diff options
1488 files changed, 21127 insertions, 13720 deletions
@@ -213,6 +213,7 @@ Kees Cook <keescook@chromium.org> <kees@ubuntu.com> Keith Busch <kbusch@kernel.org> <keith.busch@intel.com> Keith Busch <kbusch@kernel.org> <keith.busch@linux.intel.com> Kenneth W Chen <kenneth.w.chen@intel.com> +Kirill Tkhai <kirill.tkhai@openvz.org> <ktkhai@virtuozzo.com> Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru> Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Koushik <raghavendra.koushik@neterion.com> @@ -390,6 +391,10 @@ Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com> Valdis Kletnieks <Valdis.Kletnieks@vt.edu> +Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org> +Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> diff --git a/Documentation/ABI/testing/sysfs-class-firmware-attributes b/Documentation/ABI/testing/sysfs-class-firmware-attributes index 05820365f1ec..4cdba3477176 100644 --- a/Documentation/ABI/testing/sysfs-class-firmware-attributes +++ b/Documentation/ABI/testing/sysfs-class-firmware-attributes @@ -116,7 +116,7 @@ Description: <value>[ForceIf:<attribute>=<value>] <value>[ForceIfNot:<attribute>=<value>] - For example: + For example:: LegacyOrom/dell_value_modifier has value: Disabled[ForceIf:SecureBoot=Enabled] @@ -212,7 +212,7 @@ Description: the next boot. Lenovo specific class extensions - ------------------------------ + -------------------------------- On Lenovo systems the following additional settings are available: @@ -246,9 +246,7 @@ Description: that is being referenced (e.g hdd0, hdd1 etc) This attribute defaults to device 0. - certificate: - signature: - save_signature: + certificate, signature, save_signature: These attributes are used for certificate based authentication. This is used in conjunction with a signing server as an alternative to password based authentication. @@ -257,22 +255,27 @@ Description: The attributes can be displayed to check the stored value. Some usage examples: - Installing a certificate to enable feature: - echo <supervisor password > authentication/Admin/current_password - echo <signed certificate> > authentication/Admin/certificate - Updating the installed certificate: - echo <signature> > authentication/Admin/signature - echo <signed certificate> > authentication/Admin/certificate + Installing a certificate to enable feature:: + + echo "supervisor password" > authentication/Admin/current_password + echo "signed certificate" > authentication/Admin/certificate + + Updating the installed certificate:: + + echo "signature" > authentication/Admin/signature + echo "signed certificate" > authentication/Admin/certificate - Removing the installed certificate: - echo <signature> > authentication/Admin/signature - echo '' > authentication/Admin/certificate + Removing the installed certificate:: - Changing a BIOS setting: - echo <signature> > authentication/Admin/signature - echo <save signature> > authentication/Admin/save_signature - echo Enable > attribute/PasswordBeep/current_value + echo "signature" > authentication/Admin/signature + echo "" > authentication/Admin/certificate + + Changing a BIOS setting:: + + echo "signature" > authentication/Admin/signature + echo "save signature" > authentication/Admin/save_signature + echo Enable > attribute/PasswordBeep/current_value You cannot enable certificate authentication if a supervisor password has not been set. @@ -288,9 +291,10 @@ Description: certificate_to_password: Write only attribute used to switch from certificate based authentication back to password based. - Usage: - echo <signature> > authentication/Admin/signature - echo <password> > authentication/Admin/certificate_to_password + Usage:: + + echo "signature" > authentication/Admin/signature + echo "password" > authentication/Admin/certificate_to_password What: /sys/class/firmware-attributes/*/attributes/pending_reboot @@ -345,7 +349,7 @@ Description: # echo "factory" > /sys/class/firmware-attributes/*/device/attributes/reset_bios # cat /sys/class/firmware-attributes/*/device/attributes/reset_bios - # builtinsafe lastknowngood [factory] custom + builtinsafe lastknowngood [factory] custom Note that any changes to this attribute requires a reboot for changes to take effect. diff --git a/Documentation/ABI/testing/sysfs-driver-intel_sdsi b/Documentation/ABI/testing/sysfs-driver-intel_sdsi index ab122125ff9a..96b92c105ec4 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel_sdsi +++ b/Documentation/ABI/testing/sysfs-driver-intel_sdsi @@ -13,17 +13,19 @@ Description: Should the operation fail, one of the following error codes may be returned: + ========== ===== Error Code Cause - ---------- ----- - EIO General mailbox failure. Log may indicate cause. - EBUSY Mailbox is owned by another agent. - EPERM SDSI capability is not enabled in hardware. - EPROTO Failure in mailbox protocol detected by driver. + ========== ===== + EIO General mailbox failure. Log may indicate cause. + EBUSY Mailbox is owned by another agent. + EPERM SDSI capability is not enabled in hardware. + EPROTO Failure in mailbox protocol detected by driver. See log for details. - EOVERFLOW For provision commands, the size of the data + EOVERFLOW For provision commands, the size of the data exceeds what may be written. - ESPIPE Seeking is not allowed. - ETIMEDOUT Failure to complete mailbox transaction in time. + ESPIPE Seeking is not allowed. + ETIMEDOUT Failure to complete mailbox transaction in time. + ========== ===== What: /sys/bus/auxiliary/devices/intel_vsec.sdsi.X/guid Date: Feb 2022 diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index 05482374a741..bb4681a01811 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -9,8 +9,9 @@ Description: Shows all enabled kernel features. What: /sys/fs/erofs/<disk>/sync_decompress Date: November 2021 Contact: "Huang Jianan" <huangjianan@oppo.com> -Description: Control strategy of sync decompression +Description: Control strategy of sync decompression: + - 0 (default, auto): enable for readpage, and enable for - readahead on atomic contexts only, + readahead on atomic contexts only. - 1 (force on): enable for readpage and readahead. - 2 (force off): disable for all situations. diff --git a/Documentation/PCI/pci.rst b/Documentation/PCI/pci.rst index 87c6f4a6ca32..67a850b55617 100644 --- a/Documentation/PCI/pci.rst +++ b/Documentation/PCI/pci.rst @@ -278,20 +278,20 @@ appropriate parameters. In general this allows more efficient DMA on systems where System RAM exists above 4G _physical_ address. Drivers for all PCI-X and PCIe compliant devices must call -pci_set_dma_mask() as they are 64-bit DMA devices. +set_dma_mask() as they are 64-bit DMA devices. Similarly, drivers must also "register" this capability if the device -can directly address "consistent memory" in System RAM above 4G physical -address by calling pci_set_consistent_dma_mask(). +can directly address "coherent memory" in System RAM above 4G physical +address by calling dma_set_coherent_mask(). Again, this includes drivers for all PCI-X and PCIe compliant devices. Many 64-bit "PCI" devices (before PCI-X) and some PCI-X devices are 64-bit DMA capable for payload ("streaming") data but not control -("consistent") data. +("coherent") data. Setup shared control data ------------------------- -Once the DMA masks are set, the driver can allocate "consistent" (a.k.a. shared) +Once the DMA masks are set, the driver can allocate "coherent" (a.k.a. shared) memory. See Documentation/core-api/dma-api.rst for a full description of the DMA APIs. This section is just a reminder that it needs to be done before enabling DMA on the device. @@ -367,7 +367,7 @@ steps need to be performed: - Disable the device from generating IRQs - Release the IRQ (free_irq()) - Stop all DMA activity - - Release DMA buffers (both streaming and consistent) + - Release DMA buffers (both streaming and coherent) - Unregister from other subsystems (e.g. scsi or netdev) - Disable device from responding to MMIO/IO Port addresses - Release MMIO/IO Port resource(s) @@ -420,7 +420,7 @@ Once DMA is stopped, clean up streaming DMA first. I.e. unmap data buffers and return buffers to "upstream" owners if there is one. -Then clean up "consistent" buffers which contain the control data. +Then clean up "coherent" buffers which contain the control data. See Documentation/core-api/dma-api.rst for details on unmapping interfaces. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b7ccaa2ea867..3f1cc5e317ed 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4427,6 +4427,12 @@ fully seed the kernel's CRNG. Default is controlled by CONFIG_RANDOM_TRUST_CPU. + random.trust_bootloader={on,off} + [KNL] Enable or disable trusting the use of a + seed passed by the bootloader (if available) to + fully seed the kernel's CRNG. Default is controlled + by CONFIG_RANDOM_TRUST_BOOTLOADER. + randomize_kstack_offset= [KNL] Enable or disable kernel stack offset randomization, which provides roughly 5 bits of diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index a137a0e6d068..77e0ece2b1d6 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -315,11 +315,15 @@ indeed the normal API is implemented in terms of the advanced API. The advanced API is only available to modules with a GPL-compatible license. The advanced API is based around the xa_state. This is an opaque data -structure which you declare on the stack using the XA_STATE() -macro. This macro initialises the xa_state ready to start walking -around the XArray. It is used as a cursor to maintain the position -in the XArray and let you compose various operations together without -having to restart from the top every time. +structure which you declare on the stack using the XA_STATE() macro. +This macro initialises the xa_state ready to start walking around the +XArray. It is used as a cursor to maintain the position in the XArray +and let you compose various operations together without having to restart +from the top every time. The contents of the xa_state are protected by +the rcu_read_lock() or the xas_lock(). If you need to drop whichever of +those locks is protecting your state and tree, you must call xas_pause() +so that future calls do not rely on the parts of the state which were +left unprotected. The xa_state is also used to store errors. You can call xas_error() to retrieve the error. All operations check whether diff --git a/Documentation/dev-tools/kunit/architecture.rst b/Documentation/dev-tools/kunit/architecture.rst index aa2cea821e25..ff9c85a0bff2 100644 --- a/Documentation/dev-tools/kunit/architecture.rst +++ b/Documentation/dev-tools/kunit/architecture.rst @@ -26,10 +26,7 @@ The fundamental unit in KUnit is the test case. The KUnit test cases are grouped into KUnit suites. A KUnit test case is a function with type signature ``void (*)(struct kunit *test)``. These test case functions are wrapped in a struct called -``struct kunit_case``. For code, see: - -.. kernel-doc:: include/kunit/test.h - :identifiers: kunit_case +struct kunit_case. .. note: ``generate_params`` is optional for non-parameterized tests. @@ -152,18 +149,12 @@ Parameterized Tests Each KUnit parameterized test is associated with a collection of parameters. The test is invoked multiple times, once for each parameter value and the parameter is stored in the ``param_value`` field. -The test case includes a ``KUNIT_CASE_PARAM()`` macro that accepts a +The test case includes a KUNIT_CASE_PARAM() macro that accepts a generator function. The generator function is passed the previous parameter and returns the next parameter. It also provides a macro to generate common-case generators based on arrays. -For code, see: - -.. kernel-doc:: include/kunit/test.h - :identifiers: KUNIT_ARRAY_PARAM - - kunit_tool (Command Line Test Harness) ====================================== diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index ad168d16968f..867a4bba6bf6 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -41,13 +41,18 @@ or ``VFAT_FS``. To run ``FAT_KUNIT_TEST``, the ``.kunitconfig`` has: CONFIG_MSDOS_FS=y CONFIG_FAT_KUNIT_TEST=y -1. A good starting point for the ``.kunitconfig``, is the KUnit default - config. Run the command: +1. A good starting point for the ``.kunitconfig`` is the KUnit default config. + You can generate it by running: .. code-block:: bash cd $PATH_TO_LINUX_REPO - cp tools/testing/kunit/configs/default.config .kunitconfig + tools/testing/kunit/kunit.py config + cat .kunit/.kunitconfig + +.. note :: + ``.kunitconfig`` lives in the ``--build_dir`` used by kunit.py, which is + ``.kunit`` by default. .. note :: You may want to remove CONFIG_KUNIT_ALL_TESTS from the ``.kunitconfig`` as diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt b/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt index 6ce0b212ec6d..606b4b1b709d 100644 --- a/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt +++ b/Documentation/devicetree/bindings/arm/msm/qcom,idle-state.txt @@ -81,4 +81,4 @@ Example: }; }; -[1]. Documentation/devicetree/bindings/arm/idle-states.yaml +[1]. Documentation/devicetree/bindings/cpu/idle-states.yaml diff --git a/Documentation/devicetree/bindings/arm/psci.yaml b/Documentation/devicetree/bindings/arm/psci.yaml index 8b77cf83a095..dd83ef278af0 100644 --- a/Documentation/devicetree/bindings/arm/psci.yaml +++ b/Documentation/devicetree/bindings/arm/psci.yaml @@ -101,7 +101,7 @@ properties: bindings in [1]) must specify this property. [1] Kernel documentation - ARM idle states bindings - Documentation/devicetree/bindings/arm/idle-states.yaml + Documentation/devicetree/bindings/cpu/idle-states.yaml patternProperties: "^power-domain-": diff --git a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml index 0afec83cc723..564ae6aaccf7 100644 --- a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml +++ b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml @@ -14,7 +14,6 @@ properties: compatible: enum: - nvidia,tegra20-pmc - - nvidia,tegra20-pmc - nvidia,tegra30-pmc - nvidia,tegra114-pmc - nvidia,tegra124-pmc diff --git a/Documentation/devicetree/bindings/bus/ti-sysc.yaml b/Documentation/devicetree/bindings/bus/ti-sysc.yaml index bd40213302da..fced4082b047 100644 --- a/Documentation/devicetree/bindings/bus/ti-sysc.yaml +++ b/Documentation/devicetree/bindings/bus/ti-sysc.yaml @@ -35,7 +35,6 @@ properties: - items: - enum: - ti,sysc-omap2 - - ti,sysc-omap2 - ti,sysc-omap4 - ti,sysc-omap4-simple - ti,sysc-omap2-timer diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml index f14f1d39da36..d819dfaafff9 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC Audio SubSystem clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml index 4e8062860986..0589a63e273a 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml index 64d027dbe3b2..c98eff64f2b5 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml @@ -8,7 +8,7 @@ title: Samsung SoC external/osc/XXTI/XusbXTI clock maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml index 1ed64add4355..b644bbd0df38 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos4412 SoC ISP clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml index a3fac5c6809d..b05f83533e3d 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5260 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml index 032862e9f55b..b737c9d35a1c 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5410 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml index edd1b4ac4334..3f9326e09f79 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5433 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml index 599baf0b7231..c137c6744ef9 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos7 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml index 7e5a9cac2fd2..5073e569a47f 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml @@ -9,7 +9,7 @@ title: Samsung Exynos7885 SoC clock controller maintainers: - Dávid Virág <virag.david003@gmail.com> - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml index 80ba60838f2b..aa11815ad3a3 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml @@ -9,7 +9,7 @@ title: Samsung Exynos850 SoC clock controller maintainers: - Sam Protsenko <semen.protsenko@linaro.org> - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml index 1410c51e0e7d..9248bfc16d48 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2M and S5M family clock generator block maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml index ae8f8fc93233..2659854ea1c0 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml @@ -8,7 +8,7 @@ title: Samsung S5Pv210 SoC Audio SubSystem clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml index dcb29a2d1159..67a33665cf00 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml @@ -8,7 +8,7 @@ title: Samsung S5P6442/S5PC110/S5PV210 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/arm/idle-states.yaml b/Documentation/devicetree/bindings/cpu/idle-states.yaml index 4d381fa1ee57..fa4d4142ac93 100644 --- a/Documentation/devicetree/bindings/arm/idle-states.yaml +++ b/Documentation/devicetree/bindings/cpu/idle-states.yaml @@ -1,25 +1,30 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/idle-states.yaml# +$id: http://devicetree.org/schemas/cpu/idle-states.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: ARM idle states binding description +title: Idle states binding description maintainers: - Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + - Anup Patel <anup@brainfault.org> description: |+ ========================================== 1 - Introduction ========================================== - ARM systems contain HW capable of managing power consumption dynamically, - where cores can be put in different low-power states (ranging from simple wfi - to power gating) according to OS PM policies. The CPU states representing the - range of dynamic idle states that a processor can enter at run-time, can be - specified through device tree bindings representing the parameters required to - enter/exit specific idle states on a given processor. + ARM and RISC-V systems contain HW capable of managing power consumption + dynamically, where cores can be put in different low-power states (ranging + from simple wfi to power gating) according to OS PM policies. The CPU states + representing the range of dynamic idle states that a processor can enter at + run-time, can be specified through device tree bindings representing the + parameters required to enter/exit specific idle states on a given processor. + + ========================================== + 2 - ARM idle states + ========================================== According to the Server Base System Architecture document (SBSA, [3]), the power states an ARM CPU can be put into are identified by the following list: @@ -43,8 +48,23 @@ description: |+ The device tree binding definition for ARM idle states is the subject of this document. + ========================================== + 3 - RISC-V idle states + ========================================== + + On RISC-V systems, the HARTs (or CPUs) [6] can be put in platform specific + suspend (or idle) states (ranging from simple WFI, power gating, etc). The + RISC-V SBI v0.3 (or higher) [7] hart state management extension provides a + standard mechanism for OS to request HART state transitions. + + The platform specific suspend (or idle) states of a hart can be either + retentive or non-rententive in nature. A retentive suspend state will + preserve HART registers and CSR values for all privilege modes whereas + a non-retentive suspend state will not preserve HART registers and CSR + values. + =========================================== - 2 - idle-states definitions + 4 - idle-states definitions =========================================== Idle states are characterized for a specific system through a set of @@ -211,10 +231,10 @@ description: |+ properties specification that is the subject of the following sections. =========================================== - 3 - idle-states node + 5 - idle-states node =========================================== - ARM processor idle states are defined within the idle-states node, which is + The processor idle states are defined within the idle-states node, which is a direct child of the cpus node [1] and provides a container where the processor idle states, defined as device tree nodes, are listed. @@ -223,7 +243,7 @@ description: |+ just supports idle_standby, an idle-states node is not required. =========================================== - 4 - References + 6 - References =========================================== [1] ARM Linux Kernel documentation - CPUs bindings @@ -238,9 +258,15 @@ description: |+ [4] ARM Architecture Reference Manuals http://infocenter.arm.com/help/index.jsp - [6] ARM Linux Kernel documentation - Booting AArch64 Linux + [5] ARM Linux Kernel documentation - Booting AArch64 Linux Documentation/arm64/booting.rst + [6] RISC-V Linux Kernel documentation - CPUs bindings + Documentation/devicetree/bindings/riscv/cpus.yaml + + [7] RISC-V Supervisor Binary Interface (SBI) + http://github.com/riscv/riscv-sbi-doc/riscv-sbi.adoc + properties: $nodename: const: idle-states @@ -253,7 +279,7 @@ properties: On ARM 32-bit systems this property is optional This assumes that the "enable-method" property is set to "psci" in the cpu - node[6] that is responsible for setting up CPU idle management in the OS + node[5] that is responsible for setting up CPU idle management in the OS implementation. const: psci @@ -265,8 +291,8 @@ patternProperties: as follows. The idle state entered by executing the wfi instruction (idle_standby - SBSA,[3][4]) is considered standard on all ARM platforms and therefore - must not be listed. + SBSA,[3][4]) is considered standard on all ARM and RISC-V platforms and + therefore must not be listed. In addition to the properties listed above, a state node may require additional properties specific to the entry-method defined in the @@ -275,7 +301,27 @@ patternProperties: properties: compatible: - const: arm,idle-state + enum: + - arm,idle-state + - riscv,idle-state + + arm,psci-suspend-param: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + power_state parameter to pass to the ARM PSCI suspend call. + + Device tree nodes that require usage of PSCI CPU_SUSPEND function + (i.e. idle states node with entry-method property is set to "psci") + must specify this property. + + riscv,sbi-suspend-param: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + suspend_type parameter to pass to the RISC-V SBI HSM suspend call. + + This property is required in idle state nodes of device tree meant + for RISC-V systems. For more details on the suspend_type parameter + refer the SBI specifiation v0.3 (or higher) [7]. local-timer-stop: description: @@ -317,6 +363,8 @@ patternProperties: description: A string used as a descriptive name for the idle state. + additionalProperties: false + required: - compatible - entry-latency-us @@ -658,4 +706,150 @@ examples: }; }; + - | + // Example 3 (RISC-V 64-bit, 4-cpu systems, two clusters): + + cpus { + #size-cells = <0>; + #address-cells = <1>; + + cpu@0 { + device_type = "cpu"; + compatible = "riscv"; + reg = <0x0>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,sv48"; + cpu-idle-states = <&CPU_RET_0_0>, <&CPU_NONRET_0_0>, + <&CLUSTER_RET_0>, <&CLUSTER_NONRET_0>; + + cpu_intc0: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "riscv"; + reg = <0x1>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,sv48"; + cpu-idle-states = <&CPU_RET_0_0>, <&CPU_NONRET_0_0>, + <&CLUSTER_RET_0>, <&CLUSTER_NONRET_0>; + + cpu_intc1: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu@10 { + device_type = "cpu"; + compatible = "riscv"; + reg = <0x10>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,sv48"; + cpu-idle-states = <&CPU_RET_1_0>, <&CPU_NONRET_1_0>, + <&CLUSTER_RET_1>, <&CLUSTER_NONRET_1>; + + cpu_intc10: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu@11 { + device_type = "cpu"; + compatible = "riscv"; + reg = <0x11>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,sv48"; + cpu-idle-states = <&CPU_RET_1_0>, <&CPU_NONRET_1_0>, + <&CLUSTER_RET_1>, <&CLUSTER_NONRET_1>; + + cpu_intc11: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + idle-states { + CPU_RET_0_0: cpu-retentive-0-0 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x10000000>; + entry-latency-us = <20>; + exit-latency-us = <40>; + min-residency-us = <80>; + }; + + CPU_NONRET_0_0: cpu-nonretentive-0-0 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x90000000>; + entry-latency-us = <250>; + exit-latency-us = <500>; + min-residency-us = <950>; + }; + + CLUSTER_RET_0: cluster-retentive-0 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x11000000>; + local-timer-stop; + entry-latency-us = <50>; + exit-latency-us = <100>; + min-residency-us = <250>; + wakeup-latency-us = <130>; + }; + + CLUSTER_NONRET_0: cluster-nonretentive-0 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x91000000>; + local-timer-stop; + entry-latency-us = <600>; + exit-latency-us = <1100>; + min-residency-us = <2700>; + wakeup-latency-us = <1500>; + }; + + CPU_RET_1_0: cpu-retentive-1-0 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x10000010>; + entry-latency-us = <20>; + exit-latency-us = <40>; + min-residency-us = <80>; + }; + + CPU_NONRET_1_0: cpu-nonretentive-1-0 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x90000010>; + entry-latency-us = <250>; + exit-latency-us = <500>; + min-residency-us = <950>; + }; + + CLUSTER_RET_1: cluster-retentive-1 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x11000010>; + local-timer-stop; + entry-latency-us = <50>; + exit-latency-us = <100>; + min-residency-us = <250>; + wakeup-latency-us = <130>; + }; + + CLUSTER_NONRET_1: cluster-nonretentive-1 { + compatible = "riscv,idle-state"; + riscv,sbi-suspend-param = <0x91000010>; + local-timer-stop; + entry-latency-us = <600>; + exit-latency-us = <1100>; + min-residency-us = <2700>; + wakeup-latency-us = <1500>; + }; + }; + }; + ... diff --git a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml index d318fccf78f1..2bdd05af6079 100644 --- a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml +++ b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos NoC (Network on Chip) Probe maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung Exynos542x SoC has a NoC (Network on Chip) Probe for NoC bus. diff --git a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml index c9a8cb5fd555..e300df4b47f3 100644 --- a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml +++ b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC PPMU (Platform Performance Monitoring Unit) maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung Exynos SoC has PPMU (Platform Performance Monitoring Unit) for diff --git a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml index 62c3bd4cb28d..7257fd0ae4da 100644 --- a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml +++ b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml @@ -51,7 +51,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml index 5216c27fc0ad..a412a1da950f 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml @@ -39,7 +39,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml b/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml index d31483a78eab..6fb7e321f011 100644 --- a/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml +++ b/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml @@ -160,7 +160,7 @@ examples: mdss: mdss@5e00000 { #address-cells = <1>; #size-cells = <1>; - compatible = "qcom,qcm2290-mdss", "qcom,mdss"; + compatible = "qcom,qcm2290-mdss"; reg = <0x05e00000 0x1000>; reg-names = "mdss"; power-domains = <&dispcc MDSS_GDSC>; @@ -180,7 +180,7 @@ examples: <&apps_smmu 0x421 0x0>; ranges; - mdss_mdp: mdp@5e01000 { + mdss_mdp: display-controller@5e01000 { compatible = "qcom,qcm2290-dpu"; reg = <0x05e01000 0x8f000>, <0x05eb0000 0x2008>; diff --git a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml index f29789994b18..c2df8d28aaf5 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml @@ -83,6 +83,8 @@ properties: required: - compatible - reg + - width-mm + - height-mm - panel-timing unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/panel/panel-timing.yaml b/Documentation/devicetree/bindings/display/panel/panel-timing.yaml index 9bf592dc3033..7749de95ee40 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-timing.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-timing.yaml @@ -71,78 +71,72 @@ properties: hfront-porch: description: Horizontal front porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels hback-porch: description: Horizontal back porch timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels hsync-len: description: Horizontal sync length panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels vfront-porch: description: Vertical front porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines vback-porch: description: Vertical back porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines vsync-len: description: Vertical sync length panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml index f998a3a5b71f..919734c05c0b 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml index cb8e735ce3bd..63379fae3636 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml index ba40284ac66f..00e325a19cb1 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: Samsung Exynos SoC Mixer is responsible for mixing and blending multiple data diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml index 6f796835ea03..7c37470bd329 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | DECON (Display and Enhancement Controller) is the Display Controller for the diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml index 01fccb138ebd..c5c6239c28d0 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | MIC (Mobile Image Compressor) resides between DECON and MIPI DSI. MIPI DSI is diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml index afa137d47922..320eedc61a5b 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | DECON (Display and Enhancement Controller) is the Display Controller for the diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml index 9cf5f120d516..c62ea9d22843 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml index f9ffe3d6f957..128960545640 100644 --- a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77843 MicroUSB and Companion Power Management IC Extcon maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB @@ -25,7 +25,7 @@ properties: $ref: /schemas/connector/usb-connector.yaml# ports: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/properties/ports description: Any connector to the data bus of this controller should be modelled using the OF graph bindings specified diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml index 4d6bfae0653c..85f8d4764740 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml @@ -20,6 +20,7 @@ properties: - mediatek,mt8183-mali - realtek,rtd1619-mali - renesas,r9a07g044-mali + - renesas,r9a07g054-mali - rockchip,px30-mali - rockchip,rk3568-mali - const: arm,mali-bifrost # Mali Bifrost GPU model/revision is fully discoverable @@ -109,7 +110,9 @@ allOf: properties: compatible: contains: - const: renesas,r9a07g044-mali + enum: + - renesas,r9a07g044-mali + - renesas,r9a07g054-mali then: properties: interrupts: diff --git a/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml b/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml index 4b5851c326f7..b1a4c235376e 100644 --- a/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml +++ b/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LTC4151 High Voltage I2C Current and Voltage Monitor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml b/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml index c42051f8a191..028d6e570131 100644 --- a/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml +++ b/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip MCP3021 A/D converter maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml b/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml index 4669217d01e1..80df7182ea28 100644 --- a/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml +++ b/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Sensirion SHT15 humidity and temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml index d3eff4fac107..c5a889e3e27b 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TMP102 temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml index eda55bbc172d..dcbc6fbc3b48 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TMP108 temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml index 801ca9ba7d34..e7493e25a7d2 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml @@ -58,9 +58,8 @@ patternProperties: The value (two's complement) to be programmed in the channel specific N correction register. For remote channels only. $ref: /schemas/types.yaml#/definitions/int32 - items: - minimum: -128 - maximum: 127 + minimum: -128 + maximum: 127 required: - reg diff --git a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml index 19874e8b73b9..3e52a0db6c41 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung's High Speed I2C controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung's High Speed I2C controller is used to interface with I2C devices diff --git a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml index 84051b0129c2..c26230518957 100644 --- a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC I2C Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml index cf711082ad7d..666414a9c0de 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml @@ -98,6 +98,7 @@ allOf: - ti,adc121s - ti,ads7866 - ti,ads7868 + then: required: - vcc-supply # Devices with a vref diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml index 7c260f209687..92f9472a77ae 100644 --- a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml @@ -108,9 +108,7 @@ patternProperties: - [1-5]: order 1 to 5. For audio purpose it is recommended to use order 3 to 5. $ref: /schemas/types.yaml#/definitions/uint32 - items: - minimum: 0 - maximum: 5 + maximum: 5 "#io-channel-cells": const: 1 @@ -174,7 +172,7 @@ patternProperties: contains: const: st,stm32-dfsdm-adc - - then: + then: properties: st,adc-channels: minItems: 1 @@ -206,7 +204,7 @@ patternProperties: contains: const: st,stm32-dfsdm-dmic - - then: + then: properties: st,adc-channels: maxItems: 1 @@ -254,7 +252,7 @@ allOf: contains: const: st,stm32h7-dfsdm - - then: + then: patternProperties: "^filter@[0-9]+$": properties: @@ -269,7 +267,7 @@ allOf: contains: const: st,stm32mp1-dfsdm - - then: + then: patternProperties: "^filter@[0-9]+$": properties: diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml index 0d8fb56f4b09..65f86f26947c 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml @@ -59,9 +59,9 @@ allOf: contains: enum: - adi,ad5371 - then: - required: - - vref2-supply + then: + required: + - vref2-supply examples: - | diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml new file mode 100644 index 000000000000..b1770640f94b --- /dev/null +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -0,0 +1,77 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/mediatek,mt6779-keypad.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Mediatek's Keypad Controller device tree bindings + +maintainers: + - Fengping Yu <fengping.yu@mediatek.com> + +allOf: + - $ref: "/schemas/input/matrix-keymap.yaml#" + +description: | + Mediatek's Keypad controller is used to interface a SoC with a matrix-type + keypad device. The keypad controller supports multiple row and column lines. + A key can be placed at each intersection of a unique row and a unique column. + The keypad controller can sense a key-press and key-release and report the + event using a interrupt to the cpu. + +properties: + compatible: + oneOf: + - const: mediatek,mt6779-keypad + - items: + - enum: + - mediatek,mt6873-keypad + - const: mediatek,mt6779-keypad + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + items: + - const: kpd + + wakeup-source: + description: use any event on keypad as wakeup event + type: boolean + + debounce-delay-ms: + maximum: 256 + default: 16 + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + +additionalProperties: false + +examples: + - | + #include <dt-bindings/input/input.h> + #include <dt-bindings/interrupt-controller/arm-gic.h> + + soc { + #address-cells = <2>; + #size-cells = <2>; + + keyboard@10010000 { + compatible = "mediatek,mt6779-keypad"; + reg = <0 0x10010000 0 0x1000>; + interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_FALLING>; + clocks = <&clk26m>; + clock-names = "kpd"; + }; + }; diff --git a/Documentation/devicetree/bindings/input/mtk-pmic-keys.txt b/Documentation/devicetree/bindings/input/mtk-pmic-keys.txt index 535d92885372..9d00f2a8e13a 100644 --- a/Documentation/devicetree/bindings/input/mtk-pmic-keys.txt +++ b/Documentation/devicetree/bindings/input/mtk-pmic-keys.txt @@ -9,7 +9,10 @@ For MT6397/MT6323 MFD bindings see: Documentation/devicetree/bindings/mfd/mt6397.txt Required properties: -- compatible: "mediatek,mt6397-keys" or "mediatek,mt6323-keys" +- compatible: Should be one of: + - "mediatek,mt6397-keys" + - "mediatek,mt6323-keys" + - "mediatek,mt6358-keys" - linux,keycodes: See Documentation/devicetree/bindings/input/input.yaml Optional Properties: diff --git a/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml b/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml new file mode 100644 index 000000000000..e3a2b871e50c --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml @@ -0,0 +1,74 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/touchscreen/imagis,ist3038c.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Imagis IST30XXC family touchscreen controller bindings + +maintainers: + - Markuss Broks <markuss.broks@gmail.com> + +allOf: + - $ref: touchscreen.yaml# + +properties: + $nodename: + pattern: "^touchscreen@[0-9a-f]+$" + + compatible: + enum: + - imagis,ist3038c + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + vdd-supply: + description: Power supply regulator for the chip + + vddio-supply: + description: Power supply regulator for the I2C bus + + touchscreen-size-x: true + touchscreen-size-y: true + touchscreen-fuzz-x: true + touchscreen-fuzz-y: true + touchscreen-inverted-x: true + touchscreen-inverted-y: true + touchscreen-swapped-x-y: true + +additionalProperties: false + +required: + - compatible + - reg + - interrupts + - touchscreen-size-x + - touchscreen-size-y + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + i2c { + #address-cells = <1>; + #size-cells = <0>; + touchscreen@50 { + compatible = "imagis,ist3038c"; + reg = <0x50>; + interrupt-parent = <&gpio>; + interrupts = <13 IRQ_TYPE_EDGE_FALLING>; + vdd-supply = <&ldo1_reg>; + vddio-supply = <&ldo2_reg>; + touchscreen-size-x = <720>; + touchscreen-size-y = <1280>; + touchscreen-fuzz-x = <10>; + touchscreen-fuzz-y = <10>; + touchscreen-inverted-x; + touchscreen-inverted-y; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml index 89853b482513..8a676fef8c1d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml @@ -93,48 +93,48 @@ allOf: - qcom,sdm660-gnoc - qcom,sdm660-snoc - then: - properties: - clock-names: - items: - - const: bus - - const: bus_a - - clocks: - items: - - description: Bus Clock - - description: Bus A Clock - - # Child node's properties - patternProperties: - '^interconnect-[a-z0-9]+$': - type: object - description: - snoc-mm is a child of snoc, sharing snoc's register address space. - - properties: - compatible: - enum: - - qcom,msm8939-snoc-mm - - '#interconnect-cells': - const: 1 - - clock-names: - items: - - const: bus - - const: bus_a - - clocks: - items: - - description: Bus Clock - - description: Bus A Clock - - required: - - compatible - - '#interconnect-cells' - - clock-names - - clocks + then: + properties: + clock-names: + items: + - const: bus + - const: bus_a + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + + # Child node's properties + patternProperties: + '^interconnect-[a-z0-9]+$': + type: object + description: + snoc-mm is a child of snoc, sharing snoc's register address space. + + properties: + compatible: + enum: + - qcom,msm8939-snoc-mm + + '#interconnect-cells': + const: 1 + + clock-names: + items: + - const: bus + - const: bus_a + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + + required: + - compatible + - '#interconnect-cells' + - clock-names + - clocks - if: properties: diff --git a/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml index 372ccbfae771..5a583bf3dbc1 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml @@ -7,10 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell MMP/Orion Interrupt controller bindings maintainers: - - Thomas Gleixner <tglx@linutronix.de> - - Jason Cooper <jason@lakedaemon.net> - - Marc Zyngier <maz@kernel.org> - - Rob Herring <robh+dt@kernel.org> + - Andrew Lunn <andrew@lunn.ch> + - Gregory Clement <gregory.clement@bootlin.com> allOf: - if: diff --git a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml index d631b7589d50..72456a07dac9 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Interrupt Combiner Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | Samsung's Exynos4 architecture includes a interrupt combiner controller which diff --git a/Documentation/devicetree/bindings/leds/maxim,max77693.yaml b/Documentation/devicetree/bindings/leds/maxim,max77693.yaml index 86a0005cf156..e27f57bb52ae 100644 --- a/Documentation/devicetree/bindings/leds/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/leds/maxim,max77693.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77693 MicroUSB and Companion Power Management IC LEDs maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/media/coda.yaml b/Documentation/devicetree/bindings/media/coda.yaml index 36781ee4617f..c9d5adbc8c4a 100644 --- a/Documentation/devicetree/bindings/media/coda.yaml +++ b/Documentation/devicetree/bindings/media/coda.yaml @@ -65,7 +65,6 @@ properties: iram: $ref: /schemas/types.yaml#/definitions/phandle description: phandle pointing to the SRAM device node - maxItems: 1 required: - compatible diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml index 9b179bb44dfb..aa55ca65d6ed 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml @@ -63,13 +63,11 @@ properties: mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to vpu. mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to scp. diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml index e7b65a91c92c..deb5b657a2d5 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml @@ -55,13 +55,11 @@ properties: mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to vpu. mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to scp. @@ -106,7 +104,6 @@ allOf: enum: - mediatek,mt8173-vcodec-enc - mediatek,mt8192-vcodec-enc - - mediatek,mt8173-vcodec-enc then: properties: diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml index 7687be0f50aa..c73bf2352aca 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml @@ -61,7 +61,6 @@ properties: mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: | The node of system control processor (SCP), using the remoteproc & rpmsg framework. diff --git a/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml b/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml index 769f13250047..08cbdcddfead 100644 --- a/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: DDR PHY Front End (DPFE) for Broadcom STB maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Markus Mayer <mmayer@broadcom.com> properties: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml index f3e62ee07126..1daa66592477 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR2 SDRAM AC timing parameters for a given speed-bin maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml index dd2141cad866..9d78f140609b 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR2 SDRAM compliant to JEDEC JESD209-2 maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml index 97c3e988af5f..5c6512c1e1e3 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR3 SDRAM AC timing parameters for a given speed-bin maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml index c542f32c39fa..48908a19473c 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR3 SDRAM compliant to JEDEC JESD209-3 maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml index 14a6bc8f421f..9249624c4fa0 100644 --- a/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml @@ -8,7 +8,7 @@ title: Marvell MVEBU SDRAM controller maintainers: - Jan Luebbe <jlu@pengutronix.de> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml index 9566b3421f03..0c511ab906bf 100644 --- a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Atheros AR7xxx/AR9xxx DDR controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The DDR controller of the AR7xxx and AR9xxx families provides an interface to diff --git a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml index 2b18cef99511..514b2c5f8858 100644 --- a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: H8/300 bus controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Yoshinori Sato <ysato@users.sourceforge.jp> properties: diff --git a/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml b/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml index f152243f6b18..098348b2b815 100644 --- a/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml @@ -9,7 +9,7 @@ title: | Controller device maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Lukasz Luba <lukasz.luba@arm.com> description: | diff --git a/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml b/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml index fb7ae38a9c86..f46e95704f53 100644 --- a/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Synopsys IntelliDDR Multi Protocol memory controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Manish Narani <manish.narani@xilinx.com> - Michal Simek <michal.simek@xilinx.com> @@ -24,9 +24,9 @@ description: | properties: compatible: enum: + - snps,ddrc-3.80a - xlnx,zynq-ddrc-a05 - xlnx,zynqmp-ddrc-2.40a - - snps,ddrc-3.80a interrupts: maxItems: 1 @@ -43,7 +43,9 @@ allOf: properties: compatible: contains: - const: xlnx,zynqmp-ddrc-2.40a + enum: + - snps,ddrc-3.80a + - xlnx,zynqmp-ddrc-2.40a then: required: - interrupts diff --git a/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml b/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml index 9ed51185ff99..382ddab60fbd 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml @@ -8,7 +8,7 @@ title: Texas Instruments da8xx DDR2/mDDR memory controller maintainers: - Bartosz Golaszewski <bgolaszewski@baylibre.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | Documentation: diff --git a/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml b/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml index 27870b8760a6..52edd1bf549f 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml index 859655a789c3..d027aabe453b 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77686 Power Management IC maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77686 Power Management diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml index 906101197e11..1b06a77ec798 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77693 MicroUSB and Companion Power Management IC maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml index baa1346ac5d5..ad2013900b03 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77802 Power Management IC maintainers: - Javier Martinez Canillas <javier@dowhile0.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77802 Power Management diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml index 61a0f9dcb983..f30f96bbff43 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77843 MicroUSB and Companion Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml index bae55c98961c..f7bb67d10eff 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Low Power Audio Subsystem (LPASS) maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml index 017befdf8adb..055dfc337c2f 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPA01 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml index 771b3f16da96..5ff6546c72b7 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS11/13/14/15 and S2MPU02 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml index 5531718abdf0..10c7b408f33a 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5M8767 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml index ce64b3498378..f3f4d5b02744 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml @@ -197,6 +197,8 @@ allOf: - nvidia,tegra30-sdhci - nvidia,tegra114-sdhci - nvidia,tegra124-sdhci + then: + properties: clocks: items: - description: module clock diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml index 8756060895a8..99ee4b5b9346 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -27,32 +27,25 @@ description: The realtek-mdio driver is an MDIO driver and it must be inserted inside an MDIO node. + The compatible string is only used to identify which (silicon) family the + switch belongs to. Roughly speaking, a family is any set of Realtek switches + whose chip identification register(s) have a common location and semantics. + The different models in a given family can be automatically disambiguated by + parsing the chip identification register(s) according to the given family, + avoiding the need for a unique compatible string for each model. + properties: compatible: enum: - realtek,rtl8365mb - - realtek,rtl8366 - realtek,rtl8366rb - - realtek,rtl8366s - - realtek,rtl8367 - - realtek,rtl8367b - - realtek,rtl8367rb - - realtek,rtl8367s - - realtek,rtl8368s - - realtek,rtl8369 - - realtek,rtl8370 description: | - realtek,rtl8365mb: 4+1 ports - realtek,rtl8366: 5+1 ports - realtek,rtl8366rb: 5+1 ports - realtek,rtl8366s: 5+1 ports - realtek,rtl8367: - realtek,rtl8367b: - realtek,rtl8367rb: 5+2 ports - realtek,rtl8367s: 5+2 ports - realtek,rtl8368s: 8 ports - realtek,rtl8369: 8+1 ports - realtek,rtl8370: 8+2 ports + realtek,rtl8365mb: + Use with models RTL8363NB, RTL8363NB-VB, RTL8363SC, RTL8363SC-VB, + RTL8364NB, RTL8364NB-VB, RTL8365MB, RTL8366SC, RTL8367RB-VB, RTL8367S, + RTL8367SB, RTL8370MB, RTL8310SR + realtek,rtl8366rb: + Use with models RTL8366RB, RTL8366S mdc-gpios: description: GPIO line for the MDC clock line. @@ -335,7 +328,7 @@ examples: #size-cells = <0>; switch@29 { - compatible = "realtek,rtl8367s"; + compatible = "realtek,rtl8365mb"; reg = <29>; reset-gpios = <&gpio2 20 GPIO_ACTIVE_LOW>; diff --git a/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml b/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml index 15a45db3899a..1bcaf6ba822c 100644 --- a/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell International Ltd. NCI NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml index 7465aea2e1c0..e381a3c14836 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml @@ -8,7 +8,7 @@ title: NXP Semiconductors NCI NFC controller maintainers: - Charles Gorand <charles.gorand@effinnov.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml index d8ba5a18db98..0509e0166345 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP Semiconductors PN532 NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml index d520414de463..18b3a7d819df 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP Semiconductors PN544 NFC Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml b/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml index a6a1bc788d29..ef1155038a2f 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics ST NCI NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml b/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml index 4356eacde8aa..8a7274357b46 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics SAS ST21NFCA NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml b/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml index d3bca376039e..963d9531a856 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics ST95HF NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml index 40da2ac98978..404c8df99364 100644 --- a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml +++ b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Texas Instruments TRF7970A RFID/NFC/15693 Transceiver maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Mark Greer <mgreer@animalcreek.com> properties: diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 2d5248f5b919..36c85eb3dc0d 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -53,20 +53,18 @@ properties: - allwinner,sun8i-r40-gmac - allwinner,sun8i-v3s-emac - allwinner,sun50i-a64-emac - - loongson,ls2k-dwmac - - loongson,ls7a-dwmac - amlogic,meson6-dwmac - amlogic,meson8b-dwmac - amlogic,meson8m2-dwmac - amlogic,meson-gxbb-dwmac - amlogic,meson-axg-dwmac - - loongson,ls2k-dwmac - - loongson,ls7a-dwmac - ingenic,jz4775-mac - ingenic,x1000-mac - ingenic,x1600-mac - ingenic,x1830-mac - ingenic,x2000-mac + - loongson,ls2k-dwmac + - loongson,ls7a-dwmac - rockchip,px30-gmac - rockchip,rk3128-gmac - rockchip,rk3228-gmac diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index e602761f7b14..b0ebcef6801c 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -13,9 +13,6 @@ description: | This describes the devicetree bindings for AVE ethernet controller implemented on Socionext UniPhier SoCs. -allOf: - - $ref: ethernet-controller.yaml# - properties: compatible: enum: @@ -44,25 +41,13 @@ properties: minItems: 1 maxItems: 4 - clock-names: - oneOf: - - items: # for Pro4 - - const: gio - - const: ether - - const: ether-gb - - const: ether-phy - - const: ether # for others + clock-names: true resets: minItems: 1 maxItems: 2 - reset-names: - oneOf: - - items: # for Pro4 - - const: gio - - const: ether - - const: ether # for others + reset-names: true socionext,syscon-phy-mode: $ref: /schemas/types.yaml#/definitions/phandle-array @@ -78,6 +63,42 @@ properties: $ref: mdio.yaml# unevaluatedProperties: false +allOf: + - $ref: ethernet-controller.yaml# + - if: + properties: + compatible: + contains: + const: socionext,uniphier-pro4-ave4 + then: + properties: + clocks: + minItems: 4 + maxItems: 4 + clock-names: + items: + - const: gio + - const: ether + - const: ether-gb + - const: ether-phy + resets: + minItems: 2 + maxItems: 2 + reset-names: + items: + - const: gio + - const: ether + else: + properties: + clocks: + maxItems: 1 + clock-names: + const: ether + resets: + maxItems: 1 + reset-names: + const: ether + required: - compatible - reg @@ -90,7 +111,7 @@ required: - reset-names - mdio -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml index dbfca5ee9139..6f44f9516c36 100644 --- a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml +++ b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml @@ -56,6 +56,7 @@ if: compatible: contains: const: ti,davinci_mdio +then: required: - bus_freq diff --git a/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml b/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml index dfde0eaf66e1..d61585c96e31 100644 --- a/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml +++ b/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml @@ -275,17 +275,17 @@ allOf: - nvidia,hssquelch-level - nvidia,hsdiscon-level - else: - properties: - clocks: - maxItems: 4 + else: + properties: + clocks: + maxItems: 4 - clock-names: - items: - - const: reg - - const: pll_u - - const: timer - - const: utmi-pads + clock-names: + items: + - const: reg + - const: pll_u + - const: timer + - const: utmi-pads - if: properties: diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml index e23e5590eaa3..0655e485b260 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml @@ -14,24 +14,24 @@ if: compatible: contains: const: qcom,usb-hs-phy-apq8064 - then: - properties: - resets: - maxItems: 1 +then: + properties: + resets: + maxItems: 1 - reset-names: - const: por + reset-names: + const: por - else: - properties: - resets: - minItems: 2 - maxItems: 2 +else: + properties: + resets: + minItems: 2 + maxItems: 2 - reset-names: - items: - - const: phy - - const: por + reset-names: + items: + - const: phy + - const: por properties: compatible: @@ -92,6 +92,8 @@ additionalProperties: false examples: - | otg: usb-controller { + #reset-cells = <1>; + ulpi { phy { compatible = "qcom,usb-hs-phy-msm8974", "qcom,usb-hs-phy"; diff --git a/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml index 838c6d480ce6..b03b2f00cc5b 100644 --- a/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC DisplayPort PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml index c61574e10b2a..3e5f035de2e9 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml index 62b39bb46585..8751e559484f 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos5250 SoC SATA PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml index 54aa056b224d..415440aaad89 100644 --- a/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5P/Exynos SoC MIPI CSIS/DSIM DPHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml index 056e270a4e88..d9f22a801cbf 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5P/Exynos SoC USB 2.0 PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml index f83f0f8135b9..5ba55f9f20cc 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 3.0 DRD PHY USB 2.0 PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml index 8a90d8273767..6bd42e43cdab 100644 --- a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml @@ -48,13 +48,12 @@ properties: Name of one pin group to configure. enum: [ aif1, aif2, aif3, aif4, mif1, mif2, mif3, pdmspk1, pdmspk2, dmic4, dmic5, dmic6, gpio1, gpio2, gpio3, - gpio4, gpio5, gpio6, gpio7, gpio7, gpio8, gpio9, + gpio4, gpio5, gpio6, gpio7, gpio8, gpio9, gpio10, gpio11, gpio12, gpio13, gpio14, gpio15, - gpio16, gpio17, gpio17, gpio18, gpio19, gpio20, - gpio21, gpio22, gpio23, gpio24, gpio25, gpio26, - gpio27, gpio27, gpio28, gpio29, gpio30, gpio31, - gpio32, gpio33, gpio34, gpio35, gpio36, gpio37, - gpio37, gpio38, gpio39 ] + gpio16, gpio17, gpio18, gpio19, gpio20, gpio21, + gpio22, gpio23, gpio24, gpio25, gpio26, gpio27, + gpio28, gpio29, gpio30, gpio31, gpio32, gpio33, + gpio34, gpio35, gpio36, gpio37, gpio38, gpio39 ] function: description: diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml index f73348c54748..8cf3c47ab86b 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - gpio bank maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml index c71939ac8b63..9869d4dceddb 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - pins configuration maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml index a822f70f5702..1de91a51234d 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - wake-up interrupt controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml index 989e48c051cf..3a65c66ca71d 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/power/renesas,apmu.yaml b/Documentation/devicetree/bindings/power/renesas,apmu.yaml index 4d293b2b2f84..d77fc88050c8 100644 --- a/Documentation/devicetree/bindings/power/renesas,apmu.yaml +++ b/Documentation/devicetree/bindings/power/renesas,apmu.yaml @@ -36,7 +36,8 @@ properties: cpus: $ref: /schemas/types.yaml#/definitions/phandle-array items: - maxItems: 1 + minItems: 1 + maxItems: 4 description: | Array of phandles pointing to CPU cores, which should match the order of CPU cores used by the WUPCR and PSTR registers in the Advanced Power diff --git a/Documentation/devicetree/bindings/power/supply/bq2415x.yaml b/Documentation/devicetree/bindings/power/supply/bq2415x.yaml index f8461f06e6f4..118cf484cc69 100644 --- a/Documentation/devicetree/bindings/power/supply/bq2415x.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq2415x.yaml @@ -17,7 +17,6 @@ properties: compatible: enum: - ti,bq24150 - - ti,bq24150 - ti,bq24150a - ti,bq24151 - ti,bq24151a diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml index 3978b48299de..4d3a1d09036f 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC Charger maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml index a21dc1a8890f..f5fd53debbc8 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77693 MicroUSB and Companion Power Management IC Charger maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml index 9b131c6facbc..84eeaef179a5 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml @@ -18,23 +18,23 @@ description: allOf: - $ref: "regulator.yaml#" - -if: - properties: - compatible: - contains: - const: regulator-fixed-clock - required: - - clocks -else: - if: - properties: - compatible: - contains: - const: regulator-fixed-domain - required: - - power-domains - - required-opps + - if: + properties: + compatible: + contains: + const: regulator-fixed-clock + then: + required: + - clocks + - if: + properties: + compatible: + contains: + const: regulator-fixed-domain + then: + required: + - power-domains + - required-opps properties: compatible: diff --git a/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml b/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml index 16f01886a601..285dc7122977 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml index bb64b679f765..0e7cd4b3ace0 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77686 Power Management IC regulators maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77686 Power Management diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml index 20d8559bdc2b..945a539749e8 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77693 MicroUSB and Companion Power Management IC regulators maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml index f2b4dd15a0f3..236348c4710c 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77802 Power Management IC regulators maintainers: - Javier Martinez Canillas <javier@dowhile0.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77802 Power Management diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml index a963025e96c1..9695e7242882 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77843 MicroUSB and Companion Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml index e4e8c58f6046..3ff0d7d980e9 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8952 voltage regulator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml index 5898dcf10f06..b92eef68c19f 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8973/MAX77621 voltage regulator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml index d5a44ca3df04..4321f061a7f6 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8997 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Maxim MAX8997 is a Power Management IC which includes voltage and current diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml index 0627dec513da..0f9eb317ba9a 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPA01 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml index e3b780715f44..f1c50dcd0b04 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS11 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml index 579d77aefc3f..53b105a4ead1 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS13 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml index fdea290b3e94..01f9d4e236e9 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS14 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml index b3a883c94628..9576c2df45a6 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS15 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml index 0ded6953e3b6..39b652c3c3c4 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPU02 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml index 3c1617b66861..172631ca3c25 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5M8767 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml index 2424de733ee4..d99a729d2710 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml @@ -104,8 +104,7 @@ properties: qcom,smem-state-names: $ref: /schemas/types.yaml#/definitions/string description: The names of the state bits used for SMP2P output - items: - - const: stop + const: stop glink-edge: type: object @@ -130,7 +129,6 @@ properties: qcom,remote-pid: $ref: /schemas/types.yaml#/definitions/uint32 description: ID of the shared memory used by GLINK for communication with WPSS - maxItems: 1 required: - interrupts diff --git a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml index b0c41ab1a746..cdfcf32c53fa 100644 --- a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml +++ b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml @@ -24,6 +24,11 @@ properties: - const: hisilicon,hi3670-reset - const: hisilicon,hi3660-reset + hisi,rst-syscon: + deprecated: true + description: phandle of the reset's syscon, use hisilicon,rst-syscon instead + $ref: /schemas/types.yaml#/definitions/phandle + hisilicon,rst-syscon: description: phandle of the reset's syscon. $ref: /schemas/types.yaml#/definitions/phandle diff --git a/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml b/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml index 377a7d242323..6566804ec567 100644 --- a/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml +++ b/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml @@ -55,6 +55,9 @@ properties: "#reset-cells": const: 1 + resets: + maxItems: 1 + additionalProperties: false required: diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index aa5fb64d57eb..d632ac76532e 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -99,6 +99,14 @@ properties: - compatible - interrupt-controller + cpu-idle-states: + $ref: '/schemas/types.yaml#/definitions/phandle-array' + items: + maxItems: 1 + description: | + List of phandles to idle state nodes supported + by this hart (see ./idle-states.yaml). + required: - riscv,isa - interrupt-controller diff --git a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml index a50c34d5d199..765d9f9edd6e 100644 --- a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml +++ b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC True Random Number Generator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Łukasz Stelmach <l.stelmach@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml b/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml index 84bf518a5549..4754174e9849 100644 --- a/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml +++ b/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TimerIO Random Number Generator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml index beeb90e55727..0b767fec39d8 100644 --- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml @@ -16,16 +16,22 @@ properties: compatible: oneOf: - - const: allwinner,sun6i-a31-rtc - - const: allwinner,sun8i-a23-rtc - - const: allwinner,sun8i-h3-rtc - - const: allwinner,sun8i-r40-rtc - - const: allwinner,sun8i-v3-rtc - - const: allwinner,sun50i-h5-rtc + - enum: + - allwinner,sun6i-a31-rtc + - allwinner,sun8i-a23-rtc + - allwinner,sun8i-h3-rtc + - allwinner,sun8i-r40-rtc + - allwinner,sun8i-v3-rtc + - allwinner,sun50i-h5-rtc + - allwinner,sun50i-h6-rtc + - allwinner,sun50i-h616-rtc + - allwinner,sun50i-r329-rtc - items: - const: allwinner,sun50i-a64-rtc - const: allwinner,sun8i-h3-rtc - - const: allwinner,sun50i-h6-rtc + - items: + - const: allwinner,sun20i-d1-rtc + - const: allwinner,sun50i-r329-rtc reg: maxItems: 1 @@ -37,7 +43,12 @@ properties: - description: RTC Alarm 1 clocks: - maxItems: 1 + minItems: 1 + maxItems: 4 + + clock-names: + minItems: 1 + maxItems: 4 clock-output-names: minItems: 1 @@ -85,6 +96,7 @@ allOf: enum: - allwinner,sun8i-h3-rtc - allwinner,sun50i-h5-rtc + - allwinner,sun50i-h6-rtc then: properties: @@ -96,19 +108,68 @@ allOf: properties: compatible: contains: - const: allwinner,sun50i-h6-rtc + const: allwinner,sun50i-h616-rtc then: properties: - clock-output-names: + clocks: minItems: 3 maxItems: 3 + items: + - description: Bus clock for register access + - description: 24 MHz oscillator + - description: 32 kHz clock from the CCU + + clock-names: + minItems: 3 + maxItems: 3 + items: + - const: bus + - const: hosc + - const: pll-32k + + required: + - clocks + - clock-names - if: properties: compatible: contains: - const: allwinner,sun8i-r40-rtc + const: allwinner,sun50i-r329-rtc + + then: + properties: + clocks: + minItems: 3 + maxItems: 4 + items: + - description: Bus clock for register access + - description: 24 MHz oscillator + - description: AHB parent for internal SPI clock + - description: External 32768 Hz oscillator + + clock-names: + minItems: 3 + maxItems: 4 + items: + - const: bus + - const: hosc + - const: ahb + - const: ext-osc32k + + required: + - clocks + - clock-names + + - if: + properties: + compatible: + contains: + enum: + - allwinner,sun8i-r40-rtc + - allwinner,sun50i-h616-rtc + - allwinner,sun50i-r329-rtc then: properties: @@ -127,7 +188,6 @@ required: - compatible - reg - interrupts - - clock-output-names additionalProperties: false diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91sam9-rtc.txt b/Documentation/devicetree/bindings/rtc/atmel,at91sam9-rtc.txt deleted file mode 100644 index 3f0e2a5950eb..000000000000 --- a/Documentation/devicetree/bindings/rtc/atmel,at91sam9-rtc.txt +++ /dev/null @@ -1,25 +0,0 @@ -Atmel AT91SAM9260 Real Time Timer - -Required properties: -- compatible: should be one of the following: - - "atmel,at91sam9260-rtt" - - "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt" -- reg: should encode the memory region of the RTT controller -- interrupts: rtt alarm/event interrupt -- clocks: should contain the 32 KHz slow clk that will drive the RTT block. -- atmel,rtt-rtc-time-reg: should encode the GPBR register used to store - the time base when the RTT is used as an RTC. - The first cell should point to the GPBR node and the second one - encode the offset within the GPBR block (or in other words, the - GPBR register used to store the time base). - - -Example: - -rtt@fffffd20 { - compatible = "atmel,at91sam9260-rtt"; - reg = <0xfffffd20 0x10>; - interrupts = <1 4 7>; - clocks = <&clk32k>; - atmel,rtt-rtc-time-reg = <&gpbr 0x0>; -}; diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml new file mode 100644 index 000000000000..0ef1b7ff4a77 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml @@ -0,0 +1,69 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright (C) 2022 Microchip Technology, Inc. and its subsidiaries +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/atmel,at91sam9260-rtt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Atmel AT91 RTT Device Tree Bindings + +allOf: + - $ref: "rtc.yaml#" + +maintainers: + - Alexandre Belloni <alexandre.belloni@bootlin.com> + +properties: + compatible: + oneOf: + - items: + - const: atmel,at91sam9260-rtt + - items: + - const: microchip,sam9x60-rtt + - const: atmel,at91sam9260-rtt + - items: + - const: microchip,sama7g5-rtt + - const: microchip,sam9x60-rtt + - const: atmel,at91sam9260-rtt + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + atmel,rtt-rtc-time-reg: + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - items: + - description: Phandle to the GPBR node. + - description: Offset within the GPBR block. + description: + Should encode the GPBR register used to store the time base when the + RTT is used as an RTC. The first cell should point to the GPBR node + and the second one encodes the offset within the GPBR block (or in + other words, the GPBR register used to store the time base). + +required: + - compatible + - reg + - interrupts + - clocks + - atmel,rtt-rtc-time-reg + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + rtc@fffffd20 { + compatible = "atmel,at91sam9260-rtt"; + reg = <0xfffffd20 0x10>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; + clocks = <&clk32k>; + atmel,rtt-rtc-time-reg = <&gpbr 0x0>; + }; diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml index a98ed66d092e..0cabb773c397 100644 --- a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml +++ b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml @@ -8,7 +8,7 @@ title: Samsung's Exynos USI (Universal Serial Interface) binding maintainers: - Sam Protsenko <semen.protsenko@linaro.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | USI IP-core provides selectable serial protocol (UART, SPI or High-Speed I2C). diff --git a/Documentation/devicetree/bindings/sound/samsung,arndale.yaml b/Documentation/devicetree/bindings/sound/samsung,arndale.yaml index cea2bf3544f0..9bc4585bb6e5 100644 --- a/Documentation/devicetree/bindings/sound/samsung,arndale.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,arndale.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Insignal Arndale boards audio complex maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml b/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml index cb51af90435e..ac151d3c1d77 100644 --- a/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung SMDK5250 audio complex with WM8994 codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,snow.yaml b/Documentation/devicetree/bindings/sound/samsung,snow.yaml index 0c3b3302b842..51a83d3c7274 100644 --- a/Documentation/devicetree/bindings/sound/samsung,snow.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,snow.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Google Snow audio complex with MAX9809x codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,tm2.yaml b/Documentation/devicetree/bindings/sound/samsung,tm2.yaml index 74712d6f3ef4..491e08019c04 100644 --- a/Documentation/devicetree/bindings/sound/samsung,tm2.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,tm2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos5433 TM2(E) audio complex with WM5110 codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml index b3dbcba33e41..fe2e15504ebc 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml +++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml @@ -136,8 +136,7 @@ allOf: compatible: contains: const: st,stm32f4-sai - - - then: + then: properties: clocks: items: @@ -148,8 +147,7 @@ allOf: items: - const: x8k - const: x11k - - - else: + else: properties: clocks: items: diff --git a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml index b104899205f6..5de710adfa63 100644 --- a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml +++ b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml @@ -124,7 +124,6 @@ properties: description: | Override the default TX fifo size. Unit is words. Ignored if 0. $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 default: 64 renesas,rx-fifo-size: @@ -132,7 +131,6 @@ properties: description: | Override the default RX fifo size. Unit is words. Ignored if 0. $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 default: 64 required: diff --git a/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml index f0db3fb3d688..25b1b6c12d4d 100644 --- a/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Peripheral-specific properties for Samsung S3C/S5P/Exynos SoC SPI controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: See spi-peripheral-props.yaml for more info. diff --git a/Documentation/devicetree/bindings/spi/samsung,spi.yaml b/Documentation/devicetree/bindings/spi/samsung,spi.yaml index bf9a76d931d2..a50f24f9359d 100644 --- a/Documentation/devicetree/bindings/spi/samsung,spi.yaml +++ b/Documentation/devicetree/bindings/spi/samsung,spi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC SPI controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: All the SPI controller nodes should be represented in the aliases node using diff --git a/Documentation/devicetree/bindings/sram/sram.yaml b/Documentation/devicetree/bindings/sram/sram.yaml index 668a9a41a775..993430be355b 100644 --- a/Documentation/devicetree/bindings/sram/sram.yaml +++ b/Documentation/devicetree/bindings/sram/sram.yaml @@ -136,14 +136,14 @@ required: - reg if: - properties: - compatible: - contains: - enum: - - qcom,rpm-msg-ram - - rockchip,rk3288-pmu-sram - -else: + not: + properties: + compatible: + contains: + enum: + - qcom,rpm-msg-ram + - rockchip,rk3288-pmu-sram +then: required: - "#address-cells" - "#size-cells" diff --git a/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml b/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml index 17129f75d962..1344df708e2d 100644 --- a/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Thermal Management Unit (TMU) maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | For multi-instance tmu each instance should have an alias correctly numbered diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml index 22b91a27d776..6b9a3bcb3926 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 3.0 DWC3 Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml index fbf07d6e707a..340dff8d19c3 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 2.0 EHCI/OHCI Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 8fe2d934f949..01430973ecec 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -560,6 +560,8 @@ patternProperties: description: Ingenieurburo Fur Ic-Technologie (I/F/I) "^ilitek,.*": description: ILI Technology Corporation (ILITEK) + "^imagis,.*": + description: Imagis Technologies Co., Ltd. "^img,.*": description: Imagination Technologies Ltd. "^imi,.*": diff --git a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml index 91a98ccd4226..d060438e1402 100644 --- a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml @@ -55,6 +55,11 @@ properties: - renesas,r8a779a0-wdt # R-Car V3U - const: renesas,rcar-gen3-wdt # R-Car Gen3 and RZ/G2 + - items: + - enum: + - renesas,r8a779f0-wdt # R-Car S4-8 + - const: renesas,rcar-gen4-wdt # R-Car Gen4 + reg: maxItems: 1 diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 55006678394a..36a76cbe9095 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -185,6 +185,12 @@ DMA Fence Chain .. kernel-doc:: include/linux/dma-fence-chain.h :internal: +DMA Fence unwrap +~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/dma-fence-unwrap.h + :internal: + DMA Fence uABI/Sync File ~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/filesystems/caching/backend-api.rst b/Documentation/filesystems/caching/backend-api.rst index be793c49a772..d7507becf674 100644 --- a/Documentation/filesystems/caching/backend-api.rst +++ b/Documentation/filesystems/caching/backend-api.rst @@ -73,7 +73,7 @@ busy. If successful, the cache backend can then start setting up the cache. In the event that the initialisation fails, the cache backend should call:: - void fscache_relinquish_cookie(struct fscache_cache *cache); + void fscache_relinquish_cache(struct fscache_cache *cache); to reset and discard the cookie. @@ -110,9 +110,9 @@ to withdraw them, calling:: on the cookie that each object belongs to. This schedules the specified cookie for withdrawal. This gets offloaded to a workqueue. The cache backend can -test for completion by calling:: +wait for completion by calling:: - bool fscache_are_objects_withdrawn(struct fscache_cookie *cache); + void fscache_wait_for_objects(struct fscache_cache *cache); Once all the cookies are withdrawn, a cache backend can withdraw all the volumes, calling:: @@ -125,7 +125,7 @@ outstanding accesses on the volume to complete before returning. When the the cache is completely withdrawn, fscache should be notified by calling:: - void fscache_cache_relinquish(struct fscache_cache *cache); + void fscache_relinquish_cache(struct fscache_cache *cache); to clear fields in the cookie and discard the caller's ref on it. diff --git a/Documentation/filesystems/caching/netfs-api.rst b/Documentation/filesystems/caching/netfs-api.rst index 5066113acad5..7308d76a29dc 100644 --- a/Documentation/filesystems/caching/netfs-api.rst +++ b/Documentation/filesystems/caching/netfs-api.rst @@ -404,22 +404,21 @@ schedule a write of that region:: And if an error occurs before that point is reached, the marks can be removed by calling:: - void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, + void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) -In both of these functions, the cookie representing the cache object to be -written to and a pointer to the mapping to which the source pages are attached -are passed in; start and len indicate the size of the region that's going to be -written (it doesn't have to align to page boundaries necessarily, but it does -have to align to DIO boundaries on the backing filesystem). The caching -parameter indicates if caching should be skipped, and if false, the functions -do nothing. - -The write function takes some additional parameters: i_size indicates the size -of the netfs file and term_func indicates an optional completion function, to -which term_func_priv will be passed, along with the error or amount written. +In these functions, a pointer to the mapping to which the source pages are +attached is passed in and start and len indicate the size of the region that's +going to be written (it doesn't have to align to page boundaries necessarily, +but it does have to align to DIO boundaries on the backing filesystem). The +caching parameter indicates if caching should be skipped, and if false, the +functions do nothing. + +The write function takes some additional parameters: the cookie representing +the cache object to be written to, i_size indicates the size of the netfs file +and term_func indicates an optional completion function, to which +term_func_priv will be passed, along with the error or amount written. Note that the write function will always run asynchronously and will unmark all the pages upon completion before calling term_func. diff --git a/Documentation/filesystems/cifs/ksmbd.rst b/Documentation/filesystems/cifs/ksmbd.rst index b0d354fd8066..1af600db2e70 100644 --- a/Documentation/filesystems/cifs/ksmbd.rst +++ b/Documentation/filesystems/cifs/ksmbd.rst @@ -82,10 +82,10 @@ Signing Update Supported. Pre-authentication integrity Supported. SMB3 encryption(CCM, GCM) Supported. (CCM and GCM128 supported, GCM256 in progress) -SMB direct(RDMA) Partially Supported. SMB3 Multi-channel is - required to connect to Windows client. +SMB direct(RDMA) Supported. SMB3 Multi-channel Partially Supported. Planned to implement replay/retry mechanisms for future. +Receive Side Scaling mode Supported. SMB3.1.1 POSIX extension Supported. ACLs Partially Supported. only DACLs available, SACLs (auditing) is planned for the future. For diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index 1d831e3cbcb3..8cc536d08f51 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -549,7 +549,7 @@ Pagecache ~~~~~~~~~ For filesystems using Linux's pagecache, the ``->readpage()`` and -``->readpages()`` methods must be modified to verify pages before they +``->readahead()`` methods must be modified to verify pages before they are marked Uptodate. Merely hooking ``->read_iter()`` would be insufficient, since ``->read_iter()`` is not used for memory maps. @@ -611,7 +611,7 @@ workqueue, and then the workqueue work does the decryption or verification. Finally, pages where no decryption or verity error occurred are marked Uptodate, and the pages are unlocked. -Files on ext4 and f2fs may contain holes. Normally, ``->readpages()`` +Files on ext4 and f2fs may contain holes. Normally, ``->readahead()`` simply zeroes holes and sets the corresponding pages Uptodate; no bios are issued. To prevent this case from bypassing fs-verity, these filesystems use fsverity_verify_page() to verify hole pages. @@ -778,7 +778,7 @@ weren't already directly answered in other parts of this document. - To prevent bypassing verification, pages must not be marked Uptodate until they've been verified. Currently, each filesystem is responsible for marking pages Uptodate via - ``->readpages()``. Therefore, currently it's not possible for + ``->readahead()``. Therefore, currently it's not possible for the VFS to do the verification on its own. Changing this would require significant changes to the VFS and all filesystems. diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 2998cec9af4b..c26d854275a0 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -241,8 +241,6 @@ prototypes:: int (*writepages)(struct address_space *, struct writeback_control *); bool (*dirty_folio)(struct address_space *, struct folio *folio); void (*readahead)(struct readahead_control *); - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); @@ -274,7 +272,6 @@ readpage: yes, unlocks shared writepages: dirty_folio maybe readahead: yes, unlocks shared -readpages: no shared write_begin: locks the page exclusive write_end: yes, unlocks exclusive bmap: @@ -300,9 +297,6 @@ completion. ->readahead() unlocks the pages that I/O is attempted on like ->readpage(). -->readpages() populates the pagecache with the passed pages and starts -I/O against them. They come unlocked upon I/O completion. - ->writepage() is used for two purposes: for "memory cleansing" and for "sync". These are quite different operations and the behaviour may differ depending upon the mode. diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 4f373a8ec47b..69f00179fdfe 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -7,6 +7,8 @@ Network Filesystem Helper Library .. Contents: - Overview. + - Per-inode context. + - Inode context helper functions. - Buffered read helpers. - Read helper functions. - Read helper structures. @@ -28,6 +30,69 @@ Note that the library module doesn't link against local caching directly, so access must be provided by the netfs. +Per-Inode Context +================= + +The network filesystem helper library needs a place to store a bit of state for +its use on each netfs inode it is helping to manage. To this end, a context +structure is defined:: + + struct netfs_i_context { + const struct netfs_request_ops *ops; + struct fscache_cookie *cache; + }; + +A network filesystem that wants to use netfs lib must place one of these +directly after the VFS ``struct inode`` it allocates, usually as part of its +own struct. This can be done in a way similar to the following:: + + struct my_inode { + struct { + /* These must be contiguous */ + struct inode vfs_inode; + struct netfs_i_context netfs_ctx; + }; + ... + }; + +This allows netfslib to find its state by simple offset from the inode pointer, +thereby allowing the netfslib helper functions to be pointed to directly by the +VFS/VM operation tables. + +The structure contains the following fields: + + * ``ops`` + + The set of operations provided by the network filesystem to netfslib. + + * ``cache`` + + Local caching cookie, or NULL if no caching is enabled. This field does not + exist if fscache is disabled. + + +Inode Context Helper Functions +------------------------------ + +To help deal with the per-inode context, a number helper functions are +provided. Firstly, a function to perform basic initialisation on a context and +set the operations table pointer:: + + void netfs_i_context_init(struct inode *inode, + const struct netfs_request_ops *ops); + +then two functions to cast between the VFS inode structure and the netfs +context:: + + struct netfs_i_context *netfs_i_context(struct inode *inode); + struct inode *netfs_inode(struct netfs_i_context *ctx); + +and finally, a function to get the cache cookie pointer from the context +attached to an inode (or NULL if fscache is disabled):: + + struct fscache_cookie *netfs_i_cookie(struct inode *inode); + + Buffered Read Helpers ===================== @@ -70,38 +135,22 @@ Read Helper Functions Three read helpers are provided:: - void netfs_readahead(struct readahead_control *ractl, - const struct netfs_read_request_ops *ops, - void *netfs_priv); + void netfs_readahead(struct readahead_control *ractl); int netfs_readpage(struct file *file, - struct folio *folio, - const struct netfs_read_request_ops *ops, - void *netfs_priv); + struct page *page); int netfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int flags, struct folio **_folio, - void **_fsdata, - const struct netfs_read_request_ops *ops, - void *netfs_priv); - -Each corresponds to a VM operation, with the addition of a couple of parameters -for the use of the read helpers: + void **_fsdata); - * ``ops`` - - A table of operations through which the helpers can talk to the filesystem. - - * ``netfs_priv`` +Each corresponds to a VM address space operation. These operations use the +state in the per-inode context. - Filesystem private data (can be NULL). - -Both of these values will be stored into the read request structure. - -For ->readahead() and ->readpage(), the network filesystem should just jump -into the corresponding read helper; whereas for ->write_begin(), it may be a +For ->readahead() and ->readpage(), the network filesystem just point directly +at the corresponding read helper; whereas for ->write_begin(), it may be a little more complicated as the network filesystem might want to flush conflicting writes or track dirty data and needs to put the acquired folio if an error occurs after calling the helper. @@ -116,7 +165,7 @@ occurs, the request will get partially completed if sufficient data is read. Additionally, there is:: - * void netfs_subreq_terminated(struct netfs_read_subrequest *subreq, + * void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, ssize_t transferred_or_error, bool was_async); @@ -132,7 +181,7 @@ Read Helper Structures The read helpers make use of a couple of structures to maintain the state of the read. The first is a structure that manages a read request as a whole:: - struct netfs_read_request { + struct netfs_io_request { struct inode *inode; struct address_space *mapping; struct netfs_cache_resources cache_resources; @@ -140,7 +189,7 @@ the read. The first is a structure that manages a read request as a whole:: loff_t start; size_t len; loff_t i_size; - const struct netfs_read_request_ops *netfs_ops; + const struct netfs_request_ops *netfs_ops; unsigned int debug_id; ... }; @@ -187,8 +236,8 @@ The above fields are the ones the netfs can use. They are: The second structure is used to manage individual slices of the overall read request:: - struct netfs_read_subrequest { - struct netfs_read_request *rreq; + struct netfs_io_subrequest { + struct netfs_io_request *rreq; loff_t start; size_t len; size_t transferred; @@ -244,32 +293,26 @@ Read Helper Operations The network filesystem must provide the read helpers with a table of operations through which it can issue requests and negotiate:: - struct netfs_read_request_ops { - void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); - bool (*is_cache_enabled)(struct inode *inode); - int (*begin_cache_operation)(struct netfs_read_request *rreq); - void (*expand_readahead)(struct netfs_read_request *rreq); - bool (*clamp_length)(struct netfs_read_subrequest *subreq); - void (*issue_op)(struct netfs_read_subrequest *subreq); - bool (*is_still_valid)(struct netfs_read_request *rreq); + struct netfs_request_ops { + void (*init_request)(struct netfs_io_request *rreq, struct file *file); + int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); + bool (*clamp_length)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); + bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); - void (*done)(struct netfs_read_request *rreq); + void (*done)(struct netfs_io_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; The operations are as follows: - * ``init_rreq()`` + * ``init_request()`` [Optional] This is called to initialise the request structure. It is given the file for reference and can modify the ->netfs_priv value. - * ``is_cache_enabled()`` - - [Required] This is called by netfs_write_begin() to ask if the file is being - cached. It should return true if it is being cached and false otherwise. - * ``begin_cache_operation()`` [Optional] This is called to ask the network filesystem to call into the @@ -305,7 +348,7 @@ The operations are as follows: This should return 0 on success and an error code on error. - * ``issue_op()`` + * ``issue_read()`` [Required] The helpers use this to dispatch a subrequest to the server for reading. In the subrequest, ->start, ->len and ->transferred indicate what @@ -420,12 +463,12 @@ The network filesystem's ->begin_cache_operation() method is called to set up a cache and this must call into the cache to do the work. If using fscache, for example, the cache would call:: - int fscache_begin_read_operation(struct netfs_read_request *rreq, + int fscache_begin_read_operation(struct netfs_io_request *rreq, struct fscache_cookie *cookie); passing in the request pointer and the cookie corresponding to the file. -The netfs_read_request object contains a place for the cache to hang its +The netfs_io_request object contains a place for the cache to hang its state:: struct netfs_cache_resources { @@ -443,7 +486,7 @@ operation table looks like the following:: void (*expand_readahead)(struct netfs_cache_resources *cres, loff_t *_start, size_t *_len, loff_t i_size); - enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq, + enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, loff_t i_size); int (*read)(struct netfs_cache_resources *cres, @@ -562,4 +605,5 @@ API Function Reference ====================== .. kernel-doc:: include/linux/netfs.h -.. kernel-doc:: fs/netfs/read_helper.c +.. kernel-doc:: fs/netfs/buffered_read.c +.. kernel-doc:: fs/netfs/io.c diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 4f14edf93941..794bd1a66bfb 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -726,8 +726,6 @@ cache in your filesystem. The following members are defined: int (*writepages)(struct address_space *, struct writeback_control *); bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); @@ -817,15 +815,6 @@ cache in your filesystem. The following members are defined: completes successfully. Setting PageError on any page will be ignored; simply unlock the page if an I/O error occurs. -``readpages`` - called by the VM to read pages associated with the address_space - object. This is essentially just a vector version of readpage. - Instead of just one page, several pages are requested. - readpages is only used for read-ahead, so read errors are - ignored. If anything goes wrong, feel free to give up. - This interface is deprecated and will be removed by the end of - 2020; implement readahead instead. - ``write_begin`` Called by the generic buffered write code to ask the filesystem to prepare to write len bytes at the given offset in the file. diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index 2d1fc03d346e..ef19b9c13523 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -77,6 +77,17 @@ HOSTLDLIBS ---------- Additional libraries to link against when building host programs. +.. _userkbuildflags: + +USERCFLAGS +---------- +Additional options used for $(CC) when compiling userprogs. + +USERLDFLAGS +----------- +Additional options used for $(LD) when linking userprogs. userprogs are linked +with CC, so $(USERLDFLAGS) should include "-Wl," prefix as applicable. + KBUILD_KCONFIG -------------- Set the top-level Kconfig file to the value of this environment diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index d32616891dcf..b854bb413164 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -49,17 +49,36 @@ example: :: LLVM Utilities -------------- -LLVM has substitutes for GNU binutils utilities. Kbuild supports ``LLVM=1`` -to enable them. :: - - make LLVM=1 - -They can be enabled individually. The full list of the parameters: :: +LLVM has substitutes for GNU binutils utilities. They can be enabled individually. +The full list of supported make variables:: make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \ OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump READELF=llvm-readelf \ HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar HOSTLD=ld.lld +To simplify the above command, Kbuild supports the ``LLVM`` variable:: + + make LLVM=1 + +If your LLVM tools are not available in your PATH, you can supply their +location using the LLVM variable with a trailing slash:: + + make LLVM=/path/to/llvm/ + +which will use ``/path/to/llvm/clang``, ``/path/to/llvm/ld.lld``, etc. + +If your LLVM tools have a version suffix and you want to test with that +explicit version rather than the unsuffixed executables like ``LLVM=1``, you +can pass the suffix using the ``LLVM`` variable:: + + make LLVM=-14 + +which will use ``clang-14``, ``ld.lld-14``, etc. + +``LLVM=0`` is not the same as omitting ``LLVM`` altogether, it will behave like +``LLVM=1``. If you only wish to use certain LLVM utilities, use their respective +make variables. + The integrated assembler is enabled by default. You can pass ``LLVM_IAS=0`` to disable it. diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index b008b90b92c9..11a296e52d68 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -982,6 +982,8 @@ The syntax is quite similar. The difference is to use "userprogs" instead of When linking bpfilter_umh, it will be passed the extra option -static. + From command line, :ref:`USERCFLAGS and USERLDFLAGS <userkbuildflags>` will also be used. + 5.4 When userspace programs are actually built ---------------------------------------------- diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst index bfa75ea1b66a..9933faad4771 100644 --- a/Documentation/locking/locktypes.rst +++ b/Documentation/locking/locktypes.rst @@ -211,9 +211,6 @@ raw_spinlock_t and spinlock_t raw_spinlock_t -------------- -raw_spinlock_t is a strict spinning lock implementation regardless of the -kernel configuration including PREEMPT_RT enabled kernels. - raw_spinlock_t is a strict spinning lock implementation in all kernels, including PREEMPT_RT kernels. Use raw_spinlock_t only in real critical core code, low-level interrupt handling and places where disabling diff --git a/Documentation/maintainer/index.rst b/Documentation/maintainer/index.rst index f0a60435b124..3e03283c144e 100644 --- a/Documentation/maintainer/index.rst +++ b/Documentation/maintainer/index.rst @@ -12,6 +12,7 @@ additions to this manual. configure-git rebasing-and-merging pull-requests + messy-diffstat maintainer-entry-profile modifying-patches diff --git a/Documentation/maintainer/messy-diffstat.rst b/Documentation/maintainer/messy-diffstat.rst new file mode 100644 index 000000000000..c015f66d7621 --- /dev/null +++ b/Documentation/maintainer/messy-diffstat.rst @@ -0,0 +1,96 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================================== +Handling messy pull-request diffstats +===================================== + +Subsystem maintainers routinely use ``git request-pull`` as part of the +process of sending work upstream. Normally, the result includes a nice +diffstat that shows which files will be touched and how much of each will +be changed. Occasionally, though, a repository with a relatively +complicated development history will yield a massive diffstat containing a +great deal of unrelated work. The result looks ugly and obscures what the +pull request is actually doing. This document describes what is happening +and how to fix things up; it is derived from The Wisdom of Linus Torvalds, +found in Linus1_ and Linus2_. + +.. _Linus1: https://lore.kernel.org/lkml/CAHk-=wg3wXH2JNxkQi+eLZkpuxqV+wPiHhw_Jf7ViH33Sw7PHA@mail.gmail.com/ +.. _Linus2: https://lore.kernel.org/lkml/CAHk-=wgXbSa8yq8Dht8at+gxb_idnJ7X5qWZQWRBN4_CUPr=eQ@mail.gmail.com/ + +A Git development history proceeds as a series of commits. In a simplified +manner, mainline kernel development looks like this:: + + ... vM --- vN-rc1 --- vN-rc2 --- vN-rc3 --- ... --- vN-rc7 --- vN + +If one wants to see what has changed between two points, a command like +this will do the job:: + + $ git diff --stat --summary vN-rc2..vN-rc3 + +Here, there are two clear points in the history; Git will essentially +"subtract" the beginning point from the end point and display the resulting +differences. The requested operation is unambiguous and easy enough to +understand. + +When a subsystem maintainer creates a branch and commits changes to it, the +result in the simplest case is a history that looks like:: + + ... vM --- vN-rc1 --- vN-rc2 --- vN-rc3 --- ... --- vN-rc7 --- vN + | + +-- c1 --- c2 --- ... --- cN + +If that maintainer now uses ``git diff`` to see what has changed between +the mainline branch (let's call it "linus") and cN, there are still two +clear endpoints, and the result is as expected. So a pull request +generated with ``git request-pull`` will also be as expected. But now +consider a slightly more complex development history:: + + ... vM --- vN-rc1 --- vN-rc2 --- vN-rc3 --- ... --- vN-rc7 --- vN + | | + | +-- c1 --- c2 --- ... --- cN + | / + +-- x1 --- x2 --- x3 + +Our maintainer has created one branch at vN-rc1 and another at vN-rc2; the +two were then subsequently merged into c2. Now a pull request generated +for cN may end up being messy indeed, and developers often end up wondering +why. + +What is happening here is that there are no longer two clear end points for +the ``git diff`` operation to use. The development culminating in cN +started in two different places; to generate the diffstat, ``git diff`` +ends up having pick one of them and hoping for the best. If the diffstat +starts at vN-rc1, it may end up including all of the changes between there +and the second origin end point (vN-rc2), which is certainly not what our +maintainer had in mind. With all of that extra junk in the diffstat, it +may be impossible to tell what actually happened in the changes leading up +to cN. + +Maintainers often try to resolve this problem by, for example, rebasing the +branch or performing another merge with the linus branch, then recreating +the pull request. This approach tends not to lead to joy at the receiving +end of that pull request; rebasing and/or merging just before pushing +upstream is a well-known way to get a grumpy response. + +So what is to be done? The best response when confronted with this +situation is to indeed to do a merge with the branch you intend your work +to be pulled into, but to do it privately, as if it were the source of +shame. Create a new, throwaway branch and do the merge there:: + + ... vM --- vN-rc1 --- vN-rc2 --- vN-rc3 --- ... --- vN-rc7 --- vN + | | | + | +-- c1 --- c2 --- ... --- cN | + | / | | + +-- x1 --- x2 --- x3 +------------+-- TEMP + +The merge operation resolves all of the complications resulting from the +multiple beginning points, yielding a coherent result that contains only +the differences from the mainline branch. Now it will be possible to +generate a diffstat with the desired information:: + + $ git diff -C --stat --summary linus..TEMP + +Save the output from this command, then simply delete the TEMP branch; +definitely do not expose it to the outside world. Take the saved diffstat +output and edit it into the messy pull request, yielding a result that +shows what is really going on. That request can then be sent upstream. diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 525e6842dd33..43be3782e5df 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -894,7 +894,7 @@ xmit_hash_policy Uses XOR of hardware MAC addresses and packet type ID field to generate the hash. The formula is - hash = source MAC XOR destination MAC XOR packet type ID + hash = source MAC[5] XOR destination MAC[5] XOR packet type ID slave number = hash modulo slave count This algorithm will place all traffic to a particular @@ -910,7 +910,7 @@ xmit_hash_policy Uses XOR of hardware MAC addresses and IP addresses to generate the hash. The formula is - hash = source MAC XOR destination MAC XOR packet type ID + hash = source MAC[5] XOR destination MAC[5] XOR packet type ID hash = hash XOR source IP XOR destination IP hash = hash XOR (hash RSHIFT 16) hash = hash XOR (hash RSHIFT 8) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b0024aa7b051..66828293d9cb 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -267,6 +267,13 @@ ipfrag_max_dist - INTEGER from different IP datagrams, which could result in data corruption. Default: 64 +bc_forwarding - INTEGER + bc_forwarding enables the feature described in rfc1812#section-5.3.5.2 + and rfc2644. It allows the router to forward directed broadcast. + To enable this feature, the 'all' entry and the input interface entry + should be set to 1. + Default: 0 + INET peer storage ================= diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index ea915c196048..e23b876ad6eb 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -7,7 +7,6 @@ RISC-V architecture boot-image-header vm-layout - pmu patch-acceptance features diff --git a/Documentation/sphinx/kernel_abi.py b/Documentation/sphinx/kernel_abi.py index 4392b3cb4020..b5feb5b1d905 100644 --- a/Documentation/sphinx/kernel_abi.py +++ b/Documentation/sphinx/kernel_abi.py @@ -128,6 +128,7 @@ class KernelCmd(Directive): return out def nestedParse(self, lines, fname): + env = self.state.document.settings.env content = ViewList() node = nodes.section() @@ -137,7 +138,7 @@ class KernelCmd(Directive): code_block += "\n " + l lines = code_block + "\n\n" - line_regex = re.compile("^#define LINENO (\S+)\#([0-9]+)$") + line_regex = re.compile("^\.\. LINENO (\S+)\#([0-9]+)$") ln = 0 n = 0 f = fname @@ -154,6 +155,9 @@ class KernelCmd(Directive): self.do_parse(content, node) content = ViewList() + # Add the file to Sphinx build dependencies + env.note_dependency(os.path.abspath(f)) + f = new_f # sphinx counts lines from 0 diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py index 8138d69a6987..27b701ed3681 100644 --- a/Documentation/sphinx/kernel_feat.py +++ b/Documentation/sphinx/kernel_feat.py @@ -33,6 +33,7 @@ u""" import codecs import os +import re import subprocess import sys @@ -82,7 +83,7 @@ class KernelFeat(Directive): env = doc.settings.env cwd = path.dirname(doc.current_source) - cmd = "get_feat.pl rest --dir " + cmd = "get_feat.pl rest --enable-fname --dir " cmd += self.arguments[0] if len(self.arguments) > 1: @@ -102,7 +103,22 @@ class KernelFeat(Directive): shell_env["srctree"] = srctree lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env) - nodeList = self.nestedParse(lines, fname) + + line_regex = re.compile("^\.\. FILE (\S+)$") + + out_lines = "" + + for line in lines.split("\n"): + match = line_regex.search(line) + if match: + fname = match.group(1) + + # Add the file to Sphinx build dependencies + env.note_dependency(os.path.abspath(fname)) + else: + out_lines += line + "\n" + + nodeList = self.nestedParse(out_lines, fname) return nodeList def runCmd(self, cmd, **kwargs): diff --git a/Documentation/sphinx/kernel_include.py b/Documentation/sphinx/kernel_include.py index f523aa68a36b..abe768088377 100755 --- a/Documentation/sphinx/kernel_include.py +++ b/Documentation/sphinx/kernel_include.py @@ -59,6 +59,7 @@ class KernelInclude(Include): u"""KernelInclude (``kernel-include``) directive""" def run(self): + env = self.state.document.settings.env path = os.path.realpath( os.path.expandvars(self.arguments[0])) @@ -70,6 +71,8 @@ class KernelInclude(Include): self.arguments[0] = path + env.note_dependency(os.path.abspath(path)) + #return super(KernelInclude, self).run() # won't work, see HINTs in _run() return self._run() diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 8189c33b9dda..9395892c7ba3 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -130,7 +130,7 @@ class KernelDocDirective(Directive): result = ViewList() lineoffset = 0; - line_regex = re.compile("^#define LINENO ([0-9]+)$") + line_regex = re.compile("^\.\. LINENO ([0-9]+)$") for line in lines: match = line_regex.search(line) if match: diff --git a/Documentation/sphinx/kfigure.py b/Documentation/sphinx/kfigure.py index 24d2b2addcce..cefdbb7e7523 100644 --- a/Documentation/sphinx/kfigure.py +++ b/Documentation/sphinx/kfigure.py @@ -212,7 +212,7 @@ def setupTools(app): if convert_cmd: kernellog.verbose(app, "use convert(1) from: " + convert_cmd) else: - kernellog.warn(app, + kernellog.verbose(app, "Neither inkscape(1) nor convert(1) found.\n" "For SVG to PDF conversion, " "install either Inkscape (https://inkscape.org/) (preferred) or\n" @@ -296,8 +296,10 @@ def convert_image(img_node, translator, src_fname=None): if translator.builder.format == 'latex': if not inkscape_cmd and convert_cmd is None: - kernellog.verbose(app, - "no SVG to PDF conversion available / include SVG raw.") + kernellog.warn(app, + "no SVG to PDF conversion available / include SVG raw." + "\nIncluding large raw SVGs can cause xelatex error." + "\nInstall Inkscape (preferred) or ImageMagick.") img_node.replace_self(file2literal(src_fname)) else: dst_fname = path.join(translator.builder.outdir, fname + '.pdf') diff --git a/Documentation/sphinx/requirements.txt b/Documentation/sphinx/requirements.txt index 9a35f50798a6..2c573541ab71 100644 --- a/Documentation/sphinx/requirements.txt +++ b/Documentation/sphinx/requirements.txt @@ -1,2 +1,4 @@ +# jinja2>=3.1 is not compatible with Sphinx<4.0 +jinja2<3.1 sphinx_rtd_theme Sphinx==2.4.4 diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst index bddedabaca80..c180936f49fc 100644 --- a/Documentation/trace/user_events.rst +++ b/Documentation/trace/user_events.rst @@ -7,7 +7,7 @@ user_events: User-based Event Tracing Overview -------- User based trace events allow user processes to create events and trace data -that can be viewed via existing tools, such as ftrace, perf and eBPF. +that can be viewed via existing tools, such as ftrace and perf. To enable this feature, build your kernel with CONFIG_USER_EVENTS=y. Programs can view status of the events via @@ -67,8 +67,7 @@ The command string format is as follows:: Supported Flags ^^^^^^^^^^^^^^^ -**BPF_ITER** - EBPF programs attached to this event will get the raw iovec -struct instead of any data copies for max performance. +None yet Field Format ^^^^^^^^^^^^ @@ -160,7 +159,7 @@ The following values are defined to aid in checking what has been attached: **EVENT_STATUS_FTRACE** - Bit set if ftrace has been attached (Bit 0). -**EVENT_STATUS_PERF** - Bit set if perf/eBPF has been attached (Bit 1). +**EVENT_STATUS_PERF** - Bit set if perf has been attached (Bit 1). Writing Data ------------ @@ -204,13 +203,6 @@ It's advised for user programs to do the following:: **NOTE:** *The write_index is not emitted out into the trace being recorded.* -EBPF ----- -EBPF programs that attach to a user-based event tracepoint are given a pointer -to a struct user_bpf_context. The bpf context contains the data type (which can -be a user or kernel buffer, or can be a pointer to the iovec) and the data -length that was emitted (minus the write_index). - Example Code ------------ See sample code in samples/user_events. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 07a45474abe9..85c7abc51af5 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -151,12 +151,6 @@ In order to create user controlled virtual machines on S390, check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as privileged user (CAP_SYS_ADMIN). -To use hardware assisted virtualization on MIPS (VZ ASE) rather than -the default trap & emulate implementation (which changes the virtual -memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the -flag KVM_VM_MIPS_VZ. - - On arm64, the physical address size for a VM (IPA Size limit) is limited to 40bits by default. The limit can be configured if the host supports the extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use @@ -4081,6 +4075,11 @@ x2APIC MSRs are always allowed, independent of the ``default_allow`` setting, and their behavior depends on the ``X2APIC_ENABLE`` bit of the APIC base register. +.. warning:: + MSR accesses coming from nested vmentry/vmexit are not filtered. + This includes both writes to individual VMCS fields and reads/writes + through the MSR lists pointed to by the VMCS. + If a bit is within one of the defined ranges, read and write accesses are guarded by the bitmap's value for the MSR index if the kind of access is included in the ``struct kvm_msr_filter_range`` flags. If no range @@ -5293,6 +5292,10 @@ type values: KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO Sets the guest physical address of the vcpu_info for a given vCPU. + As with the shared_info page for the VM, the corresponding page may be + dirtied at any time if event channel interrupt delivery is enabled, so + userspace should always assume that the page is dirty without relying + on dirty logging. KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO Sets the guest physical address of an additional pvclock structure @@ -6187,6 +6190,7 @@ Valid values for 'type' are: unsigned long args[6]; unsigned long ret[2]; } riscv_sbi; + If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has done a SBI call which is not handled by KVM RISC-V kernel module. The details of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The @@ -7719,3 +7723,49 @@ only be invoked on a VM prior to the creation of VCPUs. At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting this capability will disable PMU virtualization for that VM. Usermode should adjust CPUID leaf 0xA to reflect that the PMU is disabled. + +9. Known KVM API problems +========================= + +In some cases, KVM's API has some inconsistencies or common pitfalls +that userspace need to be aware of. This section details some of +these issues. + +Most of them are architecture specific, so the section is split by +architecture. + +9.1. x86 +-------- + +``KVM_GET_SUPPORTED_CPUID`` issues +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In general, ``KVM_GET_SUPPORTED_CPUID`` is designed so that it is possible +to take its result and pass it directly to ``KVM_SET_CPUID2``. This section +documents some cases in which that requires some care. + +Local APIC features +~~~~~~~~~~~~~~~~~~~ + +CPU[EAX=1]:ECX[21] (X2APIC) is reported by ``KVM_GET_SUPPORTED_CPUID``, +but it can only be enabled if ``KVM_CREATE_IRQCHIP`` or +``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are used to enable in-kernel emulation of +the local APIC. + +The same is true for the ``KVM_FEATURE_PV_UNHALT`` paravirtualized feature. + +CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``. +It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel +has enabled in-kernel emulation of the local APIC. + +Obsolete ioctls and capabilities +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +KVM_CAP_DISABLE_QUIRKS does not let userspace know which quirks are actually +available. Use ``KVM_CHECK_EXTENSION(KVM_CAP_DISABLE_QUIRKS2)`` instead if +available. + +Ordering of KVM_GET_*/KVM_SET_* ioctls +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +TBD diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index b6833c7bb474..e0a2c74e1043 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -8,25 +8,13 @@ KVM :maxdepth: 2 api - amd-memory-encryption - cpuid - halt-polling - hypercalls - locking - mmu - msr - nested-vmx - ppc-pv - s390-diag - s390-pv - s390-pv-boot - timekeeping - vcpu-requests - - review-checklist + devices/index arm/index + s390/index + ppc-pv + x86/index - devices/index - - running-nested-guests + locking + vcpu-requests + review-checklist diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 5d27da356836..845a561629f1 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -210,32 +210,47 @@ time it will be set using the Dirty tracking mechanism described above. 3. Reference ------------ -:Name: kvm_lock +``kvm_lock`` +^^^^^^^^^^^^ + :Type: mutex :Arch: any :Protects: - vm_list -:Name: kvm_count_lock +``kvm_count_lock`` +^^^^^^^^^^^^^^^^^^ + :Type: raw_spinlock_t :Arch: any :Protects: - hardware virtualization enable/disable :Comment: 'raw' because hardware enabling/disabling must be atomic /wrt migration. -:Name: kvm_arch::tsc_write_lock -:Type: raw_spinlock +``kvm->mn_invalidate_lock`` +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +:Type: spinlock_t +:Arch: any +:Protects: mn_active_invalidate_count, mn_memslots_update_rcuwait + +``kvm_arch::tsc_write_lock`` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +:Type: raw_spinlock_t :Arch: x86 :Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset} - tsc offset in vmcb :Comment: 'raw' because updating the tsc offsets must not be preempted. -:Name: kvm->mmu_lock -:Type: spinlock_t +``kvm->mmu_lock`` +^^^^^^^^^^^^^^^^^ +:Type: spinlock_t or rwlock_t :Arch: any :Protects: -shadow page/shadow tlb entry :Comment: it is a spinlock since it is used in mmu notifier. -:Name: kvm->srcu +``kvm->srcu`` +^^^^^^^^^^^^^ :Type: srcu lock :Arch: any :Protects: - kvm->memslots @@ -246,10 +261,20 @@ time it will be set using the Dirty tracking mechanism described above. The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu if it is needed by multiple functions. -:Name: blocked_vcpu_on_cpu_lock +``kvm->slots_arch_lock`` +^^^^^^^^^^^^^^^^^^^^^^^^ +:Type: mutex +:Arch: any (only needed on x86 though) +:Protects: any arch-specific fields of memslots that have to be modified + in a ``kvm->srcu`` read-side critical section. +:Comment: must be held before reading the pointer to the current memslots, + until after all changes to the memslots are complete + +``wakeup_vcpus_on_cpu_lock`` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ :Type: spinlock_t :Arch: x86 -:Protects: blocked_vcpu_on_cpu +:Protects: wakeup_vcpus_on_cpu :Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts. When VT-d posted-interrupts is supported and the VM has assigned devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu diff --git a/Documentation/virt/kvm/s390/index.rst b/Documentation/virt/kvm/s390/index.rst new file mode 100644 index 000000000000..605f488f0cc5 --- /dev/null +++ b/Documentation/virt/kvm/s390/index.rst @@ -0,0 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +KVM for s390 systems +==================== + +.. toctree:: + :maxdepth: 2 + + s390-diag + s390-pv + s390-pv-boot diff --git a/Documentation/virt/kvm/s390-diag.rst b/Documentation/virt/kvm/s390/s390-diag.rst index ca85f030eb0b..ca85f030eb0b 100644 --- a/Documentation/virt/kvm/s390-diag.rst +++ b/Documentation/virt/kvm/s390/s390-diag.rst diff --git a/Documentation/virt/kvm/s390-pv-boot.rst b/Documentation/virt/kvm/s390/s390-pv-boot.rst index 73a6083cb5e7..73a6083cb5e7 100644 --- a/Documentation/virt/kvm/s390-pv-boot.rst +++ b/Documentation/virt/kvm/s390/s390-pv-boot.rst diff --git a/Documentation/virt/kvm/s390-pv.rst b/Documentation/virt/kvm/s390/s390-pv.rst index 8e41a3b63fa5..8e41a3b63fa5 100644 --- a/Documentation/virt/kvm/s390-pv.rst +++ b/Documentation/virt/kvm/s390/s390-pv.rst diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index b61d48aec36c..31f62b64e07b 100644 --- a/Documentation/virt/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ================= KVM VCPU Requests ================= @@ -135,6 +137,16 @@ KVM_REQ_UNHALT such as a pending signal, which does not indicate the VCPU's halt emulation should stop, and therefore does not make the request. +KVM_REQ_OUTSIDE_GUEST_MODE + + This "request" ensures the target vCPU has exited guest mode prior to the + sender of the request continuing on. No action needs be taken by the target, + and so no request is actually logged for the target. This request is similar + to a "kick", but unlike a kick it guarantees the vCPU has actually exited + guest mode. A kick only guarantees the vCPU will exit at some point in the + future, e.g. a previous kick may have started the process, but there's no + guarantee the to-be-kicked vCPU has fully exited guest mode. + KVM_REQUEST_MASK ---------------- diff --git a/Documentation/virt/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index 1c6847fff304..2d307811978c 100644 --- a/Documentation/virt/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ====================================== Secure Encrypted Virtualization (SEV) ====================================== diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/x86/cpuid.rst index bda3e3e737d7..bda3e3e737d7 100644 --- a/Documentation/virt/kvm/cpuid.rst +++ b/Documentation/virt/kvm/x86/cpuid.rst diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst new file mode 100644 index 000000000000..410e0aa63493 --- /dev/null +++ b/Documentation/virt/kvm/x86/errata.rst @@ -0,0 +1,39 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +Known limitations of CPU virtualization +======================================= + +Whenever perfect emulation of a CPU feature is impossible or too hard, KVM +has to choose between not implementing the feature at all or introducing +behavioral differences between virtual machines and bare metal systems. + +This file documents some of the known limitations that KVM has in +virtualizing CPU features. + +x86 +=== + +``KVM_GET_SUPPORTED_CPUID`` issues +---------------------------------- + +x87 features +~~~~~~~~~~~~ + +Unlike most other CPUID feature bits, CPUID[EAX=7,ECX=0]:EBX[6] +(FDP_EXCPTN_ONLY) and CPUID[EAX=7,ECX=0]:EBX]13] (ZERO_FCS_FDS) are +clear if the features are present and set if the features are not present. + +Clearing these bits in CPUID has no effect on the operation of the guest; +if these bits are set on hardware, the features will not be present on +any virtual machine that runs on that hardware. + +**Workaround:** It is recommended to always set these bits in guest CPUID. +Note however that any software (e.g ``WIN87EM.DLL``) expecting these features +to be present likely predates these CPUID feature bits, and therefore +doesn't know to check for them anyway. + +Nested virtualization features +------------------------------ + +TBD diff --git a/Documentation/virt/kvm/halt-polling.rst b/Documentation/virt/kvm/x86/halt-polling.rst index 4922e4a15f18..4922e4a15f18 100644 --- a/Documentation/virt/kvm/halt-polling.rst +++ b/Documentation/virt/kvm/x86/halt-polling.rst diff --git a/Documentation/virt/kvm/hypercalls.rst b/Documentation/virt/kvm/x86/hypercalls.rst index e56fa8b9cfca..e56fa8b9cfca 100644 --- a/Documentation/virt/kvm/hypercalls.rst +++ b/Documentation/virt/kvm/x86/hypercalls.rst diff --git a/Documentation/virt/kvm/x86/index.rst b/Documentation/virt/kvm/x86/index.rst new file mode 100644 index 000000000000..7ff588826b9f --- /dev/null +++ b/Documentation/virt/kvm/x86/index.rst @@ -0,0 +1,19 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================== +KVM for x86 systems +=================== + +.. toctree:: + :maxdepth: 2 + + amd-memory-encryption + cpuid + errata + halt-polling + hypercalls + mmu + msr + nested-vmx + running-nested-guests + timekeeping diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/x86/mmu.rst index 5b1ebad24c77..5b1ebad24c77 100644 --- a/Documentation/virt/kvm/mmu.rst +++ b/Documentation/virt/kvm/x86/mmu.rst diff --git a/Documentation/virt/kvm/msr.rst b/Documentation/virt/kvm/x86/msr.rst index 9315fc385fb0..9315fc385fb0 100644 --- a/Documentation/virt/kvm/msr.rst +++ b/Documentation/virt/kvm/x86/msr.rst diff --git a/Documentation/virt/kvm/nested-vmx.rst b/Documentation/virt/kvm/x86/nested-vmx.rst index ac2095d41f02..ac2095d41f02 100644 --- a/Documentation/virt/kvm/nested-vmx.rst +++ b/Documentation/virt/kvm/x86/nested-vmx.rst diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/x86/running-nested-guests.rst index bd70c69468ae..a27e6768d900 100644 --- a/Documentation/virt/kvm/running-nested-guests.rst +++ b/Documentation/virt/kvm/x86/running-nested-guests.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ============================== Running nested guests with KVM ============================== diff --git a/Documentation/virt/kvm/timekeeping.rst b/Documentation/virt/kvm/x86/timekeeping.rst index 21ae7efa29ba..21ae7efa29ba 100644 --- a/Documentation/virt/kvm/timekeeping.rst +++ b/Documentation/virt/kvm/x86/timekeeping.rst diff --git a/Documentation/virt/uml/user_mode_linux_howto_v2.rst b/Documentation/virt/uml/user_mode_linux_howto_v2.rst index d5ad96c795f6..863f67b72c05 100644 --- a/Documentation/virt/uml/user_mode_linux_howto_v2.rst +++ b/Documentation/virt/uml/user_mode_linux_howto_v2.rst @@ -1193,6 +1193,26 @@ E.g. ``os_close_file()`` is just a wrapper around ``close()`` which ensures that the userspace function close does not clash with similarly named function(s) in the kernel part. +Using UML as a Test Platform +============================ + +UML is an excellent test platform for device driver development. As +with most things UML, "some user assembly may be required". It is +up to the user to build their emulation environment. UML at present +provides only the kernel infrastructure. + +Part of this infrastructure is the ability to load and parse fdt +device tree blobs as used in Arm or Open Firmware platforms. These +are supplied as an optional extra argument to the kernel command +line:: + + dtb=filename + +The device tree is loaded and parsed at boottime and is accessible by +drivers which query it. At this moment in time this facility is +intended solely for development purposes. UML's own devices do not +query the device tree. + Security Considerations ----------------------- diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index c4de6f8dabe9..65204d7f004f 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -125,7 +125,6 @@ Usage additional function: Cull: - -c Cull by comparing stacktrace instead of total block. --cull <rules> Specify culling rules.Culling syntax is key[,key[,...]].Choose a multi-letter key from the **STANDARD FORMAT SPECIFIERS** section. diff --git a/Documentation/vm/unevictable-lru.rst b/Documentation/vm/unevictable-lru.rst index eae3af17f2d9..b280367d6a44 100644 --- a/Documentation/vm/unevictable-lru.rst +++ b/Documentation/vm/unevictable-lru.rst @@ -52,8 +52,13 @@ The infrastructure may also be able to handle other conditions that make pages unevictable, either by definition or by circumstance, in the future. -The Unevictable Page List -------------------------- +The Unevictable LRU Page List +----------------------------- + +The Unevictable LRU page list is a lie. It was never an LRU-ordered list, but a +companion to the LRU-ordered anonymous and file, active and inactive page lists; +and now it is not even a page list. But following familiar convention, here in +this document and in the source, we often imagine it as a fifth LRU page list. The Unevictable LRU infrastructure consists of an additional, per-node, LRU list called the "unevictable" list and an associated page flag, PG_unevictable, to @@ -63,8 +68,8 @@ The PG_unevictable flag is analogous to, and mutually exclusive with, the PG_active flag in that it indicates on which LRU list a page resides when PG_lru is set. -The Unevictable LRU infrastructure maintains unevictable pages on an additional -LRU list for a few reasons: +The Unevictable LRU infrastructure maintains unevictable pages as if they were +on an additional LRU list for a few reasons: (1) We get to "treat unevictable pages just like we treat other pages in the system - which means we get to use the same code to manipulate them, the @@ -72,13 +77,11 @@ LRU list for a few reasons: of the statistics, etc..." [Rik van Riel] (2) We want to be able to migrate unevictable pages between nodes for memory - defragmentation, workload management and memory hotplug. The linux kernel + defragmentation, workload management and memory hotplug. The Linux kernel can only migrate pages that it can successfully isolate from the LRU - lists. If we were to maintain pages elsewhere than on an LRU-like list, - where they can be found by isolate_lru_page(), we would prevent their - migration, unless we reworked migration code to find the unevictable pages - itself. - + lists (or "Movable" pages: outside of consideration here). If we were to + maintain pages elsewhere than on an LRU-like list, where they can be + detected by isolate_lru_page(), we would prevent their migration. The unevictable list does not differentiate between file-backed and anonymous, swap-backed pages. This differentiation is only important while the pages are, @@ -92,8 +95,8 @@ Memory Control Group Interaction -------------------------------- The unevictable LRU facility interacts with the memory control group [aka -memory controller; see Documentation/admin-guide/cgroup-v1/memory.rst] by extending the -lru_list enum. +memory controller; see Documentation/admin-guide/cgroup-v1/memory.rst] by +extending the lru_list enum. The memory controller data structure automatically gets a per-node unevictable list as a result of the "arrayification" of the per-node LRU lists (one per @@ -143,7 +146,6 @@ These are currently used in three places in the kernel: and this mark remains for the life of the inode. (2) By SYSV SHM to mark SHM_LOCK'd address spaces until SHM_UNLOCK is called. - Note that SHM_LOCK is not required to page in the locked pages if they're swapped out; the application must touch the pages manually if it wants to ensure they're in memory. @@ -156,19 +158,19 @@ These are currently used in three places in the kernel: Detecting Unevictable Pages --------------------------- -The function page_evictable() in vmscan.c determines whether a page is +The function page_evictable() in mm/internal.h determines whether a page is evictable or not using the query function outlined above [see section :ref:`Marking address spaces unevictable <mark_addr_space_unevict>`] to check the AS_UNEVICTABLE flag. For address spaces that are so marked after being populated (as SHM regions -might be), the lock action (eg: SHM_LOCK) can be lazy, and need not populate +might be), the lock action (e.g. SHM_LOCK) can be lazy, and need not populate the page tables for the region as does, for example, mlock(), nor need it make any special effort to push any pages in the SHM_LOCK'd area to the unevictable list. Instead, vmscan will do this if and when it encounters the pages during a reclamation scan. -On an unlock action (such as SHM_UNLOCK), the unlocker (eg: shmctl()) must scan +On an unlock action (such as SHM_UNLOCK), the unlocker (e.g. shmctl()) must scan the pages in the region and "rescue" them from the unevictable list if no other condition is keeping them unevictable. If an unevictable region is destroyed, the pages are also "rescued" from the unevictable list in the process of @@ -176,7 +178,7 @@ freeing them. page_evictable() also checks for mlocked pages by testing an additional page flag, PG_mlocked (as wrapped by PageMlocked()), which is set when a page is -faulted into a VM_LOCKED vma, or found in a vma being VM_LOCKED. +faulted into a VM_LOCKED VMA, or found in a VMA being VM_LOCKED. Vmscan's Handling of Unevictable Pages @@ -186,28 +188,23 @@ If unevictable pages are culled in the fault path, or moved to the unevictable list at mlock() or mmap() time, vmscan will not encounter the pages until they have become evictable again (via munlock() for example) and have been "rescued" from the unevictable list. However, there may be situations where we decide, -for the sake of expediency, to leave a unevictable page on one of the regular +for the sake of expediency, to leave an unevictable page on one of the regular active/inactive LRU lists for vmscan to deal with. vmscan checks for such pages in all of the shrink_{active|inactive|page}_list() functions and will "cull" such pages that it encounters: that is, it diverts those pages to the -unevictable list for the node being scanned. +unevictable list for the memory cgroup and node being scanned. There may be situations where a page is mapped into a VM_LOCKED VMA, but the page is not marked as PG_mlocked. Such pages will make it all the way to -shrink_page_list() where they will be detected when vmscan walks the reverse -map in try_to_unmap(). If try_to_unmap() returns SWAP_MLOCK, -shrink_page_list() will cull the page at that point. +shrink_active_list() or shrink_page_list() where they will be detected when +vmscan walks the reverse map in page_referenced() or try_to_unmap(). The page +is culled to the unevictable list when it is released by the shrinker. To "cull" an unevictable page, vmscan simply puts the page back on the LRU list using putback_lru_page() - the inverse operation to isolate_lru_page() - after dropping the page lock. Because the condition which makes the page unevictable -may change once the page is unlocked, putback_lru_page() will recheck the -unevictable state of a page that it places on the unevictable list. If the -page has become unevictable, putback_lru_page() removes it from the list and -retries, including the page_unevictable() test. Because such a race is a rare -event and movement of pages onto the unevictable list should be rare, these -extra evictabilty checks should not occur in the majority of calls to -putback_lru_page(). +may change once the page is unlocked, __pagevec_lru_add_fn() will recheck the +unevictable state of a page before placing it on the unevictable list. MLOCKED Pages @@ -227,16 +224,25 @@ Nick posted his patch as an alternative to a patch posted by Christoph Lameter to achieve the same objective: hiding mlocked pages from vmscan. In Nick's patch, he used one of the struct page LRU list link fields as a count -of VM_LOCKED VMAs that map the page. This use of the link field for a count -prevented the management of the pages on an LRU list, and thus mlocked pages -were not migratable as isolate_lru_page() could not find them, and the LRU list -link field was not available to the migration subsystem. +of VM_LOCKED VMAs that map the page (Rik van Riel had the same idea three years +earlier). But this use of the link field for a count prevented the management +of the pages on an LRU list, and thus mlocked pages were not migratable as +isolate_lru_page() could not detect them, and the LRU list link field was not +available to the migration subsystem. -Nick resolved this by putting mlocked pages back on the lru list before +Nick resolved this by putting mlocked pages back on the LRU list before attempting to isolate them, thus abandoning the count of VM_LOCKED VMAs. When Nick's patch was integrated with the Unevictable LRU work, the count was -replaced by walking the reverse map to determine whether any VM_LOCKED VMAs -mapped the page. More on this below. +replaced by walking the reverse map when munlocking, to determine whether any +other VM_LOCKED VMAs still mapped the page. + +However, walking the reverse map for each page when munlocking was ugly and +inefficient, and could lead to catastrophic contention on a file's rmap lock, +when many processes which had it mlocked were trying to exit. In 5.18, the +idea of keeping mlock_count in Unevictable LRU list link field was revived and +put to work, without preventing the migration of mlocked pages. This is why +the "Unevictable LRU list" cannot be a linked list of pages now; but there was +no use for that linked list anyway - though its size is maintained for meminfo. Basic Management @@ -250,22 +256,18 @@ PageMlocked() functions. A PG_mlocked page will be placed on the unevictable list when it is added to the LRU. Such pages can be "noticed" by memory management in several places: - (1) in the mlock()/mlockall() system call handlers; + (1) in the mlock()/mlock2()/mlockall() system call handlers; (2) in the mmap() system call handler when mmapping a region with the MAP_LOCKED flag; (3) mmapping a region in a task that has called mlockall() with the MCL_FUTURE - flag + flag; - (4) in the fault path, if mlocked pages are "culled" in the fault path, - and when a VM_LOCKED stack segment is expanded; or + (4) in the fault path and when a VM_LOCKED stack segment is expanded; or (5) as mentioned above, in vmscan:shrink_page_list() when attempting to - reclaim a page in a VM_LOCKED VMA via try_to_unmap() - -all of which result in the VM_LOCKED flag being set for the VMA if it doesn't -already have it set. + reclaim a page in a VM_LOCKED VMA by page_referenced() or try_to_unmap(). mlocked pages become unlocked and rescued from the unevictable list when: @@ -280,51 +282,53 @@ mlocked pages become unlocked and rescued from the unevictable list when: (4) before a page is COW'd in a VM_LOCKED VMA. -mlock()/mlockall() System Call Handling ---------------------------------------- +mlock()/mlock2()/mlockall() System Call Handling +------------------------------------------------ -Both [do\_]mlock() and [do\_]mlockall() system call handlers call mlock_fixup() +mlock(), mlock2() and mlockall() system call handlers proceed to mlock_fixup() for each VMA in the range specified by the call. In the case of mlockall(), this is the entire active address space of the task. Note that mlock_fixup() is used for both mlocking and munlocking a range of memory. A call to mlock() -an already VM_LOCKED VMA, or to munlock() a VMA that is not VM_LOCKED is -treated as a no-op, and mlock_fixup() simply returns. +an already VM_LOCKED VMA, or to munlock() a VMA that is not VM_LOCKED, is +treated as a no-op and mlock_fixup() simply returns. -If the VMA passes some filtering as described in "Filtering Special Vmas" +If the VMA passes some filtering as described in "Filtering Special VMAs" below, mlock_fixup() will attempt to merge the VMA with its neighbors or split -off a subset of the VMA if the range does not cover the entire VMA. Once the -VMA has been merged or split or neither, mlock_fixup() will call -populate_vma_page_range() to fault in the pages via get_user_pages() and to -mark the pages as mlocked via mlock_vma_page(). +off a subset of the VMA if the range does not cover the entire VMA. Any pages +already present in the VMA are then marked as mlocked by mlock_page() via +mlock_pte_range() via walk_page_range() via mlock_vma_pages_range(). + +Before returning from the system call, do_mlock() or mlockall() will call +__mm_populate() to fault in the remaining pages via get_user_pages() and to +mark those pages as mlocked as they are faulted. Note that the VMA being mlocked might be mapped with PROT_NONE. In this case, get_user_pages() will be unable to fault in the pages. That's okay. If pages -do end up getting faulted into this VM_LOCKED VMA, we'll handle them in the -fault path or in vmscan. - -Also note that a page returned by get_user_pages() could be truncated or -migrated out from under us, while we're trying to mlock it. To detect this, -populate_vma_page_range() checks page_mapping() after acquiring the page lock. -If the page is still associated with its mapping, we'll go ahead and call -mlock_vma_page(). If the mapping is gone, we just unlock the page and move on. -In the worst case, this will result in a page mapped in a VM_LOCKED VMA -remaining on a normal LRU list without being PageMlocked(). Again, vmscan will -detect and cull such pages. - -mlock_vma_page() will call TestSetPageMlocked() for each page returned by -get_user_pages(). We use TestSetPageMlocked() because the page might already -be mlocked by another task/VMA and we don't want to do extra work. We -especially do not want to count an mlocked page more than once in the -statistics. If the page was already mlocked, mlock_vma_page() need do nothing -more. - -If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the -page from the LRU, as it is likely on the appropriate active or inactive list -at that time. If the isolate_lru_page() succeeds, mlock_vma_page() will put -back the page - by calling putback_lru_page() - which will notice that the page -is now mlocked and divert the page to the node's unevictable list. If -mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle -it later if and when it attempts to reclaim the page. +do end up getting faulted into this VM_LOCKED VMA, they will be handled in the +fault path - which is also how mlock2()'s MLOCK_ONFAULT areas are handled. + +For each PTE (or PMD) being faulted into a VMA, the page add rmap function +calls mlock_vma_page(), which calls mlock_page() when the VMA is VM_LOCKED +(unless it is a PTE mapping of a part of a transparent huge page). Or when +it is a newly allocated anonymous page, lru_cache_add_inactive_or_unevictable() +calls mlock_new_page() instead: similar to mlock_page(), but can make better +judgments, since this page is held exclusively and known not to be on LRU yet. + +mlock_page() sets PageMlocked immediately, then places the page on the CPU's +mlock pagevec, to batch up the rest of the work to be done under lru_lock by +__mlock_page(). __mlock_page() sets PageUnevictable, initializes mlock_count +and moves the page to unevictable state ("the unevictable LRU", but with +mlock_count in place of LRU threading). Or if the page was already PageLRU +and PageUnevictable and PageMlocked, it simply increments the mlock_count. + +But in practice that may not work ideally: the page may not yet be on an LRU, or +it may have been temporarily isolated from LRU. In such cases the mlock_count +field cannot be touched, but will be set to 0 later when __pagevec_lru_add_fn() +returns the page to "LRU". Races prohibit mlock_count from being set to 1 then: +rather than risk stranding a page indefinitely as unevictable, always err with +mlock_count on the low side, so that when munlocked the page will be rescued to +an evictable LRU, then perhaps be mlocked again later if vmscan finds it in a +VM_LOCKED VMA. Filtering Special VMAs @@ -339,68 +343,48 @@ mlock_fixup() filters several classes of "special" VMAs: so there is no sense in attempting to visit them. 2) VMAs mapping hugetlbfs page are already effectively pinned into memory. We - neither need nor want to mlock() these pages. However, to preserve the - prior behavior of mlock() - before the unevictable/mlock changes - - mlock_fixup() will call make_pages_present() in the hugetlbfs VMA range to - allocate the huge pages and populate the ptes. + neither need nor want to mlock() these pages. But __mm_populate() includes + hugetlbfs ranges, allocating the huge pages and populating the PTEs. 3) VMAs with VM_DONTEXPAND are generally userspace mappings of kernel pages, - such as the VDSO page, relay channel pages, etc. These pages - are inherently unevictable and are not managed on the LRU lists. - mlock_fixup() treats these VMAs the same as hugetlbfs VMAs. It calls - make_pages_present() to populate the ptes. + such as the VDSO page, relay channel pages, etc. These pages are inherently + unevictable and are not managed on the LRU lists. __mm_populate() includes + these ranges, populating the PTEs if not already populated. + +4) VMAs with VM_MIXEDMAP set are not marked VM_LOCKED, but __mm_populate() + includes these ranges, populating the PTEs if not already populated. Note that for all of these special VMAs, mlock_fixup() does not set the VM_LOCKED flag. Therefore, we won't have to deal with them later during munlock(), munmap() or task exit. Neither does mlock_fixup() account these VMAs against the task's "locked_vm". -.. _munlock_munlockall_handling: munlock()/munlockall() System Call Handling ------------------------------------------- -The munlock() and munlockall() system calls are handled by the same functions - -do_mlock[all]() - as the mlock() and mlockall() system calls with the unlock vs -lock operation indicated by an argument. So, these system calls are also -handled by mlock_fixup(). Again, if called for an already munlocked VMA, -mlock_fixup() simply returns. Because of the VMA filtering discussed above, -VM_LOCKED will not be set in any "special" VMAs. So, these VMAs will be -ignored for munlock. +The munlock() and munlockall() system calls are handled by the same +mlock_fixup() function as mlock(), mlock2() and mlockall() system calls are. +If called to munlock an already munlocked VMA, mlock_fixup() simply returns. +Because of the VMA filtering discussed above, VM_LOCKED will not be set in +any "special" VMAs. So, those VMAs will be ignored for munlock. If the VMA is VM_LOCKED, mlock_fixup() again attempts to merge or split off the -specified range. The range is then munlocked via the function -populate_vma_page_range() - the same function used to mlock a VMA range - -passing a flag to indicate that munlock() is being performed. - -Because the VMA access protections could have been changed to PROT_NONE after -faulting in and mlocking pages, get_user_pages() was unreliable for visiting -these pages for munlocking. Because we don't want to leave pages mlocked, -get_user_pages() was enhanced to accept a flag to ignore the permissions when -fetching the pages - all of which should be resident as a result of previous -mlocking. - -For munlock(), populate_vma_page_range() unlocks individual pages by calling -munlock_vma_page(). munlock_vma_page() unconditionally clears the PG_mlocked -flag using TestClearPageMlocked(). As with mlock_vma_page(), -munlock_vma_page() use the Test*PageMlocked() function to handle the case where -the page might have already been unlocked by another task. If the page was -mlocked, munlock_vma_page() updates that zone statistics for the number of -mlocked pages. Note, however, that at this point we haven't checked whether -the page is mapped by other VM_LOCKED VMAs. - -We can't call page_mlock(), the function that walks the reverse map to -check for other VM_LOCKED VMAs, without first isolating the page from the LRU. -page_mlock() is a variant of try_to_unmap() and thus requires that the page -not be on an LRU list [more on these below]. However, the call to -isolate_lru_page() could fail, in which case we can't call page_mlock(). So, -we go ahead and clear PG_mlocked up front, as this might be the only chance we -have. If we can successfully isolate the page, we go ahead and call -page_mlock(), which will restore the PG_mlocked flag and update the zone -page statistics if it finds another VMA holding the page mlocked. If we fail -to isolate the page, we'll have left a potentially mlocked page on the LRU. -This is fine, because we'll catch it later if and if vmscan tries to reclaim -the page. This should be relatively rare. +specified range. All pages in the VMA are then munlocked by munlock_page() via +mlock_pte_range() via walk_page_range() via mlock_vma_pages_range() - the same +function used when mlocking a VMA range, with new flags for the VMA indicating +that it is munlock() being performed. + +munlock_page() uses the mlock pagevec to batch up work to be done under +lru_lock by __munlock_page(). __munlock_page() decrements the page's +mlock_count, and when that reaches 0 it clears PageMlocked and clears +PageUnevictable, moving the page from unevictable state to inactive LRU. + +But in practice that may not work ideally: the page may not yet have reached +"the unevictable LRU", or it may have been temporarily isolated from it. In +those cases its mlock_count field is unusable and must be assumed to be 0: so +that the page will be rescued to an evictable LRU, then perhaps be mlocked +again later if vmscan finds it in a VM_LOCKED VMA. Migrating MLOCKED Pages @@ -410,33 +394,38 @@ A page that is being migrated has been isolated from the LRU lists and is held locked across unmapping of the page, updating the page's address space entry and copying the contents and state, until the page table entry has been replaced with an entry that refers to the new page. Linux supports migration -of mlocked pages and other unevictable pages. This involves simply moving the -PG_mlocked and PG_unevictable states from the old page to the new page. +of mlocked pages and other unevictable pages. PG_mlocked is cleared from the +the old page when it is unmapped from the last VM_LOCKED VMA, and set when the +new page is mapped in place of migration entry in a VM_LOCKED VMA. If the page +was unevictable because mlocked, PG_unevictable follows PG_mlocked; but if the +page was unevictable for other reasons, PG_unevictable is copied explicitly. Note that page migration can race with mlocking or munlocking of the same page. -This has been discussed from the mlock/munlock perspective in the respective -sections above. Both processes (migration and m[un]locking) hold the page -locked. This provides the first level of synchronization. Page migration -zeros out the page_mapping of the old page before unlocking it, so m[un]lock -can skip these pages by testing the page mapping under page lock. +There is mostly no problem since page migration requires unmapping all PTEs of +the old page (including munlock where VM_LOCKED), then mapping in the new page +(including mlock where VM_LOCKED). The page table locks provide sufficient +synchronization. -To complete page migration, we place the new and old pages back onto the LRU -after dropping the page lock. The "unneeded" page - old page on success, new -page on failure - will be freed when the reference count held by the migration -process is released. To ensure that we don't strand pages on the unevictable -list because of a race between munlock and migration, page migration uses the -putback_lru_page() function to add migrated pages back to the LRU. +However, since mlock_vma_pages_range() starts by setting VM_LOCKED on a VMA, +before mlocking any pages already present, if one of those pages were migrated +before mlock_pte_range() reached it, it would get counted twice in mlock_count. +To prevent that, mlock_vma_pages_range() temporarily marks the VMA as VM_IO, +so that mlock_vma_page() will skip it. + +To complete page migration, we place the old and new pages back onto the LRU +afterwards. The "unneeded" page - old page on success, new page on failure - +is freed when the reference count held by the migration process is released. Compacting MLOCKED Pages ------------------------ -The unevictable LRU can be scanned for compactable regions and the default -behavior is to do so. /proc/sys/vm/compact_unevictable_allowed controls -this behavior (see Documentation/admin-guide/sysctl/vm.rst). Once scanning of the -unevictable LRU is enabled, the work of compaction is mostly handled by -the page migration code and the same work flow as described in MIGRATING -MLOCKED PAGES will apply. +The memory map can be scanned for compactable regions and the default behavior +is to let unevictable pages be moved. /proc/sys/vm/compact_unevictable_allowed +controls this behavior (see Documentation/admin-guide/sysctl/vm.rst). The work +of compaction is mostly handled by the page migration code and the same work +flow as described in Migrating MLOCKED Pages will apply. + MLOCKING Transparent Huge Pages ------------------------------- @@ -445,51 +434,44 @@ A transparent huge page is represented by a single entry on an LRU list. Therefore, we can only make unevictable an entire compound page, not individual subpages. -If a user tries to mlock() part of a huge page, we want the rest of the -page to be reclaimable. +If a user tries to mlock() part of a huge page, and no user mlock()s the +whole of the huge page, we want the rest of the page to be reclaimable. We cannot just split the page on partial mlock() as split_huge_page() can -fail and new intermittent failure mode for the syscall is undesirable. +fail and a new intermittent failure mode for the syscall is undesirable. -We handle this by keeping PTE-mapped huge pages on normal LRU lists: the -PMD on border of VM_LOCKED VMA will be split into PTE table. +We handle this by keeping PTE-mlocked huge pages on evictable LRU lists: +the PMD on the border of a VM_LOCKED VMA will be split into a PTE table. -This way the huge page is accessible for vmscan. Under memory pressure the +This way the huge page is accessible for vmscan. Under memory pressure the page will be split, subpages which belong to VM_LOCKED VMAs will be moved -to unevictable LRU and the rest can be reclaimed. +to the unevictable LRU and the rest can be reclaimed. + +/proc/meminfo's Unevictable and Mlocked amounts do not include those parts +of a transparent huge page which are mapped only by PTEs in VM_LOCKED VMAs. -See also comment in follow_trans_huge_pmd(). mmap(MAP_LOCKED) System Call Handling ------------------------------------- -In addition the mlock()/mlockall() system calls, an application can request -that a region of memory be mlocked supplying the MAP_LOCKED flag to the mmap() -call. There is one important and subtle difference here, though. mmap() + mlock() -will fail if the range cannot be faulted in (e.g. because mm_populate fails) -and returns with ENOMEM while mmap(MAP_LOCKED) will not fail. The mmaped -area will still have properties of the locked area - aka. pages will not get -swapped out - but major page faults to fault memory in might still happen. +In addition to the mlock(), mlock2() and mlockall() system calls, an application +can request that a region of memory be mlocked by supplying the MAP_LOCKED flag +to the mmap() call. There is one important and subtle difference here, though. +mmap() + mlock() will fail if the range cannot be faulted in (e.g. because +mm_populate fails) and returns with ENOMEM while mmap(MAP_LOCKED) will not fail. +The mmaped area will still have properties of the locked area - pages will not +get swapped out - but major page faults to fault memory in might still happen. -Furthermore, any mmap() call or brk() call that expands the heap by a -task that has previously called mlockall() with the MCL_FUTURE flag will result +Furthermore, any mmap() call or brk() call that expands the heap by a task +that has previously called mlockall() with the MCL_FUTURE flag will result in the newly mapped memory being mlocked. Before the unevictable/mlock -changes, the kernel simply called make_pages_present() to allocate pages and -populate the page table. +changes, the kernel simply called make_pages_present() to allocate pages +and populate the page table. -To mlock a range of memory under the unevictable/mlock infrastructure, the -mmap() handler and task address space expansion functions call +To mlock a range of memory under the unevictable/mlock infrastructure, +the mmap() handler and task address space expansion functions call populate_vma_page_range() specifying the vma and the address range to mlock. -The callers of populate_vma_page_range() will have already added the memory range -to be mlocked to the task's "locked_vm". To account for filtered VMAs, -populate_vma_page_range() returns the number of pages NOT mlocked. All of the -callers then subtract a non-negative return value from the task's locked_vm. A -negative return value represent an error - for example, from get_user_pages() -attempting to fault in a VMA with PROT_NONE access. In this case, we leave the -memory range accounted as locked_vm, as the protections could be changed later -and pages allocated into that region. - munmap()/exit()/exec() System Call Handling ------------------------------------------- @@ -500,81 +482,53 @@ munlock the pages if we're removing the last VM_LOCKED VMA that maps the pages. Before the unevictable/mlock changes, mlocking did not mark the pages in any way, so unmapping them required no processing. -To munlock a range of memory under the unevictable/mlock infrastructure, the -munmap() handler and task address space call tear down function -munlock_vma_pages_all(). The name reflects the observation that one always -specifies the entire VMA range when munlock()ing during unmap of a region. -Because of the VMA filtering when mlocking() regions, only "normal" VMAs that -actually contain mlocked pages will be passed to munlock_vma_pages_all(). - -munlock_vma_pages_all() clears the VM_LOCKED VMA flag and, like mlock_fixup() -for the munlock case, calls __munlock_vma_pages_range() to walk the page table -for the VMA's memory range and munlock_vma_page() each resident page mapped by -the VMA. This effectively munlocks the page, only if this is the last -VM_LOCKED VMA that maps the page. - - -try_to_unmap() --------------- - -Pages can, of course, be mapped into multiple VMAs. Some of these VMAs may -have VM_LOCKED flag set. It is possible for a page mapped into one or more -VM_LOCKED VMAs not to have the PG_mlocked flag set and therefore reside on one -of the active or inactive LRU lists. This could happen if, for example, a task -in the process of munlocking the page could not isolate the page from the LRU. -As a result, vmscan/shrink_page_list() might encounter such a page as described -in section "vmscan's handling of unevictable pages". To handle this situation, -try_to_unmap() checks for VM_LOCKED VMAs while it is walking a page's reverse -map. - -try_to_unmap() is always called, by either vmscan for reclaim or for page -migration, with the argument page locked and isolated from the LRU. Separate -functions handle anonymous and mapped file and KSM pages, as these types of -pages have different reverse map lookup mechanisms, with different locking. -In each case, whether rmap_walk_anon() or rmap_walk_file() or rmap_walk_ksm(), -it will call try_to_unmap_one() for every VMA which might contain the page. - -When trying to reclaim, if try_to_unmap_one() finds the page in a VM_LOCKED -VMA, it will then mlock the page via mlock_vma_page() instead of unmapping it, -and return SWAP_MLOCK to indicate that the page is unevictable: and the scan -stops there. - -mlock_vma_page() is called while holding the page table's lock (in addition -to the page lock, and the rmap lock): to serialize against concurrent mlock or -munlock or munmap system calls, mm teardown (munlock_vma_pages_all), reclaim, -holepunching, and truncation of file pages and their anonymous COWed pages. - - -page_mlock() Reverse Map Scan ---------------------------------- - -When munlock_vma_page() [see section :ref:`munlock()/munlockall() System Call -Handling <munlock_munlockall_handling>` above] tries to munlock a -page, it needs to determine whether or not the page is mapped by any -VM_LOCKED VMA without actually attempting to unmap all PTEs from the -page. For this purpose, the unevictable/mlock infrastructure -introduced a variant of try_to_unmap() called page_mlock(). - -page_mlock() walks the respective reverse maps looking for VM_LOCKED VMAs. When -such a VMA is found the page is mlocked via mlock_vma_page(). This undoes the -pre-clearing of the page's PG_mlocked done by munlock_vma_page. - -Note that page_mlock()'s reverse map walk must visit every VMA in a page's -reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA. -However, the scan can terminate when it encounters a VM_LOCKED VMA. -Although page_mlock() might be called a great many times when munlocking a -large region or tearing down a large address space that has been mlocked via -mlockall(), overall this is a fairly rare event. +For each PTE (or PMD) being unmapped from a VMA, page_remove_rmap() calls +munlock_vma_page(), which calls munlock_page() when the VMA is VM_LOCKED +(unless it was a PTE mapping of a part of a transparent huge page). + +munlock_page() uses the mlock pagevec to batch up work to be done under +lru_lock by __munlock_page(). __munlock_page() decrements the page's +mlock_count, and when that reaches 0 it clears PageMlocked and clears +PageUnevictable, moving the page from unevictable state to inactive LRU. + +But in practice that may not work ideally: the page may not yet have reached +"the unevictable LRU", or it may have been temporarily isolated from it. In +those cases its mlock_count field is unusable and must be assumed to be 0: so +that the page will be rescued to an evictable LRU, then perhaps be mlocked +again later if vmscan finds it in a VM_LOCKED VMA. + + +Truncating MLOCKED Pages +------------------------ + +File truncation or hole punching forcibly unmaps the deleted pages from +userspace; truncation even unmaps and deletes any private anonymous pages +which had been Copied-On-Write from the file pages now being truncated. + +Mlocked pages can be munlocked and deleted in this way: like with munmap(), +for each PTE (or PMD) being unmapped from a VMA, page_remove_rmap() calls +munlock_vma_page(), which calls munlock_page() when the VMA is VM_LOCKED +(unless it was a PTE mapping of a part of a transparent huge page). + +However, if there is a racing munlock(), since mlock_vma_pages_range() starts +munlocking by clearing VM_LOCKED from a VMA, before munlocking all the pages +present, if one of those pages were unmapped by truncation or hole punch before +mlock_pte_range() reached it, it would not be recognized as mlocked by this VMA, +and would not be counted out of mlock_count. In this rare case, a page may +still appear as PageMlocked after it has been fully unmapped: and it is left to +release_pages() (or __page_cache_release()) to clear it and update statistics +before freeing (this event is counted in /proc/vmstat unevictable_pgs_cleared, +which is usually 0). Page Reclaim in shrink_*_list() ------------------------------- -shrink_active_list() culls any obviously unevictable pages - i.e. -!page_evictable(page) - diverting these to the unevictable list. +vmscan's shrink_active_list() culls any obviously unevictable pages - +i.e. !page_evictable(page) pages - diverting those to the unevictable list. However, shrink_active_list() only sees unevictable pages that made it onto the -active/inactive lru lists. Note that these pages do not have PageUnevictable -set - otherwise they would be on the unevictable list and shrink_active_list +active/inactive LRU lists. Note that these pages do not have PageUnevictable +set - otherwise they would be on the unevictable list and shrink_active_list() would never see them. Some examples of these unevictable pages on the LRU lists are: @@ -586,20 +540,15 @@ Some examples of these unevictable pages on the LRU lists are: when an application accesses the page the first time after SHM_LOCK'ing the segment. - (3) mlocked pages that could not be isolated from the LRU and moved to the - unevictable list in mlock_vma_page(). - -shrink_inactive_list() also diverts any unevictable pages that it finds on the -inactive lists to the appropriate node's unevictable list. + (3) pages still mapped into VM_LOCKED VMAs, which should be marked mlocked, + but events left mlock_count too low, so they were munlocked too early. -shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd -after shrink_active_list() had moved them to the inactive list, or pages mapped -into VM_LOCKED VMAs that munlock_vma_page() couldn't isolate from the LRU to -recheck via page_mlock(). shrink_inactive_list() won't notice the latter, -but will pass on to shrink_page_list(). +vmscan's shrink_inactive_list() and shrink_page_list() also divert obviously +unevictable pages found on the inactive lists to the appropriate memory cgroup +and node unevictable list. -shrink_page_list() again culls obviously unevictable pages that it could -encounter for similar reason to shrink_inactive_list(). Pages mapped into -VM_LOCKED VMAs but without PG_mlocked set will make it all the way to -try_to_unmap(). shrink_page_list() will divert them to the unevictable list -when try_to_unmap() returns SWAP_MLOCK, as discussed above. +rmap's page_referenced_one(), called via vmscan's shrink_active_list() or +shrink_page_list(), and rmap's try_to_unmap_one() called via shrink_page_list(), +check for (3) pages still mapped into VM_LOCKED VMAs, and call mlock_vma_page() +to correct them. Such pages are culled to the unevictable list when released +by the shrinker. diff --git a/MAINTAINERS b/MAINTAINERS index cf896438366b..3c0f56b44c61 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -201,6 +201,7 @@ F: include/net/ieee80211_radiotap.h F: include/net/iw_handler.h F: include/net/wext.h F: include/uapi/linux/nl80211.h +F: include/uapi/linux/wireless.h F: net/wireless/ 8169 10/100/1000 GIGABIT ETHERNET DRIVER @@ -2636,7 +2637,7 @@ F: sound/soc/rockchip/ N: rockchip ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org @@ -3742,7 +3743,7 @@ F: include/linux/platform_data/b53.h BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Nicolas Saenz Julienne <nsaenz@kernel.org> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -3757,7 +3758,7 @@ BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained T: git git://github.com/broadcom/mach-bcm F: arch/arm/mach-bcm/ @@ -3777,7 +3778,7 @@ F: arch/mips/include/asm/mach-bcm47xx/* BROADCOM BCM4908 ETHERNET DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml @@ -3786,7 +3787,7 @@ F: drivers/net/ethernet/broadcom/unimac.h BROADCOM BCM4908 PINMUX DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-gpio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pinctrl/brcm,bcm4908-pinctrl.yaml @@ -3796,7 +3797,7 @@ BROADCOM BCM5301X ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Hauke Mehrtens <hauke@hauke-m.de> M: Rafał Miłecki <zajec5@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/bcm470* @@ -3807,7 +3808,7 @@ F: arch/arm/mach-bcm/bcm_5301x.c BROADCOM BCM53573 ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Rafał Miłecki <rafal@milecki.pl> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/bcm47189* @@ -3815,7 +3816,7 @@ F: arch/arm/boot/dts/bcm53573* BROADCOM BCM63XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3829,7 +3830,7 @@ F: drivers/usb/gadget/udc/bcm63xx_udc.* BROADCOM BCM7XXX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3847,21 +3848,21 @@ N: bcm7120 BROADCOM BDC DRIVER M: Al Cooper <alcooperx@gmail.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bdc.yaml F: drivers/usb/gadget/udc/bdc/ BROADCOM BMIPS CPUFREQ DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mips@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3927,53 +3928,53 @@ F: drivers/net/wireless/broadcom/brcm80211/ BROADCOM BRCMSTB GPIO DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml F: drivers/gpio/gpio-brcmstb.c BROADCOM BRCMSTB I2C DRIVER M: Kamal Dasu <kdasu.kdev@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-i2c@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Supported F: Documentation/devicetree/bindings/i2c/brcm,brcmstb-i2c.yaml F: drivers/i2c/busses/i2c-brcmstb.c BROADCOM BRCMSTB UART DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-serial@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml F: drivers/tty/serial/8250/8250_bcm7271.c BROADCOM BRCMSTB USB EHCI DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml F: drivers/usb/host/ehci-brcm.* BROADCOM BRCMSTB USB PIN MAP DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/usb/brcm,usb-pinmap.yaml F: drivers/usb/misc/brcmstb-usb-pinmap.c BROADCOM BRCMSTB USB2 and USB3 PHY DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-kernel@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/phy/broadcom/phy-brcm-usb* BROADCOM ETHERNET PHY DRIVERS M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt @@ -3984,7 +3985,7 @@ F: include/linux/brcmphy.h BROADCOM GENET ETHERNET DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml @@ -3998,7 +3999,7 @@ F: include/linux/platform_data/mdio-bcm-unimac.h BROADCOM IPROC ARM ARCHITECTURE M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -4026,7 +4027,7 @@ N: stingray BROADCOM IPROC GBIT ETHERNET DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/brcm,amac.yaml @@ -4035,7 +4036,7 @@ F: drivers/net/ethernet/broadcom/unimac.h BROADCOM KONA GPIO DRIVER M: Ray Jui <rjui@broadcom.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt F: drivers/gpio/gpio-bcm-kona.c @@ -4068,7 +4069,7 @@ F: drivers/firmware/broadcom/* BROADCOM PMB (POWER MANAGEMENT BUS) DRIVER M: Rafał Miłecki <rafal@milecki.pl> M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -4084,7 +4085,7 @@ F: include/linux/bcma/ BROADCOM SPI DRIVER M: Kamal Dasu <kdasu.kdev@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained F: Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.yaml F: drivers/spi/spi-bcm-qspi.* @@ -4093,7 +4094,7 @@ F: drivers/spi/spi-iproc-qspi.c BROADCOM STB AVS CPUFREQ DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt @@ -4101,7 +4102,7 @@ F: drivers/cpufreq/brcmstb* BROADCOM STB AVS TMON DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/thermal/brcm,avs-tmon.yaml @@ -4109,7 +4110,7 @@ F: drivers/thermal/broadcom/brcmstb* BROADCOM STB DPFE DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml @@ -4118,8 +4119,8 @@ F: drivers/memory/brcmstb_dpfe.c BROADCOM STB NAND FLASH DRIVER M: Brian Norris <computersforpeace@gmail.com> M: Kamal Dasu <kdasu.kdev@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mtd@lists.infradead.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mtd/nand/raw/brcmnand/ F: include/linux/platform_data/brcmnand.h @@ -4128,7 +4129,7 @@ BROADCOM STB PCIE DRIVER M: Jim Quinlan <jim2101024@gmail.com> M: Nicolas Saenz Julienne <nsaenz@kernel.org> M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml @@ -4136,7 +4137,7 @@ F: drivers/pci/controller/pcie-brcmstb.c BROADCOM SYSTEMPORT ETHERNET DRIVER M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bcmsysport.* @@ -4153,7 +4154,7 @@ F: drivers/net/ethernet/broadcom/tg3.* BROADCOM VK DRIVER M: Scott Branden <scott.branden@broadcom.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: drivers/misc/bcm-vk/ F: include/uapi/linux/misc/bcm_vk.h @@ -4640,6 +4641,7 @@ F: drivers/input/touchscreen/chipone_icn8505.c CHROME HARDWARE PLATFORM SUPPORT M: Benson Leung <bleung@chromium.org> +L: chrome-platform@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chrome-platform/linux.git F: drivers/platform/chrome/ @@ -4648,6 +4650,7 @@ CHROMEOS EC CODEC DRIVER M: Cheng-Yi Chiang <cychiang@chromium.org> M: Tzung-Bi Shih <tzungbi@google.com> R: Guenter Roeck <groeck@chromium.org> +L: chrome-platform@lists.linux.dev S: Maintained F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml F: sound/soc/codecs/cros_ec_codec.* @@ -4655,6 +4658,7 @@ F: sound/soc/codecs/cros_ec_codec.* CHROMEOS EC SUBDRIVERS M: Benson Leung <bleung@chromium.org> R: Guenter Roeck <groeck@chromium.org> +L: chrome-platform@lists.linux.dev S: Maintained F: drivers/power/supply/cros_usbpd-charger.c N: cros_ec @@ -4662,11 +4666,13 @@ N: cros-ec CHROMEOS EC USB TYPE-C DRIVER M: Prashant Malani <pmalani@chromium.org> +L: chrome-platform@lists.linux.dev S: Maintained F: drivers/platform/chrome/cros_ec_typec.c CHROMEOS EC USB PD NOTIFY DRIVER M: Prashant Malani <pmalani@chromium.org> +L: chrome-platform@lists.linux.dev S: Maintained F: drivers/platform/chrome/cros_usbpd_notify.c F: include/linux/platform_data/cros_usbpd_notify.h @@ -4786,6 +4792,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> M: Nick Desaulniers <ndesaulniers@google.com> +R: Tom Rix <trix@redhat.com> L: llvm@lists.linux.dev S: Supported W: https://clangbuiltlinux.github.io/ @@ -5157,6 +5164,20 @@ S: Supported F: drivers/cpuidle/cpuidle-psci.h F: drivers/cpuidle/cpuidle-psci-domain.c +CPUIDLE DRIVER - DT IDLE PM DOMAIN +M: Ulf Hansson <ulf.hansson@linaro.org> +L: linux-pm@vger.kernel.org +S: Supported +F: drivers/cpuidle/dt_idle_genpd.c +F: drivers/cpuidle/dt_idle_genpd.h + +CPUIDLE DRIVER - RISC-V SBI +M: Anup Patel <anup@brainfault.org> +L: linux-pm@vger.kernel.org +L: linux-riscv@lists.infradead.org +S: Maintained +F: drivers/cpuidle/cpuidle-riscv-sbi.c + CRAMFS FILESYSTEM M: Nicolas Pitre <nico@fluxnic.net> S: Maintained @@ -5696,7 +5717,7 @@ W: http://lanana.org/docs/device-list/index.html DEVICE RESOURCE MANAGEMENT HELPERS M: Hans de Goede <hdegoede@redhat.com> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Maintained F: include/linux/devm-helpers.h @@ -6038,6 +6059,7 @@ F: drivers/scsi/dpt/ DRBD DRIVER M: Philipp Reisner <philipp.reisner@linbit.com> M: Lars Ellenberg <lars.ellenberg@linbit.com> +M: Christoph Böhmwalder <christoph.boehmwalder@linbit.com> L: drbd-dev@lists.linbit.com S: Supported W: http://www.drbd.org @@ -8655,7 +8677,6 @@ F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h HFI1 DRIVER -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported @@ -9316,14 +9337,12 @@ F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver M: Dany Madden <drt@linux.ibm.com> -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* IBM Power Virtual Accelerator Switchboard -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported F: arch/powerpc/include/asm/vas.h @@ -9517,6 +9536,12 @@ M: Stanislaw Gruszka <stf_xl@wp.pl> S: Maintained F: drivers/usb/atm/ueagle-atm.c +IMAGIS TOUCHSCREEN DRIVER +M: Markuss Broks <markuss.broks@gmail.com> +S: Maintained +F: Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml +F: drivers/input/touchscreen/imagis.c + IMGTEC ASCII LCD DRIVER M: Paul Burton <paulburton@kernel.org> S: Maintained @@ -9572,6 +9597,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Jason Gunthorpe <jgg@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -10343,6 +10369,7 @@ F: include/linux/isapnp.h ISCSI M: Lee Duncan <lduncan@suse.com> M: Chris Leech <cleech@redhat.com> +M: Mike Christie <michael.christie@oracle.com> L: open-iscsi@googlegroups.com L: linux-scsi@vger.kernel.org S: Maintained @@ -10648,9 +10675,9 @@ F: tools/testing/selftests/ KERNEL SMB3 SERVER (KSMBD) M: Namjae Jeon <linkinjeon@kernel.org> -M: Sergey Senozhatsky <senozhatsky@chromium.org> M: Steve French <sfrench@samba.org> M: Hyunchul Lee <hyc.lee@gmail.com> +R: Sergey Senozhatsky <senozhatsky@chromium.org> L: linux-cifs@vger.kernel.org S: Maintained T: git git://git.samba.org/ksmbd.git @@ -11182,7 +11209,7 @@ F: scripts/spdxcheck.py LINEAR RANGES HELPERS M: Mark Brown <broonie@kernel.org> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: lib/linear_ranges.c F: lib/test_linear_ranges.c F: include/linux/linear_range.h @@ -11879,7 +11906,7 @@ F: drivers/iio/proximity/mb1232.c MAXIM MAX17040 FAMILY FUEL GAUGE DRIVERS R: Iskren Chernev <iskren.chernev@gmail.com> -R: Krzysztof Kozlowski <krzk@kernel.org> +R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Matheus Castello <matheus@castello.eng.br> L: linux-pm@vger.kernel.org @@ -11889,7 +11916,7 @@ F: drivers/power/supply/max17040_battery.c MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS R: Hans de Goede <hdegoede@redhat.com> -R: Krzysztof Kozlowski <krzk@kernel.org> +R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm> R: Purism Kernel Team <kernel@puri.sm> @@ -11941,7 +11968,7 @@ F: Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml F: drivers/power/supply/max77976_charger.c MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-pm@vger.kernel.org S: Supported @@ -11952,7 +11979,7 @@ F: drivers/power/supply/max77693_charger.c MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS M: Chanwoo Choi <cw00.choi@samsung.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org S: Supported @@ -12375,7 +12402,7 @@ F: drivers/mmc/host/mtk-sd.c MEDIATEK MT76 WIRELESS LAN DRIVER M: Felix Fietkau <nbd@nbd.name> -M: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com> +M: Lorenzo Bianconi <lorenzo@kernel.org> M: Ryder Lee <ryder.lee@mediatek.com> R: Shayne Chen <shayne.chen@mediatek.com> R: Sean Wang <sean.wang@mediatek.com> @@ -12646,7 +12673,7 @@ F: mm/memblock.c F: tools/testing/memblock/ MEMORY CONTROLLER DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl.git @@ -13597,6 +13624,7 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13644,6 +13672,7 @@ F: tools/testing/selftests/drivers/net/dsa/ NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13790,10 +13819,11 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-nfc@lists.01.org (subscribers-only) L: netdev@vger.kernel.org S: Maintained +B: mailto:linux-nfc@lists.01.org F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -14107,7 +14137,7 @@ F: Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml F: drivers/regulator/pf8x00-regulator.c NXP PTN5150A CC LOGIC AND EXTCON DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/extcon/extcon-ptn5150.yaml @@ -14622,9 +14652,14 @@ L: op-tee@lists.trustedfirmware.org S: Maintained F: drivers/char/hw_random/optee-rng.c +OP-TEE RTC DRIVER +M: Clément Léger <clement.leger@bootlin.com> +L: linux-rtc@vger.kernel.org +S: Maintained +F: drivers/rtc/rtc-optee.c + OPA-VNIC DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/ulp/opa_vnic @@ -14655,7 +14690,7 @@ F: scripts/dtc/ OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring <robh+dt@kernel.org> -M: Krzysztof Kozlowski <krzk+dt@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org> L: devicetree@vger.kernel.org S: Maintained C: irc://irc.libera.chat/devicetree @@ -15567,7 +15602,7 @@ F: drivers/pinctrl/renesas/ PIN CONTROLLER - SAMSUNG M: Tomasz Figa <tomasz.figa@gmail.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -16066,7 +16101,6 @@ F: include/uapi/linux/qemu_fw_cfg.h QIB DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qib/ @@ -16584,7 +16618,6 @@ F: drivers/net/ethernet/rdc/r6040.c RDMAVT - RDMA verbs software M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rdmavt @@ -16979,8 +17012,7 @@ S: Odd Fixes F: drivers/tty/serial/rp2.* ROHM BD99954 CHARGER IC -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/power/supply/bd99954-charger.c F: drivers/power/supply/bd99954-charger.h @@ -17003,8 +17035,7 @@ F: drivers/regulator/bd9571mwv-regulator.c F: include/linux/mfd/bd9571mwv.h ROHM POWER MANAGEMENT IC DEVICE DRIVERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/clk/clk-bd718x7.c F: drivers/gpio/gpio-bd71815.c @@ -17246,7 +17277,7 @@ W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/scsi/zfcp_* S3C ADC BATTERY DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-samsung-soc@vger.kernel.org S: Odd Fixes F: drivers/power/supply/s3c_adc_battery.c @@ -17291,7 +17322,7 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported @@ -17299,7 +17330,7 @@ F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17334,7 +17365,7 @@ S: Maintained F: drivers/platform/x86/samsung-laptop.c SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17360,7 +17391,7 @@ F: drivers/media/platform/samsung/s3c-camif/ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Krzysztof Opasiak <k.opasiak@samsung.com> L: linux-nfc@lists.01.org (subscribers-only) S: Maintained @@ -17382,7 +17413,7 @@ S: Supported F: drivers/media/i2c/s5k5baf.c SAMSUNG S5P Security SubSystem (SSS) DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Vladimir Zapolskiy <vz@mleia.com> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17417,7 +17448,7 @@ F: include/linux/clk/samsung.h F: include/linux/platform_data/clk-s3c2410.h SAMSUNG SPI DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Andi Shyti <andi@etezian.org> L: linux-spi@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17435,7 +17466,7 @@ F: drivers/net/ethernet/samsung/sxgbe/ SAMSUNG THERMAL DRIVER M: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17619,8 +17650,8 @@ K: \bTIF_SECCOMP\b SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) Broadcom BRCMSTB DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mmc@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mmc/host/sdhci-brcmstb* @@ -20539,14 +20570,15 @@ F: Documentation/admin-guide/media/zr364xx* F: drivers/media/usb/zr364xx/ USER-MODE LINUX (UML) -M: Jeff Dike <jdike@addtoit.com> M: Richard Weinberger <richard@nod.at> M: Anton Ivanov <anton.ivanov@cambridgegreys.com> +M: Johannes Berg <johannes@sipsolutions.net> L: linux-um@lists.infradead.org S: Maintained W: http://user-mode-linux.sourceforge.net Q: https://patchwork.ozlabs.org/project/linux-um/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux.git fixes F: Documentation/virt/uml/ F: arch/um/ F: arch/x86/um/ @@ -21085,7 +21117,7 @@ F: include/linux/regulator/ K: regulator_get_optional VOLTAGE AND CURRENT REGULATOR IRQ HELPERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: drivers/regulator/irq_helpers.c VRF @@ -21198,10 +21230,8 @@ S: Maintained F: drivers/hid/hid-wiimote* WILOCITY WIL6210 WIRELESS DRIVER -M: Maya Erez <merez@codeaurora.org> L: linux-wireless@vger.kernel.org -L: wil6210@qti.qualcomm.com -S: Supported +S: Orphan W: https://wireless.wiki.kernel.org/en/users/Drivers/wil6210 F: drivers/net/wireless/ath/wil6210/ @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 -PATCHLEVEL = 17 +PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc3 NAME = Superb Owl # *DOCUMENTATION* @@ -424,19 +424,26 @@ HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null) HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null) ifneq ($(LLVM),) -HOSTCC = clang -HOSTCXX = clang++ +ifneq ($(filter %/,$(LLVM)),) +LLVM_PREFIX := $(LLVM) +else ifneq ($(filter -%,$(LLVM)),) +LLVM_SUFFIX := $(LLVM) +endif + +HOSTCC = $(LLVM_PREFIX)clang$(LLVM_SUFFIX) +HOSTCXX = $(LLVM_PREFIX)clang++$(LLVM_SUFFIX) else HOSTCC = gcc HOSTCXX = g++ endif -export KBUILD_USERCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ - -O2 -fomit-frame-pointer -std=gnu11 \ - -Wdeclaration-after-statement -export KBUILD_USERLDFLAGS := +KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ + -O2 -fomit-frame-pointer -std=gnu11 \ + -Wdeclaration-after-statement +KBUILD_USERCFLAGS := $(KBUILD_USERHOSTCFLAGS) $(USERCFLAGS) +KBUILD_USERLDFLAGS := $(USERLDFLAGS) -KBUILD_HOSTCFLAGS := $(KBUILD_USERCFLAGS) $(HOST_LFS_CFLAGS) $(HOSTCFLAGS) +KBUILD_HOSTCFLAGS := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) $(HOSTCFLAGS) KBUILD_HOSTCXXFLAGS := -Wall -O2 $(HOST_LFS_CFLAGS) $(HOSTCXXFLAGS) KBUILD_HOSTLDFLAGS := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS) KBUILD_HOSTLDLIBS := $(HOST_LFS_LIBS) $(HOSTLDLIBS) @@ -444,14 +451,14 @@ KBUILD_HOSTLDLIBS := $(HOST_LFS_LIBS) $(HOSTLDLIBS) # Make variables (CC, etc...) CPP = $(CC) -E ifneq ($(LLVM),) -CC = clang -LD = ld.lld -AR = llvm-ar -NM = llvm-nm -OBJCOPY = llvm-objcopy -OBJDUMP = llvm-objdump -READELF = llvm-readelf -STRIP = llvm-strip +CC = $(LLVM_PREFIX)clang$(LLVM_SUFFIX) +LD = $(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX) +AR = $(LLVM_PREFIX)llvm-ar$(LLVM_SUFFIX) +NM = $(LLVM_PREFIX)llvm-nm$(LLVM_SUFFIX) +OBJCOPY = $(LLVM_PREFIX)llvm-objcopy$(LLVM_SUFFIX) +OBJDUMP = $(LLVM_PREFIX)llvm-objdump$(LLVM_SUFFIX) +READELF = $(LLVM_PREFIX)llvm-readelf$(LLVM_SUFFIX) +STRIP = $(LLVM_PREFIX)llvm-strip$(LLVM_SUFFIX) else CC = $(CROSS_COMPILE)gcc LD = $(CROSS_COMPILE)ld @@ -531,6 +538,7 @@ export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AW export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE +export KBUILD_USERCFLAGS KBUILD_USERLDFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE @@ -785,10 +793,6 @@ ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += -Qunused-arguments # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable. KBUILD_CFLAGS += -Wno-gnu -# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the -# source of a reference will be _MergedGlobals and not on of the whitelisted names. -# See modpost pattern 2 -KBUILD_CFLAGS += -mno-global-merge else # gcc inanely warns about local variables called 'main' @@ -1237,8 +1241,8 @@ define filechk_version.h echo \#define LINUX_VERSION_SUBLEVEL $(SUBLEVEL) endef -$(version_h): PATCHLEVEL := $(if $(PATCHLEVEL), $(PATCHLEVEL), 0) -$(version_h): SUBLEVEL := $(if $(SUBLEVEL), $(SUBLEVEL), 0) +$(version_h): PATCHLEVEL := $(or $(PATCHLEVEL), 0) +$(version_h): SUBLEVEL := $(or $(SUBLEVEL), 0) $(version_h): FORCE $(call filechk,version.h) @@ -1621,7 +1625,7 @@ help: @$(MAKE) -f $(srctree)/Documentation/Makefile dochelp @echo '' @echo 'Architecture specific targets ($(SRCARCH)):' - @$(if $(archhelp),$(archhelp),\ + @$(or $(archhelp),\ echo ' No architecture specific help defined for $(SRCARCH)') @echo '' @$(if $(boards), \ @@ -1838,7 +1842,7 @@ $(clean-dirs): clean: $(clean-dirs) $(call cmd,rmfiles) - @find $(if $(KBUILD_EXTMOD), $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \ + @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \ \( -name '*.[aios]' -o -name '*.ko' -o -name '.*.cmd' \ -o -name '*.ko.