs_mount_list_lock); - list_del(&mp->m_mount_list); - spin_unlock(&xfs_mount_list_lock); -} -#else /* !CONFIG_HOTPLUG_CPU */ -static inline void xfs_mount_list_add(struct xfs_mount *mp) {} -static inline void xfs_mount_list_del(struct xfs_mount *mp) {} -#endif - enum xfs_dax_mode { XFS_DAX_INODE = 0, XFS_DAX_ALWAYS = 1, @@ -1135,9 +1113,8 @@ xfs_inodegc_init_percpu( for_each_possible_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); -#if defined(DEBUG) || defined(XFS_WARN) gc->cpu = cpu; -#endif + gc->mp = mp; init_llist_head(&gc->list); gc->items = 0; gc->error = 0; @@ -1168,7 +1145,6 @@ xfs_fs_put_super( xfs_freesb(mp); xchk_mount_stats_free(mp); free_percpu(mp->m_stats.xs_stats); - xfs_mount_list_del(mp); xfs_inodegc_free_percpu(mp); xfs_destroy_percpu_counters(mp); xfs_destroy_mount_workqueues(mp); @@ -1577,13 +1553,6 @@ xfs_fs_fill_super( if (error) goto out_destroy_counters; - /* - * All percpu data structures requiring cleanup when a cpu goes offline - * must be allocated before adding this @mp to the cpu-dead handler's - * mount list. - */ - xfs_mount_list_add(mp); - /* Allocate stats memory before we do operations that might use it */ mp->m_stats.xs_stats = alloc_percpu(struct xfsstats); if (!mp->m_stats.xs_stats) { @@ -1781,7 +1750,6 @@ xfs_fs_fill_super( out_free_stats: free_percpu(mp->m_stats.xs_stats); out_destroy_inodegc: - xfs_mount_list_del(mp); xfs_inodegc_free_percpu(mp); out_destroy_counters: xfs_destroy_percpu_counters(mp); @@ -2326,49 +2294,6 @@ xfs_destroy_workqueues(void) destroy_workqueue(xfs_alloc_wq); } -#ifdef CONFIG_HOTPLUG_CPU -static int -xfs_cpu_dead( - unsigned int cpu) -{ - struct xfs_mount *mp, *n; - - spin_lock(&xfs_mount_list_lock); - list_for_each_entry_safe(mp, n, &xfs_mount_list, m_mount_list) { - spin_unlock(&xfs_mount_list_lock); - xfs_inodegc_cpu_dead(mp, cpu); - xlog_cil_pcp_dead(mp->m_log, cpu); - spin_lock(&xfs_mount_list_lock); - } - spin_unlock(&xfs_mount_list_lock); - return 0; -} - -static int __init -xfs_cpu_hotplug_init(void) -{ - int error; - - error = cpuhp_setup_state_nocalls(CPUHP_XFS_DEAD, "xfs:dead", NULL, - xfs_cpu_dead); - if (error < 0) - xfs_alert(NULL, -"Failed to initialise CPU hotplug, error %d. XFS is non-functional.", - error); - return error; -} - -static void -xfs_cpu_hotplug_destroy(void) -{ - cpuhp_remove_state_nocalls(CPUHP_XFS_DEAD); -} - -#else /* !CONFIG_HOTPLUG_CPU */ -static inline int xfs_cpu_hotplug_init(void) { return 0; } -static inline void xfs_cpu_hotplug_destroy(void) {} -#endif - STATIC int __init init_xfs_fs(void) { @@ -2385,13 +2310,9 @@ init_xfs_fs(void) xfs_dir_startup(); - error = xfs_cpu_hotplug_init(); - if (error) - goto out; - error = xfs_init_caches(); if (error) - goto out_destroy_hp; + goto out; error = xfs_init_workqueues(); if (error) @@ -2475,8 +2396,6 @@ init_xfs_fs(void) xfs_destroy_workqueues(); out_destroy_caches: xfs_destroy_caches(); - out_destroy_hp: - xfs_cpu_hotplug_destroy(); out: return error; } @@ -2500,7 +2419,6 @@ exit_xfs_fs(void) xfs_destroy_workqueues(); xfs_destroy_caches(); xfs_uuid_table_free(); - xfs_cpu_hotplug_destroy(); } module_init(init_xfs_fs); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 902c7f67a117..3926cf7f2a6e 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3824,6 +3824,51 @@ TRACE_EVENT(xfs_iunlink_update_dinode, __entry->new_ptr) ); +TRACE_EVENT(xfs_iunlink_reload_next, + TP_PROTO(struct xfs_inode *ip), + TP_ARGS(ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(xfs_agino_t, agino) + __field(xfs_agino_t, prev_agino) + __field(xfs_agino_t, next_agino) + ), + TP_fast_assign( + __entry->dev = ip->i_mount->m_super->s_dev; + __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino); + __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino); + __entry->prev_agino = ip->i_prev_unlinked; + __entry->next_agino = ip->i_next_unlinked; + ), + TP_printk("dev %d:%d agno 0x%x agino 0x%x prev_unlinked 0x%x next_unlinked 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, + __entry->agino, + __entry->prev_agino, + __entry->next_agino) +); + +TRACE_EVENT(xfs_inode_reload_unlinked_bucket, + TP_PROTO(struct xfs_inode *ip), + TP_ARGS(ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(xfs_agino_t, agino) + ), + TP_fast_assign( + __entry->dev = ip->i_mount->m_super->s_dev; + __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino); + __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino); + ), + TP_printk("dev %d:%d agno 0x%x agino 0x%x bucket %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, + __entry->agino, + __entry->agino % XFS_AGI_UNLINKED_BUCKETS) +); + DECLARE_EVENT_CLASS(xfs_ag_inode_class, TP_PROTO(struct xfs_inode *ip), TP_ARGS(ip), diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 43e5c219aaed..a3975f325f4e 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -46,6 +46,17 @@ xfs_attr_grab_log_assist( if (xfs_sb_version_haslogxattrs(&mp->m_sb)) return 0; + /* + * Check if the filesystem featureset is new enough to set this log + * incompat feature bit. Strictly speaking, the minimum requirement is + * a V5 filesystem for the superblock field, but we'll require rmap + * or reflink to avoid having to deal with really old kernels. + */ + if (!xfs_has_reflink(mp) && !xfs_has_rmapbt(mp)) { + error = -EOPNOTSUPP; + goto drop_incompat; + } + /* Enable log-assisted xattrs. */ error = xfs_add_incompat_log_feature(mp, XFS_SB_FEAT_INCOMPAT_LOG_XATTRS); diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 4da02798a00b..6dcf4d576970 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -76,7 +76,7 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { set_pte_at(mm, addr, ptep, pte); } diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 9c59409104f6..67d8dd2f1bde 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -138,13 +138,6 @@ * are handled as text/data or they can be discarded (which * often happens at runtime) */ -#ifdef CONFIG_HOTPLUG_CPU -#define CPU_KEEP(sec) *(.cpu##sec) -#define CPU_DISCARD(sec) -#else -#define CPU_KEEP(sec) -#define CPU_DISCARD(sec) *(.cpu##sec) -#endif #if defined(CONFIG_MEMORY_HOTPLUG) #define MEM_KEEP(sec) *(.mem##sec) diff --git a/include/linux/aer.h b/include/linux/aer.h index 2dd175f5debd..29cc10220952 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -42,11 +42,13 @@ struct aer_capability_regs { #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); +int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev) { return -EINVAL; } +static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif void cper_print_aer(struct pci_dev *dev, int aer_severity, diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 7c67c17321d4..083f85653716 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -67,6 +67,8 @@ #define ARM_SMCCC_VERSION_1_3 0x10003 #define ARM_SMCCC_1_3_SVE_HINT 0x10000 +#define ARM_SMCCC_CALL_HINTS ARM_SMCCC_1_3_SVE_HINT + #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 18f5744dfb5d..b83ef19da13d 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -459,8 +459,6 @@ raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); -#elif defined(arch_atomic_read) - return arch_atomic_read(v); #else int ret; @@ -508,8 +506,6 @@ raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); -#elif defined(arch_atomic_set) - arch_atomic_set(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); @@ -2575,8 +2571,6 @@ raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); -#elif defined(arch_atomic64_read) - return arch_atomic64_read(v); #else s64 ret; @@ -2624,8 +2618,6 @@ raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); -#elif defined(arch_atomic64_set) - arch_atomic64_set(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); @@ -4657,4 +4649,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 202b45c7db600ce36198eb1f1fc2c2d5268ace2d +// 2fdd6702823fa842f9cea57a002e6e4476ae780c diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 30063a760b5a..a34ac7f00c86 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1318,7 +1318,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { - return ERR_PTR(-EOPNOTSUPP); + return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 5f2301ee88bc..f3b3593254b9 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -467,19 +467,17 @@ union ceph_mds_request_args { } __attribute__ ((packed)); union ceph_mds_request_args_ext { - union { - union ceph_mds_request_args old; - struct { - __le32 mode; - __le32 uid; - __le32 gid; - struct ceph_timespec mtime; - struct ceph_timespec atime; - __le64 size, old_size; /* old_size needed by truncate */ - __le32 mask; /* CEPH_SETATTR_* */ - struct ceph_timespec btime; - } __attribute__ ((packed)) setattr_ext; - }; + union ceph_mds_request_args old; + struct { + __le32 mode; + __le32 uid; + __le32 gid; + struct ceph_timespec mtime; + struct ceph_timespec atime; + __le64 size, old_size; /* old_size needed by truncate */ + __le32 mask; /* CEPH_SETATTR_* */ + struct ceph_timespec btime; + } __attribute__ ((packed)) setattr_ext; }; #define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 06dda85f0424..068f7738be22 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -90,7 +90,6 @@ enum cpuhp_state { CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, - CPUHP_XFS_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5b2626063f4f..a30686e649f7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -984,7 +984,9 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif @@ -1173,7 +1175,7 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { } diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a92bce40b04b..4a1dc88ddbff 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,8 +569,12 @@ enum * 2) rcu_report_dead() reports the final quiescent states. * * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue + * + * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue */ -#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\ + BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ)) + /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 7766cf653357..9bc5b4d35494 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -54,7 +54,7 @@ extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_mem_to_shadow static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) diff --git a/include/linux/libata.h b/include/linux/libata.h index bf4913f4d7ac..2a7d2af0ed80 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -192,6 +192,7 @@ enum { ATA_PFLAG_UNLOADING = (1 << 9), /* driver is being unloaded */ ATA_PFLAG_UNLOADED = (1 << 10), /* driver is unloaded */ + ATA_PFLAG_RESUMING = (1 << 16), /* port is being resumed */ ATA_PFLAG_SUSPENDED = (1 << 17), /* port is suspended (power) */ ATA_PFLAG_PM_PENDING = (1 << 18), /* PM operation pending */ ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */ @@ -259,7 +260,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 5000, + ATA_TMOUT_PMP_SRST_WAIT = 10000, /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might * be a spurious PHY event, so ignore the first PHY event that @@ -318,9 +319,10 @@ enum { ATA_EH_ENABLE_LINK = (1 << 3), ATA_EH_PARK = (1 << 5), /* unload heads and stop I/O */ ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */ + ATA_EH_SET_ACTIVE = (1 << 7), /* Set a device to active power mode */ ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE | ATA_EH_PARK | - ATA_EH_GET_SUCCESS_SENSE, + ATA_EH_GET_SUCCESS_SENSE | ATA_EH_SET_ACTIVE, ATA_EH_ALL_ACTIONS = ATA_EH_REVALIDATE | ATA_EH_RESET | ATA_EH_ENABLE_LINK, @@ -357,7 +359,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependent */ @@ -1148,6 +1150,7 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); +extern int ata_scsi_slave_alloc(struct scsi_device *sdev); extern int ata_scsi_slave_config(struct scsi_device *sdev); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, @@ -1396,6 +1399,7 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ + .slave_alloc = ata_scsi_slave_alloc, \ .slave_destroy = ata_scsi_slave_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index e41c70ac7744..d01e850b570f 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -428,6 +428,8 @@ struct ma_wr_state { #define MAS_ROOT ((struct maple_enode *)5UL) #define MAS_NONE ((struct maple_enode *)9UL) #define MAS_PAUSE ((struct maple_enode *)17UL) +#define MAS_OVERFLOW ((struct maple_enode *)33UL) +#define MAS_UNDERFLOW ((struct maple_enode *)65UL) #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) @@ -511,6 +513,15 @@ static inline bool mas_is_paused(const struct ma_state *mas) return mas->node == MAS_PAUSE; } +/* Check if the mas is pointing to a node or not */ +static inline bool mas_is_active(struct ma_state *mas) +{ + if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE) + return true; + + return false; +} + /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ab94ad4597d0..e4e24da16d2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -920,7 +920,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(void); +void mem_cgroup_handle_over_high(gfp_t gfp_mask); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); @@ -1458,7 +1458,7 @@ static inline void mem_cgroup_unlock_pages(void) rcu_read_unlock(); } -static inline void mem_cgroup_handle_over_high(void) +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 625f491b95de..fb31312825ae 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,7 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 init[IP_CT_DIR_MAX]; u8 last_dir; u8 flags; }; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 1fba072b3dac..af7639c3b0a3 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -206,6 +206,14 @@ static inline int pmd_young(pmd_t pmd) #endif #ifndef set_ptes + +#ifndef pte_next_pfn +static inline pte_t pte_next_pfn(pte_t pte) +{ + return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); +} +#endif + /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. @@ -231,7 +239,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, if (--nr == 0) break; ptep++; - pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + pte = pte_next_pfn(pte); } arch_leave_lazy_mmu_mode(); } diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index 285189454449..f8f3e958e9cf 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -55,7 +55,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) } #endif - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 987a59d977c5..e9bd2f65d7f4 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -512,8 +512,8 @@ do { \ static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { - do_raw_write_seqcount_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); + do_raw_write_seqcount_begin(s); } /** diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b4536626f8ff..ecde0312dd52 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -172,14 +172,23 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) if (!mem) return false; - if (IS_ENABLED(CONFIG_SWIOTLB_DYNAMIC)) { - /* Pairs with smp_wmb() in swiotlb_find_slots() and - * swiotlb_dyn_alloc(), which modify the RCU lists. - */ - smp_rmb(); - return swiotlb_find_pool(dev, paddr); - } +#ifdef CONFIG_SWIOTLB_DYNAMIC + /* + * All SWIOTLB buffer addresses must have been returned by + * swiotlb_tbl_map_single() and passed to a device driver. + * If a SWIOTLB address is checked on another CPU, then it was + * presumably loaded by the device driver from an unspecified private + * data structure. Make sure that this load is ordered before reading + * dev->dma_uses_io_tlb here and mem->pools in swiotlb_find_pool(). + * + * This barrier pairs with smp_mb() in swiotlb_find_slots(). + */ + smp_rmb(); + return READ_ONCE(dev->dma_uses_io_tlb) && + swiotlb_find_pool(dev, paddr); +#else return paddr >= mem->defpool.start && paddr < mem->defpool.end; +#endif } static inline bool is_swiotlb_force_bounce(struct device *dev) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e6359f7346f1..c33348ba1657 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -350,7 +350,7 @@ struct hci_dev { struct list_head list; struct mutex lock; - char name[8]; + const char *name; unsigned long flags; __u16 id; __u8 bus; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 3a4b684f89bf..7192346e4a22 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5941,6 +5941,7 @@ void wiphy_delayed_work_cancel(struct wiphy *wiphy, * @event_lock: (private) lock for event list * @owner_nlportid: (private) owner socket port ID * @nl_owner_dead: (private) owner socket went away + * @cqm_rssi_work: (private) CQM RSSI reporting work * @cqm_config: (private) nl80211 RSSI monitor state * @pmsr_list: (private) peer measurement requests * @pmsr_lock: (private) peer measurements requests/results lock @@ -6013,7 +6014,8 @@ struct wireless_dev { } wext; #endif - struct cfg80211_cqm_config *cqm_config; + struct wiphy_work cqm_rssi_work; + struct cfg80211_cqm_config __rcu *cqm_config; struct list_head pmsr_list; spinlock_t pmsr_lock; @@ -7231,7 +7233,7 @@ struct cfg80211_rx_assoc_resp { int uapsd_queues; const u8 *ap_mld_addr; struct { - const u8 *addr; + u8 addr[ETH_ALEN] __aligned(2); struct cfg80211_bss *bss; u16 status; } links[IEEE80211_MLD_MAX_NUM_LINKS]; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 84b0a82c9df4..d4667b7797e3 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -154,6 +154,7 @@ struct fib_info { int fib_nhs; bool fib_nh_is_v6; bool nh_updated; + bool pfsrc_removed; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[] __counted_by(fib_nhs); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 38441be68592..6e3e9c1363db 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -103,9 +103,10 @@ struct mana_txq { /* skb data and frags dma mappings */ struct mana_skb_head { - dma_addr_t dma_handle[MAX_SKB_FRAGS + 1]; + /* GSO pkts may have 2 SGEs for the linear part*/ + dma_addr_t dma_handle[MAX_SKB_FRAGS + 2]; - u32 size[MAX_SKB_FRAGS + 1]; + u32 size[MAX_SKB_FRAGS + 2]; }; #define MANA_HEADROOM sizeof(struct mana_skb_head) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 6da68886fabb..07022bb0d44d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -539,7 +539,7 @@ static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); - return n->output(n, skb); + return READ_ONCE(n->output)(n, skb); } static inline struct neighbour * diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 94231533a369..8e7751464ff5 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -16,13 +16,13 @@ * page_pool_alloc_pages() call. Drivers should use * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). * - * API keeps track of in-flight pages, in order to let API user know + * The API keeps track of in-flight pages, in order to let API users know * when it is safe to free a page_pool object. Thus, API users * must call page_pool_put_page() to free the page, or attach - * the page to a page_pool-aware objects like skbs marked with + * the page to a page_pool-aware object like skbs marked with * skb_mark_for_recycle(). * - * API user must call page_pool_put_page() once on a page, as it + * API users must call page_pool_put_page() once on a page, as it * will either recycle the page, or in case of refcnt > 1, it will * release the DMA mapping and in-flight state accounting. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index af9cb37fbe53..9eb0a2855311 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -348,12 +348,14 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule); -static inline void tcp_dec_quickack_mode(struct sock *sk, - const unsigned int pkts) +static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { + /* How many ACKs S/ACKing new data have we sent? */ + const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; + if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index ec093594ba53..4498f845b112 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -157,6 +157,9 @@ enum scsi_disposition { #define SCSI_3 4 /* SPC */ #define SCSI_SPC_2 5 #define SCSI_SPC_3 6 +#define SCSI_SPC_4 7 +#define SCSI_SPC_5 8 +#define SCSI_SPC_6 14 /* * INQ PERIPHERAL QUALIFIERS diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index b9230b6add04..fd41fdac0a8e 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -161,6 +161,10 @@ struct scsi_device { * pass settings from slave_alloc to scsi * core. */ unsigned int eh_timeout; /* Error handling timeout */ + + bool manage_system_start_stop; /* Let HLD (sd) manage system start/stop */ + bool manage_runtime_start_stop; /* Let HLD (sd) manage runtime start/stop */ + unsigned removable:1; unsigned changed:1; /* Data invalid due to media change */ unsigned busy:1; /* Used to prevent races */ @@ -193,7 +197,6 @@ struct scsi_device { unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */ unsigned no_start_on_add:1; /* do not issue start on add */ unsigned allow_restart:1; /* issue START_UNIT in error handler */ - unsigned manage_start_stop:1; /* Let HLD (sd) manage start/stop */ unsigned no_start_on_resume:1; /* Do not issue START_STOP_UNIT on resume */ unsigned start_stop_pwr_cond:1; /* Set power cond. in START_STOP_UNIT */ unsigned no_uld_attach:1; /* disable connecting to upper level drivers */ diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 49f768d0ff37..4c2dc8150c6d 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -764,7 +764,7 @@ scsi_template_proc_dir(const struct scsi_host_template *sht); #define scsi_template_proc_dir(sht) NULL #endif extern void scsi_scan_host(struct Scsi_Host *); -extern void scsi_rescan_device(struct scsi_device *); +extern int scsi_rescan_device(struct scsi_device *sdev); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); extern int scsi_host_busy(struct Scsi_Host *shost); diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 7c3fc3980881..5c6c4269f7ef 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -29,6 +29,11 @@ struct TAG { MEMBERS } ATTRS NAME; \ } +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union * @@ -49,3 +54,5 @@ #ifndef __counted_by #define __counted_by(m) #endif + +#endif /* _UAPI_LINUX_STDDEF_H */ diff --git a/io_uring/fs.c b/io_uring/fs.c index f6a69a549fd4..08e3b175469c 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -243,7 +243,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); const char __user *oldf, *newf; - if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 0ad175277f89..39ea316c55e7 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -973,37 +973,31 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } -/* Most of the logic is taken from setup_kmalloc_cache_index_table() */ static __init int bpf_mem_cache_adjust_size(void) { - unsigned int size, index; + unsigned int size; - /* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be - * up-to 256-bytes. + /* Adjusting the indexes in size_index() according to the object_size + * of underlying slab cache, so bpf_mem_alloc() will select a + * bpf_mem_cache with unit_size equal to the object_size of + * the underlying slab cache. + * + * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is + * 256-bytes, so only do adjustment for [8-bytes, 192-bytes]. */ - size = KMALLOC_MIN_SIZE; - if (size <= 192) - index = size_index[(size - 1) / 8]; - else - index = fls(size - 1) - 1; - for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8) - size_index[(size - 1) / 8] = index; + for (size = 192; size >= 8; size -= 8) { + unsigned int kmalloc_size, index; - /* The minimal alignment is 64-bytes, so disable 96-bytes cache and - * use 128-bytes cache instead. - */ - if (KMALLOC_MIN_SIZE >= 64) { - index = size_index[(128 - 1) / 8]; - for (size = 64 + 8; size <= 96; size += 8) - size_index[(size - 1) / 8] = index; - } + kmalloc_size = kmalloc_size_roundup(size); + if (kmalloc_size == size) + continue; - /* The minimal alignment is 128-bytes, so disable 192-bytes cache and - * use 256-bytes cache instead. - */ - if (KMALLOC_MIN_SIZE >= 128) { - index = fls(256 - 1) - 1; - for (size = 128 + 8; size <= 192; size += 8) + if (kmalloc_size <= 192) + index = size_index[(kmalloc_size - 1) / 8]; + else + index = fls(kmalloc_size - 1) - 1; + /* Only overwrite if necessary */ + if (size_index[(size - 1) / 8] != index) size_index[(size - 1) / 8] = index; } diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c index 32d2c4829eb8..007d98c799e2 100644 --- a/kernel/bpf/mprog.c +++ b/kernel/bpf/mprog.c @@ -253,6 +253,9 @@ int bpf_mprog_attach(struct bpf_mprog_entry *entry, goto out; } idx = tidx; + } else if (bpf_mprog_total(entry) == bpf_mprog_max()) { + ret = -ERANGE; + goto out; } if (flags & BPF_F_BEFORE) { tidx = bpf_mprog_pos_before(entry, &rtuple); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 38f8718f1602..c8dae2fde115 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4132,11 +4132,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; - if (reg->type != SCALAR_VALUE) { - bt_clear_reg(bt, i); - continue; - } - reg->precise = true; + bt_clear_reg(bt, i); + if (reg->type == SCALAR_VALUE) + reg->precise = true; } return 0; } diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 03a7932cde0a..2f675ef045d4 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -740,6 +740,17 @@ subsys_initcall(crash_notes_memory_init); #define pr_fmt(fmt) "crash hp: " fmt /* + * Different than kexec/kdump loading/unloading/jumping/shrinking which + * usually rarely happen, there will be many crash hotplug events notified + * during one short period, e.g one memory board is hot added and memory + * regions are online. So mutex lock __crash_hotplug_lock is used to + * serialize the crash hotplug handling specifically. + */ +DEFINE_MUTEX(__crash_hotplug_lock); +#define crash_hotplug_lock() mutex_lock(&__crash_hotplug_lock) +#define crash_hotplug_unlock() mutex_unlock(&__crash_hotplug_lock) + +/* * This routine utilized when the crash_hotplug sysfs node is read. * It reflects the kernel's ability/permission to update the crash * elfcorehdr directly. @@ -748,9 +759,11 @@ int crash_check_update_elfcorehdr(void) { int rc = 0; + crash_hotplug_lock(); /* Obtain lock while reading crash information */ if (!kexec_trylock()) { pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n"); + crash_hotplug_unlock(); return 0; } if (kexec_crash_image) { @@ -761,6 +774,7 @@ int crash_check_update_elfcorehdr(void) } /* Release lock now that update complete */ kexec_unlock(); + crash_hotplug_unlock(); return rc; } @@ -783,9 +797,11 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) { struct kimage *image; + crash_hotplug_lock(); /* Obtain lock while changing crash information */ if (!kexec_trylock()) { pr_info("kexec_trylock() failed, elfcorehdr may be inaccurate\n"); + crash_hotplug_unlock(); return; } @@ -852,6 +868,7 @@ static void crash_handle_hotplug_event(unsigned int hp_action, unsigned int cpu) out: /* Release lock now that update complete */ kexec_unlock(); + crash_hotplug_unlock(); } static int crash_memhp_notifier(struct notifier_block *nb, unsigned long val, void *v) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 394494a6b1f3..01637677736f 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -399,14 +399,13 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, } mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area), - default_nareas), SMP_CACHE_BYTES); + nareas), SMP_CACHE_BYTES); if (!mem->areas) { pr_warn("%s: Failed to allocate mem->areas.