*' \ -o -name '*.dtb' -o -name '*.dtbo' -o -name '*.dtb.S' -o -name '*.dt.yaml' \ diff --git a/arch/Kconfig b/arch/Kconfig index 29b0167c088b..31c4fdc4a4ba 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -854,10 +854,8 @@ config HAVE_ARCH_HUGE_VMAP # # Archs that select this would be capable of PMD-sized vmaps (i.e., -# arch_vmap_pmd_supported() returns true), and they must make no assumptions -# that vmalloc memory is mapped with PAGE_SIZE ptes. The VM_NO_HUGE_VMAP flag -# can be used to prohibit arch-specific allocations from using hugepages to -# help with this (e.g., modules may require it). +# arch_vmap_pmd_supported() returns true). The VM_ALLOW_HUGE_VMAP flag +# must be used to enable allocations to use hugepages. # config HAVE_ARCH_HUGE_VMALLOC depends on HAVE_ARCH_HUGE_VMAP diff --git a/arch/alpha/include/asm/user.h b/arch/alpha/include/asm/user.h index 3df37492c7b7..c9f525a6aab8 100644 --- a/arch/alpha/include/asm/user.h +++ b/arch/alpha/include/asm/user.h @@ -45,10 +45,4 @@ struct user { char u_comm[32]; /* user command name */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_DATA_START_ADDR (u.start_data) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) - #endif /* _ALPHA_USER_H */ diff --git a/arch/alpha/kernel/syscalls/Makefile b/arch/alpha/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/alpha/kernel/syscalls/Makefile +++ b/arch/alpha/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 187a187706cb..41bcbb460fac 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -92,6 +92,8 @@ ifeq ($(CONFIG_USE_OF),y) OBJS += $(libfdt_objs) fdt_check_mem_start.o endif +OBJS += lib1funcs.o ashldi3.o bswapsdi2.o + targets := vmlinux vmlinux.lds piggy_data piggy.o \ head.o $(OBJS) @@ -126,8 +128,6 @@ endif # Next argument is a linker script LDFLAGS_vmlinux += -T -OBJS += lib1funcs.o ashldi3.o bswapsdi2.o - # We need to prevent any GOTOFF relocs being used with references # to symbols in the .bss section since we cannot relocate them # independently from the rest at run time. This can be achieved by diff --git a/arch/arm/boot/dts/at91-kizbox3-hs.dts b/arch/arm/boot/dts/at91-kizbox3-hs.dts index 2799b2a1f4d2..f7d90cf1bb77 100644 --- a/arch/arm/boot/dts/at91-kizbox3-hs.dts +++ b/arch/arm/boot/dts/at91-kizbox3-hs.dts @@ -225,7 +225,7 @@ pinctrl_pio_io_reset: gpio_io_reset { pinmux = <PIN_PB30__GPIO>; bias-disable; - drive-open-drain = <1>; + drive-open-drain; output-low; }; pinctrl_pio_input: gpio_input { diff --git a/arch/arm/boot/dts/at91-kizbox3_common.dtsi b/arch/arm/boot/dts/at91-kizbox3_common.dtsi index abe27adfa4d6..465664628419 100644 --- a/arch/arm/boot/dts/at91-kizbox3_common.dtsi +++ b/arch/arm/boot/dts/at91-kizbox3_common.dtsi @@ -211,7 +211,7 @@ pinmux = <PIN_PD12__FLEXCOM4_IO0>, //DATA <PIN_PD13__FLEXCOM4_IO1>; //CLK bias-disable; - drive-open-drain = <1>; + drive-open-drain; }; pinctrl_pwm0 { diff --git a/arch/arm/boot/dts/at91-sam9_l9260.dts b/arch/arm/boot/dts/at91-sam9_l9260.dts index 1e2a28c2f365..2fb51b9aca2a 100644 --- a/arch/arm/boot/dts/at91-sam9_l9260.dts +++ b/arch/arm/boot/dts/at91-sam9_l9260.dts @@ -101,7 +101,7 @@ nand0: nand@40000000 { nand-bus-width = <8>; nand-ecc-mode = "soft"; - nand-on-flash-bbt = <1>; + nand-on-flash-bbt; status = "okay"; }; diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts index 87c517d65f62..e9aecac4f5b5 100644 --- a/arch/arm/boot/dts/da850-evm.dts +++ b/arch/arm/boot/dts/da850-evm.dts @@ -278,7 +278,7 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&spi1_pins &spi1_cs0_pin>; - flash: m25p80@0 { + flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts index 5126e2d72ed7..778796c10af8 100644 --- a/arch/arm/boot/dts/dm8168-evm.dts +++ b/arch/arm/boot/dts/dm8168-evm.dts @@ -177,7 +177,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mcspi1_pins>; - m25p80@0 { + flash@0 { compatible = "w25x32"; spi-max-frequency = <48000000>; reg = <0>; diff --git a/arch/arm/boot/dts/imx28-ts4600.dts b/arch/arm/boot/dts/imx28-ts4600.dts index 097ec35c62d8..0d58da1c0cc5 100644 --- a/arch/arm/boot/dts/imx28-ts4600.dts +++ b/arch/arm/boot/dts/imx28-ts4600.dts @@ -26,7 +26,7 @@ pinctrl-0 = <&mmc0_4bit_pins_a &mmc0_sck_cfg &en_sd_pwr>; - broken-cd = <1>; + broken-cd; bus-width = <4>; vmmc-supply = <®_vddio_sd0>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi index 563bf9d44fe0..0b90c3f59f89 100644 --- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi @@ -154,112 +154,112 @@ regulators { bcore1 { regulator-name = "bcore1"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bcore2 { regulator-name = "bcore2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bpro { regulator-name = "bpro"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bperi { regulator-name = "bperi"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bmem { regulator-name = "bmem"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo2 { regulator-name = "ldo2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1800000>; }; ldo3 { regulator-name = "ldo3"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo4 { regulator-name = "ldo4"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo5 { regulator-name = "ldo5"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo6 { regulator-name = "ldo6"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo7 { regulator-name = "ldo7"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo8 { regulator-name = "ldo8"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo9 { regulator-name = "ldo9"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo10 { regulator-name = "ldo10"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo11 { regulator-name = "ldo11"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bio { regulator-name = "bio"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi index 7cda6944501d..205e4d462702 100644 --- a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi +++ b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi @@ -72,8 +72,8 @@ st,settling = <2>; st,fraction-z = <7>; st,i-drive = <1>; - touchscreen-inverted-x = <1>; - touchscreen-inverted-y = <1>; + touchscreen-inverted-x; + touchscreen-inverted-y; }; }; }; diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index b4664ab00256..d3da8b1b473b 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -118,8 +118,8 @@ gpmc,device-width = <2>; gpmc,wait-pin = <0>; gpmc,burst-length = <4>; - gpmc,cycle2cycle-samecsen = <1>; - gpmc,cycle2cycle-diffcsen = <1>; + gpmc,cycle2cycle-samecsen; + gpmc,cycle2cycle-diffcsen; gpmc,cs-on-ns = <0>; gpmc,cs-rd-off-ns = <45>; gpmc,cs-wr-off-ns = <45>; diff --git a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi index cbe42c4153a0..b4d286a6fab1 100644 --- a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi @@ -76,7 +76,7 @@ pinconf { pins = "gpio20", "gpio21"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -116,7 +116,7 @@ pinconf { pins = "gpio24", "gpio25"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -141,7 +141,7 @@ pinconf { pins = "gpio8", "gpio9"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -166,7 +166,7 @@ pinconf { pins = "gpio12", "gpio13"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -229,7 +229,7 @@ pinconf { pins = "gpio16", "gpio17"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -282,7 +282,7 @@ pinconf { pins = "gpio84", "gpio85"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi index 996f4458d9fc..8cb04aa8ed2f 100644 --- a/arch/arm/boot/dts/qcom-ipq8064.dtsi +++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi @@ -972,7 +972,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -996,7 +996,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1020,7 +1020,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1044,7 +1044,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts index 4cbadcb41084..ddd1cf4d0554 100644 --- a/arch/arm/boot/dts/spear1310-evb.dts +++ b/arch/arm/boot/dts/spear1310-evb.dts @@ -379,7 +379,7 @@ }; }; - m25p80@1 { + flash@1 { compatible = "st,m25p80"; reg = <1>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts index fd194ebeedc9..3a51a41eb5e4 100644 --- a/arch/arm/boot/dts/spear1340-evb.dts +++ b/arch/arm/boot/dts/spear1340-evb.dts @@ -439,7 +439,7 @@ cs-gpios = <&gpiopinctrl 80 0>, <&gpiopinctrl 24 0>, <&gpiopinctrl 85 0>; - m25p80@0 { + flash@0 { compatible = "m25p80"; reg = <0>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi index 827e887afbda..13e1bdb3ddbf 100644 --- a/arch/arm/boot/dts/spear1340.dtsi +++ b/arch/arm/boot/dts/spear1340.dtsi @@ -134,9 +134,9 @@ reg = <0xb4100000 0x1000>; interrupts = <0 105 0x4>; status = "disabled"; - dmas = <&dwdma0 12 0 1>, - <&dwdma0 13 1 0>; - dma-names = "tx", "rx"; + dmas = <&dwdma0 13 0 1>, + <&dwdma0 12 1 0>; + dma-names = "rx", "tx"; }; thermal@e07008c4 { diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi index c87b881b2c8b..913553367687 100644 --- a/arch/arm/boot/dts/spear13xx.dtsi +++ b/arch/arm/boot/dts/spear13xx.dtsi @@ -284,9 +284,9 @@ #size-cells = <0>; interrupts = <0 31 0x4>; status = "disabled"; - dmas = <&dwdma0 4 0 0>, - <&dwdma0 5 0 0>; - dma-names = "tx", "rx"; + dmas = <&dwdma0 5 0 0>, + <&dwdma0 4 0 0>; + dma-names = "rx", "tx"; }; rtc@e0580000 { diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index 33ae5e0590df..ac53ee3c496b 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -398,7 +398,7 @@ #size-cells = <0>; status = "okay"; - flash0: is25lp016d@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <133000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index e222d2d2cb44..d142dd30e16b 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -262,7 +262,7 @@ #size-cells = <0>; status = "okay"; - flash0: mx66l51235l@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-rx-bus-width = <4>; @@ -271,7 +271,7 @@ #size-cells = <1>; }; - flash1: mx66l51235l@1 { + flash1: flash@1 { compatible = "jedec,spi-nor"; reg = <1>; spi-rx-bus-width = <4>; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index a7acfee11ffc..a80bc8a43091 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -49,11 +49,13 @@ CONFIG_ATA=y CONFIG_PATA_FTIDE010=y CONFIG_NETDEVICES=y CONFIG_TUN=y +CONFIG_NET_DSA_REALTEK=y CONFIG_NET_DSA_REALTEK_SMI=y +CONFIG_NET_DSA_REALTEK_RTL8366RB=y CONFIG_GEMINI_ETHERNET=y +CONFIG_MARVELL_PHY=y CONFIG_MDIO_BITBANG=y CONFIG_MDIO_GPIO=y -CONFIG_MARVELL_PHY=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -66,6 +68,7 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C_GPIO=y CONFIG_SPI=y CONFIG_SPI_GPIO=y +CONFIG_SENSORS_DRIVETEMP=y CONFIG_SENSORS_GPIO_FAN=y CONFIG_SENSORS_LM75=y CONFIG_THERMAL=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig deleted file mode 100644 index 015b7ef237de..000000000000 --- a/arch/arm/configs/imote2_defconfig +++ /dev/null @@ -1,365 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_RD_BZIP2=y -CONFIG_RD_LZMA=y -CONFIG_EXPERT=y -# CONFIG_COMPAT_BRK is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_MODVERSIONS=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_ARCH_PXA=y -CONFIG_MACH_INTELMOTE2=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y -CONFIG_AEABI=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="root=/dev/mtdblock2 rootfstype=jffs2 console=ttyS2,115200 mem=32M" -CONFIG_KEXEC=y -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_AOUT=m -CONFIG_BINFMT_MISC=m -CONFIG_PM=y -CONFIG_APM_EMULATION=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_IP_PNP_RARP=y -CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_DIAG is not set -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_MIP6=m -CONFIG_IPV6_TUNNEL=m -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_SUBTREES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_NETLINK_QUEUE=m -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_CONNTRACK_AMANDA=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_H323=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_NETBIOS_NS=m -CONFIG_NF_CONNTRACK_PPTP=m -CONFIG_NF_CONNTRACK_SANE=m -CONFIG_NF_CONNTRACK_SIP=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_LED=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_TIME=m -CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_AH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_MH=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_BRIDGE=m -# CONFIG_BRIDGE_IGMP_SNOOPING is not set -CONFIG_IEEE802154=y -# CONFIG_WIRELESS is not set -CONFIG_DEVTMPFS=y -CONFIG_DEVTMPFS_MOUNT=y -CONFIG_FW_LOADER=m -CONFIG_CONNECTOR=m -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_AFS_PARTS=y -CONFIG_MTD_AR7_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set -# CONFIG_MTD_CFI_I2 is not set -CONFIG_MTD_OTP=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PXA2XX=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_NETDEVICES=y -CONFIG_DUMMY=y -# CONFIG_WLAN is not set -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -# CONFIG_INPUT_MOUSEDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_KEYBOARD_ATKBD is not set -CONFIG_KEYBOARD_GPIO=y -CONFIG_KEYBOARD_PXA27x=y -# CONFIG_INPUT_MOUSE is not set -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_UINPUT=y -# CONFIG_SERIO is not set -CONFIG_SERIAL_PXA=y -CONFIG_SERIAL_PXA_CONSOLE=y -CONFIG_LEGACY_PTY_COUNT=8 -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_PXA=y -CONFIG_SPI=y -CONFIG_SPI_PXA2XX=y -CONFIG_GPIO_SYSFS=y -CONFIG_POWER_SUPPLY=y -# CONFIG_HWMON is not set -CONFIG_PMIC_DA903X=y -CONFIG_REGULATOR=y -CONFIG_REGULATOR_DEBUG=y -CONFIG_REGULATOR_DA903X=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_VIDEO_DEV=y -CONFIG_MEDIA_TUNER_CUSTOMISE=y -# CONFIG_MEDIA_TUNER_SIMPLE is not set -# CONFIG_MEDIA_TUNER_TDA8290 is not set -# CONFIG_MEDIA_TUNER_TDA827X is not set -# CONFIG_MEDIA_TUNER_TDA18271 is not set -# CONFIG_MEDIA_TUNER_TDA9887 is not set -# CONFIG_MEDIA_TUNER_TEA5761 is not set -# CONFIG_MEDIA_TUNER_TEA5767 is not set -# CONFIG_MEDIA_TUNER_MT20XX is not set -# CONFIG_MEDIA_TUNER_MT2060 is not set -# CONFIG_MEDIA_TUNER_MT2266 is not set -# CONFIG_MEDIA_TUNER_MT2131 is not set -# CONFIG_MEDIA_TUNER_QT1010 is not set -# CONFIG_MEDIA_TUNER_XC2028 is not set -# CONFIG_MEDIA_TUNER_XC5000 is not set -# CONFIG_MEDIA_TUNER_MXL5005S is not set -# CONFIG_MEDIA_TUNER_MXL5007T is not set -# CONFIG_MEDIA_TUNER_MC44S803 is not set -# CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set -CONFIG_VIDEO_PXA27x=y -# CONFIG_V4L_USB_DRIVERS is not set -# CONFIG_RADIO_ADAPTERS is not set -CONFIG_FB=y -CONFIG_FB_PXA=y -CONFIG_FB_PXA_OVERLAY=y -CONFIG_FB_PXA_PARAMETERS=y -# CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FONTS=y -CONFIG_FONT_MINI_4x6=y -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_MIXER_OSS=y -CONFIG_SND_PCM_OSS=y -# CONFIG_SND_DRIVERS is not set -# CONFIG_SND_ARM is not set -# CONFIG_SND_SPI is not set -# CONFIG_SND_USB is not set -CONFIG_SND_SOC=y -CONFIG_SND_PXA2XX_SOC=y -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_USB_PXA27X=y -CONFIG_USB_ETH=m -# CONFIG_USB_ETH_RNDIS is not set -CONFIG_MMC=y -CONFIG_SDIO_UART=m -CONFIG_MMC_PXA=y -CONFIG_MMC_SPI=y -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_LP3944=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_LEDS_TRIGGER_BACKLIGHT=y -CONFIG_LEDS_TRIGGER_GPIO=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_PXA=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=m -CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=m -CONFIG_CUSE=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_FS_WBUF_VERIFY=y -CONFIG_JFFS2_SUMMARY=y -CONFIG_JFFS2_FS_XATTR=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_JFFS2_LZO=y -CONFIG_JFFS2_RUBIN=y -CONFIG_CRAMFS=m -CONFIG_SQUASHFS=m -CONFIG_ROMFS_FS=m -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFSD=m -CONFIG_NFSD_V3_ACL=y -CONFIG_SMB_FS=m -CONFIG_CIFS=m -CONFIG_CIFS_STATS=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m -CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -# CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_PROVE_LOCKING=y -# CONFIG_FTRACE is not set -CONFIG_DEBUG_USER=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_GHASH=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_AES=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC16=y diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index 3b30913d7d8d..a352207a64d7 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -20,7 +20,6 @@ CONFIG_VFP=y CONFIG_NEON=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_CMA=y CONFIG_NET=y @@ -41,6 +40,8 @@ CONFIG_MAC80211_LEDS=y CONFIG_CAIF=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_GNSS=y +CONFIG_GNSS_SIRF_SERIAL=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_NETDEVICES=y @@ -83,6 +84,8 @@ CONFIG_SPI_GPIO=y CONFIG_SPI_PL022=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_TC3589X=y +CONFIG_BATTERY_SAMSUNG_SDI=y +CONFIG_AB8500_BM=y CONFIG_SENSORS_IIO_HWMON=y CONFIG_SENSORS_NTC_THERMISTOR=y CONFIG_THERMAL=y @@ -98,10 +101,13 @@ CONFIG_VIDEO_V4L2_SUBDEV_API=y CONFIG_V4L2_FLASH_LED_CLASS=y CONFIG_DRM=y CONFIG_DRM_PANEL_NOVATEK_NT35510=y +CONFIG_DRM_PANEL_NOVATEK_NT35560=y +CONFIG_DRM_PANEL_SAMSUNG_DB7430=y CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y +CONFIG_DRM_PANEL_SAMSUNG_S6D27A1=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0_DSI=y -CONFIG_DRM_PANEL_SONY_ACX424AKP=y +CONFIG_DRM_PANEL_WIDECHIPS_WS2401=y CONFIG_DRM_LIMA=y CONFIG_DRM_MCDE=y CONFIG_FB=y @@ -129,6 +135,7 @@ CONFIG_LEDS_LM3530=y CONFIG_LEDS_GPIO=y CONFIG_LEDS_LP55XX_COMMON=y CONFIG_LEDS_LP5521=y +CONFIG_LEDS_REGULATOR=y CONFIG_LEDS_RT8515=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_RTC_CLASS=y @@ -144,17 +151,22 @@ CONFIG_IIO_SW_TRIGGER=y CONFIG_BMA180=y CONFIG_BMC150_ACCEL=y CONFIG_IIO_ST_ACCEL_3AXIS=y +# CONFIG_IIO_ST_ACCEL_SPI_3AXIS is not set CONFIG_IIO_RESCALE=y CONFIG_MPU3050_I2C=y CONFIG_IIO_ST_GYRO_3AXIS=y +# CONFIG_IIO_ST_GYRO_SPI_3AXIS is not set CONFIG_INV_MPU6050_I2C=y CONFIG_BH1780=y CONFIG_GP2AP002=y +CONFIG_TSL2772=y CONFIG_AK8974=y CONFIG_IIO_ST_MAGN_3AXIS=y +# CONFIG_IIO_ST_MAGN_SPI_3AXIS is not set CONFIG_YAMAHA_YAS530=y CONFIG_IIO_HRTIMER_TRIGGER=y CONFIG_IIO_ST_PRESS=y +# CONFIG_IIO_ST_PRESS_SPI is not set CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -173,10 +185,9 @@ CONFIG_CRYPTO_DEV_UX500_CRYP=y CONFIG_CRYPTO_DEV_UX500_HASH=y CONFIG_CRYPTO_DEV_UX500_DEBUG=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_USER=y diff --git a/arch/arm/include/asm/user.h b/arch/arm/include/asm/user.h index c799a3c49342..167d44b550f4 100644 --- a/arch/arm/include/asm/user.h +++ b/arch/arm/include/asm/user.h @@ -77,10 +77,6 @@ struct user{ struct user_fp_struct * u_fp0;/* Used by gdb to help find the values for */ /* the FP registers. */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) /* * User specific VFP registers. If only VFPv2 is present, registers 16 to 31 diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 039feb7cd590..1e8a50a97edf 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1004,7 +1004,8 @@ static void __init reserve_crashkernel(void) total_mem = get_total_mem(); ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret) + /* invalid value specified or crashkernel=0 */ + if (ret || !crash_size) return; if (crash_base <= 0) { diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index b5efecb3d730..d0fa2037460a 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -54,17 +54,17 @@ int notrace unwind_frame(struct stackframe *frame) return -EINVAL; frame->sp = frame->fp; - frame->fp = *(unsigned long *)(fp); - frame->pc = *(unsigned long *)(fp + 4); + frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); + frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 4)); #else /* check current frame pointer is within bounds */ if (fp < low + 12 || fp > high - 4) return -EINVAL; /* restore the registers from the stack frame */ - frame->fp = *(unsigned long *)(fp - 12); - frame->sp = *(unsigned long *)(fp - 8); - frame->pc = *(unsigned long *)(fp - 4); + frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 12)); + frame->sp = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 8)); + frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 4)); #endif #ifdef CONFIG_KRETPROBES if (is_kretprobe_trampoline(frame->pc)) diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index 428012687a80..7f7f6bae21c2 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -1101,11 +1101,13 @@ static int __init da850_evm_config_emac(void) int ret; u32 val; struct davinci_soc_info *soc_info = &davinci_soc_info; - u8 rmii_en = soc_info->emac_pdata->rmii_en; + u8 rmii_en; if (!machine_is_davinci_da850_evm()) return 0; + rmii_en = soc_info->emac_pdata->rmii_en; + cfg_chip3_base = DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP3_REG); val = __raw_readl(cfg_chip3_base); diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index cc75087134d3..4fa6ea5461b7 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -148,8 +148,10 @@ static struct clk_hw *ep93xx_clk_register_gate(const char *name, psc->lock = &clk_lock; clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { kfree(psc); + return ERR_CAST(clk); + } return &psc->hw; } @@ -207,7 +209,7 @@ static int ep93xx_mux_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { unsigned long rate = req->rate; - struct clk *best_parent = 0; + struct clk *best_parent = NULL; unsigned long __parent_rate; unsigned long best_rate = 0, actual_rate, mclk_rate; unsigned long best_parent_rate; diff --git a/arch/arm/mach-iop32x/cp6.c b/arch/arm/mach-iop32x/cp6.c index 2882674a1c39..7135a0ac9949 100644 --- a/arch/arm/mach-iop32x/cp6.c +++ b/arch/arm/mach-iop32x/cp6.c @@ -7,6 +7,8 @@ #include <asm/traps.h> #include <asm/ptrace.h> +#include "iop3xx.h" + void iop_enable_cp6(void) { u32 temp; diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c index 0659ab4cb0af..11677fc2968f 100644 --- a/arch/arm/mach-omap2/omap-secure.c +++ b/arch/arm/mach-omap2/omap-secure.c @@ -59,8 +59,13 @@ static void __init omap_optee_init_check(void) u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs, u32 arg1, u32 arg2, u32 arg3, u32 arg4) { + static u32 buf[NR_CPUS][5]; + u32 *param; + int cpu; u32 ret; - u32 param[5]; + + cpu = get_cpu(); + param = buf[cpu]; param[0] = nargs; param[1] = arg1; @@ -76,6 +81,8 @@ u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs, u32 arg1, u32 arg2, outer_clean_range(__pa(param), __pa(param + 5)); ret = omap_smc2(idx, flag, __pa(param)); + put_cpu(); + return ret; } @@ -119,8 +126,8 @@ phys_addr_t omap_secure_ram_mempool_base(void) #if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM) u32 omap3_save_secure_ram(void __iomem *addr, int size) { + static u32 param[5]; u32 ret; - u32 param[5]; if (size != OMAP3_SAVE_SECURE_RAM_SZ) return OMAP3_SAVE_SECURE_RAM_SZ; @@ -153,8 +160,8 @@ u32 omap3_save_secure_ram(void __iomem *addr, int size) u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs, u32 arg1, u32 arg2, u32 arg3, u32 arg4) { + static u32 param[5]; u32 ret; - u32 param[5]; param[0] = nargs+1; /* RX-51 needs number of arguments + 1 */ param[1] = arg1; diff --git a/arch/arm/mach-s3c/mach-jive.c b/arch/arm/mach-s3c/mach-jive.c index 285e1f0f4145..0d7d408c3729 100644 --- a/arch/arm/mach-s3c/mach-jive.c +++ b/arch/arm/mach-s3c/mach-jive.c @@ -236,11 +236,11 @@ static int __init jive_mtdset(char *options) unsigned long set; if (options == NULL || options[0] == '\0') - return 0; + return 1; if (kstrtoul(options, 10, &set)) { printk(KERN_ERR "failed to parse mtdset=%s\n", options); - return 0; + return 1; } switch (set) { @@ -256,7 +256,7 @@ static int __init jive_mtdset(char *options) "using default.", set); } - return 0; + return 1; } /* parse the mtdset= option given to the kernel command line */ diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 1da11bdb1dfb..6e6985e756af 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -122,13 +122,13 @@ static inline bool cluster_is_a15(u32 cluster) } /** - * ve_spc_global_wakeup_irq() + * ve_spc_global_wakeup_irq() - sets/clears global wakeup IRQs + * + * @set: if true, global wake-up IRQs are set, if false they are cleared * * Function to set/clear global wakeup IRQs. Not protected by locking since * it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @set: if true, global wake-up IRQs are set, if false they are cleared */ void ve_spc_global_wakeup_irq(bool set) { @@ -145,15 +145,15 @@ void ve_spc_global_wakeup_irq(bool set) } /** - * ve_spc_cpu_wakeup_irq() - * - * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since - * it might be used in code paths where normal cacheable locks are not - * working. Locking must be provided by the caller to ensure atomicity. + * ve_spc_cpu_wakeup_irq() - sets/clears per-CPU wake-up IRQs * * @cluster: mpidr[15:8] bitfield describing cluster affinity level * @cpu: mpidr[7:0] bitfield describing cpu affinity level * @set: if true, wake-up IRQs are set, if false they are cleared + * + * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since + * it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. */ void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set) { @@ -200,14 +200,14 @@ void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr) } /** - * ve_spc_powerdown() + * ve_spc_powerdown() - enables/disables cluster powerdown + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @enable: if true enables powerdown, if false disables it * * Function to enable/disable cluster powerdown. Not protected by locking * since it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @cluster: mpidr[15:8] bitfield describing cluster affinity level - * @enable: if true enables powerdown, if false disables it */ void ve_spc_powerdown(u32 cluster, bool enable) { @@ -228,7 +228,7 @@ static u32 standbywfi_cpu_mask(u32 cpu, u32 cluster) } /** - * ve_spc_cpu_in_wfi(u32 cpu, u32 cluster) + * ve_spc_cpu_in_wfi() - Checks if the specified CPU is in WFI or not * * @cpu: mpidr[7:0] bitfield describing CPU affinity level within cluster * @cluster: mpidr[15:8] bitfield describing cluster affinity level @@ -580,7 +580,7 @@ static int __init ve_spc_clk_init(void) } cluster = topology_physical_package_id(cpu_dev->id); - if (init_opp_table[cluster]) + if (cluster < 0 || init_opp_table[cluster]) continue; if (ve_init_opp_table(cpu_dev)) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4b61541853ea..82ffac621854 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -381,6 +381,7 @@ out: */ postcore_initcall(atomic_pool_init); +#ifdef CONFIG_CMA_AREAS struct dma_contig_early_reserve { phys_addr_t base; unsigned long size; @@ -435,6 +436,7 @@ void __init dma_contiguous_remap(void) iotable_init(&map, 1); } } +#endif static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data) { diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 9ff683612f2a..d7ffccb7fea7 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -88,6 +88,10 @@ extern phys_addr_t arm_lowmem_limit; void __init bootmem_init(void); void arm_mm_memblock_reserve(void); +#ifdef CONFIG_CMA_AREAS void dma_contiguous_remap(void); +#else +static inline void dma_contiguous_remap(void) { } +#endif unsigned long __clear_cr(unsigned long mask); diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile index 4a5c50f67ced..81f13bdf32f2 100644 --- a/arch/arm/tools/Makefile +++ b/arch/arm/tools/Makefile @@ -29,8 +29,7 @@ kapi: $(kapi-hdrs-y) $(gen-y) uapi: $(uapi-hdrs-y) # Create output directory if not already present -_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') \ - $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') +$(shell mkdir -p $(kapi) $(uapi)) quiet_cmd_gen_mach = GEN $@ cmd_gen_mach = $(AWK) -f $(real-prereqs) > $@ diff --git a/arch/arm64/boot/dts/amd/Makefile b/arch/arm64/boot/dts/amd/Makefile index 6a6093064a32..68103a8b0ef5 100644 --- a/arch/arm64/boot/dts/amd/Makefile +++ b/arch/arm64/boot/dts/amd/Makefile @@ -1,4 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -dtb-$(CONFIG_ARCH_SEATTLE) += amd-overdrive.dtb \ - amd-overdrive-rev-b0.dtb amd-overdrive-rev-b1.dtb \ - husky.dtb +dtb-$(CONFIG_ARCH_SEATTLE) += amd-overdrive-rev-b0.dtb amd-overdrive-rev-b1.dtb diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts index 8e341be9a399..c290d1ce2b03 100644 --- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts +++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts @@ -9,6 +9,7 @@ /dts-v1/; /include/ "amd-seattle-soc.dtsi" +/include/ "amd-seattle-cpus.dtsi" / { model = "AMD Seattle (Rev.B0) Development Board (Overdrive)"; @@ -36,14 +37,6 @@ status = "ok"; }; -&gpio2 { - status = "ok"; -}; - -&gpio3 { - status = "ok"; -}; - &gpio4 { status = "ok"; }; @@ -79,10 +72,6 @@ }; }; -&ipmi_kcs { - status = "ok"; -}; - &smb0 { /include/ "amd-seattle-xgbe-b.dtsi" }; diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts index 92cef05c6b74..e0926f6bb7c3 100644 --- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts +++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts @@ -9,6 +9,7 @@ /dts-v1/; /include/ "amd-seattle-soc.dtsi" +/include/ "amd-seattle-cpus.dtsi" / { model = "AMD Seattle (Rev.B1) Development Board (Overdrive)"; diff --git a/arch/arm64/boot/dts/amd/amd-overdrive.dts b/arch/arm64/boot/dts/amd/amd-overdrive.dts deleted file mode 100644 index 41b3a6c0993d..000000000000 --- a/arch/arm64/boot/dts/amd/amd-overdrive.dts +++ /dev/null @@ -1,66 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DTS file for AMD Seattle Overdrive Development Board - * - * Copyright (C) 2014 Advanced Micro Devices, Inc. - */ - -/dts-v1/; - -/include/ "amd-seattle-soc.dtsi" - -/ { - model = "AMD Seattle Development Board (Overdrive)"; - compatible = "amd,seattle-overdrive", "amd,seattle"; - - chosen { - stdout-path = &serial0; - }; -}; - -&ccp0 { - status = "ok"; -}; - -&gpio0 { - status = "ok"; -}; - -&gpio1 { - status = "ok"; -}; - -&i2c0 { - status = "ok"; -}; - -&pcie0 { - status = "ok"; -}; - -&spi0 { - status = "ok"; -}; - -&spi1 { - status = "ok"; - sdcard0: sdcard@0 { - compatible = "mmc-spi-slot"; - reg = <0>; - spi-max-frequency = <20000000>; - voltage-ranges = <3200 3400>; - gpios = <&gpio0 7 0>; - interrupt-parent = <&gpio0>; - interrupts = <7 3>; - pl022,hierarchy = <0>; - pl022,interface = <0>; - pl022,com-mode = <0x0>; - pl022,rx-level-trig = <0>; - pl022,tx-level-trig = <0>; - }; -}; - -&v2m0 { - arm,msi-base-spi = <64>; - arm,msi-num-spis = <256>; -}; diff --git a/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi new file mode 100644 index 000000000000..93688a0b6820 --- /dev/null +++ b/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 + +/ { + cpus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&CPU0>; + }; + core1 { + cpu = <&CPU1>; + }; + }; + cluster1 { + core0 { + cpu = <&CPU2>; + }; + core1 { + cpu = <&CPU3>; + }; + }; + cluster2 { + core0 { + cpu = <&CPU4>; + }; + core1 { + cpu = <&CPU5>; + }; + }; + cluster3 { + core0 { + cpu = <&CPU6>; + }; + core1 { + cpu = <&CPU7>; + }; + }; + }; + + CPU0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_0>; + + }; + + CPU1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x1>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_0>; + }; + + CPU2: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x100>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_1>; + }; + + CPU3: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x101>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_1>; + }; + + CPU4: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x200>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_2>; + }; + + CPU5: cpu@201 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x201>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_2>; + }; + + CPU6: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x300>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_3>; + }; + + CPU7: cpu@301 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x301>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_3>; + }; + }; + + L2_0: l2-cache0 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L2_1: l2-cache1 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L2_2: l2-cache2 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L2_3: l2-cache3 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L3: l3-cache { + cache-level = <3>; + cache-size = <0x800000>; + cache-line-size = <64>; + cache-sets = <8192>; + cache-unified; + }; + + pmu { + compatible = "arm,cortex-a57-pmu"; + interrupts = <0x0 0x7 0x4>, + <0x0 0x8 0x4>, + <0x0 0x9 0x4>, + <0x0 0xa 0x4>, + <0x0 0xb 0x4>, + <0x0 0xc 0x4>, + <0x0 0xd 0x4>, + <0x0 0xe 0x4>; + interrupt-affinity = <&CPU0>, + <&CPU1>, + <&CPU2>, + <&CPU3>, + <&CPU4>, + <&CPU5>, + <&CPU6>, + <&CPU7>; + }; +}; diff --git a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi index b664e7af74eb..690020589d41 100644 --- a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi +++ b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi @@ -38,18 +38,6 @@ <1 10 0xff04>; }; - pmu { - compatible = "arm,armv8-pmuv3"; - interrupts = <0 7 4>, - <0 8 4>, - <0 9 4>, - <0 10 4>, - <0 11 4>, - <0 12 4>, - <0 13 4>, - <0 14 4>; - }; - smb0: smb { compatible = "simple-bus"; #address-cells = <2>; @@ -70,6 +58,7 @@ reg = <0 0xe0300000 0 0xf0000>; interrupts = <0 355 4>; clocks = <&sataclk_333mhz>; + iommus = <&sata0_smmu 0x0 0x1f>; dma-coherent; }; @@ -80,6 +69,27 @@ reg = <0 0xe0d00000 0 0xf0000>; interrupts = <0 354 4>; clocks = <&sataclk_333mhz>; + iommus = <&sata1_smmu 0x0e>, + <&sata1_smmu 0x0f>, + <&sata1_smmu 0x1e>; + dma-coherent; + }; + + sata0_smmu: iommu@e0200000 { + compatible = "arm,mmu-401"; + reg = <0 0xe0200000 0 0x10000>; + #global-interrupts = <1>; + interrupts = <0 332 4>, <0 332 4>; + #iommu-cells = <2>; + dma-coherent; + }; + + sata1_smmu: iommu@e0c00000 { + compatible = "arm,mmu-401"; + reg = <0 0xe0c00000 0 0x10000>; + #global-interrupts = <1>; + interrupts = <0 331 4>, <0 331 4>; + #iommu-cells = <1>; dma-coherent; }; @@ -201,6 +211,10 @@ reg = <0 0xe0100000 0 0x10000>; interrupts = <0 3 4>; dma-coherent; + iommus = <&sata1_smmu 0x00>, + <&sata1_smmu 0x02>, + <&sata1_smmu 0x40>, + <&sata1_smmu 0x42>; }; pcie0: pcie@f0000000 { @@ -213,12 +227,22 @@ msi-parent = <&v2m0>; reg = <0 0xf0000000 0 0x10000000>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; + interrupt-map-mask = <0xff00 0x0 0x0 0x7>; interrupt-map = - <0x1000 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x120 0x1>, - <0x1000 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x121 0x1>, - <0x1000 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x122 0x1>, - <0x1000 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x123 0x1>; + <0x1100 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x120 0x1>, + <0x1100 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x121 0x1>, + <0x1100 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x122 0x1>, + <0x1100 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x123 0x1>, + + <0x1200 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x124 0x1>, + <0x1200 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x125 0x1>, + <0x1200 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x126 0x1>, + <0x1200 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x127 0x1>, + + <0x1300 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x128 0x1>, + <0x1300 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x129 0x1>, + <0x1300 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x12a 0x1>, + <0x1300 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x12b 0x1>; dma-coherent; dma-ranges = <0x43000000 0x0 0x0 0x0 0x0 0x100 0x0>; @@ -227,8 +251,18 @@ <0x01000000 0x00 0x00000000 0x00 0xefff0000 0x00 0x00010000>, /* 32-bit MMIO (size=2G) */ <0x02000000 0x00 0x40000000 0x00 0x40000000 0x00 0x80000000>, - /* 64-bit MMIO (size= 124G) */ + /* 64-bit MMIO (size= 508G) */ <0x03000000 0x01 0x00000000 0x01 0x00000000 0x7f 0x00000000>; + iommu-map = <0x0 &pcie_smmu 0x0 0x10000>; + }; + + pcie_smmu: iommu@e0a00000 { + compatible = "arm,mmu-401"; + reg = <0 0xe0a00000 0 0x10000>; + #global-interrupts = <1>; + interrupts = <0 333 4>, <0 333 4>; + #iommu-cells = <1>; + dma-coherent; }; /* Perf CCN504 PMU */ diff --git a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi index d97498361ce3..9259e547e2e8 100644 --- a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi +++ b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi @@ -55,7 +55,7 @@ clocks = <&xgmacclk0_dma_250mhz>, <&xgmacclk0_ptp_250mhz>; clock-names = "dma_clk", "ptp_clk"; phy-mode = "xgmii"; - #stream-id-cells = <16>; + iommus = <&xgmac0_smmu 0x00 0x17>; /* 0-7, 16-23 */ dma-coherent; }; @@ -81,11 +81,11 @@ clocks = <&xgmacclk1_dma_250mhz>, <&xgmacclk1_ptp_250mhz>; clock-names = "dma_clk", "ptp_clk"; phy-mode = "xgmii"; - #stream-id-cells = <16>; + iommus = <&xgmac1_smmu 0x00 0x17>; /* 0-7, 16-23 */ dma-coherent; }; - xgmac0_smmu: smmu@e0600000 { + xgmac0_smmu: iommu@e0600000 { compatible = "arm,mmu-401"; reg = <0 0xe0600000 0 0x10000>; #global-interrupts = <1>; @@ -94,14 +94,11 @@ */ <0 336 4>, <0 336 4>; - - mmu-masters = <&xgmac0 - 0 1 2 3 4 5 6 7 - 16 17 18 19 20 21 22 23 - >; + #iommu-cells = <2>; + dma-coherent; }; - xgmac1_smmu: smmu@e0800000 { + xgmac1_smmu: iommu@e0800000 { compatible = "arm,mmu-401"; reg = <0 0xe0800000 0 0x10000>; #global-interrupts = <1>; @@ -110,9 +107,6 @@ */ <0 335 4>, <0 335 4>; - - mmu-masters = <&xgmac1 - 0 1 2 3 4 5 6 7 - 16 17 18 19 20 21 22 23 - >; + #iommu-cells = <2>; + dma-coherent; }; diff --git a/arch/arm64/boot/dts/amd/husky.dts b/arch/arm64/boot/dts/amd/husky.dts deleted file mode 100644 index 7acde34772cb..000000000000 --- a/arch/arm64/boot/dts/amd/husky.dts +++ /dev/null @@ -1,84 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DTS file for AMD/Linaro 96Boards Enterprise Edition Server (Husky) Board - * Note: Based-on AMD Seattle Rev.B0 - * - * Copyright (C) 2015 Advanced Micro Devices, Inc. - */ - -/dts-v1/; - -/include/ "amd-seattle-soc.dtsi" - -/ { - model = "Linaro 96Boards Enterprise Edition Server (Husky) Board"; - compatible = "amd,seattle-overdrive", "amd,seattle"; - - chosen { - stdout-path = &serial0; - }; - - psci { - compatible = "arm,psci-0.2"; - method = "smc"; - }; -}; - -&ccp0 { - status = "ok"; - amd,zlib-support = <1>; -}; - -/** - * NOTE: In Rev.B, gpio0 is reserved. - */ -&gpio1 { - status = "ok"; -}; - -&gpio2 { - status = "ok"; -}; - -&gpio3 { - status = "ok"; -}; - -&gpio4 { - status = "ok"; -}; - -&i2c0 { - status = "ok"; -}; - -&i2c1 { - status = "ok"; -}; - -&pcie0 { - status = "ok"; -}; - -&spi0 { - status = "ok"; -}; - -&spi1 { - status = "ok"; - sdcard0: sdcard@0 { - compatible = "mmc-spi-slot"; - reg = <0>; - spi-max-frequency = <20000000>; - voltage-ranges = <3200 3400>; - pl022,hierarchy = <0>; - pl022,interface = <0>; - pl022,com-mode = <0x0>; - pl022,rx-level-trig = <0>; - pl022,tx-level-trig = <0>; - }; -}; - -&smb0 { - /include/ "amd-seattle-xgbe-b.dtsi" -}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index 01b01e320411..35d1939e690b 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -536,9 +536,9 @@ clock-names = "i2c"; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(1)>; - dmas = <&edma0 1 39>, - <&edma0 1 38>; - dma-names = "tx", "rx"; + dmas = <&edma0 1 38>, + <&edma0 1 39>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 687fea6d8afa..4e7bd04d9798 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -499,9 +499,9 @@ interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(2)>; - dmas = <&edma0 1 39>, - <&edma0 1 38>; - dma-names = "tx", "rx"; + dmas = <&edma0 1 38>, + <&edma0 1 39>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 1dc9d187601c..a0bd540f27d3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -89,12 +89,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index b16c7caf34c1..87b5e23c766f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -70,12 +70,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi index aff857df25cf..1df84335925b 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi @@ -262,25 +262,25 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull = <1>; + drive-push-pull; }; gpio5 { pins = "gpio5"; function = "gpio"; - drive-push-pull = <0>; + drive-push-pull; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull = <0>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts b/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts index 4631504c3c7a..1ab132c152bb 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts @@ -462,25 +462,25 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull = <1>; + drive-push-pull; }; gpio5 { pins = "gpio5"; function = "gpio"; - drive-push-pull = <0>; + drive-push-pull; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi index a7d7cfd66379..634d0f493c2e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi @@ -174,19 +174,19 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull = <1>; + drive-push-pull; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull = <0>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi index 0bd66f9c620b..0b219e72765e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi @@ -148,19 +148,19 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull = <1>; + drive-push-pull; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull = <0>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi index 75eb743a7242..0fe772b04bd0 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi @@ -59,7 +59,7 @@ gpio1 { pins = "gpio1"; function = "fps-out"; - drive-push-pull = <1>; + drive-push-pull; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <7>; maxim,active-fps-power-down-slot = <0>; @@ -68,7 +68,7 @@ gpio2_3 { pins = "gpio2", "gpio3"; function = "fps-out"; - drive-open-drain = <1>; + drive-open-drain; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; }; @@ -80,7 +80,7 @@ gpio5_6_7 { pins = "gpio5", "gpio6", "gpio7"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi index 10347b6e6e84..936a309e288c 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi @@ -1351,7 +1351,7 @@ gpio1 { pins = "gpio1"; function = "fps-out"; - drive-push-pull = <1>; + drive-push-pull; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <7>; maxim,active-fps-power-down-slot = <0>; @@ -1360,14 +1360,14 @@ gpio2 { pins = "gpio2"; function = "fps-out"; - drive-open-drain = <1>; + drive-open-drain; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; }; gpio3 { pins = "gpio3"; function = "fps-out"; - drive-open-drain = <1>; + drive-open-drain; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; }; @@ -1379,7 +1379,7 @@ gpio5_6_7 { pins = "gpio5", "gpio6", "gpio7"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts b/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts index 72c2dc3c14ea..f6446120c267 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts @@ -195,7 +195,7 @@ gpio1 { pins = "gpio1"; function = "fps-out"; - drive-push-pull = <1>; + drive-push-pull; maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>; maxim,active-fps-power-up-slot = <0>; maxim,active-fps-power-down-slot = <7>; @@ -204,7 +204,7 @@ gpio2 { pins = "gpio2"; function = "fps-out"; - drive-open-drain = <1>; + drive-open-drain; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <0>; maxim,active-fps-power-down-slot = <7>; @@ -213,7 +213,7 @@ gpio3 { pins = "gpio3"; function = "fps-out"; - drive-open-drain = <1>; + drive-open-drain; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <4>; maxim,active-fps-power-down-slot = <3>; @@ -227,7 +227,7 @@ gpio5_6_7 { pins = "gpio5", "gpio6", "gpio7"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts index a263d51882ee..e42384f097d6 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts +++ b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts @@ -1386,7 +1386,7 @@ gpio3 { pins = "gpio3"; function = "fps-out"; - drive-open-drain = <1>; + drive-open-drain; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <4>; maxim,active-fps-power-down-slot = <2>; @@ -1395,7 +1395,7 @@ gpio5_6 { pins = "gpio5", "gpio6"; function = "gpio"; - drive-push-pull = <1>; + drive-push-pull; }; gpio4 { diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index f0f81c23c16f..b9a48cfd760f 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -1249,14 +1249,14 @@ pins = "gpio47", "gpio48"; function = "blsp_i2c3"; drive-strength = <16>; - bias-disable = <0>; + bias-disable; }; blsp1_i2c3_sleep: blsp1-i2c2-sleep { pins = "gpio47", "gpio48"; function = "gpio"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; blsp2_uart3_4pins_default: blsp2-uart2-4pins { diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi index e90f99ef5323..e47c74e513af 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi @@ -33,7 +33,7 @@ ap_h1_spi: &spi0 {}; }; &alc5682 { - realtek,dmic-clk-driving-high = "true"; + realtek,dmic-clk-driving-high; }; &cpu6_alert0 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 1084d5ce9ac7..07b729f9fec5 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -630,7 +630,7 @@ pins = "gpio6", "gpio25", "gpio26"; function = "gpio"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 8553c8bf79bd..103cc40816fd 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -563,7 +563,7 @@ config { pins = "gpio6", "gpio11"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..ff8f4511df71 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..c31be7eda9df 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index d62405ce3e6d..7496deab025a 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -43,10 +43,22 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); +#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__) static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } +#else +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, + &kvm->arch.flags)); + + return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); +} +#endif static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { @@ -72,15 +84,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TVM; } - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) + if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - - /* - * TID3: trap feature register accesses that we virtualise. - * For now this is conditional, since no AArch32 feature regs - * are currently virtualised. - */ - if (!vcpu_el1_is_32bit(vcpu)) + else + /* + * TID3: trap feature register accesses that we virtualise. + * For now this is conditional, since no AArch32 feature regs + * are currently virtualised. + */ vcpu->arch.hcr_el2 |= HCR_TID3; if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e3b25dc6c367..94a27a7520f4 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -127,6 +127,16 @@ struct kvm_arch { #define KVM_ARCH_FLAG_MTE_ENABLED 1 /* At least one vCPU has ran in the VM */ #define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 + /* + * The following two bits are used to indicate the guest's EL1 + * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT + * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set. + * Otherwise, the guest's EL1 register width has not yet been + * determined yet. + */ +#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 +#define KVM_ARCH_FLAG_EL1_32BIT 4 + unsigned long flags; /* diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..2b3f3d0544b9 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,9 +91,8 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; phdr.p_type = PT_ARM_MEMTAG_MTE; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..cd868084e724 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..3b46041f2b97 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0d19259454d8..53ae2c0640bc 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1079,7 +1079,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - bool logging_perm_fault = false; + bool use_read_lock = false; unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); unsigned long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; @@ -1114,7 +1114,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; - logging_perm_fault = (fault_status == FSC_PERM && write_fault); + use_read_lock = (fault_status == FSC_PERM && write_fault && + fault_granule == PAGE_SIZE); } else { vma_shift = get_vma_page_shift(vma, hva); } @@ -1218,7 +1219,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * logging dirty logging, only acquire read lock for permission * relaxation. */ - if (logging_perm_fault) + if (use_read_lock) read_lock(&kvm->mmu_lock); else write_lock(&kvm->mmu_lock); @@ -1268,6 +1269,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (fault_status == FSC_PERM && vma_pagesize == fault_granule) { ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); } else { + WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n"); + ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, memcache); @@ -1280,7 +1283,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } out_unlock: - if (logging_perm_fault) + if (use_read_lock) read_unlock(&kvm->mmu_lock); else write_unlock(&kvm->mmu_lock); diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 372da09a2fab..baac2b405f23 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -215,15 +215,11 @@ static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) { - switch(fn) { - case PSCI_0_2_FN64_CPU_SUSPEND: - case PSCI_0_2_FN64_CPU_ON: - case PSCI_0_2_FN64_AFFINITY_INFO: - /* Disallow these functions for 32bit guests */ - if (vcpu_mode_is_32bit(vcpu)) - return PSCI_RET_NOT_SUPPORTED; - break; - } + /* + * Prevent 32 bit guests from calling 64 bit PSCI functions. + */ + if ((fn & PSCI_0_2_64BIT) && vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; return 0; } @@ -235,10 +231,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; - val = kvm_psci_check_allowed_function(vcpu, psci_fn); - if (val) - goto out; - switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -306,7 +298,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } -out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -318,9 +309,6 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) unsigned long val; int ret = 1; - if (minor > 1) - return -EINVAL; - switch(psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1; @@ -426,6 +414,15 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) */ int kvm_psci_call(struct kvm_vcpu *vcpu) { + u32 psci_fn = smccc_get_function(vcpu); + unsigned long val; + + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) { + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; + } + switch (kvm_psci_version(vcpu)) { case KVM_ARM_PSCI_1_1: return kvm_psci_1_x_call(vcpu, 1); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index ecc40c8cd6f6..6c70c6f61c70 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -181,27 +181,51 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) return 0; } -static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) +/** + * kvm_set_vm_width() - set the register width for the guest + * @vcpu: Pointer to the vcpu being configured + * + * Set both KVM_ARCH_FLAG_EL1_32BIT and KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED + * in the VM flags based on the vcpu's requested register width, the HW + * capabilities and other options (such as MTE). + * When REG_WIDTH_CONFIGURED is already set, the vcpu settings must be + * consistent with the value of the FLAG_EL1_32BIT bit in the flags. + * + * Return: 0 on success, negative error code on failure. + */ +static int kvm_set_vm_width(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *tmp; + struct kvm *kvm = vcpu->kvm; bool is32bit; - unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); + + lockdep_assert_held(&kvm->lock); + + if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) { + /* + * The guest's register width is already configured. + * Make sure that the vcpu is consistent with it. + */ + if (is32bit == test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags)) + return 0; + + return -EINVAL; + } + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) - return false; + return -EINVAL; /* MTE is incompatible with AArch32 */ - if (kvm_has_mte(vcpu->kvm) && is32bit) - return false; + if (kvm_has_mte(kvm) && is32bit) + return -EINVAL; - /* Check that the vcpus are either all 32bit or all 64bit */ - kvm_for_each_vcpu(i, tmp, vcpu->kvm) { - if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit) - return false; - } + if (is32bit) + set_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags); - return true; + set_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags); + + return 0; } /** @@ -230,10 +254,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) u32 pstate; mutex_lock(&vcpu->kvm->lock); - reset_state = vcpu->arch.reset_state; - WRITE_ONCE(vcpu->arch.reset_state.reset, false); + ret = kvm_set_vm_width(vcpu); + if (!ret) { + reset_state = vcpu->arch.reset_state; + WRITE_ONCE(vcpu->arch.reset_state.reset, false); + } mutex_unlock(&vcpu->kvm->lock); + if (ret) + return ret; + /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); @@ -260,14 +290,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } } - if (!vcpu_allowed_register_width(vcpu)) { - ret = -EINVAL; - goto out; - } - switch (vcpu->arch.target) { default: - if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { + if (vcpu_el1_is_32bit(vcpu)) { pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index f38c40a76251..78cde687383c 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -82,7 +82,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter) static void *vgic_debug_start(struct seq_file *s, loff_t *pos) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter; mutex_lock(&kvm->lock); @@ -110,7 +110,7 @@ out: static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter = kvm->arch.vgic.iter; ++*pos; @@ -122,7 +122,7 @@ static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) static void vgic_debug_stop(struct seq_file *s, void *v) { - struct kvm *kvm = (struct kvm *)s->private; + struct kvm *kvm = s->private; struct vgic_state_iter *iter; /* @@ -229,8 +229,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, static int vgic_debug_show(struct seq_file *s, void *v) { - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter = (struct vgic_state_iter *)v; + struct kvm *kvm = s->private; + struct vgic_state_iter *iter = v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; unsigned long flags; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 089fc2ffcb43..2e13402be3bd 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2143,7 +2143,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, void *ptr, void *opaque) { - struct its_device *dev = (struct its_device *)opaque; + struct its_device *dev = opaque; struct its_collection *collection; struct kvm *kvm = its->dev->kvm; struct kvm_vcpu *vcpu = NULL; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..1e7b1550e2fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) diff --git a/arch/h8300/include/asm/user.h b/arch/h8300/include/asm/user.h index 2298909f24c6..161653d84b34 100644 --- a/arch/h8300/include/asm/user.h +++ b/arch/h8300/include/asm/user.h @@ -67,9 +67,5 @@ struct user { unsigned long magic; /* To uniquely identify a core file */ char u_comm[32]; /* User command that was responsible */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif diff --git a/arch/ia64/include/asm/user.h b/arch/ia64/include/asm/user.h index 0ba486651b7c..ec03d3ab8715 100644 --- a/arch/ia64/include/asm/user.h +++ b/arch/ia64/include/asm/user.h @@ -50,10 +50,4 @@ struct user { char u_comm[32]; /* user command name */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_DATA_START_ADDR (u.start_data) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) - #endif /* _ASM_IA64_USER_H */ diff --git a/arch/ia64/kernel/syscalls/Makefile b/arch/ia64/kernel/syscalls/Makefile index 14f40ecf8b65..d009f927a048 100644 --- a/arch/ia64/kernel/syscalls/Makefile +++ b/arch/ia64/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/m68k/include/asm/user.h b/arch/m68k/include/asm/user.h index 509d555977c8..61413bff613a 100644 --- a/arch/m68k/include/asm/user.h +++ b/arch/m68k/include/asm/user.h @@ -79,9 +79,5 @@ struct user{ unsigned long magic; /* To uniquely identify a core file */ char u_comm[32]; /* User command that was responsible */ }; -#define NBPG 4096 -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif diff --git a/arch/m68k/kernel/syscalls/Makefile b/arch/m68k/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/m68k/kernel/syscalls/Makefile +++ b/arch/m68k/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile index cff570a71946..2b42c370d574 100644 --- a/arch/microblaze/boot/Makefile +++ b/arch/microblaze/boot/Makefile @@ -29,7 +29,7 @@ $(obj)/simpleImage.$(DTB).ub: $(obj)/simpleImage.$(DTB) FORCE $(call if_changed,uimage) $(obj)/simpleImage.$(DTB).unstrip: vmlinux FORCE - $(call if_changed,shipped) + $(call if_changed,copy) $(obj)/simpleImage.$(DTB).strip: vmlinux FORCE $(call if_changed,strip) diff --git a/arch/microblaze/boot/dts/Makefile b/arch/microblaze/boot/dts/Makefile index ef00dd30d19a..b84e2cbb20ee 100644 --- a/arch/microblaze/boot/dts/Makefile +++ b/arch/microblaze/boot/dts/Makefile @@ -12,7 +12,7 @@ $(obj)/linked_dtb.o: $(obj)/system.dtb # Generate system.dtb from $(DTB).dtb ifneq ($(DTB),system) $(obj)/system.dtb: $(obj)/$(DTB).dtb - $(call if_changed,shipped) + $(call if_changed,copy) endif endif diff --git a/arch/microblaze/kernel/syscalls/Makefile b/arch/microblaze/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/microblaze/kernel/syscalls/Makefile +++ b/arch/microblaze/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/mips/crypto/crc32-mips.c b/arch/mips/crypto/crc32-mips.c index 0a03529cf317..3e4f5ba104f8 100644 --- a/arch/mips/crypto/crc32-mips.c +++ b/arch/mips/crypto/crc32-mips.c @@ -28,7 +28,7 @@ enum crc_type { }; #ifndef TOOLCHAIN_SUPPORTS_CRC -#define _ASM_MACRO_CRC32(OP, SZ, TYPE) \ +#define _ASM_SET_CRC(OP, SZ, TYPE) \ _ASM_MACRO_3R(OP, rt, rs, rt2, \ ".ifnc \\rt, \\rt2\n\t" \ ".error \"invalid operands \\\"" #OP " \\rt,\\rs,\\rt2\\\"\"\n\t" \ @@ -37,30 +37,36 @@ _ASM_MACRO_3R(OP, rt, rs, rt2, \ ((SZ) << 6) | ((TYPE) << 8)) \ _ASM_INSN32_IF_MM(0x00000030 | (__rs << 16) | (__rt << 21) | \ ((SZ) << 14) | ((TYPE) << 3))) -_ASM_MACRO_CRC32(crc32b, 0, 0); -_ASM_MACRO_CRC32(crc32h, 1, 0); -_ASM_MACRO_CRC32(crc32w, 2, 0); -_ASM_MACRO_CRC32(crc32d, 3, 0); -_ASM_MACRO_CRC32(crc32cb, 0, 1); -_ASM_MACRO_CRC32(crc32ch, 1, 1); -_ASM_MACRO_CRC32(crc32cw, 2, 1); -_ASM_MACRO_CRC32(crc32cd, 3, 1); -#define _ASM_SET_CRC "" +#define _ASM_UNSET_CRC(op, SZ, TYPE) ".purgem " #op "\n\t" #else /* !TOOLCHAIN_SUPPORTS_CRC */ -#define _ASM_SET_CRC ".set\tcrc\n\t" +#define _ASM_SET_CRC(op, SZ, TYPE) ".set\tcrc\n\t" +#define _ASM_UNSET_CRC(op, SZ, TYPE) #endif -#define _CRC32(crc, value, size, type) \ -do { \ - __asm__ __volatile__( \ - ".set push\n\t" \ - _ASM_SET_CRC \ - #type #size " %0, %1, %0\n\t" \ - ".set pop" \ - : "+r" (crc) \ - : "r" (value)); \ +#define __CRC32(crc, value, op, SZ, TYPE) \ +do { \ + __asm__ __volatile__( \ + ".set push\n\t" \ + _ASM_SET_CRC(op, SZ, TYPE) \ + #op " %0, %1, %0\n\t" \ + _ASM_UNSET_CRC(op, SZ, TYPE) \ + ".set pop" \ + : "+r" (crc) \ + : "r" (value)); \ } while (0) +#define _CRC32_crc32b(crc, value) __CRC32(crc, value, crc32b, 0, 0) +#define _CRC32_crc32h(crc, value) __CRC32(crc, value, crc32h, 1, 0) +#define _CRC32_crc32w(crc, value) __CRC32(crc, value, crc32w, 2, 0) +#define _CRC32_crc32d(crc, value) __CRC32(crc, value, crc32d, 3, 0) +#define _CRC32_crc32cb(crc, value) __CRC32(crc, value, crc32cb, 0, 1) +#define _CRC32_crc32ch(crc, value) __CRC32(crc, value, crc32ch, 1, 1) +#define _CRC32_crc32cw(crc, value) __CRC32(crc, value, crc32cw, 2, 1) +#define _CRC32_crc32cd(crc, value) __CRC32(crc, value, crc32cd, 3, 1) + +#define _CRC32(crc, value, size, op) \ + _CRC32_##op##size(crc, value) + #define CRC32(crc, value, size) \ _CRC32(crc, value, size, crc32) diff --git a/arch/mips/include/asm/mach-rc32434/rb.h b/arch/mips/include/asm/mach-rc32434/rb.h index 34d179ca020b..dd9d4b026e62 100644 --- a/arch/mips/include/asm/mach-rc32434/rb.h +++ b/arch/mips/include/asm/mach-rc32434/rb.h @@ -29,15 +29,6 @@ #define DEV3TC 0x01003C #define BTCS 0x010040 #define BTCOMPARE 0x010044 -#define GPIOBASE 0x050000 -/* Offsets relative to GPIOBASE */ -#define GPIOFUNC 0x00 -#define GPIOCFG 0x04 -#define GPIOD 0x08 -#define GPIOILEVEL 0x0C -#define GPIOISTAT 0x10 -#define GPIONMIEN 0x14 -#define IMASK6 0x38 #define LO_WPX (1 << 0) #define LO_ALE (1 << 1) #define LO_CLE (1 << 2) diff --git a/arch/mips/kernel/syscalls/Makefile b/arch/mips/kernel/syscalls/Makefile index 10bf90dc02c0..e6b21de65cca 100644 --- a/arch/mips/kernel/syscalls/Makefile +++ b/arch/mips/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syshdr := $(srctree)/scripts/syscallhdr.sh sysnr := $(srctree)/$(src)/syscallnr.sh diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c index 64726c670ca6..5204fc6d6d50 100644 --- a/arch/mips/lantiq/falcon/sysctrl.c +++ b/arch/mips/lantiq/falcon/sysctrl.c @@ -167,6 +167,8 @@ static inline void clkdev_add_sys(const char *dev, unsigned int module, { struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL); + if (!clk) + return; clk->cl.dev_id = dev; clk->cl.con_id = NULL; clk->cl.clk = clk; diff --git a/arch/mips/lantiq/xway/gptu.c b/arch/mips/lantiq/xway/gptu.c index 3d5683e75cf1..200fe9ff641d 100644 --- a/arch/mips/lantiq/xway/gptu.c +++ b/arch/mips/lantiq/xway/gptu.c @@ -122,6 +122,8 @@ static inline void clkdev_add_gptu(struct device *dev, const char *con, { struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL); + if (!clk) + return; clk->cl.dev_id = dev_name(dev); clk->cl.con_id = con; clk->cl.clk = clk; diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 917fac1636b7..084f6caba5f2 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -315,6 +315,8 @@ static void clkdev_add_pmu(const char *dev, const char *con, bool deactivate, { struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL); + if (!clk) + return; clk->cl.dev_id = dev; clk->cl.con_id = con; clk->cl.clk = clk; @@ -338,6 +340,8 @@ static void clkdev_add_cgu(const char *dev, const char *con, { struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL); + if (!clk) + return; clk->cl.dev_id = dev; clk->cl.con_id = con; clk->cl.clk = clk; @@ -356,24 +360,28 @@ static void clkdev_add_pci(void) struct clk *clk_ext = kzalloc(sizeof(struct clk), GFP_KERNEL); /* main pci clock */ - clk->cl.dev_id = "17000000.pci"; - clk->cl.con_id = NULL; - clk->cl.clk = clk; - clk->rate = CLOCK_33M; - clk->rates = valid_pci_rates; - clk->enable = pci_enable; - clk->disable = pmu_disable; - clk->module = 0; - clk->bits = PMU_PCI; - clkdev_add(&clk->cl); + if (clk) { + clk->cl.dev_id = "17000000.pci"; + clk->cl.con_id = NULL; + clk->cl.clk = clk; + clk->rate = CLOCK_33M; + clk->rates = valid_pci_rates; + clk->enable = pci_enable; + clk->disable = pmu_disable; + clk->module = 0; + clk->bits = PMU_PCI; + clkdev_add(&clk->cl); + } /* use internal/external bus clock */ - clk_ext->cl.dev_id = "17000000.pci"; - clk_ext->cl.con_id = "external"; - clk_ext->cl.clk = clk_ext; - clk_ext->enable = pci_ext_enable; - clk_ext->disable = pci_ext_disable; - clkdev_add(&clk_ext->cl); + if (clk_ext) { + clk_ext->cl.dev_id = "17000000.pci"; + clk_ext->cl.con_id = "external"; + clk_ext->cl.clk = clk_ext; + clk_ext->enable = pci_ext_enable; + clk_ext->disable = pci_ext_disable; + clkdev_add(&clk_ext->cl); + } } /* xway socs can generate clocks on gpio pins */ @@ -393,9 +401,15 @@ static void clkdev_add_clkout(void) char *name; name = kzalloc(sizeof("clkout0"), GFP_KERNEL); + if (!name) + continue; sprintf(name, "clkout%d", i); clk = kzalloc(sizeof(struct clk), GFP_KERNEL); + if (!clk) { + kfree(name); + continue; + } clk->cl.dev_id = "1f103000.cgu"; clk->cl.con_id = name; clk->cl.clk = clk; diff --git a/arch/mips/rb532/gpio.c b/arch/mips/rb532/gpio.c index 94f02ada4082..29c21b9d42da 100644 --- a/arch/mips/rb532/gpio.c +++ b/arch/mips/rb532/gpio.c @@ -37,6 +37,16 @@ #include <asm/mach-rc32434/rb.h> #include <asm/mach-rc32434/gpio.h> +#define GPIOBASE 0x050000 +/* Offsets relative to GPIOBASE */ +#define GPIOFUNC 0x00 +#define GPIOCFG 0x04 +#define GPIOD 0x08 +#define GPIOILEVEL 0x0C +#define GPIOISTAT 0x10 +#define GPIONMIEN 0x14 +#define IMASK6 0x38 + struct rb532_gpio_chip { struct gpio_chip chip; void __iomem *regbase; diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c index dfc52f661ad0..38d12f417e48 100644 --- a/arch/mips/sgi-ip22/ip22-gio.c +++ b/arch/mips/sgi-ip22/ip22-gio.c @@ -363,6 +363,8 @@ static void ip22_check_gio(int slotno, unsigned long addr, int irq) printk(KERN_INFO "GIO: slot %d : %s (id %x)\n", slotno, name, id); gio_dev = kzalloc(sizeof *gio_dev, GFP_KERNEL); + if (!gio_dev) + return; gio_dev->name = name; gio_dev->slotno = slotno; gio_dev->id.id = id; diff --git a/arch/parisc/kernel/syscalls/Makefile b/arch/parisc/kernel/syscalls/Makefile index d63f18dd058d..8440c16dfb22 100644 --- a/arch/parisc/kernel/syscalls/Makefile +++ b/arch/parisc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 827038a33064..4def2bd17b9b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -16,18 +16,6 @@ #include <asm/ppc-opcode.h> #include <asm/pte-walk.h> -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif - /* * Structure for a nested guest, that is, for a guest that is managed by * one of our guests. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c583d0c37f31..838d4cb460b7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 254687258f42..f2c5c26869f1 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn(_addr)); \ +}) /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 049ca26893e6..8fa37ef5da4d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -28,11 +28,13 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES +extern bool pseries_reloc_on_exception(void); extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); void __init pseries_little_endian_exceptions(void); #else +static inline bool pseries_reloc_on_exception(void) { return false; } static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/include/asm/user.h b/arch/powerpc/include/asm/user.h index 99443b8594e7..7fae7e597ba4 100644 --- a/arch/powerpc/include/asm/user.h +++ b/arch/powerpc/include/asm/user.h @@ -44,9 +44,4 @@ struct user { char u_comm[32]; /* user command name */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_DATA_START_ADDR (u.start_data) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif /* _ASM_POWERPC_USER_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 55caeee37c08..b66dd6f775a4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -809,6 +809,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 40a583e9d3c7..97a76a8619fb 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -101,7 +101,7 @@ __module_alloc(unsigned long size, unsigned long start, unsigned long end, bool * too. */ return __vmalloc_node_range(size, 1, start, end, gfp, prot, - VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e547066a06aa..a96f05063bc9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,6 +196,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile index 5476f62eb80f..9d7bd81510b8 100644 --- a/arch/powerpc/kernel/syscalls/Makefile +++ b/arch/powerpc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 18e58085447c..ddd88179110a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR guest in user mode (problem state) and emulating all privileged instructions and registers. + This is only available for hash MMU mode and only supports + guests that use hash MMU mode. + This is not as fast as using hypervisor mode, but works on machines where hypervisor mode is not available or not usable, and can emulate processors that are different from the host processor, including emulating 32-bit processors on a 64-bit host. + Selecting this option will cause the SCV facility to be + disabled when the kernel is booted on the pseries platform in + hash MMU mode (regardless of PR VMs running). When any PR VMs + are running, "AIL" mode is disabled which may slow interrupts + and system calls on the host. + config KVM_BOOK3S_HV_EXIT_TIMING bool "Detailed timing for hypervisor real-mode code" depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 05e003eb5d90..e42d1c609e47 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) */ ld r10,HSTATE_SCRATCH0(r13) cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_common + beq .Lcall_machine_check_common cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET - beq system_reset_common + beq .Lcall_system_reset_common b . + +.Lcall_machine_check_common: + b machine_check_common + +.Lcall_system_reset_common: + b system_reset_common #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c886557638a1..6fa518f6501d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) int cpu; struct rcuwait *waitp; + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) ++vcpu->stat.generic.halt_wakeup; @@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, @@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - vcpu->cpu = pcpu; - vcpu->arch.thread_cpu = pcpu; - vc->pcpu = pcpu; - local_paca->kvm_hstate.kvm_vcpu = vcpu; - local_paca->kvm_hstate.ptid = 0; - local_paca->kvm_hstate.fake_suspend = 0; - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); trace_kvm_guest_enter(vcpu); @@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 34a801c3604a..7bf9e6ca5c2d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu->in_use = 0; svcpu_put(svcpu); -#endif /* Disable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV); + } +#endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 @@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV); + } #endif if (kvmppc_is_split_real(vcpu)) @@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); kvmppc_save_tm_pr(vcpu); - /* Enable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); - vcpu->cpu = -1; } @@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac) void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { + if (fscr & FSCR_SCV) + fscr &= ~FSCR_SCV; /* SCV must not be enabled */ if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 1f10e7dfcdd0..dc4f51ac84bc 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu) +{ + unsigned long mflags = kvmppc_get_gpr(vcpu, 4); + unsigned long resource = kvmppc_get_gpr(vcpu, 5); + + if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) { + /* KVM PR does not provide AIL!=0 to guests */ + if (mflags == 0) + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + else + kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63); + return EMULATE_DONE; + } + return EMULATE_FAIL; +} + #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { @@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_logical_ci_load(vcpu); case H_LOGICAL_CI_STORE: return kvmppc_h_pr_logical_ci_store(vcpu); + case H_SET_MODE: + return kvmppc_h_pr_set_mode(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_CEDE: case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: + case H_SET_MODE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = { H_BULK_REMOVE, H_PUT_TCE, H_CEDE, + H_SET_MODE, #ifdef CONFIG_KVM_XICS H_XIRR, H_CPPR, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9772b176e406..875c30c12db0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; #endif + case KVM_CAP_PPC_AIL_MODE_3: + r = 0; + /* + * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode. + * The POWER9s can support it if the guest runs in hash mode, + * but QEMU doesn't necessarily query the capability in time. + */ + if (hv_enabled) { + if (kvmhv_on_pseries()) { + if (pseries_reloc_on_exception()) + r = 1; + } else if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + r = 1; + } + } + break; default: r = 0; break; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8e301cd8925b..4d221d033804 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -255,7 +255,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9b7fefbb64b..13022d734951 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu) if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; - if (NODE_DATA(new_nid) == NULL) { + if (!node_online(new_nid)) { #ifdef CONFIG_MEMORY_HOTPLUG /* * Need to ensure that NODE_DATA is initialized for a node from diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 069d7b3bb142..955ff8aa1644 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -353,6 +353,14 @@ static void pseries_lpar_idle(void) pseries_idle_epilog(); } +static bool pseries_reloc_on_exception_enabled; + +bool pseries_reloc_on_exception(void) +{ + return pseries_reloc_on_exception_enabled; +} +EXPORT_SYMBOL_GPL(pseries_reloc_on_exception); + /* * Enable relocation on during exceptions. This has partition wide scope and * may take a while to complete, if it takes longer than one second we will @@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void) " on exceptions: %ld\n", rc); return false; } + pseries_reloc_on_exception_enabled = true; return true; } @@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void) break; mdelay(get_longbusy_msecs(rc)); } - if (rc != H_SUCCESS) + if (rc == H_SUCCESS) + pseries_reloc_on_exception_enabled = false; + else pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n", rc); } diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 4a7fcde5afc0..909535ca513a 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -99,6 +99,7 @@ static struct attribute *vas_def_capab_attrs[] = { &nr_used_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_def_capab); static struct attribute *vas_qos_capab_attrs[] = { &nr_total_credits_attribute.attr, @@ -106,6 +107,7 @@ static struct attribute *vas_qos_capab_attrs[] = { &update_total_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_qos_capab); static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -154,13 +156,13 @@ static const struct sysfs_ops vas_sysfs_ops = { static struct kobj_type vas_def_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_def_capab_attrs, + .default_groups = vas_def_capab_groups, }; static struct kobj_type vas_qos_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_qos_capab_attrs, + .default_groups = vas_qos_capab_groups, }; static char *vas_caps_kobj_name(struct vas_caps_entry *centry, diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index ea8ec8a960bd..00fd9c548f26 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -16,6 +16,7 @@ config RISCV select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEBUG_WX @@ -47,6 +48,7 @@ config RISCV select CLONE_BACKWARDS select CLINT_TIMER if !MMU select COMMON_CLK + select CPU_PM if CPU_IDLE select EDAC_SUPPORT select GENERIC_ARCH_TOPOLOGY if SMP select GENERIC_ATOMIC64 if !64BIT @@ -533,4 +535,10 @@ source "kernel/power/Kconfig" endmenu +menu "CPU Power Management" + +source "drivers/cpuidle/Kconfig" + +endmenu + source "arch/riscv/kvm/Kconfig" diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index c112ab2a9052..34592d00dde8 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -36,6 +36,9 @@ config SOC_VIRT select GOLDFISH select RTC_DRV_GOLDFISH if RTC_CLASS select SIFIVE_PLIC + select PM_GENERIC_DOMAINS if PM + select PM_GENERIC_DOMAINS_OF if PM && OF + select RISCV_SBI_CPUIDLE if CPU_IDLE help This enables support for QEMU Virt Machine. diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts index 984872f3d3a9..b9e30df127fe 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts @@ -203,6 +203,8 @@ compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; m25p,fast-read; broken-flash-reset; }; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts index 7ba99b4da304..8d23401b0bbb 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts @@ -205,6 +205,8 @@ compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; m25p,fast-read; broken-flash-reset; }; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts index be9b12c9b374..24fd83b43d9d 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts @@ -213,6 +213,8 @@ compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; m25p,fast-read; broken-flash-reset; }; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts index 031c0c28f819..25341f38292a 100644 --- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts +++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts @@ -178,6 +178,8 @@ compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; m25p,fast-read; broken-flash-reset; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 7cd10ded7bf8..30e3017f22bc 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -15,11 +15,14 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_PROFILING=y CONFIG_SOC_MICROCHIP_POLARFIRE=y CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y +CONFIG_PM=y +CONFIG_CPU_IDLE=y CONFIG_VIRTUALIZATION=y CONFIG_KVM=m CONFIG_JUMP_LABEL=y @@ -64,8 +67,6 @@ CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y -CONFIG_SERIAL_EARLYCON_RISCV_SBI=y -CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig index 3f42ed87dde8..2438fa39f8ae 100644 --- a/arch/riscv/configs/nommu_k210_defconfig +++ b/arch/riscv/configs/nommu_k210_defconfig @@ -21,7 +21,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_AIO is not set # CONFIG_IO_URING is not set # CONFIG_ADVISE_SYSCALLS is not set -# CONFIG_MEMBARRIER is not set # CONFIG_KALLSYMS is not set CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig index af64b95e88cc..9a133e63ae5b 100644 --- a/arch/riscv/configs/nommu_k210_sdcard_defconfig +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -13,7 +13,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_AIO is not set # CONFIG_IO_URING is not set # CONFIG_ADVISE_SYSCALLS is not set -# CONFIG_MEMBARRIER is not set # CONFIG_KALLSYMS is not set CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index e1c9864b6237..5269fbb6b4fc 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -19,7 +19,6 @@ CONFIG_EXPERT=y # CONFIG_AIO is not set # CONFIG_IO_URING is not set # CONFIG_ADVISE_SYSCALLS is not set -# CONFIG_MEMBARRIER is not set # CONFIG_KALLSYMS is not set # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index e0e5c7c09ab8..7e5efdc3829d 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -15,11 +15,14 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_PROFILING=y CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y +CONFIG_PM=y +CONFIG_CPU_IDLE=y CONFIG_VIRTUALIZATION=y CONFIG_KVM=m CONFIG_JUMP_LABEL=y @@ -62,8 +65,6 @@ CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y -CONFIG_SERIAL_EARLYCON_RISCV_SBI=y -CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 618d7c5af1a2..8c2549b16ac0 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -67,4 +67,30 @@ #error "Unexpected __SIZEOF_SHORT__" #endif +#ifdef __ASSEMBLY__ + +/* Common assembly source macros */ + +#ifdef CONFIG_XIP_KERNEL +.macro XIP_FIXUP_OFFSET reg + REG_L t0, _xip_fixup + add \reg, \reg, t0 +.endm +.macro XIP_FIXUP_FLASH_OFFSET reg + la t1, __data_loc + REG_L t1, _xip_phys_offset + sub \reg, \reg, t1 + add \reg, \reg, t0 +.endm +_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET +_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET +#else +.macro XIP_FIXUP_OFFSET reg +.endm +.macro XIP_FIXUP_FLASH_OFFSET reg +.endm +#endif /* CONFIG_XIP_KERNEL */ + +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_RISCV_ASM_H */ diff --git a/arch/riscv/include/asm/cpuidle.h b/arch/riscv/include/asm/cpuidle.h new file mode 100644 index 000000000000..71fdc607d4bc --- /dev/null +++ b/arch/riscv/include/asm/cpuidle.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2021 Allwinner Ltd + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#ifndef _ASM_RISCV_CPUIDLE_H +#define _ASM_RISCV_CPUIDLE_H + +#include <asm/barrier.h> +#include <asm/processor.h> + +static inline void cpu_do_idle(void) +{ + /* + * Add mb() here to ensure that all + * IO/MEM accesses are completed prior + * to entering WFI. + */ + mb(); + wait_for_interrupt(); +} + +#endif diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h index 1de233d8e8de..21774d868c65 100644 --- a/arch/riscv/include/asm/current.h +++ b/arch/riscv/include/asm/current.h @@ -33,6 +33,8 @@ static __always_inline struct task_struct *get_current(void) #define current get_current() +register unsigned long current_stack_pointer __asm__("sp"); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_CURRENT_H */ diff --git a/arch/riscv/include/asm/module.lds.h b/arch/riscv/include/asm/module.lds.h index 4254ff2ff049..1075beae1ac6 100644 --- a/arch/riscv/include/asm/module.lds.h +++ b/arch/riscv/include/asm/module.lds.h @@ -2,8 +2,8 @@ /* Copyright (C) 2017 Andes Technology Corporation */ #ifdef CONFIG_MODULE_SECTIONS SECTIONS { - .plt (NOLOAD) : { BYTE(0) } - .got (NOLOAD) : { BYTE(0) } - .got.plt (NOLOAD) : { BYTE(0) } + .plt : { BYTE(0) } + .got : { BYTE(0) } + .got.plt : { BYTE(0) } } #endif diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h new file mode 100644 index 000000000000..8be391c2aecb --- /dev/null +++ b/arch/riscv/include/asm/suspend.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#ifndef _ASM_RISCV_SUSPEND_H +#define _ASM_RISCV_SUSPEND_H + +#include <asm/ptrace.h> + +struct suspend_context { + /* Saved and restored by low-level functions */ + struct pt_regs regs; + /* Saved and restored by high-level functions */ + unsigned long scratch; + unsigned long tvec; + unsigned long ie; +#ifdef CONFIG_MMU + unsigned long satp; +#endif +}; + +/* Low-level CPU suspend entry function */ +int __cpu_suspend_enter(struct suspend_context *context); + +/* High-level CPU suspend which will save context and call finish() */ +int cpu_suspend(unsigned long arg, + int (*finish)(unsigned long arg, + unsigned long entry, + unsigned long context)); + +/* Low-level CPU resume entry function */ +int __cpu_resume_enter(unsigned long hartid, unsigned long context); + +#endif diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 60da0dcacf14..74d888c8d631 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -11,11 +11,17 @@ #include <asm/page.h> #include <linux/const.h> +#ifdef CONFIG_KASAN +#define KASAN_STACK_ORDER 1 +#else +#define KASAN_STACK_ORDER 0 +#endif + /* thread information allocation */ #ifdef CONFIG_64BIT -#define THREAD_SIZE_ORDER (2) +#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER) #else -#define THREAD_SIZE_ORDER (1) +#define THREAD_SIZE_ORDER (1 + KASAN_STACK_ORDER) #endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index e0133d113216..87adbe47bc15 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -48,6 +48,8 @@ obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o +obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o + obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index df0519a64eaf..df9444397908 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -13,6 +13,7 @@ #include <asm/thread_info.h> #include <asm/ptrace.h> #include <asm/cpu_ops_sbi.h> +#include <asm/suspend.h> void asm_offsets(void); @@ -113,6 +114,8 @@ void asm_offsets(void) OFFSET(PT_BADADDR, pt_regs, badaddr); OFFSET(PT_CAUSE, pt_regs, cause); + OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs); + OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero); OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra); OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp); diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index d2a936195295..ccb617791e56 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -69,11 +69,11 @@ int riscv_of_parent_hartid(struct device_node *node) .uprop = #UPROP, \ .isa_ext_id = EXTID, \ } -/** +/* * Here are the ordering rules of extension naming defined by RISC-V * specification : * 1. All extensions should be separated from other multi-letter extensions - * from other multi-letter extensions by an underscore. + * by an underscore. * 2. The first letter following the 'Z' conventionally indicates the most * closely related alphabetical extension category, IMAFDQLCBKJTPVH. * If multiple 'Z' extensions are named, they should be ordered first @@ -110,7 +110,7 @@ static void print_isa_ext(struct seq_file *f) } } -/** +/* * These are the only valid base (single letter) ISA extensions as per the spec. * It also specifies the canonical order in which it appears in the spec. * Some of the extension may just be a place holder for now (B, K, P, J). diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index 2e16f6732cdf..4f5a6f84e2a4 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -21,7 +21,7 @@ const struct cpu_operations cpu_ops_sbi; * be invoked from multiple threads in parallel. Define a per cpu data * to handle that. */ -DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data); +static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data); static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr, unsigned long priv) diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index ec07f991866a..893b8bb69391 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -16,26 +16,6 @@ #include <asm/image.h> #include "efi-header.S" -#ifdef CONFIG_XIP_KERNEL -.macro XIP_FIXUP_OFFSET reg - REG_L t0, _xip_fixup - add \reg, \reg, t0 -.endm -.macro XIP_FIXUP_FLASH_OFFSET reg - la t0, __data_loc - REG_L t1, _xip_phys_offset - sub \reg, \reg, t1 - add \reg, \reg, t0 -.endm -_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET -_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET -#else -.macro XIP_FIXUP_OFFSET reg -.endm -.macro XIP_FIXUP_FLASH_OFFSET reg -.endm -#endif /* CONFIG_XIP_KERNEL */ - __HEAD ENTRY(_start) /* @@ -89,7 +69,8 @@ pe_head_start: .align 2 #ifdef CONFIG_MMU -relocate: + .global relocate_enable_mmu +relocate_enable_mmu: /* Relocate return address */ la a1, kernel_map XIP_FIXUP_OFFSET a1 @@ -184,7 +165,7 @@ secondary_start_sbi: /* Enable virtual memory and relocate to virtual address */ la a0, swapper_pg_dir XIP_FIXUP_OFFSET a0 - call relocate + call relocate_enable_mmu #endif call setup_trap_vector tail smp_callin @@ -328,7 +309,7 @@ clear_bss_done: #ifdef CONFIG_MMU la a0, early_pg_dir XIP_FIXUP_OFFSET a0 - call relocate + call relocate_enable_mmu #endif /* CONFIG_MMU */ call setup_trap_vector diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 4a48287513c3..c29cef90d1dd 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -69,7 +69,7 @@ static int apply_r_riscv_jal_rela(struct module *me, u32 *location, return 0; } -static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location, +static int apply_r_riscv_rvc_branch_rela(struct module *me, u32 *location, Elf_Addr v) { ptrdiff_t offset = (void *)v - (void *)location; @@ -301,7 +301,7 @@ static int (*reloc_handlers_rela[]) (struct module *me, u32 *location, [R_RISCV_64] = apply_r_riscv_64_rela, [R_RISCV_BRANCH] = apply_r_riscv_branch_rela, [R_RISCV_JAL] = apply_r_riscv_jal_rela, - [R_RISCV_RVC_BRANCH] = apply_r_riscv_rcv_branch_rela, + [R_RISCV_RVC_BRANCH] = apply_r_riscv_rvc_branch_rela, [R_RISCV_RVC_JUMP] = apply_r_riscv_rvc_jump_rela, [R_RISCV_PCREL_HI20] = apply_r_riscv_pcrel_hi20_rela, [R_RISCV_PCREL_LO12_I] = apply_r_riscv_pcrel_lo12_i_rela, diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index 55faa4991b87..3348a61de7d9 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -68,7 +68,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, static bool fill_callchain(void *entry, unsigned long pc) { - return perf_callchain_store(entry, pc); + return perf_callchain_store(entry, pc) == 0; } void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 03ac3aa611f5..504b496787aa 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -23,6 +23,7 @@ #include <asm/string.h> #include <asm/switch_to.h> #include <asm/thread_info.h> +#include <asm/cpuidle.h> register unsigned long gp_in_global __asm__("gp"); @@ -37,7 +38,7 @@ extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { - wait_for_interrupt(); + cpu_do_idle(); raw_local_irq_enable(); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 14d2b53ec322..08d11a53f39e 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,8 +14,6 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); - #ifdef CONFIG_FRAME_POINTER void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, @@ -30,7 +28,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, pc = instruction_pointer(regs); } else if (task == NULL || task == current) { fp = (unsigned long)__builtin_frame_address(0); - sp = sp_in_global; + sp = current_stack_pointer; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ @@ -78,7 +76,7 @@ void notrace walk_stackframe(struct task_struct *task, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - sp = sp_in_global; + sp = current_stack_pointer; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c new file mode 100644 index 000000000000..9ba24fb8cc93 --- /dev/null +++ b/arch/riscv/kernel/suspend.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include <linux/ftrace.h> +#include <asm/csr.h> +#include <asm/suspend.h> + +static void suspend_save_csrs(struct suspend_context *context) +{ + context->scratch = csr_read(CSR_SCRATCH); + context->tvec = csr_read(CSR_TVEC); + context->ie = csr_read(CSR_IE); + + /* + * No need to save/restore IP CSR (i.e. MIP or SIP) because: + * + * 1. For no-MMU (M-mode) kernel, the bits in MIP are set by + * external devices (such as interrupt controller, timer, etc). + * 2. For MMU (S-mode) kernel, the bits in SIP are set by + * M-mode firmware and external devices (such as interrupt + * controller, etc). + */ + +#ifdef CONFIG_MMU + context->satp = csr_read(CSR_SATP); +#endif +} + +static void suspend_restore_csrs(struct suspend_context *context) +{ + csr_write(CSR_SCRATCH, context->scratch); + csr_write(CSR_TVEC, context->tvec); + csr_write(CSR_IE, context->ie); + +#ifdef CONFIG_MMU + csr_write(CSR_SATP, context->satp); +#endif +} + +int cpu_suspend(unsigned long arg, + int (*finish)(unsigned long arg, + unsigned long entry, + unsigned long context)) +{ + int rc = 0; + struct suspend_context context = { 0 }; + + /* Finisher should be non-NULL */ + if (!finish) + return -EINVAL; + + /* Save additional CSRs*/ + suspend_save_csrs(&context); + + /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka finishers) hence disable + * graph tracing during their execution. + */ + pause_graph_tracing(); + + /* Save context on stack */ + if (__cpu_suspend_enter(&context)) { + /* Call the finisher */ + rc = finish(arg, __pa_symbol(__cpu_resume_enter), + (ulong)&context); + + /* + * Should never reach here, unless the suspend finisher + * fails. Successful cpu_suspend() should return from + * __cpu_resume_entry() + */ + if (!rc) + rc = -EOPNOTSUPP; + } + + /* Enable function graph tracer */ + unpause_graph_tracing(); + + /* Restore additional CSRs */ + suspend_restore_csrs(&context); + + return rc; +} diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S new file mode 100644 index 000000000000..4b07b809a2b8 --- /dev/null +++ b/arch/riscv/kernel/suspend_entry.S @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include <linux/linkage.h> +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/csr.h> + + .text + .altmacro + .option norelax + +ENTRY(__cpu_suspend_enter) + /* Save registers (except A0 and T0-T6) */ + REG_S ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) + REG_S sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) + REG_S gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) + REG_S tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) + REG_S s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) + REG_S s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) + REG_S a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) + REG_S a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) + REG_S a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) + REG_S a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) + REG_S a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) + REG_S a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) + REG_S a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) + REG_S s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) + REG_S s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) + REG_S s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) + REG_S s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) + REG_S s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) + REG_S s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) + REG_S s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) + REG_S s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) + REG_S s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) + REG_S s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + + /* Save CSRs */ + csrr t0, CSR_EPC + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) + csrr t0, CSR_STATUS + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) + csrr t0, CSR_TVAL + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) + csrr t0, CSR_CAUSE + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) + + /* Return non-zero value */ + li a0, 1 + + /* Return to C code */ + ret +END(__cpu_suspend_enter) + +ENTRY(__cpu_resume_enter) + /* Load the global pointer */ + .option push + .option norelax + la gp, __global_pointer$ + .option pop + +#ifdef CONFIG_MMU + /* Save A0 and A1 */ + add t0, a0, zero + add t1, a1, zero + + /* Enable MMU */ + la a0, swapper_pg_dir + XIP_FIXUP_OFFSET a0 + call relocate_enable_mmu + + /* Restore A0 and A1 */ + add a0, t0, zero + add a1, t1, zero +#endif + + /* Make A0 point to suspend context */ + add a0, a1, zero + + /* Restore CSRs */ + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) + csrw CSR_EPC, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) + csrw CSR_STATUS, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) + csrw CSR_TVAL, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) + csrw CSR_CAUSE, t0 + + /* Restore registers (except A0 and T0-T6) */ + REG_L ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) + REG_L sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) + REG_L gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) + REG_L tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) + REG_L s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) + REG_L s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) + REG_L a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) + REG_L a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) + REG_L a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) + REG_L a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) + REG_L a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) + REG_L a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) + REG_L a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) + REG_L s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) + REG_L s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) + REG_L s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) + REG_L s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) + REG_L s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) + REG_L s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) + REG_L s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) + REG_L s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) + REG_L s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) + REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + + /* Return zero value */ + add a0, zero, zero + + /* Return to C code */ + ret +END(__cpu_resume_enter) diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 624166004e36..6785aef4cbd4 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -653,8 +653,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.isa); kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); - csr_write(CSR_HGATP, 0); - csr->vsstatus = csr_read(CSR_VSSTATUS); csr->vsie = csr_read(CSR_VSIE); csr->vstvec = csr_read(CSR_VSTVEC); diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index 4449a976e5a6..d4308c512007 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -11,6 +11,7 @@ #include <linux/err.h> #include <linux/kvm_host.h> #include <linux/uaccess.h> +#include <asm/hwcap.h> #ifdef CONFIG_FPU void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9b80e8bed3f6..e084c72104f8 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -58,6 +58,7 @@ config S390 select ALTERNATE_USER_ADDRESS_SPACE select ARCH_32BIT_USTAT_F_TINODE select ARCH_BINFMT_ELF_STATE + select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 @@ -254,6 +255,10 @@ config HAVE_MARCH_Z15_FEATURES def_bool n select HAVE_MARCH_Z14_FEATURES +config HAVE_MARCH_Z16_FEATURES + def_bool n + select HAVE_MARCH_Z15_FEATURES + choice prompt "Processor type" default MARCH_Z196 @@ -311,6 +316,14 @@ config MARCH_Z15 and 8561 series). The kernel will be slightly faster but will not work on older machines. +config MARCH_Z16 + bool "IBM z16" + select HAVE_MARCH_Z16_FEATURES + depends on $(cc-option,-march=z16) + help + Select this to enable optimizations for IBM z16 (3931 and + 3932 series). + endchoice config MARCH_Z10_TUNE @@ -331,6 +344,9 @@ config MARCH_Z14_TUNE config MARCH_Z15_TUNE def_bool TUNE_Z15 || MARCH_Z15 && TUNE_DEFAULT +config MARCH_Z16_TUNE + def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT + choice prompt "Tune code generation" default TUNE_DEFAULT @@ -371,6 +387,10 @@ config TUNE_Z15 bool "IBM z15" depends on $(cc-option,-mtune=z15) +config TUNE_Z16 + bool "IBM z16" + depends on $(cc-option,-mtune=z16) + endchoice config 64BIT diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7a65bca1e5af..e441b60b1812 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -42,6 +42,7 @@ mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12 mflags-$(CONFIG_MARCH_Z13) := -march=z13 mflags-$(CONFIG_MARCH_Z14) := -march=z14 mflags-$(CONFIG_MARCH_Z15) := -march=z15 +mflags-$(CONFIG_MARCH_Z16) := -march=z16 export CC_FLAGS_MARCH := $(mflags-y) @@ -54,6 +55,7 @@ cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14 cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15 +cflags-$(CONFIG_MARCH_Z16_TUNE) += -mtune=z16 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 498bed9b261b..f6dfde577ce8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -499,11 +499,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -588,13 +590,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -690,6 +692,7 @@ CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y +CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y @@ -733,6 +736,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -786,7 +790,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y @@ -814,6 +817,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_DEFERRABLE=y CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 61e36b999f67..706df3a4a867 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -490,11 +490,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -578,13 +580,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -720,6 +722,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -772,7 +775,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c55c668dc3c7..a87fcc45e307 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -26,6 +26,7 @@ CONFIG_CRASH_DUMP=y # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set # CONFIG_GCC_PLUGINS is not set +# CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set @@ -60,7 +61,6 @@ CONFIG_ZFCP=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set -# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set @@ -71,10 +71,10 @@ CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/include/asm/alternative-asm.h b/arch/s390/include/asm/alternative-asm.h index 955d620db23e..bb3837d7387c 100644 --- a/arch/s390/include/asm/alternative-asm.h +++ b/arch/s390/include/asm/alternative-asm.h @@ -37,9 +37,15 @@ * a 2-byte nop if the size of the area is not divisible by 6. */ .macro alt_pad_fill bytes - .fill ( \bytes ) / 6, 6, 0xc0040000 - .fill ( \bytes ) % 6 / 4, 4, 0x47000000 - .fill ( \bytes ) % 6 % 4 / 2, 2, 0x0700 + .rept ( \bytes ) / 6 + brcl 0,0 + .endr + .rept ( \bytes ) % 6 / 4 + nop + .endr + .rept ( \bytes ) % 6 % 4 / 2 + nopr + .endr .endm /* diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index d3880ca764ee..3f2856ed6808 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -71,11 +71,18 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); ".if " oldinstr_pad_len(num) " > 6\n" \ "\tjg " e_oldinstr_pad_end "f\n" \ "6620:\n" \ - "\t.fill (" oldinstr_pad_len(num) " - (6620b-662b)) / 2, 2, 0x0700\n" \ + "\t.rept (" oldinstr_pad_len(num) " - (6620b-662b)) / 2\n" \ + "\tnopr\n" \ ".else\n" \ - "\t.fill " oldinstr_pad_len(num) " / 6, 6, 0xc0040000\n" \ - "\t.fill " oldinstr_pad_len(num) " %% 6 / 4, 4, 0x47000000\n" \ - "\t.fill " oldinstr_pad_len(num) " %% 6 %% 4 / 2, 2, 0x0700\n" \ + "\t.rept " oldinstr_pad_len(num) " / 6\n" \ + "\t.brcl 0,0\n" \ + "\t.endr\n" \ + "\t.rept " oldinstr_pad_len(num) " %% 6 / 4\n" \ + "\tnop\n" \ + "\t.endr\n" \ + "\t.rept " oldinstr_pad_len(num) " %% 6 %% 4 / 2\n" \ + "\tnopr\n" \ + ".endr\n" \ ".endif\n" #define OLDINSTR(oldinstr, num) \ diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index ae75da592ccb..b515cfa62bd9 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -60,11 +60,11 @@ static inline bool ap_instructions_available(void) unsigned long reg1 = 0; asm volatile( - " lgr 0,%[reg0]\n" /* qid into gr0 */ - " lghi 1,0\n" /* 0 into gr1 */ - " lghi 2,0\n" /* 0 into gr2 */ - " .long 0xb2af0000\n" /* PQAP(TAPQ) */ - "0: la %[reg1],1\n" /* 1 into reg1 */ + " lgr 0,%[reg0]\n" /* qid into gr0 */ + " lghi 1,0\n" /* 0 into gr1 */ + " lghi 2,0\n" /* 0 into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */ + "0: la %[reg1],1\n" /* 1 into reg1 */ "1:\n" EX_TABLE(0b, 1b) : [reg1] "+&d" (reg1) @@ -86,11 +86,11 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) unsigned long reg2; asm volatile( - " lgr 0,%[qid]\n" /* qid into gr0 */ - " lghi 2,0\n" /* 0 into gr2 */ - " .long 0xb2af0000\n" /* PQAP(TAPQ) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - " lgr %[reg2],2\n" /* gr2 into reg2 */ + " lgr 0,%[qid]\n" /* qid into gr0 */ + " lghi 2,0\n" /* 0 into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr %[reg2],2\n" /* gr2 into reg2 */ : [reg1] "=&d" (reg1), [reg2] "=&d" (reg2) : [qid] "d" (qid) : "cc", "0", "1", "2"); @@ -128,9 +128,9 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid) struct ap_queue_status reg1; asm volatile( - " lgr 0,%[reg0]\n" /* qid arg into gr0 */ - " .long 0xb2af0000\n" /* PQAP(RAPQ) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr 0,%[reg0]\n" /* qid arg into gr0 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(RAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ : [reg1] "=&d" (reg1) : [reg0] "d" (reg0) : "cc", "0", "1"); @@ -149,9 +149,9 @@ static inline struct ap_queue_status ap_zapq(ap_qid_t qid) struct ap_queue_status reg1; asm volatile( - " lgr 0,%[reg0]\n" /* qid arg into gr0 */ - " .long 0xb2af0000\n" /* PQAP(ZAPQ) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr 0,%[reg0]\n" /* qid arg into gr0 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(ZAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ : [reg1] "=&d" (reg1) : [reg0] "d" (reg0) : "cc", "0", "1"); @@ -190,10 +190,10 @@ static inline int ap_qci(struct ap_config_info *config) struct ap_config_info *reg2 = config; asm volatile( - " lgr 0,%[reg0]\n" /* QCI fc into gr0 */ - " lgr 2,%[reg2]\n" /* ptr to config into gr2 */ - " .long 0xb2af0000\n" /* PQAP(QCI) */ - "0: la %[reg1],0\n" /* good case, QCI fc available */ + " lgr 0,%[reg0]\n" /* QCI fc into gr0 */ + " lgr 2,%[reg2]\n" /* ptr to config into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(QCI) */ + "0: la %[reg1],0\n" /* good case, QCI fc available */ "1:\n" EX_TABLE(0b, 1b) : [reg1] "+&d" (reg1) @@ -246,11 +246,11 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, reg1.qirqctrl = qirqctrl; asm volatile( - " lgr 0,%[reg0]\n" /* qid param into gr0 */ - " lgr 1,%[reg1]\n" /* irq ctrl into gr1 */ - " lgr 2,%[reg2]\n" /* ni addr into gr2 */ - " .long 0xb2af0000\n" /* PQAP(AQIC) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr 0,%[reg0]\n" /* qid param into gr0 */ + " lgr 1,%[reg1]\n" /* irq ctrl into gr1 */ + " lgr 2,%[reg2]\n" /* ni addr into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(AQIC) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ : [reg1] "+&d" (reg1) : [reg0] "d" (reg0), [reg2] "d" (reg2) : "cc", "0", "1", "2"); @@ -297,11 +297,11 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, reg1.value = apinfo->val; asm volatile( - " lgr 0,%[reg0]\n" /* qid param into gr0 */ - " lgr 1,%[reg1]\n" /* qact in info into gr1 */ - " .long 0xb2af0000\n" /* PQAP(QACT) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - " lgr %[reg2],2\n" /* qact out info into reg2 */ + " lgr 0,%[reg0]\n" /* qid param into gr0 */ + " lgr 1,%[reg1]\n" /* qact in info into gr1 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(QACT) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr %[reg2],2\n" /* qact out info into reg2 */ : [reg1] "+&d" (reg1), [reg2] "=&d" (reg2) : [reg0] "d" (reg0) : "cc", "0", "1", "2"); diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index c800199a376b..82388da3f95f 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -74,8 +74,17 @@ static __always_inline void __ctl_clear_bit(unsigned int cr, unsigned int bit) __ctl_load(reg, cr, cr); } -void smp_ctl_set_bit(int cr, int bit); -void smp_ctl_clear_bit(int cr, int bit); +void smp_ctl_set_clear_bit(int cr, int bit, bool set); + +static inline void ctl_set_bit(int cr, int bit) +{ + smp_ctl_set_clear_bit(cr, bit, true); +} + +static inline void ctl_clear_bit(int cr, int bit) +{ + smp_ctl_set_clear_bit(cr, bit, false); +} union ctlreg0 { unsigned long val; @@ -130,8 +139,5 @@ union ctlreg15 { }; }; -#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit) -#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit) - #endif /* __ASSEMBLY__ */ #endif /* __ASM_CTL_REG_H */ diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index eabab24b71dd..2f0a1cacdf85 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -58,7 +58,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static inline bool on_thread_stack(void) { - return !(((unsigned long)(current->stack) ^ current_stack_pointer()) & ~(THREAD_SIZE - 1)); + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); } #endif diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 84ec63145325..ff1e25d515a8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -200,13 +200,7 @@ unsigned long __get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static __always_inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; - - asm volatile("la %0,0(15)" : "=a" (sp)); - return sp; -} +register unsigned long current_stack_pointer asm("r15"); static __always_inline unsigned short stap(void) { @@ -319,11 +313,18 @@ extern void (*s390_base_pgm_handler_fn)(struct pt_regs *regs); extern int memcpy_real(void *, unsigned long, size_t); extern void memcpy_absolute(void *, void *, size_t); -#define mem_assign_absolute(dest, val) do { \ - __typeof__(dest) __tmp = (val); \ - \ - BUILD_BUG_ON(sizeof(__tmp) != sizeof(val)); \ - memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ +#define put_abs_lowcore(member, x) do { \ + unsigned long __abs_address = offsetof(struct lowcore, member); \ + __typeof__(((struct lowcore *)0)->member) __tmp = (x); \ + \ + memcpy_absolute(__va(__abs_address), &__tmp, sizeof(__tmp)); \ +} while (0) + +#define get_abs_lowcore(x, member) do { \ + unsigned long __abs_address = offsetof(struct lowcore, member); \ + __typeof__(((struct lowcore *)0)->member) *__ptr = &(x); \ + \ + memcpy_absolute(__ptr, __va(__abs_address), sizeof(*__ptr)); \ } while (0) extern int s390_isolate_bp(void); diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 888a2f1c9ee3..24a54443c865 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -78,7 +78,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp) { typecheck(int, lp->lock); asm_inline volatile( - ALTERNATIVE("", ".long 0xb2fa0070", 49) /* NIAI 7 */ + ALTERNATIVE("", ".insn rre,0xb2fa0000,7,0", 49) /* NIAI 7 */ " sth %1,%0\n" : "=R" (((unsigned short *) &lp->lock)[1]) : "d" (0) : "cc", "memory"); diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 275f4258fbd5..f8500191993d 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -46,7 +46,7 @@ struct stack_frame { }; /* - * Unlike current_stack_pointer() which simply returns current value of %r15 + * Unlike current_stack_pointer which simply contains the current value of %r15 * current_frame_address() returns function stack frame address, which matches * %r15 upon function invocation. It may differ from %r15 later if function * allocates stack for local variables or new stack frame to call other diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h index ad2c996e7e93..fde7e6b1df48 100644 --- a/arch/s390/include/asm/syscall_wrapper.h +++ b/arch/s390/include/asm/syscall_wrapper.h @@ -162,4 +162,4 @@ __diag_pop(); \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#endif /* _ASM_X86_SYSCALL_WRAPPER_H */ +#endif /* _ASM_S390_SYSCALL_WRAPPER_H */ diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h index 5ebf534ef753..0bf06f1682d8 100644 --- a/arch/s390/include/asm/unwind.h +++ b/arch/s390/include/asm/unwind.h @@ -4,6 +4,8 @@ #include <linux/sched.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> +#include <linux/llist.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> @@ -36,10 +38,21 @@ struct unwind_state { struct pt_regs *regs; unsigned long sp, ip; int graph_idx; + struct llist_node *kr_cur; bool reliable; bool error; }; +/* Recover the return address modified by kretprobe and ftrace_graph. */ +static inline unsigned long unwind_recover_ret_addr(struct unwind_state *state, + unsigned long ip) +{ + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); + if (is_kretprobe_trampoline(ip)) + ip = kretprobe_find_ret_addr(state->task, (void *)state->sp, &state->kr_cur); + return ip; +} + void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long first_frame); bool unwind_next_frame(struct unwind_state *state); diff --git a/arch/s390/include/asm/user.h b/arch/s390/include/asm/user.h index 0ca572ced21b..8e8aaf48582e 100644 --- a/arch/s390/include/asm/user.h +++ b/arch/s390/include/asm/user.h @@ -67,9 +67,5 @@ struct user { unsigned long magic; /* To uniquely identify a core file */ char u_comm[32]; /* User command that was responsible */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif /* _S390_USER_H */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index a601a518b569..59b69c8ab5e1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -121,22 +121,22 @@ _LPP_OFFSET = __LC_LPP .endm .macro BPOFF - ALTERNATIVE "", ".long 0xb2e8c000", 82 + ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,12,0", 82 .endm .macro BPON - ALTERNATIVE "", ".long 0xb2e8d000", 82 + ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,13,0", 82 .endm .macro BPENTER tif_ptr,tif_mask - ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .long 0xb2e8d000", \ + ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .insn rrf,0xb2e80000,0,0,13,0", \ "", 82 .endm .macro BPEXIT tif_ptr,tif_mask TSTMSK \tif_ptr,\tif_mask - ALTERNATIVE "jz .+8; .long 0xb2e8c000", \ - "jnz .+8; .long 0xb2e8d000", 82 + ALTERNATIVE "jz .+8; .insn rrf,0xb2e80000,0,0,12,0", \ + "jnz .+8; .insn rrf,0xb2e80000,0,0,13,0", 82 .endm /* diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 28ae7df26c4a..1cc85b8ff42e 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1646,8 +1646,8 @@ static void dump_reipl_run(struct shutdown_trigger *trigger) csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); - mem_assign_absolute(S390_lowcore.ipib, ipib); - mem_assign_absolute(S390_lowcore.ipib_checksum, csum); + put_abs_lowcore(ipib, ipib); + put_abs_lowcore(ipib_checksum, csum); dump_run(trigger); } diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index e32c14fd1282..0032bdbe8e3f 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -284,11 +284,11 @@ NOKPROBE_SYMBOL(pop_kprobe); void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { - ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14]; - ri->fp = NULL; + ri->ret_addr = (kprobe_opcode_t *)regs->gprs[14]; + ri->fp = (void *)regs->gprs[15]; /* Replace the return addr with trampoline addr */ - regs->gprs[14] = (unsigned long) &__kretprobe_trampoline; + regs->gprs[14] = (unsigned long)&__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -385,7 +385,7 @@ NOKPROBE_SYMBOL(arch_kretprobe_fixup_return); */ void trampoline_probe_handler(struct pt_regs *regs) { - kretprobe_trampoline_handler(regs, NULL); + kretprobe_trampoline_handler(regs, (void *)regs->gprs[15]); } NOKPROBE_SYMBOL(trampoline_probe_handler); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 088d57a3083f..6ebf02e15c85 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -54,7 +54,7 @@ static void __do_machine_kdump(void *image) * This need to be done *after* s390_reset_system set the * prefix register of this CPU to zero */ - memcpy((void *) __LC_FPREGS_SAVE_AREA, + memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA), (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512); __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); @@ -226,7 +226,7 @@ void arch_crash_save_vmcoreinfo(void) vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31); vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); + put_abs_lowcore(vmcore_info, paddr_vmcoreinfo_note()); } void machine_shutdown(void) diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 6b5b64e67eee..1acc2e05d70f 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -63,7 +63,7 @@ void __init os_info_init(void) os_info.version_minor = OS_INFO_VERSION_MINOR; os_info.magic = OS_INFO_MAGIC; os_info.csum = os_info_csum(&os_info); - mem_assign_absolute(S390_lowcore.os_info, __pa(ptr)); + put_abs_lowcore(os_info, __pa(ptr)); } #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 7a74ea5f7531..aa0e0e7fc773 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -283,6 +283,10 @@ static int __init setup_elf_platform(void) case 0x8562: strcpy(elf_platform, "z15"); break; + case 0x3931: + case 0x3932: + strcpy(elf_platform, "z16"); + break; } return 0; } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 84e23fcc1106..d860ac300919 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -481,11 +481,11 @@ static void __init setup_lowcore_dat_off(void) lc->mcck_stack = mcck_stack + STACK_INIT_OFFSET; /* Setup absolute zero lowcore */ - mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack); - mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn); - mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data); - mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source); - mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw); + put_abs_lowcore(restart_stack, lc->restart_stack); + put_abs_lowcore(restart_fn, lc->restart_fn); + put_abs_lowcore(restart_data, lc->restart_data); + put_abs_lowcore(restart_source, lc->restart_source); + put_abs_lowcore(restart_psw, lc->restart_psw); lc->spinlock_lockval = arch_spin_lockval(0); lc->spinlock_index = 0; @@ -501,6 +501,7 @@ static void __init setup_lowcore_dat_off(void) static void __init setup_lowcore_dat_on(void) { struct lowcore *lc = lowcore_ptr[0]; + int cr; __ctl_clear_bit(0, 28); S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT; @@ -509,10 +510,10 @@ static void __init setup_lowcore_dat_on(void) S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT; __ctl_store(S390_lowcore.cregs_save_area, 0, 15); __ctl_set_bit(0, 28); - mem_assign_absolute(S390_lowcore.restart_flags, RESTART_FLAG_CTLREGS); - mem_assign_absolute(S390_lowcore.program_new_psw, lc->program_new_psw); - memcpy_absolute(&S390_lowcore.cregs_save_area, lc->cregs_save_area, - sizeof(S390_lowcore.cregs_save_area)); + put_abs_lowcore(restart_flags, RESTART_FLAG_CTLREGS); + put_abs_lowcore(program_new_psw, lc->program_new_psw); + for (cr = 0; cr < ARRAY_SIZE(lc->cregs_save_area); cr++) + put_abs_lowcore(cregs_save_area[cr], lc->cregs_save_area[cr]); } static struct resource code_resource = { diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 127da1850b06..30c91d565933 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -213,7 +213,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) if (nmi_alloc_mcesa(&lc->mcesad)) goto out; lowcore_ptr[cpu] = lc; - pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc); + pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, __pa(lc)); return 0; out: @@ -326,10 +326,17 @@ static void pcpu_delegate(struct pcpu *pcpu, /* Stop target cpu (if func returns this stops the current cpu). */ pcpu_sigp_retry(pcpu, SIGP_STOP, 0); /* Restart func on the target cpu and stop the current cpu. */ - mem_assign_absolute(lc->restart_stack, stack); - mem_assign_absolute(lc->restart_fn, (unsigned long) func); - mem_assign_absolute(lc->restart_data, (unsigned long) data); - mem_assign_absolute(lc->restart_source, source_cpu); + if (lc) { + lc->restart_stack = stack; + lc->restart_fn = (unsigned long)func; + lc->restart_data = (unsigned long)data; + lc->restart_source = source_cpu; + } else { + put_abs_lowcore(restart_stack, stack); + put_abs_lowcore(restart_fn, (unsigned long)func); + put_abs_lowcore(restart_data, (unsigned long)data); + put_abs_lowcore(restart_source, source_cpu); + } __bpon(); asm volatile( "0: sigp 0,%0,%2 # sigp restart to target cpu\n" @@ -570,39 +577,27 @@ static void smp_ctl_bit_callback(void *info) } static DEFINE_SPINLOCK(ctl_lock); -static unsigned long ctlreg; -/* - * Set a bit in a control register of all cpus - */ -void smp_ctl_set_bit(int cr, int bit) +void smp_ctl_set_clear_bit(int cr, int bit, bool set) { - struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr }; - - spin_lock(&ctl_lock); - memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg)); - __set_bit(bit, &ctlreg); - memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg)); - spin_unlock(&ctl_lock); - on_each_cpu(smp_ctl_bit_callback, &parms, 1); -} -EXPORT_SYMBOL(smp_ctl_set_bit); - -/* - * Clear a bit in a control register of all cpus - */ -void smp_ctl_clear_bit(int cr, int bit) -{ - struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr }; + struct ec_creg_mask_parms parms = { .cr = cr, }; + u64 ctlreg; + if (set) { + parms.orval = 1UL << bit; + parms.andval = -1UL; + } else { + parms.orval = 0; + parms.andval = ~(1UL << bit); + } spin_lock(&ctl_lock); - memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg)); - __clear_bit(bit, &ctlreg); - memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg)); + get_abs_lowcore(ctlreg, cregs_save_area[cr]); + ctlreg = (ctlreg & parms.andval) | parms.orval; + put_abs_lowcore(cregs_save_area[cr], ctlreg); spin_unlock(&ctl_lock); on_each_cpu(smp_ctl_bit_callback, &parms, 1); } -EXPORT_SYMBOL(smp_ctl_clear_bit); +EXPORT_SYMBOL(smp_ctl_set_clear_bit); #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile index b98f25029b8e..fb85e797946d 100644 --- a/arch/s390/kernel/syscalls/Makefile +++ b/arch/s390/kernel/syscalls/Makefile @@ -21,8 +21,7 @@ uapi: $(uapi-hdrs-y) # Create output directory if not already present -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) filechk_syshdr = $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $< diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 674c65019434..1d2aa448d103 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -141,10 +141,10 @@ static inline void do_fp_trap(struct pt_regs *regs, __u32 fpc) do_trap(regs, SIGFPE, si_code, "floating point exception"); } -static void translation_exception(struct pt_regs *regs) +static void translation_specification_exception(struct pt_regs *regs) { /* May never happen. */ - panic("Translation exception"); + panic("Translation-Specification Exception"); } static void illegal_op(struct pt_regs *regs) @@ -368,7 +368,7 @@ static void (*pgm_check_table[128])(struct pt_regs *regs) = { [0x0f] = hfp_divide_exception, [0x10] = do_dat_exception, [0x11] = do_dat_exception, - [0x12] = translation_exception, + [0x12] = translation_specification_exception, [0x13] = special_op_exception, [0x14] = default_trap_handler, [0x15] = operand_exception, diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 707fd99f6734..0ece156fdd7c 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -64,8 +64,8 @@ bool unwind_next_frame(struct unwind_state *state) ip = READ_ONCE_NOCHECK(sf->gprs[8]); reliable = false; regs = NULL; - if (!__kernel_text_address(ip)) { - /* skip bogus %r14 */ + /* skip bogus %r14 or if is the same as regs->psw.addr */ + if (!__kernel_text_address(ip) || state->ip == unwind_recover_ret_addr(state, ip)) { state->regs = NULL; return unwind_next_frame(state); } @@ -103,13 +103,11 @@ bool unwind_next_frame(struct unwind_state *state) if (sp & 0x7) goto out_err; - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp); - /* Update unwind state */ state->sp = sp; - state->ip = ip; state->regs = regs; state->reliable = reliable; + state->ip = unwind_recover_ret_addr(state, ip); return true; out_err: @@ -161,12 +159,10 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, ip = READ_ONCE_NOCHECK(sf->gprs[8]); } - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); - /* Update unwind state */ state->sp = sp; - state->ip = ip; state->reliable = true; + state->ip = unwind_recover_ret_addr(state, ip); if (!first_frame) return; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ab73d99483fe..156d1c25a3c1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3462,7 +3462,7 @@ void exit_sie(struct kvm_vcpu *vcpu) /* Kick a guest cpu out of SIE to process a request synchronously */ void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu) { - kvm_make_request(req, vcpu); + __kvm_make_request(req, vcpu); kvm_s390_vcpu_request(vcpu); } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 7f7c0d6af2ce..cc7c9599f43e 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -137,12 +137,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) /* Allocate variable storage */ vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); vlen += uv_info.guest_virt_base_stor_len; - /* - * The Create Secure Configuration Ultravisor Call does not support - * using large pages for the virtual memory area. - * This is a hardware limitation. - */ - kvm->arch.pv.stor_var = vmalloc_no_huge(vlen); + kvm->arch.pv.stor_var = vzalloc(vlen); if (!kvm->arch.pv.stor_var) goto out_err; return 0; diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 692dc84cd19c..5e7ea8b111e8 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -75,7 +75,7 @@ static inline int arch_load_niai4(int *lock) int owner; asm_inline volatile( - ALTERNATIVE("", ".long 0xb2fa0040", 49) /* NIAI 4 */ + ALTERNATIVE("", ".insn rre,0xb2fa0000,4,0", 49) /* NIAI 4 */ " l %0,%1\n" : "=d" (owner) : "Q" (*lock) : "memory"); return owner; @@ -86,7 +86,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new) int expected = old; asm_inline volatile( - ALTERNATIVE("", ".long 0xb2fa0080", 49) /* NIAI 8 */ + ALTERNATIVE("", ".insn rre,0xb2fa0000,8,0", 49) /* NIAI 8 */ " cs %0,%3,%1\n" : "=d" (old), "=Q" (*lock) : "0" (old), "d" (new), "Q" (*lock) diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index c01f02887de4..5a053b393d5c 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -47,7 +47,7 @@ static void print_backtrace(char *bt) static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, unsigned long sp) { - int frame_count, prev_is_func2, seen_func2_func1; + int frame_count, prev_is_func2, seen_func2_func1, seen_kretprobe_trampoline; const int max_frames = 128; struct unwind_state state; size_t bt_pos = 0; @@ -63,6 +63,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, frame_count = 0; prev_is_func2 = 0; seen_func2_func1 = 0; + seen_kretprobe_trampoline = 0; unwind_for_each_frame(&state, task, regs, sp) { unsigned long addr = unwind_get_return_address(&state); char sym[KSYM_SYMBOL_LEN]; @@ -88,6 +89,8 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, if (prev_is_func2 && str_has_prefix(sym, "unwindme_func1")) seen_func2_func1 = 1; prev_is_func2 = str_has_prefix(sym, "unwindme_func2"); + if (str_has_prefix(sym, "__kretprobe_trampoline+0x0/")) + seen_kretprobe_trampoline = 1; } /* Check the results. */ @@ -103,6 +106,10 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, kunit_err(current_test, "Maximum number of frames exceeded\n"); ret = -EINVAL; } + if (seen_kretprobe_trampoline) { + kunit_err(current_test, "__kretprobe_trampoline+0x0 in unwinding results\n"); + ret = -EINVAL; + } if (ret || force_bt) print_backtrace(bt); kfree(bt); @@ -132,36 +139,50 @@ static struct unwindme *unwindme; #define UWM_PGM 0x40 /* Unwind from program check handler */ #define UWM_KPROBE_ON_FTRACE 0x80 /* Unwind from kprobe handler called via ftrace. */ #define UWM_FTRACE 0x100 /* Unwind from ftrace handler. */ -#define UWM_KRETPROBE 0x200 /* Unwind kretprobe handlers. */ +#define UWM_KRETPROBE 0x200 /* Unwind through kretprobed function. */ +#define UWM_KRETPROBE_HANDLER 0x400 /* Unwind from kretprobe handler. */ -static __always_inline unsigned long get_psw_addr(void) +static __always_inline struct pt_regs fake_pt_regs(void) { - unsigned long psw_addr; + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + regs.gprs[15] = current_stack_pointer; asm volatile( "basr %[psw_addr],0\n" - : [psw_addr] "=d" (psw_addr)); - return psw_addr; + : [psw_addr] "=d" (regs.psw.addr)); + return regs; } static int kretprobe_ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs) { struct unwindme *u = unwindme; + if (!(u->flags & UWM_KRETPROBE_HANDLER)) + return 0; + u->ret = test_unwind(NULL, (u->flags & UWM_REGS) ? regs : NULL, (u->flags & UWM_SP) ? u->sp : 0); return 0; } -static noinline notrace void test_unwind_kretprobed_func(void) +static noinline notrace int test_unwind_kretprobed_func(struct unwindme *u) { - asm volatile(" nop\n"); + struct pt_regs regs; + + if (!(u->flags & UWM_KRETPROBE)) + return 0; + + regs = fake_pt_regs(); + return test_unwind(NULL, (u->flags & UWM_REGS) ? ®s : NULL, + (u->flags & UWM_SP) ? u->sp : 0); } -static noinline void test_unwind_kretprobed_func_caller(void) +static noinline int test_unwind_kretprobed_func_caller(struct unwindme *u) { - test_unwind_kretprobed_func(); + return test_unwind_kretprobed_func(u); } static int test_unwind_kretprobe(struct unwindme *u) @@ -187,10 +208,12 @@ static int test_unwind_kretprobe(struct unwindme *u) return -EINVAL; } - test_unwind_kretprobed_func_caller(); + ret = test_unwind_kretprobed_func_caller(u); unregister_kretprobe(&my_kretprobe); unwindme = NULL; - return u->ret; + if (u->flags & UWM_KRETPROBE_HANDLER) + ret = u->ret; + return ret; } static int kprobe_pre_handler(struct kprobe *p, struct pt_regs *regs) @@ -304,16 +327,13 @@ static noinline int unwindme_func4(struct unwindme *u) return 0; } else if (u->flags & (UWM_PGM | UWM_KPROBE_ON_FTRACE)) { return test_unwind_kprobe(u); - } else if (u->flags & (UWM_KRETPROBE)) { + } else if (u->flags & (UWM_KRETPROBE | UWM_KRETPROBE_HANDLER)) { return test_unwind_kretprobe(u); } else if (u->flags & UWM_FTRACE) { return test_unwind_ftrace(u); } else { - struct pt_regs regs; + struct pt_regs regs = fake_pt_regs(); - memset(®s, 0, sizeof(regs)); - regs.psw.addr = get_psw_addr(); - regs.gprs[15] = current_stack_pointer(); return test_unwind(NULL, (u->flags & UWM_REGS) ? ®s : NULL, (u->flags & UWM_SP) ? u->sp : 0); @@ -452,6 +472,10 @@ static const struct test_params param_list[] = { TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_SP), TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_REGS), TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_SP | UWM_REGS), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_SP), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_REGS), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_SP | UWM_REGS), }; /* diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 792f8e0f2178..e563cb65c0c4 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -69,6 +69,7 @@ struct zpci_dev *get_zdev_by_fid(u32 fid) list_for_each_entry(tmp, &zpci_list, entry) { if (tmp->fid == fid) { zdev = tmp; + zpci_zdev_get(zdev); break; } } @@ -399,7 +400,7 @@ EXPORT_SYMBOL(pci_iounmap); static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct zpci_dev *zdev = get_zdev_by_bus(bus, devfn); + struct zpci_dev *zdev = zdev_from_bus(bus, devfn); return (zdev) ? zpci_cfg_load(zdev, where, val, size) : -ENODEV; } @@ -407,7 +408,7 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct zpci_dev *zdev = get_zdev_by_bus(bus, devfn); + struct zpci_dev *zdev = zdev_from_bus(bus, devfn); return (zdev) ? zpci_cfg_store(zdev, where, val, size) : -ENODEV; } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e359d2686178..e96c9860e064 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -19,7 +19,8 @@ void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error); void zpci_release_device(struct kref *kref); static inline void zpci_zdev_put(struct zpci_dev *zdev) { - kref_put(&zdev->kref, zpci_release_device); + if (zdev) + kref_put(&zdev->kref, zpci_release_device); } static inline void zpci_zdev_get(struct zpci_dev *zdev) @@ -32,8 +33,8 @@ void zpci_free_domain(int domain); int zpci_setup_bus_resources(struct zpci_dev *zdev, struct list_head *resources); -static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, - unsigned int devfn) +static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, + unsigned int devfn) { struct zpci_bus *zbus = bus->sysdata; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 63f3e057c168..1057d7af4a55 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -23,6 +23,8 @@ #include <asm/clp.h> #include <uapi/asm/clp.h> +#include "pci_bus.h" + bool zpci_unique_uid; void update_uid_checking(bool new) @@ -404,8 +406,11 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data) return; zdev = get_zdev_by_fid(entry->fid); - if (!zdev) - zpci_create_device(entry->fid, entry->fh, entry->config_state); + if (zdev) { + zpci_zdev_put(zdev); + return; + } + zpci_create_device(entry->fid, entry->fh, entry->config_state); } int clp_scan_pci_devices(void) diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 2e3e5b278925..ea9db5cea64e 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -269,7 +269,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); if (!pdev) - return; + goto no_pdev; switch (ccdf->pec) { case 0x003a: /* Service Action or Error Recovery Successful */ @@ -286,6 +286,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) break; } pci_dev_put(pdev); +no_pdev: + zpci_zdev_put(zdev); } void zpci_event_error(void *data) @@ -314,6 +316,7 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); + bool existing_zdev = !!zdev; enum zpci_state state; zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n", @@ -378,6 +381,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) default: break; } + if (existing_zdev) + zpci_zdev_put(zdev); } void zpci_event_availability(void *data) diff --git a/arch/sh/include/asm/user.h b/arch/sh/include/asm/user.h index 7dfd3f6461e6..12ea0f3f4419 100644 --- a/arch/sh/include/asm/user.h +++ b/arch/sh/include/asm/user.h @@ -52,10 +52,4 @@ struct user { char u_comm[32]; /* user command name */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_DATA_START_ADDR (u.start_data) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) - #endif /* __ASM_SH_USER_H */ diff --git a/arch/sh/kernel/syscalls/Makefile b/arch/sh/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/sh/kernel/syscalls/Makefile +++ b/arch/sh/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/sparc/kernel/syscalls/Makefile b/arch/sparc/kernel/syscalls/Makefile index d63f18dd058d..8440c16dfb22 100644 --- a/arch/sparc/kernel/syscalls/Makefile +++ b/arch/sparc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 6ead1e240457..8ca67a692683 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -224,7 +224,7 @@ void mconsole_go(struct mc_request *req) void mconsole_stop(struct mc_request *req) { - deactivate_fd(req->originating_fd, MCONSOLE_IRQ); + block_signals(); os_set_fd_block(req->originating_fd, 1); mconsole_reply(req, "stopped", 0, 0); for (;;) { @@ -247,6 +247,7 @@ void mconsole_stop(struct mc_request *req) } os_set_fd_block(req->originating_fd, 0); mconsole_reply(req, "", 0, 0); + unblock_signals(); } static DEFINE_SPINLOCK(mc_devices_lock); diff --git a/arch/um/drivers/port_user.c b/arch/um/drivers/port_user.c index 5b5b64cb1071..3c62ae81df62 100644 --- a/arch/um/drivers/port_user.c +++ b/arch/um/drivers/port_user.c @@ -5,6 +5,7 @@ #include <stdio.h> #include <stdlib.h> +#include <string.h> #include <errno.h> #include <termios.h> #include <unistd.h> @@ -167,14 +168,29 @@ static void port_pre_exec(void *arg) int port_connection(int fd, int *socket, int *pid_out) { int new, err; - char *argv[] = { "/usr/sbin/in.telnetd", "-L", + char *env; + char *argv[] = { "in.telnetd", "-L", OS_LIB_PATH "/uml/port-helper", NULL }; struct port_pre_exec_data data; + if ((env = getenv("UML_PORT_HELPER"))) + argv[2] = env; + new = accept(fd, NULL, 0); if (new < 0) return -errno; + err = os_access(argv[2], X_OK); + if (err < 0) { + printk(UM_KERN_ERR "port_connection : error accessing port-helper " + "executable at %s: %s\n", argv[2], strerror(-err)); + if (env == NULL) + printk(UM_KERN_ERR "Set UML_PORT_HELPER environment " + "variable to path to uml-utilities port-helper " + "binary\n"); + goto out_close; + } + err = os_pipe(socket, 0, 0); if (err < 0) goto out_close; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 69d2d0049a61..b03269faef71 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1526,13 +1526,19 @@ static void do_io(struct io_thread_req *req, struct io_desc *desc) } break; case REQ_OP_DISCARD: - case REQ_OP_WRITE_ZEROES: n = os_falloc_punch(req->fds[bit], off, len); if (n) { req->error = map_error(-n); return; } break; + case REQ_OP_WRITE_ZEROES: + n = os_falloc_zeroes(req->fds[bit], off, len); + if (n) { + req->error = map_error(-n); + return; + } + break; default: WARN_ON_ONCE(1); req->error = BLK_STS_NOTSUPP; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 4fc1a5d70dcf..1d6f6a66766c 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -67,6 +67,7 @@ static LIST_HEAD(vector_devices); static int driver_registered; static void vector_eth_configure(int n, struct arglist *def); +static int vector_mmsg_rx(struct vector_private *vp, int budget); /* Argument accessors to set variables (and/or set default values) * mtu, buffer sizing, default headroom, etc @@ -77,7 +78,6 @@ static void vector_eth_configure(int n, struct arglist *def); #define DEFAULT_VECTOR_SIZE 64 #define TX_SMALL_PACKET 128 #define MAX_IOV_SIZE (MAX_SKB_FRAGS + 1) -#define MAX_ITERATIONS 64 static const struct { const char string[ETH_GSTRING_LEN]; @@ -458,7 +458,6 @@ static int vector_send(struct vector_queue *qi) vp->estats.tx_queue_running_average = (vp->estats.tx_queue_running_average + result) >> 1; } - netif_trans_update(qi->dev); netif_wake_queue(qi->dev); /* if TX is busy, break out of the send loop, * poll write IRQ will reschedule xmit for us @@ -470,8 +469,6 @@ static int vector_send(struct vector_queue *qi) } } spin_unlock(&qi->head_lock); - } else { - tasklet_schedule(&vp->tx_poll); } return queue_depth; } @@ -608,7 +605,7 @@ out_fail: /* * We do not use the RX queue as a proper wraparound queue for now - * This is not necessary because the consumption via netif_rx() + * This is not necessary because the consumption via napi_gro_receive() * happens in-line. While we can try using the return code of * netif_rx() for flow control there are no drivers doing this today. * For this RX specific use we ignore the tail/head locks and @@ -896,7 +893,7 @@ static int vector_legacy_rx(struct vector_private *vp) skb->protocol = eth_type_trans(skb, skb->dev); vp->dev->stats.rx_bytes += skb->len; vp->dev->stats.rx_packets++; - netif_rx(skb); + napi_gro_receive(&vp->napi, skb); } else { dev_kfree_skb_irq(skb); } @@ -955,7 +952,7 @@ drop: * mmsg vector matched to an skb vector which we prepared earlier. */ -static int vector_mmsg_rx(struct vector_private *vp) +static int vector_mmsg_rx(struct vector_private *vp, int budget) { int packet_count, i; struct vector_queue *qi = vp->rx_queue; @@ -972,6 +969,9 @@ static int vector_mmsg_rx(struct vector_private *vp) /* Fire the Lazy Gun - get as many packets as we can in one go. */ + if (budget > qi->max_depth) + budget = qi->max_depth; + packet_count = uml_vector_recvmmsg( vp->fds->rx_fd, qi->mmsg_vector, qi->max_depth, 0); @@ -1021,7 +1021,7 @@ static int vector_mmsg_rx(struct vector_private *vp) */ vp->dev->stats.rx_bytes += skb->len; vp->dev->stats.rx_packets++; - netif_rx(skb); + napi_gro_receive(&vp->napi, skb); } else { /* Overlay header too short to do anything - discard. * We can actually keep this skb and reuse it, @@ -1044,23 +1044,6 @@ static int vector_mmsg_rx(struct vector_private *vp) return packet_count; } -static void vector_rx(struct vector_private *vp) -{ - int err; - int iter = 0; - - if ((vp->options & VECTOR_RX) > 0) - while (((err = vector_mmsg_rx(vp)) > 0) && (iter < MAX_ITERATIONS)) - iter++; - else - while (((err = vector_legacy_rx(vp)) > 0) && (iter < MAX_ITERATIONS)) - iter++; - if ((err != 0) && net_ratelimit()) - netdev_err(vp->dev, "vector_rx: error(%d)\n", err); - if (iter == MAX_ITERATIONS) - netdev_err(vp->dev, "vector_rx: device stuck, remote end may have closed the connection\n"); -} - static int vector_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct vector_private *vp = netdev_priv(dev); @@ -1085,25 +1068,15 @@ static int vector_net_start_xmit(struct sk_buff *skb, struct net_device *dev) netdev_sent_queue(vp->dev, skb->len); queue_depth = vector_enqueue(vp->tx_queue, skb); - /* if the device queue is full, stop the upper layers and - * flush it. - */ - - if (queue_depth >= vp->tx_queue->max_depth - 1) { - vp->estats.tx_kicks++; - netif_stop_queue(dev); - vector_send(vp->tx_queue); - return NETDEV_TX_OK; - } - if (netdev_xmit_more()) { + if (queue_depth < vp->tx_queue->max_depth && netdev_xmit_more()) { mod_timer(&vp->tl, vp->coalesce); return NETDEV_TX_OK; + } else { + queue_depth = vector_send(vp->tx_queue); + if (queue_depth > 0) + napi_schedule(&vp->napi); } - if (skb->len < TX_SMALL_PACKET) { - vp->estats.tx_kicks++; - vector_send(vp->tx_queue); - } else - tasklet_schedule(&vp->tx_poll); + return NETDEV_TX_OK; } @@ -1114,7 +1087,7 @@ static irqreturn_t vector_rx_interrupt(int irq, void *dev_id) if (!netif_running(dev)) return IRQ_NONE; - vector_rx(vp); + napi_schedule(&vp->napi); return IRQ_HANDLED; } @@ -1133,8 +1106,7 @@ static irqreturn_t vector_tx_interrupt(int irq, void *dev_id) * tweaking the IRQ mask less costly */ - if (vp->in_write_poll) - tasklet_schedule(&vp->tx_poll); + napi_schedule(&vp->napi); return IRQ_HANDLED; } @@ -1161,7 +1133,8 @@ static int vector_net_close(struct net_device *dev) um_free_irq(vp->tx_irq, dev); vp->tx_irq = 0; } - tasklet_kill(&vp->tx_poll); + napi_disable(&vp->napi); + netif_napi_del(&vp->napi); if (vp->fds->rx_fd > 0) { if (vp->bpf) uml_vector_detach_bpf(vp->fds->rx_fd, vp->bpf); @@ -1193,15 +1166,32 @@ static int vector_net_close(struct net_device *dev) return 0; } -/* TX tasklet */ - -static void vector_tx_poll(struct tasklet_struct *t) +static int vector_poll(struct napi_struct *napi, int budget) { - struct vector_private *vp = from_tasklet(vp, t, tx_poll); + struct vector_private *vp = container_of(napi, struct vector_private, napi); + int work_done = 0; + int err; + bool tx_enqueued = false; - vp->estats.tx_kicks++; - vector_send(vp->tx_queue); + if ((vp->options & VECTOR_TX) != 0) + tx_enqueued = (vector_send(vp->tx_queue) > 0); + if ((vp->options & VECTOR_RX) > 0) + err = vector_mmsg_rx(vp, budget); + else { + err = vector_legacy_rx(vp); + if (err > 0) + err = 1; + } + if (err > 0) + work_done += err; + + if (tx_enqueued || err > 0) + napi_schedule(napi); + if (work_done < budget) + napi_complete_done(napi, work_done); + return work_done; } + static void vector_reset_tx(struct work_struct *work) { struct vector_private *vp = @@ -1265,6 +1255,9 @@ static int vector_net_open(struct net_device *dev) goto out_close; } + netif_napi_add(vp->dev, &vp->napi, vector_poll, get_depth(vp->parsed)); + napi_enable(&vp->napi); + /* READ IRQ */ err = um_request_irq( irq_rr + VECTOR_BASE_IRQ, vp->fds->rx_fd, @@ -1306,15 +1299,15 @@ static int vector_net_open(struct net_device *dev) uml_vector_attach_bpf(vp->fds->rx_fd, vp->bpf); netif_start_queue(dev); + vector_reset_stats(vp); /* clear buffer - it can happen that the host side of the interface * is full when we get here. In this case, new data is never queued, * SIGIOs never arrive, and the net never works. */ - vector_rx(vp); + napi_schedule(&vp->napi); - vector_reset_stats(vp); vdevice = find_device(vp->unit); vdevice->opened = 1; @@ -1543,15 +1536,16 @@ static const struct net_device_ops vector_netdev_ops = { #endif }; - static void vector_timer_expire(struct timer_list *t) { struct vector_private *vp = from_timer(vp, t, tl); vp->estats.tx_kicks++; - vector_send(vp->tx_queue); + napi_schedule(&vp->napi); } + + static void vector_eth_configure( int n, struct arglist *def @@ -1634,7 +1628,6 @@ static void vector_eth_configure( }); dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST); - tasklet_setup(&vp->tx_poll, vector_tx_poll); INIT_WORK(&vp->reset_tx, vector_reset_tx); timer_setup(&vp->tl, vector_timer_expire, 0); diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h index 8fff93a75a92..2a1fa8e0f3e1 100644 --- a/arch/um/drivers/vector_kern.h +++ b/arch/um/drivers/vector_kern.h @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/workqueue.h> #include <linux/interrupt.h> + #include "vector_user.h" /* Queue structure specially adapted for multiple enqueue/dequeue @@ -72,6 +73,7 @@ struct vector_private { struct list_head list; spinlock_t lock; struct net_device *dev; + struct napi_struct napi ____cacheline_aligned; int unit; @@ -115,7 +117,6 @@ struct vector_private { spinlock_t stats_lock; - struct tasklet_struct tx_poll; bool rexmit_scheduled; bool opened; bool in_write_poll; diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index e4ffeb9a1fa4..c650e428432b 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -771,7 +771,7 @@ int uml_vector_detach_bpf(int fd, void *bpf) printk(KERN_ERR BPF_DETACH_FAIL, prog->len, prog->filter, fd, -errno); return err; } -void *uml_vector_default_bpf(void *mac) +void *uml_vector_default_bpf(const void *mac) { struct sock_filter *bpf; uint32_t *mac1 = (uint32_t *)(mac + 2); diff --git a/arch/um/drivers/vector_user.h b/arch/um/drivers/vector_user.h index d29d5fdd98fa..3a73d17a0161 100644 --- a/arch/um/drivers/vector_user.h +++ b/arch/um/drivers/vector_user.h @@ -97,7 +97,7 @@ extern int uml_vector_recvmmsg( unsigned int vlen, unsigned int flags ); -extern void *uml_vector_default_bpf(void *mac); +extern void *uml_vector_default_bpf(const void *mac); extern void *uml_vector_user_bpf(char *filename); extern int uml_vector_attach_bpf(int fd, void *bpf); extern int uml_vector_detach_bpf(int fd, void *bpf); diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index b08bd2966253..f1f3f52f1e9c 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -24,7 +24,6 @@ generic-y += softirq_stack.h generic-y += switch_to.h generic-y += topology.h generic-y += trace_clock.h -generic-y += word-at-a-time.h generic-y += kprobes.h generic-y += mm_hooks.h generic-y += vga.h diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h index f512704a9ec7..22b39de73c24 100644 --- a/arch/um/include/asm/xor.h +++ b/arch/um/include/asm/xor.h @@ -4,8 +4,10 @@ #ifdef CONFIG_64BIT #undef CONFIG_X86_32 +#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_sse_pf64)) #else #define CONFIG_X86_32 1 +#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_8regs)) #endif #include <asm/cpufeature.h> @@ -16,7 +18,7 @@ #undef XOR_SELECT_TEMPLATE /* pick an arbitrary one - measuring isn't possible with inf-cpu */ #define XOR_SELECT_TEMPLATE(x) \ - (time_travel_mode == TT_MODE_INFCPU ? &xor_block_8regs : NULL) + (time_travel_mode == TT_MODE_INFCPU ? TT_CPU_INF_XOR_DEFAULT : x)) #endif #endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 00214059d9ec..fafde1d5416e 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -168,6 +168,7 @@ extern unsigned os_major(unsigned long long dev); extern unsigned os_minor(unsigned long long dev); extern unsigned long long os_makedev(unsigned major, unsigned minor); extern int os_falloc_punch(int fd, unsigned long long offset, int count); +extern int os_falloc_zeroes(int fd, unsigned long long offset, int count); extern int os_eventfd(unsigned int initval, int flags); extern int os_sendmsg_fds(int fd, const void *buf, unsigned int len, const int *fds, unsigned int fds_num); diff --git a/arch/um/kernel/dtb.c b/arch/um/kernel/dtb.c index ca69d72025f3..484141b06938 100644 --- a/arch/um/kernel/dtb.c +++ b/arch/um/kernel/dtb.c @@ -25,8 +25,8 @@ void uml_dtb_init(void) return; } - unflatten_device_tree(); early_init_fdt_scan_reserved_mem(); + unflatten_device_tree(); } static int __init uml_dtb_setup(char *line, int *add) diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index e4421dbc4c36..fc4450db59bd 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -625,6 +625,15 @@ int os_falloc_punch(int fd, unsigned long long offset, int len) return n; } +int os_falloc_zeroes(int fd, unsigned long long offset, int len) +{ + int n = fallocate(fd, FALLOC_FL_ZERO_RANGE|FALLOC_FL_KEEP_SIZE, offset, len); + + if (n < 0) + return -errno; + return n; +} + int os_eventfd(unsigned int initval, int flags) { int fd = eventfd(initval, flags); diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 32e88baf18dd..b459745f52e2 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -4,6 +4,7 @@ */ #include <stdlib.h> +#include <string.h> #include <unistd.h> #include <errno.h> #include <sched.h> @@ -99,6 +100,10 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) CATCH_EINTR(waitpid(pid, NULL, __WALL)); } + if (ret < 0) + printk(UM_KERN_ERR "run_helper : failed to exec %s on host: %s\n", + argv[0], strerror(-ret)); + out_free2: kfree(data.buf); out_close: diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index 6c5041c5560b..4d5591d96d8c 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -18,12 +18,6 @@ static timer_t event_high_res_timer = 0; -static inline long long timeval_to_ns(const struct timeval *tv) -{ - return ((long long) tv->tv_sec * UM_NSEC_PER_SEC) + - tv->tv_usec * UM_NSEC_PER_USEC; -} - static inline long long timespec_to_ns(const struct timespec *ts) { return ((long long) ts->tv_sec * UM_NSEC_PER_SEC) + ts->tv_nsec; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ff45a27fc29c..b0142e01002e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -122,7 +122,6 @@ config X86 select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANT_LD_ORPHAN_WARN - select ARCH_WANTS_RT_DELAYED_SIGNALS select ARCH_WANTS_THP_SWAP if X86_64 select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 71124cf8630c..98a4852ed6a0 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1,5 +1,7 @@ +CONFIG_WERROR=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_USELIB=y CONFIG_AUDIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y @@ -11,23 +13,30 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y +CONFIG_BLK_CGROUP=y CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_MISC=y +CONFIG_CGROUP_DEBUG=y CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y -# CONFIG_64BIT is not set CONFIG_SMP=y -CONFIG_X86_GENERIC=y -CONFIG_HPET_TIMER=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_NR_CPUS=8 CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y -CONFIG_X86_REBOOTFIXUPS=y CONFIG_MICROCODE_AMD=y CONFIG_X86_MSR=y CONFIG_X86_CPUID=y -CONFIG_HIGHPTE=y CONFIG_X86_CHECK_BIOS_CORRUPTION=y # CONFIG_MTRR_SANITIZER is not set CONFIG_EFI=y @@ -43,12 +52,15 @@ CONFIG_ACPI_BGRT=y CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_X86_ACPI_CPUFREQ=y -CONFIG_EFI_VARS=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y +CONFIG_COMPAT_32BIT_TIME=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y @@ -103,12 +115,16 @@ CONFIG_IP6_NF_FILTER=y CONFIG_IP6_NF_TARGET_REJECT=y CONFIG_IP6_NF_MANGLE=y CONFIG_NET_SCHED=y +CONFIG_NET_CLS_CGROUP=y CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y +CONFIG_CGROUP_NET_PRIO=y CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MAC80211_LEDS=y CONFIG_RFKILL=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y CONFIG_PCI=y CONFIG_PCIEPORTBUS=y CONFIG_PCI_MSI=y @@ -119,13 +135,16 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y +CONFIG_EFI_VARS=y +CONFIG_EFI_CAPSULE_LOADER=y CONFIG_BLK_DEV_LOOP=y +CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y -# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_SCSI_VIRTIO=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_ATA_PIIX=y @@ -143,6 +162,7 @@ CONFIG_MACINTOSH_DRIVERS=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y CONFIG_NETCONSOLE=y +CONFIG_VIRTIO_NET=y CONFIG_BNX2=y CONFIG_TIGON3=y CONFIG_NET_TULIP=y @@ -170,6 +190,7 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y CONFIG_SERIAL_NONSTANDARD=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_NVRAM=y CONFIG_HPET=y @@ -181,12 +202,7 @@ CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y CONFIG_DRM=y CONFIG_DRM_I915=y -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_TILEBLITTING=y -CONFIG_FB_EFI=y -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_DRM_VIRTIO_GPU=y CONFIG_SOUND=y CONFIG_SND=y CONFIG_SND_HRTIMER=y @@ -219,6 +235,8 @@ CONFIG_USB_STORAGE=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set CONFIG_DMADEVICES=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_INPUT=y CONFIG_EEEPC_LAPTOP=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y @@ -240,6 +258,7 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y +CONFIG_9P_FS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y @@ -251,14 +270,15 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_PRINTK_TIME=y +CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y -CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_SCHED_DEBUG is not set CONFIG_SCHEDSTATS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_BOOT_PARAMS=y -CONFIG_KALLSYMS_ALL=y +CONFIG_UNWINDER_FRAME_POINTER=y +# CONFIG_64BIT is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 92b1169ec90b..69784505a7a8 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1,3 +1,4 @@ +CONFIG_WERROR=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y @@ -11,14 +12,25 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y +CONFIG_BLK_CGROUP=y CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_MISC=y +CONFIG_CGROUP_DEBUG=y CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_SMP=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y CONFIG_MICROCODE_AMD=y CONFIG_X86_MSR=y @@ -41,12 +53,14 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_X86_ACPI_CPUFREQ=y CONFIG_IA32_EMULATION=y -CONFIG_EFI_VARS=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y @@ -101,12 +115,16 @@ CONFIG_IP6_NF_FILTER=y CONFIG_IP6_NF_TARGET_REJECT=y CONFIG_IP6_NF_MANGLE=y CONFIG_NET_SCHED=y +CONFIG_NET_CLS_CGROUP=y CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y +CONFIG_CGROUP_NET_PRIO=y CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MAC80211_LEDS=y CONFIG_RFKILL=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y CONFIG_PCI=y CONFIG_PCIEPORTBUS=y CONFIG_HOTPLUG_PCI=y @@ -116,13 +134,15 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y +CONFIG_EFI_VARS=y CONFIG_BLK_DEV_LOOP=y +CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y -# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_SCSI_VIRTIO=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_ATA_PIIX=y @@ -138,6 +158,7 @@ CONFIG_MACINTOSH_DRIVERS=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y CONFIG_NETCONSOLE=y +CONFIG_VIRTIO_NET=y CONFIG_TIGON3=y CONFIG_NET_TULIP=y CONFIG_E100=y @@ -162,6 +183,7 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y CONFIG_SERIAL_NONSTANDARD=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y # CONFIG_HW_RANDOM_INTEL is not set # CONFIG_HW_RANDOM_AMD is not set @@ -175,12 +197,7 @@ CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y CONFIG_DRM=y CONFIG_DRM_I915=y -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_TILEBLITTING=y -CONFIG_FB_EFI=y -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_DRM_VIRTIO_GPU=y CONFIG_SOUND=y CONFIG_SND=y CONFIG_SND_HRTIMER=y @@ -213,6 +230,8 @@ CONFIG_USB_STORAGE=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set CONFIG_DMADEVICES=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_INPUT=y CONFIG_EEEPC_LAPTOP=y CONFIG_AMD_IOMMU=y CONFIG_INTEL_IOMMU=y @@ -237,6 +256,7 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y +CONFIG_9P_FS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y @@ -257,4 +277,3 @@ CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_BOOT_PARAMS=y -CONFIG_KALLSYMS_ALL=y diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index 7f3886eeb2ff..eca5d6eff132 100644 --- a/arch/x86/entry/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -3,8 +3,7 @@ out := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ - $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') +$(shell mkdir -p $(out) $(uapi)) syscall32 := $(src)/syscall_32.tbl syscall64 := $(src)/syscall_64.tbl diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..fc7f458eb3de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..5d7762288a24 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -680,6 +681,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..7695dcae280e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..4262351f52b6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,10 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -1406,6 +1410,22 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..6d759f88315c 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c878fed3056f..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -154,24 +154,24 @@ # define DEFINE_EXTABLE_TYPE_REG \ ".macro extable_type_reg type:req reg:req\n" \ - ".set found, 0\n" \ - ".set regnr, 0\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".set regnr, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".if (found != 1)\n" \ + ".if (.Lfound != 1)\n" \ ".error \"extable_type_reg: bad register argument\"\n" \ ".endif\n" \ ".endm\n" diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 4d20a293c6fd..aaf0cb0db4ae 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -78,9 +78,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 7516e4199b3c..20fd0acd7d80 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -28,15 +28,13 @@ typedef u16 compat_ipc_pid_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { - compat_dev_t st_dev; - u16 __pad1; + u32 st_dev; compat_ino_t st_ino; compat_mode_t st_mode; compat_nlink_t st_nlink; __compat_uid_t st_uid; __compat_gid_t st_gid; - compat_dev_t st_rdev; - u16 __pad2; + u32 st_rdev; u32 st_size; u32 st_blksize; u32 st_blocks; diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index f6d91ecb8026..e9736af126b2 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -210,8 +210,6 @@ void __iomem *ioremap(resource_size_t offset, unsigned long size); extern void iounmap(volatile void __iomem *addr); #define iounmap iounmap -extern void set_iounmap_nonlazy(void); - #ifdef __KERNEL__ void memcpy_fromio(void *, const volatile void __iomem *, size_t); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4138939532c6..e0c0f0e1f754 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -249,6 +249,7 @@ enum x86_intercept_stage; #define PFERR_SGX_BIT 15 #define PFERR_GUEST_FINAL_BIT 32 #define PFERR_GUEST_PAGE_BIT 33 +#define PFERR_IMPLICIT_ACCESS_BIT 48 #define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT) #define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT) @@ -259,6 +260,7 @@ enum x86_intercept_stage; #define PFERR_SGX_MASK (1U << PFERR_SGX_BIT) #define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT) #define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT) +#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT) #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ PFERR_WRITE_MASK | \ @@ -430,7 +432,7 @@ struct kvm_mmu { void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gpa_t gva_or_gpa, u32 access, + gpa_t gva_or_gpa, u64 access, struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); @@ -512,6 +514,7 @@ struct kvm_pmu { u64 global_ctrl_mask; u64 global_ovf_ctrl_mask; u64 reserved_bits; + u64 raw_event_mask; u8 version; struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; @@ -971,12 +974,10 @@ enum hv_tsc_page_status { HV_TSC_PAGE_UNSET = 0, /* TSC page MSR was written by the guest, update pending */ HV_TSC_PAGE_GUEST_CHANGED, - /* TSC page MSR was written by KVM userspace, update pending */ + /* TSC page update was triggered from the host side */ HV_TSC_PAGE_HOST_CHANGED, /* TSC page was properly set up and is currently active */ HV_TSC_PAGE_SET, - /* TSC page is currently being updated and therefore is inactive */ - HV_TSC_PAGE_UPDATING, /* TSC page was set up with an inaccessible GPA */ HV_TSC_PAGE_BROKEN, }; @@ -1040,14 +1041,17 @@ struct kvm_x86_msr_filter { struct msr_bitmap_range ranges[16]; }; -#define APICV_INHIBIT_REASON_DISABLE 0 -#define APICV_INHIBIT_REASON_HYPERV 1 -#define APICV_INHIBIT_REASON_NESTED 2 -#define APICV_INHIBIT_REASON_IRQWIN 3 -#define APICV_INHIBIT_REASON_PIT_REINJ 4 -#define APICV_INHIBIT_REASON_X2APIC 5 -#define APICV_INHIBIT_REASON_BLOCKIRQ 6 -#define APICV_INHIBIT_REASON_ABSENT 7 +enum kvm_apicv_inhibit { + APICV_INHIBIT_REASON_DISABLE, + APICV_INHIBIT_REASON_HYPERV, + APICV_INHIBIT_REASON_NESTED, + APICV_INHIBIT_REASON_IRQWIN, + APICV_INHIBIT_REASON_PIT_REINJ, + APICV_INHIBIT_REASON_X2APIC, + APICV_INHIBIT_REASON_BLOCKIRQ, + APICV_INHIBIT_REASON_ABSENT, + APICV_INHIBIT_REASON_SEV, +}; struct kvm_arch { unsigned long n_used_mmu_pages; @@ -1401,7 +1405,7 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - bool (*check_apicv_inhibit_reasons)(ulong bit); + bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason); void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); @@ -1580,12 +1584,13 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest) -int kvm_mmu_module_init(void); -void kvm_mmu_module_exit(void); +void kvm_mmu_x86_module_init(void); +int kvm_mmu_vendor_module_init(void); +void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -void kvm_mmu_init_vm(struct kvm *kvm); +int 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); @@ -1795,11 +1800,22 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, bool kvm_apicv_activated(struct kvm *kvm); void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); -void kvm_request_apicv_update(struct kvm *kvm, bool activate, - unsigned long bit); +void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set); +void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set); + +static inline void kvm_set_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason) +{ + kvm_set_or_clear_apicv_inhibit(kvm, reason, true); +} -void __kvm_request_apicv_update(struct kvm *kvm, bool activate, - unsigned long bit); +static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason) +{ + kvm_set_or_clear_apicv_inhibit(kvm, reason, false); +} int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 0eb90d21049e..ee15311b6be1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -128,9 +128,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..b06e4c573add 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2455d721503e 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -38,6 +38,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 7eb2df5417fb..f70a5108d464 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -221,8 +221,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2) +#define SVM_TSC_RATIO_RSVD 0xffffff0000000000ULL +#define SVM_TSC_RATIO_MIN 0x0000000000000001ULL +#define SVM_TSC_RATIO_MAX 0x000000ffffffffffULL +#define SVM_TSC_RATIO_DEFAULT 0x0100000000ULL + + /* AVIC */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFFULL) #define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) @@ -230,9 +236,11 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) #define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) #define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) -#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFF) +#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFFULL) + +#define AVIC_DOORBELL_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) -#define AVIC_DOORBELL_PHYSICAL_ID_MASK (0xFF) +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL #define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 #define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 diff --git a/arch/x86/include/asm/user_32.h b/arch/x86/include/asm/user_32.h index d72c3d66e94f..8963915e533f 100644 --- a/arch/x86/include/asm/user_32.h +++ b/arch/x86/include/asm/user_32.h @@ -124,9 +124,5 @@ struct user{ char u_comm[32]; /* User command that was responsible */ int u_debugreg[8]; }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif /* _ASM_X86_USER_32_H */ diff --git a/arch/x86/include/asm/user_64.h b/arch/x86/include/asm/user_64.h index db909923611c..1dd10f07ccd6 100644 --- a/arch/x86/include/asm/user_64.h +++ b/arch/x86/include/asm/user_64.h @@ -130,9 +130,5 @@ struct user { unsigned long error_code; /* CPU error code or 0 */ unsigned long fault_address; /* CR3 or 0 */ }; -#define NBPG PAGE_SIZE -#define UPAGES 1 -#define HOST_TEXT_START_ADDR (u.start_code) -#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG) #endif /* _ASM_X86_USER_64_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ed4417500700..e342ae4db3c4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1855,6 +1855,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + + tsx_ap_init(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index ee6f23f7587d..2a8e584fc991 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -55,11 +55,10 @@ enum tsx_ctrl_states { extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; extern void __init tsx_init(void); -extern void tsx_enable(void); -extern void tsx_disable(void); -extern void tsx_clear_cpuid(void); +void tsx_ap_init(void); #else static inline void tsx_init(void) { } +static inline void tsx_ap_init(void) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void get_cpu_cap(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8321c43554a1..f7a5370a9b3b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -717,13 +717,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_misc_features(c); - if (tsx_ctrl_state == TSX_CTRL_ENABLE) - tsx_enable(); - else if (tsx_ctrl_state == TSX_CTRL_DISABLE) - tsx_disable(); - else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) - tsx_clear_cpuid(); - split_lock_init(); bus_lock_init(); diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 9c7a5f049292..ec7bbac3a9f2 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -19,7 +19,7 @@ enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; -void tsx_disable(void) +static void tsx_disable(void) { u64 tsx; @@ -39,7 +39,7 @@ void tsx_disable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -void tsx_enable(void) +static void tsx_enable(void) { u64 tsx; @@ -58,7 +58,7 @@ void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool __init tsx_ctrl_is_supported(void) +static bool tsx_ctrl_is_supported(void) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -84,7 +84,45 @@ static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) return TSX_CTRL_ENABLE; } -void tsx_clear_cpuid(void) +/* + * Disabling TSX is not a trivial business. + * + * First of all, there's a CPUID bit: X86_FEATURE_RTM_ALWAYS_ABORT + * which says that TSX is practically disabled (all transactions are + * aborted by default). When that bit is set, the kernel unconditionally + * disables TSX. + * + * In order to do that, however, it needs to dance a bit: + * + * 1. The first method to disable it is through MSR_TSX_FORCE_ABORT and + * the MSR is present only when *two* CPUID bits are set: + * + * - X86_FEATURE_RTM_ALWAYS_ABORT + * - X86_FEATURE_TSX_FORCE_ABORT + * + * 2. The second method is for CPUs which do not have the above-mentioned + * MSR: those use a different MSR - MSR_IA32_TSX_CTRL and disable TSX + * through that one. Those CPUs can also have the initially mentioned + * CPUID bit X86_FEATURE_RTM_ALWAYS_ABORT set and for those the same strategy + * applies: TSX gets disabled unconditionally. + * + * When either of the two methods are present, the kernel disables TSX and + * clears the respective RTM and HLE feature flags. + * + * An additional twist in the whole thing presents late microcode loading + * which, when done, may cause for the X86_FEATURE_RTM_ALWAYS_ABORT CPUID + * bit to be set after the update. + * + * A subsequent hotplug operation on any logical CPU except the BSP will + * cause for the supported CPUID feature bits to get re-detected and, if + * RTM and HLE get cleared all of a sudden, but, userspace did consult + * them before the update, then funny explosions will happen. Long story + * short: the kernel doesn't modify CPUID feature bits after booting. + * + * That's why, this function's call in init_intel() doesn't clear the + * feature flags. + */ +static void tsx_clear_cpuid(void) { u64 msr; @@ -97,6 +135,39 @@ void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); + } else if (tsx_ctrl_is_supported()) { + rdmsrl(MSR_IA32_TSX_CTRL, msr); + msr |= TSX_CTRL_CPUID_CLEAR; + wrmsrl(MSR_IA32_TSX_CTRL, msr); + } +} + +/* + * Disable TSX development mode + * + * When the microcode released in Feb 2022 is applied, TSX will be disabled by + * default on some processors. MSR 0x122 (TSX_CTRL) and MSR 0x123 + * (IA32_MCU_OPT_CTRL) can be used to re-enable TSX for development, doing so is + * not recommended for production deployments. In particular, applying MD_CLEAR + * flows for mitigation of the Intel TSX Asynchronous Abort (TAA) transient + * execution attack may not be effective on these processors when Intel TSX is + * enabled with updated microcode. + */ +static void tsx_dev_mode_disable(void) +{ + u64 mcu_opt_ctrl; + + /* Check if RTM_ALLOW exists */ + if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + + if (mcu_opt_ctrl & RTM_ALLOW) { + mcu_opt_ctrl &= ~RTM_ALLOW; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT); } } @@ -105,14 +176,14 @@ void __init tsx_init(void) char arg[5] = {}; int ret; + tsx_dev_mode_disable(); + /* - * Hardware will always abort a TSX transaction if both CPUID bits - * RTM_ALWAYS_ABORT and TSX_FORCE_ABORT are set. In this case, it is - * better not to enumerate CPUID.RTM and CPUID.HLE bits. Clear them - * here. + * Hardware will always abort a TSX transaction when the CPUID bit + * RTM_ALWAYS_ABORT is set. In this case, it is better not to enumerate + * CPUID.RTM and CPUID.HLE bits. Clear them here. */ - if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) && - boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT)) { tsx_ctrl_state = TSX_CTRL_RTM_ALWAYS_ABORT; tsx_clear_cpuid(); setup_clear_cpu_cap(X86_FEATURE_RTM); @@ -175,3 +246,16 @@ void __init tsx_init(void) setup_force_cpu_cap(X86_FEATURE_HLE); } } + +void tsx_ap_init(void) +{ + tsx_dev_mode_disable(); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + else if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); + else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) + /* See comment over that function for more details. */ + tsx_clear_cpuid(); +} diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index a7f617a3981d..97529552dd24 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -37,7 +37,6 @@ static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, } else memcpy(buf, vaddr + offset, csize); - set_iounmap_nonlazy(); iounmap((void __iomem *)vaddr); return csize; } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 19821f027cb3..c049561f373a 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -415,9 +415,6 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU); *vpkru = xpkru->pkru; } - - /* Ensure that XCOMP_BV is set up for XSAVES */ - xstate_init_xcomp_bv(&kstate->regs.xsave, kstate->xfeatures); return 0; } EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 7c7824ae7862..39e1c8626ab9 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -81,10 +81,10 @@ static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; -static unsigned int xstate_comp_offsets[XFEATURE_MAX] __ro_after_init = - { [ 0 ... XFEATURE_MAX - 1] = -1}; -static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init = - { [ 0 ... XFEATURE_MAX - 1] = -1}; +static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init; + +#define XSTATE_FLAG_SUPERVISOR BIT(0) +#define XSTATE_FLAG_ALIGNED64 BIT(1) /* * Return whether the system supports a given xfeature. @@ -124,17 +124,41 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) } EXPORT_SYMBOL_GPL(cpu_has_xfeatures); +static bool xfeature_is_aligned64(int xfeature_nr) +{ + return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64; +} + static bool xfeature_is_supervisor(int xfeature_nr) { + return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR; +} + +static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature) +{ + unsigned int offs, i; + /* - * Extended State Enumeration Sub-leaves (EAX = 0DH, ECX = n, n > 1) - * returns ECX[0] set to (1) for a supervisor state, and cleared (0) - * for a user state. + * Non-compacted format and legacy features use the cached fixed + * offsets. */ - u32 eax, ebx, ecx, edx; + if (!cpu_feature_enabled(X86_FEATURE_XSAVES) || xfeature <= XFEATURE_SSE) + return xstate_offsets[xfeature]; - cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); - return ecx & 1; + /* + * Compacted format offsets depend on the actual content of the + * compacted xsave area which is determined by the xcomp_bv header + * field. + */ + offs = FXSAVE_SIZE + XSAVE_HDR_SIZE; + for_each_extended_xfeature(i, xcomp_bv) { + if (xfeature_is_aligned64(i)) + offs = ALIGN(offs, 64); + if (i == xfeature) + break; + offs += xstate_sizes[i]; + } + return offs; } /* @@ -182,7 +206,7 @@ static bool xfeature_enabled(enum xfeature xfeature) * Record the offsets and sizes of various xstates contained * in the XSAVE state memory layout. */ -static void __init setup_xstate_features(void) +static void __init setup_xstate_cache(void) { u32 eax, ebx, ecx, edx, i; /* start at the beginning of the "extended state" */ @@ -205,6 +229,7 @@ static void __init setup_xstate_features(void) cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); xstate_sizes[i] = eax; + xstate_flags[i] = ecx; /* * If an xfeature is supervisor state, the offset in EBX is @@ -264,94 +289,6 @@ static void __init print_xstate_features(void) } while (0) /* - * We could cache this like xstate_size[], but we only use - * it here, so it would be a waste of space. - */ -static int xfeature_is_aligned(int xfeature_nr) -{ - u32 eax, ebx, ecx, edx; - - CHECK_XFEATURE(xfeature_nr); - - if (!xfeature_enabled(xfeature_nr)) { - WARN_ONCE(1, "Checking alignment of disabled xfeature %d\n", - xfeature_nr); - return 0; - } - - cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); - /* - * The value returned by ECX[1] indicates the alignment - * of state component 'i' when the compacted format - * of the extended region of an XSAVE area is used: - */ - return !!(ecx & 2); -} - -/* - * This function sets up offsets and sizes of all extended states in - * xsave area. This supports both standard format and compacted format - * of the xsave area. - */ -static void __init setup_xstate_comp_offsets(void) -{ - unsigned int next_offset; - int i; - - /* - * The FP xstates and SSE xstates are legacy states. They are always - * in the fixed offsets in the xsave area in either compacted form - * or standard form. - */ - xstate_comp_offsets[XFEATURE_FP] = 0; - xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state, - xmm_space); - - if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) { - for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) - xstate_comp_offsets[i] = xstate_offsets[i]; - return; - } - - next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; - - for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { - if (xfeature_is_aligned(i)) - next_offset = ALIGN(next_offset, 64); - - xstate_comp_offsets[i] = next_offset; - next_offset += xstate_sizes[i]; - } -} - -/* - * Setup offsets of a supervisor-state-only XSAVES buffer: - * - * The offsets stored in xstate_comp_offsets[] only work for one specific - * value of the Requested Feature BitMap (RFBM). In cases where a different - * RFBM value is used, a different set of offsets is required. This set of - * offsets is for when RFBM=xfeatures_mask_supervisor(). - */ -static void __init setup_supervisor_only_offsets(void) -{ - unsigned int next_offset; - int i; - - next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; - - for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { - if (!xfeature_is_supervisor(i)) - continue; - - if (xfeature_is_aligned(i)) - next_offset = ALIGN(next_offset, 64); - - xstate_supervisor_only_offsets[i] = next_offset; - next_offset += xstate_sizes[i]; - } -} - -/* * Print out xstate component offsets and sizes */ static void __init print_xstate_offset_size(void) @@ -360,7 +297,8 @@ static void __init print_xstate_offset_size(void) for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", - i, xstate_comp_offsets[i], i, xstate_sizes[i]); + i, xfeature_get_offset(fpu_kernel_cfg.max_features, i), + i, xstate_sizes[i]); } } @@ -419,7 +357,6 @@ static void __init setup_init_fpu_buf(void) if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; - setup_xstate_features(); print_xstate_features(); xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features); @@ -448,25 +385,6 @@ static void __init setup_init_fpu_buf(void) fxsave(&init_fpstate.regs.fxsave); } -static int xfeature_uncompacted_offset(int xfeature_nr) -{ - u32 eax, ebx, ecx, edx; - - /* - * Only XSAVES supports supervisor states and it uses compacted - * format. Checking a supervisor state's uncompacted offset is - * an error. - */ - if (XFEATURE_MASK_SUPERVISOR_ALL & BIT_ULL(xfeature_nr)) { - WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr); - return -1; - } - - CHECK_XFEATURE(xfeature_nr); - cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); - return ebx; -} - int xfeature_size(int xfeature_nr) { u32 eax, ebx, ecx, edx; @@ -644,29 +562,15 @@ static bool __init check_xstate_against_struct(int nr) static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) { - unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; - int i; + unsigned int topmost = fls64(xfeatures) - 1; + unsigned int offset = xstate_offsets[topmost]; - for_each_extended_xfeature(i, xfeatures) { - /* Align from the end of the previous feature */ - if (xfeature_is_aligned(i)) - size = ALIGN(size, 64); - /* - * In compacted format the enabled features are packed, - * i.e. disabled features do not occupy space. - * - * In non-compacted format the offsets are fixed and - * disabled states still occupy space in the memory buffer. - */ - if (!compacted) - size = xfeature_uncompacted_offset(i); - /* - * Add the feature size even for non-compacted format - * to make the end result correct - */ - size += xfeature_size(i); - } - return size; + if (topmost <= XFEATURE_SSE) + return sizeof(struct xregs_state); + + if (compacted) + offset = xfeature_get_offset(xfeatures, topmost); + return offset + xstate_sizes[topmost]; } /* @@ -935,6 +839,10 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); + + /* Cache size, offset and flags for initialization */ + setup_xstate_cache(); + err = init_xstate_size(); if (err) goto out_disable; @@ -950,8 +858,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) fpu_user_cfg.max_features); setup_init_fpu_buf(); - setup_xstate_comp_offsets(); - setup_supervisor_only_offsets(); /* * Paranoia check whether something in the setup modified the @@ -1006,13 +912,19 @@ void fpu__resume_cpu(void) */ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { - if (!xfeature_enabled(xfeature_nr)) { - WARN_ON_FPU(1); + u64 xcomp_bv = xsave->header.xcomp_bv; + + if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; + + if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { + if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr)))) + return NULL; } - return (void *)xsave + xstate_comp_offsets[xfeature_nr]; + return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr); } + /* * Given the xsave area and a state inside, this function returns the * address of the state. @@ -1043,8 +955,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) * We should not ever be requesting features that we * have not enabled. */ - WARN_ONCE(!(fpu_kernel_cfg.max_features & BIT_ULL(xfeature_nr)), - "get of unsupported state"); + if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) + return NULL; + /* * This assumes the last 'xsave*' instruction to * have requested that 'xfeature_nr' be saved. @@ -1625,6 +1538,9 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) /* Calculate the resulting kernel state size */ mask = permitted | requested; + /* Take supervisor states into account on the host */ + if (!guest) + mask |= xfeatures_mask_supervisor(); ksize = xstate_calculate_size(mask, compacted); /* Calculate the resulting user state size */ @@ -1639,7 +1555,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) perm = guest ? &fpu->guest_perm : &fpu->perm; /* Pairs with the READ_ONCE() in xstate_get_group_perm() */ - WRITE_ONCE(perm->__state_perm, requested); + WRITE_ONCE(perm->__state_perm, mask); /* Protected by sighand lock */ perm->__state_size = ksize; perm->__user_state_size = usize; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 79e0b8d63ffa..a22deb58f86d 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -517,7 +517,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector) } else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) { ipi_bitmap <<= min - apic_id; min = apic_id; - } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) { + } else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) { max = apic_id < max ? max : apic_id; } else { ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a00cd97b2623..b24ca7f4ed7c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -735,6 +735,7 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, if (function > READ_ONCE(max_cpuid_80000000)) return entry; } + break; default: break; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f9c00c89829b..89b11e7dca8a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3540,8 +3540,10 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt) { u64 tsc_aux = 0; - if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + if (!ctxt->ops->guest_has_rdpid(ctxt)) return emulate_ud(ctxt); + + ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } @@ -3642,7 +3644,7 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt) msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX) | ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32); - r = ctxt->ops->set_msr(ctxt, msr_index, msr_data); + r = ctxt->ops->set_msr_with_filter(ctxt, msr_index, msr_data); if (r == X86EMUL_IO_NEEDED) return r; @@ -3659,7 +3661,7 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt) u64 msr_data; int r; - r = ctxt->ops->get_msr(ctxt, msr_index, &msr_data); + r = ctxt->ops->get_msr_with_filter(ctxt, msr_index, &msr_data); if (r == X86EMUL_IO_NEEDED) return r; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index a32f54ab84a2..46f9dfb60469 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -122,9 +122,13 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, else hv->synic_auto_eoi_used--; - __kvm_request_apicv_update(vcpu->kvm, - !hv->synic_auto_eoi_used, - APICV_INHIBIT_REASON_HYPERV); + /* + * Inhibit APICv if any vCPU is using SynIC's AutoEOI, which relies on + * the hypervisor to manually inject IRQs. + */ + __kvm_set_or_clear_apicv_inhibit(vcpu->kvm, + APICV_INHIBIT_REASON_HYPERV, + !!hv->synic_auto_eoi_used); up_write(&vcpu->kvm->arch.apicv_update_lock); } @@ -239,7 +243,7 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); int ret; - if (!synic->active && !host) + if (!synic->active && (!host || data)) return 1; trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); @@ -285,6 +289,9 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, case HV_X64_MSR_EOM: { int i; + if (!synic->active) + break; + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) kvm_hv_notify_acked_sint(vcpu, i); break; @@ -449,6 +456,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) struct kvm_lapic_irq irq; int ret, vector; + if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm)) + return -EINVAL; + if (sint >= ARRAY_SIZE(synic->sint)) return -EINVAL; @@ -661,7 +671,7 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); - if (!synic->active && !host) + if (!synic->active && (!host || config)) return 1; if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode && @@ -690,7 +700,7 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); - if (!synic->active && !host) + if (!synic->active && (!host || count)) return 1; trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id, @@ -1125,11 +1135,13 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence)); BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0); + mutex_lock(&hv->hv_lock); + if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || + hv->hv_tsc_page_status == HV_TSC_PAGE_SET || hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET) - return; + goto out_unlock; - mutex_lock(&hv->hv_lock); if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) goto out_unlock; @@ -1191,45 +1203,19 @@ out_unlock: mutex_unlock(&hv->hv_lock); } -void kvm_hv_invalidate_tsc_page(struct kvm *kvm) +void kvm_hv_request_tsc_page_update(struct kvm *kvm) { struct kvm_hv *hv = to_kvm_hv(kvm); - u64 gfn; - int idx; - - if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN || - hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET || - tsc_page_update_unsafe(hv)) - return; mutex_lock(&hv->hv_lock); - if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - goto out_unlock; - - /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */ - if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET) - hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING; - - gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - - hv->tsc_ref.tsc_sequence = 0; - - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&kvm->srcu); - if (kvm_write_guest(kvm, gfn_to_gpa(gfn), - &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence))) - hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN; - srcu_read_unlock(&kvm->srcu, idx); + if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET && + !tsc_page_update_unsafe(hv)) + hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED; -out_unlock: mutex_unlock(&hv->hv_lock); } - static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) { if (!hv_vcpu->enforce_cpuid) diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index e19c00ee9ab3..da2737f2a956 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -137,7 +137,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); -void kvm_hv_invalidate_tsc_page(struct kvm *kvm); +void kvm_hv_request_tsc_page_update(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 0b65a764ed3a..1c83076091af 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -305,15 +305,13 @@ void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject) * So, deactivate APICv when PIT is in reinject mode. */ if (reinject) { - kvm_request_apicv_update(kvm, false, - APICV_INHIBIT_REASON_PIT_REINJ); + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PIT_REINJ); /* The initial state is preserved while ps->reinject == 0. */ kvm_pit_reset_reinject(pit); kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier); kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); } else { - kvm_request_apicv_update(kvm, true, - APICV_INHIBIT_REASON_PIT_REINJ); + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PIT_REINJ); kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier); kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier); } diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 840ddb4a9302..8dff25d267b7 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -210,6 +210,8 @@ struct x86_emulate_ops { int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); + int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); + int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); @@ -226,6 +228,7 @@ struct x86_emulate_ops { bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); + bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt); void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 80a2020c4db4..66b0eb0bda94 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1024,6 +1024,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, *r = -1; if (irq->shorthand == APIC_DEST_SELF) { + if (KVM_BUG_ON(!src, kvm)) { + *r = 0; + return true; + } *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); return true; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bf8dbc4bb12a..e6cae6f22683 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -214,27 +214,27 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, */ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned pte_access, unsigned pte_pkey, - unsigned pfec) + u64 access) { - int cpl = static_call(kvm_x86_get_cpl)(vcpu); + /* strip nested paging fault error codes */ + unsigned int pfec = access; unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); /* - * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1. + * For explicit supervisor accesses, SMAP is disabled if EFLAGS.AC = 1. + * For implicit supervisor accesses, SMAP cannot be overridden. * - * If CPL = 3, SMAP applies to all supervisor-mode data accesses - * (these are implicit supervisor accesses) regardless of the value - * of EFLAGS.AC. + * SMAP works on supervisor accesses only, and not_smap can + * be set or not set when user access with neither has any bearing + * on the result. * - * This computes (cpl < 3) && (rflags & X86_EFLAGS_AC), leaving - * the result in X86_EFLAGS_AC. We then insert it in place of - * the PFERR_RSVD_MASK bit; this bit will always be zero in pfec, - * but it will be one in index if SMAP checks are being overridden. - * It is important to keep this branchless. + * We put the SMAP checking bit in place of the PFERR_RSVD_MASK bit; + * this bit will always be zero in pfec, but it will be one in index + * if SMAP checks are being disabled. */ - unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC); - int index = (pfec >> 1) + - (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1)); + u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; + bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; + int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1; bool fault = (mmu->permissions[index] >> pte_access) & 1; u32 errcode = PFERR_PRESENT_MASK; @@ -317,12 +317,12 @@ static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) atomic64_add(count, &kvm->stat.pages[level - 1]); } -gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, struct x86_exception *exception); static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gpa_t gpa, u32 access, + gpa_t gpa, u64 access, struct x86_exception *exception) { if (mmu != &vcpu->arch.nested_mmu) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 51671cb34fb6..f9080ee50ffa 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2696,8 +2696,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, if (*sptep == spte) { ret = RET_PF_SPURIOUS; } else { - trace_kvm_mmu_set_spte(level, gfn, sptep); flush |= mmu_spte_update(sptep, spte); + trace_kvm_mmu_set_spte(level, gfn, sptep); } if (wrprot) { @@ -3703,7 +3703,7 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu) } static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gpa_t vaddr, u32 access, + gpa_t vaddr, u64 access, struct x86_exception *exception) { if (exception) @@ -4591,11 +4591,11 @@ static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept) * - X86_CR4_SMAP is set in CR4 * - A user page is accessed * - The access is not a fetch - * - Page fault in kernel mode - * - if CPL = 3 or X86_EFLAGS_AC is clear + * - The access is supervisor mode + * - If implicit supervisor access or X86_EFLAGS_AC is clear * - * Here, we cover the first three conditions. - * The fourth is computed dynamically in permission_fault(); + * Here, we cover the first four conditions. + * The fifth is computed dynamically in permission_fault(); * PFERR_RSVD_MASK bit will be set in PFEC if the access is * *not* subject to SMAP restrictions. */ @@ -5768,17 +5768,24 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, kvm_mmu_zap_all_fast(kvm); } -void kvm_mmu_init_vm(struct kvm *kvm) +int kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + int r; + INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - kvm_mmu_init_tdp_mmu(kvm); + r = kvm_mmu_init_tdp_mmu(kvm); + if (r < 0) + return r; node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; kvm_page_track_register_notifier(kvm, node); + return 0; } void kvm_mmu_uninit_vm(struct kvm *kvm) @@ -5842,8 +5849,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (is_tdp_mmu_enabled(kvm)) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start, - gfn_end, flush); + flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, + gfn_end, true, flush); } if (flush) @@ -6230,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) return 0; } -int kvm_mmu_module_init(void) +/* + * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as + * its default value of -1 is technically undefined behavior for a boolean. + */ +void kvm_mmu_x86_module_init(void) { - int ret = -ENOMEM; - if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); +} + +/* + * The bulk of the MMU initialization is deferred until the vendor module is + * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need + * to be reset when a potentially different vendor module is loaded. + */ +int kvm_mmu_vendor_module_init(void) +{ + int ret = -ENOMEM; /* * MMU roles use union aliasing which is, generally speaking, an @@ -6283,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) mmu_free_memory_caches(vcpu); } -void kvm_mmu_module_exit(void) +void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 252c77805eb9..01fee5f67ac3 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -34,9 +34,8 @@ #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL - #define CMPXCHG cmpxchg + #define CMPXCHG "cmpxchgq" #else - #define CMPXCHG cmpxchg64 #define PT_MAX_FULL_LEVELS 2 #endif #elif PTTYPE == 32 @@ -52,7 +51,7 @@ #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true - #define CMPXCHG cmpxchg + #define CMPXCHG "cmpxchgl" #elif PTTYPE == PTTYPE_EPT #define pt_element_t u64 #define guest_walker guest_walkerEPT @@ -65,7 +64,9 @@ #define PT_GUEST_DIRTY_SHIFT 9 #define PT_GUEST_ACCESSED_SHIFT 8 #define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad) - #define CMPXCHG cmpxchg64 + #ifdef CONFIG_X86_64 + #define CMPXCHG "cmpxchgq" + #endif #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #else #error Invalid PTTYPE value @@ -147,43 +148,36 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pt_element_t __user *ptep_user, unsigned index, pt_element_t orig_pte, pt_element_t new_pte) { - int npages; - pt_element_t ret; - pt_element_t *table; - struct page *page; - - npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page); - if (likely(npages == 1)) { - table = kmap_atomic(page); - ret = CMPXCHG(&table[index], orig_pte, new_pte); - kunmap_atomic(table); - - kvm_release_page_dirty(page); - } else { - struct vm_area_struct *vma; - unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK; - unsigned long pfn; - unsigned long paddr; - - mmap_read_lock(current->mm); - vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE); - if (!vma || !(vma->vm_flags & VM_PFNMAP)) { - mmap_read_unlock(current->mm); - return -EFAULT; - } - pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - paddr = pfn << PAGE_SHIFT; - table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB); - if (!table) { - mmap_read_unlock(current->mm); - return -EFAULT; - } - ret = CMPXCHG(&table[index], orig_pte, new_pte); - memunmap(table); - mmap_read_unlock(current->mm); - } + signed char r; - return (ret != orig_pte); + if (!user_access_begin(ptep_user, sizeof(pt_element_t))) + return -EFAULT; + +#ifdef CMPXCHG + asm volatile("1:" LOCK_PREFIX CMPXCHG " %[new], %[ptr]\n" + "setnz %b[r]\n" + "2:" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %k[r]) + : [ptr] "+m" (*ptep_user), + [old] "+a" (orig_pte), + [r] "=q" (r) + : [new] "r" (new_pte) + : "memory"); +#else + asm volatile("1:" LOCK_PREFIX "cmpxchg8b %[ptr]\n" + "setnz %b[r]\n" + "2:" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %k[r]) + : [ptr] "+m" (*ptep_user), + [old] "+A" (orig_pte), + [r] "=q" (r) + : [new_lo] "b" ((u32)new_pte), + [new_hi] "c" ((u32)(new_pte >> 32)) + : "memory"); +#endif + + user_access_end(); + return r; } static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, @@ -339,7 +333,7 @@ static inline bool FNAME(is_last_gpte)(struct kvm_mmu *mmu, */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gpa_t addr, u32 access) + gpa_t addr, u64 access) { int ret; pt_element_t pte; @@ -347,7 +341,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gfn_t table_gfn; u64 pt_access, pte_access; unsigned index, accessed_dirty, pte_pkey; - unsigned nested_access; + u64 nested_access; gpa_t pte_gpa; bool have_ad; int offset; @@ -540,7 +534,7 @@ error: } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gpa_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u64 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -988,7 +982,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gpa_t addr, u32 access, + gpa_t addr, u64 access, struct x86_exception *exception) { struct guest_walker walker; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index e7e7876251b3..c472769e0300 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -14,21 +14,24 @@ static bool __read_mostly tdp_mmu_enabled = true; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); /* Initializes the TDP MMU for the VM, if enabled. */ -bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) +int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { + struct workqueue_struct *wq; + if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return false; + return 0; + + wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); + if (!wq) + return -ENOMEM; /* This should not be changed for the lifetime of the VM. */ kvm->arch.tdp_mmu_enabled = true; - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); - kvm->arch.tdp_mmu_zap_wq = - alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); - - return true; + kvm->arch.tdp_mmu_zap_wq = wq; + return 1; } /* Arbitrarily returns true so that this may be used in if statements. */ @@ -48,7 +51,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); @@ -906,10 +909,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) } /* - * Tears down the mappings for the range of gfns, [start, end), and frees the - * non-root pages mapping GFNs strictly within that range. Returns true if - * SPTEs have been cleared and a TLB flush is needed before releasing the - * MMU lock. + * Zap leafs SPTEs for the range of gfns, [start, end). Returns true if SPTEs + * have been cleared and a TLB flush is needed before releasing the MMU lock. * * If can_yield is true, will release the MMU lock and reschedule if the * scheduler needs the CPU or there is contention on the MMU lock. If this @@ -917,42 +918,25 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) * the caller must ensure it does not supply too large a GFN range, or the * operation can cause a soft lockup. */ -static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield, bool flush) +static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, + gfn_t start, gfn_t end, bool can_yield, bool flush) { - bool zap_all = (start == 0 && end >= tdp_mmu_max_gfn_host()); struct tdp_iter iter; - /* - * No need to try to step down in the iterator when zapping all SPTEs, - * zapping the top-level non-leaf SPTEs will recurse on their children. - */ - int min_level = zap_all ? root->role.level : PG_LEVEL_4K; - end = min(end, tdp_mmu_max_gfn_host()); lockdep_assert_held_write(&kvm->mmu_lock); rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, min_level, start, end) { + for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) { if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) { flush = false; continue; } - if (!is_shadow_present_pte(iter.old_spte)) - continue; - - /* - * If this is a non-last-level SPTE that covers a larger range - * than should be zapped, continue, and zap the mappings at a - * lower level, except when zapping all SPTEs. - */ - if (!zap_all && - (iter.gfn < start || - iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) && + if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) continue; @@ -960,17 +944,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, flush = true; } - /* - * Need to flush before releasing RCU. TODO: do it only if intermediate - * page tables were zapped; there is no need to flush under RCU protection - * if no 'struct kvm_mmu_page' is freed. - */ - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, start, end - start); - rcu_read_unlock(); - return false; + /* + * Because this flow zaps _only_ leaf SPTEs, the caller doesn't need + * to provide RCU protection as no 'struct kvm_mmu_page' will be freed. + */ + return flush; } /* @@ -979,13 +959,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, * SPTEs have been cleared and a TLB flush is needed before releasing the * MMU lock. */ -bool __kvm_tdp_mmu_zap_gfn_range(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, int as_id, gfn_t start, gfn_t end, + bool can_yield, bool flush) { struct kvm_mmu_page *root; for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = zap_gfn_range(kvm, root, start, end, can_yield, flush); + flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); return flush; } @@ -1233,8 +1213,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return __kvm_tdp_mmu_zap_gfn_range(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, + range->end, range->may_block, 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 5e5ef2576c81..c163f7cc23ca 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -15,14 +15,8 @@ __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_gfn_range(struct kvm *kvm, int as_id, gfn_t start, +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, bool can_yield, bool flush); -static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, - gfn_t start, gfn_t end, bool flush) -{ - return __kvm_tdp_mmu_zap_gfn_range(kvm, as_id, start, end, true, 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); @@ -72,7 +66,7 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, u64 *spte); #ifdef CONFIG_X86_64 -bool kvm_mmu_init_tdp_mmu(struct kvm *kvm); +int kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } @@ -93,7 +87,7 @@ static inline bool is_tdp_mmu(struct kvm_mmu *mmu) return sp && is_tdp_mmu_page(sp) && sp->root_count; } #else -static inline bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return false; } +static inline int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return 0; } static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index b1a02993782b..eca39f56c231 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -96,8 +96,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, - bool exclude_kernel, bool intr, - bool in_tx, bool in_tx_cp) + bool exclude_kernel, bool intr) { struct perf_event *event; struct perf_event_attr attr = { @@ -116,16 +115,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, attr.sample_period = get_sample_period(pmc, pmc->counter); - if (in_tx) - attr.config |= HSW_IN_TX; - if (in_tx_cp) { + if ((attr.config & HSW_IN_TX_CHECKPOINTED) && + guest_cpuid_is_intel(pmc->vcpu)) { /* * HSW_IN_TX_CHECKPOINTED is not supported with nonzero * period. Just clear the sample period so at least * allocating the counter doesn't fail. */ attr.sample_period = 0; - attr.config |= HSW_IN_TX_CHECKPOINTED; } event = perf_event_create_kernel_counter(&attr, -1, current, @@ -185,6 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) u32 type = PERF_TYPE_RAW; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; + struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu); bool allow_event = true; if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) @@ -221,7 +219,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & AMD64_RAW_EVENT_MASK; + config = eventsel & pmu->raw_event_mask; if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) return; @@ -232,9 +230,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT, - (eventsel & HSW_IN_TX), - (eventsel & HSW_IN_TX_CHECKPOINTED)); + eventsel & ARCH_PERFMON_EVENTSEL_INT); } EXPORT_SYMBOL_GPL(reprogram_gp_counter); @@ -270,7 +266,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc), !(en_field & 0x2), /* exclude user */ !(en_field & 0x1), /* exclude kernel */ - pmi, false, false); + pmi); } EXPORT_SYMBOL_GPL(reprogram_fixed_counter); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index b37b353ec086..421619540ff9 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -726,7 +726,7 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt; - int idx, ret = -EINVAL; + int idx, ret = 0; if (!kvm_arch_has_assigned_device(kvm) || !irq_remapping_cap(IRQ_POSTING_CAP)) @@ -737,7 +737,13 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, idx = srcu_read_lock(&kvm->irq_srcu); irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - WARN_ON(guest_irq >= irq_rt->nr_rt_entries); + + if (guest_irq >= irq_rt->nr_rt_entries || + hlist_empty(&irq_rt->map[guest_irq])) { + pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", + guest_irq, irq_rt->nr_rt_entries); + goto out; + } hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { struct vcpu_data vcpu_info; @@ -822,7 +828,7 @@ out: return ret; } -bool avic_check_apicv_inhibit_reasons(ulong bit) +bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | BIT(APICV_INHIBIT_REASON_ABSENT) | @@ -831,9 +837,10 @@ bool avic_check_apicv_inhibit_reasons(ulong bit) BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | BIT(APICV_INHIBIT_REASON_X2APIC) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ); + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | + BIT(APICV_INHIBIT_REASON_SEV); - return supported & BIT(bit); + return supported & BIT(reason); } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index d4de52409335..24eb935b6f85 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -262,12 +262,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_EVNTSELn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); if (pmc) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { + data &= ~pmu->reserved_bits; + if (data != pmc->eventsel) reprogram_gp_counter(pmc, data); - return 0; - } + return 0; } return 1; @@ -284,6 +282,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; pmu->reserved_bits = 0xfffffff000280000ull; + pmu->raw_event_mask = AMD64_RAW_EVENT_MASK; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75fa6dd268f0..537aaddc852f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -260,6 +260,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); + return 0; e_free: @@ -465,6 +467,7 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages) page_virtual = kmap_atomic(pages[i]); clflush_cache_range(page_virtual, PAGE_SIZE); kunmap_atomic(page_virtual); + cond_resched(); } } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0884c3414a1b..bd4c64b362d2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -62,20 +62,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_LBRV (1 << 1) -#define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_TSC_RATE (1 << 4) -#define SVM_FEATURE_VMCB_CLEAN (1 << 5) -#define SVM_FEATURE_FLUSH_ASID (1 << 6) -#define SVM_FEATURE_DECODE_ASSIST (1 << 7) -#define SVM_FEATURE_PAUSE_FILTER (1 << 10) - #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) -#define TSC_RATIO_RSVD 0xffffff0000000000ULL -#define TSC_RATIO_MIN 0x0000000000000001ULL -#define TSC_RATIO_MAX 0x000000ffffffffffULL - static bool erratum_383_found __read_mostly; u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; @@ -87,7 +75,6 @@ u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; static uint64_t osvw_len = 4, osvw_status; static DEFINE_PER_CPU(u64, current_tsc_ratio); -#define TSC_RATIO_DEFAULT 0x0100000000ULL static const struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ @@ -480,7 +467,7 @@ static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ if (tsc_scaling) - wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); + wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT); cpu_svm_disable(); @@ -526,8 +513,8 @@ static int svm_hardware_enable(void) * Set the default value, even if we don't use TSC scaling * to avoid having stale value in the msr */ - wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); - __this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT); + wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT); + __this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT); } @@ -2723,7 +2710,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; } - if (data & TSC_RATIO_RSVD) + if (data & SVM_TSC_RATIO_RSVD) return 1; svm->tsc_ratio_msr = data; @@ -2918,7 +2905,7 @@ static int interrupt_window_interception(struct kvm_vcpu *vcpu) * In this case AVIC was temporarily disabled for * requesting the IRQ window and we have to re-enable it. */ - kvm_request_apicv_update(vcpu->kvm, true, APICV_INHIBIT_REASON_IRQWIN); + kvm_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN); ++vcpu->stat.irq_window_exits; return 1; @@ -3516,7 +3503,7 @@ static void svm_enable_irq_window(struct kvm_vcpu *vcpu) * via AVIC. In such case, we need to temporarily disable AVIC, * and fallback to injecting IRQ via V_IRQ. */ - kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_IRQWIN); + kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN); svm_set_vintr(svm); } } @@ -3948,6 +3935,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_cpuid_entry2 *best; + struct kvm *kvm = vcpu->kvm; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -3974,16 +3962,14 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * is exposed to the guest, disable AVIC. */ if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC)) - kvm_request_apicv_update(vcpu->kvm, false, - APICV_INHIBIT_REASON_X2APIC); + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_X2APIC); /* * Currently, AVIC does not work with nested virtualization. * So, we disable AVIC when cpuid for SVM is set in the L1 guest. */ if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - kvm_request_apicv_update(vcpu->kvm, false, - APICV_INHIBIT_REASON_NESTED); + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_NESTED); } init_vmcb_after_set_cpuid(vcpu); } @@ -4766,10 +4752,10 @@ static __init int svm_hardware_setup(void) } else { pr_info("TSC scaling supported\n"); kvm_has_tsc_control = true; - kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; - kvm_tsc_scaling_ratio_frac_bits = 32; } } + kvm_max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX; + kvm_tsc_scaling_ratio_frac_bits = 32; tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index e37bb3508cfa..f77a7d2d39dd 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -22,6 +22,8 @@ #include <asm/svm.h> #include <asm/sev-common.h> +#include "kvm_cache_regs.h" + #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) #define IOPM_SIZE PAGE_SIZE * 3 @@ -569,17 +571,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -592,7 +583,7 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -bool avic_check_apicv_inhibit_reasons(ulong bit); +bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); void avic_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); void avic_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); bool avic_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 98aa981c04ec..8cdc62c74a96 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -4,7 +4,6 @@ */ #include <linux/kvm_host.h> -#include "kvm_cache_regs.h" #include <asm/mshyperv.h> diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 193f5ba930d1..e3a24b8f04be 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1339,23 +1339,25 @@ TRACE_EVENT(kvm_hv_stimer_cleanup, __entry->vcpu_id, __entry->timer_index) ); -TRACE_EVENT(kvm_apicv_update_request, - TP_PROTO(bool activate, unsigned long bit), - TP_ARGS(activate, bit), +TRACE_EVENT(kvm_apicv_inhibit_changed, + TP_PROTO(int reason, bool set, unsigned long inhibits), + TP_ARGS(reason, set, inhibits), TP_STRUCT__entry( - __field(bool, activate) - __field(unsigned long, bit) + __field(int, reason) + __field(bool, set) + __field(unsigned long, inhibits) ), TP_fast_assign( - __entry->activate = activate; - __entry->bit = bit; + __entry->reason = reason; + __entry->set = set; + __entry->inhibits = inhibits; ), - TP_printk("%s bit=%lu", - __entry->activate ? "activate" : "deactivate", - __entry->bit) + TP_printk("%s reason=%u, inhibits=0x%lx", + __entry->set ? "set" : "cleared", + __entry->reason, __entry->inhibits) ); TRACE_EVENT(kvm_apicv_accept_irq, diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 0684e519181b..bc3f8512bb64 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -389,6 +389,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) struct kvm_pmc *pmc; u32 msr = msr_info->index; u64 data = msr_info->data; + u64 reserved_bits; switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: @@ -443,7 +444,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) return 0; - if (!(data & pmu->reserved_bits)) { + reserved_bits = pmu->reserved_bits; + if ((pmc->idx == 2) && + (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED)) + reserved_bits ^= HSW_IN_TX_CHECKPOINTED; + if (!(data & reserved_bits)) { reprogram_gp_counter(pmc, data); return 0; } @@ -485,6 +490,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->version = 0; pmu->reserved_bits = 0xffffffff00200000ull; + pmu->raw_event_mask = X86_RAW_EVENT_MASK; entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); if (!entry || !vcpu->kvm->arch.enable_pmu) @@ -533,8 +539,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) entry = kvm_find_cpuid_entry(vcpu, 7, 0); if (entry && (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && - (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) - pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; + (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) { + pmu->reserved_bits ^= HSW_IN_TX; + pmu->raw_event_mask |= (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED); + } bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e8963f5af618..04d170c4b61e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2866,21 +2866,17 @@ static void enter_rmode(struct kvm_vcpu *vcpu) int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmx_uret_msr *msr = vmx_find_uret_msr(vmx, MSR_EFER); /* Nothing to do if hardware doesn't support EFER. */ - if (!msr) + if (!vmx_find_uret_msr(vmx, MSR_EFER)) return 0; vcpu->arch.efer = efer; - if (efer & EFER_LMA) { - vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - msr->data = efer; - } else { - vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); + if (efer & EFER_LMA) + vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE); + else + vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE); - msr->data = efer & ~EFER_LME; - } vmx_setup_uret_msrs(vmx); return 0; } @@ -2906,7 +2902,6 @@ static void enter_lmode(struct kvm_vcpu *vcpu) static void exit_lmode(struct kvm_vcpu *vcpu) { - vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); } @@ -7705,14 +7700,14 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -static bool vmx_check_apicv_inhibit_reasons(ulong bit) +static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ); - return supported & BIT(bit); + return supported & BIT(reason); } static struct kvm_x86_ops vmx_x86_ops __initdata = { @@ -7980,12 +7975,11 @@ static __init int hardware_setup(void) if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr = NULL; - if (cpu_has_vmx_tsc_scaling()) { + if (cpu_has_vmx_tsc_scaling()) kvm_has_tsc_control = true; - kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; - kvm_tsc_scaling_ratio_frac_bits = 48; - } + kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_tsc_scaling_ratio_frac_bits = 48; kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 02cf0a7e1d14..547ba00ef64f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1748,9 +1748,6 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, { struct msr_data msr; - if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return KVM_MSR_RET_FILTERED; - switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: @@ -1832,9 +1829,6 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, struct msr_data msr; int ret; - if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return KVM_MSR_RET_FILTERED; - switch (index) { case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) @@ -1871,6 +1865,20 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, return ret; } +static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) + return KVM_MSR_RET_FILTERED; + return kvm_get_msr_ignored_check(vcpu, index, data, false); +} + +static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) + return KVM_MSR_RET_FILTERED; + return kvm_set_msr_ignored_check(vcpu, index, data, false); +} + int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { return kvm_get_msr_ignored_check(vcpu, index, data, false); @@ -1953,7 +1961,7 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) u64 data; int r; - r = kvm_get_msr(vcpu, ecx, &data); + r = kvm_get_msr_with_filter(vcpu, ecx, &data); if (!r) { trace_kvm_msr_read(ecx, data); @@ -1978,7 +1986,7 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) u64 data = kvm_read_edx_eax(vcpu); int r; - r = kvm_set_msr(vcpu, ecx, data); + r = kvm_set_msr_with_filter(vcpu, ecx, data); if (!r) { trace_kvm_msr_write(ecx, data); @@ -2893,7 +2901,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) static void kvm_update_masterclock(struct kvm *kvm) { - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); @@ -3105,8 +3113,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (!v->vcpu_idx) - kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); + kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -5938,7 +5945,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; - kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); @@ -6233,7 +6240,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; - kvm_hv_invalidate_tsc_page(kvm); + kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); @@ -6335,7 +6342,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; - kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -6726,7 +6733,7 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, static_call(kvm_x86_get_segment)(vcpu, var, seg); } -gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -6746,7 +6753,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); @@ -6756,7 +6763,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } @@ -6766,7 +6773,7 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } @@ -6782,7 +6789,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, u32 access, + struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; @@ -6819,7 +6826,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; @@ -6844,7 +6851,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; + u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -6863,9 +6870,11 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = 0; + u64 access = 0; - if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) + if (system) + access |= PFERR_IMPLICIT_ACCESS; + else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -6881,7 +6890,7 @@ static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, } static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu, u32 access, + struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; @@ -6915,9 +6924,11 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = PFERR_WRITE_MASK; + u64 access = PFERR_WRITE_MASK; - if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) + if (system) + access |= PFERR_IMPLICIT_ACCESS; + else if (static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -6984,7 +6995,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, bool write) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) + u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* @@ -7627,13 +7638,13 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, return; } -static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 *pdata) +static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; - r = kvm_get_msr(vcpu, msr_index, pdata); + r = kvm_get_msr_with_filter(vcpu, msr_index, pdata); if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, complete_emulated_rdmsr, r)) { @@ -7644,13 +7655,13 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, return r; } -static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 data) +static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; - r = kvm_set_msr(vcpu, msr_index, data); + r = kvm_set_msr_with_filter(vcpu, msr_index, data); if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, complete_emulated_msr_access, r)) { @@ -7661,6 +7672,18 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, return r; } +static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 *pdata) +{ + return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); +} + +static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, + u32 msr_index, u64 data) +{ + return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); +} + static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); @@ -7724,6 +7747,11 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } +static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); +} + static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); @@ -7794,6 +7822,8 @@ static const struct x86_emulate_ops emulate_ops = { .set_dr = emulator_set_dr, .get_smbase = emulator_get_smbase, .set_smbase = emulator_set_smbase, + .set_msr_with_filter = emulator_set_msr_with_filter, + .get_msr_with_filter = emulator_get_msr_with_filter, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, @@ -7806,6 +7836,7 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_long_mode = emulator_guest_has_long_mode, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, + .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .exiting_smm = emulator_exiting_smm, @@ -8894,7 +8925,7 @@ int kvm_arch_init(void *opaque) } kvm_nr_uret_msrs = 0; - r = kvm_mmu_module_init(); + r = kvm_mmu_vendor_module_init(); if (r) goto out_free_percpu; @@ -8942,7 +8973,7 @@ void kvm_arch_exit(void) cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; - kvm_mmu_module_exit(); + kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN @@ -9058,15 +9089,29 @@ bool kvm_apicv_activated(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_apicv_activated); + +static void set_or_clear_apicv_inhibit(unsigned long *inhibits, + enum kvm_apicv_inhibit reason, bool set) +{ + if (set) + __set_bit(reason, inhibits); + else + __clear_bit(reason, inhibits); + + trace_kvm_apicv_inhibit_changed(reason, set, *inhibits); +} + static void kvm_apicv_init(struct kvm *kvm) { + unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons; + init_rwsem(&kvm->arch.apicv_update_lock); - set_bit(APICV_INHIBIT_REASON_ABSENT, - &kvm->arch.apicv_inhibit_reasons); + set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true); + if (!enable_apicv) - set_bit(APICV_INHIBIT_REASON_DISABLE, - &kvm->arch.apicv_inhibit_reasons); + set_or_clear_apicv_inhibit(inhibits, + APICV_INHIBIT_REASON_ABSENT, true); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -9740,24 +9785,21 @@ out: } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); -void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set) { unsigned long old, new; lockdep_assert_held_write(&kvm->arch.apicv_update_lock); - if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(bit)) + if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason)) return; old = new = kvm->arch.apicv_inhibit_reasons; - if (activate) - __clear_bit(bit, &new); - else - __set_bit(bit, &new); + set_or_clear_apicv_inhibit(&new, reason, set); if (!!old != !!new) { - trace_kvm_apicv_update_request(activate, bit); /* * Kick all vCPUs before setting apicv_inhibit_reasons to avoid * false positives in the sanity check WARN in svm_vcpu_run(). @@ -9776,20 +9818,22 @@ void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); kvm_zap_gfn_range(kvm, gfn, gfn+1); } - } else + } else { kvm->arch.apicv_inhibit_reasons = new; + } } -void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) +void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, + enum kvm_apicv_inhibit reason, bool set) { if (!enable_apicv) return; down_write(&kvm->arch.apicv_update_lock); - __kvm_request_apicv_update(kvm, activate, bit); + __kvm_set_or_clear_apicv_inhibit(kvm, reason, set); up_write(&kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(kvm_request_apicv_update); +EXPORT_SYMBOL_GPL(kvm_set_or_clear_apicv_inhibit); static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { @@ -10937,7 +10981,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { - bool inhibit = false; + bool set = false; struct kvm_vcpu *vcpu; unsigned long i; @@ -10945,11 +10989,11 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { - inhibit = true; + set = true; break; } } - __kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ); + __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set); up_write(&kvm->arch.apicv_update_lock); } @@ -11557,10 +11601,8 @@ int kvm_arch_hardware_setup(void *opaque) u64 max = min(0x7fffffffULL, __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz)); kvm_max_guest_tsc_khz = max; - - kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; } - + kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; kvm_init_msr_list(); return 0; } @@ -11629,12 +11671,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) ret = kvm_page_track_init(kvm); if (ret) - return ret; + goto out; + + ret = kvm_mmu_init_vm(kvm); + if (ret) + goto out_page_track; INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); - INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -11666,10 +11709,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_mmu_init_vm(kvm); kvm_xen_init_vm(kvm); return static_call(kvm_x86_vm_init)(kvm); + +out_page_track: + kvm_page_track_cleanup(kvm); +out: + return ret; } int kvm_arch_post_init_vm(struct kvm *kvm) @@ -12593,7 +12640,7 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; - u32 access = error_code & + u64 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || @@ -12933,9 +12980,24 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); + +static int __init kvm_x86_init(void) +{ + kvm_mmu_x86_module_init(); + return 0; +} +module_init(kvm_x86_init); + +static void __exit kvm_x86_exit(void) +{ + /* + * If module_init() is implemented, module_exit() must also be + * implemented to allow module unload. + */ +} +module_exit(kvm_x86_exit); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 4aa0f2b31665..bf6cc25eee76 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -39,8 +39,8 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) } do { - ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, false, true, - gpa, PAGE_SIZE, false); + ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN, + gpa, PAGE_SIZE); if (ret) goto out; @@ -1025,8 +1025,7 @@ static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm break; idx = srcu_read_lock(&kvm->srcu); - rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, - PAGE_SIZE, false); + rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, PAGE_SIZE); srcu_read_unlock(&kvm->srcu, idx); } while(!rc); diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index 1f8a8f895173..50734a23034c 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -93,7 +93,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) buff += 8; } if (len & 7) { -#ifdef CONFIG_DCACHE_WORD_ACCESS unsigned int shift = (8 - (len & 7)) * 8; unsigned long trail; @@ -103,31 +102,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) "adcq $0,%[res]" : [res] "+r" (temp64) : [trail] "r" (trail)); -#else - if (len & 4) { - asm("addq %[val],%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r" (temp64) - : [val] "r" ((u64)*(u32 *)buff) - : "memory"); - buff += 4; - } - if (len & 2) { - asm("addq %[val],%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r" (temp64) - : [val] "r" ((u64)*(u16 *)buff) - : "memory"); - buff += 2; - } - if (len & 1) { - asm("addq %[val],%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r" (temp64) - : [val] "r" ((u64)*(u8 *)buff) - : "memory"); - } -#endif } result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); if (unlikely(odd)) { diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index df50451d94ef..3e2f33fc33de 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -22,7 +22,7 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n) : "memory"); } -void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) +static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) { if (unlikely(!n)) return; @@ -38,9 +38,8 @@ void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) } rep_movs(to, (const void *)from, n); } -EXPORT_SYMBOL(memcpy_fromio); -void memcpy_toio(volatile void __iomem *to, const void *from, size_t n) +static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n) { if (unlikely(!n)) return; @@ -56,14 +55,64 @@ void memcpy_toio(volatile void __iomem *to, const void *from, size_t n) } rep_movs((void *)to, (const void *) from, n); } + +static void unrolled_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) +{ + const volatile char __iomem *in = from; + char *out = to; + int i; + + for (i = 0; i < n; ++i) + out[i] = readb(&in[i]); +} + +static void unrolled_memcpy_toio(volatile void __iomem *to, const void *from, size_t n) +{ + volatile char __iomem *out = to; + const char *in = from; + int i; + + for (i = 0; i < n; ++i) + writeb(in[i], &out[i]); +} + +static void unrolled_memset_io(volatile void __iomem *a, int b, size_t c) +{ + volatile char __iomem *mem = a; + int i; + + for (i = 0; i < c; ++i) + writeb(b, &mem[i]); +} + +void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) +{ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) + unrolled_memcpy_fromio(to, from, n); + else + string_memcpy_fromio(to, from, n); +} +EXPORT_SYMBOL(memcpy_fromio); + +void memcpy_toio(volatile void __iomem *to, const void *from, size_t n) +{ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) + unrolled_memcpy_toio(to, from, n); + else + string_memcpy_toio(to, from, n); +} EXPORT_SYMBOL(memcpy_toio); void memset_io(volatile void __iomem *a, int b, size_t c) { - /* - * TODO: memset can mangle the IO patterns quite a bit. - * perhaps it would be better to use a dumb one: - */ - memset((void *)a, b, c); + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { + unrolled_memset_io(a, b, c); + } else { + /* + * TODO: memset can mangle the IO patterns quite a bit. + * perhaps it would be better to use a dumb one: + */ + memset((void *)a, b, c); + } } EXPORT_SYMBOL(memset_io); diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0402a749f3a0..0ae6cf804197 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -119,7 +119,7 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) /* cache copy and flush to align dest */ if (!IS_ALIGNED(dest, 8)) { - unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest); memcpy((void *) dest, (void *) source, len); clean_cache_range((void *) dest, len); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb4d91d5365..d400b6d9d246 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -855,13 +855,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..16b6efacf7c6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else #endif diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..3822666fb73d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index ead7e5b3a975..1bcd42c53039 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -9,6 +9,7 @@ endmenu config UML_X86 def_bool y select ARCH_BINFMT_ELF_EXTRA_PHDRS if X86_32 + select DCACHE_WORD_ACCESS config 64BIT bool "64-bit kernel" if "$(SUBARCH)" = "x86" diff --git a/arch/x86/um/shared/sysdep/syscalls_64.h b/arch/x86/um/shared/sysdep/syscalls_64.h index 48d6cd12f8a5..b6b997225841 100644 --- a/arch/x86/um/shared/sysdep/syscalls_64.h +++ b/arch/x86/um/shared/sysdep/syscalls_64.h @@ -10,13 +10,12 @@ #include <linux/msg.h> #include <linux/shm.h> -typedef long syscall_handler_t(void); +typedef long syscall_handler_t(long, long, long, long, long, long); extern syscall_handler_t *sys_call_table[]; #define EXECUTE_SYSCALL(syscall, regs) \ - (((long (*)(long, long, long, long, long, long)) \ - (*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(®s->regs), \ + (((*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(®s->regs), \ UPT_SYSCALL_ARG2(®s->regs), \ UPT_SYSCALL_ARG3(®s->regs), \ UPT_SYSCALL_ARG4(®s->regs), \ diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index fe5323f0c42d..27b29ae6c471 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -12,7 +12,6 @@ #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <registers.h> #include <os.h> -#include <registers.h> long arch_prctl(struct task_struct *task, int option, unsigned long __user *arg2) diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 45cc0ae0af6f..c7b9f12896f2 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -29,7 +29,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lsave_cp_regs_cp##x: \ - xchal_cp##x##_store a2 a4 a5 a6 a7; \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ jx a0; \ .endif @@ -46,7 +46,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lload_cp_regs_cp##x: \ - xchal_cp##x##_load a2 a4 a5 a6 a7; \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ jx a0; \ .endif diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c index 0dde21e0d3de..ad1841cecdfb 100644 --- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) { struct patch *patch = data; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else { diff --git a/arch/xtensa/kernel/syscalls/Makefile b/arch/xtensa/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/xtensa/kernel/syscalls/Makefile +++ b/arch/xtensa/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 81d7c7e8f7e9..10b79d3c74e0 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -36,24 +36,19 @@ static void rs_poll(struct timer_list *); static struct tty_driver *serial_driver; static struct tty_port serial_port; static DEFINE_TIMER(serial_timer, rs_poll); -static DEFINE_SPINLOCK(timer_lock); static int rs_open(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock_bh(&timer_lock); return 0; } static void rs_close(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) del_timer_sync(&serial_timer); - spin_unlock_bh(&timer_lock); } @@ -73,8 +68,6 @@ static void rs_poll(struct timer_list *unused) int rd = 1; unsigned char c; - spin_lock(&timer_lock); - while (simc_poll(0)) { rd = simc_read(0, &c, 1); if (rd <= 0) @@ -87,7 +80,6 @@ static void rs_poll(struct timer_list *unused) tty_flip_buffer_push(port); if (rd) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock(&timer_lock); } diff --git a/block/bio.c b/block/bio.c index cdd7b2915c53..4259125e16ab 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1598,7 +1598,7 @@ EXPORT_SYMBOL(bio_split); void bio_trim(struct bio *bio, sector_t offset, sector_t size) { if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || - offset + size > bio->bi_iter.bi_size)) + offset + size > bio_sectors(bio))) return; size <<= 9; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 0430926426fe..8dfe62786cd5 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -65,19 +65,12 @@ static bool blkcg_policy_enabled(struct request_queue *q, return pol && test_bit(pol->plid, q->blkcg_pols); } -/** - * blkg_free - free a blkg - * @blkg: blkg to free - * - * Free @blkg which may be partially allocated. - */ -static void blkg_free(struct blkcg_gq *blkg) +static void blkg_free_workfn(struct work_struct *work) { + struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, + free_work); int i; - if (!blkg) - return; - for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); @@ -89,6 +82,25 @@ static void blkg_free(struct blkcg_gq *blkg) kfree(blkg); } +/** + * blkg_free - free a blkg + * @blkg: blkg to free + * + * Free @blkg which may be partially allocated. + */ +static void blkg_free(struct blkcg_gq *blkg) +{ + if (!blkg) + return; + + /* + * Both ->pd_free_fn() and request queue's release handler may + * sleep, so free us by scheduling one work func + */ + INIT_WORK(&blkg->free_work, blkg_free_workfn); + schedule_work(&blkg->free_work); +} + static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 11f49f78db32..df9cfe4ca532 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -280,7 +280,6 @@ int set_task_ioprio(struct task_struct *task, int ioprio) task_lock(task); if (task->flags & PF_EXITING) { - err = -ESRCH; kmem_cache_free(iocontext_cachep, ioc); goto out; } @@ -292,7 +291,7 @@ int set_task_ioprio(struct task_struct *task, int ioprio) task->io_context->ioprio = ioprio; out: task_unlock(task); - return err; + return 0; } EXPORT_SYMBOL_GPL(set_task_ioprio); diff --git a/block/blk-mq.c b/block/blk-mq.c index e6f24fa4a4c2..c4370d276170 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -794,7 +794,8 @@ bool blk_update_request(struct request *req, blk_status_t error, #endif if (unlikely(error && !blk_rq_is_passthrough(req) && - !(req->rq_flags & RQF_QUIET))) { + !(req->rq_flags & RQF_QUIET)) && + !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); } @@ -4462,21 +4463,28 @@ static bool blk_mq_elv_switch_none(struct list_head *head, return true; } -static void blk_mq_elv_switch_back(struct list_head *head, - struct request_queue *q) +static struct blk_mq_qe_pair *blk_lookup_qe_pair(struct list_head *head, + struct request_queue *q) { struct blk_mq_qe_pair *qe; - struct elevator_type *t = NULL; list_for_each_entry(qe, head, node) - if (qe->q == q) { - t = qe->type; - break; - } + if (qe->q == q) + return qe; - if (!t) - return; + return NULL; +} +static void blk_mq_elv_switch_back(struct list_head *head, + struct request_queue *q) +{ + struct blk_mq_qe_pair *qe; + struct elevator_type *t; + + qe = blk_lookup_qe_pair(head, q); + if (!qe) + return; + t = qe->type; list_del(&qe->node); kfree(qe); diff --git a/block/blk-wbt.h b/block/blk-wbt.h index 2eb01becde8c..7e44eccc676d 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -101,9 +101,6 @@ u64 wbt_default_latency_nsec(struct request_queue *); #else -static inline void wbt_track(struct request *rq, enum wbt_flags flags) -{ -} static inline int wbt_init(struct request_queue *q) { return -EINVAL; diff --git a/block/genhd.c b/block/genhd.c index c9a4fc90d3e9..b8b6759d670f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -335,7 +335,7 @@ int blk_alloc_ext_minor(void) { int idx; - idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT, GFP_KERNEL); + idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT - 1, GFP_KERNEL); if (idx == -ENOSPC) return -EBUSY; return idx; diff --git a/block/ioctl.c b/block/ioctl.c index 4a86340133e4..f8703db99c73 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -629,7 +629,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: - if (bdev_nr_sectors(bdev) > ~0UL) + if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, bdev_nr_sectors(bdev)); diff --git a/certs/Makefile b/certs/Makefile index 3ea7fe60823f..d8443cfb1c40 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -13,34 +13,20 @@ obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_nohashes.o endif quiet_cmd_extract_certs = CERT $@ - cmd_extract_certs = $(obj)/extract-cert $(2) $@ + cmd_extract_certs = $(obj)/extract-cert $(extract-cert-in) $@ +extract-cert-in = $(or $(filter-out $(obj)/extract-cert, $(real-prereqs)),"") $(obj)/system_certificates.o: $(obj)/x509_certificate_list $(obj)/x509_certificate_list: $(CONFIG_SYSTEM_TRUSTED_KEYS) $(obj)/extract-cert FORCE - $(call if_changed,extract_certs,$(if $(CONFIG_SYSTEM_TRUSTED_KEYS),$<,"")) + $(call if_changed,extract_certs) targets += x509_certificate_list -ifeq ($(CONFIG_MODULE_SIG),y) - SIGN_KEY = y -endif - -ifeq ($(CONFIG_IMA_APPRAISE_MODSIG),y) -ifeq ($(CONFIG_MODULES),y) - SIGN_KEY = y -endif -endif - -ifdef SIGN_KEY -############################################################################### -# # If module signing is requested, say by allyesconfig, but a key has not been # supplied, then one will need to be generated to make sure the build does not # fail and that the kernel may be used afterwards. # -############################################################################### - # We do it this way rather than having a boolean option for enabling an # external private key, because 'make randconfig' might enable such a # boolean option and we unfortunately can't make it depend on !RANDCONFIG. @@ -67,23 +53,22 @@ $(obj)/x509.genkey: endif # CONFIG_MODULE_SIG_KEY -# If CONFIG_MODULE_SIG_KEY isn't a PKCS#11 URI, depend on it -ifneq ($(filter-out pkcs11:%, $(CONFIG_MODULE_SIG_KEY)),) -X509_DEP := $(CONFIG_MODULE_SIG_KEY) -endif - $(obj)/system_certificates.o: $(obj)/signing_key.x509 -$(obj)/signing_key.x509: $(X509_DEP) $(obj)/extract-cert FORCE - $(call if_changed,extract_certs,$(if $(CONFIG_MODULE_SIG_KEY),$(if $(X509_DEP),$<,$(CONFIG_MODULE_SIG_KEY)),"")) -endif # CONFIG_MODULE_SIG +PKCS11_URI := $(filter pkcs11:%, $(CONFIG_MODULE_SIG_KEY)) +ifdef PKCS11_URI +$(obj)/signing_key.x509: extract-cert-in := $(PKCS11_URI) +endif + +$(obj)/signing_key.x509: $(filter-out $(PKCS11_URI),$(CONFIG_MODULE_SIG_KEY)) $(obj)/extract-cert FORCE + $(call if_changed,extract_certs) targets += signing_key.x509 $(obj)/revocation_certificates.o: $(obj)/x509_revocation_list $(obj)/x509_revocation_list: $(CONFIG_SYSTEM_REVOCATION_KEYS) $(obj)/extract-cert FORCE - $(call if_changed,extract_certs,$(if $(CONFIG_SYSTEM_REVOCATION_KEYS),$<,"")) + $(call if_changed,extract_certs) targets += x509_revocation_list diff --git a/certs/system_certificates.S b/certs/system_certificates.S index e1645e6f4d97..003e25d4a17e 100644 --- a/certs/system_certificates.S +++ b/certs/system_certificates.S @@ -9,10 +9,7 @@ system_certificate_list: __cert_list_start: __module_cert_start: -#if defined(CONFIG_MODULE_SIG) || (defined(CONFIG_IMA_APPRAISE_MODSIG) \ - && defined(CONFIG_MODULES)) .incbin "certs/signing_key.x509" -#endif __module_cert_end: .incbin "certs/x509_certificate_list" __cert_list_end: diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c index a5fe2926bf50..0555f68c2dfd 100644 --- a/drivers/acpi/acpi_ipmi.c +++ b/drivers/acpi/acpi_ipmi.c @@ -353,29 +353,27 @@ static void ipmi_flush_tx_msg(struct acpi_ipmi_device *ipmi) static void ipmi_cancel_tx_msg(struct acpi_ipmi_device *ipmi, struct acpi_ipmi_msg *msg) { - struct acpi_ipmi_msg *tx_msg, *temp; - bool msg_found = false; + struct acpi_ipmi_msg *tx_msg = NULL, *iter, *temp; unsigned long flags; spin_lock_irqsave(&ipmi->tx_msg_lock, flags); - list_for_each_entry_safe(tx_msg, temp, &ipmi->tx_msg_list, head) { - if (msg == tx_msg) { - msg_found = true; - list_del(&tx_msg->head); + list_for_each_entry_safe(iter, temp, &ipmi->tx_msg_list, head) { + if (msg == iter) { + tx_msg = iter; + list_del(&iter->head); break; } } spin_unlock_irqrestore(&ipmi->tx_msg_lock, flags); - if (msg_found) + if (tx_msg) acpi_ipmi_msg_put(tx_msg); } static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data) { struct acpi_ipmi_device *ipmi_device = user_msg_data; - bool msg_found = false; - struct acpi_ipmi_msg *tx_msg, *temp; + struct acpi_ipmi_msg *tx_msg = NULL, *iter, *temp; struct device *dev = ipmi_device->dev; unsigned long flags; @@ -387,16 +385,16 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data) } spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags); - list_for_each_entry_safe(tx_msg, temp, &ipmi_device->tx_msg_list, head) { - if (msg->msgid == tx_msg->tx_msgid) { - msg_found = true; - list_del(&tx_msg->head); + list_for_each_entry_safe(iter, temp, &ipmi_device->tx_msg_list, head) { + if (msg->msgid == iter->tx_msgid) { + tx_msg = iter; + list_del(&iter->head); break; } } spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags); - if (!msg_found) { + if (!tx_msg) { dev_warn(dev, "Unexpected response (msg id %ld) is returned.\n", msg->msgid); @@ -482,15 +480,14 @@ err_ref: static void ipmi_bmc_gone(int iface) { - struct acpi_ipmi_device *ipmi_device, *temp; - bool dev_found = false; + struct acpi_ipmi_device *ipmi_device = NULL, *iter, *temp; mutex_lock(&driver_data.ipmi_lock); - list_for_each_entry_safe(ipmi_device, temp, + list_for_each_entry_safe(iter, temp, &driver_data.ipmi_devices, head) { - if (ipmi_device->ipmi_ifnum != iface) { - dev_found = true; - __ipmi_dev_kill(ipmi_device); + if (iter->ipmi_ifnum != iface) { + ipmi_device = iter; + __ipmi_dev_kill(iter); break; } } @@ -500,7 +497,7 @@ static void ipmi_bmc_gone(int iface) struct acpi_ipmi_device, head); mutex_unlock(&driver_data.ipmi_lock); - if (dev_found) { + if (ipmi_device) { ipmi_flush_tx_msg(ipmi_device); acpi_ipmi_dev_put(ipmi_device); } diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index c7fdb12c3310..33b7fbbeda82 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -319,7 +319,7 @@ repeat: if (res_ins) list_add(&res_ins->list, res_list); else { - res_ins = kmalloc(sizeof(*res), GFP_KERNEL); + res_ins = kmalloc(sizeof(*res_ins), GFP_KERNEL); if (!res_ins) return -ENOMEM; res_ins->start = start; diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index d418449194ee..bc1454789a06 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -654,7 +654,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) unsigned int num_ent, i, cpc_rev; int pcc_subspace_id = -1; acpi_status status; - int ret = -EFAULT; + int ret = -ENODATA; if (osc_sb_cppc_not_supported) return -ENODEV; @@ -679,9 +679,14 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) cpc_obj = &out_obj->package.elements[0]; if (cpc_obj->type == ACPI_TYPE_INTEGER) { num_ent = cpc_obj->integer.value; + if (num_ent <= 1) { + pr_debug("Unexpected _CPC NumEntries value (%d) for CPU:%d\n", + num_ent, pr->id); + goto out_free; + } } else { - pr_debug("Unexpected entry type(%d) for NumEntries\n", - cpc_obj->type); + pr_debug("Unexpected _CPC NumEntries entry type (%d) for CPU:%d\n", + cpc_obj->type, pr->id); goto out_free; } cpc_ptr->num_entries = num_ent; @@ -691,8 +696,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) if (cpc_obj->type == ACPI_TYPE_INTEGER) { cpc_rev = cpc_obj->integer.value; } else { - pr_debug("Unexpected entry type(%d) for Revision\n", - cpc_obj->type); + pr_debug("Unexpected _CPC Revision entry type (%d) for CPU:%d\n", + cpc_obj->type, pr->id); goto out_free; } cpc_ptr->version = cpc_rev; @@ -723,7 +728,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) if (pcc_data_alloc(pcc_subspace_id)) goto out_free; } else if (pcc_subspace_id != gas_t->access_width) { - pr_debug("Mismatched PCC ids.\n"); + pr_debug("Mismatched PCC ids in _CPC for CPU:%d\n", + pr->id); goto out_free; } } else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { @@ -742,20 +748,21 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) * SystemIO doesn't implement 64-bit * registers. */ - pr_debug("Invalid access width %d for SystemIO register\n", - gas_t->access_width); + pr_debug("Invalid access width %d for SystemIO register in _CPC\n", + gas_t->access_width); goto out_free; } if (gas_t->address & OVER_16BTS_MASK) { /* SystemIO registers use 16-bit integer addresses */ - pr_debug("Invalid IO port %llu for SystemIO register\n", - gas_t->address); + pr_debug("Invalid IO port %llu for SystemIO register in _CPC\n", + gas_t->address); goto out_free; } } else { if (gas_t->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE || !cpc_ffh_supported()) { /* Support only PCC, SystemMemory, SystemIO, and FFH type regs. */ - pr_debug("Unsupported register type: %d\n", gas_t->space_id); + pr_debug("Unsupported register type (%d) in _CPC\n", + gas_t->space_id); goto out_free; } } @@ -763,7 +770,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) cpc_ptr->cpc_regs[i-2].type = ACPI_TYPE_BUFFER; memcpy(&cpc_ptr->cpc_regs[i-2].cpc_entry.reg, gas_t, sizeof(*gas_t)); } else { - pr_debug("Err in entry:%d in CPC table of CPU:%d\n", i, pr->id); + pr_debug("Invalid entry type (%d) in _CPC for CPU:%d\n", + i, pr->id); goto out_free; } } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 32b20efff5f8..4556c86c3465 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -570,8 +570,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) { struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); + ACPI_FLUSH_CPU_CACHE(); while (1) { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 9efbfe087de7..762b61f67e6c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -588,19 +588,6 @@ static struct acpi_device *handle_to_device(acpi_handle handle, return adev; } -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device) -{ - if (!device) - return -EINVAL; - - *device = handle_to_device(handle, NULL); - if (!*device) - return -ENODEV; - - return 0; -} -EXPORT_SYMBOL(acpi_bus_get_device); - /** * acpi_fetch_acpi_dev - Retrieve ACPI device object. * @handle: ACPI handle associated with the requested ACPI device object. diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index ceee808f7f2a..47ec11d4c68e 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -151,8 +151,8 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { struct acpi_madt_local_apic_override *p = (struct acpi_madt_local_apic_override *)header; - pr_info("LAPIC_ADDR_OVR (address[%p])\n", - (void *)(unsigned long)p->address); + pr_info("LAPIC_ADDR_OVR (address[0x%llx])\n", + p->address); } break; diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index e5641e6c52ee..bb45a9c00514 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -115,14 +115,16 @@ config SATA_AHCI If unsure, say N. -config SATA_LPM_POLICY +config SATA_MOBILE_LPM_POLICY int "Default SATA Link Power Management policy for low power chipsets" range 0 4 default 0 depends on SATA_AHCI help Select the Default SATA Link Power Management (LPM) policy to use - for chipsets / "South Bridges" designated as supporting low power. + for chipsets / "South Bridges" supporting low-power modes. Such + chipsets are typically found on most laptops but desktops and + servers now also widely use chipsets supporting low power modes. The value set has the following meanings: 0 => Keep firmware settings diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 84456c05e845..397dfd27c90d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1595,7 +1595,7 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, static void ahci_update_initial_lpm_policy(struct ata_port *ap, struct ahci_host_priv *hpriv) { - int policy = CONFIG_SATA_LPM_POLICY; + int policy = CONFIG_SATA_MOBILE_LPM_POLICY; /* Ignore processing for chipsets that don't use policy */ diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 6ead58c1b6e5..ad11a4c52fbe 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -236,7 +236,7 @@ enum { AHCI_HFLAG_NO_WRITE_TO_RO = (1 << 24), /* don't write to read only registers */ AHCI_HFLAG_USE_LPM_POLICY = (1 << 25), /* chipset that should use - SATA_LPM_POLICY + SATA_MOBILE_LPM_POLICY as default lpm_policy */ AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during suspend/resume */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cceedde51126..ca64837641be 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4014,6 +4014,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_NO_DMA_LOG | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b3be7a8f5bea..b1666adc1c3a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1634,7 +1634,7 @@ EXPORT_SYMBOL_GPL(ata_sff_interrupt); void ata_sff_lost_interrupt(struct ata_port *ap) { - u8 status; + u8 status = 0; struct ata_queued_cmd *qc; /* Only one outstanding command per SFF channel */ diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index bec33d781ae0..e3263e961045 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -137,7 +137,11 @@ struct sata_dwc_device { #endif }; -#define SATA_DWC_QCMD_MAX 32 +/* + * Allow one extra special slot for commands and DMA management + * to account for libata internal commands. + */ +#define SATA_DWC_QCMD_MAX (ATA_MAX_QUEUE + 1) struct sata_dwc_device_port { struct sata_dwc_device *hsdev; diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c index 2578b2d45439..e465108d9998 100644 --- a/drivers/auxdisplay/lcd2s.c +++ b/drivers/auxdisplay/lcd2s.c @@ -1,10 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* - * console driver for LCD2S 4x20 character displays connected through i2c. - * The display also has a spi interface, but the driver does not support + * Console driver for LCD2S 4x20 character displays connected through i2c. + * The display also has a SPI interface, but the driver does not support * this yet. * - * This is a driver allowing you to use a LCD2S 4x20 from modtronix + * This is a driver allowing you to use a LCD2S 4x20 from Modtronix * engineering as auxdisplay character device. * * (C) 2019 by Lemonage Software GmbH @@ -12,7 +12,9 @@ * All rights reserved. */ #include <linux/kernel.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/property.h> #include <linux/slab.h> #include <linux/i2c.h> #include <linux/delay.h> @@ -104,7 +106,7 @@ static int lcd2s_print(struct charlcd *lcd, int c) static int lcd2s_gotoxy(struct charlcd *lcd, unsigned int x, unsigned int y) { struct lcd2s_data *lcd2s = lcd->drvdata; - u8 buf[] = { LCD2S_CMD_CUR_POS, y + 1, x + 1}; + u8 buf[3] = { LCD2S_CMD_CUR_POS, y + 1, x + 1 }; lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf)); @@ -214,16 +216,15 @@ static int lcd2s_lines(struct charlcd *lcd, enum charlcd_lines lines) return 0; } +/* + * Generator: LGcxxxxx...xx; must have <c> between '0' and '7', + * representing the numerical ASCII code of the redefined character, + * and <xx...xx> a sequence of 16 hex digits representing 8 bytes + * for each character. Most LCDs will only use 5 lower bits of + * the 7 first bytes. + */ static int lcd2s_redefine_char(struct charlcd *lcd, char *esc) { - /* Generator : LGcxxxxx...xx; must have <c> between '0' - * and '7', representing the numerical ASCII code of the - * redefined character, and <xx...xx> a sequence of 16 - * hex digits representing 8 bytes for each character. - * Most LCDs will only use 5 lower bits of the 7 first - * bytes. - */ - struct lcd2s_data *lcd2s = lcd->drvdata; u8 buf[LCD2S_CHARACTER_SIZE + 2] = { LCD2S_CMD_DEF_CUSTOM_CHAR }; u8 value; @@ -286,8 +287,7 @@ static const struct charlcd_ops lcd2s_ops = { .redefine_char = lcd2s_redefine_char, }; -static int lcd2s_i2c_probe(struct i2c_client *i2c, - const struct i2c_device_id *id) +static int lcd2s_i2c_probe(struct i2c_client *i2c) { struct charlcd *lcd; struct lcd2s_data *lcd2s; @@ -355,43 +355,22 @@ static const struct i2c_device_id lcd2s_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, lcd2s_i2c_id); -#ifdef CONFIG_OF static const struct of_device_id lcd2s_of_table[] = { { .compatible = "modtronix,lcd2s" }, { } }; MODULE_DEVICE_TABLE(of, lcd2s_of_table); -#endif static struct i2c_driver lcd2s_i2c_driver = { .driver = { .name = "lcd2s", -#ifdef CONFIG_OF - .of_match_table = of_match_ptr(lcd2s_of_table), -#endif + .of_match_table = lcd2s_of_table, }, - .probe = lcd2s_i2c_probe, + .probe_new = lcd2s_i2c_probe, .remove = lcd2s_i2c_remove, .id_table = lcd2s_i2c_id, }; - -static int __init lcd2s_modinit(void) -{ - int ret = 0; - - ret = i2c_add_driver(&lcd2s_i2c_driver); - if (ret != 0) - pr_err("Failed to register lcd2s driver\n"); - - return ret; -} -module_init(lcd2s_modinit) - -static void __exit lcd2s_exit(void) -{ - i2c_del_driver(&lcd2s_i2c_driver); -} -module_exit(lcd2s_exit) +module_i2c_driver(lcd2s_i2c_driver); MODULE_DESCRIPTION("LCD2S character display driver"); MODULE_AUTHOR("Lars Poeschel"); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index af6bea56f4e2..3fc3b5940bb3 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -296,6 +296,7 @@ int driver_deferred_probe_check_state(struct device *dev) return -EPROBE_DEFER; } +EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state); static void deferred_probe_timeout_work_func(struct work_struct *work) { diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 4b55e864a0a3..4d3efaa20b7b 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1638,22 +1638,22 @@ struct sib_info { }; void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib); -extern void notify_resource_state(struct sk_buff *, +extern int notify_resource_state(struct sk_buff *, unsigned int, struct drbd_resource *, struct resource_info *, enum drbd_notification_type); -extern void notify_device_state(struct sk_buff *, +extern int notify_device_state(struct sk_buff *, unsigned int, struct drbd_device *, struct device_info *, enum drbd_notification_type); -extern void notify_connection_state(struct sk_buff *, +extern int notify_connection_state(struct sk_buff *, unsigned int, struct drbd_connection *, struct connection_info *, enum drbd_notification_type); -extern void notify_peer_device_state(struct sk_buff *, +extern int notify_peer_device_state(struct sk_buff *, unsigned int, struct drbd_peer_device *, struct peer_device_info *, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 96881d5babd9..4b0b25cc916e 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -171,7 +171,7 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr, unsigned int set_size) { struct drbd_request *r; - struct drbd_request *req = NULL; + struct drbd_request *req = NULL, *tmp = NULL; int expect_epoch = 0; int expect_size = 0; @@ -225,8 +225,11 @@ void tl_release(struct drbd_connection *connection, unsigned int barrier_nr, * to catch requests being barrier-acked "unexpectedly". * It usually should find the same req again, or some READ preceding it. */ list_for_each_entry(req, &connection->transfer_log, tl_requests) - if (req->epoch == expect_epoch) + if (req->epoch == expect_epoch) { + tmp = req; break; + } + req = list_prepare_entry(tmp, &connection->transfer_log, tl_requests); list_for_each_entry_safe_from(req, r, &connection->transfer_log, tl_requests) { if (req->epoch != expect_epoch) break; @@ -2716,6 +2719,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ @@ -2770,12 +2774,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig if (init_submitter(device)) { err = ERR_NOMEM; - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; } err = add_disk(disk); if (err) - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; /* inherit the connection state */ device->state.conn = first_connection(resource)->cstate; @@ -2789,8 +2793,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; -out_idr_remove_vol: - idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection(connection, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 02030c9c4d3b..b7216c186ba4 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -4549,7 +4549,7 @@ static int nla_put_notification_header(struct sk_buff *msg, return drbd_notification_header_to_skb(msg, &nh, true); } -void notify_resource_state(struct sk_buff *skb, +int notify_resource_state(struct sk_buff *skb, unsigned int seq, struct drbd_resource *resource, struct resource_info *resource_info, @@ -4591,16 +4591,17 @@ void notify_resource_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_device_state(struct sk_buff *skb, +int notify_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_device *device, struct device_info *device_info, @@ -4640,16 +4641,17 @@ void notify_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_connection_state(struct sk_buff *skb, +int notify_connection_state(struct sk_buff *skb, unsigned int seq, struct drbd_connection *connection, struct connection_info *connection_info, @@ -4689,16 +4691,17 @@ void notify_connection_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_peer_device_state(struct sk_buff *skb, +int notify_peer_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device *peer_device, struct peer_device_info *peer_device_info, @@ -4739,13 +4742,14 @@ void notify_peer_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } void notify_helper(enum drbd_notification_type type, @@ -4796,7 +4800,7 @@ fail: err, seq); } -static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) +static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq) { struct drbd_genlmsghdr *dh; int err; @@ -4810,11 +4814,12 @@ static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) if (nla_put_notification_header(skb, NOTIFY_EXISTS)) goto nla_put_failure; genlmsg_end(skb, dh); - return; + return 0; nla_put_failure: nlmsg_free(skb); pr_err("Error %d sending event. Event seq:%u\n", err, seq); + return err; } static void free_state_changes(struct list_head *list) @@ -4841,6 +4846,7 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) unsigned int seq = cb->args[2]; unsigned int n; enum drbd_notification_type flags = 0; + int err = 0; /* There is no need for taking notification_mutex here: it doesn't matter if the initial state events mix with later state chage @@ -4849,32 +4855,32 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) cb->args[5]--; if (cb->args[5] == 1) { - notify_initial_state_done(skb, seq); + err = notify_initial_state_done(skb, seq); goto out; } n = cb->args[4]++; if (cb->args[4] < cb->args[3]) flags |= NOTIFY_CONTINUES; if (n < 1) { - notify_resource_state_change(skb, seq, state_change->resource, + err = notify_resource_state_change(skb, seq, state_change->resource, NOTIFY_EXISTS | flags); goto next; } n--; if (n < state_change->n_connections) { - notify_connection_state_change(skb, seq, &state_change->connections[n], + err = notify_connection_state_change(skb, seq, &state_change->connections[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_connections; if (n < state_change->n_devices) { - notify_device_state_change(skb, seq, &state_change->devices[n], + err = notify_device_state_change(skb, seq, &state_change->devices[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_devices; if (n < state_change->n_devices * state_change->n_connections) { - notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], + err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], NOTIFY_EXISTS | flags); goto next; } @@ -4889,7 +4895,10 @@ next: cb->args[4] = 0; } out: - return skb->len; + if (err) + return err; + else + return skb->len; } int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index c04394518b07..75be0e16770a 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -180,7 +180,8 @@ void start_new_tl_epoch(struct drbd_connection *connection) void complete_master_bio(struct drbd_device *device, struct bio_and_error *m) { - m->bio->bi_status = errno_to_blk_status(m->error); + if (unlikely(m->error)) + m->bio->bi_status = errno_to_blk_status(m->error); bio_endio(m->bio); dec_ap_bio(device); } @@ -332,17 +333,21 @@ static void set_if_null_req_next(struct drbd_peer_device *peer_device, struct dr static void advance_conn_req_next(struct drbd_peer_device *peer_device, struct drbd_request *req) { struct drbd_connection *connection = peer_device ? peer_device->connection : NULL; + struct drbd_request *iter = req; if (!connection) return; if (connection->req_next != req) return; - list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) { - const unsigned s = req->rq_state; - if (s & RQ_NET_QUEUED) + + req = NULL; + list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) { + const unsigned int s = iter->rq_state; + + if (s & RQ_NET_QUEUED) { + req = iter; break; + } } - if (&req->tl_requests == &connection->transfer_log) - req = NULL; connection->req_next = req; } @@ -358,17 +363,21 @@ static void set_if_null_req_ack_pending(struct drbd_peer_device *peer_device, st static void advance_conn_req_ack_pending(struct drbd_peer_device *peer_device, struct drbd_request *req) { struct drbd_connection *connection = peer_device ? peer_device->connection : NULL; + struct drbd_request *iter = req; if (!connection) return; if (connection->req_ack_pending != req) return; - list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) { - const unsigned s = req->rq_state; - if ((s & RQ_NET_SENT) && (s & RQ_NET_PENDING)) + + req = NULL; + list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) { + const unsigned int s = iter->rq_state; + + if ((s & RQ_NET_SENT) && (s & RQ_NET_PENDING)) { + req = iter; break; + } } - if (&req->tl_requests == &connection->transfer_log) - req = NULL; connection->req_ack_pending = req; } @@ -384,17 +393,21 @@ static void set_if_null_req_not_net_done(struct drbd_peer_device *peer_device, s static void advance_conn_req_not_net_done(struct drbd_peer_device *peer_device, struct drbd_request *req) { struct drbd_connection *connection = peer_device ? peer_device->connection : NULL; + struct drbd_request *iter = req; if (!connection) return; if (connection->req_not_net_done != req) return; - list_for_each_entry_continue(req, &connection->transfer_log, tl_requests) { - const unsigned s = req->rq_state; - if ((s & RQ_NET_SENT) && !(s & RQ_NET_DONE)) + + req = NULL; + list_for_each_entry_continue(iter, &connection->transfer_log, tl_requests) { + const unsigned int s = iter->rq_state; + + if ((s & RQ_NET_SENT) && !(s & RQ_NET_DONE)) { + req = iter; break; + } } - if (&req->tl_requests == &connection->transfer_log) - req = NULL; connection->req_not_net_done = req; } diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index b8a27818ab3f..4ee11aef6672 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1537,7 +1537,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, return rv; } -void notify_resource_state_change(struct sk_buff *skb, +int notify_resource_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_resource_state_change *resource_state_change, enum drbd_notification_type type) @@ -1550,10 +1550,10 @@ void notify_resource_state_change(struct sk_buff *skb, .res_susp_fen = resource_state_change->susp_fen[NEW], }; - notify_resource_state(skb, seq, resource, &resource_info, type); + return notify_resource_state(skb, seq, resource, &resource_info, type); } -void notify_connection_state_change(struct sk_buff *skb, +int notify_connection_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_connection_state_change *connection_state_change, enum drbd_notification_type type) @@ -1564,10 +1564,10 @@ void notify_connection_state_change(struct sk_buff *skb, .conn_role = connection_state_change->peer_role[NEW], }; - notify_connection_state(skb, seq, connection, &connection_info, type); + return notify_connection_state(skb, seq, connection, &connection_info, type); } -void notify_device_state_change(struct sk_buff *skb, +int notify_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_device_state_change *device_state_change, enum drbd_notification_type type) @@ -1577,10 +1577,10 @@ void notify_device_state_change(struct sk_buff *skb, .dev_disk_state = device_state_change->disk_state[NEW], }; - notify_device_state(skb, seq, device, &device_info, type); + return notify_device_state(skb, seq, device, &device_info, type); } -void notify_peer_device_state_change(struct sk_buff *skb, +int notify_peer_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device_state_change *p, enum drbd_notification_type type) @@ -1594,7 +1594,7 @@ void notify_peer_device_state_change(struct sk_buff *skb, .peer_resync_susp_dependency = p->resync_susp_dependency[NEW], }; - notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); + return notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); } static void broadcast_state_change(struct drbd_state_change *state_change) @@ -1602,7 +1602,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change) struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; bool resource_state_has_changed; unsigned int n_device, n_connection, n_peer_device, n_peer_devices; - void (*last_func)(struct sk_buff *, unsigned int, void *, + int (*last_func)(struct sk_buff *, unsigned int, void *, enum drbd_notification_type) = NULL; void *last_arg = NULL; diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h index ba80f612d6ab..d5b0479bc9a6 100644 --- a/drivers/block/drbd/drbd_state_change.h +++ b/drivers/block/drbd/drbd_state_change.h @@ -44,19 +44,19 @@ extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_ extern void copy_old_to_new_state_change(struct drbd_state_change *); extern void forget_state_change(struct drbd_state_change *); -extern void notify_resource_state_change(struct sk_buff *, +extern int notify_resource_state_change(struct sk_buff *, unsigned int, struct drbd_resource_state_change *, enum drbd_notification_type type); -extern void notify_connection_state_change(struct sk_buff *, +extern int notify_connection_state_change(struct sk_buff *, unsigned int, struct drbd_connection_state_change *, enum drbd_notification_type type); -extern void notify_device_state_change(struct sk_buff *, +extern int notify_device_state_change(struct sk_buff *, unsigned int, struct drbd_device_state_change *, enum drbd_notification_type type); -extern void notify_peer_device_state_change(struct sk_buff *, +extern int notify_peer_device_state_change(struct sk_buff *, unsigned int, struct drbd_peer_device_state_change *, enum drbd_notification_type type); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 3e636a75c83a..a58595f5ee2c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1591,6 +1591,7 @@ struct compat_loop_info { compat_ulong_t lo_inode; /* ioctl r/o */ compat_dev_t lo_rdevice; /* ioctl r/o */ compat_int_t lo_offset; + compat_int_t lo_encrypt_type; /* obsolete, ignored */ compat_int_t lo_encrypt_key_size; /* ioctl w/o */ compat_int_t lo_flags; /* ioctl r/o */ char lo_name[LO_NAME_SIZE]; diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 4db9a8c244af..e094d2b8b5a9 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -88,7 +88,7 @@ static void n64cart_submit_bio(struct bio *bio) { struct bio_vec bvec; struct bvec_iter iter; - struct device *dev = bio->bi_disk->private_data; + struct device *dev = bio->bi_bdev->bd_disk->private_data; u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT; bio_for_each_segment(bvec, bio, iter) { diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 05b1120e6623..c441a4972064 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1600,7 +1600,7 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) * Only fake timeouts need to execute blk_mq_complete_request() here. */ cmd->error = BLK_STS_TIMEOUT; - if (cmd->fake_timeout) + if (cmd->fake_timeout || hctx->type == HCTX_TYPE_POLL) blk_mq_complete_request(rq); return BLK_EH_DONE; } diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index d1e26461a64e..de42458195bc 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -931,7 +931,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, if (rc) goto unmap; - for (n = 0, i = 0; n < nseg; n++) { + for (n = 0; n < nseg; n++) { uint8_t first_sect, last_sect; if ((n % SEGS_PER_INDIRECT_FRAME) == 0) { diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 378262ec47ae..003056d4f7f5 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -576,7 +576,7 @@ struct setup_rw_req { struct blkif_request *ring_req; grant_ref_t gref_head; unsigned int id; - /* Only used when persistent grant is used and it's a read request */ + /* Only used when persistent grant is used and it's a write request */ bool need_copy; unsigned int bvec_off; char *bvec_data; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 7bd10d63ddbe..2dc9da683a13 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1365,7 +1365,6 @@ out_free: */ int cdrom_number_of_slots(struct cdrom_device_info *cdi) { - int status; int nslots = 1; struct cdrom_changer_info *info; @@ -1377,7 +1376,7 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi) if (!info) return -ENOMEM; - if ((status = cdrom_read_mech_status(cdi, info)) == 0) + if (cdrom_read_mech_status(cdi, info) == 0) nslots = info->hdr.nslots; kfree(info); diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 740811893c57..55f48375e3fe 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -449,6 +449,7 @@ config RANDOM_TRUST_BOOTLOADER device randomness. Say Y here to assume the entropy provided by the booloader is trustworthy so it will be added to the kernel's entropy pool. Otherwise, say N here so it will be regarded as device input that - only mixes the entropy pool. + only mixes the entropy pool. This can also be configured at boot with + "random.trust_bootloader=on/off". endmenu diff --git a/drivers/char/random.c b/drivers/char/random.c index 66ce7c03a142..3a293f919af9 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -224,9 +224,10 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, void * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to - * a read from /dev/urandom. The integer family of functions may be - * higher performance for one-off random integers, because they do a - * bit of buffering. + * a read from /dev/urandom. The u32, u64, int, and long family of + * functions may be higher performance for one-off random integers, + * because they do a bit of buffering and do not invoke reseeding + * until the buffer is emptied. * *********************************************************************/ @@ -332,7 +333,7 @@ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); - memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); + memmove(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } @@ -436,11 +437,8 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], * This shouldn't be set by functions like add_device_randomness(), * where we can't trust the buffer passed to it is guaranteed to be * unpredictable (so it might not have any entropy at all). - * - * Returns the number of bytes processed from input, which is bounded - * by CRNG_INIT_CNT_THRESH if account is true. */ -static size_t crng_pre_init_inject(const void *input, size_t len, bool account) +static void crng_pre_init_inject(const void *input, size_t len, bool account) { static int crng_init_cnt = 0; struct blake2s_state hash; @@ -451,18 +449,15 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) spin_lock_irqsave(&base_crng.lock, flags); if (crng_init != 0) { spin_unlock_irqrestore(&base_crng.lock, flags); - return 0; + return; } - if (account) - len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); - blake2s_update(&hash, base_crng.key, sizeof(base_crng.key)); blake2s_update(&hash, input, len); blake2s_final(&hash, base_crng.key); if (account) { - crng_init_cnt += len; + crng_init_cnt += min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { ++base_crng.generation; crng_init = 1; @@ -473,8 +468,6 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) if (crng_init == 1) pr_notice("fast init done\n"); - - return len; } static void _get_random_bytes(void *buf, size_t nbytes) @@ -530,49 +523,59 @@ EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) { - bool large_request = nbytes > 256; - ssize_t ret = 0; - size_t len; + size_t len, left, ret = 0; u32 chacha_state[CHACHA_STATE_WORDS]; u8 output[CHACHA_BLOCK_SIZE]; if (!nbytes) return 0; - len = min_t(size_t, 32, nbytes); - crng_make_state(chacha_state, output, len); - - if (copy_to_user(buf, output, len)) - return -EFAULT; - nbytes -= len; - buf += len; - ret += len; - - while (nbytes) { - if (large_request && need_resched()) { - if (signal_pending(current)) - break; - schedule(); - } + /* + * Immediately overwrite the ChaCha key at index 4 with random + * bytes, in case userspace causes copy_to_user() below to sleep + * forever, so that we still retain forward secrecy in that case. + */ + crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); + /* + * However, if we're doing a read of len <= 32, we don't need to + * use chacha_state after, so we can simply return those bytes to + * the user directly. + */ + if (nbytes <= CHACHA_KEY_SIZE) { + ret = nbytes - copy_to_user(buf, &chacha_state[4], nbytes); + goto out_zero_chacha; + } + for (;;) { chacha20_block(chacha_state, output); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE); - if (copy_to_user(buf, output, len)) { - ret = -EFAULT; + left = copy_to_user(buf, output, len); + if (left) { + ret += len - left; break; } - nbytes -= len; buf += len; ret += len; + nbytes -= len; + if (!nbytes) + break; + + BUILD_BUG_ON(PAGE_SIZE % CHACHA_BLOCK_SIZE != 0); + if (ret % PAGE_SIZE == 0) { + if (signal_pending(current)) + break; + cond_resched(); + } } - memzero_explicit(chacha_state, sizeof(chacha_state)); memzero_explicit(output, sizeof(output)); - return ret; +out_zero_chacha: + memzero_explicit(chacha_state, sizeof(chacha_state)); + return ret ? ret : -EFAULT; } /* @@ -948,11 +951,17 @@ static bool drain_entropy(void *buf, size_t nbytes, bool force) **********************************************************************/ static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); +static bool trust_bootloader __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER); static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); } +static int __init parse_trust_bootloader(char *arg) +{ + return kstrtobool(arg, &trust_bootloader); +} early_param("random.trust_cpu", parse_trust_cpu); +early_param("random.trust_bootloader", parse_trust_bootloader); /* * The first collection of entropy occurs at system boot while interrupts @@ -968,6 +977,11 @@ int __init rand_initialize(void) bool arch_init = true; unsigned long rv; +#if defined(LATENT_ENTROPY_PLUGIN) + static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; + _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); +#endif + for (i = 0; i < BLAKE2S_BLOCK_SIZE; i += sizeof(rv)) { if (!arch_get_random_seed_long_early(&rv) && !arch_get_random_long_early(&rv)) { @@ -1004,7 +1018,7 @@ int __init rand_initialize(void) */ void add_device_randomness(const void *buf, size_t size) { - cycles_t cycles = random_get_entropy(); + unsigned long cycles = random_get_entropy(); unsigned long flags, now = jiffies; if (crng_init == 0 && size) @@ -1035,8 +1049,7 @@ struct timer_rand_state { */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { - cycles_t cycles = random_get_entropy(); - unsigned long flags, now = jiffies; + unsigned long cycles = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; spin_lock_irqsave(&input_pool.lock, flags); @@ -1128,13 +1141,10 @@ void rand_initialize_disk(struct gendisk *disk) void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy) { - if (unlikely(crng_init == 0)) { - size_t ret = crng_pre_init_inject(buffer, count, true); - mix_pool_bytes(buffer, ret); - count -= ret; - buffer += ret; - if (!count || crng_init == 0) - return; + if (unlikely(crng_init == 0 && entropy < POOL_MIN_BITS)) { + crng_pre_init_inject(buffer, count, true); + mix_pool_bytes(buffer, count); + return; } /* @@ -1160,7 +1170,7 @@ EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); */ void add_bootloader_randomness(const void *buf, size_t size) { - if (IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER)) + if (trust_bootloader) add_hwgenerator_randomness(buf, size, size * 8); else add_device_randomness(buf, size); @@ -1328,8 +1338,7 @@ static void mix_interrupt_randomness(struct work_struct *work) void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; - cycles_t cycles = random_get_entropy(); - unsigned long now = jiffies; + unsigned long cycles = random_get_entropy(), now = jiffies; struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; @@ -1342,16 +1351,12 @@ void add_interrupt_randomness(int irq) if (cycles == 0) cycles = get_reg(fast_pool, regs); - if (sizeof(cycles) == 8) + if (sizeof(unsigned long) == 8) { irq_data.u64[0] = cycles ^ rol64(now, 32) ^ irq; - else { + irq_data.u64[1] = regs ? instruction_pointer(regs) : _RET_IP_; + } else { irq_data.u32[0] = cycles ^ irq; irq_data.u32[1] = now; - } - - if (sizeof(unsigned long) == 8) - irq_data.u64[1] = regs ? instruction_pointer(regs) : _RET_IP_; - else { irq_data.u32[2] = regs ? instruction_pointer(regs) : _RET_IP_; irq_data.u32[3] = get_reg(fast_pool, regs); } @@ -1398,7 +1403,7 @@ static void entropy_timer(struct timer_list *t) static void try_to_generate_entropy(void) { struct { - cycles_t cycles; + unsigned long cycles; struct timer_list timer; } stack; @@ -1533,6 +1538,13 @@ static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, { static int maxwarn = 10; + /* + * Opportunistically attempt to initialize the RNG on platforms that + * have fast cycle counters, but don't (for now) require it to succeed. + */ + if (!crng_ready()) + try_to_generate_entropy(); + if (!crng_ready() && maxwarn > 0) { maxwarn--; if (__ratelimit(&urandom_warning)) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 07a27b65b773..ed119182aa1b 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -2332,15 +2332,19 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate) } EXPORT_SYMBOL_GPL(clk_set_rate_exclusive); -static int clk_set_rate_range_nolock(struct clk *clk, - unsigned long min, - unsigned long max) +/** + * clk_set_rate_range - set a rate range for a clock source + * @clk: clock source + * @min: desired minimum clock rate in Hz, inclusive + * @max: desired maximum clock rate in Hz, inclusive + * + * Returns success (0) or negative errno. + */ +int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) { int ret = 0; unsigned long old_min, old_max, rate; - lockdep_assert_held(&prepare_lock); - if (!clk) return 0; @@ -2353,6 +2357,8 @@ static int clk_set_rate_range_nolock(struct clk *clk, return -EINVAL; } + clk_prepare_lock(); + if (clk->exclusive_count) clk_core_rate_unprotect(clk->core); @@ -2396,28 +2402,6 @@ out: if (clk->exclusive_count) clk_core_rate_protect(clk->core); - return ret; -} - -/** - * clk_set_rate_range - set a rate range for a clock source - * @clk: clock source - * @min: desired minimum clock rate in Hz, inclusive - * @max: desired maximum clock rate in Hz, inclusive - * - * Return: 0 for success or negative errno on failure. - */ -int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) -{ - int ret; - - if (!clk) - return 0; - - clk_prepare_lock(); - - ret = clk_set_rate_range_nolock(clk, min, max); - clk_prepare_unlock(); return ret; @@ -4419,7 +4403,9 @@ void __clk_put(struct clk *clk) } hlist_del(&clk->clks_node); - clk_set_rate_range_nolock(clk, 0, ULONG_MAX); + if (clk->min_rate > clk->core->req_rate || + clk->max_rate < clk->core->req_rate) + clk_core_set_rate_nolock(clk->core, clk->core->req_rate); owner = clk->core->owner; kref_put(&clk->core->ref, __clk_release); diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index fd2339cc5898..6731a822f4e3 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -760,65 +760,9 @@ static void clk_range_test_multiple_set_range_rate_maximized(struct kunit *test) clk_put(user1); } -/* - * Test that if we have several subsequent calls to - * clk_set_rate_range(), across multiple users, the core will reevaluate - * whether a new rate is needed, including when a user drop its clock. - * - * With clk_dummy_maximize_rate_ops, this means that the rate will - * trail along the maximum as it evolves. - */ -static void clk_range_test_multiple_set_range_rate_put_maximized(struct kunit *test) -{ - struct clk_dummy_context *ctx = test->priv; - struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; - struct clk *user1, *user2; - unsigned long rate; - - user1 = clk_hw_get_clk(hw, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user1); - - user2 = clk_hw_get_clk(hw, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user2); - - KUNIT_ASSERT_EQ(test, - clk_set_rate(clk, DUMMY_CLOCK_RATE_2 + 1000), - 0); - - KUNIT_ASSERT_EQ(test, - clk_set_rate_range(user1, - 0, - DUMMY_CLOCK_RATE_2), - 0); - - rate = clk_get_rate(clk); - KUNIT_ASSERT_GT(test, rate, 0); - KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); - - KUNIT_ASSERT_EQ(test, - clk_set_rate_range(user2, - 0, - DUMMY_CLOCK_RATE_1), - 0); - - rate = clk_get_rate(clk); - KUNIT_ASSERT_GT(test, rate, 0); - KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); - - clk_put(user2); - - rate = clk_get_rate(clk); - KUNIT_ASSERT_GT(test, rate, 0); - KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); - - clk_put(user1); -} - static struct kunit_case clk_range_maximize_test_cases[] = { KUNIT_CASE(clk_range_test_set_range_rate_maximized), KUNIT_CASE(clk_range_test_multiple_set_range_rate_maximized), - KUNIT_CASE(clk_range_test_multiple_set_range_rate_put_maximized), {} }; @@ -933,61 +877,9 @@ static void clk_range_test_multiple_set_range_rate_minimized(struct kunit *test) clk_put(user1); } -/* - * Test that if we have several subsequent calls to - * clk_set_rate_range(), across multiple users, the core will reevaluate - * whether a new rate is needed, including when a user drop its clock. - * - * With clk_dummy_minimize_rate_ops, this means that the rate will - * trail along the minimum as it evolves. - */ -static void clk_range_test_multiple_set_range_rate_put_minimized(struct kunit *test) -{ - struct clk_dummy_context *ctx = test->priv; - struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; - struct clk *user1, *user2; - unsigned long rate; - - user1 = clk_hw_get_clk(hw, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user1); - - user2 = clk_hw_get_clk(hw, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user2); - - KUNIT_ASSERT_EQ(test, - clk_set_rate_range(user1, - DUMMY_CLOCK_RATE_1, - ULONG_MAX), - 0); - - rate = clk_get_rate(clk); - KUNIT_ASSERT_GT(test, rate, 0); - KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); - - KUNIT_ASSERT_EQ(test, - clk_set_rate_range(user2, - DUMMY_CLOCK_RATE_2, - ULONG_MAX), - 0); - - rate = clk_get_rate(clk); - KUNIT_ASSERT_GT(test, rate, 0); - KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); - - clk_put(user2); - - rate = clk_get_rate(clk); - KUNIT_ASSERT_GT(test, rate, 0); - KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); - - clk_put(user1); -} - static struct kunit_case clk_range_minimize_test_cases[] = { KUNIT_CASE(clk_range_test_set_range_rate_minimized), KUNIT_CASE(clk_range_test_multiple_set_range_rate_minimized), - KUNIT_CASE(clk_range_test_multiple_set_range_rate_put_minimized), {} }; diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index 68a94e5af8ed..461537679c04 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -69,6 +69,11 @@ config SUN6I_A31_CCU default MACH_SUN6I depends on MACH_SUN6I || COMPILE_TEST +config SUN6I_RTC_CCU + tristate "Support for the Allwinner H616/R329 RTC CCU" + default ARCH_SUNXI + depends on ARCH_SUNXI || COMPILE_TEST + config SUN8I_A23_CCU tristate "Support for the Allwinner A23 CCU" default MACH_SUN8I diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile index ec931cb7aa14..6b3ae2b620db 100644 --- a/drivers/clk/sunxi-ng/Makefile +++ b/drivers/clk/sunxi-ng/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_SUN50I_H616_CCU) += sun50i-h616-ccu.o obj-$(CONFIG_SUN4I_A10_CCU) += sun4i-a10-ccu.o obj-$(CONFIG_SUN5I_CCU) += sun5i-ccu.o obj-$(CONFIG_SUN6I_A31_CCU) += sun6i-a31-ccu.o +obj-$(CONFIG_SUN6I_RTC_CCU) += sun6i-rtc-ccu.o obj-$(CONFIG_SUN8I_A23_CCU) += sun8i-a23-ccu.o obj-$(CONFIG_SUN8I_A33_CCU) += sun8i-a33-ccu.o obj-$(CONFIG_SUN8I_A83T_CCU) += sun8i-a83t-ccu.o @@ -60,6 +61,7 @@ sun50i-h616-ccu-y += ccu-sun50i-h616.o sun4i-a10-ccu-y += ccu-sun4i-a10.o sun5i-ccu-y += ccu-sun5i.o sun6i-a31-ccu-y += ccu-sun6i-a31.o +sun6i-rtc-ccu-y += ccu-sun6i-rtc.o sun8i-a23-ccu-y += ccu-sun8i-a23.o sun8i-a33-ccu-y += ccu-sun8i-a33.o sun8i-a83t-ccu-y += ccu-sun8i-a83t.o diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c new file mode 100644 index 000000000000..8a10bade7e0d --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Copyright (c) 2021 Samuel Holland <samuel@sholland.org> +// + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_device.h> + +#include <linux/clk/sunxi-ng.h> + +#include "ccu_common.h" + +#include "ccu_div.h" +#include "ccu_gate.h" +#include "ccu_mux.h" + +#include "ccu-sun6i-rtc.h" + +#define IOSC_ACCURACY 300000000 /* 30% */ +#define IOSC_RATE 16000000 + +#define LOSC_RATE 32768 +#define LOSC_RATE_SHIFT 15 + +#define LOSC_CTRL_REG 0x0 +#define LOSC_CTRL_KEY 0x16aa0000 + +#define IOSC_32K_CLK_DIV_REG 0x8 +#define IOSC_32K_CLK_DIV GENMASK(4, 0) +#define IOSC_32K_PRE_DIV 32 + +#define IOSC_CLK_CALI_REG 0xc +#define IOSC_CLK_CALI_DIV_ONES 22 +#define IOSC_CLK_CALI_EN BIT(1) +#define IOSC_CLK_CALI_SRC_SEL BIT(0) + +#define LOSC_OUT_GATING_REG 0x60 + +#define DCXO_CTRL_REG 0x160 +#define DCXO_CTRL_CLK16M_RC_EN BIT(0) + +struct sun6i_rtc_match_data { + bool have_ext_osc32k : 1; + bool have_iosc_calibration : 1; + bool rtc_32k_single_parent : 1; + const struct clk_parent_data *osc32k_fanout_parents; + u8 osc32k_fanout_nparents; +}; + +static bool have_iosc_calibration; + +static int ccu_iosc_enable(struct clk_hw *hw) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + + return ccu_gate_helper_enable(cm, DCXO_CTRL_CLK16M_RC_EN); +} + +static void ccu_iosc_disable(struct clk_hw *hw) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + + return ccu_gate_helper_disable(cm, DCXO_CTRL_CLK16M_RC_EN); +} + +static int ccu_iosc_is_enabled(struct clk_hw *hw) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + + return ccu_gate_helper_is_enabled(cm, DCXO_CTRL_CLK16M_RC_EN); +} + +static unsigned long ccu_iosc_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + + if (have_iosc_calibration) { + u32 reg = readl(cm->base + IOSC_CLK_CALI_REG); + + /* + * Recover the IOSC frequency by shifting the ones place of + * (fixed-point divider * 32768) into bit zero. + */ + if (reg & IOSC_CLK_CALI_EN) + return reg >> (IOSC_CLK_CALI_DIV_ONES - LOSC_RATE_SHIFT); + } + + return IOSC_RATE; +} + +static unsigned long ccu_iosc_recalc_accuracy(struct clk_hw *hw, + unsigned long parent_accuracy) +{ + return IOSC_ACCURACY; +} + +static const struct clk_ops ccu_iosc_ops = { + .enable = ccu_iosc_enable, + .disable = ccu_iosc_disable, + .is_enabled = ccu_iosc_is_enabled, + .recalc_rate = ccu_iosc_recalc_rate, + .recalc_accuracy = ccu_iosc_recalc_accuracy, +}; + +static struct ccu_common iosc_clk = { + .reg = DCXO_CTRL_REG, + .hw.init = CLK_HW_INIT_NO_PARENT("iosc", &ccu_iosc_ops, + CLK_GET_RATE_NOCACHE), +}; + +static int ccu_iosc_32k_prepare(struct clk_hw *hw) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + u32 val; + + if (!have_iosc_calibration) + return 0; + + val = readl(cm->base + IOSC_CLK_CALI_REG); + writel(val | IOSC_CLK_CALI_EN | IOSC_CLK_CALI_SRC_SEL, + cm->base + IOSC_CLK_CALI_REG); + + return 0; +} + +static void ccu_iosc_32k_unprepare(struct clk_hw *hw) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + u32 val; + + if (!have_iosc_calibration) + return; + + val = readl(cm->base + IOSC_CLK_CALI_REG); + writel(val & ~(IOSC_CLK_CALI_EN | IOSC_CLK_CALI_SRC_SEL), + cm->base + IOSC_CLK_CALI_REG); +} + +static unsigned long ccu_iosc_32k_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + u32 val; + + if (have_iosc_calibration) { + val = readl(cm->base + IOSC_CLK_CALI_REG); + + /* Assume the calibrated 32k clock is accurate. */ + if (val & IOSC_CLK_CALI_SRC_SEL) + return LOSC_RATE; + } + + val = readl(cm->base + IOSC_32K_CLK_DIV_REG) & IOSC_32K_CLK_DIV; + + return parent_rate / IOSC_32K_PRE_DIV / (val + 1); +} + +static unsigned long ccu_iosc_32k_recalc_accuracy(struct clk_hw *hw, + unsigned long parent_accuracy) +{ + struct ccu_common *cm = hw_to_ccu_common(hw); + u32 val; + + if (have_iosc_calibration) { + val = readl(cm->base + IOSC_CLK_CALI_REG); + + /* Assume the calibrated 32k clock is accurate. */ + if (val & IOSC_CLK_CALI_SRC_SEL) + return 0; + } + + return parent_accuracy; +} + +static const struct clk_ops ccu_iosc_32k_ops = { + .prepare = ccu_iosc_32k_prepare, + .unprepare = ccu_iosc_32k_unprepare, + .recalc_rate = ccu_iosc_32k_recalc_rate, + .recalc_accuracy = ccu_iosc_32k_recalc_accuracy, +}; + +static struct ccu_common iosc_32k_clk = { + .hw.init = CLK_HW_INIT_HW("iosc-32k", &iosc_clk.hw, + &ccu_iosc_32k_ops, + CLK_GET_RATE_NOCACHE), +}; + +static const struct clk_hw *ext_osc32k[] = { NULL }; /* updated during probe */ + +static SUNXI_CCU_GATE_HWS(ext_osc32k_gate_clk, "ext-osc32k-gate", + ext_osc32k, 0x0, BIT(4), 0); + +static const struct clk_hw *osc32k_parents[] = { + &iosc_32k_clk.hw, + &ext_osc32k_gate_clk.common.hw +}; + +static struct clk_init_data osc32k_init_data = { + .name = "osc32k", + .ops = &ccu_mux_ops, + .parent_hws = osc32k_parents, + .num_parents = ARRAY_SIZE(osc32k_parents), /* updated during probe */ +}; + +static struct ccu_mux osc32k_clk = { + .mux = _SUNXI_CCU_MUX(0, 1), + .common = { + .reg = LOSC_CTRL_REG, + .features = CCU_FEATURE_KEY_FIELD, + .hw.init = &osc32k_init_data, + }, +}; + +/* This falls back to the global name for fwnodes without a named reference. */ +static const struct clk_parent_data osc24M[] = { + { .fw_name = "hosc", .name = "osc24M" } +}; + +static struct ccu_gate osc24M_32k_clk = { + .enable = BIT(16), + .common = { + .reg = LOSC_OUT_GATING_REG, + .prediv = 750, + .features = CCU_FEATURE_ALL_PREDIV, + .hw.init = CLK_HW_INIT_PARENTS_DATA("osc24M-32k", osc24M, + &ccu_gate_ops, 0), + }, +}; + +static const struct clk_hw *rtc_32k_parents[] = { + &osc32k_clk.common.hw, + &osc24M_32k_clk.common.hw +}; + +static struct clk_init_data rtc_32k_init_data = { + .name = "rtc-32k", + .ops = &ccu_mux_ops, + .parent_hws = rtc_32k_parents, + .num_parents = ARRAY_SIZE(rtc_32k_parents), /* updated during probe */ +}; + +static struct ccu_mux rtc_32k_clk = { + .mux = _SUNXI_CCU_MUX(1, 1), + .common = { + .reg = LOSC_CTRL_REG, + .features = CCU_FEATURE_KEY_FIELD, + .hw.init = &rtc_32k_init_data, + }, +}; + +static struct clk_init_data osc32k_fanout_init_data = { + .name = "osc32k-fanout", + .ops = &ccu_mux_ops, + /* parents are set during probe */ +}; + +static struct ccu_mux osc32k_fanout_clk = { + .enable = BIT(0), + .mux = _SUNXI_CCU_MUX(1, 2), + .common = { + .reg = LOSC_OUT_GATING_REG, + .hw.init = &osc32k_fanout_init_data, + }, +}; + +static struct ccu_common *sun6i_rtc_ccu_clks[] = { + &iosc_clk, + &iosc_32k_clk, + &ext_osc32k_gate_clk.common, + &osc32k_clk.common, + &osc24M_32k_clk.common, + &rtc_32k_clk.common, + &osc32k_fanout_clk.common, +}; + +static struct clk_hw_onecell_data sun6i_rtc_ccu_hw_clks = { + .num = CLK_NUMBER, + .hws = { + [CLK_OSC32K] = &osc32k_clk.common.hw, + [CLK_OSC32K_FANOUT] = &osc32k_fanout_clk.common.hw, + [CLK_IOSC] = &iosc_clk.hw, + [CLK_IOSC_32K] = &iosc_32k_clk.hw, + [CLK_EXT_OSC32K_GATE] = &ext_osc32k_gate_clk.common.hw, + [CLK_OSC24M_32K] = &osc24M_32k_clk.common.hw, + [CLK_RTC_32K] = &rtc_32k_clk.common.hw, + }, +}; + +static const struct sunxi_ccu_desc sun6i_rtc_ccu_desc = { + .ccu_clks = sun6i_rtc_ccu_clks, + .num_ccu_clks = ARRAY_SIZE(sun6i_rtc_ccu_clks), + + .hw_clks = &sun6i_rtc_ccu_hw_clks, +}; + +static const struct clk_parent_data sun50i_h6_osc32k_fanout_parents[] = { + { .hw = &osc32k_clk.common.hw }, +}; + +static const struct clk_parent_data sun50i_h616_osc32k_fanout_parents[] = { + { .hw = &osc32k_clk.common.hw }, + { .fw_name = "pll-32k" }, + { .hw = &osc24M_32k_clk.common.hw } +}; + +static const struct clk_parent_data sun50i_r329_osc32k_fanout_parents[] = { + { .hw = &osc32k_clk.common.hw }, + { .hw = &ext_osc32k_gate_clk.common.hw }, + { .hw = &osc24M_32k_clk.common.hw } +}; + +static const struct sun6i_rtc_match_data sun50i_h6_rtc_ccu_data = { + .have_ext_osc32k = true, + .have_iosc_calibration = true, + .osc32k_fanout_parents = sun50i_h6_osc32k_fanout_parents, + .osc32k_fanout_nparents = ARRAY_SIZE(sun50i_h6_osc32k_fanout_parents), +}; + +static const struct sun6i_rtc_match_data sun50i_h616_rtc_ccu_data = { + .have_iosc_calibration = true, + .rtc_32k_single_parent = true, + .osc32k_fanout_parents = sun50i_h616_osc32k_fanout_parents, + .osc32k_fanout_nparents = ARRAY_SIZE(sun50i_h616_osc32k_fanout_parents), +}; + +static const struct sun6i_rtc_match_data sun50i_r329_rtc_ccu_data = { + .have_ext_osc32k = true, + .osc32k_fanout_parents = sun50i_r329_osc32k_fanout_parents, + .osc32k_fanout_nparents = ARRAY_SIZE(sun50i_r329_osc32k_fanout_parents), +}; + +static const struct of_device_id sun6i_rtc_ccu_match[] = { + { + .compatible = "allwinner,sun50i-h6-rtc", + .data = &sun50i_h6_rtc_ccu_data, + }, + { + .compatible = "allwinner,sun50i-h616-rtc", + .data = &sun50i_h616_rtc_ccu_data, + }, + { + .compatible = "allwinner,sun50i-r329-rtc", + .data = &sun50i_r329_rtc_ccu_data, + }, +}; + +int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg) +{ + const struct sun6i_rtc_match_data *data; + struct clk *ext_osc32k_clk = NULL; + const struct of_device_id *match; + + /* This driver is only used for newer variants of the hardware. */ + match = of_match_device(sun6i_rtc_ccu_match, dev); + if (!match) + return 0; + + data = match->data; + have_iosc_calibration = data->have_iosc_calibration; + + if (data->have_ext_osc32k) { + const char *fw_name; + + /* ext-osc32k was the only input clock in the old binding. */ + fw_name = of_property_read_bool(dev->of_node, "clock-names") + ? "ext-osc32k" : NULL; + ext_osc32k_clk = devm_clk_get_optional(dev, fw_name); + if (IS_ERR(ext_osc32k_clk)) + return PTR_ERR(ext_osc32k_clk); + } + + if (ext_osc32k_clk) { + /* Link ext-osc32k-gate to its parent. */ + *ext_osc32k = __clk_get_hw(ext_osc32k_clk); + } else { + /* ext-osc32k-gate is an orphan, so do not register it. */ + sun6i_rtc_ccu_hw_clks.hws[CLK_EXT_OSC32K_GATE] = NULL; + osc32k_init_data.num_parents = 1; + } + + if (data->rtc_32k_single_parent) + rtc_32k_init_data.num_parents = 1; + + osc32k_fanout_init_data.parent_data = data->osc32k_fanout_parents; + osc32k_fanout_init_data.num_parents = data->osc32k_fanout_nparents; + + return devm_sunxi_ccu_probe(dev, reg, &sun6i_rtc_ccu_desc); +} + +MODULE_IMPORT_NS(SUNXI_CCU); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h new file mode 100644 index 000000000000..9ae821fc2599 --- /dev/null +++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _CCU_SUN6I_RTC_H +#define _CCU_SUN6I_RTC_H + +#include <dt-bindings/clock/sun6i-rtc.h> + +#define CLK_IOSC_32K 3 +#define CLK_EXT_OSC32K_GATE 4 +#define CLK_OSC24M_32K 5 +#define CLK_RTC_32K 6 + +#define CLK_NUMBER (CLK_RTC_32K + 1) + +#endif /* _CCU_SUN6I_RTC_H */ diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h index 98a1834b58bb..fbf16c6b896d 100644 --- a/drivers/clk/sunxi-ng/ccu_common.h +++ b/drivers/clk/sunxi-ng/ccu_common.h @@ -17,6 +17,7 @@ #define CCU_FEATURE_LOCK_REG BIT(5) #define CCU_FEATURE_MMC_TIMING_SWITCH BIT(6) #define CCU_FEATURE_SIGMA_DELTA_MOD BIT(7) +#define CCU_FEATURE_KEY_FIELD BIT(8) /* MMC timing mode switch bit */ #define CCU_MMC_NEW_TIMING_MODE BIT(30) diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c index 2306a1cd83e4..1d557e323169 100644 --- a/drivers/clk/sunxi-ng/ccu_mux.c +++ b/drivers/clk/sunxi-ng/ccu_mux.c @@ -12,6 +12,8 @@ #include "ccu_gate.h" #include "ccu_mux.h" +#define CCU_MUX_KEY_VALUE 0x16aa0000 + static u16 ccu_mux_get_prediv(struct ccu_common *common, struct ccu_mux_internal *cm, int parent_index) @@ -191,6 +193,11 @@ int ccu_mux_helper_set_parent(struct ccu_common *common, spin_lock_irqsave(common->lock, flags); reg = readl(common->base + common->reg); + + /* The key field always reads as zero. */ + if (common->features & CCU_FEATURE_KEY_FIELD) + reg |= CCU_MUX_KEY_VALUE; + reg &= ~GENMASK(cm->width + cm->shift - 1, cm->shift); writel(reg | (index << cm->shift), common->base + common->reg); diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index c0aeedd66f02..ff71dd662880 100644 --- a/drivers/cpuidle/Kconfig +++ b/drivers/cpuidle/Kconfig @@ -47,6 +47,10 @@ config CPU_IDLE_GOV_HALTPOLL config DT_IDLE_STATES bool +config DT_IDLE_GENPD + depends on PM_GENERIC_DOMAINS_OF + bool + menu "ARM CPU Idle Drivers" depends on ARM || ARM64 source "drivers/cpuidle/Kconfig.arm" @@ -62,6 +66,11 @@ depends on PPC source "drivers/cpuidle/Kconfig.powerpc" endmenu +menu "RISC-V CPU Idle Drivers" +depends on RISCV +source "drivers/cpuidle/Kconfig.riscv" +endmenu + config HALTPOLL_CPUIDLE tristate "Halt poll cpuidle driver" depends on X86 && KVM_GUEST diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm index 15d6c46c0a47..be7f512109f7 100644 --- a/drivers/cpuidle/Kconfig.arm +++ b/drivers/cpuidle/Kconfig.arm @@ -27,6 +27,7 @@ config ARM_PSCI_CPUIDLE_DOMAIN bool "PSCI CPU idle Domain" depends on ARM_PSCI_CPUIDLE depends on PM_GENERIC_DOMAINS_OF + select DT_IDLE_GENPD default y help Select this to enable the PSCI based CPUidle driver to use PM domains, diff --git a/drivers/cpuidle/Kconfig.riscv b/drivers/cpuidle/Kconfig.riscv new file mode 100644 index 000000000000..78518c26af74 --- /dev/null +++ b/drivers/cpuidle/Kconfig.riscv @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# RISC-V CPU Idle drivers +# + +config RISCV_SBI_CPUIDLE + bool "RISC-V SBI CPU idle Driver" + depends on RISCV_SBI + select DT_IDLE_STATES + select CPU_IDLE_MULTIPLE_DRIVERS + select DT_IDLE_GENPD if PM_GENERIC_DOMAINS_OF + help + Select this option to enable RISC-V SBI firmware based CPU idle + driver for RISC-V systems. This drivers also supports hierarchical + DT based layout of the idle state. diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile index 26bbc5e74123..d103342b7cfc 100644 --- a/drivers/cpuidle/Makefile +++ b/drivers/cpuidle/Makefile @@ -6,6 +6,7 @@ obj-y += cpuidle.o driver.o governor.o sysfs.o governors/ obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o obj-$(CONFIG_DT_IDLE_STATES) += dt_idle_states.o +obj-$(CONFIG_DT_IDLE_GENPD) += dt_idle_genpd.o obj-$(CONFIG_ARCH_HAS_CPU_RELAX) += poll_state.o obj-$(CONFIG_HALTPOLL_CPUIDLE) += cpuidle-haltpoll.o @@ -34,3 +35,7 @@ obj-$(CONFIG_MIPS_CPS_CPUIDLE) += cpuidle-cps.o # POWERPC drivers obj-$(CONFIG_PSERIES_CPUIDLE) += cpuidle-pseries.o obj-$(CONFIG_POWERNV_CPUIDLE) += cpuidle-powernv.o + +############################################################################### +# RISC-V drivers +obj-$(CONFIG_RISCV_SBI_CPUIDLE) += cpuidle-riscv-sbi.o diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index ff2c3f8e4668..755bbdfc5b82 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -47,73 +47,14 @@ static int psci_pd_power_off(struct generic_pm_domain *pd) return 0; } -static int psci_pd_parse_state_nodes(struct genpd_power_state *states, - int state_count) -{ - int i, ret; - u32 psci_state, *psci_state_buf; - - for (i = 0; i < state_count; i++) { - ret = psci_dt_parse_state_node(to_of_node(states[i].fwnode), - &psci_state); - if (ret) - goto free_state; - - psci_state_buf = kmalloc(sizeof(u32), GFP_KERNEL); - if (!psci_state_buf) { - ret = -ENOMEM; - goto free_state; - } - *psci_state_buf = psci_state; - states[i].data = psci_state_buf; - } - - return 0; - -free_state: - i--; - for (; i >= 0; i--) - kfree(states[i].data); - return ret; -} - -static int psci_pd_parse_states(struct device_node *np, - struct genpd_power_state **states, int *state_count) -{ - int ret; - - /* Parse the domain idle states. */ - ret = of_genpd_parse_idle_states(np, states, state_count); - if (ret) - return ret; - - /* Fill out the PSCI specifics for each found state. */ - ret = psci_pd_parse_state_nodes(*states, *state_count); - if (ret) - kfree(*states); - - return ret; -} - -static void psci_pd_free_states(struct genpd_power_state *states, - unsigned int state_count) -{ - int i; - - for (i = 0; i < state_count; i++) - kfree(states[i].data); - kfree(states); -} - static int psci_pd_init(struct device_node *np, bool use_osi) { struct generic_pm_domain *pd; struct psci_pd_provider *pd_provider; struct dev_power_governor *pd_gov; - struct genpd_power_state *states = NULL; int ret = -ENOMEM, state_count = 0; - pd = kzalloc(sizeof(*pd), GFP_KERNEL); + pd = dt_idle_pd_alloc(np, psci_dt_parse_state_node); if (!pd) goto out; @@ -121,22 +62,6 @@ static int psci_pd_init(struct device_node *np, bool use_osi) if (!pd_provider) goto free_pd; - pd->name = kasprintf(GFP_KERNEL, "%pOF", np); - if (!pd->name) - goto free_pd_prov; - - /* - * Parse the domain idle states and let genpd manage the state selection - * for those being compatible with "domain-idle-state". - */ - ret = psci_pd_parse_states(np, &states, &state_count); - if (ret) - goto free_name; - - pd->free_states = psci_pd_free_states; - pd->name = kbasename(pd->name); - pd->states = states; - pd->state_count = state_count; pd->flags |= GENPD_FLAG_IRQ_SAFE | GENPD_FLAG_CPU_DOMAIN; /* Allow power off when OSI has been successfully enabled. */ @@ -149,10 +74,8 @@ static int psci_pd_init(struct device_node *np, bool use_osi) pd_gov = state_count > 0 ? &pm_domain_cpu_gov : NULL; ret = pm_genpd_init(pd, pd_gov, false); - if (ret) { - psci_pd_free_states(states, state_count); - goto free_name; - } + if (ret) + goto free_pd_prov; ret = of_genpd_add_provider_simple(np, pd); if (ret) @@ -166,12 +89,10 @@ static int psci_pd_init(struct device_node *np, bool use_osi) remove_pd: pm_genpd_remove(pd); -free_name: - kfree(pd->name); free_pd_prov: kfree(pd_provider); free_pd: - kfree(pd); + dt_idle_pd_free(pd); out: pr_err("failed to init PM domain ret=%d %pOF\n", ret, np); return ret; @@ -195,30 +116,6 @@ static void psci_pd_remove(void) } } -static int psci_pd_init_topology(struct device_node *np) -{ - struct device_node *node; - struct of_phandle_args child, parent; - int ret; - - for_each_child_of_node(np, node) { - if (of_parse_phandle_with_args(node, "power-domains", - "#power-domain-cells", 0, &parent)) - continue; - - child.np = node; - child.args_count = 0; - ret = of_genpd_add_subdomain(&parent, &child); - of_node_put(parent.np); - if (ret) { - of_node_put(node); - return ret; - } - } - - return 0; -} - static bool psci_pd_try_set_osi_mode(void) { int ret; @@ -282,7 +179,7 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev) goto no_pd; /* Link genpd masters/subdomains to model the CPU topology. */ - ret = psci_pd_init_topology(np); + ret = dt_idle_pd_init_topology(np); if (ret) goto remove_pd; @@ -314,28 +211,3 @@ static int __init psci_idle_init_domains(void) return platform_driver_register(&psci_cpuidle_domain_driver); } subsys_initcall(psci_idle_init_domains); - -struct device *psci_dt_attach_cpu(int cpu) -{ - struct device *dev; - - dev = dev_pm_domain_attach_by_name(get_cpu_device(cpu), "psci"); - if (IS_ERR_OR_NULL(dev)) - return dev; - - pm_runtime_irq_safe(dev); - if (cpu_online(cpu)) - pm_runtime_get_sync(dev); - - dev_pm_syscore_device(dev, true); - - return dev; -} - -void psci_dt_detach_cpu(struct device *dev) -{ - if (IS_ERR_OR_NULL(dev)) - return; - - dev_pm_domain_detach(dev, false); -} diff --git a/drivers/cpuidle/cpuidle-psci.h b/drivers/cpuidle/cpuidle-psci.h index d8e925e84c27..4e132640ed64 100644 --- a/drivers/cpuidle/cpuidle-psci.h +++ b/drivers/cpuidle/cpuidle-psci.h @@ -10,8 +10,19 @@ void psci_set_domain_state(u32 state); int psci_dt_parse_state_node(struct device_node *np, u32 *state); #ifdef CONFIG_ARM_PSCI_CPUIDLE_DOMAIN -struct device *psci_dt_attach_cpu(int cpu); -void psci_dt_detach_cpu(struct device *dev); + +#include "dt_idle_genpd.h" + +static inline struct device *psci_dt_attach_cpu(int cpu) +{ + return dt_idle_attach_cpu(cpu, "psci"); +} + +static inline void psci_dt_detach_cpu(struct device *dev) +{ + dt_idle_detach_cpu(dev); +} + #else static inline struct device *psci_dt_attach_cpu(int cpu) { return NULL; } static inline void psci_dt_detach_cpu(struct device *dev) { } diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c new file mode 100644 index 000000000000..b459eda2cd37 --- /dev/null +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -0,0 +1,627 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * RISC-V SBI CPU idle driver. + * + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "cpuidle-riscv-sbi: " fmt + +#include <linux/cpuidle.h> +#include <linux/cpumask.h> +#include <linux/cpu_pm.h> +#include <linux/cpu_cooling.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/slab.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <asm/cpuidle.h> +#include <asm/sbi.h> +#include <asm/suspend.h> + +#include "dt_idle_states.h" +#include "dt_idle_genpd.h" + +struct sbi_cpuidle_data { + u32 *states; + struct device *dev; +}; + +struct sbi_domain_state { + bool available; + u32 state; +}; + +static DEFINE_PER_CPU_READ_MOSTLY(struct sbi_cpuidle_data, sbi_cpuidle_data); +static DEFINE_PER_CPU(struct sbi_domain_state, domain_state); +static bool sbi_cpuidle_use_osi; +static bool sbi_cpuidle_use_cpuhp; +static bool sbi_cpuidle_pd_allow_domain_state; + +static inline void sbi_set_domain_state(u32 state) +{ + struct sbi_domain_state *data = this_cpu_ptr(&domain_state); + + data->available = true; + data->state = state; +} + +static inline u32 sbi_get_domain_state(void) +{ + struct sbi_domain_state *data = this_cpu_ptr(&domain_state); + + return data->state; +} + +static inline void sbi_clear_domain_state(void) +{ + struct sbi_domain_state *data = this_cpu_ptr(&domain_state); + + data->available = false; +} + +static inline bool sbi_is_domain_state_available(void) +{ + struct sbi_domain_state *data = this_cpu_ptr(&domain_state); + + return data->available; +} + +static int sbi_suspend_finisher(unsigned long suspend_type, + unsigned long resume_addr, + unsigned long opaque) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_SUSPEND, + suspend_type, resume_addr, opaque, 0, 0, 0); + + return (ret.error) ? sbi_err_map_linux_errno(ret.error) : 0; +} + +static int sbi_suspend(u32 state) +{ + if (state & SBI_HSM_SUSP_NON_RET_BIT) + return cpu_suspend(state, sbi_suspend_finisher); + else + return sbi_suspend_finisher(state, 0, 0); +} + +static int sbi_cpuidle_enter_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx) +{ + u32 *states = __this_cpu_read(sbi_cpuidle_data.states); + + return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, states[idx]); +} + +static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx, + bool s2idle) +{ + struct sbi_cpuidle_data *data = this_cpu_ptr(&sbi_cpuidle_data); + u32 *states = data->states; + struct device *pd_dev = data->dev; + u32 state; + int ret; + + ret = cpu_pm_enter(); + if (ret) + return -1; + + /* Do runtime PM to manage a hierarchical CPU toplogy. */ + rcu_irq_enter_irqson(); + if (s2idle) + dev_pm_genpd_suspend(pd_dev); + else + pm_runtime_put_sync_suspend(pd_dev); + rcu_irq_exit_irqson(); + + if (sbi_is_domain_state_available()) + state = sbi_get_domain_state(); + else + state = states[idx]; + + ret = sbi_suspend(state) ? -1 : idx; + + rcu_irq_enter_irqson(); + if (s2idle) + dev_pm_genpd_resume(pd_dev); + else + pm_runtime_get_sync(pd_dev); + rcu_irq_exit_irqson(); + + cpu_pm_exit(); + + /* Clear the domain state to start fresh when back from idle. */ + sbi_clear_domain_state(); + return ret; +} + +static int sbi_enter_domain_idle_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx) +{ + return __sbi_enter_domain_idle_state(dev, drv, idx, false); +} + +static int sbi_enter_s2idle_domain_idle_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int idx) +{ + return __sbi_enter_domain_idle_state(dev, drv, idx, true); +} + +static int sbi_cpuidle_cpuhp_up(unsigned int cpu) +{ + struct device *pd_dev = __this_cpu_read(sbi_cpuidle_data.dev); + + if (pd_dev) + pm_runtime_get_sync(pd_dev); + + return 0; +} + +static int sbi_cpuidle_cpuhp_down(unsigned int cpu) +{ + struct device *pd_dev = __this_cpu_read(sbi_cpuidle_data.dev); + + if (pd_dev) { + pm_runtime_put_sync(pd_dev); + /* Clear domain state to start fresh at next online. */ + sbi_clear_domain_state(); + } + + return 0; +} + +static void sbi_idle_init_cpuhp(void) +{ + int err; + + if (!sbi_cpuidle_use_cpuhp) + return; + + err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING, + "cpuidle/sbi:online", + sbi_cpuidle_cpuhp_up, + sbi_cpuidle_cpuhp_down); + if (err) + pr_warn("Failed %d while setup cpuhp state\n", err); +} + +static const struct of_device_id sbi_cpuidle_state_match[] = { + { .compatible = "riscv,idle-state", + .data = sbi_cpuidle_enter_state }, + { }, +}; + +static bool sbi_suspend_state_is_valid(u32 state) +{ + if (state > SBI_HSM_SUSPEND_RET_DEFAULT && + state < SBI_HSM_SUSPEND_RET_PLATFORM) + return false; + if (state > SBI_HSM_SUSPEND_NON_RET_DEFAULT && + state < SBI_HSM_SUSPEND_NON_RET_PLATFORM) + return false; + return true; +} + +static int sbi_dt_parse_state_node(struct device_node *np, u32 *state) +{ + int err = of_property_read_u32(np, "riscv,sbi-suspend-param", state); + + if (err) { + pr_warn("%pOF missing riscv,sbi-suspend-param property\n", np); + return err; + } + + if (!sbi_suspend_state_is_valid(*state)) { + pr_warn("Invalid SBI suspend state %#x\n", *state); + return -EINVAL; + } + + return 0; +} + +static int sbi_dt_cpu_init_topology(struct cpuidle_driver *drv, + struct sbi_cpuidle_data *data, + unsigned int state_count, int cpu) +{ + /* Currently limit the hierarchical topology to be used in OSI mode. */ + if (!sbi_cpuidle_use_osi) + return 0; + + data->dev = dt_idle_attach_cpu(cpu, "sbi"); + if (IS_ERR_OR_NULL(data->dev)) + return PTR_ERR_OR_ZERO(data->dev); + + /* + * Using the deepest state for the CPU to trigger a potential selection + * of a shared state for the domain, assumes the domain states are all + * deeper states. + */ + drv->states[state_count - 1].enter = sbi_enter_domain_idle_state; + drv->states[state_count - 1].enter_s2idle = + sbi_enter_s2idle_domain_idle_state; + sbi_cpuidle_use_cpuhp = true; + + return 0; +} + +static int sbi_cpuidle_dt_init_states(struct device *dev, + struct cpuidle_driver *drv, + unsigned int cpu, + unsigned int state_count) +{ + struct sbi_cpuidle_data *data = per_cpu_ptr(&sbi_cpuidle_data, cpu); + struct device_node *state_node; + struct device_node *cpu_node; + u32 *states; + int i, ret; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) + return -ENODEV; + + states = devm_kcalloc(dev, state_count, sizeof(*states), GFP_KERNEL); + if (!states) { + ret = -ENOMEM; + goto fail; + } + + /* Parse SBI specific details from state DT nodes */ + for (i = 1; i < state_count; i++) { + state_node = of_get_cpu_state_node(cpu_node, i - 1); + if (!state_node) + break; + + ret = sbi_dt_parse_state_node(state_node, &states[i]); + of_node_put(state_node); + + if (ret) + return ret; + + pr_debug("sbi-state %#x index %d\n", states[i], i); + } + if (i != state_count) { + ret = -ENODEV; + goto fail; + } + + /* Initialize optional data, used for the hierarchical topology. */ + ret = sbi_dt_cpu_init_topology(drv, data, state_count, cpu); + if (ret < 0) + return ret; + + /* Store states in the per-cpu struct. */ + data->states = states; + +fail: + of_node_put(cpu_node); + + return ret; +} + +static void sbi_cpuidle_deinit_cpu(int cpu) +{ + struct sbi_cpuidle_data *data = per_cpu_ptr(&sbi_cpuidle_data, cpu); + + dt_idle_detach_cpu(data->dev); + sbi_cpuidle_use_cpuhp = false; +} + +static int sbi_cpuidle_init_cpu(struct device *dev, int cpu) +{ + struct cpuidle_driver *drv; + unsigned int state_count = 0; + int ret = 0; + + drv = devm_kzalloc(dev, sizeof(*drv), GFP_KERNEL); + if (!drv) + return -ENOMEM; + + drv->name = "sbi_cpuidle"; + drv->owner = THIS_MODULE; + drv->cpumask = (struct cpumask *)cpumask_of(cpu); + + /* RISC-V architectural WFI to be represented as state index 0. */ + drv->states[0].enter = sbi_cpuidle_enter_state; + drv->states[0].exit_latency = 1; + drv->states[0].target_residency = 1; + drv->states[0].power_usage = UINT_MAX; + strcpy(drv->states[0].name, "WFI"); + strcpy(drv->states[0].desc, "RISC-V WFI"); + + /* + * If no DT idle states are detected (ret == 0) let the driver + * initialization fail accordingly since there is no reason to + * initialize the idle driver if only wfi is supported, the + * default archictectural back-end already executes wfi + * on idle entry. + */ + ret = dt_init_idle_driver(drv, sbi_cpuidle_state_match, 1); + if (ret <= 0) { + pr_debug("HART%ld: failed to parse DT idle states\n", + cpuid_to_hartid_map(cpu)); + return ret ? : -ENODEV; + } + state_count = ret + 1; /* Include WFI state as well */ + + /* Initialize idle states from DT. */ + ret = sbi_cpuidle_dt_init_states(dev, drv, cpu, state_count); + if (ret) { + pr_err("HART%ld: failed to init idle states\n", + cpuid_to_hartid_map(cpu)); + return ret; + } + + ret = cpuidle_register(drv, NULL); + if (ret) + goto deinit; + + cpuidle_cooling_register(drv); + + return 0; +deinit: + sbi_cpuidle_deinit_cpu(cpu); + return ret; +} + +static void sbi_cpuidle_domain_sync_state(struct device *dev) +{ + /* + * All devices have now been attached/probed to the PM domain + * topology, hence it's fine to allow domain states to be picked. + */ + sbi_cpuidle_pd_allow_domain_state = true; +} + +#ifdef CONFIG_DT_IDLE_GENPD + +static int sbi_cpuidle_pd_power_off(struct generic_pm_domain *pd) +{ + struct genpd_power_state *state = &pd->states[pd->state_idx]; + u32 *pd_state; + + if (!state->data) + return 0; + + if (!sbi_cpuidle_pd_allow_domain_state) + return -EBUSY; + + /* OSI mode is enabled, set the corresponding domain state. */ + pd_state = state->data; + sbi_set_domain_state(*pd_state); + + return 0; +} + +struct sbi_pd_provider { + struct list_head link; + struct device_node *node; +}; + +static LIST_HEAD(sbi_pd_providers); + +static int sbi_pd_init(struct device_node *np) +{ + struct generic_pm_domain *pd; + struct sbi_pd_provider *pd_provider; + struct dev_power_governor *pd_gov; + int ret = -ENOMEM, state_count = 0; + + pd = dt_idle_pd_alloc(np, sbi_dt_parse_state_node); + if (!pd) + goto out; + + pd_provider = kzalloc(sizeof(*pd_provider), GFP_KERNEL); + if (!pd_provider) + goto free_pd; + + pd->flags |= GENPD_FLAG_IRQ_SAFE | GENPD_FLAG_CPU_DOMAIN; + + /* Allow power off when OSI is available. */ + if (sbi_cpuidle_use_osi) + pd->power_off = sbi_cpuidle_pd_power_off; + else + pd->flags |= GENPD_FLAG_ALWAYS_ON; + + /* Use governor for CPU PM domains if it has some states to manage. */ + pd_gov = state_count > 0 ? &pm_domain_cpu_gov : NULL; + + ret = pm_genpd_init(pd, pd_gov, false); + if (ret) + goto free_pd_prov; + + ret = of_genpd_add_provider_simple(np, pd); + if (ret) + goto remove_pd; + + pd_provider->node = of_node_get(np); + list_add(&pd_provider->link, &sbi_pd_providers); + + pr_debug("init PM domain %s\n", pd->name); + return 0; + +remove_pd: + pm_genpd_remove(pd); +free_pd_prov: + kfree(pd_provider); +free_pd: + dt_idle_pd_free(pd); +out: + pr_err("failed to init PM domain ret=%d %pOF\n", ret, np); + return ret; +} + +static void sbi_pd_remove(void) +{ + struct sbi_pd_provider *pd_provider, *it; + struct generic_pm_domain *genpd; + + list_for_each_entry_safe(pd_provider, it, &sbi_pd_providers, link) { + of_genpd_del_provider(pd_provider->node); + + genpd = of_genpd_remove_last(pd_provider->node); + if (!IS_ERR(genpd)) + kfree(genpd); + + of_node_put(pd_provider->node); + list_del(&pd_provider->link); + kfree(pd_provider); + } +} + +static int sbi_genpd_probe(struct device_node *np) +{ + struct device_node *node; + int ret = 0, pd_count = 0; + + if (!np) + return -ENODEV; + + /* + * Parse child nodes for the "#power-domain-cells" property and + * initialize a genpd/genpd-of-provider pair when it's found. + */ + for_each_child_of_node(np, node) { + if (!of_find_property(node, "#power-domain-cells", NULL)) + continue; + + ret = sbi_pd_init(node); + if (ret) + goto put_node; + + pd_count++; + } + + /* Bail out if not using the hierarchical CPU topology. */ + if (!pd_count) + goto no_pd; + + /* Link genpd masters/subdomains to model the CPU topology. */ + ret = dt_idle_pd_init_topology(np); + if (ret) + goto remove_pd; + + return 0; + +put_node: + of_node_put(node); +remove_pd: + sbi_pd_remove(); + pr_err("failed to create CPU PM domains ret=%d\n", ret); +no_pd: + return ret; +} + +#else + +static inline int sbi_genpd_probe(struct device_node *np) +{ + return 0; +} + +#endif + +static int sbi_cpuidle_probe(struct platform_device *pdev) +{ + int cpu, ret; + struct cpuidle_driver *drv; + struct cpuidle_device *dev; + struct device_node *np, *pds_node; + + /* Detect OSI support based on CPU DT nodes */ + sbi_cpuidle_use_osi = true; + for_each_possible_cpu(cpu) { + np = of_cpu_device_node_get(cpu); + if (np && + of_find_property(np, "power-domains", NULL) && + of_find_property(np, "power-domain-names", NULL)) { + continue; + } else { + sbi_cpuidle_use_osi = false; + break; + } + } + + /* Populate generic power domains from DT nodes */ + pds_node = of_find_node_by_path("/cpus/power-domains"); + if (pds_node) { + ret = sbi_genpd_probe(pds_node); + of_node_put(pds_node); + if (ret) + return ret; + } + + /* Initialize CPU idle driver for each CPU */ + for_each_possible_cpu(cpu) { + ret = sbi_cpuidle_init_cpu(&pdev->dev, cpu); + if (ret) { + pr_debug("HART%ld: idle driver init failed\n", + cpuid_to_hartid_map(cpu)); + goto out_fail; + } + } + + /* Setup CPU hotplut notifiers */ + sbi_idle_init_cpuhp(); + + pr_info("idle driver registered for all CPUs\n"); + + return 0; + +out_fail: + while (--cpu >= 0) { + dev = per_cpu(cpuidle_devices, cpu); + drv = cpuidle_get_cpu_driver(dev); + cpuidle_unregister(drv); + sbi_cpuidle_deinit_cpu(cpu); + } + + return ret; +} + +static struct platform_driver sbi_cpuidle_driver = { + .probe = sbi_cpuidle_probe, + .driver = { + .name = "sbi-cpuidle", + .sync_state = sbi_cpuidle_domain_sync_state, + }, +}; + +static int __init sbi_cpuidle_init(void) +{ + int ret; + struct platform_device *pdev; + + /* + * The SBI HSM suspend function is only available when: + * 1) SBI version is 0.3 or higher + * 2) SBI HSM extension is available + */ + if ((sbi_spec_version < sbi_mk_version(0, 3)) || + sbi_probe_extension(SBI_EXT_HSM) <= 0) { + pr_info("HSM suspend not available\n"); + return 0; + } + + ret = platform_driver_register(&sbi_cpuidle_driver); + if (ret) + return ret; + + pdev = platform_device_register_simple("sbi-cpuidle", + -1, NULL, 0); + if (IS_ERR(pdev)) { + platform_driver_unregister(&sbi_cpuidle_driver); + return PTR_ERR(pdev); + } + + return 0; +} +device_initcall(sbi_cpuidle_init); diff --git a/drivers/cpuidle/dt_idle_genpd.c b/drivers/cpuidle/dt_idle_genpd.c new file mode 100644 index 000000000000..b37165514d4e --- /dev/null +++ b/drivers/cpuidle/dt_idle_genpd.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PM domains for CPUs via genpd. + * + * Copyright (C) 2019 Linaro Ltd. + * Author: Ulf Hansson <ulf.hansson@linaro.org> + * + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "dt-idle-genpd: " fmt + +#include <linux/cpu.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> +#include <linux/string.h> + +#include "dt_idle_genpd.h" + +static int pd_parse_state_nodes( + int (*parse_state)(struct device_node *, u32 *), + struct genpd_power_state *states, int state_count) +{ + int i, ret; + u32 state, *state_buf; + + for (i = 0; i < state_count; i++) { + ret = parse_state(to_of_node(states[i].fwnode), &state); + if (ret) + goto free_state; + + state_buf = kmalloc(sizeof(u32), GFP_KERNEL); + if (!state_buf) { + ret = -ENOMEM; + goto free_state; + } + *state_buf = state; + states[i].data = state_buf; + } + + return 0; + +free_state: + i--; + for (; i >= 0; i--) + kfree(states[i].data); + return ret; +} + +static int pd_parse_states(struct device_node *np, + int (*parse_state)(struct device_node *, u32 *), + struct genpd_power_state **states, + int *state_count) +{ + int ret; + + /* Parse the domain idle states. */ + ret = of_genpd_parse_idle_states(np, states, state_count); + if (ret) + return ret; + + /* Fill out the dt specifics for each found state. */ + ret = pd_parse_state_nodes(parse_state, *states, *state_count); + if (ret) + kfree(*states); + + return ret; +} + +static void pd_free_states(struct genpd_power_state *states, + unsigned int state_count) +{ + int i; + + for (i = 0; i < state_count; i++) + kfree(states[i].data); + kfree(states); +} + +void dt_idle_pd_free(struct generic_pm_domain *pd) +{ + pd_free_states(pd->states, pd->state_count); + kfree(pd->name); + kfree(pd); +} + +struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, + int (*parse_state)(struct device_node *, u32 *)) +{ + struct generic_pm_domain *pd; + struct genpd_power_state *states = NULL; + int ret, state_count = 0; + + pd = kzalloc(sizeof(*pd), GFP_KERNEL); + if (!pd) + goto out; + + pd->name = kasprintf(GFP_KERNEL, "%pOF", np); + if (!pd->name) + goto free_pd; + + /* + * Parse the domain idle states and let genpd manage the state selection + * for those being compatible with "domain-idle-state". + */ + ret = pd_parse_states(np, parse_state, &states, &state_count); + if (ret) + goto free_name; + + pd->free_states = pd_free_states; + pd->name = kbasename(pd->name); + pd->states = states; + pd->state_count = state_count; + + pr_debug("alloc PM domain %s\n", pd->name); + return pd; + +free_name: + kfree(pd->name); +free_pd: + kfree(pd); +out: + pr_err("failed to alloc PM domain %pOF\n", np); + return NULL; +} + +int dt_idle_pd_init_topology(struct device_node *np) +{ + struct device_node *node; + struct of_phandle_args child, parent; + int ret; + + for_each_child_of_node(np, node) { + if (of_parse_phandle_with_args(node, "power-domains", + "#power-domain-cells", 0, &parent)) + continue; + + child.np = node; + child.args_count = 0; + ret = of_genpd_add_subdomain(&parent, &child); + of_node_put(parent.np); + if (ret) { + of_node_put(node); + return ret; + } + } + + return 0; +} + +struct device *dt_idle_attach_cpu(int cpu, const char *name) +{ + struct device *dev; + + dev = dev_pm_domain_attach_by_name(get_cpu_device(cpu), name); + if (IS_ERR_OR_NULL(dev)) + return dev; + + pm_runtime_irq_safe(dev); + if (cpu_online(cpu)) + pm_runtime_get_sync(dev); + + dev_pm_syscore_device(dev, true); + + return dev; +} + +void dt_idle_detach_cpu(struct device *dev) +{ + if (IS_ERR_OR_NULL(dev)) + return; + + dev_pm_domain_detach(dev, false); +} diff --git a/drivers/cpuidle/dt_idle_genpd.h b/drivers/cpuidle/dt_idle_genpd.h new file mode 100644 index 000000000000..a95483d08a02 --- /dev/null +++ b/drivers/cpuidle/dt_idle_genpd.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DT_IDLE_GENPD +#define __DT_IDLE_GENPD + +struct device_node; +struct generic_pm_domain; + +#ifdef CONFIG_DT_IDLE_GENPD + +void dt_idle_pd_free(struct generic_pm_domain *pd); + +struct generic_pm_domain *dt_idle_pd_alloc(struct device_node *np, + int (*parse_state)(struct device_node *, u32 *)); + +int dt_idle_pd_init_topology(struct device_node *np); + +struct device *dt_idle_attach_cpu(int cpu, const char *name); + +void dt_idle_detach_cpu(struct device *dev); + +#else + +static inline void dt_idle_pd_free(struct generic_pm_domain *pd) +{ +} + +static inline struct generic_pm_domain *dt_idle_pd_alloc( + struct device_node *np, + int (*parse_state)(struct device_node *, u32 *)) +{ + return NULL; +} + +static inline int dt_idle_pd_init_topology(struct device_node *np) +{ + return 0; +} + +static inline struct device *dt_idle_attach_cpu(int cpu, const char *name) +{ + return NULL; +} + +static inline void dt_idle_detach_cpu(struct device *dev) +{ +} + +#endif + +#endif diff --git a/drivers/crypto/virtio/Kconfig b/drivers/crypto/virtio/Kconfig index b894e3a8be4f..5f8915f4a9ff 100644 --- a/drivers/crypto/virtio/Kconfig +++ b/drivers/crypto/virtio/Kconfig @@ -3,8 +3,11 @@ config CRYPTO_DEV_VIRTIO tristate "VirtIO crypto driver" depends on VIRTIO select CRYPTO_AEAD + select CRYPTO_AKCIPHER2 select CRYPTO_SKCIPHER select CRYPTO_ENGINE + select CRYPTO_RSA + select MPILIB help This driver provides support for virtio crypto device. If you choose 'M' here, this module will be called virtio_crypto. diff --git a/drivers/crypto/virtio/Makefile b/drivers/crypto/virtio/Makefile index cbfccccfa135..bfa6cbae342e 100644 --- a/drivers/crypto/virtio/Makefile +++ b/drivers/crypto/virtio/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio_crypto.o virtio_crypto-objs := \ - virtio_crypto_algs.o \ + virtio_crypto_skcipher_algs.o \ + virtio_crypto_akcipher_algs.o \ virtio_crypto_mgr.o \ virtio_crypto_core.o diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c new file mode 100644 index 000000000000..f3ec9420215e --- /dev/null +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -0,0 +1,585 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + /* Asymmetric algorithms supported by virtio crypto device + * + * Authors: zhenwei pi <pizhenwei@bytedance.com> + * lei he <helei.sig11@bytedance.com> + * + * Copyright 2022 Bytedance CO., LTD. + */ + +#include <linux/mpi.h> +#include <linux/scatterlist.h> +#include <crypto/algapi.h> +#include <crypto/internal/akcipher.h> +#include <crypto/internal/rsa.h> +#include <linux/err.h> +#include <crypto/scatterwalk.h> +#include <linux/atomic.h> + +#include <uapi/linux/virtio_crypto.h> +#include "virtio_crypto_common.h" + +struct virtio_crypto_rsa_ctx { + MPI n; +}; + +struct virtio_crypto_akcipher_ctx { + struct crypto_engine_ctx enginectx; + struct virtio_crypto *vcrypto; + struct crypto_akcipher *tfm; + bool session_valid; + __u64 session_id; + union { + struct virtio_crypto_rsa_ctx rsa_ctx; + }; +}; + +struct virtio_crypto_akcipher_request { + struct virtio_crypto_request base; + struct virtio_crypto_akcipher_ctx *akcipher_ctx; + struct akcipher_request *akcipher_req; + void *src_buf; + void *dst_buf; + uint32_t opcode; +}; + +struct virtio_crypto_akcipher_algo { + uint32_t algonum; + uint32_t service; + unsigned int active_devs; + struct akcipher_alg algo; +}; + +static DEFINE_MUTEX(algs_lock); + +static void virtio_crypto_akcipher_finalize_req( + struct virtio_crypto_akcipher_request *vc_akcipher_req, + struct akcipher_request *req, int err) +{ + virtcrypto_clear_request(&vc_akcipher_req->base); + + crypto_finalize_akcipher_request(vc_akcipher_req->base.dataq->engine, req, err); +} + +static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request *vc_req, int len) +{ + struct virtio_crypto_akcipher_request *vc_akcipher_req = + container_of(vc_req, struct virtio_crypto_akcipher_request, base); + struct akcipher_request *akcipher_req; + int error; + + switch (vc_req->status) { + case VIRTIO_CRYPTO_OK: + error = 0; + break; + case VIRTIO_CRYPTO_INVSESS: + case VIRTIO_CRYPTO_ERR: + error = -EINVAL; + break; + case VIRTIO_CRYPTO_BADMSG: + error = -EBADMSG; + break; + + case VIRTIO_CRYPTO_KEY_REJECTED: + error = -EKEYREJECTED; + break; + + default: + error = -EIO; + break; + } + + akcipher_req = vc_akcipher_req->akcipher_req; + if (vc_akcipher_req->opcode != VIRTIO_CRYPTO_AKCIPHER_VERIFY) + sg_copy_from_buffer(akcipher_req->dst, sg_nents(akcipher_req->dst), + vc_akcipher_req->dst_buf, akcipher_req->dst_len); + virtio_crypto_akcipher_finalize_req(vc_akcipher_req, akcipher_req, error); +} + +static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, + struct virtio_crypto_ctrl_header *header, void *para, + const uint8_t *key, unsigned int keylen) +{ + struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; + struct virtio_crypto *vcrypto = ctx->vcrypto; + uint8_t *pkey; + unsigned int inlen; + int err; + unsigned int num_out = 0, num_in = 0; + + pkey = kmemdup(key, keylen, GFP_ATOMIC); + if (!pkey) + return -ENOMEM; + + spin_lock(&vcrypto->ctrl_lock); + memcpy(&vcrypto->ctrl.header, header, sizeof(vcrypto->ctrl.header)); + memcpy(&vcrypto->ctrl.u, para, sizeof(vcrypto->ctrl.u)); + vcrypto->input.status = cpu_to_le32(VIRTIO_CRYPTO_ERR); + + sg_init_one(&outhdr_sg, &vcrypto->ctrl, sizeof(vcrypto->ctrl)); + sgs[num_out++] = &outhdr_sg; + + sg_init_one(&key_sg, pkey, keylen); + sgs[num_out++] = &key_sg; + + sg_init_one(&inhdr_sg, &vcrypto->input, sizeof(vcrypto->input)); + sgs[num_out + num_in++] = &inhdr_sg; + + err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, num_out, num_in, vcrypto, GFP_ATOMIC); + if (err < 0) + goto out; + + virtqueue_kick(vcrypto->ctrl_vq); + while (!virtqueue_get_buf(vcrypto->ctrl_vq, &inlen) && + !virtqueue_is_broken(vcrypto->ctrl_vq)) + cpu_relax(); + + if (le32_to_cpu(vcrypto->input.status) != VIRTIO_CRYPTO_OK) { + err = -EINVAL; + goto out; + } + + ctx->session_id = le64_to_cpu(vcrypto->input.session_id); + ctx->session_valid = true; + err = 0; + +out: + spin_unlock(&vcrypto->ctrl_lock); + kfree_sensitive(pkey); + + if (err < 0) + pr_err("virtio_crypto: Create session failed status: %u\n", + le32_to_cpu(vcrypto->input.status)); + + return err; +} + +static int virtio_crypto_alg_akcipher_close_session(struct virtio_crypto_akcipher_ctx *ctx) +{ + struct scatterlist outhdr_sg, inhdr_sg, *sgs[2]; + struct virtio_crypto_destroy_session_req *destroy_session; + struct virtio_crypto *vcrypto = ctx->vcrypto; + unsigned int num_out = 0, num_in = 0, inlen; + int err; + + spin_lock(&vcrypto->ctrl_lock); + if (!ctx->session_valid) { + err = 0; + goto out; + } + vcrypto->ctrl_status.status = VIRTIO_CRYPTO_ERR; + vcrypto->ctrl.header.opcode = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_DESTROY_SESSION); + vcrypto->ctrl.header.queue_id = 0; + + destroy_session = &vcrypto->ctrl.u.destroy_session; + destroy_session->session_id = cpu_to_le64(ctx->session_id); + + sg_init_one(&outhdr_sg, &vcrypto->ctrl, sizeof(vcrypto->ctrl)); + sgs[num_out++] = &outhdr_sg; + + sg_init_one(&inhdr_sg, &vcrypto->ctrl_status.status, sizeof(vcrypto->ctrl_status.status)); + sgs[num_out + num_in++] = &inhdr_sg; + + err = virtqueue_add_sgs(vcrypto->ctrl_vq, sgs, num_out, num_in, vcrypto, GFP_ATOMIC); + if (err < 0) + goto out; + + virtqueue_kick(vcrypto->ctrl_vq); + while (!virtqueue_get_buf(vcrypto->ctrl_vq, &inlen) && + !virtqueue_is_broken(vcrypto->ctrl_vq)) + cpu_relax(); + + if (vcrypto->ctrl_status.status != VIRTIO_CRYPTO_OK) { + err = -EINVAL; + goto out; + } + + err = 0; + ctx->session_valid = false; + +out: + spin_unlock(&vcrypto->ctrl_lock); + if (err < 0) { + pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n", + vcrypto->ctrl_status.status, destroy_session->session_id); + } + + return err; +} + +static int __virtio_crypto_akcipher_do_req(struct virtio_crypto_akcipher_request *vc_akcipher_req, + struct akcipher_request *req, struct data_queue *data_vq) +{ + struct virtio_crypto_akcipher_ctx *ctx = vc_akcipher_req->akcipher_ctx; + struct virtio_crypto_request *vc_req = &vc_akcipher_req->base; + struct virtio_crypto *vcrypto = ctx->vcrypto; + struct virtio_crypto_op_data_req *req_data = vc_req->req_data; + struct scatterlist *sgs[4], outhdr_sg, inhdr_sg, srcdata_sg, dstdata_sg; + void *src_buf = NULL, *dst_buf = NULL; + unsigned int num_out = 0, num_in = 0; + int node = dev_to_node(&vcrypto->vdev->dev); + unsigned long flags; + int ret = -ENOMEM; + bool verify = vc_akcipher_req->opcode == VIRTIO_CRYPTO_AKCIPHER_VERIFY; + unsigned int src_len = verify ? req->src_len + req->dst_len : req->src_len; + + /* out header */ + sg_init_one(&outhdr_sg, req_data, sizeof(*req_data)); + sgs[num_out++] = &outhdr_sg; + + /* src data */ + src_buf = kcalloc_node(src_len, 1, GFP_KERNEL, node); + if (!src_buf) + goto err; + + if (verify) { + /* for verify operation, both src and dst data work as OUT direction */ + sg_copy_to_buffer(req->src, sg_nents(req->src), src_buf, src_len); + sg_init_one(&srcdata_sg, src_buf, src_len); + sgs[num_out++] = &srcdata_sg; + } else { + sg_copy_to_buffer(req->src, sg_nents(req->src), src_buf, src_len); + sg_init_one(&srcdata_sg, src_buf, src_len); + sgs[num_out++] = &srcdata_sg; + + /* dst data */ + dst_buf = kcalloc_node(req->dst_len, 1, GFP_KERNEL, node); + if (!dst_buf) + goto err; + + sg_init_one(&dstdata_sg, dst_buf, req->dst_len); + sgs[num_out + num_in++] = &dstdata_sg; + } + + vc_akcipher_req->src_buf = src_buf; + vc_akcipher_req->dst_buf = dst_buf; + + /* in header */ + sg_init_one(&inhdr_sg, &vc_req->status, sizeof(vc_req->status)); + sgs[num_out + num_in++] = &inhdr_sg; + + spin_lock_irqsave(&data_vq->lock, flags); + ret = virtqueue_add_sgs(data_vq->vq, sgs, num_out, num_in, vc_req, GFP_ATOMIC); + virtqueue_kick(data_vq->vq); + spin_unlock_irqrestore(&data_vq->lock, flags); + if (ret) + goto err; + + return 0; + +err: + kfree(src_buf); + kfree(dst_buf); + + return -ENOMEM; +} + +static int virtio_crypto_rsa_do_req(struct crypto_engine *engine, void *vreq) +{ + struct akcipher_request *req = container_of(vreq, struct akcipher_request, base); + struct virtio_crypto_akcipher_request *vc_akcipher_req = akcipher_request_ctx(req); + struct virtio_crypto_request *vc_req = &vc_akcipher_req->base; + struct virtio_crypto_akcipher_ctx *ctx = vc_akcipher_req->akcipher_ctx; + struct virtio_crypto *vcrypto = ctx->vcrypto; + struct data_queue *data_vq = vc_req->dataq; + struct virtio_crypto_op_header *header; + struct virtio_crypto_akcipher_data_req *akcipher_req; + int ret; + + vc_req->sgs = NULL; + vc_req->req_data = kzalloc_node(sizeof(*vc_req->req_data), + GFP_KERNEL, dev_to_node(&vcrypto->vdev->dev)); + if (!vc_req->req_data) + return -ENOMEM; + + /* build request header */ + header = &vc_req->req_data->header; + header->opcode = cpu_to_le32(vc_akcipher_req->opcode); + header->algo = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_RSA); + header->session_id = cpu_to_le64(ctx->session_id); + + /* build request akcipher data */ + akcipher_req = &vc_req->req_data->u.akcipher_req; + akcipher_req->para.src_data_len = cpu_to_le32(req->src_len); + akcipher_req->para.dst_data_len = cpu_to_le32(req->dst_len); + + ret = __virtio_crypto_akcipher_do_req(vc_akcipher_req, req, data_vq); + if (ret < 0) { + kfree_sensitive(vc_req->req_data); + vc_req->req_data = NULL; + return ret; + } + + return 0; +} + +static int virtio_crypto_rsa_req(struct akcipher_request *req, uint32_t opcode) +{ + struct crypto_akcipher *atfm = crypto_akcipher_reqtfm(req); + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(atfm); + struct virtio_crypto_akcipher_request *vc_akcipher_req = akcipher_request_ctx(req); + struct virtio_crypto_request *vc_req = &vc_akcipher_req->base; + struct virtio_crypto *vcrypto = ctx->vcrypto; + /* Use the first data virtqueue as default */ + struct data_queue *data_vq = &vcrypto->data_vq[0]; + + vc_req->dataq = data_vq; + vc_req->alg_cb = virtio_crypto_dataq_akcipher_callback; + vc_akcipher_req->akcipher_ctx = ctx; + vc_akcipher_req->akcipher_req = req; + vc_akcipher_req->opcode = opcode; + + return crypto_transfer_akcipher_request_to_engine(data_vq->engine, req); +} + +static int virtio_crypto_rsa_encrypt(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_ENCRYPT); +} + +static int virtio_crypto_rsa_decrypt(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_DECRYPT); +} + +static int virtio_crypto_rsa_sign(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_SIGN); +} + +static int virtio_crypto_rsa_verify(struct akcipher_request *req) +{ + return virtio_crypto_rsa_req(req, VIRTIO_CRYPTO_AKCIPHER_VERIFY); +} + +static int virtio_crypto_rsa_set_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen, + bool private, + int padding_algo, + int hash_algo) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + struct virtio_crypto_rsa_ctx *rsa_ctx = &ctx->rsa_ctx; + struct virtio_crypto *vcrypto; + struct virtio_crypto_ctrl_header header; + struct virtio_crypto_akcipher_session_para para; + struct rsa_key rsa_key = {0}; + int node = virtio_crypto_get_current_node(); + uint32_t keytype; + int ret; + + /* mpi_free will test n, just free it. */ + mpi_free(rsa_ctx->n); + rsa_ctx->n = NULL; + + if (private) { + keytype = VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PRIVATE; + ret = rsa_parse_priv_key(&rsa_key, key, keylen); + } else { + keytype = VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PUBLIC; + ret = rsa_parse_pub_key(&rsa_key, key, keylen); + } + + if (ret) + return ret; + + rsa_ctx->n = mpi_read_raw_data(rsa_key.n, rsa_key.n_sz); + if (!rsa_ctx->n) + return -ENOMEM; + + if (!ctx->vcrypto) { + vcrypto = virtcrypto_get_dev_node(node, VIRTIO_CRYPTO_SERVICE_AKCIPHER, + VIRTIO_CRYPTO_AKCIPHER_RSA); + if (!vcrypto) { + pr_err("virtio_crypto: Could not find a virtio device in the system or unsupported algo\n"); + return -ENODEV; + } + + ctx->vcrypto = vcrypto; + } else { + virtio_crypto_alg_akcipher_close_session(ctx); + } + + /* set ctrl header */ + header.opcode = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_CREATE_SESSION); + header.algo = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_RSA); + header.queue_id = 0; + + /* set RSA para */ + para.algo = cpu_to_le32(VIRTIO_CRYPTO_AKCIPHER_RSA); + para.keytype = cpu_to_le32(keytype); + para.keylen = cpu_to_le32(keylen); + para.u.rsa.padding_algo = cpu_to_le32(padding_algo); + para.u.rsa.hash_algo = cpu_to_le32(hash_algo); + + return virtio_crypto_alg_akcipher_init_session(ctx, &header, ¶, key, keylen); +} + +static int virtio_crypto_rsa_raw_set_priv_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 1, + VIRTIO_CRYPTO_RSA_RAW_PADDING, + VIRTIO_CRYPTO_RSA_NO_HASH); +} + + +static int virtio_crypto_p1pad_rsa_sha1_set_priv_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 1, + VIRTIO_CRYPTO_RSA_PKCS1_PADDING, + VIRTIO_CRYPTO_RSA_SHA1); +} + +static int virtio_crypto_rsa_raw_set_pub_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 0, + VIRTIO_CRYPTO_RSA_RAW_PADDING, + VIRTIO_CRYPTO_RSA_NO_HASH); +} + +static int virtio_crypto_p1pad_rsa_sha1_set_pub_key(struct crypto_akcipher *tfm, + const void *key, + unsigned int keylen) +{ + return virtio_crypto_rsa_set_key(tfm, key, keylen, 0, + VIRTIO_CRYPTO_RSA_PKCS1_PADDING, + VIRTIO_CRYPTO_RSA_SHA1); +} + +static unsigned int virtio_crypto_rsa_max_size(struct crypto_akcipher *tfm) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + struct virtio_crypto_rsa_ctx *rsa_ctx = &ctx->rsa_ctx; + + return mpi_get_size(rsa_ctx->n); +} + +static int virtio_crypto_rsa_init_tfm(struct crypto_akcipher *tfm) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + + ctx->tfm = tfm; + ctx->enginectx.op.do_one_request = virtio_crypto_rsa_do_req; + ctx->enginectx.op.prepare_request = NULL; + ctx->enginectx.op.unprepare_request = NULL; + + return 0; +} + +static void virtio_crypto_rsa_exit_tfm(struct crypto_akcipher *tfm) +{ + struct virtio_crypto_akcipher_ctx *ctx = akcipher_tfm_ctx(tfm); + struct virtio_crypto_rsa_ctx *rsa_ctx = &ctx->rsa_ctx; + + virtio_crypto_alg_akcipher_close_session(ctx); + virtcrypto_dev_put(ctx->vcrypto); + mpi_free(rsa_ctx->n); + rsa_ctx->n = NULL; +} + +static struct virtio_crypto_akcipher_algo virtio_crypto_akcipher_algs[] = { + { + .algonum = VIRTIO_CRYPTO_AKCIPHER_RSA, + .service = VIRTIO_CRYPTO_SERVICE_AKCIPHER, + .algo = { + .encrypt = virtio_crypto_rsa_encrypt, + .decrypt = virtio_crypto_rsa_decrypt, + .set_pub_key = virtio_crypto_rsa_raw_set_pub_key, + .set_priv_key = virtio_crypto_rsa_raw_set_priv_key, + .max_size = virtio_crypto_rsa_max_size, + .init = virtio_crypto_rsa_init_tfm, + .exit = virtio_crypto_rsa_exit_tfm, + .reqsize = sizeof(struct virtio_crypto_akcipher_request), + .base = { + .cra_name = "rsa", + .cra_driver_name = "virtio-crypto-rsa", + .cra_priority = 150, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct virtio_crypto_akcipher_ctx), + }, + }, + }, + { + .algonum = VIRTIO_CRYPTO_AKCIPHER_RSA, + .service = VIRTIO_CRYPTO_SERVICE_AKCIPHER, + .algo = { + .encrypt = virtio_crypto_rsa_encrypt, + .decrypt = virtio_crypto_rsa_decrypt, + .sign = virtio_crypto_rsa_sign, + .verify = virtio_crypto_rsa_verify, + .set_pub_key = virtio_crypto_p1pad_rsa_sha1_set_pub_key, + .set_priv_key = virtio_crypto_p1pad_rsa_sha1_set_priv_key, + .max_size = virtio_crypto_rsa_max_size, + .init = virtio_crypto_rsa_init_tfm, + .exit = virtio_crypto_rsa_exit_tfm, + .reqsize = sizeof(struct virtio_crypto_akcipher_request), + .base = { + .cra_name = "pkcs1pad(rsa,sha1)", + .cra_driver_name = "virtio-pkcs1-rsa-with-sha1", + .cra_priority = 150, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct virtio_crypto_akcipher_ctx), + }, + }, + }, +}; + +int virtio_crypto_akcipher_algs_register(struct virtio_crypto *vcrypto) +{ + int ret = 0; + int i = 0; + + mutex_lock(&algs_lock); + + for (i = 0; i < ARRAY_SIZE(virtio_crypto_akcipher_algs); i++) { + uint32_t service = virtio_crypto_akcipher_algs[i].service; + uint32_t algonum = virtio_crypto_akcipher_algs[i].algonum; + + if (!virtcrypto_algo_is_supported(vcrypto, service, algonum)) + continue; + + if (virtio_crypto_akcipher_algs[i].active_devs == 0) { + ret = crypto_register_akcipher(&virtio_crypto_akcipher_algs[i].algo); + if (ret) + goto unlock; + } + + virtio_crypto_akcipher_algs[i].active_devs++; + dev_info(&vcrypto->vdev->dev, "Registered akcipher algo %s\n", + virtio_crypto_akcipher_algs[i].algo.base.cra_name); + } + +unlock: + mutex_unlock(&algs_lock); + return ret; +} + +void virtio_crypto_akcipher_algs_unregister(struct virtio_crypto *vcrypto) +{ + int i = 0; + + mutex_lock(&algs_lock); + + for (i = 0; i < ARRAY_SIZE(virtio_crypto_akcipher_algs); i++) { + uint32_t service = virtio_crypto_akcipher_algs[i].service; + uint32_t algonum = virtio_crypto_akcipher_algs[i].algonum; + + if (virtio_crypto_akcipher_algs[i].active_devs == 0 || + !virtcrypto_algo_is_supported(vcrypto, service, algonum)) + continue; + + if (virtio_crypto_akcipher_algs[i].active_devs == 1) + crypto_unregister_akcipher(&virtio_crypto_akcipher_algs[i].algo); + + virtio_crypto_akcipher_algs[i].active_devs--; + } + + mutex_unlock(&algs_lock); +} diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h index a24f85c589e7..e693d4ee83a6 100644 --- a/drivers/crypto/virtio/virtio_crypto_common.h +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -56,6 +56,7 @@ struct virtio_crypto { u32 mac_algo_l; u32 mac_algo_h; u32 aead_algo; + u32 akcipher_algo; /* Maximum length of cipher key */ u32 max_cipher_key_len; @@ -129,7 +130,9 @@ static inline int virtio_crypto_get_current_node(void) return node; } -int virtio_crypto_algs_register(struct virtio_crypto *vcrypto); -void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto); +int virtio_crypto_skcipher_algs_register(struct virtio_crypto *vcrypto); +void virtio_crypto_skcipher_algs_unregister(struct virtio_crypto *vcrypto); +int virtio_crypto_akcipher_algs_register(struct virtio_crypto *vcrypto); +void virtio_crypto_akcipher_algs_unregister(struct virtio_crypto *vcrypto); #endif /* _VIRTIO_CRYPTO_COMMON_H */ diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 8e977b7627cb..c6f482db0bc0 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -297,6 +297,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) u32 mac_algo_l = 0; u32 mac_algo_h = 0; u32 aead_algo = 0; + u32 akcipher_algo = 0; u32 crypto_services = 0; if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) @@ -348,6 +349,9 @@ static int virtcrypto_probe(struct virtio_device *vdev) mac_algo_h, &mac_algo_h); virtio_cread_le(vdev, struct virtio_crypto_config, aead_algo, &aead_algo); + if (crypto_services & (1 << VIRTIO_CRYPTO_SERVICE_AKCIPHER)) + virtio_cread_le(vdev, struct virtio_crypto_config, + akcipher_algo, &akcipher_algo); /* Add virtio crypto device to global table */ err = virtcrypto_devmgr_add_dev(vcrypto); @@ -374,7 +378,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) vcrypto->mac_algo_h = mac_algo_h; vcrypto->hash_algo = hash_algo; vcrypto->aead_algo = aead_algo; - + vcrypto->akcipher_algo = akcipher_algo; dev_info(&vdev->dev, "max_queues: %u, max_cipher_key_len: %u, max_auth_key_len: %u, max_size 0x%llx\n", diff --git a/drivers/crypto/virtio/virtio_crypto_mgr.c b/drivers/crypto/virtio/virtio_crypto_mgr.c index 6860f8180c7c..70e778aac0f2 100644 --- a/drivers/crypto/virtio/virtio_crypto_mgr.c +++ b/drivers/crypto/virtio/virtio_crypto_mgr.c @@ -237,8 +237,14 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node, uint32_t service, */ int virtcrypto_dev_start(struct virtio_crypto *vcrypto) { - if (virtio_crypto_algs_register(vcrypto)) { - pr_err("virtio_crypto: Failed to register crypto algs\n"); + if (virtio_crypto_skcipher_algs_register(vcrypto)) { + pr_err("virtio_crypto: Failed to register crypto skcipher algs\n"); + return -EFAULT; + } + + if (virtio_crypto_akcipher_algs_register(vcrypto)) { + pr_err("virtio_crypto: Failed to register crypto akcipher algs\n"); + virtio_crypto_skcipher_algs_unregister(vcrypto); return -EFAULT; } @@ -257,7 +263,8 @@ int virtcrypto_dev_start(struct virtio_crypto *vcrypto) */ void virtcrypto_dev_stop(struct virtio_crypto *vcrypto) { - virtio_crypto_algs_unregister(vcrypto); + virtio_crypto_skcipher_algs_unregister(vcrypto); + virtio_crypto_akcipher_algs_unregister(vcrypto); } /* @@ -312,6 +319,10 @@ bool virtcrypto_algo_is_supported(struct virtio_crypto *vcrypto, case VIRTIO_CRYPTO_SERVICE_AEAD: algo_mask = vcrypto->aead_algo; break; + + case VIRTIO_CRYPTO_SERVICE_AKCIPHER: + algo_mask = vcrypto->akcipher_algo; + break; } if (!(algo_mask & (1u << algo))) diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c index 583c0b535d13..a618c46a52b8 100644 --- a/drivers/crypto/virtio/virtio_crypto_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c @@ -613,7 +613,7 @@ static struct virtio_crypto_algo virtio_crypto_algs[] = { { }, } }; -int virtio_crypto_algs_register(struct virtio_crypto *vcrypto) +int virtio_crypto_skcipher_algs_register(struct virtio_crypto *vcrypto) { int ret = 0; int i = 0; @@ -644,7 +644,7 @@ unlock: return ret; } -void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto) +void virtio_crypto_skcipher_algs_unregister(struct virtio_crypto *vcrypto) { int i = 0; diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8a7267d116b7..3f2182d66829 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -436,7 +436,6 @@ static int wait_for_media_ready(struct cxl_dev_state *cxlds) for (i = mbox_ready_timeout; i; i--) { u32 temp; - int rc; rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 511805dbeb75..4c9eb53ba3f8 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -12,6 +12,7 @@ dmabuf_selftests-y := \ selftest.o \ st-dma-fence.o \ st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ st-dma-resv.o obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index cb1bacb5a42b..5c8a7084577b 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence_array *array; size_t size = sizeof(*array); + WARN_ON(!num_fences || !fences); + /* Allocate the callback structures behind the array. */ size += num_fences * sizeof(struct dma_fence_array_cb); array = kzalloc(size, GFP_KERNEL); @@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h index 97d73aaa31da..851965867d9c 100644 --- a/drivers/dma-buf/selftests.h +++ b/drivers/dma-buf/selftests.h @@ -12,4 +12,5 @@ selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ selftest(dma_fence, dma_fence) selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..039f016b57be --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence-unwrap.h> +#if 0 +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> +#endif + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + return NULL; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto cleanup; + return &array->base; + +cleanup: + for (i = 0; i < num_fences; ++i) + dma_fence_put(fences[i]); + kfree(fences); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(array); + return 0; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 394e6e1e9686..514d213261df 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 Google, Inc. */ +#include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file, return 0; } -static struct dma_fence **get_fences(struct sync_file *sync_file, - int *num_fences) -{ - if (dma_fence_is_array(sync_file->fence)) { - struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); - - *num_fences = array->num_fences; - return array->fences; - } - - *num_fences = 1; - return &sync_file->fence; -} - static void add_fence(struct dma_fence **fences, int *i, struct dma_fence *fence) { @@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences, static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { + struct dma_fence *a_fence, *b_fence, **fences; + struct dma_fence_unwrap a_iter, b_iter; + unsigned int index, num_fences; struct sync_file *sync_file; - struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; - int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) - goto err; + num_fences = 0; + dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence) + ++num_fences; + dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence) + ++num_fences; - num_fences = a_num_fences + b_num_fences; + if (num_fences > INT_MAX) + goto err_free_sync_file; fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); if (!fences) - goto err; + goto err_free_sync_file; /* - * Assume sync_file a and b are both ordered and have no - * duplicates with the same context. + * We can't guarantee that fences in both a and b are ordered, but it is + * still quite likely. * - * If a sync_file can only be created with sync_file_merge - * and sync_file_create, this is a reasonable assumption. + * So attempt to order the fences as we pass over them and merge fences + * with the same context. */ - for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { - struct dma_fence *pt_a = a_fences[i_a]; - struct dma_fence *pt_b = b_fences[i_b]; - if (pt_a->context < pt_b->context) { - add_fence(fences, &i, pt_a); + index = 0; + for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter), + b_fence = dma_fence_unwrap_first(b->fence, &b_iter); + a_fence || b_fence; ) { + + if (!b_fence) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + + } else if (!a_fence) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (a_fence->context < b_fence->context) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); - i_a++; - } else if (pt_a->context > pt_b->context) { - add_fence(fences, &i, pt_b); + } else if (b_fence->context < a_fence->context) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno, + a_fence->ops)) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); - i_b++; } else { - if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno, - pt_a->ops)) - add_fence(fences, &i, pt_a); - else - add_fence(fences, &i, pt_b); - - i_a++; - i_b++; + add_fence(fences, &index, b_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); } } - for (; i_a < a_num_fences; i_a++) - add_fence(fences, &i, a_fences[i_a]); - - for (; i_b < b_num_fences; i_b++) - add_fence(fences, &i, b_fences[i_b]); - - if (i == 0) - fences[i++] = dma_fence_get(a_fences[0]); + if (index == 0) + fences[index++] = dma_fence_get_stub(); - if (num_fences > i) { - nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL); - if (!nfences) - goto err; + if (num_fences > index) { + struct dma_fence **tmp; - fences = nfences; + /* Keep going even when reducing the size failed */ + tmp = krealloc_array(fences, index, sizeof(*fences), + GFP_KERNEL); + if (tmp) + fences = tmp; } - if (sync_file_set_fence(sync_file, fences, i) < 0) - goto err; + if (sync_file_set_fence(sync_file, fences, index) < 0) + goto err_put_fences; strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; -err: - while (i) - dma_fence_put(fences[--i]); +err_put_fences: + while (index) + dma_fence_put(fences[--index]); kfree(fences); + +err_free_sync_file: fput(sync_file->file); return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index cf6fed6dec77..45600acc0f45 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -49,7 +49,7 @@ struct scmi_msg_resp_clock_describe_rates { struct { __le32 value_low; __le32 value_high; - } rate[0]; + } rate[]; #define RATE_TO_U64(X) \ ({ \ typeof(X) x = (X); \ @@ -210,7 +210,8 @@ scmi_clock_describe_rates_get(const struct scmi_protocol_handle *ph, u32 clk_id, if (rate_discrete && rate) { clk->list.num_rates = tot_rate_cnt; - sort(rate, tot_rate_cnt, sizeof(*rate), rate_cmp_func, NULL); + sort(clk->list.rates, tot_rate_cnt, sizeof(*rate), + rate_cmp_func, NULL); } clk->rate_discrete = rate_discrete; diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 46118300a4d1..e17c6568344d 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -679,7 +679,8 @@ static void scmi_handle_response(struct scmi_chan_info *cinfo, xfer = scmi_xfer_command_acquire(cinfo, msg_hdr); if (IS_ERR(xfer)) { - scmi_clear_channel(info, cinfo); + if (MSG_XTRACT_TYPE(msg_hdr) == MSG_TYPE_DELAYED_RESP) + scmi_clear_channel(info, cinfo); return; } diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index 734f1eeee161..8302a2b4aeeb 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -405,8 +405,8 @@ static int scmi_optee_chan_free(int id, void *p, void *data) return 0; } -static struct scmi_shared_mem *get_channel_shm(struct scmi_optee_channel *chan, - struct scmi_xfer *xfer) +static struct scmi_shared_mem __iomem * +get_channel_shm(struct scmi_optee_channel *chan, struct scmi_xfer *xfer) { if (!chan) return NULL; @@ -419,7 +419,7 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer) { struct scmi_optee_channel *channel = cinfo->transport_info; - struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer); + struct scmi_shared_mem __iomem *shmem = get_channel_shm(channel, xfer); int ret; mutex_lock(&channel->mu); @@ -436,7 +436,7 @@ static void scmi_optee_fetch_response(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer) { struct scmi_optee_channel *channel = cinfo->transport_info; - struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer); + struct scmi_shared_mem __iomem *shmem = get_channel_shm(channel, xfer); shmem_fetch_response(shmem, xfer); } diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 8e5d87984a48..41c31b10ae84 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -134,7 +134,7 @@ static int gpio_sim_get_multiple(struct gpio_chip *gc, struct gpio_sim_chip *chip = gpiochip_get_data(gc); mutex_lock(&chip->lock); - bitmap_copy(bits, chip->value_map, gc->ngpio); + bitmap_replace(bits, bits, chip->value_map, mask, gc->ngpio); mutex_unlock(&chip->lock); return 0; @@ -146,7 +146,7 @@ static void gpio_sim_set_multiple(struct gpio_chip *gc, struct gpio_sim_chip *chip = gpiochip_get_data(gc); mutex_lock(&chip->lock); - bitmap_copy(chip->value_map, bits, gc->ngpio); + bitmap_replace(chip->value_map, chip->value_map, bits, mask, gc->ngpio); mutex_unlock(&chip->lock); } diff --git a/drivers/gpio/gpio-ts4900.c b/drivers/gpio/gpio-ts4900.c index 69854fd2382a..416725c26e94 100644 --- a/drivers/gpio/gpio-ts4900.c +++ b/drivers/gpio/gpio-ts4900.c @@ -47,8 +47,9 @@ static int ts4900_gpio_direction_input(struct gpio_chip *chip, { struct ts4900_gpio_priv *priv = gpiochip_get_data(chip); - /* Only clear the OE bit here, requires a RMW. Prevents potential issue - * with OE and data getting to the physical pin at different times. + /* + * Only clear the OE bit here, requires a RMW. Prevents a potential issue + * with OE and DAT getting to the physical pin at different times. */ return regmap_update_bits(priv->regmap, offset, TS4900_GPIO_OE, 0); } @@ -60,9 +61,10 @@ static int ts4900_gpio_direction_output(struct gpio_chip *chip, unsigned int reg; int ret; - /* If changing from an input to an output, we need to first set the - * proper data bit to what is requested and then set OE bit. This - * prevents a glitch that can occur on the IO line + /* + * If changing from an input to an output, we need to first set the + * GPIO's DAT bit to what is requested and then set the OE bit. This + * prevents a glitch that can occur on the IO line. */ regmap_read(priv->regmap, offset, ®); if (!(reg & TS4900_GPIO_OE)) { diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c index b159e92a3612..8e03614c7a24 100644 --- a/drivers/gpio/gpio-ts5500.c +++ b/drivers/gpio/gpio-ts5500.c @@ -11,11 +11,11 @@ * Actually, the following platforms have DIO support: * * TS-5500: - * Documentation: http://wiki.embeddedarm.com/wiki/TS-5500 + * Documentation: https://docs.embeddedts.com/TS-5500 * Blocks: DIO1, DIO2 and LCD port. * * TS-5600: - * Documentation: http://wiki.embeddedarm.com/wiki/TS-5600 + * Documentation: https://docs.embeddedts.com/TS-5600 * Blocks: LCD port (identical to TS-5500 LCD). */ diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index a5495ad31c9c..c2523ac26fac 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -108,7 +108,7 @@ static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) * controller does not have GPIO chip registered at the moment. This is to * support probe deferral. */ -static struct gpio_desc *acpi_get_gpiod(char *path, int pin) +static struct gpio_desc *acpi_get_gpiod(char *path, unsigned int pin) { struct gpio_chip *chip; acpi_handle handle; @@ -136,7 +136,7 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) * as it is intended for use outside of the GPIO layer (in a similar fashion to * gpiod_get_index() for example) it also holds a reference to the GPIO device. */ -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label) +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label) { struct gpio_desc *gpio; int ret; @@ -317,11 +317,12 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, return desc; } -static bool acpi_gpio_in_ignore_list(const char *controller_in, int pin_in) +static bool acpi_gpio_in_ignore_list(const char *controller_in, unsigned int pin_in) { const char *controller, *pin_str; - int len, pin; + unsigned int pin; char *endp; + int len; controller = ignore_wake; while (controller) { @@ -354,13 +355,13 @@ err: static bool acpi_gpio_irq_is_wake(struct device *parent, struct acpi_resource_gpio *agpio) { - int pin = agpio->pin_table[0]; + unsigned int pin = agpio->pin_table[0]; if (agpio->wake_capable != ACPI_WAKE_CAPABLE) return false; if (acpi_gpio_in_ignore_list(dev_name(parent), pin)) { - dev_info(parent, "Ignoring wakeup on pin %d\n", pin); + dev_info(parent, "Ignoring wakeup on pin %u\n", pin); return false; } @@ -378,7 +379,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, struct acpi_gpio_event *event; irq_handler_t handler = NULL; struct gpio_desc *desc; - int ret, pin, irq; + unsigned int pin; + int ret, irq; if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; @@ -387,8 +389,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, pin = agpio->pin_table[0]; if (pin <= 255) { - char ev_name[5]; - sprintf(ev_name, "_%c%02hhX", + char ev_name[8]; + sprintf(ev_name, "_%c%02X", agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L', pin); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) @@ -1098,7 +1100,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, length = min_t(u16, agpio->pin_table_length, pin_index + bits); for (i = pin_index; i < length; ++i) { - int pin = agpio->pin_table[i]; + unsigned int pin = agpio->pin_table[i]; struct acpi_gpio_connection *conn; struct gpio_desc *desc; bool found; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e59884cc12a7..085348e08986 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1404,6 +1404,16 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) { struct irq_domain *domain = gc->irq.domain; +#ifdef CONFIG_GPIOLIB_IRQCHIP + /* + * Avoid race condition with other code, which tries to lookup + * an IRQ before the irqchip has been properly registered, + * i.e. while gpiochip is still being brought up. + */ + if (!gc->irq.initialized) + return -EPROBE_DEFER; +#endif + if (!gpiochip_irqchip_irq_valid(gc, offset)) return -ENXIO; @@ -1593,6 +1603,15 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, acpi_gpiochip_request_interrupts(gc); + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before initialization of above + * GPIO chip irq members. + */ + barrier(); + + gc->irq.initialized = true; + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..29e9419a914b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); @@ -2323,18 +2323,23 @@ static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else adev->in_s3 = true; - r = amdgpu_device_suspend(drm_dev, true); - if (r) - return r; + return amdgpu_device_suspend(drm_dev, true); +} + +static int amdgpu_pmops_suspend_noirq(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + if (!adev->in_s0ix) - r = amdgpu_asic_reset(adev); - return r; + return amdgpu_asic_reset(adev); + + return 0; } static int amdgpu_pmops_resume(struct device *dev) @@ -2575,6 +2580,7 @@ static const struct dev_pm_ops amdgpu_pm_ops = { .prepare = amdgpu_pmops_prepare, .complete = amdgpu_pmops_complete, .suspend = amdgpu_pmops_suspend, + .suspend_noirq = amdgpu_pmops_suspend_noirq, .resume = amdgpu_pmops_resume, .freeze = amdgpu_pmops_freeze, .thaw = amdgpu_pmops_thaw, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25731719c627..940752488330 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f99093f2ebc7..a0ee828a4a97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -52,7 +52,7 @@ #define FIRMWARE_ALDEBARAN "amdgpu/aldebaran_vcn.bin" #define FIRMWARE_BEIGE_GOBY "amdgpu/beige_goby_vcn.bin" #define FIRMWARE_YELLOW_CARP "amdgpu/yellow_carp_vcn.bin" -#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2_vcn.bin" +#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN); MODULE_FIRMWARE(FIRMWARE_PICASSO); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 46d4bf27ebbb..b8cfcc6b1125 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1205,6 +1205,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, + /* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */ + { 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..5228421b0f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 339e12c94cff..62aa6c9d5123 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, } /* Verify module parameters regarding mapped process number*/ - if ((hws_max_conc_proc < 0) - || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { - dev_err(kfd_device, - "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n", - hws_max_conc_proc, kfd->vm_info.vmid_num_kfd, - kfd->vm_info.vmid_num_kfd); + if (hws_max_conc_proc >= 0) + kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd); + else kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd; - } else - kfd->max_proc_per_quantum = hws_max_conc_proc; /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * @@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_doorbell_error; } - kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; + if (amdgpu_use_xgmi_p2p) + kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; kfd->noretry = kfd->adev->gmc.noretry; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index deecccebe5b6..64f4a51cc880 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) event_waiters = kmalloc_array(num_events, sizeof(struct kfd_event_waiter), GFP_KERNEL); + if (!event_waiters) + return NULL; for (i = 0; (event_waiters) && (i < num_events) ; i++) { init_wait(&event_waiters[i].wait); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index e4beebb1c80a..f2e1d506ba21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) return ret; } - ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, - O_RDWR); - if (ret < 0) { - kfifo_free(&client->fifo); - kfree(client); - return ret; - } - *fd = ret; - init_waitqueue_head(&client->wait_queue); spin_lock_init(&client->lock); client->events = 0; @@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) list_add_rcu(&client->list, &dev->smi_clients); spin_unlock(&dev->smi_lock); + ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, + O_RDWR); + if (ret < 0) { + spin_lock(&dev->smi_lock); + list_del_rcu(&client->list); + spin_unlock(&dev->smi_lock); + + synchronize_rcu(); + + kfifo_free(&client->fifo); + kfree(client); + return ret; + } + *fd = ret; + return 0; } 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 b30656959fd8..62139ff35476 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2714,7 +2714,8 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->mst_port) + if (aconnector->dc_link && + aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); @@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap max - min); } -static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, +static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { @@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx); } - return rc ? 