\n", __func__); return; } - swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, - default_nareas); + swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas); add_mem_pool(&io_tlb_default_mem, mem); if (flags & SWIOTLB_VERBOSE) @@ -729,9 +728,6 @@ static void swiotlb_dyn_alloc(struct work_struct *work) } add_mem_pool(mem, pool); - - /* Pairs with smp_rmb() in is_swiotlb_buffer(). */ - smp_wmb(); } /** @@ -1152,9 +1148,26 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); found: - dev->dma_uses_io_tlb = true; - /* Pairs with smp_rmb() in is_swiotlb_buffer() */ - smp_wmb(); + WRITE_ONCE(dev->dma_uses_io_tlb, true); + + /* + * The general barrier orders reads and writes against a presumed store + * of the SWIOTLB buffer address by a device driver (to a driver private + * data structure). It serves two purposes. + * + * First, the store to dev->dma_uses_io_tlb must be ordered before the + * presumed store. This guarantees that the returned buffer address + * cannot be passed to another CPU before updating dev->dma_uses_io_tlb. + * + * Second, the load from mem->pools must be ordered before the same + * presumed store. This guarantees that the returned buffer address + * cannot be observed by another CPU before an update of the RCU list + * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy + * atomicity). + * + * See also the comment in is_swiotlb_buffer(). + */ + smp_mb(); *retpool = pool; return index; diff --git a/kernel/pid.c b/kernel/pid.c index fee14a4486a3..6500ef956f2f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -609,7 +609,7 @@ int pidfd_create(struct pid *pid, unsigned int flags) } /** - * pidfd_open() - Open new pid file descriptor. + * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2299a5cfbfb9..802551e0009b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9269,7 +9269,7 @@ void __init init_idle(struct task_struct *idle, int cpu) * PF_KTHREAD should already be set at this point; regardless, make it * look like a proper per-CPU kthread. */ - idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; + idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); #ifdef CONFIG_SMP diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index a286e726eb4b..42c40cfdf836 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -101,6 +101,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p, if (lowest_mask) { cpumask_and(lowest_mask, &p->cpus_mask, vec->mask); + cpumask_and(lowest_mask, lowest_mask, cpu_active_mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 342f58a329f5..5007b25c5bc6 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -373,6 +373,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise); void cpu_startup_entry(enum cpuhp_state state) { + current->flags |= PF_IDLE; arch_cpu_idle_prepare(); cpuhp_online_idle(state); while (1) diff --git a/kernel/task_work.c b/kernel/task_work.c index 065e1ef8fc8d..95a7e1b7f1da 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -78,6 +78,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call + * @data: data to be passed in to match function * * RETURNS: * The found work or NULL if not found. diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..515cafdb18d9 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -1132,6 +1137,9 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, if (full) { poll_wait(filp, &work->full_waiters, poll_table); work->full_waiters_pending = true; + if (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full) + cpu_buffer->shortest_full = full; } else { poll_wait(filp, &work->waiters, poll_table); work->waiters_pending = true; @@ -2003,7 +2011,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2375,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2520,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2663,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2676,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2702,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4219,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4727,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5821,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 91951d038ba4..f49d6ddb6342 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2770,6 +2770,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) update_event_fields(call, map[i]); } } + cond_resched(); } up_write(&trace_event_sem); } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 6f046650e527..b87f41187c6a 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -127,8 +127,13 @@ struct user_event_enabler { /* Bit 7 is for freeing status of enablement */ #define ENABLE_VAL_FREEING_BIT 7 -/* Only duplicate the bit value */ -#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK +/* Bit 8 is for marking 32-bit on 64-bit */ +#define ENABLE_VAL_32_ON_64_BIT 8 + +#define ENABLE_VAL_COMPAT_MASK (1 << ENABLE_VAL_32_ON_64_BIT) + +/* Only duplicate the bit and compat values */ +#define ENABLE_VAL_DUP_MASK (ENABLE_VAL_BIT_MASK | ENABLE_VAL_COMPAT_MASK) #define ENABLE_BITOPS(e) (&(e)->values) @@ -174,6 +179,30 @@ struct user_event_validator { int flags; }; +static inline void align_addr_bit(unsigned long *addr, int *bit, + unsigned long *flags) +{ + if (IS_ALIGNED(*addr, sizeof(long))) { +#ifdef __BIG_ENDIAN + /* 32 bit on BE 64 bit requires a 32 bit offset when aligned. */ + if (test_bit(ENABLE_VAL_32_ON_64_BIT, flags)) + *bit += 32; +#endif + return; + } + + *addr = ALIGN_DOWN(*addr, sizeof(long)); + + /* + * We only support 32 and 64 bit values. The only time we need + * to align is a 32 bit value on a 64 bit kernel, which on LE + * is always 32 bits, and on BE requires no change when unaligned. + */ +#ifdef __LITTLE_ENDIAN + *bit += 32; +#endif +} + typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, void *tpdata, bool *faulted); @@ -482,6 +511,7 @@ static int user_event_enabler_write(struct user_event_mm *mm, unsigned long *ptr; struct page *page; void *kaddr; + int bit = ENABLE_BIT(enabler); int ret; lockdep_assert_held(&event_mutex); @@ -497,6 +527,8 @@ static int user_event_enabler_write(struct user_event_mm *mm, test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)))) return -EBUSY; + align_addr_bit(&uaddr, &bit, ENABLE_BITOPS(enabler)); + ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT, &page, NULL); @@ -515,9 +547,9 @@ static int user_event_enabler_write(struct user_event_mm *mm, /* Update bit atomically, user tracers must be atomic as well */ if (enabler->event && enabler->event->status) - set_bit(ENABLE_BIT(enabler), ptr); + set_bit(bit, ptr); else - clear_bit(ENABLE_BIT(enabler), ptr); + clear_bit(bit, ptr); kunmap_local(kaddr); unpin_user_pages_dirty_lock(&page, 1, true); @@ -849,6 +881,12 @@ static struct user_event_enabler enabler->event = user; enabler->addr = uaddr; enabler->values = reg->enable_bit; + +#if BITS_PER_LONG >= 64 + if (reg->enable_size == 4) + set_bit(ENABLE_VAL_32_ON_64_BIT, ENABLE_BITOPS(enabler)); +#endif + retry: /* Prevents state changes from racing with new enablers */ mutex_lock(&event_mutex); @@ -2377,7 +2415,8 @@ static long user_unreg_get(struct user_unreg __user *ureg, } static int user_event_mm_clear_bit(struct user_event_mm *user_mm, - unsigned long uaddr, unsigned char bit) + unsigned long uaddr, unsigned char bit, + unsigned long flags) { struct user_event_enabler enabler; int result; @@ -2385,7 +2424,7 @@ static int user_event_mm_clear_bit(struct user_event_mm *user_mm, memset(&enabler, 0, sizeof(enabler)); enabler.addr = uaddr; - enabler.values = bit; + enabler.values = bit | flags; retry: /* Prevents state changes from racing with new enablers */ mutex_lock(&event_mutex); @@ -2415,6 +2454,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) struct user_event_mm *mm = current->user_event_mm; struct user_event_enabler *enabler, *next; struct user_unreg reg; + unsigned long flags; long ret; ret = user_unreg_get(ureg, ®); @@ -2425,6 +2465,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) if (!mm) return -ENOENT; + flags = 0; ret = -ENOENT; /* @@ -2441,6 +2482,9 @@ static long user_events_ioctl_unreg(unsigned long uarg) ENABLE_BIT(enabler) == reg.disable_bit) { set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); + /* We must keep compat flags for the clear */ + flags |= enabler->values & ENABLE_VAL_COMPAT_MASK; + if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) user_event_enabler_destroy(enabler, true); @@ -2454,7 +2498,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) /* Ensure bit is now cleared for user, regardless of event status */ if (!ret) ret = user_event_mm_clear_bit(mm, reg.disable_addr, - reg.disable_bit); + reg.disable_bit, flags); return ret; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c85825e17df8..b9f053a5a5f0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6535,9 +6535,6 @@ void __init workqueue_init_early(void) BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); - wq_update_pod_attrs_buf = alloc_workqueue_attrs(); - BUG_ON(!wq_update_pod_attrs_buf); - pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; @@ -6605,13 +6602,13 @@ static void __init wq_cpu_intensive_thresh_init(void) unsigned long thresh; unsigned long bogo; + pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); + BUG_ON(IS_ERR(pwq_release_worker)); + /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; - pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); - BUG_ON(IS_ERR(pwq_release_worker)); - /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what diff --git a/lib/argv_split.c b/lib/argv_split.c index 1a19a0a93dc1..e28db8e3b58c 100644 --- a/lib/argv_split.c +++ b/lib/argv_split.c @@ -28,7 +28,7 @@ static int count_argc(const char *str) /** * argv_free - free an argv - * @argv - the argument vector to be freed + * @argv: the argument vector to be freed * * Frees an argv and the strings it points to. */ @@ -46,7 +46,7 @@ EXPORT_SYMBOL(argv_free); * @str: the string to be split * @argcp: returned argument count * - * Returns an array of pointers to strings which are split out from + * Returns: an array of pointers to strings which are split out from * @str. This is performed by strictly splitting on white-space; no * quote processing is performed. Multiple whitespace characters are * considered to be a single argument separator. The returned array diff --git a/lib/maple_tree.c b/lib/maple_tree.c index ee1ff0c59fd7..0e00a84e8e8f 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -256,6 +256,22 @@ bool mas_is_err(struct ma_state *mas) return xa_is_err(mas->node); } +static __always_inline bool mas_is_overflow(struct ma_state *mas) +{ + if (unlikely(mas->node == MAS_OVERFLOW)) + return true; + + return false; +} + +static __always_inline bool mas_is_underflow(struct ma_state *mas) +{ + if (unlikely(mas->node == MAS_UNDERFLOW)) + return true; + + return false; +} + static inline bool mas_searchable(struct ma_state *mas) { if (mas_is_none(mas)) @@ -4415,10 +4431,13 @@ no_entry: * * @mas: The maple state * @max: The minimum starting range + * @empty: Can be empty + * @set_underflow: Set the @mas->node to underflow state on limit. * * Return: The entry in the previous slot which is possibly NULL */ -static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) +static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty, + bool set_underflow) { void *entry; void __rcu **slots; @@ -4435,7 +4454,6 @@ retry: if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; -again: if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); @@ -4443,9 +4461,10 @@ again: goto retry; if (pivot <= min) - return NULL; + goto underflow; } +again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; @@ -4457,7 +4476,7 @@ again: } if (mas_is_none(mas)) - return NULL; + goto underflow; mas->last = mas->max; node = mas_mn(mas); @@ -4474,10 +4493,19 @@ again: if (likely(entry)) return entry; - if (!empty) + if (!empty) { + if (mas->index <= min) + goto underflow; + goto again; + } return entry; + +underflow: + if (set_underflow) + mas->node = MAS_UNDERFLOW; + return NULL; } /* @@ -4567,10 +4595,13 @@ no_entry: * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty + * @set_overflow: Should @mas->node be set to overflow when the limit is + * reached. * * Return: The entry in the next slot which is possibly NULL */ -static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) +static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty, + bool set_overflow) { void __rcu **slots; unsigned long *pivots; @@ -4589,22 +4620,22 @@ retry: if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; -again: if (mas->max >= max) { if (likely(mas->offset < data_end)) pivot = pivots[mas->offset]; else - return NULL; /* must be mas->max */ + goto overflow; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) - return NULL; + goto overflow; } if (likely(mas->offset < data_end)) { mas->index = pivots[mas->offset] + 1; +again: mas->offset++; if (likely(mas->offset < data_end)) mas->last = pivots[mas->offset]; @@ -4616,8 +4647,11 @@ again: goto retry; } - if (mas_is_none(mas)) + if (WARN_ON_ONCE(mas_is_none(mas))) { + mas->node = MAS_OVERFLOW; return NULL; + goto overflow; + } mas->offset = 0; mas->index = mas->min; @@ -4636,12 +4670,20 @@ again: return entry; if (!empty) { - if (!mas->offset) - data_end = 2; + if (mas->last >= max) + goto overflow; + + mas->index = mas->last + 1; + /* Node cannot end on NULL, so it's safe to short-cut here */ goto again; } return entry; + +overflow: + if (set_overflow) + mas->node = MAS_OVERFLOW; + return NULL; } /* @@ -4651,17 +4693,20 @@ again: * * Set the @mas->node to the next entry and the range_start to * the beginning value for the entry. Does not check beyond @limit. - * Sets @mas->index and @mas->last to the limit if it is hit. + * Sets @mas->index and @mas->last to the range, Does not update @mas->index and + * @mas->last on overflow. * Restarts on dead nodes. * * Return: the next entry or %NULL. */ static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { - if (mas->last >= limit) + if (mas->last >= limit) { + mas->node = MAS_OVERFLOW; return NULL; + } - return mas_next_slot(mas, limit, false); + return mas_next_slot(mas, limit, false, true); } /* @@ -4837,7 +4882,7 @@ void *mas_walk(struct ma_state *mas) { void *entry; - if (mas_is_none(mas) || mas_is_paused(mas) || mas_is_ptr(mas)) + if (!mas_is_active(mas) || !mas_is_start(mas)) mas->node = MAS_START; retry: entry = mas_state_walk(mas); @@ -5294,14 +5339,22 @@ static inline void mte_destroy_walk(struct maple_enode *enode, static void mas_wr_store_setup(struct ma_wr_state *wr_mas) { - if (mas_is_start(wr_mas->mas)) - return; + if (!mas_is_active(wr_mas->mas)) { + if (mas_is_start(wr_mas->mas)) + return; - if (unlikely(mas_is_paused(wr_mas->mas))) - goto reset; + if (unlikely(mas_is_paused(wr_mas->mas))) + goto reset; - if (unlikely(mas_is_none(wr_mas->mas))) - goto reset; + if (unlikely(mas_is_none(wr_mas->mas))) + goto reset; + + if (unlikely(mas_is_overflow(wr_mas->mas))) + goto reset; + + if (unlikely(mas_is_underflow(wr_mas->mas))) + goto reset; + } /* * A less strict version of mas_is_span_wr() where we allow spanning @@ -5595,8 +5648,25 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, { bool was_none = mas_is_none(mas); - if (mas_is_none(mas) || mas_is_paused(mas)) + if (unlikely(mas->last >= max)) { + mas->node = MAS_OVERFLOW; + return true; + } + + if (mas_is_active(mas)) + return false; + + if (mas_is_none(mas) || mas_is_paused(mas)) { + mas->node = MAS_START; + } else if (mas_is_overflow(mas)) { + /* Overflowed before, but the max changed */ mas->node = MAS_START; + } else if (mas_is_underflow(mas)) { + mas->node = MAS_START; + *entry = mas_walk(mas); + if (*entry) + return true; + } if (mas_is_start(mas)) *entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ @@ -5615,6 +5685,7 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, if (mas_is_none(mas)) return true; + return false; } @@ -5637,7 +5708,7 @@ void *mas_next(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false); + return mas_next_slot(mas, max, false, true); } EXPORT_SYMBOL_GPL(mas_next); @@ -5660,7 +5731,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true); + return mas_next_slot(mas, max, true, true); } EXPORT_SYMBOL_GPL(mas_next_range); @@ -5691,18 +5762,31 @@ EXPORT_SYMBOL_GPL(mt_next); static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { - if (mas->index <= min) - goto none; + if (unlikely(mas->index <= min)) { + mas->node = MAS_UNDERFLOW; + return true; + } - if (mas_is_none(mas) || mas_is_paused(mas)) + if (mas_is_active(mas)) + return false; + + if (mas_is_overflow(mas)) { mas->node = MAS_START; + *entry = mas_walk(mas); + if (*entry) + return true; + } - if (mas_is_start(mas)) { - mas_walk(mas); - if (!mas->index) - goto none; + if (mas_is_none(mas) || mas_is_paused(mas)) { + mas->node = MAS_START; + } else if (mas_is_underflow(mas)) { + /* underflowed before but the min changed */ + mas->node = MAS_START; } + if (mas_is_start(mas)) + mas_walk(mas); + if (unlikely(mas_is_ptr(mas))) { if (!mas->index) goto none; @@ -5747,7 +5831,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, false); + return mas_prev_slot(mas, min, false, true); } EXPORT_SYMBOL_GPL(mas_prev); @@ -5770,7 +5854,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, true); + return mas_prev_slot(mas, min, true, true); } EXPORT_SYMBOL_GPL(mas_prev_range); @@ -5828,24 +5912,35 @@ EXPORT_SYMBOL_GPL(mas_pause); static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { - *entry = NULL; + if (mas_is_active(mas)) { + if (mas->last < max) + return false; - if (unlikely(mas_is_none(mas))) { + return true; + } + + if (mas_is_paused(mas)) { if (unlikely(mas->last >= max)) return true; - mas->index = mas->last; + mas->index = ++mas->last; mas->node = MAS_START; - } else if (unlikely(mas_is_paused(mas))) { + } else if (mas_is_none(mas)) { if (unlikely(mas->last >= max)) return true; + mas->index = mas->last; mas->node = MAS_START; - mas->index = ++mas->last; - } else if (unlikely(mas_is_ptr(mas))) - goto ptr_out_of_range; + } else if (mas_is_overflow(mas) || mas_is_underflow(mas)) { + if (mas->index > max) { + mas->node = MAS_OVERFLOW; + return true; + } + + mas->node = MAS_START; + } - if (unlikely(mas_is_start(mas))) { + if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; @@ -5895,7 +5990,7 @@ void *mas_find(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false); + return mas_next_slot(mas, max, false, false); } EXPORT_SYMBOL_GPL(mas_find); @@ -5913,13 +6008,13 @@ EXPORT_SYMBOL_GPL(mas_find); */ void *mas_find_range(struct ma_state *mas, unsigned long max) { - void *entry; + void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true); + return mas_next_slot(mas, max, true, false); } EXPORT_SYMBOL_GPL(mas_find_range); @@ -5934,26 +6029,36 @@ EXPORT_SYMBOL_GPL(mas_find_range); static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { - *entry = NULL; - - if (unlikely(mas_is_none(mas))) { - if (mas->index <= min) - goto none; + if (mas_is_active(mas)) { + if (mas->index > min) + return false; - mas->last = mas->index; - mas->node = MAS_START; + return true; } - if (unlikely(mas_is_paused(mas))) { + if (mas_is_paused(mas)) { if (unlikely(mas->index <= min)) { mas->node = MAS_NONE; return true; } mas->node = MAS_START; mas->last = --mas->index; + } else if (mas_is_none(mas)) { + if (mas->index <= min) + goto none; + + mas->last = mas->index; + mas->node = MAS_START; + } else if (mas_is_underflow(mas) || mas_is_overflow(mas)) { + if (mas->last <= min) { + mas->node = MAS_UNDERFLOW; + return true; + } + + mas->node = MAS_START; } - if (unlikely(mas_is_start(mas))) { + if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; @@ -6004,13 +6109,13 @@ none: */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { - void *entry; + void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, false); + return mas_prev_slot(mas, min, false, false); } EXPORT_SYMBOL_GPL(mas_find_rev); @@ -6030,13 +6135,13 @@ EXPORT_SYMBOL_GPL(mas_find_rev); */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { - void *entry; + void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, true); + return mas_prev_slot(mas, min, true, false); } EXPORT_SYMBOL_GPL(mas_find_range_rev); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index c65566b4dc66..68b45c82c37a 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -265,7 +265,8 @@ EXPORT_SYMBOL(sg_free_table); * @table: The sg table header to use * @nents: Number of entries in sg list * @max_ents: The maximum number of entries the allocator returns per call - * @nents_first_chunk: Number of entries int the (preallocated) first + * @first_chunk: first SGL if preallocated (may be %NULL) + * @nents_first_chunk: Number of entries in the (preallocated) first * scatterlist chunk, 0 means no such preallocated chunk provided by user * @gfp_mask: GFP allocation mask * @alloc_fn: Allocator to use @@ -788,6 +789,7 @@ EXPORT_SYMBOL(__sg_page_iter_dma_next); * @miter: sg mapping iter to be started * @sgl: sg list to iterate over * @nents: number of sg entries + * @flags: sg iterator flags * * Description: * Starts mapping iterator @miter. diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 0674aebd4423..06959165e2f9 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2166,7 +2166,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt) MT_BUG_ON(mt, val != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 5); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); mas.index = 0; mas.last = 5; @@ -2917,6 +2917,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * exists MAS_NONE active range * exists active active range * DNE active active set to last range + * ERANGE active MAS_OVERFLOW last range * * Function ENTRY Start Result index & last * mas_prev() @@ -2945,6 +2946,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * any MAS_ROOT MAS_NONE 0 * exists active active range * DNE active active last range + * ERANGE active MAS_UNDERFLOW last range * * Function ENTRY Start Result index & last * mas_find() @@ -2955,7 +2957,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE MAS_START MAS_NONE 0 * DNE MAS_PAUSE MAS_NONE 0 * DNE MAS_ROOT MAS_NONE 0 - * DNE MAS_NONE MAS_NONE 0 + * DNE MAS_NONE MAS_NONE 1 * if index == 0 * exists MAS_START MAS_ROOT 0 * exists MAS_PAUSE MAS_ROOT 0 @@ -2967,7 +2969,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE MAS_START active set to max * exists MAS_PAUSE active range * DNE MAS_PAUSE active set to max - * exists MAS_NONE active range + * exists MAS_NONE active range (start at last) * exists active active range * DNE active active last range (max < last) * @@ -2992,7 +2994,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE MAS_START active set to min * exists MAS_PAUSE active range * DNE MAS_PAUSE active set to min - * exists MAS_NONE active range + * exists MAS_NONE active range (start at index) * exists active active range * DNE active active last range (min > index) * @@ -3039,10 +3041,10 @@ static noinline void __init check_state_handling(struct maple_tree *mt) mtree_store_range(mt, 0, 0, ptr, GFP_KERNEL); mas_lock(&mas); - /* prev: Start -> none */ + /* prev: Start -> underflow*/ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); /* prev: Start -> root */ mas_set(&mas, 10); @@ -3069,7 +3071,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.node != MAS_NONE); - /* next: start -> none */ + /* next: start -> none*/ mas_set(&mas, 10); entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, mas.index != 1); @@ -3268,25 +3270,46 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x2500); MT_BUG_ON(mt, !mas_active(mas)); - /* next:active -> active out of range*/ + /* next:active -> active beyond data */ entry = mas_next(&mas, 0x2999); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x2501); MT_BUG_ON(mt, mas.last != 0x2fff); MT_BUG_ON(mt, !mas_active(mas)); - /* Continue after out of range*/ + /* Continue after last range ends after max */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); MT_BUG_ON(mt, !mas_active(mas)); - /* next:active -> active out of range*/ + /* next:active -> active continued */ + entry = mas_next(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x3501); + MT_BUG_ON(mt, mas.last != ULONG_MAX); + MT_BUG_ON(mt, !mas_active(mas)); + + /* next:active -> overflow */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); + MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + + /* next:overflow -> overflow */ + entry = mas_next(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x3501); + MT_BUG_ON(mt, mas.last != ULONG_MAX); + MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + + /* prev:overflow -> active */ + entry = mas_prev(&mas, 0); + MT_BUG_ON(mt, entry != ptr3); + MT_BUG_ON(mt, mas.index != 0x3000); + MT_BUG_ON(mt, mas.last != 0x3500); MT_BUG_ON(mt, !mas_active(mas)); /* next: none -> active, skip value at location */ @@ -3307,11 +3330,46 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x1500); MT_BUG_ON(mt, !mas_active(mas)); - /* prev:active -> active out of range*/ + /* prev:active -> active spanning end range */ + entry = mas_prev(&mas, 0x0100); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 0x0FFF); + MT_BUG_ON(mt, !mas_active(mas)); + + /* prev:active -> underflow */ + entry = mas_prev(&mas, 0); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 0x0FFF); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + + /* prev:underflow -> underflow */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + + /* next:underflow -> active */ + entry = mas_next(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != ptr); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, !mas_active(mas)); + + /* prev:first value -> underflow */ + entry = mas_prev(&mas, 0x1000); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + + /* find:underflow -> first value */ + entry = mas_find(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != ptr); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); MT_BUG_ON(mt, !mas_active(mas)); /* prev: pause ->active */ @@ -3325,14 +3383,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x2500); MT_BUG_ON(mt, !mas_active(mas)); - /* prev:active -> active out of range*/ + /* prev:active -> active spanning min */ entry = mas_prev(&mas, 0x1600); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1FFF); MT_BUG_ON(mt, !mas_active(mas)); - /* prev: active ->active, continue*/ + /* prev: active ->active, continue */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); @@ -3379,7 +3437,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x2FFF); MT_BUG_ON(mt, !mas_active(mas)); - /* find: none ->active */ + /* find: overflow ->active */ entry = mas_find(&mas, 0x5000); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); @@ -3778,7 +3836,6 @@ static int __init maple_tree_seed(void) check_empty_area_fill(&tree); mtree_destroy(&tree); - mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_state_handling(&tree); mtree_destroy(&tree); diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index c4b455b5ee30..dcf1ca6b31cc 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -148,6 +148,8 @@ static void damon_do_test_apply_three_regions(struct kunit *test, KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]); KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]); } + + damon_destroy_target(t); } /* diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 4c81a9dbd044..cf8a9fc5c9d1 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -341,13 +341,14 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, bool referenced = false; pte_t entry = huge_ptep_get(pte); struct folio *folio = pfn_folio(pte_pfn(entry)); + unsigned long psize = huge_page_size(hstate_vma(vma)); folio_get(folio); if (pte_young(entry)) { referenced = true; entry = pte_mkold(entry); - set_huge_pte_at(mm, addr, pte, entry); + set_huge_pte_at(mm, addr, pte, entry, psize); } #ifdef CONFIG_MMU_NOTIFIER diff --git a/mm/filemap.c b/mm/filemap.c index 582f5317ff71..f0a15ce1bd1b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3475,13 +3475,11 @@ skip: */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, - unsigned long addr, unsigned int nr_pages) + unsigned long addr, unsigned int nr_pages, + unsigned int *mmap_miss) { vm_fault_t ret = 0; - struct vm_area_struct *vma = vmf->vma; - struct file *file = vma->vm_file; struct page *page = folio_page(folio, start); - unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); unsigned int count = 0; pte_t *old_ptep = vmf->pte; @@ -3489,8 +3487,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, if (PageHWPoison(page + count)) goto skip; - if (mmap_miss > 0) - mmap_miss--; + (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be @@ -3506,7 +3503,7 @@ skip: if (count) { set_pte_range(vmf, folio, page, count, addr); folio_ref_add(folio, count); - if (in_range(vmf->address, addr, count)) + if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } @@ -3520,12 +3517,40 @@ skip: if (count) { set_pte_range(vmf, folio, page, count, addr); folio_ref_add(folio, count); - if (in_range(vmf->address, addr, count)) + if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; - WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); + + return ret; +} + +static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, + struct folio *folio, unsigned long addr, + unsigned int *mmap_miss) +{ + vm_fault_t ret = 0; + struct page *page = &folio->page; + + if (PageHWPoison(page)) + return ret; + + (*mmap_miss)++; + + /* + * NOTE: If there're PTE markers, we'll leave them to be + * handled in the specific fault path, and it'll prohibit + * the fault-around logic. + */ + if (!pte_none(ptep_get(vmf->pte))) + return ret; + + if (vmf->address == addr) + ret = VM_FAULT_NOPAGE; + + set_pte_range(vmf, folio, page, 1, addr); + folio_ref_inc(folio); return ret; } @@ -3541,7 +3566,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; - int nr_pages = 0; + unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); @@ -3569,25 +3594,27 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, end = folio->index + folio_nr_pages(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; - /* - * NOTE: If there're PTE markers, we'll leave them to be - * handled in the specific fault path, and it'll prohibit the - * fault-around logic. - */ - if (!pte_none(ptep_get(vmf->pte))) - goto unlock; - - ret |= filemap_map_folio_range(vmf, folio, - xas.xa_index - folio->index, addr, nr_pages); + if (!folio_test_large(folio)) + ret |= filemap_map_order0_folio(vmf, + folio, addr, &mmap_miss); + else + ret |= filemap_map_folio_range(vmf, folio, + xas.xa_index - folio->index, addr, + nr_pages, &mmap_miss); -unlock: folio_unlock(folio); folio_put(folio); - folio = next_uptodate_folio(&xas, mapping, end_pgoff); - } while (folio); + } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); + + mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); + if (mmap_miss >= mmap_miss_saved) + WRITE_ONCE(file->f_ra.mmap_miss, 0); + else + WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); + return ret; } EXPORT_SYMBOL(filemap_map_pages); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ba6d39b71cb1..52d26072dfda 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4980,7 +4980,7 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte) static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, - struct folio *new_folio, pte_t old) + struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); @@ -4988,7 +4988,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add hugepage_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); - set_huge_pte_at(vma->vm_mm, addr, ptep, newpte); + set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } @@ -5065,7 +5065,7 @@ again: } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(dst, addr, dst_pte, entry); + set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); @@ -5080,18 +5080,18 @@ again: entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); - set_huge_pte_at(src, addr, src_pte, entry); + set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(dst, addr, dst_pte, entry); + set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, - make_pte_marker(marker)); + make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_pte); pte_folio = page_folio(pte_page(entry)); @@ -5145,7 +5145,7 @@ again: goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, - new_folio, src_pte_old); + new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -5166,7 +5166,7 @@ again: if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(dst, addr, dst_pte, entry); + set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); @@ -5184,7 +5184,8 @@ again: } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte) + unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, + unsigned long sz) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; @@ -5202,7 +5203,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); - set_huge_pte_at(mm, new_addr, dst_pte, pte); + set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); if (src_ptl != dst_ptl) spin_unlock(src_ptl); @@ -5259,7 +5260,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (!dst_pte) break; - move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); + move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) @@ -5337,7 +5338,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP)); + make_pte_marker(PTE_MARKER_UFFD_WP), + sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); @@ -5371,7 +5373,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP)); + make_pte_marker(PTE_MARKER_UFFD_WP), + sz); hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); @@ -5676,7 +5679,7 @@ retry_avoidcopy: hugepage_add_new_anon_rmap(new_folio, vma, haddr); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); - set_huge_pte_at(mm, haddr, ptep, newpte); + set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; @@ -5972,7 +5975,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, */ if (unlikely(pte_marker_uffd_wp(old_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); - set_huge_pte_at(mm, haddr, ptep, new_pte); + set_huge_pte_at(mm, haddr, ptep, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { @@ -6261,7 +6264,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); - set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, + huge_page_size(h)); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); @@ -6412,7 +6416,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); - set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), dst_mm); @@ -6598,7 +6602,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) - set_huge_pte_at(mm, address, ptep, newpte); + set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* No other markers apply for now. */ WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); @@ -6623,7 +6627,8 @@ long hugetlb_change_protection(struct vm_area_struct *vma, if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP)); + make_pte_marker(PTE_MARKER_UFFD_WP), + psize); } spin_unlock(ptl); } diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index aa4a6a89cc54..8b06bab5c406 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -291,7 +291,7 @@ struct kasan_stack_ring { #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_shadow_to_mem static inline const void *kasan_shadow_to_mem(const void *shadow_addr) { return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET) @@ -299,15 +299,13 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) } #endif +#ifndef addr_has_metadata static __always_inline bool addr_has_metadata(const void *addr) { -#ifdef __HAVE_ARCH_SHADOW_MAP - return (kasan_mem_to_shadow((void *)addr) != NULL); -#else return (kasan_reset_tag(addr) >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START)); -#endif } +#endif /** * kasan_check_range - Check memory region, and report if invalid access. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a4d3282493b6..5b009b233ab8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2555,7 +2555,7 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg, * Scheduled by try_charge() to be executed from the userland return path * and reclaims memory over the high limit. */ -void mem_cgroup_handle_over_high(void) +void mem_cgroup_handle_over_high(gfp_t gfp_mask) { unsigned long penalty_jiffies; unsigned long pflags; @@ -2583,7 +2583,7 @@ retry_reclaim: */ nr_reclaimed = reclaim_high(memcg, in_retry ? SWAP_CLUSTER_MAX : nr_pages, - GFP_KERNEL); + gfp_mask); /* * memory.high is breached and reclaim is unable to keep up. Throttle @@ -2819,7 +2819,7 @@ done_restock: if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH && !(current->flags & PF_MEMALLOC) && gfpflags_allow_blocking(gfp_mask)) { - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(gfp_mask); } return 0; } @@ -3867,6 +3867,13 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, case _MEMSWAP: ret = mem_cgroup_resize_max(memcg, nr_pages, true); break; + case _KMEM: + pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. " + "Writing any value to this file has no effect. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + ret = 0; + break; case _TCP: ret = memcg_update_tcp_max(memcg, nr_pages); break; @@ -5078,6 +5085,12 @@ static struct cftype mem_cgroup_legacy_files[] = { }, #endif { + .name = "kmem.limit_in_bytes", + .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { .name = "kmem.usage_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE), .read_u64 = mem_cgroup_read_u64, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ unlock: * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out: diff --git a/mm/migrate.c b/mm/migrate.c index b7fa020003f3..2053b54556ca 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -243,7 +243,9 @@ static bool remove_migration_pte(struct folio *folio, #ifdef CONFIG_HUGETLB_PAGE if (folio_test_hugetlb(folio)) { - unsigned int shift = huge_page_shift(hstate_vma(vma)); + struct hstate *h = hstate_vma(vma); + unsigned int shift = huge_page_shift(h); + unsigned long psize = huge_page_size(h); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) @@ -251,7 +253,8 @@ static bool remove_migration_pte(struct folio *folio, rmap_flags); else page_dup_file_rmap(new, true); - set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); + set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, + psize); } else #endif { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0c5be12f9336..95546f376302 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2400,7 +2400,7 @@ void free_unref_page(struct page *page, unsigned int order) struct per_cpu_pages *pcp; struct zone *zone; unsigned long pfn = page_to_pfn(page); - int migratetype; + int migratetype, pcpmigratetype; if (!free_unref_page_prepare(page, pfn, order)) return; @@ -2408,24 +2408,24 @@ void free_unref_page(struct page *page, unsigned int order) /* * We only track unmovable, reclaimable and movable on pcp lists. * Place ISOLATE pages on the isolated list because they are being - * offlined but treat HIGHATOMIC as movable pages so we can get those - * areas back if necessary. Otherwise, we may have to free + * offlined but treat HIGHATOMIC and CMA as movable pages so we can + * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - migratetype = get_pcppage_migratetype(page); + migratetype = pcpmigratetype = get_pcppage_migratetype(page); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); return; } - migratetype = MIGRATE_MOVABLE; + pcpmigratetype = MIGRATE_MOVABLE; } zone = page_zone(page); pcp_trylock_prepare(UP_flags); pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { - free_unref_page_commit(zone, pcp, page, migratetype, order); + free_unref_page_commit(zone, pcp, page, pcpmigratetype, order); pcp_spin_unlock(pcp); } else { free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); diff --git a/mm/rmap.c b/mm/rmap.c index ec7f8e6c9e48..9f795b93cf40 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1480,6 +1480,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; + unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, @@ -1511,6 +1512,9 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + + /* We need the huge page size for set_huge_pte_at() */ + hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); @@ -1628,7 +1632,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, pteval, + hsz); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); @@ -1820,6 +1825,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; + unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, @@ -1855,6 +1861,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + + /* We need the huge page size for set_huge_pte_at() */ + hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); @@ -2020,7 +2029,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, pteval, + hsz); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); @@ -2044,7 +2054,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, + pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; @@ -2058,7 +2069,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (anon_exclusive && page_try_share_anon_rmap(subpage)) { if (folio_test_hugetlb(folio)) - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, + pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; @@ -2090,7 +2102,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); if (folio_test_hugetlb(folio)) - set_huge_pte_at(mm, address, pvmw.pte, swp_pte); + set_huge_pte_at(mm, address, pvmw.pte, swp_pte, + hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), diff --git a/mm/slab_common.c b/mm/slab_common.c index cd71f9581e67..8fda308e400d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -479,7 +479,7 @@ void slab_kmem_cache_release(struct kmem_cache *s) void kmem_cache_destroy(struct kmem_cache *s) { - int refcnt; + int err = -EBUSY; bool rcu_set; if (unlikely(!s) || !kasan_check_byte(s)) @@ -490,17 +490,17 @@ void kmem_cache_destroy(struct kmem_cache *s) rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU; - refcnt = --s->refcount; - if (refcnt) + s->refcount--; + if (s->refcount) goto out_unlock; - WARN(shutdown_cache(s), - "%s %s: Slab cache still has objects when called from %pS", + err = shutdown_cache(s); + WARN(err, "%s %s: Slab cache still has objects when called from %pS", __func__, s->name, (void *)_RET_IP_); out_unlock: mutex_unlock(&slab_mutex); cpus_read_unlock(); - if (!refcnt && !rcu_set) + if (!err && !rcu_set) kmem_cache_release(s); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -745,24 +745,24 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller) size_t kmalloc_size_roundup(size_t size) { - struct kmem_cache *c; + if (size && size <= KMALLOC_MAX_CACHE_SIZE) { + /* + * The flags don't matter since size_index is common to all. + * Neither does the caller for just getting ->object_size. + */ + return kmalloc_slab(size, GFP_KERNEL, 0)->object_size; + } - /* Short-circuit the 0 size case. */ - if (unlikely(size == 0)) - return 0; - /* Short-circuit saturated "too-large" case. */ - if (unlikely(size == SIZE_MAX)) - return SIZE_MAX; /* Above the smaller buckets, size is a multiple of page size. */ - if (size > KMALLOC_MAX_CACHE_SIZE) + if (size && size <= KMALLOC_MAX_SIZE) return PAGE_SIZE << get_order(size); /* - * The flags don't matter since size_index is common to all. - * Neither does the caller for just getting ->object_size. + * Return 'size' for 0 - kmalloc() returns ZERO_SIZE_PTR + * and very large size - kmalloc() may fail. */ - c = kmalloc_slab(size, GFP_KERNEL, 0); - return c ? c->object_size : 0; + return size; + } EXPORT_SYMBOL(kmalloc_size_roundup); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ef8599d394fd..a3fedb3ee0db 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -111,7 +111,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t entry = pfn_pte(pfn, prot); entry = arch_make_huge_pte(entry, ilog2(size), 0); - set_huge_pte_at(&init_mm, addr, pte, entry); + set_huge_pte_at(&init_mm, addr, pte, entry, size); pfn += PFN_DOWN(size); continue; } diff --git a/mm/zswap.c b/mm/zswap.c index 412b1409a0d7..083c693602b8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1219,6 +1219,19 @@ bool zswap_store(struct folio *folio) return false; /* + * If this is a duplicate, it must be removed before attempting to store + * it, otherwise, if the store fails the old page won't be removed from + * the tree, and it might be written back overriding the new data. + */ + spin_lock(&tree->lock); + dupentry = zswap_rb_search(&tree->rbroot, offset); + if (dupentry) { + zswap_duplicate_entry++; + zswap_invalidate_entry(tree, dupentry); + } + spin_unlock(&tree->lock); + + /* * XXX: zswap reclaim does not work with cgroups yet. Without a * cgroup-aware entry LRU, we will push out entries system-wide based on * local cgroup limits. @@ -1333,7 +1346,14 @@ insert_entry: /* map */ spin_lock(&tree->lock); + /* + * A duplicate entry should have been removed at the beginning of this + * function. Since the swap entry should be pinned, if a duplicate is + * found again here it means that something went wrong in the swap + * cache. + */ while (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) { + WARN_ON(1); zswap_duplicate_entry++; zswap_invalidate_entry(tree, dupentry); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 9d5057cef30a..7a6f20338db8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -2413,34 +2413,41 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, if (!test_bit(HCI_CONN_AUTH, &conn->flags)) goto auth; - /* An authenticated FIPS approved combination key has sufficient - * security for security level 4. */ - if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 && - sec_level == BT_SECURITY_FIPS) - goto encrypt; - - /* An authenticated combination key has sufficient security for - security level 3. */ - if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 || - conn->key_type == HCI_LK_AUTH_COMBINATION_P256) && - sec_level == BT_SECURITY_HIGH) - goto encrypt; - - /* An unauthenticated combination key has sufficient security for - security level 1 and 2. */ - if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 || - conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) && - (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW)) - goto encrypt; - - /* A combination key has always sufficient security for the security - levels 1 or 2. High security level requires the combination key - is generated using maximum PIN code length (16). - For pre 2.1 units. */ - if (conn->key_type == HCI_LK_COMBINATION && - (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW || - conn->pin_length == 16)) - goto encrypt; + switch (conn->key_type) { + case HCI_LK_AUTH_COMBINATION_P256: + /* An authenticated FIPS approved combination key has + * sufficient security for security level 4 or lower. + */ + if (sec_level <= BT_SECURITY_FIPS) + goto encrypt; + break; + case HCI_LK_AUTH_COMBINATION_P192: + /* An authenticated combination key has sufficient security for + * security level 3 or lower. + */ + if (sec_level <= BT_SECURITY_HIGH) + goto encrypt; + break; + case HCI_LK_UNAUTH_COMBINATION_P192: + case HCI_LK_UNAUTH_COMBINATION_P256: + /* An unauthenticated combination key has sufficient security + * for security level 2 or lower. + */ + if (sec_level <= BT_SECURITY_MEDIUM) + goto encrypt; + break; + case HCI_LK_COMBINATION: + /* A combination key has always sufficient security for the + * security levels 2 or lower. High security level requires the + * combination key is generated using maximum PIN code length + * (16). For pre 2.1 units. + */ + if (sec_level <= BT_SECURITY_MEDIUM || conn->pin_length == 16) + goto encrypt; + break; + default: + break; + } auth: if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a5992f1b3c9b..195aea2198a9 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2617,7 +2617,11 @@ int hci_register_dev(struct hci_dev *hdev) if (id < 0) return id; - snprintf(hdev->name, sizeof(hdev->name), "hci%d", id); + error = dev_set_name(&hdev->dev, "hci%u", id); + if (error) + return error; + + hdev->name = dev_name(&hdev->dev); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); @@ -2639,8 +2643,6 @@ int hci_register_dev(struct hci_dev *hdev) if (!IS_ERR_OR_NULL(bt_debugfs)) hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs); - dev_set_name(&hdev->dev, "%s", hdev->name); - error = device_add(&hdev->dev); if (error < 0) goto err_wqueue; @@ -2784,6 +2786,7 @@ void hci_release_dev(struct hci_dev *hdev) hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); + hci_codec_list_clear(&hdev->local_codecs); hci_dev_unlock(hdev); ida_simple_remove(&hci_index_ida, hdev->id); @@ -3418,7 +3421,12 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); + /* hci_disconnect might sleep, so, we have to release + * the RCU read lock before calling it. + */ + rcu_read_unlock(); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); + rcu_read_lock(); } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 35f251041eeb..31d02b54eea1 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -33,6 +33,7 @@ #include "hci_request.h" #include "hci_debugfs.h" +#include "hci_codec.h" #include "a2mp.h" #include "amp.h" #include "smp.h" diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index b9c5a9823837..0be75cf0efed 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -71,7 +71,5 @@ struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn); void hci_req_add_le_passive_scan(struct hci_request *req); -void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next); - void hci_request_setup(struct hci_dev *hdev); void hci_request_cancel_all(struct hci_dev *hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 9b93653c6197..d06e07a0ea5a 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -413,11 +413,6 @@ static int hci_le_scan_restart_sync(struct hci_dev *hdev) LE_SCAN_FILTER_DUP_ENABLE); } -static int le_scan_restart_sync(struct hci_dev *hdev, void *data) -{ - return hci_le_scan_restart_sync(hdev); -} - static void le_scan_restart(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -427,15 +422,15 @@ static void le_scan_restart(struct work_struct *work) bt_dev_dbg(hdev, ""); - hci_dev_lock(hdev); - - status = hci_cmd_sync_queue(hdev, le_scan_restart_sync, NULL, NULL); + status = hci_le_scan_restart_sync(hdev); if (status) { bt_dev_err(hdev, "failed to restart LE scan: status %d", status); - goto unlock; + return; } + hci_dev_lock(hdev); + if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) || !hdev->discovery.scan_start) goto unlock; @@ -5079,6 +5074,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); bacpy(&hdev->random_addr, BDADDR_ANY); + hci_codec_list_clear(&hdev->local_codecs); hci_dev_put(hdev); return err; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 16da946f5881..71248163ce9a 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -502,7 +502,7 @@ drop: } /* -------- Socket interface ---------- */ -static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *ba) +static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *src, bdaddr_t *dst) { struct sock *sk; @@ -510,7 +510,10 @@ static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *ba) if (sk->sk_state != BT_LISTEN) continue; - if (!bacmp(&iso_pi(sk)->src, ba)) + if (bacmp(&iso_pi(sk)->dst, dst)) + continue; + + if (!bacmp(&iso_pi(sk)->src, src)) return sk; } @@ -952,7 +955,7 @@ static int iso_listen_cis(struct sock *sk) write_lock(&iso_sk_list.lock); - if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src)) + if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src, &iso_pi(sk)->dst)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 15186247b59a..033034d68f1f 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -294,7 +294,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ /* tell br_dev_xmit to continue with forwarding */ nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ - ret = neigh->output(neigh, skb); + ret = READ_ONCE(neigh->output)(neigh, skb); } neigh_release(neigh); return ret; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6b76cd103195..9c09f091cbff 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -410,7 +410,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, */ __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; - n->output = neigh_blackhole; + WRITE_ONCE(n->output, neigh_blackhole); if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else @@ -920,7 +920,7 @@ static void neigh_suspect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is suspected\n", neigh); - neigh->output = neigh->ops->output; + WRITE_ONCE(neigh->output, neigh->ops->output); } /* Neighbour state is OK; @@ -932,7 +932,7 @@ static void neigh_connect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is connected\n", neigh); - neigh->output = neigh->ops->connected_output; + WRITE_ONCE(neigh->output, neigh->ops->connected_output); } static void neigh_periodic_work(struct work_struct *work) @@ -988,7 +988,9 @@ static void neigh_periodic_work(struct work_struct *work) (state == NUD_FAILED || !time_in_range_open(jiffies, n->used, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); write_unlock(&n->lock); neigh_cleanup_and_release(n); @@ -1447,7 +1449,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, if (n2) n1 = n2; } - n1->output(n1, skb); + READ_ONCE(n1->output)(n1, skb); if (n2) neigh_release(n2); rcu_read_unlock(); @@ -3153,7 +3155,7 @@ int neigh_xmit(int index, struct net_device *dev, rcu_read_unlock(); goto out_kfree_skb; } - err = neigh->output(neigh, skb); + err = READ_ONCE(neigh->output)(neigh, skb); rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { diff --git a/net/core/sock_map.c b/net/core/sock_map.c index cb11750b1df5..4292c2ed1828 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; @@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index b238a1afe9ae..b1e2e3b5027f 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -21,16 +21,6 @@ struct plca_reply_data { #define PLCA_REPDATA(__reply_base) \ container_of(__reply_base, struct plca_reply_data, base) -static void plca_update_sint(int *dst, const struct nlattr *attr, - bool *mod) -{ - if (!attr) - return; - - *dst = nla_get_u32(attr); - *mod = true; -} - // PLCA get configuration message ------------------------------------------- // const struct nla_policy ethnl_plca_get_cfg_policy[] = { @@ -38,6 +28,29 @@ const struct nla_policy ethnl_plca_get_cfg_policy[] = { NLA_POLICY_NESTED(ethnl_header_policy), }; +static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, + bool *mod) +{ + const struct nlattr *attr = tb[attrid]; + + if (!attr || + WARN_ON_ONCE(attrid >= ARRAY_SIZE(ethnl_plca_set_cfg_policy))) + return; + + switch (ethnl_plca_set_cfg_policy[attrid].type) { + case NLA_U8: + *dst = nla_get_u8(attr); + break; + case NLA_U32: + *dst = nla_get_u32(attr); + break; + default: + WARN_ON_ONCE(1); + } + + *mod = true; +} + static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) @@ -144,13 +157,13 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) return -EOPNOTSUPP; memset(&plca_cfg, 0xff, sizeof(plca_cfg)); - plca_update_sint(&plca_cfg.enabled, tb[ETHTOOL_A_PLCA_ENABLED], &mod); - plca_update_sint(&plca_cfg.node_id, tb[ETHTOOL_A_PLCA_NODE_ID], &mod); - plca_update_sint(&plca_cfg.node_cnt, tb[ETHTOOL_A_PLCA_NODE_CNT], &mod); - plca_update_sint(&plca_cfg.to_tmr, tb[ETHTOOL_A_PLCA_TO_TMR], &mod); - plca_update_sint(&plca_cfg.burst_cnt, tb[ETHTOOL_A_PLCA_BURST_CNT], + plca_update_sint(&plca_cfg.enabled, tb, ETHTOOL_A_PLCA_ENABLED, &mod); + plca_update_sint(&plca_cfg.node_id, tb, ETHTOOL_A_PLCA_NODE_ID, &mod); + plca_update_sint(&plca_cfg.node_cnt, tb, ETHTOOL_A_PLCA_NODE_CNT, &mod); + plca_update_sint(&plca_cfg.to_tmr, tb, ETHTOOL_A_PLCA_TO_TMR, &mod); + plca_update_sint(&plca_cfg.burst_cnt, tb, ETHTOOL_A_PLCA_BURST_CNT, &mod); - plca_update_sint(&plca_cfg.burst_tmr, tb[ETHTOOL_A_PLCA_BURST_TMR], + plca_update_sint(&plca_cfg.burst_tmr, tb, ETHTOOL_A_PLCA_BURST_TMR, &mod); if (!mod) return 0; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index eafa4a033515..1ea82bc33ef1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1887,6 +1887,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; + fi->pfsrc_removed = true; ret++; } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d13fb9e76b97..9bdfdab906fe 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2027,6 +2027,7 @@ void fib_table_flush_external(struct fib_table *tb) int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; + struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; @@ -2089,6 +2090,9 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); + if (fi->pfsrc_removed) + rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, + KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ac332e2e4fff..e2bf4602b559 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3417,6 +3417,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = + READ_ONCE(fa->offload_failed); break; } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e54f91eb943b..9a8b134d8ada 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1621,16 +1621,13 @@ EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; struct sk_buff *skb; int copied = 0; - u32 offset; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; @@ -1643,13 +1640,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) copied = used; break; } - seq += used; copied += used; - if (tcp_flags & TCPHDR_FIN) { - ++seq; + if (tcp_flags & TCPHDR_FIN) break; - } } return copied; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 81f0dff69e0b..327268203001 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -222,6 +222,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int *addr_len) { struct tcp_sock *tcp = tcp_sk(sk); + int peek = flags & MSG_PEEK; u32 seq = tcp->copied_seq; struct sk_psock *psock; int copied = 0; @@ -311,7 +312,8 @@ msg_bytes_ready: copied = -EAGAIN; } out: - WRITE_ONCE(tcp->copied_seq, seq); + if (!peek) + WRITE_ONCE(tcp->copied_seq, seq); tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 22c2a7c2e65e..4b8f2e74d71d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -253,6 +253,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); + /* If the skb has a len of exactly 1*MSS and has the PSH bit + * set then it is likely the end of an application write. So + * more data may not be arriving soon, and yet the data sender + * may be waiting for an ACK if cwnd-bound or using TX zero + * copy. So we set ICSK_ACK_PUSHED here so that + * tcp_cleanup_rbuf() will send an ACK immediately if the app + * reads all of the data and is not ping-pong. If len > MSS + * then this logic does not matter (and does not hurt) because + * tcp_cleanup_rbuf() will always ACK immediately if the app + * reads data and there is more than an MSS of unACKed data. + */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8885552dff8e..f207712eece1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -177,8 +177,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1380,7 +1379,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8a6e2e97f673..bfe7d19ff4fd 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1639,9 +1639,12 @@ process: struct sock *nsk; sk = req->rsk_listener; - drop_reason = tcp_inbound_md5_hash(sk, skb, - &hdr->saddr, &hdr->daddr, - AF_INET6, dif, sdif); + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + drop_reason = SKB_DROP_REASON_XFRM_POLICY; + else + drop_reason = tcp_inbound_md5_hash(sk, skb, + &hdr->saddr, &hdr->daddr, + AF_INET6, dif, sdif); if (drop_reason) { sk_drops_add(sk, skb); reqsk_put(req); @@ -1688,6 +1691,7 @@ process: } goto discard_and_relse; } + nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 44cfb72bbd18..bb373e249237 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -507,7 +507,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ if (len > INT_MAX - transhdrlen) return -EMSGSIZE; - ulen = len + transhdrlen; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) @@ -628,6 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); + ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 45e7a5d9c7d9..0e3a1753a51c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -566,6 +566,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, } err = ieee80211_key_link(key, link, sta); + /* KRACK protection, shouldn't happen but just silently accept key */ + if (err == -EALREADY) + err = 0; out_unlock: mutex_unlock(&local->sta_mtx); @@ -1857,7 +1860,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, - params->vht_capa, link_sta); + params->vht_capa, NULL, + link_sta); if (params->he_capa) ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index e1900077bc4b..5542c93edfba 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1072,7 +1072,7 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, &chandef); memcpy(&cap_ie, elems->vht_cap_elem, sizeof(cap_ie)); ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, - &cap_ie, + &cap_ie, NULL, &sta->deflink); if (memcmp(&cap, &sta->sta.deflink.vht_cap, sizeof(cap))) rates_updated |= true; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 06bd406846d2..98ef1fe1226e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -676,7 +676,7 @@ struct ieee80211_if_mesh { struct timer_list mesh_path_root_timer; unsigned long wrkq_flags; - unsigned long mbss_changed; + unsigned long mbss_changed[64 / BITS_PER_LONG]; bool userspace_handles_dfs; @@ -2141,6 +2141,7 @@ void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_vht_cap *vht_cap_ie, + const struct ieee80211_vht_cap *vht_cap_ie2, struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 13050dc9321f..0665ff5e456e 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -802,6 +802,9 @@ static void ieee80211_key_destroy(struct ieee80211_key *key, void ieee80211_key_free_unused(struct ieee80211_key *key) { + if (!key) + return; + WARN_ON(key->sdata || key->local); ieee80211_key_free_common(key); } @@ -854,7 +857,7 @@ int ieee80211_key_link(struct ieee80211_key *key, * can cause warnings to appear. */ bool delay_tailroom = sdata->vif.type == NL80211_IFTYPE_STATION; - int ret = -EOPNOTSUPP; + int ret; mutex_lock(&sdata->local->key_mtx); @@ -868,8 +871,10 @@ int ieee80211_key_link(struct ieee80211_key *key, * the same cipher. Enforce the assumption for pairwise keys. */ if ((alt_key && alt_key->conf.cipher != key->conf.cipher) || - (old_key && old_key->conf.cipher != key->conf.cipher)) + (old_key && old_key->conf.cipher != key->conf.cipher)) { + ret = -EOPNOTSUPP; goto out; + } } else if (sta) { struct link_sta_info *link_sta = &sta->deflink; int link_id = key->conf.link_id; @@ -895,8 +900,10 @@ int ieee80211_key_link(struct ieee80211_key *key, /* Non-pairwise keys must also not switch the cipher on rekey */ if (!pairwise) { - if (old_key && old_key->conf.cipher != key->conf.cipher) + if (old_key && old_key->conf.cipher != key->conf.cipher) { + ret = -EOPNOTSUPP; goto out; + } } /* @@ -904,9 +911,8 @@ int ieee80211_key_link(struct ieee80211_key *key, * new version of the key to avoid nonce reuse or replay issues. */ if (ieee80211_key_identical(sdata, old_key, key)) { - ieee80211_key_free_unused(key); - ret = 0; - goto out; + ret = -EALREADY; + goto unlock; } key->local = sdata->local; @@ -930,7 +936,11 @@ int ieee80211_key_link(struct ieee80211_key *key, ieee80211_key_free(key, delay_tailroom); } + key = NULL; + out: + ieee80211_key_free_unused(key); + unlock: mutex_unlock(&sdata->local->key_mtx); return ret; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index af8c5fc2db14..e31c312c124a 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1175,7 +1175,7 @@ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, /* if we race with running work, worst case this work becomes a noop */ for_each_set_bit(bit, &bits, sizeof(changed) * BITS_PER_BYTE) - set_bit(bit, &ifmsh->mbss_changed); + set_bit(bit, ifmsh->mbss_changed); set_bit(MESH_WORK_MBSS_CHANGED, &ifmsh->wrkq_flags); wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work); } @@ -1257,7 +1257,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) /* clear any mesh work (for next join) we may have accrued */ ifmsh->wrkq_flags = 0; - ifmsh->mbss_changed = 0; + memset(ifmsh->mbss_changed, 0, sizeof(ifmsh->mbss_changed)); local->fif_other_bss--; atomic_dec(&local->iff_allmultis); @@ -1724,9 +1724,9 @@ static void mesh_bss_info_changed(struct ieee80211_sub_if_data *sdata) u32 bit; u64 changed = 0; - for_each_set_bit(bit, &ifmsh->mbss_changed, + for_each_set_bit(bit, ifmsh->mbss_changed, sizeof(changed) * BITS_PER_BYTE) { - clear_bit(bit, &ifmsh->mbss_changed); + clear_bit(bit, ifmsh->mbss_changed); changed |= BIT(bit); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index f3d5bb0a59f1..a1e526419e9d 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -451,7 +451,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, changed |= IEEE80211_RC_BW_CHANGED; ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, - elems->vht_cap_elem, + elems->vht_cap_elem, NULL, &sta->deflink); ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, elems->he_cap, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index f93eb38ae0b8..0c9198997482 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4202,10 +4202,33 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, elems->ht_cap_elem, link_sta); - if (elems->vht_cap_elem && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) + if (elems->vht_cap_elem && + !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) { + const struct ieee80211_vht_cap *bss_vht_cap = NULL; + const struct cfg80211_bss_ies *ies; + + /* + * Cisco AP module 9115 with FW 17.3 has a bug and sends a + * too large maximum MPDU length in the association response + * (indicating 12k) that it cannot actually process ... + * Work around that. + */ + rcu_read_lock(); + ies = rcu_dereference(cbss->ies); + if (ies) { + const struct element *elem; + + elem = cfg80211_find_elem(WLAN_EID_VHT_CAPABILITY, + ies->data, ies->len); + if (elem && elem->datalen >= sizeof(*bss_vht_cap)) + bss_vht_cap = (const void *)elem->data; + } + ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, elems->vht_cap_elem, - link_sta); + bss_vht_cap, link_sta); + rcu_read_unlock(); + } if (elems->he_operation && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && elems->he_cap) { @@ -5107,9 +5130,10 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, continue; valid_links |= BIT(link_id); - if (assoc_data->link[link_id].disabled) { + if (assoc_data->link[link_id].disabled) dormant_links |= BIT(link_id); - } else if (link_id != assoc_data->assoc_link_id) { + + if (link_id != assoc_data->assoc_link_id) { err = ieee80211_sta_allocate_link(sta, link_id); if (err) goto out_err; @@ -5124,7 +5148,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link; struct link_sta_info *link_sta; - if (!cbss || assoc_data->link[link_id].disabled) + if (!cbss) continue; link = sdata_dereference(sdata->link[link_id], sdata); @@ -5429,17 +5453,18 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct ieee80211_link_data *link; - link = sdata_dereference(sdata->link[link_id], sdata); - if (!link) - continue; - if (!assoc_data->link[link_id].bss) continue; resp.links[link_id].bss = assoc_data->link[link_id].bss; - resp.links[link_id].addr = link->conf->addr; + ether_addr_copy(resp.links[link_id].addr, + assoc_data->link[link_id].addr); resp.links[link_id].status = assoc_data->link[link_id].status; + link = sdata_dereference(sdata->link[link_id], sdata); + if (!link) + continue; + /* get uapsd queues configuration - same for all links */ resp.uapsd_queues = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 7fe7280e8437..d45d4be63dd8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -665,7 +665,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) } if (unlikely(tx->key && tx->key->flags & KEY_FLAG_TAINTED && - !ieee80211_is_deauth(hdr->frame_control))) + !ieee80211_is_deauth(hdr->frame_control)) && + tx->skb->protocol != tx->sdata->control_port_protocol) return TX_DROP; if (!skip_hw && tx->key && diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index c1250aa47808..b3a5c3e96a72 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -4,7 +4,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2022 Intel Corporation + * Copyright (C) 2018 - 2023 Intel Corporation */ #include <linux/ieee80211.h> @@ -116,12 +116,14 @@ void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_vht_cap *vht_cap_ie, + const struct ieee80211_vht_cap *vht_cap_ie2, struct link_sta_info *link_sta) { struct ieee80211_sta_vht_cap *vht_cap = &link_sta->pub->vht_cap; struct ieee80211_sta_vht_cap own_cap; u32 cap_info, i; bool have_80mhz; + u32 mpdu_len; memset(vht_cap, 0, sizeof(*vht_cap)); @@ -318,10 +320,20 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, link_sta->pub->bandwidth = ieee80211_sta_cur_vht_bw(link_sta); /* + * Work around the Cisco 9115 FW 17.3 bug by taking the min of + * both reported MPDU lengths. + */ + mpdu_len = vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK; + if (vht_cap_ie2) + mpdu_len = min_t(u32, mpdu_len, + le32_get_bits(vht_cap_ie2->vht_cap_info, + IEEE80211_VHT_CAP_MAX_MPDU_MASK)); + + /* * FIXME - should the amsdu len be per link? store per link * and maintain a minimum? */ - switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) { + switch (mpdu_len) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: link_sta->pub->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; break; diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index b5a8aa4c1ebd..d042d32beb4d 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -307,12 +307,6 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } - if (addr_l.id == 0) { - NL_SET_ERR_MSG_ATTR(info->extack, laddr, "missing local addr id"); - err = -EINVAL; - goto create_err; - } - err = mptcp_pm_parse_addr(raddr, info, &addr_r); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr"); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e252539b1e19..c3b83cb390d9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3425,24 +3425,21 @@ static void schedule_3rdack_retransmission(struct sock *ssk) sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); } -void mptcp_subflow_process_delegated(struct sock *ssk) +void mptcp_subflow_process_delegated(struct sock *ssk, long status) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (status & BIT(MPTCP_DELEGATE_SEND)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); } - if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); - mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); - } } static int mptcp_hash(struct sock *sk) @@ -3968,14 +3965,17 @@ static int mptcp_napi_poll(struct napi_struct *napi, int budget) struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bh_lock_sock_nested(ssk); - if (!sock_owned_by_user(ssk) && - mptcp_subflow_has_delegated_action(subflow)) - mptcp_subflow_process_delegated(ssk); - /* ... elsewhere tcp_release_cb_override already processed - * the action or will do at next release_sock(). - * In both case must dequeue the subflow here - on the same - * CPU that scheduled it. - */ + if (!sock_owned_by_user(ssk)) { + mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0)); + } else { + /* tcp_release_cb_override already processed + * the action or will do at next release_sock(). + * In both case must dequeue the subflow here - on the same + * CPU that scheduled it. + */ + smp_wmb(); + clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status); + } bh_unlock_sock(ssk); sock_put(ssk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ed61d6850cce..3612545fa62e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -444,9 +444,11 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); -#define MPTCP_DELEGATE_SEND 0 -#define MPTCP_DELEGATE_ACK 1 +#define MPTCP_DELEGATE_SCHEDULED 0 +#define MPTCP_DELEGATE_SEND 1 +#define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ struct mptcp_subflow_context { struct list_head node;/* conn_list of subflows */ @@ -564,23 +566,24 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow) return subflow->map_seq + mptcp_subflow_get_map_offset(subflow); } -void mptcp_subflow_process_delegated(struct sock *ssk); +void mptcp_subflow_process_delegated(struct sock *ssk, long actions); static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { + long old, set_bits = BIT(MPTCP_DELEGATE_SCHEDULED) | BIT(action); struct mptcp_delegated_action *delegated; bool schedule; /* the caller held the subflow bh socket lock */ lockdep_assert_in_softirq(); - /* The implied barrier pairs with mptcp_subflow_delegated_done(), and - * ensures the below list check sees list updates done prior to status - * bit changes + /* The implied barrier pairs with tcp_release_cb_override() + * mptcp_napi_poll(), and ensures the below list check sees list + * updates done prior to delegated status bits changes */ - if (!test_and_set_bit(action, &subflow->delegated_status)) { - /* still on delegated list from previous scheduling */ - if (!list_empty(&subflow->delegated_node)) + old = set_mask_bits(&subflow->delegated_status, 0, set_bits); + if (!