0 : 1; + if (rc) + dm->actual_brightness[bl_idx] = user_brightness; } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -9947,7 +9949,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* restore the backlight level */ for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i] && - (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i])) + (dm->actual_brightness[i] != dm->brightness[i])) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 6a908d736d6a..7e44b0429448 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,12 @@ struct amdgpu_display_manager { * cached backlight values. */ u32 brightness[AMDGPU_DM_MAX_NUM_EDP]; + /** + * @actual_brightness: + * + * last successfully applied backlight values. + */ + u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c index dfba6138f538..26feefbb8990 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c @@ -374,7 +374,7 @@ void dce_clock_read_ss_info(struct clk_mgr_internal *clk_mgr_dce) clk_mgr_dce->dprefclk_ss_percentage = info.spread_spectrum_percentage; } - if (clk_mgr_dce->base.ctx->dc->debug.ignore_dpref_ss) + if (clk_mgr_dce->base.ctx->dc->config.ignore_dpref_ss) clk_mgr_dce->dprefclk_ss_percentage = 0; } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index edda572dc570..8be4c1970628 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params( struct integrated_info *bios_info, const DpmClocks_315_t *clock_table) { - int i, j; + int i; struct clk_bw_params *bw_params = clk_mgr->base.bw_params; - uint32_t max_dispclk = 0, max_dppclk = 0; - - j = -1; - - ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL); - - /* Find lowest DPM, FCLK is filled in reverse order*/ - - for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) { - if (clock_table->DfPstateTable[i].FClk != 0) { - j = i; - break; + uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0; + struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1]; + + max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); + max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); + max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled); + + /* Find highest fclk pstate */ + for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) { + if (clock_table->DfPstateTable[i].FClk > max_fclk) { + max_fclk = clock_table->DfPstateTable[i].FClk; + max_pstate = i; } } - if (j == -1) { - /* clock table is all 0s, just use our own hardcode */ - ASSERT(0); - return; - } - - bw_params->clk_table.num_entries = j + 1; - - /* dispclk and dppclk can be max at any voltage, same number of levels for both */ - if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS && - clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) { - max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); - max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); - } else { - ASSERT(0); - } + /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */ + for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) { + int j; + uint32_t min_fclk = clock_table->DfPstateTable[0].FClk; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { - int temp; + for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) { + if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i] + && clock_table->DfPstateTable[j].FClk < min_fclk) { + min_fclk = clock_table->DfPstateTable[j].FClk; + min_pstate = j; + } + } - bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk; - bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk; - bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage; + bw_params->clk_table.entries[i].fclk_mhz = min_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i]; + bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i]; + bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; + bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; bw_params->clk_table.entries[i].wck_ratio = 1; - temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].dcfclk_mhz = temp; - temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].socclk_mhz = temp; + }; + + /* Make sure to include at least one entry and highest pstate */ + if (max_pstate != min_pstate) { + bw_params->clk_table.entries[i].fclk_mhz = max_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage( + clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage); + bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage( + clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage); bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; + bw_params->clk_table.entries[i].wck_ratio = 1; + i++; } + bw_params->clk_table.num_entries = i; + + /* Include highest socclk */ + if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk) + bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk; + /* Set any 0 clocks to max default setting. Not an issue for + * power since we aren't doing switching in such case anyway + */ + for (i = 0; i < bw_params->clk_table.num_entries; i++) { + if (!bw_params->clk_table.entries[i].fclk_mhz) { + bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz; + bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz; + bw_params->clk_table.entries[i].voltage = def_max.voltage; + } + if (!bw_params->clk_table.entries[i].dcfclk_mhz) + bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz) + bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz; + if (!bw_params->clk_table.entries[i].dispclk_mhz) + bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz; + if (!bw_params->clk_table.entries[i].dppclk_mhz) + bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz; + } bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 880ffea2afc6..2600313fea57 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D #define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ #define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ #define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ -#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency -#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ +#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency +#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ #define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected #define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power #define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event @@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) return (dprefclk_get_mhz * 1000); } -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr) { int fclk_get_mhz = -1; if (clk_mgr->smu_present) { fclk_get_mhz = dcn315_smu_send_msg_with_param( clk_mgr, - VBIOSSMC_MSG_GetFclkFrequency, + VBIOSSMC_MSG_GetDtbclkFreq, 0); } return (fclk_get_mhz * 1000); } + +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) +{ + if (!clk_mgr->smu_present) + return; + + dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_SetDtbClk, + enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 66fa42f8dd18..5aa3275ac7d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -37,6 +37,7 @@ #define NUM_SOC_VOLTAGE_LEVELS 4 #define NUM_DF_PSTATE_LEVELS 4 + typedef struct { uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz) uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz) @@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr); +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 702d00ce7da4..3121dd2d2a91 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -686,8 +686,8 @@ void dcn316_clk_mgr_construct( clk_mgr->base.base.dprefclk_khz = dcn316_smu_get_dpref_clk(&clk_mgr->base); clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz; dce_clock_read_ss_info(&clk_mgr->base); - clk_mgr->base.dccg->ref_dtbclk_khz = - dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz); + /*clk_mgr->base.dccg->ref_dtbclk_khz = + dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);*/ clk_mgr->base.base.bw_params = &dcn316_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f6e19efea756..c436db416708 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->mst_bw_update) su_flags->bits.mst_bw = 1; + if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc)) + su_flags->bits.crtc_timing_adjust = 1; if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_infopacket) stream->vrr_infopacket = *update->vrr_infopacket; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause) pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst); } +/* + * dc_extended_blank_supported: Decide whether extended blank is supported + * + * Extended blank is a freesync optimization feature to be enabled in the future. + * During the extra vblank period gained from freesync, we have the ability to enter z9/z10. + * + * @param [in] dc: Current DC state + * @return: Indicate whether extended blank is supported (true or false) + */ +bool dc_extended_blank_supported(struct dc *dc) +{ + return dc->debug.extended_blank_optimization && !dc->debug.disable_z10 + && dc->caps.zstate_support && dc->caps.is_apu; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index cb87dd643180..bbaa5abdf888 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) - destrictive = true; + } return destrictive; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 351081f574cb..22dabe596dfc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link) &link->dpcd_caps.cable_id, &usbc_cable_id); } +/* DPRX may take some time to respond to AUX messages after HPD asserted. + * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600). + */ +static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms) +{ + enum dc_status status = DC_ERROR_UNEXPECTED; + uint8_t dpcd_data = 0; + uint64_t start_ts = 0; + uint64_t current_ts = 0; + uint64_t time_taken_ms = 0; + enum dc_connection_type type = dc_connection_none; + + status = core_link_read_dpcd( + link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + &dpcd_data, + sizeof(dpcd_data)); + + if (status != DC_OK) { + DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.", + __func__, + timeout_ms); + start_ts = dm_get_timestamp(link->ctx); + + do { + if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) + break; + + dpcd_data = DP_SET_POWER_D3; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + dpcd_data = DP_SET_POWER_D0; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + current_ts = dm_get_timestamp(link->ctx); + time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000); + } while (status != DC_OK && time_taken_ms < timeout_ms); + + DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s", + __func__, + (status == DC_OK) ? "succeeded" : "failed", + time_taken_ms, + (type == dc_connection_none) ? ". Unplugged." : "."); + } + + return status; +} + static bool retrieve_link_cap(struct dc_link *link) { /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, @@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + /* Try to ensure AUX channel active before proceeding. */ + if (link->dc->debug.aux_wake_wa.bits.enable_wa) { + uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms; + + if (link->dc->debug.aux_wake_wa.bits.use_default_timeout) + timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS; + status = wa_try_to_wake_dprx(link, timeout_ms); + } + is_lttpr_present = dp_retrieve_lttpr_cap(link); /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7af153434e9e..d251c3f3a714 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; - // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks - if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + /*compare audio info*/ + if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4ffab7bb1098..9e79f60e6129 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -188,6 +188,7 @@ struct dc_caps { bool psp_setup_panel_mode; bool extended_aux_timeout_support; bool dmcub_support; + bool zstate_support; uint32_t num_of_internal_disp; enum dp_protocol_version max_dp_protocol_version; unsigned int mall_size_per_mem_channel; @@ -339,6 +340,7 @@ struct dc_config { bool is_asymmetric_memory; bool is_single_rank_dimm; bool use_pipe_ctx_sync_logic; + bool ignore_dpref_ss; }; enum visual_confirm { @@ -525,6 +527,22 @@ union dpia_debug_options { uint32_t raw; }; +/* AUX wake work around options + * 0: enable/disable work around + * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS + * 15-2: reserved + * 31-16: timeout in ms + */ +union aux_wake_wa_options { + struct { + uint32_t enable_wa : 1; + uint32_t use_default_timeout : 1; + uint32_t rsvd: 14; + uint32_t timeout_ms : 16; + } bits; + uint32_t raw; +}; + struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; @@ -703,14 +721,15 @@ struct dc_debug_options { bool enable_driver_sequence_debug; enum det_size crb_alloc_policy; int crb_alloc_policy_min_disp_count; -#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; +#if defined(CONFIG_DRM_AMD_DC_DCN) bool enable_z9_disable_interface; bool enable_sw_cntl_psr; union dpia_debug_options dpia_debug; #endif bool apply_vendor_specific_lttpr_wa; - bool ignore_dpref_ss; + bool extended_blank_optimization; + union aux_wake_wa_options aux_wake_wa; uint8_t psr_power_use_phy_fsm; }; @@ -1369,6 +1388,8 @@ struct dc_sink_init_data { bool converter_disable_audio; }; +bool dc_extended_blank_supported(struct dc *dc); + struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params); /* Newer interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 99a750f561f8..c4168c11257c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -131,6 +131,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; } bits; uint32_t raw; @@ -289,6 +290,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index c3e141c19a77..83fbea2df410 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc) link->link_status.link_active = true; } - /* Power gate DSCs */ - if (!is_optimized_init_done) { - for (i = 0; i < res_pool->res_cap->num_dsc; i++) - if (hws->funcs.dsc_pg_control != NULL) - hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); - } - /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (dc->clk_mgr->funcs->notify_wm_ranges) dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); @@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, { struct dc_context *dc_ctx = dc->ctx; int i, master = -1, embedded = -1; - struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0}; + struct dc_crtc_timing *hw_crtc_timing; uint64_t phase[MAX_PIPES]; uint64_t modulo[MAX_PIPES]; unsigned int pclk; @@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, uint32_t dp_ref_clk_100hz = dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10; + hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL); + if (!hw_crtc_timing) + return master; + if (dc->config.vblank_alignment_dto_params && dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) { embedded_h_total = @@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, } } + + kfree(hw_crtc_timing); return master; } @@ -2522,14 +2522,18 @@ void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else 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 ab910deed481..b627c41713cc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth( struct dc_state *context) { struct hubbub *hubbub = dc->res_pool->hubbub; + int i; /* program dchubbub watermarks */ hubbub->funcs->program_watermarks(hubbub, @@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); + if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) { + for (i = 0; i < dc->res_pool->pipe_count; ++i) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank + && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max + && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total) + pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp, + pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); + } + } /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); @@ -2332,14 +2344,18 @@ void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d473708d5399..7802d603f796 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags( /*If need split for odm but 4 way split already*/ if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe) || !pipe->next_odm_pipe)) { - ASSERT(0); /* NOT expected yet */ merge[i] = true; /* 4 -> 2 ODM */ } else if (split[i] == 0 && pipe->prev_odm_pipe) { ASSERT(0); /* NOT expected yet */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 612732656772..3fe4bfbb98a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index ed0a0e5fd805..f61ec8763844 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 3e6d6ebd199e..51c5f3685470 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31, hubbub31->detile_buf_size = det_size_kb * 1024; hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024; hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB; + + hubbub31->debug_test_index_pstate = 0x6; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 53b792b997b7..8ae6117953ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset); } +void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized); +} + static struct hubp_funcs dcn31_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, @@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, .hubp_in_blank = hubp1_in_blank, + .program_extended_blank = hubp31_program_extended_blank, }; bool hubp31_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 4be228680909..631d8ac63aa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); @@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane( bool enable) { bool force_on = true; /* disable power gating */ + uint32_t org_ip_request_cntl = 0; if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate) force_on = false; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); /* DPP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); force_on = true; /* disable power gating */ if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) @@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane( /* DCS0/1/2/3/4/5 */ REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); } void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 8afe2130d7c5..e05527a3a8ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc) static bool optc31_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line * in the vertical blank region */ @@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); + optc1_clear_optc_underflow(optc); return true; } @@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc) OTG_BUSY, 0, 1, 100000); + /* clear the false state */ + optc1_clear_optc_underflow(optc); + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 89b7b6b7254a..63934ecf6be8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); // Disable fast_validate to set min dcfclk in alculate_wm_and_dlg if (pipe_cnt == 0) @@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct( dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; dc->caps.is_apu = true; + dc->caps.zstate_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2f6122153bdb..f93af45aeab4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; + unsigned int optimized_min_dst_y_next_start_us; plane_count = 0; + optimized_min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + if (dc_extended_blank_supported(dc)) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream == context->streams[0] + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) { + optimized_min_dst_y_next_start_us = + context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us; + break; + } + } + } /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ if (link->link_index != 0 || stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; @@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) @@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params( &pipes[pipe_idx].pipe); pipe_idx++; } + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); } static void swizzle_to_dml_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index e0fecf127bd5..53d760e169e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params( float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA + int blank_lines; memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs)); memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs)); @@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params( dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start; disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2)); + blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1); + if (blank_lines < 0) + blank_lines = 0; + if (blank_lines != 0) { + disp_dlg_regs->optimized_min_dst_y_next_start_us = + ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz; + disp_dlg_regs->optimized_min_dst_y_next_start = + (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2)); + } else { + // use unoptimized value + disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; + } ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18)); dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 59f0a61c33cf..2df660cd8801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st { unsigned int refcyc_h_blank_end; unsigned int dlg_vblank_end; unsigned int min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start_us; unsigned int refcyc_per_htotal; unsigned int refcyc_x_after_scaler; unsigned int dst_y_after_scaler; diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index efc2339f1fa0..4385d19bc489 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -864,11 +864,11 @@ static bool setup_dsc_config( min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h); } + is_dsc_possible = (min_slices_h <= max_slices_h); + if (pic_width % min_slices_h != 0) min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first? - is_dsc_possible = (min_slices_h <= max_slices_h); - if (min_slices_h == 0 && max_slices_h == 0) is_dsc_possible = false; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index ab9939db8cea..44f167d2584f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -33,6 +33,7 @@ #define MAX_MTP_SLOT_COUNT 64 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #define TRAINING_AUX_RD_INTERVAL 100 //us +#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX. struct dc_link; struct dc_stream_state; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index e45b7993c5c5..ad69d78c4ac3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,9 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*program_extended_blank)(struct hubp *hubp, + unsigned int min_dst_y_next_start_optimized); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index b691aa45e84f..79bc207415bc 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -100,7 +100,8 @@ enum vsc_packet_revision { //PB7 = MD0 #define MASK_VTEM_MD0__VRR_EN 0x01 #define MASK_VTEM_MD0__M_CONST 0x02 -#define MASK_VTEM_MD0__RESERVED2 0x0C +#define MASK_VTEM_MD0__QMS_EN 0x04 +#define MASK_VTEM_MD0__RESERVED2 0x08 #define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0 //MD1 @@ -109,7 +110,7 @@ enum vsc_packet_revision { //MD2 #define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03 #define MASK_VTEM_MD2__RB 0x04 -#define MASK_VTEM_MD2__RESERVED3 0xF8 +#define MASK_VTEM_MD2__NEXT_TFR 0xF8 //MD3 #define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 89fbee568be4..5504d81c77b7 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) if (!pp_funcs || !pp_funcs->get_asic_baco_capability) return false; + /* Don't use baco for reset in S3. + * This is a workaround for some platforms + * where entering BACO during suspend + * seems to cause reboots or hangs. + * This might be related to the fact that BACO controls + * power to the whole GPU including devices like audio and USB. + * Powering down/up everything may adversely affect these other + * devices. Needs more investigation. + */ + if (adev->in_s3) + return false; mutex_lock(&adev->pm.mutex); @@ -500,6 +511,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_pages_num(smu, size); mutex_unlock(&adev->pm.mutex); @@ -512,6 +526,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_channel_flag(smu, size); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ddd8491ff00..ede71de2343d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : + (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 7bfac029e513..b81711c4ff33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu, return -EINVAL; } - if (sclk_min && sclk_max) { + if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) { ret = smu_v13_0_5_set_soft_freq_limited_range(smu, SMU_SCLK, sclk_min, diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 026e4e29a0f3..f4df344509a8 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -214,6 +214,29 @@ int drm_of_encoder_active_endpoint(struct device_node *node, } EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint); +static int find_panel_or_bridge(struct device_node *node, + struct drm_panel **panel, + struct drm_bridge **bridge) +{ + if (panel) { + *panel = of_drm_find_panel(node); + if (!IS_ERR(*panel)) + return 0; + + /* Clear the panel pointer in case of error. */ + *panel = NULL; + } + + /* No panel found yet, check for a bridge next. */ + if (bridge) { + *bridge = of_drm_find_bridge(node); + if (*bridge) + return 0; + } + + return -EPROBE_DEFER; +} + /** * drm_of_find_panel_or_bridge - return connected panel or bridge device * @np: device tree node containing encoder output ports @@ -236,66 +259,44 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, struct drm_panel **panel, struct drm_bridge **bridge) { - int ret = -EPROBE_DEFER; - struct device_node *remote; + struct device_node *node; + int ret; if (!panel && !bridge) return -EINVAL; + if (panel) *panel = NULL; - - /** - * Devices can also be child nodes when we also control that device - * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device). - * - * Lookup for a child node of the given parent that isn't either port - * or ports. - */ - for_each_available_child_of_node(np, remote) { - if (of_node_name_eq(remote, "port") || - of_node_name_eq(remote, "ports")) - continue; - - goto of_find_panel_or_bridge; + if (bridge) + *bridge = NULL; + + /* Check for a graph on the device node first. */ + if (of_graph_is_present(np)) { + node = of_graph_get_remote_node(np, port, endpoint); + if (node) { + ret = find_panel_or_bridge(node, panel, bridge); + of_node_put(node); + + if (!ret) + return 0; + } } - /* - * of_graph_get_remote_node() produces a noisy error message if port - * node isn't found and the absence of the port is a legit case here, - * so at first we silently check whether graph presents in the - * device-tree node. - */ - if (!of_graph_is_present(np)) - return -ENODEV; - - remote = of_graph_get_remote_node(np, port, endpoint); - -of_find_panel_or_bridge: - if (!remote) - return -ENODEV; + /* Otherwise check for any child node other than port/ports. */ + for_each_available_child_of_node(np, node) { + if (of_node_name_eq(node, "port") || + of_node_name_eq(node, "ports")) + continue; - if (panel) { - *panel = of_drm_find_panel(remote); - if (!IS_ERR(*panel)) - ret = 0; - else - *panel = NULL; - } - - /* No panel found yet, check for a bridge next. */ - if (bridge) { - if (ret) { - *bridge = of_drm_find_bridge(remote); - if (*bridge) - ret = 0; - } else { - *bridge = NULL; - } + ret = find_panel_or_bridge(node, panel, bridge); + of_node_put(node); + /* Stop at the first found occurrence. */ + if (!ret) + return 0; } - of_node_put(remote); - return ret; + return -EPROBE_DEFER; } EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index c3ea243d414d..0c5c43852e24 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -70,7 +70,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, * mmap ioctl is disallowed for all discrete platforms, * and for all platforms with GRAPHICS_VER > 12. */ - if (IS_DGFX(i915) || GRAPHICS_VER(i915) > 12) + if (IS_DGFX(i915) || GRAPHICS_VER_FULL(i915) > IP_VER(12, 0)) return -EOPNOTSUPP; if (args->flags & ~(I915_MMAP_WC)) diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 87428fb23d9f..a2277a0d6d06 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np); struct imx_hdmi *hdmi; + int ret; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); if (!hdmi) @@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) hdmi->bridge = of_drm_find_bridge(np); if (!hdmi->bridge) { dev_err(hdmi->dev, "Unable to find bridge\n"); + dw_hdmi_remove(hdmi->hdmi); return -ENODEV; } - return component_add(&pdev->dev, &dw_hdmi_imx_ops); + ret = component_add(&pdev->dev, &dw_hdmi_imx_ops); + if (ret) + dw_hdmi_remove(hdmi->hdmi); + + return ret; } static int dw_hdmi_imx_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index e5078d03020d..fb0e951248f6 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -572,6 +572,8 @@ static int imx_ldb_panel_ddc(struct device *dev, edidp = of_get_property(child, "edid", &edid_len); if (edidp) { channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); + if (!channel->edid) + return -ENOMEM; } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06cb1a59b9bc..63ba2ad84679 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); - if (ret) + if (ret) { + drm_mode_destroy(connector->dev, mode); return ret; + } drm_mode_copy(mode, &imxpd->mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 83c31b2ad865..ccc4fcf7a630 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1742,7 +1742,7 @@ a6xx_create_private_address_space(struct msm_gpu *gpu) return ERR_CAST(mmu); return msm_gem_address_space_create(mmu, - "gpu", 0x100000000ULL, 0x1ffffffffULL); + "gpu", 0x100000000ULL, SZ_4G); } static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 89cfd84760d7..8706bcdd1472 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -599,43 +599,91 @@ static const struct of_device_id dt_match[] = { {} }; -#ifdef CONFIG_PM -static int adreno_resume(struct device *dev) +static int adreno_runtime_resume(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); return gpu->funcs->pm_resume(gpu); } -static int active_submits(struct msm_gpu *gpu) +static int adreno_runtime_suspend(struct device *dev) { - int active_submits; - mutex_lock(&gpu->active_lock); - active_submits = gpu->active_submits; - mutex_unlock(&gpu->active_lock); - return active_submits; + struct msm_gpu *gpu = dev_to_gpu(dev); + + /* + * We should be holding a runpm ref, which will prevent + * runtime suspend. In the system suspend path, we've + * already waited for active jobs to complete. + */ + WARN_ON_ONCE(gpu->active_submits); + + return gpu->funcs->pm_suspend(gpu); +} + +static void suspend_scheduler(struct msm_gpu *gpu) +{ + int i; + + /* + * Shut down the scheduler before we force suspend, so that + * suspend isn't racing with scheduler kthread feeding us + * more work. + * + * Note, we just want to park the thread, and let any jobs + * that are already on the hw queue complete normally, as + * opposed to the drm_sched_stop() path used for handling + * faulting/timed-out jobs. We can't really cancel any jobs + * already on the hw queue without racing with the GPU. + */ + for (i = 0; i < gpu->nr_rings; i++) { + struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched; + kthread_park(sched->thread); + } } -static int adreno_suspend(struct device *dev) +static void resume_scheduler(struct msm_gpu *gpu) +{ + int i; + + for (i = 0; i < gpu->nr_rings; i++) { + struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched; + kthread_unpark(sched->thread); + } +} + +static int adreno_system_suspend(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); - int remaining; + int remaining, ret; + + suspend_scheduler(gpu); remaining = wait_event_timeout(gpu->retire_event, - active_submits(gpu) == 0, + gpu->active_submits == 0, msecs_to_jiffies(1000)); if (remaining == 0) { dev_err(dev, "Timeout waiting for GPU to suspend\n"); - return -EBUSY; + ret = -EBUSY; + goto out; } - return gpu->funcs->pm_suspend(gpu); + ret = pm_runtime_force_suspend(dev); +out: + if (ret) + resume_scheduler(gpu); + + return ret; +} + +static int adreno_system_resume(struct device *dev) +{ + resume_scheduler(dev_to_gpu(dev)); + return pm_runtime_force_resume(dev); } -#endif static const struct dev_pm_ops adreno_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) - SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL) + SYSTEM_SLEEP_PM_OPS(adreno_system_suspend, adreno_system_resume) + RUNTIME_PM_OPS(adreno_runtime_suspend, adreno_runtime_resume, NULL) }; static struct platform_driver adreno_driver = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index c515b7cf922c..c61b5b283f08 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -54,87 +54,87 @@ struct dpu_intr_reg { * When making changes be sure to sync with dpu_hw_intr_reg */ static const struct dpu_intr_reg dpu_intr_set[] = { - { + [MDP_SSPP_TOP0_INTR] = { MDP_SSPP_TOP0_OFF+INTR_CLEAR, MDP_SSPP_TOP0_OFF+INTR_EN, MDP_SSPP_TOP0_OFF+INTR_STATUS }, - { + [MDP_SSPP_TOP0_INTR2] = { MDP_SSPP_TOP0_OFF+INTR2_CLEAR, MDP_SSPP_TOP0_OFF+INTR2_EN, MDP_SSPP_TOP0_OFF+INTR2_STATUS }, - { + [MDP_SSPP_TOP0_HIST_INTR] = { MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR, MDP_SSPP_TOP0_OFF+HIST_INTR_EN, MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS }, - { + [MDP_INTF0_INTR] = { MDP_INTF_0_OFF+INTF_INTR_CLEAR, MDP_INTF_0_OFF+INTF_INTR_EN, MDP_INTF_0_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF1_INTR] = { MDP_INTF_1_OFF+INTF_INTR_CLEAR, MDP_INTF_1_OFF+INTF_INTR_EN, MDP_INTF_1_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF2_INTR] = { MDP_INTF_2_OFF+INTF_INTR_CLEAR, MDP_INTF_2_OFF+INTF_INTR_EN, MDP_INTF_2_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF3_INTR] = { MDP_INTF_3_OFF+INTF_INTR_CLEAR, MDP_INTF_3_OFF+INTF_INTR_EN, MDP_INTF_3_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF4_INTR] = { MDP_INTF_4_OFF+INTF_INTR_CLEAR, MDP_INTF_4_OFF+INTF_INTR_EN, MDP_INTF_4_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF5_INTR] = { MDP_INTF_5_OFF+INTF_INTR_CLEAR, MDP_INTF_5_OFF+INTF_INTR_EN, MDP_INTF_5_OFF+INTF_INTR_STATUS }, - { + [MDP_AD4_0_INTR] = { MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF, }, - { + [MDP_AD4_1_INTR] = { MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF, }, - { + [MDP_INTF0_7xxx_INTR] = { MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF1_7xxx_INTR] = { MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF2_7xxx_INTR] = { MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF3_7xxx_INTR] = { MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF4_7xxx_INTR] = { MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF5_7xxx_INTR] = { MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_STATUS diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index 1ee824600995..c478d25f7825 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -98,7 +98,10 @@ static void mdp5_plane_reset(struct drm_plane *plane) __drm_atomic_helper_plane_destroy_state(plane->state); kfree(to_mdp5_plane_state(plane->state)); + plane->state = NULL; mdp5_state = kzalloc(sizeof(*mdp5_state), GFP_KERNEL); + if (!mdp5_state) + return; __drm_atomic_helper_plane_reset(plane, &mdp5_state->base); } diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index 5d2ff6791058..acfe1b31e079 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -176,6 +176,8 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len, va_list va; new_blk = kzalloc(sizeof(struct msm_disp_state_block), GFP_KERNEL); + if (!new_blk) + return; va_start(va, fmt); diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 178b774a5fbd..a42732b67349 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -580,6 +580,12 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) dp->dp_display.connector_type, state); mutex_unlock(&dp->event_mutex); + /* + * add fail safe mode outside event_mutex scope + * to avoid potiential circular lock with drm thread + */ + dp_panel_add_fail_safe_mode(dp->dp_display.connector); + /* uevent will complete connection part */ return 0; }; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index f1418722c549..26c3653c99ec 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -151,6 +151,15 @@ static int dp_panel_update_modes(struct drm_connector *connector, return rc; } +void dp_panel_add_fail_safe_mode(struct drm_connector *connector) +{ + /* fail safe edid */ + mutex_lock(&connector->dev->mode_config.mutex); + if (drm_add_modes_noedid(connector, 640, 480)) + drm_set_preferred_mode(connector, 640, 480); + mutex_unlock(&connector->dev->mode_config.mutex); +} + int dp_panel_read_sink_caps(struct dp_panel *dp_panel, struct drm_connector *connector) { @@ -207,16 +216,7 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel, goto end; } - /* fail safe edid */ - mutex_lock(&connector->dev->mode_config.mutex); - if (drm_add_modes_noedid(connector, 640, 480)) - drm_set_preferred_mode(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); - } else { - /* always add fail-safe mode as backup mode */ - mutex_lock(&connector->dev->mode_config.mutex); - drm_add_modes_noedid(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); + dp_panel_add_fail_safe_mode(connector); } if (panel->aux_cfg_update_done) { diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index 9023e5bb4b8b..99739ea679a7 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -59,6 +59,7 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel); int dp_panel_deinit(struct dp_panel *dp_panel); int dp_panel_timing_cfg(struct dp_panel *dp_panel); void dp_panel_dump_regs(struct dp_panel *dp_panel); +void dp_panel_add_fail_safe_mode(struct drm_connector *connector); int dp_panel_read_sink_caps(struct dp_panel *dp_panel, struct drm_connector *connector); u32 dp_panel_get_mode_bpp(struct dp_panel *dp_panel, u32 mode_max_bpp, diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 0c1b7dde377c..9f6af0f0fe00 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -638,7 +638,7 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id) return connector; fail: - connector->funcs->destroy(msm_dsi->connector); + connector->funcs->destroy(connector); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index affa95eb05fc..9c36b505daab 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -274,7 +274,7 @@ bool msm_use_mmu(struct drm_device *dev) struct msm_drm_private *priv = dev->dev_private; /* a2xx comes with its own MMU */ - return priv->is_a2xx || iommu_present(&platform_bus_type); + return priv->is_a2xx || device_iommu_mapped(dev->dev); } static int msm_init_vram(struct drm_device *dev) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 02b9ae65a96a..a4f61972667b 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -926,6 +926,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, get_pid_task(aspace->pid, PIDTYPE_PID); if (task) { comm = kstrdup(task->comm, GFP_KERNEL); + put_task_struct(task); } else { comm = NULL; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index e1772211b0a4..612310d5d481 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -216,6 +216,7 @@ gm20b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gf100_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c index 6bf7fc1bd1e3..1a6f9c3af5ec 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c @@ -23,7 +23,7 @@ */ #include "priv.h" -static void +void gp102_pmu_reset(struct nvkm_pmu *pmu) { struct nvkm_device *device = pmu->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c index ba1583bb618b..94cfb1791af6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -83,6 +83,7 @@ gp10b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gp102_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h index bcaade758ff7..21abf31f4442 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h @@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32); bool gf100_pmu_enabled(struct nvkm_pmu *); void gf100_pmu_reset(struct nvkm_pmu *); +void gp102_pmu_reset(struct nvkm_pmu *pmu); void gk110_pmu_pgob(struct nvkm_pmu *, bool); diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index a07ef26234e5..6826f4d4826a 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc, int ret; vcc = devm_regulator_get_optional(dev, "vcc"); - if (IS_ERR(vcc)) + if (IS_ERR(vcc)) { dev_err(dev, "get optional vcc failed\n"); + vcc = NULL; + } dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver, struct mipi_dbi_dev, drm); diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c index 666223c6bec4..0a34e0ab4fe6 100644 --- a/drivers/gpu/ipu-v3/ipu-di.c +++ b/drivers/gpu/ipu-v3/ipu-di.c @@ -447,8 +447,9 @@ static void ipu_di_config_clock(struct ipu_di *di, error = rate / (sig->mode.pixelclock / 1000); - dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %d.%u%%\n", - rate, div, (signed)(error - 1000) / 10, error % 10); + dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %c%d.%d%%\n", + rate, div, error < 1000 ? '-' : '+', + abs(error - 1000) / 10, abs(error - 1000) % 10); /* Allow a 1% error */ if (error < 1010 && error >= 990) { diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 7a674873d794..a95a7cbc4a59 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -405,14 +405,25 @@ config HOLTEK_FF Say Y here if you have a Holtek On Line Grip based game controller and want to have force feedback support for it. +config HID_VIVALDI_COMMON + tristate + help + ChromeOS Vivaldi HID parsing support library. This is a hidden + option so that drivers can use common code to parse the HID + descriptors for vivaldi function row keymap. + config HID_GOOGLE_HAMMER tristate "Google Hammer Keyboard" + select HID_VIVALDI_COMMON + select INPUT_VIVALDIFMAP depends on USB_HID && LEDS_CLASS && CROS_EC help Say Y here if you have a Google Hammer device. config HID_VIVALDI tristate "Vivaldi Keyboard" + select HID_VIVALDI_COMMON + select INPUT_VIVALDIFMAP depends on HID help Say Y here if you want to enable support for Vivaldi keyboards. diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index d5ce8d747b14..345ac5581bd8 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -50,6 +50,7 @@ obj-$(CONFIG_HID_FT260) += hid-ft260.o obj-$(CONFIG_HID_GEMBIRD) += hid-gembird.o obj-$(CONFIG_HID_GFRM) += hid-gfrm.o obj-$(CONFIG_HID_GLORIOUS) += hid-glorious.o +obj-$(CONFIG_HID_VIVALDI_COMMON) += hid-vivaldi-common.o obj-$(CONFIG_HID_GOOGLE_HAMMER) += hid-google-hammer.o obj-$(CONFIG_HID_VIVALDI) += hid-vivaldi.o obj-$(CONFIG_HID_GT683R) += hid-gt683r.o diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index ddbe0de177e2..ff40f1e55c21 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -15,6 +15,7 @@ #include <linux/acpi.h> #include <linux/hid.h> +#include <linux/input/vivaldi-fmap.h> #include <linux/leds.h> #include <linux/module.h> #include <linux/of.h> @@ -25,6 +26,7 @@ #include <asm/unaligned.h> #include "hid-ids.h" +#include "hid-vivaldi-common.h" /* * C(hrome)B(ase)A(ttached)S(witch) - switch exported by Chrome EC and reporting @@ -340,9 +342,9 @@ static int hammer_kbd_brightness_set_blocking(struct led_classdev *cdev, static int hammer_register_leds(struct hid_device *hdev) { struct hammer_kbd_leds *kbd_backlight; - int error; - kbd_backlight = kzalloc(sizeof(*kbd_backlight), GFP_KERNEL); + kbd_backlight = devm_kzalloc(&hdev->dev, sizeof(*kbd_backlight), + GFP_KERNEL); if (!kbd_backlight) return -ENOMEM; @@ -356,26 +358,7 @@ static int hammer_register_leds(struct hid_device *hdev) /* Set backlight to 0% initially. */ hammer_kbd_brightness_set_blocking(&kbd_backlight->cdev, 0); - error = led_classdev_register(&hdev->dev, &kbd_backlight->cdev); - if (error) - goto err_free_mem; - - hid_set_drvdata(hdev, kbd_backlight); - return 0; - -err_free_mem: - kfree(kbd_backlight); - return error; -} - -static void hammer_unregister_leds(struct hid_device *hdev) -{ - struct hammer_kbd_leds *kbd_backlight = hid_get_drvdata(hdev); - - if (kbd_backlight) { - led_classdev_unregister(&kbd_backlight->cdev); - kfree(kbd_backlight); - } + return devm_led_classdev_register(&hdev->dev, &kbd_backlight->cdev); } #define HID_UP_GOOGLEVENDOR 0xffd10000 @@ -512,11 +495,23 @@ out: kfree(buf); } +static void hammer_stop(void *hdev) +{ + hid_hw_stop(hdev); +} + static int hammer_probe(struct hid_device *hdev, const struct hid_device_id *id) { + struct vivaldi_data *vdata; int error; + vdata = devm_kzalloc(&hdev->dev, sizeof(*vdata), GFP_KERNEL); + if (!vdata) + return -ENOMEM; + + hid_set_drvdata(hdev, vdata); + error = hid_parse(hdev); if (error) return error; @@ -525,6 +520,10 @@ static int hammer_probe(struct hid_device *hdev, if (error) return error; + error = devm_add_action(&hdev->dev, hammer_stop, hdev); + if (error) + return error; + /* * We always want to poll for, and handle tablet mode events from * devices that have folded usage, even when nobody has opened the input @@ -577,15 +576,13 @@ static void hammer_remove(struct hid_device *hdev) spin_unlock_irqrestore(&cbas_ec_lock, flags); } - hammer_unregister_leds(hdev); - - hid_hw_stop(hdev); + /* Unregistering LEDs and stopping the hardware is done via devm */ } static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) }, - { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + { HID_DEVICE(BUS_USB, HID_GROUP_VIVALDI, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_EEL) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, @@ -610,6 +607,8 @@ static struct hid_driver hammer_driver = { .id_table = hammer_devices, .probe = hammer_probe, .remove = hammer_remove, + .feature_mapping = vivaldi_feature_mapping, + .input_configured = vivaldi_input_configured, .input_mapping = hammer_input_mapping, .event = hammer_event, }; diff --git a/drivers/hid/hid-vivaldi-common.c b/drivers/hid/hid-vivaldi-common.c new file mode 100644 index 000000000000..8b3e515d0f06 --- /dev/null +++ b/drivers/hid/hid-vivaldi-common.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for ChromeOS HID Vivaldi keyboards + * + * Copyright (C) 2022 Google, Inc + */ + +#include <linux/export.h> +#include <linux/hid.h> +#include <linux/input/vivaldi-fmap.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/types.h> + +#include "hid-vivaldi-common.h" + +#define MIN_FN_ROW_KEY 1 +#define MAX_FN_ROW_KEY VIVALDI_MAX_FUNCTION_ROW_KEYS +#define HID_VD_FN_ROW_PHYSMAP 0x00000001 +#define HID_USAGE_FN_ROW_PHYSMAP (HID_UP_GOOGLEVENDOR | HID_VD_FN_ROW_PHYSMAP) + +/** + * vivaldi_feature_mapping - Fill out vivaldi keymap data exposed via HID + * @hdev: HID device to parse + * @field: HID field to parse + * @usage: HID usage to parse + * + * Note: this function assumes that driver data attached to @hdev contains an + * instance of &struct vivaldi_data at the very beginning. + */ +void vivaldi_feature_mapping(struct hid_device *hdev, + struct hid_field *field, struct hid_usage *usage) +{ + struct vivaldi_data *data = hid_get_drvdata(hdev); + struct hid_report *report = field->report; + u8 *report_data, *buf; + u32 report_len; + unsigned int fn_key; + int ret; + + if (field->logical != HID_USAGE_FN_ROW_PHYSMAP || + (usage->hid & HID_USAGE_PAGE) != HID_UP_ORDINAL) + return; + + fn_key = usage->hid & HID_USAGE; + if (fn_key < MIN_FN_ROW_KEY || fn_key > MAX_FN_ROW_KEY) + return; + + if (fn_key > data->num_function_row_keys) + data->num_function_row_keys = fn_key; + + report_data = buf = hid_alloc_report_buf(report, GFP_KERNEL); + if (!report_data) + return; + + report_len = hid_report_len(report); + if (!report->id) { + /* + * hid_hw_raw_request() will stuff report ID (which will be 0) + * into the first byte of the buffer even for unnumbered + * reports, so we need to account for this to avoid getting + * -EOVERFLOW in return. + * Note that hid_alloc_report_buf() adds 7 bytes to the size + * so we can safely say that we have space for an extra byte. + */ + report_len++; + } + + ret = hid_hw_raw_request(hdev, report->id, report_data, + report_len, HID_FEATURE_REPORT, + HID_REQ_GET_REPORT); + if (ret < 0) { + dev_warn(&hdev->dev, "failed to fetch feature %d\n", + field->report->id); + goto out; + } + + if (!report->id) { + /* + * Undo the damage from hid_hw_raw_request() for unnumbered + * reports. + */ + report_data++; + report_len--; + } + + ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, report_data, + report_len, 0); + if (ret) { + dev_warn(&hdev->dev, "failed to report feature %d\n", + field->report->id); + goto out; + } + + data->function_row_physmap[fn_key - MIN_FN_ROW_KEY] = + field->value[usage->usage_index]; + +out: + kfree(buf); +} +EXPORT_SYMBOL_GPL(vivaldi_feature_mapping); + +static ssize_t function_row_physmap_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hid_device *hdev = to_hid_device(dev); + struct vivaldi_data *data = hid_get_drvdata(hdev); + + return vivaldi_function_row_physmap_show(data, buf); +} + +static DEVICE_ATTR_RO(function_row_physmap); +static struct attribute *vivaldi_sysfs_attrs[] = { + &dev_attr_function_row_physmap.attr, + NULL +}; + +static const struct attribute_group vivaldi_attribute_group = { + .attrs = vivaldi_sysfs_attrs, +}; + +/** + * vivaldi_input_configured - Complete initialization of device using vivaldi map + * @hdev: HID device to which vivaldi attributes should be attached + * @hidinput: HID input device (unused) + */ +int vivaldi_input_configured(struct hid_device *hdev, + struct hid_input *hidinput) +{ + struct vivaldi_data *data = hid_get_drvdata(hdev); + + if (!data->num_function_row_keys) + return 0; + + return devm_device_add_group(&hdev->dev, &vivaldi_attribute_group); +} +EXPORT_SYMBOL_GPL(vivaldi_input_configured); + +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-vivaldi-common.h b/drivers/hid/hid-vivaldi-common.h new file mode 100644 index 000000000000..d42e82d77825 --- /dev/null +++ b/drivers/hid/hid-vivaldi-common.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _HID_VIVALDI_COMMON_H +#define _HID_VIVALDI_COMMON_H + +struct hid_device; +struct hid_field; +struct hid_input; +struct hid_usage; + +void vivaldi_feature_mapping(struct hid_device *hdev, + struct hid_field *field, struct hid_usage *usage); + +int vivaldi_input_configured(struct hid_device *hdev, + struct hid_input *hidinput); + +#endif /* _HID_VIVALDI_COMMON_H */ diff --git a/drivers/hid/hid-vivaldi.c b/drivers/hid/hid-vivaldi.c index 42ceb2058a09..3a979123e7d3 100644 --- a/drivers/hid/hid-vivaldi.c +++ b/drivers/hid/hid-vivaldi.c @@ -8,48 +8,11 @@ #include <linux/device.h> #include <linux/hid.h> +#include <linux/input/vivaldi-fmap.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/sysfs.h> -#define MIN_FN_ROW_KEY 1 -#define MAX_FN_ROW_KEY 24 -#define HID_VD_FN_ROW_PHYSMAP 0x00000001 -#define HID_USAGE_FN_ROW_PHYSMAP (HID_UP_GOOGLEVENDOR | HID_VD_FN_ROW_PHYSMAP) - -struct vivaldi_data { - u32 function_row_physmap[MAX_FN_ROW_KEY - MIN_FN_ROW_KEY + 1]; - int max_function_row_key; -}; - -static ssize_t function_row_physmap_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct hid_device *hdev = to_hid_device(dev); - struct vivaldi_data *drvdata = hid_get_drvdata(hdev); - ssize_t size = 0; - int i; - - if (!drvdata->max_function_row_key) - return 0; - - for (i = 0; i < drvdata->max_function_row_key; i++) - size += sprintf(buf + size, "%02X ", - drvdata->function_row_physmap[i]); - size += sprintf(buf + size, "\n"); - return size; -} - -static DEVICE_ATTR_RO(function_row_physmap); -static struct attribute *sysfs_attrs[] = { - &dev_attr_function_row_physmap.attr, - NULL -}; - -static const struct attribute_group input_attribute_group = { - .attrs = sysfs_attrs -}; +#include "hid-vivaldi-common.h" static int vivaldi_probe(struct hid_device *hdev, const struct hid_device_id *id) @@ -70,86 +33,8 @@ static int vivaldi_probe(struct hid_device *hdev, return hid_hw_start(hdev, HID_CONNECT_DEFAULT); } -static void vivaldi_feature_mapping(struct hid_device *hdev, - struct hid_field *field, - struct hid_usage *usage) -{ - struct vivaldi_data *drvdata = hid_get_drvdata(hdev); - struct hid_report *report = field->report; - int fn_key; - int ret; - u32 report_len; - u8 *report_data, *buf; - - if (field->logical != HID_USAGE_FN_ROW_PHYSMAP || - (usage->hid & HID_USAGE_PAGE) != HID_UP_ORDINAL) - return; - - fn_key = (usage->hid & HID_USAGE); - if (fn_key < MIN_FN_ROW_KEY || fn_key > MAX_FN_ROW_KEY) - return; - if (fn_key > drvdata->max_function_row_key) - drvdata->max_function_row_key = fn_key; - - report_data = buf = hid_alloc_report_buf(report, GFP_KERNEL); - if (!report_data) - return; - - report_len = hid_report_len(report); - if (!report->id) { - /* - * hid_hw_raw_request() will stuff report ID (which will be 0) - * into the first byte of the buffer even for unnumbered - * reports, so we need to account for this to avoid getting - * -EOVERFLOW in return. - * Note that hid_alloc_report_buf() adds 7 bytes to the size - * so we can safely say that we have space for an extra byte. - */ - report_len++; - } - - ret = hid_hw_raw_request(hdev, report->id, report_data, - report_len, HID_FEATURE_REPORT, - HID_REQ_GET_REPORT); - if (ret < 0) { - dev_warn(&hdev->dev, "failed to fetch feature %d\n", - field->report->id); - goto out; - } - - if (!report->id) { - /* - * Undo the damage from hid_hw_raw_request() for unnumbered - * reports. - */ - report_data++; - report_len--; - } - - ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, report_data, - report_len, 0); - if (ret) { - dev_warn(&hdev->dev, "failed to report feature %d\n", - field->report->id); - goto out; - } - - drvdata->function_row_physmap[fn_key - MIN_FN_ROW_KEY] = - field->value[usage->usage_index]; - -out: - kfree(buf); -} - -static int vivaldi_input_configured(struct hid_device *hdev, - struct hid_input *hidinput) -{ - return devm_device_add_group(&hdev->dev, &input_attribute_group); -} - static const struct hid_device_id vivaldi_table[] = { - { HID_DEVICE(HID_BUS_ANY, HID_GROUP_VIVALDI, HID_ANY_ID, - HID_ANY_ID) }, + { HID_DEVICE(HID_BUS_ANY, HID_GROUP_VIVALDI, HID_ANY_ID, HID_ANY_ID) }, { } }; diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 26d269ba947c..85a2142c9384 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * execute: * * (a) In the "normal (i.e., not resuming from hibernation)" path, - * the full barrier in smp_store_mb() guarantees that the store + * the full barrier in virt_store_mb() guarantees that the store * is propagated to all CPUs before the add_channel_work work * is queued. In turn, add_channel_work is queued before the * channel's ring buffer is allocated/initialized and the @@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * recv_int_page before retrieving the channel pointer from the * array of channels. * - * (b) In the "resuming from hibernation" path, the smp_store_mb() + * (b) In the "resuming from hibernation" path, the virt_store_mb() * guarantees that the store is propagated to all CPUs before * the VMBus connection is marked as ready for the resume event * (cf. check_ready_for_resume_event()). The interrupt handler * of the VMBus driver and vmbus_chan_sched() can not run before * vmbus_bus_resume() has completed execution (cf. resume_noirq). */ - smp_store_mb( + virt_store_mb( vmbus_connection.channels[channel->offermsg.child_relid], channel); } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 439f99b8b5de..3248b48f37f6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/kthread.h> #include <linux/completion.h> +#include <linux/count_zeros.h> #include <linux/memory_hotplug.h> #include <linux/memory.h> #include <linux/notifier.h> @@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm) struct dm_status status; unsigned long now = jiffies; unsigned long last_post = last_post_time; + unsigned long num_pages_avail, num_pages_committed; if (pressure_report_delay > 0) { --pressure_report_delay; @@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm) * num_pages_onlined) as committed to the host, otherwise it can try * asking us to balloon them out. */ - status.num_avail = si_mem_available(); - status.num_committed = vm_memory_committed() + + num_pages_avail = si_mem_available(); + num_pages_committed = vm_memory_committed() + dm->num_pages_ballooned + (dm->num_pages_added > dm->num_pages_onlined ? dm->num_pages_added - dm->num_pages_onlined : 0) + compute_balloon_floor(); - trace_balloon_status(status.num_avail, status.num_committed, + trace_balloon_status(num_pages_avail, num_pages_committed, vm_memory_committed(), dm->num_pages_ballooned, dm->num_pages_added, dm->num_pages_onlined); + + /* Convert numbers of pages into numbers of HV_HYP_PAGEs. */ + status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE; + status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE; + /* * If our transaction ID is no longer current, just don't * send the status. This can happen if we were interrupted @@ -1653,6 +1660,38 @@ static void disable_page_reporting(void) } } +static int ballooning_enabled(void) +{ + /* + * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE), + * since currently it's unclear to us whether an unballoon request can + * make sure all page ranges are guest page size aligned. + */ + if (PAGE_SIZE != HV_HYP_PAGE_SIZE) { + pr_info("Ballooning disabled because page size is not 4096 bytes\n"); + return 0; + } + + return 1; +} + +static int hot_add_enabled(void) +{ + /* + * Disable hot add on ARM64, because we currently rely on + * memory_add_physaddr_to_nid() to get a node id of a hot add range, + * however ARM64's memory_add_physaddr_to_nid() always return 0 and + * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for + * add_memory(). + */ + if (IS_ENABLED(CONFIG_ARM64)) { + pr_info("Memory hot add disabled on ARM64\n"); + return 0; + } + + return 1; +} + static int balloon_connect_vsp(struct hv_device *dev) { struct dm_version_request version_req; @@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev) * currently still requires the bits to be set, so we have to add code * to fail the host's hot-add and balloon up/down requests, if any. */ - cap_msg.caps.cap_bits.balloon = 1; - cap_msg.caps.cap_bits.hot_add = 1; + cap_msg.caps.cap_bits.balloon = ballooning_enabled(); + cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* * Specify our alignment requirements as it relates diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index c1dd21d0d7ef..ae68298c0dca 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,6 +20,7 @@ #include <linux/panic_notifier.h> #include <linux/ptrace.h> #include <linux/slab.h> +#include <linux/dma-map-ops.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query) } EXPORT_SYMBOL_GPL(hv_query_ext_cap); +void hv_setup_dma_ops(struct device *dev, bool coherent) +{ + /* + * Hyper-V does not offer a vIOMMU in the guest + * VM, so pass 0/NULL for the IOMMU settings + */ + arch_setup_dma_ops(dev, 0, 0, NULL, coherent); +} +EXPORT_SYMBOL_GPL(hv_setup_dma_ops); + bool hv_is_hibernation_supported(void) { return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 71efacb90965..3d215d9dec43 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) { u32 priv_read_loc = rbi->priv_read_index; - u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + u32 write_loc; + + /* + * The Hyper-V host writes the packet data, then uses + * store_release() to update the write_index. Use load_acquire() + * here to prevent loads of the packet data from being re-ordered + * before the read of the write_index and potentially getting + * stale data. + */ + write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 60ee8b329f9e..14de17087864 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE && hyperv_report_reg()) { @@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (hyperv_report_reg()) hyperv_report_panic(regs, val, true); @@ -921,6 +921,21 @@ static int vmbus_probe(struct device *child_device) } /* + * vmbus_dma_configure -- Configure DMA coherence for VMbus device + */ +static int vmbus_dma_configure(struct device *child_device) +{ + /* + * On ARM64, propagate the DMA coherence setting from the top level + * VMbus ACPI device to the child VMbus device being added here. + * On x86/x64 coherence is assumed and these calls have no effect. + */ + hv_setup_dma_ops(child_device, + device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + return 0; +} + +/* * vmbus_remove - Remove a vmbus device */ static void vmbus_remove(struct device *child_device) @@ -1040,6 +1055,7 @@ static struct bus_type hv_bus = { .remove = vmbus_remove, .probe = vmbus_probe, .uevent = vmbus_uevent, + .dma_configure = vmbus_dma_configure, .dev_groups = vmbus_dev_groups, .drv_groups = vmbus_drv_groups, .bus_groups = vmbus_bus_groups, @@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Only register if the crash MSRs are available */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { u64 hyperv_crash_ctl; /* - * Sysctl registration is not fatal, since by default - * reporting is enabled. + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. */ hv_ctl_table_hdr = register_sysctl_table(hv_root_table); if (!hv_ctl_table_hdr) @@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj) child_device_obj->device.parent = &hv_acpi_dev->dev; child_device_obj->device.release = vmbus_device_release; + child_device_obj->device.dma_parms = &child_device_obj->dma_parms; + child_device_obj->device.dma_mask = &child_device_obj->dma_mask; + dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); + /* * Register with the LDM. This will kick off the driver/device * binding...which will eventually call vmbus_match() and vmbus_probe() @@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj) } hv_debug_add_dev_dir(child_device_obj); - child_device_obj->device.dma_parms = &child_device_obj->dma_parms; - child_device_obj->device.dma_mask = &child_device_obj->dma_mask; - dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); return 0; err_kset_unregister: @@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device) hv_acpi_dev = device; + /* + * Older versions of Hyper-V for ARM64 fail to include the _CCA + * method on the top level VMbus device in the DSDT. But devices + * are hardware coherent in all current Hyper-V use cases, so fix + * up the ACPI device to behave as if _CCA is present and indicates + * hardware coherence. + */ + ACPI_COMPANION_SET(&device->dev, device); + if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) && + device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) { + pr_info("No ACPI _CCA found; assuming coherent device I/O\n"); + device->flags.cca_seen = true; + device->flags.coherent_dma = true; + } + result = acpi_walk_resources(device->handle, METHOD_NAME__CRS, vmbus_walk_resources, NULL); @@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void) if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { kmsg_dump_unregister(&hv_kmsg_dumper); unregister_die_notifier(&hyperv_die_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_block); } + /* + * The panic notifier is always registered, hence we should + * also unconditionally unregister it here as well. + */ + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_block); + free_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 27f969b3dc07..e9e2db68b9fb 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -179,6 +179,12 @@ struct imx_i2c_hwdata { unsigned int ndivs; unsigned int i2sr_clr_opcode; unsigned int i2cr_ien_opcode; + /* + * Errata ERR007805 or e7805: + * I2C: When the I2C clock speed is configured for 400 kHz, + * the SCL low period violates the I2C spec of 1.3 uS min. + */ + bool has_err007805; }; struct imx_i2c_dma { @@ -240,6 +246,16 @@ static const struct imx_i2c_hwdata imx21_i2c_hwdata = { }; +static const struct imx_i2c_hwdata imx6_i2c_hwdata = { + .devtype = IMX21_I2C, + .regshift = IMX_I2C_REGSHIFT, + .clk_div = imx_i2c_clk_div, + .ndivs = ARRAY_SIZE(imx_i2c_clk_div), + .i2sr_clr_opcode = I2SR_CLR_OPCODE_W0C, + .i2cr_ien_opcode = I2CR_IEN_OPCODE_1, + .has_err007805 = true, +}; + static struct imx_i2c_hwdata vf610_i2c_hwdata = { .devtype = VF610_I2C, .regshift = VF610_I2C_REGSHIFT, @@ -266,6 +282,16 @@ MODULE_DEVICE_TABLE(platform, imx_i2c_devtype); static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx1-i2c", .data = &imx1_i2c_hwdata, }, { .compatible = "fsl,imx21-i2c", .data = &imx21_i2c_hwdata, }, + { .compatible = "fsl,imx6q-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sl-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sll-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sx-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6ul-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx7s-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mm-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mn-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mp-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mq-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,vf610-i2c", .data = &vf610_i2c_hwdata, }, { /* sentinel */ } }; @@ -551,6 +577,13 @@ static void i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, unsigned int div; int i; + if (i2c_imx->hwdata->has_err007805 && i2c_imx->bitrate > 384000) { + dev_dbg(&i2c_imx->adapter.dev, + "SoC errata ERR007805 or e7805 applies, bus frequency limited from %d Hz to 384000 Hz.\n", + i2c_imx->bitrate); + i2c_imx->bitrate = 384000; + } + /* Divider value calculation */ if (i2c_imx->cur_clk == i2c_clk_rate) return; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index f4820fd3dc13..c0364314877e 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -145,8 +145,8 @@ #define ISMT_SPGT_SPD_MASK 0xc0000000 /* SMBus Speed mask */ #define ISMT_SPGT_SPD_80K 0x00 /* 80 kHz */ #define ISMT_SPGT_SPD_100K (0x1 << 30) /* 100 kHz */ -#define ISMT_SPGT_SPD_400K (0x2 << 30) /* 400 kHz */ -#define ISMT_SPGT_SPD_1M (0x3 << 30) /* 1 MHz */ +#define ISMT_SPGT_SPD_400K (0x2U << 30) /* 400 kHz */ +#define ISMT_SPGT_SPD_1M (0x3U << 30) /* 1 MHz */ /* MSI Control Register (MSICTL) bit definitions */ diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 7728c8460dc0..9028ffb58cc0 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -137,6 +137,12 @@ static int pasemi_i2c_xfer_msg(struct i2c_adapter *adapter, TXFIFO_WR(smbus, msg->buf[msg->len-1] | (stop ? MTXFIFO_STOP : 0)); + + if (stop) { + err = pasemi_smb_waitready(smbus); + if (err) + goto reset_out; + } } return 0; diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index fc1dcc19f2a1..5b920f0fc7dd 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -843,10 +843,8 @@ static int geni_i2c_probe(struct platform_device *pdev) /* FIFO is disabled, so we can only use GPI DMA */ gi2c->gpi_mode = true; ret = setup_gpi_dma(gi2c); - if (ret) { - dev_err(dev, "Failed to setup GPI DMA mode:%d ret\n", ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n"); dev_dbg(dev, "Using GPI DMA mode for I2C\n"); } else { diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index cf5d049342ea..ab0adaa130da 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -557,7 +557,7 @@ static long compat_i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned lo .addr = umsg.addr, .flags = umsg.flags, .len = umsg.len, - .buf = compat_ptr(umsg.buf) + .buf = (__force __u8 *)compat_ptr(umsg.buf), }; } @@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy) i2c_dev->dev.class = i2c_dev_class; i2c_dev->dev.parent = &adap->dev; i2c_dev->dev.release = i2cdev_dev_release; - dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr); + + res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr); + if (res) + goto err_put_i2c_dev; res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev); - if (res) { - put_i2c_dev(i2c_dev, false); - return res; - } + if (res) + goto err_put_i2c_dev; pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr); return 0; + +err_put_i2c_dev: + put_i2c_dev(i2c_dev, false); + return res; } static int i2cdev_detach_adapter(struct device *dev, void *dummy) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 35f0d5e7533d..1c107d6d03b9 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2824,6 +2824,7 @@ static int cm_dreq_handler(struct cm_work *work) switch (cm_id_priv->id.state) { case IB_CM_REP_SENT: case IB_CM_DREQ_SENT: + case IB_CM_MRA_REP_RCVD: ib_cancel_mad(cm_id_priv->msg); break; case IB_CM_ESTABLISHED: @@ -2831,8 +2832,6 @@ static int cm_dreq_handler(struct cm_work *work) cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD) ib_cancel_mad(cm_id_priv->msg); break; - case IB_CM_MRA_REP_RCVD: - break; case IB_CM_TIMEWAIT: atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES] [CM_DREQ_COUNTER]); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 876cc78a22cc..7333646021bb 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -80,6 +80,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) unsigned long flags; struct list_head del_list; + /* Prevent freeing of mm until we are completely finished. */ + mmgrab(handler->mn.mm); + /* Unregister first so we don't get any more notifications. */ mmu_notifier_unregister(&handler->mn, handler->mn.mm); @@ -102,6 +105,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) do_remove(handler, &del_list); + /* Now the mm may be freed. */ + mmdrop(handler->mn.mm); + kfree(handler); } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 956f8e875daa..32ef67e9a6a7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -574,8 +574,10 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) spin_lock_irq(&ent->lock); if (ent->disabled) goto out; - if (need_delay) + if (need_delay) { queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ); + goto out; + } remove_cache_mr_locked(ent); queue_adjust_cache_locked(ent); } @@ -625,6 +627,7 @@ static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { struct mlx5_cache_ent *ent = mr->cache_ent; + WRITE_ONCE(dev->cache.last_add, jiffies); spin_lock_irq(&ent->lock); list_add_tail(&mr->list, &ent->head); ent->available_mrs++; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index ae50b56e8913..8ef112f883a7 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -3190,7 +3190,11 @@ serr_no_r_lock: spin_lock_irqsave(&sqp->s_lock, flags); rvt_send_complete(sqp, wqe, send_status); if (sqp->ibqp.qp_type == IB_QPT_RC) { - int lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + int lastwqe; + + spin_lock(&sqp->r_lock); + lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + spin_unlock(&sqp->r_lock); sqp->s_flags &= ~RVT_S_BUSY; spin_unlock_irqrestore(&sqp->s_lock, flags); diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig index 5baebf62df33..e2752f7364bc 100644 --- a/drivers/input/Kconfig +++ b/drivers/input/Kconfig @@ -77,6 +77,13 @@ config INPUT_MATRIXKMAP To compile this driver as a module, choose M here: the module will be called matrix-keymap. +config INPUT_VIVALDIFMAP + tristate + help + ChromeOS Vivaldi keymap support library. This is a hidden + option so that drivers can use common code to parse and + expose the vivaldi function row keymap. + comment "Userland interfaces" config INPUT_MOUSEDEV diff --git a/drivers/input/Makefile b/drivers/input/Makefile index 037cc595106c..2266c7d010ef 100644 --- a/drivers/input/Makefile +++ b/drivers/input/Makefile @@ -12,6 +12,7 @@ input-core-y += touchscreen.o obj-$(CONFIG_INPUT_FF_MEMLESS) += ff-memless.o obj-$(CONFIG_INPUT_SPARSEKMAP) += sparse-keymap.o obj-$(CONFIG_INPUT_MATRIXKMAP) += matrix-keymap.o +obj-$(CONFIG_INPUT_VIVALDIFMAP) += vivaldi-fmap.o obj-$(CONFIG_INPUT_LEDS) += input-leds.o obj-$(CONFIG_INPUT_MOUSEDEV) += mousedev.o diff --git a/drivers/input/input.c b/drivers/input/input.c index c3139bc2aa0d..e5a668ce884d 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -47,6 +47,17 @@ static DEFINE_MUTEX(input_mutex); static const struct input_value input_value_sync = { EV_SYN, SYN_REPORT, 1 }; +static const unsigned int input_max_code[EV_CNT] = { + [EV_KEY] = KEY_MAX, + [EV_REL] = REL_MAX, + [EV_ABS] = ABS_MAX, + [EV_MSC] = MSC_MAX, + [EV_SW] = SW_MAX, + [EV_LED] = LED_MAX, + [EV_SND] = SND_MAX, + [EV_FF] = FF_MAX, +}; + static inline int is_event_supported(unsigned int code, unsigned long *bm, unsigned int max) { @@ -511,6 +522,9 @@ void input_set_abs_params(struct input_dev *dev, unsigned int axis, { struct input_absinfo *absinfo; + __set_bit(EV_ABS, dev->evbit); + __set_bit(axis, dev->absbit); + input_alloc_absinfo(dev); if (!dev->absinfo) return; @@ -520,12 +534,45 @@ void input_set_abs_params(struct input_dev *dev, unsigned int axis, absinfo->maximum = max; absinfo->fuzz = fuzz; absinfo->flat = flat; - - __set_bit(EV_ABS, dev->evbit); - __set_bit(axis, dev->absbit); } EXPORT_SYMBOL(input_set_abs_params); +/** + * input_copy_abs - Copy absinfo from one input_dev to another + * @dst: Destination input device to copy the abs settings to + * @dst_axis: ABS_* value selecting the destination axis + * @src: Source input device to copy the abs settings from + * @src_axis: ABS_* value selecting the source axis + * + * Set absinfo for the selected destination axis by copying it from + * the specified source input device's source axis. + * This is useful to e.g. setup a pen/stylus input-device for combined + * touchscreen/pen hardware where the pen uses the same coordinates as + * the touchscreen. + */ +void input_copy_abs(struct input_dev *dst, unsigned int dst_axis, + const struct input_dev *src, unsigned int src_axis) +{ + /* src must have EV_ABS and src_axis set */ + if (WARN_ON(!(test_bit(EV_ABS, src->evbit) && + test_bit(src_axis, src->absbit)))) + return; + + /* + * input_alloc_absinfo() may have failed for the source. Our caller is + * expected to catch this when registering the input devices, which may + * happen after the input_copy_abs() call. + */ + if (!src->absinfo) + return; + + input_set_capability(dst, EV_ABS, dst_axis); + if (!dst->absinfo) + return; + + dst->absinfo[dst_axis] = src->absinfo[src_axis]; +} +EXPORT_SYMBOL(input_copy_abs); /** * input_grab_device - grabs device for exclusive use @@ -2074,6 +2121,14 @@ EXPORT_SYMBOL(input_get_timestamp); */ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code) { + if (type < EV_CNT && input_max_code[type] && + code > input_max_code[type]) { + pr_err("%s: invalid code %u for type %u\n", __func__, code, + type); + dump_stack(); + return; + } + switch (type) { case EV_KEY: __set_bit(code, dev->keybit); @@ -2085,9 +2140,6 @@ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int case EV_ABS: input_alloc_absinfo(dev); - if (!dev->absinfo) - return; - __set_bit(code, dev->absbit); break; @@ -2285,12 +2337,6 @@ int input_register_device(struct input_dev *dev) /* KEY_RESERVED is not supposed to be transmitted to userspace. */ __clear_bit(KEY_RESERVED, dev->keybit); - /* Buttonpads should not map BTN_RIGHT and/or BTN_MIDDLE. */ - if (test_bit(INPUT_PROP_BUTTONPAD, dev->propbit)) { - __clear_bit(BTN_RIGHT, dev->keybit); - __clear_bit(BTN_MIDDLE, dev->keybit); - } - /* Make sure that bitmasks not mentioned in dev->evbit are clean. */ input_cleanse_bitmasks(dev); diff --git a/drivers/input/joystick/adi.c b/drivers/input/joystick/adi.c index 592c95b87f54..e10d57bf1180 100644 --- a/drivers/input/joystick/adi.c +++ b/drivers/input/joystick/adi.c @@ -123,7 +123,7 @@ static void adi_read_packet(struct adi_port *port) { struct adi *adi = port->adi; struct gameport *gameport = port->gameport; - unsigned char u, v, w, x, z; + unsigned char u, v, w, x; int t[2], s[2], i; unsigned long flags; @@ -136,7 +136,7 @@ static void adi_read_packet(struct adi_port *port) local_irq_save(flags); gameport_trigger(gameport); - v = z = gameport_read(gameport); + v = gameport_read(gameport); do { u = v; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 4c914f75a902..18190b529bca 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -131,7 +131,7 @@ static const struct xpad_device { { 0x045e, 0x02e3, "Microsoft X-Box One Elite pad", 0, XTYPE_XBOXONE }, { 0x045e, 0x02ea, "Microsoft X-Box One S pad", 0, XTYPE_XBOXONE }, { 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, - { 0x045e, 0x0b12, "Microsoft Xbox One X pad", MAP_SELECT_BUTTON, XTYPE_XBOXONE }, + { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE }, { 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 }, { 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 }, { 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 }, diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 9417ee0b1eff..4ea79db8f134 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -103,6 +103,7 @@ config KEYBOARD_ATKBD select SERIO_LIBPS2 select SERIO_I8042 if ARCH_MIGHT_HAVE_PC_SERIO select SERIO_GSCPS2 if GSC + select INPUT_VIVALDIFMAP help Say Y here if you want to use a standard AT or PS/2 keyboard. Usually you'll need this, unless you have a different type keyboard (USB, ADB @@ -749,6 +750,7 @@ config KEYBOARD_XTKBD config KEYBOARD_CROS_EC tristate "ChromeOS EC keyboard" select INPUT_MATRIXKMAP + select INPUT_VIVALDIFMAP depends on CROS_EC help Say Y here to enable the matrix keyboard used by ChromeOS devices @@ -779,6 +781,18 @@ config KEYBOARD_BCM To compile this driver as a module, choose M here: the module will be called bcm-keypad. +config KEYBOARD_MT6779 + tristate "MediaTek Keypad Support" + depends on ARCH_MEDIATEK || COMPILE_TEST + select REGMAP_MMIO + select INPUT_MATRIXKMAP + help + Say Y here if you want to use the keypad on MediaTek SoCs. + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called mt6779-keypad. + config KEYBOARD_MTK_PMIC tristate "MediaTek PMIC keys support" depends on MFD_MT6397 diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index e3c8648f834e..721936e90290 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_KEYBOARD_MATRIX) += matrix_keypad.o obj-$(CONFIG_KEYBOARD_MAX7359) += max7359_keypad.o obj-$(CONFIG_KEYBOARD_MCS) += mcs_touchkey.o obj-$(CONFIG_KEYBOARD_MPR121) += mpr121_touchkey.o +obj-$(CONFIG_KEYBOARD_MT6779) += mt6779-keypad.o obj-$(CONFIG_KEYBOARD_MTK_PMIC) += mtk-pmic-keys.o obj-$(CONFIG_KEYBOARD_NEWTON) += newtonkbd.o obj-$(CONFIG_KEYBOARD_NOMADIK) += nomadik-ske-keypad.o diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index fbdef95291e9..d4131236d18c 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -19,6 +19,7 @@ #include <linux/interrupt.h> #include <linux/init.h> #include <linux/input.h> +#include <linux/input/vivaldi-fmap.h> #include <linux/serio.h> #include <linux/workqueue.h> #include <linux/libps2.h> @@ -64,8 +65,6 @@ static bool atkbd_terminal; module_param_named(terminal, atkbd_terminal, bool, 0); MODULE_PARM_DESC(terminal, "Enable break codes on an IBM Terminal keyboard connected via AT/PS2"); -#define MAX_FUNCTION_ROW_KEYS 24 - #define SCANCODE(keymap) ((keymap >> 16) & 0xFFFF) #define KEYCODE(keymap) (keymap & 0xFFFF) @@ -237,8 +236,7 @@ struct atkbd { /* Serializes reconnect(), attr->set() and event work */ struct mutex mutex; - u32 function_row_physmap[MAX_FUNCTION_ROW_KEYS]; - int num_function_row_keys; + struct vivaldi_data vdata; }; /* @@ -308,17 +306,7 @@ static struct attribute *atkbd_attributes[] = { static ssize_t atkbd_show_function_row_physmap(struct atkbd *atkbd, char *buf) { - ssize_t size = 0; - int i; - - if (!atkbd->num_function_row_keys) - return 0; - - for (i = 0; i < atkbd->num_function_row_keys; i++) - size += scnprintf(buf + size, PAGE_SIZE - size, "%02X ", - atkbd->function_row_physmap[i]); - size += scnprintf(buf + size, PAGE_SIZE - size, "\n"); - return size; + return vivaldi_function_row_physmap_show(&atkbd->vdata, buf); } static umode_t atkbd_attr_is_visible(struct kobject *kobj, @@ -329,7 +317,7 @@ static umode_t atkbd_attr_is_visible(struct kobject *kobj, struct atkbd *atkbd = serio_get_drvdata(serio); if (attr == &atkbd_attr_function_row_physmap.attr && - !atkbd->num_function_row_keys) + !atkbd->vdata.num_function_row_keys) return 0; return attr->mode; @@ -1206,10 +1194,11 @@ static void atkbd_parse_fwnode_data(struct serio *serio) /* Parse "function-row-physmap" property */ n = device_property_count_u32(dev, "function-row-physmap"); - if (n > 0 && n <= MAX_FUNCTION_ROW_KEYS && + if (n > 0 && n <= VIVALDI_MAX_FUNCTION_ROW_KEYS && !device_property_read_u32_array(dev, "function-row-physmap", - atkbd->function_row_physmap, n)) { - atkbd->num_function_row_keys = n; + atkbd->vdata.function_row_physmap, + n)) { + atkbd->vdata.num_function_row_keys = n; dev_dbg(dev, "FW reported %d function-row key locations\n", n); } } diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index fc02c540636e..6534dfca60b4 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -15,6 +15,7 @@ #include <linux/bitops.h> #include <linux/i2c.h> #include <linux/input.h> +#include <linux/input/vivaldi-fmap.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/notifier.h> @@ -27,8 +28,6 @@ #include <asm/unaligned.h> -#define MAX_NUM_TOP_ROW_KEYS 15 - /** * struct cros_ec_keyb - Structure representing EC keyboard device * @@ -44,9 +43,7 @@ * @idev: The input device for the matrix keys. * @bs_idev: The input device for non-matrix buttons and switches (or NULL). * @notifier: interrupt event notifier for transport devices - * @function_row_physmap: An array of the encoded rows/columns for the top - * row function keys, in an order from left to right - * @num_function_row_keys: The number of top row keys in a custom keyboard + * @vdata: vivaldi function row data */ struct cros_ec_keyb { unsigned int rows; @@ -64,8 +61,7 @@ struct cros_ec_keyb { struct input_dev *bs_idev; struct notifier_block notifier; - u16 function_row_physmap[MAX_NUM_TOP_ROW_KEYS]; - size_t num_function_row_keys; + struct vivaldi_data vdata; }; /** @@ -537,9 +533,9 @@ static int cros_ec_keyb_register_matrix(struct cros_ec_keyb *ckdev) int err; struct property *prop; const __be32 *p; - u16 *physmap; + u32 *physmap; u32 key_pos; - int row, col; + unsigned int row, col, scancode, n_physmap; err = matrix_keypad_parse_properties(dev, &ckdev->rows, &ckdev->cols); if (err) @@ -591,20 +587,21 @@ static int cros_ec_keyb_register_matrix(struct cros_ec_keyb *ckdev) ckdev->idev = idev; cros_ec_keyb_compute_valid_keys(ckdev); - physmap = ckdev->function_row_physmap; + physmap = ckdev->vdata.function_row_physmap; + n_physmap = 0; of_property_for_each_u32(dev->of_node, "function-row-physmap", prop, p, key_pos) { - if (ckdev->num_function_row_keys == MAX_NUM_TOP_ROW_KEYS) { + if (n_physmap == VIVALDI_MAX_FUNCTION_ROW_KEYS) { dev_warn(dev, "Only support up to %d top row keys\n", - MAX_NUM_TOP_ROW_KEYS); + VIVALDI_MAX_FUNCTION_ROW_KEYS); break; } row = KEY_ROW(key_pos); col = KEY_COL(key_pos); - *physmap = MATRIX_SCAN_CODE(row, col, ckdev->row_shift); - physmap++; - ckdev->num_function_row_keys++; + scancode = MATRIX_SCAN_CODE(row, col, ckdev->row_shift); + physmap[n_physmap++] = scancode; } + ckdev->vdata.num_function_row_keys = n_physmap; err = input_register_device(ckdev->idev); if (err) { @@ -619,18 +616,10 @@ static ssize_t function_row_physmap_show(struct device *dev, struct device_attribute *attr, char *buf) { - ssize_t size = 0; - int i; - struct cros_ec_keyb *ckdev = dev_get_drvdata(dev); - u16 *physmap = ckdev->function_row_physmap; - - for (i = 0; i < ckdev->num_function_row_keys; i++) - size += scnprintf(buf + size, PAGE_SIZE - size, - "%s%02X", size ? " " : "", physmap[i]); - if (size) - size += scnprintf(buf + size, PAGE_SIZE - size, "\n"); + const struct cros_ec_keyb *ckdev = dev_get_drvdata(dev); + const struct vivaldi_data *data = &ckdev->vdata; - return size; + return vivaldi_function_row_physmap_show(data, buf); } static DEVICE_ATTR_RO(function_row_physmap); @@ -648,7 +637,7 @@ static umode_t cros_ec_keyb_attr_is_visible(struct kobject *kobj, struct cros_ec_keyb *ckdev = dev_get_drvdata(dev); if (attr == &dev_attr_function_row_physmap.attr && - !ckdev->num_function_row_keys) + !ckdev->vdata.num_function_row_keys) return 0; return attr->mode; diff --git a/drivers/input/keyboard/mt6779-keypad.c b/drivers/input/keyboard/mt6779-keypad.c new file mode 100644 index 000000000000..0dbbddc7f298 --- /dev/null +++ b/drivers/input/keyboard/mt6779-keypad.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 MediaTek Inc. + * Author Fengping Yu <fengping.yu@mediatek.com> + */ +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/input/matrix_keypad.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/property.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> + +#define MTK_KPD_NAME "mt6779-keypad" +#define MTK_KPD_MEM 0x0004 +#define MTK_KPD_DEBOUNCE 0x0018 +#define MTK_KPD_DEBOUNCE_MASK GENMASK(13, 0) +#define MTK_KPD_DEBOUNCE_MAX_MS 256 +#define MTK_KPD_NUM_MEMS 5 +#define MTK_KPD_NUM_BITS 136 /* 4*32+8 MEM5 only use 8 BITS */ + +struct mt6779_keypad { + struct regmap *regmap; + struct input_dev *input_dev; + struct clk *clk; + void __iomem *base; + u32 n_rows; + u32 n_cols; + DECLARE_BITMAP(keymap_state, MTK_KPD_NUM_BITS); +}; + +static const struct regmap_config mt6779_keypad_regmap_cfg = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = sizeof(u32), + .max_register = 36, +}; + +static irqreturn_t mt6779_keypad_irq_handler(int irq, void *dev_id) +{ + struct mt6779_keypad *keypad = dev_id; + const unsigned short *keycode = keypad->input_dev->keycode; + DECLARE_BITMAP(new_state, MTK_KPD_NUM_BITS); + DECLARE_BITMAP(change, MTK_KPD_NUM_BITS); + unsigned int bit_nr; + unsigned int row, col; + unsigned int scancode; + unsigned int row_shift = get_count_order(keypad->n_cols); + bool pressed; + + regmap_bulk_read(keypad->regmap, MTK_KPD_MEM, + new_state, MTK_KPD_NUM_MEMS); + + bitmap_xor(change, new_state, keypad->keymap_state, MTK_KPD_NUM_BITS); + + for_each_set_bit(bit_nr, change, MTK_KPD_NUM_BITS) { + /* + * Registers are 32bits, but only bits [15:0] are used to + * indicate key status. + */ + if (bit_nr % 32 >= 16) + continue; + + row = bit_nr / 32; + col = bit_nr % 32; + scancode = MATRIX_SCAN_CODE(row, col, row_shift); + /* 1: not pressed, 0: pressed */ + pressed = !test_bit(bit_nr, new_state); + dev_dbg(&keypad->input_dev->dev, "%s", + pressed ? "pressed" : "released"); + + input_event(keypad->input_dev, EV_MSC, MSC_SCAN, scancode); + input_report_key(keypad->input_dev, keycode[scancode], pressed); + input_sync(keypad->input_dev); + + dev_dbg(&keypad->input_dev->dev, + "report Linux keycode = %d\n", keycode[scancode]); + } + + bitmap_copy(keypad->keymap_state, new_state, MTK_KPD_NUM_BITS); + + return IRQ_HANDLED; +} + +static void mt6779_keypad_clk_disable(void *data) +{ + clk_disable_unprepare(data); +} + +static int mt6779_keypad_pdrv_probe(struct platform_device *pdev) +{ + struct mt6779_keypad *keypad; + int irq; + u32 debounce; + bool wakeup; + int error; + + keypad = devm_kzalloc(&pdev->dev, sizeof(*keypad), GFP_KERNEL); + if (!keypad) + return -ENOMEM; + + keypad->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(keypad->base)) + return PTR_ERR(keypad->base); + + keypad->regmap = devm_regmap_init_mmio(&pdev->dev, keypad->base, + &mt6779_keypad_regmap_cfg); + if (IS_ERR(keypad->regmap)) { + dev_err(&pdev->dev, + "regmap init failed:%pe\n", keypad->regmap); + return PTR_ERR(keypad->regmap); + } + + bitmap_fill(keypad->keymap_state, MTK_KPD_NUM_BITS); + + keypad->input_dev = devm_input_allocate_device(&pdev->dev); + if (!keypad->input_dev) { + dev_err(&pdev->dev, "Failed to allocate input dev\n"); + return -ENOMEM; + } + + keypad->input_dev->name = MTK_KPD_NAME; + keypad->input_dev->id.bustype = BUS_HOST; + + error = matrix_keypad_parse_properties(&pdev->dev, &keypad->n_rows, + &keypad->n_cols); + if (error) { + dev_err(&pdev->dev, "Failed to parse keypad params\n"); + return error; + } + + if (device_property_read_u32(&pdev->dev, "debounce-delay-ms", + &debounce)) + debounce = 16; + + if (debounce > MTK_KPD_DEBOUNCE_MAX_MS) { + dev_err(&pdev->dev, + "Debounce time exceeds the maximum allowed time %dms\n", + MTK_KPD_DEBOUNCE_MAX_MS); + return -EINVAL; + } + + wakeup = device_property_read_bool(&pdev->dev, "wakeup-source"); + + dev_dbg(&pdev->dev, "n_row=%d n_col=%d debounce=%d\n", + keypad->n_rows, keypad->n_cols, debounce); + + error = matrix_keypad_build_keymap(NULL, NULL, + keypad->n_rows, keypad->n_cols, + NULL, keypad->input_dev); + if (error) { + dev_err(&pdev->dev, "Failed to build keymap\n"); + return error; + } + + input_set_capability(keypad->input_dev, EV_MSC, MSC_SCAN); + + regmap_write(keypad->regmap, MTK_KPD_DEBOUNCE, + (debounce * (1 << 5)) & MTK_KPD_DEBOUNCE_MASK); + + keypad->clk = devm_clk_get(&pdev->dev, "kpd"); + if (IS_ERR(keypad->clk)) + return PTR_ERR(keypad->clk); + + error = clk_prepare_enable(keypad->clk); + if (error) { + dev_err(&pdev->dev, "cannot prepare/enable keypad clock\n"); + return error; + } + + error = devm_add_action_or_reset(&pdev->dev, mt6779_keypad_clk_disable, + keypad->clk); + if (error) + return error; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + error = devm_request_threaded_irq(&pdev->dev, irq, + NULL, mt6779_keypad_irq_handler, + IRQF_ONESHOT, MTK_KPD_NAME, keypad); + if (error) { + dev_err(&pdev->dev, "Failed to request IRQ#%d: %d\n", + irq, error); + return error; + } + + error = input_register_device(keypad->input_dev); + if (error) { + dev_err(&pdev->dev, "Failed to register device\n"); + return error; + } + + error = device_init_wakeup(&pdev->dev, wakeup); + if (error) + dev_warn(&pdev->dev, "device_init_wakeup() failed: %d\n", + error); + + return 0; +} + +static const struct of_device_id mt6779_keypad_of_match[] = { + { .compatible = "mediatek,mt6779-keypad" }, + { .compatible = "mediatek,mt6873-keypad" }, + { /* sentinel */ } +}; + +static struct platform_driver mt6779_keypad_pdrv = { + .probe = mt6779_keypad_pdrv_probe, + .driver = { + .name = MTK_KPD_NAME, + .of_match_table = mt6779_keypad_of_match, + }, +}; +module_platform_driver(mt6779_keypad_pdrv); + +MODULE_AUTHOR("Mediatek Corporation"); +MODULE_DESCRIPTION("MTK Keypad (KPD) Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c index 62391d6c7da6..c31ab4368388 100644 --- a/drivers/input/keyboard/mtk-pmic-keys.c +++ b/drivers/input/keyboard/mtk-pmic-keys.c @@ -9,6 +9,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/mfd/mt6323/registers.h> +#include <linux/mfd/mt6358/registers.h> #include <linux/mfd/mt6397/core.h> #include <linux/mfd/mt6397/registers.h> #include <linux/module.h> @@ -74,11 +75,22 @@ static const struct mtk_pmic_regs mt6323_regs = { .pmic_rst_reg = MT6323_TOP_RST_MISC, }; +static const struct mtk_pmic_regs mt6358_regs = { + .keys_regs[MTK_PMIC_PWRKEY_INDEX] = + MTK_PMIC_KEYS_REGS(MT6358_TOPSTATUS, + 0x2, MT6358_PSC_TOP_INT_CON0, 0x5), + .keys_regs[MTK_PMIC_HOMEKEY_INDEX] = + MTK_PMIC_KEYS_REGS(MT6358_TOPSTATUS, + 0x8, MT6358_PSC_TOP_INT_CON0, 0xa), + .pmic_rst_reg = MT6358_TOP_RST_MISC, +}; + struct mtk_pmic_keys_info { struct mtk_pmic_keys *keys; const struct mtk_pmic_keys_regs *regs; unsigned int keycode; int irq; + int irq_r; /* optional: release irq if different */ bool wakeup:1; }; @@ -188,6 +200,18 @@ static int mtk_pmic_key_setup(struct mtk_pmic_keys *keys, return ret; } + if (info->irq_r > 0) { + ret = devm_request_threaded_irq(keys->dev, info->irq_r, NULL, + mtk_pmic_keys_irq_handler_thread, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + "mtk-pmic-keys", info); + if (ret) { + dev_err(keys->dev, "Failed to request IRQ_r: %d: %d\n", + info->irq, ret); + return ret; + } + } + input_set_capability(keys->input_dev, EV_KEY, info->keycode); return 0; @@ -199,8 +223,11 @@ static int __maybe_unused mtk_pmic_keys_suspend(struct device *dev) int index; for (index = 0; index < MTK_PMIC_MAX_KEY_COUNT; index++) { - if (keys->keys[index].wakeup) + if (keys->keys[index].wakeup) { enable_irq_wake(keys->keys[index].irq); + if (keys->keys[index].irq_r > 0) + enable_irq_wake(keys->keys[index].irq_r); + } } return 0; @@ -212,8 +239,11 @@ static int __maybe_unused mtk_pmic_keys_resume(struct device *dev) int index; for (index = 0; index < MTK_PMIC_MAX_KEY_COUNT; index++) { - if (keys->keys[index].wakeup) + if (keys->keys[index].wakeup) { disable_irq_wake(keys->keys[index].irq); + if (keys->keys[index].irq_r > 0) + disable_irq_wake(keys->keys[index].irq_r); + } } return 0; @@ -230,6 +260,9 @@ static const struct of_device_id of_mtk_pmic_keys_match_tbl[] = { .compatible = "mediatek,mt6323-keys", .data = &mt6323_regs, }, { + .compatible = "mediatek,mt6358-keys", + .data = &mt6358_regs, + }, { /* sentinel */ } }; @@ -241,6 +274,8 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev) unsigned int keycount; struct mt6397_chip *pmic_chip = dev_get_drvdata(pdev->dev.parent); struct device_node *node = pdev->dev.of_node, *child; + static const char *const irqnames[] = { "powerkey", "homekey" }; + static const char *const irqnames_r[] = { "powerkey_r", "homekey_r" }; struct mtk_pmic_keys *keys; const struct mtk_pmic_regs *mtk_pmic_regs; struct input_dev *input_dev; @@ -268,7 +303,8 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev) input_dev->id.version = 0x0001; keycount = of_get_available_child_count(node); - if (keycount > MTK_PMIC_MAX_KEY_COUNT) { + if (keycount > MTK_PMIC_MAX_KEY_COUNT || + keycount > ARRAY_SIZE(irqnames)) { dev_err(keys->dev, "too many keys defined (%d)\n", keycount); return -EINVAL; } @@ -276,12 +312,23 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev) for_each_child_of_node(node, child) { keys->keys[index].regs = &mtk_pmic_regs->keys_regs[index]; - keys->keys[index].irq = platform_get_irq(pdev, index); + keys->keys[index].irq = + platform_get_irq_byname(pdev, irqnames[index]); if (keys->keys[index].irq < 0) { of_node_put(child); return keys->keys[index].irq; } + if (of_device_is_compatible(node, "mediatek,mt6358-keys")) { + keys->keys[index].irq_r = platform_get_irq_byname(pdev, + irqnames_r[index]); + + if (keys->keys[index].irq_r < 0) { + of_node_put(child); + return keys->keys[index].irq_r; + } + } + error = of_property_read_u32(child, "linux,keycodes", &keys->keys[index].keycode); if (error) { diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c index 79851923ee57..b14a389600c9 100644 --- a/drivers/input/misc/da9063_onkey.c +++ b/drivers/input/misc/da9063_onkey.c @@ -4,6 +4,7 @@ * Copyright (C) 2015 Dialog Semiconductor Ltd. */ +#include <linux/devm-helpers.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/input.h> @@ -182,13 +183,6 @@ static irqreturn_t da9063_onkey_irq_handler(int irq, void *data) return IRQ_HANDLED; } -static void da9063_cancel_poll(void *data) -{ - struct da9063_onkey *onkey = data; - - cancel_delayed_work_sync(&onkey->work); -} - static int da9063_onkey_probe(struct platform_device *pdev) { struct da9063_onkey *onkey; @@ -234,9 +228,8 @@ static int da9063_onkey_probe(struct platform_device *pdev) input_set_capability(onkey->input, EV_KEY, KEY_POWER); - INIT_DELAYED_WORK(&onkey->work, da9063_poll_on); - - error = devm_add_action(&pdev->dev, da9063_cancel_poll, onkey); + error = devm_delayed_work_autocancel(&pdev->dev, &onkey->work, + da9063_poll_on); if (error) { dev_err(&pdev->dev, "Failed to add cancel poll action: %d\n", diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index ffad142801b3..434d48ae4b12 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -186,6 +186,7 @@ static const char * const smbus_pnp_ids[] = { "LEN2044", /* L470 */ "LEN2054", /* E480 */ "LEN2055", /* E580 */ + "LEN2064", /* T14 Gen 1 AMD / P14s Gen 1 AMD */ "LEN2068", /* T14 Gen 1 */ "SYN3052", /* HP EliteBook 840 G4 */ "SYN3221", /* HP 15-ay000 */ diff --git a/drivers/input/serio/ps2-gpio.c b/drivers/input/serio/ps2-gpio.c index 8970b49ea09a..9b02dd5dd2b9 100644 --- a/drivers/input/serio/ps2-gpio.c +++ b/drivers/input/serio/ps2-gpio.c @@ -19,6 +19,7 @@ #include <linux/of.h> #include <linux/jiffies.h> #include <linux/delay.h> +#include <linux/timekeeping.h> #define DRIVER_NAME "ps2-gpio" @@ -36,14 +37,37 @@ #define PS2_DATA_BIT7 8 #define PS2_PARITY_BIT 9 #define PS2_STOP_BIT 10 -#define PS2_TX_TIMEOUT 11 -#define PS2_ACK_BIT 12 +#define PS2_ACK_BIT 11 #define PS2_DEV_RET_ACK 0xfa #define PS2_DEV_RET_NACK 0xfe #define PS2_CMD_RESEND 0xfe +/* + * The PS2 protocol specifies a clock frequency between 10kHz and 16.7kHz, + * therefore the maximal interrupt interval should be 100us and the minimum + * interrupt interval should be ~60us. Let's allow +/- 20us for frequency + * deviations and interrupt latency. + * + * The data line must be samples after ~30us to 50us after the falling edge, + * since the device updates the data line at the rising edge. + * + * ___ ______ ______ ______ ___ + * \ / \ / \ / \ / + * \ / \ / \ / \ / + * \______/ \______/ \______/ \______/ + * + * |-----------------| |--------| + * 60us/100us 30us/50us + */ +#define PS2_CLK_FREQ_MIN_HZ 10000 +#define PS2_CLK_FREQ_MAX_HZ 16700 +#define PS2_CLK_MIN_INTERVAL_US ((1000 * 1000) / PS2_CLK_FREQ_MAX_HZ) +#define PS2_CLK_MAX_INTERVAL_US ((1000 * 1000) / PS2_CLK_FREQ_MIN_HZ) +#define PS2_IRQ_MIN_INTERVAL_US (PS2_CLK_MIN_INTERVAL_US - 20) +#define PS2_IRQ_MAX_INTERVAL_US (PS2_CLK_MAX_INTERVAL_US + 20) + struct ps2_gpio_data { struct device *dev; struct serio *serio; @@ -52,19 +76,30 @@ struct ps2_gpio_data { struct gpio_desc *gpio_data; bool write_enable; int irq; - unsigned char rx_cnt; - unsigned char rx_byte; - unsigned char tx_cnt; - unsigned char tx_byte; - struct completion tx_done; - struct mutex tx_mutex; - struct delayed_work tx_work; + ktime_t t_irq_now; + ktime_t t_irq_last; + struct { + unsigned char cnt; + unsigned char byte; + } rx; + struct { + unsigned char cnt; + unsigned char byte; + ktime_t t_xfer_start; + ktime_t t_xfer_end; + struct completion complete; + struct mutex mutex; + struct delayed_work work; + } tx; }; static int ps2_gpio_open(struct serio *serio) { struct ps2_gpio_data *drvdata = serio->port_data; + drvdata->t_irq_last = 0; + drvdata->tx.t_xfer_end = 0; + enable_irq(drvdata->irq); return 0; } @@ -73,7 +108,7 @@ static void ps2_gpio_close(struct serio *serio) { struct ps2_gpio_data *drvdata = serio->port_data; - flush_delayed_work(&drvdata->tx_work); + flush_delayed_work(&drvdata->tx.work); disable_irq(drvdata->irq); } @@ -85,9 +120,9 @@ static int __ps2_gpio_write(struct serio *serio, unsigned char val) gpiod_direction_output(drvdata->gpio_clk, 0); drvdata->mode = PS2_MODE_TX; - drvdata->tx_byte = val; + drvdata->tx.byte = val; - schedule_delayed_work(&drvdata->tx_work, usecs_to_jiffies(200)); + schedule_delayed_work(&drvdata->tx.work, usecs_to_jiffies(200)); return 0; } @@ -98,12 +133,12 @@ static int ps2_gpio_write(struct serio *serio, unsigned char val) int ret = 0; if (in_task()) { - mutex_lock(&drvdata->tx_mutex); + mutex_lock(&drvdata->tx.mutex); __ps2_gpio_write(serio, val); - if (!wait_for_completion_timeout(&drvdata->tx_done, + if (!wait_for_completion_timeout(&drvdata->tx.complete, msecs_to_jiffies(10000))) ret = SERIO_TIMEOUT; - mutex_unlock(&drvdata->tx_mutex); + mutex_unlock(&drvdata->tx.mutex); } else { __ps2_gpio_write(serio, val); } @@ -115,9 +150,10 @@ static void ps2_gpio_tx_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct ps2_gpio_data *drvdata = container_of(dwork, - struct ps2_gpio_data, - tx_work); + struct ps2_gpio_data, + tx.work); + drvdata->tx.t_xfer_start = ktime_get(); enable_irq(drvdata->irq); gpiod_direction_output(drvdata->gpio_data, 0); gpiod_direction_input(drvdata->gpio_clk); @@ -128,20 +164,31 @@ static irqreturn_t ps2_gpio_irq_rx(struct ps2_gpio_data *drvdata) unsigned char byte, cnt; int data; int rxflags = 0; - static unsigned long old_jiffies; + s64 us_delta; - byte = drvdata->rx_byte; - cnt = drvdata->rx_cnt; + byte = drvdata->rx.byte; + cnt = drvdata->rx.cnt; - if (old_jiffies == 0) - old_jiffies = jiffies; + drvdata->t_irq_now = ktime_get(); + + /* + * We need to consider spurious interrupts happening right after + * a TX xfer finished. + */ + us_delta = ktime_us_delta(drvdata->t_irq_now, drvdata->tx.t_xfer_end); + if (unlikely(us_delta < PS2_IRQ_MIN_INTERVAL_US)) + goto end; - if ((jiffies - old_jiffies) > usecs_to_jiffies(100)) { + us_delta = ktime_us_delta(drvdata->t_irq_now, drvdata->t_irq_last); + if (us_delta > PS2_IRQ_MAX_INTERVAL_US && cnt) { dev_err(drvdata->dev, "RX: timeout, probably we missed an interrupt\n"); goto err; + } else if (unlikely(us_delta < PS2_IRQ_MIN_INTERVAL_US)) { + /* Ignore spurious IRQs. */ + goto end; } - old_jiffies = jiffies; + drvdata->t_irq_last = drvdata->t_irq_now; data = gpiod_get_value(drvdata->gpio_data); if (unlikely(data < 0)) { @@ -178,8 +225,16 @@ static irqreturn_t ps2_gpio_irq_rx(struct ps2_gpio_data *drvdata) if (!drvdata->write_enable) goto err; } + break; + case PS2_STOP_BIT: + /* stop bit should be high */ + if (unlikely(!data)) { + dev_err(drvdata->dev, "RX: stop bit should be high\n"); + goto err; + } - /* Do not send spurious ACK's and NACK's when write fn is + /* + * Do not send spurious ACK's and NACK's when write fn is * not provided. */ if (!drvdata->write_enable) { @@ -189,23 +244,11 @@ static irqreturn_t ps2_gpio_irq_rx(struct ps2_gpio_data *drvdata) break; } - /* Let's send the data without waiting for the stop bit to be - * sent. It may happen that we miss the stop bit. When this - * happens we have no way to recover from this, certainly - * missing the parity bit would be recognized when processing - * the stop bit. When missing both, data is lost. - */ serio_interrupt(drvdata->serio, byte, rxflags); dev_dbg(drvdata->dev, "RX: sending byte 0x%x\n", byte); - break; - case PS2_STOP_BIT: - /* stop bit should be high */ - if (unlikely(!data)) { - dev_err(drvdata->dev, "RX: stop bit should be high\n"); - goto err; - } + cnt = byte = 0; - old_jiffies = 0; + goto end; /* success */ default: dev_err(drvdata->dev, "RX: got out of sync with the device\n"); @@ -217,11 +260,10 @@ static irqreturn_t ps2_gpio_irq_rx(struct ps2_gpio_data *drvdata) err: cnt = byte = 0; - old_jiffies = 0; __ps2_gpio_write(drvdata->serio, PS2_CMD_RESEND); end: - drvdata->rx_cnt = cnt; - drvdata->rx_byte = byte; + drvdata->rx.cnt = cnt; + drvdata->rx.byte = byte; return IRQ_HANDLED; } @@ -229,20 +271,34 @@ static irqreturn_t ps2_gpio_irq_tx(struct ps2_gpio_data *drvdata) { unsigned char byte, cnt; int data; - static unsigned long old_jiffies; + s64 us_delta; + + cnt = drvdata->tx.cnt; + byte = drvdata->tx.byte; - cnt = drvdata->tx_cnt; - byte = drvdata->tx_byte; + drvdata->t_irq_now = ktime_get(); - if (old_jiffies == 0) - old_jiffies = jiffies; + /* + * There might be pending IRQs since we disabled IRQs in + * __ps2_gpio_write(). We can expect at least one clock period until + * the device generates the first falling edge after releasing the + * clock line. + */ + us_delta = ktime_us_delta(drvdata->t_irq_now, + drvdata->tx.t_xfer_start); + if (unlikely(us_delta < PS2_CLK_MIN_INTERVAL_US)) + goto end; - if ((jiffies - old_jiffies) > usecs_to_jiffies(100)) { + us_delta = ktime_us_delta(drvdata->t_irq_now, drvdata->t_irq_last); + if (us_delta > PS2_IRQ_MAX_INTERVAL_US && cnt > 1) { dev_err(drvdata->dev, "TX: timeout, probably we missed an interrupt\n"); goto err; + } else if (unlikely(us_delta < PS2_IRQ_MIN_INTERVAL_US)) { + /* Ignore spurious IRQs. */ + goto end; } - old_jiffies = jiffies; + drvdata->t_irq_last = drvdata->t_irq_now; switch (cnt) { case PS2_START_BIT: @@ -270,27 +326,22 @@ static irqreturn_t ps2_gpio_irq_tx(struct ps2_gpio_data *drvdata) /* release data line to generate stop bit */ gpiod_direction_input(drvdata->gpio_data); break; - case PS2_TX_TIMEOUT: - /* Devices generate one extra clock pulse before sending the - * acknowledgment. - */ - break; case PS2_ACK_BIT: - gpiod_direction_input(drvdata->gpio_data); data = gpiod_get_value(drvdata->gpio_data); if (data) { dev_warn(drvdata->dev, "TX: received NACK, retry\n"); goto err; } + drvdata->tx.t_xfer_end = ktime_get(); drvdata->mode = PS2_MODE_RX; - complete(&drvdata->tx_done); + complete(&drvdata->tx.complete); cnt = 1; - old_jiffies = 0; goto end; /* success */ default: - /* Probably we missed the stop bit. Therefore we release data + /* + * Probably we missed the stop bit. Therefore we release data * line and try again. */ gpiod_direction_input(drvdata->gpio_data); @@ -303,11 +354,10 @@ static irqreturn_t ps2_gpio_irq_tx(struct ps2_gpio_data *drvdata) err: cnt = 1; - old_jiffies = 0; gpiod_direction_input(drvdata->gpio_data); - __ps2_gpio_write(drvdata->serio, drvdata->tx_byte); + __ps2_gpio_write(drvdata->serio, drvdata->tx.byte); end: - drvdata->tx_cnt = cnt; + drvdata->tx.cnt = cnt; return IRQ_HANDLED; } @@ -322,14 +372,19 @@ static irqreturn_t ps2_gpio_irq(int irq, void *dev_id) static int ps2_gpio_get_props(struct device *dev, struct ps2_gpio_data *drvdata) { - drvdata->gpio_data = devm_gpiod_get(dev, "data", GPIOD_IN); + enum gpiod_flags gflags; + + /* Enforce open drain, since this is required by the PS/2 bus. */ + gflags = GPIOD_IN | GPIOD_FLAGS_BIT_OPEN_DRAIN; + + drvdata->gpio_data = devm_gpiod_get(dev, "data", gflags); if (IS_ERR(drvdata->gpio_data)) { dev_err(dev, "failed to request data gpio: %ld", PTR_ERR(drvdata->gpio_data)); return PTR_ERR(drvdata->gpio_data); } - drvdata->gpio_clk = devm_gpiod_get(dev, "clk", GPIOD_IN); + drvdata->gpio_clk = devm_gpiod_get(dev, "clk", gflags); if (IS_ERR(drvdata->gpio_clk)) { dev_err(dev, "failed to request clock gpio: %ld", PTR_ERR(drvdata->gpio_clk)); @@ -387,7 +442,8 @@ static int ps2_gpio_probe(struct platform_device *pdev) serio->id.type = SERIO_8042; serio->open = ps2_gpio_open; serio->close = ps2_gpio_close; - /* Write can be enabled in platform/dt data, but possibly it will not + /* + * Write can be enabled in platform/dt data, but possibly it will not * work because of the tough timings. */ serio->write = drvdata->write_enable ? ps2_gpio_write : NULL; @@ -400,14 +456,15 @@ static int ps2_gpio_probe(struct platform_device *pdev) drvdata->dev = dev; drvdata->mode = PS2_MODE_RX; - /* Tx count always starts at 1, as the start bit is sent implicitly by + /* + * Tx count always starts at 1, as the start bit is sent implicitly by * host-to-device communication initialization. */ - drvdata->tx_cnt = 1; + drvdata->tx.cnt = 1; - INIT_DELAYED_WORK(&drvdata->tx_work, ps2_gpio_tx_work_fn); - init_completion(&drvdata->tx_done); - mutex_init(&drvdata->tx_mutex); + INIT_DELAYED_WORK(&drvdata->tx.work, ps2_gpio_tx_work_fn); + init_completion(&drvdata->tx.complete); + mutex_init(&drvdata->tx.mutex); serio_register_port(serio); platform_set_drvdata(pdev, drvdata); diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index ff7794cecf69..43c7d6e5bdc0 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -638,6 +638,16 @@ config TOUCHSCREEN_MTOUCH To compile this driver as a module, choose M here: the module will be called mtouch. +config TOUCHSCREEN_IMAGIS + tristate "Imagis touchscreen support" + depends on I2C + help + Say Y here if you have an Imagis IST30xxC touchscreen. + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called imagis. + config TOUCHSCREEN_IMX6UL_TSC tristate "Freescale i.MX6UL touchscreen controller" depends on ((OF && GPIOLIB) || COMPILE_TEST) && HAS_IOMEM diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 39a8127cf6a5..557f84fd2075 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -49,6 +49,7 @@ obj-$(CONFIG_TOUCHSCREEN_GOODIX) += goodix_ts.o obj-$(CONFIG_TOUCHSCREEN_HIDEEP) += hideep.o obj-$(CONFIG_TOUCHSCREEN_ILI210X) += ili210x.o obj-$(CONFIG_TOUCHSCREEN_ILITEK) += ilitek_ts_i2c.o +obj-$(CONFIG_TOUCHSCREEN_IMAGIS) += imagis.o obj-$(CONFIG_TOUCHSCREEN_IMX6UL_TSC) += imx6ul_tsc.o obj-$(CONFIG_TOUCHSCREEN_INEXIO) += inexio.o obj-$(CONFIG_TOUCHSCREEN_IPROC) += bcm_iproc_tsc.o diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 752e8ba4fecb..3ad9870db108 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -298,32 +298,17 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data) return -ENOMSG; } -static struct input_dev *goodix_create_pen_input(struct goodix_ts_data *ts) +static int goodix_create_pen_input(struct goodix_ts_data *ts) { struct device *dev = &ts->client->dev; struct input_dev *input; input = devm_input_allocate_device(dev); if (!input) - return NULL; - - input_alloc_absinfo(input); - if (!input->absinfo) { - input_free_device(input); - return NULL; - } - - input->absinfo[ABS_X] = ts->input_dev->absinfo[ABS_MT_POSITION_X]; - input->absinfo[ABS_Y] = ts->input_dev->absinfo[ABS_MT_POSITION_Y]; - __set_bit(ABS_X, input->absbit); - __set_bit(ABS_Y, input->absbit); - input_set_abs_params(input, ABS_PRESSURE, 0, 255, 0, 0); + return -ENOMEM; - input_set_capability(input, EV_KEY, BTN_TOUCH); - input_set_capability(input, EV_KEY, BTN_TOOL_PEN); - input_set_capability(input, EV_KEY, BTN_STYLUS); - input_set_capability(input, EV_KEY, BTN_STYLUS2); - __set_bit(INPUT_PROP_DIRECT, input->propbit); + input_copy_abs(input, ABS_X, ts->input_dev, ABS_MT_POSITION_X); + input_copy_abs(input, ABS_Y, ts->input_dev, ABS_MT_POSITION_Y); /* * The resolution of these touchscreens is about 10 units/mm, the actual * resolution does not matter much since we set INPUT_PROP_DIRECT. @@ -331,6 +316,13 @@ static struct input_dev *goodix_create_pen_input(struct goodix_ts_data *ts) */ input_abs_set_res(input, ABS_X, 10); input_abs_set_res(input, ABS_Y, 10); + input_set_abs_params(input, ABS_PRESSURE, 0, 255, 0, 0); + + input_set_capability(input, EV_KEY, BTN_TOUCH); + input_set_capability(input, EV_KEY, BTN_TOOL_PEN); + input_set_capability(input, EV_KEY, BTN_STYLUS); + input_set_capability(input, EV_KEY, BTN_STYLUS2); + __set_bit(INPUT_PROP_DIRECT, input->propbit); input->name = "Goodix Active Pen"; input->phys = "input/pen"; @@ -340,25 +332,23 @@ static struct input_dev *goodix_create_pen_input(struct goodix_ts_data *ts) input->id.product = 0x1001; input->id.version = ts->version; - if (input_register_device(input) != 0) { - input_free_device(input); - return NULL; - } - - return input; + ts->input_pen = input; + return 0; } static void goodix_ts_report_pen_down(struct goodix_ts_data *ts, u8 *data) { - int input_x, input_y, input_w; + int input_x, input_y, input_w, error; u8 key_value; - if (!ts->input_pen) { - ts->input_pen = goodix_create_pen_input(ts); - if (!ts->input_pen) - return; + if (!ts->pen_input_registered) { + error = input_register_device(ts->input_pen); + ts->pen_input_registered = (error == 0) ? 1 : error; } + if (ts->pen_input_registered < 0) + return; + if (ts->contact_size == 9) { input_x = get_unaligned_le16(&data[4]); input_y = get_unaligned_le16(&data[6]); @@ -1215,6 +1205,17 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) return error; } + /* + * Create the input_pen device before goodix_request_irq() calls + * devm_request_threaded_irq() so that the devm framework frees + * it after disabling the irq. + * Unfortunately there is no way to detect if the touchscreen has pen + * support, so registering the dev is delayed till the first pen event. + */ + error = goodix_create_pen_input(ts); + if (error) + return error; + ts->irq_flags = goodix_irq_flags[ts->int_trigger_type] | IRQF_ONESHOT; error = goodix_request_irq(ts); if (error) { diff --git a/drivers/input/touchscreen/goodix.h b/drivers/input/touchscreen/goodix.h index fa8602e78a64..87797cc88b32 100644 --- a/drivers/input/touchscreen/goodix.h +++ b/drivers/input/touchscreen/goodix.h @@ -94,6 +94,7 @@ struct goodix_ts_data { u16 version; bool reset_controller_at_probe; bool load_cfg_from_disk; + int pen_input_registered; struct completion firmware_loading_complete; unsigned long irq_flags; enum goodix_irq_pin_access_method irq_pin_access_method; diff --git a/drivers/input/touchscreen/imagis.c b/drivers/input/touchscreen/imagis.c new file mode 100644 index 000000000000..e2697e6c6d2a --- /dev/null +++ b/drivers/input/touchscreen/imagis.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bits.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/input.h> +#include <linux/input/mt.h> +#include <linux/input/touchscreen.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/property.h> +#include <linux/regulator/consumer.h> + +#define IST3038C_HIB_ACCESS (0x800B << 16) +#define IST3038C_DIRECT_ACCESS BIT(31) +#define IST3038C_REG_CHIPID 0x40001000 +#define IST3038C_REG_HIB_BASE 0x30000100 +#define IST3038C_REG_TOUCH_STATUS (IST3038C_REG_HIB_BASE | IST3038C_HIB_ACCESS) +#define IST3038C_REG_TOUCH_COORD (IST3038C_REG_HIB_BASE | IST3038C_HIB_ACCESS | 0x8) +#define IST3038C_REG_INTR_MESSAGE (IST3038C_REG_HIB_BASE | IST3038C_HIB_ACCESS | 0x4) +#define IST3038C_WHOAMI 0x38c +#define IST3038C_CHIP_ON_DELAY_MS 60 +#define IST3038C_I2C_RETRY_COUNT 3 +#define IST3038C_MAX_FINGER_NUM 10 +#define IST3038C_X_MASK GENMASK(23, 12) +#define IST3038C_X_SHIFT 12 +#define IST3038C_Y_MASK GENMASK(11, 0) +#define IST3038C_AREA_MASK GENMASK(27, 24) +#define IST3038C_AREA_SHIFT 24 +#define IST3038C_FINGER_COUNT_MASK GENMASK(15, 12) +#define IST3038C_FINGER_COUNT_SHIFT 12 +#define IST3038C_FINGER_STATUS_MASK GENMASK(9, 0) + +struct imagis_ts { + struct i2c_client *client; + struct input_dev *input_dev; + struct touchscreen_properties prop; + struct regulator_bulk_data supplies[2]; +}; + +static int imagis_i2c_read_reg(struct imagis_ts *ts, + unsigned int reg, u32 *data) +{ + __be32 ret_be; + __be32 reg_be = cpu_to_be32(reg); + struct i2c_msg msg[] = { + { + .addr = ts->client->addr, + .flags = 0, + .buf = (unsigned char *)®_be, + .len = sizeof(reg_be), + }, { + .addr = ts->client->addr, + .flags = I2C_M_RD, + .buf = (unsigned char *)&ret_be, + .len = sizeof(ret_be), + }, + }; + int ret, error; + int retry = IST3038C_I2C_RETRY_COUNT; + + /* Retry in case the controller fails to respond */ + do { + ret = i2c_transfer(ts->client->adapter, msg, ARRAY_SIZE(msg)); + if (ret == ARRAY_SIZE(msg)) { + *data = be32_to_cpu(ret_be); + return 0; + } + + error = ret < 0 ? ret : -EIO; + dev_err(&ts->client->dev, + "%s - i2c_transfer failed: %d (%d)\n", + __func__, error, ret); + } while (--retry); + + return error; +} + +static irqreturn_t imagis_interrupt(int irq, void *dev_id) +{ + struct imagis_ts *ts = dev_id; + u32 intr_message, finger_status; + unsigned int finger_count, finger_pressed; + int i; + int error; + + error = imagis_i2c_read_reg(ts, IST3038C_REG_INTR_MESSAGE, + &intr_message); + if (error) { + dev_err(&ts->client->dev, + "failed to read the interrupt message: %d\n", error); + goto out; + } + + finger_count = (intr_message & IST3038C_FINGER_COUNT_MASK) >> + IST3038C_FINGER_COUNT_SHIFT; + if (finger_count > IST3038C_MAX_FINGER_NUM) { + dev_err(&ts->client->dev, + "finger count %d is more than maximum supported\n", + finger_count); + goto out; + } + + finger_pressed = intr_message & IST3038C_FINGER_STATUS_MASK; + + for (i = 0; i < finger_count; i++) { + error = imagis_i2c_read_reg(ts, + IST3038C_REG_TOUCH_COORD + (i * 4), + &finger_status); + if (error) { + dev_err(&ts->client->dev, + "failed to read coordinates for finger %d: %d\n", + i, error); + goto out; + } + + input_mt_slot(ts->input_dev, i); + input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, + finger_pressed & BIT(i)); + touchscreen_report_pos(ts->input_dev, &ts->prop, + (finger_status & IST3038C_X_MASK) >> + IST3038C_X_SHIFT, + finger_status & IST3038C_Y_MASK, 1); + input_report_abs(ts->input_dev, ABS_MT_TOUCH_MAJOR, + (finger_status & IST3038C_AREA_MASK) >> + IST3038C_AREA_SHIFT); + } + + input_mt_sync_frame(ts->input_dev); + input_sync(ts->input_dev); + +out: + return IRQ_HANDLED; +} + +static void imagis_power_off(void *_ts) +{ + struct imagis_ts *ts = _ts; + + regulator_bulk_disable(ARRAY_SIZE(ts->supplies), ts->supplies); +} + +static int imagis_power_on(struct imagis_ts *ts) +{ + int error; + + error = regulator_bulk_enable(ARRAY_SIZE(ts->supplies), ts->supplies); + if (error) + return error; + + msleep(IST3038C_CHIP_ON_DELAY_MS); + + return 0; +} + +static int imagis_start(struct imagis_ts *ts) +{ + int error; + + error = imagis_power_on(ts); + if (error) + return error; + + enable_irq(ts->client->irq); + + return 0; +} + +static int imagis_stop(struct imagis_ts *ts) +{ + disable_irq(ts->client->irq); + + imagis_power_off(ts); + + return 0; +} + +static int imagis_input_open(struct input_dev *dev) +{ + struct imagis_ts *ts = input_get_drvdata(dev); + + return imagis_start(ts); +} + +static void imagis_input_close(struct input_dev *dev) +{ + struct imagis_ts *ts = input_get_drvdata(dev); + + imagis_stop(ts); +} + +static int imagis_init_input_dev(struct imagis_ts *ts) +{ + struct input_dev *input_dev; + int error; + + input_dev = devm_input_allocate_device(&ts->client->dev); + if (!input_dev) + return -ENOMEM; + + ts->input_dev = input_dev; + + input_dev->name = "Imagis capacitive touchscreen"; + input_dev->phys = "input/ts"; + input_dev->id.bustype = BUS_I2C; + input_dev->open = imagis_input_open; + input_dev->close = imagis_input_close; + + input_set_drvdata(input_dev, ts); + + input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_X); + input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_Y); + input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); + + touchscreen_parse_properties(input_dev, true, &ts->prop); + if (!ts->prop.max_x || !ts->prop.max_y) { + dev_err(&ts->client->dev, + "Touchscreen-size-x and/or touchscreen-size-y not set in dts\n"); + return -EINVAL; + } + + error = input_mt_init_slots(input_dev, + IST3038C_MAX_FINGER_NUM, + INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); + if (error) { + dev_err(&ts->client->dev, + "Failed to initialize MT slots: %d", error); + return error; + } + + error = input_register_device(input_dev); + if (error) { + dev_err(&ts->client->dev, + "Failed to register input device: %d", error); + return error; + } + + return 0; +} + +static int imagis_init_regulators(struct imagis_ts *ts) +{ + struct i2c_client *client = ts->client; + + ts->supplies[0].supply = "vdd"; + ts->supplies[1].supply = "vddio"; + return devm_regulator_bulk_get(&client->dev, + ARRAY_SIZE(ts->supplies), + ts->supplies); +} + +static int imagis_probe(struct i2c_client *i2c) +{ + struct device *dev = &i2c->dev; + struct imagis_ts *ts; + int chip_id, error; + + ts = devm_kzalloc(dev, sizeof(*ts), GFP_KERNEL); + if (!ts) + return -ENOMEM; + + ts->client = i2c; + + error = imagis_init_regulators(ts); + if (error) { + dev_err(dev, "regulator init error: %d\n", error); + return error; + } + + error = imagis_power_on(ts); + if (error) { + dev_err(dev, "failed to enable regulators: %d\n", error); + return error; + } + + error = devm_add_action_or_reset(dev, imagis_power_off, ts); + if (error) { + dev_err(dev, "failed to install poweroff action: %d\n", error); + return error; + } + + error = imagis_i2c_read_reg(ts, + IST3038C_REG_CHIPID | IST3038C_DIRECT_ACCESS, + &chip_id); + if (error) { + dev_err(dev, "chip ID read failure: %d\n", error); + return error; + } + + if (chip_id != IST3038C_WHOAMI) { + dev_err(dev, "unknown chip ID: 0x%x\n", chip_id); + return -EINVAL; + } + + error = devm_request_threaded_irq(dev, i2c->irq, + NULL, imagis_interrupt, + IRQF_ONESHOT | IRQF_NO_AUTOEN, + "imagis-touchscreen", ts); + if (error) { + dev_err(dev, "IRQ %d allocation failure: %d\n", + i2c->irq, error); + return error; + } + + error = imagis_init_input_dev(ts); + if (error) + return error; + + return 0; +} + +static int __maybe_unused imagis_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct imagis_ts *ts = i2c_get_clientdata(client); + int retval = 0; + + mutex_lock(&ts->input_dev->mutex); + + if (input_device_enabled(ts->input_dev)) + retval = imagis_stop(ts); + + mutex_unlock(&ts->input_dev->mutex); + + return retval; +} + +static int __maybe_unused imagis_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + struct imagis_ts *ts = i2c_get_clientdata(client); + int retval = 0; + + mutex_lock(&ts->input_dev->mutex); + + if (input_device_enabled(ts->input_dev)) + retval = imagis_start(ts); + + mutex_unlock(&ts->input_dev->mutex); + + return retval; +} + +static SIMPLE_DEV_PM_OPS(imagis_pm_ops, imagis_suspend, imagis_resume); + +#ifdef CONFIG_OF +static const struct of_device_id imagis_of_match[] = { + { .compatible = "imagis,ist3038c", }, + { }, +}; +MODULE_DEVICE_TABLE(of, imagis_of_match); +#endif + +static struct i2c_driver imagis_ts_driver = { + .driver = { + .name = "imagis-touchscreen", + .pm = &imagis_pm_ops, + .of_match_table = of_match_ptr(imagis_of_match), + }, + .probe_new = imagis_probe, +}; + +module_i2c_driver(imagis_ts_driver); + +MODULE_DESCRIPTION("Imagis IST3038C Touchscreen Driver"); +MODULE_AUTHOR("Markuss Broks <markuss.broks@gmail.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/input/touchscreen/iqs5xx.c b/drivers/input/touchscreen/iqs5xx.c index b3fa71213d60..34c4cca57d13 100644 --- a/drivers/input/touchscreen/iqs5xx.c +++ b/drivers/input/touchscreen/iqs5xx.c @@ -486,11 +486,11 @@ static int iqs5xx_axis_init(struct i2c_client *client) { struct iqs5xx_private *iqs5xx = i2c_get_clientdata(client); struct touchscreen_properties *prop = &iqs5xx->prop; - struct input_dev *input; + struct input_dev *input = iqs5xx->input; u16 max_x, max_y; int error; - if (!iqs5xx->input) { + if (!input) { input = devm_input_allocate_device(&client->dev); if (!input) return -ENOMEM; @@ -512,11 +512,11 @@ static int iqs5xx_axis_init(struct i2c_client *client) if (error) return error; - input_set_abs_params(iqs5xx->input, ABS_MT_POSITION_X, 0, max_x, 0, 0); - input_set_abs_params(iqs5xx->input, ABS_MT_POSITION_Y, 0, max_y, 0, 0); - input_set_abs_params(iqs5xx->input, ABS_MT_PRESSURE, 0, U16_MAX, 0, 0); + input_set_abs_params(input, ABS_MT_POSITION_X, 0, max_x, 0, 0); + input_set_abs_params(input, ABS_MT_POSITION_Y, 0, max_y, 0, 0); + input_set_abs_params(input, ABS_MT_PRESSURE, 0, U16_MAX, 0, 0); - touchscreen_parse_properties(iqs5xx->input, true, prop); + touchscreen_parse_properties(input, true, prop); /* * The device reserves 0xFFFF for coordinates that correspond to slots @@ -540,7 +540,7 @@ static int iqs5xx_axis_init(struct i2c_client *client) return error; } - error = input_mt_init_slots(iqs5xx->input, IQS5XX_NUM_CONTACTS, + error = input_mt_init_slots(input, IQS5XX_NUM_CONTACTS, INPUT_MT_DIRECT); if (error) dev_err(&client->dev, "Failed to initialize slots: %d\n", @@ -674,7 +674,7 @@ static irqreturn_t iqs5xx_irq(int irq, void *data) input_mt_slot(input, i); if (input_mt_report_slot_state(input, MT_TOOL_FINGER, pressure != 0)) { - touchscreen_report_pos(iqs5xx->input, &iqs5xx->prop, + touchscreen_report_pos(input, &iqs5xx->prop, be16_to_cpu(touch_data->abs_x), be16_to_cpu(touch_data->abs_y), true); diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c index bc11203c9cf7..72e0b767e1ba 100644 --- a/drivers/input/touchscreen/stmfts.c +++ b/drivers/input/touchscreen/stmfts.c @@ -339,11 +339,11 @@ static int stmfts_input_open(struct input_dev *dev) err = pm_runtime_get_sync(&sdata->client->dev); if (err < 0) - return err; + goto out; err = i2c_smbus_write_byte(sdata->client, STMFTS_MS_MT_SENSE_ON); if (err) - return err; + goto out; mutex_lock(&sdata->mutex); sdata->running = true; @@ -366,7 +366,9 @@ static int stmfts_input_open(struct input_dev *dev) "failed to enable touchkey\n"); } - return 0; +out: + pm_runtime_put_noidle(&sdata->client->dev); + return err; } static void stmfts_input_close(struct input_dev *dev) diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c index 27810f6c69f6..72c7258b93a5 100644 --- a/drivers/input/touchscreen/tsc200x-core.c +++ b/drivers/input/touchscreen/tsc200x-core.c @@ -88,6 +88,8 @@ struct tsc200x { int in_z1; int in_z2; + struct touchscreen_properties prop; + spinlock_t lock; struct timer_list penup_timer; @@ -113,8 +115,7 @@ static void tsc200x_update_pen_state(struct tsc200x *ts, int x, int y, int pressure) { if (pressure) { - input_report_abs(ts->idev, ABS_X, x); - input_report_abs(ts->idev, ABS_Y, y); + touchscreen_report_pos(ts->idev, &ts->prop, x, y, false); input_report_abs(ts->idev, ABS_PRESSURE, pressure); if (!ts->pen_down) { input_report_key(ts->idev, BTN_TOUCH, !!pressure); @@ -533,7 +534,7 @@ int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, input_set_abs_params(input_dev, ABS_PRESSURE, 0, MAX_12BIT, TSC200X_DEF_P_FUZZ, 0); - touchscreen_parse_properties(input_dev, false, NULL); + touchscreen_parse_properties(input_dev, false, &ts->prop); /* Ensure the touchscreen is off */ tsc200x_stop_scan(ts); diff --git a/drivers/input/vivaldi-fmap.c b/drivers/input/vivaldi-fmap.c new file mode 100644 index 000000000000..6dae83d96806 --- /dev/null +++ b/drivers/input/vivaldi-fmap.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for ChromeOS Vivaldi keyboard function row mapping + * + * Copyright (C) 2022 Google, Inc + */ + +#include <linux/export.h> +#include <linux/input/vivaldi-fmap.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/types.h> + +/** + * vivaldi_function_row_physmap_show - Print vivaldi function row physmap attribute + * @data: The vivaldi function row map + * @buf: Buffer to print the function row phsymap to + */ +ssize_t vivaldi_function_row_physmap_show(const struct vivaldi_data *data, + char *buf) +{ + ssize_t size = 0; + int i; + const u32 *physmap = data->function_row_physmap; + + if (!data->num_function_row_keys) + return 0; + + for (i = 0; i < data->num_function_row_keys; i++) + size += scnprintf(buf + size, PAGE_SIZE - size, + "%s%02X", size ? " " : "", physmap[i]); + if (size) + size += scnprintf(buf + size, PAGE_SIZE - size, "\n"); + + return size; +} +EXPORT_SYMBOL_GPL(vivaldi_function_row_physmap_show); + +MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 4aab631ef517..d9cf2820c02e 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1661,7 +1661,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus", sizeof(phandle)); if (num_iommus < 0) - return 0; + return ERR_PTR(-ENODEV); arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL); if (!arch_data) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 680d2fcf2686..15edb9a6fcae 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -433,6 +433,7 @@ config QCOM_PDC config QCOM_MPM tristate "QCOM MPM" depends on ARCH_QCOM + depends on MAILBOX select IRQ_DOMAIN_HIERARCHY help MSM Power Manager driver to manage and configure wakeup diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cd772973114a..a0fc764ec9dc 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3011,18 +3011,12 @@ static int __init allocate_lpi_tables(void) return 0; } -static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +static u64 read_vpend_dirty_clear(void __iomem *vlpi_base) { u32 count = 1000000; /* 1s! */ bool clean; u64 val; - val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - val &= ~clr; - val |= set; - gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - do { val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); @@ -3033,10 +3027,26 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) } } while (!clean && count); - if (unlikely(val & GICR_VPENDBASER_Dirty)) { + if (unlikely(!clean)) pr_err_ratelimited("ITS virtual pending table not cleaning\n"); + + return val; +} + +static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +{ + u64 val; + + /* Make sure we wait until the RD is done with the initial scan */ + val = read_vpend_dirty_clear(vlpi_base); + val &= ~GICR_VPENDBASER_Valid; + val &= ~clr; + val |= set; + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + val = read_vpend_dirty_clear(vlpi_base); + if (unlikely(val & GICR_VPENDBASER_Dirty)) val |= GICR_VPENDBASER_PendingLast; - } return val; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 0efe1a9a9f3b..b252d5534547 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -206,11 +206,11 @@ static inline void __iomem *gic_dist_base(struct irq_data *d) } } -static void gic_do_wait_for_rwp(void __iomem *base) +static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 count = 1000000; /* 1s! */ - while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) { + while (readl_relaxed(base + GICD_CTLR) & bit) { count--; if (!count) { pr_err_ratelimited("RWP timeout, gone fishing\n"); @@ -224,13 +224,13 @@ static void gic_do_wait_for_rwp(void __iomem *base) /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data.dist_base); + gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data_rdist_rd_base()); + gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } #ifdef CONFIG_ARM64 @@ -1466,6 +1466,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 58ba835bee1f..09c710ecc387 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -1123,6 +1123,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c index eea5a753618c..d30614661eea 100644 --- a/drivers/irqchip/irq-qcom-mpm.c +++ b/drivers/irqchip/irq-qcom-mpm.c @@ -375,7 +375,7 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent) raw_spin_lock_init(&priv->lock); priv->base = devm_platform_ioremap_resource(pdev, 0); - if (!priv->base) + if (IS_ERR(priv->base)) return PTR_ERR(priv->base); for (i = 0; i < priv->reg_stride; i++) { diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 4081cb6cf7b3..4277853c7535 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -210,7 +210,7 @@ struct dm_table { #define DM_TIO_MAGIC 28714 struct dm_target_io { unsigned short magic; - unsigned short flags; + blk_short_t flags; unsigned int target_bio_nr; struct dm_io *io; struct dm_target *ti; @@ -244,7 +244,7 @@ static inline void dm_tio_set_flag(struct dm_target_io *tio, unsigned int bit) #define DM_IO_MAGIC 19577 struct dm_io { unsigned short magic; - unsigned short flags; + blk_short_t flags; atomic_t io_count; struct mapped_device *md; struct bio *orig_bio; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index c58a5111cb57..36ae30b73a6e 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2472,9 +2472,11 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start, dm_integrity_io_error(ic, "invalid sector in journal", -EIO); sec &= ~(sector_t)(ic->sectors_per_block - 1); } + if (unlikely(sec >= ic->provided_data_sectors)) { + journal_entry_set_unused(je); + continue; + } } - if (unlikely(sec >= ic->provided_data_sectors)) - continue; get_area_and_offset(ic, sec, &area, &offset); restore_last_bytes(ic, access_journal_data(ic, i, j), je); for (k = j + 1; k < ic->journal_section_entries; k++) { @@ -4397,6 +4399,7 @@ try_smaller_buffer: } if (ic->internal_hash) { + size_t recalc_tags_size; ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1); if (!ic->recalc_wq ) { ti->error = "Cannot allocate workqueue"; @@ -4410,8 +4413,10 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } - ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block, - ic->tag_size, GFP_KERNEL); + recalc_tags_size = (RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size; + if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size) + recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size; + ic->recalc_tags = kvmalloc(recalc_tags_size, GFP_KERNEL); if (!ic->recalc_tags) { ti->error = "Cannot allocate tags for recalculating"; r = -ENOMEM; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 901abd6dea41..87310fceb0d8 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -891,15 +891,21 @@ static struct hash_cell *__find_device_hash_cell(struct dm_ioctl *param) struct hash_cell *hc = NULL; if (*param->uuid) { - if (*param->name || param->dev) + if (*param->name || param->dev) { + DMERR("Invalid ioctl structure: uuid %s, name %s, dev %llx", + param->uuid, param->name, (unsigned long long)param->dev); return NULL; + } hc = __get_uuid_cell(param->uuid); if (!hc) return NULL; } else if (*param->name) { - if (param->dev) + if (param->dev) { + DMERR("Invalid ioctl structure: name %s, dev %llx", + param->name, (unsigned long long)param->dev); return NULL; + } hc = __get_name_cell(param->name); if (!hc) @@ -1851,8 +1857,11 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern if (copy_from_user(param_kernel, user, minimum_data_size)) return -EFAULT; - if (param_kernel->data_size < minimum_data_size) + if (param_kernel->data_size < minimum_data_size) { + DMERR("Invalid data size in the ioctl structure: %u", + param_kernel->data_size); return -EINVAL; + } secure_data = param_kernel->flags & DM_SECURE_DATA_FLAG; diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index 875bca30a0dd..82f2a06153dc 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -27,7 +27,6 @@ #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/module.h> -#include <linux/sched/clock.h> #define DM_MSG_PREFIX "multipath historical-service-time" @@ -433,7 +432,7 @@ static struct dm_path *hst_select_path(struct path_selector *ps, { struct selector *s = ps->context; struct path_info *pi = NULL, *best = NULL; - u64 time_now = sched_clock(); + u64 time_now = ktime_get_ns(); struct dm_path *ret = NULL; unsigned long flags; @@ -474,7 +473,7 @@ static int hst_start_io(struct path_selector *ps, struct dm_path *path, static u64 path_service_time(struct path_info *pi, u64 start_time) { - u64 sched_now = ktime_get_ns(); + u64 now = ktime_get_ns(); /* if a previous disk request has finished after this IO was * sent to the hardware, pretend the submission happened @@ -483,11 +482,11 @@ static u64 path_service_time(struct path_info *pi, u64 start_time) if (time_after64(pi->last_finish, start_time)) start_time = pi->last_finish; - pi->last_finish = sched_now; - if (time_before64(sched_now, start_time)) + pi->last_finish = now; + if (time_before64(now, start_time)) return 0; - return sched_now - start_time; + return now - start_time; } static int hst_end_io(struct path_selector *ps, struct dm_path *path, diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index c1ca9be4b79e..57daa86c19cf 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -360,16 +360,20 @@ static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno, return 0; } +struct orig_bio_details { + unsigned int op; + unsigned int nr_sectors; +}; + /* * First phase of BIO mapping for targets with zone append emulation: * check all BIO that change a zone writer pointer and change zone * append operations into regular write operations. */ static bool dm_zone_map_bio_begin(struct mapped_device *md, - struct bio *orig_bio, struct bio *clone) + unsigned int zno, struct bio *clone) { sector_t zsectors = blk_queue_zone_sectors(md->queue); - unsigned int zno = bio_zone_no(orig_bio); unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); /* @@ -384,7 +388,7 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, WRITE_ONCE(md->zwp_offset[zno], zwp_offset); } - switch (bio_op(orig_bio)) { + switch (bio_op(clone)) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: return true; @@ -401,9 +405,8 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, * target zone. */ clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE | - (orig_bio->bi_opf & (~REQ_OP_MASK)); - clone->bi_iter.bi_sector = - orig_bio->bi_iter.bi_sector + zwp_offset; + (clone->bi_opf & (~REQ_OP_MASK)); + clone->bi_iter.bi_sector += zwp_offset; break; default: DMWARN_LIMIT("Invalid BIO operation"); @@ -423,11 +426,10 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, * data written to a zone. Note that at this point, the remapped clone BIO * may already have completed, so we do not touch it. */ -static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, - struct bio *orig_bio, +static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno, + struct orig_bio_details *orig_bio_details, unsigned int nr_sectors) { - unsigned int zno = bio_zone_no(orig_bio); unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); /* The clone BIO may already have been completed and failed */ @@ -435,7 +437,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, return BLK_STS_IOERR; /* Update the zone wp offset */ - switch (bio_op(orig_bio)) { + switch (orig_bio_details->op) { case REQ_OP_ZONE_RESET: WRITE_ONCE(md->zwp_offset[zno], 0); return BLK_STS_OK; @@ -452,7 +454,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, * Check that the target did not truncate the write operation * emulating a zone append. */ - if (nr_sectors != bio_sectors(orig_bio)) { + if (nr_sectors != orig_bio_details->nr_sectors) { DMWARN_LIMIT("Truncated write for zone append"); return BLK_STS_IOERR; } @@ -488,7 +490,7 @@ static inline void dm_zone_unlock(struct request_queue *q, bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED); } -static bool dm_need_zone_wp_tracking(struct bio *orig_bio) +static bool dm_need_zone_wp_tracking(struct bio *bio) { /* * Special processing is not needed for operations that do not need the @@ -496,15 +498,15 @@ static bool dm_need_zone_wp_tracking(struct bio *orig_bio) * zones and all operations that do not modify directly a sequential * zone write pointer. */ - if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio)) + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; - switch (bio_op(orig_bio)) { + switch (bio_op(bio)) { case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_APPEND: - return bio_zone_is_seq(orig_bio); + return bio_zone_is_seq(bio); default: return false; } @@ -519,8 +521,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) struct dm_target *ti = tio->ti; struct mapped_device *md = io->md; struct request_queue *q = md->queue; - struct bio *orig_bio = io->orig_bio; struct bio *clone = &tio->clone; + struct orig_bio_details orig_bio_details; unsigned int zno; blk_status_t sts; int r; @@ -529,18 +531,21 @@ int dm_zone_map_bio(struct dm_target_io *tio) * IOs that do not change a zone write pointer do not need * any additional special processing. */ - if (!dm_need_zone_wp_tracking(orig_bio)) + if (!dm_need_zone_wp_tracking(clone)) return ti->type->map(ti, clone); /* Lock the target zone */ - zno = bio_zone_no(orig_bio); + zno = bio_zone_no(clone); dm_zone_lock(q, zno, clone); + orig_bio_details.nr_sectors = bio_sectors(clone); + orig_bio_details.op = bio_op(clone); + /* * Check that the bio and the target zone write pointer offset are * both valid, and if the bio is a zone append, remap it to a write. */ - if (!dm_zone_map_bio_begin(md, orig_bio, clone)) { + if (!dm_zone_map_bio_begin(md, zno, clone)) { dm_zone_unlock(q, zno, clone); return DM_MAPIO_KILL; } @@ -560,7 +565,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) * The target submitted the clone BIO. The target zone will * be unlocked on completion of the clone. */ - sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, + *tio->len_ptr); break; case DM_MAPIO_REMAPPED: /* @@ -568,7 +574,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) * unlock the target zone here as the clone will not be * submitted. */ - sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, + *tio->len_ptr); if (sts != BLK_STS_OK) dm_zone_unlock(q, zno, clone); break; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ad2e0bbeb559..82957bd460e8 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -892,13 +892,19 @@ static void dm_io_complete(struct dm_io *io) if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); - if (io_error == BLK_STS_DM_REQUEUE) { - /* - * Upper layer won't help us poll split bio, io->orig_bio - * may only reflect a subset of the pre-split original, - * so clear REQ_POLLED in case of requeue - */ - bio->bi_opf &= ~REQ_POLLED; + if (io_error == BLK_STS_DM_REQUEUE || io_error == BLK_STS_AGAIN) { + if (bio->bi_opf & REQ_POLLED) { + /* + * Upper layer won't help us poll split bio (io->orig_bio + * may only reflect a subset of the pre-split original) + * so clear REQ_POLLED in case of requeue. + */ + bio->bi_opf &= ~REQ_POLLED; + if (io_error == BLK_STS_AGAIN) { + /* io_uring doesn't handle BLK_STS_AGAIN (yet) */ + queue_io(md, bio); + } + } return; } @@ -1317,8 +1323,7 @@ static void __map_bio(struct bio *clone) } static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, - struct dm_target *ti, unsigned num_bios, - unsigned *len) + struct dm_target *ti, unsigned num_bios) { struct bio *bio; int try; @@ -1329,7 +1334,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, if (try) mutex_lock(&ci->io->md->table_devices_lock); for (bio_nr = 0; bio_nr < num_bios; bio_nr++) { - bio = alloc_tio(ci, ti, bio_nr, len, + bio = alloc_tio(ci, ti, bio_nr, NULL, try ? GFP_NOIO : GFP_NOWAIT); if (!bio) break; @@ -1357,11 +1362,11 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, break; case 1: clone = alloc_tio(ci, ti, 0, len, GFP_NOIO); - dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); __map_bio(clone); break; default: - alloc_multiple_bios(&blist, ci, ti, num_bios, len); + /* dm_accept_partial_bio() is not supported with shared tio->len_ptr */ + alloc_multiple_bios(&blist, ci, ti, num_bios); while ((clone = bio_list_pop(&blist))) { dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); __map_bio(clone); @@ -1386,6 +1391,7 @@ static void __send_empty_flush(struct clone_info *ci) ci->bio = &flush_bio; ci->sector_count = 0; + ci->io->tio.clone.bi_iter.bi_size = 0; while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); @@ -1401,14 +1407,10 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target len = min_t(sector_t, ci->sector_count, max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector))); - /* - * dm_accept_partial_bio cannot be used with duplicate bios, - * so update clone_info cursor before __send_duplicate_bios(). - */ + __send_duplicate_bios(ci, ti, num_bios, &len); + ci->sector += len; ci->sector_count -= len; - - __send_duplicate_bios(ci, ti, num_bios, &len); } static bool is_abnormal_io(struct bio *bio) diff --git a/drivers/media/platform/nxp/Kconfig b/drivers/media/platform/nxp/Kconfig index 28f2bafc14d2..5afa373e534f 100644 --- a/drivers/media/platform/nxp/Kconfig +++ b/drivers/media/platform/nxp/Kconfig @@ -7,6 +7,7 @@ comment "NXP media platform drivers" config VIDEO_IMX_MIPI_CSIS tristate "NXP MIPI CSI-2 CSIS receiver found on i.MX7 and i.MX8 models" depends on ARCH_MXC || COMPILE_TEST + depends on VIDEO_DEV select MEDIA_CONTROLLER select V4L2_FWNODE select VIDEO_V4L2_SUBDEV_API diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index 4de5e8d2b261..3d3d1062e212 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -892,7 +892,7 @@ static int rga_probe(struct platform_device *pdev) } rga->dst_mmu_pages = (unsigned int *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 3); - if (rga->dst_mmu_pages) { + if (!rga->dst_mmu_pages) { ret = -ENOMEM; goto free_src_pages; } diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index 47029746b89e..0de587b412d4 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -77,16 +77,16 @@ err_mutex_unlock: } static const struct si2157_tuner_info si2157_tuners[] = { - { SI2141, false, 0x60, SI2141_60_FIRMWARE, SI2141_A10_FIRMWARE }, - { SI2141, false, 0x61, SI2141_61_FIRMWARE, SI2141_A10_FIRMWARE }, - { SI2146, false, 0x11, SI2146_11_FIRMWARE, NULL }, - { SI2147, false, 0x50, SI2147_50_FIRMWARE, NULL }, - { SI2148, true, 0x32, SI2148_32_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2148, true, 0x33, SI2148_33_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2157, false, 0x50, SI2157_50_FIRMWARE, SI2157_A30_FIRMWARE }, - { SI2158, false, 0x50, SI2158_50_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2158, false, 0x51, SI2158_51_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2177, false, 0x50, SI2177_50_FIRMWARE, SI2157_A30_FIRMWARE }, + { SI2141, 0x60, false, SI2141_60_FIRMWARE, SI2141_A10_FIRMWARE }, + { SI2141, 0x61, false, SI2141_61_FIRMWARE, SI2141_A10_FIRMWARE }, + { SI2146, 0x11, false, SI2146_11_FIRMWARE, NULL }, + { SI2147, 0x50, false, SI2147_50_FIRMWARE, NULL }, + { SI2148, 0x32, true, SI2148_32_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2148, 0x33, true, SI2148_33_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2157, 0x50, false, SI2157_50_FIRMWARE, SI2157_A30_FIRMWARE }, + { SI2158, 0x50, false, SI2158_50_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2158, 0x51, false, SI2158_51_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2177, 0x50, false, SI2177_50_FIRMWARE, SI2157_A30_FIRMWARE }, }; static int si2157_load_firmware(struct dvb_frontend *fe, @@ -178,7 +178,7 @@ static int si2157_find_and_load_firmware(struct dvb_frontend *fe) } } - if (!fw_name && !fw_alt_name) { + if (required && !fw_name && !fw_alt_name) { dev_err(&client->dev, "unknown chip version Si21%d-%c%c%c ROM 0x%02x\n", part_id, cmd.args[1], cmd.args[3], cmd.args[4], rom_id); diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index c267283b01fd..e749dcb3ddea 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -544,20 +544,27 @@ static int atmel_ebi_probe(struct platform_device *pdev) smc_np = of_parse_phandle(dev->of_node, "atmel,smc", 0); ebi->smc.regmap = syscon_node_to_regmap(smc_np); - if (IS_ERR(ebi->smc.regmap)) - return PTR_ERR(ebi->smc.regmap); + if (IS_ERR(ebi->smc.regmap)) { + ret = PTR_ERR(ebi->smc.regmap); + goto put_node; + } ebi->smc.layout = atmel_hsmc_get_reg_layout(smc_np); - if (IS_ERR(ebi->smc.layout)) - return PTR_ERR(ebi->smc.layout); + if (IS_ERR(ebi->smc.layout)) { + ret = PTR_ERR(ebi->smc.layout); + goto put_node; + } ebi->smc.clk = of_clk_get(smc_np, 0); if (IS_ERR(ebi->smc.clk)) { - if (PTR_ERR(ebi->smc.clk) != -ENOENT) - return PTR_ERR(ebi->smc.clk); + if (PTR_ERR(ebi->smc.clk) != -ENOENT) { + ret = PTR_ERR(ebi->smc.clk); + goto put_node; + } ebi->smc.clk = NULL; } + of_node_put(smc_np); ret = clk_prepare_enable(ebi->smc.clk); if (ret) return ret; @@ -608,6 +615,10 @@ static int atmel_ebi_probe(struct platform_device *pdev) } return of_platform_populate(np, NULL, NULL, dev); + +put_node: + of_node_put(smc_np); + return ret; } static __maybe_unused int atmel_ebi_resume(struct device *dev) diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c index 2f6939da21cd..e83b61c925a4 100644 --- a/drivers/memory/fsl_ifc.c +++ b/drivers/memory/fsl_ifc.c @@ -287,8 +287,7 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev) } /* legacy dts may still use "simple-bus" compatible */ - ret = of_platform_populate(dev->dev.of_node, NULL, NULL, - &dev->dev); + ret = of_platform_default_populate(dev->dev.of_node, NULL, &dev->dev); if (ret) goto err_free_nandirq; diff --git a/drivers/memory/renesas-rpc-if.c b/drivers/memory/renesas-rpc-if.c index e4cc64f56019..2e545f473cc6 100644 --- a/drivers/memory/renesas-rpc-if.c +++ b/drivers/memory/renesas-rpc-if.c @@ -651,6 +651,7 @@ static int rpcif_probe(struct platform_device *pdev) struct platform_device *vdev; struct device_node *flash; const char *name; + int ret; flash = of_get_next_child(pdev->dev.of_node, NULL); if (!flash) { @@ -674,7 +675,14 @@ static int rpcif_probe(struct platform_device *pdev) return -ENOMEM; vdev->dev.parent = &pdev->dev; platform_set_drvdata(pdev, vdev); - return platform_device_add(vdev); + + ret = platform_device_add(vdev); + if (ret) { + platform_device_put(vdev); + return ret; + } + + return 0; } static int rpcif_remove(struct platform_device *pdev) diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index e90adfa57950..9b3ba2df71c7 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -6658,13 +6658,13 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v) static int mpt_version_proc_show(struct seq_file *m, void *v) { u8 cb_idx; - int scsi, fc, sas, lan, ctl, targ, dmp; + int scsi, fc, sas, lan, ctl, targ; char *drvname; seq_printf(m, "%s-%s\n", "mptlinux", MPT_LINUX_VERSION_COMMON); seq_printf(m, " Fusion MPT base driver\n"); - scsi = fc = sas = lan = ctl = targ = dmp = 0; + scsi = fc = sas = lan = ctl = targ = 0; for (cb_idx = MPT_MAX_PROTOCOL_DRIVERS-1; cb_idx; cb_idx--) { drvname = NULL; if (MptCallbacks[cb_idx]) { diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index e008d82e4ba3..a13506dd8119 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -111,10 +111,10 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, if (contiguous) { if (is_power_of_2(page_size)) - paddr = (u64) (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, - total_size, NULL, page_size); + paddr = (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, + total_size, NULL, page_size); else - paddr = (u64) (uintptr_t) gen_pool_alloc(vm->dram_pg_pool, total_size); + paddr = gen_pool_alloc(vm->dram_pg_pool, total_size); if (!paddr) { dev_err(hdev->dev, "failed to allocate %llu contiguous pages with total size of %llu\n", @@ -150,12 +150,12 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, for (i = 0 ; i < num_pgs ; i++) { if (is_power_of_2(page_size)) phys_pg_pack->pages[i] = - (u64) gen_pool_dma_alloc_align(vm->dram_pg_pool, - page_size, NULL, - page_size); + (uintptr_t)gen_pool_dma_alloc_align(vm->dram_pg_pool, + page_size, NULL, + page_size); else - phys_pg_pack->pages[i] = (u64) gen_pool_alloc(vm->dram_pg_pool, - page_size); + phys_pg_pack->pages[i] = gen_pool_alloc(vm->dram_pg_pool, + page_size); if (!phys_pg_pack->pages[i]) { dev_err(hdev->dev, "Failed to allocate device memory (out of memory)\n"); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4e67c1403cc9..506dc900f5c7 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -993,7 +993,7 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, return -EEXIST; md->reset_done |= type; - err = mmc_hw_reset(host); + err = mmc_hw_reset(host->card); /* Ensure we switch back to the correct partition */ if (err) { struct mmc_blk_data *main_md = @@ -1880,6 +1880,31 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq) brq->data.error || brq->cmd.resp[0] & CMD_ERRORS; } +static int mmc_spi_err_check(struct mmc_card *card) +{ + u32 status = 0; + int err; + + /* + * SPI does not have a TRAN state we have to wait on, instead the + * card is ready again when it no longer holds the line LOW. + * We still have to ensure two things here before we know the write + * was successful: + * 1. The card has not disconnected during busy and we actually read our + * own pull-up, thinking it was still connected, so ensure it + * still responds. + * 2. Check for any error bits, in particular R1_SPI_IDLE to catch a + * just reconnected card after being disconnected during busy. + */ + err = __mmc_send_status(card, &status, 0); + if (err) + return err; + /* All R1 and R2 bits of SPI are errors in our case */ + if (status) + return -EIO; + return 0; +} + static int mmc_blk_busy_cb(void *cb_data, bool *busy) { struct mmc_blk_busy_data *data = cb_data; @@ -1903,9 +1928,16 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) struct mmc_blk_busy_data cb_data; int err; - if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ) + if (rq_data_dir(req) == READ) return 0; + if (mmc_host_is_spi(card->host)) { + err = mmc_spi_err_check(card); + if (err) + mqrq->brq.data.bytes_xfered = 0; + return err; + } + cb_data.card = card; cb_data.status = 0; err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, @@ -2350,6 +2382,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; + bool cache_enabled = false; + bool fua_enabled = false; devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL); if (devidx < 0) { @@ -2429,13 +2463,17 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->flags |= MMC_BLK_CMD23; } - if (mmc_card_mmc(card) && - md->flags & MMC_BLK_CMD23 && + if (md->flags & MMC_BLK_CMD23 && ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || card->ext_csd.rel_sectors)) { md->flags |= MMC_BLK_REL_WR; - blk_queue_write_cache(md->queue.queue, true, true); + fua_enabled = true; + cache_enabled = true; } + if (mmc_cache_enabled(card->host)) + cache_enabled = true; + + blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled); string_get_size((u64)size, 512, STRING_UNITS_2, cap_str, sizeof(cap_str)); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 368f10405e13..c6ae16d40766 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1995,7 +1995,7 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) /** * mmc_hw_reset - reset the card in hardware - * @host: MMC host to which the card is attached + * @card: card to be reset * * Hard reset the card. This function is only for upper layers, like the * block layer or card drivers. You cannot use it in host drivers (struct @@ -2003,8 +2003,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) * * Return: 0 on success, -errno on failure */ -int mmc_hw_reset(struct mmc_host *host) +int mmc_hw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; ret = host->bus_ops->hw_reset(host); diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index e6a2fd2c6d5c..8d9bceeff986 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -2325,10 +2325,9 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; - struct mmc_host *host = card->host; int err; - err = mmc_hw_reset(host); + err = mmc_hw_reset(card); if (!err) { /* * Reset will re-enable the card's command queue, but tests diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 9c13f2c31365..4566d7fc9055 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -62,8 +62,8 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, * excepted the last element which has no constraint on idmasize */ for_each_sg(data->sg, sg, data->sg_len - 1, i) { - if (!IS_ALIGNED(data->sg->offset, sizeof(u32)) || - !IS_ALIGNED(data->sg->length, SDMMC_IDMA_BURST)) { + if (!IS_ALIGNED(sg->offset, sizeof(u32)) || + !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) { dev_err(mmc_dev(host->mmc), "unaligned scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); @@ -71,7 +71,7 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, } } - if (!IS_ALIGNED(data->sg->offset, sizeof(u32))) { + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { dev_err(mmc_dev(host->mmc), "unaligned last scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 2797a9c0f17d..ddb5ca2f559e 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -144,9 +144,9 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, return clk_get_rate(priv->clk); if (priv->clkh) { + /* HS400 with 4TAP needs different clock settings */ bool use_4tap = priv->quirks && priv->quirks->hs400_4taps; - bool need_slow_clkh = (host->mmc->ios.timing == MMC_TIMING_UHS_SDR104) || - (host->mmc->ios.timing == MMC_TIMING_MMC_HS400); + bool need_slow_clkh = host->mmc->ios.timing == MMC_TIMING_MMC_HS400; clkh_shift = use_4tap && need_slow_clkh ? 1 : 2; ref_clk = priv->clkh; } @@ -396,10 +396,10 @@ static void renesas_sdhi_hs400_complete(struct mmc_host *mmc) SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) | sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2)); - /* Set the sampling clock selection range of HS400 mode */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL, SH_MOBILE_SDHI_SCC_DTCNTL_TAPEN | - 0x4 << SH_MOBILE_SDHI_SCC_DTCNTL_TAPNUM_SHIFT); + sd_scc_read32(host, priv, + SH_MOBILE_SDHI_SCC_DTCNTL)); /* Avoid bad TAP */ if (bad_taps & BIT(priv->tap_set)) { diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 666cee4c7f7c..08e838400b52 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -241,16 +241,6 @@ static void xenon_voltage_switch(struct sdhci_host *host) { /* Wait for 5ms after set 1.8V signal enable bit */ usleep_range(5000, 5500); - - /* - * For some reason the controller's Host Control2 register reports - * the bit representing 1.8V signaling as 0 when read after it was - * written as 1. Subsequent read reports 1. - * - * Since this may cause some issues, do an empty read of the Host - * Control2 register here to circumvent this. - */ - sdhci_readw(host, SDHCI_HOST_CONTROL2); } static unsigned int xenon_get_max_clock(struct sdhci_host *host) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index a7e3eb9befb6..a32050fecabf 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -351,9 +351,6 @@ static ssize_t dev_attribute_show(struct device *dev, * we still can use 'ubi->ubi_num'. */ ubi = container_of(dev, struct ubi_device, dev); - ubi = ubi_get_device(ubi->ubi_num); - if (!ubi) - return -ENODEV; if (attr == &dev_eraseblock_size) ret = sprintf(buf, "%d\n", ubi->leb_size); @@ -382,7 +379,6 @@ static ssize_t dev_attribute_show(struct device *dev, else ret = -EINVAL; - ubi_put_device(ubi); return ret; } @@ -979,9 +975,6 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, goto out_detach; } - /* Make device "available" before it becomes accessible via sysfs */ - ubi_devices[ubi_num] = ubi; - err = uif_init(ubi); if (err) goto out_detach; @@ -1026,6 +1019,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, wake_up_process(ubi->bgt_thread); spin_unlock(&ubi->wl_lock); + ubi_devices[ubi_num] = ubi; ubi_notify_all(ubi, UBI_VOLUME_ADDED, NULL); return ubi_num; @@ -1034,7 +1028,6 @@ out_debugfs: out_uif: uif_close(ubi); out_detach: - ubi_devices[ubi_num] = NULL; ubi_wl_close(ubi); ubi_free_all_volumes(ubi); vfree(ubi->vtbl); diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 022af59906aa..6b5f1ffd961b 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -468,7 +468,9 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai, if (err == UBI_IO_FF_BITFLIPS) scrub = 1; - add_aeb(ai, free, pnum, ec, scrub); + ret = add_aeb(ai, free, pnum, ec, scrub); + if (ret) + goto out; continue; } else if (err == 0 || err == UBI_IO_BITFLIPS) { dbg_bld("Found non empty PEB:%i in pool", pnum); @@ -638,8 +640,10 @@ static int ubi_attach_fastmap(struct ubi_device *ubi, if (fm_pos >= fm_size) goto fail_bad; - add_aeb(ai, &ai->free, be32_to_cpu(fmec->pnum), - be32_to_cpu(fmec->ec), 0); + ret = add_aeb(ai, &ai->free, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 0); + if (ret) + goto fail; } /* read EC values from used list */ @@ -649,8 +653,10 @@ static int ubi_attach_fastmap(struct ubi_device *ubi, if (fm_pos >= fm_size) goto fail_bad; - add_aeb(ai, &used, be32_to_cpu(fmec->pnum), - be32_to_cpu(fmec->ec), 0); + ret = add_aeb(ai, &used, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 0); + if (ret) + goto fail; } /* read EC values from scrub list */ @@ -660,8 +666,10 @@ static int ubi_attach_fastmap(struct ubi_device *ubi, if (fm_pos >= fm_size) goto fail_bad; - add_aeb(ai, &used, be32_to_cpu(fmec->pnum), - be32_to_cpu(fmec->ec), 1); + ret = add_aeb(ai, &used, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 1); + if (ret) + goto fail; } /* read EC values from erase list */ @@ -671,8 +679,10 @@ static int ubi_attach_fastmap(struct ubi_device *ubi, if (fm_pos >= fm_size) goto fail_bad; - add_aeb(ai, &ai->erase, be32_to_cpu(fmec->pnum), - be32_to_cpu(fmec->ec), 1); + ret = add_aeb(ai, &ai->erase, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 1); + if (ret) + goto fail; } ai->mean_ec = div_u64(ai->ec_sum, ai->ec_count); diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 139ee132bfbc..1bc7b3a05604 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -56,16 +56,11 @@ static ssize_t vol_attribute_show(struct device *dev, { int ret; struct ubi_volume *vol = container_of(dev, struct ubi_volume, dev); - struct ubi_device *ubi; - - ubi = ubi_get_device(vol->ubi->ubi_num); - if (!ubi) - return -ENODEV; + struct ubi_device *ubi = vol->ubi; spin_lock(&ubi->volumes_lock); if (!ubi->volumes[vol->vol_id]) { spin_unlock(&ubi->volumes_lock); - ubi_put_device(ubi); return -ENODEV; } /* Take a reference to prevent volume removal */ @@ -103,7 +98,6 @@ static ssize_t vol_attribute_show(struct device *dev, vol->ref_count -= 1; ubi_assert(vol->ref_count >= 0); spin_unlock(&ubi->volumes_lock); - ubi_put_device(ubi); return ret; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15eddca7b4b6..38e152548126 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4027,14 +4027,19 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v return true; } -static u32 bond_ip_hash(u32 hash, struct flow_keys *flow) +static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); + /* discard lowest hash bit to deal with the common even ports pattern */ - return hash >> 1; + if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || + xmit_policy == BOND_XMIT_POLICY_ENCAP34) + return hash >> 1; + + return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize @@ -4064,7 +4069,7 @@ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const voi memcpy(&hash, &flow.ports.ports, sizeof(hash)); } - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** @@ -5259,7 +5264,7 @@ static u32 bond_sk_hash_l34(struct sock *sk) /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index a416240d001b..12c15da55664 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1681,9 +1681,6 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, break; case PHY_INTERFACE_MODE_RMII: miicfg |= GSWIP_MII_CFG_MODE_RMIIM; - - /* Configure the RMII clock as output: */ - miicfg |= GSWIP_MII_CFG_RMII_CLK; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: diff --git a/drivers/net/dsa/mv88e6xxx/port_hidden.c b/drivers/net/dsa/mv88e6xxx/port_hidden.c index b49d05f0e117..7a9f9ff6dedf 100644 --- a/drivers/net/dsa/mv88e6xxx/port_hidden.c +++ b/drivers/net/dsa/mv88e6xxx/port_hidden.c @@ -40,8 +40,9 @@ int mv88e6xxx_port_hidden_wait(struct mv88e6xxx_chip *chip) { int bit = __bf_shf(MV88E6XXX_PORT_RESERVED_1A_BUSY); - return mv88e6xxx_wait_bit(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, - MV88E6XXX_PORT_RESERVED_1A, bit, 0); + return mv88e6xxx_port_wait_bit(chip, + MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, + MV88E6XXX_PORT_RESERVED_1A, bit, 0); } int mv88e6xxx_port_hidden_read(struct mv88e6xxx_chip *chip, int block, int port, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 413b0006e9a2..9e28219b223d 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -670,6 +670,8 @@ static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); enum dsa_tag_protocol old_proto = felix->tag_proto; + bool cpu_port_active = false; + struct dsa_port *dp; int err; if (proto != DSA_TAG_PROTO_SEVILLE && @@ -677,6 +679,27 @@ static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, proto != DSA_TAG_PROTO_OCELOT_8021Q) return -EPROTONOSUPPORT; + /* We don't support multiple CPU ports, yet the DT blob may have + * multiple CPU ports defined. The first CPU port is the active one, + * the others are inactive. In this case, DSA will call + * ->change_tag_protocol() multiple times, once per CPU port. + * Since we implement the tagging protocol change towards "ocelot" or + * "seville" as effectively initializing the NPI port, what we are + * doing is effectively changing who the NPI port is to the last @cpu + * argument passed, which is an unused DSA CPU port and not the one + * that should actively pass traffic. + * Suppress DSA's calls on CPU ports that are inactive. + */ + dsa_switch_for_each_user_port(dp, ds) { + if (dp->cpu_dp->index == cpu) { + cpu_port_active = true; + break; + } + } + + if (!cpu_port_active) + return 0; + felix_del_tag_protocol(ds, cpu, old_proto); err = felix_set_tag_protocol(ds, cpu, proto); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 8d382b27e625..52a8566071ed 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -2316,7 +2316,7 @@ static int felix_pci_probe(struct pci_dev *pdev, err = dsa_register_switch(ds); if (err) { - dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err); + dev_err_probe(&pdev->dev, err, "Failed to register DSA switch\n"); goto err_register_ds; } diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig index 1aa79735355f..060165a85fb7 100644 --- a/drivers/net/dsa/realtek/Kconfig +++ b/drivers/net/dsa/realtek/Kconfig @@ -9,34 +9,46 @@ menuconfig NET_DSA_REALTEK help Select to enable support for Realtek Ethernet switch chips. + Note that at least one interface driver must be enabled for the + subdrivers to be loaded. Moreover, an interface driver cannot achieve + anything without at least one subdriver enabled. + +if NET_DSA_REALTEK + config NET_DSA_REALTEK_MDIO - tristate "Realtek MDIO connected switch driver" - depends on NET_DSA_REALTEK + tristate "Realtek MDIO interface driver" depends on OF + depends on NET_DSA_REALTEK_RTL8365MB || NET_DSA_REALTEK_RTL8366RB + depends on NET_DSA_REALTEK_RTL8365MB || !NET_DSA_REALTEK_RTL8365MB + depends on NET_DSA_REALTEK_RTL8366RB || !NET_DSA_REALTEK_RTL8366RB help Select to enable support for registering switches configured through MDIO. config NET_DSA_REALTEK_SMI - tristate "Realtek SMI connected switch driver" - depends on NET_DSA_REALTEK + tristate "Realtek SMI interface driver" depends on OF + depends on NET_DSA_REALTEK_RTL8365MB || NET_DSA_REALTEK_RTL8366RB + depends on NET_DSA_REALTEK_RTL8365MB || !NET_DSA_REALTEK_RTL8365MB + depends on NET_DSA_REALTEK_RTL8366RB || !NET_DSA_REALTEK_RTL8366RB help Select to enable support for registering switches connected through SMI. config NET_DSA_REALTEK_RTL8365MB tristate "Realtek RTL8365MB switch subdriver" - depends on NET_DSA_REALTEK - depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + imply NET_DSA_REALTEK_SMI + imply NET_DSA_REALTEK_MDIO select NET_DSA_TAG_RTL8_4 help Select to enable support for Realtek RTL8365MB-VC and RTL8367S. config NET_DSA_REALTEK_RTL8366RB tristate "Realtek RTL8366RB switch subdriver" - depends on NET_DSA_REALTEK - depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + imply NET_DSA_REALTEK_SMI + imply NET_DSA_REALTEK_MDIO select NET_DSA_TAG_RTL4_A help - Select to enable support for Realtek RTL8366RB + Select to enable support for Realtek RTL8366RB. + +endif diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c index 31e1f100e48e..c58f49d558d2 100644 --- a/drivers/net/dsa/realtek/realtek-mdio.c +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -267,7 +267,6 @@ static const struct of_device_id realtek_mdio_of_match[] = { #endif #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c index 2243d3da55b2..45992f79ec8d 100644 --- a/drivers/net/dsa/realtek/realtek-smi.c +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -546,20 +546,11 @@ static const struct of_device_id realtek_smi_of_match[] = { .data = &rtl8366rb_variant, }, #endif - { - /* FIXME: add support for RTL8366S and more */ - .compatible = "realtek,rtl8366s", - .data = NULL, - }, #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { - .compatible = "realtek,rtl8367s", - .data = &rtl8365mb_variant, - }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index bd4cb9d7c35d..827993022386 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -35,15 +35,6 @@ source "drivers/net/ethernet/aquantia/Kconfig" source "drivers/net/ethernet/arc/Kconfig" source "drivers/net/ethernet/asix/Kconfig" source "drivers/net/ethernet/atheros/Kconfig" -source "drivers/net/ethernet/broadcom/Kconfig" -source "drivers/net/ethernet/brocade/Kconfig" -source "drivers/net/ethernet/cadence/Kconfig" -source "drivers/net/ethernet/calxeda/Kconfig" -source "drivers/net/ethernet/cavium/Kconfig" -source "drivers/net/ethernet/chelsio/Kconfig" -source "drivers/net/ethernet/cirrus/Kconfig" -source "drivers/net/ethernet/cisco/Kconfig" -source "drivers/net/ethernet/cortina/Kconfig" config CX_ECAT tristate "Beckhoff CX5020 EtherCAT master support" @@ -57,6 +48,14 @@ config CX_ECAT To compile this driver as a module, choose M here. The module will be called ec_bhf. +source "drivers/net/ethernet/broadcom/Kconfig" +source "drivers/net/ethernet/cadence/Kconfig" +source "drivers/net/ethernet/calxeda/Kconfig" +source "drivers/net/ethernet/cavium/Kconfig" +source "drivers/net/ethernet/chelsio/Kconfig" +source "drivers/net/ethernet/cirrus/Kconfig" +source "drivers/net/ethernet/cisco/Kconfig" +source "drivers/net/ethernet/cortina/Kconfig" source "drivers/net/ethernet/davicom/Kconfig" config DNET @@ -85,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/microsoft/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" config JME @@ -128,8 +126,9 @@ source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" source "drivers/net/ethernet/micrel/Kconfig" source "drivers/net/ethernet/microchip/Kconfig" -source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/mscc/Kconfig" +source "drivers/net/ethernet/microsoft/Kconfig" +source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/myricom/Kconfig" config FEALNX @@ -141,10 +140,10 @@ config FEALNX Say Y here to support the Myson MTD-800 family of PCI-based Ethernet cards. <http://www.myson.com.tw/> +source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/natsemi/Kconfig" source "drivers/net/ethernet/neterion/Kconfig" source "drivers/net/ethernet/netronome/Kconfig" -source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/8390/Kconfig" source "drivers/net/ethernet/nvidia/Kconfig" source "drivers/net/ethernet/nxp/Kconfig" @@ -164,6 +163,7 @@ source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" source "drivers/net/ethernet/pensando/Kconfig" source "drivers/net/ethernet/qlogic/Kconfig" +source "drivers/net/ethernet/brocade/Kconfig" source "drivers/net/ethernet/qualcomm/Kconfig" source "drivers/net/ethernet/rdc/Kconfig" source "drivers/net/ethernet/realtek/Kconfig" @@ -171,10 +171,10 @@ source "drivers/net/ethernet/renesas/Kconfig" source "drivers/net/ethernet/rocker/Kconfig" source "drivers/net/ethernet/samsung/Kconfig" source "drivers/net/ethernet/seeq/Kconfig" -source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/sgi/Kconfig" source "drivers/net/ethernet/silan/Kconfig" source "drivers/net/ethernet/sis/Kconfig" +source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/smsc/Kconfig" source "drivers/net/ethernet/socionext/Kconfig" source "drivers/net/ethernet/stmicro/Kconfig" diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 33f1a1377588..24d715c28a35 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -486,8 +486,8 @@ int aq_nic_start(struct aq_nic_s *self) if (err < 0) goto err_exit; - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + aq_vec = self->aq_vec[i]; err = aq_vec_start(aq_vec); if (err < 0) goto err_exit; @@ -517,8 +517,8 @@ int aq_nic_start(struct aq_nic_s *self) mod_timer(&self->polling_timer, jiffies + AQ_CFG_POLLING_TIMER_INTERVAL); } else { - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + aq_vec = self->aq_vec[i]; err = aq_pci_func_alloc_irq(self, i, self->ndev->name, aq_vec_isr, aq_vec, aq_vec_get_affinity_mask(aq_vec)); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 797a95142d1f..3a529ee8c834 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -444,22 +444,22 @@ err_exit: static int aq_pm_freeze(struct device *dev) { - return aq_suspend_common(dev, false); + return aq_suspend_common(dev, true); } static int aq_pm_suspend_poweroff(struct device *dev) { - return aq_suspend_common(dev, true); + return aq_suspend_common(dev, false); } static int aq_pm_thaw(struct device *dev) { - return atl_resume_common(dev, false); + return atl_resume_common(dev, true); } static int aq_pm_resume_restore(struct device *dev) { - return atl_resume_common(dev, true); + return atl_resume_common(dev, false); } static const struct dev_pm_ops aq_pm_ops = { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index f4774cf051c9..6ab1f3212d24 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -43,8 +43,8 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (!self) { err = -EINVAL; } else { - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; u64_stats_update_begin(&ring[AQ_VEC_RX_ID].stats.rx.syncp); ring[AQ_VEC_RX_ID].stats.rx.polls++; u64_stats_update_end(&ring[AQ_VEC_RX_ID].stats.rx.syncp); @@ -182,8 +182,8 @@ int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops, self->aq_hw_ops = aq_hw_ops; self->aq_hw = aq_hw; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; err = aq_ring_init(&ring[AQ_VEC_TX_ID], ATL_RING_TX); if (err < 0) goto err_exit; @@ -224,8 +224,8 @@ int aq_vec_start(struct aq_vec_s *self) unsigned int i = 0U; int err = 0; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; err = self->aq_hw_ops->hw_ring_tx_start(self->aq_hw, &ring[AQ_VEC_TX_ID]); if (err < 0) @@ -248,8 +248,8 @@ void aq_vec_stop(struct aq_vec_s *self) struct aq_ring_s *ring = NULL; unsigned int i = 0U; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; self->aq_hw_ops->hw_ring_tx_stop(self->aq_hw, &ring[AQ_VEC_TX_ID]); @@ -268,8 +268,8 @@ void aq_vec_deinit(struct aq_vec_s *self) if (!self) goto err_exit; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]); } @@ -297,8 +297,8 @@ void aq_vec_ring_free(struct aq_vec_s *self) if (!self) goto err_exit; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; aq_ring_free(&ring[AQ_VEC_TX_ID]); if (i < self->rx_rings) aq_ring_free(&ring[AQ_VEC_RX_ID]); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 2dd79af9411b..bf1ec8fdc2ad 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -76,7 +76,7 @@ static inline void bcmgenet_writel(u32 value, void __iomem *offset) if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) __raw_writel(value, offset); else - writel(value, offset); + writel_relaxed(value, offset); } static inline u32 bcmgenet_readl(void __iomem *offset) @@ -84,7 +84,7 @@ static inline u32 bcmgenet_readl(void __iomem *offset) if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) return __raw_readl(offset); else - return readl(offset); + return readl_relaxed(offset); } static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv, @@ -2035,6 +2035,11 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev, return skb; } +static void bcmgenet_hide_tsb(struct sk_buff *skb) +{ + __skb_pull(skb, sizeof(struct status_64)); +} + static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -2141,6 +2146,8 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } GENET_CB(skb)->last_cb = tx_cb_ptr; + + bcmgenet_hide_tsb(skb); skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 800d5ced5800..e475be29845c 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1658,6 +1658,7 @@ static void macb_tx_restart(struct macb_queue *queue) unsigned int head = queue->tx_head; unsigned int tail = queue->tx_tail; struct macb *bp = queue->bp; + unsigned int head_idx, tbqp; if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(TXUBR)); @@ -1665,6 +1666,13 @@ static void macb_tx_restart(struct macb_queue *queue) if (head == tail) return; + tbqp = queue_readl(queue, TBQP) / macb_dma_desc_get_size(bp); + tbqp = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, tbqp)); + head_idx = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, head)); + + if (tbqp == head_idx) + return; + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index d5356db7539a..caf48023f8ea 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1835,11 +1835,6 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); priv->is_aspeed = true; - /* Disable ast2600 problematic HW arbitration */ - if (of_device_is_compatible(np, "aspeed,ast2600-mac")) { - iowrite32(FTGMAC100_TM_DEFAULT, - priv->base + FTGMAC100_OFFSET_TM); - } } else { priv->rxdes0_edorr_mask = BIT(15); priv->txdes0_edotr_mask = BIT(15); @@ -1911,6 +1906,11 @@ static int ftgmac100_probe(struct platform_device *pdev) err = ftgmac100_setup_clk(priv); if (err) goto err_phy_connect; + + /* Disable ast2600 problematic HW arbitration */ + if (of_device_is_compatible(np, "aspeed,ast2600-mac")) + iowrite32(FTGMAC100_TM_DEFAULT, + priv->base + FTGMAC100_OFFSET_TM); } /* Default ring sizes */ diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 763d2c7b5fb1..5750f9a56393 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -489,11 +489,15 @@ static int dpaa_get_ts_info(struct net_device *net_dev, info->phc_index = -1; fman_node = of_get_parent(mac_node); - if (fman_node) + if (fman_node) { ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0); + of_node_put(fman_node); + } - if (ptp_node) + if (ptp_node) { ptp_dev = of_find_device_by_node(ptp_node); + of_node_put(ptp_node); + } if (ptp_dev) ptp = platform_get_drvdata(ptp_dev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 7edf8569514c..928d934cb21a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -1065,19 +1065,23 @@ int hns_mac_init(struct dsaf_device *dsaf_dev) device_for_each_child_node(dsaf_dev->dev, child) { ret = fwnode_property_read_u32(child, "reg", &port_id); if (ret) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "get reg fail, ret=%d!\n", ret); return ret; } if (port_id >= max_port_num) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "reg(%u) out of range!\n", port_id); return -EINVAL; } mac_cb = devm_kzalloc(dsaf_dev->dev, sizeof(*mac_cb), GFP_KERNEL); - if (!mac_cb) + if (!mac_cb) { + fwnode_handle_put(child); return -ENOMEM; + } mac_cb->fw_port = child; mac_cb->mac_id = (u8)port_id; dsaf_dev->mac_cb[port_id] = mac_cb; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 0c60f41fca8a..f3c9395d8351 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -75,7 +75,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, tx = %u.\n", + "failed to get tqp stat, ret = %d, rx = %u.\n", ret, i); return ret; } @@ -89,7 +89,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, rx = %u.\n", + "failed to get tqp stat, ret = %d, tx = %u.\n", ret, i); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 44d9b560b337..93aeb615191d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -562,12 +562,12 @@ static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf, for (i = 0; i < ring_num; i++) { j = 0; - sprintf(result[j++], "%8u", i); - sprintf(result[j++], "%9u", ring->tx_copybreak); - sprintf(result[j++], "%3u", tx_spare->len); - sprintf(result[j++], "%3u", tx_spare->next_to_use); - sprintf(result[j++], "%3u", tx_spare->next_to_clean); - sprintf(result[j++], "%3u", tx_spare->last_to_clean); + sprintf(result[j++], "%u", i); + sprintf(result[j++], "%u", ring->tx_copybreak); + sprintf(result[j++], "%u", tx_spare->len); + sprintf(result[j++], "%u", tx_spare->next_to_use); + sprintf(result[j++], "%u", tx_spare->next_to_clean); + sprintf(result[j++], "%u", tx_spare->last_to_clean); sprintf(result[j++], "%pad", &tx_spare->dma); hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items, @@ -598,35 +598,35 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); + sprintf(result[j++], "%u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_NUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_LEN_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%9u", ring->rx_copybreak); + sprintf(result[j++], "%u", ring->rx_copybreak); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BASEADDR_H_REG); @@ -700,36 +700,36 @@ static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", index); + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BD_NUM_REG)); - sprintf(result[j++], "%2u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TC_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_OFFSET_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BASEADDR_H_REG); @@ -848,15 +848,15 @@ static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%5d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info)); - sprintf(result[j++], "%7u", le16_to_cpu(desc->rx.pkt_len)); - sprintf(result[j++], "%4u", le16_to_cpu(desc->rx.size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.pkt_len)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->rx.fd_id)); - sprintf(result[j++], "%8u", le16_to_cpu(desc->rx.vlan_tag)); - sprintf(result[j++], "%15u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); - sprintf(result[j++], "%11u", le16_to_cpu(desc->rx.ot_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.fd_id)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.ot_vlan_tag)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info)); if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) { u32 ol_info = le32_to_cpu(desc->rx.ol_info); @@ -930,19 +930,19 @@ static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%6d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.send_size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.send_size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.type_cs_vlan_tso_len)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.outer_vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.tv)); - sprintf(result[j++], "%10u", + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.outer_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.tv)); + sprintf(result[j++], "%u", le32_to_cpu(desc->tx.ol_type_vlan_len_msec)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs)); sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.mss_hw_csum)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.mss_hw_csum)); } static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 14dc12c2155d..a3ee7875d6a7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5203,6 +5203,13 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state); } +static void hns3_state_uninit(struct hnae3_handle *handle) +{ + struct hns3_nic_priv *priv = handle->priv; + + clear_bit(HNS3_NIC_STATE_INITED, &priv->state); +} + static int hns3_client_init(struct hnae3_handle *handle) { struct pci_dev *pdev = handle->pdev; @@ -5320,7 +5327,9 @@ static int hns3_client_init(struct hnae3_handle *handle) return ret; out_reg_netdev_fail: + hns3_state_uninit(handle); hns3_dbg_uninit(handle); + hns3_client_stop(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 6799d16de34b..7998ca617a92 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -94,6 +94,13 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, enum hclge_comm_cmd_status status; struct hclge_desc desc; + if (msg_len > HCLGE_MBX_MAX_MSG_SIZE) { + dev_err(&hdev->pdev->dev, + "msg data length(=%u) exceeds maximum(=%u)\n", + msg_len, HCLGE_MBX_MAX_MSG_SIZE); + return -EMSGSIZE; + } + resp_pf_to_vf = (struct hclge_mbx_pf_to_vf_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_PF_TO_VF, false); @@ -176,7 +183,7 @@ static int hclge_get_ring_chain_from_mbx( ring_num = req->msg.ring_num; if (ring_num > HCLGE_MBX_MAX_RING_CHAIN_PARAM_NUM) - return -ENOMEM; + return -EINVAL; for (i = 0; i < ring_num; i++) { if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) { @@ -587,9 +594,9 @@ static int hclge_set_vf_mtu(struct hclge_vport *vport, return hclge_set_vport_mtu(vport, mtu); } -static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_queue_id_in_pf(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { struct hnae3_handle *handle = &vport->nic; struct hclge_dev *hdev = vport->back; @@ -599,17 +606,18 @@ static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, if (queue_id >= handle->kinfo.num_tqps) { dev_err(&hdev->pdev->dev, "Invalid queue id(%u) from VF %u\n", queue_id, mbx_req->mbx_src_vfid); - return; + return -EINVAL; } qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id); memcpy(resp_msg->data, &qid_in_pf, sizeof(qid_in_pf)); resp_msg->len = sizeof(qid_in_pf); + return 0; } -static void hclge_get_rss_key(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_rss_key(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { #define HCLGE_RSS_MBX_RESP_LEN 8 struct hclge_dev *hdev = vport->back; @@ -627,13 +635,14 @@ static void hclge_get_rss_key(struct hclge_vport *vport, dev_warn(&hdev->pdev->dev, "failed to get the rss hash key, the index(%u) invalid !\n", index); - return; + return -EINVAL; } memcpy(resp_msg->data, &rss_cfg->rss_hash_key[index * HCLGE_RSS_MBX_RESP_LEN], HCLGE_RSS_MBX_RESP_LEN); resp_msg->len = HCLGE_RSS_MBX_RESP_LEN; + return 0; } static void hclge_link_fail_parse(struct hclge_dev *hdev, u8 link_fail_code) @@ -809,10 +818,10 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "VF fail(%d) to set mtu\n", ret); break; case HCLGE_MBX_GET_QID_IN_PF: - hclge_get_queue_id_in_pf(vport, req, &resp_msg); + ret = hclge_get_queue_id_in_pf(vport, req, &resp_msg); break; case HCLGE_MBX_GET_RSS_KEY: - hclge_get_rss_key(vport, req, &resp_msg); + ret = hclge_get_rss_key(vport, req, &resp_msg); break; case HCLGE_MBX_GET_LINK_MODE: hclge_get_link_mode(vport, req); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index d60e2016d03c..e6c8e6d5234f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1009,8 +1009,8 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) { u32 reg = link << (E1000_LTRV_REQ_SHIFT + E1000_LTRV_NOSNOOP_SHIFT) | link << E1000_LTRV_REQ_SHIFT | E1000_LTRV_SEND; - u16 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ - u16 lat_enc_d = 0; /* latency decoded */ + u32 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ + u32 lat_enc_d = 0; /* latency decoded */ u16 lat_enc = 0; /* latency encoded */ if (link) { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 190590d32faf..7dfcf78b57fb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2871,7 +2871,6 @@ continue_reset: running = adapter->state == __IAVF_RUNNING; if (running) { - netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2988,7 +2987,7 @@ continue_reset: * to __IAVF_RUNNING */ iavf_up_complete(adapter); - netdev->flags |= IFF_UP; + iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -3004,10 +3003,8 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) { + if (running) iavf_change_state(adapter, __IAVF_RUNNING); - netdev->flags |= IFF_UP; - } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 5daade32ea62..fba178e07600 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; - if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list) + if (!vsi || vsi->type != ICE_VSI_PF) return; netdev = vsi->netdev; @@ -599,7 +599,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) int base_idx, i; if (!vsi || vsi->type != ICE_VSI_PF) - return -EINVAL; + return 0; pf = vsi->back; netdev = vsi->netdev; @@ -636,7 +636,6 @@ void ice_remove_arfs(struct ice_pf *pf) if (!pf_vsi) return; - ice_free_cpu_rx_rmap(pf_vsi); ice_clear_arfs(pf_vsi); } @@ -653,9 +652,5 @@ void ice_rebuild_arfs(struct ice_pf *pf) return; ice_remove_arfs(pf); - if (ice_set_cpu_rx_rmap(pf_vsi)) { - dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n"); - return; - } ice_init_arfs(pf_vsi); } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 9a84d746a6c4..6a463b242c7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -361,7 +361,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; - if (ice_is_reset_in_progress(vsi->back->state)) + if (ice_is_reset_in_progress(vsi->back->state) || + test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; repr = ice_netdev_to_repr(netdev); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index bd58d9d2e565..6a413331572b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -52,7 +52,7 @@ static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { - return -EOPNOTSUPP; + return 0; } static inline int ice_eswitch_rebuild(struct ice_pf *pf) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 2774cbd5b12a..6d19c58ccacd 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2689,6 +2689,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; + ice_free_cpu_rx_rmap(vsi); + ice_for_each_q_vector(vsi, i) { u16 vector = i + base; int irq_num; @@ -2702,7 +2704,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) continue; /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + if (!IS_ENABLED(CONFIG_RFS_ACCEL)) + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint(irq_num, NULL); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d768925785ca..9a0a358a15c2 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2510,6 +2510,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } + err = ice_set_cpu_rx_rmap(vsi); + if (err) { + netdev_err(vsi->netdev, "Failed to setup CPU RMAP on VSI %u: %pe\n", + vsi->vsi_num, ERR_PTR(err)); + goto free_q_irqs; + } + vsi->irqs_ready = true; return 0; @@ -3692,20 +3699,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf) */ ice_napi_add(vsi); - status = ice_set_cpu_rx_rmap(vsi); - if (status) { - dev_err(dev, "Failed to set CPU Rx map VSI %d error %d\n", - vsi->vsi_num, status); - goto unroll_napi_add; - } status = ice_init_mac_fltr(pf); if (status) - goto free_cpu_rx_map; + goto unroll_napi_add; return 0; -free_cpu_rx_map: - ice_free_cpu_rx_rmap(vsi); unroll_napi_add: ice_tc_indir_block_unregister(vsi); unroll_cfg_netdev: @@ -5167,7 +5166,6 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } - ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); @@ -6931,12 +6929,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); +#define ICE_EMP_RESET_SLEEP_MS 5000 if (reset_type == ICE_RESET_EMPR) { /* If an EMP reset has occurred, any previously pending flash * update will have completed. We no longer know whether or * not the NVM update EMP reset is restricted. */ pf->fw_emp_reset_disabled = false; + + msleep(ICE_EMP_RESET_SLEEP_MS); } err = ice_init_all_ctrlq(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 4eb0599714f4..13cdb5ea594d 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -641,6 +641,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0, orom_data, hw->flash.banks.orom_size); if (status) { + vfree(orom_data); ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n"); return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 8915a9d39e36..0c438219f7a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1046,8 +1046,8 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { - ice_mbx_deinit_snapshot(&pf->hw); ice_free_vfs(pf); + ice_mbx_deinit_snapshot(&pf->hw); if (pf->lag) ice_enable_lag(pf->lag); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 69ff4b929772..b72606c9e6d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3625,6 +3625,8 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) return; } + mutex_lock(&vf->cfg_lock); + /* Check if VF is disabled. */ if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { err = -EPERM; @@ -3642,32 +3644,20 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) err = -EINVAL; } - if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { - ice_vc_send_msg_to_vf(vf, v_opcode, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, - 0); - ice_put_vf(vf); - return; - } - error_handler: if (err) { ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); dev_err(dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", vf_id, v_opcode, msglen, err); - ice_put_vf(vf); - return; + goto finish; } - /* VF is being configured in another context that triggers a VFR, so no - * need to process this message - */ - if (!mutex_trylock(&vf->cfg_lock)) { - dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", - vf->vf_id); - ice_put_vf(vf); - return; + if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { + ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, + 0); + goto finish; } switch (v_opcode) { @@ -3780,6 +3770,7 @@ error_handler: vf_id, v_opcode, err); } +finish: mutex_unlock(&vf->cfg_lock); ice_put_vf(vf); } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 866ee4df9671..9dd38f667059 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -415,8 +415,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, */ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { + u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; - u32 nb_buffs_extra = 0, nb_buffs; u16 ntu = rx_ring->next_to_use; u16 total_count = count; struct xdp_buff **xdp; @@ -428,6 +428,10 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } rx_desc = ICE_RX_DESC(rx_ring, 0); xdp = ice_xdp_buf(rx_ring, 0); ntu = 0; @@ -441,6 +445,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) if (ntu == rx_ring->count) ntu = 0; +exit: if (rx_ring->next_to_use != ntu) ice_release_rx_desc(rx_ring, ntu); diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 66ea566488d1..59d5c467ea6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask) { u32 swfw_sync; - while (igc_get_hw_semaphore_i225(hw)) - ; /* Empty */ + /* Releasing the resource requires first getting the HW semaphore. + * If we fail to get the semaphore, there is nothing we can do, + * except log an error and quit. We are not allowed to hang here + * indefinitely, as it may cause denial of service or system crash. + */ + if (igc_get_hw_semaphore_i225(hw)) { + hw_dbg("Failed to release SW_FW_SYNC.