(old & BIT(MPTCP_DELEGATE_SCHEDULED))) { + if (WARN_ON_ONCE(!list_empty(&subflow->delegated_node))) return; delegated = this_cpu_ptr(&mptcp_delegated_actions); @@ -605,20 +608,6 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) return ret; } -static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) -{ - return !!READ_ONCE(subflow->delegated_status); -} - -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) -{ - /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before - * touching the status bit - */ - smp_wmb(); - clear_bit(action, &subflow->delegated_status); -} - int mptcp_is_enabled(const struct net *net); unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 918c1a235790..9c1f8d1d63d2 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1956,9 +1956,15 @@ static void subflow_ulp_clone(const struct request_sock *req, static void tcp_release_cb_override(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + long status; - if (mptcp_subflow_has_delegated_action(subflow)) - mptcp_subflow_process_delegated(ssk); + /* process and clear all the pending actions, but leave the subflow into + * the napi queue. To respect locking, only the same CPU that originated + * the action can touch the list. mptcp_napi_poll will take care of it. + */ + status = set_mask_bits(&subflow->delegated_status, MPTCP_DELEGATE_ACTIONS_MASK, 0); + if (status) + mptcp_subflow_process_delegated(ssk, status); tcp_release_cb(ssk); } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 4f6c795588fb..eaf9f2ed0067 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1435,7 +1435,7 @@ static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) sin.sin_addr.s_addr = addr; sin.sin_port = 0; - return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin)); + return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin)); } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, @@ -1501,8 +1501,8 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id, } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); - result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr, - salen, 0); + result = kernel_connect(sock, (struct sockaddr *)&mcast_addr, + salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; @@ -1542,7 +1542,7 @@ static int make_receive_sock(struct netns_ipvs *ipvs, int id, get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); sock->sk->sk_bound_dev_if = dev->ifindex; - result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); + result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index b6bcc8f2f46b..c6bd533983c1 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, /* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, /* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, /* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -412,6 +412,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; + } else if (sch->type == SCTP_CID_COOKIE_ACK) { + ct->proto.sctp.init[dir] = 0; + ct->proto.sctp.init[!dir] = 0; } else if (sch->type == SCTP_CID_HEARTBEAT) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); @@ -461,16 +464,18 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } /* If it is an INIT or an INIT ACK note down the vtag */ - if (sch->type == SCTP_CID_INIT || - sch->type == SCTP_CID_INIT_ACK) { - struct sctp_inithdr _inithdr, *ih; + if (sch->type == SCTP_CID_INIT) { + struct sctp_inithdr _ih, *ih; - ih = skb_header_pointer(skb, offset + sizeof(_sch), - sizeof(_inithdr), &_inithdr); - if (ih == NULL) + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) goto out_unlock; - pr_debug("Setting vtag %x for dir %d\n", - ih->init_tag, !dir); + + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) + ct->proto.sctp.init[!dir] = 0; + ct->proto.sctp.init[dir] = 1; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; /* don't renew timeout on init retransmit so @@ -481,6 +486,24 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, old_state == SCTP_CONNTRACK_CLOSED && nf_ct_is_confirmed(ct)) ignore = true; + } else if (sch->type == SCTP_CID_INIT_ACK) { + struct sctp_inithdr _ih, *ih; + __be32 vtag; + + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) + goto out_unlock; + + vtag = ct->proto.sctp.vtag[!dir]; + if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag) + goto out_unlock; + /* collision */ + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && + vtag != ih->init_tag) + goto out_unlock; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); + ct->proto.sctp.vtag[!dir] = ih->init_tag; } ct->proto.sctp.state = new_state; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7e2e76086d25..b4405db710b0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7879,24 +7879,14 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, return nft_delobj(&ctx, obj); } -void nft_obj_notify(struct net *net, const struct nft_table *table, - struct nft_object *obj, u32 portid, u32 seq, int event, - u16 flags, int family, int report, gfp_t gfp) +static void +__nft_obj_notify(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; - char *buf = kasprintf(gfp, "%s:%u", - table->name, nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - obj->handle, - event == NFT_MSG_NEWOBJ ? - AUDIT_NFT_OP_OBJ_REGISTER : - AUDIT_NFT_OP_OBJ_UNREGISTER, - gfp); - kfree(buf); if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -7919,13 +7909,35 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } + +void nft_obj_notify(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + char *buf = kasprintf(gfp, "%s:%u", + table->name, nft_net->base_seq); + + audit_log_nfcfg(buf, + family, + obj->handle, + event == NFT_MSG_NEWOBJ ? + AUDIT_NFT_OP_OBJ_REGISTER : + AUDIT_NFT_OP_OBJ_UNREGISTER, + gfp); + kfree(buf); + + __nft_obj_notify(net, table, obj, portid, seq, event, + flags, family, report, gfp); +} EXPORT_SYMBOL_GPL(nft_obj_notify); static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { - nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->flags, ctx->family, ctx->report, GFP_KERNEL); + __nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, + ctx->seq, event, ctx->flags, ctx->family, + ctx->report, GFP_KERNEL); } /* diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 8cb800989947..120f6d395b98 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -154,6 +154,17 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt) return pkt->inneroff; } +static bool nft_payload_need_vlan_copy(const struct nft_payload *priv) +{ + unsigned int len = priv->offset + priv->len; + + /* data past ether src/dst requested, copy needed */ + if (len > offsetof(struct ethhdr, h_proto)) + return true; + + return false; +} + void nft_payload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -172,7 +183,7 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; if (skb_vlan_tag_present(skb) && - priv->offset >= offsetof(struct ethhdr, h_proto)) { + nft_payload_need_vlan_copy(priv)) { if (!nft_payload_copy_vlan(dest, skb, priv->offset, priv->len)) goto err; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 487572dcd614..2660ceab3759 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -233,10 +233,9 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, rb_erase(&rbe->node, &priv->root); } -static int nft_rbtree_gc_elem(const struct nft_set *__set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, - u8 genmask) +static const struct nft_rbtree_elem * +nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe, u8 genmask) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -246,7 +245,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); if (!gc) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they @@ -261,6 +260,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, prev = rb_prev(prev); } + rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); nft_rbtree_gc_remove(net, set, priv, rbe_prev); @@ -272,7 +272,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, */ gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe_prev); } @@ -280,13 +280,13 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, nft_rbtree_gc_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe); nft_trans_gc_queue_sync_done(gc); - return 0; + return rbe_prev; } static bool nft_rbtree_update_first(const struct nft_set *set, @@ -314,7 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); - int d, err; + int d; /* Descend the tree to search for an existing element greater than the * key value to insert that is greater than the new element. This is the @@ -363,9 +363,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (nft_set_elem_expired(&rbe->ext) && nft_set_elem_active(&rbe->ext, cur_genmask)) { - err = nft_rbtree_gc_elem(set, priv, rbe, genmask); - if (err < 0) - return err; + const struct nft_rbtree_elem *removed_end; + + removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + if (IS_ERR(removed_end)) + return PTR_ERR(removed_end); + + if (removed_end == rbe_le || removed_end == rbe_ge) + return -EAGAIN; continue; } @@ -486,11 +491,18 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *rbe = elem->priv; int err; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); - err = __nft_rbtree_insert(net, set, rbe, ext); - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + do { + if (fatal_signal_pending(current)) + return -EINTR; + + cond_resched(); + + write_lock_bh(&priv->lock); + write_seqcount_begin(&priv->count); + err = __nft_rbtree_insert(net, set, rbe, ext); + write_seqcount_end(&priv->count); + write_unlock_bh(&priv->lock); + } while (err == -EAGAIN); return err; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 642b9d382fb4..eb086b06d60d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -352,7 +352,7 @@ static void netlink_overrun(struct sock *sk) if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { - sk->sk_err = ENOBUFS; + WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } @@ -1605,7 +1605,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) goto out; } - sk->sk_err = p->code; + WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; @@ -1991,7 +1991,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { - sk->sk_err = -ret; + WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } @@ -2511,7 +2511,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, err_bad_put: nlmsg_free(skb); err_skb: - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index f60e424e0607..6705bb895e23 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -1636,7 +1636,9 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) timer_setup(&local->sdreq_timer, nfc_llcp_sdreq_timer, 0); INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work); + spin_lock(&llcp_devices_lock); list_add(&local->list, &llcp_devices); + spin_unlock(&llcp_devices_lock); return 0; } diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index f0c477c5d1db..a0046e99d6df 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -145,7 +145,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) addrlen = sizeof(sin); } - ret = sock->ops->bind(sock, addr, addrlen); + ret = kernel_bind(sock, addr, addrlen); if (ret) { rdsdebug("bind failed with %d at address %pI6c\n", ret, &conn->c_laddr); @@ -173,7 +173,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) * own the socket */ rds_tcp_set_callbacks(sock, cp); - ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK); + ret = kernel_connect(sock, addr, addrlen, O_NONBLOCK); rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 014fa24418c1..53b3535a1e4a 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -306,7 +306,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6) addr_len = sizeof(*sin); } - ret = sock->ops->bind(sock, (struct sockaddr *)&ss, addr_len); + ret = kernel_bind(sock, (struct sockaddr *)&ss, addr_len); if (ret < 0) { rdsdebug("could not bind %s listener socket: %d\n", isv6 ? "IPv6" : "IPv4", ret); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 01fca7a10b4b..08630896b6c8 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -48,6 +48,7 @@ struct rfkill { bool persistent; bool polling_paused; bool suspended; + bool need_sync; const struct rfkill_ops *ops; void *data; @@ -368,6 +369,17 @@ static void rfkill_set_block(struct rfkill *rfkill, bool blocked) rfkill_event(rfkill); } +static void rfkill_sync(struct rfkill *rfkill) +{ + lockdep_assert_held(&rfkill_global_mutex); + + if (!rfkill->need_sync) + return; + + rfkill_set_block(rfkill, rfkill_global_states[rfkill->type].cur); + rfkill->need_sync = false; +} + static void rfkill_update_global_state(enum rfkill_type type, bool blocked) { int i; @@ -730,6 +742,10 @@ static ssize_t soft_show(struct device *dev, struct device_attribute *attr, { struct rfkill *rfkill = to_rfkill(dev); + mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); + mutex_unlock(&rfkill_global_mutex); + return sysfs_emit(buf, "%d\n", (rfkill->state & RFKILL_BLOCK_SW) ? 1 : 0); } @@ -751,6 +767,7 @@ static ssize_t soft_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); rfkill_set_block(rfkill, state); mutex_unlock(&rfkill_global_mutex); @@ -783,6 +800,10 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr, { struct rfkill *rfkill = to_rfkill(dev); + mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); + mutex_unlock(&rfkill_global_mutex); + return sysfs_emit(buf, "%d\n", user_state_from_blocked(rfkill->state)); } @@ -805,6 +826,7 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); rfkill_set_block(rfkill, state == RFKILL_USER_STATE_SOFT_BLOCKED); mutex_unlock(&rfkill_global_mutex); @@ -1032,14 +1054,10 @@ static void rfkill_uevent_work(struct work_struct *work) static void rfkill_sync_work(struct work_struct *work) { - struct rfkill *rfkill; - bool cur; - - rfkill = container_of(work, struct rfkill, sync_work); + struct rfkill *rfkill = container_of(work, struct rfkill, sync_work); mutex_lock(&rfkill_global_mutex); - cur = rfkill_global_states[rfkill->type].cur; - rfkill_set_block(rfkill, cur); + rfkill_sync(rfkill); mutex_unlock(&rfkill_global_mutex); } @@ -1087,6 +1105,7 @@ int __must_check rfkill_register(struct rfkill *rfkill) round_jiffies_relative(POLL_INTERVAL)); if (!rfkill->persistent || rfkill_epo_lock_active) { + rfkill->need_sync = true; schedule_work(&rfkill->sync_work); } else { #ifdef CONFIG_RFKILL_INPUT @@ -1171,6 +1190,7 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) goto free; + rfkill_sync(rfkill); rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); list_add_tail(&ev->list, &data->events); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 796529167e8d..c45c192b7878 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1159,8 +1159,7 @@ int sctp_assoc_update(struct sctp_association *asoc, /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && - !sctp_assoc_add_peer(asoc, &trans->ipaddr, + if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ab943e8fb1db..7f89e43154c0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2450,6 +2450,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); + sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); diff --git a/net/socket.c b/net/socket.c index c8b08b32f097..c4a6f5532955 100644 --- a/net/socket.c +++ b/net/socket.c @@ -737,6 +737,14 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) return ret; } +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + int err = security_socket_sendmsg(sock, msg, + msg_data_left(msg)); + + return err ?: sock_sendmsg_nosec(sock, msg); +} + /** * sock_sendmsg - send a message through @sock * @sock: socket @@ -747,10 +755,19 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { - int err = security_socket_sendmsg(sock, msg, - msg_data_left(msg)); + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int ret; - return err ?: sock_sendmsg_nosec(sock, msg); + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + + return ret; } EXPORT_SYMBOL(sock_sendmsg); @@ -1138,7 +1155,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -2174,7 +2191,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2538,7 +2555,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. @@ -3499,7 +3516,12 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { - return READ_ONCE(sock->ops)->bind(sock, addr, addrlen); + struct sockaddr_storage address; + + memcpy(&address, addr, addrlen); + + return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)&address, + addrlen); } EXPORT_SYMBOL(kernel_bind); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 2f16f9d17966..814b0169f972 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -769,9 +769,14 @@ int rpcauth_wrap_req(struct rpc_task *task, struct xdr_stream *xdr) * @task: controlling RPC task * @xdr: xdr_stream containing RPC Reply header * - * On success, @xdr is updated to point past the verifier and - * zero is returned. Otherwise, @xdr is in an undefined state - * and a negative errno is returned. + * Return values: + * %0: Verifier is valid. @xdr now points past the verifier. + * %-EIO: Verifier is corrupted or message ended early. + * %-EACCES: Verifier is intact but not valid. + * %-EPROTONOSUPPORT: Server does not support the requested auth type. + * + * When a negative errno is returned, @xdr is left in an undefined + * state. */ int rpcauth_checkverf(struct rpc_task *task, struct xdr_stream *xdr) diff --git a/net/sunrpc/auth_tls.c b/net/sunrpc/auth_tls.c index de7678f8a23d..87f570fd3b00 100644 --- a/net/sunrpc/auth_tls.c +++ b/net/sunrpc/auth_tls.c @@ -129,9 +129,9 @@ static int tls_validate(struct rpc_task *task, struct xdr_stream *xdr) if (*p != rpc_auth_null) return -EIO; if (xdr_stream_decode_opaque_inline(xdr, &str, starttls_len) != starttls_len) - return -EIO; + return -EPROTONOSUPPORT; if (memcmp(str, starttls_token, starttls_len)) - return -EIO; + return -EPROTONOSUPPORT; return 0; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 37b0b212b934..9c210273d06b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2476,8 +2476,7 @@ call_status(struct rpc_task *task) goto out_exit; } task->tk_action = call_encode; - if (status != -ECONNRESET && status != -ECONNABORTED) - rpc_check_timeout(task); + rpc_check_timeout(task); return; out_exit: rpc_call_rpcerror(task, status); @@ -2725,7 +2724,15 @@ out_unparsable: out_verifier: trace_rpc_bad_verifier(task); - goto out_garbage; + switch (error) { + case -EPROTONOSUPPORT: + goto out_err; + case -EACCES: + /* Re-encode with a fresh cred */ + fallthrough; + default: + goto out_garbage; + } out_msg_denied: error = -EACCES; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 71cd916e384f..a15bf2ede89b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2672,6 +2672,10 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) rcu_read_lock(); lower_xprt = rcu_dereference(lower_clnt->cl_xprt); rcu_read_unlock(); + + if (wait_on_bit_lock(&lower_xprt->state, XPRT_LOCKED, TASK_KILLABLE)) + goto out_unlock; + status = xs_tls_handshake_sync(lower_xprt, &upper_xprt->xprtsec); if (status) { trace_rpc_tls_not_started(upper_clnt, upper_xprt); @@ -2681,6 +2685,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) status = xs_tcp_tls_finish_connecting(lower_xprt, upper_transport); if (status) goto out_close; + xprt_release_write(lower_xprt, NULL); trace_rpc_socket_connect(upper_xprt, upper_transport->sock, 0); if (!xprt_test_and_set_connected(upper_xprt)) { @@ -2702,6 +2707,7 @@ out_unlock: return; out_close: + xprt_release_write(lower_xprt, NULL); rpc_shutdown_client(lower_clnt); /* xprt_force_disconnect() wakes tasks with a fixed tk_status code. diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 302fd749c424..43c3f1c971b8 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1441,14 +1441,14 @@ static int tipc_crypto_key_revoke(struct net *net, u8 tx_key) struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_key key; - spin_lock(&tx->lock); + spin_lock_bh(&tx->lock); key = tx->key; WARN_ON(!key.active || tx_key != key.active); /* Free the active key */ tipc_crypto_key_set_state(tx, key.passive, 0, key.pending); tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); - spin_unlock(&tx->lock); + spin_unlock_bh(&tx->lock); pr_warn("%s: key is revoked\n", tx->name); return -EKEYREVOKED; diff --git a/net/wireless/core.c b/net/wireless/core.c index 25bc2e50a061..64e861617110 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1181,16 +1181,11 @@ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state_reason); -void cfg80211_cqm_config_free(struct wireless_dev *wdev) -{ - kfree(wdev->cqm_config); - wdev->cqm_config = NULL; -} - static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, bool unregister_netdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_cqm_config *cqm_config; unsigned int link_id; ASSERT_RTNL(); @@ -1227,7 +1222,10 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, kfree_sensitive(wdev->wext.keys); wdev->wext.keys = NULL; #endif - cfg80211_cqm_config_free(wdev); + wiphy_work_cancel(wdev->wiphy, &wdev->cqm_rssi_work); + /* deleted from the list, so can't be found from nl80211 any more */ + cqm_config = rcu_access_pointer(wdev->cqm_config); + kfree_rcu(cqm_config, rcu_head); /* * Ensure that all events have been processed and @@ -1379,6 +1377,8 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; #endif + wiphy_work_init(&wdev->cqm_rssi_work, cfg80211_cqm_rssi_notify_work); + if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) wdev->ps = true; else diff --git a/net/wireless/core.h b/net/wireless/core.h index 507d184b8b40..ba9c7170afa4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -295,12 +295,17 @@ struct cfg80211_beacon_registration { }; struct