\n"); + return; + } swfw_sync = rd32(IGC_SW_FW_SYNC); swfw_sync &= ~mask; diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 40dbf4b43234..6961f65d36b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -581,7 +581,7 @@ static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; @@ -638,7 +638,7 @@ static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 0d6e3215e98f..653e9f1e35b5 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -992,6 +992,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter) igc_ptp_write_i225(adapter, &ts); } +static void igc_ptm_stop(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_EN; + + wr32(IGC_PTM_CTRL, ctrl); +} + /** * igc_ptp_suspend - Disable PTP work items and prepare for suspend * @adapter: Board private structure @@ -1009,8 +1020,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); - if (pci_device_is_present(adapter->pdev)) + if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); + igc_ptm_stop(adapter); + } } /** diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 939b692ffc33..ce843ea91464 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -650,6 +650,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, return 0; errout: + mutex_destroy(&mlxsw_i2c->cmd.lock); i2c_set_clientdata(client, NULL); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index b73466470f75..fe663b0ab708 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,7 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, parms.link, tun->fwmark, 0); + 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c index ce5970bdcc6a..005e56ea5da1 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c @@ -346,7 +346,8 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - WARN_ON(dest_idx > lan966x->num_phys_ports); + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) + continue; /* If the entry in SW is found, then there is nothing * to do @@ -392,7 +393,8 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - WARN_ON(dest_idx > lan966x->num_phys_ports); + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) + continue; mac_entry = lan966x_mac_alloc_entry(mac, vid, dest_idx); if (!mac_entry) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 1f8c67f0261b..95830e3e2b1f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -446,6 +446,12 @@ static bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, ANA_CPU_FWD_CFG_MLD_REDIR_ENA))) return true; + if (eth_type_vlan(skb->protocol)) { + skb = skb_vlan_untag(skb); + if (unlikely(!skb)) + return false; + } + if (skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_IGMP) return false; @@ -665,6 +671,9 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) disable_irq(lan966x->ana_irq); lan966x->ana_irq = -ENXIO; } + + if (lan966x->ptp_irq) + devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x); } static int lan966x_probe_port(struct lan966x *lan966x, u32 p, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index ae782778d6dd..0a1041da4384 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -29,10 +29,10 @@ enum { static u64 lan966x_ptp_get_nominal_value(void) { - u64 res = 0x304d2df1; - - res <<= 32; - return res; + /* This is the default value that for each system clock, the time of day + * is increased. It has the format 5.59 nanosecond. + */ + return 0x304d4873ecade305; } int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c index e3555c94294d..df2bee678559 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c @@ -322,8 +322,7 @@ static int lan966x_port_prechangeupper(struct net_device *dev, if (netif_is_bridge_master(info->upper_dev) && !info->linking) switchdev_bridge_port_unoffload(port->dev, port, - &lan966x_switchdev_nb, - &lan966x_switchdev_blocking_nb); + NULL, NULL); return NOTIFY_DONE; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e443bd8b2d09..ca71b62a44dc 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -551,7 +551,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, struct ocelot_vcap_block *block = &ocelot->block[VCAP_IS1]; struct ocelot_port *ocelot_port = ocelot->ports[port]; struct ocelot_vcap_filter *filter; - int err; + int err = 0; u32 val; list_for_each_entry(filter, &block->rules, list) { @@ -570,7 +570,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, if (vlan_aware) err = ocelot_del_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); - else + else if (ocelot_port->bridge) err = ocelot_add_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); if (err) @@ -629,6 +629,13 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, { int err; + /* Ignore VID 0 added to our RX filter by the 8021q module, since + * that collides with OCELOT_STANDALONE_PVID and changes it from + * egress-untagged to egress-tagged. + */ + if (!vid) + return 0; + err = ocelot_vlan_member_add(ocelot, port, vid, untagged); if (err) return err; @@ -651,6 +658,9 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) bool del_pvid = false; int err; + if (!vid) + return 0; + if (ocelot_port->pvid_vlan && ocelot_port->pvid_vlan->vid == vid) del_pvid = true; @@ -2859,6 +2869,8 @@ static void ocelot_port_set_mcast_flood(struct ocelot *ocelot, int port, val = BIT(port); ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MC); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV4); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV6); } static void ocelot_port_set_bcast_flood(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index cd478d2cd871..00f6d347eaf7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -57,10 +57,6 @@ #define TSE_PCS_USE_SGMII_ENA BIT(0) #define TSE_PCS_IF_USE_SGMII 0x03 -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_DISABLE 0x0001 -#define SGMII_ADAPTER_ENABLE 0x0000 - #define AUTONEGO_LINK_TIMER 20 static int tse_pcs_reset(void __iomem *base, struct tse_pcs *pcs) @@ -202,12 +198,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, unsigned int speed) { void __iomem *tse_pcs_base = pcs->tse_pcs_base; - void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; u32 val; - writew(SGMII_ADAPTER_ENABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - pcs->autoneg = phy_dev->autoneg; if (phy_dev->autoneg == AUTONEG_ENABLE) { diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h index 442812c0a4bd..694ac25ef426 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h @@ -10,6 +10,10 @@ #include <linux/phy.h> #include <linux/timer.h> +#define SGMII_ADAPTER_CTRL_REG 0x00 +#define SGMII_ADAPTER_ENABLE 0x0000 +#define SGMII_ADAPTER_DISABLE 0x0001 + struct tse_pcs { struct device *dev; void __iomem *tse_pcs_base; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index b7c2579c963b..6b447d8f0bd8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -18,9 +18,6 @@ #include "altr_tse_pcs.h" -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_DISABLE 0x0001 - #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0x0 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII 0x1 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII 0x2 @@ -62,14 +59,13 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) { struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv; void __iomem *splitter_base = dwmac->splitter_base; - void __iomem *tse_pcs_base = dwmac->pcs.tse_pcs_base; void __iomem *sgmii_adapter_base = dwmac->pcs.sgmii_adapter_base; struct device *dev = dwmac->dev; struct net_device *ndev = dev_get_drvdata(dev); struct phy_device *phy_dev = ndev->phydev; u32 val; - if ((tse_pcs_base) && (sgmii_adapter_base)) + if (sgmii_adapter_base) writew(SGMII_ADAPTER_DISABLE, sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); @@ -93,8 +89,11 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG); } - if (tse_pcs_base && sgmii_adapter_base) + if (phy_dev && sgmii_adapter_base) { + writew(SGMII_ADAPTER_ENABLE, + sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); tse_pcs_fix_mac_speed(&dwmac->pcs, phy_dev, speed); + } } static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 22fea0f67245..92d32940aff0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -71,9 +71,9 @@ static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) writel(value, ioaddr + PTP_TCR); /* wait for present system time initialize to complete */ - return readl_poll_timeout(ioaddr + PTP_TCR, value, + return readl_poll_timeout_atomic(ioaddr + PTP_TCR, value, !(value & PTP_TCR_TSINIT), - 10000, 100000); + 10, 100000); } static int config_addend(void __iomem *ioaddr, u32 addend) diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 16105292b140..74e845fa2e07 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1355,7 +1355,9 @@ static int rr_close(struct net_device *dev) rrpriv->fw_running = 0; + spin_unlock_irqrestore(&rrpriv->lock, flags); del_timer_sync(&rrpriv->timer); + spin_lock_irqsave(&rrpriv->lock, flags); writel(0, ®s->TxPi); writel(0, ®s->IpRxPi); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 069e8824c264..b00bc8173abe 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -460,8 +460,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); - if (macvlan_forward_source(skb, port, eth->h_source)) + if (macvlan_forward_source(skb, port, eth->h_source)) { + kfree_skb(skb); return RX_HANDLER_CONSUMED; + } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { @@ -480,8 +482,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; } - if (macvlan_forward_source(skb, port, eth->h_source)) + if (macvlan_forward_source(skb, port, eth->h_source)) { + kfree_skb(skb); return RX_HANDLER_CONSUMED; + } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 1becb1a731f6..1c1584fca632 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -43,6 +43,11 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int rc; rc = fwnode_irq_get(child, 0); + /* Don't wait forever if the IRQ provider doesn't become available, + * just fall back to poll mode + */ + if (rc == -EPROBE_DEFER) + rc = driver_deferred_probe_check_state(&phy->mdio.dev); if (rc == -EPROBE_DEFER) return rc; diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index b6fea119fe13..2b7d0720720b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -880,7 +880,7 @@ static int mv3310_read_status_copper(struct phy_device *phydev) cssr1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_CSSR1); if (cssr1 < 0) - return val; + return cssr1; /* If the link settings are not resolved, mark the link down */ if (!(cssr1 & MV_PCS_CSSR1_RESOLVED)) { diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 389df3f4293c..c2c0e361fd3d 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -706,7 +706,6 @@ static int lan87xx_read_status(struct phy_device *phydev) static int lan87xx_config_aneg(struct phy_device *phydev) { u16 ctl = 0; - int rc; switch (phydev->master_slave_set) { case MASTER_SLAVE_CFG_MASTER_FORCE: @@ -722,11 +721,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev) return -EOPNOTSUPP; } - rc = phy_modify_changed(phydev, MII_CTRL1000, CTL1000_AS_MASTER, ctl); - if (rc == 1) - rc = genphy_soft_reset(phydev); - - return rc; + return phy_modify_changed(phydev, MII_CTRL1000, CTL1000_AS_MASTER, ctl); } static struct phy_driver microchip_t1_phy_driver[] = { @@ -748,6 +743,7 @@ static struct phy_driver microchip_t1_phy_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X), .name = "Microchip LAN937x T1", + .flags = PHY_POLL_CABLE_TEST, .features = PHY_BASIC_T1_FEATURES, .config_init = lan87xx_config_init, .suspend = genphy_suspend, diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 276a0e42ca8e..dbe4c0a4be2c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1124,7 +1124,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) /* NETIF_F_LLTX requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); - queue->trans_start = jiffies; + txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 1b5714926d81..eb0121a64d6d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -320,7 +320,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); rcv = rcu_dereference(priv->peer); - if (unlikely(!rcv)) { + if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) { kfree_skb(skb); goto drop; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 11f26b00a226..cbba9d2e8f32 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -169,6 +169,24 @@ struct receive_queue { struct xdp_rxq_info xdp_rxq; }; +/* This structure can contain rss message with maximum settings for indirection table and keysize + * Note, that default structure that describes RSS configuration virtio_net_rss_config + * contains same info but can't handle table values. + * In any case, structure would be passed to virtio hw through sg_buf split by parts + * because table sizes may be differ according to the device configuration. + */ +#define VIRTIO_NET_RSS_MAX_KEY_SIZE 40 +#define VIRTIO_NET_RSS_MAX_TABLE_LEN 128 +struct virtio_net_ctrl_rss { + u32 hash_types; + u16 indirection_table_mask; + u16 unclassified_queue; + u16 indirection_table[VIRTIO_NET_RSS_MAX_TABLE_LEN]; + u16 max_tx_vq; + u8 hash_key_length; + u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE]; +}; + /* Control VQ buffers: protected by the rtnl lock */ struct control_buf { struct virtio_net_ctrl_hdr hdr; @@ -178,6 +196,7 @@ struct control_buf { u8 allmulti; __virtio16 vid; __virtio64 offloads; + struct virtio_net_ctrl_rss rss; }; struct virtnet_info { @@ -206,6 +225,14 @@ struct virtnet_info { /* Host will merge rx buffers for big packets (shake it! shake it!) */ bool mergeable_rx_bufs; + /* Host supports rss and/or hash report */ + bool has_rss; + bool has_rss_hash_report; + u8 rss_key_size; + u16 rss_indir_table_size; + u32 rss_hash_types_supported; + u32 rss_hash_types_saved; + /* Has control virtqueue */ bool has_cvq; @@ -242,13 +269,13 @@ struct virtnet_info { }; struct padded_vnet_hdr { - struct virtio_net_hdr_mrg_rxbuf hdr; + struct virtio_net_hdr_v1_hash hdr; /* * hdr is in a separate sg buffer, and data sg buffer shares same page * with this header sg. This padding makes next sg 16 byte aligned * after the header. */ - char padding[4]; + char padding[12]; }; static bool is_xdp_frame(void *ptr) @@ -396,7 +423,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, hdr_len = vi->hdr_len; if (vi->mergeable_rx_bufs) - hdr_padded_len = sizeof(*hdr); + hdr_padded_len = hdr_len; else hdr_padded_len = sizeof(struct padded_vnet_hdr); @@ -978,6 +1005,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, * xdp.data_meta were adjusted */ len = xdp.data_end - xdp.data + vi->hdr_len + metasize; + + /* recalculate headroom if xdp.data or xdp_data_meta + * were adjusted, note that offset should always point + * to the start of the reserved bytes for virtio_net + * header which are followed by xdp.data, that means + * that offset is equal to the headroom (when buf is + * starting at the beginning of the page, otherwise + * there is a base offset inside the page) but it's used + * with a different starting point (buf start) than + * xdp.data (buf start + vnet hdr size). If xdp.data or + * data_meta were adjusted by the xdp prog then the + * headroom size has changed and so has the offset, we + * can use data_hard_start, which points at buf start + + * vnet hdr size, to calculate the new headroom and use + * it later to compute buf start in page_to_skb() + */ + headroom = xdp.data - xdp.data_hard_start - metasize; + /* We can only create skb based on xdp_page. */ if (unlikely(xdp_page != page)) { rcu_read_unlock(); @@ -985,7 +1030,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE, false, metasize, - VIRTIO_XDP_HEADROOM); + headroom); return head_skb; } break; @@ -1123,6 +1168,35 @@ xdp_xmit: return NULL; } +static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash, + struct sk_buff *skb) +{ + enum pkt_hash_types rss_hash_type; + + if (!hdr_hash || !skb) + return; + + switch ((int)hdr_hash->hash_report) { + case VIRTIO_NET_HASH_REPORT_TCPv4: + case VIRTIO_NET_HASH_REPORT_UDPv4: + case VIRTIO_NET_HASH_REPORT_TCPv6: + case VIRTIO_NET_HASH_REPORT_UDPv6: + case VIRTIO_NET_HASH_REPORT_TCPv6_EX: + case VIRTIO_NET_HASH_REPORT_UDPv6_EX: + rss_hash_type = PKT_HASH_TYPE_L4; + break; + case VIRTIO_NET_HASH_REPORT_IPv4: + case VIRTIO_NET_HASH_REPORT_IPv6: + case VIRTIO_NET_HASH_REPORT_IPv6_EX: + rss_hash_type = PKT_HASH_TYPE_L3; + break; + case VIRTIO_NET_HASH_REPORT_NONE: + default: + rss_hash_type = PKT_HASH_TYPE_NONE; + } + skb_set_hash(skb, (unsigned int)hdr_hash->hash_value, rss_hash_type); +} + static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf, unsigned int len, void **ctx, unsigned int *xdp_xmit, @@ -1157,6 +1231,8 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, return; hdr = skb_vnet_hdr(skb); + if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) + virtio_skb_set_hash((const struct virtio_net_hdr_v1_hash *)hdr, skb); if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1266,7 +1342,8 @@ static unsigned int get_mergeable_buf_len(struct receive_queue *rq, struct ewma_pkt_len *avg_pkt_len, unsigned int room) { - const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + struct virtnet_info *vi = rq->vq->vdev->priv; + const size_t hdr_len = vi->hdr_len; unsigned int len; if (room) @@ -2183,6 +2260,174 @@ static void virtnet_get_ringparam(struct net_device *dev, ring->tx_pending = ring->tx_max_pending; } +static bool virtnet_commit_rss_command(struct virtnet_info *vi) +{ + struct net_device *dev = vi->dev; + struct scatterlist sgs[4]; + unsigned int sg_buf_size; + + /* prepare sgs */ + sg_init_table(sgs, 4); + + sg_buf_size = offsetof(struct virtio_net_ctrl_rss, indirection_table); + sg_set_buf(&sgs[0], &vi->ctrl->rss, sg_buf_size); + + sg_buf_size = sizeof(uint16_t) * (vi->ctrl->rss.indirection_table_mask + 1); + sg_set_buf(&sgs[1], vi->ctrl->rss.indirection_table, sg_buf_size); + + sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key) + - offsetof(struct virtio_net_ctrl_rss, max_tx_vq); + sg_set_buf(&sgs[2], &vi->ctrl->rss.max_tx_vq, sg_buf_size); + + sg_buf_size = vi->rss_key_size; + sg_set_buf(&sgs[3], vi->ctrl->rss.key, sg_buf_size); + + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, + vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG + : VIRTIO_NET_CTRL_MQ_HASH_CONFIG, sgs)) { + dev_warn(&dev->dev, "VIRTIONET issue with committing RSS sgs\n"); + return false; + } + return true; +} + +static void virtnet_init_default_rss(struct virtnet_info *vi) +{ + u32 indir_val = 0; + int i = 0; + + vi->ctrl->rss.hash_types = vi->rss_hash_types_supported; + vi->rss_hash_types_saved = vi->rss_hash_types_supported; + vi->ctrl->rss.indirection_table_mask = vi->rss_indir_table_size + ? vi->rss_indir_table_size - 1 : 0; + vi->ctrl->rss.unclassified_queue = 0; + + for (; i < vi->rss_indir_table_size; ++i) { + indir_val = ethtool_rxfh_indir_default(i, vi->curr_queue_pairs); + vi->ctrl->rss.indirection_table[i] = indir_val; + } + + vi->ctrl->rss.max_tx_vq = vi->curr_queue_pairs; + vi->ctrl->rss.hash_key_length = vi->rss_key_size; + + netdev_rss_key_fill(vi->ctrl->rss.key, vi->rss_key_size); +} + +static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info) +{ + info->data = 0; + switch (info->flow_type) { + case TCP_V4_FLOW: + if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv4) { + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { + info->data = RXH_IP_SRC | RXH_IP_DST; + } + break; + case TCP_V6_FLOW: + if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv6) { + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { + info->data = RXH_IP_SRC | RXH_IP_DST; + } + break; + case UDP_V4_FLOW: + if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv4) { + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { + info->data = RXH_IP_SRC | RXH_IP_DST; + } + break; + case UDP_V6_FLOW: + if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv6) { + info->data = RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3; + } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { + info->data = RXH_IP_SRC | RXH_IP_DST; + } + break; + case IPV4_FLOW: + if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) + info->data = RXH_IP_SRC | RXH_IP_DST; + + break; + case IPV6_FLOW: + if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) + info->data = RXH_IP_SRC | RXH_IP_DST; + + break; + default: + info->data = 0; + break; + } +} + +static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *info) +{ + u32 new_hashtypes = vi->rss_hash_types_saved; + bool is_disable = info->data & RXH_DISCARD; + bool is_l4 = info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3); + + /* supports only 'sd', 'sdfn' and 'r' */ + if (!((info->data == (RXH_IP_SRC | RXH_IP_DST)) | is_l4 | is_disable)) + return false; + + switch (info->flow_type) { + case TCP_V4_FLOW: + new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4); + if (!is_disable) + new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 + | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv4 : 0); + break; + case UDP_V4_FLOW: + new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_UDPv4); + if (!is_disable) + new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 + | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv4 : 0); + break; + case IPV4_FLOW: + new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv4; + if (!is_disable) + new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv4; + break; + case TCP_V6_FLOW: + new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_TCPv6); + if (!is_disable) + new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 + | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv6 : 0); + break; + case UDP_V6_FLOW: + new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_UDPv6); + if (!is_disable) + new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 + | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv6 : 0); + break; + case IPV6_FLOW: + new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv6; + if (!is_disable) + new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv6; + break; + default: + /* unsupported flow */ + return false; + } + + /* if unsupported hashtype was set */ + if (new_hashtypes != (new_hashtypes & vi->rss_hash_types_supported)) + return false; + + if (new_hashtypes != vi->rss_hash_types_saved) { + vi->rss_hash_types_saved = new_hashtypes; + vi->ctrl->rss.hash_types = vi->rss_hash_types_saved; + if (vi->dev->features & NETIF_F_RXHASH) + return virtnet_commit_rss_command(vi); + } + + return true; +} static void virtnet_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) @@ -2411,6 +2656,92 @@ static void virtnet_update_settings(struct virtnet_info *vi) vi->duplex = duplex; } +static u32 virtnet_get_rxfh_key_size(struct net_device *dev) +{ + return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size; +} + +static u32 virtnet_get_rxfh_indir_size(struct net_device *dev) +{ + return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size; +} + +static int virtnet_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc) +{ + struct virtnet_info *vi = netdev_priv(dev); + int i; + + if (indir) { + for (i = 0; i < vi->rss_indir_table_size; ++i) + indir[i] = vi->ctrl->rss.indirection_table[i]; + } + + if (key) + memcpy(key, vi->ctrl->rss.key, vi->rss_key_size); + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int virtnet_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) +{ + struct virtnet_info *vi = netdev_priv(dev); + int i; + + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + if (indir) { + for (i = 0; i < vi->rss_indir_table_size; ++i) + vi->ctrl->rss.indirection_table[i] = indir[i]; + } + if (key) + memcpy(vi->ctrl->rss.key, key, vi->rss_key_size); + + virtnet_commit_rss_command(vi); + + return 0; +} + +static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) +{ + struct virtnet_info *vi = netdev_priv(dev); + int rc = 0; + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = vi->curr_queue_pairs; + break; + case ETHTOOL_GRXFH: + virtnet_get_hashflow(vi, info); + break; + default: + rc = -EOPNOTSUPP; + } + + return rc; +} + +static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) +{ + struct virtnet_info *vi = netdev_priv(dev); + int rc = 0; + + switch (info->cmd) { + case ETHTOOL_SRXFH: + if (!virtnet_set_hashflow(vi, info)) + rc = -EINVAL; + + break; + default: + rc = -EOPNOTSUPP; + } + + return rc; +} + static const struct ethtool_ops virtnet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES, .get_drvinfo = virtnet_get_drvinfo, @@ -2426,6 +2757,12 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .set_link_ksettings = virtnet_set_link_ksettings, .set_coalesce = virtnet_set_coalesce, .get_coalesce = virtnet_get_coalesce, + .get_rxfh_key_size = virtnet_get_rxfh_key_size, + .get_rxfh_indir_size = virtnet_get_rxfh_indir_size, + .get_rxfh = virtnet_get_rxfh, + .set_rxfh = virtnet_set_rxfh, + .get_rxnfc = virtnet_get_rxnfc, + .set_rxnfc = virtnet_set_rxnfc, }; static void virtnet_freeze_down(struct virtio_device *vdev) @@ -2678,6 +3015,16 @@ static int virtnet_set_features(struct net_device *dev, vi->guest_offloads = offloads; } + if ((dev->features ^ features) & NETIF_F_RXHASH) { + if (features & NETIF_F_RXHASH) + vi->ctrl->rss.hash_types = vi->rss_hash_types_saved; + else + vi->ctrl->rss.hash_types = VIRTIO_NET_HASH_REPORT_NONE; + + if (!virtnet_commit_rss_command(vi)) + return -EINVAL; + } + return 0; } @@ -2851,7 +3198,7 @@ static void virtnet_del_vqs(struct virtnet_info *vi) */ static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq) { - const unsigned int hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + const unsigned int hdr_len = vi->hdr_len; unsigned int rq_size = virtqueue_get_vring_size(vq); unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu; unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len; @@ -3072,6 +3419,10 @@ static bool virtnet_validate_features(struct virtio_device *vdev) "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_MQ, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR, + "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_RSS, + "VIRTIO_NET_F_CTRL_VQ") || + VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT, "VIRTIO_NET_F_CTRL_VQ"))) { return false; } @@ -3112,13 +3463,14 @@ static int virtnet_probe(struct virtio_device *vdev) u16 max_queue_pairs; int mtu; - /* Find if host supports multiqueue virtio_net device */ - err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ, - struct virtio_net_config, - max_virtqueue_pairs, &max_queue_pairs); + /* Find if host supports multiqueue/rss virtio_net device */ + max_queue_pairs = 1; + if (virtio_has_feature(vdev, VIRTIO_NET_F_MQ) || virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) + max_queue_pairs = + virtio_cread16(vdev, offsetof(struct virtio_net_config, max_virtqueue_pairs)); /* We need at least 2 queue's */ - if (err || max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || + if (max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) max_queue_pairs = 1; @@ -3206,8 +3558,33 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) vi->mergeable_rx_bufs = true; - if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) || - virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) + vi->has_rss_hash_report = true; + + if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) + vi->has_rss = true; + + if (vi->has_rss || vi->has_rss_hash_report) { + vi->rss_indir_table_size = + virtio_cread16(vdev, offsetof(struct virtio_net_config, + rss_max_indirection_table_length)); + vi->rss_key_size = + virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); + + vi->rss_hash_types_supported = + virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types)); + vi->rss_hash_types_supported &= + ~(VIRTIO_NET_RSS_HASH_TYPE_IP_EX | + VIRTIO_NET_RSS_HASH_TYPE_TCP_EX | + VIRTIO_NET_RSS_HASH_TYPE_UDP_EX); + + dev->hw_features |= NETIF_F_RXHASH; + } + + if (vi->has_rss_hash_report) + vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash); + else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) || + virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); else vi->hdr_len = sizeof(struct virtio_net_hdr); @@ -3274,6 +3651,9 @@ static int virtnet_probe(struct virtio_device *vdev) } } + if (vi->has_rss || vi->has_rss_hash_report) + virtnet_init_default_rss(vi); + err = register_netdev(dev); if (err) { pr_debug("virtio_net: registering device failed\n"); @@ -3405,7 +3785,8 @@ static struct virtio_device_id id_table[] = { VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \ VIRTIO_NET_F_CTRL_MAC_ADDR, \ VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \ - VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY + VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \ + VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT static unsigned int features[] = { VIRTNET_FEATURES, diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index de97ff98d36e..8a5e3a6d32d7 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -651,11 +651,11 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) - return -ENOBUFS; + return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); - return -ENOBUFS; + return -ENOMEM; } rd->remote_ip = *ip; diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 23d2954d9747..1e5672019922 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -349,7 +349,7 @@ static int __init cosa_init(void) } } else { cosa_major = register_chrdev(0, "cosa", &cosa_fops); - if (!cosa_major) { + if (cosa_major < 0) { pr_warn("unable to register chardev\n"); err = -EIO; goto out; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 0fad1331303c..aa9a7a5970fd 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -19,6 +19,7 @@ #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> +#include <net/dst_metadata.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> @@ -167,7 +168,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) goto err_peer; } - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 63e1c2d783c5..73693c66cef1 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1633,7 +1633,7 @@ static void ath10k_sdio_hif_power_down(struct ath10k *ar) return; } - ret = mmc_hw_reset(ar_sdio->func->card->host); + ret = mmc_hw_reset(ar_sdio->func->card); if (ret) ath10k_warn(ar, "unable to reset sdio: %d\n", ret); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index d5b83f90d27a..e6b34b0d61bd 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -3136,6 +3136,20 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, arvif->do_not_send_tmpl = true; else arvif->do_not_send_tmpl = false; + + if (vif->bss_conf.he_support) { + ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, + WMI_VDEV_PARAM_BA_MODE, + WMI_BA_MODE_BUFFER_SIZE_256); + if (ret) + ath11k_warn(ar->ab, + "failed to set BA BUFFER SIZE 256 for vdev: %d\n", + arvif->vdev_id); + else + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "Set BA BUFFER SIZE 256 for VDEV: %d\n", + arvif->vdev_id); + } } if (changed & (BSS_CHANGED_BEACON_INFO | BSS_CHANGED_BEACON)) { @@ -3171,14 +3185,6 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, if (arvif->is_up && vif->bss_conf.he_support && vif->bss_conf.he_oper.params) { - ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, - WMI_VDEV_PARAM_BA_MODE, - WMI_BA_MODE_BUFFER_SIZE_256); - if (ret) - ath11k_warn(ar->ab, - "failed to set BA BUFFER SIZE 256 for vdev: %d\n", - arvif->vdev_id); - param_id = WMI_VDEV_PARAM_HEOPS_0_31; param_value = vif->bss_conf.he_oper.params; ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 98090e40e1cf..e2791d45f5f5 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -839,7 +839,7 @@ static bool ath9k_txq_list_has_key(struct list_head *txq_list, u32 keyix) continue; txinfo = IEEE80211_SKB_CB(bf->bf_mpdu); - fi = (struct ath_frame_info *)&txinfo->rate_driver_data[0]; + fi = (struct ath_frame_info *)&txinfo->status.status_driver_data[0]; if (fi->keyix == keyix) return true; } diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index d0caf1de2bde..db83cc4ba810 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -141,8 +141,8 @@ static struct ath_frame_info *get_frame_info(struct sk_buff *skb) { struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); BUILD_BUG_ON(sizeof(struct ath_frame_info) > - sizeof(tx_info->rate_driver_data)); - return (struct ath_frame_info *) &tx_info->rate_driver_data[0]; + sizeof(tx_info->status.status_driver_data)); + return (struct ath_frame_info *) &tx_info->status.status_driver_data[0]; } static void ath_send_bar(struct ath_atx_tid *tid, u16 seqno) @@ -2542,6 +2542,16 @@ skip_tx_complete: spin_unlock_irqrestore(&sc->tx.txbuflock, flags); } +static void ath_clear_tx_status(struct ieee80211_tx_info *tx_info) +{ + void *ptr = &tx_info->status; + + memset(ptr + sizeof(tx_info->status.rates), 0, + sizeof(tx_info->status) - + sizeof(tx_info->status.rates) - + sizeof(tx_info->status.status_driver_data)); +} + static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_tx_status *ts, int nframes, int nbad, int txok) @@ -2553,6 +2563,8 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_hw *ah = sc->sc_ah; u8 i, tx_rateindex; + ath_clear_tx_status(tx_info); + if (txok) tx_info->status.ack_signal = ts->ts_rssi; @@ -2567,6 +2579,13 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, tx_info->status.ampdu_len = nframes; tx_info->status.ampdu_ack_len = nframes - nbad; + tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; + + for (i = tx_rateindex + 1; i < hw->max_rates; i++) { + tx_info->status.rates[i].count = 0; + tx_info->status.rates[i].idx = -1; + } + if ((ts->ts_status & ATH9K_TXERR_FILT) == 0 && (tx_info->flags & IEEE80211_TX_CTL_NO_ACK) == 0) { /* @@ -2588,16 +2607,6 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, tx_info->status.rates[tx_rateindex].count = hw->max_rate_tries; } - - for (i = tx_rateindex + 1; i < hw->max_rates; i++) { - tx_info->status.rates[i].count = 0; - tx_info->status.rates[i].idx = -1; - } - - tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; - - /* we report airtime in ath_tx_count_airtime(), don't report twice */ - tx_info->status.tx_time = 0; } static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index ba3c159111d3..212fbbe1cd7e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -557,7 +557,7 @@ enum brcmf_sdio_frmtype { BRCMF_SDIO_FT_SUB, }; -#define SDIOD_DRVSTR_KEY(chip, pmu) (((chip) << 16) | (pmu)) +#define SDIOD_DRVSTR_KEY(chip, pmu) (((unsigned int)(chip) << 16) | (pmu)) /* SDIO Pad drive strength to select value mappings */ struct sdiod_drive_str { @@ -4165,7 +4165,7 @@ static int brcmf_sdio_bus_reset(struct device *dev) /* reset the adapter */ sdio_claim_host(sdiodev->func1); - mmc_hw_reset(sdiodev->func1->card->host); + mmc_hw_reset(sdiodev->func1->card); sdio_release_host(sdiodev->func1); brcmf_bus_change_state(sdiodev->bus_if, BRCMF_BUS_DOWN); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index bde9e4bbfffe..4f3238d2a171 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -2639,7 +2639,7 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter) /* Run a HW reset of the SDIO interface. */ sdio_claim_host(func); - ret = mmc_hw_reset(func->card->host); + ret = mmc_hw_reset(func->card); sdio_release_host(func); switch (ret) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index 8a22ee581674..df85ebc6e1df 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -80,7 +80,7 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id) mt76_rmw_field(dev, 0x15a10, 0x1f << 16, 0x9); /* RG_SSUSB_G1_CDR_BIC_LTR = 0xf */ - mt76_rmw_field(dev, 0x15a0c, 0xf << 28, 0xf); + mt76_rmw_field(dev, 0x15a0c, 0xfU << 28, 0xf); /* RG_SSUSB_CDR_BR_PE1D = 0x3 */ mt76_rmw_field(dev, 0x15c58, 0x3 << 6, 0x3); diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index 72fc41ac83c0..9140b0163474 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -146,7 +146,7 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) * To guarantee that the SDIO card is power cycled, as required to make * the FW programming to succeed, let's do a brute force HW reset. */ - mmc_hw_reset(card->host); + mmc_hw_reset(card); sdio_enable_func(func); sdio_release_host(func); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 677fa4bf76d3..e1846d04817f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -366,7 +366,7 @@ static inline void nvme_end_req(struct request *req) { blk_status_t status = nvme_error_status(nvme_req(req)->status); - if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS)) + if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) nvme_log_error(req); nvme_end_req_zoned(req); nvme_trace_bio_complete(req); @@ -1015,6 +1015,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, goto out; } + req->rq_flags |= RQF_QUIET; ret = nvme_execute_rq(req, at_head); if (result && ret >= 0) *result = nvme_req(req)->result; @@ -1287,6 +1288,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_EUI64_LEN; memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN); return NVME_NIDT_EUI64_LEN; case NVME_NIDT_NGUID: @@ -1295,6 +1298,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_NGUID_LEN; memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN); return NVME_NIDT_NGUID_LEN; case NVME_NIDT_UUID: @@ -1303,6 +1308,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_UUID_LEN; uuid_copy(&ids->uuid, data + sizeof(*cur)); return NVME_NIDT_UUID_LEN; case NVME_NIDT_CSI: @@ -1399,12 +1406,18 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, if ((*id)->ncap == 0) /* namespace not allocated or attached */ goto out_free_id; - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); - if (ctrl->vs >= NVME_VS(1, 2, 0) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { + dev_info(ctrl->device, + "Ignoring bogus Namespace Identifiers\n"); + } else { + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + } return 0; @@ -1830,9 +1843,6 @@ static void nvme_update_disk_info(struct gendisk *disk, nvme_config_discard(disk, ns); blk_queue_max_write_zeroes_sectors(disk->queue, ns->ctrl->max_zeroes_sectors); - - set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) || - test_bit(NVME_NS_FORCE_RO, &ns->flags)); } static inline bool nvme_first_scan(struct gendisk *disk) @@ -1891,6 +1901,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) goto out_unfreeze; } + set_disk_ro(ns->disk, (id->nsattr & NVME_NS_ATTR_RO) || + test_bit(NVME_NS_FORCE_RO, &ns->flags)); set_bit(NVME_NS_READY, &ns->flags); blk_mq_unfreeze_queue(ns->disk->queue); @@ -1903,6 +1915,9 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) if (nvme_ns_head_multipath(ns->head)) { blk_mq_freeze_queue(ns->head->disk->queue); nvme_update_disk_info(ns->head->disk, ns, id); + set_disk_ro(ns->head->disk, + (id->nsattr & NVME_NS_ATTR_RO) || + test_bit(NVME_NS_FORCE_RO, &ns->flags)); nvme_mpath_revalidate_paths(ns); blk_stack_limits(&ns->head->disk->queue->limits, &ns->queue->limits, 0); @@ -3589,15 +3604,20 @@ static const struct attribute_group *nvme_dev_attr_groups[] = { NULL, }; -static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys, +static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns_head *h; - lockdep_assert_held(&subsys->lock); + lockdep_assert_held(&ctrl->subsys->lock); - list_for_each_entry(h, &subsys->nsheads, entry) { - if (h->ns_id != nsid) + list_for_each_entry(h, &ctrl->subsys->nsheads, entry) { + /* + * Private namespaces can share NSIDs under some conditions. + * In that case we can't use the same ns_head for namespaces + * with the same NSID. + */ + if (h->ns_id != nsid || !nvme_is_unique_nsid(ctrl, h)) continue; if (!list_empty(&h->list) && nvme_tryget_ns_head(h)) return h; @@ -3791,7 +3811,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, } mutex_lock(&ctrl->subsys->lock); - head = nvme_find_ns_head(ctrl->subsys, nsid); + head = nvme_find_ns_head(ctrl, nsid); if (!head) { ret = nvme_subsys_check_duplicate_ids(ctrl->subsys, ids); if (ret) { @@ -3988,6 +4008,16 @@ static void nvme_ns_remove(struct nvme_ns *ns) set_capacity(ns->disk, 0); nvme_fault_inject_fini(&ns->fault_inject); + /* + * Ensure that !NVME_NS_READY is seen by other threads to prevent + * this ns going back into current_path. + */ + synchronize_srcu(&ns->head->srcu); + + /* wait for concurrent submissions */ + if (nvme_mpath_clear_current_path(ns)) + synchronize_srcu(&ns->head->srcu); + mutex_lock(&ns->ctrl->subsys->lock); list_del_rcu(&ns->siblings); if (list_empty(&ns->head->list)) { @@ -3999,10 +4029,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) /* guarantee not available in head->list */ synchronize_rcu(); - /* wait for concurrent submissions */ - if (nvme_mpath_clear_current_path(ns)) - synchronize_srcu(&ns->head->srcu); - if (!nvme_ns_head_multipath(ns->head)) nvme_cdev_del(&ns->cdev, &ns->cdev_device); del_gendisk(ns->disk); @@ -4480,6 +4506,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) if (ctrl->queue_count > 1) { nvme_queue_scan(ctrl); nvme_start_queues(ctrl); + nvme_mpath_update(ctrl); } nvme_change_uevent(ctrl, "NVME_EVENT=connected"); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 1b31f19e1053..d464fdf978fb 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -482,10 +482,11 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) /* * Add a multipath node if the subsystems supports multiple controllers. - * We also do this for private namespaces as the namespace sharing data could - * change after a rescan. + * We also do this for private namespaces as the namespace sharing flag + * could change after a rescan. */ - if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath) + if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || + !nvme_is_unique_nsid(ctrl, head) || !multipath) return 0; head->disk = blk_alloc_disk(ctrl->numa_node); @@ -612,8 +613,17 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags); - - if (nvme_state_is_live(ns->ana_state)) + /* + * nvme_mpath_set_live() will trigger I/O to the multipath path device + * and in turn to this path device. However we cannot accept this I/O + * if the controller is not live. This may deadlock if called from + * nvme_mpath_init_identify() and the ctrl will never complete + * initialization, preventing I/O from completing. For this case we + * will reprocess the ANA log page in nvme_mpath_update() once the + * controller is ready. + */ + if (nvme_state_is_live(ns->ana_state) && + ns->ctrl->state == NVME_CTRL_LIVE) nvme_mpath_set_live(ns); } @@ -700,6 +710,18 @@ static void nvme_ana_work(struct work_struct *work) nvme_read_ana_log(ctrl); } +void nvme_mpath_update(struct nvme_ctrl *ctrl) +{ + u32 nr_change_groups = 0; + + if (!ctrl->ana_log_buf) + return; + + mutex_lock(&ctrl->ana_lock); + nvme_parse_ana_log(ctrl, &nr_change_groups, nvme_update_ana_state); + mutex_unlock(&ctrl->ana_lock); +} + static void nvme_anatt_timeout(struct timer_list *t) { struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index f4b674a8ce20..a2b53ca63335 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -144,6 +144,11 @@ enum nvme_quirks { * encoding the generation sequence number. */ NVME_QUIRK_SKIP_CID_GEN = (1 << 17), + + /* + * Reports garbage in the namespace identifiers (eui64, nguid, uuid). + */ + NVME_QUIRK_BOGUS_NID = (1 << 18), }; /* @@ -723,6 +728,25 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, return queue_live; return __nvme_check_ready(ctrl, rq, queue_live); } + +/* + * NSID shall be unique for all shared namespaces, or if at least one of the + * following conditions is met: + * 1. Namespace Management is supported by the controller + * 2. ANA is supported by the controller + * 3. NVM Set are supported by the controller + * + * In other case, private namespace are not required to report a unique NSID. + */ +static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl, + struct nvme_ns_head *head) +{ + return head->shared || + (ctrl->oacs & NVME_CTRL_OACS_NS_MNGT_SUPP) || + (ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) || + (ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS); +} + int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buf, unsigned bufflen); int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, @@ -782,6 +806,7 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); void nvme_mpath_remove_disk(struct nvme_ns_head *head); int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); +void nvme_mpath_update(struct nvme_ctrl *ctrl); void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); @@ -853,6 +878,9 @@ static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, "Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n"); return 0; } +static inline void nvme_mpath_update(struct nvme_ctrl *ctrl) +{ +} static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl) { } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 2e98ac3f3ad6..3aacf1c0d5a5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -45,7 +45,7 @@ #define NVME_MAX_SEGS 127 static int use_threaded_interrupts; -module_param(use_threaded_interrupts, int, 0); +module_param(use_threaded_interrupts, int, 0444); static bool use_cmb_sqes = true; module_param(use_cmb_sqes, bool, 0444); @@ -3409,7 +3409,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | - NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, + { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ @@ -3447,6 +3450,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1e4B, 0x1002), /* MAXIO MAP1002 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), @@ -3467,7 +3474,10 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_128_BYTES_SQES | NVME_QUIRK_SHARED_TAGS | NVME_QUIRK_SKIP_CID_GEN }, - + { PCI_DEVICE(0x144d, 0xa808), /* Samsung X5 */ + .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY| + NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { 0, } }; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 46d0dab686dd..397daaf51f1b 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -988,7 +988,7 @@ void nvmet_execute_async_event(struct nvmet_req *req) ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req; mutex_unlock(&ctrl->lock); - schedule_work(&ctrl->async_event_work); + queue_work(nvmet_wq, &ctrl->async_event_work); } void nvmet_execute_keep_alive(struct nvmet_req *req) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 8fedd1e052fe..e44b2988759e 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1555,7 +1555,7 @@ static void nvmet_port_release(struct config_item *item) struct nvmet_port *port = to_nvmet_port(item); /* Let inflight controllers teardown complete */ - flush_scheduled_work(); + flush_workqueue(nvmet_wq); list_del(&port->global_entry); kfree(port->ana_state); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 64c2d2f3e25c..90e75324dae0 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -20,6 +20,9 @@ struct workqueue_struct *zbd_wq; static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX]; static DEFINE_IDA(cntlid_ida); +struct workqueue_struct *nvmet_wq; +EXPORT_SYMBOL_GPL(nvmet_wq); + /* * This read/write semaphore is used to synchronize access to configuration * information on a target system that will result in discovery log page @@ -205,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, list_add_tail(&aen->entry, &ctrl->async_events); mutex_unlock(&ctrl->lock); - schedule_work(&ctrl->async_event_work); + queue_work(nvmet_wq, &ctrl->async_event_work); } static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid) @@ -385,7 +388,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work) if (reset_tbkas) { pr_debug("ctrl %d reschedule traffic based keep-alive timer\n", ctrl->cntlid); - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ); return; } @@ -403,7 +406,7 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) pr_debug("ctrl %d start keep-alive timer for %d secs\n", ctrl->cntlid, ctrl->kato); - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ); } void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl) @@ -1120,7 +1123,7 @@ static inline u8 nvmet_cc_iocqes(u32 cc) static inline bool nvmet_css_supported(u8 cc_css) { - switch (cc_css <<= NVME_CC_CSS_SHIFT) { + switch (cc_css << NVME_CC_CSS_SHIFT) { case NVME_CC_CSS_NVM: case NVME_CC_CSS_CSI: return true; @@ -1478,7 +1481,7 @@ void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl) mutex_lock(&ctrl->lock); if (!(ctrl->csts & NVME_CSTS_CFS)) { ctrl->csts |= NVME_CSTS_CFS; - schedule_work(&ctrl->fatal_err_work); + queue_work(nvmet_wq, &ctrl->fatal_err_work); } mutex_unlock(&ctrl->lock); } @@ -1619,9 +1622,15 @@ static int __init nvmet_init(void) goto out_free_zbd_work_queue; } + nvmet_wq = alloc_workqueue("nvmet-wq", WQ_MEM_RECLAIM, 0); + if (!nvmet_wq) { + error = -ENOMEM; + goto out_free_buffered_work_queue; + } + error = nvmet_init_discovery(); if (error) - goto out_free_work_queue; + goto out_free_nvmet_work_queue; error = nvmet_init_configfs(); if (error) @@ -1630,7 +1639,9 @@ static int __init nvmet_init(void) out_exit_discovery: nvmet_exit_discovery(); -out_free_work_queue: +out_free_nvmet_work_queue: + destroy_workqueue(nvmet_wq); +out_free_buffered_work_queue: destroy_workqueue(buffered_io_wq); out_free_zbd_work_queue: destroy_workqueue(zbd_wq); @@ -1642,6 +1653,7 @@ static void __exit nvmet_exit(void) nvmet_exit_configfs(); nvmet_exit_discovery(); ida_destroy(&cntlid_ida); + destroy_workqueue(nvmet_wq); destroy_workqueue(buffered_io_wq); destroy_workqueue(zbd_wq); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index de90001fc5c4..ab2627e17bb9 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1491,7 +1491,7 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport) list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (!nvmet_fc_tgt_a_get(assoc)) continue; - if (!schedule_work(&assoc->del_work)) + if (!queue_work(nvmet_wq, &assoc->del_work)) /* already deleting - release local reference */ nvmet_fc_tgt_a_put(assoc); } @@ -1546,7 +1546,7 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port, continue; assoc->hostport->invalid = 1; noassoc = false; - if (!schedule_work(&assoc->del_work)) + if (!queue_work(nvmet_wq, &assoc->del_work)) /* already deleting - release local reference */ nvmet_fc_tgt_a_put(assoc); } @@ -1592,7 +1592,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) nvmet_fc_tgtport_put(tgtport); if (found_ctrl) { - if (!schedule_work(&assoc->del_work)) + if (!queue_work(nvmet_wq, &assoc->del_work)) /* already deleting - release local reference */ nvmet_fc_tgt_a_put(assoc); return; @@ -2060,7 +2060,7 @@ nvmet_fc_rcv_ls_req(struct nvmet_fc_target_port *target_port, iod->rqstdatalen = lsreqbuf_len; iod->hosthandle = hosthandle; - schedule_work(&iod->work); + queue_work(nvmet_wq, &iod->work); return 0; } diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 54606f1872b4..5c16372f3b53 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -360,7 +360,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport, spin_lock(&rport->lock); list_add_tail(&rport->ls_list, &tls_req->ls_list); spin_unlock(&rport->lock); - schedule_work(&rport->ls_work); + queue_work(nvmet_wq, &rport->ls_work); return ret; } @@ -393,7 +393,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport, spin_lock(&rport->lock); list_add_tail(&rport->ls_list, &tls_req->ls_list); spin_unlock(&rport->lock); - schedule_work(&rport->ls_work); + queue_work(nvmet_wq, &rport->ls_work); } return 0; @@ -448,7 +448,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle, spin_lock(&tport->lock); list_add_tail(&tport->ls_list, &tls_req->ls_list); spin_unlock(&tport->lock); - schedule_work(&tport->ls_work); + queue_work(nvmet_wq, &tport->ls_work); return ret; } @@ -480,7 +480,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport, spin_lock(&tport->lock); list_add_tail(&tport->ls_list, &tls_req->ls_list); spin_unlock(&tport->lock); - schedule_work(&tport->ls_work); + queue_work(nvmet_wq, &tport->ls_work); } return 0; @@ -520,7 +520,7 @@ fcloop_tgt_discovery_evt(struct nvmet_fc_target_port *tgtport) tgt_rscn->tport = tgtport->private; INIT_WORK(&tgt_rscn->work, fcloop_tgt_rscn_work); - schedule_work(&tgt_rscn->work); + queue_work(nvmet_wq, &tgt_rscn->work); } static void @@ -739,7 +739,7 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport, INIT_WORK(&tfcp_req->tio_done_work, fcloop_tgt_fcprqst_done_work); kref_init(&tfcp_req->ref); - schedule_work(&tfcp_req->fcp_rcv_work); + queue_work(nvmet_wq, &tfcp_req->fcp_rcv_work); return 0; } @@ -921,7 +921,7 @@ fcloop_fcp_req_release(struct nvmet_fc_target_port *tgtport, { struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq); - schedule_work(&tfcp_req->tio_done_work); + queue_work(nvmet_wq, &tfcp_req->tio_done_work); } static void @@ -976,7 +976,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, if (abortio) /* leave the reference while the work item is scheduled */ - WARN_ON(!schedule_work(&tfcp_req->abort_rcv_work)); + WARN_ON(!queue_work(nvmet_wq, &tfcp_req->abort_rcv_work)); else { /* * as the io has already had the done callback made, diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 6485dc8eb974..f3d58abf11e0 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -283,7 +283,7 @@ static void nvmet_file_execute_flush(struct nvmet_req *req) if (!nvmet_check_transfer_len(req, 0)) return; INIT_WORK(&req->f.work, nvmet_file_flush_work); - schedule_work(&req->f.work); + queue_work(nvmet_wq, &req->f.work); } static void nvmet_file_execute_discard(struct nvmet_req *req) @@ -343,7 +343,7 @@ static void nvmet_file_execute_dsm(struct nvmet_req *req) if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req))) return; INIT_WORK(&req->f.work, nvmet_file_dsm_work); - schedule_work(&req->f.work); + queue_work(nvmet_wq, &req->f.work); } static void nvmet_file_write_zeroes_work(struct work_struct *w) @@ -373,7 +373,7 @@ static void nvmet_file_execute_write_zeroes(struct nvmet_req *req) if (!nvmet_check_transfer_len(req, 0)) return; INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work); - schedule_work(&req->f.work); + queue_work(nvmet_wq, &req->f.work); } u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 23f9d6f88804..59024af2da2e 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -166,7 +166,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, iod->req.transfer_len = blk_rq_payload_bytes(req); } - schedule_work(&iod->work); + queue_work(nvmet_wq, &iod->work); return BLK_STS_OK; } @@ -187,7 +187,7 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg) return; } - schedule_work(&iod->work); + queue_work(nvmet_wq, &iod->work); } static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl, diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index d910c6aad4b6..69818752a33a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -366,6 +366,7 @@ struct nvmet_req { extern struct workqueue_struct *buffered_io_wq; extern struct workqueue_struct *zbd_wq; +extern struct workqueue_struct *nvmet_wq; static inline void nvmet_set_result(struct nvmet_req *req, u32 result) { diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index a4de1e0d518b..5247c24538eb 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -283,7 +283,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) if (req->p.use_workqueue || effects) { INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work); req->p.rq = rq; - schedule_work(&req->p.work); + queue_work(nvmet_wq, &req->p.work); } else { rq->end_io_data = req; blk_execute_rq_nowait(rq, false, nvmet_passthru_req_done); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 2446d0918a41..2fab0b219b25 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1584,7 +1584,7 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, if (queue->host_qid == 0) { /* Let inflight controller teardown complete */ - flush_scheduled_work(); + flush_workqueue(nvmet_wq); } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); @@ -1669,7 +1669,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) if (disconnect) { rdma_disconnect(queue->cm_id); - schedule_work(&queue->release_work); + queue_work(nvmet_wq, &queue->release_work); } } @@ -1699,7 +1699,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); pr_err("failed to connect queue %d\n", queue->idx); - schedule_work(&queue->release_work); + queue_work(nvmet_wq, &queue->release_work); } /** @@ -1773,7 +1773,7 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, if (!queue) { struct nvmet_rdma_port *port = cm_id->context; - schedule_delayed_work(&port->repair_work, 0); + queue_delayed_work(nvmet_wq, &port->repair_work, 0); break; } fallthrough; @@ -1903,7 +1903,7 @@ static void nvmet_rdma_repair_port_work(struct work_struct *w) nvmet_rdma_disable_port(port); ret = nvmet_rdma_enable_port(port); if (ret) - schedule_delayed_work(&port->repair_work, 5 * HZ); + queue_delayed_work(nvmet_wq, &port->repair_work, 5 * HZ); } static int nvmet_rdma_add_port(struct nvmet_port *nport) @@ -2053,7 +2053,7 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data } mutex_unlock(&nvmet_rdma_queue_mutex); - flush_scheduled_work(); + flush_workqueue(nvmet_wq); } static struct ib_client nvmet_rdma_ib_client = { diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 83ca577f72be..2793554e622e 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1269,7 +1269,7 @@ static void nvmet_tcp_schedule_release_queue(struct nvmet_tcp_queue *queue) spin_lock(&queue->state_lock); if (queue->state != NVMET_TCP_Q_DISCONNECTING) { queue->state = NVMET_TCP_Q_DISCONNECTING; - schedule_work(&queue->release_work); + queue_work(nvmet_wq, &queue->release_work); } spin_unlock(&queue->state_lock); } @@ -1684,7 +1684,7 @@ static void nvmet_tcp_listen_data_ready(struct sock *sk) goto out; if (sk->sk_state == TCP_LISTEN) - schedule_work(&port->accept_work); + queue_work(nvmet_wq, &port->accept_work); out: read_unlock_bh(&sk->sk_callback_lock); } @@ -1815,7 +1815,7 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq) if (sq->qid == 0) { /* Let inflight controller teardown complete */ - flush_scheduled_work(); + flush_workqueue(nvmet_wq); } queue->nr_cmds = sq->size * 2; @@ -1876,12 +1876,12 @@ static void __exit nvmet_tcp_exit(void) nvmet_unregister_transport(&nvmet_tcp_ops); - flush_scheduled_work(); + flush_workqueue(nvmet_wq); mutex_lock(&nvmet_tcp_queue_mutex); list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list) kernel_sock_shutdown(queue->sock, SHUT_RDWR); mutex_unlock(&nvmet_tcp_queue_mutex); - flush_scheduled_work(); + flush_workqueue(nvmet_wq); destroy_workqueue(nvmet_tcp_wq); } diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index df84d221e3de..d270a204324e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -766,14 +766,6 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *irqd) return irqd->parent_data->hwirq; } -static void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry, - struct msi_desc *msi_desc) -{ - msi_entry->address = ((u64)msi_desc->msg.address_hi << 32) | - msi_desc->msg.address_lo; - msi_entry->data = msi_desc->msg.data; -} - /* * @nr_bm_irqs: Indicates the number of IRQs that were allocated from * the bitmap. @@ -3415,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; +#elif defined(CONFIG_ARM64) + /* + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. + */ + hbus->sysdata.parent = hdev->device.parent; #endif hbus->hdev = hdev; diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index afdcb91601d2..1e2d69453771 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -187,7 +187,7 @@ source "drivers/perf/hisilicon/Kconfig" config MARVELL_CN10K_DDR_PMU tristate "Enable MARVELL CN10K DRAM Subsystem(DSS) PMU Support" - depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT) help Enable perf support for Marvell DDR Performance monitoring event on CN10K platform. diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 94ebc1ecace7..b1b2a55de77f 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -29,7 +29,7 @@ #define CNTL_OVER_MASK 0xFFFFFFFE #define CNTL_CSV_SHIFT 24 -#define CNTL_CSV_MASK (0xFF << CNTL_CSV_SHIFT) +#define CNTL_CSV_MASK (0xFFU << CNTL_CSV_SHIFT) #define EVENT_CYCLES_ID 0 #define EVENT_CYCLES_COUNTER 0 diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index 7640491aab12..30234c261b05 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -736,7 +736,7 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( { u64 mpidr; int cpu_cluster_id; - struct cluster_pmu *cluster = NULL; + struct cluster_pmu *cluster; /* * This assumes that the cluster_id is in MPIDR[aff1] for @@ -758,10 +758,10 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( cluster->cluster_id); cpumask_set_cpu(cpu, &cluster->cluster_cpus); *per_cpu_ptr(l2cache_pmu->pmu_cluster, cpu) = cluster; - break; + return cluster; } - return cluster; + return NULL; } static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 5d4be9735d9d..6420ca129548 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -2,6 +2,7 @@ # tell define_trace.h where to find the cros ec trace header CFLAGS_cros_ec_trace.o:= -I$(src) +CFLAGS_cros_ec_sensorhub_ring.o:= -I$(src) obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o obj-$(CONFIG_CHROMEOS_PRIVACY_SCREEN) += chromeos_privacy_screen.o @@ -21,7 +22,7 @@ obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_chardev.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o obj-$(CONFIG_CROS_EC_DEBUGFS) += cros_ec_debugfs.o -cros-ec-sensorhub-objs := cros_ec_sensorhub.o cros_ec_sensorhub_ring.o cros_ec_trace.o +cros-ec-sensorhub-objs := cros_ec_sensorhub.o cros_ec_sensorhub_ring.o obj-$(CONFIG_CROS_EC_SENSORHUB) += cros-ec-sensorhub.o obj-$(CONFIG_CROS_EC_SYSFS) += cros_ec_sysfs.o obj-$(CONFIG_CROS_USBPD_LOGGER) += cros_usbpd_logger.o diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index 272c89837d74..0dbceee87a4b 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -25,6 +25,9 @@ #define CIRC_ADD(idx, size, value) (((idx) + (value)) & ((size) - 1)) +/* waitqueue for log readers */ +static DECLARE_WAIT_QUEUE_HEAD(cros_ec_debugfs_log_wq); + /** * struct cros_ec_debugfs - EC debugging information. * @@ -33,7 +36,6 @@ * @log_buffer: circular buffer for console log information * @read_msg: preallocated EC command and buffer to read console log * @log_mutex: mutex to protect circular buffer - * @log_wq: waitqueue for log readers * @log_poll_work: recurring task to poll EC for new console log data * @panicinfo_blob: panicinfo debugfs blob */ @@ -44,7 +46,6 @@ struct cros_ec_debugfs { struct circ_buf log_buffer; struct cros_ec_command *read_msg; struct mutex log_mutex; - wait_queue_head_t log_wq; struct delayed_work log_poll_work; /* EC panicinfo */ struct debugfs_blob_wrapper panicinfo_blob; @@ -107,7 +108,7 @@ static void cros_ec_console_log_work(struct work_struct *__work) buf_space--; } - wake_up(&debug_info->log_wq); + wake_up(&cros_ec_debugfs_log_wq); } mutex_unlock(&debug_info->log_mutex); @@ -141,7 +142,7 @@ static ssize_t cros_ec_console_log_read(struct file *file, char __user *buf, mutex_unlock(&debug_info->log_mutex); - ret = wait_event_interruptible(debug_info->log_wq, + ret = wait_event_interruptible(cros_ec_debugfs_log_wq, CIRC_CNT(cb->head, cb->tail, LOG_SIZE)); if (ret < 0) return ret; @@ -173,7 +174,7 @@ static __poll_t cros_ec_console_log_poll(struct file *file, struct cros_ec_debugfs *debug_info = file->private_data; __poll_t mask = 0; - poll_wait(file, &debug_info->log_wq, wait); + poll_wait(file, &cros_ec_debugfs_log_wq, wait); mutex_lock(&debug_info->log_mutex); if (CIRC_CNT(debug_info->log_buffer.head, @@ -377,7 +378,6 @@ static int cros_ec_create_console_log(struct cros_ec_debugfs *debug_info) debug_info->log_buffer.tail = 0; mutex_init(&debug_info->log_mutex); - init_waitqueue_head(&debug_info->log_wq); debugfs_create_file("console_log", S_IFREG | 0444, debug_info->dir, debug_info, &cros_ec_console_log_fops); diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index 98e37080f760..71948dade0e2 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -17,7 +17,8 @@ #include <linux/sort.h> #include <linux/slab.h> -#include "cros_ec_trace.h" +#define CREATE_TRACE_POINTS +#include "cros_ec_sensorhub_trace.h" /* Precision of fixed point for the m values from the filter */ #define M_PRECISION BIT(23) diff --git a/drivers/platform/chrome/cros_ec_sensorhub_trace.h b/drivers/platform/chrome/cros_ec_sensorhub_trace.h new file mode 100644 index 000000000000..57d9b4785969 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_sensorhub_trace.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Trace events for the ChromeOS Sensorhub kernel module + * + * Copyright 2021 Google LLC. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cros_ec + +#if !defined(_CROS_EC_SENSORHUB_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _CROS_EC_SENSORHUB_TRACE_H_ + +#include <linux/types.h> +#include <linux/platform_data/cros_ec_sensorhub.h> + +#include <linux/tracepoint.h> + +TRACE_EVENT(cros_ec_sensorhub_timestamp, + TP_PROTO(u32 ec_sample_timestamp, u32 ec_fifo_timestamp, s64 fifo_timestamp, + s64 current_timestamp, s64 current_time), + TP_ARGS(ec_sample_timestamp, ec_fifo_timestamp, fifo_timestamp, current_timestamp, + current_time), + TP_STRUCT__entry( + __field(u32, ec_sample_timestamp) + __field(u32, ec_fifo_timestamp) + __field(s64, fifo_timestamp) + __field(s64, current_timestamp) + __field(s64, current_time) + __field(s64, delta) + ), + TP_fast_assign( + __entry->ec_sample_timestamp = ec_sample_timestamp; + __entry->ec_fifo_timestamp = ec_fifo_timestamp; + __entry->fifo_timestamp = fifo_timestamp; + __entry->current_timestamp = current_timestamp; + __entry->current_time = current_time; + __entry->delta = current_timestamp - current_time; + ), + TP_printk("ec_ts: %9u, ec_fifo_ts: %9u, fifo_ts: %12lld, curr_ts: %12lld, curr_time: %12lld, delta %12lld", + __entry->ec_sample_timestamp, + __entry->ec_fifo_timestamp, + __entry->fifo_timestamp, + __entry->current_timestamp, + __entry->current_time, + __entry->delta + ) +); + +TRACE_EVENT(cros_ec_sensorhub_data, + TP_PROTO(u32 ec_sensor_num, u32 ec_fifo_timestamp, s64 fifo_timestamp, + s64 current_timestamp, s64 current_time), + TP_ARGS(ec_sensor_num, ec_fifo_timestamp, fifo_timestamp, current_timestamp, current_time), + TP_STRUCT__entry( + __field(u32, ec_sensor_num) + __field(u32, ec_fifo_timestamp) + __field(s64, fifo_timestamp) + __field(s64, current_timestamp) + __field(s64, current_time) + __field(s64, delta) + ), + TP_fast_assign( + __entry->ec_sensor_num = ec_sensor_num; + __entry->ec_fifo_timestamp = ec_fifo_timestamp; + __entry->fifo_timestamp = fifo_timestamp; + __entry->current_timestamp = current_timestamp; + __entry->current_time = current_time; + __entry->delta = current_timestamp - current_time; + ), + TP_printk("ec_num: %4u, ec_fifo_ts: %9u, fifo_ts: %12lld, curr_ts: %12lld, curr_time: %12lld, delta %12lld", + __entry->ec_sensor_num, + __entry->ec_fifo_timestamp, + __entry->fifo_timestamp, + __entry->current_timestamp, + __entry->current_time, + __entry->delta + ) +); + +TRACE_EVENT(cros_ec_sensorhub_filter, + TP_PROTO(struct cros_ec_sensors_ts_filter_state *state, s64 dx, s64 dy), + TP_ARGS(state, dx, dy), + TP_STRUCT__entry( + __field(s64, dx) + __field(s64, dy) + __field(s64, median_m) + __field(s64, median_error) + __field(s64, history_len) + __field(s64, x) + __field(s64, y) + ), + TP_fast_assign( + __entry->dx = dx; + __entry->dy = dy; + __entry->median_m = state->median_m; + __entry->median_error = state->median_error; + __entry->history_len = state->history_len; + __entry->x = state->x_offset; + __entry->y = state->y_offset; + ), + TP_printk("dx: %12lld. dy: %12lld median_m: %12lld median_error: %12lld len: %lld x: %12lld y: %12lld", + __entry->dx, + __entry->dy, + __entry->median_m, + __entry->median_error, + __entry->history_len, + __entry->x, + __entry->y + ) +); + + +#endif /* _CROS_EC_SENSORHUB_TRACE_H_ */ + +/* this part must be outside header guard */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE cros_ec_sensorhub_trace + +#include <trace/define_trace.h> diff --git a/drivers/platform/chrome/cros_ec_trace.h b/drivers/platform/chrome/cros_ec_trace.h index 7e7cfc98657a..9bb5cd2c98b8 100644 --- a/drivers/platform/chrome/cros_ec_trace.h +++ b/drivers/platform/chrome/cros_ec_trace.h @@ -15,7 +15,6 @@ #include <linux/types.h> #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> -#include <linux/platform_data/cros_ec_sensorhub.h> #include <linux/tracepoint.h> @@ -71,100 +70,6 @@ TRACE_EVENT(cros_ec_request_done, __entry->retval) ); -TRACE_EVENT(cros_ec_sensorhub_timestamp, - TP_PROTO(u32 ec_sample_timestamp, u32 ec_fifo_timestamp, s64 fifo_timestamp, - s64 current_timestamp, s64 current_time), - TP_ARGS(ec_sample_timestamp, ec_fifo_timestamp, fifo_timestamp, current_timestamp, - current_time), - TP_STRUCT__entry( - __field(u32, ec_sample_timestamp) - __field(u32, ec_fifo_timestamp) - __field(s64, fifo_timestamp) - __field(s64, current_timestamp) - __field(s64, current_time) - __field(s64, delta) - ), - TP_fast_assign( - __entry->ec_sample_timestamp = ec_sample_timestamp; - __entry->ec_fifo_timestamp = ec_fifo_timestamp; - __entry->fifo_timestamp = fifo_timestamp; - __entry->current_timestamp = current_timestamp; - __entry->current_time = current_time; - __entry->delta = current_timestamp - current_time; - ), - TP_printk("ec_ts: %9u, ec_fifo_ts: %9u, fifo_ts: %12lld, curr_ts: %12lld, curr_time: %12lld, delta %12lld", - __entry->ec_sample_timestamp, - __entry->ec_fifo_timestamp, - __entry->fifo_timestamp, - __entry->current_timestamp, - __entry->current_time, - __entry->delta - ) -); - -TRACE_EVENT(cros_ec_sensorhub_data, - TP_PROTO(u32 ec_sensor_num, u32 ec_fifo_timestamp, s64 fifo_timestamp, - s64 current_timestamp, s64 current_time), - TP_ARGS(ec_sensor_num, ec_fifo_timestamp, fifo_timestamp, current_timestamp, current_time), - TP_STRUCT__entry( - __field(u32, ec_sensor_num) - __field(u32, ec_fifo_timestamp) - __field(s64, fifo_timestamp) - __field(s64, current_timestamp) - __field(s64, current_time) - __field(s64, delta) - ), - TP_fast_assign( - __entry->ec_sensor_num = ec_sensor_num; - __entry->ec_fifo_timestamp = ec_fifo_timestamp; - __entry->fifo_timestamp = fifo_timestamp; - __entry->current_timestamp = current_timestamp; - __entry->current_time = current_time; - __entry->delta = current_timestamp - current_time; - ), - TP_printk("ec_num: %4u, ec_fifo_ts: %9u, fifo_ts: %12lld, curr_ts: %12lld, curr_time: %12lld, delta %12lld", - __entry->ec_sensor_num, - __entry->ec_fifo_timestamp, - __entry->fifo_timestamp, - __entry->current_timestamp, - __entry->current_time, - __entry->delta - ) -); - -TRACE_EVENT(cros_ec_sensorhub_filter, - TP_PROTO(struct cros_ec_sensors_ts_filter_state *state, s64 dx, s64 dy), - TP_ARGS(state, dx, dy), - TP_STRUCT__entry( - __field(s64, dx) - __field(s64, dy) - __field(s64, median_m) - __field(s64, median_error) - __field(s64, history_len) - __field(s64, x) - __field(s64, y) - ), - TP_fast_assign( - __entry->dx = dx; - __entry->dy = dy; - __entry->median_m = state->median_m; - __entry->median_error = state->median_error; - __entry->history_len = state->history_len; - __entry->x = state->x_offset; - __entry->y = state->y_offset; - ), - TP_printk("dx: %12lld. dy: %12lld median_m: %12lld median_error: %12lld len: %lld x: %12lld y: %12lld", - __entry->dx, - __entry->dy, - __entry->median_m, - __entry->median_error, - __entry->history_len, - __entry->x, - __entry->y - ) -); - - #endif /* _CROS_EC_TRACE_H_ */ /* this part must be outside header guard */ diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 5de0bfb0bc4d..4bd2752c0823 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -115,17 +115,18 @@ static int cros_typec_parse_port_props(struct typec_capability *cap, return ret; cap->data = ret; + /* Try-power-role is optional. */ ret = fwnode_property_read_string(fwnode, "try-power-role", &buf); if (ret) { - dev_err(dev, "try-power-role not found: %d\n", ret); - return ret; + dev_warn(dev, "try-power-role not found: %d\n", ret); + cap->prefer_role = TYPEC_NO_PREFERRED_ROLE; + } else { + ret = typec_find_power_role(buf); + if (ret < 0) + return ret; + cap->prefer_role = ret; } - ret = typec_find_power_role(buf); - if (ret < 0) - return ret; - cap->prefer_role = ret; - cap->fwnode = fwnode; return 0; @@ -227,6 +228,7 @@ static void cros_typec_remove_partner(struct cros_typec_data *typec, cros_typec_unregister_altmodes(typec, port_num, true); cros_typec_usb_disconnect_state(port); + port->mux_flags = USB_PD_MUX_NONE; typec_unregister_partner(port->partner); port->partner = NULL; @@ -512,20 +514,38 @@ static int cros_typec_enable_usb4(struct cros_typec_data *typec, } static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, - uint8_t mux_flags, struct ec_response_usb_pd_control_v2 *pd_ctrl) { struct cros_typec_port *port = typec->ports[port_num]; + struct ec_response_usb_pd_mux_info resp; + struct ec_params_usb_pd_mux_info req = { + .port = port_num, + }; struct ec_params_usb_pd_mux_ack mux_ack; enum typec_orientation orientation; int ret; - if (mux_flags == USB_PD_MUX_NONE) { + ret = cros_ec_command(typec->ec, 0, EC_CMD_USB_PD_MUX_INFO, + &req, sizeof(req), &resp, sizeof(resp)); + if (ret < 0) { + dev_warn(typec->dev, "Failed to get mux info for port: %d, err = %d\n", + port_num, ret); + return ret; + } + + /* No change needs to be made, let's exit early. */ + if (port->mux_flags == resp.flags && port->role == pd_ctrl->role) + return 0; + + port->mux_flags = resp.flags; + port->role = pd_ctrl->role; + + if (port->mux_flags == USB_PD_MUX_NONE) { ret = cros_typec_usb_disconnect_state(port); goto mux_ack; } - if (mux_flags & USB_PD_MUX_POLARITY_INVERTED) + if (port->mux_flags & USB_PD_MUX_POLARITY_INVERTED) orientation = TYPEC_ORIENTATION_REVERSE; else orientation = TYPEC_ORIENTATION_NORMAL; @@ -540,22 +560,22 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num, if (ret) return ret; - if (mux_flags & USB_PD_MUX_USB4_ENABLED) { + if (port->mux_flags & USB_PD_MUX_USB4_ENABLED) { ret = cros_typec_enable_usb4(typec, port_num, pd_ctrl); - } else if (mux_flags & USB_PD_MUX_TBT_COMPAT_ENABLED) { + } else if (port->mux_flags & USB_PD_MUX_TBT_COMPAT_ENABLED) { ret = cros_typec_enable_tbt(typec, port_num, pd_ctrl); - } else if (mux_flags & USB_PD_MUX_DP_ENABLED) { + } else if (port->mux_flags & USB_PD_MUX_DP_ENABLED) { ret = cros_typec_enable_dp(typec, port_num, pd_ctrl); - } else if (mux_flags & USB_PD_MUX_SAFE_MODE) { + } else if (port->mux_flags & USB_PD_MUX_SAFE_MODE) { ret = cros_typec_usb_safe_state(port); - } else if (mux_flags & USB_PD_MUX_USB_ENABLED) { + } else if (port->mux_flags & USB_PD_MUX_USB_ENABLED) { port->state.alt = NULL; port->state.mode = TYPEC_STATE_USB; ret = typec_mux_set(port->mux, &port->state); } else { dev_dbg(typec->dev, "Unrecognized mode requested, mux flags: %x\n", - mux_flags); + port->mux_flags); } mux_ack: @@ -630,17 +650,6 @@ static void cros_typec_set_port_params_v1(struct cros_typec_data *typec, } } -static int cros_typec_get_mux_info(struct cros_typec_data *typec, int port_num, - struct ec_response_usb_pd_mux_info *resp) -{ - struct ec_params_usb_pd_mux_info req = { - .port = port_num, - }; - - return cros_ec_command(typec->ec, 0, EC_CMD_USB_PD_MUX_INFO, &req, - sizeof(req), resp, sizeof(*resp)); -} - /* * Helper function to register partner/plug altmodes. */ @@ -938,7 +947,6 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) { struct ec_params_usb_pd_control req; struct ec_response_usb_pd_control_v2 resp; - struct ec_response_usb_pd_mux_info mux_resp; int ret; if (port_num < 0 || port_num >= typec->num_ports) { @@ -958,6 +966,11 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) if (ret < 0) return ret; + /* Update the switches if they exist, according to requested state */ + ret = cros_typec_configure_mux(typec, port_num, &resp); + if (ret) + dev_warn(typec->dev, "Configure muxes failed, err = %d\n", ret); + dev_dbg(typec->dev, "Enabled %d: 0x%hhx\n", port_num, resp.enabled); dev_dbg(typec->dev, "Role %d: 0x%hhx\n", port_num, resp.role); dev_dbg(typec->dev, "Polarity %d: 0x%hhx\n", port_num, resp.polarity); @@ -973,27 +986,7 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num) if (typec->typec_cmd_supported) cros_typec_handle_status(typec, port_num); - /* Update the switches if they exist, according to requested state */ - ret = cros_typec_get_mux_info(typec, port_num, &mux_resp); - if (ret < 0) { - dev_warn(typec->dev, - "Failed to get mux info for port: %d, err = %d\n", - port_num, ret); - return 0; - } - - /* No change needs to be made, let's exit early. */ - if (typec->ports[port_num]->mux_flags == mux_resp.flags && - typec->ports[port_num]->role == resp.role) - return 0; - - typec->ports[port_num]->mux_flags = mux_resp.flags; - typec->ports[port_num]->role = resp.role; - ret = cros_typec_configure_mux(typec, port_num, mux_resp.flags, &resp); - if (ret) - dev_warn(typec->dev, "Configure muxes failed, err = %d\n", ret); - - return ret; + return 0; } static int cros_typec_get_cmd_version(struct cros_typec_data *typec) @@ -1075,7 +1068,13 @@ static int cros_typec_probe(struct platform_device *pdev) return -ENOMEM; typec->dev = dev; + typec->ec = dev_get_drvdata(pdev->dev.parent); + if (!typec->ec) { + dev_err(dev, "couldn't find parent EC device\n"); + return -ENODEV; + } + platform_set_drvdata(pdev, typec); ret = cros_typec_get_cmd_version(typec); diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index 6b8b3ab8db48..3463629f8764 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -584,21 +584,6 @@ static struct platform_driver acerhdf_driver = { .remove = acerhdf_remove, }; -/* checks if str begins with start */ -static int str_starts_with(const char *str, const char *start) -{ - unsigned long str_len = 0, start_len = 0; - - str_len = strlen(str); - start_len = strlen(start); - - if (str_len >= start_len && - !strncmp(str, start, start_len)) - return 1; - - return 0; -} - /* check hardware */ static int __init acerhdf_check_hardware(void) { @@ -651,9 +636,9 @@ static int __init acerhdf_check_hardware(void) * check if actual hardware BIOS vendor, product and version * IDs start with the strings of BIOS table entry */ - if (str_starts_with(vendor, bt->vendor) && - str_starts_with(product, bt->product) && - str_starts_with(version, bt->version)) { + if (strstarts(vendor, bt->vendor) && + strstarts(product, bt->product) && + strstarts(version, bt->version)) { found = 1; break; } diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index e9d0dbbb2887..fa4123dbdf7f 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -160,8 +160,10 @@ MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); static struct amd_pmc_dev pmc; static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); -static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf); +#ifdef CONFIG_SUSPEND +static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); +#endif static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset) { @@ -325,6 +327,7 @@ static int get_metrics_table(struct amd_pmc_dev *pdev, struct smu_metrics *table return 0; } +#ifdef CONFIG_SUSPEND static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev) { struct smu_metrics table; @@ -338,6 +341,7 @@ static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev) dev_dbg(pdev->dev, "Last suspend in deepest state for %lluus\n", table.timein_s0i3_lastcapture); } +#endif #ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) @@ -569,6 +573,7 @@ out_unlock: return rc; } +#ifdef CONFIG_SUSPEND static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) { switch (dev->cpu_id) { @@ -694,6 +699,7 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = { .prepare = amd_pmc_s2idle_prepare, .restore = amd_pmc_s2idle_restore, }; +#endif static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) }, @@ -733,6 +739,7 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) return 0; } +#ifdef CONFIG_SUSPEND static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) { int err; @@ -753,6 +760,7 @@ static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) return 0; } +#endif static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf) { @@ -859,9 +867,11 @@ static int amd_pmc_probe(struct platform_device *pdev) amd_pmc_get_smu_version(dev); platform_set_drvdata(pdev, dev); +#ifdef CONFIG_SUSPEND err = acpi_register_lps0_dev(&amd_pmc_s2idle_dev_ops); if (err) dev_warn(dev->dev, "failed to register LPS0 sleep handler, expect increased power consumption\n"); +#endif amd_pmc_dbgfs_register(dev); return 0; @@ -875,7 +885,9 @@ static int amd_pmc_remove(struct platform_device *pdev) { struct amd_pmc_dev *dev = platform_get_drvdata(pdev); +#ifdef CONFIG_SUSPEND acpi_unregister_lps0_dev(&amd_pmc_s2idle_dev_ops); +#endif amd_pmc_dbgfs_unregister(dev); pci_dev_put(dev->rdev); mutex_destroy(&dev->lock); diff --git a/drivers/platform/x86/barco-p50-gpio.c b/drivers/platform/x86/barco-p50-gpio.c index f5c72e33f9ae..05534287bc26 100644 --- a/drivers/platform/x86/barco-p50-gpio.c +++ b/drivers/platform/x86/barco-p50-gpio.c @@ -10,7 +10,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/io.h> #include <linux/delay.h> #include <linux/dmi.h> #include <linux/err.h> diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index c1d9ed9b7b67..19f6b456234f 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -1121,8 +1121,6 @@ static void kbd_led_set(struct led_classdev *led_cdev, if (value > samsung->kbd_led.max_brightness) value = samsung->kbd_led.max_brightness; - else if (value < 0) - value = 0; samsung->kbd_led_wk = value; queue_work(samsung->led_workqueue, &samsung->kbd_led_work); diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index bce17ca97947..a01a92769c1a 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -740,16 +740,8 @@ static ssize_t certificate_store(struct kobject *kobj, if (!tlmi_priv.certificate_support) return -EOPNOTSUPP; - new_cert = kstrdup(buf, GFP_KERNEL); - if (!new_cert) - return -ENOMEM; - /* Strip out CR if one is present */ - strip_cr(new_cert); - /* If empty then clear installed certificate */ - if (new_cert[0] == '\0') { /* Clear installed certificate */ - kfree(new_cert); - + if ((buf[0] == '\0') || (buf[0] == '\n')) { /* Clear installed certificate */ /* Check that signature is set */ if (!setting->signature || !setting->signature[0]) return -EACCES; @@ -763,14 +755,16 @@ static ssize_t certificate_store(struct kobject *kobj, ret = tlmi_simple_call(LENOVO_CLEAR_BIOS_CERT_GUID, auth_str); kfree(auth_str); - if (ret) - return ret; - kfree(setting->certificate); - setting->certificate = NULL; - return count; + return ret ?: count; } + new_cert = kstrdup(buf, GFP_KERNEL); + if (!new_cert) + return -ENOMEM; + /* Strip out CR if one is present */ + strip_cr(new_cert); + if (setting->cert_installed) { /* Certificate is installed so this is an update */ if (!setting->signature || !setting->signature[0]) { @@ -792,21 +786,14 @@ static ssize_t certificate_store(struct kobject *kobj, auth_str = kasprintf(GFP_KERNEL, "%s,%s", new_cert, setting->password); } - if (!auth_str) { - kfree(new_cert); + kfree(new_cert); + if (!auth_str) return -ENOMEM; - } ret = tlmi_simple_call(guid, auth_str); kfree(auth_str); - if (ret) { - kfree(new_cert); - return ret; - } - kfree(setting->certificate); - setting->certificate = new_cert; - return count; + return ret ?: count; } static struct kobj_attribute auth_certificate = __ATTR_WO(certificate); @@ -1194,6 +1181,10 @@ static void tlmi_release_attr(void) kset_unregister(tlmi_priv.attribute_kset); + /* Free up any saved signatures */ + kfree(tlmi_priv.pwd_admin->signature); + kfree(tlmi_priv.pwd_admin->save_signature); + /* Authentication structures */ sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group); kobject_put(&tlmi_priv.pwd_admin->kobj); @@ -1210,11 +1201,6 @@ static void tlmi_release_attr(void) } kset_unregister(tlmi_priv.authentication_kset); - - /* Free up any saved certificates/signatures */ - kfree(tlmi_priv.pwd_admin->certificate); - kfree(tlmi_priv.pwd_admin->signature); - kfree(tlmi_priv.pwd_admin->save_signature); } static int tlmi_sysfs_init(void) diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index 4f69df6eed07..4daba6151cd6 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -63,7 +63,6 @@ struct tlmi_pwd_setting { int index; /*Used for HDD and NVME auth */ enum level_option level; bool cert_installed; - char *certificate; char *signature; char *save_signature; }; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index ea02c8dcd748..d925cb137e12 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -604,6 +604,12 @@ int power_supply_get_battery_info(struct power_supply *psy, err = samsung_sdi_battery_get_info(&psy->dev, value, &info); if (!err) goto out_ret_pointer; + else if (err == -ENODEV) + /* + * Device does not have a static battery. + * Proceed to look for a simple battery. + */ + err = 0; if (strcmp("simple-battery", value)) { err = -ENODEV; diff --git a/drivers/power/supply/samsung-sdi-battery.c b/drivers/power/supply/samsung-sdi-battery.c index 9d59f277f519..b33daab798b9 100644 --- a/drivers/power/supply/samsung-sdi-battery.c +++ b/drivers/power/supply/samsung-sdi-battery.c @@ -824,6 +824,7 @@ static struct samsung_sdi_battery samsung_sdi_batteries[] = { .constant_charge_current_max_ua = 900000, .constant_charge_voltage_max_uv = 4200000, .charge_term_current_ua = 200000, + .charge_restart_voltage_uv = 4170000, .maintenance_charge = samsung_maint_charge_table, .maintenance_charge_size = ARRAY_SIZE(samsung_maint_charge_table), .alert_low_temp_charge_current_ua = 300000, @@ -867,6 +868,7 @@ static struct samsung_sdi_battery samsung_sdi_batteries[] = { .constant_charge_current_max_ua = 1500000, .constant_charge_voltage_max_uv = 4350000, .charge_term_current_ua = 120000, + .charge_restart_voltage_uv = 4300000, .maintenance_charge = samsung_maint_charge_table, .maintenance_charge_size = ARRAY_SIZE(samsung_maint_charge_table), .alert_low_temp_charge_current_ua = 300000, diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c index 05147d2c3842..485e58b264c0 100644 --- a/drivers/regulator/atc260x-regulator.c +++ b/drivers/regulator/atc260x-regulator.c @@ -292,6 +292,7 @@ enum atc2603c_reg_ids { .bypass_mask = BIT(5), \ .active_discharge_reg = ATC2603C_PMU_SWITCH_CTL, \ .active_discharge_mask = BIT(1), \ + .active_discharge_on = BIT(1), \ .owner = THIS_MODULE, \ } diff --git a/drivers/regulator/rtq2134-regulator.c b/drivers/regulator/rtq2134-regulator.c index f21e3f8b21f2..8e13dea354a2 100644 --- a/drivers/regulator/rtq2134-regulator.c +++ b/drivers/regulator/rtq2134-regulator.c @@ -285,6 +285,7 @@ static const unsigned int rtq2134_buck_ramp_delay_table[] = { .enable_mask = RTQ2134_VOUTEN_MASK, \ .active_discharge_reg = RTQ2134_REG_BUCK##_id##_CFG0, \ .active_discharge_mask = RTQ2134_ACTDISCHG_MASK, \ + .active_discharge_on = RTQ2134_ACTDISCHG_MASK, \ .ramp_reg = RTQ2134_REG_BUCK##_id##_RSPCFG, \ .ramp_mask = RTQ2134_RSPUP_MASK, \ .ramp_delay_table = rtq2134_buck_ramp_delay_table, \ diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index cadea0344486..40befdd9dfa9 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -82,6 +82,35 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .min_uV = 2400000, .uV_step = 100000, .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, + { + .name = "LDO2", + .id = 2, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO2_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_2, + .vsel_mask = WM8994_LDO2_VSEL_MASK, + .ops = &wm8994_ldo2_ops, + .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, +}; + +static const struct regulator_desc wm8958_ldo_desc[] = { + { + .name = "LDO1", + .id = 1, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO1_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_1, + .vsel_mask = WM8994_LDO1_VSEL_MASK, + .ops = &wm8994_ldo1_ops, + .min_uV = 2400000, + .uV_step = 100000, + .enable_time = 3000, .owner = THIS_MODULE, }, { @@ -172,9 +201,16 @@ static int wm8994_ldo_probe(struct platform_device *pdev) * regulator core and we need not worry about it on the * error path. */ - ldo->regulator = devm_regulator_register(&pdev->dev, - &wm8994_ldo_desc[id], - &config); + if (ldo->wm8994->type == WM8994) { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8994_ldo_desc[id], + &config); + } else { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8958_ldo_desc[id], + &config); + } + if (IS_ERR(ldo->regulator)) { ret = PTR_ERR(ldo->regulator); dev_err(wm8994->dev, "Failed to register LDO%d: %d\n", diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c index 1e8315038850..a8dde4606360 100644 --- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c +++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c @@ -121,7 +121,9 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->rstc), "failed to get reset\n"); - reset_control_deassert(priv->rstc); + error = reset_control_deassert(priv->rstc); + if (error) + return error; priv->rcdev.ops = &rzg2l_usbphy_ctrl_reset_ops; priv->rcdev.of_reset_n_cells = 1; diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 24d3395964cc..4c5bba52b105 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; + int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - return tegra_bpmp_transfer(bpmp, &msg); + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index f6d6d4c26361..41c65b4d2baf 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1293,6 +1293,16 @@ config RTC_DRV_OPAL This driver can also be built as a module. If so, the module will be called rtc-opal. +config RTC_DRV_OPTEE + tristate "OP-TEE based RTC driver" + depends on OPTEE + help + Select this to get support for OP-TEE based RTC control on SoCs where + RTC are not accessible to the normal world (Linux). + + This driver can also be built as a module. If so, the module + will be called rtc-optee. + config RTC_DRV_ZYNQMP tristate "Xilinx Zynq Ultrascale+ MPSoC RTC" depends on OF && HAS_IOMEM diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index e92f3e943245..2d827d8261d5 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -115,6 +115,7 @@ obj-$(CONFIG_RTC_DRV_GAMECUBE) += rtc-gamecube.o obj-$(CONFIG_RTC_DRV_NTXEC) += rtc-ntxec.o obj-$(CONFIG_RTC_DRV_OMAP) += rtc-omap.o obj-$(CONFIG_RTC_DRV_OPAL) += rtc-opal.o +obj-$(CONFIG_RTC_DRV_OPTEE) += rtc-optee.o obj-$(CONFIG_RTC_DRV_PALMAS) += rtc-palmas.o obj-$(CONFIG_RTC_DRV_PCAP) += rtc-pcap.o obj-$(CONFIG_RTC_DRV_PCF2123) += rtc-pcf2123.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 4b460c61f1d8..3c8eec2218df 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -26,6 +26,15 @@ struct class *rtc_class; static void rtc_device_release(struct device *dev) { struct rtc_device *rtc = to_rtc_device(dev); + struct timerqueue_head *head = &rtc->timerqueue; + struct timerqueue_node *node; + + mutex_lock(&rtc->ops_lock); + while ((node = timerqueue_getnext(head))) + timerqueue_del(head, node); + mutex_unlock(&rtc->ops_lock); + + cancel_work_sync(&rtc->irqwork); ida_simple_remove(&rtc_ida, rtc->id); mutex_destroy(&rtc->ops_lock); @@ -390,9 +399,6 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) if (!rtc->ops->set_alarm) clear_bit(RTC_FEATURE_ALARM, rtc->features); - if (rtc->uie_unsupported) - clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); - if (rtc->ops->set_offset) set_bit(RTC_FEATURE_CORRECTION, rtc->features); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index d8e835798153..9edd662c69ac 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -804,9 +804,13 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) struct timerqueue_node *next = timerqueue_getnext(&rtc->timerqueue); struct rtc_time tm; ktime_t now; + int err; + + err = __rtc_read_time(rtc, &tm); + if (err) + return err; timer->enabled = 1; - __rtc_read_time(rtc, &tm); now = rtc_tm_to_ktime(tm); /* Skip over expired timers */ @@ -820,7 +824,6 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) trace_rtc_timer_enqueue(timer); if (!next || ktime_before(timer->node.expires, next->expires)) { struct rtc_wkalrm alarm; - int err; alarm.time = rtc_ktime_to_tm(timer->node.expires); alarm.enabled = 1; diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 336cb9aa5e33..d51565bcc189 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1955,7 +1955,7 @@ static int ds1307_probe(struct i2c_client *client, dev_info(ds1307->dev, "'wakeup-source' is set, request for an IRQ is disabled!\n"); /* We cannot support UIE mode if we do not have an IRQ line */ - ds1307->rtc->uie_unsupported = 1; + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, ds1307->rtc->features); } if (want_irq) { diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 75db7ab654a5..a24331ba8a5f 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1273,7 +1273,7 @@ ds1685_rtc_probe(struct platform_device *pdev) /* See if the platform doesn't support UIE. */ if (pdata->uie_unsupported) - rtc_dev->uie_unsupported = 1; + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc_dev->features); rtc->dev = rtc_dev; @@ -1285,13 +1285,10 @@ ds1685_rtc_probe(struct platform_device *pdev) * there won't be an automatic way of notifying the kernel about it, * unless ctrlc is explicitly polled. */ - if (!pdata->no_irq) { - ret = platform_get_irq(pdev, 0); - if (ret <= 0) - return ret; - - rtc->irq_num = ret; - + rtc->irq_num = platform_get_irq(pdev, 0); + if (rtc->irq_num <= 0) { + clear_bit(RTC_FEATURE_ALARM, rtc_dev->features); + } else { /* Request an IRQ. */ ret = devm_request_threaded_irq(&pdev->dev, rtc->irq_num, NULL, ds1685_rtc_irq_handler, @@ -1305,7 +1302,6 @@ ds1685_rtc_probe(struct platform_device *pdev) rtc->irq_num = 0; } } - rtc->no_irq = pdata->no_irq; /* Setup complete. */ ds1685_rtc_switch_to_bank0(rtc); @@ -1394,7 +1390,7 @@ ds1685_rtc_poweroff(struct platform_device *pdev) * have been taken care of by the shutdown scripts and this * is the final function call. */ - if (!rtc->no_irq) + if (rtc->irq_num) disable_irq_nosync(rtc->irq_num); /* Oscillator must be on and the countdown chain enabled. */ diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c index 138c5e0046c8..11850c2880ad 100644 --- a/drivers/rtc/rtc-efi.c +++ b/drivers/rtc/rtc-efi.c @@ -261,15 +261,17 @@ static int __init efi_rtc_probe(struct platform_device *dev) if (efi.get_time(&eft, &cap) != EFI_SUCCESS) return -ENODEV; - rtc = devm_rtc_device_register(&dev->dev, "rtc-efi", &efi_rtc_ops, - THIS_MODULE); + rtc = devm_rtc_allocate_device(&dev->dev); if (IS_ERR(rtc)) return PTR_ERR(rtc); - rtc->uie_unsupported = 1; platform_set_drvdata(dev, rtc); - return 0; + rtc->ops = &efi_rtc_ops; + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); + set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + + return devm_rtc_register_device(rtc); } static struct platform_driver efi_rtc_driver = { diff --git a/drivers/rtc/rtc-gamecube.c b/drivers/rtc/rtc-gamecube.c index f717b36f4738..18ca3b38b2d0 100644 --- a/drivers/rtc/rtc-gamecube.c +++ b/drivers/rtc/rtc-gamecube.c @@ -235,6 +235,7 @@ static int gamecube_rtc_read_offset_from_sram(struct priv *d) } ret = of_address_to_resource(np, 0, &res); + of_node_put(np); if (ret) { pr_err("no io memory range found\n"); return -1; diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c index 0751cae27285..90e602e99d03 100644 --- a/drivers/rtc/rtc-hym8563.c +++ b/drivers/rtc/rtc-hym8563.c @@ -220,24 +220,6 @@ static int hym8563_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) u8 buf[4]; int ret; - /* - * The alarm has no seconds so deal with it - */ - if (alm_tm->tm_sec) { - alm_tm->tm_sec = 0; - alm_tm->tm_min++; - if (alm_tm->tm_min >= 60) { - alm_tm->tm_min = 0; - alm_tm->tm_hour++; - if (alm_tm->tm_hour >= 24) { - alm_tm->tm_hour = 0; - alm_tm->tm_mday++; - if (alm_tm->tm_mday > 31) - alm_tm->tm_mday = 0; - } - } - } - ret = i2c_smbus_read_byte_data(client, HYM8563_CTL2); if (ret < 0) return ret; @@ -523,6 +505,10 @@ static int hym8563_probe(struct i2c_client *client, if (!hym8563) return -ENOMEM; + hym8563->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(hym8563->rtc)) + return PTR_ERR(hym8563->rtc); + hym8563->client = client; i2c_set_clientdata(client, hym8563); @@ -557,19 +543,15 @@ static int hym8563_probe(struct i2c_client *client, dev_dbg(&client->dev, "rtc information is %s\n", (ret & HYM8563_SEC_VL) ? "invalid" : "valid"); - hym8563->rtc = devm_rtc_device_register(&client->dev, client->name, - &hym8563_rtc_ops, THIS_MODULE); - if (IS_ERR(hym8563->rtc)) - return PTR_ERR(hym8563->rtc); - - /* the hym8563 alarm only supports a minute accuracy */ - hym8563->rtc->uie_unsupported = 1; + hym8563->rtc->ops = &hym8563_rtc_ops; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, hym8563->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, hym8563->rtc->features); #ifdef CONFIG_COMMON_CLK hym8563_clkout_register_clk(hym8563); #endif - return 0; + return devm_rtc_register_device(hym8563->rtc); } static const struct i2c_device_id hym8563_id[] = { diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 6d383b629d20..d868458cd40e 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -932,10 +932,8 @@ static int m41t80_probe(struct i2c_client *client, m41t80_data->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; m41t80_data->rtc->range_max = RTC_TIMESTAMP_END_2099; - if (client->irq <= 0) { - /* We cannot support UIE mode if we do not have an IRQ line */ - m41t80_data->rtc->uie_unsupported = 1; - } + if (client->irq <= 0) + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, m41t80_data->rtc->features); /* Make sure HT (Halt Update) bit is cleared */ rc = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_HOUR); diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index ae9f131b43c0..522449b25921 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -176,6 +176,17 @@ int mc146818_get_time(struct rtc_time *time) } EXPORT_SYMBOL_GPL(mc146818_get_time); +/* AMD systems don't allow access to AltCentury with DV1 */ +static bool apply_amd_register_a_behavior(void) +{ +#ifdef CONFIG_X86 + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + return true; +#endif + return false; +} + /* Set the current date and time in the real time clock. */ int mc146818_set_time(struct rtc_time *time) { @@ -232,8 +243,10 @@ int mc146818_set_time(struct rtc_time *time) if (yrs >= 100) yrs -= 100; - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) - || RTC_ALWAYS_BCD) { + spin_lock_irqsave(&rtc_lock, flags); + save_control = CMOS_READ(RTC_CONTROL); + spin_unlock_irqrestore(&rtc_lock, flags); + if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { sec = bin2bcd(sec); min = bin2bcd(min); hrs = bin2bcd(hrs); @@ -247,7 +260,10 @@ int mc146818_set_time(struct rtc_time *time) save_control = CMOS_READ(RTC_CONTROL); CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + if (apply_amd_register_a_behavior()) + CMOS_WRITE((save_freq_select & ~RTC_AMD_BANK_SELECT), RTC_FREQ_SELECT); + else + CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); #ifdef CONFIG_MACH_DECSTATION CMOS_WRITE(real_yrs, RTC_DEC_YEAR); diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c index bb2ea9bc56f2..6d7656a75cae 100644 --- a/drivers/rtc/rtc-mpc5121.c +++ b/drivers/rtc/rtc-mpc5121.c @@ -210,20 +210,6 @@ static int mpc5121_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) struct mpc5121_rtc_data *rtc = dev_get_drvdata(dev); struct mpc5121_rtc_regs __iomem *regs = rtc->regs; - /* - * the alarm has no seconds so deal with it - */ - if (alarm->time.tm_sec) { - alarm->time.tm_sec = 0; - alarm->time.tm_min++; - if (alarm->time.tm_min >= 60) { - alarm->time.tm_min = 0; - alarm->time.tm_hour++; - if (alarm->time.tm_hour >= 24) - alarm->time.tm_hour = 0; - } - } - alarm->time.tm_mday = -1; alarm->time.tm_mon = -1; alarm->time.tm_year = -1; @@ -349,7 +335,8 @@ static int mpc5121_rtc_probe(struct platform_device *op) } rtc->rtc->ops = &mpc5200_rtc_ops; - rtc->rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->rtc->features); rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_0000; rtc->rtc->range_max = 65733206399ULL; /* 4052-12-31 23:59:59 */ diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c index f8f49a969c23..ad41aaf8a17f 100644 --- a/drivers/rtc/rtc-opal.c +++ b/drivers/rtc/rtc-opal.c @@ -250,7 +250,7 @@ static int opal_rtc_probe(struct platform_device *pdev) rtc->ops = &opal_rtc_ops; rtc->range_min = RTC_TIMESTAMP_BEGIN_0000; rtc->range_max = RTC_TIMESTAMP_END_9999; - rtc->uie_unsupported = 1; + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); return devm_rtc_register_device(rtc); } diff --git a/drivers/rtc/rtc-optee.c b/drivers/rtc/rtc-optee.c new file mode 100644 index 000000000000..9f8b5d4a8f6b --- /dev/null +++ b/drivers/rtc/rtc-optee.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Microchip. + */ + +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/rtc.h> +#include <linux/tee_drv.h> + +#define RTC_INFO_VERSION 0x1 + +#define TA_CMD_RTC_GET_INFO 0x0 +#define TA_CMD_RTC_GET_TIME 0x1 +#define TA_CMD_RTC_SET_TIME 0x2 +#define TA_CMD_RTC_GET_OFFSET 0x3 +#define TA_CMD_RTC_SET_OFFSET 0x4 + +#define TA_RTC_FEATURE_CORRECTION BIT(0) + +struct optee_rtc_time { + u32 tm_sec; + u32 tm_min; + u32 tm_hour; + u32 tm_mday; + u32 tm_mon; + u32 tm_year; + u32 tm_wday; +}; + +struct optee_rtc_info { + u64 version; + u64 features; + struct optee_rtc_time range_min; + struct optee_rtc_time range_max; +}; + +/** + * struct optee_rtc - OP-TEE RTC private data + * @dev: OP-TEE based RTC device. + * @ctx: OP-TEE context handler. + * @session_id: RTC TA session identifier. + * @shm: Memory pool shared with RTC device. + * @features: Bitfield of RTC features + */ +struct optee_rtc { + struct device *dev; + struct tee_context *ctx; + u32 session_id; + struct tee_shm *shm; + u64 features; +}; + +static int optee_rtc_readtime(struct device *dev, struct rtc_time *tm) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct optee_rtc_time *optee_tm; + struct tee_param param[4] = {0}; + int ret; + + inv_arg.func = TA_CMD_RTC_GET_TIME; + inv_arg.session = priv->session_id; + inv_arg.num_params = 4; + + /* Fill invoke cmd params */ + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; + param[0].u.memref.shm = priv->shm; + param[0].u.memref.size = sizeof(struct optee_rtc_time); + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + optee_tm = tee_shm_get_va(priv->shm, 0); + if (IS_ERR(optee_tm)) + return PTR_ERR(optee_tm); + + if (param[0].u.memref.size != sizeof(*optee_tm)) + return -EPROTO; + + tm->tm_sec = optee_tm->tm_sec; + tm->tm_min = optee_tm->tm_min; + tm->tm_hour = optee_tm->tm_hour; + tm->tm_mday = optee_tm->tm_mday; + tm->tm_mon = optee_tm->tm_mon; + tm->tm_year = optee_tm->tm_year - 1900; + tm->tm_wday = optee_tm->tm_wday; + tm->tm_yday = rtc_year_days(tm->tm_mday, tm->tm_mon, tm->tm_year); + + return 0; +} + +static int optee_rtc_settime(struct device *dev, struct rtc_time *tm) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[4] = {0}; + struct optee_rtc_time optee_tm; + void *rtc_data; + int ret; + + optee_tm.tm_sec = tm->tm_sec; + optee_tm.tm_min = tm->tm_min; + optee_tm.tm_hour = tm->tm_hour; + optee_tm.tm_mday = tm->tm_mday; + optee_tm.tm_mon = tm->tm_mon; + optee_tm.tm_year = tm->tm_year + 1900; + optee_tm.tm_wday = tm->tm_wday; + + inv_arg.func = TA_CMD_RTC_SET_TIME; + inv_arg.session = priv->session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT; + param[0].u.memref.shm = priv->shm; + param[0].u.memref.size = sizeof(struct optee_rtc_time); + + rtc_data = tee_shm_get_va(priv->shm, 0); + if (IS_ERR(rtc_data)) + return PTR_ERR(rtc_data); + + memcpy(rtc_data, &optee_tm, sizeof(struct optee_rtc_time)); + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + return 0; +} + +static int optee_rtc_readoffset(struct device *dev, long *offset) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[4] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_CORRECTION)) + return -EOPNOTSUPP; + + inv_arg.func = TA_CMD_RTC_GET_OFFSET; + inv_arg.session = priv->session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + *offset = param[0].u.value.a; + + return 0; +} + +static int optee_rtc_setoffset(struct device *dev, long offset) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[4] = {0}; + int ret; + + if (!(priv->features & TA_RTC_FEATURE_CORRECTION)) + return -EOPNOTSUPP; + + inv_arg.func = TA_CMD_RTC_SET_OFFSET; + inv_arg.session = priv->session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT; + param[0].u.value.a = offset; + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + return 0; +} + +static const struct rtc_class_ops optee_rtc_ops = { + .read_time = optee_rtc_readtime, + .set_time = optee_rtc_settime, + .set_offset = optee_rtc_setoffset, + .read_offset = optee_rtc_readoffset, +}; + +static int optee_rtc_read_info(struct device *dev, struct rtc_device *rtc, + u64 *features) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + struct tee_ioctl_invoke_arg inv_arg = {0}; + struct tee_param param[4] = {0}; + struct optee_rtc_info *info; + struct optee_rtc_time *tm; + int ret; + + inv_arg.func = TA_CMD_RTC_GET_INFO; + inv_arg.session = priv->session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; + param[0].u.memref.shm = priv->shm; + param[0].u.memref.size = sizeof(*info); + + ret = tee_client_invoke_func(priv->ctx, &inv_arg, param); + if (ret < 0 || inv_arg.ret != 0) + return ret ? ret : -EPROTO; + + info = tee_shm_get_va(priv->shm, 0); + if (IS_ERR(info)) + return PTR_ERR(info); + + if (param[0].u.memref.size != sizeof(*info)) + return -EPROTO; + + if (info->version != RTC_INFO_VERSION) + return -EPROTO; + + *features = info->features; + + tm = &info->range_min; + rtc->range_min = mktime64(tm->tm_year, tm->tm_mon, tm->tm_mday, tm->tm_hour, tm->tm_min, + tm->tm_sec); + tm = &info->range_max; + rtc->range_max = mktime64(tm->tm_year, tm->tm_mon, tm->tm_mday, tm->tm_hour, tm->tm_min, + tm->tm_sec); + + return 0; +} + +static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data) +{ + if (ver->impl_id == TEE_IMPL_ID_OPTEE) + return 1; + else + return 0; +} + +static int optee_rtc_probe(struct device *dev) +{ + struct tee_client_device *rtc_device = to_tee_client_device(dev); + struct tee_ioctl_open_session_arg sess_arg; + struct optee_rtc *priv; + struct rtc_device *rtc; + struct tee_shm *shm; + int ret, err; + + memset(&sess_arg, 0, sizeof(sess_arg)); + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + rtc = devm_rtc_allocate_device(dev); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + + /* Open context with TEE driver */ + priv->ctx = tee_client_open_context(NULL, optee_ctx_match, NULL, NULL); + if (IS_ERR(priv->ctx)) + return -ENODEV; + + /* Open session with rtc Trusted App */ + export_uuid(sess_arg.uuid, &rtc_device->id.uuid); + sess_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL; + + ret = tee_client_open_session(priv->ctx, &sess_arg, NULL); + if (ret < 0 || sess_arg.ret != 0) { + dev_err(dev, "tee_client_open_session failed, err: %x\n", sess_arg.ret); + err = -EINVAL; + goto out_ctx; + } + priv->session_id = sess_arg.session; + + shm = tee_shm_alloc_kernel_buf(priv->ctx, sizeof(struct optee_rtc_info)); + if (IS_ERR(shm)) { + dev_err(priv->dev, "tee_shm_alloc_kernel_buf failed\n"); + err = PTR_ERR(shm); + goto out_sess; + } + + priv->shm = shm; + priv->dev = dev; + dev_set_drvdata(dev, priv); + + rtc->ops = &optee_rtc_ops; + + err = optee_rtc_read_info(dev, rtc, &priv->features); + if (err) { + dev_err(dev, "Failed to get RTC features from OP-TEE\n"); + goto out_shm; + } + + err = devm_rtc_register_device(rtc); + if (err) + goto out_shm; + + /* + * We must clear this bit after registering because rtc_register_device + * will set it if it sees that .set_offset is provided. + */ + if (!(priv->features & TA_RTC_FEATURE_CORRECTION)) + clear_bit(RTC_FEATURE_CORRECTION, rtc->features); + + return 0; + +out_shm: + tee_shm_free(priv->shm); +out_sess: + tee_client_close_session(priv->ctx, priv->session_id); +out_ctx: + tee_client_close_context(priv->ctx); + + return err; +} + +static int optee_rtc_remove(struct device *dev) +{ + struct optee_rtc *priv = dev_get_drvdata(dev); + + tee_client_close_session(priv->ctx, priv->session_id); + tee_client_close_context(priv->ctx); + + return 0; +} + +static const struct tee_client_device_id optee_rtc_id_table[] = { + {UUID_INIT(0xf389f8c8, 0x845f, 0x496c, + 0x8b, 0xbe, 0xd6, 0x4b, 0xd2, 0x4c, 0x92, 0xfd)}, + {} +}; + +MODULE_DEVICE_TABLE(tee, optee_rtc_id_table); + +static struct tee_client_driver optee_rtc_driver = { + .id_table = optee_rtc_id_table, + .driver = { + .name = "optee_rtc", + .bus = &tee_bus_type, + .probe = optee_rtc_probe, + .remove = optee_rtc_remove, + }, +}; + +static int __init optee_rtc_mod_init(void) +{ + return driver_register(&optee_rtc_driver.driver); +} + +static void __exit optee_rtc_mod_exit(void) +{ + driver_unregister(&optee_rtc_driver.driver); +} + +module_init(optee_rtc_mod_init); +module_exit(optee_rtc_mod_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Clément Léger <clement.leger@bootlin.com>"); +MODULE_DESCRIPTION("OP-TEE based RTC driver"); diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c index 7473e6c8a183..e13b5e695d06 100644 --- a/drivers/rtc/rtc-pcf2123.c +++ b/drivers/rtc/rtc-pcf2123.c @@ -427,7 +427,8 @@ static int pcf2123_probe(struct spi_device *spi) * support to this driver to generate interrupts more than once * per minute. */ - rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); rtc->ops = &pcf2123_rtc_ops; rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; rtc->range_max = RTC_TIMESTAMP_END_2099; diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 81a5b1f2e68c..63b275b014bd 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -374,7 +374,8 @@ static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127) static int pcf2127_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) { struct pcf2127 *pcf2127 = dev_get_drvdata(dev); - unsigned int buf[5], ctrl2; + u8 buf[5]; + unsigned int ctrl2; int ret; ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL2, &ctrl2); @@ -655,13 +656,25 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap, pcf2127->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; pcf2127->rtc->range_max = RTC_TIMESTAMP_END_2099; pcf2127->rtc->set_start_time = true; /* Sets actual start to 1970 */ - pcf2127->rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_2S, pcf2127->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, pcf2127->rtc->features); clear_bit(RTC_FEATURE_ALARM, pcf2127->rtc->features); if (alarm_irq > 0) { + unsigned long flags; + + /* + * If flags = 0, devm_request_threaded_irq() will use IRQ flags + * obtained from device tree. + */ + if (dev_fwnode(dev)) + flags = 0; + else + flags = IRQF_TRIGGER_LOW; + ret = devm_request_threaded_irq(dev, alarm_irq, NULL, pcf2127_rtc_irq, - IRQF_TRIGGER_LOW | IRQF_ONESHOT, + flags | IRQF_ONESHOT, dev_name(dev), dev); if (ret) { dev_err(dev, "failed to request alarm irq\n"); diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index df2b072c394d..9760824ec199 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -616,7 +616,8 @@ static int pcf85063_probe(struct i2c_client *client) pcf85063->rtc->ops = &pcf85063_rtc_ops; pcf85063->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; pcf85063->rtc->range_max = RTC_TIMESTAMP_END_2099; - pcf85063->rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_2S, pcf85063->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, pcf85063->rtc->features); clear_bit(RTC_FEATURE_ALARM, pcf85063->rtc->features); if (config->has_alarms && client->irq > 0) { diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index c93acade7205..b1b1943de844 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -212,14 +212,6 @@ static int pcf8523_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm) if (err < 0) return err; - /* The alarm has no seconds, round up to nearest minute */ - if (tm->time.tm_sec) { - time64_t alarm_time = rtc_tm_to_time64(&tm->time); - - alarm_time += 60 - tm->time.tm_sec; - rtc_time64_to_tm(alarm_time, &tm->time); - } - regs[0] = bin2bcd(tm->time.tm_min); regs[1] = bin2bcd(tm->time.tm_hour); regs[2] = bin2bcd(tm->time.tm_mday); @@ -240,9 +232,9 @@ static int pcf8523_param_get(struct device *dev, struct rtc_param *param) { struct pcf8523 *pcf8523 = dev_get_drvdata(dev); int ret; + u32 value; switch(param->param) { - u32 value; case RTC_PARAM_BACKUP_SWITCH_MODE: ret = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL3, &value); @@ -279,9 +271,9 @@ static int pcf8523_param_get(struct device *dev, struct rtc_param *param) static int pcf8523_param_set(struct device *dev, struct rtc_param *param) { struct pcf8523 *pcf8523 = dev_get_drvdata(dev); + u8 mode; switch(param->param) { - u8 mode; case RTC_PARAM_BACKUP_SWITCH_MODE: switch (param->uvalue) { case RTC_BSM_DISABLED: @@ -450,7 +442,8 @@ static int pcf8523_probe(struct i2c_client *client, rtc->ops = &pcf8523_rtc_ops; rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; rtc->range_max = RTC_TIMESTAMP_END_2099; - rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); if (client->irq > 0) { err = regmap_write(pcf8523->regmap, PCF8523_TMR_CLKOUT_CTRL, 0x38); diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index c8bddfb94129..9d06813e2e6d 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -330,19 +330,6 @@ static int pcf8563_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm) unsigned char buf[4]; int err; - /* The alarm has no seconds, round up to nearest minute */ - if (tm->time.tm_sec) { - time64_t alarm_time = rtc_tm_to_time64(&tm->time); - - alarm_time += 60 - tm->time.tm_sec; - rtc_time64_to_tm(alarm_time, &tm->time); - } - - dev_dbg(dev, "%s, min=%d hour=%d wday=%d mday=%d " - "enabled=%d pending=%d\n", __func__, - tm->time.tm_min, tm->time.tm_hour, tm->time.tm_wday, - tm->time.tm_mday, tm->enabled, tm->pending); - buf[0] = bin2bcd(tm->time.tm_min); buf[1] = bin2bcd(tm->time.tm_hour); buf[2] = bin2bcd(tm->time.tm_mday); @@ -565,7 +552,8 @@ static int pcf8563_probe(struct i2c_client *client, pcf8563->rtc->ops = &pcf8563_rtc_ops; /* the pcf8563 alarm only supports a minute accuracy */ - pcf8563->rtc->uie_unsupported = 1; + set_bit(RTC_FEATURE_ALARM_RES_MINUTE, pcf8563->rtc->features); + clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, pcf8563->rtc->features); pcf8563->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; pcf8563->rtc->range_max = RTC_TIMESTAMP_END_2099; pcf8563->rtc->set_start_time = true; diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c index e38ee8848385..bad6a5d9c683 100644 --- a/drivers/rtc/rtc-pl031.c +++ b/drivers/rtc/rtc-pl031.c @@ -350,9 +350,6 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id) } } - if (!adev->irq[0]) - clear_bit(RTC_FEATURE_ALARM, ldata->rtc->features); - device_init_wakeup(&adev->dev, true); ldata->rtc = devm_rtc_allocate_device(&adev->dev); if (IS_ERR(ldata->rtc)) { @@ -360,6 +357,9 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id) goto out; } + if (!adev->irq[0]) + clear_bit(RTC_FEATURE_ALARM, ldata->rtc->features); + ldata->rtc->ops = ops; ldata->rtc->range_min = vendor->range_min; ldata->rtc->range_max = vendor->range_max; diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c index 29a1c65661e9..dc6d1476baa5 100644 --- a/drivers/rtc/rtc-pm8xxx.c +++ b/drivers/rtc/rtc-pm8xxx.c @@ -7,6 +7,7 @@ #include <linux/rtc.h> #include <linux/platform_device.h> #include <linux/pm.h> +#include <linux/pm_wakeirq.h> #include <linux/regmap.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -83,7 +84,7 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm) const struct pm8xxx_rtc_regs *regs = rtc_dd->regs; if (!rtc_dd->allow_set_time) - return -EACCES; + return -ENODEV; secs = rtc_tm_to_time64(tm); @@ -527,40 +528,28 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev) return rc; } - return devm_rtc_register_device(rtc_dd->rtc); -} - -#ifdef CONFIG_PM_SLEEP -static int pm8xxx_rtc_resume(struct device *dev) -{ - struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev); + rc = devm_rtc_register_device(rtc_dd->rtc); + if (rc) + return rc; - if (device_may_wakeup(dev)) - disable_irq_wake(rtc_dd->rtc_alarm_irq); + rc = dev_pm_set_wake_irq(&pdev->dev, rtc_dd->rtc_alarm_irq); + if (rc) + return rc; return 0; } -static int pm8xxx_rtc_suspend(struct device *dev) +static int pm8xxx_remove(struct platform_device *pdev) { - struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev); - - if (device_may_wakeup(dev)) - enable_irq_wake(rtc_dd->rtc_alarm_irq); - + dev_pm_clear_wake_irq(&pdev->dev); return 0; } -#endif - -static SIMPLE_DEV_PM_OPS(pm8xxx_rtc_pm_ops, - pm8xxx_rtc_suspend, - pm8xxx_rtc_resume); static struct platform_driver pm8xxx_rtc_driver = { .probe = pm8xxx_rtc_probe, + .remove = pm8xxx_remove, .driver = { .name = "rtc-pm8xxx", - .pm = &pm8xxx_rtc_pm_ops, .of_match_table = pm8xxx_id_table, }, }; diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c index b4a520056b1a..d4777b01ab22 100644 --- a/drivers/rtc/rtc-spear.c +++ b/drivers/rtc/rtc-spear.c @@ -204,8 +204,10 @@ static int spear_rtc_read_time(struct device *dev, struct rtc_time *tm) /* we don't report wday/yday/isdst ... */ rtc_wait_not_busy(config); - time = readl(config->ioaddr + TIME_REG); - date = readl(config->ioaddr + DATE_REG); + do { + time = readl(config->ioaddr + TIME_REG); + date = readl(config->ioaddr + DATE_REG); + } while (time == readl(config->ioaddr + TIME_REG)); tm->tm_sec = (time >> SECOND_SHIFT) & SECOND_MASK; tm->tm_min = (time >> MINUTE_SHIFT) & MIN_MASK; tm->tm_hour = (time >> HOUR_SHIFT) & HOUR_MASK; @@ -352,6 +354,10 @@ static int spear_rtc_probe(struct platform_device *pdev) if (!config) return -ENOMEM; + config->rtc = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(config->rtc)) + return PTR_ERR(config->rtc); + /* alarm irqs */ irq = platform_get_irq(pdev, 0); if (irq < 0) @@ -380,16 +386,13 @@ static int spear_rtc_probe(struct platform_device *pdev) spin_lock_init(&config->lock); platform_set_drvdata(pdev, config); - config->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, - &spear_rtc_ops, THIS_MODULE); - if (IS_ERR(config->rtc)) { - dev_err(&pdev->dev, "can't register RTC device, err %ld\n", - PTR_ERR(config->rtc)); - status = PTR_ERR(config->rtc); - goto err_disable_clock; - } + config->rtc->ops = &spear_rtc_ops; + config->rtc->range_min = RTC_TIMESTAMP_BEGIN_0000; + config->rtc->range_min = RTC_TIMESTAMP_END_9999; - config->rtc->uie_unsupported = 1; + status = devm_rtc_register_device(config->rtc); + if (status) + goto err_disable_clock; if (!device_can_wakeup(&pdev->dev)) device_init_wakeup(&pdev->dev, 1); diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index 711832c758ae..5b3e4da63406 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -13,6 +13,7 @@ #include <linux/clk.h> #include <linux/clk-provider.h> +#include <linux/clk/sunxi-ng.h> #include <linux/delay.h> #include <linux/err.h> #include <linux/fs.h> @@ -48,7 +49,8 @@ /* Alarm 0 (counter) */ #define SUN6I_ALRM_COUNTER 0x0020 -#define SUN6I_ALRM_CUR_VAL 0x0024 +/* This holds the remaining alarm seconds on older SoCs (current value) */ +#define SUN6I_ALRM_COUNTER_HMS 0x0024 #define SUN6I_ALRM_EN 0x0028 #define SUN6I_ALRM_EN_CNT_EN BIT(0) #define SUN6I_ALRM_IRQ_EN 0x002c @@ -110,6 +112,8 @@ #define SUN6I_YEAR_MIN 1970 #define SUN6I_YEAR_OFF (SUN6I_YEAR_MIN - 1900) +#define SECS_PER_DAY (24 * 3600ULL) + /* * There are other differences between models, including: * @@ -133,12 +137,15 @@ struct sun6i_rtc_clk_data { unsigned int has_auto_swt : 1; }; +#define RTC_LINEAR_DAY BIT(0) + struct sun6i_rtc_dev { struct rtc_device *rtc; const struct sun6i_rtc_clk_data *data; void __iomem *base; int irq; - unsigned long alarm; + time64_t alarm; + unsigned long flags; struct clk_hw hw; struct clk_hw *int_osc; @@ -363,23 +370,6 @@ CLK_OF_DECLARE_DRIVER(sun8i_h3_rtc_clk, "allwinner,sun8i-h3-rtc", CLK_OF_DECLARE_DRIVER(sun50i_h5_rtc_clk, "allwinner,sun50i-h5-rtc", sun8i_h3_rtc_clk_init); -static const struct sun6i_rtc_clk_data sun50i_h6_rtc_data = { - .rc_osc_rate = 16000000, - .fixed_prescaler = 32, - .has_prescaler = 1, - .has_out_clk = 1, - .export_iosc = 1, - .has_losc_en = 1, - .has_auto_swt = 1, -}; - -static void __init sun50i_h6_rtc_clk_init(struct device_node *node) -{ - sun6i_rtc_clk_init(node, &sun50i_h6_rtc_data); -} -CLK_OF_DECLARE_DRIVER(sun50i_h6_rtc_clk, "allwinner,sun50i-h6-rtc", - sun50i_h6_rtc_clk_init); - /* * The R40 user manual is self-conflicting on whether the prescaler is * fixed or configurable. The clock diagram shows it as fixed, but there @@ -467,22 +457,30 @@ static int sun6i_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) } while ((date != readl(chip->base + SUN6I_RTC_YMD)) || (time != readl(chip->base + SUN6I_RTC_HMS))); + if (chip->flags & RTC_LINEAR_DAY) { + /* + * Newer chips store a linear day number, the manual + * does not mandate any epoch base. The BSP driver uses + * the UNIX epoch, let's just copy that, as it's the + * easiest anyway. + */ + rtc_time64_to_tm((date & 0xffff) * SECS_PER_DAY, rtc_tm); + } else { + rtc_tm->tm_mday = SUN6I_DATE_GET_DAY_VALUE(date); + rtc_tm->tm_mon = SUN6I_DATE_GET_MON_VALUE(date) - 1; + rtc_tm->tm_year = SUN6I_DATE_GET_YEAR_VALUE(date); + + /* + * switch from (data_year->min)-relative offset to + * a (1900)-relative one + */ + rtc_tm->tm_year += SUN6I_YEAR_OFF; + } + rtc_tm->tm_sec = SUN6I_TIME_GET_SEC_VALUE(time); rtc_tm->tm_min = SUN6I_TIME_GET_MIN_VALUE(time); rtc_tm->tm_hour = SUN6I_TIME_GET_HOUR_VALUE(time); - rtc_tm->tm_mday = SUN6I_DATE_GET_DAY_VALUE(date); - rtc_tm->tm_mon = SUN6I_DATE_GET_MON_VALUE(date); - rtc_tm->tm_year = SUN6I_DATE_GET_YEAR_VALUE(date); - - rtc_tm->tm_mon -= 1; - - /* - * switch from (data_year->min)-relative offset to - * a (1900)-relative one - */ - rtc_tm->tm_year += SUN6I_YEAR_OFF; - return 0; } @@ -510,36 +508,54 @@ static int sun6i_rtc_setalarm(struct device *dev, struct rtc_wkalrm *wkalrm) struct sun6i_rtc_dev *chip = dev_get_drvdata(dev); struct rtc_time *alrm_tm = &wkalrm->time; struct rtc_time tm_now; - unsigned long time_now = 0; - unsigned long time_set = 0; - unsigned long time_gap = 0; - int ret = 0; - - ret = sun6i_rtc_gettime(dev, &tm_now); - if (ret < 0) { - dev_err(dev, "Error in getting time\n"); - return -EINVAL; - } + time64_t time_set; + u32 counter_val, counter_val_hms; + int ret; time_set = rtc_tm_to_time64(alrm_tm); - time_now = rtc_tm_to_time64(&tm_now); - if (time_set <= time_now) { - dev_err(dev, "Date to set in the past\n"); - return -EINVAL; - } - - time_gap = time_set - time_now; - if (time_gap > U32_MAX) { - dev_err(dev, "Date too far in the future\n"); - return -EINVAL; + if (chip->flags & RTC_LINEAR_DAY) { + /* + * The alarm registers hold the actual alarm time, encoded + * in the same way (linear day + HMS) as the current time. + */ + counter_val_hms = SUN6I_TIME_SET_SEC_VALUE(alrm_tm->tm_sec) | + SUN6I_TIME_SET_MIN_VALUE(alrm_tm->tm_min) | + SUN6I_TIME_SET_HOUR_VALUE(alrm_tm->tm_hour); + /* The division will cut off the H:M:S part of alrm_tm. */ + counter_val = div_u64(rtc_tm_to_time64(alrm_tm), SECS_PER_DAY); + } else { + /* The alarm register holds the number of seconds left. */ + time64_t time_now; + + ret = sun6i_rtc_gettime(dev, &tm_now); + if (ret < 0) { + dev_err(dev, "Error in getting time\n"); + return -EINVAL; + } + + time_now = rtc_tm_to_time64(&tm_now); + if (time_set <= time_now) { + dev_err(dev, "Date to set in the past\n"); + return -EINVAL; + } + if ((time_set - time_now) > U32_MAX) { + dev_err(dev, "Date too far in the future\n"); + return -EINVAL; + } + + counter_val = time_set - time_now; } sun6i_rtc_setaie(0, chip); writel(0, chip->base + SUN6I_ALRM_COUNTER); + if (chip->flags & RTC_LINEAR_DAY) + writel(0, chip->base + SUN6I_ALRM_COUNTER_HMS); usleep_range(100, 300); - writel(time_gap, chip->base + SUN6I_ALRM_COUNTER); + writel(counter_val, chip->base + SUN6I_ALRM_COUNTER); + if (chip->flags & RTC_LINEAR_DAY) + writel(counter_val_hms, chip->base + SUN6I_ALRM_COUNTER_HMS); chip->alarm = time_set; sun6i_rtc_setaie(wkalrm->enabled, chip); @@ -571,20 +587,25 @@ static int sun6i_rtc_settime(struct device *dev, struct rtc_time *rtc_tm) u32 date = 0; u32 time = 0; - rtc_tm->tm_year -= SUN6I_YEAR_OFF; - rtc_tm->tm_mon += 1; - - date = SUN6I_DATE_SET_DAY_VALUE(rtc_tm->tm_mday) | - SUN6I_DATE_SET_MON_VALUE(rtc_tm->tm_mon) | - SUN6I_DATE_SET_YEAR_VALUE(rtc_tm->tm_year); - - if (is_leap_year(rtc_tm->tm_year + SUN6I_YEAR_MIN)) - date |= SUN6I_LEAP_SET_VALUE(1); - time = SUN6I_TIME_SET_SEC_VALUE(rtc_tm->tm_sec) | SUN6I_TIME_SET_MIN_VALUE(rtc_tm->tm_min) | SUN6I_TIME_SET_HOUR_VALUE(rtc_tm->tm_hour); + if (chip->flags & RTC_LINEAR_DAY) { + /* The division will cut off the H:M:S part of rtc_tm. */ + date = div_u64(rtc_tm_to_time64(rtc_tm), SECS_PER_DAY); + } else { + rtc_tm->tm_year -= SUN6I_YEAR_OFF; + rtc_tm->tm_mon += 1; + + date = SUN6I_DATE_SET_DAY_VALUE(rtc_tm->tm_mday) | + SUN6I_DATE_SET_MON_VALUE(rtc_tm->tm_mon) | + SUN6I_DATE_SET_YEAR_VALUE(rtc_tm->tm_year); + + if (is_leap_year(rtc_tm->tm_year + SUN6I_YEAR_MIN)) + date |= SUN6I_LEAP_SET_VALUE(1); + } + /* Check whether registers are writable */ if (sun6i_rtc_wait(chip, SUN6I_LOSC_CTRL, SUN6I_LOSC_CTRL_ACC_MASK, 50)) { @@ -668,11 +689,35 @@ static int sun6i_rtc_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(sun6i_rtc_pm_ops, sun6i_rtc_suspend, sun6i_rtc_resume); +static void sun6i_rtc_bus_clk_cleanup(void *data) +{ + struct clk *bus_clk = data; + + clk_disable_unprepare(bus_clk); +} + static int sun6i_rtc_probe(struct platform_device *pdev) { struct sun6i_rtc_dev *chip = sun6i_rtc; + struct device *dev = &pdev->dev; + struct clk *bus_clk; int ret; + bus_clk = devm_clk_get_optional(dev, "bus"); + if (IS_ERR(bus_clk)) + return PTR_ERR(bus_clk); + + if (bus_clk) { + ret = clk_prepare_enable(bus_clk); + if (ret) + return ret; + + ret = devm_add_action_or_reset(dev, sun6i_rtc_bus_clk_cleanup, + bus_clk); + if (ret) + return ret; + } + if (!chip) { chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL); if (!chip) @@ -683,10 +728,18 @@ static int sun6i_rtc_probe(struct platform_device *pdev) chip->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(chip->base)) return PTR_ERR(chip->base); + + if (IS_REACHABLE(CONFIG_SUN6I_RTC_CCU)) { + ret = sun6i_rtc_ccu_probe(dev, chip->base); + if (ret) + return ret; + } } platform_set_drvdata(pdev, chip); + chip->flags = (unsigned long)of_device_get_match_data(&pdev->dev); + chip->irq = platform_get_irq(pdev, 0); if (chip->irq < 0) return chip->irq; @@ -733,7 +786,10 @@ static int sun6i_rtc_probe(struct platform_device *pdev) return PTR_ERR(chip->rtc); chip->rtc->ops = &sun6i_rtc_ops; - chip->rtc->range_max = 2019686399LL; /* 2033-12-31 23:59:59 */ + if (chip->flags & RTC_LINEAR_DAY) + chip->rtc->range_max = (65536 * SECS_PER_DAY) - 1; + else + chip->rtc->range_max = 2019686399LL; /* 2033-12-31 23:59:59 */ ret = devm_rtc_register_device(chip->rtc); if (ret) @@ -758,6 +814,8 @@ static const struct of_device_id sun6i_rtc_dt_ids[] = { { .compatible = "allwinner,sun8i-v3-rtc" }, { .compatible = "allwinner,sun50i-h5-rtc" }, { .compatible = "allwinner,sun50i-h6-rtc" }, + { .compatible = "allwinner,sun50i-h616-rtc", + .data = (void *)RTC_LINEAR_DAY }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, sun6i_rtc_dt_ids); diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c index 2018614f258f..6eaa9321c074 100644 --- a/drivers/rtc/rtc-wm8350.c +++ b/drivers/rtc/rtc-wm8350.c @@ -432,14 +432,21 @@ static int wm8350_rtc_probe(struct platform_device *pdev) return ret; } - wm8350_register_irq(wm8350, WM8350_IRQ_RTC_SEC, + ret = wm8350_register_irq(wm8350, WM8350_IRQ_RTC_SEC, wm8350_rtc_update_handler, 0, "RTC Seconds", wm8350); + if (ret) + return ret; + wm8350_mask_irq(wm8350, WM8350_IRQ_RTC_SEC); - wm8350_register_irq(wm8350, WM8350_IRQ_RTC_ALM, + ret = wm8350_register_irq(wm8350, WM8350_IRQ_RTC_ALM, wm8350_rtc_alarm_handler, 0, "RTC Alarm", wm8350); + if (ret) { + wm8350_free_irq(wm8350, WM8350_IRQ_RTC_SEC, wm8350); + return ret; + } return 0; } diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c index cf68a9b1c9eb..d3d0054e21fd 100644 --- a/drivers/rtc/rtc-xgene.c +++ b/drivers/rtc/rtc-xgene.c @@ -180,8 +180,6 @@ static int xgene_rtc_probe(struct platform_device *pdev) return ret; } - /* HW does not support update faster than 1 seconds */ - pdata->rtc->uie_unsupported = 1; pdata->rtc->ops = &xgene_rtc_ops; pdata->rtc->range_max = U32_MAX; diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index f0763e36b861..cb2491761958 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -745,9 +745,7 @@ sclp_sync_wait(void) /* Loop until driver state indicates finished request */ while (sclp_running_state != sclp_running_state_idle) { /* Check for expired request timer */ - if (timer_pending(&sclp_request_timer) && - get_tod_clock_fast() > timeout && - del_timer(&sclp_request_timer)) + if (get_tod_clock_fast() > timeout && del_timer(&sclp_request_timer)) sclp_request_timer.function(&sclp_request_timer); cpu_relax(); } diff --git a/drivers/s390/char/sclp_con.c b/drivers/s390/char/sclp_con.c index de028868c6f4..fe5ee2646fcf 100644 --- a/drivers/s390/char/sclp_con.c +++ b/drivers/s390/char/sclp_con.c @@ -109,8 +109,7 @@ static void sclp_console_sync_queue(void) unsigned long flags; spin_lock_irqsave(&sclp_con_lock, flags); - if (timer_pending(&sclp_con_timer)) - del_timer(&sclp_con_timer); + del_timer(&sclp_con_timer); while (sclp_con_queue_running) { spin_unlock_irqrestore(&sclp_con_lock, flags); sclp_sync_wait(); diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c index 7bc4e4a10937..3b4e7e5d9b71 100644 --- a/drivers/s390/char/sclp_vt220.c +++ b/drivers/s390/char/sclp_vt220.c @@ -231,8 +231,7 @@ sclp_vt220_emit_current(void) list_add_tail(&sclp_vt220_current_request->list, &sclp_vt220_outqueue); sclp_vt220_current_request = NULL; - if (timer_pending(&sclp_vt220_timer)) - del_timer(&sclp_vt220_timer); + del_timer(&sclp_vt220_timer); } sclp_vt220_flush_later = 0; } @@ -776,8 +775,7 @@ static void __sclp_vt220_flush_buffer(void) sclp_vt220_emit_current(); spin_lock_irqsave(&sclp_vt220_lock, flags); - if (timer_pending(&sclp_vt220_timer)) - del_timer(&sclp_vt220_timer); + del_timer(&sclp_vt220_timer); while (sclp_vt220_queue_running) { spin_unlock_irqrestore(&sclp_vt220_lock, flags); sclp_sync_wait(); diff --git a/drivers/s390/char/tape_34xx.c b/drivers/s390/char/tape_34xx.c index 7ada994d4592..38cc1565d6ae 100644 --- a/drivers/s390/char/tape_34xx.c +++ b/drivers/s390/char/tape_34xx.c @@ -354,10 +354,10 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request, if (( sense[0] == SENSE_DATA_CHECK || sense[0] == SENSE_EQUIPMENT_CHECK || - sense[0] == SENSE_EQUIPMENT_CHECK + SENSE_DEFERRED_UNIT_CHECK + sense[0] == (SENSE_EQUIPMENT_CHECK | SENSE_DEFERRED_UNIT_CHECK) ) && ( sense[1] == SENSE_DRIVE_ONLINE || - sense[1] == SENSE_BEGINNING_OF_TAPE + SENSE_WRITE_MODE + sense[1] == (SENSE_BEGINNING_OF_TAPE | SENSE_WRITE_MODE) )) { switch (request->op) { /* diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c index 05e136cfb8be..6d63b968309a 100644 --- a/drivers/s390/cio/device_fsm.c +++ b/drivers/s390/cio/device_fsm.c @@ -113,16 +113,10 @@ ccw_device_timeout(struct timer_list *t) void ccw_device_set_timeout(struct ccw_device *cdev, int expires) { - if (expires == 0) { + if (expires == 0) del_timer(&cdev->private->timer); - return; - } - if (timer_pending(&cdev->private->timer)) { - if (mod_timer(&cdev->private->timer, jiffies + expires)) - return; - } - cdev->private->timer.expires = jiffies + expires; - add_timer(&cdev->private->timer); + else + mod_timer(&cdev->private->timer, jiffies + expires); } int diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c index 8b463681a149..ab6a7495180a 100644 --- a/drivers/s390/cio/eadm_sch.c +++ b/drivers/s390/cio/eadm_sch.c @@ -112,16 +112,10 @@ static void eadm_subchannel_set_timeout(struct subchannel *sch, int expires) { struct eadm_private *private = get_eadm_private(sch); - if (expires == 0) { + if (expires == 0) del_timer(&private->timer); - return; - } - if (timer_pending(&private->timer)) { - if (mod_timer(&private->timer, jiffies + expires)) - return; - } - private->timer.expires = jiffies + expires; - add_timer(&private->timer); + else + mod_timer(&private->timer, jiffies + expires); } static void eadm_subchannel_irq(struct subchannel *sch) diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 8fd5a17bdf99..6a65885f5f43 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -315,6 +315,7 @@ struct ap_perms { unsigned long ioctlm[BITS_TO_LONGS(AP_IOCTLS)]; unsigned long apm[BITS_TO_LONGS(AP_DEVICES)]; unsigned long aqm[BITS_TO_LONGS(AP_DOMAINS)]; + unsigned long adm[BITS_TO_LONGS(AP_DOMAINS)]; }; extern struct ap_perms ap_perms; extern struct mutex ap_perms_mutex; diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index cf23ce1b1146..7f69ca695fc2 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -155,7 +155,7 @@ static int pkey_skey2pkey(const u8 *key, struct pkey_protkey *pkey) /* * The cca_xxx2protkey call may fail when a card has been * addressed where the master key was changed after last fetch - * of the mkvp into the cache. Try 3 times: First witout verify + * of the mkvp into the cache. Try 3 times: First without verify * then with verify and last round with verify and old master * key verification pattern match not ignored. */ diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 7dc26365e29a..6e08d04b605d 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1189,13 +1189,6 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = { * @matrix_mdev: a mediated matrix device * @kvm: reference to KVM instance * - * Note: The matrix_dev->lock must be taken prior to calling - * this function; however, the lock will be temporarily released while the - * guest's AP configuration is set to avoid a potential lockdep splat. - * The kvm->lock is taken to set the guest's AP configuration which, under - * certain circumstances, will result in a circular lock dependency if this is - * done under the @matrix_mdev->lock. - * * Return: 0 if no other mediated matrix device has a reference to @kvm; * otherwise, returns an -EPERM. */ @@ -1269,18 +1262,11 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb, * by @matrix_mdev. * * @matrix_mdev: a matrix mediated device - * @kvm: the pointer to the kvm structure being unset. - * - * Note: The matrix_dev->lock must be taken prior to calling - * this function; however, the lock will be temporarily released while the - * guest's AP configuration is cleared to avoid a potential lockdep splat. - * The kvm->lock is taken to clear the guest's AP configuration which, under - * certain circumstances, will result in a circular lock dependency if this is - * done under the @matrix_mdev->lock. */ -static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev, - struct kvm *kvm) +static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) { + struct kvm *kvm = matrix_mdev->kvm; + if (kvm && kvm->arch.crypto.crycbd) { down_write(&kvm->arch.crypto.pqap_hook_rwsem); kvm->arch.crypto.pqap_hook = NULL; @@ -1311,7 +1297,7 @@ static int vfio_ap_mdev_group_notifier(struct notifier_block *nb, matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); if (!data) - vfio_ap_mdev_unset_kvm(matrix_mdev, matrix_mdev->kvm); + vfio_ap_mdev_unset_kvm(matrix_mdev); else if (vfio_ap_mdev_set_kvm(matrix_mdev, data)) notify_rc = NOTIFY_DONE; @@ -1448,7 +1434,7 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev) &matrix_mdev->iommu_notifier); vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY, &matrix_mdev->group_notifier); - vfio_ap_mdev_unset_kvm(matrix_mdev, matrix_mdev->kvm); + vfio_ap_mdev_unset_kvm(matrix_mdev); } static int vfio_ap_mdev_get_device_info(unsigned long arg) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 80e2a306709a..aa6dc3c0c353 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -285,10 +285,53 @@ static ssize_t aqmask_store(struct device *dev, static DEVICE_ATTR_RW(aqmask); +static ssize_t admask_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int i, rc; + struct zcdn_device *zcdndev = to_zcdn_dev(dev); + + if (mutex_lock_interruptible(&ap_perms_mutex)) + return -ERESTARTSYS; + + buf[0] = '0'; + buf[1] = 'x'; + for (i = 0; i < sizeof(zcdndev->perms.adm) / sizeof(long); i++) + snprintf(buf + 2 + 2 * i * sizeof(long), + PAGE_SIZE - 2 - 2 * i * sizeof(long), + "%016lx", zcdndev->perms.adm[i]); + buf[2 + 2 * i * sizeof(long)] = '\n'; + buf[2 + 2 * i * sizeof(long) + 1] = '\0'; + rc = 2 + 2 * i * sizeof(long) + 1; + + mutex_unlock(&ap_perms_mutex); + + return rc; +} + +static ssize_t admask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int rc; + struct zcdn_device *zcdndev = to_zcdn_dev(dev); + + rc = ap_parse_mask_str(buf, zcdndev->perms.adm, + AP_DOMAINS, &ap_perms_mutex); + if (rc) + return rc; + + return count; +} + +static DEVICE_ATTR_RW(admask); + static struct attribute *zcdn_dev_attrs[] = { &dev_attr_ioctlmask.attr, &dev_attr_apmask.attr, &dev_attr_aqmask.attr, + &dev_attr_admask.attr, NULL }; @@ -880,11 +923,22 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (rc) goto out; + tdom = *domain; + if (perms != &ap_perms && tdom < AP_DOMAINS) { + if (ap_msg.flags & AP_MSG_FLAG_ADMIN) { + if (!test_bit_inv(tdom, perms->adm)) { + rc = -ENODEV; + goto out; + } + } else if ((ap_msg.flags & AP_MSG_FLAG_USAGE) == 0) { + rc = -EOPNOTSUPP; + goto out; + } + } /* * If a valid target domain is set and this domain is NOT a usage * domain but a control only domain, autoselect target domain. */ - tdom = *domain; if (tdom < AP_DOMAINS && !ap_test_config_usage_domain(tdom) && ap_test_config_ctrl_domain(tdom)) @@ -1062,6 +1116,18 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (rc) goto out_free; + if (perms != &ap_perms && domain < AUTOSEL_DOM) { + if (ap_msg.flags & AP_MSG_FLAG_ADMIN) { + if (!test_bit_inv(domain, perms->adm)) { + rc = -ENODEV; + goto out_free; + } + } else if ((ap_msg.flags & AP_MSG_FLAG_USAGE) == 0) { + rc = -EOPNOTSUPP; + goto out_free; + } + } + pref_zc = NULL; pref_zq = NULL; spin_lock(&zcrypt_list_lock); diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c index 3e259befd30a..fcbd537530e8 100644 --- a/drivers/s390/crypto/zcrypt_card.c +++ b/drivers/s390/crypto/zcrypt_card.c @@ -90,7 +90,7 @@ static ssize_t online_store(struct device *dev, list_for_each_entry(zq, &zc->zqueues, list) maxzqs++; if (maxzqs > 0) - zq_uelist = kcalloc(maxzqs + 1, sizeof(zq), GFP_ATOMIC); + zq_uelist = kcalloc(maxzqs + 1, sizeof(*zq_uelist), GFP_ATOMIC); list_for_each_entry(zq, &zc->zqueues, list) if (zcrypt_queue_force_online(zq, online)) if (zq_uelist) { diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 9ce5a71da69b..98d33f932b0b 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -1109,7 +1109,7 @@ static int ep11_wrapkey(u16 card, u16 domain, if (kb->head.type == TOKTYPE_NON_CCA && kb->head.version == TOKVER_EP11_AES) { has_header = true; - keysize = kb->head.len < keysize ? kb->head.len : keysize; + keysize = min_t(size_t, kb->head.len, keysize); } /* request cprb and payload */ diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index 5f554a3a0f62..caeebfb67149 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -317,14 +317,18 @@ enum { }; struct aha152x_cmd_priv { - struct scsi_pointer scsi_pointer; + char *ptr; + int this_residual; + struct scatterlist *buffer; + int status; + int message; + int sent_command; + int phase; }; -static struct scsi_pointer *aha152x_scsi_pointer(struct scsi_cmnd *cmd) +static struct aha152x_cmd_priv *aha152x_priv(struct scsi_cmnd *cmd) { - struct aha152x_cmd_priv *acmd = scsi_cmd_priv(cmd); - - return &acmd->scsi_pointer; + return scsi_cmd_priv(cmd); } MODULE_AUTHOR("Jürgen Fischer"); @@ -890,17 +894,16 @@ void aha152x_release(struct Scsi_Host *shpnt) static int setup_expected_interrupts(struct Scsi_Host *shpnt) { if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; - if (scsi_pointer->phase & selecting) { + if (acp->phase & selecting) { SETPORT(SSTAT1, SELTO); SETPORT(SIMODE0, ENSELDO | (DISCONNECTED_SC ? ENSELDI : 0)); SETPORT(SIMODE1, ENSELTIMO); } else { - SETPORT(SIMODE0, (scsi_pointer->phase & spiordy) ? ENSPIORDY : 0); + SETPORT(SIMODE0, (acp->phase & spiordy) ? ENSPIORDY : 0); SETPORT(SIMODE1, ENPHASEMIS | ENSCSIRST | ENSCSIPERR | ENBUSFREE); } } else if(STATE==seldi) { @@ -924,17 +927,16 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt) static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, struct completion *complete, int phase) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(SCpnt); + struct aha152x_cmd_priv *acp = aha152x_priv(SCpnt); struct Scsi_Host *shpnt = SCpnt->device->host; unsigned long flags; - scsi_pointer->phase = not_issued | phase; - scsi_pointer->Status = 0x1; /* Ilegal status by SCSI standard */ - scsi_pointer->Message = 0; - scsi_pointer->have_data_in = 0; - scsi_pointer->sent_command = 0; + acp->phase = not_issued | phase; + acp->status = 0x1; /* Illegal status by SCSI standard */ + acp->message = 0; + acp->sent_command = 0; - if (scsi_pointer->phase & (resetting | check_condition)) { + if (acp->phase & (resetting | check_condition)) { if (!SCpnt->host_scribble || SCSEM(SCpnt) || SCNEXT(SCpnt)) { scmd_printk(KERN_ERR, SCpnt, "cannot reuse command\n"); return FAILED; @@ -957,15 +959,15 @@ static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, SCp.phase : current state of the command */ if ((phase & resetting) || !scsi_sglist(SCpnt)) { - scsi_pointer->ptr = NULL; - scsi_pointer->this_residual = 0; + acp->ptr = NULL; + acp->this_residual = 0; scsi_set_resid(SCpnt, 0); - scsi_pointer->buffer = NULL; + acp->buffer = NULL; } else { scsi_set_resid(SCpnt, scsi_bufflen(SCpnt)); - scsi_pointer->buffer = scsi_sglist(SCpnt); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = scsi_sglist(SCpnt); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } DO_LOCK(flags); @@ -1015,7 +1017,7 @@ static void reset_done(struct scsi_cmnd *SCpnt) static void aha152x_scsi_done(struct scsi_cmnd *SCpnt) { - if (aha152x_scsi_pointer(SCpnt)->phase & resetting) + if (aha152x_priv(SCpnt)->phase & resetting) reset_done(SCpnt); else scsi_done(SCpnt); @@ -1101,7 +1103,7 @@ static int aha152x_device_reset(struct scsi_cmnd * SCpnt) DO_LOCK(flags); - if (aha152x_scsi_pointer(SCpnt)->phase & resetted) { + if (aha152x_priv(SCpnt)->phase & resetted) { HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); @@ -1395,31 +1397,30 @@ static void busfree_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRBUSFREE); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase &= ~syncneg; + acp->phase &= ~syncneg; - if (scsi_pointer->phase & completed) { + if (acp->phase & completed) { /* target sent COMMAND COMPLETE */ - done(shpnt, scsi_pointer->Status, DID_OK); + done(shpnt, acp->status, DID_OK); - } else if (scsi_pointer->phase & aborted) { - done(shpnt, scsi_pointer->Status, DID_ABORT); + } else if (acp->phase & aborted) { + done(shpnt, acp->status, DID_ABORT); - } else if (scsi_pointer->phase & resetted) { - done(shpnt, scsi_pointer->Status, DID_RESET); + } else if (acp->phase & resetted) { + done(shpnt, acp->status, DID_RESET); - } else if (scsi_pointer->phase & disconnected) { + } else if (acp->phase & disconnected) { /* target sent DISCONNECT */ #if defined(AHA152X_STAT) HOSTDATA(shpnt)->disconnections++; #endif append_SC(&DISCONNECTED_SC, CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; CURRENT_SC = NULL; } else { @@ -1438,24 +1439,23 @@ static void busfree_run(struct Scsi_Host *shpnt) action++; #endif - if (aha152x_scsi_pointer(DONE_SC)->phase & check_condition) { + if (aha152x_priv(DONE_SC)->phase & check_condition) { struct scsi_cmnd *cmd = HOSTDATA(shpnt)->done_SC; struct aha152x_scdata *sc = SCDATA(cmd); scsi_eh_restore_cmnd(cmd, &sc->ses); - aha152x_scsi_pointer(cmd)->Status = SAM_STAT_CHECK_CONDITION; + aha152x_priv(cmd)->status = SAM_STAT_CHECK_CONDITION; HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - } else if (aha152x_scsi_pointer(DONE_SC)->Status == - SAM_STAT_CHECK_CONDITION) { + } else if (aha152x_priv(DONE_SC)->status == SAM_STAT_CHECK_CONDITION) { #if defined(AHA152X_STAT) HOSTDATA(shpnt)->busfree_with_check_condition++; #endif - if(!(aha152x_scsi_pointer(DONE_SC)->phase & not_issued)) { + if (!(aha152x_priv(DONE_SC)->phase & not_issued)) { struct aha152x_scdata *sc; struct scsi_cmnd *ptr = DONE_SC; DONE_SC=NULL; @@ -1480,7 +1480,7 @@ static void busfree_run(struct Scsi_Host *shpnt) if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - if (!(aha152x_scsi_pointer(ptr)->phase & resetting)) { + if (!(aha152x_priv(ptr)->phase & resetting)) { kfree(ptr->host_scribble); ptr->host_scribble=NULL; } @@ -1503,13 +1503,12 @@ static void busfree_run(struct Scsi_Host *shpnt) DO_UNLOCK(flags); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase |= selecting; + acp->phase |= selecting; /* clear selection timeout */ SETPORT(SSTAT1, SELTO); @@ -1537,13 +1536,13 @@ static void busfree_run(struct Scsi_Host *shpnt) */ static void seldo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); SETPORT(SCSISIG, 0); SETPORT(SSTAT1, CLRBUSFREE); SETPORT(SSTAT1, CLRPHASECHG); - scsi_pointer->phase &= ~(selecting | not_issued); + acp->phase &= ~(selecting | not_issued); SETPORT(SCSISEQ, 0); @@ -1558,12 +1557,12 @@ static void seldo_run(struct Scsi_Host *shpnt) ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); - if (scsi_pointer->phase & aborting) { + if (acp->phase & aborting) { ADDMSGO(ABORT); - } else if (scsi_pointer->phase & resetting) { + } else if (acp->phase & resetting) { ADDMSGO(BUS_DEVICE_RESET); } else if (SYNCNEG==0 && SYNCHRONOUS) { - scsi_pointer->phase |= syncneg; + acp->phase |= syncneg; MSGOLEN += spi_populate_sync_msg(&MSGO(MSGOLEN), 50, 8); SYNCNEG=1; /* negotiation in progress */ } @@ -1578,7 +1577,7 @@ static void seldo_run(struct Scsi_Host *shpnt) */ static void selto_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp; SETPORT(SCSISEQ, 0); SETPORT(SSTAT1, CLRSELTIMO); @@ -1586,9 +1585,10 @@ static void selto_run(struct Scsi_Host *shpnt) if (!CURRENT_SC) return; - scsi_pointer->phase &= ~selecting; + acp = aha152x_priv(CURRENT_SC); + acp->phase &= ~selecting; - if (scsi_pointer->phase & aborted) + if (acp->phase & aborted) done(shpnt, SAM_STAT_GOOD, DID_ABORT); else if (TESTLO(SSTAT0, SELINGO)) done(shpnt, SAM_STAT_GOOD, DID_BUS_BUSY); @@ -1616,10 +1616,9 @@ static void seldi_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRPHASECHG); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - if (!(scsi_pointer->phase & not_issued)) + if (!(acp->phase & not_issued)) scmd_printk(KERN_ERR, CURRENT_SC, "command should not have been issued yet\n"); @@ -1676,7 +1675,7 @@ static void seldi_run(struct Scsi_Host *shpnt) static void msgi_run(struct Scsi_Host *shpnt) { for(;;) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; int sstat1 = GETPORT(SSTAT1); if(sstat1 & (PHASECHG|PHASEMIS|BUSFREE) || !(sstat1 & REQINIT)) @@ -1714,9 +1713,9 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); - scsi_pointer->phase &= ~disconnected; + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); + acp->phase &= ~disconnected; MSGILEN=0; @@ -1724,8 +1723,8 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); switch (MSGI(0)) { case DISCONNECT: @@ -1733,11 +1732,11 @@ static void msgi_run(struct Scsi_Host *shpnt) scmd_printk(KERN_WARNING, CURRENT_SC, "target was not allowed to disconnect\n"); - scsi_pointer->phase |= disconnected; + acp->phase |= disconnected; break; case COMMAND_COMPLETE: - scsi_pointer->phase |= completed; + acp->phase |= completed; break; case MESSAGE_REJECT: @@ -1867,11 +1866,9 @@ static void msgi_end(struct Scsi_Host *shpnt) */ static void msgo_init(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if(MSGOLEN==0) { - if ((scsi_pointer->phase & syncneg) && SYNCNEG==2 && - SYNCRATE==0) { + if ((aha152x_priv(CURRENT_SC)->phase & syncneg) && + SYNCNEG == 2 && SYNCRATE == 0) { ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); } else { scmd_printk(KERN_INFO, CURRENT_SC, @@ -1888,7 +1885,7 @@ static void msgo_init(struct Scsi_Host *shpnt) */ static void msgo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); while(MSGO_I<MSGOLEN) { if (TESTLO(SSTAT0, SPIORDY)) @@ -1901,13 +1898,13 @@ static void msgo_run(struct Scsi_Host *shpnt) if (MSGO(MSGO_I) & IDENTIFY_BASE) - scsi_pointer->phase |= identified; + acp->phase |= identified; if (MSGO(MSGO_I)==ABORT) - scsi_pointer->phase |= aborted; + acp->phase |= aborted; if (MSGO(MSGO_I)==BUS_DEVICE_RESET) - scsi_pointer->phase |= resetted; + acp->phase |= resetted; SETPORT(SCSIDAT, MSGO(MSGO_I++)); } @@ -1936,7 +1933,7 @@ static void msgo_end(struct Scsi_Host *shpnt) */ static void cmd_init(struct Scsi_Host *shpnt) { - if (aha152x_scsi_pointer(CURRENT_SC)->sent_command) { + if (aha152x_priv(CURRENT_SC)->sent_command) { scmd_printk(KERN_ERR, CURRENT_SC, "command already sent\n"); done(shpnt, SAM_STAT_GOOD, DID_ERROR); @@ -1967,7 +1964,7 @@ static void cmd_end(struct Scsi_Host *shpnt) "command sent incompletely (%d/%d)\n", CMD_I, CURRENT_SC->cmd_len); else - aha152x_scsi_pointer(CURRENT_SC)->sent_command++; + aha152x_priv(CURRENT_SC)->sent_command++; } /* @@ -1979,7 +1976,7 @@ static void status_run(struct Scsi_Host *shpnt) if (TESTLO(SSTAT0, SPIORDY)) return; - aha152x_scsi_pointer(CURRENT_SC)->Status = GETPORT(SCSIDAT); + aha152x_priv(CURRENT_SC)->status = GETPORT(SCSIDAT); } @@ -2003,7 +2000,7 @@ static void datai_init(struct Scsi_Host *shpnt) static void datai_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; unsigned long the_time; int fifodata, data_count; @@ -2041,36 +2038,35 @@ static void datai_run(struct Scsi_Host *shpnt) fifodata = GETPORT(FIFOSTAT); } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if (scsi_pointer->this_residual > 0) { - while (fifodata > 0 && scsi_pointer->this_residual > 0) { - data_count = fifodata > scsi_pointer->this_residual ? - scsi_pointer->this_residual : - fifodata; + acp = aha152x_priv(CURRENT_SC); + if (acp->this_residual > 0) { + while (fifodata > 0 && acp->this_residual > 0) { + data_count = fifodata > acp->this_residual ? + acp->this_residual : fifodata; fifodata -= data_count; if (data_count & 1) { SETPORT(DMACNTRL0, ENDMA|_8BIT); - *scsi_pointer->ptr++ = GETPORT(DATAPORT); - scsi_pointer->this_residual--; + *acp->ptr++ = GETPORT(DATAPORT); + acp->this_residual--; DATA_LEN++; SETPORT(DMACNTRL0, ENDMA); } if (data_count > 1) { data_count >>= 1; - insw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + insw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; DATA_LEN += 2 * data_count; } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && + !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } } } else if (fifodata > 0) { @@ -2138,15 +2134,15 @@ static void datao_init(struct Scsi_Host *shpnt) static void datao_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); unsigned long the_time; int data_count; /* until phase changes or all data sent */ - while (TESTLO(DMASTAT, INTSTAT) && scsi_pointer->this_residual > 0) { + while (TESTLO(DMASTAT, INTSTAT) && acp->this_residual > 0) { data_count = 128; - if (data_count > scsi_pointer->this_residual) - data_count = scsi_pointer->this_residual; + if (data_count > acp->this_residual) + data_count = acp->this_residual; if(TESTLO(DMASTAT, DFIFOEMP)) { scmd_printk(KERN_ERR, CURRENT_SC, @@ -2157,26 +2153,25 @@ static void datao_run(struct Scsi_Host *shpnt) if(data_count & 1) { SETPORT(DMACNTRL0,WRITE_READ|ENDMA|_8BIT); - SETPORT(DATAPORT, *scsi_pointer->ptr++); - scsi_pointer->this_residual--; + SETPORT(DATAPORT, *acp->ptr++); + acp->this_residual--; CMD_INC_RESID(CURRENT_SC, -1); SETPORT(DMACNTRL0,WRITE_READ|ENDMA); } if(data_count > 1) { data_count >>= 1; - outsw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + outsw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; CMD_INC_RESID(CURRENT_SC, -2 * data_count); } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } the_time=jiffies + 100*HZ; @@ -2192,7 +2187,7 @@ static void datao_run(struct Scsi_Host *shpnt) static void datao_end(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); if(TESTLO(DMASTAT, DFIFOEMP)) { u32 datao_cnt = GETSTCNT(); @@ -2211,10 +2206,9 @@ static void datao_end(struct Scsi_Host *shpnt) sg = sg_next(sg); } - scsi_pointer->buffer = sg; - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer) + done; - scsi_pointer->this_residual = scsi_pointer->buffer->length - - done; + acp->buffer = sg; + acp->ptr = SG_ADDRESS(acp->buffer) + done; + acp->this_residual = acp->buffer->length - done; } SETPORT(SXFRCTL0, CH1|CLRCH1|CLRSTCNT); @@ -2229,7 +2223,6 @@ static void datao_end(struct Scsi_Host *shpnt) */ static int update_state(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); int dataphase=0; unsigned int stat0 = GETPORT(SSTAT0); unsigned int stat1 = GETPORT(SSTAT1); @@ -2244,7 +2237,7 @@ static int update_state(struct Scsi_Host *shpnt) } else if (stat0 & SELDI && PREVSTATE == busfree) { STATE=seldi; } else if (stat0 & SELDO && CURRENT_SC && - (scsi_pointer->phase & selecting)) { + (aha152x_priv(CURRENT_SC)->phase & selecting)) { STATE=seldo; } else if(stat1 & SELTO) { STATE=selto; @@ -2376,8 +2369,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(SXFRCTL0, CH1); SETPORT(DMACNTRL0, 0); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase &= - ~spiordy; + aha152x_priv(CURRENT_SC)->phase &= ~spiordy; } /* @@ -2399,8 +2391,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(DMACNTRL0, 0); SETPORT(SXFRCTL0, CH1|SPIOEN); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase |= - spiordy; + aha152x_priv(CURRENT_SC)->phase |= spiordy; } /* @@ -2490,7 +2481,7 @@ static void disp_enintr(struct Scsi_Host *shpnt) */ static void show_command(struct scsi_cmnd *ptr) { - const int phase = aha152x_scsi_pointer(ptr)->phase; + const int phase = aha152x_priv(ptr)->phase; scsi_print_command(ptr); scmd_printk(KERN_DEBUG, ptr, @@ -2538,8 +2529,8 @@ static void show_queues(struct Scsi_Host *shpnt) static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(ptr); - const int phase = scsi_pointer->phase; + struct aha152x_cmd_priv *acp = aha152x_priv(ptr); + const int phase = acp->phase; int i; seq_printf(m, "%p: target=%d; lun=%d; cmnd=( ", @@ -2549,8 +2540,8 @@ static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) seq_printf(m, "0x%02x ", ptr->cmnd[i]); seq_printf(m, "); resid=%d; residual=%d; buffers=%d; phase |", - scsi_get_resid(ptr), scsi_pointer->this_residual, - sg_nents(scsi_pointer->buffer) - 1); + scsi_get_resid(ptr), acp->this_residual, + sg_nents(acp->buffer) - 1); if (phase & not_issued) seq_puts(m, "not issued|"); diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.h b/drivers/scsi/aic7xxx/aic79xx_osm.h index 679a4fd13874..793fe19993a9 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.h +++ b/drivers/scsi/aic7xxx/aic79xx_osm.h @@ -420,8 +420,6 @@ ahd_unlock(struct ahd_softc *ahd, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e /****************************** PCI-X definitions *****************************/ #define PCIXR_COMMAND 0x96 diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c index 2f0bdb9225a4..5fad41b1ab58 100644 --- a/drivers/scsi/aic7xxx/aic79xx_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_pci.c @@ -260,8 +260,8 @@ ahd_find_pci_device(ahd_dev_softc_t pci) vendor = ahd_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahd_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahd_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahd_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahd_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahd_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahd_compose_id(device, vendor, subdevice, @@ -298,7 +298,7 @@ ahd_pci_config(struct ahd_softc *ahd, const struct ahd_pci_identity *entry) * Record if this is an HP board. */ subvendor = ahd_pci_read_config(ahd->dev_softc, - PCIR_SUBVEND_0, /*bytes*/2); + PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); if (subvendor == SUBID_HP) ahd->flags |= AHD_HP_BOARD; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.h b/drivers/scsi/aic7xxx/aic7xxx_osm.h index 4782a304e93c..51d9f4de0734 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.h +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.h @@ -433,8 +433,6 @@ ahc_unlock(struct ahc_softc *ahc, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e typedef enum { diff --git a/drivers/scsi/aic7xxx/aic7xxx_pci.c b/drivers/scsi/aic7xxx/aic7xxx_pci.c index dab3a6d12c4d..2d4c85426dc3 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_pci.c @@ -673,8 +673,8 @@ ahc_find_pci_device(ahc_dev_softc_t pci) vendor = ahc_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahc_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahc_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahc_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahc_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahc_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahc_compose_id(device, vendor, subdevice, subvendor); /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 0103f811cc25..776544385598 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1169,7 +1169,7 @@ static void bnx2fc_process_ofld_cmpl(struct bnx2fc_hba *hba, ofld_kcqe->fcoe_conn_context_id); interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mismatch\n"); goto ofld_cmpl_err; } /* @@ -1226,12 +1226,12 @@ static void bnx2fc_process_enable_conn_cmpl(struct bnx2fc_hba *hba, * and enable */ if (tgt->context_id != context_id) { - printk(KERN_ERR PFX "context id mis-match\n"); + printk(KERN_ERR PFX "context id mismatch\n"); return; } interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mismatch\n"); goto enbl_cmpl_err; } if (!ofld_kcqe->completion_status) diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 5521469ce678..6c864b093ac9 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1977,7 +1977,7 @@ static int bnx2i_process_new_cqes(struct bnx2i_conn *bnx2i_conn) if (nopin->cq_req_sn != qp->cqe_exp_seq_sn) break; - if (unlikely(test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx))) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { if (nopin->op_code == ISCSI_OP_NOOP_IN && nopin->itt == (u16) RESERVED_ITT) { printk(KERN_ALERT "bnx2i: Unsolicited " @@ -2398,7 +2398,7 @@ static void bnx2i_process_conn_destroy_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "conn destroy- error hba mis-match\n"); + printk(KERN_ALERT "conn destroy- error hba mismatch\n"); return; } @@ -2432,7 +2432,7 @@ static void bnx2i_process_ofld_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "ofld_cmpl: error hba mis-match\n"); + printk(KERN_ALERT "ofld_cmpl: error hba mismatch\n"); return; } diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c index fe86fd61a995..15fbd09baa94 100644 --- a/drivers/scsi/bnx2i/bnx2i_iscsi.c +++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c @@ -1721,7 +1721,7 @@ static int bnx2i_tear_down_conn(struct bnx2i_hba *hba, struct iscsi_conn *conn = ep->conn->cls_conn->dd_data; /* Must suspend all rx queue activity for this ep */ - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); } /* CONN_DISCONNECT timeout may or may not be an issue depending * on what transcribed in TCP layer, different targets behave diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 8c7d4dda4cf2..4365d52c6430 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -1634,11 +1634,11 @@ void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk) log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, conn 0x%p.\n", csk, conn); - if (unlikely(!conn || conn->suspend_rx)) { + if (unlikely(!conn || test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { log_debug(1 << CXGBI_DBG_PDU_RX, - "csk 0x%p, conn 0x%p, id %d, suspend_rx %lu!\n", + "csk 0x%p, conn 0x%p, id %d, conn flags 0x%lx!\n", csk, conn, conn ? conn->id : 0xFF, - conn ? conn->suspend_rx : 0xFF); + conn ? conn->flags : 0xFF); return; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 461ef8a76c4c..4bda2f6cb352 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -442,7 +442,6 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_INTERNAL_ABORT: hisi_sas_task_prep_abort(hisi_hba, slot); break; - fallthrough; default: return; } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 80238e6a3c98..eee1a24f7e15 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -36,7 +36,7 @@ #define IBMVSCSIS_VERSION "v0.2" -#define INITIAL_SRP_LIMIT 800 +#define INITIAL_SRP_LIMIT 1024 #define DEFAULT_MAX_SECTORS 256 #define MAX_TXU 1024 * 1024 diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index d690d9cf7eb1..35589b6af90d 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -413,7 +413,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for io request object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -428,7 +428,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for remote device object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -462,7 +462,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) } else dev_err(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received event 0x%x " - "for remote device object 0x%0x that doesnt " + "for remote device object 0x%0x that doesn't " "exist.\n", __func__, ihost, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d09926e6c8a8..797abf4f5399 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -678,7 +678,8 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, struct iscsi_task *task; itt_t itt; - if (session->state == ISCSI_STATE_TERMINATE) + if (session->state == ISCSI_STATE_TERMINATE || + !test_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags)) return NULL; if (opcode == ISCSI_OP_LOGIN || opcode == ISCSI_OP_TEXT) { @@ -1392,8 +1393,8 @@ static bool iscsi_set_conn_failed(struct iscsi_conn *conn) if (conn->stop_stage == 0) session->state = ISCSI_STATE_FAILED; - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); return true; } @@ -1454,7 +1455,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, * Do this after dropping the extra ref because if this was a requeue * it's removed from that list and cleanup_queued_task would miss it. */ - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { /* * Save the task and ref in case we weren't cleaning up this * task and get woken up again. @@ -1532,7 +1533,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) int rc = 0; spin_lock_bh(&conn->session->frwd_lock); - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { ISCSI_DBG_SESSION(conn->session, "Tx suspended!\n"); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1746,7 +1747,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto fault; } - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { reason = FAILURE_SESSION_IN_RECOVERY; sc->result = DID_REQUEUE << 16; goto fault; @@ -1935,7 +1936,7 @@ static void fail_scsi_tasks(struct iscsi_conn *conn, u64 lun, int error) void iscsi_suspend_queue(struct iscsi_conn *conn) { spin_lock_bh(&conn->session->frwd_lock); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_suspend_queue); @@ -1953,7 +1954,7 @@ void iscsi_suspend_tx(struct iscsi_conn *conn) struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); if (ihost->workq) flush_workqueue(ihost->workq); } @@ -1961,7 +1962,7 @@ EXPORT_SYMBOL_GPL(iscsi_suspend_tx); static void iscsi_start_tx(struct iscsi_conn *conn) { - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); iscsi_conn_queue_work(conn); } @@ -2214,6 +2215,8 @@ void iscsi_conn_unbind(struct iscsi_cls_conn *cls_conn, bool is_active) iscsi_suspend_tx(conn); spin_lock_bh(&session->frwd_lock); + clear_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); + if (!is_active) { /* * if logout timed out before userspace could even send a PDU @@ -3045,7 +3048,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, if (!cls_conn) return NULL; conn = cls_conn->dd_data; - memset(conn, 0, sizeof(*conn) + dd_size); conn->dd_data = cls_conn->dd_data + sizeof(*conn); conn->session = session; @@ -3318,6 +3320,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, spin_lock_bh(&session->frwd_lock); if (is_leading) session->leadconn = conn; + + set_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); spin_unlock_bh(&session->frwd_lock); /* @@ -3330,8 +3334,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, /* * Unblock xmitworker(), Login Phase will pass through. */ - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); return 0; } EXPORT_SYMBOL_GPL(iscsi_conn_bind); diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 2e9ffe3d1a55..883005757ddb 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -927,7 +927,7 @@ int iscsi_tcp_recv_skb(struct iscsi_conn *conn, struct sk_buff *skb, */ conn->last_recv = jiffies; - if (unlikely(conn->suspend_rx)) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { ISCSI_DBG_TCP(conn, "Rx suspended!\n"); *status = ISCSI_TCP_SUSPENDED; return 0; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index f0cf8ffdc5f3..0025760230e5 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -897,6 +897,11 @@ enum lpfc_irq_chann_mode { NHT_MODE, }; +enum lpfc_hba_bit_flags { + FABRIC_COMANDS_BLOCKED, + HBA_PCI_ERR, +}; + struct lpfc_hba { /* SCSI interface function jump table entries */ struct lpfc_io_buf * (*lpfc_get_scsi_buf) @@ -1043,7 +1048,6 @@ struct lpfc_hba { * Firmware supports Forced Link Speed * capability */ -#define HBA_PCI_ERR 0x80000 /* The PCI slot is offline */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ #define HBA_SHORT_CMF 0x200000 /* shorter CMF timer routine */ #define HBA_CGN_DAY_WRAP 0x400000 /* HBA Congestion info day wraps */ @@ -1350,7 +1354,6 @@ struct lpfc_hba { atomic_t fabric_iocb_count; struct timer_list fabric_block_timer; unsigned long bit_flags; -#define FABRIC_COMANDS_BLOCKED 0 atomic_t num_rsrc_err; atomic_t num_cmd_success; unsigned long last_rsrc_error_time; diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 96408cd6c4c8..9897a1aa387b 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -670,3 +670,6 @@ struct lpfc_vmid *lpfc_get_vmid_from_hashtable(struct lpfc_vport *vport, uint32_t hash, uint8_t *buf); void lpfc_vmid_vport_cleanup(struct lpfc_vport *vport); int lpfc_issue_els_qfpa(struct lpfc_vport *vport); + +void lpfc_sli_rpi_release(struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 0144da30e3db..2b877dff5ed4 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -109,8 +109,8 @@ lpfc_rport_invalid(struct fc_rport *rport) ndlp = rdata->pnode; if (!rdata->pnode) { - pr_err("**** %s: NULL ndlp on rport x%px SID x%x\n", - __func__, rport, rport->scsi_target_id); + pr_info("**** %s: NULL ndlp on rport x%px SID x%x\n", + __func__, rport, rport->scsi_target_id); return -EINVAL; } @@ -169,9 +169,10 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, "3181 dev_loss_callbk x%06x, rport x%px flg x%x " - "load_flag x%x refcnt %d\n", + "load_flag x%x refcnt %d state %d xpt x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag, - vport->load_flag, kref_read(&ndlp->kref)); + vport->load_flag, kref_read(&ndlp->kref), + ndlp->nlp_state, ndlp->fc4_xpt_flags); /* Don't schedule a worker thread event if the vport is going down. * The teardown process cleans up the node via lpfc_drop_node. @@ -181,6 +182,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; ndlp->fc4_xpt_flags &= ~SCSI_XPT_REGD; + /* clear the NLP_XPT_REGD if the node is not registered + * with nvme-fc + */ + if (ndlp->fc4_xpt_flags == NLP_XPT_REGD) + ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD; /* Remove the node reference from remote_port_add now. * The driver will not call remote_port_delete. @@ -225,18 +231,36 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; spin_unlock_irqrestore(&ndlp->lock, iflags); - /* We need to hold the node by incrementing the reference - * count until this queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); + if (phba->worker_thread) { + /* We need to hold the node by incrementing the reference + * count until this queued work is done + */ + evtp->evt_arg1 = lpfc_nlp_get(ndlp); + + spin_lock_irqsave(&phba->hbalock, iflags); + if (evtp->evt_arg1) { + evtp->evt = LPFC_EVT_DEV_LOSS; + list_add_tail(&evtp->evt_listp, &phba->work_list); + lpfc_worker_wake_up(phba); + } + spin_unlock_irqrestore(&phba->hbalock, iflags); + } else { + lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, + "3188 worker thread is stopped %s x%06x, " + " rport x%px flg x%x load_flag x%x refcnt " + "%d\n", __func__, ndlp->nlp_DID, + ndlp->rport, ndlp->nlp_flag, + vport->load_flag, kref_read(&ndlp->kref)); + if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) { + spin_lock_irqsave(&ndlp->lock, iflags); + /* Node is in dev loss. No further transaction. */ + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_disc_state_machine(vport, ndlp, NULL, + NLP_EVT_DEVICE_RM); + } - spin_lock_irqsave(&phba->hbalock, iflags); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_DEV_LOSS; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); } - spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -503,11 +527,12 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, "0203 Devloss timeout on " "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x " - "NPort x%06x Data: x%x x%x x%x\n", + "NPort x%06x Data: x%x x%x x%x refcnt %d\n", *name, *(name+1), *(name+2), *(name+3), *(name+4), *(name+5), *(name+6), *(name+7), ndlp->nlp_DID, ndlp->nlp_flag, - ndlp->nlp_state, ndlp->nlp_rpi); + ndlp->nlp_state, ndlp->nlp_rpi, + kref_read(&ndlp->kref)); } else { lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT, "0204 Devloss timeout on " @@ -755,18 +780,22 @@ lpfc_work_list_done(struct lpfc_hba *phba) int free_evt; int fcf_inuse; uint32_t nlp_did; + bool hba_pci_err; spin_lock_irq(&phba->hbalock); while (!list_empty(&phba->work_list)) { list_remove_head((&phba->work_list), evtp, typeof(*evtp), evt_listp); spin_unlock_irq(&phba->hbalock); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); free_evt = 1; switch (evtp->evt) { case LPFC_EVT_ELS_RETRY: ndlp = (struct lpfc_nodelist *) (evtp->evt_arg1); - lpfc_els_retry_delay_handler(ndlp); - free_evt = 0; /* evt is part of ndlp */ + if (!hba_pci_err) { + lpfc_els_retry_delay_handler(ndlp); + free_evt = 0; /* evt is part of ndlp */ + } /* decrement the node reference count held * for this queued work */ @@ -788,8 +817,10 @@ lpfc_work_list_done(struct lpfc_hba *phba) break; case LPFC_EVT_RECOVER_PORT: ndlp = (struct lpfc_nodelist *)(evtp->evt_arg1); - lpfc_sli_abts_recover_port(ndlp->vport, ndlp); - free_evt = 0; + if (!hba_pci_err) { + lpfc_sli_abts_recover_port(ndlp->vport, ndlp); + free_evt = 0; + } /* decrement the node reference count held for * this queued work */ @@ -859,14 +890,18 @@ lpfc_work_done(struct lpfc_hba *phba) struct lpfc_vport **vports; struct lpfc_vport *vport; int i; + bool hba_pci_err; + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); spin_lock_irq(&phba->hbalock); ha_copy = phba->work_ha; phba->work_ha = 0; spin_unlock_irq(&phba->hbalock); + if (hba_pci_err) + ha_copy = 0; /* First, try to post the next mailbox command to SLI4 device */ - if (phba->pci_dev_grp == LPFC_PCI_DEV_OC) + if (phba->pci_dev_grp == LPFC_PCI_DEV_OC && !hba_pci_err) lpfc_sli4_post_async_mbox(phba); if (ha_copy & HA_ERATT) { @@ -886,7 +921,7 @@ lpfc_work_done(struct lpfc_hba *phba) lpfc_handle_latt(phba); /* Handle VMID Events */ - if (lpfc_is_vmid_enabled(phba)) { + if (lpfc_is_vmid_enabled(phba) && !hba_pci_err) { if (phba->pport->work_port_events & WORKER_CHECK_VMID_ISSUE_QFPA) { lpfc_check_vmid_qfpa_issue(phba); @@ -936,6 +971,8 @@ lpfc_work_done(struct lpfc_hba *phba) work_port_events = vport->work_port_events; vport->work_port_events &= ~work_port_events; spin_unlock_irq(&vport->work_port_lock); + if (hba_pci_err) + continue; if (work_port_events & WORKER_DISC_TMO) lpfc_disc_timeout_handler(vport); if (work_port_events & WORKER_ELS_TMO) @@ -1173,12 +1210,14 @@ lpfc_linkdown(struct lpfc_hba *phba) struct lpfc_vport **vports; LPFC_MBOXQ_t *mb; int i; + int offline; if (phba->link_state == LPFC_LINK_DOWN) return 0; /* Block all SCSI stack I/Os */ lpfc_scsi_dev_block(phba); + offline = pci_channel_offline(phba->pcidev); phba->defer_flogi_acc_flag = false; @@ -1219,7 +1258,7 @@ lpfc_linkdown(struct lpfc_hba *phba) lpfc_destroy_vport_work_array(phba, vports); /* Clean up any SLI3 firmware default rpi's */ - if (phba->sli_rev > LPFC_SLI_REV3) + if (phba->sli_rev > LPFC_SLI_REV3 || offline) goto skip_unreg_did; mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); @@ -4712,6 +4751,11 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); if (!(ndlp->fc4_xpt_flags & NLP_XPT_REGD)) { spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "0999 %s Not regd: ndlp x%px rport x%px DID " + "x%x FLG x%x XPT x%x\n", + __func__, ndlp, ndlp->rport, ndlp->nlp_DID, + ndlp->nlp_flag, ndlp->fc4_xpt_flags); return; } @@ -4722,6 +4766,13 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->fc4_xpt_flags & SCSI_XPT_REGD) { vport->phba->nport_event_cnt++; lpfc_unregister_remote_port(ndlp); + } else if (!ndlp->rport) { + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "1999 %s NDLP in devloss x%px DID x%x FLG x%x" + " XPT x%x refcnt %d\n", + __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->fc4_xpt_flags, + kref_read(&ndlp->kref)); } if (ndlp->fc4_xpt_flags & NVME_XPT_REGD) { @@ -5371,6 +5422,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; mempool_free(mbox, phba->mbox_mem_pool); acc_plogi = 1; + lpfc_nlp_put(ndlp); } } else { lpfc_printf_vlog(vport, KERN_INFO, @@ -6097,12 +6149,34 @@ lpfc_disc_flush_list(struct lpfc_vport *vport) } } +/* + * lpfc_notify_xport_npr - notifies xport of node disappearance + * @vport: Pointer to Virtual Port object. + * + * Transitions all ndlps to NPR state. When lpfc_nlp_set_state + * calls lpfc_nlp_state_cleanup, the ndlp->rport is unregistered + * and transport notified that the node is gone. + * Return Code: + * none + */ +static void +lpfc_notify_xport_npr(struct lpfc_vport *vport) +{ + struct lpfc_nodelist *ndlp, *next_ndlp; + + list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, + nlp_listp) { + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + } +} void lpfc_cleanup_discovery_resources(struct lpfc_vport *vport) { lpfc_els_flush_rscn(vport); lpfc_els_flush_cmd(vport); lpfc_disc_flush_list(vport); + if (pci_channel_offline(vport->phba->pcidev)) + lpfc_notify_xport_npr(vport); } /*****************************************************************************/ diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index eed6464bd880..461d333b1b3a 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -95,6 +95,7 @@ static void lpfc_sli4_oas_verify(struct lpfc_hba *phba); static uint16_t lpfc_find_cpu_handle(struct lpfc_hba *, uint16_t, int); static void lpfc_setup_bg(struct lpfc_hba *, struct Scsi_Host *); static int lpfc_sli4_cgn_parm_chg_evt(struct lpfc_hba *); +static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba); static struct scsi_transport_template *lpfc_transport_template = NULL; static struct scsi_transport_template *lpfc_vport_transport_template = NULL; @@ -1642,7 +1643,7 @@ lpfc_sli4_offline_eratt(struct lpfc_hba *phba) { spin_lock_irq(&phba->hbalock); if (phba->link_state == LPFC_HBA_ERROR && - phba->hba_flag & HBA_PCI_ERR) { + test_bit(HBA_PCI_ERR, &phba->bit_flags)) { spin_unlock_irq(&phba->hbalock); return; } @@ -1985,6 +1986,7 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) if (pci_channel_offline(phba->pcidev)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "3166 pci channel is offline\n"); + lpfc_sli_flush_io_rings(phba); return; } @@ -2973,6 +2975,22 @@ lpfc_cleanup(struct lpfc_vport *vport) NLP_EVT_DEVICE_RM); } + /* This is a special case flush to return all + * IOs before entering this loop. There are + * two points in the code where a flush is + * avoided if the FC_UNLOADING flag is set. + * one is in the multipool destroy, + * (this prevents a crash) and the other is + * in the nvme abort handler, ( also prevents + * a crash). Both of these exceptions are + * cases where the slot is still accessible. + * The flush here is only when the pci slot + * is offline. + */ + if (vport->load_flag & FC_UNLOADING && + pci_channel_offline(phba->pcidev)) + lpfc_sli_flush_io_rings(vport->phba); + /* At this point, ALL ndlp's should be gone * because of the previous NLP_EVT_DEVICE_RM. * Lets wait for this to happen, if needed. @@ -2985,7 +3003,7 @@ lpfc_cleanup(struct lpfc_vport *vport) list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) { lpfc_printf_vlog(ndlp->vport, KERN_ERR, - LOG_TRACE_EVENT, + LOG_DISCOVERY, "0282 did:x%x ndlp:x%px " "refcnt:%d xflags x%x nflag x%x\n", ndlp->nlp_DID, (void *)ndlp, @@ -3682,7 +3700,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) struct lpfc_vport **vports; struct Scsi_Host *shost; int i; - int offline = 0; + int offline; + bool hba_pci_err; if (vport->fc_flag & FC_OFFLINE_MODE) return; @@ -3692,6 +3711,7 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) lpfc_linkdown(phba); offline = pci_channel_offline(phba->pcidev); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); /* Issue an unreg_login to all nodes on all vports */ vports = lpfc_create_vport_work_array(phba); @@ -3715,11 +3735,14 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) ndlp->nlp_flag &= ~NLP_NPR_ADISC; spin_unlock_irq(&ndlp->lock); - if (offline) { + if (offline || hba_pci_err) { spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~(NLP_UNREG_INP | NLP_RPI_REGISTERED); spin_unlock_irq(&ndlp->lock); + if (phba->sli_rev == LPFC_SLI_REV4) + lpfc_sli_rpi_release(vports[i], + ndlp); } else { lpfc_unreg_rpi(vports[i], ndlp); } @@ -13354,8 +13377,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Abort all iocbs associated with the hba */ lpfc_sli_hba_iocb_abort(phba); - /* Wait for completion of device XRI exchange busy */ - lpfc_sli4_xri_exchange_busy_wait(phba); + if (!pci_channel_offline(phba->pcidev)) + /* Wait for completion of device XRI exchange busy */ + lpfc_sli4_xri_exchange_busy_wait(phba); /* per-phba callback de-registration for hotplug event */ if (phba->pport) @@ -13374,15 +13398,12 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Disable FW logging to host memory */ lpfc_ras_stop_fwlog(phba); - /* Unset the queues shared with the hardware then release all - * allocated resources. - */ - lpfc_sli4_queue_unset(phba); - lpfc_sli4_queue_destroy(phba); - /* Reset SLI4 HBA FCoE function */ lpfc_pci_function_reset(phba); + /* release all queue allocated resources. */ + lpfc_sli4_queue_destroy(phba); + /* Free RAS DMA memory */ if (phba->ras_fwlog.ras_enabled) lpfc_sli4_ras_dma_free(phba); @@ -14262,6 +14283,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba) "2711 PCI channel permanent disable for failure\n"); /* Block all SCSI devices' I/Os on the host */ lpfc_scsi_dev_block(phba); + lpfc_sli4_prep_dev_for_reset(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -15057,24 +15079,28 @@ lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba) static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2826 PCI channel disable preparing for reset\n"); + int offline = pci_channel_offline(phba->pcidev); + + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2826 PCI channel disable preparing for reset offline" + " %d\n", offline); /* Block any management I/Os to the device */ lpfc_block_mgmt_io(phba, LPFC_MBX_NO_WAIT); - /* Block all SCSI devices' I/Os on the host */ - lpfc_scsi_dev_block(phba); + /* HBA_PCI_ERR was set in io_error_detect */ + lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); /* Flush all driver's outstanding I/Os as we are to reset */ lpfc_sli_flush_io_rings(phba); + lpfc_offline(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); + lpfc_sli4_queue_destroy(phba); /* Disable interrupt and pci device */ lpfc_sli4_disable_intr(phba); - lpfc_sli4_queue_destroy(phba); pci_disable_device(phba->pcidev); } @@ -15123,6 +15149,7 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) { struct Scsi_Host *shost = pci_get_drvdata(pdev); struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + bool hba_pci_err; switch (state) { case pci_channel_io_normal: @@ -15130,17 +15157,24 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) lpfc_sli4_prep_dev_for_recover(phba); return PCI_ERS_RESULT_CAN_RECOVER; case pci_channel_io_frozen: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Fatal error, prepare for slot reset */ - lpfc_sli4_prep_dev_for_reset(phba); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); + else + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2832 Already handling PCI error " + "state: x%x\n", state); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: - phba->hba_flag |= HBA_PCI_ERR; + set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Permanent failure, prepare for device down */ lpfc_sli4_prep_dev_for_perm_failure(phba); return PCI_ERS_RESULT_DISCONNECT; default: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); /* Unknown state, prepare and request slot reset */ lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "2825 Unknown PCI error state: x%x\n", state); @@ -15174,17 +15208,21 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; struct lpfc_sli *psli = &phba->sli; uint32_t intr_mode; + bool hba_pci_err; dev_printk(KERN_INFO, &pdev->dev, "recovering from a slot reset.\n"); if (pci_enable_device_mem(pdev)) { printk(KERN_ERR "lpfc: Cannot re-enable " - "PCI device after reset.\n"); + "PCI device after reset.\n"); return PCI_ERS_RESULT_DISCONNECT; } pci_restore_state(pdev); - phba->hba_flag &= ~HBA_PCI_ERR; + hba_pci_err = test_and_clear_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + dev_info(&pdev->dev, + "hba_pci_err was not set, recovering slot reset.\n"); /* * As the new kernel behavior of pci_restore_state() API call clears * device saved_state flag, need to save the restored state again. @@ -15198,6 +15236,8 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) psli->sli_flag &= ~LPFC_SLI_ACTIVE; spin_unlock_irq(&phba->hbalock); + /* Init cpu_map array */ + lpfc_cpu_map_array_init(phba); /* Configure and enable interrupt */ intr_mode = lpfc_sli4_enable_intr(phba, phba->intr_mode); if (intr_mode == LPFC_INTR_ERROR) { @@ -15239,8 +15279,6 @@ lpfc_io_resume_s4(struct pci_dev *pdev) */ if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE)) { /* Perform device reset */ - lpfc_offline_prep(phba, LPFC_MBX_WAIT); - lpfc_offline(phba); lpfc_sli_brdrestart(phba); /* Bring the device back online */ lpfc_online(phba); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 1213a299f9aa..8d26f207ebd2 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -93,6 +93,11 @@ lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport, lport = (struct lpfc_nvme_lport *)pnvme_lport->private; vport = lport->vport; + + if (!vport || vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; + qhandle = kzalloc(sizeof(struct lpfc_nvme_qhandle), GFP_KERNEL); if (qhandle == NULL) return -ENOMEM; @@ -267,7 +272,8 @@ lpfc_nvme_handle_lsreq(struct lpfc_hba *phba, return -EINVAL; remoteport = lpfc_rport->remoteport; - if (!vport->localport) + if (!vport->localport || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -EINVAL; lport = vport->localport->private; @@ -559,6 +565,8 @@ __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_DID, ntype, nstate); return -ENODEV; } + if (vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; if (!vport->phba->sli4_hba.nvmels_wq) return -ENOMEM; @@ -662,7 +670,8 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, return -EINVAL; vport = lport->vport; - if (vport->load_flag & FC_UNLOADING) + if (vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -ENODEV; atomic_inc(&lport->fc4NvmeLsRequests); @@ -1516,7 +1525,8 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, phba = vport->phba; - if (unlikely(vport->load_flag & FC_UNLOADING)) { + if ((unlikely(vport->load_flag & FC_UNLOADING)) || + phba->hba_flag & HBA_IOQ_FLUSH) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, "6124 Fail IO, Driver unload\n"); atomic_inc(&lport->xmt_fcp_err); @@ -2169,8 +2179,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_nvme = 0; for (i = 0; i < phba->cfg_hdw_queue; i++) { qp = &phba->sli4_hba.hdwq[i]; - if (!vport || !vport->localport || - !qp || !qp->io_wq) + if (!vport->localport || !qp || !qp->io_wq) return; pring = qp->io_wq->pring; @@ -2180,8 +2189,9 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_scsi += qp->abts_scsi_io_bufs; abts_nvme += qp->abts_nvme_io_bufs; } - if (!vport || !vport->localport || - vport->phba->hba_flag & HBA_PCI_ERR) + if (!vport->localport || + test_bit(HBA_PCI_ERR, &vport->phba->bit_flags) || + vport->load_flag & FC_UNLOADING) return; lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -2541,8 +2551,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * return values is ignored. The upcall is a courtesy to the * transport. */ - if (vport->load_flag & FC_UNLOADING || - unlikely(vport->phba->hba_flag & HBA_PCI_ERR)) + if (vport->load_flag & FC_UNLOADING) (void)nvme_fc_set_remoteport_devloss(remoteport, 0); ret = nvme_fc_unregister_remoteport(remoteport); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 3c132604fd91..ba9dbb51b75f 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5929,13 +5929,15 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) } lpfc_cmd->waitq = &waitq; - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->sli_rev == LPFC_SLI_REV4) { spin_unlock(&pring_s4->ring_lock); - else + ret_val = lpfc_sli4_issue_abort_iotag(phba, iocb, + lpfc_sli_abort_fcp_cmpl); + } else { pring = &phba->sli.sli3_ring[LPFC_FCP_RING]; - - ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, - lpfc_sli_abort_fcp_cmpl); + ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, + lpfc_sli_abort_fcp_cmpl); + } /* Make sure HBA is alive */ lpfc_issue_hb_tmo(phba); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 20d40957a385..bda2a7ba4e77 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2828,6 +2828,12 @@ __lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; } +void +lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ + __lpfc_sli_rpi_release(vport, ndlp); +} + /** * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler * @phba: Pointer to HBA context object. @@ -3715,7 +3721,15 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, unsigned long iflag; u32 ulp_command, ulp_status, ulp_word4, ulp_context, iotag; + if (phba->sli_rev == LPFC_SLI_REV4) + spin_lock_irqsave(&pring->ring_lock, iflag); + else + spin_lock_irqsave(&phba->hbalock, iflag); cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring, saveq); + if (phba->sli_rev == LPFC_SLI_REV4) + spin_unlock_irqrestore(&pring->ring_lock, iflag); + else + spin_unlock_irqrestore(&phba->hbalock, iflag); ulp_command = get_job_cmnd(phba, saveq); ulp_status = get_job_ulpstatus(phba, saveq); @@ -4052,10 +4066,8 @@ lpfc_sli_handle_fast_ring_event(struct lpfc_hba *phba, break; } - spin_unlock_irqrestore(&phba->hbalock, iflag); cmdiocbq = lpfc_sli_iocbq_lookup(phba, pring, &rspiocbq); - spin_lock_irqsave(&phba->hbalock, iflag); if (unlikely(!cmdiocbq)) break; if (cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED) @@ -4536,42 +4548,62 @@ lpfc_sli_handle_slow_ring_event_s4(struct lpfc_hba *phba, void lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring) { - LIST_HEAD(completions); + LIST_HEAD(tx_completions); + LIST_HEAD(txcmplq_completions); struct lpfc_iocbq *iocb, *next_iocb; + int offline; if (pring->ringno == LPFC_ELS_RING) { lpfc_fabric_abort_hba(phba); } + offline = pci_channel_offline(phba->pcidev); /* Error everything on txq and txcmplq * First do the txq. */ if (phba->sli_rev >= LPFC_SLI_REV4) { spin_lock_irq(&pring->ring_lock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - spin_unlock_irq(&pring->ring_lock); - spin_lock_irq(&phba->hbalock); - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); - spin_unlock_irq(&phba->hbalock); + if (offline) { + list_splice_init(&pring->txcmplq, + &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } + spin_unlock_irq(&pring->ring_lock); } else { spin_lock_irq(&phba->hbalock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); + if (offline) { + list_splice_init(&pring->txcmplq, &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } spin_unlock_irq(&phba->hbalock); } - /* Make sure HBA is alive */ - lpfc_issue_hb_tmo(phba); + if (offline) { + /* Cancel all the IOCBs from the completions list */ + lpfc_sli_cancel_iocbs(phba, &txcmplq_completions, + IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); + } else { + /* Make sure HBA is alive */ + lpfc_issue_hb_tmo(phba); + } /* Cancel all the IOCBs from the completions list */ - lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT, + lpfc_sli_cancel_iocbs(phba, &tx_completions, IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); } @@ -4624,11 +4656,6 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); - if (phba->hba_flag & HBA_IOQ_FLUSH || - !phba->sli4_hba.hdwq) { - spin_unlock_irq(&phba->hbalock); - return; - } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -10997,6 +11024,10 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, unsigned long iflags; int rc; + /* If the PCI channel is in offline state, do not post iocbs. */ + if (unlikely(pci_channel_offline(phba->pcidev))) + return IOCB_ERROR; + if (phba->sli_rev == LPFC_SLI_REV4) { lpfc_sli_prep_wqe(phba, piocb); diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index e52f37e5d896..a4d3259b8c52 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.2.0.0" +#define LPFC_DRIVER_VERSION "14.2.0.1" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 611871ef15b5..4919ea54b827 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2560,6 +2560,9 @@ struct megasas_instance_template { #define MEGASAS_IS_LOGICAL(sdev) \ ((sdev->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) +#define MEGASAS_IS_LUN_VALID(sdev) \ + (((sdev)->lun == 0) ? 1 : 0) + #define MEGASAS_DEV_INDEX(scp) \ (((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ scp->device->id) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 8bf72dbc33b7..db6793608447 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2126,6 +2126,9 @@ static int megasas_slave_alloc(struct scsi_device *sdev) goto scan_target; } return -ENXIO; + } else if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return -ENXIO; } scan_target: @@ -2156,6 +2159,10 @@ static void megasas_slave_destroy(struct scsi_device *sdev) instance = megasas_lookup_instance(sdev->host->host_no); if (MEGASAS_IS_LOGICAL(sdev)) { + if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return; + } ld_tgt_id = MEGASAS_TARGET_ID(sdev); instance->ld_tgtid_status[ld_tgt_id] = LD_TARGET_ID_DELETED; if (megasas_dbg_lvl & LD_PD_DEBUG) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index b57f1803371e..538d2c0cd971 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5716,13 +5716,12 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) /** * mpt3sas_check_same_4gb_region - checks whether all reply queues in a set are * having same upper 32bits in their base memory address. - * @reply_pool_start_address: Base address of a reply queue set + * @start_address: Base address of a reply queue set * @pool_sz: Size of single Reply Descriptor Post Queues pool size * * Return: 1 if reply queues in a set have a same upper 32bits in their base * memory address, else 0. */ - static int mpt3sas_check_same_4gb_region(dma_addr_t start_address, u32 pool_sz) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c index 0563078227de..a8dd14c91efd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_config.c +++ b/drivers/scsi/mpt3sas/mpt3sas_config.c @@ -394,10 +394,13 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t retry_count++; if (ioc->config_cmds.smid == smid) mpt3sas_base_free_smid(ioc, smid); - if ((ioc->shost_recovery) || (ioc->config_cmds.status & - MPT3_CMD_RESET) || ioc->pci_error_recovery) + if (ioc->config_cmds.status & MPT3_CMD_RESET) goto retry_config; - issue_host_reset = 1; + if (ioc->shost_recovery || ioc->pci_error_recovery) { + issue_host_reset = 0; + r = -EFAULT; + } else + issue_host_reset = 1; goto free_mem; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 00792767c620..7e476f50935b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11035,6 +11035,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, { struct _sas_port *mpt3sas_port, *next; unsigned long flags; + int port_id; /* remove sibling ports attached to this expander */ list_for_each_entry_safe(mpt3sas_port, next, @@ -11055,6 +11056,8 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, mpt3sas_port->hba_port); } + port_id = sas_expander->port->port_id; + mpt3sas_transport_port_remove(ioc, sas_expander->sas_address, sas_expander->sas_address_parent, sas_expander->port); @@ -11062,7 +11065,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, "expander_remove: handle(0x%04x), sas_addr(0x%016llx), port:%d\n", sas_expander->handle, (unsigned long long) sas_expander->sas_address, - sas_expander->port->port_id); + port_id); spin_lock_irqsave(&ioc->sas_node_lock, flags); list_del(&sas_expander->list); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 7ac63eb5ccd3..2fde496fff5f 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -647,6 +647,7 @@ static struct pci_device_id mvs_pci_table[] = { { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1300), chip_1300 }, { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1320), chip_1320 }, { PCI_VDEVICE(ADAPTEC2, 0x0450), chip_6440 }, + { PCI_VDEVICE(TTI, 0x2640), chip_6440 }, { PCI_VDEVICE(TTI, 0x2710), chip_9480 }, { PCI_VDEVICE(TTI, 0x2720), chip_9480 }, { PCI_VDEVICE(TTI, 0x2721), chip_9480 }, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index c4a838635893..5d7dfefd6f6c 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -192,10 +192,11 @@ struct sym53c500_data { int fast_pio; }; -static struct scsi_pointer *sym53c500_scsi_pointer(struct scsi_cmnd *cmd) -{ - return scsi_cmd_priv(cmd); -} +struct sym53c500_cmd_priv { + int status; + int message; + int phase; +}; enum Phase { idle, @@ -356,7 +357,7 @@ SYM53C500_intr(int irq, void *dev_id) struct sym53c500_data *data = (struct sym53c500_data *)dev->hostdata; struct scsi_cmnd *curSC = data->current_SC; - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(curSC); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(curSC); int fast_pio = data->fast_pio; spin_lock_irqsave(dev->host_lock, flags); @@ -403,12 +404,11 @@ SYM53C500_intr(int irq, void *dev_id) if (int_reg & 0x20) { /* Disconnect */ DEB(printk("SYM53C500: disconnect intr received\n")); - if (scsi_pointer->phase != message_in) { /* Unexpected disconnect */ + if (scp->phase != message_in) { /* Unexpected disconnect */ curSC->result = DID_NO_CONNECT << 16; } else { /* Command complete, return status and message */ - curSC->result = (scsi_pointer->Status & 0xff) | - ((scsi_pointer->Message & 0xff) << 8) | - (DID_OK << 16); + curSC->result = (scp->status & 0xff) | + ((scp->message & 0xff) << 8) | (DID_OK << 16); } goto idle_out; } @@ -419,7 +419,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_out; + scp->phase = data_out; VDEB(printk("SYM53C500: Data-Out phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -438,7 +438,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_in; + scp->phase = data_in; VDEB(printk("SYM53C500: Data-In phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -453,12 +453,12 @@ SYM53C500_intr(int irq, void *dev_id) break; case 0x02: /* COMMAND */ - scsi_pointer->phase = command_ph; + scp->phase = command_ph; printk("SYM53C500: Warning: Unknown interrupt occurred in command phase!\n"); break; case 0x03: /* STATUS */ - scsi_pointer->phase = status_ph; + scp->phase = status_ph; VDEB(printk("SYM53C500: Status phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); outb(INIT_CMD_COMPLETE, port_base + CMD_REG); @@ -471,24 +471,22 @@ SYM53C500_intr(int irq, void *dev_id) case 0x06: /* MESSAGE-OUT */ DEB(printk("SYM53C500: Message-Out phase\n")); - scsi_pointer->phase = message_out; + scp->phase = message_out; outb(SET_ATN, port_base + CMD_REG); /* Reject the message */ outb(MSG_ACCEPT, port_base + CMD_REG); break; case 0x07: /* MESSAGE-IN */ VDEB(printk("SYM53C500: Message-In phase\n")); - scsi_pointer->phase = message_in; + scp->phase = message_in; - scsi_pointer->Status = inb(port_base + SCSI_FIFO); - scsi_pointer->Message = inb(port_base + SCSI_FIFO); + scp->status = inb(port_base + SCSI_FIFO); + scp->message = inb(port_base + SCSI_FIFO); VDEB(printk("SCSI FIFO size=%d\n", inb(port_base + FIFO_FLAGS) & 0x1f)); - DEB(printk("Status = %02x Message = %02x\n", - scsi_pointer->Status, scsi_pointer->Message)); + DEB(printk("Status = %02x Message = %02x\n", scp->status, scp->message)); - if (scsi_pointer->Message == SAVE_POINTERS || - scsi_pointer->Message == DISCONNECT) { + if (scp->message == SAVE_POINTERS || scp->message == DISCONNECT) { outb(SET_ATN, port_base + CMD_REG); /* Reject message */ DEB(printk("Discarding SAVE_POINTERS message\n")); } @@ -500,7 +498,7 @@ out: return IRQ_HANDLED; idle_out: - scsi_pointer->phase = idle; + scp->phase = idle; scsi_done(curSC); goto out; } @@ -548,7 +546,7 @@ SYM53C500_info(struct Scsi_Host *SChost) static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) { - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(SCpnt); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(SCpnt); int i; int port_base = SCpnt->device->host->io_port; struct sym53c500_data *data = @@ -565,9 +563,9 @@ static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) VDEB(printk("\n")); data->current_SC = SCpnt; - scsi_pointer->phase = command_ph; - scsi_pointer->Status = 0; - scsi_pointer->Message = 0; + scp->phase = command_ph; + scp->status = 0; + scp->message = 0; /* We are locked here already by the mid layer */ REG0(port_base); @@ -682,7 +680,7 @@ static struct scsi_host_template sym53c500_driver_template = { .this_id = 7, .sg_tablesize = 32, .shost_groups = SYM53C500_shost_groups, - .cmd_size = sizeof(struct scsi_pointer), + .cmd_size = sizeof(struct sym53c500_cmd_priv), }; static int SYM53C500_config_check(struct pcmcia_device *p_dev, void *priv_data) diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index f90b707c190b..01c5e8ff4cc5 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -766,6 +766,10 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) pm8001_ha->main_cfg_tbl.pm80xx_tbl.pcs_event_log_severity = 0x01; pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt = 0x01; + /* Enable higher IQs and OQs, 32 to 63, bit 16 */ + if (pm8001_ha->max_q_num > 32) + pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt |= + 1 << 16; /* Disable end to end CRC checking */ pm8001_ha->main_cfg_tbl.pm80xx_tbl.crc_core_dump = (0x1 << 16); @@ -1027,6 +1031,13 @@ static int mpi_init_check(struct pm8001_hba_info *pm8001_ha) if (0x0000 != gst_len_mpistate) return -EBUSY; + /* + * As per controller datasheet, after successful MPI + * initialization minimum 500ms delay is required before + * issuing commands. + */ + msleep(500); + return 0; } @@ -1727,10 +1738,11 @@ static void pm80xx_chip_interrupt_enable(struct pm8001_hba_info *pm8001_ha, u8 vec) { #ifdef PM8001_USE_MSIX - u32 mask; - mask = (u32)(1 << vec); - - pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR, (u32)(mask & 0xFFFFFFFF)); + if (vec < 32) + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR, 1U << vec); + else + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR_U, + 1U << (vec - 32)); return; #endif pm80xx_chip_intx_interrupt_enable(pm8001_ha); @@ -1746,12 +1758,15 @@ static void pm80xx_chip_interrupt_disable(struct pm8001_hba_info *pm8001_ha, u8 vec) { #ifdef PM8001_USE_MSIX - u32 mask; - if (vec == 0xFF) - mask = 0xFFFFFFFF; + if (vec == 0xFF) { + /* disable all vectors 0-31, 32-63 */ + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, 0xFFFFFFFF); + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_U, 0xFFFFFFFF); + } else if (vec < 32) + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, 1U << vec); else - mask = (u32)(1 << vec); - pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, (u32)(mask & 0xFFFFFFFF)); + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_U, + 1U << (vec - 32)); return; #endif pm80xx_chip_intx_interrupt_disable(pm8001_ha); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 928532180d32..fd674ed1febe 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -3182,124 +3182,6 @@ static int pmcraid_build_ioadl( } /** - * pmcraid_free_sglist - Frees an allocated SG buffer list - * @sglist: scatter/gather list pointer - * - * Free a DMA'able memory previously allocated with pmcraid_alloc_sglist - * - * Return value: - * none - */ -static void pmcraid_free_sglist(struct pmcraid_sglist *sglist) -{ - sgl_free_order(sglist->scatterlist, sglist->order); - kfree(sglist); -} - -/** - * pmcraid_alloc_sglist - Allocates memory for a SG list - * @buflen: buffer length - * - * Allocates a DMA'able buffer in chunks and assembles a scatter/gather - * list. - * - * Return value - * pointer to sglist / NULL on failure - */ -static struct pmcraid_sglist *pmcraid_alloc_sglist(int buflen) -{ - struct pmcraid_sglist *sglist; - int sg_size; - int order; - - sg_size = buflen / (PMCRAID_MAX_IOADLS - 1); - order = (sg_size > 0) ? get_order(sg_size) : 0; - - /* Allocate a scatter/gather list for the DMA */ - sglist = kzalloc(sizeof(struct pmcraid_sglist), GFP_KERNEL); - if (sglist == NULL) - return NULL; - - sglist->order = order; - sgl_alloc_order(buflen, order, false, GFP_KERNEL | __GFP_ZERO, - &sglist->num_sg); - - return sglist; -} - -/** - * pmcraid_copy_sglist - Copy user buffer to kernel buffer's SG list - * @sglist: scatter/gather list pointer - * @buffer: buffer pointer - * @len: buffer length - * @direction: data transfer direction - * - * Copy a user buffer into a buffer allocated by pmcraid_alloc_sglist - * - * Return value: - * 0 on success / other on failure - */ -static int pmcraid_copy_sglist( - struct pmcraid_sglist *sglist, - void __user *buffer, - u32 len, - int direction -) -{ - struct scatterlist *sg; - void *kaddr; - int bsize_elem; - int i; - int rc = 0; - - /* Determine the actual number of bytes per element */ - bsize_elem = PAGE_SIZE * (1 << sglist->order); - - sg = sglist->scatterlist; - - for (i = 0; i < (len / bsize_elem); i++, sg = sg_next(sg), buffer += bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, bsize_elem); - else - rc = copy_to_user(buffer, kaddr, bsize_elem); - - kunmap(page); - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - return -EFAULT; - } - - sg->length = bsize_elem; - } - - if (len % bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, len % bsize_elem); - else - rc = copy_to_user(buffer, kaddr, len % bsize_elem); - - kunmap(page); - - sg->length = len % bsize_elem; - } - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - rc = -EFAULT; - } - - return rc; -} - -/** * pmcraid_queuecommand_lck - Queue a mid-layer request * @scsi_cmd: scsi command struct * @@ -3454,365 +3336,6 @@ static int pmcraid_chr_fasync(int fd, struct file *filep, int mode) return rc; } - -/** - * pmcraid_build_passthrough_ioadls - builds SG elements for passthrough - * commands sent over IOCTL interface - * - * @cmd : pointer to struct pmcraid_cmd - * @buflen : length of the request buffer - * @direction : data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static int pmcraid_build_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = NULL; - struct scatterlist *sg = NULL; - struct pmcraid_ioarcb *ioarcb = &cmd->ioa_cb->ioarcb; - struct pmcraid_ioadl_desc *ioadl; - int i; - - sglist = pmcraid_alloc_sglist(buflen); - - if (!sglist) { - pmcraid_err("can't allocate memory for passthrough SGls\n"); - return -ENOMEM; - } - - sglist->num_dma_sg = dma_map_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, direction); - - if (!sglist->num_dma_sg || sglist->num_dma_sg > PMCRAID_MAX_IOADLS) { - dev_err(&cmd->drv_inst->pdev->dev, - "Failed to map passthrough buffer!\n"); - pmcraid_free_sglist(sglist); - return -EIO; - } - - cmd->sglist = sglist; - ioarcb->request_flags0 |= NO_LINK_DESCS; - - ioadl = pmcraid_init_ioadls(cmd, sglist->num_dma_sg); - - /* Initialize IOADL descriptor addresses */ - for_each_sg(sglist->scatterlist, sg, sglist->num_dma_sg, i) { - ioadl[i].data_len = cpu_to_le32(sg_dma_len(sg)); - ioadl[i].address = cpu_to_le64(sg_dma_address(sg)); - ioadl[i].flags = 0; - } - - /* setup the last descriptor */ - ioadl[i - 1].flags = IOADL_FLAGS_LAST_DESC; - - return 0; -} - - -/** - * pmcraid_release_passthrough_ioadls - release passthrough ioadls - * - * @cmd: pointer to struct pmcraid_cmd for which ioadls were allocated - * @buflen: size of the request buffer - * @direction: data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static void pmcraid_release_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = cmd->sglist; - - if (buflen > 0) { - dma_unmap_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, - direction); - pmcraid_free_sglist(sglist); - cmd->sglist = NULL; - } -} - -/** - * pmcraid_ioctl_passthrough - handling passthrough IOCTL commands - * - * @pinstance: pointer to adapter instance structure - * @ioctl_cmd: ioctl code - * @buflen: unused - * @arg: pointer to pmcraid_passthrough_buffer user buffer - * - * Return value - * 0 on success, non-zero error code on failure - */ -static long pmcraid_ioctl_passthrough( - struct pmcraid_instance *pinstance, - unsigned int ioctl_cmd, - unsigned int buflen, - void __user *arg -) -{ - struct pmcraid_passthrough_ioctl_buffer *buffer; - struct pmcraid_ioarcb *ioarcb; - struct pmcraid_cmd *cmd; - struct pmcraid_cmd *cancel_cmd; - void __user *request_buffer; - unsigned long request_offset; - unsigned long lock_flags; - void __user *ioasa; - u32 ioasc; - int request_size; - int buffer_size; - u8 direction; - int rc = 0; - - /* If IOA reset is in progress, wait 10 secs for reset to complete */ - if (pinstance->ioa_reset_in_progress) { - rc = wait_event_interruptible_timeout( - pinstance->reset_wait_q, - !pinstance->ioa_reset_in_progress, - msecs_to_jiffies(10000)); - - if (!rc) - return -ETIMEDOUT; - else if (rc < 0) - return -ERESTARTSYS; - } - - /* If adapter is not in operational state, return error */ - if (pinstance->ioa_state != IOA_STATE_OPERATIONAL) { - pmcraid_err("IOA is not operational\n"); - return -ENOTTY; - } - - buffer_size = sizeof(struct pmcraid_passthrough_ioctl_buffer); - buffer = kmalloc(buffer_size, GFP_KERNEL); - - if (!buffer) { - pmcraid_err("no memory for passthrough buffer\n"); - return -ENOMEM; - } - - request_offset = - offsetof(struct pmcraid_passthrough_ioctl_buffer, request_buffer); - - request_buffer = arg + request_offset; - - rc = copy_from_user(buffer, arg, - sizeof(struct pmcraid_passthrough_ioctl_buffer)); - - ioasa = arg + offsetof(struct pmcraid_passthrough_ioctl_buffer, ioasa); - - if (rc) { - pmcraid_err("ioctl: can't copy passthrough buffer\n"); - rc = -EFAULT; - goto out_free_buffer; - } - - request_size = le32_to_cpu(buffer->ioarcb.data_transfer_length); - - if (buffer->ioarcb.request_flags0 & TRANSFER_DIR_WRITE) { - direction = DMA_TO_DEVICE; - } else { - direction = DMA_FROM_DEVICE; - } - - if (request_size < 0) { - rc = -EINVAL; - goto out_free_buffer; - } - - /* check if we have any additional command parameters */ - if (le16_to_cpu(buffer->ioarcb.add_cmd_param_length) - > PMCRAID_ADD_CMD_PARAM_LEN) { - rc = -EINVAL; - goto out_free_buffer; - } - - cmd = pmcraid_get_free_cmd(pinstance); - - if (!cmd) { - pmcraid_err("free command block is not available\n"); - rc = -ENOMEM; - goto out_free_buffer; - } - - cmd->scsi_cmd = NULL; - ioarcb = &(cmd->ioa_cb->ioarcb); - - /* Copy the user-provided IOARCB stuff field by field */ - ioarcb->resource_handle = buffer->ioarcb.resource_handle; - ioarcb->data_transfer_length = buffer->ioarcb.data_transfer_length; - ioarcb->cmd_timeout = buffer->ioarcb.cmd_timeout; - ioarcb->request_type = buffer->ioarcb.request_type; - ioarcb->request_flags0 = buffer->ioarcb.request_flags0; - ioarcb->request_flags1 = buffer->ioarcb.request_flags1; - memcpy(ioarcb->cdb, buffer->ioarcb.cdb, PMCRAID_MAX_CDB_LEN); - - if (buffer->ioarcb.add_cmd_param_length) { - ioarcb->add_cmd_param_length = - buffer->ioarcb.add_cmd_param_length; - ioarcb->add_cmd_param_offset = - buffer->ioarcb.add_cmd_param_offset; - memcpy(ioarcb->add_data.u.add_cmd_params, - buffer->ioarcb.add_data.u.add_cmd_params, - le16_to_cpu(buffer->ioarcb.add_cmd_param_length)); - } - - /* set hrrq number where the IOA should respond to. Note that all cmds - * generated internally uses hrrq_id 0, exception to this is the cmd - * block of scsi_cmd which is re-used (e.g. cancel/abort), which uses - * hrrq_id assigned here in queuecommand - */ - ioarcb->hrrq_id = atomic_add_return(1, &(pinstance->last_message_id)) % - pinstance->num_hrrq; - - if (request_size) { - rc = pmcraid_build_passthrough_ioadls(cmd, - request_size, - direction); - if (rc) { - pmcraid_err("couldn't build passthrough ioadls\n"); - goto out_free_cmd; - } - } - - /* If data is being written into the device, copy the data from user - * buffers - */ - if (direction == DMA_TO_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - goto out_free_sglist; - } - } - - /* passthrough ioctl is a blocking command so, put the user to sleep - * until timeout. Note that a timeout value of 0 means, do timeout. - */ - cmd->cmd_done = pmcraid_internal_done; - init_completion(&cmd->wait_for_completion); - cmd->completion_req = 1; - - pmcraid_info("command(%d) (CDB[0] = %x) for %x\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0], - le32_to_cpu(cmd->ioa_cb->ioarcb.resource_handle)); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - _pmcraid_fire_command(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - /* NOTE ! Remove the below line once abort_task is implemented - * in firmware. This line disables ioctl command timeout handling logic - * similar to IO command timeout handling, making ioctl commands to wait - * until the command completion regardless of timeout value specified in - * ioarcb - */ - buffer->ioarcb.cmd_timeout = 0; - - /* If command timeout is specified put caller to wait till that time, - * otherwise it would be blocking wait. If command gets timed out, it - * will be aborted. - */ - if (buffer->ioarcb.cmd_timeout == 0) { - wait_for_completion(&cmd->wait_for_completion); - } else if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(le16_to_cpu(buffer->ioarcb.cmd_timeout) * 1000))) { - - pmcraid_info("aborting cmd %d (CDB[0] = %x) due to timeout\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0]); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - cancel_cmd = pmcraid_abort_cmd(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - if (cancel_cmd) { - wait_for_completion(&cancel_cmd->wait_for_completion); - ioasc = le32_to_cpu(cancel_cmd->ioa_cb->ioasa.ioasc); - pmcraid_return_cmd(cancel_cmd); - - /* if abort task couldn't find the command i.e it got - * completed prior to aborting, return good completion. - * if command got aborted successfully or there was IOA - * reset due to abort task itself getting timedout then - * return -ETIMEDOUT - */ - if (ioasc == PMCRAID_IOASC_IOA_WAS_RESET || - PMCRAID_IOASC_SENSE_KEY(ioasc) == 0x00) { - if (ioasc != PMCRAID_IOASC_GC_IOARCB_NOTFOUND) - rc = -ETIMEDOUT; - goto out_handle_response; - } - } - - /* no command block for abort task or abort task failed to abort - * the IOARCB, then wait for 150 more seconds and initiate reset - * sequence after timeout - */ - if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(150 * 1000))) { - pmcraid_reset_bringup(cmd->drv_inst); - rc = -ETIMEDOUT; - } - } - -out_handle_response: - /* copy entire IOASA buffer and return IOCTL success. - * If copying IOASA to user-buffer fails, return - * EFAULT - */ - if (copy_to_user(ioasa, &cmd->ioa_cb->ioasa, - sizeof(struct pmcraid_ioasa))) { - pmcraid_err("failed to copy ioasa buffer to user\n"); - rc = -EFAULT; - } - - /* If the data transfer was from device, copy the data onto user - * buffers - */ - else if (direction == DMA_FROM_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - rc = -EFAULT; - } - } - -out_free_sglist: - pmcraid_release_passthrough_ioadls(cmd, request_size, direction); - -out_free_cmd: - pmcraid_return_cmd(cmd); - -out_free_buffer: - kfree(buffer); - - return rc; -} - - - - /** * pmcraid_ioctl_driver - ioctl handler for commands handled by driver itself * @@ -3922,20 +3445,6 @@ static long pmcraid_chr_ioctl( switch (_IOC_TYPE(cmd)) { - case PMCRAID_PASSTHROUGH_IOCTL: - /* If ioctl code is to download microcode, we need to block - * mid-layer requests. - */ - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_block_requests(pinstance->host); - - retval = pmcraid_ioctl_passthrough(pinstance, cmd, - hdr->buffer_length, argp); - - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_unblock_requests(pinstance->host); - break; - case PMCRAID_DRIVER_IOCTL: arg += sizeof(struct pmcraid_ioctl_header); retval = pmcraid_ioctl_driver(pinstance, cmd, diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index bbb75318f1e7..9f59930e8b4f 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -1023,40 +1023,15 @@ struct pmcraid_ioctl_header { #define PMCRAID_IOCTL_SIGNATURE "PMCRAID" /* - * pmcraid_passthrough_ioctl_buffer - structure given as argument to - * passthrough(or firmware handled) IOCTL commands. Note that ioarcb requires - * 32-byte alignment so, it is necessary to pack this structure to avoid any - * holes between ioctl_header and passthrough buffer - * - * .ioactl_header : ioctl header - * .ioarcb : filled-up ioarcb buffer, driver always reads this buffer - * .ioasa : buffer for ioasa, driver fills this with IOASA from firmware - * .request_buffer: The I/O buffer (flat), driver reads/writes to this based on - * the transfer directions passed in ioarcb.flags0. Contents - * of this buffer are valid only when ioarcb.data_transfer_len - * is not zero. - */ -struct pmcraid_passthrough_ioctl_buffer { - struct pmcraid_ioctl_header ioctl_header; - struct pmcraid_ioarcb ioarcb; - struct pmcraid_ioasa ioasa; - u8 request_buffer[]; -} __attribute__ ((packed, aligned(PMCRAID_IOARCB_ALIGNMENT))); - -/* * keys to differentiate between driver handled IOCTLs and passthrough * IOCTLs passed to IOA. driver determines the ioctl type using macro * _IOC_TYPE */ #define PMCRAID_DRIVER_IOCTL 'D' -#define PMCRAID_PASSTHROUGH_IOCTL 'F' #define DRV_IOCTL(n, size) \ _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_DRIVER_IOCTL, (n), (size)) -#define FMW_IOCTL(n, size) \ - _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_PASSTHROUGH_IOCTL, (n), (size)) - /* * _ARGSIZE: macro that gives size of the argument type passed to an IOCTL cmd. * This is to facilitate applications avoiding un-necessary memory allocations. @@ -1069,12 +1044,4 @@ struct pmcraid_passthrough_ioctl_buffer { #define PMCRAID_IOCTL_RESET_ADAPTER \ DRV_IOCTL(5, sizeof(struct pmcraid_ioctl_header)) -/* passthrough/firmware handled commands */ -#define PMCRAID_IOCTL_PASSTHROUGH_COMMAND \ - FMW_IOCTL(1, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - -#define PMCRAID_IOCTL_DOWNLOAD_MICROCODE \ - FMW_IOCTL(2, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - - #endif /* _PMCRAID_H */ diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 8196f89f404e..31ec429104e2 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -860,6 +860,37 @@ static int qedi_task_xmit(struct iscsi_task *task) return qedi_iscsi_send_ioreq(task); } +static void qedi_offload_work(struct work_struct *work) +{ + struct qedi_endpoint *qedi_ep = + container_of(work, struct qedi_endpoint, offload_work); + struct qedi_ctx *qedi; + int wait_delay = 5 * HZ; + int ret; + + qedi = qedi_ep->qedi; + + ret = qedi_iscsi_offload_conn(qedi_ep); + if (ret) { + QEDI_ERR(&qedi->dbg_ctx, + "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", + qedi_ep->iscsi_cid, qedi_ep, ret); + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + return; + } + + ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, + (qedi_ep->state == + EP_STATE_OFLDCONN_COMPL), + wait_delay); + if (ret <= 0 || qedi_ep->state != EP_STATE_OFLDCONN_COMPL) { + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + QEDI_ERR(&qedi->dbg_ctx, + "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", + qedi_ep->iscsi_cid, qedi_ep); + } +} + static struct iscsi_endpoint * qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, int non_blocking) @@ -908,6 +939,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, } qedi_ep = ep->dd_data; memset(qedi_ep, 0, sizeof(struct qedi_endpoint)); + INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); qedi_ep->state = EP_STATE_IDLE; qedi_ep->iscsi_cid = (u32)-1; qedi_ep->qedi = qedi; @@ -1056,12 +1088,11 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) qedi_ep = ep->dd_data; qedi = qedi_ep->qedi; + flush_work(&qedi_ep->offload_work); + if (qedi_ep->state == EP_STATE_OFLDCONN_START) goto ep_exit_recover; - if (qedi_ep->state != EP_STATE_OFLDCONN_NONE) - flush_work(&qedi_ep->offload_work); - if (qedi_ep->conn) { qedi_conn = qedi_ep->conn; abrt_conn = qedi_conn->abrt_conn; @@ -1235,37 +1266,6 @@ static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid) return rc; } -static void qedi_offload_work(struct work_struct *work) -{ - struct qedi_endpoint *qedi_ep = - container_of(work, struct qedi_endpoint, offload_work); - struct qedi_ctx *qedi; - int wait_delay = 5 * HZ; - int ret; - - qedi = qedi_ep->qedi; - - ret = qedi_iscsi_offload_conn(qedi_ep); - if (ret) { - QEDI_ERR(&qedi->dbg_ctx, - "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", - qedi_ep->iscsi_cid, qedi_ep, ret); - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - return; - } - - ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, - (qedi_ep->state == - EP_STATE_OFLDCONN_COMPL), - wait_delay); - if ((ret <= 0) || (qedi_ep->state != EP_STATE_OFLDCONN_COMPL)) { - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - QEDI_ERR(&qedi->dbg_ctx, - "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", - qedi_ep->iscsi_cid, qedi_ep); - } -} - static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) { struct qedi_ctx *qedi; @@ -1381,7 +1381,6 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) qedi_ep->dst_addr, qedi_ep->dst_port); } - INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); queue_work(qedi->offload_thread, &qedi_ep->offload_work); ret = 0; diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index c607755cce00..592a290e6cfa 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -32,7 +32,6 @@ #include <linux/blkdev.h> #include <linux/crc-t10dif.h> #include <linux/spinlock.h> -#include <linux/mutex.h> #include <linux/interrupt.h> #include <linux/atomic.h> #include <linux/hrtimer.h> @@ -732,9 +731,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEM_P1 + 1] = { {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, }; -static atomic_t sdebug_num_hosts; -static DEFINE_MUTEX(add_host_mutex); - +static int sdebug_num_hosts; static int sdebug_add_host = DEF_NUM_HOST; /* in sysfs this is relative */ static int sdebug_ato = DEF_ATO; static int sdebug_cdb_len = DEF_CDB_LEN; @@ -781,7 +778,6 @@ static int sdebug_uuid_ctl = DEF_UUID_CTL; static bool sdebug_random = DEF_RANDOM; static bool sdebug_per_host_store = DEF_PER_HOST_STORE; static bool sdebug_removable = DEF_REMOVABLE; -static bool sdebug_deflect_incoming; static bool sdebug_clustering; static bool sdebug_host_lock = DEF_HOST_LOCK; static bool sdebug_strict = DEF_STRICT; @@ -5122,10 +5118,6 @@ static int scsi_debug_slave_configure(struct scsi_device *sdp) sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); if (sdp->host->max_cmd_len != SDEBUG_MAX_CMD_LEN) sdp->host->max_cmd_len = SDEBUG_MAX_CMD_LEN; - if (smp_load_acquire(&sdebug_deflect_incoming)) { - pr_info("Exit early due to deflect_incoming\n"); - return 1; - } if (devip == NULL) { devip = find_build_dev_info(sdp); if (devip == NULL) @@ -5211,7 +5203,7 @@ static bool stop_queued_cmnd(struct scsi_cmnd *cmnd) } /* Deletes (stops) timers or work queues of all queued commands */ -static void stop_all_queued(bool done_with_no_conn) +static void stop_all_queued(void) { unsigned long iflags; int j, k; @@ -5220,15 +5212,13 @@ static void stop_all_queued(bool done_with_no_conn) struct sdebug_queued_cmd *sqcp; struct sdebug_dev_info *devip; struct sdebug_defer *sd_dp; - struct scsi_cmnd *scp; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { spin_lock_irqsave(&sqp->qc_lock, iflags); for (k = 0; k < SDEBUG_CANQUEUE; ++k) { if (test_bit(k, sqp->in_use_bm)) { sqcp = &sqp->qc_arr[k]; - scp = sqcp->a_cmnd; - if (!scp) + if (sqcp->a_cmnd == NULL) continue; devip = (struct sdebug_dev_info *) sqcp->a_cmnd->device->hostdata; @@ -5243,10 +5233,6 @@ static void stop_all_queued(bool done_with_no_conn) l_defer_t = SDEB_DEFER_NONE; spin_unlock_irqrestore(&sqp->qc_lock, iflags); stop_qc_helper(sd_dp, l_defer_t); - if (done_with_no_conn && l_defer_t != SDEB_DEFER_NONE) { - scp->result = DID_NO_CONNECT << 16; - scsi_done(scp); - } clear_bit(k, sqp->in_use_bm); spin_lock_irqsave(&sqp->qc_lock, iflags); } @@ -5389,7 +5375,7 @@ static int scsi_debug_host_reset(struct scsi_cmnd *SCpnt) } } spin_unlock(&sdebug_host_list_lock); - stop_all_queued(false); + stop_all_queued(); if (SDEBUG_OPT_RESET_NOISE & sdebug_opts) sdev_printk(KERN_INFO, SCpnt->device, "%s: %d device(s) found\n", __func__, k); @@ -5449,50 +5435,13 @@ static void sdebug_build_parts(unsigned char *ramp, unsigned long store_size) } } -static void sdeb_block_all_queues(void) -{ - int j; - struct sdebug_queue *sqp; - - for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) - atomic_set(&sqp->blocked, (int)true); -} - -static void sdeb_unblock_all_queues(void) +static void block_unblock_all_queues(bool block) { int j; struct sdebug_queue *sqp; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) - atomic_set(&sqp->blocked, (int)false); -} - -static void -sdeb_add_n_hosts(int num_hosts) -{ - if (num_hosts < 1) - return; - do { - bool found; - unsigned long idx; - struct sdeb_store_info *sip; - bool want_phs = (sdebug_fake_rw == 0) && sdebug_per_host_store; - - found = false; - if (want_phs) { - xa_for_each_marked(per_store_ap, idx, sip, SDEB_XA_NOT_IN_USE) { - sdeb_most_recent_idx = (int)idx; - found = true; - break; - } - if (found) /* re-use case */ - sdebug_add_host_helper((int)idx); - else - sdebug_do_add_host(true /* make new store */); - } else { - sdebug_do_add_host(false); - } - } while (--num_hosts); + atomic_set(&sqp->blocked, (int)block); } /* Adjust (by rounding down) the sdebug_cmnd_count so abs(every_nth)-1 @@ -5505,10 +5454,10 @@ static void tweak_cmnd_count(void) modulo = abs(sdebug_every_nth); if (modulo < 2) return; - sdeb_block_all_queues(); + block_unblock_all_queues(true); count = atomic_read(&sdebug_cmnd_count); atomic_set(&sdebug_cmnd_count, (count / modulo) * modulo); - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } static void clear_queue_stats(void) @@ -5526,15 +5475,6 @@ static bool inject_on_this_cmd(void) return (atomic_read(&sdebug_cmnd_count) % abs(sdebug_every_nth)) == 0; } -static int process_deflect_incoming(struct scsi_cmnd *scp) -{ - u8 opcode = scp->cmnd[0]; - - if (opcode == SYNCHRONIZE_CACHE || opcode == SYNCHRONIZE_CACHE_16) - return 0; - return DID_NO_CONNECT << 16; -} - #define INCLUSIVE_TIMING_MAX_NS 1000000 /* 1 millisecond */ /* Complete the processing of the thread that queued a SCSI command to this @@ -5544,7 +5484,8 @@ static int process_deflect_incoming(struct scsi_cmnd *scp) */ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, int scsi_result, - int (*pfp)(struct scsi_cmnd *, struct sdebug_dev_info *), + int (*pfp)(struct scsi_cmnd *, + struct sdebug_dev_info *), int delta_jiff, int ndelay) { bool new_sd_dp; @@ -5565,27 +5506,13 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, } sdp = cmnd->device; - if (delta_jiff == 0) { - sqp = get_queue(cmnd); - if (atomic_read(&sqp->blocked)) { - if (smp_load_acquire(&sdebug_deflect_incoming)) - return process_deflect_incoming(cmnd); - else - return SCSI_MLQUEUE_HOST_BUSY; - } + if (delta_jiff == 0) goto respond_in_thread; - } sqp = get_queue(cmnd); spin_lock_irqsave(&sqp->qc_lock, iflags); if (unlikely(atomic_read(&sqp->blocked))) { spin_unlock_irqrestore(&sqp->qc_lock, iflags); - if (smp_load_acquire(&sdebug_deflect_incoming)) { - scsi_result = process_deflect_incoming(cmnd); - goto respond_in_thread; - } - if (sdebug_verbose) - pr_info("blocked --> SCSI_MLQUEUE_HOST_BUSY\n"); return SCSI_MLQUEUE_HOST_BUSY; } num_in_q = atomic_read(&devip->num_in_q); @@ -5774,12 +5701,8 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, respond_in_thread: /* call back to mid-layer using invocation thread */ cmnd->result = pfp != NULL ? pfp(cmnd, devip) : 0; cmnd->result &= ~SDEG_RES_IMMED_MASK; - if (cmnd->result == 0 && scsi_result != 0) { + if (cmnd->result == 0 && scsi_result != 0) cmnd->result = scsi_result; - if (sdebug_verbose) - pr_info("respond_in_thread: tag=0x%x, scp->result=0x%x\n", - blk_mq_unique_tag(scsi_cmd_to_rq(cmnd)), scsi_result); - } scsi_done(cmnd); return 0; } @@ -6064,7 +5987,7 @@ static ssize_t delay_store(struct device_driver *ddp, const char *buf, int j, k; struct sdebug_queue *sqp; - sdeb_block_all_queues(); + block_unblock_all_queues(true); for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { k = find_first_bit(sqp->in_use_bm, @@ -6078,7 +6001,7 @@ static ssize_t delay_store(struct device_driver *ddp, const char *buf, sdebug_jdelay = jdelay; sdebug_ndelay = 0; } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } return res; } @@ -6104,7 +6027,7 @@ static ssize_t ndelay_store(struct device_driver *ddp, const char *buf, int j, k; struct sdebug_queue *sqp; - sdeb_block_all_queues(); + block_unblock_all_queues(true); for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { k = find_first_bit(sqp->in_use_bm, @@ -6119,7 +6042,7 @@ static ssize_t ndelay_store(struct device_driver *ddp, const char *buf, sdebug_jdelay = ndelay ? JDELAY_OVERRIDDEN : DEF_JDELAY; } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } return res; } @@ -6433,7 +6356,7 @@ static ssize_t max_queue_store(struct device_driver *ddp, const char *buf, if ((count > 0) && (1 == sscanf(buf, "%d", &n)) && (n > 0) && (n <= SDEBUG_CANQUEUE) && (sdebug_host_max_queue == 0)) { - sdeb_block_all_queues(); + block_unblock_all_queues(true); k = 0; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { @@ -6448,7 +6371,7 @@ static ssize_t max_queue_store(struct device_driver *ddp, const char *buf, atomic_set(&retired_max_queue, k + 1); else atomic_set(&retired_max_queue, 0); - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return count; } return -EINVAL; @@ -6537,48 +6460,43 @@ static DRIVER_ATTR_RW(virtual_gb); static ssize_t add_host_show(struct device_driver *ddp, char *buf) { /* absolute number of hosts currently active is what is shown */ - return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&sdebug_num_hosts)); + return scnprintf(buf, PAGE_SIZE, "%d\n", sdebug_num_hosts); } -/* - * Accept positive and negative values. Hex values (only positive) may be prefixed by '0x'. - * To remove all hosts use a large negative number (e.g. -9999). The value 0 does nothing. - * Returns -EBUSY if another add_host sysfs invocation is active. - */ static ssize_t add_host_store(struct device_driver *ddp, const char *buf, size_t count) { + bool found; + unsigned long idx; + struct sdeb_store_info *sip; + bool want_phs = (sdebug_fake_rw == 0) && sdebug_per_host_store; int delta_hosts; - if (count == 0 || kstrtoint(buf, 0, &delta_hosts)) + if (sscanf(buf, "%d", &delta_hosts) != 1) return -EINVAL; - if (sdebug_verbose) - pr_info("prior num_hosts=%d, num_to_add=%d\n", - atomic_read(&sdebug_num_hosts), delta_hosts); - if (delta_hosts == 0) - return count; - if (mutex_trylock(&add_host_mutex) == 0) - return -EBUSY; if (delta_hosts > 0) { - sdeb_add_n_hosts(delta_hosts); - } else if (delta_hosts < 0) { - smp_store_release(&sdebug_deflect_incoming, true); - sdeb_block_all_queues(); - if (delta_hosts >= atomic_read(&sdebug_num_hosts)) - stop_all_queued(true); do { - if (atomic_read(&sdebug_num_hosts) < 1) { - free_all_queued(); - break; + found = false; + if (want_phs) { + xa_for_each_marked(per_store_ap, idx, sip, + SDEB_XA_NOT_IN_USE) { + sdeb_most_recent_idx = (int)idx; + found = true; + break; + } + if (found) /* re-use case */ + sdebug_add_host_helper((int)idx); + else + sdebug_do_add_host(true); + } else { + sdebug_do_add_host(false); } + } while (--delta_hosts); + } else if (delta_hosts < 0) { + do { sdebug_do_remove_host(false); } while (++delta_hosts); - sdeb_unblock_all_queues(); - smp_store_release(&sdebug_deflect_incoming, false); } - mutex_unlock(&add_host_mutex); - if (sdebug_verbose) - pr_info("post num_hosts=%d\n", atomic_read(&sdebug_num_hosts)); return count; } static DRIVER_ATTR_RW(add_host); @@ -7089,10 +7007,6 @@ static int __init scsi_debug_init(void) sdebug_add_host = 0; for (k = 0; k < hosts_to_add; k++) { - if (smp_load_acquire(&sdebug_deflect_incoming)) { - pr_info("exit early as sdebug_deflect_incoming is set\n"); - return 0; - } if (want_store && k == 0) { ret = sdebug_add_host_helper(idx); if (ret < 0) { @@ -7110,12 +7024,8 @@ static int __init scsi_debug_init(void) } } if (sdebug_verbose) - pr_info("built %d host(s)\n", atomic_read(&sdebug_num_hosts)); + pr_info("built %d host(s)\n", sdebug_num_hosts); - /* - * Even though all the hosts have been established, due to async device (LU) scanning - * by the scsi mid-level, there may still be devices (LUs) being set up. - */ return 0; bus_unreg: @@ -7131,17 +7041,12 @@ free_q_arr: static void __exit scsi_debug_exit(void) { - int k; + int k = sdebug_num_hosts; - /* Possible race with LUs still being set up; stop them asap */ - sdeb_block_all_queues(); - smp_store_release(&sdebug_deflect_incoming, true); - stop_all_queued(false); - for (k = 0; atomic_read(&sdebug_num_hosts) > 0; k++) + stop_all_queued(); + for (; k; k--) sdebug_do_remove_host(true); free_all_queued(); - if (sdebug_verbose) - pr_info("removed %d hosts\n", k); driver_unregister(&sdebug_driverfs_driver); bus_unregister(&pseudo_lld_bus); root_device_unregister(pseudo_primary); @@ -7311,13 +7216,13 @@ static int sdebug_add_host_helper(int per_host_idx) sdbg_host->dev.bus = &pseudo_lld_bus; sdbg_host->dev.parent = pseudo_primary; sdbg_host->dev.release = &sdebug_release_adapter; - dev_set_name(&sdbg_host->dev, "adapter%d", atomic_read(&sdebug_num_hosts)); + dev_set_name(&sdbg_host->dev, "adapter%d", sdebug_num_hosts); error = device_register(&sdbg_host->dev); if (error) goto clean; - atomic_inc(&sdebug_num_hosts); + ++sdebug_num_hosts; return 0; clean: @@ -7381,7 +7286,7 @@ static void sdebug_do_remove_host(bool the_end) return; device_unregister(&sdbg_host->dev); - atomic_dec(&sdebug_num_hosts); + --sdebug_num_hosts; } static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) @@ -7389,10 +7294,10 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) int num_in_q = 0; struct sdebug_dev_info *devip; - sdeb_block_all_queues(); + block_unblock_all_queues(true); devip = (struct sdebug_dev_info *)sdev->hostdata; if (NULL == devip) { - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return -ENODEV; } num_in_q = atomic_read(&devip->num_in_q); @@ -7411,7 +7316,7 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) sdev_printk(KERN_INFO, sdev, "%s: qdepth=%d, num_in_q=%d\n", __func__, qdepth, num_in_q); } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return sdev->queue_depth; } @@ -7519,12 +7424,13 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) struct sdebug_defer *sd_dp; sqp = sdebug_q_arr + queue_num; - qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); - if (qc_idx >= sdebug_max_queue) - return 0; spin_lock_irqsave(&sqp->qc_lock, iflags); + qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); + if (qc_idx >= sdebug_max_queue) + goto unlock; + for (first = true; first || qc_idx + 1 < sdebug_max_queue; ) { if (first) { first = false; @@ -7589,6 +7495,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) break; } +unlock: spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (num_entries > 0) diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c index ff89de86545d..b02af340c2d3 100644 --- a/drivers/scsi/scsi_logging.c +++ b/drivers/scsi/scsi_logging.c @@ -30,7 +30,7 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd) { struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd); - if (!rq->q->disk) + if (!rq->q || !rq->q->disk) return NULL; return rq->q->disk->disk_name; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f4e6c68ac99e..2ef78083f1ef 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -223,6 +223,8 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int ret; struct sbitmap sb_backup; + depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev)); + /* * realloc if new shift is calculated, which is caused by setting * up one new default queue depth after calling ->slave_configure @@ -245,6 +247,9 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, scsi_device_max_queue_depth(sdev), new_shift, GFP_KERNEL, sdev->request_queue->node, false, true); + if (!ret) + sbitmap_resize(&sdev->budget_map, depth); + if (need_free) { if (ret) sdev->budget_map = sb_backup; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 226a50944c00..dc6872e352bd 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1384,10 +1384,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) if (IS_ENABLED(CONFIG_BLK_DEV_BSG)) { sdev->bsg_dev = scsi_bsg_register_queue(sdev); if (IS_ERR(sdev->bsg_dev)) { - /* - * We're treating error on bsg register as non-fatal, so - * pretend nothing went wrong. - */ error = PTR_ERR(sdev->bsg_dev); sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 27951ea05dd4..2c0dd64159b0 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -86,6 +86,9 @@ struct iscsi_internal { struct transport_container session_cont; }; +static DEFINE_IDR(iscsi_ep_idr); +static DEFINE_MUTEX(iscsi_ep_idr_mutex); + static atomic_t iscsi_session_nr; /* sysfs session id for next new session */ static struct workqueue_struct *iscsi_conn_cleanup_workq; @@ -168,6 +171,11 @@ struct device_attribute dev_attr_##_prefix##_##_name = \ static void iscsi_endpoint_release(struct device *dev) { struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); + + mutex_lock(&iscsi_ep_idr_mutex); + idr_remove(&iscsi_ep_idr, ep->id); + mutex_unlock(&iscsi_ep_idr_mutex); + kfree(ep); } @@ -180,7 +188,7 @@ static ssize_t show_ep_handle(struct device *dev, struct device_attribute *attr, char *buf) { struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); - return sysfs_emit(buf, "%llu\n", (unsigned long long) ep->id); + return sysfs_emit(buf, "%d\n", ep->id); } static ISCSI_ATTR(ep, handle, S_IRUGO, show_ep_handle, NULL); @@ -193,48 +201,32 @@ static struct attribute_group iscsi_endpoint_group = { .attrs = iscsi_endpoint_attrs, }; -#define ISCSI_MAX_EPID -1 - -static int iscsi_match_epid(struct device *dev, const void *data) -{ - struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); - const uint64_t *epid = data; - - return *epid == ep->id; -} - struct iscsi_endpoint * iscsi_create_endpoint(int dd_size) { - struct device *dev; struct iscsi_endpoint *ep; - uint64_t id; - int err; - - for (id = 1; id < ISCSI_MAX_EPID; id++) { - dev = class_find_device(&iscsi_endpoint_class, NULL, &id, - iscsi_match_epid); - if (!dev) - break; - else - put_device(dev); - } - if (id == ISCSI_MAX_EPID) { - printk(KERN_ERR "Too many connections. Max supported %u\n", - ISCSI_MAX_EPID - 1); - return NULL; - } + int err, id; ep = kzalloc(sizeof(*ep) + dd_size, GFP_KERNEL); if (!ep) return NULL; + mutex_lock(&iscsi_ep_idr_mutex); + id = idr_alloc(&iscsi_ep_idr, ep, 0, -1, GFP_NOIO); + if (id < 0) { + mutex_unlock(&iscsi_ep_idr_mutex); + printk(KERN_ERR "Could not allocate endpoint ID. Error %d.\n", + id); + goto free_ep; + } + mutex_unlock(&iscsi_ep_idr_mutex); + ep->id = id; ep->dev.class = &iscsi_endpoint_class; - dev_set_name(&ep->dev, "ep-%llu", (unsigned long long) id); + dev_set_name(&ep->dev, "ep-%d", id); err = device_register(&ep->dev); if (err) - goto free_ep; + goto free_id; err = sysfs_create_group(&ep->dev.kobj, &iscsi_endpoint_group); if (err) @@ -248,6 +240,10 @@ unregister_dev: device_unregister(&ep->dev); return NULL; +free_id: + mutex_lock(&iscsi_ep_idr_mutex); + idr_remove(&iscsi_ep_idr, id); + mutex_unlock(&iscsi_ep_idr_mutex); free_ep: kfree(ep); return NULL; @@ -275,14 +271,17 @@ EXPORT_SYMBOL_GPL(iscsi_put_endpoint); */ struct iscsi_endpoint *iscsi_lookup_endpoint(u64 handle) { - struct device *dev; + struct iscsi_endpoint *ep; - dev = class_find_device(&iscsi_endpoint_class, NULL, &handle, - iscsi_match_epid); - if (!dev) - return NULL; + mutex_lock(&iscsi_ep_idr_mutex); + ep = idr_find(&iscsi_ep_idr, handle); + if (!ep) + goto unlock; - return iscsi_dev_to_endpoint(dev); + get_device(&ep->dev); +unlock: + mutex_unlock(&iscsi_ep_idr_mutex); + return ep; } EXPORT_SYMBOL_GPL(iscsi_lookup_endpoint); @@ -2202,10 +2201,10 @@ static void iscsi_stop_conn(struct iscsi_cls_conn *conn, int flag) switch (flag) { case STOP_CONN_RECOVER: - conn->state = ISCSI_CONN_FAILED; + WRITE_ONCE(conn->state, ISCSI_CONN_FAILED); break; case STOP_CONN_TERM: - conn->state = ISCSI_CONN_DOWN; + WRITE_ONCE(conn->state, ISCSI_CONN_DOWN); break; default: iscsi_cls_conn_printk(KERN_ERR, conn, "invalid stop flag %d\n", @@ -2217,6 +2216,49 @@ static void iscsi_stop_conn(struct iscsi_cls_conn *conn, int flag) ISCSI_DBG_TRANS_CONN(conn, "Stopping conn done.\n"); } +static void iscsi_ep_disconnect(struct iscsi_cls_conn *conn, bool is_active) +{ + struct iscsi_cls_session *session = iscsi_conn_to_session(conn); + struct iscsi_endpoint *ep; + + ISCSI_DBG_TRANS_CONN(conn, "disconnect ep.\n"); + WRITE_ONCE(conn->state, ISCSI_CONN_FAILED); + + if (!conn->ep || !session->transport->ep_disconnect) + return; + + ep = conn->ep; + conn->ep = NULL; + + session->transport->unbind_conn(conn, is_active); + session->transport->ep_disconnect(ep); + ISCSI_DBG_TRANS_CONN(conn, "disconnect ep done.\n"); +} + +static void iscsi_if_disconnect_bound_ep(struct iscsi_cls_conn *conn, + struct iscsi_endpoint *ep, + bool is_active) +{ + /* Check if this was a conn error and the kernel took ownership */ + spin_lock_irq(&conn->lock); + if (!test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); + iscsi_ep_disconnect(conn, is_active); + } else { + spin_unlock_irq(&conn->lock); + ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); + mutex_unlock(&conn->ep_mutex); + + flush_work(&conn->cleanup_work); + /* + * Userspace is now done with the EP so we can release the ref + * iscsi_cleanup_conn_work_fn took. + */ + iscsi_put_endpoint(ep); + mutex_lock(&conn->ep_mutex); + } +} + static int iscsi_if_stop_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev) { @@ -2238,11 +2280,24 @@ static int iscsi_if_stop_conn(struct iscsi_transport *transport, iscsi_stop_conn(conn, flag); } else { /* + * For offload, when iscsid is restarted it won't know about + * existing endpoints so it can't do a ep_disconnect. We clean + * it up here for userspace. + */ + mutex_lock(&conn->ep_mutex); + if (conn->ep) + iscsi_if_disconnect_bound_ep(conn, conn->ep, true); + mutex_unlock(&conn->ep_mutex); + + /* * Figure out if it was the kernel or userspace initiating this. */ + spin_lock_irq(&conn->lock); if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); iscsi_stop_conn(conn, flag); } else { + spin_unlock_irq(&conn->lock); ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); flush_work(&conn->cleanup_work); @@ -2251,31 +2306,14 @@ static int iscsi_if_stop_conn(struct iscsi_transport *transport, * Only clear for recovery to avoid extra cleanup runs during * termination. */ + spin_lock_irq(&conn->lock); clear_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags); + spin_unlock_irq(&conn->lock); } ISCSI_DBG_TRANS_CONN(conn, "iscsi if conn stop done.\n"); return 0; } -static void iscsi_ep_disconnect(struct iscsi_cls_conn *conn, bool is_active) -{ - struct iscsi_cls_session *session = iscsi_conn_to_session(conn); - struct iscsi_endpoint *ep; - - ISCSI_DBG_TRANS_CONN(conn, "disconnect ep.\n"); - conn->state = ISCSI_CONN_FAILED; - - if (!conn->ep || !session->transport->ep_disconnect) - return; - - ep = conn->ep; - conn->ep = NULL; - - session->transport->unbind_conn(conn, is_active); - session->transport->ep_disconnect(ep); - ISCSI_DBG_TRANS_CONN(conn, "disconnect ep done.\n"); -} - static void iscsi_cleanup_conn_work_fn(struct work_struct *work) { struct iscsi_cls_conn *conn = container_of(work, struct iscsi_cls_conn, @@ -2284,18 +2322,11 @@ static void iscsi_cleanup_conn_work_fn(struct work_struct *work) mutex_lock(&conn->ep_mutex); /* - * If we are not at least bound there is nothing for us to do. Userspace - * will do a ep_disconnect call if offload is used, but will not be - * doing a stop since there is nothing to clean up, so we have to clear - * the cleanup bit here. + * Get a ref to the ep, so we don't release its ID until after + * userspace is done referencing it in iscsi_if_disconnect_bound_ep. */ - if (conn->state != ISCSI_CONN_BOUND && conn->state != ISCSI_CONN_UP) { - ISCSI_DBG_TRANS_CONN(conn, "Got error while conn is already failed. Ignoring.\n"); - clear_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags); - mutex_unlock(&conn->ep_mutex); - return; - } - + if (conn->ep) + get_device(&conn->ep->dev); iscsi_ep_disconnect(conn, false); if (system_state != SYSTEM_RUNNING) { @@ -2340,11 +2371,12 @@ iscsi_alloc_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid) conn->dd_data = &conn[1]; mutex_init(&conn->ep_mutex); + spin_lock_init(&conn->lock); INIT_LIST_HEAD(&conn->conn_list); INIT_WORK(&conn->cleanup_work, iscsi_cleanup_conn_work_fn); conn->transport = transport; conn->cid = cid; - conn->state = ISCSI_CONN_DOWN; + WRITE_ONCE(conn->state, ISCSI_CONN_DOWN); /* this is released in the dev's release function */ if (!get_device(&session->dev)) @@ -2542,9 +2574,32 @@ void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error) struct iscsi_uevent *ev; struct iscsi_internal *priv; int len = nlmsg_total_size(sizeof(*ev)); + unsigned long flags; + int state; - if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) - queue_work(iscsi_conn_cleanup_workq, &conn->cleanup_work); + spin_lock_irqsave(&conn->lock, flags); + /* + * Userspace will only do a stop call if we are at least bound. And, we + * only need to do the in kernel cleanup if in the UP state so cmds can + * be released to upper layers. If in other states just wait for + * userspace to avoid races that can leave the cleanup_work queued. + */ + state = READ_ONCE(conn->state); + switch (state) { + case ISCSI_CONN_BOUND: + case ISCSI_CONN_UP: + if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, + &conn->flags)) { + queue_work(iscsi_conn_cleanup_workq, + &conn->cleanup_work); + } + break; + default: + ISCSI_DBG_TRANS_CONN(conn, "Got conn error in state %d\n", + state); + break; + } + spin_unlock_irqrestore(&conn->lock, flags); priv = iscsi_if_transport_lookup(conn->transport); if (!priv) @@ -2894,7 +2949,7 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) char *data = (char*)ev + sizeof(*ev); struct iscsi_cls_conn *conn; struct iscsi_cls_session *session; - int err = 0, value = 0; + int err = 0, value = 0, state; if (ev->u.set_param.len > PAGE_SIZE) return -EINVAL; @@ -2911,8 +2966,8 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) session->recovery_tmo = value; break; default: - if ((conn->state == ISCSI_CONN_BOUND) || - (conn->state == ISCSI_CONN_UP)) { + state = READ_ONCE(conn->state); + if (state == ISCSI_CONN_BOUND || state == ISCSI_CONN_UP) { err = transport->set_param(conn, ev->u.set_param.param, data, ev->u.set_param.len); } else { @@ -2984,16 +3039,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport, } mutex_lock(&conn->ep_mutex); - /* Check if this was a conn error and the kernel took ownership */ - if (test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { - ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); - mutex_unlock(&conn->ep_mutex); - - flush_work(&conn->cleanup_work); - goto put_ep; - } - - iscsi_ep_disconnect(conn, false); + iscsi_if_disconnect_bound_ep(conn, ep, false); mutex_unlock(&conn->ep_mutex); put_ep: iscsi_put_endpoint(ep); @@ -3696,24 +3742,17 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, return -EINVAL; mutex_lock(&conn->ep_mutex); + spin_lock_irq(&conn->lock); if (test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); mutex_unlock(&conn->ep_mutex); ev->r.retcode = -ENOTCONN; return 0; } + spin_unlock_irq(&conn->lock); switch (nlh->nlmsg_type) { case ISCSI_UEVENT_BIND_CONN: - if (conn->ep) { - /* - * For offload boot support where iscsid is restarted - * during the pivot root stage, the ep will be intact - * here when the new iscsid instance starts up and - * reconnects. - */ - iscsi_ep_disconnect(conn, true); - } - session = iscsi_session_lookup(ev->u.b_conn.sid); if (!session) { err = -EINVAL; @@ -3724,7 +3763,7 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, ev->u.b_conn.transport_eph, ev->u.b_conn.is_leading); if (!ev->r.retcode) - conn->state = ISCSI_CONN_BOUND; + WRITE_ONCE(conn->state, ISCSI_CONN_BOUND); if (ev->r.retcode || !transport->ep_connect) break; @@ -3743,7 +3782,8 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, case ISCSI_UEVENT_START_CONN: ev->r.retcode = transport->start_conn(conn); if (!ev->r.retcode) - conn->state = ISCSI_CONN_UP; + WRITE_ONCE(conn->state, ISCSI_CONN_UP); + break; case ISCSI_UEVENT_SEND_PDU: pdu_len = nlh->nlmsg_len - sizeof(*nlh) - sizeof(*ev); @@ -4050,10 +4090,11 @@ static ssize_t show_conn_state(struct device *dev, { struct iscsi_cls_conn *conn = iscsi_dev_to_conn(dev->parent); const char *state = "unknown"; + int conn_state = READ_ONCE(conn->state); - if (conn->state >= 0 && - conn->state < ARRAY_SIZE(connection_state_names)) - state = connection_state_names[conn->state]; + if (conn_state >= 0 && + conn_state < ARRAY_SIZE(connection_state_names)) + state = connection_state_names[conn_state]; return sysfs_emit(buf, "%s\n", state); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a390679cf458..dc6e55761fd1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3216,6 +3216,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_block_limits(sdkp); sd_read_block_characteristics(sdkp); sd_zbc_read_zones(sdkp, buffer); + sd_read_cpr(sdkp); } sd_print_capacity(sdkp, old_capacity); @@ -3225,7 +3226,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); - sd_read_cpr(sdkp); } /* @@ -3475,6 +3475,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { put_device(&sdkp->disk_dev); + blk_cleanup_disk(gd); goto out; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 5ba9df334968..cbd92891a762 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -535,7 +535,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, scsi_autopm_get_device(sdev); - if (ret != CDROMCLOSETRAY && ret != CDROMEJECT) { + if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) goto put; diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 0d2e950d0865..586c0e567ff9 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -957,18 +957,6 @@ static const struct reset_control_ops ufs_qcom_reset_ops = { .deassert = ufs_qcom_reset_deassert, }; -#define ANDROID_BOOT_DEV_MAX 30 -static char android_boot_dev[ANDROID_BOOT_DEV_MAX]; - -#ifndef MODULE -static int __init get_android_boot_dev(char *str) -{ - strlcpy(android_boot_dev, str, ANDROID_BOOT_DEV_MAX); - return 1; -} -__setup("androidboot.bootdevice=", get_android_boot_dev); -#endif - /** * ufs_qcom_init - bind phy with controller * @hba: host controller instance @@ -988,9 +976,6 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct resource *res; struct ufs_clk_info *clki; - if (strlen(android_boot_dev) && strcmp(android_boot_dev, dev_name(dev))) - return -ENODEV; - host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) { err = -ENOMEM; diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f76692053ca1..e892b9feffb1 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -428,6 +428,12 @@ static int ufs_intel_adl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mtl_init(struct ufs_hba *hba) +{ + hba->caps |= UFSHCD_CAP_CRYPTO | UFSHCD_CAP_WB_EN; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -465,6 +471,16 @@ static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_mtl_init, + .exit = ufs_intel_common_exit, + .hce_enable_notify = ufs_intel_hce_enable_notify, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -579,6 +595,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x7E47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 88c20f3608c2..94f545be183a 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -820,8 +820,6 @@ struct ufs_hba { enum ufs_pm_level rpm_lvl; /* Desired UFS power management level during system PM */ enum ufs_pm_level spm_lvl; - struct device_attribute rpm_lvl_attr; - struct device_attribute spm_lvl_attr; int pm_op_in_progress; /* Auto-Hibernate Idle Timer register value */ diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index b2bec19022cd..81099b68bbfb 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -867,12 +867,6 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) struct ufshpb_region *rgn, *victim_rgn = NULL; list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) { - if (!rgn) { - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "%s: no region allocated\n", - __func__); - return NULL; - } if (ufshpb_check_srgns_issue_state(hpb, rgn)) continue; @@ -888,6 +882,11 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) break; } + if (!victim_rgn) + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "%s: no region allocated\n", + __func__); + return victim_rgn; } diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 0e6110da69e7..578c4b6d0f7d 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -988,7 +988,7 @@ static struct virtio_driver virtio_scsi_driver = { .remove = virtscsi_remove, }; -static int __init init(void) +static int __init virtio_scsi_init(void) { int ret = -ENOMEM; @@ -1020,14 +1020,14 @@ error: return ret; } -static void __exit fini(void) +static void __exit virtio_scsi_fini(void) { unregister_virtio_driver(&virtio_scsi_driver); mempool_destroy(virtscsi_cmd_pool); kmem_cache_destroy(virtscsi_cmd_cache); } -module_init(init); -module_exit(fini); +module_init(virtio_scsi_init); +module_exit(virtio_scsi_fini); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio SCSI HBA driver"); diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c index 27b9e2baab1a..7acf9193a9e8 100644 --- a/drivers/scsi/zorro7xx.c +++ b/drivers/scsi/zorro7xx.c @@ -159,6 +159,8 @@ static void zorro7xx_remove_one(struct zorro_dev *z) scsi_remove_host(host); NCR_700_release(host); + if (host->base > 0x01000000) + iounmap(hostdata->base); kfree(hostdata); free_irq(host->irq, host); zorro_release_device(z); diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index 92d9610df1fd..938017a60c8e 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -277,6 +277,9 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op) static bool atmel_qspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + if (!spi_mem_default_supports_op(mem, op)) + return false; + if (atmel_qspi_find_mode(op) < 0) return false; diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 86c76211b3d3..cad2d55dcd3d 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1205,7 +1205,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, addr = op->addr.val; len = op->data.nbytes; - if (bcm_qspi_bspi_ver_three(qspi) == true) { + if (has_bspi(qspi) && bcm_qspi_bspi_ver_three(qspi) == true) { /* * The address coming into this function is a raw flash offset. * But for BSPI <= V3, we need to convert it to a remapped BSPI @@ -1224,7 +1224,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, len < 4) mspi_read = true; - if (mspi_read) + if (!has_bspi(qspi) || mspi_read) return bcm_qspi_mspi_exec_mem_op(spi, op); ret = bcm_qspi_bspi_set_mode(qspi, op, 0); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index b0c9f62ccefb..19686fb47bb3 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -19,6 +19,7 @@ #include <linux/iopoll.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/of.h> @@ -102,12 +103,6 @@ struct cqspi_driver_platdata { #define CQSPI_TIMEOUT_MS 500 #define CQSPI_READ_TIMEOUT_MS 10 -/* Instruction type */ -#define CQSPI_INST_TYPE_SINGLE 0 -#define CQSPI_INST_TYPE_DUAL 1 -#define CQSPI_INST_TYPE_QUAD 2 -#define CQSPI_INST_TYPE_OCTAL 3 - #define CQSPI_DUMMY_CLKS_PER_BYTE 8 #define CQSPI_DUMMY_BYTES_MAX 4 #define CQSPI_DUMMY_CLKS_MAX 31 @@ -376,10 +371,6 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, const struct spi_mem_op *op) { - f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - /* * For an op to be DTR, cmd phase along with every other non-empty * phase should have dtr field set to 1. If an op phase has zero @@ -389,32 +380,23 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, (!op->addr.nbytes || op->addr.dtr) && (!op->data.nbytes || op->data.dtr); - switch (op->data.buswidth) { - case 0: - break; - case 1: - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - break; - case 2: - f_pdata->data_width = CQSPI_INST_TYPE_DUAL; - break; - case 4: - f_pdata->data_width = CQSPI_INST_TYPE_QUAD; - break; - case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } + f_pdata->inst_width = 0; + if (op->cmd.buswidth) + f_pdata->inst_width = ilog2(op->cmd.buswidth); + + f_pdata->addr_width = 0; + if (op->addr.buswidth) + f_pdata->addr_width = ilog2(op->addr.buswidth); + + f_pdata->data_width = 0; + if (op->data.buswidth) + f_pdata->data_width = ilog2(op->data.buswidth); /* Right now we only support 8-8-8 DTR mode. */ if (f_pdata->dtr) { switch (op->cmd.buswidth) { case 0: - break; case 8: - f_pdata->inst_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -422,9 +404,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->addr.buswidth) { case 0: - break; case 8: - f_pdata->addr_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -432,9 +412,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->data.buswidth) { case 0: - break; case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -1437,9 +1415,24 @@ static bool cqspi_supports_mem_op(struct spi_mem *mem, all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr && !op->data.dtr; - /* Mixed DTR modes not supported. */ - if (!(all_true || all_false)) + if (all_true) { + /* Right now we only support 8-8-8 DTR mode. */ + if (op->cmd.nbytes && op->cmd.buswidth != 8) + return false; + if (op->addr.nbytes && op->addr.buswidth != 8) + return false; + if (op->data.nbytes && op->data.buswidth != 8) + return false; + } else if (all_false) { + /* Only 1-1-X ops are supported without DTR */ + if (op->cmd.nbytes && op->cmd.buswidth > 1) + return false; + if (op->addr.nbytes && op->addr.buswidth > 1) + return false; + } else { + /* Mixed DTR modes are not supported. */ return false; + } return spi_mem_default_supports_op(mem, op); } diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index a5ef7a526a7f..f6eec7a869b6 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -72,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info }, diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c index 94fb09696677..d167699a1a96 100644 --- a/drivers/spi/spi-mtk-nor.c +++ b/drivers/spi/spi-mtk-nor.c @@ -960,7 +960,17 @@ static int __maybe_unused mtk_nor_suspend(struct device *dev) static int __maybe_unused mtk_nor_resume(struct device *dev) { - return pm_runtime_force_resume(dev); + struct spi_controller *ctlr = dev_get_drvdata(dev); + struct mtk_nor *sp = spi_controller_get_devdata(ctlr); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + mtk_nor_init(sp); + + return 0; } static const struct dev_pm_ops mtk_nor_pm_ops = { diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index 55c092069301..65be8e085ab8 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -813,6 +813,7 @@ static int mxic_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "spi_register_master failed\n"); pm_runtime_disable(&pdev->dev); + mxic_spi_mem_ecc_remove(mxic); } return ret; diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index fe82f3575df4..24ec1c83f379 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -158,14 +158,18 @@ static int rpcif_spi_probe(struct platform_device *pdev) error = rpcif_hw_init(rpc, false); if (error) - return error; + goto out_disable_rpm; error = spi_register_controller(ctlr); if (error) { dev_err(&pdev->dev, "spi_register_controller failed\n"); - rpcif_disable_rpm(rpc); + goto out_disable_rpm; } + return 0; + +out_disable_rpm: + rpcif_disable_rpm(rpc); return error; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c4dd1200fe99..2e6d6bbeb784 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1130,11 +1130,15 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg) if (ctlr->dma_tx) tx_dev = ctlr->dma_tx->device->dev; + else if (ctlr->dma_map_dev) + tx_dev = ctlr->dma_map_dev; else tx_dev = ctlr->dev.parent; if (ctlr->dma_rx) rx_dev = ctlr->dma_rx->device->dev; + else if (ctlr->dma_map_dev) + rx_dev = ctlr->dma_map_dev; else rx_dev = ctlr->dev.parent; @@ -2406,7 +2410,8 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data) } else { struct acpi_device *adev; - if (acpi_bus_get_device(parent_handle, &adev)) + adev = acpi_fetch_acpi_dev(parent_handle); + if (!adev) return -ENODEV; ctlr = acpi_spi_find_controller_by_adev(adev); diff --git a/drivers/staging/r8188eu/core/rtw_br_ext.c b/drivers/staging/r8188eu/core/rtw_br_ext.c index d68611ef22f8..f056204c0fdb 100644 --- a/drivers/staging/r8188eu/core/rtw_br_ext.c +++ b/drivers/staging/r8188eu/core/rtw_br_ext.c @@ -70,7 +70,7 @@ static int __nat25_add_pppoe_tag(struct sk_buff *skb, struct pppoe_tag *tag) struct pppoe_hdr *ph = (struct pppoe_hdr *)(skb->data + ETH_HLEN); int data_len; - data_len = tag->tag_len + TAG_HDR_LEN; + data_len = be16_to_cpu(tag->tag_len) + TAG_HDR_LEN; if (skb_tailroom(skb) < data_len) return -1; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 95d4ca50a605..fd7267baa707 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1821,6 +1821,7 @@ static struct page *tcmu_try_get_data_page(struct tcmu_dev *udev, uint32_t dpi) mutex_lock(&udev->cmdr_lock); page = xa_load(&udev->data_pages, dpi); if (likely(page)) { + get_page(page); mutex_unlock(&udev->cmdr_lock); return page; } @@ -1877,6 +1878,7 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) /* For the vmalloc()ed cmd area pages */ addr = (void *)(unsigned long)info->mem[mi].addr + offset; page = vmalloc_to_page(addr); + get_page(page); } else { uint32_t dpi; @@ -1887,7 +1889,6 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - get_page(page); vmf->page = page; return 0; } diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c index 8a6958377764..3acc0f185762 100644 --- a/drivers/tty/serial/mpc52xx_uart.c +++ b/drivers/tty/serial/mpc52xx_uart.c @@ -436,31 +436,31 @@ static void mpc512x_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_512x(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc512x_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc512x_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc512x_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->rxsr) & in_be32(&FIFO_512x(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & in_be32(&FIFO_512x(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_empty(struct uart_port *port) +static unsigned int mpc512x_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; @@ -780,29 +780,29 @@ static void mpc5125_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_5125(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc5125_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc5125_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc5125_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->rxsr) & in_be32(&FIFO_5125(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & in_be32(&FIFO_5125(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_empty(struct uart_port *port) +static unsigned int mpc5125_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; } diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c index 7d41dfe48ade..48c4dadb0c7c 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.c +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -10,45 +10,29 @@ #include "ifcvf_base.h" -static inline u8 ifc_ioread8(u8 __iomem *addr) -{ - return ioread8(addr); -} -static inline u16 ifc_ioread16 (__le16 __iomem *addr) +struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw) { - return ioread16(addr); + return container_of(hw, struct ifcvf_adapter, vf); } -static inline u32 ifc_ioread32(__le32 __iomem *addr) +u16 ifcvf_set_vq_vector(struct ifcvf_hw *hw, u16 qid, int vector) { - return ioread32(addr); -} + struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg; -static inline void ifc_iowrite8(u8 value, u8 __iomem *addr) -{ - iowrite8(value, addr); -} + vp_iowrite16(qid, &cfg->queue_select); + vp_iowrite16(vector, &cfg->queue_msix_vector); -static inline void ifc_iowrite16(u16 value, __le16 __iomem *addr) -{ - iowrite16(value, addr); + return vp_ioread16(&cfg->queue_msix_vector); } -static inline void ifc_iowrite32(u32 value, __le32 __iomem *addr) +u16 ifcvf_set_config_vector(struct ifcvf_hw *hw, int vector) { - iowrite32(value, addr); -} + struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg; -static void ifc_iowrite64_twopart(u64 val, - __le32 __iomem *lo, __le32 __iomem *hi) -{ - ifc_iowrite32((u32)val, lo); - ifc_iowrite32(val >> 32, hi); -} + cfg = hw->common_cfg; + vp_iowrite16(vector, &cfg->msix_config); -struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw) -{ - return container_of(hw, struct ifcvf_adapter, vf); + return vp_ioread16(&cfg->msix_config); } static void __iomem *get_cap_addr(struct ifcvf_hw *hw, @@ -158,15 +142,16 @@ next: return -EIO; } - hw->nr_vring = ifc_ioread16(&hw->common_cfg->num_queues); + hw->nr_vring = vp_ioread16(&hw->common_cfg->num_queues); for (i = 0; i < hw->nr_vring; i++) { - ifc_iowrite16(i, &hw->common_cfg->queue_select); - notify_off = ifc_ioread16(&hw->common_cfg->queue_notify_off); + vp_iowrite16(i, &hw->common_cfg->queue_select); + notify_off = vp_ioread16(&hw->common_cfg->queue_notify_off); hw->vring[i].notify_addr = hw->notify_base + notify_off * hw->notify_off_multiplier; hw->vring[i].notify_pa = hw->notify_base_pa + notify_off * hw->notify_off_multiplier; + hw->vring[i].irq = -EINVAL; } hw->lm_cfg = hw->base[IFCVF_LM_BAR]; @@ -176,17 +161,20 @@ next: hw->common_cfg, hw->notify_base, hw->isr, hw->dev_cfg, hw->notify_off_multiplier); + hw->vqs_reused_irq = -EINVAL; + hw->config_irq = -EINVAL; + return 0; } u8 ifcvf_get_status(struct ifcvf_hw *hw) { - return ifc_ioread8(&hw->common_cfg->device_status); + return vp_ioread8(&hw->common_cfg->device_status); } void ifcvf_set_status(struct ifcvf_hw *hw, u8 status) { - ifc_iowrite8(status, &hw->common_cfg->device_status); + vp_iowrite8(status, &hw->common_cfg->device_status); } void ifcvf_reset(struct ifcvf_hw *hw) @@ -214,11 +202,11 @@ u64 ifcvf_get_hw_features(struct ifcvf_hw *hw) u32 features_lo, features_hi; u64 features; - ifc_iowrite32(0, &cfg->device_feature_select); - features_lo = ifc_ioread32(&cfg->device_feature); + vp_iowrite32(0, &cfg->device_feature_select); + features_lo = vp_ioread32(&cfg->device_feature); - ifc_iowrite32(1, &cfg->device_feature_select); - features_hi = ifc_ioread32(&cfg->device_feature); + vp_iowrite32(1, &cfg->device_feature_select); + features_hi = vp_ioread32(&cfg->device_feature); features = ((u64)features_hi << 32) | features_lo; @@ -271,12 +259,12 @@ void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset, WARN_ON(offset + length > hw->config_size); do { - old_gen = ifc_ioread8(&hw->common_cfg->config_generation); + old_gen = vp_ioread8(&hw->common_cfg->config_generation); p = dst; for (i = 0; i < length; i++) - *p++ = ifc_ioread8(hw->dev_cfg + offset + i); + *p++ = vp_ioread8(hw->dev_cfg + offset + i); - new_gen = ifc_ioread8(&hw->common_cfg->config_generation); + new_gen = vp_ioread8(&hw->common_cfg->config_generation); } while (old_gen != new_gen); } @@ -289,18 +277,18 @@ void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset, p = src; WARN_ON(offset + length > hw->config_size); for (i = 0; i < length; i++) - ifc_iowrite8(*p++, hw->dev_cfg + offset + i); + vp_iowrite8(*p++, hw->dev_cfg + offset + i); } static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features) { struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg; - ifc_iowrite32(0, &cfg->guest_feature_select); - ifc_iowrite32((u32)features, &cfg->guest_feature); + vp_iowrite32(0, &cfg->guest_feature_select); + vp_iowrite32((u32)features, &cfg->guest_feature); - ifc_iowrite32(1, &cfg->guest_feature_select); - ifc_iowrite32(features >> 32, &cfg->guest_feature); + vp_iowrite32(1, &cfg->guest_feature_select); + vp_iowrite32(features >> 32, &cfg->guest_feature); } static int ifcvf_config_features(struct ifcvf_hw *hw) @@ -329,7 +317,7 @@ u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid) ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; q_pair_id = qid / hw->nr_vring; avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2]; - last_avail_idx = ifc_ioread16(avail_idx_addr); + last_avail_idx = vp_ioread16(avail_idx_addr); return last_avail_idx; } @@ -344,7 +332,7 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num) q_pair_id = qid / hw->nr_vring; avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2]; hw->vring[qid].last_avail_idx = num; - ifc_iowrite16(num, avail_idx_addr); + vp_iowrite16(num, avail_idx_addr); return 0; } @@ -352,41 +340,23 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num) static int ifcvf_hw_enable(struct ifcvf_hw *hw) { struct virtio_pci_common_cfg __iomem *cfg; - struct ifcvf_adapter *ifcvf; u32 i; - ifcvf = vf_to_adapter(hw); cfg = hw->common_cfg; - ifc_iowrite16(IFCVF_MSI_CONFIG_OFF, &cfg->msix_config); - - if (ifc_ioread16(&cfg->msix_config) == VIRTIO_MSI_NO_VECTOR) { - IFCVF_ERR(ifcvf->pdev, "No msix vector for device config\n"); - return -EINVAL; - } - for (i = 0; i < hw->nr_vring; i++) { if (!hw->vring[i].ready) break; - ifc_iowrite16(i, &cfg->queue_select); - ifc_iowrite64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo, + vp_iowrite16(i, &cfg->queue_select); + vp_iowrite64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo, &cfg->queue_desc_hi); - ifc_iowrite64_twopart(hw->vring[i].avail, &cfg->queue_avail_lo, + vp_iowrite64_twopart(hw->vring[i].avail, &cfg->queue_avail_lo, &cfg->queue_avail_hi); - ifc_iowrite64_twopart(hw->vring[i].used, &cfg->queue_used_lo, + vp_iowrite64_twopart(hw->vring[i].used, &cfg->queue_used_lo, &cfg->queue_used_hi); - ifc_iowrite16(hw->vring[i].size, &cfg->queue_size); - ifc_iowrite16(i + IFCVF_MSI_QUEUE_OFF, &cfg->queue_msix_vector); - - if (ifc_ioread16(&cfg->queue_msix_vector) == - VIRTIO_MSI_NO_VECTOR) { - IFCVF_ERR(ifcvf->pdev, - "No msix vector for queue %u\n", i); - return -EINVAL; - } - + vp_iowrite16(hw->vring[i].size, &cfg->queue_size); ifcvf_set_vq_state(hw, i, hw->vring[i].last_avail_idx); - ifc_iowrite16(1, &cfg->queue_enable); + vp_iowrite16(1, &cfg->queue_enable); } return 0; @@ -394,18 +364,12 @@ static int ifcvf_hw_enable(struct ifcvf_hw *hw) static void ifcvf_hw_disable(struct ifcvf_hw *hw) { - struct virtio_pci_common_cfg __iomem *cfg; u32 i; - cfg = hw->common_cfg; - ifc_iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->msix_config); - + ifcvf_set_config_vector(hw, VIRTIO_MSI_NO_VECTOR); for (i = 0; i < hw->nr_vring; i++) { - ifc_iowrite16(i, &cfg->queue_select); - ifc_iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->queue_msix_vector); + ifcvf_set_vq_vector(hw, i, VIRTIO_MSI_NO_VECTOR); } - - ifc_ioread16(&cfg->queue_msix_vector); } int ifcvf_start_hw(struct ifcvf_hw *hw) @@ -433,5 +397,5 @@ void ifcvf_stop_hw(struct ifcvf_hw *hw) void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid) { - ifc_iowrite16(qid, hw->vring[qid].notify_addr); + vp_iowrite16(qid, hw->vring[qid].notify_addr); } diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h index c486873f370a..115b61f4924b 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.h +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -14,6 +14,7 @@ #include <linux/pci.h> #include <linux/pci_regs.h> #include <linux/vdpa.h> +#include <linux/virtio_pci_modern.h> #include <uapi/linux/virtio_net.h> #include <uapi/linux/virtio_blk.h> #include <uapi/linux/virtio_config.h> @@ -27,8 +28,6 @@ #define IFCVF_QUEUE_ALIGNMENT PAGE_SIZE #define IFCVF_QUEUE_MAX 32768 -#define IFCVF_MSI_CONFIG_OFF 0 -#define IFCVF_MSI_QUEUE_OFF 1 #define IFCVF_PCI_MAX_RESOURCE 6 #define IFCVF_LM_CFG_SIZE 0x40 @@ -42,6 +41,13 @@ #define ifcvf_private_to_vf(adapter) \ (&((struct ifcvf_adapter *)adapter)->vf) +/* all vqs and config interrupt has its own vector */ +#define MSIX_VECTOR_PER_VQ_AND_CONFIG 1 +/* all vqs share a vector, and config interrupt has a separate vector */ +#define MSIX_VECTOR_SHARED_VQ_AND_CONFIG 2 +/* all vqs and config interrupt share a vector */ +#define MSIX_VECTOR_DEV_SHARED 3 + struct vring_info { u64 desc; u64 avail; @@ -60,25 +66,27 @@ struct ifcvf_hw { u8 __iomem *isr; /* Live migration */ u8 __iomem *lm_cfg; - u16 nr_vring; /* Notification bar number */ u8 notify_bar; + u8 msix_vector_status; + /* virtio-net or virtio-blk device config size */ + u32 config_size; /* Notificaiton bar address */ void __iomem *notify_base; phys_addr_t notify_base_pa; u32 notify_off_multiplier; + u32 dev_type; u64 req_features; u64 hw_features; - u32 dev_type; struct virtio_pci_common_cfg __iomem *common_cfg; void __iomem *dev_cfg; struct vring_info vring[IFCVF_MAX_QUEUES]; void __iomem * const *base; char config_msix_name[256]; struct vdpa_callback config_cb; - unsigned int config_irq; - /* virtio-net or virtio-blk device config size */ - u32 config_size; + int config_irq; + int vqs_reused_irq; + u16 nr_vring; }; struct ifcvf_adapter { @@ -123,4 +131,6 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num); struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw); int ifcvf_probed_virtio_net(struct ifcvf_hw *hw); u32 ifcvf_get_config_size(struct ifcvf_hw *hw); +u16 ifcvf_set_vq_vector(struct ifcvf_hw *hw, u16 qid, int vector); +u16 ifcvf_set_config_vector(struct ifcvf_hw *hw, int vector); #endif /* _IFCVF_H_ */ diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index d1a6b5ab543c..4366320fb68d 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -27,7 +27,7 @@ static irqreturn_t ifcvf_config_changed(int irq, void *arg) return IRQ_HANDLED; } -static irqreturn_t ifcvf_intr_handler(int irq, void *arg) +static irqreturn_t ifcvf_vq_intr_handler(int irq, void *arg) { struct vring_info *vring = arg; @@ -37,76 +37,324 @@ static irqreturn_t ifcvf_intr_handler(int irq, void *arg) return IRQ_HANDLED; } +static irqreturn_t ifcvf_vqs_reused_intr_handler(int irq, void *arg) +{ + struct ifcvf_hw *vf = arg; + struct vring_info *vring; + int i; + + for (i = 0; i < vf->nr_vring; i++) { + vring = &vf->vring[i]; + if (vring->cb.callback) + vring->cb.callback(vring->cb.private); + } + + return IRQ_HANDLED; +} + +static irqreturn_t ifcvf_dev_intr_handler(int irq, void *arg) +{ + struct ifcvf_hw *vf = arg; + u8 isr; + + isr = vp_ioread8(vf->isr); + if (isr & VIRTIO_PCI_ISR_CONFIG) + ifcvf_config_changed(irq, arg); + + return ifcvf_vqs_reused_intr_handler(irq, arg); +} + static void ifcvf_free_irq_vectors(void *data) { pci_free_irq_vectors(data); } -static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues) +static void ifcvf_free_per_vq_irq(struct ifcvf_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct ifcvf_hw *vf = &adapter->vf; int i; + for (i = 0; i < vf->nr_vring; i++) { + if (vf->vring[i].irq != -EINVAL) { + devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]); + vf->vring[i].irq = -EINVAL; + } + } +} - for (i = 0; i < queues; i++) { - devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]); - vf->vring[i].irq = -EINVAL; +static void ifcvf_free_vqs_reused_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + + if (vf->vqs_reused_irq != -EINVAL) { + devm_free_irq(&pdev->dev, vf->vqs_reused_irq, vf); + vf->vqs_reused_irq = -EINVAL; } - devm_free_irq(&pdev->dev, vf->config_irq, vf); +} + +static void ifcvf_free_vq_irq(struct ifcvf_adapter *adapter) +{ + struct ifcvf_hw *vf = &adapter->vf; + + if (vf->msix_vector_status == MSIX_VECTOR_PER_VQ_AND_CONFIG) + ifcvf_free_per_vq_irq(adapter); + else + ifcvf_free_vqs_reused_irq(adapter); +} + +static void ifcvf_free_config_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + + if (vf->config_irq == -EINVAL) + return; + + /* If the irq is shared by all vqs and the config interrupt, + * it is already freed in ifcvf_free_vq_irq, so here only + * need to free config irq when msix_vector_status != MSIX_VECTOR_DEV_SHARED + */ + if (vf->msix_vector_status != MSIX_VECTOR_DEV_SHARED) { + devm_free_irq(&pdev->dev, vf->config_irq, vf); + vf->config_irq = -EINVAL; + } +} + +static void ifcvf_free_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + + ifcvf_free_vq_irq(adapter); + ifcvf_free_config_irq(adapter); ifcvf_free_irq_vectors(pdev); } -static int ifcvf_request_irq(struct ifcvf_adapter *adapter) +/* ifcvf MSIX vectors allocator, this helper tries to allocate + * vectors for all virtqueues and the config interrupt. + * It returns the number of allocated vectors, negative + * return value when fails. + */ +static int ifcvf_alloc_vectors(struct ifcvf_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct ifcvf_hw *vf = &adapter->vf; - int vector, i, ret, irq; - u16 max_intr; + int max_intr, ret; /* all queues and config interrupt */ max_intr = vf->nr_vring + 1; + ret = pci_alloc_irq_vectors(pdev, 1, max_intr, PCI_IRQ_MSIX | PCI_IRQ_AFFINITY); - ret = pci_alloc_irq_vectors(pdev, max_intr, - max_intr, PCI_IRQ_MSIX); if (ret < 0) { IFCVF_ERR(pdev, "Failed to alloc IRQ vectors\n"); return ret; } + if (ret < max_intr) + IFCVF_INFO(pdev, + "Requested %u vectors, however only %u allocated, lower performance\n", + max_intr, ret); + + return ret; +} + +static int ifcvf_request_per_vq_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int i, vector, ret, irq; + + vf->vqs_reused_irq = -EINVAL; + for (i = 0; i < vf->nr_vring; i++) { + snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", pci_name(pdev), i); + vector = i; + irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, irq, + ifcvf_vq_intr_handler, 0, + vf->vring[i].msix_name, + &vf->vring[i]); + if (ret) { + IFCVF_ERR(pdev, "Failed to request irq for vq %d\n", i); + goto err; + } + + vf->vring[i].irq = irq; + ret = ifcvf_set_vq_vector(vf, i, vector); + if (ret == VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(pdev, "No msix vector for vq %u\n", i); + goto err; + } + } + + return 0; +err: + ifcvf_free_irq(adapter); + + return -EFAULT; +} + +static int ifcvf_request_vqs_reused_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int i, vector, ret, irq; + + vector = 0; + snprintf(vf->vring[0].msix_name, 256, "ifcvf[%s]-vqs-reused-irq\n", pci_name(pdev)); + irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, irq, + ifcvf_vqs_reused_intr_handler, 0, + vf->vring[0].msix_name, vf); + if (ret) { + IFCVF_ERR(pdev, "Failed to request reused irq for the device\n"); + goto err; + } + + vf->vqs_reused_irq = irq; + for (i = 0; i < vf->nr_vring; i++) { + vf->vring[i].irq = -EINVAL; + ret = ifcvf_set_vq_vector(vf, i, vector); + if (ret == VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(pdev, "No msix vector for vq %u\n", i); + goto err; + } + } + + return 0; +err: + ifcvf_free_irq(adapter); + + return -EFAULT; +} + +static int ifcvf_request_dev_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int i, vector, ret, irq; + + vector = 0; + snprintf(vf->vring[0].msix_name, 256, "ifcvf[%s]-dev-irq\n", pci_name(pdev)); + irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, irq, + ifcvf_dev_intr_handler, 0, + vf->vring[0].msix_name, vf); + if (ret) { + IFCVF_ERR(pdev, "Failed to request irq for the device\n"); + goto err; + } + + vf->vqs_reused_irq = irq; + for (i = 0; i < vf->nr_vring; i++) { + vf->vring[i].irq = -EINVAL; + ret = ifcvf_set_vq_vector(vf, i, vector); + if (ret == VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(pdev, "No msix vector for vq %u\n", i); + goto err; + } + } + + vf->config_irq = irq; + ret = ifcvf_set_config_vector(vf, vector); + if (ret == VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(pdev, "No msix vector for device config\n"); + goto err; + } + + return 0; +err: + ifcvf_free_irq(adapter); + + return -EFAULT; + +} + +static int ifcvf_request_vq_irq(struct ifcvf_adapter *adapter) +{ + struct ifcvf_hw *vf = &adapter->vf; + int ret; + + if (vf->msix_vector_status == MSIX_VECTOR_PER_VQ_AND_CONFIG) + ret = ifcvf_request_per_vq_irq(adapter); + else + ret = ifcvf_request_vqs_reused_irq(adapter); + + return ret; +} + +static int ifcvf_request_config_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int config_vector, ret; + + if (vf->msix_vector_status == MSIX_VECTOR_DEV_SHARED) + return 0; + + if (vf->msix_vector_status == MSIX_VECTOR_PER_VQ_AND_CONFIG) + /* vector 0 ~ vf->nr_vring for vqs, num vf->nr_vring vector for config interrupt */ + config_vector = vf->nr_vring; + + if (vf->msix_vector_status == MSIX_VECTOR_SHARED_VQ_AND_CONFIG) + /* vector 0 for vqs and 1 for config interrupt */ + config_vector = 1; + snprintf(vf->config_msix_name, 256, "ifcvf[%s]-config\n", pci_name(pdev)); - vector = 0; - vf->config_irq = pci_irq_vector(pdev, vector); + vf->config_irq = pci_irq_vector(pdev, config_vector); ret = devm_request_irq(&pdev->dev, vf->config_irq, ifcvf_config_changed, 0, vf->config_msix_name, vf); if (ret) { IFCVF_ERR(pdev, "Failed to request config irq\n"); - return ret; + goto err; } - for (i = 0; i < vf->nr_vring; i++) { - snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", - pci_name(pdev), i); - vector = i + IFCVF_MSI_QUEUE_OFF; - irq = pci_irq_vector(pdev, vector); - ret = devm_request_irq(&pdev->dev, irq, - ifcvf_intr_handler, 0, - vf->vring[i].msix_name, - &vf->vring[i]); - if (ret) { - IFCVF_ERR(pdev, - "Failed to request irq for vq %d\n", i); - ifcvf_free_irq(adapter, i); + ret = ifcvf_set_config_vector(vf, config_vector); + if (ret == VIRTIO_MSI_NO_VECTOR) { + IFCVF_ERR(pdev, "No msix vector for device config\n"); + goto err; + } - return ret; - } + return 0; +err: + ifcvf_free_irq(adapter); - vf->vring[i].irq = irq; + return -EFAULT; +} + +static int ifcvf_request_irq(struct ifcvf_adapter *adapter) +{ + struct ifcvf_hw *vf = &adapter->vf; + int nvectors, ret, max_intr; + + nvectors = ifcvf_alloc_vectors(adapter); + if (nvectors <= 0) + return -EFAULT; + + vf->msix_vector_status = MSIX_VECTOR_PER_VQ_AND_CONFIG; + max_intr = vf->nr_vring + 1; + if (nvectors < max_intr) + vf->msix_vector_status = MSIX_VECTOR_SHARED_VQ_AND_CONFIG; + + if (nvectors == 1) { + vf->msix_vector_status = MSIX_VECTOR_DEV_SHARED; + ret = ifcvf_request_dev_irq(adapter); + + return ret; } + ret = ifcvf_request_vq_irq(adapter); + if (ret) + return ret; + + ret = ifcvf_request_config_irq(adapter); + + if (ret) + return ret; + return 0; } @@ -263,7 +511,7 @@ static int ifcvf_vdpa_reset(struct vdpa_device *vdpa_dev) if (status_old & VIRTIO_CONFIG_S_DRIVER_OK) { ifcvf_stop_datapath(adapter); - ifcvf_free_irq(adapter, vf->nr_vring); + ifcvf_free_irq(adapter); } ifcvf_reset_vring(adapter); @@ -348,7 +596,7 @@ static u32 ifcvf_vdpa_get_generation(struct vdpa_device *vdpa_dev) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - return ioread8(&vf->common_cfg->config_generation); + return vp_ioread8(&vf->common_cfg->config_generation); } static u32 ifcvf_vdpa_get_device_id(struct vdpa_device *vdpa_dev) @@ -410,7 +658,10 @@ static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev, { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); - return vf->vring[qid].irq; + if (vf->vqs_reused_irq < 0) + return vf->vring[qid].irq; + else + return -EINVAL; } static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_device *vdpa_dev, diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index d0f91078600e..79001301b383 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -163,6 +163,7 @@ struct mlx5_vdpa_net { u32 cur_num_vqs; struct notifier_block nb; struct vdpa_callback config_cb; + struct mlx5_vdpa_wq_ent cvq_ent; }; static void free_resources(struct mlx5_vdpa_net *ndev); @@ -1475,7 +1476,7 @@ static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd) virtio_net_ctrl_ack status = VIRTIO_NET_ERR; struct mlx5_core_dev *pfmdev; size_t read; - u8 mac[ETH_ALEN]; + u8 mac[ETH_ALEN], mac_back[ETH_ALEN]; pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev)); switch (cmd) { @@ -1489,6 +1490,9 @@ static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd) break; } + if (is_zero_ether_addr(mac)) + break; + if (!is_zero_ether_addr(ndev->config.mac)) { if (mlx5_mpfs_del_mac(pfmdev, ndev->config.mac)) { mlx5_vdpa_warn(mvdev, "failed to delete old MAC %pM from MPFS table\n", @@ -1503,7 +1507,47 @@ static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd) break; } + /* backup the original mac address so that if failed to add the forward rules + * we could restore it + */ + memcpy(mac_back, ndev->config.mac, ETH_ALEN); + memcpy(ndev->config.mac, mac, ETH_ALEN); + + /* Need recreate the flow table entry, so that the packet could forward back + */ + remove_fwd_to_tir(ndev); + + if (add_fwd_to_tir(ndev)) { + mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n"); + + /* Although it hardly run here, we still need double check */ + if (is_zero_ether_addr(mac_back)) { + mlx5_vdpa_warn(mvdev, "restore mac failed: Original MAC is zero\n"); + break; + } + + /* Try to restore original mac address to MFPS table, and try to restore + * the forward rule entry. + */ + if (mlx5_mpfs_del_mac(pfmdev, ndev->config.mac)) { + mlx5_vdpa_warn(mvdev, "restore mac failed: delete MAC %pM from MPFS table failed\n", + ndev->config.mac); + } + + if (mlx5_mpfs_add_mac(pfmdev, mac_back)) { + mlx5_vdpa_warn(mvdev, "restore mac failed: insert old MAC %pM into MPFS table failed\n", + mac_back); + } + + memcpy(ndev->config.mac, mac_back, ETH_ALEN); + + if (add_fwd_to_tir(ndev)) + mlx5_vdpa_warn(mvdev, "restore forward rules failed: insert forward rules failed\n"); + + break; + } + status = VIRTIO_NET_OK; break; @@ -1615,6 +1659,12 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) mvdev = wqent->mvdev; ndev = to_mlx5_vdpa_ndev(mvdev); cvq = &mvdev->cvq; + + mutex_lock(&ndev->reslock); + + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) goto out; @@ -1653,9 +1703,13 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) if (vringh_need_notify_iotlb(&cvq->vring)) vringh_notify(&cvq->vring); + + queue_work(mvdev->wq, &wqent->work); + break; } + out: - kfree(wqent); + mutex_unlock(&ndev->reslock); } static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) @@ -1663,22 +1717,15 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - struct mlx5_vdpa_wq_ent *wqent; if (!is_index_valid(mvdev, idx)) return; if (unlikely(is_ctrl_vq_idx(mvdev, idx))) { - if (!mvdev->cvq.ready) - return; - - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) + if (!mvdev->wq || !mvdev->cvq.ready) return; - wqent->mvdev = mvdev; - INIT_WORK(&wqent->work, mlx5_cvq_kick_handler); - queue_work(mvdev->wq, &wqent->work); + queue_work(mvdev->wq, &ndev->cvq_ent.work); return; } @@ -2137,7 +2184,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb goto err_mr; if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) - return 0; + goto err_mr; restore_channels_info(ndev); err = setup_driver(mvdev); @@ -2152,12 +2199,14 @@ err_mr: return err; } +/* reslock must be held for this function */ static int setup_driver(struct mlx5_vdpa_dev *mvdev) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); int err; - mutex_lock(&ndev->reslock); + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (ndev->setup) { mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n"); err = 0; @@ -2187,7 +2236,6 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) goto err_fwd; } ndev->setup = true; - mutex_unlock(&ndev->reslock); return 0; @@ -2198,23 +2246,23 @@ err_tir: err_rqt: teardown_virtqueues(ndev); out: - mutex_unlock(&ndev->reslock); return err; } +/* reslock must be held for this function */ static void teardown_driver(struct mlx5_vdpa_net *ndev) { - mutex_lock(&ndev->reslock); + + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (!ndev->setup) - goto out; + return; remove_fwd_to_tir(ndev); destroy_tir(ndev); destroy_rqt(ndev); teardown_virtqueues(ndev); ndev->setup = false; -out: - mutex_unlock(&ndev->reslock); } static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) @@ -2235,6 +2283,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) print_status(mvdev, status, true); + mutex_lock(&ndev->reslock); + if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { if (status & VIRTIO_CONFIG_S_DRIVER_OK) { err = setup_driver(mvdev); @@ -2244,16 +2294,19 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); - return; + goto err_clear; } } ndev->mvdev.status = status; + mutex_unlock(&ndev->reslock); return; err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; +err_clear: + mutex_unlock(&ndev->reslock); } static int mlx5_vdpa_reset(struct vdpa_device *vdev) @@ -2263,6 +2316,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) print_status(mvdev, 0, true); mlx5_vdpa_info(mvdev, "performing device reset\n"); + + mutex_lock(&ndev->reslock); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2275,6 +2330,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) if (mlx5_vdpa_create_mr(mvdev, NULL)) mlx5_vdpa_warn(mvdev, "create MR failed\n"); } + mutex_unlock(&ndev->reslock); return 0; } @@ -2310,19 +2366,24 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); bool change_map; int err; + mutex_lock(&ndev->reslock); + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); if (err) { mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); - return err; + goto err; } if (change_map) - return mlx5_vdpa_change_map(mvdev, iotlb); + err = mlx5_vdpa_change_map(mvdev, iotlb); - return 0; +err: + mutex_unlock(&ndev->reslock); + return err; } static void mlx5_vdpa_free(struct vdpa_device *vdev) @@ -2565,6 +2626,28 @@ static int event_handler(struct notifier_block *nb, unsigned long event, void *p return ret; } +static int config_func_mtu(struct mlx5_core_dev *mdev, u16 mtu) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); + void *in; + int err; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_nic_vport_context_in, in, field_select.mtu, 1); + MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.mtu, + mtu + MLX5V_ETH_HARD_MTU); + MLX5_SET(modify_nic_vport_context_in, in, opcode, + MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT); + + err = mlx5_cmd_exec_in(mdev, modify_nic_vport_context, in); + + kvfree(in); + return err; +} + static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, const struct vdpa_dev_set_config *add_config) { @@ -2624,6 +2707,13 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, init_mvqs(ndev); mutex_init(&ndev->reslock); config = &ndev->config; + + if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU)) { + err = config_func_mtu(mdev, add_config->net.mtu); + if (err) + goto err_mtu; + } + err = query_mtu(mdev, &mtu); if (err) goto err_mtu; @@ -2668,6 +2758,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_mr; + ndev->cvq_ent.mvdev = mvdev; + INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler); mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq"); if (!mvdev->wq) { err = -ENOMEM; @@ -2707,9 +2799,12 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device * struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev); struct mlx5_vdpa_dev *mvdev = to_mvdev(dev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); + struct workqueue_struct *wq; mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); - destroy_workqueue(mvdev->wq); + wq = mvdev->wq; + mvdev->wq = NULL; + destroy_workqueue(wq); _vdpa_unregister_device(dev); mgtdev->ndev = NULL; } @@ -2741,7 +2836,8 @@ static int mlx5v_probe(struct auxiliary_device *adev, mgtdev->mgtdev.device = mdev->device; mgtdev->mgtdev.id_table = id_table; mgtdev->mgtdev.config_attr_mask = BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | - BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP); + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP) | + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU); mgtdev->mgtdev.max_supported_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues) + 1; mgtdev->mgtdev.supported_features = get_supported_features(mdev); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 1ea525433a5c..2b75c00b1005 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -232,7 +232,7 @@ static int vdpa_name_match(struct device *dev, const void *data) return (strcmp(dev_name(&vdev->dev), data) == 0); } -static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs) +static int __vdpa_register_device(struct vdpa_device *vdev, u32 nvqs) { struct device *dev; @@ -257,7 +257,7 @@ static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs) * * Return: Returns an error when fail to add device to vDPA bus */ -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs) +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs) { if (!vdev->mdev) return -EINVAL; @@ -274,7 +274,7 @@ EXPORT_SYMBOL_GPL(_vdpa_register_device); * * Return: Returns an error when fail to add to vDPA bus */ -int vdpa_register_device(struct vdpa_device *vdev, int nvqs) +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs) { int err; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index b7bb16f92ac6..06b6f3594a13 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -36,6 +36,10 @@ static bool nointxmask; static bool disable_vga; static bool disable_idle_d3; +/* List of PF's that vfio_pci_core_sriov_configure() has been called on */ +static DEFINE_MUTEX(vfio_pci_sriov_pfs_mutex); +static LIST_HEAD(vfio_pci_sriov_pfs); + static inline bool vfio_vga_disabled(void) { #ifdef CONFIG_VFIO_PCI_VGA @@ -434,47 +438,17 @@ out: } EXPORT_SYMBOL_GPL(vfio_pci_core_disable); -static struct vfio_pci_core_device *get_pf_vdev(struct vfio_pci_core_device *vdev) -{ - struct pci_dev *physfn = pci_physfn(vdev->pdev); - struct vfio_device *pf_dev; - - if (!vdev->pdev->is_virtfn) - return NULL; - - pf_dev = vfio_device_get_from_dev(&physfn->dev); - if (!pf_dev) - return NULL; - - if (pci_dev_driver(physfn) != pci_dev_driver(vdev->pdev)) { - vfio_device_put(pf_dev); - return NULL; - } - - return container_of(pf_dev, struct vfio_pci_core_device, vdev); -} - -static void vfio_pci_vf_token_user_add(struct vfio_pci_core_device *vdev, int val) -{ - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); - - if (!pf_vdev) - return; - - mutex_lock(&pf_vdev->vf_token->lock); - pf_vdev->vf_token->users += val; - WARN_ON(pf_vdev->vf_token->users < 0); - mutex_unlock(&pf_vdev->vf_token->lock); - - vfio_device_put(&pf_vdev->vdev); -} - void vfio_pci_core_close_device(struct vfio_device *core_vdev) { struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); - vfio_pci_vf_token_user_add(vdev, -1); + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + WARN_ON(!vdev->sriov_pf_core_dev->vf_token->users); + vdev->sriov_pf_core_dev->vf_token->users--; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_core_disable(vdev); @@ -495,7 +469,12 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) { vfio_pci_probe_mmaps(vdev); vfio_spapr_pci_eeh_open(vdev->pdev); - vfio_pci_vf_token_user_add(vdev, 1); + + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + vdev->sriov_pf_core_dev->vf_token->users++; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } } EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); @@ -1583,11 +1562,8 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, * * If the VF token is provided but unused, an error is generated. */ - if (!vdev->pdev->is_virtfn && !vdev->vf_token && !vf_token) - return 0; /* No VF token provided or required */ - if (vdev->pdev->is_virtfn) { - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); + struct vfio_pci_core_device *pf_vdev = vdev->sriov_pf_core_dev; bool match; if (!pf_vdev) { @@ -1600,7 +1576,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, } if (!vf_token) { - vfio_device_put(&pf_vdev->vdev); pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); return -EACCES; @@ -1610,8 +1585,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, match = uuid_equal(uuid, &pf_vdev->vf_token->uuid); mutex_unlock(&pf_vdev->vf_token->lock); - vfio_device_put(&pf_vdev->vdev); - if (!match) { pci_info_ratelimited(vdev->pdev, "Incorrect VF token provided for device\n"); @@ -1732,8 +1705,30 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb, static int vfio_pci_vf_init(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_core_device *cur; + struct pci_dev *physfn; int ret; + if (pdev->is_virtfn) { + /* + * If this VF was created by our vfio_pci_core_sriov_configure() + * then we can find the PF vfio_pci_core_device now, and due to + * the locking in pci_disable_sriov() it cannot change until + * this VF device driver is removed. + */ + physfn = pci_physfn(vdev->pdev); + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_for_each_entry(cur, &vfio_pci_sriov_pfs, sriov_pfs_item) { + if (cur->pdev == physfn) { + vdev->sriov_pf_core_dev = cur; + break; + } + } + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + return 0; + } + + /* Not a SRIOV PF */ if (!pdev->is_physfn) return 0; @@ -1805,6 +1800,7 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, INIT_LIST_HEAD(&vdev->ioeventfds_list); mutex_init(&vdev->vma_lock); INIT_LIST_HEAD(&vdev->vma_list); + INIT_LIST_HEAD(&vdev->sriov_pfs_item); init_rwsem(&vdev->memory_lock); } EXPORT_SYMBOL_GPL(vfio_pci_core_init_device); @@ -1896,7 +1892,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; - pci_disable_sriov(pdev); + vfio_pci_core_sriov_configure(pdev, 0); vfio_unregister_group_dev(&vdev->vdev); @@ -1935,21 +1931,49 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected); int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) { + struct vfio_pci_core_device *vdev; struct vfio_device *device; int ret = 0; + device_lock_assert(&pdev->dev); + device = vfio_device_get_from_dev(&pdev->dev); if (!device) return -ENODEV; - if (nr_virtfn == 0) - pci_disable_sriov(pdev); - else + vdev = container_of(device, struct vfio_pci_core_device, vdev); + + if (nr_virtfn) { + mutex_lock(&vfio_pci_sriov_pfs_mutex); + /* + * The thread that adds the vdev to the list is the only thread + * that gets to call pci_enable_sriov() and we will only allow + * it to be called once without going through + * pci_disable_sriov() + */ + if (!list_empty(&vdev->sriov_pfs_item)) { + ret = -EINVAL; + goto out_unlock; + } + list_add_tail(&vdev->sriov_pfs_item, &vfio_pci_sriov_pfs); + mutex_unlock(&vfio_pci_sriov_pfs_mutex); ret = pci_enable_sriov(pdev, nr_virtfn); + if (ret) + goto out_del; + ret = nr_virtfn; + goto out_put; + } - vfio_device_put(device); + pci_disable_sriov(pdev); - return ret < 0 ? ret : nr_virtfn; +out_del: + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_del_init(&vdev->sriov_pfs_item); +out_unlock: + mutex_unlock(&vfio_pci_sriov_pfs_mutex); +out_put: + vfio_device_put(device); + return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index 40b098320b2a..5829cf2d0552 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -62,8 +62,12 @@ int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, */ if (start == 0 && last == ULONG_MAX) { u64 mid = last / 2; + int err = vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, + perm, opaque); + + if (err) + return err; - vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, perm, opaque); addr += mid + 1; start = mid + 1; } diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ec5249e8c32d..4c2f0bd06285 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -42,7 +42,7 @@ struct vhost_vdpa { struct device dev; struct cdev cdev; atomic_t opened; - int nvqs; + u32 nvqs; int virtio_id; int minor; struct eventfd_ctx *config_ctx; @@ -97,8 +97,11 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid) return; irq = ops->get_vq_irq(vdpa, qid); + if (irq < 0) + return; + irq_bypass_unregister_producer(&vq->call_ctx.producer); - if (!vq->call_ctx.ctx || irq < 0) + if (!vq->call_ctx.ctx) return; vq->call_ctx.producer.token = vq->call_ctx.ctx; @@ -158,7 +161,8 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; u8 status, status_old; - int ret, nvqs = v->nvqs; + u32 nvqs = v->nvqs; + int ret; u16 i; if (copy_from_user(&status, statusp, sizeof(status))) @@ -355,6 +359,30 @@ static long vhost_vdpa_get_iova_range(struct vhost_vdpa *v, u32 __user *argp) return 0; } +static long vhost_vdpa_get_config_size(struct vhost_vdpa *v, u32 __user *argp) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + u32 size; + + size = ops->get_config_size(vdpa); + + if (copy_to_user(argp, &size, sizeof(size))) + return -EFAULT; + + return 0; +} + +static long vhost_vdpa_get_vqs_count(struct vhost_vdpa *v, u32 __user *argp) +{ + struct vdpa_device *vdpa = v->vdpa; + + if (copy_to_user(argp, &vdpa->nvqs, sizeof(vdpa->nvqs))) + return -EFAULT; + + return 0; +} + static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -492,6 +520,12 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_GET_IOVA_RANGE: r = vhost_vdpa_get_iova_range(v, argp); break; + case VHOST_VDPA_GET_CONFIG_SIZE: + r = vhost_vdpa_get_config_size(v, argp); + break; + case VHOST_VDPA_GET_VQS_COUNT: + r = vhost_vdpa_get_vqs_count(v, argp); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) @@ -948,7 +982,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) struct vhost_vdpa *v; struct vhost_dev *dev; struct vhost_virtqueue **vqs; - int nvqs, i, r, opened; + int r, opened; + u32 i, nvqs; v = container_of(inode->i_cdev, struct vhost_vdpa, cdev); @@ -1001,7 +1036,7 @@ err: static void vhost_vdpa_clean_irq(struct vhost_vdpa *v) { - int i; + u32 i; for (i = 0; i < v->nvqs; i++) vhost_vdpa_unsetup_vq_irq(v, i); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 1768362115c6..d02173fb290c 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2550,8 +2550,9 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) &vq->avail->idx, r); return false; } + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); - return vhost16_to_cpu(vq, avail_idx) != vq->avail_idx; + return vq->avail_idx != vq->last_avail_idx; } EXPORT_SYMBOL_GPL(vhost_enable_notify); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 34d6bb1bf82e..a6bb0e438216 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1579,7 +1579,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a, * If it's not a platform device, at least print a warning. A * fix would add code to remove the device from the system. */ - if (dev_is_platform(device)) { + if (!device) { + /* TODO: Represent each OF framebuffer as its own + * device in the device hierarchy. For now, offb + * doesn't have such a device, so unregister the + * framebuffer as before without warning. + */ + do_unregister_framebuffer(registered_fb[i]); + } else if (dev_is_platform(device)) { registered_fb[i]->forced_out = true; platform_device_unregister(to_platform_device(device)); } else { diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c index 0ae1a39f2e28..a1c467a0e9f7 100644 --- a/drivers/virt/vmgenid.c +++ b/drivers/virt/vmgenid.c @@ -78,6 +78,7 @@ static void vmgenid_notify(struct acpi_device *device, u32 event) } static const struct acpi_device_id vmgenid_ids[] = { + { "VMGENCTR", 0 }, { "VM_GEN_COUNTER", 0 }, { } }; diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 492fc26f0b65..b5adf6abd241 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -105,7 +105,7 @@ config VIRTIO_BALLOON config VIRTIO_MEM tristate "Virtio mem driver" - depends on X86_64 + depends on X86_64 || ARM64 depends on VIRTIO depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE @@ -115,8 +115,9 @@ config VIRTIO_MEM This driver provides access to virtio-mem paravirtualized memory devices, allowing to hotplug and hotunplug memory. - This driver was only tested under x86-64, but should theoretically - work on all architectures that support memory hotplug and hotremove. + This driver was only tested under x86-64 and arm64, but should + theoretically work on all architectures that support memory hotplug + and hotremove. If unsure, say M. diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index fdbde1db5ec5..d724f676608b 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -24,46 +24,17 @@ MODULE_PARM_DESC(force_legacy, "Force legacy mode for transitional virtio 1 devices"); #endif -/* disable irq handlers */ -void vp_disable_cbs(struct virtio_device *vdev) +/* wait for pending irq handlers */ +void vp_synchronize_vectors(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i; - if (vp_dev->intx_enabled) { - /* - * The below synchronize() guarantees that any - * interrupt for this line arriving after - * synchronize_irq() has completed is guaranteed to see - * intx_soft_enabled == false. - */ - WRITE_ONCE(vp_dev->intx_soft_enabled, false); + if (vp_dev->intx_enabled) synchronize_irq(vp_dev->pci_dev->irq); - } - - for (i = 0; i < vp_dev->msix_vectors; ++i) - disable_irq(pci_irq_vector(vp_dev->pci_dev, i)); -} - -/* enable irq handlers */ -void vp_enable_cbs(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - int i; - - if (vp_dev->intx_enabled) { - disable_irq(vp_dev->pci_dev->irq); - /* - * The above disable_irq() provides TSO ordering and - * as such promotes the below store to store-release. - */ - WRITE_ONCE(vp_dev->intx_soft_enabled, true); - enable_irq(vp_dev->pci_dev->irq); - return; - } for (i = 0; i < vp_dev->msix_vectors; ++i) - enable_irq(pci_irq_vector(vp_dev->pci_dev, i)); + synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i)); } /* the notify function used when creating a virt queue */ @@ -113,9 +84,6 @@ static irqreturn_t vp_interrupt(int irq, void *opaque) struct virtio_pci_device *vp_dev = opaque; u8 isr; - if (!READ_ONCE(vp_dev->intx_soft_enabled)) - return IRQ_NONE; - /* reading the ISR has the effect of also clearing it so it's very * important to save off the value. */ isr = ioread8(vp_dev->isr); @@ -173,8 +141,7 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, "%s-config", name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), - vp_config_changed, IRQF_NO_AUTOEN, - vp_dev->msix_names[v], + vp_config_changed, 0, vp_dev->msix_names[v], vp_dev); if (err) goto error; @@ -193,8 +160,7 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, "%s-virtqueues", name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), - vp_vring_interrupt, IRQF_NO_AUTOEN, - vp_dev->msix_names[v], + vp_vring_interrupt, 0, vp_dev->msix_names[v], vp_dev); if (err) goto error; @@ -371,7 +337,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs, "%s-%s", dev_name(&vp_dev->vdev.dev), names[i]); err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), - vring_interrupt, IRQF_NO_AUTOEN, + vring_interrupt, 0, vp_dev->msix_names[msix_vec], vqs[i]); if (err) diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 23f6c5c678d5..eb17a29fc7ef 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -63,7 +63,6 @@ struct virtio_pci_device { /* MSI-X support */ int msix_enabled; int intx_enabled; - bool intx_soft_enabled; cpumask_var_t *msix_affinity_masks; /* Name strings for interrupts. This size should be enough, * and I'm too lazy to allocate each name separately. */ @@ -102,10 +101,8 @@ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev) return container_of(vdev, struct virtio_pci_device, vdev); } -/* disable irq handlers */ -void vp_disable_cbs(struct virtio_device *vdev); -/* enable irq handlers */ -void vp_enable_cbs(struct virtio_device *vdev); +/* wait for pending irq handlers */ +void vp_synchronize_vectors(struct virtio_device *vdev); /* the notify function used when creating a virt queue */ bool vp_notify(struct virtqueue *vq); /* the config->del_vqs() implementation */ diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index 34141b9abe27..6f4e34ce96b8 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -98,8 +98,8 @@ static void vp_reset(struct virtio_device *vdev) /* Flush out the status write, and flush in device writes, * including MSi-X interrupts, if any. */ vp_legacy_get_status(&vp_dev->ldev); - /* Disable VQ/configuration callbacks. */ - vp_disable_cbs(vdev); + /* Flush pending VQ/configuration callbacks. */ + vp_synchronize_vectors(vdev); } static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) @@ -185,7 +185,6 @@ static void del_vq(struct virtio_pci_vq_info *info) } static const struct virtio_config_ops virtio_pci_config_ops = { - .enable_cbs = vp_enable_cbs, .get = vp_get, .set = vp_set, .get_status = vp_get_status, diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 5455bc041fb6..a2671a20ef77 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -172,8 +172,8 @@ static void vp_reset(struct virtio_device *vdev) */ while (vp_modern_get_status(mdev)) msleep(1); - /* Disable VQ/configuration callbacks. */ - vp_disable_cbs(vdev); + /* Flush pending VQ/configuration callbacks. */ + vp_synchronize_vectors(vdev); } static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) @@ -293,7 +293,7 @@ static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id, for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0; pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) { - u8 type, cap_len, id; + u8 type, cap_len, id, res_bar; u32 tmp32; u64 res_offset, res_length; @@ -315,9 +315,14 @@ static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id, if (id != required_id) continue; - /* Type, and ID match, looks good */ pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap, - bar), bar); + bar), &res_bar); + if (res_bar >= PCI_STD_NUM_BARS) + continue; + + /* Type and ID match, and the BAR value isn't reserved. + * Looks good. + */ /* Read the lower 32bit of length and offset */ pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap, @@ -337,6 +342,7 @@ static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id, length_hi), &tmp32); res_length |= ((u64)tmp32) << 32; + *bar = res_bar; *offset = res_offset; *len = res_length; @@ -380,7 +386,6 @@ static bool vp_get_shm_region(struct virtio_device *vdev, } static const struct virtio_config_ops virtio_pci_config_nodev_ops = { - .enable_cbs = vp_enable_cbs, .get = NULL, .set = NULL, .generation = vp_generation, @@ -398,7 +403,6 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { }; static const struct virtio_config_ops virtio_pci_config_ops = { - .enable_cbs = vp_enable_cbs, .get = vp_get, .set = vp_set, .generation = vp_generation, diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index e8b3ff2b9fbc..591738ad3d56 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -35,6 +35,13 @@ vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length), &length); + /* Check if the BAR may have changed since we requested the region. */ + if (bar >= PCI_STD_NUM_BARS || !(mdev->modern_bars & (1 << bar))) { + dev_err(&dev->dev, + "virtio_pci: bar unexpectedly changed to %u\n", bar); + return NULL; + } + if (length <= start) { dev_err(&dev->dev, "virtio_pci: bad capability len %u (>%u expected)\n", @@ -120,7 +127,7 @@ static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, &bar); /* Ignore structures with reserved BAR values */ - if (bar > 0x5) + if (bar >= PCI_STD_NUM_BARS) continue; if (type == cfg_type) { diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 962f1477b1fa..cfb028ca238e 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -379,19 +379,11 @@ static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq, flags = virtio16_to_cpu(vq->vq.vdev, desc->flags); - if (flags & VRING_DESC_F_INDIRECT) { - dma_unmap_single(vring_dma_dev(vq), - virtio64_to_cpu(vq->vq.vdev, desc->addr), - virtio32_to_cpu(vq->vq.vdev, desc->len), - (flags & VRING_DESC_F_WRITE) ? - DMA_FROM_DEVICE : DMA_TO_DEVICE); - } else { - dma_unmap_page(vring_dma_dev(vq), - virtio64_to_cpu(vq->vq.vdev, desc->addr), - virtio32_to_cpu(vq->vq.vdev, desc->len), - (flags & VRING_DESC_F_WRITE) ? - DMA_FROM_DEVICE : DMA_TO_DEVICE); - } + dma_unmap_page(vring_dma_dev(vq), + virtio64_to_cpu(vq->vq.vdev, desc->addr), + virtio32_to_cpu(vq->vq.vdev, desc->len), + (flags & VRING_DESC_F_WRITE) ? + DMA_FROM_DEVICE : DMA_TO_DEVICE); } static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq, @@ -984,24 +976,24 @@ static struct virtqueue *vring_create_virtqueue_split( * Packed ring specific functions - *_packed(). */ -static void vring_unmap_state_packed(const struct vring_virtqueue *vq, - struct vring_desc_extra *state) +static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, + struct vring_desc_extra *extra) { u16 flags; if (!vq->use_dma_api) return; - flags = state->flags; + flags = extra->flags; if (flags & VRING_DESC_F_INDIRECT) { dma_unmap_single(vring_dma_dev(vq), - state->addr, state->len, + extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } else { dma_unmap_page(vring_dma_dev(vq), - state->addr, state->len, + extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } @@ -1017,19 +1009,11 @@ static void vring_unmap_desc_packed(const struct vring_virtqueue *vq, flags = le16_to_cpu(desc->flags); - if (flags & VRING_DESC_F_INDIRECT) { - dma_unmap_single(vring_dma_dev(vq), - le64_to_cpu(desc->addr), - le32_to_cpu(desc->len), - (flags & VRING_DESC_F_WRITE) ? - DMA_FROM_DEVICE : DMA_TO_DEVICE); - } else { - dma_unmap_page(vring_dma_dev(vq), - le64_to_cpu(desc->addr), - le32_to_cpu(desc->len), - (flags & VRING_DESC_F_WRITE) ? - DMA_FROM_DEVICE : DMA_TO_DEVICE); - } + dma_unmap_page(vring_dma_dev(vq), + le64_to_cpu(desc->addr), + le32_to_cpu(desc->len), + (flags & VRING_DESC_F_WRITE) ? + DMA_FROM_DEVICE : DMA_TO_DEVICE); } static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg, @@ -1303,8 +1287,7 @@ unmap_release: for (n = 0; n < total_sg; n++) { if (i == err_idx) break; - vring_unmap_state_packed(vq, - &vq->packed.desc_extra[curr]); + vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; i++; if (i >= vq->packed.vring.num) @@ -1383,8 +1366,8 @@ static void detach_buf_packed(struct vring_virtqueue *vq, if (unlikely(vq->use_dma_api)) { curr = id; for (i = 0; i < state->num; i++) { - vring_unmap_state_packed(vq, - &vq->packed.desc_extra[curr]); + vring_unmap_extra_packed(vq, + &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; } } diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 085f5a4ad06c..c4e82a8d863f 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1779,7 +1779,7 @@ config BCM7038_WDT tristate "BCM63xx/BCM7038 Watchdog" select WATCHDOG_CORE depends on HAS_IOMEM - depends on ARCH_BRCMSTB || BMIPS_GENERIC || BCM63XX || COMPILE_TEST + depends on ARCH_BCM4908 || ARCH_BRCMSTB || BMIPS_GENERIC || BCM63XX || COMPILE_TEST help Watchdog driver for the built-in hardware in Broadcom 7038 and later SoCs used in set-top boxes. BCM7038 was made public diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c index 436571b6fc79..bd06622813eb 100644 --- a/drivers/watchdog/aspeed_wdt.c +++ b/drivers/watchdog/aspeed_wdt.c @@ -13,6 +13,11 @@ #include <linux/platform_device.h> #include <linux/watchdog.h> +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, 0); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + struct aspeed_wdt { struct watchdog_device wdd; void __iomem *base; @@ -266,6 +271,8 @@ static int aspeed_wdt_probe(struct platform_device *pdev) wdt->wdd.timeout = WDT_DEFAULT_TIMEOUT; watchdog_init_timeout(&wdt->wdd, 0, dev); + watchdog_set_nowayout(&wdt->wdd, nowayout); + np = dev->of_node; ofdid = of_match_node(aspeed_wdt_of_table, np); diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c index 51bfb796898b..d0c5d47ddede 100644 --- a/drivers/watchdog/imx2_wdt.c +++ b/drivers/watchdog/imx2_wdt.c @@ -66,6 +66,7 @@ struct imx2_wdt_device { struct watchdog_device wdog; bool ext_reset; bool clk_is_on; + bool no_ping; }; static bool nowayout = WATCHDOG_NOWAYOUT; @@ -312,12 +313,18 @@ static int __init imx2_wdt_probe(struct platform_device *pdev) wdev->ext_reset = of_property_read_bool(dev->of_node, "fsl,ext-reset-output"); + /* + * The i.MX7D doesn't support low power mode, so we need to ping the watchdog + * during suspend. + */ + wdev->no_ping = !of_device_is_compatible(dev->of_node, "fsl,imx7d-wdt"); platform_set_drvdata(pdev, wdog); watchdog_set_drvdata(wdog, wdev); watchdog_set_nowayout(wdog, nowayout); watchdog_set_restart_priority(wdog, 128); watchdog_init_timeout(wdog, timeout, dev); - watchdog_stop_ping_on_suspend(wdog); + if (wdev->no_ping) + watchdog_stop_ping_on_suspend(wdog); if (imx2_wdt_is_running(wdev)) { imx2_wdt_set_timeout(wdog, wdog->timeout); @@ -366,9 +373,11 @@ static int __maybe_unused imx2_wdt_suspend(struct device *dev) imx2_wdt_ping(wdog); } - clk_disable_unprepare(wdev->clk); + if (wdev->no_ping) { + clk_disable_unprepare(wdev->clk); - wdev->clk_is_on = false; + wdev->clk_is_on = false; + } return 0; } @@ -380,11 +389,14 @@ static int __maybe_unused imx2_wdt_resume(struct device *dev) struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog); int ret; - ret = clk_prepare_enable(wdev->clk); - if (ret) - return ret; + if (wdev->no_ping) { + ret = clk_prepare_enable(wdev->clk); - wdev->clk_is_on = true; + if (ret) + return ret; + + wdev->clk_is_on = true; + } if (watchdog_active(wdog) && !imx2_wdt_is_running(wdev)) { /* @@ -407,6 +419,7 @@ static SIMPLE_DEV_PM_OPS(imx2_wdt_pm_ops, imx2_wdt_suspend, static const struct of_device_id imx2_wdt_dt_ids[] = { { .compatible = "fsl,imx21-wdt", }, + { .compatible = "fsl,imx7d-wdt", }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, imx2_wdt_dt_ids); diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c index 31b03fa71341..281a48d9889f 100644 --- a/drivers/watchdog/ixp4xx_wdt.c +++ b/drivers/watchdog/ixp4xx_wdt.c @@ -84,10 +84,24 @@ static int ixp4xx_wdt_set_timeout(struct watchdog_device *wdd, return 0; } +static int ixp4xx_wdt_restart(struct watchdog_device *wdd, + unsigned long action, void *data) +{ + struct ixp4xx_wdt *iwdt = to_ixp4xx_wdt(wdd); + + __raw_writel(IXP4XX_WDT_KEY, iwdt->base + IXP4XX_OSWK_OFFSET); + __raw_writel(0, iwdt->base + IXP4XX_OSWT_OFFSET); + __raw_writel(IXP4XX_WDT_COUNT_ENABLE | IXP4XX_WDT_RESET_ENABLE, + iwdt->base + IXP4XX_OSWE_OFFSET); + + return 0; +} + static const struct watchdog_ops ixp4xx_wdt_ops = { .start = ixp4xx_wdt_start, .stop = ixp4xx_wdt_stop, .set_timeout = ixp4xx_wdt_set_timeout, + .restart = ixp4xx_wdt_restart, .owner = THIS_MODULE, }; diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c index 127eefc9161d..e25e6bf4647f 100644 --- a/drivers/watchdog/orion_wdt.c +++ b/drivers/watchdog/orion_wdt.c @@ -238,8 +238,10 @@ static int armada370_start(struct watchdog_device *wdt_dev) atomic_io_modify(dev->reg + TIMER_A370_STATUS, WDT_A370_EXPIRED, 0); /* Enable watchdog timer */ - atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, - dev->data->wdt_enable_bit); + reg = dev->data->wdt_enable_bit; + if (dev->wdt.info->options & WDIOF_PRETIMEOUT) + reg |= TIMER1_ENABLE_BIT; + atomic_io_modify(dev->reg + TIMER_CTRL, reg, reg); /* Enable reset on watchdog */ reg = readl(dev->rstout); @@ -312,7 +314,7 @@ static int armada375_stop(struct watchdog_device *wdt_dev) static int armada370_stop(struct watchdog_device *wdt_dev) { struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev); - u32 reg; + u32 reg, mask; /* Disable reset on watchdog */ reg = readl(dev->rstout); @@ -320,7 +322,10 @@ static int armada370_stop(struct watchdog_device *wdt_dev) writel(reg, dev->rstout); /* Disable watchdog timer */ - atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, 0); + mask = dev->data->wdt_enable_bit; + if (wdt_dev->info->options & WDIOF_PRETIMEOUT) + mask |= TIMER1_ENABLE_BIT; + atomic_io_modify(dev->reg + TIMER_CTRL, mask, 0); return 0; } diff --git a/drivers/watchdog/renesas_wdt.c b/drivers/watchdog/renesas_wdt.c index 5791198960e6..41d58ea5eb2f 100644 --- a/drivers/watchdog/renesas_wdt.c +++ b/drivers/watchdog/renesas_wdt.c @@ -327,6 +327,7 @@ static SIMPLE_DEV_PM_OPS(rwdt_pm_ops, rwdt_suspend, rwdt_resume); static const struct of_device_id rwdt_ids[] = { { .compatible = "renesas,rcar-gen2-wdt", }, { .compatible = "renesas,rcar-gen3-wdt", }, + { .compatible = "renesas,rcar-gen4-wdt", }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, rwdt_ids); diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c index 117bc2a8eb0a..db843f825860 100644 --- a/drivers/watchdog/rti_wdt.c +++ b/drivers/watchdog/rti_wdt.c @@ -228,6 +228,7 @@ static int rti_wdt_probe(struct platform_device *pdev) ret = pm_runtime_get_sync(dev); if (ret) { pm_runtime_put_noidle(dev); + pm_runtime_disable(&pdev->dev); return dev_err_probe(dev, ret, "runtime pm failed\n"); } diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index dd9a744f82f8..86ffb58fbc85 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -49,7 +49,7 @@ /* internal variables */ enum tco_reg_layout { - sp5100, sb800, efch + sp5100, sb800, efch, efch_mmio }; struct sp5100_tco { @@ -87,6 +87,10 @@ static enum tco_reg_layout tco_reg_layout(struct pci_dev *dev) dev->revision < 0x40) { return sp5100; } else if (dev->vendor == PCI_VENDOR_ID_AMD && + sp5100_tco_pci->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && + sp5100_tco_pci->revision >= AMD_ZEN_SMBUS_PCI_REV) { + return efch_mmio; + } else if (dev->vendor == PCI_VENDOR_ID_AMD && ((dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS && dev->revision >= 0x41) || (dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && @@ -209,6 +213,8 @@ static void tco_timer_enable(struct sp5100_tco *tco) ~EFCH_PM_WATCHDOG_DISABLE, EFCH_PM_DECODEEN_SECOND_RES); break; + default: + break; } } @@ -223,14 +229,195 @@ static u32 sp5100_tco_read_pm_reg32(u8 index) return val; } +static u32 sp5100_tco_request_region(struct device *dev, + u32 mmio_addr, + const char *dev_name) +{ + if (!devm_request_mem_region(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE, + dev_name)) { + dev_dbg(dev, "MMIO address 0x%08x already in use\n", mmio_addr); + return 0; + } + + return mmio_addr; +} + +static u32 sp5100_tco_prepare_base(struct sp5100_tco *tco, + u32 mmio_addr, + u32 alt_mmio_addr, + const char *dev_name) +{ + struct device *dev = tco->wdd.parent; + + dev_dbg(dev, "Got 0x%08x from SBResource_MMIO register\n", mmio_addr); + + if (!mmio_addr && !alt_mmio_addr) + return -ENODEV; + + /* Check for MMIO address and alternate MMIO address conflicts */ + if (mmio_addr) + mmio_addr = sp5100_tco_request_region(dev, mmio_addr, dev_name); + + if (!mmio_addr && alt_mmio_addr) + mmio_addr = sp5100_tco_request_region(dev, alt_mmio_addr, dev_name); + + if (!mmio_addr) { + dev_err(dev, "Failed to reserve MMIO or alternate MMIO region\n"); + return -EBUSY; + } + + tco->tcobase = devm_ioremap(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE); + if (!tco->tcobase) { + dev_err(dev, "MMIO address 0x%08x failed mapping\n", mmio_addr); + devm_release_mem_region(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE); + return -ENOMEM; + } + + dev_info(dev, "Using 0x%08x for watchdog MMIO address\n", mmio_addr); + + return 0; +} + +static int sp5100_tco_timer_init(struct sp5100_tco *tco) +{ + struct watchdog_device *wdd = &tco->wdd; + struct device *dev = wdd->parent; + u32 val; + + val = readl(SP5100_WDT_CONTROL(tco->tcobase)); + if (val & SP5100_WDT_DISABLED) { + dev_err(dev, "Watchdog hardware is disabled\n"); + return -ENODEV; + } + + /* + * Save WatchDogFired status, because WatchDogFired flag is + * cleared here. + */ + if (val & SP5100_WDT_FIRED) + wdd->bootstatus = WDIOF_CARDRESET; + + /* Set watchdog action to reset the system */ + val &= ~SP5100_WDT_ACTION_RESET; + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + + /* Set a reasonable heartbeat before we stop the timer */ + tco_timer_set_timeout(wdd, wdd->timeout); + + /* + * Stop the TCO before we change anything so we don't race with + * a zeroed timer. + */ + tco_timer_stop(wdd); + + return 0; +} + +static u8 efch_read_pm_reg8(void __iomem *addr, u8 index) +{ + return readb(addr + index); +} + +static void efch_update_pm_reg8(void __iomem *addr, u8 index, u8 reset, u8 set) +{ + u8 val; + + val = readb(addr + index); + val &= reset; + val |= set; + writeb(val, addr + index); +} + +static void tco_timer_enable_mmio(void __iomem *addr) +{ + efch_update_pm_reg8(addr, EFCH_PM_DECODEEN3, + ~EFCH_PM_WATCHDOG_DISABLE, + EFCH_PM_DECODEEN_SECOND_RES); +} + +static int sp5100_tco_setupdevice_mmio(struct device *dev, + struct watchdog_device *wdd) +{ + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); + const char *dev_name = SB800_DEVNAME; + u32 mmio_addr = 0, alt_mmio_addr = 0; + struct resource *res; + void __iomem *addr; + int ret; + u32 val; + + res = request_mem_region_muxed(EFCH_PM_ACPI_MMIO_PM_ADDR, + EFCH_PM_ACPI_MMIO_PM_SIZE, + "sp5100_tco"); + + if (!res) { + dev_err(dev, + "Memory region 0x%08x already in use\n", + EFCH_PM_ACPI_MMIO_PM_ADDR); + return -EBUSY; + } + + addr = ioremap(EFCH_PM_ACPI_MMIO_PM_ADDR, EFCH_PM_ACPI_MMIO_PM_SIZE); + if (!addr) { + dev_err(dev, "Address mapping failed\n"); + ret = -ENOMEM; + goto out; + } + + /* + * EFCH_PM_DECODEEN_WDT_TMREN is dual purpose. This bitfield + * enables sp5100_tco register MMIO space decoding. The bitfield + * also starts the timer operation. Enable if not already enabled. + */ + val = efch_read_pm_reg8(addr, EFCH_PM_DECODEEN); + if (!(val & EFCH_PM_DECODEEN_WDT_TMREN)) { + efch_update_pm_reg8(addr, EFCH_PM_DECODEEN, 0xff, + EFCH_PM_DECODEEN_WDT_TMREN); + } + + /* Error if the timer could not be enabled */ + val = efch_read_pm_reg8(addr, EFCH_PM_DECODEEN); + if (!(val & EFCH_PM_DECODEEN_WDT_TMREN)) { + dev_err(dev, "Failed to enable the timer\n"); + ret = -EFAULT; + goto out; + } + + mmio_addr = EFCH_PM_WDT_ADDR; + + /* Determine alternate MMIO base address */ + val = efch_read_pm_reg8(addr, EFCH_PM_ISACONTROL); + if (val & EFCH_PM_ISACONTROL_MMIOEN) + alt_mmio_addr = EFCH_PM_ACPI_MMIO_ADDR + + EFCH_PM_ACPI_MMIO_WDT_OFFSET; + + ret = sp5100_tco_prepare_base(tco, mmio_addr, alt_mmio_addr, dev_name); + if (!ret) { + tco_timer_enable_mmio(addr); + ret = sp5100_tco_timer_init(tco); + } + +out: + if (addr) + iounmap(addr); + + release_resource(res); + + return ret; +} + static int sp5100_tco_setupdevice(struct device *dev, struct watchdog_device *wdd) { struct sp5100_tco *tco = watchdog_get_drvdata(wdd); const char *dev_name; u32 mmio_addr = 0, val; + u32 alt_mmio_addr = 0; int ret; + if (tco->tco_reg_layout == efch_mmio) + return sp5100_tco_setupdevice_mmio(dev, wdd); + /* Request the IO ports used by this driver */ if (!request_muxed_region(SP5100_IO_PM_INDEX_REG, SP5100_PM_IOPORTS_SIZE, "sp5100_tco")) { @@ -247,138 +434,55 @@ static int sp5100_tco_setupdevice(struct device *dev, dev_name = SP5100_DEVNAME; mmio_addr = sp5100_tco_read_pm_reg32(SP5100_PM_WATCHDOG_BASE) & 0xfffffff8; + + /* + * Secondly, find the watchdog timer MMIO address + * from SBResource_MMIO register. + */ + + /* Read SBResource_MMIO from PCI config(PCI_Reg: 9Ch) */ + pci_read_config_dword(sp5100_tco_pci, + SP5100_SB_RESOURCE_MMIO_BASE, + &val); + + /* Verify MMIO is enabled and using bar0 */ + if ((val & SB800_ACPI_MMIO_MASK) == SB800_ACPI_MMIO_DECODE_EN) + alt_mmio_addr = (val & ~0xfff) + SB800_PM_WDT_MMIO_OFFSET; break; case sb800: dev_name = SB800_DEVNAME; mmio_addr = sp5100_tco_read_pm_reg32(SB800_PM_WATCHDOG_BASE) & 0xfffffff8; + + /* Read SBResource_MMIO from AcpiMmioEn(PM_Reg: 24h) */ + val = sp5100_tco_read_pm_reg32(SB800_PM_ACPI_MMIO_EN); + + /* Verify MMIO is enabled and using bar0 */ + if ((val & SB800_ACPI_MMIO_MASK) == SB800_ACPI_MMIO_DECODE_EN) + alt_mmio_addr = (val & ~0xfff) + SB800_PM_WDT_MMIO_OFFSET; break; case efch: dev_name = SB800_DEVNAME; - /* - * On Family 17h devices, the EFCH_PM_DECODEEN_WDT_TMREN bit of - * EFCH_PM_DECODEEN not only enables the EFCH_PM_WDT_ADDR memory - * region, it also enables the watchdog itself. - */ - if (boot_cpu_data.x86 == 0x17) { - val = sp5100_tco_read_pm_reg8(EFCH_PM_DECODEEN); - if (!(val & EFCH_PM_DECODEEN_WDT_TMREN)) { - sp5100_tco_update_pm_reg8(EFCH_PM_DECODEEN, 0xff, - EFCH_PM_DECODEEN_WDT_TMREN); - } - } val = sp5100_tco_read_pm_reg8(EFCH_PM_DECODEEN); if (val & EFCH_PM_DECODEEN_WDT_TMREN) mmio_addr = EFCH_PM_WDT_ADDR; + + val = sp5100_tco_read_pm_reg8(EFCH_PM_ISACONTROL); + if (val & EFCH_PM_ISACONTROL_MMIOEN) + alt_mmio_addr = EFCH_PM_ACPI_MMIO_ADDR + + EFCH_PM_ACPI_MMIO_WDT_OFFSET; break; default: return -ENODEV; } - /* Check MMIO address conflict */ - if (!mmio_addr || - !devm_request_mem_region(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE, - dev_name)) { - if (mmio_addr) - dev_dbg(dev, "MMIO address 0x%08x already in use\n", - mmio_addr); - switch (tco->tco_reg_layout) { - case sp5100: - /* - * Secondly, Find the watchdog timer MMIO address - * from SBResource_MMIO register. - */ - /* Read SBResource_MMIO from PCI config(PCI_Reg: 9Ch) */ - pci_read_config_dword(sp5100_tco_pci, - SP5100_SB_RESOURCE_MMIO_BASE, - &mmio_addr); - if ((mmio_addr & (SB800_ACPI_MMIO_DECODE_EN | - SB800_ACPI_MMIO_SEL)) != - SB800_ACPI_MMIO_DECODE_EN) { - ret = -ENODEV; - goto unreg_region; - } - mmio_addr &= ~0xFFF; - mmio_addr += SB800_PM_WDT_MMIO_OFFSET; - break; - case sb800: - /* Read SBResource_MMIO from AcpiMmioEn(PM_Reg: 24h) */ - mmio_addr = - sp5100_tco_read_pm_reg32(SB800_PM_ACPI_MMIO_EN); - if ((mmio_addr & (SB800_ACPI_MMIO_DECODE_EN | - SB800_ACPI_MMIO_SEL)) != - SB800_ACPI_MMIO_DECODE_EN) { - ret = -ENODEV; - goto unreg_region; - } - mmio_addr &= ~0xFFF; - mmio_addr += SB800_PM_WDT_MMIO_OFFSET; - break; - case efch: - val = sp5100_tco_read_pm_reg8(EFCH_PM_ISACONTROL); - if (!(val & EFCH_PM_ISACONTROL_MMIOEN)) { - ret = -ENODEV; - goto unreg_region; - } - mmio_addr = EFCH_PM_ACPI_MMIO_ADDR + - EFCH_PM_ACPI_MMIO_WDT_OFFSET; - break; - } - dev_dbg(dev, "Got 0x%08x from SBResource_MMIO register\n", - mmio_addr); - if (!devm_request_mem_region(dev, mmio_addr, - SP5100_WDT_MEM_MAP_SIZE, - dev_name)) { - dev_dbg(dev, "MMIO address 0x%08x already in use\n", - mmio_addr); - ret = -EBUSY; - goto unreg_region; - } - } - - tco->tcobase = devm_ioremap(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE); - if (!tco->tcobase) { - dev_err(dev, "failed to get tcobase address\n"); - ret = -ENOMEM; - goto unreg_region; - } - - dev_info(dev, "Using 0x%08x for watchdog MMIO address\n", mmio_addr); - - /* Setup the watchdog timer */ - tco_timer_enable(tco); - - val = readl(SP5100_WDT_CONTROL(tco->tcobase)); - if (val & SP5100_WDT_DISABLED) { - dev_err(dev, "Watchdog hardware is disabled\n"); - ret = -ENODEV; - goto unreg_region; + ret = sp5100_tco_prepare_base(tco, mmio_addr, alt_mmio_addr, dev_name); + if (!ret) { + /* Setup the watchdog timer */ + tco_timer_enable(tco); + ret = sp5100_tco_timer_init(tco); } - /* - * Save WatchDogFired status, because WatchDogFired flag is - * cleared here. - */ - if (val & SP5100_WDT_FIRED) - wdd->bootstatus = WDIOF_CARDRESET; - /* Set watchdog action to reset the system */ - val &= ~SP5100_WDT_ACTION_RESET; - writel(val, SP5100_WDT_CONTROL(tco->tcobase)); - - /* Set a reasonable heartbeat before we stop the timer */ - tco_timer_set_timeout(wdd, wdd->timeout); - - /* - * Stop the TCO before we change anything so we don't race with - * a zeroed timer. - */ - tco_timer_stop(wdd); - - release_region(SP5100_IO_PM_INDEX_REG, SP5100_PM_IOPORTS_SIZE); - - return 0; - -unreg_region: release_region(SP5100_IO_PM_INDEX_REG, SP5100_PM_IOPORTS_SIZE); return ret; } diff --git a/drivers/watchdog/sp5100_tco.h b/drivers/watchdog/sp5100_tco.h index adf015aa4126..6a0986d2c94b 100644 --- a/drivers/watchdog/sp5100_tco.h +++ b/drivers/watchdog/sp5100_tco.h @@ -58,6 +58,7 @@ #define SB800_PM_WATCHDOG_SECOND_RES GENMASK(1, 0) #define SB800_ACPI_MMIO_DECODE_EN BIT(0) #define SB800_ACPI_MMIO_SEL BIT(1) +#define SB800_ACPI_MMIO_MASK GENMASK(1, 0) #define SB800_PM_WDT_MMIO_OFFSET 0xB00 @@ -82,4 +83,10 @@ #define EFCH_PM_ISACONTROL_MMIOEN BIT(1) #define EFCH_PM_ACPI_MMIO_ADDR 0xfed80000 +#define EFCH_PM_ACPI_MMIO_PM_OFFSET 0x00000300 #define EFCH_PM_ACPI_MMIO_WDT_OFFSET 0x00000b00 + +#define EFCH_PM_ACPI_MMIO_PM_ADDR (EFCH_PM_ACPI_MMIO_ADDR + \ + EFCH_PM_ACPI_MMIO_PM_OFFSET) +#define EFCH_PM_ACPI_MMIO_PM_SIZE 8 +#define AMD_ZEN_SMBUS_PCI_REV 0x51 diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 3a3d8b5c7ad5..54903f3c851e 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -171,17 +171,17 @@ static int __watchdog_ping(struct watchdog_device *wdd) } /* - * watchdog_ping: ping the watchdog. - * @wdd: the watchdog device to ping + * watchdog_ping - ping the watchdog + * @wdd: The watchdog device to ping * - * The caller must hold wd_data->lock. + * If the watchdog has no own ping operation then it needs to be + * restarted via the start operation. This wrapper function does + * exactly that. + * We only ping when the watchdog device is running. + * The caller must hold wd_data->lock. * - * If the watchdog has no own ping operation then it needs to be - * restarted via the start operation. This wrapper function does - * exactly that. - * We only ping when the watchdog device is running. + * Return: 0 on success, error otherwise. */ - static int watchdog_ping(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; @@ -231,16 +231,14 @@ static enum hrtimer_restart watchdog_timer_expired(struct hrtimer *timer) } /* - * watchdog_start: wrapper to start the watchdog. - * @wdd: the watchdog device to start + * watchdog_start - wrapper to start the watchdog + * @wdd: The watchdog device to start * - * The caller must hold wd_data->lock. + * Start the watchdog if it is not active and mark it active. + * The caller must hold wd_data->lock. * - * Start the watchdog if it is not active and mark it active. - * This function returns zero on success or a negative errno code for - * failure. + * Return: 0 on success or a negative errno code for failure. */ - static int watchdog_start(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; @@ -274,17 +272,15 @@ static int watchdog_start(struct watchdog_device *wdd) } /* - * watchdog_stop: wrapper to stop the watchdog. - * @wdd: the watchdog device to stop + * watchdog_stop - wrapper to stop the watchdog + * @wdd: The watchdog device to stop * - * The caller must hold wd_data->lock. + * Stop the watchdog if it is still active and unmark it active. + * If the 'nowayout' feature was set, the watchdog cannot be stopped. + * The caller must hold wd_data->lock. * - * Stop the watchdog if it is still active and unmark it active. - * This function returns zero on success or a negative errno code for - * failure. - * If the 'nowayout' feature was set, the watchdog cannot be stopped. + * Return: 0 on success or a negative errno code for failure. */ - static int watchdog_stop(struct watchdog_device *wdd) { int err = 0; @@ -315,14 +311,14 @@ static int watchdog_stop(struct watchdog_device *wdd) } /* - * watchdog_get_status: wrapper to get the watchdog status - * @wdd: the watchdog device to get the status from + * watchdog_get_status - wrapper to get the watchdog status + * @wdd: The watchdog device to get the status from * - * The caller must hold wd_data->lock. + * Get the watchdog's status flags. + * The caller must hold wd_data->lock. * - * Get the watchdog's status flags. + * Return: watchdog's status flags. */ - static unsigned int watchdog_get_status(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; @@ -352,13 +348,14 @@ static unsigned int watchdog_get_status(struct watchdog_device *wdd) } /* - * watchdog_set_timeout: set the watchdog timer timeout - * @wdd: the watchdog device to set the timeout for - * @timeout: timeout to set in seconds + * watchdog_set_timeout - set the watchdog timer timeout + * @wdd: The watchdog device to set the timeout for + * @timeout: Timeout to set in seconds + * + * The caller must hold wd_data->lock. * - * The caller must hold wd_data->lock. + * Return: 0 if successful, error otherwise. */ - static int watchdog_set_timeout(struct watchdog_device *wdd, unsigned int timeout) { @@ -385,11 +382,12 @@ static int watchdog_set_timeout(struct watchdog_device *wdd, } /* - * watchdog_set_pretimeout: set the watchdog timer pretimeout - * @wdd: the watchdog device to set the timeout for - * @timeout: pretimeout to set in seconds + * watchdog_set_pretimeout - set the watchdog timer pretimeout + * @wdd: The watchdog device to set the timeout for + * @timeout: pretimeout to set in seconds + * + * Return: 0 if successful, error otherwise. */ - static int watchdog_set_pretimeout(struct watchdog_device *wdd, unsigned int timeout) { @@ -410,15 +408,15 @@ static int watchdog_set_pretimeout(struct watchdog_device *wdd, } /* - * watchdog_get_timeleft: wrapper to get the time left before a reboot - * @wdd: the watchdog device to get the remaining time from - * @timeleft: the time that's left + * watchdog_get_timeleft - wrapper to get the time left before a reboot + * @wdd: The watchdog device to get the remaining time from + * @timeleft: The time that's left * - * The caller must hold wd_data->lock. + * Get the time before a watchdog will reboot (if not pinged). + * The caller must hold wd_data->lock. * - * Get the time before a watchdog will reboot (if not pinged). + * Return: 0 if successful, error otherwise. */ - static int watchdog_get_timeleft(struct watchdog_device *wdd, unsigned int *timeleft) { @@ -635,14 +633,15 @@ __ATTRIBUTE_GROUPS(wdt); #endif /* - * watchdog_ioctl_op: call the watchdog drivers ioctl op if defined - * @wdd: the watchdog device to do the ioctl on - * @cmd: watchdog command - * @arg: argument pointer + * watchdog_ioctl_op - call the watchdog drivers ioctl op if defined + * @wdd: The watchdog device to do the ioctl on + * @cmd: Watchdog command + * @arg: Argument pointer * - * The caller must hold wd_data->lock. + * The caller must hold wd_data->lock. + * + * Return: 0 if successful, error otherwise. */ - static int watchdog_ioctl_op(struct watchdog_device *wdd, unsigned int cmd, unsigned long arg) { @@ -653,17 +652,18 @@ static int watchdog_ioctl_op(struct watchdog_device *wdd, unsigned int cmd, } /* - * watchdog_write: writes to the watchdog. - * @file: file from VFS - * @data: user address of data - * @len: length of data - * @ppos: pointer to the file offset + * watchdog_write - writes to the watchdog + * @file: File from VFS + * @data: User address of data + * @len: Length of data + * @ppos: Pointer to the file offset * - * A write to a watchdog device is defined as a keepalive ping. - * Writing the magic 'V' sequence allows the next close to turn - * off the watchdog (if 'nowayout' is not set). + * A write to a watchdog device is defined as a keepalive ping. + * Writing the magic 'V' sequence allows the next close to turn + * off the watchdog (if 'nowayout' is not set). + * + * Return: @len if successful, error otherwise. */ - static ssize_t watchdog_write(struct file *file, const char __user *data, size_t len, loff_t *ppos) { @@ -706,13 +706,15 @@ static ssize_t watchdog_write(struct file *file, const char __user *data, } /* - * watchdog_ioctl: handle the different ioctl's for the watchdog device. - * @file: file handle to the device - * @cmd: watchdog command - * @arg: argument pointer + * watchdog_ioctl - handle the different ioctl's for the watchdog device + * @file: File handle to the device + * @cmd: Watchdog command + * @arg: Argument pointer * - * The watchdog API defines a common set of functions for all watchdogs - * according to their available features. + * The watchdog API defines a common set of functions for all watchdogs + * according to their available features. + * + * Return: 0 if successful, error otherwise. */ static long watchdog_ioctl(struct file *file, unsigned int cmd, @@ -819,15 +821,16 @@ out_ioctl: } /* - * watchdog_open: open the /dev/watchdog* devices. - * @inode: inode of device - * @file: file handle to device + * watchdog_open - open the /dev/watchdog* devices + * @inode: Inode of device + * @file: File handle to device + * + * When the /dev/watchdog* device gets opened, we start the watchdog. + * Watch out: the /dev/watchdog device is single open, so we make sure + * it can only be opened once. * - * When the /dev/watchdog* device gets opened, we start the watchdog. - * Watch out: the /dev/watchdog device is single open, so we make sure - * it can only be opened once. + * Return: 0 if successful, error otherwise. */ - static int watchdog_open(struct inode *inode, struct file *file) { struct watchdog_core_data *wd_data; @@ -896,15 +899,16 @@ static void watchdog_core_data_release(struct device *dev) } /* - * watchdog_release: release the watchdog device. - * @inode: inode of device - * @file: file handle to device + * watchdog_release - release the watchdog device + * @inode: Inode of device + * @file: File handle to device + * + * This is the code for when /dev/watchdog gets closed. We will only + * stop the watchdog when we have received the magic char (and nowayout + * was not set), else the watchdog will keep running. * - * This is the code for when /dev/watchdog gets closed. We will only - * stop the watchdog when we have received the magic char (and nowayout - * was not set), else the watchdog will keep running. + * Always returns 0. */ - static int watchdog_release(struct inode *inode, struct file *file) { struct watchdog_core_data *wd_data = file->private_data; @@ -977,14 +981,15 @@ static struct class watchdog_class = { }; /* - * watchdog_cdev_register: register watchdog character device - * @wdd: watchdog device + * watchdog_cdev_register - register watchdog character device + * @wdd: Watchdog device + * + * Register a watchdog character device including handling the legacy + * /dev/watchdog node. /dev/watchdog is actually a miscdevice and + * thus we set it up like that. * - * Register a watchdog character device including handling the legacy - * /dev/watchdog node. /dev/watchdog is actually a miscdevice and - * thus we set it up like that. + * Return: 0 if successful, error otherwise. */ - static int watchdog_cdev_register(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data; @@ -1074,13 +1079,12 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) } /* - * watchdog_cdev_unregister: unregister watchdog character device - * @watchdog: watchdog device + * watchdog_cdev_unregister - unregister watchdog character device + * @wdd: Watchdog device * - * Unregister watchdog character device and if needed the legacy - * /dev/watchdog device. + * Unregister watchdog character device and if needed the legacy + * /dev/watchdog device. */ - static void watchdog_cdev_unregister(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; @@ -1109,15 +1113,16 @@ static void watchdog_cdev_unregister(struct watchdog_device *wdd) put_device(&wd_data->dev); } -/* - * watchdog_dev_register: register a watchdog device - * @wdd: watchdog device +/** + * watchdog_dev_register - register a watchdog device + * @wdd: Watchdog device + * + * Register a watchdog device including handling the legacy + * /dev/watchdog node. /dev/watchdog is actually a miscdevice and + * thus we set it up like that. * - * Register a watchdog device including handling the legacy - * /dev/watchdog node. /dev/watchdog is actually a miscdevice and - * thus we set it up like that. + * Return: 0 if successful, error otherwise. */ - int watchdog_dev_register(struct watchdog_device *wdd) { int ret; @@ -1133,30 +1138,31 @@ int watchdog_dev_register(struct watchdog_device *wdd) return ret; } -/* - * watchdog_dev_unregister: unregister a watchdog device - * @watchdog: watchdog device +/** + * watchdog_dev_unregister - unregister a watchdog device + * @wdd: watchdog device * - * Unregister watchdog device and if needed the legacy - * /dev/watchdog device. + * Unregister watchdog device and if needed the legacy + * /dev/watchdog device. */ - void watchdog_dev_unregister(struct watchdog_device *wdd) { watchdog_unregister_pretimeout(wdd); watchdog_cdev_unregister(wdd); } -/* - * watchdog_set_last_hw_keepalive: set last HW keepalive time for watchdog - * @wdd: watchdog device - * @last_ping_ms: time since last HW heartbeat +/** + * watchdog_set_last_hw_keepalive - set last HW keepalive time for watchdog + * @wdd: Watchdog device + * @last_ping_ms: Time since last HW heartbeat * - * Adjusts the last known HW keepalive time for a watchdog timer. - * This is needed if the watchdog is already running when the probe - * function is called, and it can't be pinged immediately. This - * function must be called immediately after watchdog registration, - * and min_hw_heartbeat_ms must be set for this to be useful. + * Adjusts the last known HW keepalive time for a watchdog timer. + * This is needed if the watchdog is already running when the probe + * function is called, and it can't be pinged immediately. This + * function must be called immediately after watchdog registration, + * and min_hw_heartbeat_ms must be set for this to be useful. + * + * Return: 0 if successful, error otherwise. */ int watchdog_set_last_hw_keepalive(struct watchdog_device *wdd, unsigned int last_ping_ms) @@ -1180,12 +1186,13 @@ int watchdog_set_last_hw_keepalive(struct watchdog_device *wdd, } EXPORT_SYMBOL_GPL(watchdog_set_last_hw_keepalive); -/* - * watchdog_dev_init: init dev part of watchdog core +/** + * watchdog_dev_init - init dev part of watchdog core * - * Allocate a range of chardev nodes to use for watchdog devices + * Allocate a range of chardev nodes to use for watchdog devices. + * + * Return: 0 if successful, error otherwise. */ - int __init watchdog_dev_init(void) { int err; @@ -1218,12 +1225,11 @@ err_register: return err; } -/* - * watchdog_dev_exit: exit dev part of watchdog core +/** + * watchdog_dev_exit - exit dev part of watchdog core * - * Release the range of chardev nodes used for watchdog devices + * Release the range of chardev nodes used for watchdog devices. */ - void __exit watchdog_dev_exit(void) { unregister_chrdev_region(watchdog_devt, MAX_DOGS); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index dfe26fa17e95..617a7f4f07a8 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -689,29 +689,34 @@ void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_ballooned_pages); -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) -static void __init balloon_add_region(unsigned long start_pfn, - unsigned long pages) +static void __init balloon_add_regions(void) { +#if defined(CONFIG_XEN_PV) + unsigned long start_pfn, pages; unsigned long pfn, extra_pfn_end; + unsigned int i; - /* - * If the amount of usable memory has been limited (e.g., with - * the 'mem' command line parameter), don't add pages beyond - * this limit. - */ - extra_pfn_end = min(max_pfn, start_pfn + pages); + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + pages = xen_extra_mem[i].n_pfns; + if (!pages) + continue; - for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { - /* totalram_pages and totalhigh_pages do not - include the boot-time balloon extension, so - don't subtract from it. */ - balloon_append(pfn_to_page(pfn)); - } + start_pfn = xen_extra_mem[i].start_pfn; - balloon_stats.total_pages += extra_pfn_end - start_pfn; -} + /* + * If the amount of usable memory has been limited (e.g., with + * the 'mem' command line parameter), don't add pages beyond + * this limit. + */ + extra_pfn_end = min(max_pfn, start_pfn + pages); + + for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) + balloon_append(pfn_to_page(pfn)); + + balloon_stats.total_pages += extra_pfn_end - start_pfn; + } #endif +} static int __init balloon_init(void) { @@ -745,20 +750,7 @@ static int __init balloon_init(void) register_sysctl_table(xen_root); #endif -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) - { - int i; - - /* - * Initialize the balloon with pages from the extra memory - * regions (see arch/x86/xen/setup.c). - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) - if (xen_extra_mem[i].n_pfns) - balloon_add_region(xen_extra_mem[i].start_pfn, - xen_extra_mem[i].n_pfns); - } -#endif + balloon_add_regions(); task = kthread_run(balloon_thread, NULL, "xen-balloon"); if (IS_ERR(task)) { diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index a8b41057c382..a39f2d36dd9c 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -230,39 +230,6 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_unpopulated_pages); -#ifdef CONFIG_XEN_PV -static int __init init(void) -{ - unsigned int i; - - if (!xen_domain()) - return -ENODEV; - - if (!xen_pv_domain()) - return 0; - - /* - * Initialize with pages from the extra memory regions (see - * arch/x86/xen/setup.c). - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - unsigned int j; - - for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { - struct page *pg = - pfn_to_page(xen_extra_mem[i].start_pfn + j); - - pg->zone_device_data = page_list; - page_list = pg; - list_count++; - } - } - - return 0; -} -subsys_initcall(init); -#endif - static int __init unpopulated_init(void) { int ret; diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 55e108e5e133..1c8dc696d516 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -49,22 +49,20 @@ int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, void v9fs_cache_inode_get_cookie(struct inode *inode) { - struct v9fs_inode *v9inode; + struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses; __le32 version; __le64 path; if (!S_ISREG(inode->i_mode)) return; - - v9inode = V9FS_I(inode); - if (WARN_ON(v9inode->fscache)) + if (WARN_ON(v9fs_inode_cookie(v9inode))) return; version = cpu_to_le32(v9inode->qid.version); path = cpu_to_le64(v9inode->qid.path); v9ses = v9fs_inode2v9ses(inode); - v9inode->fscache = + v9inode->netfs_ctx.cache = fscache_acquire_cookie(v9fs_session_cache(v9ses), 0, &path, sizeof(path), @@ -72,5 +70,5 @@ void v9fs_cache_inode_get_cookie(struct inode *inode) i_size_read(&v9inode->vfs_inode)); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", - inode, v9inode->fscache); + inode, v9fs_inode_cookie(v9inode)); } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 08f65c40af4f..e28ddf763b3b 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -623,9 +623,7 @@ static void v9fs_sysfs_cleanup(void) static void v9fs_inode_init_once(void *foo) { struct v9fs_inode *v9inode = (struct v9fs_inode *)foo; -#ifdef CONFIG_9P_FSCACHE - v9inode->fscache = NULL; -#endif + memset(&v9inode->qid, 0, sizeof(v9inode->qid)); inode_init_once(&v9inode->vfs_inode); } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index bc8b30205d36..ec0e8df3b2eb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -9,6 +9,7 @@ #define FS_9P_V9FS_H #include <linux/backing-dev.h> +#include <linux/netfs.h> /** * enum p9_session_flags - option flags for each 9P session @@ -108,14 +109,15 @@ struct v9fs_session_info { #define V9FS_INO_INVALID_ATTR 0x01 struct v9fs_inode { -#ifdef CONFIG_9P_FSCACHE - struct fscache_cookie *fscache; -#endif + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct p9_qid qid; unsigned int cache_validity; struct p9_fid *writeback_fid; struct mutex v_mutex; - struct inode vfs_inode; }; static inline struct v9fs_inode *V9FS_I(const struct inode *inode) @@ -126,7 +128,7 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode) { #ifdef CONFIG_9P_FSCACHE - return v9inode->fscache; + return netfs_i_cookie(&v9inode->vfs_inode); #else return NULL; #endif @@ -163,6 +165,7 @@ extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses, extern const struct inode_operations v9fs_dir_inode_operations_dotl; extern const struct inode_operations v9fs_file_inode_operations_dotl; extern const struct inode_operations v9fs_symlink_inode_operations_dotl; +extern const struct netfs_request_ops v9fs_req_ops; extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid, struct super_block *sb, int new); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 76956c9d2af9..501128188343 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -28,12 +28,12 @@ #include "fid.h" /** - * v9fs_req_issue_op - Issue a read from 9P + * v9fs_issue_read - Issue a read from 9P * @subreq: The read to make */ -static void v9fs_req_issue_op(struct netfs_read_subrequest *subreq) +static void v9fs_issue_read(struct netfs_io_subrequest *subreq) { - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct p9_fid *fid = rreq->netfs_priv; struct iov_iter to; loff_t pos = subreq->start + subreq->transferred; @@ -52,20 +52,21 @@ static void v9fs_req_issue_op(struct netfs_read_subrequest *subreq) } /** - * v9fs_init_rreq - Initialise a read request + * v9fs_init_request - Initialise a read request * @rreq: The read request * @file: The file being read from */ -static void v9fs_init_rreq(struct netfs_read_request *rreq, struct file *file) +static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file) { struct p9_fid *fid = file->private_data; refcount_inc(&fid->count); rreq->netfs_priv = fid; + return 0; } /** - * v9fs_req_cleanup - Cleanup request initialized by v9fs_init_rreq + * v9fs_req_cleanup - Cleanup request initialized by v9fs_init_request * @mapping: unused mapping of request to cleanup * @priv: private data to cleanup, a fid, guaranted non-null. */ @@ -77,21 +78,10 @@ static void v9fs_req_cleanup(struct address_space *mapping, void *priv) } /** - * v9fs_is_cache_enabled - Determine if caching is enabled for an inode - * @inode: The inode to check - */ -static bool v9fs_is_cache_enabled(struct inode *inode) -{ - struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(inode)); - - return fscache_cookie_enabled(cookie) && cookie->cache_priv; -} - -/** * v9fs_begin_cache_operation - Begin a cache operation for a read * @rreq: The read request */ -static int v9fs_begin_cache_operation(struct netfs_read_request *rreq) +static int v9fs_begin_cache_operation(struct netfs_io_request *rreq) { #ifdef CONFIG_9P_FSCACHE struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode)); @@ -102,37 +92,14 @@ static int v9fs_begin_cache_operation(struct netfs_read_request *rreq) #endif } -static const struct netfs_read_request_ops v9fs_req_ops = { - .init_rreq = v9fs_init_rreq, - .is_cache_enabled = v9fs_is_cache_enabled, +const struct netfs_request_ops v9fs_req_ops = { + .init_request = v9fs_init_request, .begin_cache_operation = v9fs_begin_cache_operation, - .issue_op = v9fs_req_issue_op, + .issue_read = v9fs_issue_read, .cleanup = v9fs_req_cleanup, }; /** - * v9fs_vfs_readpage - read an entire page in from 9P - * @file: file being read - * @page: structure to page - * - */ -static int v9fs_vfs_readpage(struct file *file, struct page *page) -{ - struct folio *folio = page_folio(page); - - return netfs_readpage(file, folio, &v9fs_req_ops, NULL); -} - -/** - * v9fs_vfs_readahead - read a set of pages from 9P - * @ractl: The readahead parameters - */ -static void v9fs_vfs_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &v9fs_req_ops, NULL); -} - -/** * v9fs_release_page - release the private state associated with a page * @page: The page to be released * @gfp: The caller's allocation restrictions @@ -308,8 +275,7 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata, - &v9fs_req_ops, NULL); + retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata); if (retval < 0) return retval; @@ -370,8 +336,8 @@ static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio) #endif const struct address_space_operations v9fs_addr_operations = { - .readpage = v9fs_vfs_readpage, - .readahead = v9fs_vfs_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .dirty_folio = v9fs_dirty_folio, .writepage = v9fs_vfs_writepage, .write_begin = v9fs_write_begin, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 84c3cf7dffa5..55367ecb9442 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -231,9 +231,6 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) v9inode = alloc_inode_sb(sb, v9fs_inode_cache, GFP_KERNEL); if (!v9inode) return NULL; -#ifdef CONFIG_9P_FSCACHE - v9inode->fscache = NULL; -#endif v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; mutex_init(&v9inode->v_mutex); @@ -250,6 +247,14 @@ void v9fs_free_inode(struct inode *inode) kmem_cache_free(v9fs_inode_cache, V9FS_I(inode)); } +/* + * Set parameters for the netfs library + */ +static void v9fs_set_netfs_context(struct inode *inode) +{ + netfs_i_context_init(inode, &v9fs_req_ops); +} + int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev) { @@ -338,6 +343,8 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, err = -EINVAL; goto error; } + + v9fs_set_netfs_context(inode); error: return err; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index db832cc931c8..f120bcb8bf73 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -76,6 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) /* there shouldn't be an existing inode */ BUG_ON(!(inode->i_state & I_NEW)); + netfs_i_context_init(inode, NULL); inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; if (root) { diff --git a/fs/afs/file.c b/fs/afs/file.c index 0f9fdb284a20..26292a110a8f 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -19,13 +19,11 @@ #include "internal.h" static int afs_file_mmap(struct file *file, struct vm_area_struct *vma); -static int afs_readpage(struct file *file, struct page *page); static int afs_symlink_readpage(struct file *file, struct page *page); static void afs_invalidate_folio(struct folio *folio, size_t offset, size_t length); static int afs_releasepage(struct page *page, gfp_t gfp_flags); -static void afs_readahead(struct readahead_control *ractl); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); static void afs_vm_open(struct vm_area_struct *area); static void afs_vm_close(struct vm_area_struct *area); @@ -52,8 +50,8 @@ const struct inode_operations afs_file_inode_operations = { }; const struct address_space_operations afs_file_aops = { - .readpage = afs_readpage, - .readahead = afs_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .dirty_folio = afs_dirty_folio, .launder_folio = afs_launder_folio, .releasepage = afs_releasepage, @@ -240,7 +238,7 @@ void afs_put_read(struct afs_read *req) static void afs_fetch_data_notify(struct afs_operation *op) { struct afs_read *req = op->fetch.req; - struct netfs_read_subrequest *subreq = req->subreq; + struct netfs_io_subrequest *subreq = req->subreq; int error = op->error; if (error == -ECONNABORTED) @@ -310,7 +308,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req) return afs_do_sync_operation(op); } -static void afs_req_issue_op(struct netfs_read_subrequest *subreq) +static void afs_issue_read(struct netfs_io_subrequest *subreq) { struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode); struct afs_read *fsreq; @@ -359,19 +357,13 @@ static int afs_symlink_readpage(struct file *file, struct page *page) return ret; } -static void afs_init_rreq(struct netfs_read_request *rreq, struct file *file) +static int afs_init_request(struct netfs_io_request *rreq, struct file *file) { rreq->netfs_priv = key_get(afs_file_key(file)); + return 0; } -static bool afs_is_cache_enabled(struct inode *inode) -{ - struct fscache_cookie *cookie = afs_vnode_cache(AFS_FS_I(inode)); - - return fscache_cookie_enabled(cookie) && cookie->cache_priv; -} - -static int afs_begin_cache_operation(struct netfs_read_request *rreq) +static int afs_begin_cache_operation(struct netfs_io_request *rreq) { #ifdef CONFIG_AFS_FSCACHE struct afs_vnode *vnode = AFS_FS_I(rreq->inode); @@ -396,27 +388,14 @@ static void afs_priv_cleanup(struct address_space *mapping, void *netfs_priv) key_put(netfs_priv); } -const struct netfs_read_request_ops afs_req_ops = { - .init_rreq = afs_init_rreq, - .is_cache_enabled = afs_is_cache_enabled, +const struct netfs_request_ops afs_req_ops = { + .init_request = afs_init_request, .begin_cache_operation = afs_begin_cache_operation, .check_write_begin = afs_check_write_begin, - .issue_op = afs_req_issue_op, + .issue_read = afs_issue_read, .cleanup = afs_priv_cleanup, }; -static int afs_readpage(struct file *file, struct page *page) -{ - struct folio *folio = page_folio(page); - - return netfs_readpage(file, folio, &afs_req_ops, NULL); -} - -static void afs_readahead(struct readahead_control *ractl) -{ - netfs_readahead(ractl, &afs_req_ops, NULL); -} - int afs_write_inode(struct inode *inode, struct writeback_control *wbc) { fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode))); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 5964f8aee090..2fe402483ad5 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -54,6 +54,14 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren } /* + * Set parameters for the netfs library + */ +static void afs_set_netfs_context(struct afs_vnode *vnode) +{ + netfs_i_context_init(&vnode->vfs_inode, &afs_req_ops); +} + +/* * Initialise an inode from the vnode status. */ static int afs_inode_init_from_status(struct afs_operation *op, @@ -128,6 +136,7 @@ static int afs_inode_init_from_status(struct afs_operation *op, } afs_set_i_size(vnode, status->size); + afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); @@ -237,6 +246,7 @@ static void afs_apply_status(struct afs_operation *op, * idea of what the size should be that's not the same as * what's on the server. */ + vnode->netfs_ctx.remote_i_size = status->size; if (change_size) { afs_set_i_size(vnode, status->size); inode->i_ctime = t; @@ -420,7 +430,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) struct afs_vnode_cache_aux aux; if (vnode->status.type != AFS_FTYPE_FILE) { - vnode->cache = NULL; + vnode->netfs_ctx.cache = NULL; return; } @@ -430,12 +440,14 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) key.vnode_id_ext[1] = htonl(vnode->fid.vnode_hi); afs_set_cache_aux(vnode, &aux); - vnode->cache = fscache_acquire_cookie( - vnode->volume->cache, - vnode->status.type == AFS_FTYPE_FILE ? 0 : FSCACHE_ADV_SINGLE_CHUNK, - &key, sizeof(key), - &aux, sizeof(aux), - vnode->status.size); + afs_vnode_set_cache(vnode, + fscache_acquire_cookie( + vnode->volume->cache, + vnode->status.type == AFS_FTYPE_FILE ? + 0 : FSCACHE_ADV_SINGLE_CHUNK, + &key, sizeof(key), + &aux, sizeof(aux), + vnode->status.size)); #endif } @@ -528,6 +540,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key) vnode = AFS_FS_I(inode); vnode->cb_v_break = as->volume->cb_v_break, + afs_set_netfs_context(vnode); op = afs_alloc_operation(key, as->volume); if (IS_ERR(op)) { @@ -786,11 +799,8 @@ void afs_evict_inode(struct inode *inode) afs_put_wb_key(wbk); } -#ifdef CONFIG_AFS_FSCACHE - fscache_relinquish_cookie(vnode->cache, + fscache_relinquish_cookie(afs_vnode_cache(vnode), test_bit(AFS_VNODE_DELETED, &vnode->flags)); - vnode->cache = NULL; -#endif afs_prune_wb_keys(vnode); afs_put_permits(rcu_access_pointer(vnode->permit_cache)); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index dc5032e10244..7b7ef945dc78 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -207,7 +207,7 @@ struct afs_read { loff_t file_size; /* File size returned by server */ struct key *key; /* The key to use to reissue the read */ struct afs_vnode *vnode; /* The file being read into. */ - struct netfs_read_subrequest *subreq; /* Fscache helper read request this belongs to */ + struct netfs_io_subrequest *subreq; /* Fscache helper read request this belongs to */ afs_dataversion_t data_version; /* Version number returned by server */ refcount_t usage; unsigned int call_debug_id; @@ -619,15 +619,16 @@ enum afs_lock_state { * leak from one inode to another. */ struct afs_vnode { - struct inode vfs_inode; /* the VFS's inode record */ + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct afs_volume *volume; /* volume on which vnode resides */ struct afs_fid fid; /* the file identifier for this inode */ struct afs_file_status status; /* AFS status info for this file */ afs_dataversion_t invalid_before; /* Child dentries are invalid before this */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ struct mutex io_lock; /* Lock for serialising I/O on this mutex */ struct rw_semaphore validate_lock; /* lock for validating this vnode */ @@ -674,12 +675,20 @@ struct afs_vnode { static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) { #ifdef CONFIG_AFS_FSCACHE - return vnode->cache; + return netfs_i_cookie(&vnode->vfs_inode); #else return NULL; #endif } +static inline void afs_vnode_set_cache(struct afs_vnode *vnode, + struct fscache_cookie *cookie) +{ +#ifdef CONFIG_AFS_FSCACHE + vnode->netfs_ctx.cache = cookie; +#endif +} + /* * cached security record for one user's attempt to access a vnode */ @@ -1063,7 +1072,7 @@ extern const struct address_space_operations afs_file_aops; extern const struct address_space_operations afs_symlink_aops; extern const struct inode_operations afs_file_inode_operations; extern const struct file_operations afs_file_operations; -extern const struct netfs_read_request_ops afs_req_ops; +extern const struct netfs_request_ops afs_req_ops; extern int afs_cache_wb_key(struct afs_vnode *, struct afs_file *); extern void afs_put_wb_key(struct afs_wb_key *); diff --git a/fs/afs/super.c b/fs/afs/super.c index 7592c0f469f1..1fea195b0b27 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -688,13 +688,11 @@ static struct inode *afs_alloc_inode(struct super_block *sb) /* Reset anything that shouldn't leak from one inode to the next. */ memset(&vnode->fid, 0, sizeof(vnode->fid)); memset(&vnode->status, 0, sizeof(vnode->status)); + afs_vnode_set_cache(vnode, NULL); vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; -#ifdef CONFIG_AFS_FSCACHE - vnode->cache = NULL; -#endif vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; diff --git a/fs/afs/write.c b/fs/afs/write.c index e1c17081d18e..4763132ca57e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -60,8 +60,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata, - &afs_req_ops, NULL); + ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata); if (ret < 0) return ret; @@ -355,9 +354,10 @@ static const struct afs_operation_ops afs_store_data_operation = { static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t pos, bool laundering) { + struct netfs_i_context *ictx = &vnode->netfs_ctx; struct afs_operation *op; struct afs_wb_key *wbk = NULL; - loff_t size = iov_iter_count(iter), i_size; + loff_t size = iov_iter_count(iter); int ret = -ENOKEY; _enter("%s{%llx:%llu.%u},%llx,%llx", @@ -379,15 +379,13 @@ static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t return -ENOMEM; } - i_size = i_size_read(&vnode->vfs_inode); - afs_op_set_vnode(op, 0, vnode); op->file[0].dv_delta = 1; op->file[0].modification = true; op->store.write_iter = iter; op->store.pos = pos; op->store.size = size; - op->store.i_size = max(pos + size, i_size); + op->store.i_size = max(pos + size, ictx->remote_i_size); op->store.laundering = laundering; op->mtime = vnode->vfs_inode.i_mtime; op->flags |= AFS_OPERATION_UNINTR; @@ -618,8 +616,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, _debug("write discard %x @%llx [%llx]", len, start, i_size); /* The dirty region was entirely beyond the EOF. */ - fscache_clear_page_bits(afs_vnode_cache(vnode), - mapping, start, len, caching); + fscache_clear_page_bits(mapping, start, len, caching); afs_pages_written_back(vnode, start, len); ret = 0; } @@ -1552,7 +1552,6 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb, file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; - ret = -EINVAL; if (unlikely(!file->f_op->read_iter)) return -EINVAL; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6556e13ed95f..63c7ebb0da89 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1117,11 +1117,11 @@ out_free_interp: * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). */ - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); - if (interpreter || alignment > ELF_MIN_ALIGN) { + if (interpreter) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); if (alignment) load_bias &= ~(alignment - 1); elf_flags |= MAP_FIXED_NOREPLACE; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c22d287e020b..0dd6de994199 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2503,12 +2503,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - /* - * New block group is likely to be used soon. Try to activate it now. - * Failure is OK for now. - */ - btrfs_zone_activate(cache); - ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2946,7 +2940,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) struct btrfs_path *path = NULL; LIST_HEAD(dirty); struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); @@ -3012,7 +3005,6 @@ again: cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; /* @@ -3113,7 +3105,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) int should_put; struct btrfs_path *path; struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; path = btrfs_alloc_path(); if (!path) @@ -3171,7 +3162,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; list_add_tail(&cache->io_list, io); } else { @@ -3455,7 +3445,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } -static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) { struct btrfs_block_group *bg; int ret; @@ -3542,7 +3532,11 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) out: btrfs_trans_release_chunk_metadata(trans); - return ret; + if (ret) + return ERR_PTR(ret); + + btrfs_get_block_group(bg); + return bg; } /* @@ -3657,10 +3651,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *space_info; + struct btrfs_block_group *ret_bg; bool wait_for_alloc = false; bool should_alloc = false; + bool from_extent_allocation = false; int ret = 0; + if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) { + from_extent_allocation = true; + force = CHUNK_ALLOC_FORCE; + } + /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; @@ -3750,9 +3751,22 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - ret = do_chunk_alloc(trans, flags); + ret_bg = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; + if (IS_ERR(ret_bg)) { + ret = PTR_ERR(ret_bg); + } else if (from_extent_allocation) { + /* + * New block group is likely to be used soon. Try to activate + * it now. Failure is OK for now. + */ + btrfs_zone_activate(ret_bg); + } + + if (!ret) + btrfs_put_block_group(ret_bg); + spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 93aabc68bb6a..e8308f2ad07d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -35,11 +35,15 @@ enum btrfs_discard_state { * the FS with empty chunks * * CHUNK_ALLOC_FORCE means it must try to allocate one + * + * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from + * find_free_extent() that also activaes the zone */ enum btrfs_chunk_alloc_enum { CHUNK_ALLOC_NO_FORCE, CHUNK_ALLOC_LIMITED, CHUNK_ALLOC_FORCE, + CHUNK_ALLOC_FORCE_FOR_EXTENT, }; struct btrfs_caching_control { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index be476f094300..19bf36d8ffea 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -537,6 +537,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->orig_bio = NULL; cb->nr_pages = nr_pages; + if (blkcg_css) + kthread_associate_blkcg(blkcg_css); + while (cur_disk_bytenr < disk_start + compressed_len) { u64 offset = cur_disk_bytenr - disk_start; unsigned int index = offset >> PAGE_SHIFT; @@ -555,6 +558,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bio = NULL; goto finish_cb; } + if (blkcg_css) + bio->bi_opf |= REQ_CGROUP_PUNT; } /* * We should never reach next_stripe_start start as we will @@ -612,6 +617,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, return 0; finish_cb: + if (blkcg_css) + kthread_associate_blkcg(NULL); + if (bio) { bio->bi_status = ret; bio_endio(bio); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b30309f187cf..126f244cdf88 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1850,9 +1850,10 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { - btrfs_put_root(root); - if (ret == -EEXIST) + if (ret == -EEXIST) { + btrfs_put_root(root); goto again; + } goto fail; } return root; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f477035a2ac2..6aa92f84f465 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4082,7 +4082,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info, } ret = btrfs_chunk_alloc(trans, ffe_ctl->flags, - CHUNK_ALLOC_FORCE); + CHUNK_ALLOC_FORCE_FOR_EXTENT); /* Do not bail out on ENOSPC since we can do more. */ if (ret == -ENOSPC) diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 0399cf8e3c32..151e9da5da2d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -118,7 +118,7 @@ struct btrfs_bio_ctrl { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - unsigned int bytes_changed; + u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9f455c96c974..380054c94e4b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2957,8 +2957,9 @@ out: return ret; } -static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; @@ -2990,6 +2991,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } + ret = file_modified(file); + if (ret) + goto out_only_mutex; + lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode))); lockend = round_down(offset + len, btrfs_inode_sectorsize(BTRFS_I(inode))) - 1; @@ -3430,7 +3435,7 @@ static long btrfs_fallocate(struct file *file, int mode, return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) - return btrfs_punch_hole(inode, offset, len); + return btrfs_punch_hole(file, offset, len); /* * Only trigger disk allocation, don't trigger qgroup reserve @@ -3452,6 +3457,10 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } + ret = file_modified(file); + if (ret) + goto out; + /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index aa0a60ee26cb..5082b9c70f8c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1128,7 +1128,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, int ret = 0; if (btrfs_is_free_space_inode(inode)) { - WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; } @@ -2017,8 +2016,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page * to use run_delalloc_nocow() here, like for regular * preallocated inodes. */ - ASSERT(!zoned || - (zoned && btrfs_is_data_reloc_root(inode->root))); + ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); } else if (!inode_can_compress(inode) || @@ -4488,6 +4486,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); return -EPERM; } + if (atomic_read(&dest->nr_swapfiles)) { + spin_unlock(&dest->root_item_lock); + btrfs_warn(fs_info, + "attempt to delete subvolume %llu with active swapfile", + root->root_key.objectid); + return -EPERM; + } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); @@ -7438,6 +7443,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, u64 block_start, orig_start, orig_block_len, ram_bytes; bool can_nocow = false; bool space_reserved = false; + u64 prev_len; int ret = 0; /* @@ -7465,6 +7471,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, can_nocow = true; } + prev_len = len; if (can_nocow) { struct extent_map *em2; @@ -7494,8 +7501,6 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, goto out; } } else { - const u64 prev_len = len; - /* Our caller expects us to free the input extent map. */ free_extent_map(em); *map = NULL; @@ -7526,7 +7531,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, * We have created our ordered extent, so we can now release our reservation * for an outstanding extent. */ - btrfs_delalloc_release_extents(BTRFS_I(inode), len); + btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len); /* * Need to update the i_size under the extent lock so buffered @@ -8296,7 +8301,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset, * cover the full folio, like invalidating the last folio, we're * still safe to wait for ordered extent to finish. */ - if (!