cfg80211_cqm_config { + struct rcu_head rcu_head; u32 rssi_hyst; s32 last_rssi_event_value; + enum nl80211_cqm_rssi_threshold_event last_rssi_event_type; int n_rssi_thresholds; s32 rssi_thresholds[] __counted_by(n_rssi_thresholds); }; +void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, + struct wiphy_work *work); + void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev); /* free object */ @@ -566,8 +571,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, #define CFG80211_DEV_WARN_ON(cond) ({bool __r = (cond); __r; }) #endif -void cfg80211_cqm_config_free(struct wireless_dev *wdev); - void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid); void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev); void cfg80211_pmsr_free_wk(struct work_struct *work); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 775cac4d6100..3e2c398abddc 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -52,7 +52,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, cr.links[link_id].bssid = data->links[link_id].bss->bssid; cr.links[link_id].addr = data->links[link_id].addr; /* need to have local link addresses for MLO connections */ - WARN_ON(cr.ap_mld_addr && !cr.links[link_id].addr); + WARN_ON(cr.ap_mld_addr && + !is_valid_ether_addr(cr.links[link_id].addr)); BUG_ON(!cr.links[link_id].bss->channel); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index de47838aca4f..931a03f4549c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5909,6 +5909,21 @@ out: nlmsg_free(msg); } +static int nl80211_validate_ap_phy_operation(struct cfg80211_ap_settings *params) +{ + struct ieee80211_channel *channel = params->chandef.chan; + + if ((params->he_cap || params->he_oper) && + (channel->flags & IEEE80211_CHAN_NO_HE)) + return -EOPNOTSUPP; + + if ((params->eht_cap || params->eht_oper) && + (channel->flags & IEEE80211_CHAN_NO_EHT)) + return -EOPNOTSUPP; + + return 0; +} + static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6178,6 +6193,10 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (err) goto out_unlock; + err = nl80211_validate_ap_phy_operation(params); + if (err) + goto out_unlock; + if (info->attrs[NL80211_ATTR_AP_SETTINGS_FLAGS]) params->flags = nla_get_u32( info->attrs[NL80211_ATTR_AP_SETTINGS_FLAGS]); @@ -8482,7 +8501,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct mesh_config cfg; + struct mesh_config cfg = {}; u32 mask; int err; @@ -12796,7 +12815,8 @@ static int nl80211_set_cqm_txe(struct genl_info *info, } static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, + struct cfg80211_cqm_config *cqm_config) { struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; @@ -12805,7 +12825,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, int err; /* RSSI reporting disabled? */ - if (!wdev->cqm_config) + if (!cqm_config) return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); /* @@ -12814,7 +12834,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, * connection is established and enough beacons received to calculate * the average. */ - if (!wdev->cqm_config->last_rssi_event_value && + if (!cqm_config->last_rssi_event_value && wdev->links[0].client.current_bss && rdev->ops->get_station) { struct station_info sinfo = {}; @@ -12828,30 +12848,30 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, cfg80211_sinfo_release_content(&sinfo); if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) - wdev->cqm_config->last_rssi_event_value = + cqm_config->last_rssi_event_value = (s8) sinfo.rx_beacon_signal_avg; } - last = wdev->cqm_config->last_rssi_event_value; - hyst = wdev->cqm_config->rssi_hyst; - n = wdev->cqm_config->n_rssi_thresholds; + last = cqm_config->last_rssi_event_value; + hyst = cqm_config->rssi_hyst; + n = cqm_config->n_rssi_thresholds; for (i = 0; i < n; i++) { i = array_index_nospec(i, n); - if (last < wdev->cqm_config->rssi_thresholds[i]) + if (last < cqm_config->rssi_thresholds[i]) break; } low_index = i - 1; if (low_index >= 0) { low_index = array_index_nospec(low_index, n); - low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; + low = cqm_config->rssi_thresholds[low_index] - hyst; } else { low = S32_MIN; } if (i < n) { i = array_index_nospec(i, n); - high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; + high = cqm_config->rssi_thresholds[i] + hyst - 1; } else { high = S32_MAX; } @@ -12864,6 +12884,7 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, u32 hysteresis) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_cqm_config *cqm_config = NULL, *old; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; int i, err; @@ -12881,10 +12902,6 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - wdev_lock(wdev); - cfg80211_cqm_config_free(wdev); - wdev_unlock(wdev); - if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) { if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */ return rdev_set_cqm_rssi_config(rdev, dev, 0, 0); @@ -12901,9 +12918,10 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, n_thresholds = 0; wdev_lock(wdev); - if (n_thresholds) { - struct cfg80211_cqm_config *cqm_config; + old = rcu_dereference_protected(wdev->cqm_config, + lockdep_is_held(&wdev->mtx)); + if (n_thresholds) { cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, n_thresholds), GFP_KERNEL); @@ -12918,11 +12936,18 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, flex_array_size(cqm_config, rssi_thresholds, n_thresholds)); - wdev->cqm_config = cqm_config; + rcu_assign_pointer(wdev->cqm_config, cqm_config); + } else { + RCU_INIT_POINTER(wdev->cqm_config, NULL); } - err = cfg80211_cqm_rssi_update(rdev, dev); - + err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); + if (err) { + rcu_assign_pointer(wdev->cqm_config, old); + kfree_rcu(cqm_config, rcu_head); + } else { + kfree_rcu(old, rcu_head); + } unlock: wdev_unlock(wdev); @@ -19073,9 +19098,8 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, s32 rssi_level, gfp_t gfp) { - struct sk_buff *msg; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_cqm_config *cqm_config; trace_cfg80211_cqm_rssi_notify(dev, rssi_event, rssi_level); @@ -19083,18 +19107,41 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH)) return; - if (wdev->cqm_config) { - wdev->cqm_config->last_rssi_event_value = rssi_level; + rcu_read_lock(); + cqm_config = rcu_dereference(wdev->cqm_config); + if (cqm_config) { + cqm_config->last_rssi_event_value = rssi_level; + cqm_config->last_rssi_event_type = rssi_event; + wiphy_work_queue(wdev->wiphy, &wdev->cqm_rssi_work); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); - cfg80211_cqm_rssi_update(rdev, dev); +void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + cqm_rssi_work); + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + enum nl80211_cqm_rssi_threshold_event rssi_event; + struct cfg80211_cqm_config *cqm_config; + struct sk_buff *msg; + s32 rssi_level; - if (rssi_level == 0) - rssi_level = wdev->cqm_config->last_rssi_event_value; - } + wdev_lock(wdev); + cqm_config = rcu_dereference_protected(wdev->cqm_config, + lockdep_is_held(&wdev->mtx)); + if (!wdev->cqm_config) + goto unlock; - msg = cfg80211_prepare_cqm(dev, NULL, gfp); + cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); + + rssi_level = cqm_config->last_rssi_event_value; + rssi_event = cqm_config->last_rssi_event_type; + + msg = cfg80211_prepare_cqm(wdev->netdev, NULL, GFP_KERNEL); if (!msg) - return; + goto unlock; if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, rssi_event)) @@ -19104,14 +19151,15 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_level)) goto nla_put_failure; - cfg80211_send_cqm(msg, gfp); + cfg80211_send_cqm(msg, GFP_KERNEL); - return; + goto unlock; nla_put_failure: nlmsg_free(msg); + unlock: + wdev_unlock(wdev); } -EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, u32 num_packets, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 0cf1ce7b6934..939deecf0bbe 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -908,6 +908,10 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) !cfg80211_find_ssid_match(ap, request)) continue; + if (!is_broadcast_ether_addr(request->bssid) && + !ether_addr_equal(request->bssid, ap->bssid)) + continue; + if (!request->n_ssids && ap->multi_bss && !ap->transmitted_bssid) continue; diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 346f5ec50682..0afd75472679 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -144,7 +144,7 @@ endif quiet_cmd_gzip = GZIP $@ cmd_gzip = $(KGZIP) -n -f $< quiet_cmd_xz = XZ $@ - cmd_xz = $(XZ) --lzma2=dict=2MiB -f $< + cmd_xz = $(XZ) --check=crc32 --lzma2=dict=1MiB -f $< quiet_cmd_zstd = ZSTD $@ cmd_zstd = $(ZSTD) -T0 --rm -f -q $< diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh index c0c8a85d7c81..a45154cefa48 100755 --- a/scripts/atomic/gen-atomic-fallback.sh +++ b/scripts/atomic/gen-atomic-fallback.sh @@ -102,7 +102,7 @@ gen_proto_order_variant() fi # Allow ACQUIRE/RELEASE/RELAXED ops to be defined in terms of FULL ops - if [ ! -z "${order}" ]; then + if [ ! -z "${order}" ] && ! meta_is_implicitly_relaxed "${meta}"; then printf "#elif defined(arch_${basename})\n" printf "\t${retstmt}arch_${basename}(${args});\n" fi diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 5179edd1b627..c8047f4441e6 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -111,12 +111,11 @@ lx-symbols command.""" return "{textaddr} {sections}".format( textaddr=textaddr, sections="".join(args)) - def load_module_symbols(self, module, module_file=None): + def load_module_symbols(self, module): module_name = module['name'].string() module_addr = str(module['mem'][constants.LX_MOD_TEXT]['base']).split()[0] - if not module_file: - module_file = self._get_module_file(module_name) + module_file = self._get_module_file(module_name) if not module_file and not self.module_files_updated: self._update_module_files() module_file = self._get_module_file(module_name) @@ -139,19 +138,6 @@ lx-symbols command.""" else: gdb.write("no module object found for '{0}'\n".format(module_name)) - def load_ko_symbols(self, mod_path): - self.loaded_modules = [] - module_list = modules.module_list() - - for module in module_list: - module_name = module['name'].string() - module_pattern = ".*/{0}\.ko(?:.debug)?$".format( - module_name.replace("_", r"[_\-]")) - if re.match(module_pattern, mod_path) and os.path.exists(mod_path): - self.load_module_symbols(module, mod_path) - return - raise gdb.GdbError("%s is not a valid .ko\n" % mod_path) - def load_all_symbols(self): gdb.write("loading vmlinux\n") @@ -190,11 +176,6 @@ lx-symbols command.""" self.module_files = [] self.module_files_updated = False - argv = gdb.string_to_argv(arg) - if len(argv) == 1: - self.load_ko_symbols(argv[0]) - return - self.load_all_symbols() if hasattr(gdb, 'Breakpoint'): diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 38120f932b0d..7056751c29b1 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1604,7 +1604,7 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, /* First handle the "special" cases */ if (sym_is(name, namelen, "usb")) do_usb_table(symval, sym->st_size, mod); - if (sym_is(name, namelen, "of")) + else if (sym_is(name, namelen, "of")) do_of_table(symval, sym->st_size, mod); else if (sym_is(name, namelen, "pnp")) do_pnp_device_entry(symval, sym->st_size, mod); diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index de499dce5265..b3dee80497cb 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1015,9 +1015,20 @@ static int secref_whitelist(const char *fromsec, const char *fromsym, "*_console"))) return 0; - /* symbols in data sections that may refer to meminit/exit sections */ + /* symbols in data sections that may refer to meminit sections */ if (match(fromsec, PATTERNS(DATA_SECTIONS)) && - match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS, ALL_EXIT_SECTIONS)) && + match(tosec, PATTERNS(ALL_XXXINIT_SECTIONS, ALL_XXXEXIT_SECTIONS)) && + match(fromsym, PATTERNS("*driver"))) + return 0; + + /* + * symbols in data sections must not refer to .exit.*, but there are + * quite a few offenders, so hide these unless for W=1 builds until + * these are fixed. + */ + if (!extra_warn && + match(fromsec, PATTERNS(DATA_SECTIONS)) && + match(tosec, PATTERNS(EXIT_SECTIONS)) && match(fromsym, PATTERNS("*driver"))) return 0; diff --git a/scripts/package/builddeb b/scripts/package/builddeb index bf3f8561aa68..d7dd0d04c70c 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -64,7 +64,6 @@ install_linux_image () { ${MAKE} -f ${srctree}/Makefile INSTALL_MOD_PATH="${pdir}" modules_install rm -f "${pdir}/lib/modules/${KERNELRELEASE}/build" - rm -f "${pdir}/lib/modules/${KERNELRELEASE}/source" # Install the kernel if [ "${ARCH}" = um ] ; then diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec index ac3f2ee6d7a0..3eee0143e0c5 100644 --- a/scripts/package/kernel.spec +++ b/scripts/package/kernel.spec @@ -68,7 +68,6 @@ cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/vmlinuz-%{KERNELRELEA cp System.map %{buildroot}/boot/System.map-%{KERNELRELEASE} cp .config %{buildroot}/boot/config-%{KERNELRELEASE} ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEASE}/build -ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEASE}/source %if %{with_devel} %{make} %{makeflags} run-command KBUILD_RUN_COMMAND='${srctree}/scripts/package/install-extmod-build %{buildroot}/usr/src/kernels/%{KERNELRELEASE}' %endif @@ -101,7 +100,6 @@ fi %defattr (-, root, root) /lib/modules/%{KERNELRELEASE} %exclude /lib/modules/%{KERNELRELEASE}/build -%exclude /lib/modules/%{KERNELRELEASE}/source /boot/* %files headers @@ -113,5 +111,4 @@ fi %defattr (-, root, root) /usr/src/kernels/%{KERNELRELEASE} /lib/modules/%{KERNELRELEASE}/build -/lib/modules/%{KERNELRELEASE}/source %endif diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index ecddc807c536..a6bd817efc1a 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -29,9 +29,11 @@ config IMA to learn more about IMA. If unsure, say N. +if IMA + config IMA_KEXEC bool "Enable carrying the IMA measurement list across a soft boot" - depends on IMA && TCG_TPM && HAVE_IMA_KEXEC + depends on TCG_TPM && HAVE_IMA_KEXEC default n help TPM PCRs are only reset on a hard reboot. In order to validate @@ -43,7 +45,6 @@ config IMA_KEXEC config IMA_MEASURE_PCR_IDX int - depends on IMA range 8 14 default 10 help @@ -53,7 +54,7 @@ config IMA_MEASURE_PCR_IDX config IMA_LSM_RULES bool - depends on IMA && AUDIT && (SECURITY_SELINUX || SECURITY_SMACK || SECURITY_APPARMOR) + depends on AUDIT && (SECURITY_SELINUX || SECURITY_SMACK || SECURITY_APPARMOR) default y help Disabling this option will disregard LSM based policy rules. @@ -61,7 +62,6 @@ config IMA_LSM_RULES choice prompt "Default template" default IMA_NG_TEMPLATE - depends on IMA help Select the default IMA measurement template. @@ -80,14 +80,12 @@ endchoice config IMA_DEFAULT_TEMPLATE string - depends on IMA default "ima-ng" if IMA_NG_TEMPLATE default "ima-sig" if IMA_SIG_TEMPLATE choice prompt "Default integrity hash algorithm" default IMA_DEFAULT_HASH_SHA1 - depends on IMA help Select the default hash algorithm used for the measurement list, integrity appraisal and audit log. The compiled default @@ -117,7 +115,6 @@ endchoice config IMA_DEFAULT_HASH string - depends on IMA default "sha1" if IMA_DEFAULT_HASH_SHA1 default "sha256" if IMA_DEFAULT_HASH_SHA256 default "sha512" if IMA_DEFAULT_HASH_SHA512 @@ -126,7 +123,6 @@ config IMA_DEFAULT_HASH config IMA_WRITE_POLICY bool "Enable multiple writes to the IMA policy" - depends on IMA default n help IMA policy can now be updated multiple times. The new rules get @@ -137,7 +133,6 @@ config IMA_WRITE_POLICY config IMA_READ_POLICY bool "Enable reading back the current IMA policy" - depends on IMA default y if IMA_WRITE_POLICY default n if !IMA_WRITE_POLICY help @@ -147,7 +142,6 @@ config IMA_READ_POLICY config IMA_APPRAISE bool "Appraise integrity measurements" - depends on IMA default n help This option enables local measurement integrity appraisal. @@ -269,7 +263,7 @@ config IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY config IMA_BLACKLIST_KEYRING bool "Create IMA machine owner blacklist keyrings (EXPERIMENTAL)" depends on SYSTEM_TRUSTED_KEYRING - depends on IMA_TRUSTED_KEYRING + depends on INTEGRITY_TRUSTED_KEYRING default n help This option creates an IMA blacklist keyring, which contains all @@ -279,7 +273,7 @@ config IMA_BLACKLIST_KEYRING config IMA_LOAD_X509 bool "Load X509 certificate onto the '.ima' trusted keyring" - depends on IMA_TRUSTED_KEYRING + depends on INTEGRITY_TRUSTED_KEYRING default n help File signature verification is based on the public keys @@ -304,7 +298,6 @@ config IMA_APPRAISE_SIGNED_INIT config IMA_MEASURE_ASYMMETRIC_KEYS bool - depends on IMA depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y default y @@ -323,7 +316,8 @@ config IMA_SECURE_AND_OR_TRUSTED_BOOT config IMA_DISABLE_HTABLE bool "Disable htable to allow measurement of duplicate records" - depends on IMA default n help This option disables htable to allow measurement of duplicate records. + +endif diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index a00a53e15ab7..1d111350197f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -57,6 +57,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -155,6 +156,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -178,6 +188,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index fd6c1cb585db..abe087c53b4b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -820,8 +820,11 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) #define __NR_cachestat 451 __SYSCALL(__NR_cachestat, sys_cachestat) +#define __NR_fchmodat2 452 +__SYSCALL(__NR_fchmodat2, sys_fchmodat2) + #undef __NR_syscalls -#define __NR_syscalls 452 +#define __NR_syscalls 453 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index a87bbbbca2d4..794c1d857677 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -673,8 +673,11 @@ struct drm_gem_open { * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT * and &DRM_PRIME_CAP_EXPORT. * - * PRIME buffers are exposed as dma-buf file descriptors. See - * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing". + * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and + * &DRM_PRIME_CAP_EXPORT are always advertised. + * + * PRIME buffers are exposed as dma-buf file descriptors. + * See :ref:`prime_buffer_sharing`. */ #define DRM_CAP_PRIME 0x5 /** @@ -682,6 +685,8 @@ struct drm_gem_open { * * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. */ #define DRM_PRIME_CAP_IMPORT 0x1 /** @@ -689,6 +694,8 @@ struct drm_gem_open { * * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. */ #define DRM_PRIME_CAP_EXPORT 0x2 /** @@ -756,15 +763,14 @@ struct drm_gem_open { /** * DRM_CAP_SYNCOBJ * - * If set to 1, the driver supports sync objects. See - * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ 0x13 /** * DRM_CAP_SYNCOBJ_TIMELINE * * If set to 1, the driver supports timeline operations on sync objects. See - * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + * :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 @@ -909,6 +915,27 @@ struct drm_syncobj_timeline_wait { __u32 pad; }; +/** + * struct drm_syncobj_eventfd + * @handle: syncobj handle. + * @flags: Zero to wait for the point to be signalled, or + * &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be + * available for the point. + * @point: syncobj timeline point (set to zero for binary syncobjs). + * @fd: Existing eventfd to sent events to. + * @pad: Must be zero. + * + * Register an eventfd to be signalled by a syncobj. The eventfd counter will + * be incremented by one. + */ +struct drm_syncobj_eventfd { + __u32 handle; + __u32 flags; + __u64 point; + __s32 fd; + __u32 pad; +}; + struct drm_syncobj_array { __u64 handles; @@ -1169,6 +1196,8 @@ extern "C" { */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) +#define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. @@ -1180,25 +1209,50 @@ extern "C" { #define DRM_COMMAND_BASE 0x40 #define DRM_COMMAND_END 0xA0 -/* - * Header for events written back to userspace on the drm fd. The - * type defines the type of event, the length specifies the total - * length of the event (including the header), and user_data is - * typically a 64 bit value passed with the ioctl that triggered the - * event. A read on the drm fd will always only return complete - * events, that is, if for example the read buffer is 100 bytes, and - * there are two 64 byte events pending, only one will be returned. +/** + * struct drm_event - Header for DRM events + * @type: event type. + * @length: total number of payload bytes (including header). * - * Event types 0 - 0x7fffffff are generic drm events, 0x80000000 and - * up are chipset specific. + * This struct is a header for events written back to user-space on the DRM FD. + * A read on the DRM FD will always only return complete events: e.g. if the + * read buffer is 100 bytes large and there are two 64 byte events pending, + * only one will be returned. + * + * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and + * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK, + * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE. */ struct drm_event { __u32 type; __u32 length; }; +/** + * DRM_EVENT_VBLANK - vertical blanking event + * + * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the + * &_DRM_VBLANK_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ #define DRM_EVENT_VBLANK 0x01 +/** + * DRM_EVENT_FLIP_COMPLETE - page-flip completion event + * + * This event is sent in response to an atomic commit or legacy page-flip with + * the &DRM_MODE_PAGE_FLIP_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ #define DRM_EVENT_FLIP_COMPLETE 0x02 +/** + * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event + * + * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE. + * + * The event payload is a struct drm_event_crtc_sequence. + */ #define DRM_EVENT_CRTC_SEQUENCE 0x03 struct drm_event_vblank { diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h new file mode 100644 index 000000000000..dbfc9b37fcae --- /dev/null +++ b/tools/include/uapi/linux/seccomp.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_SECCOMP_H +#define _UAPI_LINUX_SECCOMP_H + +#include <linux/compiler.h> +#include <linux/types.h> + + +/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */ +#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */ +#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */ +#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */ + +/* Valid operations for seccomp syscall. */ +#define SECCOMP_SET_MODE_STRICT 0 +#define SECCOMP_SET_MODE_FILTER 1 +#define SECCOMP_GET_ACTION_AVAIL 2 +#define SECCOMP_GET_NOTIF_SIZES 3 + +/* Valid flags for SECCOMP_SET_MODE_FILTER */ +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) +#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) + +/* + * All BPF programs must return a 32-bit value. + * The bottom 16-bits are for optional return data. + * The upper 16-bits are ordered from least permissive values to most, + * as a signed value (so 0x8000000 is negative). + * + * The ordering ensures that a min_t() over composed return values always + * selects the least permissive choice. + */ +#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ + +/* Masks for the return value sections. */ +#define SECCOMP_RET_ACTION_FULL 0xffff0000U +#define SECCOMP_RET_ACTION 0x7fff0000U +#define SECCOMP_RET_DATA 0x0000ffffU + +/** + * struct seccomp_data - the format the BPF program executes over. + * @nr: the system call number + * @arch: indicates system call convention as an AUDIT_ARCH_* value + * as defined in <linux/audit.h>. + * @instruction_pointer: at the time of the system call. + * @args: up to 6 system call arguments always stored as 64-bit values + * regardless of the architecture. + */ +struct seccomp_data { + int nr; + __u32 arch; + __u64 instruction_pointer; + __u64 args[6]; +}; + +struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; +}; + +struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; +}; + +/* + * Valid flags for struct seccomp_notif_resp + * + * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution! + * If set by the process supervising the syscalls of another process the + * syscall will continue. This is problematic because of an inherent TOCTOU. + * An attacker can exploit the time while the supervised process is waiting on + * a response from the supervising process to rewrite syscall arguments which + * are passed as pointers of the intercepted syscall. + * It should be absolutely clear that this means that the seccomp notifier + * _cannot_ be used to implement a security policy! It should only ever be used + * in scenarios where a more privileged process supervises the syscalls of a + * lesser privileged process to get around kernel-enforced security + * restrictions when the privileged process deems this safe. In other words, + * in order to continue a syscall the supervising process should be sure that + * another security mechanism or the kernel itself will sufficiently block + * syscalls if arguments are rewritten to something unsafe. + * + * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF + * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the + * same syscall, the most recently added filter takes precedence. This means + * that the new SECCOMP_RET_USER_NOTIF filter can override any + * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all + * such filtered syscalls to be executed by sending the response + * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally + * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE. + */ +#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0) + +struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; +}; + +#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ +#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */ + +/** + * struct seccomp_notif_addfd + * @id: The ID of the seccomp notification + * @flags: SECCOMP_ADDFD_FLAG_* + * @srcfd: The local fd number + * @newfd: Optional remote FD number if SETFD option is set, otherwise 0. + * @newfd_flags: The O_* flags the remote FD should have applied + */ +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; + +#define SECCOMP_IOC_MAGIC '!' +#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) +#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + +/* Flags for seccomp notification fd ioctl. */ +#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) +#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ + struct seccomp_notif_resp) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64) + +#endif /* _UAPI_LINUX_SECCOMP_H */ diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index cfda2511badf..cb5e757f6621 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -366,3 +366,4 @@ 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 n64 cachestat sys_cachestat +452 n64 fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 8c0b08b7a80e..20e50586e8a2 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -538,3 +538,4 @@ 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index a6935af2235c..0122cc156952 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 227538b0ce80..1d6eee30eceb 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -373,6 +373,8 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 64 map_shadow_stack sys_map_shadow_stack # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c index b04ebcde4036..a01c40131493 100644 --- a/tools/perf/bench/sched-seccomp-notify.c +++ b/tools/perf/bench/sched-seccomp-notify.c @@ -9,7 +9,7 @@ #include <sys/syscall.h> #include <sys/ioctl.h> #include <linux/time64.h> -#include <linux/seccomp.h> +#include <uapi/linux/seccomp.h> #include <sys/prctl.h> #include <unistd.h> diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 4314c9197850..e21caadda7c1 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -21,6 +21,7 @@ FILES=( "include/uapi/linux/perf_event.h" "include/uapi/linux/prctl.h" "include/uapi/linux/sched.h" + "include/uapi/linux/seccomp.h" "include/uapi/linux/stat.h" "include/uapi/linux/usbdevice_fs.h" "include/uapi/linux/vhost.h" diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index a7e88332276d..72ba4a9239c6 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -991,7 +991,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) } } free(cpuid); - if (!pmu) + if (!pmu || !table) return table; for (i = 0; i < table->num_pmus; i++) { diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 0e9ec65d92ae..3e673f25d5fd 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -413,10 +413,10 @@ def has_event(event: Event) -> Function: # pylint: disable=invalid-name return Function('has_event', event) -def strcmp_cpuid_str(event: str) -> Function: +def strcmp_cpuid_str(cpuid: Event) -> Function: # pylint: disable=redefined-builtin # pylint: disable=invalid-name - return Function('strcmp_cpuid_str', event) + return Function('strcmp_cpuid_str', cpuid) class Metric: """An individual metric that will specifiable on the perf command line.""" diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c deleted file mode 100644 index 9887ae09242d..000000000000 --- a/tools/perf/util/bpf-prologue.c +++ /dev/null @@ -1,508 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-prologue.c - * - * Copyright (C) 2015 He Kuang <hekuang@huawei.com> - * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015 Huawei Inc. - */ - -#include <bpf/libbpf.h> -#include "debug.h" -#include "bpf-loader.h" -#include "bpf-prologue.h" -#include "probe-finder.h" -#include <errno.h> -#include <stdlib.h> -#include <dwarf-regs.h> -#include <linux/filter.h> - -#define BPF_REG_SIZE 8 - -#define JMP_TO_ERROR_CODE -1 -#define JMP_TO_SUCCESS_CODE -2 -#define JMP_TO_USER_CODE -3 - -struct bpf_insn_pos { - struct bpf_insn *begin; - struct bpf_insn *end; - struct bpf_insn *pos; -}; - -static inline int -pos_get_cnt(struct bpf_insn_pos *pos) -{ - return pos->pos - pos->begin; -} - -static int -append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos) -{ - if (!pos->pos) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - - if (pos->pos + 1 >= pos->end) { - pr_err("bpf prologue: prologue too long\n"); - pos->pos = NULL; - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - } - - *(pos->pos)++ = new_insn; - return 0; -} - -static int -check_pos(struct bpf_insn_pos *pos) -{ - if (!pos->pos || pos->pos >= pos->end) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - return 0; -} - -/* - * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see - * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM - * instruction (BPF_{B,H,W,DW}). - */ -static int -argtype_to_ldx_size(const char *type) -{ - int arg_size = type ? atoi(&type[1]) : 64; - - switch (arg_size) { - case 8: - return BPF_B; - case 16: - return BPF_H; - case 32: - return BPF_W; - case 64: - default: - return BPF_DW; - } -} - -static const char * -insn_sz_to_str(int insn_sz) -{ - switch (insn_sz) { - case BPF_B: - return "BPF_B"; - case BPF_H: - return "BPF_H"; - case BPF_W: - return "BPF_W"; - case BPF_DW: - return "BPF_DW"; - default: - return "UNKNOWN"; - } -} - -/* Give it a shorter name */ -#define ins(i, p) append_insn((i), (p)) - -/* - * Give a register name (in 'reg'), generate instruction to - * load register into an eBPF register rd: - * 'ldd target_reg, offset(ctx_reg)', where: - * ctx_reg is pre initialized to pointer of 'struct pt_regs'. - */ -static int -gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg, - const char *reg, int target_reg) -{ - int offset = regs_query_register_offset(reg); - - if (offset < 0) { - pr_err("bpf: prologue: failed to get register %s\n", - reg); - return offset; - } - ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos); - - return check_pos(pos); -} - -/* - * Generate a BPF_FUNC_probe_read function call. - * - * src_base_addr_reg is a register holding base address, - * dst_addr_reg is a register holding dest address (on stack), - * result is: - * - * *[dst_addr_reg] = *([src_base_addr_reg] + offset) - * - * Arguments of BPF_FUNC_probe_read: - * ARG1: ptr to stack (dest) - * ARG2: size (8) - * ARG3: unsafe ptr (src) - */ -static int -gen_read_mem(struct bpf_insn_pos *pos, - int src_base_addr_reg, - int dst_addr_reg, - long offset, - int probeid) -{ - /* mov arg3, src_base_addr_reg */ - if (src_base_addr_reg != BPF_REG_ARG3) - ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos); - /* add arg3, #offset */ - if (offset) - ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos); - - /* mov arg2, #reg_size */ - ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos); - - /* mov arg1, dst_addr_reg */ - if (dst_addr_reg != BPF_REG_ARG1) - ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos); - - /* Call probe_read */ - ins(BPF_EMIT_CALL(probeid), pos); - /* - * Error processing: if read fail, goto error code, - * will be relocated. Target should be the start of - * error processing code. - */ - ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE), - pos); - - return check_pos(pos); -} - -/* - * Each arg should be bare register. Fetch and save them into argument - * registers (r3 - r5). - * - * BPF_REG_1 should have been initialized with pointer to - * 'struct pt_regs'. - */ -static int -gen_prologue_fastpath(struct bpf_insn_pos *pos, - struct probe_trace_arg *args, int nargs) -{ - int i, err = 0; - - for (i = 0; i < nargs; i++) { - err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value, - BPF_PROLOGUE_START_ARG_REG + i); - if (err) - goto errout; - } - - return check_pos(pos); -errout: - return err; -} - -/* - * Slow path: - * At least one argument has the form of 'offset($rx)'. - * - * Following code first stores them into stack, then loads all of then - * to r2 - r5. - * Before final loading, the final result should be: - * - * low address - * BPF_REG_FP - 24 ARG3 - * BPF_REG_FP - 16 ARG2 - * BPF_REG_FP - 8 ARG1 - * BPF_REG_FP - * high address - * - * For each argument (described as: offn(...off2(off1(reg)))), - * generates following code: - * - * r7 <- fp - * r7 <- r7 - stack_offset // Ideal code should initialize r7 using - * // fp before generating args. However, - * // eBPF won't regard r7 as stack pointer - * // if it is generated by minus 8 from - * // another stack pointer except fp. - * // This is why we have to set r7 - * // to fp for each variable. - * r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx() - * (r7) <- r3 // skip following instructions for bare reg - * r3 <- r3 + off1 . // skip if off1 == 0 - * r2 <- 8 \ - * r1 <- r7 |-> generated by gen_read_mem() - * call probe_read / - * jnei r0, 0, err ./ - * r3 <- (r7) - * r3 <- r3 + off2 . // skip if off2 == 0 - * r2 <- 8 \ // r2 may be broken by probe_read, so set again - * r1 <- r7 |-> generated by gen_read_mem() - * call probe_read / - * jnei r0, 0, err ./ - * ... - */ -static int -gen_prologue_slowpath(struct bpf_insn_pos *pos, - struct probe_trace_arg *args, int nargs) -{ - int err, i, probeid; - - for (i = 0; i < nargs; i++) { - struct probe_trace_arg *arg = &args[i]; - const char *reg = arg->value; - struct probe_trace_arg_ref *ref = NULL; - int stack_offset = (i + 1) * -8; - - pr_debug("prologue: fetch arg %d, base reg is %s\n", - i, reg); - - /* value of base register is stored into ARG3 */ - err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg, - BPF_REG_ARG3); - if (err) { - pr_err("prologue: failed to get offset of register %s\n", - reg); - goto errout; - } - - /* Make r7 the stack pointer. */ - ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos); - /* r7 += -8 */ - ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos); - /* - * Store r3 (base register) onto stack - * Ensure fp[offset] is set. - * fp is the only valid base register when storing - * into stack. We are not allowed to use r7 as base - * register here. - */ - ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3, - stack_offset), pos); - - ref = arg->ref; - probeid = BPF_FUNC_probe_read_kernel; - while (ref) { - pr_debug("prologue: arg %d: offset %ld\n", - i, ref->offset); - - if (ref->user_access) - probeid = BPF_FUNC_probe_read_user; - - err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7, - ref->offset, probeid); - if (err) { - pr_err("prologue: failed to generate probe_read function call\n"); - goto errout; - } - - ref = ref->next; - /* - * Load previous result into ARG3. Use - * BPF_REG_FP instead of r7 because verifier - * allows FP based addressing only. - */ - if (ref) - ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3, - BPF_REG_FP, stack_offset), pos); - } - } - - /* Final pass: read to registers */ - for (i = 0; i < nargs; i++) { - int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW; - - pr_debug("prologue: load arg %d, insn_sz is %s\n", - i, insn_sz_to_str(insn_sz)); - ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i, - BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); - } - - ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); - - return check_pos(pos); -errout: - return err; -} - -static int -prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code, - struct bpf_insn *success_code, struct bpf_insn *user_code) -{ - struct bpf_insn *insn; - - if (check_pos(pos)) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - - for (insn = pos->begin; insn < pos->pos; insn++) { - struct bpf_insn *target; - u8 class = BPF_CLASS(insn->code); - u8 opcode; - - if (class != BPF_JMP) - continue; - opcode = BPF_OP(insn->code); - if (opcode == BPF_CALL) - continue; - - switch (insn->off) { - case JMP_TO_ERROR_CODE: - target = error_code; - break; - case JMP_TO_SUCCESS_CODE: - target = success_code; - break; - case JMP_TO_USER_CODE: - target = user_code; - break; - default: - pr_err("bpf prologue: internal error: relocation failed\n"); - return -BPF_LOADER_ERRNO__PROLOGUE; - } - - insn->off = target - (insn + 1); - } - return 0; -} - -int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, - struct bpf_insn *new_prog, size_t *new_cnt, - size_t cnt_space) -{ - struct bpf_insn *success_code = NULL; - struct bpf_insn *error_code = NULL; - struct bpf_insn *user_code = NULL; - struct bpf_insn_pos pos; - bool fastpath = true; - int err = 0, i; - - if (!new_prog || !new_cnt) - return -EINVAL; - - if (cnt_space > BPF_MAXINSNS) - cnt_space = BPF_MAXINSNS; - - pos.begin = new_prog; - pos.end = new_prog + cnt_space; - pos.pos = new_prog; - - if (!nargs) { - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), - &pos); - - if (check_pos(&pos)) - goto errout; - - *new_cnt = pos_get_cnt(&pos); - return 0; - } - - if (nargs > BPF_PROLOGUE_MAX_ARGS) { - pr_warning("bpf: prologue: %d arguments are dropped\n", - nargs - BPF_PROLOGUE_MAX_ARGS); - nargs = BPF_PROLOGUE_MAX_ARGS; - } - - /* First pass: validation */ - for (i = 0; i < nargs; i++) { - struct probe_trace_arg_ref *ref = args[i].ref; - - if (args[i].value[0] == '@') { - /* TODO: fetch global variable */ - pr_err("bpf: prologue: global %s%+ld not support\n", - args[i].value, ref ? ref->offset : 0); - return -ENOTSUP; - } - - while (ref) { - /* fastpath is true if all args has ref == NULL */ - fastpath = false; - - /* - * Instruction encodes immediate value using - * s32, ref->offset is long. On systems which - * can't fill long in s32, refuse to process if - * ref->offset too large (or small). - */ -#ifdef __LP64__ -#define OFFSET_MAX ((1LL << 31) - 1) -#define OFFSET_MIN ((1LL << 31) * -1) - if (ref->offset > OFFSET_MAX || - ref->offset < OFFSET_MIN) { - pr_err("bpf: prologue: offset out of bound: %ld\n", - ref->offset); - return -BPF_LOADER_ERRNO__PROLOGUEOOB; - } -#endif - ref = ref->next; - } - } - pr_debug("prologue: pass validation\n"); - - if (fastpath) { - /* If all variables are registers... */ - pr_debug("prologue: fast path\n"); - err = gen_prologue_fastpath(&pos, args, nargs); - if (err) - goto errout; - } else { - pr_debug("prologue: slow path\n"); - - /* Initialization: move ctx to a callee saved register. */ - ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos); - - err = gen_prologue_slowpath(&pos, args, nargs); - if (err) - goto errout; - /* - * start of ERROR_CODE (only slow pass needs error code) - * mov r2 <- 1 // r2 is error number - * mov r3 <- 0 // r3, r4... should be touched or - * // verifier would complain - * mov r4 <- 0 - * ... - * goto usercode - */ - error_code = pos.pos; - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1), - &pos); - - for (i = 0; i < nargs; i++) - ins(BPF_ALU64_IMM(BPF_MOV, - BPF_PROLOGUE_START_ARG_REG + i, - 0), - &pos); - ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE), - &pos); - } - - /* - * start of SUCCESS_CODE: - * mov r2 <- 0 - * goto usercode // skip - */ - success_code = pos.pos; - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos); - - /* - * start of USER_CODE: - * Restore ctx to r1 - */ - user_code = pos.pos; - if (!fastpath) { - /* - * Only slow path needs restoring of ctx. In fast path, - * register are loaded directly from r1. - */ - ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos); - err = prologue_relocate(&pos, error_code, success_code, - user_code); - if (err) - goto errout; - } - - err = check_pos(&pos); - if (err) - goto errout; - - *new_cnt = pos_get_cnt(&pos); - return 0; -errout: - return err; -} diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 90ce22f9c1a9..939ec769bf4a 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -23,7 +23,9 @@ #define MAX_CPUS 4096 // FIXME: These should come from system headers +#ifndef bool typedef char bool; +#endif typedef int pid_t; typedef long long int __s64; typedef __s64 time64_t; diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index 0a5bf1937a7c..c12f8320e668 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -80,16 +80,6 @@ struct hashmap { size_t sz; }; -#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ - .hash_fn = (hash_fn), \ - .equal_fn = (equal_fn), \ - .ctx = (ctx), \ - .buckets = NULL, \ - .cap = 0, \ - .cap_bits = 0, \ - .sz = 0, \ -} - void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, hashmap_equal_fn equal_fn, void *ctx); struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d85602aa4b9f..8de6f39abd1b 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -520,7 +520,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, pmu_name = pe->pmu; } - alias = malloc(sizeof(*alias)); + alias = zalloc(sizeof(*alias)); if (!alias) return -ENOMEM; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 42806add0114..1a21d6beebc6 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -92,7 +92,7 @@ endif TARGETS += tmpfs TARGETS += tpm2 TARGETS += tty -TARGETS += uevents +TARGETS += uevent TARGETS += user TARGETS += user_events TARGETS += vDSO diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index a53c254c6058..4aabeaa525d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -185,6 +185,8 @@ static void test_cubic(void) do_test("bpf_cubic", NULL); + ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called"); + bpf_link__destroy(link); bpf_cubic__destroy(cubic_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 064cc5e8d9ad..dda7060e86a0 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -475,6 +475,55 @@ out: test_sockmap_drop_prog__destroy(drop); } +static void test_sockmap_skb_verdict_peek(void) +{ + int err, map, verdict, s, c1, p1, zero = 0, sent, recvd, avail; + struct test_sockmap_pass_prog *pass; + char snd[256] = "0123456789"; + char rcv[256] = "0"; + + pass = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(pass, "open_and_load")) + return; + verdict = bpf_program__fd(pass->progs.prog_skb_verdict); + map = bpf_map__fd(pass->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (!ASSERT_GT(s, -1, "socket_loopback(s)")) + goto out; + + err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + if (!ASSERT_OK(err, "create_pairs(s)")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, snd, sizeof(snd), 0); + ASSERT_EQ(sent, sizeof(snd), "xsend(p1)"); + recvd = recv(c1, rcv, sizeof(rcv), MSG_PEEK); + ASSERT_EQ(recvd, sizeof(rcv), "recv(c1)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, sizeof(snd), "after peek ioctl(FIONREAD)"); + recvd = recv(c1, rcv, sizeof(rcv), 0); + ASSERT_EQ(recvd, sizeof(rcv), "recv(p0)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, 0, "after read ioctl(FIONREAD)"); + +out_close: + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(pass); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -515,4 +564,6 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); + if (test__start_subtest("sockmap skb_verdict msg_f_peek")) + test_sockmap_skb_verdict_peek(); } diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index 7a2ecd4eca5d..99af79ea21a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -2378,3 +2378,87 @@ void serial_test_tc_opts_chain_mixed(void) test_tc_chain_mixed(BPF_TCX_INGRESS); test_tc_chain_mixed(BPF_TCX_EGRESS); } + +static int generate_dummy_prog(void) +{ + const struct bpf_insn prog_insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); + LIBBPF_OPTS(bpf_prog_load_opts, opts); + const size_t log_buf_sz = 256; + char *log_buf; + int fd = -1; + + log_buf = malloc(log_buf_sz); + if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc")) + return fd; + opts.log_buf = log_buf; + opts.log_size = log_buf_sz; + + log_buf[0] = '\0'; + opts.log_level = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SCHED_CLS, "tcx_prog", "GPL", + prog_insns, prog_insn_cnt, &opts); + ASSERT_STREQ(log_buf, "", "log_0"); + ASSERT_GE(fd, 0, "prog_fd"); + free(log_buf); + return fd; +} + +static void test_tc_opts_max_target(int target, int flags, bool relative) +{ + int err, ifindex, i, prog_fd, last_fd = -1; + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + const int max_progs = 63; + + ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth"); + ifindex = if_nametoindex("tcx_opts1"); + ASSERT_NEQ(ifindex, 0, "non_zero_ifindex"); + + assert_mprog_count_ifindex(ifindex, target, 0); + + for (i = 0; i < max_progs; i++) { + prog_fd = generate_dummy_prog(); + if (!ASSERT_GE(prog_fd, 0, "dummy_prog")) + goto cleanup; + err = bpf_prog_attach_opts(prog_fd, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + assert_mprog_count_ifindex(ifindex, target, i + 1); + if (i == max_progs - 1 && relative) + last_fd = prog_fd; + else + close(prog_fd); + } + + prog_fd = generate_dummy_prog(); + if (!ASSERT_GE(prog_fd, 0, "dummy_prog")) + goto cleanup; + opta.flags = flags; + if (last_fd > 0) + opta.relative_fd = last_fd; + err = bpf_prog_attach_opts(prog_fd, ifindex, target, &opta); + ASSERT_EQ(err, -ERANGE, "prog_64_attach"); + assert_mprog_count_ifindex(ifindex, target, max_progs); + close(prog_fd); +cleanup: + if (last_fd > 0) + close(last_fd); + ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); + ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); + ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); +} + +void serial_test_tc_opts_max(void) +{ + test_tc_opts_max_target(BPF_TCX_INGRESS, 0, false); + test_tc_opts_max_target(BPF_TCX_EGRESS, 0, false); + + test_tc_opts_max_target(BPF_TCX_INGRESS, BPF_F_BEFORE, false); + test_tc_opts_max_target(BPF_TCX_EGRESS, BPF_F_BEFORE, true); + + test_tc_opts_max_target(BPF_TCX_INGRESS, BPF_F_AFTER, true); + test_tc_opts_max_target(BPF_TCX_EGRESS, BPF_F_AFTER, false); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index d9660e7200e2..c997e3e3d3fb 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -490,6 +490,8 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay) } } +int bpf_cubic_acked_called = 0; + void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample) { @@ -497,6 +499,7 @@ void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk, struct bictcp *ca = inet_csk_ca(sk); __u32 delay; + bpf_cubic_acked_called = 1; /* Some calls are for duplicates without timetamps */ if (sample->rtt_us < 0) return; diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile index 20839f8e43f2..71ec34bf1501 100644 --- a/tools/testing/selftests/fchmodat2/Makefile +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan $(KHDR_INCLUDES) TEST_GEN_PROGS := fchmodat2_test include ../lib.mk diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 3e36019eeb4a..5d7f28b02d73 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -387,7 +387,7 @@ char *strdup_printf(const char *fmt, ...) char *str; va_start(ap, fmt); - vasprintf(&str, fmt, ap); + TEST_ASSERT(vasprintf(&str, fmt, ap) >= 0, "vasprintf() failed"); va_end(ap); return str; diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index d8ecacd03ecf..9f99ea42f45f 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -12,19 +12,37 @@ #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK) +static bool isa_ext_cant_disable[KVM_RISCV_ISA_EXT_MAX]; + bool filter_reg(__u64 reg) { + switch (reg & ~REG_MASK) { /* - * Some ISA extensions are optional and not present on all host, - * but they can't be disabled through ISA_EXT registers when present. - * So, to make life easy, just filtering out these kind of registers. + * Same set of ISA_EXT registers are not present on all host because + * ISA_EXT registers are visible to the KVM user space based on the + * ISA extensions available on the host. Also, disabling an ISA + * extension using corresponding ISA_EXT register does not affect + * the visibility of the ISA_EXT register itself. + * + * Based on above, we should filter-out all ISA_EXT registers. */ - switch (reg & ~REG_MASK) { + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_V: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR: @@ -32,6 +50,15 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM: return true; + /* AIA registers are always available when Ssaia can't be disabled */ + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(sieh): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h): + return isa_ext_cant_disable[KVM_RISCV_ISA_EXT_SSAIA]; default: break; } @@ -50,24 +77,27 @@ static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext) unsigned long value; ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value); - if (ret) { - printf("Failed to get ext %d", ext); - return false; - } - - return !!value; + return (ret) ? false : !!value; } void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) { + unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 }; struct vcpu_reg_sublist *s; + int rc; + + for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) + __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(i), &isa_ext_state[i]); /* * Disable all extensions which were enabled by default * if they were available in the risc-v host. */ - for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) - __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(i), 0); + for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { + rc = __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(i), 0); + if (rc && isa_ext_state[i]) + isa_ext_cant_disable[i] = true; + } for_each_sublist(c, s) { if (!s->feature) @@ -506,10 +536,6 @@ static __u64 base_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M, KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01, KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME, KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI, diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index a5cb4b09a46c..0899019a7fcb 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -25,7 +25,7 @@ if [[ "$1" == "-cgroup-v2" ]]; then fi if [[ $cgroup2 ]]; then - cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}') if [[ -z "$cgroup_path" ]]; then cgroup_path=/dev/cgroup/memory mount -t cgroup2 none $cgroup_path @@ -33,7 +33,7 @@ if [[ $cgroup2 ]]; then fi echo "+hugetlb" >$cgroup_path/cgroup.subtree_control else - cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}') if [[ -z "$cgroup_path" ]]; then cgroup_path=/dev/cgroup/memory mount -t cgroup memory,hugetlb $cgroup_path diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index bf2d2a684edf..14d26075c863 100755 --- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh @@ -20,7 +20,7 @@ fi if [[ $cgroup2 ]]; then - CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') + CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}') if [[ -z "$CGROUP_ROOT" ]]; then CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup2 none $CGROUP_ROOT @@ -28,7 +28,7 @@ if [[ $cgroup2 ]]; then fi echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control else - CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}') + CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}') if [[ -z "$CGROUP_ROOT" ]]; then CGROUP_ROOT=/dev/cgroup/memory mount -t cgroup memory,hugetlb $CGROUP_ROOT diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 321db8850da0..ef90aca4cc96 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -6,13 +6,14 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ - conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh + conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \ + conntrack_sctp_collision.sh HOSTPKG_CONFIG := pkg-config CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) -TEST_GEN_FILES = nf-queue connect_close audit_logread +TEST_GEN_FILES = nf-queue connect_close audit_logread sctp_collision include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_sctp_collision.sh b/tools/testing/selftests/netfilter/conntrack_sctp_collision.sh new file mode 100755 index 000000000000..a924e595cfd8 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_sctp_collision.sh @@ -0,0 +1,89 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Testing For SCTP COLLISION SCENARIO as Below: +# +# 14:35:47.655279 IP CLIENT_IP.PORT > SERVER_IP.PORT: sctp (1) [INIT] [init tag: 2017837359] +# 14:35:48.353250 IP SERVER_IP.PORT > CLIENT_IP.PORT: sctp (1) [INIT] [init tag: 1187206187] +# 14:35:48.353275 IP CLIENT_IP.PORT > SERVER_IP.PORT: sctp (1) [INIT ACK] [init tag: 2017837359] +# 14:35:48.353283 IP SERVER_IP.PORT > CLIENT_IP.PORT: sctp (1) [COOKIE ECHO] +# 14:35:48.353977 IP CLIENT_IP.PORT > SERVER_IP.PORT: sctp (1) [COOKIE ACK] +# 14:35:48.855335 IP SERVER_IP.PORT > CLIENT_IP.PORT: sctp (1) [INIT ACK] [init tag: 164579970] +# +# TOPO: SERVER_NS (link0)<--->(link1) ROUTER_NS (link2)<--->(link3) CLIENT_NS + +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +CLIENT_IP="198.51.200.1" +CLIENT_PORT=1234 + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +SERVER_IP="198.51.100.1" +SERVER_PORT=1234 + +ROUTER_NS=$(mktemp -u router-XXXXXXXX) +CLIENT_GW="198.51.200.2" +SERVER_GW="198.51.100.2" + +# setup the topo +setup() { + ip net add $CLIENT_NS + ip net add $SERVER_NS + ip net add $ROUTER_NS + ip -n $SERVER_NS link add link0 type veth peer name link1 netns $ROUTER_NS + ip -n $CLIENT_NS link add link3 type veth peer name link2 netns $ROUTER_NS + + ip -n $SERVER_NS link set link0 up + ip -n $SERVER_NS addr add $SERVER_IP/24 dev link0 + ip -n $SERVER_NS route add $CLIENT_IP dev link0 via $SERVER_GW + + ip -n $ROUTER_NS link set link1 up + ip -n $ROUTER_NS link set link2 up + ip -n $ROUTER_NS addr add $SERVER_GW/24 dev link1 + ip -n $ROUTER_NS addr add $CLIENT_GW/24 dev link2 + ip net exec $ROUTER_NS sysctl -wq net.ipv4.ip_forward=1 + + ip -n $CLIENT_NS link set link3 up + ip -n $CLIENT_NS addr add $CLIENT_IP/24 dev link3 + ip -n $CLIENT_NS route add $SERVER_IP dev link3 via $CLIENT_GW + + # simulate the delay on OVS upcall by setting up a delay for INIT_ACK with + # tc on $SERVER_NS side + tc -n $SERVER_NS qdisc add dev link0 root handle 1: htb + tc -n $SERVER_NS class add dev link0 parent 1: classid 1:1 htb rate 100mbit + tc -n $SERVER_NS filter add dev link0 parent 1: protocol ip u32 match ip protocol 132 \ + 0xff match u8 2 0xff at 32 flowid 1:1 + tc -n $SERVER_NS qdisc add dev link0 parent 1:1 handle 10: netem delay 1200ms + + # simulate the ctstate check on OVS nf_conntrack + ip net exec $ROUTER_NS iptables -A FORWARD -m state --state INVALID,UNTRACKED -j DROP + ip net exec $ROUTER_NS iptables -A INPUT -p sctp -j DROP + + # use a smaller number for assoc's max_retrans to reproduce the issue + modprobe sctp + ip net exec $CLIENT_NS sysctl -wq net.sctp.association_max_retrans=3 +} + +cleanup() { + ip net exec $CLIENT_NS pkill sctp_collision 2>&1 >/dev/null + ip net exec $SERVER_NS pkill sctp_collision 2>&1 >/dev/null + ip net del "$CLIENT_NS" + ip net del "$SERVER_NS" + ip net del "$ROUTER_NS" +} + +do_test() { + ip net exec $SERVER_NS ./sctp_collision server \ + $SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT & + ip net exec $CLIENT_NS ./sctp_collision client \ + $CLIENT_IP $CLIENT_PORT $SERVER_IP $SERVER_PORT +} + +# NOTE: one way to work around the issue is set a smaller hb_interval +# ip net exec $CLIENT_NS sysctl -wq net.sctp.hb_interval=3500 + +# run the test case +trap cleanup EXIT +setup && \ +echo "Test for SCTP Collision in nf_conntrack:" && \ +do_test && echo "PASS!" +exit $? diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh index 83c271b1c735..bb34329e02a7 100755 --- a/tools/testing/selftests/netfilter/nft_audit.sh +++ b/tools/testing/selftests/netfilter/nft_audit.sh @@ -12,10 +12,11 @@ nft --version >/dev/null 2>&1 || { } logfile=$(mktemp) +rulefile=$(mktemp) echo "logging into $logfile" ./audit_logread >"$logfile" & logread_pid=$! -trap 'kill $logread_pid; rm -f $logfile' EXIT +trap 'kill $logread_pid; rm -f $logfile $rulefile' EXIT exec 3<"$logfile" do_test() { # (cmd, log) @@ -26,12 +27,14 @@ do_test() { # (cmd, log) res=$(diff -a -u <(echo "$2") - <&3) [ $? -eq 0 ] && { echo "OK"; return; } echo "FAIL" - echo "$res" - ((RC++)) + grep -v '^\(---\|+++\|@@\)' <<< "$res" + ((RC--)) } nft flush ruleset +# adding tables, chains and rules + for table in t1 t2; do do_test "nft add table $table" \ "table=$table family=2 entries=1 op=nft_register_table" @@ -62,6 +65,48 @@ for table in t1 t2; do "table=$table family=2 entries=6 op=nft_register_rule" done +for ((i = 0; i < 500; i++)); do + echo "add rule t2 c3 counter accept comment \"rule $i\"" +done >$rulefile +do_test "nft -f $rulefile" \ +'table=t2 family=2 entries=500 op=nft_register_rule' + +# adding sets and elements + +settype='type inet_service; counter' +setelem='{ 22, 80, 443 }' +setblock="{ $settype; elements = $setelem; }" +do_test "nft add set t1 s $setblock" \ +"table=t1 family=2 entries=4 op=nft_register_set" + +do_test "nft add set t1 s2 $setblock; add set t1 s3 { $settype; }" \ +"table=t1 family=2 entries=5 op=nft_register_set" + +do_test "nft add element t1 s3 $setelem" \ +"table=t1 family=2 entries=3 op=nft_register_setelem" + +# adding counters + +do_test 'nft add counter t1 c1' \ +'table=t1 family=2 entries=1 op=nft_register_obj' + +do_test 'nft add counter t2 c1; add counter t2 c2' \ +'table=t2 family=2 entries=2 op=nft_register_obj' + +# adding/updating quotas + +do_test 'nft add quota t1 q1 { 10 bytes }' \ +'table=t1 family=2 entries=1 op=nft_register_obj' + +do_test 'nft add quota t2 q1 { 10 bytes }; add quota t2 q2 { 10 bytes }' \ +'table=t2 family=2 entries=2 op=nft_register_obj' + +# changing the quota value triggers obj update path +do_test 'nft add quota t1 q1 { 20 bytes }' \ +'table=t1 family=2 entries=1 op=nft_register_obj' + +# resetting rules + do_test 'nft reset rules t1 c2' \ 'table=t1 family=2 entries=3 op=nft_reset_rule' @@ -70,19 +115,6 @@ do_test 'nft reset rules table t1' \ table=t1 family=2 entries=3 op=nft_reset_rule table=t1 family=2 entries=3 op=nft_reset_rule' -do_test 'nft reset rules' \ -'table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t1 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule -table=t2 family=2 entries=3 op=nft_reset_rule' - -for ((i = 0; i < 500; i++)); do - echo "add rule t2 c3 counter accept comment \"rule $i\"" -done | do_test 'nft -f -' \ -'table=t2 family=2 entries=500 op=nft_register_rule' - do_test 'nft reset rules t2 c3' \ 'table=t2 family=2 entries=189 op=nft_reset_rule table=t2 family=2 entries=188 op=nft_reset_rule @@ -105,4 +137,57 @@ table=t2 family=2 entries=180 op=nft_reset_rule table=t2 family=2 entries=188 op=nft_reset_rule table=t2 family=2 entries=135 op=nft_reset_rule' +# resetting sets and elements + +elem=(22 ,80 ,443) +relem="" +for i in {1..3}; do + relem+="${elem[((i - 1))]}" + do_test "nft reset element t1 s { $relem }" \ + "table=t1 family=2 entries=$i op=nft_reset_setelem" +done + +do_test 'nft reset set t1 s' \ +'table=t1 family=2 entries=3 op=nft_reset_setelem' + +# deleting rules + +readarray -t handles < <(nft -a list chain t1 c1 | \ + sed -n 's/.*counter.* handle \(.*\)$/\1/p') + +do_test "nft delete rule t1 c1 handle ${handles[0]}" \ +'table=t1 family=2 entries=1 op=nft_unregister_rule' + +cmd='delete rule t1 c1 handle' +do_test "nft $cmd ${handles[1]}; $cmd ${handles[2]}" \ +'table=t1 family=2 entries=2 op=nft_unregister_rule' + +do_test 'nft flush chain t1 c2' \ +'table=t1 family=2 entries=3 op=nft_unregister_rule' + +do_test 'nft flush table t2' \ +'table=t2 family=2 entries=509 op=nft_unregister_rule' + +# deleting chains + +do_test 'nft delete chain t2 c2' \ +'table=t2 family=2 entries=1 op=nft_unregister_chain' + +# deleting sets and elements + +do_test 'nft delete element t1 s { 22 }' \ +'table=t1 family=2 entries=1 op=nft_unregister_setelem' + +do_test 'nft delete element t1 s { 80, 443 }' \ +'table=t1 family=2 entries=2 op=nft_unregister_setelem' + +do_test 'nft flush set t1 s2' \ +'table=t1 family=2 entries=3 op=nft_unregister_setelem' + +do_test 'nft delete set t1 s2' \ +'table=t1 family=2 entries=1 op=nft_unregister_set' + +do_test 'nft delete set t1 s3' \ +'table=t1 family=2 entries=1 op=nft_unregister_set' + exit $RC diff --git a/tools/testing/selftests/netfilter/sctp_collision.c b/tools/testing/selftests/netfilter/sctp_collision.c new file mode 100644 index 000000000000..21bb1cfd8a85 --- /dev/null +++ b/tools/testing/selftests/netfilter/sctp_collision.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <arpa/inet.h> + +int main(int argc, char *argv[]) +{ + struct sockaddr_in saddr = {}, daddr = {}; + int sd, ret, len = sizeof(daddr); + struct timeval tv = {25, 0}; + char buf[] = "hello"; + + if (argc != 6 || (strcmp(argv[1], "server") && strcmp(argv[1], "client"))) { + printf("%s <server|client> <LOCAL_IP> <LOCAL_PORT> <REMOTE_IP> <REMOTE_PORT>\n", + argv[0]); + return -1; + } + + sd = socket(AF_INET, SOCK_SEQPACKET, IPPROTO_SCTP); + if (sd < 0) { + printf("Failed to create sd\n"); + return -1; + } + + saddr.sin_family = AF_INET; + saddr.sin_addr.s_addr = inet_addr(argv[2]); + saddr.sin_port = htons(atoi(argv[3])); + + ret = bind(sd, (struct sockaddr *)&saddr, sizeof(saddr)); + if (ret < 0) { + printf("Failed to bind to address\n"); + goto out; + } + + ret = listen(sd, 5); + if (ret < 0) { + printf("Failed to listen on port\n"); + goto out; + } + + daddr.sin_family = AF_INET; + daddr.sin_addr.s_addr = inet_addr(argv[4]); + daddr.sin_port = htons(atoi(argv[5])); + + /* make test shorter than 25s */ + ret = setsockopt(sd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)); + if (ret < 0) { + printf("Failed to setsockopt SO_RCVTIMEO\n"); + goto out; + } + + if (!strcmp(argv[1], "server")) { + sleep(1); /* wait a bit for client's INIT */ + ret = connect(sd, (struct sockaddr *)&daddr, len); + if (ret < 0) { + printf("Failed to connect to peer\n"); + goto out; + } + ret = recvfrom(sd, buf, sizeof(buf), 0, (struct sockaddr *)&daddr, &len); + if (ret < 0) { + printf("Failed to recv msg %d\n", ret); + goto out; + } + ret = sendto(sd, buf, strlen(buf) + 1, 0, (struct sockaddr *)&daddr, len); + if (ret < 0) { + printf("Failed to send msg %d\n", ret); + goto out; + } + printf("Server: sent! %d\n", ret); + } + + if (!strcmp(argv[1], "client")) { + usleep(300000); /* wait a bit for server's listening */ + ret = connect(sd, (struct sockaddr *)&daddr, len); + if (ret < 0) { + printf("Failed to connect to peer\n"); + goto out; + } + sleep(1); /* wait a bit for server's delayed INIT_ACK to reproduce the issue */ + ret = sendto(sd, buf, strlen(buf) + 1, 0, (struct sockaddr *)&daddr, len); + if (ret < 0) { + printf("Failed to send msg %d\n", ret); + goto out; + } + ret = recvfrom(sd, buf, sizeof(buf), 0, (struct sockaddr *)&daddr, &len); + if (ret < 0) { + printf("Failed to recv msg %d\n", ret); + goto out; + } + printf("Client: rcvd! %d\n", ret); + } + ret = 0; +out: + close(sd); + return ret; +} diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 843ba56d8e49..254d676a2689 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 49f2ad1793fd..7ea42fa02eab 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -59,12 +59,11 @@ override define INSTALL_RULE done; endef -override define EMIT_TESTS +emit_tests: +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET $@;\ done; -endef override define CLEAN +@for TARGET in $(SUB_DIRS); do \ @@ -77,4 +76,4 @@ endef tags: find . -name '*.c' -o -name '*.h' | xargs ctags -.PHONY: tags $(SUB_DIRS) +.PHONY: tags $(SUB_DIRS) emit_tests diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 2b95e44d20ff..a284fa874a9f 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -30,13 +30,14 @@ override define RUN_TESTS +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef -DEFAULT_EMIT_TESTS := $(EMIT_TESTS) -override define EMIT_TESTS - $(DEFAULT_EMIT_TESTS) +emit_tests: + for TEST in $(TEST_GEN_PROGS); do \ + BASENAME_TEST=`basename $$TEST`; \ + echo "$(COLLECTION):$$BASENAME_TEST"; \ + done +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests -endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE @@ -64,4 +65,4 @@ sampling_tests: event_code_tests: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests ebb sampling_tests event_code_tests +.PHONY: all run_tests ebb sampling_tests event_code_tests emit_tests diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index b16c13688b88..ee71ce52cb6a 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -267,6 +267,7 @@ static const char g_smaps_rollup[] = "Private_Dirty: 0 kB\n" "Referenced: 0 kB\n" "Anonymous: 0 kB\n" +"KSM: 0 kB\n" "LazyFree: 0 kB\n" "AnonHugePages: 0 kB\n" "ShmemPmdMapped: 0 kB\n" diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 22374d29ffdd..8202f1327c39 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -91,16 +91,18 @@ static int reg_disable(long *enable, int bit) FIXTURE(user) { long check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); change_event(false); self->check = 0; } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); } TEST_F(user, enablement) { diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 32c827a52d7d..a85980190bea 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -144,13 +144,16 @@ do { \ FIXTURE(user) { int check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); + wait_for_delete(); } diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 6a260caeeddc..dcd7509fe2e0 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -204,10 +204,11 @@ FIXTURE(user) { int data_fd; int enable_fd; int check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); self->status_fd = open(status_file, O_RDONLY); ASSERT_NE(-1, self->status_fd); @@ -219,6 +220,8 @@ FIXTURE_SETUP(user) { } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); + close(self->status_fd); close(self->data_fd); diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index f893398cda05..5288e768b207 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -111,16 +111,19 @@ static int clear(int *check) FIXTURE(user) { int data_fd; int check; + bool umount; }; FIXTURE_SETUP(user) { - USER_EVENT_FIXTURE_SETUP(return); + USER_EVENT_FIXTURE_SETUP(return, self->umount); self->data_fd = open(data_file, O_RDWR); ASSERT_NE(-1, self->data_fd); } FIXTURE_TEARDOWN(user) { + USER_EVENT_FIXTURE_TEARDOWN(self->umount); + close(self->data_fd); if (clear(&self->check) != 0) diff --git a/tools/testing/selftests/user_events/user_events_selftests.h b/tools/testing/selftests/user_events/user_events_selftests.h index 690378942f82..e1c3c063c031 100644 --- a/tools/testing/selftests/user_events/user_events_selftests.h +++ b/tools/testing/selftests/user_events/user_events_selftests.h @@ -11,13 +11,19 @@ #include "../kselftest.h" -static inline bool tracefs_enabled(char **message, bool *fail) +static inline void tracefs_unmount(void) +{ + umount("/sys/kernel/tracing"); +} + +static inline bool tracefs_enabled(char **message, bool *fail, bool *umount) { struct stat buf; int ret; *message = ""; *fail = false; + *umount = false; /* Ensure tracefs is installed */ ret = stat("/sys/kernel/tracing", &buf); @@ -37,6 +43,8 @@ static inline bool tracefs_enabled(char **message, bool *fail) return false; } + *umount = true; + ret = stat("/sys/kernel/tracing/README", &buf); } @@ -49,13 +57,14 @@ static inline bool tracefs_enabled(char **message, bool *fail) return true; } -static inline bool user_events_enabled(char **message, bool *fail) +static inline bool user_events_enabled(char **message, bool *fail, bool *umount) { struct stat buf; int ret; *message = ""; *fail = false; + *umount = false; if (getuid() != 0) { *message = "Must be run as root"; @@ -63,7 +72,7 @@ static inline bool user_events_enabled(char **message, bool *fail) return false; } - if (!tracefs_enabled(message, fail)) + if (!tracefs_enabled(message, fail, umount)) return false; /* Ensure user_events is installed */ @@ -85,10 +94,10 @@ static inline bool user_events_enabled(char **message, bool *fail) return true; } -#define USER_EVENT_FIXTURE_SETUP(statement) do { \ +#define USER_EVENT_FIXTURE_SETUP(statement, umount) do { \ char *message; \ bool fail; \ - if (!user_events_enabled(&message, &fail)) { \ + if (!user_events_enabled(&message, &fail, &(umount))) { \ if (fail) { \ TH_LOG("Setup failed due to: %s", message); \ ASSERT_FALSE(fail); \ @@ -97,4 +106,9 @@ static inline bool user_events_enabled(char **message, bool *fail) } \ } while (0) +#define USER_EVENT_FIXTURE_TEARDOWN(umount) do { \ + if ((umount)) \ + tracefs_unmount(); \ +} while (0) + #endif /* _USER_EVENTS_SELFTESTS_H */ diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c index e0ffe69c271c..7093fd5333be 100644 --- a/tools/tracing/rtla/src/timerlat_aa.c +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -159,6 +159,7 @@ static int timerlat_aa_irq_latency(struct timerlat_aa_data *taa_data, taa_data->thread_nmi_sum = 0; taa_data->thread_irq_sum = 0; taa_data->thread_softirq_sum = 0; + taa_data->thread_thread_sum = 0; taa_data->thread_blocking_duration = 0; taa_data->timer_irq_start_time = 0; taa_data->timer_irq_duration = 0; @@ -337,7 +338,23 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor taa_data->timer_irq_start_time = start; taa_data->timer_irq_duration = duration; - taa_data->timer_irq_start_delay = taa_data->timer_irq_start_time - expected_start; + /* + * We are dealing with two different clock sources: the + * external clock source that timerlat uses as a reference + * and the clock used by the tracer. There are also two + * moments: the time reading the clock and the timer in + * which the event is placed in the buffer (the trace + * event timestamp). If the processor is slow or there + * is some hardware noise, the difference between the + * timestamp and the external clock read can be longer + * than the IRQ handler delay, resulting in a negative + * time. If so, set IRQ start delay as 0. In the end, + * it is less relevant than the noise. + */ + if (expected_start < taa_data->timer_irq_start_time) + taa_data->timer_irq_start_delay = taa_data->timer_irq_start_time - expected_start; + else + taa_data->timer_irq_start_delay = 0; /* * not exit from idle. @@ -528,7 +545,7 @@ static int timerlat_aa_kworker_start_handler(struct trace_seq *s, struct tep_rec static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, int irq_thresh, int thread_thresh) { - unsigned long long exp_irq_ts; + long long exp_irq_ts; int total; int irq; @@ -545,12 +562,15 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, /* * Expected IRQ arrival time using the trace clock as the base. + * + * TODO: Add a list of previous IRQ, and then run the list backwards. */ exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay; - - if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) - printf(" Previous IRQ interference: \t\t up to %9.2f us\n", - ns_to_usf(taa_data->prev_irq_duration)); + if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) { + if (taa_data->prev_irq_timstamp < taa_data->timer_irq_start_time) + printf(" Previous IRQ interference: \t\t up to %9.2f us\n", + ns_to_usf(taa_data->prev_irq_duration)); + } /* * The delay that the IRQ suffered before starting. diff --git a/tools/tracing/rtla/src/timerlat_u.c b/tools/tracing/rtla/src/timerlat_u.c index 05e310696dd5..01dbf9a6b5a5 100644 --- a/tools/tracing/rtla/src/timerlat_u.c +++ b/tools/tracing/rtla/src/timerlat_u.c @@ -45,7 +45,7 @@ static int timerlat_u_main(int cpu, struct timerlat_u_params *params) retval = sched_setaffinity(gettid(), sizeof(set), &set); if (retval == -1) { - err_msg("Error setting user thread affinity\n"); + debug_msg("Error setting user thread affinity %d, is the CPU online?\n", cpu); exit(1); } @@ -193,7 +193,9 @@ void *timerlat_u_dispatcher(void *data) procs_count--; } } - break; + + if (!procs_count) + break; } sleep(1); |