(offset == 0 && length == PAGE_SIZE)) { + if (!(offset == 0 && length == folio_size(folio))) { btrfs_releasepage(&folio->page, GFP_NOFS); return; } @@ -11107,8 +11112,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, * set. We use this counter to prevent snapshots. We must increment it * before walking the extents because we don't want a concurrent * snapshot to run after we've already checked the extents. + * + * It is possible that subvolume is marked for deletion but still not + * removed yet. To prevent this race, we check the root status before + * activating the swapfile. */ + spin_lock(&root->root_item_lock); + if (btrfs_root_dead(root)) { + spin_unlock(&root->root_item_lock); + + btrfs_exclop_finish(fs_info); + btrfs_warn(fs_info, + "cannot activate swapfile because subvolume %llu is being deleted", + root->root_key.objectid); + return -EPERM; + } atomic_inc(&root->nr_swapfiles); + spin_unlock(&root->root_item_lock); isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 238cee5b5254..be6c24577dbe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1239,7 +1239,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em) } static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, - bool locked) + u32 extent_thresh, u64 newer_than, bool locked) { struct extent_map *next; bool ret = false; @@ -1249,11 +1249,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, return false; /* - * We want to check if the next extent can be merged with the current - * one, which can be an extent created in a past generation, so we pass - * a minimum generation of 0 to defrag_lookup_extent(). + * Here we need to pass @newer_then when checking the next extent, or + * we will hit a case we mark current extent for defrag, but the next + * one will not be a target. + * This will just cause extra IO without really reducing the fragments. */ - next = defrag_lookup_extent(inode, em->start + em->len, 0, locked); + next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked); /* No more em or hole */ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) goto out; @@ -1265,6 +1266,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, */ if (next->len >= get_extent_max_capacity(em)) goto out; + /* Skip older extent */ + if (next->generation < newer_than) + goto out; + /* Also check extent size */ + if (next->len >= extent_thresh) + goto out; + ret = true; out: free_extent_map(next); @@ -1470,7 +1478,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto next; next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, - locked); + extent_thresh, newer_than, locked); if (!next_mergeable) { struct defrag_target_range *last; @@ -5448,8 +5456,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_fs_info(fs_info, argp); case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(fs_info, argp); - case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_TREE_SEARCH: return btrfs_ioctl_tree_search(inode, argp); case BTRFS_IOC_TREE_SEARCH_V2: diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 04a88bfe4fcf..998e3f180d90 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -645,7 +645,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len, int ret; /* - * Lock destination range to serialize with concurrent readpages() and + * Lock destination range to serialize with concurrent readahead() and * source range to serialize with relocation. */ btrfs_double_extent_lock(src, loff, dst, dst_loff, len); @@ -739,7 +739,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, } /* - * Lock destination range to serialize with concurrent readpages() and + * Lock destination range to serialize with concurrent readahead() and * source range to serialize with relocation. */ btrfs_double_extent_lock(src, off, inode, destoff, len); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1be7cb2f955f..a8cc736731fd 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1896,23 +1896,18 @@ static void update_dev_time(const char *device_path) path_put(&path); } -static int btrfs_rm_dev_item(struct btrfs_device *device) +static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans, + struct btrfs_device *device) { struct btrfs_root *root = device->fs_info->chunk_root; int ret; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_trans_handle *trans; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); - } key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.type = BTRFS_DEV_ITEM_KEY; key.offset = device->devid; @@ -1923,21 +1918,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device) if (ret) { if (ret > 0) ret = -ENOENT; - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); goto out; } ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - } - out: btrfs_free_path(path); - if (!ret) - ret = btrfs_commit_transaction(trans); return ret; } @@ -2078,6 +2064,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, struct block_device **bdev, fmode_t *mode) { + struct btrfs_trans_handle *trans; struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2098,7 +2085,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1); if (ret) - goto out; + return ret; device = btrfs_find_device(fs_info->fs_devices, args); if (!device) { @@ -2106,27 +2093,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; else ret = -ENOENT; - goto out; + return ret; } if (btrfs_pinned_by_swapfile(fs_info, device)) { btrfs_warn_in_rcu(fs_info, "cannot remove device %s (devid %llu) due to active swapfile", rcu_str_deref(device->name), device->devid); - ret = -ETXTBSY; - goto out; + return -ETXTBSY; } - if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { - ret = BTRFS_ERROR_DEV_TGT_REPLACE; - goto out; - } + if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) + return BTRFS_ERROR_DEV_TGT_REPLACE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && - fs_info->fs_devices->rw_devices == 1) { - ret = BTRFS_ERROR_DEV_ONLY_WRITABLE; - goto out; - } + fs_info->fs_devices->rw_devices == 1) + return BTRFS_ERROR_DEV_ONLY_WRITABLE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); @@ -2139,14 +2121,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, if (ret) goto error_undo; - /* - * TODO: the superblock still includes this device in its num_devices - * counter although write_all_supers() is not locked out. This - * could give a filesystem state which requires a degraded mount. - */ - ret = btrfs_rm_dev_item(device); - if (ret) + trans = btrfs_start_transaction(fs_info->chunk_root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); goto error_undo; + } + + ret = btrfs_rm_dev_item(trans, device); + if (ret) { + /* Any error in dev item removal is critical */ + btrfs_crit(fs_info, + "failed to remove device item for devid %llu: %d", + device->devid, ret); + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); btrfs_scrub_cancel_dev(device); @@ -2229,7 +2219,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, free_fs_devices(cur_devices); } -out: + ret = btrfs_commit_transaction(trans); + return ret; error_undo: @@ -2240,7 +2231,7 @@ error_undo: device->fs_devices->rw_devices++; mutex_unlock(&fs_info->chunk_mutex); } - goto out; + return ret; } void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev) @@ -4439,10 +4430,12 @@ static int balance_kthread(void *data) struct btrfs_fs_info *fs_info = data; int ret = 0; + sb_start_write(fs_info->sb); mutex_lock(&fs_info->balance_mutex); if (fs_info->balance_ctl) ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL); mutex_unlock(&fs_info->balance_mutex); + sb_end_write(fs_info->sb); return ret; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b7b5fac1c779..1b1b310c3c51 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1801,7 +1801,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, map = em->map_lookup; /* We only support single profile for now */ - ASSERT(map->num_stripes == 1); device = map->stripes[0].dev; free_extent_map(em); @@ -1976,18 +1975,16 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) { + struct btrfs_fs_info *fs_info = fs_devices->fs_info; struct btrfs_device *device; bool ret = false; - if (!btrfs_is_zoned(fs_devices->fs_info)) + if (!btrfs_is_zoned(fs_info)) return true; - /* Non-single profiles are not supported yet */ - ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0); - /* Check if there is a device with active zones left */ - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) { + mutex_lock(&fs_info->chunk_mutex); + list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { struct btrfs_zoned_device_info *zinfo = device->zone_info; if (!device->bdev) @@ -1999,7 +1996,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) break; } } - mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index d67fbe063a3a..2b5561ae5d0b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2352,8 +2352,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size) if (err) goto out; - err = pagecache_write_begin(NULL, mapping, size, 0, - AOP_FLAG_CONT_EXPAND, &page, &fsdata); + err = pagecache_write_begin(NULL, mapping, size, 0, 0, &page, &fsdata); if (err) goto out; diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index bc7c7a7d9260..9dc81e781f2b 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -380,18 +380,18 @@ presubmission_error: * Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ -static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subrequest *subreq, +static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *subreq, loff_t i_size) { enum cachefiles_prepare_read_trace why; - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct netfs_cache_resources *cres = &rreq->cache_resources; struct cachefiles_object *object; struct cachefiles_cache *cache; struct fscache_cookie *cookie = fscache_cres_cookie(cres); const struct cred *saved_cred; struct file *file = cachefiles_cres_file(cres); - enum netfs_read_source ret = NETFS_DOWNLOAD_FROM_SERVER; + enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER; loff_t off, to; ino_t ino = file ? file_inode(file)->i_ino : 0; @@ -404,7 +404,7 @@ static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subreque } if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) { - __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); why = cachefiles_trace_read_no_data; goto out_no_object; } @@ -473,7 +473,7 @@ static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subreque goto out; download_and_store: - __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __set_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); out: cachefiles_end_secure(cache, saved_cred); out_no_object: diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index f256c8aff7bb..ca9f3e4ec4b3 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -57,6 +57,16 @@ static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, trace_cachefiles_mark_inactive(object, inode); } +static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + + inode_lock(inode); + __cachefiles_unmark_inode_in_use(object, dentry); + inode_unlock(inode); +} + /* * Unmark a backing inode and tell cachefilesd that there's something that can * be culled. @@ -68,9 +78,7 @@ void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, struct inode *inode = file_inode(file); if (inode) { - inode_lock(inode); - __cachefiles_unmark_inode_in_use(object, file->f_path.dentry); - inode_unlock(inode); + cachefiles_do_unmark_inode_in_use(object, file->f_path.dentry); if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { atomic_long_add(inode->i_blocks, &cache->b_released); @@ -484,7 +492,7 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) object, d_backing_inode(path.dentry), ret, cachefiles_trace_trunc_error); file = ERR_PTR(ret); - goto out_dput; + goto out_unuse; } } @@ -494,15 +502,20 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, d_backing_inode(path.dentry), PTR_ERR(file), cachefiles_trace_open_error); - goto out_dput; + goto out_unuse; } if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { fput(file); pr_notice("Cache does not support read_iter and write_iter\n"); file = ERR_PTR(-EINVAL); + goto out_unuse; } + goto out_dput; + +out_unuse: + cachefiles_do_unmark_inode_in_use(object, path.dentry); out_dput: dput(path.dentry); out: @@ -590,14 +603,16 @@ static bool cachefiles_open_file(struct cachefiles_object *object, check_failed: fscache_cookie_lookup_negative(object->cookie); cachefiles_unmark_inode_in_use(object, file); - if (ret == -ESTALE) { - fput(file); - dput(dentry); + fput(file); + dput(dentry); + if (ret == -ESTALE) return cachefiles_create_file(object); - } + return false; + error_fput: fput(file); error: + cachefiles_do_unmark_inode_in_use(object, dentry); dput(dentry); return false; } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 35465109d9c4..00b087c14995 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -203,7 +203,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) if (!buf) return false; buf->reserved = cpu_to_be32(0); - memcpy(buf->data, p, len); + memcpy(buf->data, p, volume->vcookie->coherency_len); ret = cachefiles_inject_write_error(); if (ret == 0) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c7a0ab0d298b..aa25bffd4823 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -182,7 +182,7 @@ static int ceph_releasepage(struct page *page, gfp_t gfp) return 1; } -static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq) +static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) { struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); @@ -199,7 +199,7 @@ static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq) rreq->len = roundup(rreq->len, lo->stripe_unit); } -static bool ceph_netfs_clamp_length(struct netfs_read_subrequest *subreq) +static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq) { struct inode *inode = subreq->rreq->inode; struct ceph_fs_client *fsc = ceph_inode_to_client(inode); @@ -218,7 +218,7 @@ static void finish_netfs_read(struct ceph_osd_request *req) { struct ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode); struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0); - struct netfs_read_subrequest *subreq = req->r_priv; + struct netfs_io_subrequest *subreq = req->r_priv; int num_pages; int err = req->r_result; @@ -244,9 +244,9 @@ static void finish_netfs_read(struct ceph_osd_request *req) iput(req->r_inode); } -static bool ceph_netfs_issue_op_inline(struct netfs_read_subrequest *subreq) +static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) { - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct inode *inode = rreq->inode; struct ceph_mds_reply_info_parsed *rinfo; struct ceph_mds_reply_info_in *iinfo; @@ -258,7 +258,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_read_subrequest *subreq) size_t len; __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); if (subreq->start >= inode->i_size) goto out; @@ -297,9 +297,9 @@ out: return true; } -static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq) +static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) { - struct netfs_read_request *rreq = subreq->rreq; + struct netfs_io_request *rreq = subreq->rreq; struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); @@ -353,6 +353,45 @@ out: dout("%s: result %d\n", __func__, err); } +static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) +{ + struct inode *inode = rreq->inode; + int got = 0, want = CEPH_CAP_FILE_CACHE; + int ret = 0; + + if (rreq->origin != NETFS_READAHEAD) + return 0; + + if (file) { + struct ceph_rw_context *rw_ctx; + struct ceph_file_info *fi = file->private_data; + + rw_ctx = ceph_find_rw_context(fi); + if (rw_ctx) + return 0; + } + + /* + * readahead callers do not necessarily hold Fcb caps + * (e.g. fadvise, madvise). + */ + ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got); + if (ret < 0) { + dout("start_read %p, error getting cap\n", inode); + return ret; + } + + if (!(got & want)) { + dout("start_read %p, no cache cap\n", inode); + return -EACCES; + } + if (ret == 0) + return -EACCES; + + rreq->netfs_priv = (void *)(uintptr_t)got; + return 0; +} + static void ceph_readahead_cleanup(struct address_space *mapping, void *priv) { struct inode *inode = mapping->host; @@ -363,64 +402,16 @@ static void ceph_readahead_cleanup(struct address_space *mapping, void *priv) ceph_put_cap_refs(ci, got); } -static const struct netfs_read_request_ops ceph_netfs_read_ops = { - .is_cache_enabled = ceph_is_cache_enabled, +const struct netfs_request_ops ceph_netfs_ops = { + .init_request = ceph_init_request, .begin_cache_operation = ceph_begin_cache_operation, - .issue_op = ceph_netfs_issue_op, + .issue_read = ceph_netfs_issue_read, .expand_readahead = ceph_netfs_expand_readahead, .clamp_length = ceph_netfs_clamp_length, .check_write_begin = ceph_netfs_check_write_begin, .cleanup = ceph_readahead_cleanup, }; -/* read a single page, without unlocking it. */ -static int ceph_readpage(struct file *file, struct page *subpage) -{ - struct folio *folio = page_folio(subpage); - struct inode *inode = file_inode(file); - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_vino vino = ceph_vino(inode); - size_t len = folio_size(folio); - u64 off = folio_file_pos(folio); - - dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n inline %d", - vino.ino, vino.snap, file, off, len, folio, folio_index(folio), - ci->i_inline_version != CEPH_INLINE_NONE); - - return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL); -} - -static void ceph_readahead(struct readahead_control *ractl) -{ - struct inode *inode = file_inode(ractl->file); - struct ceph_file_info *fi = ractl->file->private_data; - struct ceph_rw_context *rw_ctx; - int got = 0; - int ret = 0; - - if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE) - return; - - rw_ctx = ceph_find_rw_context(fi); - if (!rw_ctx) { - /* - * readahead callers do not necessarily hold Fcb caps - * (e.g. fadvise, madvise). - */ - int want = CEPH_CAP_FILE_CACHE; - - ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got); - if (ret < 0) - dout("start_read %p, error getting cap\n", inode); - else if (!(got & want)) - dout("start_read %p, no cache cap\n", inode); - - if (ret <= 0) - return; - } - netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got); -} - #ifdef CONFIG_CEPH_FSCACHE static void ceph_set_page_fscache(struct page *page) { @@ -1327,8 +1318,7 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, struct folio *folio = NULL; int r; - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL, - &ceph_netfs_read_ops, NULL); + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL); if (r == 0) folio_wait_fscache(folio); if (r < 0) { @@ -1382,8 +1372,8 @@ out: } const struct address_space_operations ceph_aops = { - .readpage = ceph_readpage, - .readahead = ceph_readahead, + .readpage = netfs_readpage, + .readahead = netfs_readahead, .writepage = ceph_writepage, .writepages = ceph_writepages_start, .write_begin = ceph_write_begin, diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 7d22850623ef..ddea99922073 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -29,26 +29,25 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) if (!(inode->i_state & I_NEW)) return; - WARN_ON_ONCE(ci->fscache); + WARN_ON_ONCE(ci->netfs_ctx.cache); - ci->fscache = fscache_acquire_cookie(fsc->fscache, 0, - &ci->i_vino, sizeof(ci->i_vino), - &ci->i_version, sizeof(ci->i_version), - i_size_read(inode)); + ci->netfs_ctx.cache = + fscache_acquire_cookie(fsc->fscache, 0, + &ci->i_vino, sizeof(ci->i_vino), + &ci->i_version, sizeof(ci->i_version), + i_size_read(inode)); } -void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci) { - struct fscache_cookie *cookie = ci->fscache; - - fscache_relinquish_cookie(cookie, false); + fscache_relinquish_cookie(ceph_fscache_cookie(ci), false); } void ceph_fscache_use_cookie(struct inode *inode, bool will_modify) { struct ceph_inode_info *ci = ceph_inode(inode); - fscache_use_cookie(ci->fscache, will_modify); + fscache_use_cookie(ceph_fscache_cookie(ci), will_modify); } void ceph_fscache_unuse_cookie(struct inode *inode, bool update) @@ -58,9 +57,10 @@ void ceph_fscache_unuse_cookie(struct inode *inode, bool update) if (update) { loff_t i_size = i_size_read(inode); - fscache_unuse_cookie(ci->fscache, &ci->i_version, &i_size); + fscache_unuse_cookie(ceph_fscache_cookie(ci), + &ci->i_version, &i_size); } else { - fscache_unuse_cookie(ci->fscache, NULL, NULL); + fscache_unuse_cookie(ceph_fscache_cookie(ci), NULL, NULL); } } @@ -69,14 +69,14 @@ void ceph_fscache_update(struct inode *inode) struct ceph_inode_info *ci = ceph_inode(inode); loff_t i_size = i_size_read(inode); - fscache_update_cookie(ci->fscache, &ci->i_version, &i_size); + fscache_update_cookie(ceph_fscache_cookie(ci), &ci->i_version, &i_size); } void ceph_fscache_invalidate(struct inode *inode, bool dio_write) { struct ceph_inode_info *ci = ceph_inode(inode); - fscache_invalidate(ceph_inode(inode)->fscache, + fscache_invalidate(ceph_fscache_cookie(ci), &ci->i_version, i_size_read(inode), dio_write ? FSCACHE_INVAL_DIO_WRITE : 0); } diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index b90f3016994d..7255b790a4c1 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -26,14 +26,9 @@ void ceph_fscache_unuse_cookie(struct inode *inode, bool update); void ceph_fscache_update(struct inode *inode); void ceph_fscache_invalidate(struct inode *inode, bool dio_write); -static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) -{ - ci->fscache = NULL; -} - static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci) { - return ci->fscache; + return netfs_i_cookie(&ci->vfs_inode); } static inline void ceph_fscache_resize(struct inode *inode, loff_t to) @@ -62,7 +57,7 @@ static inline int ceph_fscache_dirty_folio(struct address_space *mapping, return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci)); } -static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq) +static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq) { struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode)); @@ -91,10 +86,6 @@ static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) { } -static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) -{ -} - static inline void ceph_fscache_register_inode_cookie(struct inode *inode) { } @@ -144,7 +135,7 @@ static inline bool ceph_is_cache_enabled(struct inode *inode) return false; } -static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq) +static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq) { return -ENOBUFS; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index feb75eb1cd82..6c9e837aa1d3 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1869,7 +1869,7 @@ retry_snap: * are pending vmtruncate. So write and vmtruncate * can not run at the same time */ - written = generic_perform_write(file, from, pos); + written = generic_perform_write(iocb, from); if (likely(written >= 0)) iocb->ki_pos = pos + written; ceph_end_io_write(inode); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index d80911dc91c2..63113e2a4890 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -459,6 +459,9 @@ struct inode *ceph_alloc_inode(struct super_block *sb) dout("alloc_inode %p\n", &ci->vfs_inode); + /* Set parameters for the netfs library */ + netfs_i_context_init(&ci->vfs_inode, &ceph_netfs_ops); + spin_lock_init(&ci->i_ceph_lock); ci->i_version = 0; @@ -544,9 +547,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_WORK(&ci->i_work, ceph_inode_work); ci->i_work_mask = 0; memset(&ci->i_btime, '\0', sizeof(ci->i_btime)); - - ceph_fscache_inode_init(ci); - return &ci->vfs_inode; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a1ecc410a495..20ceab74e871 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -17,13 +17,11 @@ #include <linux/posix_acl.h> #include <linux/refcount.h> #include <linux/security.h> +#include <linux/netfs.h> +#include <linux/fscache.h> #include <linux/ceph/libceph.h> -#ifdef CONFIG_CEPH_FSCACHE -#include <linux/fscache.h> -#endif - /* large granularity for statfs utilization stats to facilitate * large volume sizes on 32-bit machines. */ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */ @@ -318,6 +316,11 @@ struct ceph_inode_xattrs_info { * Ceph inode. */ struct ceph_inode_info { + struct { + /* These must be contiguous */ + struct inode vfs_inode; + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; struct ceph_vino i_vino; /* ceph ino + snap */ spinlock_t i_ceph_lock; @@ -428,11 +431,6 @@ struct ceph_inode_info { struct work_struct i_work; unsigned long i_work_mask; - -#ifdef CONFIG_CEPH_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; /* at end */ }; static inline struct ceph_inode_info * @@ -1216,6 +1214,7 @@ extern void __ceph_touch_fmode(struct ceph_inode_info *ci, /* addr.c */ extern const struct address_space_operations ceph_aops; +extern const struct netfs_request_ops ceph_netfs_ops; extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); extern int ceph_uninline_data(struct file *file); extern int ceph_pool_perm_check(struct inode *inode, int need); diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index ea00e1a91250..9d334816eac0 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -94,7 +94,7 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon) le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics), le32_to_cpu(tcon->fsAttrInfo.Attributes), le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength), - tcon->tidStatus); + tcon->status); if (dev_type == FILE_DEVICE_DISK) seq_puts(m, " type: DISK "); else if (dev_type == FILE_DEVICE_CD_ROM) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d1211ad4e85b..2b1a1c029c75 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -266,22 +266,24 @@ static void cifs_kill_sb(struct super_block *sb) * before we kill the sb. */ if (cifs_sb->root) { + for (node = rb_first(root); node; node = rb_next(node)) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + tcon = tlink_tcon(tlink); + if (IS_ERR(tcon)) + continue; + cfid = &tcon->crfid; + mutex_lock(&cfid->fid_mutex); + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; + } + mutex_unlock(&cfid->fid_mutex); + } + + /* finally release root dentry */ dput(cifs_sb->root); cifs_sb->root = NULL; } - node = rb_first(root); - while (node != NULL) { - tlink = rb_entry(node, struct tcon_link, tl_rbnode); - tcon = tlink_tcon(tlink); - cfid = &tcon->crfid; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - mutex_unlock(&cfid->fid_mutex); - node = rb_next(node); - } kill_anon_super(sb); cifs_umount(cifs_sb); @@ -699,14 +701,14 @@ static void cifs_umount_begin(struct super_block *sb) tcon = cifs_sb_master_tcon(cifs_sb); spin_lock(&cifs_tcp_ses_lock); - if ((tcon->tc_count > 1) || (tcon->tidStatus == CifsExiting)) { + if ((tcon->tc_count > 1) || (tcon->status == TID_EXITING)) { /* we have other mounts to same share or we have already tried to force umount this and woken up all waiting network requests, nothing to do */ spin_unlock(&cifs_tcp_ses_lock); return; } else if (tcon->tc_count == 1) - tcon->tidStatus = CifsExiting; + tcon->status = TID_EXITING; spin_unlock(&cifs_tcp_ses_lock); /* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */ @@ -944,7 +946,7 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t rc; struct inode *inode = file_inode(iocb->ki_filp); - if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return cifs_user_readv(iocb, iter); rc = cifs_revalidate_mapping(inode); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 15a5c5db038b..c0542bdcd06b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,5 +153,5 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ #define SMB3_PRODUCT_BUILD 35 -#define CIFS_VERSION "2.35" +#define CIFS_VERSION "2.36" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 48b343d03430..8de977c359b1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -16,6 +16,7 @@ #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/utsname.h> +#include <linux/netfs.h> #include "cifs_fs_sb.h" #include "cifsacl.h" #include <crypto/internal/hash.h> @@ -115,10 +116,18 @@ enum statusEnum { CifsInNegotiate, CifsNeedSessSetup, CifsInSessSetup, - CifsNeedTcon, - CifsInTcon, - CifsNeedFilesInvalidate, - CifsInFilesInvalidate +}; + +/* associated with each tree connection to the server */ +enum tid_status_enum { + TID_NEW = 0, + TID_GOOD, + TID_EXITING, + TID_NEED_RECON, + TID_NEED_TCON, + TID_IN_TCON, + TID_NEED_FILES_INVALIDATE, /* currently unused */ + TID_IN_FILES_INVALIDATE }; enum securityEnum { @@ -852,13 +861,7 @@ compare_mid(__u16 mid, const struct smb_hdr *smb) #define CIFS_MAX_RFC1002_WSIZE ((1<<17) - 1 - sizeof(WRITE_REQ) + 4) #define CIFS_MAX_RFC1002_RSIZE ((1<<17) - 1 - sizeof(READ_RSP) + 4) -/* - * The default wsize is 1M. find_get_pages seems to return a maximum of 256 - * pages in a single call. With PAGE_SIZE == 4k, this means we can fill - * a single wsize request with a single call. - */ #define CIFS_DEFAULT_IOSIZE (1024 * 1024) -#define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024) /* * Windows only supports a max of 60kb reads and 65535 byte writes. Default to @@ -1038,7 +1041,7 @@ struct cifs_tcon { char *password; /* for share-level security */ __u32 tid; /* The 4 byte tree id */ __u16 Flags; /* optional support bits */ - enum statusEnum tidStatus; + enum tid_status_enum status; atomic_t num_smbs_sent; union { struct { @@ -1402,6 +1405,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); */ struct cifsInodeInfo { + struct { + /* These must be contiguous */ + struct inode vfs_inode; /* the VFS's inode record */ + struct netfs_i_context netfs_ctx; /* Netfslib context */ + }; bool can_cache_brlcks; struct list_head llist; /* locks helb by this inode */ /* @@ -1432,10 +1440,6 @@ struct cifsInodeInfo { u64 uniqueid; /* server inode number */ u64 createtime; /* creation time on server */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for this inode */ -#ifdef CONFIG_CIFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; struct list_head deferred_closes; /* list of deferred closes */ spinlock_t deferred_lock; /* protection on deferred list */ bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 68b9a436af4b..aeba371c4c70 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -123,18 +123,6 @@ */ #define CIFS_SESS_KEY_SIZE (16) -/* - * Size of the smb3 signing key - */ -#define SMB3_SIGN_KEY_SIZE (16) - -/* - * Size of the smb3 encryption/decryption key storage. - * This size is big enough to store any cipher key types. - */ -#define SMB3_ENC_DEC_KEY_SIZE (32) - -#define CIFS_CLIENT_CHALLENGE_SIZE (8) #define CIFS_SERVER_CHALLENGE_SIZE (8) #define CIFS_HMAC_MD5_HASH_SIZE (16) #define CIFS_CPHTXT_SIZE (16) @@ -1658,7 +1646,7 @@ struct smb_t2_rsp { #define SMB_FIND_FILE_ID_FULL_DIR_INFO 0x105 #define SMB_FIND_FILE_ID_BOTH_DIR_INFO 0x106 #define SMB_FIND_FILE_UNIX 0x202 -#define SMB_FIND_FILE_POSIX_INFO 0x064 +/* #define SMB_FIND_FILE_POSIX_INFO 0x064 */ typedef struct smb_com_transaction2_qpi_req { struct smb_hdr hdr; /* wct = 14+ */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 071e2f21a7db..47e927c4ff8d 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -75,12 +75,11 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) /* only send once per connect */ spin_lock(&cifs_tcp_ses_lock); - if (tcon->ses->status != CifsGood || - tcon->tidStatus != CifsNeedReconnect) { + if ((tcon->ses->status != CifsGood) || (tcon->status != TID_NEED_RECON)) { spin_unlock(&cifs_tcp_ses_lock); return; } - tcon->tidStatus = CifsInFilesInvalidate; + tcon->status = TID_IN_FILES_INVALIDATE; spin_unlock(&cifs_tcp_ses_lock); /* list all files open on tree connection and mark them invalid */ @@ -100,8 +99,8 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) mutex_unlock(&tcon->crfid.fid_mutex); spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsInFilesInvalidate) - tcon->tidStatus = CifsNeedTcon; + if (tcon->status == TID_IN_FILES_INVALIDATE) + tcon->status = TID_NEED_TCON; spin_unlock(&cifs_tcp_ses_lock); /* @@ -136,7 +135,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) * have tcon) are allowed as we start force umount */ spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsExiting) { + if (tcon->status == TID_EXITING) { if (smb_command != SMB_COM_WRITE_ANDX && smb_command != SMB_COM_OPEN_ANDX && smb_command != SMB_COM_TREE_DISCONNECT) { @@ -597,7 +596,7 @@ CIFSSMBNegotiate(const unsigned int xid, set_credits(server, server->maxReq); /* probably no need to store and check maxvcs */ server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize); - /* set up max_read for readpages check */ + /* set up max_read for readahead check */ server->max_read = server->maxBuf; server->max_rw = le32_to_cpu(pSMBr->MaxRawSize); cifs_dbg(NOISY, "Max buf = %d\n", ses->server->maxBuf); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9964c3634322..902e8c6c0f9c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -245,7 +245,7 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { tcon->need_reconnect = true; - tcon->tidStatus = CifsNeedReconnect; + tcon->status = TID_NEED_RECON; } if (ses->tcon_ipc) ses->tcon_ipc->need_reconnect = true; @@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ return rc; } -static int -reconnect_dfs_server(struct TCP_Server_Info *server, - bool mark_smb_session) +static int reconnect_dfs_server(struct TCP_Server_Info *server) { int rc = 0; const char *refpath = server->current_fullpath + 1; @@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server, if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); + /* + * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a + * different server or share during failover. It could be improved by adding some logic to + * only do that in case it connects to a different server or share, though. + */ + cifs_mark_tcp_ses_conns_for_reconnect(server, true); cifs_abort_connection(server); @@ -537,7 +540,7 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) } spin_unlock(&cifs_tcp_ses_lock); - return reconnect_dfs_server(server, mark_smb_session); + return reconnect_dfs_server(server); } #else int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) @@ -1046,7 +1049,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_hdr_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_server_dbg(FYI, "%s: added %u credits total=%d\n", @@ -2207,7 +2210,7 @@ get_ses_fail: static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) { - if (tcon->tidStatus == CifsExiting) + if (tcon->status == TID_EXITING) return 0; if (strncmp(tcon->treeName, ctx->UNC, MAX_TREE_SIZE)) return 0; @@ -3513,6 +3516,9 @@ static int connect_dfs_target(struct mount_ctx *mnt_ctx, const char *full_path, struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; char *oldmnt = cifs_sb->ctx->mount_options; + cifs_dbg(FYI, "%s: full_path=%s ref_path=%s target=%s\n", __func__, full_path, ref_path, + dfs_cache_get_tgt_name(tit)); + rc = dfs_cache_get_tgt_referral(ref_path, tit, &ref); if (rc) goto out; @@ -3611,13 +3617,18 @@ static int __follow_dfs_link(struct mount_ctx *mnt_ctx) if (rc) goto out; - /* Try all dfs link targets */ + /* Try all dfs link targets. If an I/O fails from currently connected DFS target with an + * error other than STATUS_PATH_NOT_COVERED (-EREMOTE), then retry it from other targets as + * specified in MS-DFSC "3.1.5.2 I/O Operation to Target Fails with an Error Other Than + * STATUS_PATH_NOT_COVERED." + */ for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(&tl); tit; tit = dfs_cache_get_next_tgt(&tl, tit)) { rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->leaf_fullpath + 1, tit); if (!rc) { rc = is_path_remote(mnt_ctx); - break; + if (!rc || rc == -EREMOTE) + break; } } @@ -3691,7 +3702,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; rc = is_path_remote(&mnt_ctx); - if (rc == -EREMOTE) + if (rc) rc = follow_dfs_link(&mnt_ctx); if (rc) goto error; @@ -4457,7 +4468,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco */ if (rc && server->current_fullpath != server->origin_fullpath) { server->current_fullpath = server->origin_fullpath; - cifs_reconnect(tcon->ses->server, true); + cifs_signal_cifsd_for_reconnect(server, true); } dfs_cache_free_tgts(tl); @@ -4478,12 +4489,12 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&cifs_tcp_ses_lock); if (tcon->ses->status != CifsGood || - (tcon->tidStatus != CifsNew && - tcon->tidStatus != CifsNeedTcon)) { + (tcon->status != TID_NEW && + tcon->status != TID_NEED_TCON)) { spin_unlock(&cifs_tcp_ses_lock); return 0; } - tcon->tidStatus = CifsInTcon; + tcon->status = TID_IN_TCON; spin_unlock(&cifs_tcp_ses_lock); tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); @@ -4524,13 +4535,13 @@ out: if (rc) { spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsInTcon) - tcon->tidStatus = CifsNeedTcon; + if (tcon->status == TID_IN_TCON) + tcon->status = TID_NEED_TCON; spin_unlock(&cifs_tcp_ses_lock); } else { spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsInTcon) - tcon->tidStatus = CifsGood; + if (tcon->status == TID_IN_TCON) + tcon->status = TID_GOOD; spin_unlock(&cifs_tcp_ses_lock); tcon->need_reconnect = false; } @@ -4546,24 +4557,24 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&cifs_tcp_ses_lock); if (tcon->ses->status != CifsGood || - (tcon->tidStatus != CifsNew && - tcon->tidStatus != CifsNeedTcon)) { + (tcon->status != TID_NEW && + tcon->status != TID_NEED_TCON)) { spin_unlock(&cifs_tcp_ses_lock); return 0; } - tcon->tidStatus = CifsInTcon; + tcon->status = TID_IN_TCON; spin_unlock(&cifs_tcp_ses_lock); rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, nlsc); if (rc) { spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsInTcon) - tcon->tidStatus = CifsNeedTcon; + if (tcon->status == TID_IN_TCON) + tcon->status = TID_NEED_TCON; spin_unlock(&cifs_tcp_ses_lock); } else { spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsInTcon) - tcon->tidStatus = CifsGood; + if (tcon->status == TID_IN_TCON) + tcon->status = TID_GOOD; spin_unlock(&cifs_tcp_ses_lock); tcon->need_reconnect = false; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 60f43bff7ccb..d511a78383c3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4210,13 +4210,19 @@ cifs_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; + /* Wait for the page to be written to the cache before we allow it to + * be modified. We then assume the entire page will need writing back. + */ #ifdef CONFIG_CIFS_FSCACHE if (PageFsCache(page) && wait_on_page_fscache_killable(page) < 0) return VM_FAULT_RETRY; #endif - lock_page(page); + wait_on_page_writeback(page); + + if (lock_page_killable(page) < 0) + return VM_FAULT_RETRY; return VM_FAULT_LOCKED; } diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 33af72e0ac0c..a638b29e9062 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -103,7 +103,7 @@ void cifs_fscache_get_inode_cookie(struct inode *inode) cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd); - cifsi->fscache = + cifsi->netfs_ctx.cache = fscache_acquire_cookie(tcon->fscache, 0, &cifsi->uniqueid, sizeof(cifsi->uniqueid), &cd, sizeof(cd), @@ -126,22 +126,15 @@ void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) void cifs_fscache_release_inode_cookie(struct inode *inode) { struct cifsInodeInfo *cifsi = CIFS_I(inode); + struct fscache_cookie *cookie = cifs_inode_cookie(inode); - if (cifsi->fscache) { - cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache); - fscache_relinquish_cookie(cifsi->fscache, false); - cifsi->fscache = NULL; + if (cookie) { + cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cookie); + fscache_relinquish_cookie(cookie, false); + cifsi->netfs_ctx.cache = NULL; } } -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * Fallback page reading interface. */ diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 55129908e2c1..52355c0912ae 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -61,7 +61,7 @@ void cifs_fscache_fill_coherency(struct inode *inode, static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { - return CIFS_I(inode)->fscache; + return netfs_i_cookie(inode); } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 60d853c92f6a..2f9e7d2f81b6 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -49,7 +49,7 @@ static void cifs_set_ops(struct inode *inode) inode->i_fop = &cifs_file_ops; } - /* check if server can support readpages */ + /* check if server can support readahead */ if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read < PAGE_SIZE + MAX_CIFS_HDR_SIZE) inode->i_data.a_ops = &cifs_addr_ops_smallbuf; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 852e54ee82c2..bbdf3281559c 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -85,6 +85,9 @@ parse_mf_symlink(const u8 *buf, unsigned int buf_len, unsigned int *_link_len, if (rc != 1) return -EINVAL; + if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN) + return -EINVAL; + rc = symlink_hash(link_len, link_str, md5_hash); if (rc) { cifs_dbg(FYI, "%s: MD5 hash failure: %d\n", __func__, rc); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 56598f7dbe00..afaf59c22193 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -116,7 +116,7 @@ tconInfoAlloc(void) } atomic_inc(&tconInfoAllocCount); - ret_buf->tidStatus = CifsNew; + ret_buf->status = TID_NEW; ++ret_buf->tc_count; INIT_LIST_HEAD(&ret_buf->openFileList); INIT_LIST_HEAD(&ret_buf->tcon_list); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index ebe236b9d9f5..235aa1b395eb 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) if (class == ERRSRV && code == ERRbaduid) { cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n", code); - cifs_reconnect(mid->server, false); + cifs_signal_cifsd_for_reconnect(mid->server, false); } } diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index 4125fd113cfb..82e916ad167c 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -41,15 +41,4 @@ #define END_OF_CHAIN 4 #define RELATED_REQUEST 8 -#define SMB2_SIGNATURE_SIZE (16) -#define SMB2_NTLMV2_SESSKEY_SIZE (16) -#define SMB2_HMACSHA256_SIZE (32) -#define SMB2_CMACAES_SIZE (16) -#define SMB3_SIGNKEY_SIZE (16) -#define SMB3_GCM128_CRYPTKEY_SIZE (16) -#define SMB3_GCM256_CRYPTKEY_SIZE (32) - -/* Maximum buffer size value we can send with 1 credit */ -#define SMB2_MAX_BUFFER_SIZE 65536 - #endif /* _SMB2_GLOB_H */ diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index b25623e3fe3d..3fe47a88f47d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -150,16 +150,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) struct smb2_transform_hdr *thdr = (struct smb2_transform_hdr *)buf; struct cifs_ses *ses = NULL; + struct cifs_ses *iter; /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) { - if (ses->Suid == le64_to_cpu(thdr->SessionId)) + list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) { + if (iter->Suid == le64_to_cpu(thdr->SessionId)) { + ses = iter; break; + } } spin_unlock(&cifs_tcp_ses_lock); - if (list_entry_is_head(ses, &srvr->smb_ses_list, - smb_ses_list)) { + if (!ses) { cifs_dbg(VFS, "no decryption - session id not found\n"); return 1; } @@ -203,7 +205,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) { if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 || - pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2)) { + pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) { /* error packets have 9 byte structure size */ cifs_dbg(VFS, "Invalid response size %u for command %d\n", le16_to_cpu(pdu->StructureSize2), command); @@ -303,7 +305,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) /* error responses do not have data area */ if (shdr->Status && shdr->Status != STATUS_MORE_PROCESSING_REQUIRED && (((struct smb2_err_rsp *)shdr)->StructureSize) == - SMB2_ERROR_STRUCTURE_SIZE2) + SMB2_ERROR_STRUCTURE_SIZE2_LE) return NULL; /* @@ -478,11 +480,11 @@ smb2_get_lease_state(struct cifsInodeInfo *cinode) __le32 lease = 0; if (CIFS_CACHE_WRITE(cinode)) - lease |= SMB2_LEASE_WRITE_CACHING; + lease |= SMB2_LEASE_WRITE_CACHING_LE; if (CIFS_CACHE_HANDLE(cinode)) - lease |= SMB2_LEASE_HANDLE_CACHING; + lease |= SMB2_LEASE_HANDLE_CACHING_LE; if (CIFS_CACHE_READ(cinode)) - lease |= SMB2_LEASE_READ_CACHING; + lease |= SMB2_LEASE_READ_CACHING_LE; return lease; } @@ -832,8 +834,8 @@ smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *serve rc = __smb2_handle_cancelled_cmd(tcon, le16_to_cpu(hdr->Command), le64_to_cpu(hdr->MessageId), - le64_to_cpu(rsp->PersistentFileId), - le64_to_cpu(rsp->VolatileFileId)); + rsp->PersistentFileId, + rsp->VolatileFileId); if (rc) cifs_put_tcon(tcon); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 891b11576e55..a67df8eaf702 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -86,6 +86,9 @@ smb2_add_credits(struct TCP_Server_Info *server, if (*val > 65000) { *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ pr_warn_once("server overflowed SMB3 credits\n"); + trace_smb3_overflow_credits(server->CurrentMid, + server->conn_id, server->hostname, *val, + add, server->in_flight); } server->in_flight--; if (server->in_flight == 0 && @@ -251,7 +254,7 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_wait_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(credits->value), in_flight); cifs_dbg(FYI, "%s: removed %u credits total=%d\n", __func__, credits->value, scredits); @@ -300,7 +303,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server, spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_adj_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, credits->value - new_val, in_flight); cifs_dbg(FYI, "%s: adjust added %u credits total=%d\n", @@ -897,8 +900,8 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, atomic_inc(&tcon->num_remote_opens); o_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base; - oparms.fid->persistent_fid = le64_to_cpu(o_rsp->PersistentFileId); - oparms.fid->volatile_fid = le64_to_cpu(o_rsp->VolatileFileId); + oparms.fid->persistent_fid = o_rsp->PersistentFileId; + oparms.fid->volatile_fid = o_rsp->VolatileFileId; #ifdef CONFIG_CIFS_DEBUG2 oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ @@ -1192,17 +1195,12 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb) { int rc; - __le16 *utf16_path; struct kvec rsp_iov = {NULL, 0}; int buftype = CIFS_NO_BUFFER; struct smb2_query_info_rsp *rsp; struct smb2_file_full_ea_info *info = NULL; - utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); - if (!utf16_path) - return -ENOMEM; - - rc = smb2_query_info_compound(xid, tcon, utf16_path, + rc = smb2_query_info_compound(xid, tcon, path, FILE_READ_EA, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, @@ -1235,7 +1233,6 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, le32_to_cpu(rsp->OutputBufferLength), ea_name); qeas_exit: - kfree(utf16_path); free_rsp_buf(buftype, rsp_iov.iov_base); return rc; } @@ -1295,7 +1292,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, * the new EA. If not we should not add it since we * would not be able to even read the EAs back. */ - rc = smb2_query_info_compound(xid, tcon, utf16_path, + rc = smb2_query_info_compound(xid, tcon, path, FILE_READ_EA, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, @@ -1643,6 +1640,7 @@ smb2_ioctl_query_info(const unsigned int xid, unsigned int size[2]; void *data[2]; int create_options = is_dir ? CREATE_NOT_FILE : CREATE_NOT_DIR; + void (*free_req1_func)(struct smb_rqst *r); vars = kzalloc(sizeof(*vars), GFP_ATOMIC); if (vars == NULL) @@ -1652,27 +1650,29 @@ smb2_ioctl_query_info(const unsigned int xid, resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; - if (copy_from_user(&qi, arg, sizeof(struct smb_query_info))) - goto e_fault; - + if (copy_from_user(&qi, arg, sizeof(struct smb_query_info))) { + rc = -EFAULT; + goto free_vars; + } if (qi.output_buffer_length > 1024) { - kfree(vars); - return -EINVAL; + rc = -EINVAL; + goto free_vars; } if (!ses || !server) { - kfree(vars); - return -EIO; + rc = -EIO; + goto free_vars; } if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - buffer = memdup_user(arg + sizeof(struct smb_query_info), - qi.output_buffer_length); - if (IS_ERR(buffer)) { - kfree(vars); - return PTR_ERR(buffer); + if (qi.output_buffer_length) { + buffer = memdup_user(arg + sizeof(struct smb_query_info), qi.output_buffer_length); + if (IS_ERR(buffer)) { + rc = PTR_ERR(buffer); + goto free_vars; + } } /* Open */ @@ -1710,45 +1710,45 @@ smb2_ioctl_query_info(const unsigned int xid, rc = SMB2_open_init(tcon, server, &rqst[0], &oplock, &oparms, path); if (rc) - goto iqinf_exit; + goto free_output_buffer; smb2_set_next_command(tcon, &rqst[0]); /* Query */ if (qi.flags & PASSTHRU_FSCTL) { /* Can eventually relax perm check since server enforces too */ - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) { rc = -EPERM; - else { - rqst[1].rq_iov = &vars->io_iov[0]; - rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; - - rc = SMB2_ioctl_init(tcon, server, - &rqst[1], - COMPOUND_FID, COMPOUND_FID, - qi.info_type, true, buffer, - qi.output_buffer_length, - CIFSMaxBufSize - - MAX_SMB2_CREATE_RESPONSE_SIZE - - MAX_SMB2_CLOSE_RESPONSE_SIZE); + goto free_open_req; } + rqst[1].rq_iov = &vars->io_iov[0]; + rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; + + rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID, + qi.info_type, true, buffer, qi.output_buffer_length, + CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE); + free_req1_func = SMB2_ioctl_free; } else if (qi.flags == PASSTHRU_SET_INFO) { /* Can eventually relax perm check since server enforces too */ - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) { rc = -EPERM; - else { - rqst[1].rq_iov = &vars->si_iov[0]; - rqst[1].rq_nvec = 1; - - size[0] = 8; - data[0] = buffer; - - rc = SMB2_set_info_init(tcon, server, - &rqst[1], - COMPOUND_FID, COMPOUND_FID, - current->tgid, - FILE_END_OF_FILE_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); + goto free_open_req; } + if (qi.output_buffer_length < 8) { + rc = -EINVAL; + goto free_open_req; + } + rqst[1].rq_iov = &vars->si_iov[0]; + rqst[1].rq_nvec = 1; + + /* MS-FSCC 2.4.13 FileEndOfFileInformation */ + size[0] = 8; + data[0] = buffer; + + rc = SMB2_set_info_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID, + current->tgid, FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, data, size); + free_req1_func = SMB2_set_info_free; } else if (qi.flags == PASSTHRU_QUERY_INFO) { rqst[1].rq_iov = &vars->qi_iov[0]; rqst[1].rq_nvec = 1; @@ -1759,6 +1759,7 @@ smb2_ioctl_query_info(const unsigned int xid, qi.info_type, qi.additional_information, qi.input_buffer_length, qi.output_buffer_length, buffer); + free_req1_func = SMB2_query_info_free; } else { /* unknown flags */ cifs_tcon_dbg(VFS, "Invalid passthru query flags: 0x%x\n", qi.flags); @@ -1766,7 +1767,7 @@ smb2_ioctl_query_info(const unsigned int xid, } if (rc) - goto iqinf_exit; + goto free_open_req; smb2_set_next_command(tcon, &rqst[1]); smb2_set_related(&rqst[1]); @@ -1777,14 +1778,14 @@ smb2_ioctl_query_info(const unsigned int xid, rc = SMB2_close_init(tcon, server, &rqst[2], COMPOUND_FID, COMPOUND_FID, false); if (rc) - goto iqinf_exit; + goto free_req_1; smb2_set_related(&rqst[2]); rc = compound_send_recv(xid, ses, server, flags, 3, rqst, resp_buftype, rsp_iov); if (rc) - goto iqinf_exit; + goto out; /* No need to bump num_remote_opens since handle immediately closed */ if (qi.flags & PASSTHRU_FSCTL) { @@ -1794,18 +1795,22 @@ smb2_ioctl_query_info(const unsigned int xid, qi.input_buffer_length = le32_to_cpu(io_rsp->OutputCount); if (qi.input_buffer_length > 0 && le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length - > rsp_iov[1].iov_len) - goto e_fault; + > rsp_iov[1].iov_len) { + rc = -EFAULT; + goto out; + } if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) - goto e_fault; + sizeof(qi.input_buffer_length))) { + rc = -EFAULT; + goto out; + } if (copy_to_user((void __user *)pqi + sizeof(struct smb_query_info), (const void *)io_rsp + le32_to_cpu(io_rsp->OutputOffset), qi.input_buffer_length)) - goto e_fault; + rc = -EFAULT; } else { pqi = (struct smb_query_info __user *)arg; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; @@ -1813,28 +1818,30 @@ smb2_ioctl_query_info(const unsigned int xid, qi.input_buffer_length = le32_to_cpu(qi_rsp->OutputBufferLength); if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) - goto e_fault; + sizeof(qi.input_buffer_length))) { + rc = -EFAULT; + goto out; + } if (copy_to_user(pqi + 1, qi_rsp->Buffer, qi.input_buffer_length)) - goto e_fault; + rc = -EFAULT; } - iqinf_exit: - cifs_small_buf_release(rqst[0].rq_iov[0].iov_base); - cifs_small_buf_release(rqst[1].rq_iov[0].iov_base); - cifs_small_buf_release(rqst[2].rq_iov[0].iov_base); +out: free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); - kfree(vars); + SMB2_close_free(&rqst[2]); +free_req_1: + free_req1_func(&rqst[1]); +free_open_req: + SMB2_open_free(&rqst[0]); +free_output_buffer: kfree(buffer); +free_vars: + kfree(vars); return rc; - -e_fault: - rc = -EFAULT; - goto iqinf_exit; } static ssize_t @@ -2407,8 +2414,8 @@ again: cifs_dbg(FYI, "query_dir_first: open failed rc=%d\n", rc); goto qdf_free; } - fid->persistent_fid = le64_to_cpu(op_rsp->PersistentFileId); - fid->volatile_fid = le64_to_cpu(op_rsp->VolatileFileId); + fid->persistent_fid = op_rsp->PersistentFileId; + fid->volatile_fid = op_rsp->VolatileFileId; /* Anything else than ENODATA means a genuine error */ if (rc && rc != -ENODATA) { @@ -2488,7 +2495,7 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_pend_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_dbg(FYI, "%s: status pending add %u credits total=%d\n", @@ -2646,7 +2653,7 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst) */ int smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, - __le16 *utf16_path, u32 desired_access, + const char *path, u32 desired_access, u32 class, u32 type, u32 output_len, struct kvec *rsp, int *buftype, struct cifs_sb_info *cifs_sb) @@ -2664,6 +2671,14 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; int rc; + __le16 *utf16_path; + struct cached_fid *cfid = NULL; + + if (!path) + path = ""; + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return -ENOMEM; if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; @@ -2672,6 +2687,8 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; memset(rsp_iov, 0, sizeof(rsp_iov)); + rc = open_cached_dir(xid, tcon, path, cifs_sb, &cfid); + memset(&open_iov, 0, sizeof(open_iov)); rqst[0].rq_iov = open_iov; rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; @@ -2693,15 +2710,29 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = qi_iov; rqst[1].rq_nvec = 1; - rc = SMB2_query_info_init(tcon, server, - &rqst[1], COMPOUND_FID, COMPOUND_FID, - class, type, 0, - output_len, 0, - NULL); + if (cfid) { + rc = SMB2_query_info_init(tcon, server, + &rqst[1], + cfid->fid->persistent_fid, + cfid->fid->volatile_fid, + class, type, 0, + output_len, 0, + NULL); + } else { + rc = SMB2_query_info_init(tcon, server, + &rqst[1], + COMPOUND_FID, + COMPOUND_FID, + class, type, 0, + output_len, 0, + NULL); + } if (rc) goto qic_exit; - smb2_set_next_command(tcon, &rqst[1]); - smb2_set_related(&rqst[1]); + if (!cfid) { + smb2_set_next_command(tcon, &rqst[1]); + smb2_set_related(&rqst[1]); + } memset(&close_iov, 0, sizeof(close_iov)); rqst[2].rq_iov = close_iov; @@ -2713,9 +2744,15 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, goto qic_exit; smb2_set_related(&rqst[2]); - rc = compound_send_recv(xid, ses, server, - flags, 3, rqst, - resp_buftype, rsp_iov); + if (cfid) { + rc = compound_send_recv(xid, ses, server, + flags, 1, &rqst[1], + &resp_buftype[1], &rsp_iov[1]); + } else { + rc = compound_send_recv(xid, ses, server, + flags, 3, rqst, + resp_buftype, rsp_iov); + } if (rc) { free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); if (rc == -EREMCHG) { @@ -2729,11 +2766,14 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, *buftype = resp_buftype[1]; qic_exit: + kfree(utf16_path); SMB2_open_free(&rqst[0]); SMB2_query_info_free(&rqst[1]); SMB2_close_free(&rqst[2]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + if (cfid) + close_cached_dir(cfid); return rc; } @@ -2743,13 +2783,12 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, { struct smb2_query_info_rsp *rsp; struct smb2_fs_full_size_info *info = NULL; - __le16 utf16_path = 0; /* Null - open root of share */ struct kvec rsp_iov = {NULL, 0}; int buftype = CIFS_NO_BUFFER; int rc; - rc = smb2_query_info_compound(xid, tcon, &utf16_path, + rc = smb2_query_info_compound(xid, tcon, "", FILE_READ_ATTRIBUTES, FS_FULL_SIZE_INFORMATION, SMB2_O_INFO_FILESYSTEM, @@ -4293,12 +4332,12 @@ static __le32 map_oplock_to_lease(u8 oplock) { if (oplock == SMB2_OPLOCK_LEVEL_EXCLUSIVE) - return SMB2_LEASE_WRITE_CACHING | SMB2_LEASE_READ_CACHING; + return SMB2_LEASE_WRITE_CACHING_LE | SMB2_LEASE_READ_CACHING_LE; else if (oplock == SMB2_OPLOCK_LEVEL_II) - return SMB2_LEASE_READ_CACHING; + return SMB2_LEASE_READ_CACHING_LE; else if (oplock == SMB2_OPLOCK_LEVEL_BATCH) - return SMB2_LEASE_HANDLE_CACHING | SMB2_LEASE_READ_CACHING | - SMB2_LEASE_WRITE_CACHING; + return SMB2_LEASE_HANDLE_CACHING_LE | SMB2_LEASE_READ_CACHING_LE | + SMB2_LEASE_WRITE_CACHING_LE; return 0; } @@ -4360,7 +4399,7 @@ smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key) struct create_lease *lc = (struct create_lease *)buf; *epoch = 0; /* not used */ - if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) + if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE) return SMB2_OPLOCK_LEVEL_NOCHANGE; return le32_to_cpu(lc->lcontext.LeaseState); } @@ -4371,7 +4410,7 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key) struct create_lease_v2 *lc = (struct create_lease_v2 *)buf; *epoch = le16_to_cpu(lc->lcontext.Epoch); - if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) + if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE) return SMB2_OPLOCK_LEVEL_NOCHANGE; if (lease_key) memcpy(lease_key, &lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); @@ -5814,8 +5853,8 @@ struct smb_version_values smb20_values = { .protocol_id = SMB20_PROT_ID, .req_capabilities = 0, /* MBZ */ .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, @@ -5835,8 +5874,8 @@ struct smb_version_values smb21_values = { .protocol_id = SMB21_PROT_ID, .req_capabilities = 0, /* MBZ on negotiate req until SMB3 dialect */ .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, @@ -5856,8 +5895,8 @@ struct smb_version_values smb3any_values = { .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, @@ -5877,8 +5916,8 @@ struct smb_version_values smbdefault_values = { .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, @@ -5898,8 +5937,8 @@ struct smb_version_values smb30_values = { .protocol_id = SMB30_PROT_ID, .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, @@ -5919,8 +5958,8 @@ struct smb_version_values smb302_values = { .protocol_id = SMB302_PROT_ID, .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, @@ -5940,8 +5979,8 @@ struct smb_version_values smb311_values = { .protocol_id = SMB311_PROT_ID, .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, - .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, - .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE, + .shared_lock_type = SMB2_LOCKFLAG_SHARED, .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7e7909b1ae11..1b7ad0c09566 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -163,7 +163,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, return 0; spin_lock(&cifs_tcp_ses_lock); - if (tcon->tidStatus == CifsExiting) { + if (tcon->status == TID_EXITING) { /* * only tree disconnect, open, and write, * (and ulogoff which does not have tcon) @@ -2734,13 +2734,10 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, goto err_free_req; } - trace_smb3_posix_mkdir_done(xid, le64_to_cpu(rsp->PersistentFileId), - tcon->tid, - ses->Suid, CREATE_NOT_FILE, - FILE_WRITE_ATTRIBUTES); + trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid, ses->Suid, + CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES); - SMB2_close(xid, tcon, le64_to_cpu(rsp->PersistentFileId), - le64_to_cpu(rsp->VolatileFileId)); + SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId); /* Eventually save off posix specific response info and timestaps */ @@ -3009,14 +3006,12 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } else if (rsp == NULL) /* unlikely to happen, but safer to check */ goto creat_exit; else - trace_smb3_open_done(xid, le64_to_cpu(rsp->PersistentFileId), - tcon->tid, - ses->Suid, oparms->create_options, - oparms->desired_access); + trace_smb3_open_done(xid, rsp->PersistentFileId, tcon->tid, ses->Suid, + oparms->create_options, oparms->desired_access); atomic_inc(&tcon->num_remote_opens); - oparms->fid->persistent_fid = le64_to_cpu(rsp->PersistentFileId); - oparms->fid->volatile_fid = le64_to_cpu(rsp->VolatileFileId); + oparms->fid->persistent_fid = rsp->PersistentFileId; + oparms->fid->volatile_fid = rsp->VolatileFileId; oparms->fid->access = oparms->desired_access; #ifdef CONFIG_CIFS_DEBUG2 oparms->fid->mid = le64_to_cpu(rsp->hdr.MessageId); @@ -3313,8 +3308,8 @@ SMB2_close_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, if (rc) return rc; - req->PersistentFileId = cpu_to_le64(persistent_fid); - req->VolatileFileId = cpu_to_le64(volatile_fid); + req->PersistentFileId = persistent_fid; + req->VolatileFileId = volatile_fid; if (query_attrs) req->Flags = SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB; else @@ -3677,8 +3672,8 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst, if (rc) return rc; - req->PersistentFileId = cpu_to_le64(persistent_fid); - req->VolatileFileId = cpu_to_le64(volatile_fid); + req->PersistentFileId = persistent_fid; + req->VolatileFileId = volatile_fid; /* See note 354 of MS-SMB2, 64K max */ req->OutputBufferLength = cpu_to_le32(SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE); @@ -3858,12 +3853,14 @@ void smb2_reconnect_server(struct work_struct *work) tcon = kzalloc(sizeof(struct cifs_tcon), GFP_KERNEL); if (!tcon) { resched = true; - list_del_init(&ses->rlist); - cifs_put_smb_ses(ses); + list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) { + list_del_init(&ses->rlist); + cifs_put_smb_ses(ses); + } goto done; } - tcon->tidStatus = CifsGood; + tcon->status = TID_GOOD; tcon->retry = false; tcon->need_reconnect = false; @@ -3951,8 +3948,8 @@ SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst, if (rc) return rc; - req->PersistentFileId = cpu_to_le64(persistent_fid); - req->VolatileFileId = cpu_to_le64(volatile_fid); + req->PersistentFileId = persistent_fid; + req->VolatileFileId = volatile_fid; iov[0].iov_base = (char *)req; iov[0].iov_len = total_len; @@ -4033,8 +4030,8 @@ smb2_new_read_req(void **buf, unsigned int *total_len, shdr = &req->hdr; shdr->Id.SyncId.ProcessId = cpu_to_le32(io_parms->pid); - req->PersistentFileId = cpu_to_le64(io_parms->persistent_fid); - req->VolatileFileId = cpu_to_le64(io_parms->volatile_fid); + req->PersistentFileId = io_parms->persistent_fid; + req->VolatileFileId = io_parms->volatile_fid; req->ReadChannelInfoOffset = 0; /* reserved */ req->ReadChannelInfoLength = 0; /* reserved */ req->Channel = 0; /* reserved */ @@ -4094,8 +4091,8 @@ smb2_new_read_req(void **buf, unsigned int *total_len, */ shdr->SessionId = cpu_to_le64(0xFFFFFFFFFFFFFFFF); shdr->Id.SyncId.TreeId = cpu_to_le32(0xFFFFFFFF); - req->PersistentFileId = cpu_to_le64(0xFFFFFFFFFFFFFFFF); - req->VolatileFileId = cpu_to_le64(0xFFFFFFFFFFFFFFFF); + req->PersistentFileId = (u64)-1; + req->VolatileFileId = (u64)-1; } } if (remaining_bytes > io_parms->length) @@ -4307,21 +4304,19 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); cifs_dbg(VFS, "Send error in read = %d\n", rc); trace_smb3_read_err(xid, - le64_to_cpu(req->PersistentFileId), + req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length, rc); } else - trace_smb3_read_done(xid, - le64_to_cpu(req->PersistentFileId), - io_parms->tcon->tid, ses->Suid, - io_parms->offset, 0); + trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid, + ses->Suid, io_parms->offset, 0); free_rsp_buf(resp_buftype, rsp_iov.iov_base); cifs_small_buf_release(req); return rc == -ENODATA ? 0 : rc; } else trace_smb3_read_done(xid, - le64_to_cpu(req->PersistentFileId), + req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length); @@ -4463,8 +4458,8 @@ smb2_async_writev(struct cifs_writedata *wdata, shdr = (struct smb2_hdr *)req; shdr->Id.SyncId.ProcessId = cpu_to_le32(wdata->cfile->pid); - req->PersistentFileId = cpu_to_le64(wdata->cfile->fid.persistent_fid); - req->VolatileFileId = cpu_to_le64(wdata->cfile->fid.volatile_fid); + req->PersistentFileId = wdata->cfile->fid.persistent_fid; + req->VolatileFileId = wdata->cfile->fid.volatile_fid; req->WriteChannelInfoOffset = 0; req->WriteChannelInfoLength = 0; req->Channel = 0; @@ -4562,7 +4557,7 @@ smb2_async_writev(struct cifs_writedata *wdata, if (rc) { trace_smb3_write_err(0 /* no xid */, - le64_to_cpu(req->PersistentFileId), + req->PersistentFileId, tcon->tid, tcon->ses->Suid, wdata->offset, wdata->bytes, rc); kref_put(&wdata->refcount, release); @@ -4615,8 +4610,8 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, req->hdr.Id.SyncId.ProcessId = cpu_to_le32(io_parms->pid); - req->PersistentFileId = cpu_to_le64(io_parms->persistent_fid); - req->VolatileFileId = cpu_to_le64(io_parms->volatile_fid); + req->PersistentFileId = io_parms->persistent_fid; + req->VolatileFileId = io_parms->volatile_fid; req->WriteChannelInfoOffset = 0; req->WriteChannelInfoLength = 0; req->Channel = 0; @@ -4645,7 +4640,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, if (rc) { trace_smb3_write_err(xid, - le64_to_cpu(req->PersistentFileId), + req->PersistentFileId, io_parms->tcon->tid, io_parms->tcon->ses->Suid, io_parms->offset, io_parms->length, rc); @@ -4654,7 +4649,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, } else { *nbytes = le32_to_cpu(rsp->DataLength); trace_smb3_write_done(xid, - le64_to_cpu(req->PersistentFileId), + req->PersistentFileId, io_parms->tcon->tid, io_parms->tcon->ses->Suid, io_parms->offset, *nbytes); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 33cfd0a1adf1..d8c4388b190d 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -56,16 +56,6 @@ struct smb2_rdma_crypto_transform { #define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL -#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9) - -struct smb2_err_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; - __le16 Reserved; /* MBZ */ - __le32 ByteCount; /* even if zero, at least one byte follows */ - __u8 ErrorData[1]; /* variable length */ -} __packed; - #define SYMLINK_ERROR_TAG 0x4c4d5953 struct smb2_symlink_err_rsp { @@ -139,47 +129,6 @@ struct share_redirect_error_context_rsp { #define SMB2_LEASE_HANDLE_CACHING_HE 0x02 #define SMB2_LEASE_WRITE_CACHING_HE 0x04 -#define SMB2_LEASE_NONE cpu_to_le32(0x00) -#define SMB2_LEASE_READ_CACHING cpu_to_le32(0x01) -#define SMB2_LEASE_HANDLE_CACHING cpu_to_le32(0x02) -#define SMB2_LEASE_WRITE_CACHING cpu_to_le32(0x04) - -#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x00000002) -#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET cpu_to_le32(0x00000004) - -#define SMB2_LEASE_KEY_SIZE 16 - -struct lease_context { - u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; - __le32 LeaseState; - __le32 LeaseFlags; - __le64 LeaseDuration; -} __packed; - -struct lease_context_v2 { - u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; - __le32 LeaseState; - __le32 LeaseFlags; - __le64 LeaseDuration; - __le64 ParentLeaseKeyLow; - __le64 ParentLeaseKeyHigh; - __le16 Epoch; - __le16 Reserved; -} __packed; - -struct create_lease { - struct create_context ccontext; - __u8 Name[8]; - struct lease_context lcontext; -} __packed; - -struct create_lease_v2 { - struct create_context ccontext; - __u8 Name[8]; - struct lease_context_v2 lcontext; - __u8 Pad[4]; -} __packed; - struct create_durable { struct create_context ccontext; __u8 Name[8]; @@ -192,13 +141,6 @@ struct create_durable { } Data; } __packed; -struct create_posix { - struct create_context ccontext; - __u8 Name[16]; - __le32 Mode; - __u32 Reserved; -} __packed; - /* See MS-SMB2 2.2.13.2.11 */ /* Flags */ #define SMB2_DHANDLE_FLAG_PERSISTENT 0x00000002 @@ -287,12 +229,6 @@ struct copychunk_ioctl { __u32 Reserved2; } __packed; -/* this goes in the ioctl buffer when doing FSCTL_SET_ZERO_DATA */ -struct file_zero_data_information { - __le64 FileOffset; - __le64 BeyondFinalZero; -} __packed; - struct copychunk_ioctl_rsp { __le32 ChunksWritten; __le32 ChunkBytesWritten; @@ -338,11 +274,6 @@ struct fsctl_get_integrity_information_rsp { __le32 ClusterSizeInBytes; } __packed; -struct file_allocated_range_buffer { - __le64 file_offset; - __le64 length; -} __packed; - /* Integrity ChecksumAlgorithm choices for above */ #define CHECKSUM_TYPE_NONE 0x0000 #define CHECKSUM_TYPE_CRC64 0x0002 @@ -351,53 +282,6 @@ struct file_allocated_range_buffer { /* Integrity flags for above */ #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF 0x00000001 -/* Reparse structures - see MS-FSCC 2.1.2 */ - -/* struct fsctl_reparse_info_req is empty, only response structs (see below) */ - -struct reparse_data_buffer { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __u8 DataBuffer[]; /* Variable Length */ -} __packed; - -struct reparse_guid_data_buffer { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __u8 ReparseGuid[16]; - __u8 DataBuffer[]; /* Variable Length */ -} __packed; - -struct reparse_mount_point_data_buffer { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __le16 SubstituteNameOffset; - __le16 SubstituteNameLength; - __le16 PrintNameOffset; - __le16 PrintNameLength; - __u8 PathBuffer[]; /* Variable Length */ -} __packed; - -#define SYMLINK_FLAG_RELATIVE 0x00000001 - -struct reparse_symlink_data_buffer { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __le16 SubstituteNameOffset; - __le16 SubstituteNameLength; - __le16 PrintNameOffset; - __le16 PrintNameLength; - __le32 Flags; - __u8 PathBuffer[]; /* Variable Length */ -} __packed; - -/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */ - - /* See MS-DFSC 2.2.2 */ struct fsctl_get_dfs_referral_req { __le16 MaxReferralLevel; @@ -413,22 +297,6 @@ struct network_resiliency_req { } __packed; /* There is no buffer for the response ie no struct network_resiliency_rsp */ - -struct validate_negotiate_info_req { - __le32 Capabilities; - __u8 Guid[SMB2_CLIENT_GUID_SIZE]; - __le16 SecurityMode; - __le16 DialectCount; - __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */ -} __packed; - -struct validate_negotiate_info_rsp { - __le32 Capabilities; - __u8 Guid[SMB2_CLIENT_GUID_SIZE]; - __le16 SecurityMode; - __le16 Dialect; /* Dialect in use for the connection */ -} __packed; - #define RSS_CAPABLE cpu_to_le32(0x00000001) #define RDMA_CAPABLE cpu_to_le32(0x00000002) @@ -464,14 +332,6 @@ struct compress_ioctl { __le16 CompressionState; /* See cifspdu.h for possible flag values */ } __packed; -struct duplicate_extents_to_file { - __u64 PersistentFileHandle; /* source file handle, opaque endianness */ - __u64 VolatileFileHandle; - __le64 SourceFileOffset; - __le64 TargetFileOffset; - __le64 ByteCount; /* Bytes to be copied */ -} __packed; - /* * Maximum number of iovs we need for an ioctl request. * [0] : struct smb2_ioctl_req @@ -479,370 +339,11 @@ struct duplicate_extents_to_file { */ #define SMB2_IOCTL_IOV_SIZE 2 -struct smb2_ioctl_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 57 */ - __u16 Reserved; - __le32 CtlCode; - __u64 PersistentFileId; /* opaque endianness */ - __u64 VolatileFileId; /* opaque endianness */ - __le32 InputOffset; - __le32 InputCount; - __le32 MaxInputResponse; - __le32 OutputOffset; - __le32 OutputCount; - __le32 MaxOutputResponse; - __le32 Flags; - __u32 Reserved2; - __u8 Buffer[]; -} __packed; - -struct smb2_ioctl_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 57 */ - __u16 Reserved; - __le32 CtlCode; - __u64 PersistentFileId; /* opaque endianness */ - __u64 VolatileFileId; /* opaque endianness */ - __le32 InputOffset; - __le32 InputCount; - __le32 OutputOffset; - __le32 OutputCount; - __le32 Flags; - __u32 Reserved2; - /* char * buffer[] */ -} __packed; - -#define SMB2_LOCKFLAG_SHARED_LOCK 0x0001 -#define SMB2_LOCKFLAG_EXCLUSIVE_LOCK 0x0002 -#define SMB2_LOCKFLAG_UNLOCK 0x0004 -#define SMB2_LOCKFLAG_FAIL_IMMEDIATELY 0x0010 - -struct smb2_lock_element { - __le64 Offset; - __le64 Length; - __le32 Flags; - __le32 Reserved; -} __packed; - -struct smb2_lock_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 48 */ - __le16 LockCount; - /* - * The least significant four bits are the index, the other 28 bits are - * the lock sequence number (0 to 64). See MS-SMB2 2.2.26 - */ - __le32 LockSequenceNumber; - __u64 PersistentFileId; /* opaque endianness */ - __u64 VolatileFileId; /* opaque endianness */ - /* Followed by at least one */ - struct smb2_lock_element locks[1]; -} __packed; - -struct smb2_lock_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_echo_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __u16 Reserved; -} __packed; - -struct smb2_echo_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __u16 Reserved; -} __packed; - -/* search (query_directory) Flags field */ -#define SMB2_RESTART_SCANS 0x01 -#define SMB2_RETURN_SINGLE_ENTRY 0x02 -#define SMB2_INDEX_SPECIFIED 0x04 -#define SMB2_REOPEN 0x10 - -#define SMB2_QUERY_DIRECTORY_IOV_SIZE 2 - -/* - * Valid FileInformation classes. - * - * Note that these are a subset of the (file) QUERY_INFO levels defined - * later in this file (but since QUERY_DIRECTORY uses equivalent numbers - * we do not redefine them here) - * - * FileDirectoryInfomation 0x01 - * FileFullDirectoryInformation 0x02 - * FileIdFullDirectoryInformation 0x26 - * FileBothDirectoryInformation 0x03 - * FileIdBothDirectoryInformation 0x25 - * FileNamesInformation 0x0C - * FileIdExtdDirectoryInformation 0x3C - */ - -struct smb2_query_directory_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 33 */ - __u8 FileInformationClass; - __u8 Flags; - __le32 FileIndex; - __u64 PersistentFileId; /* opaque endianness */ - __u64 VolatileFileId; /* opaque endianness */ - __le16 FileNameOffset; - __le16 FileNameLength; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - -struct smb2_query_directory_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 OutputBufferOffset; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - -/* Possible InfoType values */ -#define SMB2_O_INFO_FILE 0x01 -#define SMB2_O_INFO_FILESYSTEM 0x02 -#define SMB2_O_INFO_SECURITY 0x03 -#define SMB2_O_INFO_QUOTA 0x04 - -/* Security info type additionalinfo flags. See MS-SMB2 (2.2.37) or MS-DTYP */ -#define OWNER_SECINFO 0x00000001 -#define GROUP_SECINFO 0x00000002 -#define DACL_SECINFO 0x00000004 -#define SACL_SECINFO 0x00000008 -#define LABEL_SECINFO 0x00000010 -#define ATTRIBUTE_SECINFO 0x00000020 -#define SCOPE_SECINFO 0x00000040 -#define BACKUP_SECINFO 0x00010000 -#define UNPROTECTED_SACL_SECINFO 0x10000000 -#define UNPROTECTED_DACL_SECINFO 0x20000000 -#define PROTECTED_SACL_SECINFO 0x40000000 -#define PROTECTED_DACL_SECINFO 0x80000000 - -/* Flags used for FileFullEAinfo */ -#define SL_RESTART_SCAN 0x00000001 -#define SL_RETURN_SINGLE_ENTRY 0x00000002 -#define SL_INDEX_SPECIFIED 0x00000004 - -struct smb2_query_info_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 41 */ - __u8 InfoType; - __u8 FileInfoClass; - __le32 OutputBufferLength; - __le16 InputBufferOffset; - __u16 Reserved; - __le32 InputBufferLength; - __le32 AdditionalInformation; - __le32 Flags; - __u64 PersistentFileId; /* opaque endianness */ - __u64 VolatileFileId; /* opaque endianness */ - __u8 Buffer[1]; -} __packed; - -struct smb2_query_info_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 OutputBufferOffset; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - -/* - * Maximum number of iovs we need for a set-info request. - * The largest one is rename/hardlink - * [0] : struct smb2_set_info_req + smb2_file_[rename|link]_info - * [1] : path - * [2] : compound padding - */ -#define SMB2_SET_INFO_IOV_SIZE 3 - -struct smb2_set_info_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 33 */ - __u8 InfoType; - __u8 FileInfoClass; - __le32 BufferLength; - __le16 BufferOffset; - __u16 Reserved; - __le32 AdditionalInformation; - __u64 PersistentFileId; /* opaque endianness */ - __u64 VolatileFileId; /* opaque endianness */ - __u8 Buffer[1]; -} __packed; - -struct smb2_set_info_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 2 */ -} __packed; - -struct smb2_oplock_break { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 24 */ - __u8 OplockLevel; - __u8 Reserved; - __le32 Reserved2; - __u64 PersistentFid; - __u64 VolatileFid; -} __packed; - -#define SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED cpu_to_le32(0x01) - -struct smb2_lease_break { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 44 */ - __le16 Epoch; - __le32 Flags; - __u8 LeaseKey[16]; - __le32 CurrentLeaseState; - __le32 NewLeaseState; - __le32 BreakReason; - __le32 AccessMaskHint; - __le32 ShareMaskHint; -} __packed; - -struct smb2_lease_ack { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 36 */ - __le16 Reserved; - __le32 Flags; - __u8 LeaseKey[16]; - __le32 LeaseState; - __le64 LeaseDuration; -} __packed; - /* - * PDU infolevel structure definitions + * PDU query infolevel structure definitions * BB consider moving to a different header */ -/* File System Information Classes */ -#define FS_VOLUME_INFORMATION 1 /* Query */ -#define FS_LABEL_INFORMATION 2 /* Local only */ -#define FS_SIZE_INFORMATION 3 /* Query */ -#define FS_DEVICE_INFORMATION 4 /* Query */ -#define FS_ATTRIBUTE_INFORMATION 5 /* Query */ -#define FS_CONTROL_INFORMATION 6 /* Query, Set */ -#define FS_FULL_SIZE_INFORMATION 7 /* Query */ -#define FS_OBJECT_ID_INFORMATION 8 /* Query, Set */ -#define FS_DRIVER_PATH_INFORMATION 9 /* Local only */ -#define FS_VOLUME_FLAGS_INFORMATION 10 /* Local only */ -#define FS_SECTOR_SIZE_INFORMATION 11 /* SMB3 or later. Query */ -#define FS_POSIX_INFORMATION 100 /* SMB3.1.1 POSIX. Query */ - -struct smb2_fs_full_size_info { - __le64 TotalAllocationUnits; - __le64 CallerAvailableAllocationUnits; - __le64 ActualAvailableAllocationUnits; - __le32 SectorsPerAllocationUnit; - __le32 BytesPerSector; -} __packed; - -#define SSINFO_FLAGS_ALIGNED_DEVICE 0x00000001 -#define SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE 0x00000002 -#define SSINFO_FLAGS_NO_SEEK_PENALTY 0x00000004 -#define SSINFO_FLAGS_TRIM_ENABLED 0x00000008 - -/* sector size info struct */ -struct smb3_fs_ss_info { - __le32 LogicalBytesPerSector; - __le32 PhysicalBytesPerSectorForAtomicity; - __le32 PhysicalBytesPerSectorForPerf; - __le32 FileSystemEffectivePhysicalBytesPerSectorForAtomicity; - __le32 Flags; - __le32 ByteOffsetForSectorAlignment; - __le32 ByteOffsetForPartitionAlignment; -} __packed; - -/* volume info struct - see MS-FSCC 2.5.9 */ -#define MAX_VOL_LABEL_LEN 32 -struct smb3_fs_vol_info { - __le64 VolumeCreationTime; - __u32 VolumeSerialNumber; - __le32 VolumeLabelLength; /* includes trailing null */ - __u8 SupportsObjects; /* True if eg like NTFS, supports objects */ - __u8 Reserved; - __u8 VolumeLabel[]; /* variable len */ -} __packed; - -/* partial list of QUERY INFO levels */ -#define FILE_DIRECTORY_INFORMATION 1 -#define FILE_FULL_DIRECTORY_INFORMATION 2 -#define FILE_BOTH_DIRECTORY_INFORMATION 3 -#define FILE_BASIC_INFORMATION 4 -#define FILE_STANDARD_INFORMATION 5 -#define FILE_INTERNAL_INFORMATION 6 -#define FILE_EA_INFORMATION 7 -#define FILE_ACCESS_INFORMATION 8 -#define FILE_NAME_INFORMATION 9 -#define FILE_RENAME_INFORMATION 10 -#define FILE_LINK_INFORMATION 11 -#define FILE_NAMES_INFORMATION 12 -#define FILE_DISPOSITION_INFORMATION 13 -#define FILE_POSITION_INFORMATION 14 -#define FILE_FULL_EA_INFORMATION 15 -#define FILE_MODE_INFORMATION 16 -#define FILE_ALIGNMENT_INFORMATION 17 -#define FILE_ALL_INFORMATION 18 -#define FILE_ALLOCATION_INFORMATION 19 -#define FILE_END_OF_FILE_INFORMATION 20 -#define FILE_ALTERNATE_NAME_INFORMATION 21 -#define FILE_STREAM_INFORMATION 22 -#define FILE_PIPE_INFORMATION 23 -#define FILE_PIPE_LOCAL_INFORMATION 24 -#define FILE_PIPE_REMOTE_INFORMATION 25 -#define FILE_MAILSLOT_QUERY_INFORMATION 26 -#define FILE_MAILSLOT_SET_INFORMATION 27 -#define FILE_COMPRESSION_INFORMATION 28 -#define FILE_OBJECT_ID_INFORMATION 29 -/* Number 30 not defined in documents */ -#define FILE_MOVE_CLUSTER_INFORMATION 31 -#define FILE_QUOTA_INFORMATION 32 -#define FILE_REPARSE_POINT_INFORMATION 33 -#define FILE_NETWORK_OPEN_INFORMATION 34 -#define FILE_ATTRIBUTE_TAG_INFORMATION 35 -#define FILE_TRACKING_INFORMATION 36 -#define FILEID_BOTH_DIRECTORY_INFORMATION 37 -#define FILEID_FULL_DIRECTORY_INFORMATION 38 -#define FILE_VALID_DATA_LENGTH_INFORMATION 39 -#define FILE_SHORT_NAME_INFORMATION 40 -#define FILE_SFIO_RESERVE_INFORMATION 44 -#define FILE_SFIO_VOLUME_INFORMATION 45 -#define FILE_HARD_LINK_INFORMATION 46 -#define FILE_NORMALIZED_NAME_INFORMATION 48 -#define FILEID_GLOBAL_TX_DIRECTORY_INFORMATION 50 -#define FILE_STANDARD_LINK_INFORMATION 54 -#define FILE_ID_INFORMATION 59 -#define FILE_ID_EXTD_DIRECTORY_INFORMATION 60 - -struct smb2_file_internal_info { - __le64 IndexNumber; -} __packed; /* level 6 Query */ - -struct smb2_file_rename_info { /* encoding of request for level 10 */ - __u8 ReplaceIfExists; /* 1 = replace existing target with new */ - /* 0 = fail if target already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; - char FileName[]; /* New name to be assigned */ - /* padding - overall struct size must be >= 24 so filename + pad >= 6 */ -} __packed; /* level 10 Set */ - -struct smb2_file_link_info { /* encoding of request for level 11 */ - __u8 ReplaceIfExists; /* 1 = replace existing link with new */ - /* 0 = fail if link already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; - char FileName[]; /* Name to be assigned to new link */ -} __packed; /* level 11 Set */ - struct smb2_file_full_ea_info { /* encoding of response for level 15 */ __le32 next_entry_offset; __u8 flags; @@ -851,38 +352,6 @@ struct smb2_file_full_ea_info { /* encoding of response for level 15 */ char ea_data[]; /* \0 terminated name plus value */ } __packed; /* level 15 Set */ -/* - * This level 18, although with struct with same name is different from cifs - * level 0x107. Level 0x107 has an extra u64 between AccessFlags and - * CurrentByteOffset. - */ -struct smb2_file_all_info { /* data block encoding of response to level 18 */ - __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le32 Attributes; - __u32 Pad1; /* End of FILE_BASIC_INFO_INFO equivalent */ - __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */ - __le64 EndOfFile; /* size ie offset to first free byte in file */ - __le32 NumberOfLinks; /* hard links */ - __u8 DeletePending; - __u8 Directory; - __u16 Pad2; /* End of FILE_STANDARD_INFO equivalent */ - __le64 IndexNumber; - __le32 EASize; - __le32 AccessFlags; - __le64 CurrentByteOffset; - __le32 Mode; - __le32 AlignmentRequirement; - __le32 FileNameLength; - char FileName[1]; -} __packed; /* level 18 Query */ - -struct smb2_file_eof_info { /* encoding of request for level 10 */ - __le64 EndOfFile; /* new end of file value */ -} __packed; /* level 20 Set */ - struct smb2_file_reparse_point_info { __le64 IndexNumber; __le32 Tag; @@ -935,6 +404,8 @@ struct create_posix_rsp { struct cifs_sid group; /* var-sized on the wire */ } __packed; +#define SMB2_QUERY_DIRECTORY_IOV_SIZE 2 + /* * SMB2-only POSIX info level for query dir * @@ -966,31 +437,6 @@ struct smb2_posix_info { */ } __packed; -/* Level 100 query info */ -struct smb311_posix_qinfo { - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 EndOfFile; - __le64 AllocationSize; - __le32 DosAttributes; - __le64 Inode; - __le32 DeviceId; - __le32 Zero; - /* beginning of POSIX Create Context Response */ - __le32 HardLinks; - __le32 ReparseTag; - __le32 Mode; - u8 Sids[]; - /* - * var sized owner SID - * var sized group SID - * le32 filenamelength - * u8 filename[] - */ -} __packed; - /* * Parsed version of the above struct. Allows direct access to the * variable length fields diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 4a7062fd1c26..a69f1eed1cfe 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -283,7 +283,7 @@ extern int smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec); extern int smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, - __le16 *utf16_path, u32 desired_access, + const char *path, u32 desired_access, u32 class, u32 type, u32 output_len, struct kvec *rsp, int *buftype, struct cifs_sb_info *cifs_sb); diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 6cecf302dcfd..bc279616c513 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -1006,6 +1006,13 @@ DEFINE_SMB3_CREDIT_EVENT(credit_timeout); DEFINE_SMB3_CREDIT_EVENT(insufficient_credits); DEFINE_SMB3_CREDIT_EVENT(too_many_credits); DEFINE_SMB3_CREDIT_EVENT(add_credits); +DEFINE_SMB3_CREDIT_EVENT(adj_credits); +DEFINE_SMB3_CREDIT_EVENT(hdr_credits); +DEFINE_SMB3_CREDIT_EVENT(nblk_credits); +DEFINE_SMB3_CREDIT_EVENT(pend_credits); +DEFINE_SMB3_CREDIT_EVENT(wait_credits); +DEFINE_SMB3_CREDIT_EVENT(waitff_credits); +DEFINE_SMB3_CREDIT_EVENT(overflow_credits); DEFINE_SMB3_CREDIT_EVENT(set_credits); #endif /* _CIFS_TRACE_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index eeb1a699bd6f..d9d1c353bafc 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -542,7 +542,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_nblk_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -1, in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", __func__, 1, scredits); @@ -648,7 +648,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_waitff_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(num_credits), in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 4fcca79f39ae..526a4c1bed99 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -248,7 +248,7 @@ EXPORT_SYMBOL(fscrypt_encrypt_block_inplace); * which must still be locked and not uptodate. Normally, blocksize == * PAGE_SIZE and the whole page is decrypted at once. * - * This is for use by the filesystem's ->readpages() method. + * This is for use by the filesystem's ->readahead() method. * * Return: 0 on success; -errno on failure */ diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0ed880f42525..e6dea6dfca16 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1066,12 +1066,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -1217,7 +1214,7 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1419,8 +1416,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e043216b545f..800b11c53f57 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -97,7 +97,7 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; }; diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 619e5b4bed10..c6800b880920 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -203,7 +203,8 @@ struct exfat_mount_options { /* on error: continue, panic, remount-ro */ enum exfat_error_mode errors; unsigned utf8:1, /* Use of UTF-8 character set */ - discard:1; /* Issue discard requests on deletions */ + discard:1, /* Issue discard requests on deletions */ + keep_last_dots:1; /* Keep trailing periods in paths */ int time_offset; /* Offset of timestamps from UTC (in minutes) */ }; diff --git a/fs/exfat/file.c b/fs/exfat/file.c index d890fd34bb2d..2f5130059236 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -218,8 +218,6 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) if (exfat_free_cluster(inode, &clu)) return -EIO; - exfat_clear_volume_dirty(sb); - return 0; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index af4eb39cc0c3..a02a04a993bf 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -65,11 +65,14 @@ static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags) return ret; } -/* returns the length of a struct qstr, ignoring trailing dots */ -static unsigned int exfat_striptail_len(unsigned int len, const char *name) +/* returns the length of a struct qstr, ignoring trailing dots if necessary */ +static unsigned int exfat_striptail_len(unsigned int len, const char *name, + bool keep_last_dots) { - while (len && name[len - 1] == '.') - len--; + if (!keep_last_dots) { + while (len && name[len - 1] == '.') + len--; + } return len; } @@ -83,7 +86,8 @@ static int exfat_d_hash(const struct dentry *dentry, struct qstr *qstr) struct super_block *sb = dentry->d_sb; struct nls_table *t = EXFAT_SB(sb)->nls_io; const unsigned char *name = qstr->name; - unsigned int len = exfat_striptail_len(qstr->len, qstr->name); + unsigned int len = exfat_striptail_len(qstr->len, qstr->name, + EXFAT_SB(sb)->options.keep_last_dots); unsigned long hash = init_name_hash(dentry); int i, charlen; wchar_t c; @@ -104,8 +108,10 @@ static int exfat_d_cmp(const struct dentry *dentry, unsigned int len, { struct super_block *sb = dentry->d_sb; struct nls_table *t = EXFAT_SB(sb)->nls_io; - unsigned int alen = exfat_striptail_len(name->len, name->name); - unsigned int blen = exfat_striptail_len(len, str); + unsigned int alen = exfat_striptail_len(name->len, name->name, + EXFAT_SB(sb)->options.keep_last_dots); + unsigned int blen = exfat_striptail_len(len, str, + EXFAT_SB(sb)->options.keep_last_dots); wchar_t c1, c2; int charlen, i; @@ -136,7 +142,8 @@ static int exfat_utf8_d_hash(const struct dentry *dentry, struct qstr *qstr) { struct super_block *sb = dentry->d_sb; const unsigned char *name = qstr->name; - unsigned int len = exfat_striptail_len(qstr->len, qstr->name); + unsigned int len = exfat_striptail_len(qstr->len, qstr->name, + EXFAT_SB(sb)->options.keep_last_dots); unsigned long hash = init_name_hash(dentry); int i, charlen; unicode_t u; @@ -161,8 +168,11 @@ static int exfat_utf8_d_cmp(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct super_block *sb = dentry->d_sb; - unsigned int alen = exfat_striptail_len(name->len, name->name); - unsigned int blen = exfat_striptail_len(len, str); + unsigned int alen = exfat_striptail_len(name->len, name->name, + EXFAT_SB(sb)->options.keep_last_dots); + unsigned int blen = exfat_striptail_len(len, str, + EXFAT_SB(sb)->options.keep_last_dots); + unicode_t u_a, u_b; int charlen, i; @@ -416,13 +426,25 @@ static int __exfat_resolve_path(struct inode *inode, const unsigned char *path, struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); + int pathlen = strlen(path); - /* strip all trailing periods */ - namelen = exfat_striptail_len(strlen(path), path); + /* + * get the length of the pathname excluding + * trailing periods, if any. + */ + namelen = exfat_striptail_len(pathlen, path, false); + if (EXFAT_SB(sb)->options.keep_last_dots) { + /* + * Do not allow the creation of files with names + * ending with period(s). + */ + if (!lookup && (namelen < pathlen)) + return -EINVAL; + namelen = pathlen; + } if (!namelen) return -ENOENT; - - if (strlen(path) > (MAX_NAME_LENGTH * MAX_CHARSET_SIZE)) + if (pathlen > (MAX_NAME_LENGTH * MAX_CHARSET_SIZE)) return -ENAMETOOLONG; /* @@ -554,7 +576,6 @@ static int exfat_create(struct user_namespace *mnt_userns, struct inode *dir, exfat_set_volume_dirty(sb); err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_FILE, &info); - exfat_clear_volume_dirty(sb); if (err) goto unlock; @@ -812,7 +833,6 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) /* This doesn't modify ei */ ei->dir.dir = DIR_DELETED; - exfat_clear_volume_dirty(sb); inode_inc_iversion(dir); dir->i_mtime = dir->i_atime = current_time(dir); @@ -846,7 +866,6 @@ static int exfat_mkdir(struct user_namespace *mnt_userns, struct inode *dir, exfat_set_volume_dirty(sb); err = exfat_add_entry(dir, dentry->d_name.name, &cdir, TYPE_DIR, &info); - exfat_clear_volume_dirty(sb); if (err) goto unlock; @@ -976,7 +995,6 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) goto unlock; } ei->dir.dir = DIR_DELETED; - exfat_clear_volume_dirty(sb); inode_inc_iversion(dir); dir->i_mtime = dir->i_atime = current_time(dir); @@ -1311,7 +1329,6 @@ del_out: */ new_ei->dir.dir = DIR_DELETED; } - exfat_clear_volume_dirty(sb); out: return ret; } diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 9f892903419a..8ca21e7917d1 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -100,7 +100,6 @@ static int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flags) { struct exfat_sb_info *sbi = EXFAT_SB(sb); struct boot_sector *p_boot = (struct boot_sector *)sbi->boot_bh->b_data; - bool sync; /* retain persistent-flags */ new_flags |= sbi->vol_flags_persistent; @@ -119,16 +118,11 @@ static int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flags) p_boot->vol_flags = cpu_to_le16(new_flags); - if ((new_flags & VOLUME_DIRTY) && !buffer_dirty(sbi->boot_bh)) - sync = true; - else - sync = false; - set_buffer_uptodate(sbi->boot_bh); mark_buffer_dirty(sbi->boot_bh); - if (sync) - sync_dirty_buffer(sbi->boot_bh); + __sync_dirty_buffer(sbi->boot_bh, REQ_SYNC | REQ_FUA | REQ_PREFLUSH); + return 0; } @@ -174,6 +168,8 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",errors=remount-ro"); if (opts->discard) seq_puts(m, ",discard"); + if (opts->keep_last_dots) + seq_puts(m, ",keep_last_dots"); if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); return 0; @@ -217,6 +213,7 @@ enum { Opt_charset, Opt_errors, Opt_discard, + Opt_keep_last_dots, Opt_time_offset, /* Deprecated options */ @@ -243,6 +240,7 @@ static const struct fs_parameter_spec exfat_parameters[] = { fsparam_string("iocharset", Opt_charset), fsparam_enum("errors", Opt_errors, exfat_param_enums), fsparam_flag("discard", Opt_discard), + fsparam_flag("keep_last_dots", Opt_keep_last_dots), fsparam_s32("time_offset", Opt_time_offset), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), @@ -297,6 +295,9 @@ static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_discard: opts->discard = 1; break; + case Opt_keep_last_dots: + opts->keep_last_dots = 1; + break; case Opt_time_offset: /* * Make the limit 24 just in case someone invents something diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8bd66cdc41be..6feb07e3e1eb 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -267,7 +267,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, goto out; current->backing_dev_info = inode_to_bdi(inode); - ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos); + ret = generic_perform_write(iocb, from); current->backing_dev_info = NULL; out: diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1ce13f69fbec..13740f2d0e61 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3589,7 +3589,7 @@ const struct iomap_ops ext4_iomap_report_ops = { static bool ext4_journalled_dirty_folio(struct address_space *mapping, struct folio *folio) { - WARN_ON_ONCE(!page_has_buffers(&folio->page)); + WARN_ON_ONCE(!folio_buffers(folio)); folio_set_checked(folio); return filemap_dirty_folio(mapping, folio); } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 1aa26d6634fc..af491e170c4a 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -109,7 +109,7 @@ static void verity_work(struct work_struct *work) struct bio *bio = ctx->bio; /* - * fsverity_verify_bio() may call readpages() again, and although verity + * fsverity_verify_bio() may call readahead() again, and although verity * will be disabled for that, decryption may still be needed, causing * another bio_post_read_ctx to be allocated. So to guarantee that * mempool_alloc() never deadlocks we must free the current ctx first. diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index a8fc4fa511a8..f5366feea82d 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -456,7 +456,7 @@ static bool f2fs_dirty_meta_folio(struct address_space *mapping, folio_mark_uptodate(folio); if (!folio_test_dirty(folio)) { filemap_dirty_folio(mapping, folio); - inc_page_count(F2FS_P_SB(&folio->page), F2FS_DIRTY_META); + inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_META); set_page_private_reference(&folio->page); return true; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f8fcbe91059b..8e0c2e773c8d 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -164,7 +164,7 @@ static void f2fs_verify_bio(struct work_struct *work) bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS); /* - * fsverity_verify_bio() may call readpages() again, and while verity + * fsverity_verify_bio() may call readahead() again, and while verity * will be disabled for this, decryption and/or decompression may still * be needed, resulting in another bio_post_read_ctx being allocated. * So to prevent deadlocks we need to release the current ctx to the @@ -2392,7 +2392,7 @@ static void f2fs_readahead(struct readahead_control *rac) if (!f2fs_is_compress_backend_ready(inode)) return; - /* If the file has inline data, skip readpages */ + /* If the file has inline data, skip readahead */ if (f2fs_has_inline_data(inode)) return; @@ -3571,7 +3571,7 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping, f2fs_update_dirty_folio(inode, folio); return true; } - return true; + return false; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d3f39a704b8b..5b89af0f27f0 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4448,7 +4448,7 @@ static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb, return -EOPNOTSUPP; current->backing_dev_info = inode_to_bdi(inode); - ret = generic_perform_write(file, from, iocb->ki_pos); + ret = generic_perform_write(iocb, from); current->backing_dev_info = NULL; if (ret > 0) { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 0b6e741e94a0..c45d341dcf6e 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2146,11 +2146,11 @@ static bool f2fs_dirty_node_folio(struct address_space *mapping, folio_mark_uptodate(folio); #ifdef CONFIG_F2FS_CHECK_FS if (IS_INODE(&folio->page)) - f2fs_inode_chksum_set(F2FS_P_SB(&folio->page), &folio->page); + f2fs_inode_chksum_set(F2FS_M_SB(mapping), &folio->page); #endif if (!folio_test_dirty(folio)) { filemap_dirty_folio(mapping, folio); - inc_page_count(F2FS_P_SB(&folio->page), F2FS_DIRTY_NODES); + inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); set_page_private_reference(&folio->page); return true; } diff --git a/fs/file_table.c b/fs/file_table.c index 7d2e692b66a9..ada8fe814db9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -412,6 +412,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); +EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 76316c4a3fb7..b313a978ae0a 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -38,6 +38,3 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_OLD_API - bool diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index 2749933852a9..d645f8b302a2 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -214,7 +214,7 @@ void fscache_relinquish_cache(struct fscache_cache *cache) cache->ops = NULL; cache->cache_priv = NULL; - smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 9bb1ab5fe5ed..9d3cf0111709 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -30,7 +30,7 @@ static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; -unsigned int fscache_lru_cookie_timeout = 10 * HZ; +static unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { @@ -1069,6 +1069,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie, } EXPORT_SYMBOL(__fscache_invalidate); +#ifdef CONFIG_PROC_FS /* * Generate a list of extant cookies in /proc/fs/fscache/cookies */ @@ -1145,3 +1146,4 @@ const struct seq_operations fscache_cookies_seq_ops = { .stop = fscache_cookies_seq_stop, .show = fscache_cookies_seq_show, }; +#endif diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index f121c21590dc..1336f517e9b1 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -56,7 +56,9 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, * cookie.c */ extern struct kmem_cache *fscache_cookie_jar; +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_cookies_seq_ops; +#endif extern struct timer_list fscache_cookie_lru_timer; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); @@ -71,17 +73,6 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie, } /* - * io.c - */ -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - -/* * main.c */ extern unsigned fscache_debug; @@ -148,7 +139,9 @@ int fscache_stats_show(struct seq_file *m, void *v); /* * volume.c */ +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_volumes_seq_ops; +#endif struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where); diff --git a/fs/fscache/io.c b/fs/fscache/io.c index c8c7fe9e9a6e..3af3b08a9bb3 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -235,8 +235,7 @@ static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, { struct fscache_write_request *wreq = priv; - fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), - wreq->mapping, wreq->start, wreq->len, + fscache_clear_page_bits(wreq->mapping, wreq->start, wreq->len, wreq->set_bits); if (wreq->term_func) @@ -296,7 +295,7 @@ abandon_end: abandon_free: kfree(wreq); abandon: - fscache_clear_page_bits(cookie, mapping, start, len, cond); + fscache_clear_page_bits(mapping, start, len, cond); if (term_func) term_func(term_func_priv, ret, false); } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index eac4984cc753..488b460e046f 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -627,7 +627,7 @@ struct fuse_conn { /** Connection successful. Only set in INIT */ unsigned conn_init:1; - /** Do readpages asynchronously? Only set in INIT */ + /** Do readahead asynchronously? Only set in INIT */ unsigned async_read:1; /** Return an unique read error after abort. Only set in INIT */ diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index d67108489148..39080b2d6cf8 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -606,9 +606,9 @@ out: return ret; } -static inline __be64 *gfs2_indirect_init(struct metapath *mp, - struct gfs2_glock *gl, unsigned int i, - unsigned offset, u64 bn) +static inline void gfs2_indirect_init(struct metapath *mp, + struct gfs2_glock *gl, unsigned int i, + unsigned offset, u64 bn) { __be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data + ((i > 1) ? sizeof(struct gfs2_meta_header) : @@ -621,7 +621,6 @@ static inline __be64 *gfs2_indirect_init(struct metapath *mp, gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header)); ptr += offset; *ptr = cpu_to_be64(bn); - return ptr; } enum alloc_state { @@ -2146,7 +2145,7 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) ret = do_shrink(inode, newsize); out: - gfs2_rs_delete(ip, NULL); + gfs2_rs_delete(ip); gfs2_qa_put(ip); return ret; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 8c39a8571b1f..22b41acfbbc3 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -706,7 +706,7 @@ static int gfs2_release(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) { if (gfs2_rs_active(&ip->i_res)) - gfs2_rs_delete(ip, &inode->i_writecount); + gfs2_rs_delete(ip); gfs2_qa_put(ip); } return 0; @@ -775,8 +775,7 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, size_t *window_size) { size_t count = iov_iter_count(i); - char __user *p; - int pages = 1; + size_t size, offs; if (likely(!count)) return false; @@ -785,18 +784,20 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, if (!iter_is_iovec(i)) return false; + size = PAGE_SIZE; + offs = offset_in_page(i->iov[0].iov_base + i->iov_offset); if (*prev_count != count || !*window_size) { - int pages, nr_dirtied; + size_t nr_dirtied; - pages = min_t(int, BIO_MAX_VECS, DIV_ROUND_UP(count, PAGE_SIZE)); + size = ALIGN(offs + count, PAGE_SIZE); + size = min_t(size_t, size, SZ_1M); nr_dirtied = max(current->nr_dirtied_pause - - current->nr_dirtied, 1); - pages = min(pages, nr_dirtied); + current->nr_dirtied, 8); + size = min(size, nr_dirtied << PAGE_SHIFT); } *prev_count = count; - p = i->iov[0].iov_base + i->iov_offset; - *window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p); + *window_size = size - offs; return true; } @@ -851,9 +852,9 @@ retry_under_glock: leftover = fault_in_iov_iter_writeable(to, window_size); gfs2_holder_disallow_demote(gh); if (leftover != window_size) { - if (!gfs2_holder_queued(gh)) - goto retry; - goto retry_under_glock; + if (gfs2_holder_queued(gh)) + goto retry_under_glock; + goto retry; } } if (gfs2_holder_queued(gh)) @@ -920,9 +921,9 @@ retry_under_glock: leftover = fault_in_iov_iter_readable(from, window_size); gfs2_holder_disallow_demote(gh); if (leftover != window_size) { - if (!gfs2_holder_queued(gh)) - goto retry; - goto retry_under_glock; + if (gfs2_holder_queued(gh)) + goto retry_under_glock; + goto retry; } } out: @@ -950,20 +951,19 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * and retry. */ - if (iocb->ki_flags & IOCB_DIRECT) { - ret = gfs2_file_direct_read(iocb, to, &gh); - if (likely(ret != -ENOTBLK)) - return ret; - iocb->ki_flags &= ~IOCB_DIRECT; - } + if (iocb->ki_flags & IOCB_DIRECT) + return gfs2_file_direct_read(iocb, to, &gh); + + pagefault_disable(); iocb->ki_flags |= IOCB_NOIO; ret = generic_file_read_iter(iocb, to); iocb->ki_flags &= ~IOCB_NOIO; + pagefault_enable(); if (ret >= 0) { if (!iov_iter_count(to)) return ret; written = ret; - } else { + } else if (ret != -EFAULT) { if (ret != -EAGAIN) return ret; if (iocb->ki_flags & IOCB_NOWAIT) @@ -989,12 +989,11 @@ retry_under_glock: leftover = fault_in_iov_iter_writeable(to, window_size); gfs2_holder_disallow_demote(&gh); if (leftover != window_size) { - if (!gfs2_holder_queued(&gh)) { - if (written) - goto out_uninit; - goto retry; - } - goto retry_under_glock; + if (gfs2_holder_queued(&gh)) + goto retry_under_glock; + if (written) + goto out_uninit; + goto retry; } } if (gfs2_holder_queued(&gh)) @@ -1068,12 +1067,11 @@ retry_under_glock: gfs2_holder_disallow_demote(gh); if (leftover != window_size) { from->count = min(from->count, window_size - leftover); - if (!gfs2_holder_queued(gh)) { - if (read) - goto out_uninit; - goto retry; - } - goto retry_under_glock; + if (gfs2_holder_queued(gh)) + goto retry_under_glock; + if (read && !(iocb->ki_flags & IOCB_DIRECT)) + goto out_uninit; + goto retry; } } out_unlock: @@ -1083,6 +1081,7 @@ out_uninit: gfs2_holder_uninit(gh); if (statfs_gh) kfree(statfs_gh); + from->count = orig_count - read; return read ? read : ret; } @@ -1497,7 +1496,6 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (error != GLR_TRYFAILED) break; fl_gh->gh_flags = LM_FLAG_TRY | GL_EXACT; - fl_gh->gh_error = 0; msleep(sleeptime); } if (error) { diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6b23399eaee0..630c6550eacf 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -542,7 +542,7 @@ restart: * some reason. If this holder is the head of the list, it * means we have a blocked holder at the head, so return 1. */ - if (gh->gh_list.prev == &gl->gl_holders) + if (list_is_first(&gh->gh_list, &gl->gl_holders)) return 1; do_error(gl, 0); break; @@ -669,6 +669,8 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) /* Check for state != intended state */ if (unlikely(state != gl->gl_target)) { + if (gh && (ret & LM_OUT_CANCELED)) + gfs2_holder_wake(gh); if (gh && !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) { /* move to back of queue and try next entry */ if (ret & LM_OUT_CANCELED) { @@ -1259,7 +1261,6 @@ void __gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags, gh->gh_owner_pid = get_pid(task_pid(current)); gh->gh_state = state; gh->gh_flags = flags; - gh->gh_error = 0; gh->gh_iflags = 0; gfs2_glock_hold(gl); } @@ -1565,6 +1566,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) if (test_bit(GLF_LRU, &gl->gl_flags)) gfs2_glock_remove_from_lru(gl); + gh->gh_error = 0; spin_lock(&gl->gl_lockref.lock); add_to_queue(gh); if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) && @@ -1691,6 +1693,14 @@ void gfs2_glock_dq(struct gfs2_holder *gh) struct gfs2_glock *gl = gh->gh_gl; spin_lock(&gl->gl_lockref.lock); + if (list_is_first(&gh->gh_list, &gl->gl_holders) && + !test_bit(HIF_HOLDER, &gh->gh_iflags)) { + spin_unlock(&gl->gl_lockref.lock); + gl->gl_name.ln_sbd->sd_lockstruct.ls_ops->lm_cancel(gl); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, TASK_UNINTERRUPTIBLE); + spin_lock(&gl->gl_lockref.lock); + } + __gfs2_glock_dq(gh); spin_unlock(&gl->gl_lockref.lock); } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 89905f4f29bb..c8ec876f33ea 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -131,7 +131,21 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_glock *io_gl; - error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); + error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, + &ip->i_gl); + if (unlikely(error)) + goto fail; + + error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, + &io_gl); + if (unlikely(error)) + goto fail; + + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, + &ip->i_iopen_gh); + gfs2_glock_put(io_gl); if (unlikely(error)) goto fail; @@ -161,16 +175,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags); - error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (unlikely(error)) - goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(io_gl); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); - gfs2_glock_put(io_gl); - if (unlikely(error)) - goto fail; - /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */ inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1); inode->i_atime.tv_nsec = 0; @@ -716,13 +720,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr); BUG_ON(error); - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (error) goto fail_gunlock2; + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + if (error) + goto fail_gunlock3; + error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_gunlock2; + goto fail_gunlock3; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -731,10 +739,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, init_dinode(dip, ip, symname); gfs2_trans_end(sdp); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); - if (error) - goto fail_gunlock2; - glock_set_object(ip->i_gl, ip); glock_set_object(io_gl, ip); gfs2_set_iop(inode); @@ -745,14 +749,14 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (default_acl) { error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); if (error) - goto fail_gunlock3; + goto fail_gunlock4; posix_acl_release(default_acl); default_acl = NULL; } if (acl) { error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS); if (error) - goto fail_gunlock3; + goto fail_gunlock4; posix_acl_release(acl); acl = NULL; } @@ -760,11 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name, &gfs2_initxattrs, NULL); if (error) - goto fail_gunlock3; + goto fail_gunlock4; error = link_dinode(dip, name, ip, &da); if (error) - goto fail_gunlock3; + goto fail_gunlock4; mark_inode_dirty(inode); d_instantiate(dentry, inode); @@ -782,9 +786,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, unlock_new_inode(inode); return error; -fail_gunlock3: +fail_gunlock4: glock_clear_object(ip->i_gl, ip); glock_clear_object(io_gl, ip); +fail_gunlock3: gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: gfs2_glock_put(io_gl); @@ -793,7 +798,7 @@ fail_free_inode: if (free_vfs_inode) /* else evict will do the put for us */ gfs2_glock_put(ip->i_gl); } - gfs2_rs_delete(ip, NULL); + gfs2_rs_deltree(&ip->i_res); gfs2_qa_put(ip); fail_free_acls: posix_acl_release(default_acl); diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 50578f881e6d..2559a79cf14b 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -261,6 +261,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, int req; u32 lkf; char strname[GDLM_STRNAME_BYTES] = ""; + int error; req = make_mode(gl->gl_name.ln_sbd, req_state); lkf = make_flags(gl, flags, req); @@ -279,8 +280,14 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, * Submit the actual lock request. */ - return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname, +again: + error = dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname, GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast); + if (error == -EBUSY) { + msleep(20); + goto again; + } + return error; } static void gdlm_put_lock(struct gfs2_glock *gl) @@ -312,8 +319,14 @@ static void gdlm_put_lock(struct gfs2_glock *gl) return; } +again: error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK, NULL, gl); + if (error == -EBUSY) { + msleep(20); + goto again; + } + if (error) { fs_err(sdp, "gdlm_unlock %x,%llx err=%d\n", gl->gl_name.ln_type, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 0fb3c01bc557..801ad9f4f2be 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -680,13 +680,14 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs) /** * gfs2_rs_delete - delete a multi-block reservation * @ip: The inode for this reservation - * @wcount: The inode's write count, or NULL * */ -void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount) +void gfs2_rs_delete(struct gfs2_inode *ip) { + struct inode *inode = &ip->i_inode; + down_write(&ip->i_rw_mutex); - if ((wcount == NULL) || (atomic_read(wcount) <= 1)) + if (atomic_read(&inode->i_writecount) <= 1) gfs2_rs_deltree(&ip->i_res); up_write(&ip->i_rw_mutex); } @@ -922,15 +923,15 @@ static int read_rindex_entry(struct gfs2_inode *ip) spin_lock_init(&rgd->rd_rsspin); mutex_init(&rgd->rd_mutex); - error = compute_bitstructs(rgd); - if (error) - goto fail; - error = gfs2_glock_get(sdp, rgd->rd_addr, &gfs2_rgrp_glops, CREATE, &rgd->rd_gl); if (error) goto fail; + error = compute_bitstructs(rgd); + if (error) + goto fail_glock; + rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; rgd->rd_flags &= ~GFS2_RDF_PREFERRED; if (rgd->rd_data > sdp->sd_max_rg_data) @@ -944,6 +945,7 @@ static int read_rindex_entry(struct gfs2_inode *ip) } error = 0; /* someone else read in the rgrp; free it and ignore it */ +fail_glock: gfs2_glock_put(rgd->rd_gl); fail: @@ -1415,7 +1417,8 @@ int gfs2_fitrim(struct file *filp, void __user *argp) start = r.start >> bs_shift; end = start + (r.len >> bs_shift); - minlen = max_t(u64, r.minlen, + minlen = max_t(u64, r.minlen, sdp->sd_sb.sb_bsize); + minlen = max_t(u64, minlen, q->limits.discard_granularity) >> bs_shift; if (end <= start || minlen > sdp->sd_max_rg_data) diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 3e2ca1fb4305..46dd94e9e085 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -45,7 +45,7 @@ extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, bool dinode, u64 *generation); extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); -extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount); +extern void gfs2_rs_delete(struct gfs2_inode *ip); extern void __gfs2_free_blocks(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index cf9cf66522b3..bdb773e5c88f 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1396,7 +1396,7 @@ out: truncate_inode_pages_final(&inode->i_data); if (ip->i_qadata) gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0); - gfs2_rs_delete(ip, NULL); + gfs2_rs_deltree(&ip->i_res); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); diff --git a/fs/internal.h b/fs/internal.h index fb2c2ea807d7..08503dc68d2b 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -74,7 +74,7 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, * namespace.c */ extern struct vfsmount *lookup_mnt(const struct path *); -extern int finish_automount(struct vfsmount *, struct path *); +extern int finish_automount(struct vfsmount *, const struct path *); extern int sb_prepare_remount_readonly(struct super_block *); diff --git a/fs/io_uring.c b/fs/io_uring.c index b94d57c1b0e5..4479013854d2 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -63,7 +63,6 @@ #include <net/sock.h> #include <net/af_unix.h> #include <net/scm.h> -#include <net/busy_poll.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -112,8 +111,7 @@ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) + REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -412,11 +410,6 @@ struct io_ring_ctx { struct list_head sqd_list; unsigned long check_cq_overflow; -#ifdef CONFIG_NET_RX_BUSY_POLL - /* used to track busy poll napi_id */ - struct list_head napi_list; - spinlock_t napi_lock; /* napi_list lock */ -#endif struct { unsigned cached_cq_tail; @@ -500,7 +493,6 @@ struct io_uring_task { const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; - atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; @@ -592,7 +584,8 @@ struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; - u64 len; + u32 len; + u32 flags; }; struct io_connect { @@ -611,6 +604,7 @@ struct io_sr_msg { int msg_flags; int bgid; size_t len; + size_t done_io; }; struct io_open { @@ -653,10 +647,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -781,6 +775,7 @@ enum { REQ_F_SKIP_LINK_CQES_BIT, REQ_F_SINGLE_POLL_BIT, REQ_F_DOUBLE_POLL_BIT, + REQ_F_PARTIAL_IO_BIT, /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, @@ -843,6 +838,8 @@ enum { REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT), /* double poll may active */ REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT), + /* request has already done partial IO */ + REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), }; struct async_poll { @@ -910,7 +907,11 @@ struct io_kiocb { u64 user_data; u32 result; - u32 cflags; + /* fd initially, then cflags for completion */ + union { + u32 cflags; + int fd; + }; struct io_ring_ctx *ctx; struct task_struct *task; @@ -919,11 +920,14 @@ struct io_kiocb { /* store used ubuf, so we can prevent reloading */ struct io_mapped_ubuf *imu; - /* used by request caches, completion batching and iopoll */ - struct io_wq_work_node comp_list; + union { + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + /* cache ->apoll->events */ + int apoll_events; + }; atomic_t refs; atomic_t poll_refs; - struct io_kiocb *link; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; @@ -931,9 +935,11 @@ struct io_kiocb { struct async_poll *apoll; /* opcode allocated if it needs to store data for async defer */ void *async_data; - /* custom credentials, valid IFF REQ_F_CREDS is set */ /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ struct io_buffer *kbuf; + /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + struct io_kiocb *link; + /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; struct io_wq_work work; }; @@ -962,6 +968,7 @@ struct io_op_def { /* set if opcode supports polled "wait" */ unsigned pollin : 1; unsigned pollout : 1; + unsigned poll_exclusive : 1; /* op supports buffer selection */ unsigned buffer_select : 1; /* do prep async if is going to be punted */ @@ -1056,6 +1063,7 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, + .poll_exclusive = 1, }, [IORING_OP_ASYNC_CANCEL] = { .audit_skip = 1, @@ -1175,8 +1183,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); +static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static void io_drop_inflight_file(struct io_kiocb *req); +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -1306,13 +1317,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) } static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) + struct io_ring_ctx *ctx, + unsigned int issue_flags) { if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(req->fixed_rsrc_refs); + } } } @@ -1330,6 +1348,8 @@ static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list) static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req) { + lockdep_assert_held(&req->ctx->completion_lock); + if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) return 0; return __io_put_kbuf(req, &req->ctx->io_buffers_comp); @@ -1362,6 +1382,8 @@ static inline unsigned int io_put_kbuf(struct io_kiocb *req, cflags = __io_put_kbuf(req, &ctx->io_buffers_comp); spin_unlock(&ctx->completion_lock); } else { + lockdep_assert_held(&req->ctx->uring_lock); + cflags = __io_put_kbuf(req, &req->ctx->io_buffers_cache); } @@ -1382,7 +1404,7 @@ static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, return NULL; } -static void io_kbuf_recycle(struct io_kiocb *req) +static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; @@ -1390,6 +1412,12 @@ static void io_kbuf_recycle(struct io_kiocb *req) if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) return; + /* don't recycle if we already did IO to this buffer */ + if (req->flags & REQ_F_PARTIAL_IO) + return; + + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); lockdep_assert_held(&ctx->uring_lock); @@ -1398,35 +1426,18 @@ static void io_kbuf_recycle(struct io_kiocb *req) list_add(&buf->list, &bl->buf_list); req->flags &= ~REQ_F_BUFFER_SELECTED; req->kbuf = NULL; + + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); } static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *req; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; + return cancel_all; } /* @@ -1436,24 +1447,9 @@ static bool io_match_linked(struct io_kiocb *head) static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { - bool matched; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; + return cancel_all; } static inline bool req_has_async_data(struct io_kiocb *req) @@ -1575,10 +1571,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); -#ifdef CONFIG_NET_RX_BUSY_POLL - INIT_LIST_HEAD(&ctx->napi_list); - spin_lock_init(&ctx->napi_lock); -#endif return ctx; err: kfree(ctx->dummy_ubuf); @@ -1616,14 +1608,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req) return req->flags & REQ_F_FIXED_FILE; } -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(¤t->io_uring->inflight_tracked); - } -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -1667,14 +1651,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - switch (req->opcode) { - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!S_ISREG(file_inode(req->splice.file_in)->i_mode)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } } static void io_prep_async_link(struct io_kiocb *req) @@ -1768,12 +1744,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_kiocb *req, *tmp; spin_lock_irq(&ctx->timeout_lock); - while (!list_empty(&ctx->timeout_list)) { + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; - struct io_kiocb *req = list_first_entry(&ctx->timeout_list, - struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; @@ -1790,7 +1765,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - list_del_init(&req->timeout.list); io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; @@ -2104,6 +2078,12 @@ static void __io_req_complete_post(struct io_kiocb *req, s32 res, } } io_req_put_rsrc(req, ctx); + /* + * Selected buffer deallocation in io_clean_op() assumes that + * we don't hold ->completion_lock. Clean them here to avoid + * deadlocks. + */ + io_put_kbuf_comp(req); io_dismantle_req(req); io_put_task(req->task, 1); wq_list_add_head(&req->comp_list, &ctx->locked_free_list); @@ -2148,7 +2128,7 @@ static inline void io_req_complete(struct io_kiocb *req, s32 res) static void io_req_complete_failed(struct io_kiocb *req, s32 res) { req_set_fail(req); - io_req_complete_post(req, res, io_put_kbuf(req, 0)); + io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED)); } static void io_req_complete_fail_submit(struct io_kiocb *req) @@ -2437,6 +2417,8 @@ static void handle_prev_tw_list(struct io_wq_work_node *node, struct io_kiocb *req = container_of(node, struct io_kiocb, io_task_work.node); + prefetch(container_of(next, struct io_kiocb, io_task_work.node)); + if (req->ctx != *ctx) { if (unlikely(!*uring_locked && *ctx)) ctx_commit_and_unlock(*ctx); @@ -2469,6 +2451,8 @@ static void handle_tw_list(struct io_wq_work_node *node, struct io_kiocb *req = container_of(node, struct io_kiocb, io_task_work.node); + prefetch(container_of(next, struct io_kiocb, io_task_work.node)); + if (req->ctx != *ctx) { ctx_flush_and_put(*ctx, locked); *ctx = req->ctx; @@ -2532,6 +2516,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) WARN_ON_ONCE(!tctx); + io_drop_inflight_file(req); + spin_lock_irqsave(&tctx->task_lock, flags); if (priority) wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); @@ -2974,8 +2960,12 @@ static bool io_rw_should_reissue(struct io_kiocb *req) static bool __io_complete_rw_common(struct io_kiocb *req, long res) { - if (req->rw.kiocb.ki_flags & IOCB_WRITE) + if (req->rw.kiocb.ki_flags & IOCB_WRITE) { kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } if (unlikely(res != req->result)) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { @@ -3152,42 +3142,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; unsigned ioprio; int ret; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - kiocb->ki_pos = READ_ONCE(sqe->off); - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -3203,6 +3162,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); + req->rw.flags = READ_ONCE(sqe->rw_flags); req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3231,19 +3191,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; - bool is_stream = req->file->f_mode & FMODE_STREAM; - if (kiocb->ki_pos == -1) { - if (!is_stream) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } else { - kiocb->ki_pos = 0; - return NULL; - } + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } - return is_stream ? NULL : &kiocb->ki_pos; + + kiocb->ki_pos = 0; + return NULL; } static void kiocb_done(struct io_kiocb *req, ssize_t ret, @@ -3333,7 +3292,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter return 0; } -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + unsigned int issue_flags) { struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; @@ -3343,7 +3303,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, issue_flags); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3505,7 +3465,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter); + ret = io_import_fixed(req, rw, iter, issue_flags); if (ret) return ERR_PTR(ret); return NULL; @@ -3706,13 +3666,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) return 0; } -static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_READ))) - return -EBADF; - return io_prep_rw(req, sqe); -} - /* * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. @@ -3800,6 +3753,49 @@ static bool need_read_all(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, req->rw.flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3835,6 +3831,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3938,13 +3937,6 @@ out_free: return 0; } -static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) - return -EBADF; - return io_prep_rw(req, sqe); -} - static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3965,6 +3957,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -4335,18 +4330,11 @@ static int __io_splice_prep(struct io_kiocb *req, if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; - - sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) - return -EBADF; - req->flags |= REQ_F_NEED_CLEANUP; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -4361,20 +4349,29 @@ static int io_tee_prep(struct io_kiocb *req, static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4393,15 +4390,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; @@ -4410,8 +4416,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4439,9 +4444,6 @@ static int io_msg_ring_prep(struct io_kiocb *req, sqe->splice_fd_in || sqe->buf_index || sqe->personality)) return -EINVAL; - if (req->file->f_op != &io_uring_fops) - return -EBADFD; - req->msg.user_data = READ_ONCE(sqe->off); req->msg.len = READ_ONCE(sqe->len); return 0; @@ -4451,14 +4453,18 @@ static int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx; struct io_msg *msg = &req->msg; - int ret = -EOVERFLOW; bool filled; + int ret; + + ret = -EBADFD; + if (req->file->f_op != &io_uring_fops) + goto done; + ret = -EOVERFLOW; target_ctx = req->file->private_data; spin_lock(&target_ctx->completion_lock); - filled = io_fill_cqe_aux(target_ctx, msg->user_data, msg->len, - IORING_CQE_F_MSG); + filled = io_fill_cqe_aux(target_ctx, msg->user_data, msg->len, 0); io_commit_cqring(target_ctx); spin_unlock(&target_ctx->completion_lock); @@ -4467,6 +4473,9 @@ static int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) ret = 0; } +done: + if (ret < 0) + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4475,9 +4484,6 @@ static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -4537,6 +4543,8 @@ static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) req->sync.len); if (ret < 0) req_set_fail(req); + else + fsnotify_modify(req->file); io_req_complete(req, ret); return 0; } @@ -5419,12 +5427,21 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; struct io_buffer *kbuf; unsigned flags; @@ -5467,6 +5484,11 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { req_set_fail(req); @@ -5476,6 +5498,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags)); return 0; } @@ -5526,12 +5552,23 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { out_free: req_set_fail(req); } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags)); return 0; } @@ -5569,9 +5606,6 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; - if (req->file->f_flags & O_NONBLOCK) - req->flags |= REQ_F_NOWAIT; - if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); if (unlikely(fd < 0)) @@ -5691,108 +5725,6 @@ IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ -#ifdef CONFIG_NET_RX_BUSY_POLL - -#define NAPI_TIMEOUT (60 * SEC_CONVERSION) - -struct napi_entry { - struct list_head list; - unsigned int napi_id; - unsigned long timeout; -}; - -/* - * Add busy poll NAPI ID from sk. - */ -static void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ - unsigned int napi_id; - struct socket *sock; - struct sock *sk; - struct napi_entry *ne; - - if (!net_busy_loop_on()) - return; - - sock = sock_from_file(file); - if (!sock) - return; - - sk = sock->sk; - if (!sk) - return; - - napi_id = READ_ONCE(sk->sk_napi_id); - - /* Non-NAPI IDs can be rejected */ - if (napi_id < MIN_NAPI_ID) - return; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(ne, &ctx->napi_list, list) { - if (ne->napi_id == napi_id) { - ne->timeout = jiffies + NAPI_TIMEOUT; - goto out; - } - } - - ne = kmalloc(sizeof(*ne), GFP_NOWAIT); - if (!ne) - goto out; - - ne->napi_id = napi_id; - ne->timeout = jiffies + NAPI_TIMEOUT; - list_add_tail(&ne->list, &ctx->napi_list); -out: - spin_unlock(&ctx->napi_lock); -} - -static inline void io_check_napi_entry_timeout(struct napi_entry *ne) -{ - if (time_after(jiffies, ne->timeout)) { - list_del(&ne->list); - kfree(ne); - } -} - -/* - * Busy poll if globally on and supporting sockets found - */ -static bool io_napi_busy_loop(struct list_head *napi_list) -{ - struct napi_entry *ne, *n; - - list_for_each_entry_safe(ne, n, napi_list, list) { - napi_busy_loop(ne->napi_id, NULL, NULL, true, - BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - } - return !list_empty(napi_list); -} - -static void io_free_napi_list(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->napi_lock); - while (!list_empty(&ctx->napi_list)) { - struct napi_entry *ne = - list_first_entry(&ctx->napi_list, struct napi_entry, - list); - - list_del(&ne->list); - kfree(ne); - } - spin_unlock(&ctx->napi_lock); -} -#else -static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ -} - -static inline void io_free_napi_list(struct io_ring_ctx *ctx) -{ -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; @@ -5801,7 +5733,7 @@ struct io_poll_table { }; #define IO_POLL_CANCEL_FLAG BIT(31) -#define IO_POLL_REF_MASK ((1u << 20)-1) +#define IO_POLL_REF_MASK GENMASK(30, 0) /* * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can @@ -5906,10 +5838,9 @@ static void io_poll_remove_entries(struct io_kiocb *req) * either spurious wakeup or multishot CQE is served. 0 when it's done with * the request, then the mask is stored in req->result. */ -static int io_poll_check_events(struct io_kiocb *req) +static int io_poll_check_events(struct io_kiocb *req, bool locked) { struct io_ring_ctx *ctx = req->ctx; - struct io_poll_iocb *poll = io_poll_get_single(req); int v; /* req->task == current here, checking PF_EXITING is safe */ @@ -5926,14 +5857,17 @@ static int io_poll_check_events(struct io_kiocb *req) return -ECANCELED; if (!req->result) { - struct poll_table_struct pt = { ._key = req->cflags }; + struct poll_table_struct pt = { ._key = req->apoll_events }; + unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED; - req->result = vfs_poll(req->file, &pt) & req->cflags; + if (unlikely(!io_assign_file(req, flags))) + return -EBADF; + req->result = vfs_poll(req->file, &pt) & req->apoll_events; } /* multishot, just fill an CQE and proceed */ - if (req->result && !(req->cflags & EPOLLONESHOT)) { - __poll_t mask = mangle_poll(req->result & poll->events); + if (req->result && !(req->apoll_events & EPOLLONESHOT)) { + __poll_t mask = mangle_poll(req->result & req->apoll_events); bool filled; spin_lock(&ctx->completion_lock); @@ -5944,7 +5878,6 @@ static int io_poll_check_events(struct io_kiocb *req) if (unlikely(!filled)) return -ECANCELED; io_cqring_ev_posted(ctx); - io_add_napi(req->file, ctx); } else if (req->result) { return 0; } @@ -5963,7 +5896,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -5988,7 +5921,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6012,7 +5945,7 @@ static void __io_poll_execute(struct io_kiocb *req, int mask, int events) * CPU. We want to avoid pulling in req->apoll->events for that * case. */ - req->cflags = events; + req->apoll_events = events; if (req->opcode == IORING_OP_POLL_ADD) req->io_task_work.func = io_poll_task_func; else @@ -6035,10 +5968,13 @@ static void io_poll_cancel_req(struct io_kiocb *req) io_poll_execute(req, 0, 0); } +#define wqe_to_req(wait) ((void *)((unsigned long) (wait)->private & ~1)) +#define wqe_is_double(wait) ((unsigned long) (wait)->private & 1) + static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { - struct io_kiocb *req = wait->private; + struct io_kiocb *req = wqe_to_req(wait); struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, wait); __poll_t mask = key_to_poll(key); @@ -6076,7 +6012,10 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (mask && poll->events & EPOLLONESHOT) { list_del_init(&poll->wait.entry); poll->head = NULL; - req->flags &= ~REQ_F_SINGLE_POLL; + if (wqe_is_double(wait)) + req->flags &= ~REQ_F_DOUBLE_POLL; + else + req->flags &= ~REQ_F_SINGLE_POLL; } __io_poll_execute(req, mask, poll->events); } @@ -6088,6 +6027,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, struct io_poll_iocb **poll_ptr) { struct io_kiocb *req = pt->req; + unsigned long wqe_private = (unsigned long) req; /* * The file being polled uses multiple waitqueues for poll handling @@ -6113,6 +6053,8 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, pt->error = -ENOMEM; return; } + /* mark as double wq entry */ + wqe_private |= 1; req->flags |= REQ_F_DOUBLE_POLL; io_init_poll_iocb(poll, first->events, first->wait.func); *poll_ptr = poll; @@ -6123,7 +6065,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, req->flags |= REQ_F_SINGLE_POLL; pt->nr_entries++; poll->head = head; - poll->wait.private = req; + poll->wait.private = (void *) wqe_private; if (poll->events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(head, &poll->wait); @@ -6150,7 +6092,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, INIT_HLIST_NODE(&req->hash_node); io_init_poll_iocb(poll, mask, io_poll_wake); poll->file = req->file; - poll->wait.private = req; ipt->pt._key = mask; ipt->req = req; @@ -6187,7 +6128,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, __io_poll_execute(req, mask, poll->events); return 0; } - io_add_napi(req->file, req->ctx); /* * Release ownership. If someone tried to queue a tw while it was @@ -6238,7 +6178,8 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) } else { mask |= POLLOUT | POLLWRNORM; } - + if (def->poll_exclusive) + mask |= EPOLLEXCLUSIVE; if (!(issue_flags & IO_URING_F_UNLOCKED) && !list_empty(&ctx->apoll_cache)) { apoll = list_first_entry(&ctx->apoll_cache, struct async_poll, @@ -6254,6 +6195,8 @@ static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) req->flags |= REQ_F_POLLED; ipt.pt._qproc = io_async_queue_proc; + io_kbuf_recycle(req, issue_flags); + ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask); if (ret || ipt.error) return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; @@ -6281,6 +6224,7 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { if (io_match_task_safe(req, tsk, cancel_all)) { + hlist_del_init(&req->hash_node); io_poll_cancel_req(req); found = true; } @@ -6393,7 +6337,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return -EINVAL; io_req_set_refcount(req); - req->cflags = poll->events = io_poll_parse_events(sqe, flags); + req->apoll_events = poll->events = io_poll_parse_events(sqe, flags); return 0; } @@ -6688,6 +6632,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); @@ -6894,6 +6839,7 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) up.nr = 0; up.tags = 0; up.resv = 0; + up.resv2 = 0; io_ring_submit_lock(ctx, needs_lock); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, @@ -6914,11 +6860,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - return io_write_prep(req, sqe); + return io_prep_rw(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: @@ -7075,8 +7020,11 @@ fail: static void io_clean_op(struct io_kiocb *req) { - if (req->flags & REQ_F_BUFFER_SELECTED) + if (req->flags & REQ_F_BUFFER_SELECTED) { + spin_lock(&req->ctx->completion_lock); io_put_kbuf_comp(req); + spin_unlock(&req->ctx->completion_lock); + } if (req->flags & REQ_F_NEED_CLEANUP) { switch (req->opcode) { @@ -7098,11 +7046,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(req->splice.file_in); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) @@ -7137,11 +7080,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->apoll); req->apoll = NULL; } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { @@ -7151,11 +7089,31 @@ static void io_clean_op(struct io_kiocb *req) req->flags &= ~IO_REQ_CLEAN_FLAGS; } +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->fd, issue_flags); + else + req->file = io_file_get_normal(req, req->fd); + if (req->file) + return true; + + req_set_fail(req); + req->result = -EBADF; + return false; +} + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct cred *creds = NULL; int ret; + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; + if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) creds = override_creds(req->creds); @@ -7305,10 +7263,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; struct io_kiocb *timeout; - int ret = 0; + int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) @@ -7320,14 +7279,20 @@ static void io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { - io_req_task_queue_fail(req, -ECANCELED); +fail: + io_req_task_queue_fail(req, err); return; } + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + goto fail; + } if (req->flags & REQ_F_FORCE_ASYNC) { - const struct io_op_def *def = &io_op_defs[req->opcode]; bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && file_can_poll(req->file)) { @@ -7384,46 +7349,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file file_slot->file_ptr = file_ptr; } -static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; unsigned long file_ptr; + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, 0); +out: + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); return file; } -static struct file *io_file_get_normal(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +/* + * Drop the file for requeue operations. Only used of req->file is the + * io_uring descriptor itself. + */ +static void io_drop_inflight_file(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_INFLIGHT)) { + fput(req->file); + req->file = NULL; + req->flags &= ~REQ_F_INFLIGHT; + } +} + +static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(ctx, req, req->user_data, fd); + trace_io_uring_file_get(req->ctx, req, req->user_data, fd); /* we don't allow fixed io_uring files */ - if (file && unlikely(file->f_op == &io_uring_fops)) - io_req_track_inflight(req); + if (file && file->f_op == &io_uring_fops) + req->flags |= REQ_F_INFLIGHT; return file; } -static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) -{ - if (fixed) - return io_file_get_fixed(ctx, req, fd); - else - return io_file_get_normal(ctx, req, fd); -} - static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; @@ -7505,11 +7480,9 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req) * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ - io_kbuf_recycle(req); io_queue_async_work(req, NULL); break; case IO_APOLL_OK: - io_kbuf_recycle(req); break; } @@ -7665,6 +7638,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; + req->fd = READ_ONCE(sqe->fd); + /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. @@ -7674,11 +7649,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); - if (unlikely(!req->file)) - return -EBADF; } personality = READ_ONCE(sqe->personality); @@ -7953,13 +7923,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); -#ifdef CONFIG_NET_RX_BUSY_POLL - spin_lock(&ctx->napi_lock); - if (!list_empty(&ctx->napi_list) && - io_napi_busy_loop(&ctx->napi_list)) - ++ret; - spin_unlock(&ctx->napi_lock); -#endif + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) @@ -8053,6 +8017,13 @@ static int io_sq_thread(void *data) needs_sched = false; break; } + + /* + * Ensure the store of the wakeup flag is not + * reordered with the load of the SQ tail + */ + smp_mb(); + if (io_sqring_entries(ctx)) { needs_sched = false; break; @@ -8090,9 +8061,6 @@ struct io_wait_queue { struct io_ring_ctx *ctx; unsigned cq_tail; unsigned nr_timeouts; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned busy_poll_to; -#endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) @@ -8154,87 +8122,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return 1; } -#ifdef CONFIG_NET_RX_BUSY_POLL -static void io_adjust_busy_loop_timeout(struct timespec64 *ts, - struct io_wait_queue *iowq) -{ - unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll); - struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to); - - if (timespec64_compare(ts, &pollto) > 0) { - *ts = timespec64_sub(*ts, pollto); - iowq->busy_poll_to = busy_poll_to; - } else { - u64 to = timespec64_to_ns(ts); - - do_div(to, 1000); - iowq->busy_poll_to = to; - ts->tv_sec = 0; - ts->tv_nsec = 0; - } -} - -static inline bool io_busy_loop_timeout(unsigned long start_time, - unsigned long bp_usec) -{ - if (bp_usec) { - unsigned long end_time = start_time + bp_usec; - unsigned long now = busy_loop_current_time(); - - return time_after(now, end_time); - } - return true; -} - -static bool io_busy_loop_end(void *p, unsigned long start_time) -{ - struct io_wait_queue *iowq = p; - - return signal_pending(current) || - io_should_wake(iowq) || - io_busy_loop_timeout(start_time, iowq->busy_poll_to); -} - -static void io_blocking_napi_busy_loop(struct list_head *napi_list, - struct io_wait_queue *iowq) -{ - unsigned long start_time = - list_is_singular(napi_list) ? 0 : - busy_loop_current_time(); - - do { - if (list_is_singular(napi_list)) { - struct napi_entry *ne = - list_first_entry(napi_list, - struct napi_entry, list); - - napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq, - true, BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - break; - } - } while (io_napi_busy_loop(napi_list) && - !io_busy_loop_end(iowq, start_time)); -} - -static void io_putback_napi_list(struct io_ring_ctx *ctx, - struct list_head *napi_list) -{ - struct napi_entry *cne, *lne; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(cne, &ctx->napi_list, list) - list_for_each_entry(lne, napi_list, list) - if (cne->napi_id == lne->napi_id) { - list_del(&lne->list); - kfree(lne); - break; - } - list_splice(napi_list, &ctx->napi_list); - spin_unlock(&ctx->napi_lock); -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. @@ -8247,9 +8134,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, struct io_rings *rings = ctx->rings; ktime_t timeout = KTIME_MAX; int ret; -#ifdef CONFIG_NET_RX_BUSY_POLL - LIST_HEAD(local_napi_list); -#endif do { io_cqring_overflow_flush(ctx); @@ -8272,29 +8156,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } -#ifdef CONFIG_NET_RX_BUSY_POLL - iowq.busy_poll_to = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { - spin_lock(&ctx->napi_lock); - list_splice_init(&ctx->napi_list, &local_napi_list); - spin_unlock(&ctx->napi_lock); - } -#endif if (uts) { struct timespec64 ts; if (get_timespec64(&ts, uts)) return -EFAULT; -#ifdef CONFIG_NET_RX_BUSY_POLL - if (!list_empty(&local_napi_list)) - io_adjust_busy_loop_timeout(&ts, &iowq); -#endif timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } -#ifdef CONFIG_NET_RX_BUSY_POLL - else if (!list_empty(&local_napi_list)) - iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll); -#endif init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; @@ -8304,12 +8172,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; trace_io_uring_cqring_wait(ctx, min_events); -#ifdef CONFIG_NET_RX_BUSY_POLL - if (iowq.busy_poll_to) - io_blocking_napi_busy_loop(&local_napi_list, &iowq); - if (!list_empty(&local_napi_list)) - io_putback_napi_list(ctx, &local_napi_list); -#endif do { /* if we can't even flush overflow, don't wait for more */ if (!io_cqring_overflow_flush(ctx)) { @@ -8778,10 +8640,15 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_queue_head(&sk->sk_receive_queue, skb); - for (i = 0; i < nr_files; i++) - fput(fpl->fp[i]); + for (i = 0; i < nr; i++) { + struct file *file = io_file_from_index(ctx, i + offset); + + if (file) + fput(file); + } } else { kfree_skb(skb); + free_uid(fpl->user); kfree(fpl); } @@ -9069,13 +8936,15 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { + u64 *tag_slot = io_get_tag_slot(data, idx); struct io_rsrc_put *prsrc; prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); if (!prsrc) return -ENOMEM; - prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->tag = *tag_slot; + *tag_slot = 0; prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; @@ -9144,7 +9013,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; - int ret, i; + int ret; io_ring_submit_lock(ctx, needs_lock); ret = -ENXIO; @@ -9157,8 +9026,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) if (ret) goto out; - i = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); ret = -EBADF; if (!file_slot->file_ptr) goto out; @@ -9214,8 +9083,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (file_slot->file_ptr) { file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, up->offset + done, - ctx->rsrc_node, file); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; file_slot->file_ptr = 0; @@ -9240,7 +9108,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, up->offset + done) = tag; + *io_get_tag_slot(data, i) = tag; io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { @@ -9324,7 +9192,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); @@ -9899,7 +9766,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, i = array_index_nospec(offset, ctx->nr_user_bufs); if (ctx->user_bufs[i] != ctx->dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, offset, + err = io_queue_rsrc_removal(ctx->buf_data, i, ctx->rsrc_node, ctx->user_bufs[i]); if (unlikely(err)) { io_buffer_unmap(ctx, &imu); @@ -10094,7 +9961,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); - io_free_napi_list(ctx); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); kfree(ctx->io_buffers); @@ -10517,7 +10383,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) - return atomic_read(&tctx->inflight_tracked); + return 0; return percpu_counter_sum(&tctx->inflight); } @@ -10668,6 +10534,11 @@ static int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, break; } + if (reg.resv) { + ret = -EINVAL; + break; + } + if (reg.offset == -1U) { start = 0; end = IO_RINGFD_REG_MAX; @@ -10714,7 +10585,7 @@ static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, ret = -EFAULT; break; } - if (reg.offset >= IO_RINGFD_REG_MAX) { + if (reg.resv || reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } @@ -10841,6 +10712,8 @@ static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz return -EINVAL; if (copy_from_user(&arg, argp, sizeof(arg))) return -EFAULT; + if (arg.pad) + return -EINVAL; *sig = u64_to_user_ptr(arg.sigmask); *argsz = arg.sigmask_sz; *ts = u64_to_user_ptr(arg.ts); @@ -11322,7 +11195,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | - IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP; + IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | + IORING_FEAT_LINKED_FILE; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -11533,8 +11407,6 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, __u32 tmp; int err; - if (up->resv) - return -EINVAL; if (check_add_overflow(up->offset, nr_args, &tmp)) return -EOVERFLOW; err = io_rsrc_node_switch_start(ctx); @@ -11560,6 +11432,8 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, memset(&up, 0, sizeof(up)); if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); } @@ -11572,7 +11446,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; - if (!up.nr || up.resv) + if (!up.nr || up.resv || up.resv2) return -EINVAL; return __io_register_rsrc_update(ctx, type, &up, up.nr); } @@ -11620,7 +11494,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, if (len > cpumask_size()) len = cpumask_size(); - if (copy_from_user(new_mask, arg, len)) { + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } + + if (ret) { free_cpumask_var(new_mask); return -EFAULT; } diff --git a/fs/ioctl.c b/fs/ioctl.c index 090bf47606ab..80ac36aea913 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -173,7 +173,7 @@ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, if (*len == 0) return -EINVAL; - if (start > maxbytes) + if (start >= maxbytes) return -EFBIG; /* diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 49dccd9050f1..8ce8720093b9 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -435,18 +435,17 @@ bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { struct iomap_page *iop = to_iomap_page(folio); struct inode *inode = folio->mapping->host; - size_t len; unsigned first, last, i; if (!iop) return false; - /* Limit range to this folio */ - len = min(folio_size(folio) - from, count); + /* Caller's range may extend past the end of this folio */ + count = min(folio_size(folio) - from, count); - /* First and last blocks in range within page */ + /* First and last blocks in range within folio */ first = from >> inode->i_blkbits; - last = (from + len - 1) >> inode->i_blkbits; + last = (from + count - 1) >> inode->i_blkbits; for (i = first; i <= last; i++) if (!test_bit(i, iop->uptodate)) diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index b288c8ae1236..837cd55fd4c5 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -415,13 +415,15 @@ int jffs2_do_mount_fs(struct jffs2_sb_info *c) jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); ret = -EIO; - goto out_free; + goto out_sum_exit; } jffs2_calc_trigger_levels(c); return 0; + out_sum_exit: + jffs2_sum_exit(c); out_free: kvfree(c->blocks); diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 2ac410477c4f..71f03a5d36ed 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -603,8 +603,8 @@ out_root: jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); kvfree(c->blocks); - out_inohash: jffs2_clear_xattr_subsystem(c); + out_inohash: kfree(c->inocache_list); out_wbuf: jffs2_flash_cleanup(c); diff --git a/fs/jffs2/jffs2_fs_i.h b/fs/jffs2/jffs2_fs_i.h index 2e4a86763c07..93a2951538ce 100644 --- a/fs/jffs2/jffs2_fs_i.h +++ b/fs/jffs2/jffs2_fs_i.h @@ -18,11 +18,11 @@ #include <linux/mutex.h> struct jffs2_inode_info { - /* We need an internal mutex similar to inode->i_mutex. + /* We need an internal mutex similar to inode->i_rwsem. Unfortunately, we can't used the existing one, because either the GC would deadlock, or we'd have to release it before letting GC proceed. Or we'd have to put ugliness - into the GC code so it didn't attempt to obtain the i_mutex + into the GC code so it didn't attempt to obtain the i_rwsem for the inode(s) which are already locked */ struct mutex sem; diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index b676056826be..29671e33a171 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -136,7 +136,7 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) if (!s) { JFFS2_WARNING("Can't allocate memory for summary\n"); ret = -ENOMEM; - goto out; + goto out_buf; } } @@ -275,13 +275,15 @@ int jffs2_scan_medium(struct jffs2_sb_info *c) } ret = 0; out: + jffs2_sum_reset_collected(s); + kfree(s); + out_buf: if (buf_size) kfree(flashbuf); #ifndef __ECOS else mtd_unpoint(c->mtd, 0, c->mtd->size); #endif - kfree(s); return ret; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 74067a73ff78..88423069407c 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -120,13 +120,8 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; - } else { - /* - * The same behavior and code as single_open(). Returns - * !NULL if pos is at the beginning; otherwise, NULL. - */ - return NULL + !*ppos; } + return single_start(sf, ppos); } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 077b8761d099..23871b18a429 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -656,8 +656,8 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp->OplockLevel = SMB2_OPLOCK_LEVEL_NONE; rsp->Reserved = 0; rsp->Reserved2 = 0; - rsp->PersistentFid = cpu_to_le64(fp->persistent_id); - rsp->VolatileFid = cpu_to_le64(fp->volatile_id); + rsp->PersistentFid = fp->persistent_id; + rsp->VolatileFid = fp->volatile_id; inc_rfc1001_len(work->response_buf, 24); diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 2e12f6d8483b..4cd03d661df0 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -585,7 +585,7 @@ static int __init ksmbd_server_init(void) if (ret) goto err_crypto_destroy; - pr_warn_once("The ksmbd server is experimental, use at your own risk.\n"); + pr_warn_once("The ksmbd server is experimental\n"); return 0; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 67e8e28e3fc3..3bf6c56c654c 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -377,12 +377,8 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) * command in the compound request */ if (req->Command == SMB2_CREATE && rsp->Status == STATUS_SUCCESS) { - work->compound_fid = - le64_to_cpu(((struct smb2_create_rsp *)rsp)-> - VolatileFileId); - work->compound_pfid = - le64_to_cpu(((struct smb2_create_rsp *)rsp)-> - PersistentFileId); + work->compound_fid = ((struct smb2_create_rsp *)rsp)->VolatileFileId; + work->compound_pfid = ((struct smb2_create_rsp *)rsp)->PersistentFileId; work->compound_sid = le64_to_cpu(rsp->SessionId); } @@ -2129,7 +2125,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) rsp->EndofFile = cpu_to_le64(0); rsp->FileAttributes = FILE_ATTRIBUTE_NORMAL_LE; rsp->Reserved2 = 0; - rsp->VolatileFileId = cpu_to_le64(id); + rsp->VolatileFileId = id; rsp->PersistentFileId = 0; rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; @@ -3157,8 +3153,8 @@ int smb2_open(struct ksmbd_work *work) rsp->Reserved2 = 0; - rsp->PersistentFileId = cpu_to_le64(fp->persistent_id); - rsp->VolatileFileId = cpu_to_le64(fp->volatile_id); + rsp->PersistentFileId = fp->persistent_id; + rsp->VolatileFileId = fp->volatile_id; rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; @@ -3865,9 +3861,7 @@ int smb2_query_dir(struct ksmbd_work *work) goto err_out2; } - dir_fp = ksmbd_lookup_fd_slow(work, - le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + dir_fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); if (!dir_fp) { rc = -EBADF; goto err_out2; @@ -4088,12 +4082,12 @@ static int smb2_get_info_file_pipe(struct ksmbd_session *sess, * Windows can sometime send query file info request on * pipe without opening it, checking error condition here */ - id = le64_to_cpu(req->VolatileFileId); + id = req->VolatileFileId; if (!ksmbd_session_rpc_method(sess, id)) return -ENOENT; ksmbd_debug(SMB, "FileInfoClass %u, FileId 0x%llx\n", - req->FileInfoClass, le64_to_cpu(req->VolatileFileId)); + req->FileInfoClass, req->VolatileFileId); switch (req->FileInfoClass) { case FILE_STANDARD_INFORMATION: @@ -4738,7 +4732,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, } if (work->next_smb2_rcv_hdr_off) { - if (!has_file_id(le64_to_cpu(req->VolatileFileId))) { + if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); id = work->compound_fid; @@ -4747,8 +4741,8 @@ static int smb2_get_info_file(struct ksmbd_work *work, } if (!has_file_id(id)) { - id = le64_to_cpu(req->VolatileFileId); - pid = le64_to_cpu(req->PersistentFileId); + id = req->VolatileFileId; + pid = req->PersistentFileId; } fp = ksmbd_lookup_fd_slow(work, id, pid); @@ -5113,7 +5107,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, } if (work->next_smb2_rcv_hdr_off) { - if (!has_file_id(le64_to_cpu(req->VolatileFileId))) { + if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); id = work->compound_fid; @@ -5122,8 +5116,8 @@ static int smb2_get_info_sec(struct ksmbd_work *work, } if (!has_file_id(id)) { - id = le64_to_cpu(req->VolatileFileId); - pid = le64_to_cpu(req->PersistentFileId); + id = req->VolatileFileId; + pid = req->PersistentFileId; } fp = ksmbd_lookup_fd_slow(work, id, pid); @@ -5221,7 +5215,7 @@ static noinline int smb2_close_pipe(struct ksmbd_work *work) struct smb2_close_req *req = smb2_get_msg(work->request_buf); struct smb2_close_rsp *rsp = smb2_get_msg(work->response_buf); - id = le64_to_cpu(req->VolatileFileId); + id = req->VolatileFileId; ksmbd_session_rpc_close(work->sess, id); rsp->StructureSize = cpu_to_le16(60); @@ -5280,7 +5274,7 @@ int smb2_close(struct ksmbd_work *work) } if (work->next_smb2_rcv_hdr_off && - !has_file_id(le64_to_cpu(req->VolatileFileId))) { + !has_file_id(req->VolatileFileId)) { if (!has_file_id(work->compound_fid)) { /* file already closed, return FILE_CLOSED */ ksmbd_debug(SMB, "file already closed\n"); @@ -5299,7 +5293,7 @@ int smb2_close(struct ksmbd_work *work) work->compound_pfid = KSMBD_NO_FID; } } else { - volatile_id = le64_to_cpu(req->VolatileFileId); + volatile_id = req->VolatileFileId; } ksmbd_debug(SMB, "volatile_id = %llu\n", volatile_id); @@ -5988,7 +5982,7 @@ int smb2_set_info(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); - if (!has_file_id(le64_to_cpu(req->VolatileFileId))) { + if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); id = work->compound_fid; @@ -6000,8 +5994,8 @@ int smb2_set_info(struct ksmbd_work *work) } if (!has_file_id(id)) { - id = le64_to_cpu(req->VolatileFileId); - pid = le64_to_cpu(req->PersistentFileId); + id = req->VolatileFileId; + pid = req->PersistentFileId; } fp = ksmbd_lookup_fd_slow(work, id, pid); @@ -6079,7 +6073,7 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) struct smb2_read_req *req = smb2_get_msg(work->request_buf); struct smb2_read_rsp *rsp = smb2_get_msg(work->response_buf); - id = le64_to_cpu(req->VolatileFileId); + id = req->VolatileFileId; inc_rfc1001_len(work->response_buf, 16); rpc_resp = ksmbd_rpc_read(work->sess, id); @@ -6215,8 +6209,7 @@ int smb2_read(struct ksmbd_work *work) goto out; } - fp = ksmbd_lookup_fd_slow(work, le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); if (!fp) { err = -ENOENT; goto out; @@ -6335,7 +6328,7 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) size_t length; length = le32_to_cpu(req->Length); - id = le64_to_cpu(req->VolatileFileId); + id = req->VolatileFileId; if (le16_to_cpu(req->DataOffset) == offsetof(struct smb2_write_req, Buffer)) { @@ -6471,8 +6464,7 @@ int smb2_write(struct ksmbd_work *work) goto out; } - fp = ksmbd_lookup_fd_slow(work, le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); if (!fp) { err = -ENOENT; goto out; @@ -6584,12 +6576,9 @@ int smb2_flush(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - ksmbd_debug(SMB, "SMB2_FLUSH called for fid %llu\n", - le64_to_cpu(req->VolatileFileId)); + ksmbd_debug(SMB, "SMB2_FLUSH called for fid %llu\n", req->VolatileFileId); - err = ksmbd_vfs_fsync(work, - le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + err = ksmbd_vfs_fsync(work, req->VolatileFileId, req->PersistentFileId); if (err) goto out; @@ -6618,8 +6607,7 @@ int smb2_cancel(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); struct smb2_hdr *chdr; - struct ksmbd_work *cancel_work = NULL; - int canceled = 0; + struct ksmbd_work *cancel_work = NULL, *iter; struct list_head *command_list; ksmbd_debug(SMB, "smb2 cancel called on mid %llu, async flags 0x%x\n", @@ -6629,11 +6617,11 @@ int smb2_cancel(struct ksmbd_work *work) command_list = &conn->async_requests; spin_lock(&conn->request_lock); - list_for_each_entry(cancel_work, command_list, + list_for_each_entry(iter, command_list, async_request_entry) { - chdr = smb2_get_msg(cancel_work->request_buf); + chdr = smb2_get_msg(iter->request_buf); - if (cancel_work->async_id != + if (iter->async_id != le64_to_cpu(hdr->Id.AsyncId)) continue; @@ -6641,7 +6629,7 @@ int smb2_cancel(struct ksmbd_work *work) "smb2 with AsyncId %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->Id.AsyncId), le16_to_cpu(chdr->Command)); - canceled = 1; + cancel_work = iter; break; } spin_unlock(&conn->request_lock); @@ -6649,24 +6637,24 @@ int smb2_cancel(struct ksmbd_work *work) command_list = &conn->requests; spin_lock(&conn->request_lock); - list_for_each_entry(cancel_work, command_list, request_entry) { - chdr = smb2_get_msg(cancel_work->request_buf); + list_for_each_entry(iter, command_list, request_entry) { + chdr = smb2_get_msg(iter->request_buf); if (chdr->MessageId != hdr->MessageId || - cancel_work == work) + iter == work) continue; ksmbd_debug(SMB, "smb2 with mid %llu cancelled command = 0x%x\n", le64_to_cpu(hdr->MessageId), le16_to_cpu(chdr->Command)); - canceled = 1; + cancel_work = iter; break; } spin_unlock(&conn->request_lock); } - if (canceled) { + if (cancel_work) { cancel_work->state = KSMBD_WORK_CANCELLED; if (cancel_work->cancel_fn) cancel_work->cancel_fn(cancel_work->cancel_argv); @@ -6804,12 +6792,9 @@ int smb2_lock(struct ksmbd_work *work) int prior_lock = 0; ksmbd_debug(SMB, "Received lock request\n"); - fp = ksmbd_lookup_fd_slow(work, - le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); if (!fp) { - ksmbd_debug(SMB, "Invalid file id for lock : %llu\n", - le64_to_cpu(req->VolatileFileId)); + ksmbd_debug(SMB, "Invalid file id for lock : %llu\n", req->VolatileFileId); err = -ENOENT; goto out2; } @@ -7164,8 +7149,8 @@ static int fsctl_copychunk(struct ksmbd_work *work, ci_rsp = (struct copychunk_ioctl_rsp *)&rsp->Buffer[0]; - rsp->VolatileFileId = cpu_to_le64(volatile_id); - rsp->PersistentFileId = cpu_to_le64(persistent_id); + rsp->VolatileFileId = volatile_id; + rsp->PersistentFileId = persistent_id; ci_rsp->ChunksWritten = cpu_to_le32(ksmbd_server_side_copy_max_chunk_count()); ci_rsp->ChunkBytesWritten = @@ -7379,8 +7364,8 @@ ipv6_retry: if (nii_rsp) nii_rsp->Next = 0; - rsp->PersistentFileId = cpu_to_le64(SMB2_NO_FID); - rsp->VolatileFileId = cpu_to_le64(SMB2_NO_FID); + rsp->PersistentFileId = SMB2_NO_FID; + rsp->VolatileFileId = SMB2_NO_FID; return nbytes; } @@ -7547,9 +7532,7 @@ static int fsctl_request_resume_key(struct ksmbd_work *work, { struct ksmbd_file *fp; - fp = ksmbd_lookup_fd_slow(work, - le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId)); + fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); if (!fp) return -ENOENT; @@ -7579,7 +7562,7 @@ int smb2_ioctl(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); - if (!has_file_id(le64_to_cpu(req->VolatileFileId))) { + if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); id = work->compound_fid; @@ -7590,14 +7573,14 @@ int smb2_ioctl(struct ksmbd_work *work) } if (!has_file_id(id)) - id = le64_to_cpu(req->VolatileFileId); + id = req->VolatileFileId; if (req->Flags != cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL)) { rsp->hdr.Status = STATUS_NOT_SUPPORTED; goto out; } - cnt_code = le32_to_cpu(req->CntCode); + cnt_code = le32_to_cpu(req->CtlCode); ret = smb2_calc_max_out_buf_len(work, 48, le32_to_cpu(req->MaxOutputResponse)); if (ret < 0) { @@ -7656,8 +7639,8 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; nbytes = sizeof(struct validate_negotiate_info_rsp); - rsp->PersistentFileId = cpu_to_le64(SMB2_NO_FID); - rsp->VolatileFileId = cpu_to_le64(SMB2_NO_FID); + rsp->PersistentFileId = SMB2_NO_FID; + rsp->VolatileFileId = SMB2_NO_FID; break; case FSCTL_QUERY_NETWORK_INTERFACE_INFO: ret = fsctl_query_iface_info_ioctl(conn, rsp, out_buf_len); @@ -7703,10 +7686,10 @@ int smb2_ioctl(struct ksmbd_work *work) rsp->PersistentFileId = req->PersistentFileId; fsctl_copychunk(work, (struct copychunk_ioctl_req *)&req->Buffer[0], - le32_to_cpu(req->CntCode), + le32_to_cpu(req->CtlCode), le32_to_cpu(req->InputCount), - le64_to_cpu(req->VolatileFileId), - le64_to_cpu(req->PersistentFileId), + req->VolatileFileId, + req->PersistentFileId, rsp); break; case FSCTL_SET_SPARSE: @@ -7857,7 +7840,7 @@ dup_ext_out: goto out; } - rsp->CntCode = cpu_to_le32(cnt_code); + rsp->CtlCode = cpu_to_le32(cnt_code); rsp->InputCount = cpu_to_le32(0); rsp->InputOffset = cpu_to_le32(112); rsp->OutputOffset = cpu_to_le32(112); @@ -7903,8 +7886,8 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) char req_oplevel = 0, rsp_oplevel = 0; unsigned int oplock_change_type; - volatile_id = le64_to_cpu(req->VolatileFid); - persistent_id = le64_to_cpu(req->PersistentFid); + volatile_id = req->VolatileFid; + persistent_id = req->PersistentFid; req_oplevel = req->OplockLevel; ksmbd_debug(OPLOCK, "v_id %llu, p_id %llu request oplock level %d\n", volatile_id, persistent_id, req_oplevel); @@ -7999,8 +7982,8 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->OplockLevel = rsp_oplevel; rsp->Reserved = 0; rsp->Reserved2 = 0; - rsp->VolatileFid = cpu_to_le64(volatile_id); - rsp->PersistentFid = cpu_to_le64(persistent_id); + rsp->VolatileFid = volatile_id; + rsp->PersistentFid = persistent_id; inc_rfc1001_len(work->response_buf, 24); return; @@ -8500,7 +8483,7 @@ static void fill_transform_hdr(void *tr_buf, char *old_buf, __le16 cipher_type) struct smb2_hdr *hdr = smb2_get_msg(old_buf); unsigned int orig_len = get_rfc1002_len(old_buf); - memset(tr_buf, 0, sizeof(struct smb2_transform_hdr) + 4); + /* tr_buf must be cleared by the caller */ tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM; tr_hdr->OriginalMessageSize = cpu_to_le32(orig_len); tr_hdr->Flags = cpu_to_le16(TRANSFORM_FLAG_ENCRYPTED); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index d49468426576..af455278d005 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -16,42 +16,13 @@ #define FILE_CREATED 0x00000002 #define FILE_OVERWRITTEN 0x00000003 -/* - * Size of the session key (crypto key encrypted with the password - */ -#define SMB2_NTLMV2_SESSKEY_SIZE 16 -#define SMB2_SIGNATURE_SIZE 16 -#define SMB2_HMACSHA256_SIZE 32 -#define SMB2_CMACAES_SIZE 16 -#define SMB3_GCM128_CRYPTKEY_SIZE 16 -#define SMB3_GCM256_CRYPTKEY_SIZE 32 - -/* - * Size of the smb3 encryption/decryption keys - */ -#define SMB3_ENC_DEC_KEY_SIZE 32 - -/* - * Size of the smb3 signing key - */ -#define SMB3_SIGN_KEY_SIZE 16 - -#define CIFS_CLIENT_CHALLENGE_SIZE 8 -#define SMB_SERVER_CHALLENGE_SIZE 8 - /* SMB2 Max Credits */ #define SMB2_MAX_CREDITS 8192 -/* Maximum buffer size value we can send with 1 credit */ -#define SMB2_MAX_BUFFER_SIZE 65536 - -#define NUMBER_OF_SMB2_COMMANDS 0x0013 - /* BB FIXME - analyze following length BB */ #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ #define SMB21_DEFAULT_IOSIZE (1024 * 1024) -#define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024) #define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) #define SMB3_MIN_IOSIZE (64 * 1024) #define SMB3_MAX_IOSIZE (8 * 1024 * 1024) @@ -65,18 +36,6 @@ * */ -#define SMB2_ERROR_STRUCTURE_SIZE2 9 -#define SMB2_ERROR_STRUCTURE_SIZE2_LE cpu_to_le16(SMB2_ERROR_STRUCTURE_SIZE2) - -struct smb2_err_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; - __u8 ErrorContextCount; - __u8 Reserved; - __le32 ByteCount; /* even if zero, at least one byte follows */ - __u8 ErrorData[1]; /* variable length */ -} __packed; - struct preauth_integrity_info { /* PreAuth integrity Hash ID */ __le16 Preauth_HashId; @@ -116,8 +75,8 @@ struct create_durable_reconn_req { union { __u8 Reserved[16]; struct { - __le64 PersistentFileId; - __le64 VolatileFileId; + __u64 PersistentFileId; + __u64 VolatileFileId; } Fid; } Data; } __packed; @@ -126,8 +85,8 @@ struct create_durable_reconn_v2_req { struct create_context ccontext; __u8 Name[8]; struct { - __le64 PersistentFileId; - __le64 VolatileFileId; + __u64 PersistentFileId; + __u64 VolatileFileId; } Fid; __u8 CreateGuid[16]; __le32 Flags; @@ -161,13 +120,6 @@ struct create_alloc_size_req { __le64 AllocationSize; } __packed; -struct create_posix { - struct create_context ccontext; - __u8 Name[16]; - __le32 Mode; - __u32 Reserved; -} __packed; - struct create_durable_rsp { struct create_context ccontext; __u8 Name[8]; @@ -209,45 +161,6 @@ struct create_posix_rsp { u8 SidBuffer[40]; } __packed; -#define SMB2_LEASE_NONE_LE cpu_to_le32(0x00) -#define SMB2_LEASE_READ_CACHING_LE cpu_to_le32(0x01) -#define SMB2_LEASE_HANDLE_CACHING_LE cpu_to_le32(0x02) -#define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04) - -#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) - -#define SMB2_LEASE_KEY_SIZE 16 - -struct lease_context { - __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; - __le32 LeaseState; - __le32 LeaseFlags; - __le64 LeaseDuration; -} __packed; - -struct lease_context_v2 { - __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; - __le32 LeaseState; - __le32 LeaseFlags; - __le64 LeaseDuration; - __u8 ParentLeaseKey[SMB2_LEASE_KEY_SIZE]; - __le16 Epoch; - __le16 Reserved; -} __packed; - -struct create_lease { - struct create_context ccontext; - __u8 Name[8]; - struct lease_context lcontext; -} __packed; - -struct create_lease_v2 { - struct create_context ccontext; - __u8 Name[8]; - struct lease_context_v2 lcontext; - __u8 Pad[4]; -} __packed; - struct smb2_buffer_desc_v1 { __le64 offset; __le32 token; @@ -256,63 +169,6 @@ struct smb2_buffer_desc_v1 { #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 -struct duplicate_extents_to_file { - __u64 PersistentFileHandle; /* source file handle, opaque endianness */ - __u64 VolatileFileHandle; - __le64 SourceFileOffset; - __le64 TargetFileOffset; - __le64 ByteCount; /* Bytes to be copied */ -} __packed; - -struct smb2_ioctl_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 57 */ - __le16 Reserved; /* offset from start of SMB2 header to write data */ - __le32 CntCode; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 InputOffset; /* Reserved MBZ */ - __le32 InputCount; - __le32 MaxInputResponse; - __le32 OutputOffset; - __le32 OutputCount; - __le32 MaxOutputResponse; - __le32 Flags; - __le32 Reserved2; - __u8 Buffer[1]; -} __packed; - -struct smb2_ioctl_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 49 */ - __le16 Reserved; /* offset from start of SMB2 header to write data */ - __le32 CntCode; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 InputOffset; /* Reserved MBZ */ - __le32 InputCount; - __le32 OutputOffset; - __le32 OutputCount; - __le32 Flags; - __le32 Reserved2; - __u8 Buffer[1]; -} __packed; - -struct validate_negotiate_info_req { - __le32 Capabilities; - __u8 Guid[SMB2_CLIENT_GUID_SIZE]; - __le16 SecurityMode; - __le16 DialectCount; - __le16 Dialects[1]; /* dialect (someday maybe list) client asked for */ -} __packed; - -struct validate_negotiate_info_rsp { - __le32 Capabilities; - __u8 Guid[SMB2_CLIENT_GUID_SIZE]; - __le16 SecurityMode; - __le16 Dialect; /* Dialect in use for the connection */ -} __packed; - struct smb_sockaddr_in { __be16 Port; __be32 IPv4address; @@ -357,7 +213,7 @@ struct file_object_buf_type1_ioctl_rsp { } __packed; struct resume_key_ioctl_rsp { - __le64 ResumeKey[3]; + __u64 ResumeKey[3]; __le32 ContextLength; __u8 Context[4]; /* ignored, Windows sets to 4 bytes of zero */ } __packed; @@ -386,167 +242,6 @@ struct file_sparse { __u8 SetSparse; } __packed; -struct file_zero_data_information { - __le64 FileOffset; - __le64 BeyondFinalZero; -} __packed; - -struct file_allocated_range_buffer { - __le64 file_offset; - __le64 length; -} __packed; - -struct reparse_data_buffer { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __u8 DataBuffer[]; /* Variable Length */ -} __packed; - -/* SMB2 Notify Action Flags */ -#define FILE_ACTION_ADDED 0x00000001 -#define FILE_ACTION_REMOVED 0x00000002 -#define FILE_ACTION_MODIFIED 0x00000003 -#define FILE_ACTION_RENAMED_OLD_NAME 0x00000004 -#define FILE_ACTION_RENAMED_NEW_NAME 0x00000005 -#define FILE_ACTION_ADDED_STREAM 0x00000006 -#define FILE_ACTION_REMOVED_STREAM 0x00000007 -#define FILE_ACTION_MODIFIED_STREAM 0x00000008 -#define FILE_ACTION_REMOVED_BY_DELETE 0x00000009 - -#define SMB2_LOCKFLAG_SHARED 0x0001 -#define SMB2_LOCKFLAG_EXCLUSIVE 0x0002 -#define SMB2_LOCKFLAG_UNLOCK 0x0004 -#define SMB2_LOCKFLAG_FAIL_IMMEDIATELY 0x0010 -#define SMB2_LOCKFLAG_MASK 0x0007 - -struct smb2_lock_element { - __le64 Offset; - __le64 Length; - __le32 Flags; - __le32 Reserved; -} __packed; - -struct smb2_lock_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 48 */ - __le16 LockCount; - __le32 Reserved; - __le64 PersistentFileId; - __le64 VolatileFileId; - /* Followed by at least one */ - struct smb2_lock_element locks[1]; -} __packed; - -struct smb2_lock_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_echo_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __u16 Reserved; -} __packed; - -struct smb2_echo_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __u16 Reserved; -} __packed; - -/* search (query_directory) Flags field */ -#define SMB2_RESTART_SCANS 0x01 -#define SMB2_RETURN_SINGLE_ENTRY 0x02 -#define SMB2_INDEX_SPECIFIED 0x04 -#define SMB2_REOPEN 0x10 - -struct smb2_query_directory_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 33 */ - __u8 FileInformationClass; - __u8 Flags; - __le32 FileIndex; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le16 FileNameOffset; - __le16 FileNameLength; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - -struct smb2_query_directory_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 OutputBufferOffset; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - -/* Possible InfoType values */ -#define SMB2_O_INFO_FILE 0x01 -#define SMB2_O_INFO_FILESYSTEM 0x02 -#define SMB2_O_INFO_SECURITY 0x03 -#define SMB2_O_INFO_QUOTA 0x04 - -/* Security info type additionalinfo flags. See MS-SMB2 (2.2.37) or MS-DTYP */ -#define OWNER_SECINFO 0x00000001 -#define GROUP_SECINFO 0x00000002 -#define DACL_SECINFO 0x00000004 -#define SACL_SECINFO 0x00000008 -#define LABEL_SECINFO 0x00000010 -#define ATTRIBUTE_SECINFO 0x00000020 -#define SCOPE_SECINFO 0x00000040 -#define BACKUP_SECINFO 0x00010000 -#define UNPROTECTED_SACL_SECINFO 0x10000000 -#define UNPROTECTED_DACL_SECINFO 0x20000000 -#define PROTECTED_SACL_SECINFO 0x40000000 -#define PROTECTED_DACL_SECINFO 0x80000000 - -struct smb2_query_info_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 41 */ - __u8 InfoType; - __u8 FileInfoClass; - __le32 OutputBufferLength; - __le16 InputBufferOffset; - __u16 Reserved; - __le32 InputBufferLength; - __le32 AdditionalInformation; - __le32 Flags; - __le64 PersistentFileId; - __le64 VolatileFileId; - __u8 Buffer[1]; -} __packed; - -struct smb2_query_info_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 OutputBufferOffset; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - -struct smb2_set_info_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 33 */ - __u8 InfoType; - __u8 FileInfoClass; - __le32 BufferLength; - __le16 BufferOffset; - __u16 Reserved; - __le32 AdditionalInformation; - __le64 PersistentFileId; - __le64 VolatileFileId; - __u8 Buffer[1]; -} __packed; - -struct smb2_set_info_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 2 */ -} __packed; - /* FILE Info response size */ #define FILE_DIRECTORY_INFORMATION_SIZE 1 #define FILE_FULL_DIRECTORY_INFORMATION_SIZE 2 @@ -602,145 +297,11 @@ struct fs_type_info { long magic_number; } __packed; -struct smb2_oplock_break { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 24 */ - __u8 OplockLevel; - __u8 Reserved; - __le32 Reserved2; - __le64 PersistentFid; - __le64 VolatileFid; -} __packed; - -#define SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED cpu_to_le32(0x01) - -struct smb2_lease_break { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 44 */ - __le16 Epoch; - __le32 Flags; - __u8 LeaseKey[16]; - __le32 CurrentLeaseState; - __le32 NewLeaseState; - __le32 BreakReason; - __le32 AccessMaskHint; - __le32 ShareMaskHint; -} __packed; - -struct smb2_lease_ack { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 36 */ - __le16 Reserved; - __le32 Flags; - __u8 LeaseKey[16]; - __le32 LeaseState; - __le64 LeaseDuration; -} __packed; - /* - * PDU infolevel structure definitions + * PDU query infolevel structure definitions * BB consider moving to a different header */ -/* File System Information Classes */ -#define FS_VOLUME_INFORMATION 1 /* Query */ -#define FS_LABEL_INFORMATION 2 /* Set */ -#define FS_SIZE_INFORMATION 3 /* Query */ -#define FS_DEVICE_INFORMATION 4 /* Query */ -#define FS_ATTRIBUTE_INFORMATION 5 /* Query */ -#define FS_CONTROL_INFORMATION 6 /* Query, Set */ -#define FS_FULL_SIZE_INFORMATION 7 /* Query */ -#define FS_OBJECT_ID_INFORMATION 8 /* Query, Set */ -#define FS_DRIVER_PATH_INFORMATION 9 /* Query */ -#define FS_SECTOR_SIZE_INFORMATION 11 /* SMB3 or later. Query */ -#define FS_POSIX_INFORMATION 100 /* SMB3.1.1 POSIX. Query */ - -struct smb2_fs_full_size_info { - __le64 TotalAllocationUnits; - __le64 CallerAvailableAllocationUnits; - __le64 ActualAvailableAllocationUnits; - __le32 SectorsPerAllocationUnit; - __le32 BytesPerSector; -} __packed; - -#define SSINFO_FLAGS_ALIGNED_DEVICE 0x00000001 -#define SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE 0x00000002 -#define SSINFO_FLAGS_NO_SEEK_PENALTY 0x00000004 -#define SSINFO_FLAGS_TRIM_ENABLED 0x00000008 - -/* sector size info struct */ -struct smb3_fs_ss_info { - __le32 LogicalBytesPerSector; - __le32 PhysicalBytesPerSectorForAtomicity; - __le32 PhysicalBytesPerSectorForPerf; - __le32 FSEffPhysicalBytesPerSectorForAtomicity; - __le32 Flags; - __le32 ByteOffsetForSectorAlignment; - __le32 ByteOffsetForPartitionAlignment; -} __packed; - -/* File System Control Information */ -struct smb2_fs_control_info { - __le64 FreeSpaceStartFiltering; - __le64 FreeSpaceThreshold; - __le64 FreeSpaceStopFiltering; - __le64 DefaultQuotaThreshold; - __le64 DefaultQuotaLimit; - __le32 FileSystemControlFlags; - __le32 Padding; -} __packed; - -/* partial list of QUERY INFO levels */ -#define FILE_DIRECTORY_INFORMATION 1 -#define FILE_FULL_DIRECTORY_INFORMATION 2 -#define FILE_BOTH_DIRECTORY_INFORMATION 3 -#define FILE_BASIC_INFORMATION 4 -#define FILE_STANDARD_INFORMATION 5 -#define FILE_INTERNAL_INFORMATION 6 -#define FILE_EA_INFORMATION 7 -#define FILE_ACCESS_INFORMATION 8 -#define FILE_NAME_INFORMATION 9 -#define FILE_RENAME_INFORMATION 10 -#define FILE_LINK_INFORMATION 11 -#define FILE_NAMES_INFORMATION 12 -#define FILE_DISPOSITION_INFORMATION 13 -#define FILE_POSITION_INFORMATION 14 -#define FILE_FULL_EA_INFORMATION 15 -#define FILE_MODE_INFORMATION 16 -#define FILE_ALIGNMENT_INFORMATION 17 -#define FILE_ALL_INFORMATION 18 -#define FILE_ALLOCATION_INFORMATION 19 -#define FILE_END_OF_FILE_INFORMATION 20 -#define FILE_ALTERNATE_NAME_INFORMATION 21 -#define FILE_STREAM_INFORMATION 22 -#define FILE_PIPE_INFORMATION 23 -#define FILE_PIPE_LOCAL_INFORMATION 24 -#define FILE_PIPE_REMOTE_INFORMATION 25 -#define FILE_MAILSLOT_QUERY_INFORMATION 26 -#define FILE_MAILSLOT_SET_INFORMATION 27 -#define FILE_COMPRESSION_INFORMATION 28 -#define FILE_OBJECT_ID_INFORMATION 29 -/* Number 30 not defined in documents */ -#define FILE_MOVE_CLUSTER_INFORMATION 31 -#define FILE_QUOTA_INFORMATION 32 -#define FILE_REPARSE_POINT_INFORMATION 33 -#define FILE_NETWORK_OPEN_INFORMATION 34 -#define FILE_ATTRIBUTE_TAG_INFORMATION 35 -#define FILE_TRACKING_INFORMATION 36 -#define FILEID_BOTH_DIRECTORY_INFORMATION 37 -#define FILEID_FULL_DIRECTORY_INFORMATION 38 -#define FILE_VALID_DATA_LENGTH_INFORMATION 39 -#define FILE_SHORT_NAME_INFORMATION 40 -#define FILE_SFIO_RESERVE_INFORMATION 44 -#define FILE_SFIO_VOLUME_INFORMATION 45 -#define FILE_HARD_LINK_INFORMATION 46 -#define FILE_NORMALIZED_NAME_INFORMATION 48 -#define FILEID_GLOBAL_TX_DIRECTORY_INFORMATION 50 -#define FILE_STANDARD_LINK_INFORMATION 54 - -#define OP_BREAK_STRUCT_SIZE_20 24 -#define OP_BREAK_STRUCT_SIZE_21 36 - struct smb2_file_access_info { __le32 AccessFlags; } __packed; @@ -749,56 +310,6 @@ struct smb2_file_alignment_info { __le32 AlignmentRequirement; } __packed; -struct smb2_file_internal_info { - __le64 IndexNumber; -} __packed; /* level 6 Query */ - -struct smb2_file_rename_info { /* encoding of request for level 10 */ - __u8 ReplaceIfExists; /* 1 = replace existing target with new */ - /* 0 = fail if target already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; - char FileName[]; /* New name to be assigned */ -} __packed; /* level 10 Set */ - -struct smb2_file_link_info { /* encoding of request for level 11 */ - __u8 ReplaceIfExists; /* 1 = replace existing link with new */ - /* 0 = fail if link already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; - char FileName[]; /* Name to be assigned to new link */ -} __packed; /* level 11 Set */ - -/* - * This level 18, although with struct with same name is different from cifs - * level 0x107. Level 0x107 has an extra u64 between AccessFlags and - * CurrentByteOffset. - */ -struct smb2_file_all_info { /* data block encoding of response to level 18 */ - __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le32 Attributes; - __u32 Pad1; /* End of FILE_BASIC_INFO_INFO equivalent */ - __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */ - __le64 EndOfFile; /* size ie offset to first free byte in file */ - __le32 NumberOfLinks; /* hard links */ - __u8 DeletePending; - __u8 Directory; - __u16 Pad2; /* End of FILE_STANDARD_INFO equivalent */ - __le64 IndexNumber; - __le32 EASize; - __le32 AccessFlags; - __le64 CurrentByteOffset; - __le32 Mode; - __le32 AlignmentRequirement; - __le32 FileNameLength; - char FileName[1]; -} __packed; /* level 18 Query */ - struct smb2_file_basic_info { /* data block encoding of response to level 18 */ __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ __le64 LastAccessTime; @@ -821,10 +332,6 @@ struct smb2_file_stream_info { char StreamName[]; } __packed; -struct smb2_file_eof_info { /* encoding of request for level 10 */ - __le64 EndOfFile; /* new end of file value */ -} __packed; /* level 20 Set */ - struct smb2_file_ntwrk_info { __le64 CreationTime; __le64 LastAccessTime; @@ -915,34 +422,6 @@ struct create_sd_buf_req { struct smb_ntsd ntsd; } __packed; -/* Find File infolevels */ -#define SMB_FIND_FILE_POSIX_INFO 0x064 - -/* Level 100 query info */ -struct smb311_posix_qinfo { - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 EndOfFile; - __le64 AllocationSize; - __le32 DosAttributes; - __le64 Inode; - __le32 DeviceId; - __le32 Zero; - /* beginning of POSIX Create Context Response */ - __le32 HardLinks; - __le32 ReparseTag; - __le32 Mode; - u8 Sids[]; - /* - * var sized owner SID - * var sized group SID - * le32 filenamelength - * u8 filename[] - */ -} __packed; - struct smb2_posix_info { __le32 NextEntryOffset; __u32 Ignored; diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index 82a1429bbe12..8fef9de787d3 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -476,7 +476,7 @@ static int ksmbd_netdev_event(struct notifier_block *nb, unsigned long event, switch (event) { case NETDEV_UP: - if (netdev->priv_flags & IFF_BRIDGE_PORT) + if (netif_is_bridge_port(netdev)) return NOTIFY_OK; list_for_each_entry(iface, &iface_list, entry) { @@ -585,7 +585,7 @@ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz) rtnl_lock(); for_each_netdev(&init_net, netdev) { - if (netdev->priv_flags & IFF_BRIDGE_PORT) + if (netif_is_bridge_port(netdev)) continue; if (!alloc_iface(kstrdup(netdev->name, GFP_KERNEL))) return -ENOMEM; diff --git a/fs/namei.c b/fs/namei.c index 3f1829b3ab5b..509657fdf4f5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3673,18 +3673,14 @@ static struct dentry *filename_create(int dfd, struct filename *name, { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; + bool want_dir = lookup_flags & LOOKUP_DIRECTORY; + unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; + unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; - bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); - /* - * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any - * other flags passed in are ignored! - */ - lookup_flags &= LOOKUP_REVAL; - - error = filename_parentat(dfd, name, lookup_flags, path, &last, &type); + error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); @@ -3698,11 +3694,13 @@ static struct dentry *filename_create(int dfd, struct filename *name, /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* - * Do the final lookup. + * Do the final lookup. Suppress 'create' if there is a trailing + * '/', and a directory wasn't requested. */ - lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; + if (last.name[last.len] && !want_dir) + create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, lookup_flags); + dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -3716,7 +3714,7 @@ static struct dentry *filename_create(int dfd, struct filename *name, * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ - if (unlikely(!is_dir && last.name[last.len])) { + if (unlikely(!create_flags)) { error = -ENOENT; goto fail; } diff --git a/fs/namespace.c b/fs/namespace.c index 6e9844b8c6fb..a0a36bfa3aa0 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2112,22 +2112,23 @@ static int invent_group_ids(struct mount *mnt, bool recurse) int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); - unsigned int mounts = 0, old, pending, sum; + unsigned int mounts = 0; struct mount *p; + if (ns->mounts >= max) + return -ENOSPC; + max -= ns->mounts; + if (ns->pending_mounts >= max) + return -ENOSPC; + max -= ns->pending_mounts; + for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; - old = ns->mounts; - pending = ns->pending_mounts; - sum = old + pending; - if ((old > sum) || - (pending > sum) || - (max < sum) || - (mounts > (max - sum))) + if (mounts > max) return -ENOSPC; - ns->pending_mounts = pending + mounts; + ns->pending_mounts += mounts; return 0; } @@ -2921,7 +2922,7 @@ static int do_move_mount_old(struct path *path, const char *old_name) * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, - struct path *path, int mnt_flags) + const struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); @@ -3044,7 +3045,7 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, return err; } -int finish_automount(struct vfsmount *m, struct path *path) +int finish_automount(struct vfsmount *m, const struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile index c15bfc966d96..f684c0cd1ec5 100644 --- a/fs/netfs/Makefile +++ b/fs/netfs/Makefile @@ -1,5 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -netfs-y := read_helper.o stats.o +netfs-y := \ + buffered_read.o \ + io.o \ + main.o \ + objects.o + +netfs-$(CONFIG_NETFS_STATS) += stats.o obj-$(CONFIG_NETFS_SUPPORT) := netfs.o diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c new file mode 100644 index 000000000000..281a88a5b8dc --- /dev/null +++ b/fs/netfs/buffered_read.c @@ -0,0 +1,428 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level buffered read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/export.h> +#include <linux/task_io_accounting_ops.h> +#include "internal.h" + +/* + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. + */ +void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + unsigned int iopos, account = 0; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { + __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + } + } + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + iopos = 0; + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); + bool pg_failed = false; + + for (;;) { + if (!subreq) { + pg_failed = true; + break; + } + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + folio_start_fscache(folio); + pg_failed |= subreq_failed; + if (pgend < iopos + subreq->len) + break; + + account += subreq->transferred; + iopos += subreq->len; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + if (pgend == iopos) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); + + task_io_account_read(account); + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, + loff_t *_start, size_t *_len, loff_t i_size) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops && cres->ops->expand_readahead) + cres->ops->expand_readahead(cres, _start, _len, i_size); +} + +static void netfs_rreq_expand(struct netfs_io_request *rreq, + struct readahead_control *ractl) +{ + /* Give the cache a chance to change the request parameters. The + * resultant request must contain the original region. + */ + netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); + + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); + + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); + + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_expanded); + } +} + +/** + * netfs_readahead - Helper to manage a read request + * @ractl: The description of the readahead request + * + * Fulfil a readahead request by drawing data from the cache if possible, or + * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O + * requests from different sources will get munged together. If necessary, the + * readahead window can be expanded in either direction to a more convenient + * alighment for RPC efficiency or to make storage in the cache feasible. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +void netfs_readahead(struct readahead_control *ractl) +{ + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(ractl->mapping->host); + int ret; + + _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); + + if (readahead_count(ractl) == 0) + return; + + rreq = netfs_alloc_request(ractl->mapping, ractl->file, + readahead_pos(ractl), + readahead_length(ractl), + NETFS_READAHEAD); + if (IS_ERR(rreq)) + return; + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; + } + + netfs_stat(&netfs_n_rh_readahead); + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_readahead); + + netfs_rreq_expand(rreq, ractl); + + /* Drop the refs on the folios here rather than in the cache or + * filesystem. The locks will be dropped in netfs_rreq_unlock(). + */ + while (readahead_folio(ractl)) + ; + + netfs_begin_read(rreq, false); + return; + +cleanup_free: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); + return; +} +EXPORT_SYMBOL(netfs_readahead); + +/** + * netfs_readpage - Helper to manage a readpage request + * @file: The file to read from + * @subpage: A subpage of the folio to read + * + * Fulfil a readpage request by drawing data from the cache if possible, or the + * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests + * from different sources will get munged together. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_readpage(struct file *file, struct page *subpage) +{ + struct folio *folio = page_folio(subpage); + struct address_space *mapping = folio_file_mapping(folio); + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(mapping->host); + int ret; + + _enter("%lx", folio_index(folio)); + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READPAGE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto alloc_error; + } + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; + } + + netfs_stat(&netfs_n_rh_readpage); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); + return netfs_begin_read(rreq, true); + +discard: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +alloc_error: + folio_unlock(folio); + return ret; +} +EXPORT_SYMBOL(netfs_readpage); + +/* + * Prepare a folio for writing without reading first + * @folio: The folio being prepared + * @pos: starting position for the write + * @len: length of write + * @always_fill: T if the folio should always be completely filled/cleared + * + * In some cases, write_begin doesn't need to read at all: + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it + * + * If any of these criteria are met, then zero out the unwritten parts + * of the folio and return true. Otherwise, return false. + */ +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len, + bool always_fill) +{ + struct inode *inode = folio_inode(folio); + loff_t i_size = i_size_read(inode); + size_t offset = offset_in_folio(folio, pos); + size_t plen = folio_size(folio); + + if (unlikely(always_fill)) { + if (pos - offset + len <= i_size) + return false; /* Page entirely before EOF */ + zero_user_segment(&folio->page, 0, plen); + folio_mark_uptodate(folio); + return true; + } + + /* Full folio write */ + if (offset == 0 && len >= plen) + return true; + + /* Page entirely beyond the end of the file */ + if (pos - offset >= i_size) + goto zero_out; + + /* Write that covers from the start of the folio to EOF or beyond */ + if (offset == 0 && (pos + len) >= i_size) + goto zero_out; + + return false; +zero_out: + zero_user_segments(&folio->page, 0, offset, offset + len, plen); + return true; +} + +/** + * netfs_write_begin - Helper to prepare for writing + * @file: The file to read from + * @mapping: The mapping to read from + * @pos: File position at which the write will begin + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @aop_flags: AOP_* flags + * @_folio: Where to put the resultant folio + * @_fsdata: Place for the netfs to store a cookie + * + * Pre-read data for a write-begin request by drawing data from the cache if + * possible, or the netfs if not. Space beyond the EOF is zero-filled. + * Multiple I/O requests from different sources will get munged together. If + * necessary, the readahead window can be expanded in either direction to a + * more convenient alighment for RPC efficiency or to make storage in the cache + * feasible. + * + * The calling netfs must provide a table of operations, only one of which, + * issue_op, is mandatory. + * + * The check_write_begin() operation can be provided to check for and flush + * conflicting writes once the folio is grabbed and locked. It is passed a + * pointer to the fsdata cookie that gets returned to the VM to be passed to + * write_end. It is permitted to sleep. It should return 0 if the request + * should go ahead; unlock the folio and return -EAGAIN to cause the folio to + * be regot; or return an error. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int aop_flags, + struct folio **_folio, void **_fsdata) +{ + struct netfs_io_request *rreq; + struct netfs_i_context *ctx = netfs_i_context(file_inode(file )); + struct folio *folio; + unsigned int fgp_flags; + pgoff_t index = pos >> PAGE_SHIFT; + int ret; + + DEFINE_READAHEAD(ractl, file, NULL, mapping, index); + +retry: + fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) + return -ENOMEM; + + if (ctx->ops->check_write_begin) { + /* Allow the netfs (eg. ceph) to flush conflicts. */ + ret = ctx->ops->check_write_begin(file, pos, len, folio, _fsdata); + if (ret < 0) { + trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); + if (ret == -EAGAIN) + goto retry; + goto error; + } + } + + if (folio_test_uptodate(folio)) + goto have_folio; + + /* If the page is beyond the EOF, we want to clear it - unless it's + * within the cache granule containing the EOF, in which case we need + * to preload the granule. + */ + if (!netfs_is_cache_enabled(ctx) && + netfs_skip_folio_read(folio, pos, len, false)) { + netfs_stat(&netfs_n_rh_write_zskip); + goto have_folio_no_wait; + } + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READ_FOR_WRITE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto error; + } + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto error_put; + } + + netfs_stat(&netfs_n_rh_write_begin); + trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); + + /* Expand the request to meet caching requirements and download + * preferences. + */ + ractl._nr_pages = folio_nr_pages(folio); + netfs_rreq_expand(rreq, &ractl); + + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; + + ret = netfs_begin_read(rreq, true); + if (ret < 0) + goto error; + +have_folio: + ret = folio_wait_fscache_killable(folio); + if (ret < 0) + goto error; +have_folio_no_wait: + *_folio = folio; + _leave(" = 0"); + return 0; + +error_put: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); +error: + folio_unlock(folio); + folio_put(folio); + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_write_begin); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index b7f2c4459f33..b7b0e3d18d9e 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -5,6 +5,10 @@ * Written by David Howells (dhowells@redhat.com) */ +#include <linux/netfs.h> +#include <linux/fscache.h> +#include <trace/events/netfs.h> + #ifdef pr_fmt #undef pr_fmt #endif @@ -12,11 +16,40 @@ #define pr_fmt(fmt) "netfs: " fmt /* - * read_helper.c + * buffered_read.c + */ +void netfs_rreq_unlock_folios(struct netfs_io_request *rreq); + +/* + * io.c + */ +int netfs_begin_read(struct netfs_io_request *rreq, bool sync); + +/* + * main.c */ extern unsigned int netfs_debug; /* + * objects.c + */ +struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, + struct file *file, + loff_t start, size_t len, + enum netfs_io_origin origin); +void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what); +void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async); +void netfs_put_request(struct netfs_io_request *rreq, bool was_async, + enum netfs_rreq_ref_trace what); +struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq); + +static inline void netfs_see_request(struct netfs_io_request *rreq, + enum netfs_rreq_ref_trace what) +{ + trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what); +} + +/* * stats.c */ #ifdef CONFIG_NETFS_STATS @@ -55,6 +88,21 @@ static inline void netfs_stat_d(atomic_t *stat) #define netfs_stat_d(x) do {} while(0) #endif +/* + * Miscellaneous functions. + */ +static inline bool netfs_is_cache_enabled(struct netfs_i_context *ctx) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cookie = ctx->cache; + + return fscache_cookie_valid(cookie) && cookie->cache_priv && + fscache_cookie_enabled(cookie); +#else + return false; +#endif +} + /*****************************************************************************/ /* * debug tracing diff --git a/fs/netfs/io.c b/fs/netfs/io.c new file mode 100644 index 000000000000..428925899282 --- /dev/null +++ b/fs/netfs/io.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/module.h> +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/uio.h> +#include <linux/sched/mm.h> +#include <linux/task_io_accounting_ops.h> +#include "internal.h" + +/* + * Clear the unread part of an I/O request. + */ +static void netfs_clear_unread(struct netfs_io_subrequest *subreq) +{ + struct iov_iter iter; + + iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + iov_iter_zero(iov_iter_count(&iter), &iter); +} + +static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + + netfs_subreq_terminated(subreq, transferred_or_error, was_async); +} + +/* + * Issue a read against the cache. + * - Eats the caller's ref on subreq. + */ +static void netfs_read_from_cache(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + enum netfs_read_from_hole read_hole) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct iov_iter iter; + + netfs_stat(&netfs_n_rh_read); + iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + + cres->ops->read(cres, subreq->start, &iter, read_hole, + netfs_cache_read_terminated, subreq); +} + +/* + * Fill a subrequest region with zeroes. + */ +static void netfs_fill_with_zeroes(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + netfs_stat(&netfs_n_rh_zero); + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + netfs_subreq_terminated(subreq, 0, false); +} + +/* + * Ask the netfs to issue a read request to the server for us. + * + * The netfs is expected to read from subreq->pos + subreq->transferred to + * subreq->pos + subreq->len - 1. It may not backtrack and write data into the + * buffer prior to the transferred point as it might clobber dirty data + * obtained from the cache. + * + * Alternatively, the netfs is allowed to indicate one of two things: + * + * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and + * make progress. + * + * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be + * cleared. + */ +static void netfs_read_from_server(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + netfs_stat(&netfs_n_rh_download); + rreq->netfs_ops->issue_read(subreq); +} + +/* + * Release those waiting. + */ +static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_done); + netfs_clear_subrequests(rreq, was_async); + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); +} + +/* + * Deal with the completion of writing the data to the cache. We have to clear + * the PG_fscache bits on the folios involved and release the caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio_index(folio) <= unlocked) + continue; + unlocked = folio_index(folio); + folio_end_fscache(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * Perform any outstanding writes to the cache. We inherit a ref from the + * caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + +/* + * Handle a short read. + */ +static void netfs_rreq_short_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + __clear_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); + + netfs_stat(&netfs_n_rh_short_read); + trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_short_read); + atomic_inc(&rreq->nr_outstanding); + if (subreq->source == NETFS_READ_FROM_CACHE) + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); + else + netfs_read_from_server(rreq, subreq); +} + +/* + * Resubmit any short or failed operations. Returns true if we got the rreq + * ref back. + */ +static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + WARN_ON(in_interrupt()); + + trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); + + /* We don't want terminating submissions trying to wake us up whilst + * we're still going through the list. + */ + atomic_inc(&rreq->nr_outstanding); + + __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->error) { + if (subreq->source != NETFS_READ_FROM_CACHE) + break; + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->error = 0; + netfs_stat(&netfs_n_rh_download_instead); + trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + atomic_inc(&rreq->nr_outstanding); + netfs_read_from_server(rreq, subreq); + } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) { + netfs_rreq_short_read(rreq, subreq); + } + } + + /* If we decrement nr_outstanding to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_outstanding)) + return true; + + wake_up_var(&rreq->nr_outstanding); + return false; +} + +/* + * Check to see if the data read is still valid. + */ +static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + if (!rreq->netfs_ops->is_still_valid || + rreq->netfs_ops->is_still_valid(rreq)) + return; + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->source == NETFS_READ_FROM_CACHE) { + subreq->error = -ESTALE; + __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } + } +} + +/* + * Assess the state of a read request and decide what to do next. + * + * Note that we could be in an ordinary kernel thread, on a workqueue or in + * softirq context at this point. We inherit a ref from the caller. + */ +static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async) +{ + trace_netfs_rreq(rreq, netfs_rreq_trace_assess); + +again: + netfs_rreq_is_still_valid(rreq); + + if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && + test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { + if (netfs_rreq_perform_resubmissions(rreq)) + goto again; + return; + } + + netfs_rreq_unlock_folios(rreq); + + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_work(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + netfs_rreq_assess(rreq, false); +} + +/* + * Handle the completion of all outstanding I/O operations on a read request. + * We inherit a ref from the caller. + */ +static void netfs_rreq_terminated(struct netfs_io_request *rreq, + bool was_async) +{ + if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && + was_async) { + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_rreq_assess(rreq, was_async); + } +} + +/** + * netfs_subreq_terminated - Note the termination of an I/O operation. + * @subreq: The I/O request that has terminated. + * @transferred_or_error: The amount of data transferred or an error code. + * @was_async: The termination was asynchronous + * + * This tells the read helper that a contributory I/O operation has terminated, + * one way or another, and that it should integrate the results. + * + * The caller indicates in @transferred_or_error the outcome of the operation, + * supplying a positive value to indicate the number of bytes transferred, 0 to + * indicate a failure to transfer anything that should be retried or a negative + * error code. The helper will look after reissuing I/O operations as + * appropriate and writing downloaded data to the cache. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, + ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + int u; + + _enter("[%u]{%llx,%lx},%zd", + subreq->debug_index, subreq->start, subreq->flags, + transferred_or_error); + + switch (subreq->source) { + case NETFS_READ_FROM_CACHE: + netfs_stat(&netfs_n_rh_read_done); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_stat(&netfs_n_rh_download_done); + break; + default: + break; + } + + if (IS_ERR_VALUE(transferred_or_error)) { + subreq->error = transferred_or_error; + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_read); + goto failed; + } + + if (WARN(transferred_or_error > subreq->len - subreq->transferred, + "Subreq overread: R%x[%x] %zd > %zu - %zu", + rreq->debug_id, subreq->debug_index, + transferred_or_error, subreq->len, subreq->transferred)) + transferred_or_error = subreq->len - subreq->transferred; + + subreq->error = 0; + subreq->transferred += transferred_or_error; + if (subreq->transferred < subreq->len) + goto incomplete; + +complete: + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + set_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + +out: + trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); + + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + u = atomic_dec_return(&rreq->nr_outstanding); + if (u == 0) + netfs_rreq_terminated(rreq, was_async); + else if (u == 1) + wake_up_var(&rreq->nr_outstanding); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); + return; + +incomplete: + if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { + netfs_clear_unread(subreq); + subreq->transferred = subreq->len; + goto complete; + } + + if (transferred_or_error == 0) { + if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + subreq->error = -ENODATA; + goto failed; + } + } else { + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + + __set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + goto out; + +failed: + if (subreq->source == NETFS_READ_FROM_CACHE) { + netfs_stat(&netfs_n_rh_read_failed); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } else { + netfs_stat(&netfs_n_rh_download_failed); + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + rreq->error = subreq->error; + } + goto out; +} +EXPORT_SYMBOL(netfs_subreq_terminated); + +static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest *subreq, + loff_t i_size) +{ + struct netfs_io_request *rreq = subreq->rreq; + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops) + return cres->ops->prepare_read(subreq, i_size); + if (subreq->start >= rreq->i_size) + return NETFS_FILL_WITH_ZEROES; + return NETFS_DOWNLOAD_FROM_SERVER; +} + +/* + * Work out what sort of subrequest the next one will be. + */ +static enum netfs_io_source +netfs_rreq_prepare_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ + enum netfs_io_source source; + + _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); + + source = netfs_cache_prepare_read(subreq, rreq->i_size); + if (source == NETFS_INVALID_READ) + goto out; + + if (source == NETFS_DOWNLOAD_FROM_SERVER) { + /* Call out to the netfs to let it shrink the request to fit + * its own I/O sizes and boundaries. If it shinks it here, it + * will be called again to make simultaneous calls; if it wants + * to make serial calls, it can indicate a short read and then + * we will call it again. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; + + if (rreq->netfs_ops->clamp_length && + !rreq->netfs_ops->clamp_length(subreq)) { + source = NETFS_INVALID_READ; + goto out; + } + } + + if (WARN_ON(subreq->len == 0)) + source = NETFS_INVALID_READ; + +out: + subreq->source = source; + trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); + return source; +} + +/* + * Slice off a piece of a read request and submit an I/O request for it. + */ +static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq, + unsigned int *_debug_index) +{ + struct netfs_io_subrequest *subreq; + enum netfs_io_source source; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + return false; + + subreq->debug_index = (*_debug_index)++; + subreq->start = rreq->start + rreq->submitted; + subreq->len = rreq->len - rreq->submitted; + + _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + + /* Call out to the cache to find out what it can do with the remaining + * subset. It tells us in subreq->flags what it decided should be done + * and adjusts subreq->len down if the subset crosses a cache boundary. + * + * Then when we hand the subset, it can choose to take a subset of that + * (the starts must coincide), in which case, we go around the loop + * again and ask it to download the next piece. + */ + source = netfs_rreq_prepare_read(rreq, subreq); + if (source == NETFS_INVALID_READ) + goto subreq_failed; + + atomic_inc(&rreq->nr_outstanding); + + rreq->submitted += subreq->len; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + switch (source) { + case NETFS_FILL_WITH_ZEROES: + netfs_fill_with_zeroes(rreq, subreq); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_read_from_server(rreq, subreq); + break; + case NETFS_READ_FROM_CACHE: + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); + break; + default: + BUG(); + } + + return true; + +subreq_failed: + rreq->error = subreq->error; + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_failed); + return false; +} + +/* + * Begin the process of reading in a chunk of data, where that data may be + * stitched together from multiple sources, including multiple servers and the + * local cache. + */ +int netfs_begin_read(struct netfs_io_request *rreq, bool sync) +{ + unsigned int debug_index = 0; + int ret; + + _enter("R=%x %llx-%llx", + rreq->debug_id, rreq->start, rreq->start + rreq->len - 1); + + if (rreq->len == 0) { + pr_err("Zero-sized read [R=%x]\n", rreq->debug_id); + netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len); + return -EIO; + } + + INIT_WORK(&rreq->work, netfs_rreq_work); + + if (sync) + netfs_get_request(rreq, netfs_rreq_trace_get_hold); + + /* Chop the read into slices according to what the cache and the netfs + * want and submit each one. + */ + atomic_set(&rreq->nr_outstanding, 1); + do { + if (!netfs_rreq_submit_slice(rreq, &debug_index)) + break; + + } while (rreq->submitted < rreq->len); + + if (sync) { + /* Keep nr_outstanding incremented so that the ref always belongs to + * us, and the service code isn't punted off to a random thread pool to + * process. + */ + for (;;) { + wait_var_event(&rreq->nr_outstanding, + atomic_read(&rreq->nr_outstanding) == 1); + netfs_rreq_assess(rreq, false); + if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + break; + cond_resched(); + } + + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } + netfs_put_request(rreq, false, netfs_rreq_trace_put_hold); + } else { + /* If we decrement nr_outstanding to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_outstanding)) + netfs_rreq_assess(rreq, false); + ret = 0; + } + return ret; +} diff --git a/fs/netfs/main.c b/fs/netfs/main.c new file mode 100644 index 000000000000..068568702957 --- /dev/null +++ b/fs/netfs/main.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Miscellaneous bits for the netfs support library. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/module.h> +#include <linux/export.h> +#include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/netfs.h> + +MODULE_DESCRIPTION("Network fs support"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +unsigned netfs_debug; +module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c new file mode 100644 index 000000000000..e86107b30ba4 --- /dev/null +++ b/fs/netfs/objects.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Object lifetime handling and tracing. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/slab.h> +#include "internal.h" + +/* + * Allocate an I/O request and initialise it. + */ +struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, + struct file *file, + loff_t start, size_t len, + enum netfs_io_origin origin) +{ + static atomic_t debug_ids; + struct inode *inode = file ? file_inode(file) : mapping->host; + struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_io_request *rreq; + int ret; + + rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL); + if (!rreq) + return ERR_PTR(-ENOMEM); + + rreq->start = start; + rreq->len = len; + rreq->origin = origin; + rreq->netfs_ops = ctx->ops; + rreq->mapping = mapping; + rreq->inode = inode; + rreq->i_size = i_size_read(inode); + rreq->debug_id = atomic_inc_return(&debug_ids); + INIT_LIST_HEAD(&rreq->subrequests); + refcount_set(&rreq->ref, 1); + __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + if (rreq->netfs_ops->init_request) { + ret = rreq->netfs_ops->init_request(rreq, file); + if (ret < 0) { + kfree(rreq); + return ERR_PTR(ret); + } + } + + netfs_stat(&netfs_n_rh_rreq); + return rreq; +} + +void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what) +{ + int r; + + __refcount_inc(&rreq->ref, &r); + trace_netfs_rreq_ref(rreq->debug_id, r + 1, what); +} + +void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async) +{ + struct netfs_io_subrequest *subreq; + + while (!list_empty(&rreq->subrequests)) { + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, was_async, + netfs_sreq_trace_put_clear); + } +} + +static void netfs_free_request(struct work_struct *work) +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_clear_subrequests(rreq, false); + if (rreq->netfs_priv) + rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); + trace_netfs_rreq(rreq, netfs_rreq_trace_free); + if (rreq->cache_resources.ops) + rreq->cache_resources.ops->end_operation(&rreq->cache_resources); + kfree(rreq); + netfs_stat_d(&netfs_n_rh_rreq); +} + +void netfs_put_request(struct netfs_io_request *rreq, bool was_async, + enum netfs_rreq_ref_trace what) +{ + unsigned int debug_id = rreq->debug_id; + bool dead; + int r; + + dead = __refcount_dec_and_test(&rreq->ref, &r); + trace_netfs_rreq_ref(debug_id, r - 1, what); + if (dead) { + if (was_async) { + rreq->work.func = netfs_free_request; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_free_request(&rreq->work); + } + } +} + +/* + * Allocate and partially initialise an I/O request structure. + */ +struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + subreq = kzalloc(sizeof(struct netfs_io_subrequest), GFP_KERNEL); + if (subreq) { + INIT_LIST_HEAD(&subreq->rreq_link); + refcount_set(&subreq->ref, 2); + subreq->rreq = rreq; + netfs_get_request(rreq, netfs_rreq_trace_get_subreq); + netfs_stat(&netfs_n_rh_sreq); + } + + return subreq; +} + +void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what) +{ + int r; + + __refcount_inc(&subreq->ref, &r); + trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, r + 1, + what); +} + +static void netfs_free_subrequest(struct netfs_io_subrequest *subreq, + bool was_async) +{ + struct netfs_io_request *rreq = subreq->rreq; + + trace_netfs_sreq(subreq, netfs_sreq_trace_free); + kfree(subreq); + netfs_stat_d(&netfs_n_rh_sreq); + netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq); +} + +void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, + enum netfs_sreq_ref_trace what) +{ + unsigned int debug_index = subreq->debug_index; + unsigned int debug_id = subreq->rreq->debug_id; + bool dead; + int r; + + dead = __refcount_dec_and_test(&subreq->ref, &r); + trace_netfs_sreq_ref(debug_id, debug_index, r - 1, what); + if (dead) + netfs_free_subrequest(subreq, was_async); +} diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c deleted file mode 100644 index 501da990c259..000000000000 --- a/fs/netfs/read_helper.c +++ /dev/null @@ -1,1205 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Network filesystem high-level read support. - * - * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/module.h> -#include <linux/export.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/pagemap.h> -#include <linux/slab.h> -#include <linux/uio.h> -#include <linux/sched/mm.h> -#include <linux/task_io_accounting_ops.h> -#include <linux/netfs.h> -#include "internal.h" -#define CREATE_TRACE_POINTS -#include <trace/events/netfs.h> - -MODULE_DESCRIPTION("Network fs support"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - -unsigned netfs_debug; -module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); - -static void netfs_rreq_work(struct work_struct *); -static void __netfs_put_subrequest(struct netfs_read_subrequest *, bool); - -static void netfs_put_subrequest(struct netfs_read_subrequest *subreq, - bool was_async) -{ - if (refcount_dec_and_test(&subreq->usage)) - __netfs_put_subrequest(subreq, was_async); -} - -static struct netfs_read_request *netfs_alloc_read_request( - const struct netfs_read_request_ops *ops, void *netfs_priv, - struct file *file) -{ - static atomic_t debug_ids; - struct netfs_read_request *rreq; - - rreq = kzalloc(sizeof(struct netfs_read_request), GFP_KERNEL); - if (rreq) { - rreq->netfs_ops = ops; - rreq->netfs_priv = netfs_priv; - rreq->inode = file_inode(file); - rreq->i_size = i_size_read(rreq->inode); - rreq->debug_id = atomic_inc_return(&debug_ids); - INIT_LIST_HEAD(&rreq->subrequests); - INIT_WORK(&rreq->work, netfs_rreq_work); - refcount_set(&rreq->usage, 1); - __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (ops->init_rreq) - ops->init_rreq(rreq, file); - netfs_stat(&netfs_n_rh_rreq); - } - - return rreq; -} - -static void netfs_get_read_request(struct netfs_read_request *rreq) -{ - refcount_inc(&rreq->usage); -} - -static void netfs_rreq_clear_subreqs(struct netfs_read_request *rreq, - bool was_async) -{ - struct netfs_read_subrequest *subreq; - - while (!list_empty(&rreq->subrequests)) { - subreq = list_first_entry(&rreq->subrequests, - struct netfs_read_subrequest, rreq_link); - list_del(&subreq->rreq_link); - netfs_put_subrequest(subreq, was_async); - } -} - -static void netfs_free_read_request(struct work_struct *work) -{ - struct netfs_read_request *rreq = - container_of(work, struct netfs_read_request, work); - netfs_rreq_clear_subreqs(rreq, false); - if (rreq->netfs_priv) - rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); - trace_netfs_rreq(rreq, netfs_rreq_trace_free); - if (rreq->cache_resources.ops) - rreq->cache_resources.ops->end_operation(&rreq->cache_resources); - kfree(rreq); - netfs_stat_d(&netfs_n_rh_rreq); -} - -static void netfs_put_read_request(struct netfs_read_request *rreq, bool was_async) -{ - if (refcount_dec_and_test(&rreq->usage)) { - if (was_async) { - rreq->work.func = netfs_free_read_request; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_free_read_request(&rreq->work); - } - } -} - -/* - * Allocate and partially initialise an I/O request structure. - */ -static struct netfs_read_subrequest *netfs_alloc_subrequest( - struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - - subreq = kzalloc(sizeof(struct netfs_read_subrequest), GFP_KERNEL); - if (subreq) { - INIT_LIST_HEAD(&subreq->rreq_link); - refcount_set(&subreq->usage, 2); - subreq->rreq = rreq; - netfs_get_read_request(rreq); - netfs_stat(&netfs_n_rh_sreq); - } - - return subreq; -} - -static void netfs_get_read_subrequest(struct netfs_read_subrequest *subreq) -{ - refcount_inc(&subreq->usage); -} - -static void __netfs_put_subrequest(struct netfs_read_subrequest *subreq, - bool was_async) -{ - struct netfs_read_request *rreq = subreq->rreq; - - trace_netfs_sreq(subreq, netfs_sreq_trace_free); - kfree(subreq); - netfs_stat_d(&netfs_n_rh_sreq); - netfs_put_read_request(rreq, was_async); -} - -/* - * Clear the unread part of an I/O request. - */ -static void netfs_clear_unread(struct netfs_read_subrequest *subreq) -{ - struct iov_iter iter; - - iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - iov_iter_zero(iov_iter_count(&iter), &iter); -} - -static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_read_subrequest *subreq = priv; - - netfs_subreq_terminated(subreq, transferred_or_error, was_async); -} - -/* - * Issue a read against the cache. - * - Eats the caller's ref on subreq. - */ -static void netfs_read_from_cache(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq, - enum netfs_read_from_hole read_hole) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct iov_iter iter; - - netfs_stat(&netfs_n_rh_read); - iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, - subreq->start + subreq->transferred, - subreq->len - subreq->transferred); - - cres->ops->read(cres, subreq->start, &iter, read_hole, - netfs_cache_read_terminated, subreq); -} - -/* - * Fill a subrequest region with zeroes. - */ -static void netfs_fill_with_zeroes(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_zero); - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); - netfs_subreq_terminated(subreq, 0, false); -} - -/* - * Ask the netfs to issue a read request to the server for us. - * - * The netfs is expected to read from subreq->pos + subreq->transferred to - * subreq->pos + subreq->len - 1. It may not backtrack and write data into the - * buffer prior to the transferred point as it might clobber dirty data - * obtained from the cache. - * - * Alternatively, the netfs is allowed to indicate one of two things: - * - * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and - * make progress. - * - * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be - * cleared. - */ -static void netfs_read_from_server(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - netfs_stat(&netfs_n_rh_download); - rreq->netfs_ops->issue_op(subreq); -} - -/* - * Release those waiting. - */ -static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_done); - netfs_rreq_clear_subreqs(rreq, was_async); - netfs_put_read_request(rreq, was_async); -} - -/* - * Deal with the completion of writing the data to the cache. We have to clear - * the PG_fscache bits on the folios involved and release the caller's ref. - * - * May be called in softirq mode and we inherit a ref from the caller. - */ -static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, - bool was_async) -{ - struct netfs_read_subrequest *subreq; - struct folio *folio; - pgoff_t unlocked = 0; - bool have_unlocked = false; - - rcu_read_lock(); - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - - xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { - /* We might have multiple writes from the same huge - * folio, but we mustn't unlock a folio more than once. - */ - if (have_unlocked && folio_index(folio) <= unlocked) - continue; - unlocked = folio_index(folio); - folio_end_fscache(folio); - have_unlocked = true; - } - } - - rcu_read_unlock(); - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_read_subrequest *subreq = priv; - struct netfs_read_request *rreq = subreq->rreq; - - if (IS_ERR_VALUE(transferred_or_error)) { - netfs_stat(&netfs_n_rh_write_failed); - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_copy_to_cache); - } else { - netfs_stat(&netfs_n_rh_write_done); - } - - trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); - - /* If we decrement nr_wr_ops to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_wr_ops)) - netfs_rreq_unmark_after_write(rreq, was_async); - - netfs_put_subrequest(subreq, was_async); -} - -/* - * Perform any outstanding writes to the cache. We inherit a ref from the - * caller. - */ -static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - struct netfs_read_subrequest *subreq, *next, *p; - struct iov_iter iter; - int ret; - - trace_netfs_rreq(rreq, netfs_rreq_trace_write); - - /* We don't want terminating writes trying to wake us up whilst we're - * still going through the list. - */ - atomic_inc(&rreq->nr_wr_ops); - - list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { - if (!test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) { - list_del_init(&subreq->rreq_link); - netfs_put_subrequest(subreq, false); - } - } - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - /* Amalgamate adjacent writes */ - while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - next = list_next_entry(subreq, rreq_link); - if (next->start != subreq->start + subreq->len) - break; - subreq->len += next->len; - list_del_init(&next->rreq_link); - netfs_put_subrequest(next, false); - } - - ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size, true); - if (ret < 0) { - trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); - trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); - continue; - } - - iov_iter_xarray(&iter, WRITE, &rreq->mapping->i_pages, - subreq->start, subreq->len); - - atomic_inc(&rreq->nr_wr_ops); - netfs_stat(&netfs_n_rh_write); - netfs_get_read_subrequest(subreq); - trace_netfs_sreq(subreq, netfs_sreq_trace_write); - cres->ops->write(cres, subreq->start, &iter, - netfs_rreq_copy_terminated, subreq); - } - - /* If we decrement nr_wr_ops to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_wr_ops)) - netfs_rreq_unmark_after_write(rreq, false); -} - -static void netfs_rreq_write_to_cache_work(struct work_struct *work) -{ - struct netfs_read_request *rreq = - container_of(work, struct netfs_read_request, work); - - netfs_rreq_do_write_to_cache(rreq); -} - -static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq) -{ - rreq->work.func = netfs_rreq_write_to_cache_work; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); -} - -/* - * Unlock the folios in a read operation. We need to set PG_fscache on any - * folios we're going to write back before we unlock them. - */ -static void netfs_rreq_unlock(struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - struct folio *folio; - unsigned int iopos, account = 0; - pgoff_t start_page = rreq->start / PAGE_SIZE; - pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; - bool subreq_failed = false; - - XA_STATE(xas, &rreq->mapping->i_pages, start_page); - - if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { - __clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); - } - } - - /* Walk through the pagecache and the I/O request lists simultaneously. - * We may have a mixture of cached and uncached sections and we only - * really want to write out the uncached sections. This is slightly - * complicated by the possibility that we might have huge pages with a - * mixture inside. - */ - subreq = list_first_entry(&rreq->subrequests, - struct netfs_read_subrequest, rreq_link); - iopos = 0; - subreq_failed = (subreq->error < 0); - - trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); - - rcu_read_lock(); - xas_for_each(&xas, folio, last_page) { - unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; - unsigned int pgend = pgpos + folio_size(folio); - bool pg_failed = false; - - for (;;) { - if (!subreq) { - pg_failed = true; - break; - } - if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - folio_start_fscache(folio); - pg_failed |= subreq_failed; - if (pgend < iopos + subreq->len) - break; - - account += subreq->transferred; - iopos += subreq->len; - if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { - subreq = list_next_entry(subreq, rreq_link); - subreq_failed = (subreq->error < 0); - } else { - subreq = NULL; - subreq_failed = false; - } - if (pgend == iopos) - break; - } - - if (!pg_failed) { - flush_dcache_folio(folio); - folio_mark_uptodate(folio); - } - - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio_index(folio) == rreq->no_unlock_folio && - test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) - _debug("no unlock"); - else - folio_unlock(folio); - } - } - rcu_read_unlock(); - - task_io_account_read(account); - if (rreq->netfs_ops->done) - rreq->netfs_ops->done(rreq); -} - -/* - * Handle a short read. - */ -static void netfs_rreq_short_read(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - __clear_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); - __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); - - netfs_stat(&netfs_n_rh_short_read); - trace_netfs_sreq(subreq, netfs_sreq_trace_resubmit_short); - - netfs_get_read_subrequest(subreq); - atomic_inc(&rreq->nr_rd_ops); - if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); - else - netfs_read_from_server(rreq, subreq); -} - -/* - * Resubmit any short or failed operations. Returns true if we got the rreq - * ref back. - */ -static bool netfs_rreq_perform_resubmissions(struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - - WARN_ON(in_interrupt()); - - trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); - - /* We don't want terminating submissions trying to wake us up whilst - * we're still going through the list. - */ - atomic_inc(&rreq->nr_rd_ops); - - __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->error) { - if (subreq->source != NETFS_READ_FROM_CACHE) - break; - subreq->source = NETFS_DOWNLOAD_FROM_SERVER; - subreq->error = 0; - netfs_stat(&netfs_n_rh_download_instead); - trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead); - netfs_get_read_subrequest(subreq); - atomic_inc(&rreq->nr_rd_ops); - netfs_read_from_server(rreq, subreq); - } else if (test_bit(NETFS_SREQ_SHORT_READ, &subreq->flags)) { - netfs_rreq_short_read(rreq, subreq); - } - } - - /* If we decrement nr_rd_ops to 0, the usage ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_rd_ops)) - return true; - - wake_up_var(&rreq->nr_rd_ops); - return false; -} - -/* - * Check to see if the data read is still valid. - */ -static void netfs_rreq_is_still_valid(struct netfs_read_request *rreq) -{ - struct netfs_read_subrequest *subreq; - - if (!rreq->netfs_ops->is_still_valid || - rreq->netfs_ops->is_still_valid(rreq)) - return; - - list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { - if (subreq->source == NETFS_READ_FROM_CACHE) { - subreq->error = -ESTALE; - __set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } - } -} - -/* - * Assess the state of a read request and decide what to do next. - * - * Note that we could be in an ordinary kernel thread, on a workqueue or in - * softirq context at this point. We inherit a ref from the caller. - */ -static void netfs_rreq_assess(struct netfs_read_request *rreq, bool was_async) -{ - trace_netfs_rreq(rreq, netfs_rreq_trace_assess); - -again: - netfs_rreq_is_still_valid(rreq); - - if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && - test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { - if (netfs_rreq_perform_resubmissions(rreq)) - goto again; - return; - } - - netfs_rreq_unlock(rreq); - - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); - - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags)) - return netfs_rreq_write_to_cache(rreq); - - netfs_rreq_completed(rreq, was_async); -} - -static void netfs_rreq_work(struct work_struct *work) -{ - struct netfs_read_request *rreq = - container_of(work, struct netfs_read_request, work); - netfs_rreq_assess(rreq, false); -} - -/* - * Handle the completion of all outstanding I/O operations on a read request. - * We inherit a ref from the caller. - */ -static void netfs_rreq_terminated(struct netfs_read_request *rreq, - bool was_async) -{ - if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && - was_async) { - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_rreq_assess(rreq, was_async); - } -} - -/** - * netfs_subreq_terminated - Note the termination of an I/O operation. - * @subreq: The I/O request that has terminated. - * @transferred_or_error: The amount of data transferred or an error code. - * @was_async: The termination was asynchronous - * - * This tells the read helper that a contributory I/O operation has terminated, - * one way or another, and that it should integrate the results. - * - * The caller indicates in @transferred_or_error the outcome of the operation, - * supplying a positive value to indicate the number of bytes transferred, 0 to - * indicate a failure to transfer anything that should be retried or a negative - * error code. The helper will look after reissuing I/O operations as - * appropriate and writing downloaded data to the cache. - * - * If @was_async is true, the caller might be running in softirq or interrupt - * context and we can't sleep. - */ -void netfs_subreq_terminated(struct netfs_read_subrequest *subreq, - ssize_t transferred_or_error, - bool was_async) -{ - struct netfs_read_request *rreq = subreq->rreq; - int u; - - _enter("[%u]{%llx,%lx},%zd", - subreq->debug_index, subreq->start, subreq->flags, - transferred_or_error); - - switch (subreq->source) { - case NETFS_READ_FROM_CACHE: - netfs_stat(&netfs_n_rh_read_done); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_stat(&netfs_n_rh_download_done); - break; - default: - break; - } - - if (IS_ERR_VALUE(transferred_or_error)) { - subreq->error = transferred_or_error; - trace_netfs_failure(rreq, subreq, transferred_or_error, - netfs_fail_read); - goto failed; - } - - if (WARN(transferred_or_error > subreq->len - subreq->transferred, - "Subreq overread: R%x[%x] %zd > %zu - %zu", - rreq->debug_id, subreq->debug_index, - transferred_or_error, subreq->len, subreq->transferred)) - transferred_or_error = subreq->len - subreq->transferred; - - subreq->error = 0; - subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len) - goto incomplete; - -complete: - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - -out: - trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - - /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ - u = atomic_dec_return(&rreq->nr_rd_ops); - if (u == 0) - netfs_rreq_terminated(rreq, was_async); - else if (u == 1) - wake_up_var(&rreq->nr_rd_ops); - - netfs_put_subrequest(subreq, was_async); - return; - -incomplete: - if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { - netfs_clear_unread(subreq); - subreq->transferred = subreq->len; - goto complete; - } - - if (transferred_or_error == 0) { - if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - subreq->error = -ENODATA; - goto failed; - } - } else { - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - } - - __set_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - goto out; - -failed: - if (subreq->source == NETFS_READ_FROM_CACHE) { - netfs_stat(&netfs_n_rh_read_failed); - set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); - } else { - netfs_stat(&netfs_n_rh_download_failed); - set_bit(NETFS_RREQ_FAILED, &rreq->flags); - rreq->error = subreq->error; - } - goto out; -} -EXPORT_SYMBOL(netfs_subreq_terminated); - -static enum netfs_read_source netfs_cache_prepare_read(struct netfs_read_subrequest *subreq, - loff_t i_size) -{ - struct netfs_read_request *rreq = subreq->rreq; - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops) - return cres->ops->prepare_read(subreq, i_size); - if (subreq->start >= rreq->i_size) - return NETFS_FILL_WITH_ZEROES; - return NETFS_DOWNLOAD_FROM_SERVER; -} - -/* - * Work out what sort of subrequest the next one will be. - */ -static enum netfs_read_source -netfs_rreq_prepare_read(struct netfs_read_request *rreq, - struct netfs_read_subrequest *subreq) -{ - enum netfs_read_source source; - - _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); - - source = netfs_cache_prepare_read(subreq, rreq->i_size); - if (source == NETFS_INVALID_READ) - goto out; - - if (source == NETFS_DOWNLOAD_FROM_SERVER) { - /* Call out to the netfs to let it shrink the request to fit - * its own I/O sizes and boundaries. If it shinks it here, it - * will be called again to make simultaneous calls; if it wants - * to make serial calls, it can indicate a short read and then - * we will call it again. - */ - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; - - if (rreq->netfs_ops->clamp_length && - !rreq->netfs_ops->clamp_length(subreq)) { - source = NETFS_INVALID_READ; - goto out; - } - } - - if (WARN_ON(subreq->len == 0)) - source = NETFS_INVALID_READ; - -out: - subreq->source = source; - trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); - return source; -} - -/* - * Slice off a piece of a read request and submit an I/O request for it. - */ -static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq, - unsigned int *_debug_index) -{ - struct netfs_read_subrequest *subreq; - enum netfs_read_source source; - - subreq = netfs_alloc_subrequest(rreq); - if (!subreq) - return false; - - subreq->debug_index = (*_debug_index)++; - subreq->start = rreq->start + rreq->submitted; - subreq->len = rreq->len - rreq->submitted; - - _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); - list_add_tail(&subreq->rreq_link, &rreq->subrequests); - - /* Call out to the cache to find out what it can do with the remaining - * subset. It tells us in subreq->flags what it decided should be done - * and adjusts subreq->len down if the subset crosses a cache boundary. - * - * Then when we hand the subset, it can choose to take a subset of that - * (the starts must coincide), in which case, we go around the loop - * again and ask it to download the next piece. - */ - source = netfs_rreq_prepare_read(rreq, subreq); - if (source == NETFS_INVALID_READ) - goto subreq_failed; - - atomic_inc(&rreq->nr_rd_ops); - - rreq->submitted += subreq->len; - - trace_netfs_sreq(subreq, netfs_sreq_trace_submit); - switch (source) { - case NETFS_FILL_WITH_ZEROES: - netfs_fill_with_zeroes(rreq, subreq); - break; - case NETFS_DOWNLOAD_FROM_SERVER: - netfs_read_from_server(rreq, subreq); - break; - case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); - break; - default: - BUG(); - } - - return true; - -subreq_failed: - rreq->error = subreq->error; - netfs_put_subrequest(subreq, false); - return false; -} - -static void netfs_cache_expand_readahead(struct netfs_read_request *rreq, - loff_t *_start, size_t *_len, loff_t i_size) -{ - struct netfs_cache_resources *cres = &rreq->cache_resources; - - if (cres->ops && cres->ops->expand_readahead) - cres->ops->expand_readahead(cres, _start, _len, i_size); -} - -static void netfs_rreq_expand(struct netfs_read_request *rreq, - struct readahead_control *ractl) -{ - /* Give the cache a chance to change the request parameters. The - * resultant request must contain the original region. - */ - netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); - - /* Give the netfs a chance to change the request parameters. The - * resultant request must contain the original region. - */ - if (rreq->netfs_ops->expand_readahead) - rreq->netfs_ops->expand_readahead(rreq); - - /* Expand the request if the cache wants it to start earlier. Note - * that the expansion may get further extended if the VM wishes to - * insert THPs and the preferred start and/or end wind up in the middle - * of THPs. - * - * If this is the case, however, the THP size should be an integer - * multiple of the cache granule size, so we get a whole number of - * granules to deal with. - */ - if (rreq->start != readahead_pos(ractl) || - rreq->len != readahead_length(ractl)) { - readahead_expand(ractl, rreq->start, rreq->len); - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); - - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_expanded); - } -} - -/** - * netfs_readahead - Helper to manage a read request - * @ractl: The description of the readahead request - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request - * - * Fulfil a readahead request by drawing data from the cache if possible, or - * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O - * requests from different sources will get munged together. If necessary, the - * readahead window can be expanded in either direction to a more convenient - * alighment for RPC efficiency or to make storage in the cache feasible. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. It may also be passed a private token, which will - * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). - * - * This is usable whether or not caching is enabled. - */ -void netfs_readahead(struct readahead_control *ractl, - const struct netfs_read_request_ops *ops, - void *netfs_priv) -{ - struct netfs_read_request *rreq; - unsigned int debug_index = 0; - int ret; - - _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); - - if (readahead_count(ractl) == 0) - goto cleanup; - - rreq = netfs_alloc_read_request(ops, netfs_priv, ractl->file); - if (!rreq) - goto cleanup; - rreq->mapping = ractl->mapping; - rreq->start = readahead_pos(ractl); - rreq->len = readahead_length(ractl); - - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto cleanup_free; - } - - netfs_stat(&netfs_n_rh_readahead); - trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), - netfs_read_trace_readahead); - - netfs_rreq_expand(rreq, ractl); - - atomic_set(&rreq->nr_rd_ops, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - /* Drop the refs on the folios here rather than in the cache or - * filesystem. The locks will be dropped in netfs_rreq_unlock(). - */ - while (readahead_folio(ractl)) - ; - - /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ - if (atomic_dec_and_test(&rreq->nr_rd_ops)) - netfs_rreq_assess(rreq, false); - return; - -cleanup_free: - netfs_put_read_request(rreq, false); - return; -cleanup: - if (netfs_priv) - ops->cleanup(ractl->mapping, netfs_priv); - return; -} -EXPORT_SYMBOL(netfs_readahead); - -/** - * netfs_readpage - Helper to manage a readpage request - * @file: The file to read from - * @folio: The folio to read - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request - * - * Fulfil a readpage request by drawing data from the cache if possible, or the - * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests - * from different sources will get munged together. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. It may also be passed a private token, which will - * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). - * - * This is usable whether or not caching is enabled. - */ -int netfs_readpage(struct file *file, - struct folio *folio, - const struct netfs_read_request_ops *ops, - void *netfs_priv) -{ - struct netfs_read_request *rreq; - unsigned int debug_index = 0; - int ret; - - _enter("%lx", folio_index(folio)); - - rreq = netfs_alloc_read_request(ops, netfs_priv, file); - if (!rreq) { - if (netfs_priv) - ops->cleanup(folio_file_mapping(folio), netfs_priv); - folio_unlock(folio); - return -ENOMEM; - } - rreq->mapping = folio_file_mapping(folio); - rreq->start = folio_file_pos(folio); - rreq->len = folio_size(folio); - - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) { - folio_unlock(folio); - goto out; - } - } - - netfs_stat(&netfs_n_rh_readpage); - trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); - - netfs_get_read_request(rreq); - - atomic_set(&rreq->nr_rd_ops, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - /* Keep nr_rd_ops incremented so that the ref always belongs to us, and - * the service code isn't punted off to a random thread pool to - * process. - */ - do { - wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1); - netfs_rreq_assess(rreq, false); - } while (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)); - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_readpage); - ret = -EIO; - } -out: - netfs_put_read_request(rreq, false); - return ret; -} -EXPORT_SYMBOL(netfs_readpage); - -/* - * Prepare a folio for writing without reading first - * @folio: The folio being prepared - * @pos: starting position for the write - * @len: length of write - * - * In some cases, write_begin doesn't need to read at all: - * - full folio write - * - write that lies in a folio that is completely beyond EOF - * - write that covers the folio from start to EOF or beyond it - * - * If any of these criteria are met, then zero out the unwritten parts - * of the folio and return true. Otherwise, return false. - */ -static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) -{ - struct inode *inode = folio_inode(folio); - loff_t i_size = i_size_read(inode); - size_t offset = offset_in_folio(folio, pos); - - /* Full folio write */ - if (offset == 0 && len >= folio_size(folio)) - return true; - - /* pos beyond last folio in the file */ - if (pos - offset >= i_size) - goto zero_out; - - /* Write that covers from the start of the folio to EOF or beyond */ - if (offset == 0 && (pos + len) >= i_size) - goto zero_out; - - return false; -zero_out: - zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio)); - return true; -} - -/** - * netfs_write_begin - Helper to prepare for writing - * @file: The file to read from - * @mapping: The mapping to read from - * @pos: File position at which the write will begin - * @len: The length of the write (may extend beyond the end of the folio chosen) - * @aop_flags: AOP_* flags - * @_folio: Where to put the resultant folio - * @_fsdata: Place for the netfs to store a cookie - * @ops: The network filesystem's operations for the helper to use - * @netfs_priv: Private netfs data to be retained in the request - * - * Pre-read data for a write-begin request by drawing data from the cache if - * possible, or the netfs if not. Space beyond the EOF is zero-filled. - * Multiple I/O requests from different sources will get munged together. If - * necessary, the readahead window can be expanded in either direction to a - * more convenient alighment for RPC efficiency or to make storage in the cache - * feasible. - * - * The calling netfs must provide a table of operations, only one of which, - * issue_op, is mandatory. - * - * The check_write_begin() operation can be provided to check for and flush - * conflicting writes once the folio is grabbed and locked. It is passed a - * pointer to the fsdata cookie that gets returned to the VM to be passed to - * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the folio and return -EAGAIN to cause the folio to - * be regot; or return an error. - * - * This is usable whether or not caching is enabled. - */ -int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int aop_flags, - struct folio **_folio, void **_fsdata, - const struct netfs_read_request_ops *ops, - void *netfs_priv) -{ - struct netfs_read_request *rreq; - struct folio *folio; - struct inode *inode = file_inode(file); - unsigned int debug_index = 0, fgp_flags; - pgoff_t index = pos >> PAGE_SHIFT; - int ret; - - DEFINE_READAHEAD(ractl, file, NULL, mapping, index); - -retry: - fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; - if (aop_flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - folio = __filemap_get_folio(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (!folio) - return -ENOMEM; - - if (ops->check_write_begin) { - /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ops->check_write_begin(file, pos, len, folio, _fsdata); - if (ret < 0) { - trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); - if (ret == -EAGAIN) - goto retry; - goto error; - } - } - - if (folio_test_uptodate(folio)) - goto have_folio; - - /* If the page is beyond the EOF, we want to clear it - unless it's - * within the cache granule containing the EOF, in which case we need - * to preload the granule. - */ - if (!ops->is_cache_enabled(inode) && - netfs_skip_folio_read(folio, pos, len)) { - netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio_no_wait; - } - - ret = -ENOMEM; - rreq = netfs_alloc_read_request(ops, netfs_priv, file); - if (!rreq) - goto error; - rreq->mapping = folio_file_mapping(folio); - rreq->start = folio_file_pos(folio); - rreq->len = folio_size(folio); - rreq->no_unlock_folio = folio_index(folio); - __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); - netfs_priv = NULL; - - if (ops->begin_cache_operation) { - ret = ops->begin_cache_operation(rreq); - if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) - goto error_put; - } - - netfs_stat(&netfs_n_rh_write_begin); - trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); - - /* Expand the request to meet caching requirements and download - * preferences. - */ - ractl._nr_pages = folio_nr_pages(folio); - netfs_rreq_expand(rreq, &ractl); - netfs_get_read_request(rreq); - - /* We hold the folio locks, so we can drop the references */ - folio_get(folio); - while (readahead_folio(&ractl)) - ; - - atomic_set(&rreq->nr_rd_ops, 1); - do { - if (!netfs_rreq_submit_slice(rreq, &debug_index)) - break; - - } while (rreq->submitted < rreq->len); - - /* Keep nr_rd_ops incremented so that the ref always belongs to us, and - * the service code isn't punted off to a random thread pool to - * process. - */ - for (;;) { - wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1); - netfs_rreq_assess(rreq, false); - if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) - break; - cond_resched(); - } - - ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_write_begin); - ret = -EIO; - } - netfs_put_read_request(rreq, false); - if (ret < 0) - goto error; - -have_folio: - ret = folio_wait_fscache_killable(folio); - if (ret < 0) - goto error; -have_folio_no_wait: - if (netfs_priv) - ops->cleanup(mapping, netfs_priv); - *_folio = folio; - _leave(" = 0"); - return 0; - -error_put: - netfs_put_read_request(rreq, false); -error: - folio_unlock(folio); - folio_put(folio); - if (netfs_priv) - ops->cleanup(mapping, netfs_priv); - _leave(" = %d", ret); - return ret; -} -EXPORT_SYMBOL(netfs_write_begin); diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index 9ae538c85378..5510a7a14a40 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -7,7 +7,6 @@ #include <linux/export.h> #include <linux/seq_file.h> -#include <linux/netfs.h> #include "internal.h" atomic_t netfs_n_rh_readahead; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 47a53b3362b6..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,10 +4,6 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC - select CRYPTO - select CRYPTO_HASH - select XXHASH - select CRYPTO_XXHASH select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bac4cf1a308e..c6b263b5faf1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,7 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> -#include <linux/xxhash.h> +#include <linux/hash.h> #include "delegation.h" #include "iostat.h" @@ -350,10 +350,7 @@ out: * of directory cookies. Content is addressed by the value of the * cookie index of the first readdir entry in a page. * - * The xxhash algorithm is chosen because it is fast, and is supposed - * to result in a decent flat distribution of hashes. - * - * We then select only the first 18 bits to avoid issues with excessive + * We select only the first 18 bits to avoid issues with excessive * memory use for the page cache XArray. 18 bits should allow the caching * of 262144 pages of sequences of readdir entries. Since each page holds * 127 readdir entries for a typical 64-bit system, that works out to a @@ -363,7 +360,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) { if (cookie == 0) return 0; - return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK; + return hash_64(cookie, 18); } static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, @@ -1991,16 +1988,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); -static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index b0ca244c50d0..150b7fa8f0a7 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -646,7 +646,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) result = generic_write_checks(iocb, from); if (result > 0) { current->backing_dev_info = inode_to_bdi(inode); - result = generic_perform_write(file, from, iocb->ki_pos); + result = generic_perform_write(iocb, from); current->backing_dev_info = NULL; } nfs_end_io_write(inode); diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 4dee53ceb941..f73c09a9cf0a 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -238,14 +238,6 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) } } -static inline void fscache_end_operation(struct netfs_cache_resources *cres) -{ - const struct netfs_cache_ops *ops = fscache_operation_valid(cres); - - if (ops) - ops->end_operation(cres); -} - /* * Fallback page reading interface. */ diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7eb3b08d702f..b4e46b0ffa2d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 57b0497105c8..7eefa16ed381 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; } +static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index ad3405c64b9e..e7b34f7e0614 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void) nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index d258933cf8c8..7b861e4f0533 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err; @@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err; + f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + f_mode |= flags_to_mode(openflags); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e3f5b380cefe..16106f805ffa 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9615,6 +9615,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); status = rpc_wait_for_completion_task(task); if (status != 0) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c..6f325e10056c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return ERR_PTR(-ENOMEM); + task_setup_data.task = &data->task; task_setup_data.callback_data = data; data->cred = get_current_cred(); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index c08882f5867b..2c1b027774d4 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -237,6 +237,13 @@ nfsd_file_check_write_error(struct nfsd_file *nf) } static void +nfsd_file_flush(struct nfsd_file *nf) +{ + if (nf->nf_file && vfs_fsync(nf->nf_file, 1) != 0) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); +} + +static void nfsd_file_do_unhash(struct nfsd_file *nf) { lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); @@ -295,19 +302,15 @@ nfsd_file_put_noref(struct nfsd_file *nf) void nfsd_file_put(struct nfsd_file *nf) { - bool is_hashed; - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) { + nfsd_file_flush(nf); nfsd_file_put_noref(nf); - return; + } else { + nfsd_file_put_noref(nf); + if (nf->nf_file) + nfsd_file_schedule_laundrette(); } - - filemap_flush(nf->nf_file->f_mapping); - is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - nfsd_file_put_noref(nf); - if (is_hashed) - nfsd_file_schedule_laundrette(); if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) nfsd_file_gc(); } @@ -328,6 +331,7 @@ nfsd_file_dispose_list(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); nfsd_file_put_noref(nf); } } @@ -341,6 +345,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); if (!refcount_dec_and_test(&nf->nf_ref)) continue; if (nfsd_file_free(nf)) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 367551bddfc6..b5760801d377 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -249,34 +249,34 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) int w; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; if (dentry == NULL || d_really_is_negative(dentry)) - return 1; + return true; inode = d_inode(dentry); if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; rqstp->rq_res.page_len = w = nfsacl_size( (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 1; + return true; w -= PAGE_SIZE; } if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, resp->mask & NFS_ACL, 0)) - return 0; + return false; if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return 0; + return false; - return 1; + return true; } /* ACCESS */ @@ -286,17 +286,17 @@ nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; } - return 1; + return true; } /* diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 66bdaa2cf496..ca611ac09f7c 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -20,6 +20,23 @@ #include "page.h" #include "btnode.h" + +/** + * nilfs_init_btnc_inode - initialize B-tree node cache inode + * @btnc_inode: inode to be initialized + * + * nilfs_init_btnc_inode() sets up an inode for B-tree node cache. + */ +void nilfs_init_btnc_inode(struct inode *btnc_inode) +{ + struct nilfs_inode_info *ii = NILFS_I(btnc_inode); + + btnc_inode->i_mode = S_IFREG; + ii->i_flags = 0; + memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); +} + void nilfs_btnode_cache_clear(struct address_space *btnc) { invalidate_mapping_pages(btnc, 0, -1); @@ -29,7 +46,7 @@ void nilfs_btnode_cache_clear(struct address_space *btnc) struct buffer_head * nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) { - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct buffer_head *bh; bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); @@ -57,7 +74,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, struct buffer_head **pbh, sector_t *submit_ptr) { struct buffer_head *bh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; struct page *page; int err; @@ -157,7 +174,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, struct nilfs_btnode_chkey_ctxt *ctxt) { struct buffer_head *obh, *nbh; - struct inode *inode = NILFS_BTNC_I(btnc); + struct inode *inode = btnc->host; __u64 oldkey = ctxt->oldkey, newkey = ctxt->newkey; int err; diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 11663650add7..bd5544e63a01 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -30,6 +30,7 @@ struct nilfs_btnode_chkey_ctxt { struct buffer_head *newbh; }; +void nilfs_init_btnc_inode(struct inode *btnc_inode); void nilfs_btnode_cache_clear(struct address_space *); struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 3594eabe1419..f544c22fff78 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -58,7 +58,8 @@ static void nilfs_btree_free_path(struct nilfs_btree_path *path) static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); @@ -470,7 +471,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, struct buffer_head **bhp, const struct nilfs_btree_readahead_info *ra) { - struct address_space *btnc = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btnc = btnc_inode->i_mapping; struct buffer_head *bh, *ra_bh; sector_t submit_ptr = 0; int ret; @@ -1741,6 +1743,10 @@ nilfs_btree_prepare_convert_and_insert(struct nilfs_bmap *btree, __u64 key, dat = nilfs_bmap_get_dat(btree); } + ret = nilfs_attach_btree_node_cache(&NILFS_BMAP_I(btree)->vfs_inode); + if (ret < 0) + return ret; + ret = nilfs_bmap_prepare_alloc_ptr(btree, dreq, dat); if (ret < 0) return ret; @@ -1913,7 +1919,7 @@ static int nilfs_btree_prepare_update_v(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = path[level].bp_newreq.bpr_ptr; path[level].bp_ctxt.bh = path[level].bp_bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) { nilfs_dat_abort_update(dat, @@ -1939,7 +1945,7 @@ static void nilfs_btree_commit_update_v(struct nilfs_bmap *btree, if (buffer_nilfs_node(path[level].bp_bh)) { nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); path[level].bp_bh = path[level].bp_ctxt.bh; } @@ -1958,7 +1964,7 @@ static void nilfs_btree_abort_update_v(struct nilfs_bmap *btree, &path[level].bp_newreq.bpr_req); if (buffer_nilfs_node(path[level].bp_bh)) nilfs_btnode_abort_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); } @@ -2134,7 +2140,8 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree, static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, struct list_head *listp) { - struct address_space *btcache = &NILFS_BMAP_I(btree)->i_btnode_cache; + struct inode *btnc_inode = NILFS_BMAP_I(btree)->i_assoc_inode; + struct address_space *btcache = btnc_inode->i_mapping; struct list_head lists[NILFS_BTREE_LEVEL_MAX]; struct pagevec pvec; struct buffer_head *bh, *head; @@ -2188,12 +2195,12 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, path[level].bp_ctxt.newkey = blocknr; path[level].bp_ctxt.bh = *bh; ret = nilfs_btnode_prepare_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); if (ret < 0) return ret; nilfs_btnode_commit_change_key( - &NILFS_BMAP_I(btree)->i_btnode_cache, + NILFS_BMAP_I(btree)->i_assoc_inode->i_mapping, &path[level].bp_ctxt); *bh = path[level].bp_ctxt.bh; } @@ -2398,6 +2405,10 @@ int nilfs_btree_init(struct nilfs_bmap *bmap) if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode)) ret = -EIO; + else + ret = nilfs_attach_btree_node_cache( + &NILFS_BMAP_I(bmap)->vfs_inode); + return ret; } diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index dc51d3b7a7bf..3b55e239705f 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -497,7 +497,9 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size, di = NILFS_DAT_I(dat); lockdep_set_class(&di->mi.mi_sem, &dat_lock_key); nilfs_palloc_setup_cache(dat, &di->palloc_cache); - nilfs_mdt_setup_shadow_map(dat, &di->shadow); + err = nilfs_mdt_setup_shadow_map(dat, &di->shadow); + if (err) + goto failed; err = nilfs_read_inode_common(dat, raw_inode); if (err) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index a8f5315f01e3..04fdd420eae7 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -126,9 +126,10 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn, __u64 vbn, struct buffer_head **out_bh) { + struct inode *btnc_inode = NILFS_I(inode)->i_assoc_inode; int ret; - ret = nilfs_btnode_submit_block(&NILFS_I(inode)->i_btnode_cache, + ret = nilfs_btnode_submit_block(btnc_inode->i_mapping, vbn ? : pbn, pbn, REQ_OP_READ, 0, out_bh, &pbn); if (ret == -EEXIST) /* internal code (cache hit) */ @@ -170,7 +171,7 @@ int nilfs_init_gcinode(struct inode *inode) ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); - return 0; + return nilfs_attach_btree_node_cache(inode); } /** @@ -185,7 +186,7 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) ii = list_first_entry(head, struct nilfs_inode_info, i_dirty); list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 476a4a649f38..6045cea21f52 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -29,12 +29,16 @@ * @cno: checkpoint number * @root: pointer on NILFS root object (mounted checkpoint) * @for_gc: inode for GC flag + * @for_btnc: inode for B-tree node cache flag + * @for_shadow: inode for shadowed page cache flag */ struct nilfs_iget_args { u64 ino; __u64 cno; struct nilfs_root *root; - int for_gc; + bool for_gc; + bool for_btnc; + bool for_shadow; }; static int nilfs_iget_test(struct inode *inode, void *opaque); @@ -312,7 +316,8 @@ static int nilfs_insert_inode_locked(struct inode *inode, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return insert_inode_locked4(inode, ino, nilfs_iget_test, &args); @@ -525,6 +530,19 @@ static int nilfs_iget_test(struct inode *inode, void *opaque) return 0; ii = NILFS_I(inode); + if (test_bit(NILFS_I_BTNC, &ii->i_state)) { + if (!args->for_btnc) + return 0; + } else if (args->for_btnc) { + return 0; + } + if (test_bit(NILFS_I_SHADOW, &ii->i_state)) { + if (!args->for_shadow) + return 0; + } else if (args->for_shadow) { + return 0; + } + if (!test_bit(NILFS_I_GCINODE, &ii->i_state)) return !args->for_gc; @@ -536,15 +554,17 @@ static int nilfs_iget_set(struct inode *inode, void *opaque) struct nilfs_iget_args *args = opaque; inode->i_ino = args->ino; - if (args->for_gc) { + NILFS_I(inode)->i_cno = args->cno; + NILFS_I(inode)->i_root = args->root; + if (args->root && args->ino == NILFS_ROOT_INO) + nilfs_get_root(args->root); + + if (args->for_gc) NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE); - NILFS_I(inode)->i_cno = args->cno; - NILFS_I(inode)->i_root = NULL; - } else { - if (args->root && args->ino == NILFS_ROOT_INO) - nilfs_get_root(args->root); - NILFS_I(inode)->i_root = args->root; - } + if (args->for_btnc) + NILFS_I(inode)->i_state |= BIT(NILFS_I_BTNC); + if (args->for_shadow) + NILFS_I(inode)->i_state |= BIT(NILFS_I_SHADOW); return 0; } @@ -552,7 +572,8 @@ struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return ilookup5(sb, ino, nilfs_iget_test, &args); @@ -562,7 +583,8 @@ struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root, unsigned long ino) { struct nilfs_iget_args args = { - .ino = ino, .root = root, .cno = 0, .for_gc = 0 + .ino = ino, .root = root, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = false }; return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args); @@ -593,7 +615,8 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno) { struct nilfs_iget_args args = { - .ino = ino, .root = NULL, .cno = cno, .for_gc = 1 + .ino = ino, .root = NULL, .cno = cno, .for_gc = true, + .for_btnc = false, .for_shadow = false }; struct inode *inode; int err; @@ -613,6 +636,113 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, return inode; } +/** + * nilfs_attach_btree_node_cache - attach a B-tree node cache to the inode + * @inode: inode object + * + * nilfs_attach_btree_node_cache() attaches a B-tree node cache to @inode, + * or does nothing if the inode already has it. This function allocates + * an additional inode to maintain page cache of B-tree nodes one-on-one. + * + * Return Value: On success, 0 is returned. On errors, one of the following + * negative error code is returned. + * + * %-ENOMEM - Insufficient memory available. + */ +int nilfs_attach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode; + struct nilfs_iget_args args; + + if (ii->i_assoc_inode) + return 0; + + args.ino = inode->i_ino; + args.root = ii->i_root; + args.cno = ii->i_cno; + args.for_gc = test_bit(NILFS_I_GCINODE, &ii->i_state) != 0; + args.for_btnc = true; + args.for_shadow = test_bit(NILFS_I_SHADOW, &ii->i_state) != 0; + + btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!btnc_inode)) + return -ENOMEM; + if (btnc_inode->i_state & I_NEW) { + nilfs_init_btnc_inode(btnc_inode); + unlock_new_inode(btnc_inode); + } + NILFS_I(btnc_inode)->i_assoc_inode = inode; + NILFS_I(btnc_inode)->i_bmap = ii->i_bmap; + ii->i_assoc_inode = btnc_inode; + + return 0; +} + +/** + * nilfs_detach_btree_node_cache - detach the B-tree node cache from the inode + * @inode: inode object + * + * nilfs_detach_btree_node_cache() detaches the B-tree node cache and its + * holder inode bound to @inode, or does nothing if @inode doesn't have it. + */ +void nilfs_detach_btree_node_cache(struct inode *inode) +{ + struct nilfs_inode_info *ii = NILFS_I(inode); + struct inode *btnc_inode = ii->i_assoc_inode; + + if (btnc_inode) { + NILFS_I(btnc_inode)->i_assoc_inode = NULL; + ii->i_assoc_inode = NULL; + iput(btnc_inode); + } +} + +/** + * nilfs_iget_for_shadow - obtain inode for shadow mapping + * @inode: inode object that uses shadow mapping + * + * nilfs_iget_for_shadow() allocates a pair of inodes that holds page + * caches for shadow mapping. The page cache for data pages is set up + * in one inode and the one for b-tree node pages is set up in the + * other inode, which is attached to the former inode. + * + * Return Value: On success, a pointer to the inode for data pages is + * returned. On errors, one of the following negative error code is returned + * in a pointer type. + * + * %-ENOMEM - Insufficient memory available. + */ +struct inode *nilfs_iget_for_shadow(struct inode *inode) +{ + struct nilfs_iget_args args = { + .ino = inode->i_ino, .root = NULL, .cno = 0, .for_gc = false, + .for_btnc = false, .for_shadow = true + }; + struct inode *s_inode; + int err; + + s_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test, + nilfs_iget_set, &args); + if (unlikely(!s_inode)) + return ERR_PTR(-ENOMEM); + if (!(s_inode->i_state & I_NEW)) + return inode; + + NILFS_I(s_inode)->i_flags = 0; + memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); + mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + + err = nilfs_attach_btree_node_cache(s_inode); + if (unlikely(err)) { + iget_failed(s_inode); + return ERR_PTR(err); + } + unlock_new_inode(s_inode); + return s_inode; +} + void nilfs_write_inode_common(struct inode *inode, struct nilfs_inode *raw_inode, int has_bmap) { @@ -760,7 +890,8 @@ static void nilfs_clear_inode(struct inode *inode) if (test_bit(NILFS_I_BMAP, &ii->i_state)) nilfs_bmap_clear(ii->i_bmap); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + if (!test_bit(NILFS_I_BTNC, &ii->i_state)) + nilfs_detach_btree_node_cache(inode); if (ii->i_root && inode->i_ino == NILFS_ROOT_INO) nilfs_put_root(ii->i_root); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 78db33decd72..d29a0f2b9c16 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -471,9 +471,18 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz) void nilfs_mdt_clear(struct inode *inode) { struct nilfs_mdt_info *mdi = NILFS_MDT(inode); + struct nilfs_shadow_map *shadow = mdi->mi_shadow; if (mdi->mi_palloc_cache) nilfs_palloc_destroy_cache(inode); + + if (shadow) { + struct inode *s_inode = shadow->inode; + + shadow->inode = NULL; + iput(s_inode); + mdi->mi_shadow = NULL; + } } /** @@ -507,12 +516,15 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, struct nilfs_shadow_map *shadow) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); + struct inode *s_inode; INIT_LIST_HEAD(&shadow->frozen_buffers); - address_space_init_once(&shadow->frozen_data); - nilfs_mapping_init(&shadow->frozen_data, inode); - address_space_init_once(&shadow->frozen_btnodes); - nilfs_mapping_init(&shadow->frozen_btnodes, inode); + + s_inode = nilfs_iget_for_shadow(inode); + if (IS_ERR(s_inode)) + return PTR_ERR(s_inode); + + shadow->inode = s_inode; mi->mi_shadow = shadow; return 0; } @@ -526,14 +538,15 @@ int nilfs_mdt_save_to_shadow_map(struct inode *inode) struct nilfs_mdt_info *mi = NILFS_MDT(inode); struct nilfs_inode_info *ii = NILFS_I(inode); struct nilfs_shadow_map *shadow = mi->mi_shadow; + struct inode *s_inode = shadow->inode; int ret; - ret = nilfs_copy_dirty_pages(&shadow->frozen_data, inode->i_mapping); + ret = nilfs_copy_dirty_pages(s_inode->i_mapping, inode->i_mapping); if (ret) goto out; - ret = nilfs_copy_dirty_pages(&shadow->frozen_btnodes, - &ii->i_btnode_cache); + ret = nilfs_copy_dirty_pages(NILFS_I(s_inode)->i_assoc_inode->i_mapping, + ii->i_assoc_inode->i_mapping); if (ret) goto out; @@ -549,7 +562,7 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int blkbits = inode->i_blkbits; - page = grab_cache_page(&shadow->frozen_data, bh->b_page->index); + page = grab_cache_page(shadow->inode->i_mapping, bh->b_page->index); if (!page) return -ENOMEM; @@ -581,7 +594,7 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh) struct page *page; int n; - page = find_lock_page(&shadow->frozen_data, bh->b_page->index); + page = find_lock_page(shadow->inode->i_mapping, bh->b_page->index); if (page) { if (page_has_buffers(page)) { n = bh_offset(bh) >> inode->i_blkbits; @@ -622,10 +635,11 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) nilfs_palloc_clear_cache(inode); nilfs_clear_dirty_pages(inode->i_mapping, true); - nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data); + nilfs_copy_back_pages(inode->i_mapping, shadow->inode->i_mapping); - nilfs_clear_dirty_pages(&ii->i_btnode_cache, true); - nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes); + nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true); + nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping, + NILFS_I(shadow->inode)->i_assoc_inode->i_mapping); nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store); @@ -640,10 +654,11 @@ void nilfs_mdt_clear_shadow_map(struct inode *inode) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); struct nilfs_shadow_map *shadow = mi->mi_shadow; + struct inode *shadow_btnc_inode = NILFS_I(shadow->inode)->i_assoc_inode; down_write(&mi->mi_sem); nilfs_release_frozen_buffers(shadow); - truncate_inode_pages(&shadow->frozen_data, 0); - truncate_inode_pages(&shadow->frozen_btnodes, 0); + truncate_inode_pages(shadow->inode->i_mapping, 0); + truncate_inode_pages(shadow_btnc_inode->i_mapping, 0); up_write(&mi->mi_sem); } diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index 8f86080a436d..9e23bab3ff12 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -18,14 +18,12 @@ /** * struct nilfs_shadow_map - shadow mapping of meta data file * @bmap_store: shadow copy of bmap state - * @frozen_data: shadowed dirty data pages - * @frozen_btnodes: shadowed dirty b-tree nodes' pages + * @inode: holder of page caches used in shadow mapping * @frozen_buffers: list of frozen buffers */ struct nilfs_shadow_map { struct nilfs_bmap_store bmap_store; - struct address_space frozen_data; - struct address_space frozen_btnodes; + struct inode *inode; struct list_head frozen_buffers; }; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index a7b81755c350..1344f7d475d3 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -28,7 +28,7 @@ * @i_xattr: <TODO> * @i_dir_start_lookup: page index of last successful search * @i_cno: checkpoint number for GC inode - * @i_btnode_cache: cached pages of b-tree nodes + * @i_assoc_inode: associated inode (B-tree node cache holder or back pointer) * @i_dirty: list for connecting dirty files * @xattr_sem: semaphore for extended attributes processing * @i_bh: buffer contains disk inode @@ -43,7 +43,7 @@ struct nilfs_inode_info { __u64 i_xattr; /* sector_t ??? */ __u32 i_dir_start_lookup; __u64 i_cno; /* check point number for GC inode */ - struct address_space i_btnode_cache; + struct inode *i_assoc_inode; struct list_head i_dirty; /* List for connecting dirty files */ #ifdef CONFIG_NILFS_XATTR @@ -75,13 +75,6 @@ NILFS_BMAP_I(const struct nilfs_bmap *bmap) return container_of(bmap, struct nilfs_inode_info, i_bmap_data); } -static inline struct inode *NILFS_BTNC_I(struct address_space *btnc) -{ - struct nilfs_inode_info *ii = - container_of(btnc, struct nilfs_inode_info, i_btnode_cache); - return &ii->vfs_inode; -} - /* * Dynamic state flags of NILFS on-memory inode (i_state) */ @@ -98,6 +91,8 @@ enum { NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */ NILFS_I_BMAP, /* has bmap and btnode_cache */ NILFS_I_GCINODE, /* inode for GC, on memory only */ + NILFS_I_BTNC, /* inode for btree node cache */ + NILFS_I_SHADOW, /* inode for shadowed page cache */ }; /* @@ -267,6 +262,9 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, unsigned long ino); extern struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino, __u64 cno); +int nilfs_attach_btree_node_cache(struct inode *inode); +void nilfs_detach_btree_node_cache(struct inode *inode); +struct inode *nilfs_iget_for_shadow(struct inode *inode); extern void nilfs_update_inode(struct inode *, struct buffer_head *, int); extern void nilfs_truncate(struct inode *); extern void nilfs_evict_inode(struct inode *); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 063dd16d75b5..a8e88cc38e16 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -436,22 +436,12 @@ unsigned int nilfs_page_count_clean_buffers(struct page *page, return nc; } -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode) -{ - mapping->host = inode; - mapping->flags = 0; - mapping_set_gfp_mask(mapping, GFP_NOFS); - mapping->private_data = NULL; - mapping->a_ops = &empty_aops; -} - /* * NILFS2 needs clear_page_dirty() in the following two cases: * - * 1) For B-tree node pages and data pages of the dat/gcdat, NILFS2 clears - * page dirty flags when it copies back pages from the shadow cache - * (gcdat->{i_mapping,i_btnode_cache}) to its original cache - * (dat->{i_mapping,i_btnode_cache}). + * 1) For B-tree node pages and data pages of DAT file, NILFS2 clears dirty + * flag of pages when it copies back pages from shadow cache to the + * original cache. * * 2) Some B-tree operations like insertion or deletion may dispose buffers * in dirty state, and this needs to cancel the dirty state of their pages. diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index 569263b23c0c..21ddcdd4d63e 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -43,7 +43,6 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); void nilfs_clear_dirty_page(struct page *, bool); void nilfs_clear_dirty_pages(struct address_space *, bool); -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode); unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int, unsigned int); unsigned long nilfs_find_uncommitted_extent(struct inode *inode, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 85a853334771..0afe0832c754 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -733,15 +733,18 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, struct list_head *listp) { struct nilfs_inode_info *ii = NILFS_I(inode); - struct address_space *mapping = &ii->i_btnode_cache; + struct inode *btnc_inode = ii->i_assoc_inode; struct pagevec pvec; struct buffer_head *bh, *head; unsigned int i; pgoff_t index = 0; + if (!btnc_inode) + return; + pagevec_init(&pvec); - while (pagevec_lookup_tag(&pvec, mapping, &index, + while (pagevec_lookup_tag(&pvec, btnc_inode->i_mapping, &index, PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); @@ -2410,7 +2413,7 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) continue; list_del_init(&ii->i_dirty); truncate_inode_pages(&ii->vfs_inode.i_data, 0); - nilfs_btnode_cache_clear(&ii->i_btnode_cache); + nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 3e05c98631ec..ba108f915391 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -157,7 +157,8 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) ii->i_bh = NULL; ii->i_state = 0; ii->i_cno = 0; - nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode); + ii->i_assoc_inode = NULL; + ii->i_bmap = &ii->i_bmap_data; return &ii->vfs_inode; } @@ -1377,8 +1378,6 @@ static void nilfs_inode_init_once(void *obj) #ifdef CONFIG_NILFS_XATTR init_rwsem(&ii->xattr_sem); #endif - address_space_init_once(&ii->i_btnode_cache); - ii->i_bmap = &ii->i_bmap_data; inode_init_once(&ii->vfs_inode); } diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index d154dcfe06af..90e3dad8ee45 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -1746,7 +1746,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) { set_buffer_dirty(bh); } while ((bh = bh->b_this_page) != head); spin_unlock(&mapping->private_lock); - block_dirty_folio(mapping, page_folio(page)); + filemap_dirty_folio(mapping, page_folio(page)); if (unlikely(buffers_to_free)) { do { bh = buffers_to_free->b_this_page; diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 273f65e0aaba..0b6f551a342a 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -337,7 +337,6 @@ void ocfs2_unlock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex) /* Read information header from global quota file */ int ocfs2_global_read_info(struct super_block *sb, int type) { - struct inode *gqinode = NULL; unsigned int ino[OCFS2_MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE, GROUP_QUOTA_SYSTEM_INODE }; struct ocfs2_global_disk_dqinfo dinfo; @@ -346,29 +345,31 @@ int ocfs2_global_read_info(struct super_block *sb, int type) u64 pcount; int status; + oinfo->dqi_gi.dqi_sb = sb; + oinfo->dqi_gi.dqi_type = type; + ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo); + oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk); + oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops; + oinfo->dqi_gqi_bh = NULL; + oinfo->dqi_gqi_count = 0; + /* Read global header */ - gqinode = ocfs2_get_system_file_inode(OCFS2_SB(sb), ino[type], + oinfo->dqi_gqinode = ocfs2_get_system_file_inode(OCFS2_SB(sb), ino[type], OCFS2_INVALID_SLOT); - if (!gqinode) { + if (!oinfo->dqi_gqinode) { mlog(ML_ERROR, "failed to get global quota inode (type=%d)\n", type); status = -EINVAL; goto out_err; } - oinfo->dqi_gi.dqi_sb = sb; - oinfo->dqi_gi.dqi_type = type; - oinfo->dqi_gi.dqi_entry_size = sizeof(struct ocfs2_global_disk_dqblk); - oinfo->dqi_gi.dqi_ops = &ocfs2_global_ops; - oinfo->dqi_gqi_bh = NULL; - oinfo->dqi_gqi_count = 0; - oinfo->dqi_gqinode = gqinode; + status = ocfs2_lock_global_qf(oinfo, 0); if (status < 0) { mlog_errno(status); goto out_err; } - status = ocfs2_extent_map_get_blocks(gqinode, 0, &oinfo->dqi_giblk, + status = ocfs2_extent_map_get_blocks(oinfo->dqi_gqinode, 0, &oinfo->dqi_giblk, &pcount, NULL); if (status < 0) goto out_unlock; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 0e4b16d4c037..b1a8b046f4c2 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -702,8 +702,6 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) info->dqi_priv = oinfo; oinfo->dqi_type = type; INIT_LIST_HEAD(&oinfo->dqi_chunk); - oinfo->dqi_gqinode = NULL; - ocfs2_qinfo_lock_res_init(&oinfo->dqi_gqlock, oinfo); oinfo->dqi_rec = NULL; oinfo->dqi_lqi_bh = NULL; oinfo->dqi_libh = NULL; diff --git a/fs/pipe.c b/fs/pipe.c index 9648ac15164a..e140ea150bbb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; - pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer), + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { @@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); - kvfree(pipe->bufs); + kfree(pipe->bufs); kfree(pipe); } @@ -1264,7 +1264,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) if (nr_slots < n) return -EBUSY; - bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT); + bufs = kcalloc(nr_slots, sizeof(*bufs), + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; @@ -1291,7 +1292,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) head = n; tail = 0; - kvfree(pipe->bufs); + kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 80acb6885cf9..962d32468eb4 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -759,9 +759,14 @@ static void posix_acl_fix_xattr_userns( } void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, @@ -769,9 +774,14 @@ void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, } void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c index 6d8d4bf20837..2e244ada1f97 100644 --- a/fs/proc/bootconfig.c +++ b/fs/proc/bootconfig.c @@ -32,6 +32,8 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size) int ret = 0; key = kzalloc(XBC_KEYLEN_MAX, GFP_KERNEL); + if (!key) + return -ENOMEM; xbc_for_each_key_value(leaf, val) { ret = xbc_node_compose_key(leaf, key, XBC_KEYLEN_MAX); diff --git a/fs/read_write.c b/fs/read_write.c index dc5000173b80..e643aec2b0ef 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1630,7 +1630,6 @@ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) if (!*count) return 0; - /* FIXME: this is for backwards compatibility with 2.4 */ if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); diff --git a/fs/seq_file.c b/fs/seq_file.c index f8e1f4ee87ff..7ab8a58c29b6 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -554,9 +554,9 @@ int seq_dentry(struct seq_file *m, struct dentry *dentry, const char *esc) } EXPORT_SYMBOL(seq_dentry); -static void *single_start(struct seq_file *p, loff_t *pos) +void *single_start(struct seq_file *p, loff_t *pos) { - return NULL + (*pos == 0); + return *pos ? NULL : SEQ_START_TOKEN; } static void *single_next(struct seq_file *p, void *v, loff_t *pos) diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smbfs_common/smb2pdu.h index 38b8fc514860..0507aecfc669 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smbfs_common/smb2pdu.h @@ -61,6 +61,40 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 /* + * Size of the session key (crypto key encrypted with the password + */ +#define SMB2_NTLMV2_SESSKEY_SIZE 16 +#define SMB2_SIGNATURE_SIZE 16 +#define SMB2_HMACSHA256_SIZE 32 +#define SMB2_CMACAES_SIZE 16 +#define SMB3_GCM128_CRYPTKEY_SIZE 16 +#define SMB3_GCM256_CRYPTKEY_SIZE 32 + +/* + * Size of the smb3 encryption/decryption keys + * This size is big enough to store any cipher key types. + */ +#define SMB3_ENC_DEC_KEY_SIZE 32 + +/* + * Size of the smb3 signing key + */ +#define SMB3_SIGN_KEY_SIZE 16 + +#define CIFS_CLIENT_CHALLENGE_SIZE 8 + +/* Maximum buffer size value we can send with 1 credit */ +#define SMB2_MAX_BUFFER_SIZE 65536 + +/* + * The default wsize is 1M for SMB2 (and for some CIFS cases). + * find_get_pages seems to return a maximum of 256 + * pages in a single call. With PAGE_SIZE == 4k, this means we can + * fill a single wsize request with a single call. + */ +#define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024) + +/* * SMB2 Header Definition * * "MBZ" : Must be Zero @@ -88,6 +122,15 @@ #define SMB2_FLAGS_DFS_OPERATIONS cpu_to_le32(0x10000000) #define SMB2_FLAGS_REPLAY_OPERATION cpu_to_le32(0x20000000) /* SMB3 & up */ +/* + * Definitions for SMB2 Protocol Data Units (network frames) + * + * See MS-SMB2.PDF specification for protocol details. + * The Naming convention is the lower case version of the SMB2 + * command code name for the struct. Note that structures must be packed. + * + */ + /* See MS-SMB2 section 2.2.1 */ struct smb2_hdr { __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */ @@ -115,6 +158,18 @@ struct smb2_pdu { __le16 StructureSize2; /* size of wct area (varies, request specific) */ } __packed; +#define SMB2_ERROR_STRUCTURE_SIZE2 9 +#define SMB2_ERROR_STRUCTURE_SIZE2_LE cpu_to_le16(SMB2_ERROR_STRUCTURE_SIZE2) + +struct smb2_err_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; + __u8 ErrorContextCount; + __u8 Reserved; + __le32 ByteCount; /* even if zero, at least one byte follows */ + __u8 ErrorData[1]; /* variable length */ +} __packed; + #define SMB3_AES_CCM_NONCE 11 #define SMB3_AES_GCM_NONCE 12 @@ -608,8 +663,8 @@ struct smb2_close_req { __le16 StructureSize; /* Must be 24 */ __le16 Flags; __le32 Reserved; - __le64 PersistentFileId; /* opaque endianness */ - __le64 VolatileFileId; /* opaque endianness */ + __u64 PersistentFileId; /* opaque endianness */ + __u64 VolatileFileId; /* opaque endianness */ } __packed; /* @@ -653,8 +708,8 @@ struct smb2_read_req { __u8 Flags; /* MBZ unless SMB3.02 or later */ __le32 Length; __le64 Offset; - __le64 PersistentFileId; - __le64 VolatileFileId; + __u64 PersistentFileId; + __u64 VolatileFileId; __le32 MinimumCount; __le32 Channel; /* MBZ except for SMB3 or later */ __le32 RemainingBytes; @@ -692,8 +747,8 @@ struct smb2_write_req { __le16 DataOffset; /* offset from start of SMB2 header to write data */ __le32 Length; __le64 Offset; - __le64 PersistentFileId; /* opaque endianness */ - __le64 VolatileFileId; /* opaque endianness */ + __u64 PersistentFileId; /* opaque endianness */ + __u64 VolatileFileId; /* opaque endianness */ __le32 Channel; /* MBZ unless SMB3.02 or later */ __le32 RemainingBytes; __le16 WriteChannelInfoOffset; @@ -722,8 +777,8 @@ struct smb2_flush_req { __le16 StructureSize; /* Must be 24 */ __le16 Reserved1; __le32 Reserved2; - __le64 PersistentFileId; - __le64 VolatileFileId; + __u64 PersistentFileId; + __u64 VolatileFileId; } __packed; struct smb2_flush_rsp { @@ -732,6 +787,123 @@ struct smb2_flush_rsp { __le16 Reserved; } __packed; +#define SMB2_LOCKFLAG_SHARED 0x0001 +#define SMB2_LOCKFLAG_EXCLUSIVE 0x0002 +#define SMB2_LOCKFLAG_UNLOCK 0x0004 +#define SMB2_LOCKFLAG_FAIL_IMMEDIATELY 0x0010 +#define SMB2_LOCKFLAG_MASK 0x0007 + +struct smb2_lock_element { + __le64 Offset; + __le64 Length; + __le32 Flags; + __le32 Reserved; +} __packed; + +struct smb2_lock_req { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 48 */ + __le16 LockCount; + /* + * The least significant four bits are the index, the other 28 bits are + * the lock sequence number (0 to 64). See MS-SMB2 2.2.26 + */ + __le32 LockSequenceNumber; + __u64 PersistentFileId; + __u64 VolatileFileId; + /* Followed by at least one */ + struct smb2_lock_element locks[1]; +} __packed; + +struct smb2_lock_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 4 */ + __le16 Reserved; +} __packed; + +struct smb2_echo_req { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 4 */ + __u16 Reserved; +} __packed; + +struct smb2_echo_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 4 */ + __u16 Reserved; +} __packed; + +/* + * Valid FileInformation classes for query directory + * + * Note that these are a subset of the (file) QUERY_INFO levels defined + * later in this file (but since QUERY_DIRECTORY uses equivalent numbers + * we do not redefine them here) + * + * FileDirectoryInfomation 0x01 + * FileFullDirectoryInformation 0x02 + * FileIdFullDirectoryInformation 0x26 + * FileBothDirectoryInformation 0x03 + * FileIdBothDirectoryInformation 0x25 + * FileNamesInformation 0x0C + * FileIdExtdDirectoryInformation 0x3C + */ + +/* search (query_directory) Flags field */ +#define SMB2_RESTART_SCANS 0x01 +#define SMB2_RETURN_SINGLE_ENTRY 0x02 +#define SMB2_INDEX_SPECIFIED 0x04 +#define SMB2_REOPEN 0x10 + +struct smb2_query_directory_req { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 33 */ + __u8 FileInformationClass; + __u8 Flags; + __le32 FileIndex; + __u64 PersistentFileId; + __u64 VolatileFileId; + __le16 FileNameOffset; + __le16 FileNameLength; + __le32 OutputBufferLength; + __u8 Buffer[1]; +} __packed; + +struct smb2_query_directory_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 9 */ + __le16 OutputBufferOffset; + __le32 OutputBufferLength; + __u8 Buffer[1]; +} __packed; + +/* + * Maximum number of iovs we need for a set-info request. + * The largest one is rename/hardlink + * [0] : struct smb2_set_info_req + smb2_file_[rename|link]_info + * [1] : path + * [2] : compound padding + */ +#define SMB2_SET_INFO_IOV_SIZE 3 + +struct smb2_set_info_req { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 33 */ + __u8 InfoType; + __u8 FileInfoClass; + __le32 BufferLength; + __le16 BufferOffset; + __u16 Reserved; + __le32 AdditionalInformation; + __u64 PersistentFileId; + __u64 VolatileFileId; + __u8 Buffer[1]; +} __packed; + +struct smb2_set_info_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 2 */ +} __packed; /* * SMB2_NOTIFY See MS-SMB2 section 2.2.35 @@ -769,8 +941,8 @@ struct smb2_change_notify_req { __le16 StructureSize; __le16 Flags; __le32 OutputBufferLength; - __le64 PersistentFileId; /* opaque endianness */ - __le64 VolatileFileId; /* opaque endianness */ + __u64 PersistentFileId; /* opaque endianness */ + __u64 VolatileFileId; /* opaque endianness */ __le32 CompletionFilter; __u32 Reserved; } __packed; @@ -978,12 +1150,455 @@ struct smb2_create_rsp { __le64 EndofFile; __le32 FileAttributes; __le32 Reserved2; - __le64 PersistentFileId; - __le64 VolatileFileId; + __u64 PersistentFileId; + __u64 VolatileFileId; __le32 CreateContextsOffset; __le32 CreateContextsLength; __u8 Buffer[1]; } __packed; +struct create_posix { + struct create_context ccontext; + __u8 Name[16]; + __le32 Mode; + __u32 Reserved; +} __packed; + +#define SMB2_LEASE_NONE_LE cpu_to_le32(0x00) +#define SMB2_LEASE_READ_CACHING_LE cpu_to_le32(0x01) +#define SMB2_LEASE_HANDLE_CACHING_LE cpu_to_le32(0x02) +#define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04) + +#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) + +#define SMB2_LEASE_KEY_SIZE 16 + +struct lease_context { + __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; + __le32 LeaseState; + __le32 LeaseFlags; + __le64 LeaseDuration; +} __packed; + +struct lease_context_v2 { + __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; + __le32 LeaseState; + __le32 LeaseFlags; + __le64 LeaseDuration; + __u8 ParentLeaseKey[SMB2_LEASE_KEY_SIZE]; + __le16 Epoch; + __le16 Reserved; +} __packed; + +struct create_lease { + struct create_context ccontext; + __u8 Name[8]; + struct lease_context lcontext; +} __packed; + +struct create_lease_v2 { + struct create_context ccontext; + __u8 Name[8]; + struct lease_context_v2 lcontext; + __u8 Pad[4]; +} __packed; + +/* See MS-SMB2 2.2.31 and 2.2.32 */ +struct smb2_ioctl_req { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 57 */ + __le16 Reserved; /* offset from start of SMB2 header to write data */ + __le32 CtlCode; + __u64 PersistentFileId; + __u64 VolatileFileId; + __le32 InputOffset; /* Reserved MBZ */ + __le32 InputCount; + __le32 MaxInputResponse; + __le32 OutputOffset; + __le32 OutputCount; + __le32 MaxOutputResponse; + __le32 Flags; + __le32 Reserved2; + __u8 Buffer[]; +} __packed; + +struct smb2_ioctl_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 49 */ + __le16 Reserved; + __le32 CtlCode; + __u64 PersistentFileId; + __u64 VolatileFileId; + __le32 InputOffset; /* Reserved MBZ */ + __le32 InputCount; + __le32 OutputOffset; + __le32 OutputCount; + __le32 Flags; + __le32 Reserved2; + __u8 Buffer[]; +} __packed; + +/* this goes in the ioctl buffer when doing FSCTL_SET_ZERO_DATA */ +struct file_zero_data_information { + __le64 FileOffset; + __le64 BeyondFinalZero; +} __packed; + +/* Reparse structures - see MS-FSCC 2.1.2 */ + +/* struct fsctl_reparse_info_req is empty, only response structs (see below) */ +struct reparse_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __u8 DataBuffer[]; /* Variable Length */ +} __packed; + +struct reparse_guid_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __u8 ReparseGuid[16]; + __u8 DataBuffer[]; /* Variable Length */ +} __packed; + +struct reparse_mount_point_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __u8 PathBuffer[]; /* Variable Length */ +} __packed; + +#define SYMLINK_FLAG_RELATIVE 0x00000001 + +struct reparse_symlink_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __le32 Flags; + __u8 PathBuffer[]; /* Variable Length */ +} __packed; + +/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */ + +struct validate_negotiate_info_req { + __le32 Capabilities; + __u8 Guid[SMB2_CLIENT_GUID_SIZE]; + __le16 SecurityMode; + __le16 DialectCount; + __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */ +} __packed; + +struct validate_negotiate_info_rsp { + __le32 Capabilities; + __u8 Guid[SMB2_CLIENT_GUID_SIZE]; + __le16 SecurityMode; + __le16 Dialect; /* Dialect in use for the connection */ +} __packed; + +struct duplicate_extents_to_file { + __u64 PersistentFileHandle; /* source file handle, opaque endianness */ + __u64 VolatileFileHandle; + __le64 SourceFileOffset; + __le64 TargetFileOffset; + __le64 ByteCount; /* Bytes to be copied */ +} __packed; + +/* Possible InfoType values */ +#define SMB2_O_INFO_FILE 0x01 +#define SMB2_O_INFO_FILESYSTEM 0x02 +#define SMB2_O_INFO_SECURITY 0x03 +#define SMB2_O_INFO_QUOTA 0x04 + +/* SMB2 Query Info see MS-SMB2 (2.2.37) or MS-DTYP */ + +/* List of QUERY INFO levels (those also valid for QUERY_DIR are noted below */ +#define FILE_DIRECTORY_INFORMATION 1 /* also for QUERY_DIR */ +#define FILE_FULL_DIRECTORY_INFORMATION 2 /* also for QUERY_DIR */ +#define FILE_BOTH_DIRECTORY_INFORMATION 3 /* also for QUERY_DIR */ +#define FILE_BASIC_INFORMATION 4 +#define FILE_STANDARD_INFORMATION 5 +#define FILE_INTERNAL_INFORMATION 6 +#define FILE_EA_INFORMATION 7 +#define FILE_ACCESS_INFORMATION 8 +#define FILE_NAME_INFORMATION 9 +#define FILE_RENAME_INFORMATION 10 +#define FILE_LINK_INFORMATION 11 +#define FILE_NAMES_INFORMATION 12 /* also for QUERY_DIR */ +#define FILE_DISPOSITION_INFORMATION 13 +#define FILE_POSITION_INFORMATION 14 +#define FILE_FULL_EA_INFORMATION 15 +#define FILE_MODE_INFORMATION 16 +#define FILE_ALIGNMENT_INFORMATION 17 +#define FILE_ALL_INFORMATION 18 +#define FILE_ALLOCATION_INFORMATION 19 +#define FILE_END_OF_FILE_INFORMATION 20 +#define FILE_ALTERNATE_NAME_INFORMATION 21 +#define FILE_STREAM_INFORMATION 22 +#define FILE_PIPE_INFORMATION 23 +#define FILE_PIPE_LOCAL_INFORMATION 24 +#define FILE_PIPE_REMOTE_INFORMATION 25 +#define FILE_MAILSLOT_QUERY_INFORMATION 26 +#define FILE_MAILSLOT_SET_INFORMATION 27 +#define FILE_COMPRESSION_INFORMATION 28 +#define FILE_OBJECT_ID_INFORMATION 29 +/* Number 30 not defined in documents */ +#define FILE_MOVE_CLUSTER_INFORMATION 31 +#define FILE_QUOTA_INFORMATION 32 +#define FILE_REPARSE_POINT_INFORMATION 33 +#define FILE_NETWORK_OPEN_INFORMATION 34 +#define FILE_ATTRIBUTE_TAG_INFORMATION 35 +#define FILE_TRACKING_INFORMATION 36 +#define FILEID_BOTH_DIRECTORY_INFORMATION 37 /* also for QUERY_DIR */ +#define FILEID_FULL_DIRECTORY_INFORMATION 38 /* also for QUERY_DIR */ +#define FILE_VALID_DATA_LENGTH_INFORMATION 39 +#define FILE_SHORT_NAME_INFORMATION 40 +#define FILE_SFIO_RESERVE_INFORMATION 44 +#define FILE_SFIO_VOLUME_INFORMATION 45 +#define FILE_HARD_LINK_INFORMATION 46 +#define FILE_NORMALIZED_NAME_INFORMATION 48 +#define FILEID_GLOBAL_TX_DIRECTORY_INFORMATION 50 +#define FILE_STANDARD_LINK_INFORMATION 54 +#define FILE_ID_INFORMATION 59 +#define FILE_ID_EXTD_DIRECTORY_INFORMATION 60 /* also for QUERY_DIR */ +/* Used for Query Info and Find File POSIX Info for SMB3.1.1 and SMB1 */ +#define SMB_FIND_FILE_POSIX_INFO 0x064 + +/* Security info type additionalinfo flags. */ +#define OWNER_SECINFO 0x00000001 +#define GROUP_SECINFO 0x00000002 +#define DACL_SECINFO 0x00000004 +#define SACL_SECINFO 0x00000008 +#define LABEL_SECINFO 0x00000010 +#define ATTRIBUTE_SECINFO 0x00000020 +#define SCOPE_SECINFO 0x00000040 +#define BACKUP_SECINFO 0x00010000 +#define UNPROTECTED_SACL_SECINFO 0x10000000 +#define UNPROTECTED_DACL_SECINFO 0x20000000 +#define PROTECTED_SACL_SECINFO 0x40000000 +#define PROTECTED_DACL_SECINFO 0x80000000 + +/* Flags used for FileFullEAinfo */ +#define SL_RESTART_SCAN 0x00000001 +#define SL_RETURN_SINGLE_ENTRY 0x00000002 +#define SL_INDEX_SPECIFIED 0x00000004 + +struct smb2_query_info_req { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 41 */ + __u8 InfoType; + __u8 FileInfoClass; + __le32 OutputBufferLength; + __le16 InputBufferOffset; + __u16 Reserved; + __le32 InputBufferLength; + __le32 AdditionalInformation; + __le32 Flags; + __u64 PersistentFileId; + __u64 VolatileFileId; + __u8 Buffer[1]; +} __packed; + +struct smb2_query_info_rsp { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 9 */ + __le16 OutputBufferOffset; + __le32 OutputBufferLength; + __u8 Buffer[1]; +} __packed; + +/* + * PDU query infolevel structure definitions + */ + +struct file_allocated_range_buffer { + __le64 file_offset; + __le64 length; +} __packed; + +struct smb2_file_internal_info { + __le64 IndexNumber; +} __packed; /* level 6 Query */ + +struct smb2_file_rename_info { /* encoding of request for level 10 */ + __u8 ReplaceIfExists; /* 1 = replace existing target with new */ + /* 0 = fail if target already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + char FileName[]; /* New name to be assigned */ + /* padding - overall struct size must be >= 24 so filename + pad >= 6 */ +} __packed; /* level 10 Set */ + +struct smb2_file_link_info { /* encoding of request for level 11 */ + __u8 ReplaceIfExists; /* 1 = replace existing link with new */ + /* 0 = fail if link already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + char FileName[]; /* Name to be assigned to new link */ +} __packed; /* level 11 Set */ + +/* + * This level 18, although with struct with same name is different from cifs + * level 0x107. Level 0x107 has an extra u64 between AccessFlags and + * CurrentByteOffset. + */ +struct smb2_file_all_info { /* data block encoding of response to level 18 */ + __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le32 Attributes; + __u32 Pad1; /* End of FILE_BASIC_INFO_INFO equivalent */ + __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */ + __le64 EndOfFile; /* size ie offset to first free byte in file */ + __le32 NumberOfLinks; /* hard links */ + __u8 DeletePending; + __u8 Directory; + __u16 Pad2; /* End of FILE_STANDARD_INFO equivalent */ + __le64 IndexNumber; + __le32 EASize; + __le32 AccessFlags; + __le64 CurrentByteOffset; + __le32 Mode; + __le32 AlignmentRequirement; + __le32 FileNameLength; + char FileName[1]; +} __packed; /* level 18 Query */ + +struct smb2_file_eof_info { /* encoding of request for level 10 */ + __le64 EndOfFile; /* new end of file value */ +} __packed; /* level 20 Set */ + +/* Level 100 query info */ +struct smb311_posix_qinfo { + __le64 CreationTime; + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le64 EndOfFile; + __le64 AllocationSize; + __le32 DosAttributes; + __le64 Inode; + __le32 DeviceId; + __le32 Zero; + /* beginning of POSIX Create Context Response */ + __le32 HardLinks; + __le32 ReparseTag; + __le32 Mode; + u8 Sids[]; + /* + * var sized owner SID + * var sized group SID + * le32 filenamelength + * u8 filename[] + */ +} __packed; + +/* File System Information Classes */ +#define FS_VOLUME_INFORMATION 1 /* Query */ +#define FS_LABEL_INFORMATION 2 /* Set */ +#define FS_SIZE_INFORMATION 3 /* Query */ +#define FS_DEVICE_INFORMATION 4 /* Query */ +#define FS_ATTRIBUTE_INFORMATION 5 /* Query */ +#define FS_CONTROL_INFORMATION 6 /* Query, Set */ +#define FS_FULL_SIZE_INFORMATION 7 /* Query */ +#define FS_OBJECT_ID_INFORMATION 8 /* Query, Set */ +#define FS_DRIVER_PATH_INFORMATION 9 /* Query */ +#define FS_SECTOR_SIZE_INFORMATION 11 /* SMB3 or later. Query */ +#define FS_POSIX_INFORMATION 100 /* SMB3.1.1 POSIX. Query */ + +struct smb2_fs_full_size_info { + __le64 TotalAllocationUnits; + __le64 CallerAvailableAllocationUnits; + __le64 ActualAvailableAllocationUnits; + __le32 SectorsPerAllocationUnit; + __le32 BytesPerSector; +} __packed; + +#define SSINFO_FLAGS_ALIGNED_DEVICE 0x00000001 +#define SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE 0x00000002 +#define SSINFO_FLAGS_NO_SEEK_PENALTY 0x00000004 +#define SSINFO_FLAGS_TRIM_ENABLED 0x00000008 + +/* sector size info struct */ +struct smb3_fs_ss_info { + __le32 LogicalBytesPerSector; + __le32 PhysicalBytesPerSectorForAtomicity; + __le32 PhysicalBytesPerSectorForPerf; + __le32 FSEffPhysicalBytesPerSectorForAtomicity; + __le32 Flags; + __le32 ByteOffsetForSectorAlignment; + __le32 ByteOffsetForPartitionAlignment; +} __packed; + +/* File System Control Information */ +struct smb2_fs_control_info { + __le64 FreeSpaceStartFiltering; + __le64 FreeSpaceThreshold; + __le64 FreeSpaceStopFiltering; + __le64 DefaultQuotaThreshold; + __le64 DefaultQuotaLimit; + __le32 FileSystemControlFlags; + __le32 Padding; +} __packed; + +/* volume info struct - see MS-FSCC 2.5.9 */ +#define MAX_VOL_LABEL_LEN 32 +struct smb3_fs_vol_info { + __le64 VolumeCreationTime; + __u32 VolumeSerialNumber; + __le32 VolumeLabelLength; /* includes trailing null */ + __u8 SupportsObjects; /* True if eg like NTFS, supports objects */ + __u8 Reserved; + __u8 VolumeLabel[]; /* variable len */ +} __packed; + +/* See MS-SMB2 2.2.23 through 2.2.25 */ +struct smb2_oplock_break { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 24 */ + __u8 OplockLevel; + __u8 Reserved; + __le32 Reserved2; + __u64 PersistentFid; + __u64 VolatileFid; +} __packed; + +#define SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED cpu_to_le32(0x01) + +struct smb2_lease_break { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 44 */ + __le16 Epoch; + __le32 Flags; + __u8 LeaseKey[16]; + __le32 CurrentLeaseState; + __le32 NewLeaseState; + __le32 BreakReason; + __le32 AccessMaskHint; + __le32 ShareMaskHint; +} __packed; + +struct smb2_lease_ack { + struct smb2_hdr hdr; + __le16 StructureSize; /* Must be 36 */ + __le16 Reserved; + __le32 Flags; + __u8 LeaseKey[16]; + __le32 LeaseState; + __le64 LeaseDuration; +} __packed; +#define OP_BREAK_STRUCT_SIZE_20 24 +#define OP_BREAK_STRUCT_SIZE_21 36 #endif /* _COMMON_SMB2PDU_H */ diff --git a/fs/stat.c b/fs/stat.c index 7f734be0e57e..5c2c94464e8b 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -348,9 +348,6 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev(x),true) -#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) - #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif @@ -359,7 +356,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; - if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -367,7 +366,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) #endif INIT_STRUCT_STAT_PADDING(tmp); - tmp.st_dev = encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -377,7 +376,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -665,11 +664,13 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -679,7 +680,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = old_encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 42dcf96881b6..a12ac0356c69 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -703,19 +703,6 @@ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) ktype = get_ktype(kobj); if (ktype) { - struct attribute **kattr; - - /* - * Change owner of the default attributes associated with the - * ktype of @kobj. - */ - for (kattr = ktype->default_attrs; kattr && *kattr; kattr++) { - error = sysfs_file_change_owner(kobj, (*kattr)->name, - kuid, kgid); - if (error) - return error; - } - /* * Change owner of the default groups associated with the * ktype of @kobj. diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index dbe72f664abf..86151889548e 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -349,20 +349,97 @@ out_budg: return err; } -static int do_tmpfile(struct inode *dir, struct dentry *dentry, - umode_t mode, struct inode **whiteout) +static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) +{ + int err; + umode_t mode = S_IFCHR | WHITEOUT_MODE; + struct inode *inode; + struct ubifs_info *c = dir->i_sb->s_fs_info; + struct fscrypt_name nm; + + /* + * Create an inode('nlink = 1') for whiteout without updating journal, + * let ubifs_jnl_rename() store it on flash to complete rename whiteout + * atomically. + */ + + dbg_gen("dent '%pd', mode %#hx in dir ino %lu", + dentry, mode, dir->i_ino); + + err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); + if (err) + return ERR_PTR(err); + + inode = ubifs_new_inode(c, dir, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_free; + } + + init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); + ubifs_assert(c, inode->i_op == &ubifs_file_inode_operations); + + err = ubifs_init_security(dir, inode, &dentry->d_name); + if (err) + goto out_inode; + + /* The dir size is updated by do_rename. */ + insert_inode_hash(inode); + + return inode; + +out_inode: + make_bad_inode(inode); + iput(inode); +out_free: + fscrypt_free_filename(&nm); + ubifs_err(c, "cannot create whiteout file, error %d", err); + return ERR_PTR(err); +} + +/** + * lock_2_inodes - a wrapper for locking two UBIFS inodes. + * @inode1: first inode + * @inode2: second inode + * + * We do not implement any tricks to guarantee strict lock ordering, because + * VFS has already done it for us on the @i_mutex. So this is just a simple + * wrapper function. + */ +static void lock_2_inodes(struct inode *inode1, struct inode *inode2) +{ + mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1); + mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2); +} + +/** + * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes. + * @inode1: first inode + * @inode2: second inode + */ +static void unlock_2_inodes(struct inode *inode1, struct inode *inode2) +{ + mutex_unlock(&ubifs_inode(inode2)->ui_mutex); + mutex_unlock(&ubifs_inode(inode1)->ui_mutex); +} + +static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; - struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1}; + struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, + .dirtied_ino = 1}; struct ubifs_budget_req ino_req = { .dirtied_ino = 1 }; - struct ubifs_inode *ui, *dir_ui = ubifs_inode(dir); + struct ubifs_inode *ui; int err, instantiated = 0; struct fscrypt_name nm; /* - * Budget request settings: new dirty inode, new direntry, - * budget for dirtied inode will be released via writeback. + * Budget request settings: new inode, new direntry, changing the + * parent directory inode. + * Allocate budget separately for new dirtied inode, the budget will + * be released via writeback. */ dbg_gen("dent '%pd', mode %#hx in dir ino %lu", @@ -392,42 +469,30 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry, } ui = ubifs_inode(inode); - if (whiteout) { - init_special_inode(inode, inode->i_mode, WHITEOUT_DEV); - ubifs_assert(c, inode->i_op == &ubifs_file_inode_operations); - } - err = ubifs_init_security(dir, inode, &dentry->d_name); if (err) goto out_inode; mutex_lock(&ui->ui_mutex); insert_inode_hash(inode); - - if (whiteout) { - mark_inode_dirty(inode); - drop_nlink(inode); - *whiteout = inode; - } else { - d_tmpfile(dentry, inode); - } + d_tmpfile(dentry, inode); ubifs_assert(c, ui->dirty); instantiated = 1; mutex_unlock(&ui->ui_mutex); - mutex_lock(&dir_ui->ui_mutex); + lock_2_inodes(dir, inode); err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0); if (err) goto out_cancel; - mutex_unlock(&dir_ui->ui_mutex); + unlock_2_inodes(dir, inode); ubifs_release_budget(c, &req); return 0; out_cancel: - mutex_unlock(&dir_ui->ui_mutex); + unlock_2_inodes(dir, inode); out_inode: make_bad_inode(inode); if (!instantiated) @@ -441,12 +506,6 @@ out_budg: return err; } -static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, - struct dentry *dentry, umode_t mode) -{ - return do_tmpfile(dir, dentry, mode, NULL); -} - /** * vfs_dent_type - get VFS directory entry type. * @type: UBIFS directory entry type @@ -660,32 +719,6 @@ static int ubifs_dir_release(struct inode *dir, struct file *file) return 0; } -/** - * lock_2_inodes - a wrapper for locking two UBIFS inodes. - * @inode1: first inode - * @inode2: second inode - * - * We do not implement any tricks to guarantee strict lock ordering, because - * VFS has already done it for us on the @i_mutex. So this is just a simple - * wrapper function. - */ -static void lock_2_inodes(struct inode *inode1, struct inode *inode2) -{ - mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1); - mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2); -} - -/** - * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes. - * @inode1: first inode - * @inode2: second inode - */ -static void unlock_2_inodes(struct inode *inode1, struct inode *inode2) -{ - mutex_unlock(&ubifs_inode(inode2)->ui_mutex); - mutex_unlock(&ubifs_inode(inode1)->ui_mutex); -} - static int ubifs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { @@ -949,7 +982,8 @@ static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct ubifs_inode *dir_ui = ubifs_inode(dir); struct ubifs_info *c = dir->i_sb->s_fs_info; int err, sz_change; - struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1 }; + struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, + .dirtied_ino = 1}; struct fscrypt_name nm; /* @@ -1264,17 +1298,19 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, .dirtied_ino = 3 }; struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; + struct ubifs_budget_req wht_req; struct timespec64 time; unsigned int saved_nlink; struct fscrypt_name old_nm, new_nm; /* - * Budget request settings: deletion direntry, new direntry, removing - * the old inode, and changing old and new parent directory inodes. + * Budget request settings: + * req: deletion direntry, new direntry, removing the old inode, + * and changing old and new parent directory inodes. + * + * wht_req: new whiteout inode for RENAME_WHITEOUT. * - * However, this operation also marks the target inode as dirty and - * does not write it, so we allocate budget for the target inode - * separately. + * ino_req: marks the target inode as dirty and does not write it. */ dbg_gen("dent '%pd' ino %lu in dir ino %lu to dent '%pd' in dir ino %lu flags 0x%x", @@ -1331,20 +1367,44 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_release; } - err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout); - if (err) { + /* + * The whiteout inode without dentry is pinned in memory, + * umount won't happen during rename process because we + * got parent dentry. + */ + whiteout = create_whiteout(old_dir, old_dentry); + if (IS_ERR(whiteout)) { + err = PTR_ERR(whiteout); kfree(dev); goto out_release; } - spin_lock(&whiteout->i_lock); - whiteout->i_state |= I_LINKABLE; - spin_unlock(&whiteout->i_lock); - whiteout_ui = ubifs_inode(whiteout); whiteout_ui->data = dev; whiteout_ui->data_len = ubifs_encode_dev(dev, MKDEV(0, 0)); ubifs_assert(c, !whiteout_ui->dirty); + + memset(&wht_req, 0, sizeof(struct ubifs_budget_req)); + wht_req.new_ino = 1; + wht_req.new_ino_d = ALIGN(whiteout_ui->data_len, 8); + /* + * To avoid deadlock between space budget (holds ui_mutex and + * waits wb work) and writeback work(waits ui_mutex), do space + * budget before ubifs inodes locked. + */ + err = ubifs_budget_space(c, &wht_req); + if (err) { + /* + * Whiteout inode can not be written on flash by + * ubifs_jnl_write_inode(), because it's neither + * dirty nor zero-nlink. + */ + iput(whiteout); + goto out_release; + } + + /* Add the old_dentry size to the old_dir size. */ + old_sz -= CALC_DENT_SIZE(fname_len(&old_nm)); } lock_4_inodes(old_dir, new_dir, new_inode, whiteout); @@ -1416,29 +1476,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, sync = IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir); if (unlink && IS_SYNC(new_inode)) sync = 1; - } - - if (whiteout) { - struct ubifs_budget_req wht_req = { .dirtied_ino = 1, - .dirtied_ino_d = \ - ALIGN(ubifs_inode(whiteout)->data_len, 8) }; - - err = ubifs_budget_space(c, &wht_req); - if (err) { - kfree(whiteout_ui->data); - whiteout_ui->data_len = 0; - iput(whiteout); - goto out_release; - } - - inc_nlink(whiteout); - mark_inode_dirty(whiteout); - - spin_lock(&whiteout->i_lock); - whiteout->i_state &= ~I_LINKABLE; - spin_unlock(&whiteout->i_lock); - - iput(whiteout); + /* + * S_SYNC flag of whiteout inherits from the old_dir, and we + * have already checked the old dir inode. So there is no need + * to check whiteout. + */ } err = ubifs_jnl_rename(c, old_dir, old_inode, &old_nm, new_dir, @@ -1449,6 +1491,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); ubifs_release_budget(c, &req); + if (whiteout) { + ubifs_release_budget(c, &wht_req); + iput(whiteout); + } + mutex_lock(&old_inode_ui->ui_mutex); release = old_inode_ui->dirty; mark_inode_dirty_sync(old_inode); @@ -1457,11 +1504,16 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, if (release) ubifs_release_budget(c, &ino_req); if (IS_SYNC(old_inode)) - err = old_inode->i_sb->s_op->write_inode(old_inode, NULL); + /* + * Rename finished here. Although old inode cannot be updated + * on flash, old ctime is not a big problem, don't return err + * code to userspace. + */ + old_inode->i_sb->s_op->write_inode(old_inode, NULL); fscrypt_free_filename(&old_nm); fscrypt_free_filename(&new_nm); - return err; + return 0; out_cancel: if (unlink) { @@ -1482,11 +1534,11 @@ out_cancel: inc_nlink(old_dir); } } + unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); if (whiteout) { - drop_nlink(whiteout); + ubifs_release_budget(c, &wht_req); iput(whiteout); } - unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); out_release: ubifs_release_budget(c, &ino_req); ubifs_release_budget(c, &req); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 8a9ffc2d4167..0383fbdc95ff 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -570,7 +570,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, } if (!PagePrivate(page)) { - SetPagePrivate(page); + attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); __set_page_dirty_nobuffers(page); } @@ -947,7 +947,7 @@ static int do_writepage(struct page *page, int len) release_existing_page_budget(c); atomic_long_dec(&c->dirty_pg_cnt); - ClearPagePrivate(page); + detach_page_private(page); ClearPageChecked(page); kunmap(page); @@ -1304,7 +1304,7 @@ static void ubifs_invalidate_folio(struct folio *folio, size_t offset, release_existing_page_budget(c); atomic_long_dec(&c->dirty_pg_cnt); - folio_clear_private(folio); + folio_detach_private(folio); folio_clear_checked(folio); } @@ -1471,8 +1471,8 @@ static int ubifs_migrate_page(struct address_space *mapping, return rc; if (PagePrivate(page)) { - ClearPagePrivate(page); - SetPagePrivate(newpage); + detach_page_private(page); + attach_page_private(newpage, (void *)1); } if (mode != MIGRATE_SYNC_NO_COPY) @@ -1496,7 +1496,7 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) return 0; ubifs_assert(c, PagePrivate(page)); ubifs_assert(c, 0); - ClearPagePrivate(page); + detach_page_private(page); ClearPageChecked(page); return 1; } @@ -1567,7 +1567,7 @@ static vm_fault_t ubifs_vm_page_mkwrite(struct vm_fault *vmf) else { if (!PageChecked(page)) ubifs_convert_page_budget(c); - SetPagePrivate(page); + attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); __set_page_dirty_nobuffers(page); } diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 789a7813f3fa..1607a3c76681 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -854,16 +854,42 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) */ n = aligned_len >> c->max_write_shift; if (n) { - n <<= c->max_write_shift; + int m = n - 1; + dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum, wbuf->offs); - err = ubifs_leb_write(c, wbuf->lnum, buf + written, - wbuf->offs, n); + + if (m) { + /* '(n-1)<<c->max_write_shift < len' is always true. */ + m <<= c->max_write_shift; + err = ubifs_leb_write(c, wbuf->lnum, buf + written, + wbuf->offs, m); + if (err) + goto out; + wbuf->offs += m; + aligned_len -= m; + len -= m; + written += m; + } + + /* + * The non-written len of buf may be less than 'n' because + * parameter 'len' is not 8 bytes aligned, so here we read + * min(len, n) bytes from buf. + */ + n = 1 << c->max_write_shift; + memcpy(wbuf->buf, buf + written, min(len, n)); + if (n > len) { + ubifs_assert(c, n - len < 8); + ubifs_pad(c, wbuf->buf + len, n - len); + } + + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, n); if (err) goto out; wbuf->offs += n; aligned_len -= n; - len -= n; + len -= min(len, n); written += n; } diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index c6a863487780..71bcebe45f9c 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -108,7 +108,7 @@ static int setflags(struct inode *inode, int flags) struct ubifs_inode *ui = ubifs_inode(inode); struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_budget_req req = { .dirtied_ino = 1, - .dirtied_ino_d = ui->data_len }; + .dirtied_ino_d = ALIGN(ui->data_len, 8) }; err = ubifs_budget_space(c, &req); if (err) diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 8ea680dba61e..75dab0ae3939 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1207,9 +1207,9 @@ out_free: * @sync: non-zero if the write-buffer has to be synchronized * * This function implements the re-name operation which may involve writing up - * to 4 inodes and 2 directory entries. It marks the written inodes as clean - * and returns zero on success. In case of failure, a negative error code is - * returned. + * to 4 inodes(new inode, whiteout inode, old and new parent directory inodes) + * and 2 directory entries. It marks the written inodes as clean and returns + * zero on success. In case of failure, a negative error code is returned. */ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, const struct inode *old_inode, @@ -1222,14 +1222,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, void *p; union ubifs_key key; struct ubifs_dent_node *dent, *dent2; - int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0; + int err, dlen1, dlen2, ilen, wlen, lnum, offs, len, orphan_added = 0; int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ; int last_reference = !!(new_inode && new_inode->i_nlink == 0); int move = (old_dir != new_dir); - struct ubifs_inode *new_ui; + struct ubifs_inode *new_ui, *whiteout_ui; u8 hash_old_dir[UBIFS_HASH_ARR_SZ]; u8 hash_new_dir[UBIFS_HASH_ARR_SZ]; u8 hash_new_inode[UBIFS_HASH_ARR_SZ]; + u8 hash_whiteout_inode[UBIFS_HASH_ARR_SZ]; u8 hash_dent1[UBIFS_HASH_ARR_SZ]; u8 hash_dent2[UBIFS_HASH_ARR_SZ]; @@ -1249,9 +1250,20 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, } else ilen = 0; + if (whiteout) { + whiteout_ui = ubifs_inode(whiteout); + ubifs_assert(c, mutex_is_locked(&whiteout_ui->ui_mutex)); + ubifs_assert(c, whiteout->i_nlink == 1); + ubifs_assert(c, !whiteout_ui->dirty); + wlen = UBIFS_INO_NODE_SZ; + wlen += whiteout_ui->data_len; + } else + wlen = 0; + aligned_dlen1 = ALIGN(dlen1, 8); aligned_dlen2 = ALIGN(dlen2, 8); - len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8); + len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + + ALIGN(wlen, 8) + ALIGN(plen, 8); if (move) len += plen; @@ -1313,6 +1325,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, p += ALIGN(ilen, 8); } + if (whiteout) { + pack_inode(c, p, whiteout, 0); + err = ubifs_node_calc_hash(c, p, hash_whiteout_inode); + if (err) + goto out_release; + + p += ALIGN(wlen, 8); + } + if (!move) { pack_inode(c, p, old_dir, 1); err = ubifs_node_calc_hash(c, p, hash_old_dir); @@ -1352,6 +1373,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, if (new_inode) ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, new_inode->i_ino); + if (whiteout) + ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, + whiteout->i_ino); } release_head(c, BASEHD); @@ -1368,8 +1392,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, old_nm); if (err) goto out_ro; - - ubifs_delete_orphan(c, whiteout->i_ino); } else { err = ubifs_add_dirt(c, lnum, dlen2); if (err) @@ -1390,6 +1412,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, offs += ALIGN(ilen, 8); } + if (whiteout) { + ino_key_init(c, &key, whiteout->i_ino); + err = ubifs_tnc_add(c, &key, lnum, offs, wlen, + hash_whiteout_inode); + if (err) + goto out_ro; + offs += ALIGN(wlen, 8); + } + ino_key_init(c, &key, old_dir->i_ino); err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_old_dir); if (err) @@ -1410,6 +1441,11 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, new_ui->synced_i_size = new_ui->ui_size; spin_unlock(&new_ui->ui_lock); } + /* + * No need to mark whiteout inode clean. + * Whiteout doesn't have non-zero size, no need to update + * synced_i_size for whiteout_ui. + */ mark_inode_clean(c, ubifs_inode(old_dir)); if (move) mark_inode_clean(c, ubifs_inode(new_dir)); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index f55828c0a300..008fa46ef61e 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -381,7 +381,7 @@ struct ubifs_gced_idx_leb { * @ui_mutex exists for two main reasons. At first it prevents inodes from * being written back while UBIFS changing them, being in the middle of an VFS * operation. This way UBIFS makes sure the inode fields are consistent. For - * example, in 'ubifs_rename()' we change 3 inodes simultaneously, and + * example, in 'ubifs_rename()' we change 4 inodes simultaneously, and * write-back must not write any of them before we have finished. * * The second reason is budgeting - UBIFS has to budget all operations. If an diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 0cc87423de82..0e51c0025a16 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -33,7 +33,7 @@ $(obj)/utf8data.c: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE else $(obj)/utf8data.c: $(src)/utf8data.c_shipped FORCE - $(call if_changed,shipped) + $(call if_changed,copy) endif diff --git a/fs/verity/verify.c b/fs/verity/verify.c index 0adb970f4e73..14e2fb49cff5 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Data verification functions, i.e. hooks for ->readpages() + * Data verification functions, i.e. hooks for ->readahead() * * Copyright 2019 Google LLC */ @@ -214,7 +214,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_page); * that fail verification are set to the Error state. Verification is skipped * for pages already in the Error state, e.g. due to fscrypt decryption failure. * - * This is a helper function for use by the ->readpages() method of filesystems + * This is a helper function for use by the ->readahead() method of filesystems * that issue bios to read data directly into the page cache. Filesystems that * populate the page cache without issuing bios (e.g. non block-based * filesystems) must instead call fsverity_verify_page() directly on each page. diff --git a/fs/xattr.c b/fs/xattr.c index 5c8c5175b385..998045165916 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -569,7 +569,8 @@ setxattr(struct user_namespace *mnt_userns, struct dentry *d, } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size); + posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), + kvalue, size); } error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); @@ -667,7 +668,8 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d, if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error); + posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d), + kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 353e53b892e6..b52ed339727f 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -82,6 +82,24 @@ xfs_prealloc_blocks( } /* + * The number of blocks per AG that we withhold from xfs_mod_fdblocks to + * guarantee that we can refill the AGFL prior to allocating space in a nearly + * full AG. Although the the space described by the free space btrees, the + * blocks used by the freesp btrees themselves, and the blocks owned by the + * AGFL are counted in the ondisk fdblocks, it's a mistake to let the ondisk + * free space in the AG drop so low that the free space btrees cannot refill an + * empty AGFL up to the minimum level. Rather than grind through empty AGs + * until the fs goes down, we subtract this many AG blocks from the incore + * fdblocks to ensure user allocation does not overcommit the space the + * filesystem needs for the AGFLs. The rmap btree uses a per-AG reservation to + * withhold space from xfs_mod_fdblocks, so we do not account for that here. + */ +#define XFS_ALLOCBT_AGFL_RESERVE 4 + +/* + * Compute the number of blocks that we set aside to guarantee the ability to + * refill the AGFL and handle a full bmap btree split. + * * In order to avoid ENOSPC-related deadlock caused by out-of-order locking of * AGF buffer (PV 947395), we place constraints on the relationship among * actual allocations for data blocks, freelist blocks, and potential file data @@ -93,14 +111,14 @@ xfs_prealloc_blocks( * extents need to be actually allocated. To get around this, we explicitly set * aside a few blocks which will not be reserved in delayed allocation. * - * We need to reserve 4 fsbs _per AG_ for the freelist and 4 more to handle a - * potential split of the file's bmap btree. + * For each AG, we need to reserve enough blocks to replenish a totally empty + * AGFL and 4 more to handle a potential split of the file's bmap btree. */ unsigned int xfs_alloc_set_aside( struct xfs_mount *mp) { - return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4); + return mp->m_sb.sb_agcount * (XFS_ALLOCBT_AGFL_RESERVE + 4); } /* @@ -124,12 +142,12 @@ xfs_alloc_ag_max_usable( unsigned int blocks; blocks = XFS_BB_TO_FSB(mp, XFS_FSS_TO_BB(mp, 4)); /* ag headers */ - blocks += XFS_ALLOC_AGFL_RESERVE; + blocks += XFS_ALLOCBT_AGFL_RESERVE; blocks += 3; /* AGF, AGI btree root blocks */ if (xfs_has_finobt(mp)) blocks++; /* finobt root block */ if (xfs_has_rmapbt(mp)) - blocks++; /* rmap root block */ + blocks++; /* rmap root block */ if (xfs_has_reflink(mp)) blocks++; /* refcount root block */ diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 1c14a0b1abea..d4c057b764f9 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -88,7 +88,6 @@ typedef struct xfs_alloc_arg { #define XFS_ALLOC_NOBUSY (1 << 2)/* Busy extents not allowed */ /* freespace limit calculations */ -#define XFS_ALLOC_AGFL_RESERVE 4 unsigned int xfs_alloc_set_aside(struct xfs_mount *mp); unsigned int xfs_alloc_ag_max_usable(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_bio_io.c b/fs/xfs/xfs_bio_io.c index 32fa02945f73..ae4345b37621 100644 --- a/fs/xfs/xfs_bio_io.c +++ b/fs/xfs/xfs_bio_io.c @@ -9,39 +9,6 @@ static inline unsigned int bio_max_vecs(unsigned int count) return bio_max_segs(howmany(count, PAGE_SIZE)); } -static void -xfs_flush_bdev_async_endio( - struct bio *bio) -{ - complete(bio->bi_private); -} - -/* - * Submit a request for an async cache flush to run. If the request queue does - * not require flush operations, just skip it altogether. If the caller needs - * to wait for the flush completion at a later point in time, they must supply a - * valid completion. This will be signalled when the flush completes. The - * caller never sees the bio that is issued here. - */ -void -xfs_flush_bdev_async( - struct bio *bio, - struct block_device *bdev, - struct completion *done) -{ - struct request_queue *q = bdev->bd_disk->queue; - - if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { - complete(done); - return; - } - - bio_init(bio, bdev, NULL, 0, REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC); - bio->bi_private = done; - bio->bi_end_io = xfs_flush_bdev_async_endio; - - submit_bio(bio); -} int xfs_rw_bdev( struct block_device *bdev, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 33e26690a8c4..68f74549fa22 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -17,6 +17,7 @@ #include "xfs_fsops.h" #include "xfs_trans_space.h" #include "xfs_log.h" +#include "xfs_log_priv.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_trace.h" @@ -347,7 +348,7 @@ xfs_fs_counts( cnt->allocino = percpu_counter_read_positive(&mp->m_icount); cnt->freeino = percpu_counter_read_positive(&mp->m_ifree); cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) - - mp->m_alloc_set_aside; + xfs_fdblocks_unavailable(mp); spin_lock(&mp->m_sb_lock); cnt->freertx = mp->m_sb.sb_frextents; @@ -430,46 +431,36 @@ xfs_reserve_blocks( * If the request is larger than the current reservation, reserve the * blocks before we update the reserve counters. Sample m_fdblocks and * perform a partial reservation if the request exceeds free space. + * + * The code below estimates how many blocks it can request from + * fdblocks to stash in the reserve pool. This is a classic TOCTOU + * race since fdblocks updates are not always coordinated via + * m_sb_lock. Set the reserve size even if there's not enough free + * space to fill it because mod_fdblocks will refill an undersized + * reserve when it can. */ - error = -ENOSPC; - do { - free = percpu_counter_sum(&mp->m_fdblocks) - - mp->m_alloc_set_aside; - if (free <= 0) - break; - - delta = request - mp->m_resblks; - lcounter = free - delta; - if (lcounter < 0) - /* We can't satisfy the request, just get what we can */ - fdblks_delta = free; - else - fdblks_delta = delta; - + free = percpu_counter_sum(&mp->m_fdblocks) - + xfs_fdblocks_unavailable(mp); + delta = request - mp->m_resblks; + mp->m_resblks = request; + if (delta > 0 && free > 0) { /* * We'll either succeed in getting space from the free block - * count or we'll get an ENOSPC. If we get a ENOSPC, it means - * things changed while we were calculating fdblks_delta and so - * we should try again to see if there is anything left to - * reserve. + * count or we'll get an ENOSPC. Don't set the reserved flag + * here - we don't want to reserve the extra reserve blocks + * from the reserve. * - * Don't set the reserved flag here - we don't want to reserve - * the extra reserve blocks from the reserve..... + * The desired reserve size can change after we drop the lock. + * Use mod_fdblocks to put the space into the reserve or into + * fdblocks as appropriate. */ + fdblks_delta = min(free, delta); spin_unlock(&mp->m_sb_lock); error = xfs_mod_fdblocks(mp, -fdblks_delta, 0); + if (!error) + xfs_mod_fdblocks(mp, fdblks_delta, 0); spin_lock(&mp->m_sb_lock); - } while (error == -ENOSPC); - - /* - * Update the reserve counters if blocks have been successfully - * allocated. - */ - if (!error && fdblks_delta) { - mp->m_resblks += fdblks_delta; - mp->m_resblks_avail += fdblks_delta; } - out: if (outval) { outval->resblks = mp->m_resblks; @@ -528,8 +519,11 @@ xfs_do_force_shutdown( int tag; const char *why; - if (test_and_set_bit(XFS_OPSTATE_SHUTDOWN, &mp->m_opstate)) + + if (test_and_set_bit(XFS_OPSTATE_SHUTDOWN, &mp->m_opstate)) { + xlog_shutdown_wait(mp->m_log); return; + } if (mp->m_sb_bp) mp->m_sb_bp->b_flags |= XBF_DONE; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 20186c584c7d..bffd6eb0b298 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -883,7 +883,7 @@ xfs_reclaim_inode( */ if (xlog_is_shutdown(ip->i_mount->m_log)) { xfs_iunpin_wait(ip); - xfs_iflush_abort(ip); + xfs_iflush_shutdown_abort(ip); goto reclaim; } if (xfs_ipincount(ip)) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 26227d26f274..9de6205fe134 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3631,7 +3631,7 @@ xfs_iflush_cluster( /* * We must use the safe variant here as on shutdown xfs_iflush_abort() - * can remove itself from the list. + * will remove itself from the list. */ list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { iip = (struct xfs_inode_log_item *)lip; diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 11158fa81a09..9e6ef55cf29e 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -544,10 +544,17 @@ xfs_inode_item_push( uint rval = XFS_ITEM_SUCCESS; int error; - ASSERT(iip->ili_item.li_buf); + if (!bp || (ip->i_flags & XFS_ISTALE)) { + /* + * Inode item/buffer is being being aborted due to cluster + * buffer deletion. Trigger a log force to have that operation + * completed and items removed from the AIL before the next push + * attempt. + */ + return XFS_ITEM_PINNED; + } - if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp) || - (ip->i_flags & XFS_ISTALE)) + if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) return XFS_ITEM_PINNED; if (xfs_iflags_test(ip, XFS_IFLUSHING)) @@ -834,46 +841,143 @@ xfs_buf_inode_io_fail( } /* - * This is the inode flushing abort routine. It is called when - * the filesystem is shutting down to clean up the inode state. It is - * responsible for removing the inode item from the AIL if it has not been - * re-logged and clearing the inode's flush state. + * Clear the inode logging fields so no more flushes are attempted. If we are + * on a buffer list, it is now safe to remove it because the buffer is + * guaranteed to be locked. The caller will drop the reference to the buffer + * the log item held. + */ +static void +xfs_iflush_abort_clean( + struct xfs_inode_log_item *iip) +{ + iip->ili_last_fields = 0; + iip->ili_fields = 0; + iip->ili_fsync_fields = 0; + iip->ili_flush_lsn = 0; + iip->ili_item.li_buf = NULL; + list_del_init(&iip->ili_item.li_bio_list); +} + +/* + * Abort flushing the inode from a context holding the cluster buffer locked. + * + * This is the normal runtime method of aborting writeback of an inode that is + * attached to a cluster buffer. It occurs when the inode and the backing + * cluster buffer have been freed (i.e. inode is XFS_ISTALE), or when cluster + * flushing or buffer IO completion encounters a log shutdown situation. + * + * If we need to abort inode writeback and we don't already hold the buffer + * locked, call xfs_iflush_shutdown_abort() instead as this should only ever be + * necessary in a shutdown situation. */ void xfs_iflush_abort( struct xfs_inode *ip) { struct xfs_inode_log_item *iip = ip->i_itemp; - struct xfs_buf *bp = NULL; + struct xfs_buf *bp; - if (iip) { - /* - * Clear the failed bit before removing the item from the AIL so - * xfs_trans_ail_delete() doesn't try to clear and release the - * buffer attached to the log item before we are done with it. - */ - clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags); - xfs_trans_ail_delete(&iip->ili_item, 0); + if (!iip) { + /* clean inode, nothing to do */ + xfs_iflags_clear(ip, XFS_IFLUSHING); + return; + } + + /* + * Remove the inode item from the AIL before we clear its internal + * state. Whilst the inode is in the AIL, it should have a valid buffer + * pointer for push operations to access - it is only safe to remove the + * inode from the buffer once it has been removed from the AIL. + * + * We also clear the failed bit before removing the item from the AIL + * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer + * references the inode item owns and needs to hold until we've fully + * aborted the inode log item and detached it from the buffer. + */ + clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags); + xfs_trans_ail_delete(&iip->ili_item, 0); + + /* + * Grab the inode buffer so can we release the reference the inode log + * item holds on it. + */ + spin_lock(&iip->ili_lock); + bp = iip->ili_item.li_buf; + xfs_iflush_abort_clean(iip); + spin_unlock(&iip->ili_lock); + xfs_iflags_clear(ip, XFS_IFLUSHING); + if (bp) + xfs_buf_rele(bp); +} + +/* + * Abort an inode flush in the case of a shutdown filesystem. This can be called + * from anywhere with just an inode reference and does not require holding the + * inode cluster buffer locked. If the inode is attached to a cluster buffer, + * it will grab and lock it safely, then abort the inode flush. + */ +void +xfs_iflush_shutdown_abort( + struct xfs_inode *ip) +{ + struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_buf *bp; + + if (!iip) { + /* clean inode, nothing to do */ + xfs_iflags_clear(ip, XFS_IFLUSHING); + return; + } + + spin_lock(&iip->ili_lock); + bp = iip->ili_item.li_buf; + if (!bp) { + spin_unlock(&iip->ili_lock); + xfs_iflush_abort(ip); + return; + } + + /* + * We have to take a reference to the buffer so that it doesn't get + * freed when we drop the ili_lock and then wait to lock the buffer. + * We'll clean up the extra reference after we pick up the ili_lock + * again. + */ + xfs_buf_hold(bp); + spin_unlock(&iip->ili_lock); + xfs_buf_lock(bp); + + spin_lock(&iip->ili_lock); + if (!iip->ili_item.li_buf) { /* - * Clear the inode logging fields so no more flushes are - * attempted. + * Raced with another removal, hold the only reference + * to bp now. Inode should not be in the AIL now, so just clean + * up and return; */ - spin_lock(&iip->ili_lock); - iip->ili_last_fields = 0; - iip->ili_fields = 0; - iip->ili_fsync_fields = 0; - iip->ili_flush_lsn = 0; - bp = iip->ili_item.li_buf; - iip->ili_item.li_buf = NULL; - list_del_init(&iip->ili_item.li_bio_list); + ASSERT(list_empty(&iip->ili_item.li_bio_list)); + ASSERT(!test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags)); + xfs_iflush_abort_clean(iip); spin_unlock(&iip->ili_lock); + xfs_iflags_clear(ip, XFS_IFLUSHING); + xfs_buf_relse(bp); + return; } - xfs_iflags_clear(ip, XFS_IFLUSHING); - if (bp) - xfs_buf_rele(bp); + + /* + * Got two references to bp. The first will get dropped by + * xfs_iflush_abort() when the item is removed from the buffer list, but + * we can't drop our reference until _abort() returns because we have to + * unlock the buffer as well. Hence we abort and then unlock and release + * our reference to the buffer. + */ + ASSERT(iip->ili_item.li_buf == bp); + spin_unlock(&iip->ili_lock); + xfs_iflush_abort(ip); + xfs_buf_relse(bp); } + /* * convert an xfs_inode_log_format struct from the old 32 bit version * (which can have different field alignments) to the native 64 bit version diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 1a302000d604..bbd836a44ff0 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -44,6 +44,7 @@ static inline int xfs_inode_clean(struct xfs_inode *ip) extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *); extern void xfs_inode_item_destroy(struct xfs_inode *); extern void xfs_iflush_abort(struct xfs_inode *); +extern void xfs_iflush_shutdown_abort(struct xfs_inode *); extern int xfs_inode_item_format_convert(xfs_log_iovec_t *, struct xfs_inode_log_format *); diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 09a8fba84ff9..cb9105d667db 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -197,8 +197,6 @@ static inline uint64_t howmany_64(uint64_t x, uint32_t y) int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, char *data, unsigned int op); -void xfs_flush_bdev_async(struct bio *bio, struct block_device *bdev, - struct completion *done); #define ASSERT_ALWAYS(expr) \ (likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__)) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a8034c0afdf2..499e15b24215 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -487,7 +487,10 @@ out_error: * Run all the pending iclog callbacks and wake log force waiters and iclog * space waiters so they can process the newly set shutdown state. We really * don't care what order we process callbacks here because the log is shut down - * and so state cannot change on disk anymore. + * and so state cannot change on disk anymore. However, we cannot wake waiters + * until the callbacks have been processed because we may be in unmount and + * we must ensure that all AIL operations the callbacks perform have completed + * before we tear down the AIL. * * We avoid processing actively referenced iclogs so that we don't run callbacks * while the iclog owner might still be preparing the iclog for IO submssion. @@ -501,7 +504,6 @@ xlog_state_shutdown_callbacks( struct xlog_in_core *iclog; LIST_HEAD(cb_list); - spin_lock(&log->l_icloglock); iclog = log->l_iclog; do { if (atomic_read(&iclog->ic_refcnt)) { @@ -509,26 +511,22 @@ xlog_state_shutdown_callbacks( continue; } list_splice_init(&iclog->ic_callbacks, &cb_list); + spin_unlock(&log->l_icloglock); + + xlog_cil_process_committed(&cb_list); + + spin_lock(&log->l_icloglock); wake_up_all(&iclog->ic_write_wait); wake_up_all(&iclog->ic_force_wait); } while ((iclog = iclog->ic_next) != log->l_iclog); wake_up_all(&log->l_flush_wait); - spin_unlock(&log->l_icloglock); - - xlog_cil_process_committed(&cb_list); } /* * Flush iclog to disk if this is the last reference to the given iclog and the * it is in the WANT_SYNC state. * - * If the caller passes in a non-zero @old_tail_lsn and the current log tail - * does not match, there may be metadata on disk that must be persisted before - * this iclog is written. To satisfy that requirement, set the - * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new - * log tail value. - * * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the * log tail is updated correctly. NEED_FUA indicates that the iclog will be * written to stable storage, and implies that a commit record is contained @@ -545,12 +543,10 @@ xlog_state_shutdown_callbacks( * always capture the tail lsn on the iclog on the first NEED_FUA release * regardless of the number of active reference counts on this iclog. */ - int xlog_state_release_iclog( struct xlog *log, - struct xlog_in_core *iclog, - xfs_lsn_t old_tail_lsn) + struct xlog_in_core *iclog) { xfs_lsn_t tail_lsn; bool last_ref; @@ -561,18 +557,14 @@ xlog_state_release_iclog( /* * Grabbing the current log tail needs to be atomic w.r.t. the writing * of the tail LSN into the iclog so we guarantee that the log tail does - * not move between deciding if a cache flush is required and writing - * the LSN into the iclog below. + * not move between the first time we know that the iclog needs to be + * made stable and when we eventually submit it. */ - if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) { + if ((iclog->ic_state == XLOG_STATE_WANT_SYNC || + (iclog->ic_flags & XLOG_ICL_NEED_FUA)) && + !iclog->ic_header.h_tail_lsn) { tail_lsn = xlog_assign_tail_lsn(log->l_mp); - - if (old_tail_lsn && tail_lsn != old_tail_lsn) - iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; - - if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) && - !iclog->ic_header.h_tail_lsn) - iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); + iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); } last_ref = atomic_dec_and_test(&iclog->ic_refcnt); @@ -583,11 +575,8 @@ xlog_state_release_iclog( * pending iclog callbacks that were waiting on the release of * this iclog. */ - if (last_ref) { - spin_unlock(&log->l_icloglock); + if (last_ref) xlog_state_shutdown_callbacks(log); - spin_lock(&log->l_icloglock); - } return -EIO; } @@ -600,8 +589,6 @@ xlog_state_release_iclog( } iclog->ic_state = XLOG_STATE_SYNCING; - if (!iclog->ic_header.h_tail_lsn) - iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn); xlog_verify_tail_lsn(log, iclog); trace_xlog_iclog_syncing(iclog, _RET_IP_); @@ -873,7 +860,7 @@ xlog_force_iclog( iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); - return xlog_state_release_iclog(iclog->ic_log, iclog, 0); + return xlog_state_release_iclog(iclog->ic_log, iclog); } /* @@ -1373,7 +1360,7 @@ xlog_ioend_work( */ if (XFS_TEST_ERROR(error, log->l_mp, XFS_ERRTAG_IODONE_IOERR)) { xfs_alert(log->l_mp, "log I/O error %d", error); - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } xlog_state_done_syncing(iclog); @@ -1912,7 +1899,7 @@ xlog_write_iclog( iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) { - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); return; } if (is_vmalloc_addr(iclog->ic_data)) @@ -2411,7 +2398,7 @@ xlog_write_copy_finish( ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC || xlog_is_shutdown(log)); release_iclog: - error = xlog_state_release_iclog(log, iclog, 0); + error = xlog_state_release_iclog(log, iclog); spin_unlock(&log->l_icloglock); return error; } @@ -2487,7 +2474,7 @@ xlog_write( xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, "ctx ticket reservation ran out. Need to up reservation"); xlog_print_tic_res(log->l_mp, ticket); - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } len = xlog_write_calc_vec_length(ticket, log_vector, optype); @@ -2628,7 +2615,7 @@ next_lv: spin_lock(&log->l_icloglock); xlog_state_finish_copy(log, iclog, record_cnt, data_cnt); - error = xlog_state_release_iclog(log, iclog, 0); + error = xlog_state_release_iclog(log, iclog); spin_unlock(&log->l_icloglock); return error; @@ -3052,7 +3039,7 @@ restart: * reference to the iclog. */ if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1)) - error = xlog_state_release_iclog(log, iclog, 0); + error = xlog_state_release_iclog(log, iclog); spin_unlock(&log->l_icloglock); if (error) return error; @@ -3821,9 +3808,10 @@ xlog_verify_iclog( #endif /* - * Perform a forced shutdown on the log. This should be called once and once - * only by the high level filesystem shutdown code to shut the log subsystem - * down cleanly. + * Perform a forced shutdown on the log. + * + * This can be called from low level log code to trigger a shutdown, or from the + * high level mount shutdown code when the mount shuts down. * * Our main objectives here are to make sure that: * a. if the shutdown was not due to a log IO error, flush the logs to @@ -3832,6 +3820,8 @@ xlog_verify_iclog( * parties to find out. Nothing new gets queued after this is done. * c. Tasks sleeping on log reservations, pinned objects and * other resources get woken up. + * d. The mount is also marked as shut down so that log triggered shutdowns + * still behave the same as if they called xfs_forced_shutdown(). * * Return true if the shutdown cause was a log IO error and we actually shut the * log down. @@ -3843,25 +3833,25 @@ xlog_force_shutdown( { bool log_error = (shutdown_flags & SHUTDOWN_LOG_IO_ERROR); - /* - * If this happens during log recovery then we aren't using the runtime - * log mechanisms yet so there's nothing to shut down. - */ - if (!log || xlog_in_recovery(log)) + if (!log) return false; - ASSERT(!xlog_is_shutdown(log)); - /* * Flush all the completed transactions to disk before marking the log * being shut down. We need to do this first as shutting down the log * before the force will prevent the log force from flushing the iclogs * to disk. * - * Re-entry due to a log IO error shutdown during the log force is - * prevented by the atomicity of higher level shutdown code. + * When we are in recovery, there are no transactions to flush, and + * we don't want to touch the log because we don't want to perturb the + * current head/tail for future recovery attempts. Hence we need to + * avoid a log force in this case. + * + * If we are shutting down due to a log IO error, then we must avoid + * trying to write the log as that may just result in more IO errors and + * an endless shutdown/force loop. */ - if (!log_error) + if (!log_error && !xlog_in_recovery(log)) xfs_log_force(log->l_mp, XFS_LOG_SYNC); /* @@ -3878,12 +3868,25 @@ xlog_force_shutdown( spin_lock(&log->l_icloglock); if (test_and_set_bit(XLOG_IO_ERROR, &log->l_opstate)) { spin_unlock(&log->l_icloglock); - ASSERT(0); return false; } spin_unlock(&log->l_icloglock); /* + * If this log shutdown also sets the mount shutdown state, issue a + * shutdown warning message. + */ + if (!test_and_set_bit(XFS_OPSTATE_SHUTDOWN, &log->l_mp->m_opstate)) { + xfs_alert_tag(log->l_mp, XFS_PTAG_SHUTDOWN_LOGERROR, +"Filesystem has been shut down due to log error (0x%x).", + shutdown_flags); + xfs_alert(log->l_mp, +"Please unmount the filesystem and rectify the problem(s)."); + if (xfs_error_level >= XFS_ERRLEVEL_HIGH) + xfs_stack_trace(); + } + + /* * We don't want anybody waiting for log reservations after this. That * means we have to wake up everybody queued up on reserveq as well as * writeq. In addition, we make sure in xlog_{re}grant_log_space that @@ -3903,8 +3906,12 @@ xlog_force_shutdown( wake_up_all(&log->l_cilp->xc_start_wait); wake_up_all(&log->l_cilp->xc_commit_wait); spin_unlock(&log->l_cilp->xc_push_lock); + + spin_lock(&log->l_icloglock); xlog_state_shutdown_callbacks(log); + spin_unlock(&log->l_icloglock); + wake_up_var(&log->l_opstate); return log_error; } diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 796e4464f809..ba57323bfdce 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -540,7 +540,7 @@ xlog_cil_insert_items( spin_unlock(&cil->xc_cil_lock); if (tp->t_ticket->t_curr_res < 0) - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } static void @@ -705,11 +705,21 @@ xlog_cil_set_ctx_write_state( * The LSN we need to pass to the log items on transaction * commit is the LSN reported by the first log vector write, not * the commit lsn. If we use the commit record lsn then we can - * move the tail beyond the grant write head. + * move the grant write head beyond the tail LSN and overwrite + * it. */ ctx->start_lsn = lsn; wake_up_all(&cil->xc_start_wait); spin_unlock(&cil->xc_push_lock); + + /* + * Make sure the metadata we are about to overwrite in the log + * has been flushed to stable storage before this iclog is + * issued. + */ + spin_lock(&cil->xc_log->l_icloglock); + iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; + spin_unlock(&cil->xc_log->l_icloglock); return; } @@ -854,7 +864,7 @@ xlog_cil_write_commit_record( error = xlog_write(log, ctx, &vec, ctx->ticket, XLOG_COMMIT_TRANS); if (error) - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); return error; } @@ -888,10 +898,7 @@ xlog_cil_push_work( struct xfs_trans_header thdr; struct xfs_log_iovec lhdr; struct xfs_log_vec lvhdr = { NULL }; - xfs_lsn_t preflush_tail_lsn; xfs_csn_t push_seq; - struct bio bio; - DECLARE_COMPLETION_ONSTACK(bdev_flush); bool push_commit_stable; new_ctx = xlog_cil_ctx_alloc(); @@ -962,23 +969,6 @@ xlog_cil_push_work( spin_unlock(&cil->xc_push_lock); /* - * The CIL is stable at this point - nothing new will be added to it - * because we hold the flush lock exclusively. Hence we can now issue - * a cache flush to ensure all the completed metadata in the journal we - * are about to overwrite is on stable storage. - * - * Because we are issuing this cache flush before we've written the - * tail lsn to the iclog, we can have metadata IO completions move the - * tail forwards between the completion of this flush and the iclog - * being written. In this case, we need to re-issue the cache flush - * before the iclog write. To detect whether the log tail moves, sample - * the tail LSN *before* we issue the flush. - */ - preflush_tail_lsn = atomic64_read(&log->l_tail_lsn); - xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev, - &bdev_flush); - - /* * Pull all the log vectors off the items in the CIL, and remove the * items from the CIL. We don't need the CIL lock here because it's only * needed on the transaction commit side which is currently locked out @@ -1054,12 +1044,6 @@ xlog_cil_push_work( lvhdr.lv_iovecp = &lhdr; lvhdr.lv_next = ctx->lv_chain; - /* - * Before we format and submit the first iclog, we have to ensure that - * the metadata writeback ordering cache flush is complete. - */ - wait_for_completion(&bdev_flush); - error = xlog_cil_write_chain(ctx, &lvhdr); if (error) goto out_abort_free_ticket; @@ -1118,7 +1102,7 @@ xlog_cil_push_work( if (push_commit_stable && ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(log, ctx->commit_iclog, 0); - xlog_state_release_iclog(log, ctx->commit_iclog, preflush_tail_lsn); + xlog_state_release_iclog(log, ctx->commit_iclog); /* Not safe to reference ctx now! */ @@ -1139,7 +1123,7 @@ out_abort_free_ticket: return; } spin_lock(&log->l_icloglock); - xlog_state_release_iclog(log, ctx->commit_iclog, 0); + xlog_state_release_iclog(log, ctx->commit_iclog); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); } diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 23103d68423c..401cdc400980 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -484,6 +484,17 @@ xlog_is_shutdown(struct xlog *log) return test_bit(XLOG_IO_ERROR, &log->l_opstate); } +/* + * Wait until the xlog_force_shutdown() has marked the log as shut down + * so xlog_is_shutdown() will always return true. + */ +static inline void +xlog_shutdown_wait( + struct xlog *log) +{ + wait_var_event(&log->l_opstate, xlog_is_shutdown(log)); +} + /* common routines */ extern int xlog_recover( @@ -524,8 +535,7 @@ void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket); void xlog_state_switch_iclogs(struct xlog *log, struct xlog_in_core *iclog, int eventual_size); -int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog, - xfs_lsn_t log_tail_lsn); +int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog); /* * When we crack an atomic LSN, we sample it first so that the value will not diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 96c997ed2ec8..c4ad4296c540 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2485,7 +2485,7 @@ xlog_finish_defer_ops( error = xfs_trans_alloc(mp, &resv, dfc->dfc_blkres, dfc->dfc_rtxres, XFS_TRANS_RESERVE, &tp); if (error) { - xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(mp->m_log, SHUTDOWN_LOG_IO_ERROR); return error; } @@ -2519,21 +2519,22 @@ xlog_abort_defer_ops( xfs_defer_ops_capture_free(mp, dfc); } } + /* * When this is called, all of the log intent items which did not have - * corresponding log done items should be in the AIL. What we do now - * is update the data structures associated with each one. + * corresponding log done items should be in the AIL. What we do now is update + * the data structures associated with each one. * - * Since we process the log intent items in normal transactions, they - * will be removed at some point after the commit. This prevents us - * from just walking down the list processing each one. We'll use a - * flag in the intent item to skip those that we've already processed - * and use the AIL iteration mechanism's generation count to try to - * speed this up at least a bit. + * Since we process the log intent items in normal transactions, they will be + * removed at some point after the commit. This prevents us from just walking + * down the list processing each one. We'll use a flag in the intent item to + * skip those that we've already processed and use the AIL iteration mechanism's + * generation count to try to speed this up at least a bit. * - * When we start, we know that the intents are the only things in the - * AIL. As we process them, however, other items are added to the - * AIL. + * When we start, we know that the intents are the only things in the AIL. As we + * process them, however, other items are added to the AIL. Hence we know we + * have started recovery on all the pending intents when we find an non-intent + * item in the AIL. */ STATIC int xlog_recover_process_intents( @@ -2556,17 +2557,8 @@ xlog_recover_process_intents( for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); lip != NULL; lip = xfs_trans_ail_cursor_next(ailp, &cur)) { - /* - * We're done when we see something other than an intent. - * There should be no intents left in the AIL now. - */ - if (!xlog_item_is_intent(lip)) { -#ifdef DEBUG - for (; lip; lip = xfs_trans_ail_cursor_next(ailp, &cur)) - ASSERT(!xlog_item_is_intent(lip)); -#endif + if (!xlog_item_is_intent(lip)) break; - } /* * We should never see a redo item with a LSN higher than @@ -2607,8 +2599,9 @@ err: } /* - * A cancel occurs when the mount has failed and we're bailing out. - * Release all pending log intent items so they don't pin the AIL. + * A cancel occurs when the mount has failed and we're bailing out. Release all + * pending log intent items that we haven't started recovery on so they don't + * pin the AIL. */ STATIC void xlog_recover_cancel_intents( @@ -2622,17 +2615,8 @@ xlog_recover_cancel_intents( spin_lock(&ailp->ail_lock); lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); while (lip != NULL) { - /* - * We're done when we see something other than an intent. - * There should be no intents left in the AIL now. - */ - if (!xlog_item_is_intent(lip)) { -#ifdef DEBUG - for (; lip; lip = xfs_trans_ail_cursor_next(ailp, &cur)) - ASSERT(!xlog_item_is_intent(lip)); -#endif + if (!xlog_item_is_intent(lip)) break; - } spin_unlock(&ailp->ail_lock); lip->li_ops->iop_release(lip); @@ -3470,7 +3454,7 @@ xlog_recover_finish( */ xlog_recover_cancel_intents(log); xfs_alert(log->l_mp, "Failed to recover intents"); - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); return error; } @@ -3517,7 +3501,7 @@ xlog_recover_finish( * end of intents processing can be pushed through the CIL * and AIL. */ - xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } return 0; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index bed73e8002a5..c5f153c3693f 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -21,6 +21,7 @@ #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" +#include "xfs_log_priv.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_fsops.h" @@ -1146,7 +1147,7 @@ xfs_mod_fdblocks( * problems (i.e. transaction abort, pagecache discards, etc.) than * slightly premature -ENOSPC. */ - set_aside = mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks); + set_aside = xfs_fdblocks_unavailable(mp); percpu_counter_add_batch(&mp->m_fdblocks, delta, batch); if (__percpu_counter_compare(&mp->m_fdblocks, set_aside, XFS_FDBLOCKS_BATCH) >= 0) { diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 00720a02e761..f6dc19de8322 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -479,6 +479,21 @@ extern void xfs_unmountfs(xfs_mount_t *); */ #define XFS_FDBLOCKS_BATCH 1024 +/* + * Estimate the amount of free space that is not available to userspace and is + * not explicitly reserved from the incore fdblocks. This includes: + * + * - The minimum number of blocks needed to support splitting a bmap btree + * - The blocks currently in use by the freespace btrees because they record + * the actual blocks that will fill per-AG metadata space reservations + */ +static inline uint64_t +xfs_fdblocks_unavailable( + struct xfs_mount *mp) +{ + return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks); +} + extern int xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta, bool reserved); extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d84714e4e46a..54be9d64093e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -815,7 +815,8 @@ xfs_fs_statfs( spin_unlock(&mp->m_sb_lock); /* make sure statp->f_bfree does not underflow */ - statp->f_bfree = max_t(int64_t, fdblocks - mp->m_alloc_set_aside, 0); + statp->f_bfree = max_t(int64_t, 0, + fdblocks - xfs_fdblocks_unavailable(mp)); statp->f_bavail = statp->f_bfree; fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 917a69f0a6ff..0ac717aad380 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -836,6 +836,7 @@ __xfs_trans_commit( bool regrant) { struct xfs_mount *mp = tp->t_mountp; + struct xlog *log = mp->m_log; xfs_csn_t commit_seq = 0; int error = 0; int sync = tp->t_flags & XFS_TRANS_SYNC; @@ -864,7 +865,13 @@ __xfs_trans_commit( if (!(tp->t_flags & XFS_TRANS_DIRTY)) goto out_unreserve; - if (xfs_is_shutdown(mp)) { + /* + * We must check against log shutdown here because we cannot abort log + * items and leave them dirty, inconsistent and unpinned in memory while + * the log is active. This leaves them open to being written back to + * disk, and that will lead to on-disk corruption. + */ + if (xlog_is_shutdown(log)) { error = -EIO; goto out_unreserve; } @@ -878,7 +885,7 @@ __xfs_trans_commit( xfs_trans_apply_sb_deltas(tp); xfs_trans_apply_dquot_deltas(tp); - xlog_cil_commit(mp->m_log, tp, &commit_seq, regrant); + xlog_cil_commit(log, tp, &commit_seq, regrant); xfs_trans_free(tp); @@ -905,10 +912,10 @@ out_unreserve: */ xfs_trans_unreserve_and_mod_dquots(tp); if (tp->t_ticket) { - if (regrant && !xlog_is_shutdown(mp->m_log)) - xfs_log_ticket_regrant(mp->m_log, tp->t_ticket); + if (regrant && !xlog_is_shutdown(log)) + xfs_log_ticket_regrant(log, tp->t_ticket); else - xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); + xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; } xfs_trans_free_items(tp, !!error); @@ -926,18 +933,27 @@ xfs_trans_commit( } /* - * Unlock all of the transaction's items and free the transaction. - * The transaction must not have modified any of its items, because - * there is no way to restore them to their previous state. + * Unlock all of the transaction's items and free the transaction. If the + * transaction is dirty, we must shut down the filesystem because there is no + * way to restore them to their previous state. * - * If the transaction has made a log reservation, make sure to release - * it as well. + * If the transaction has made a log reservation, make sure to release it as + * well. + * + * This is a high level function (equivalent to xfs_trans_commit()) and so can + * be called after the transaction has effectively been aborted due to the mount + * being shut down. However, if the mount has not been shut down and the + * transaction is dirty we will shut the mount down and, in doing so, that + * guarantees that the log is shut down, too. Hence we don't need to be as + * careful with shutdown state and dirty items here as we need to be in + * xfs_trans_commit(). */ void xfs_trans_cancel( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; + struct xlog *log = mp->m_log; bool dirty = (tp->t_flags & XFS_TRANS_DIRTY); trace_xfs_trans_cancel(tp, _RET_IP_); @@ -955,16 +971,18 @@ xfs_trans_cancel( } /* - * See if the caller is relying on us to shut down the - * filesystem. This happens in paths where we detect - * corruption and decide to give up. + * See if the caller is relying on us to shut down the filesystem. We + * only want an error report if there isn't already a shutdown in + * progress, so we only need to check against the mount shutdown state + * here. */ if (dirty && !xfs_is_shutdown(mp)) { XFS_ERROR_REPORT("xfs_trans_cancel", XFS_ERRLEVEL_LOW, mp); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); } #ifdef DEBUG - if (!dirty && !xfs_is_shutdown(mp)) { + /* Log items need to be consistent until the log is shut down. */ + if (!dirty && !xlog_is_shutdown(log)) { struct xfs_log_item *lip; list_for_each_entry(lip, &tp->t_items, li_trans) @@ -975,7 +993,7 @@ xfs_trans_cancel( xfs_trans_unreserve_and_mod_dquots(tp); if (tp->t_ticket) { - xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); + xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; } diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index c2ccb98c7bcd..d3a97a028560 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -873,17 +873,17 @@ xfs_trans_ail_delete( int shutdown_type) { struct xfs_ail *ailp = lip->li_ailp; - struct xfs_mount *mp = ailp->ail_log->l_mp; + struct xlog *log = ailp->ail_log; xfs_lsn_t tail_lsn; spin_lock(&ailp->ail_lock); if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) { spin_unlock(&ailp->ail_lock); - if (shutdown_type && !xlog_is_shutdown(ailp->ail_log)) { - xfs_alert_tag(mp, XFS_PTAG_AILDELETE, + if (shutdown_type && !xlog_is_shutdown(log)) { + xfs_alert_tag(log->l_mp, XFS_PTAG_AILDELETE, "%s: attempting to delete a log item that is not in the AIL", __func__); - xfs_force_shutdown(mp, shutdown_type); + xlog_force_shutdown(log, shutdown_type); } return; } diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f7f01f03869..c4b78c21d793 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -509,7 +509,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); * External Functions */ -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c08758b6b364..c05d2ce9b6cd 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); void *hv_map_memory(void *addr, unsigned long size); void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fd7feb5c7894..eee6f7763a39 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 8fc637379899..df30f11b4a46 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -143,7 +143,7 @@ static inline void put_unaligned_be48(const u64 val, void *p) static inline u64 __get_unaligned_be48(const u8 *p) { - return (u64)p[0] << 40 | (u64)p[1] << 32 | p[2] << 24 | + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } diff --git a/include/dt-bindings/clock/sun6i-rtc.h b/include/dt-bindings/clock/sun6i-rtc.h new file mode 100644 index 000000000000..c845493e4d37 --- /dev/null +++ b/include/dt-bindings/clock/sun6i-rtc.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ + +#ifndef _DT_BINDINGS_CLK_SUN6I_RTC_H_ +#define _DT_BINDINGS_CLK_SUN6I_RTC_H_ + +#define CLK_OSC32K 0 +#define CLK_OSC32K_FANOUT 1 +#define CLK_IOSC 2 + +#endif /* _DT_BINDINGS_CLK_SUN6I_RTC_H_ */ diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 338aa27e4773..edb7f6d41faa 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -80,12 +80,6 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) #ifdef CONFIG_BALLOON_COMPACTION extern const struct address_space_operations balloon_aops; -extern bool balloon_page_isolate(struct page *page, - isolate_mode_t mode); -extern void balloon_page_putback(struct page *page); -extern int balloon_page_migrate(struct address_space *mapping, - struct page *newpage, - struct page *page, enum migrate_mode mode); /* * balloon_page_insert - insert a page into the balloon's page list and make @@ -155,22 +149,6 @@ static inline void balloon_page_delete(struct page *page) list_del(&page->lru); } -static inline bool balloon_page_isolate(struct page *page) -{ - return false; -} - -static inline void balloon_page_putback(struct page *page) -{ - return; -} - -static inline int balloon_page_migrate(struct page *newpage, - struct page *page, enum migrate_mode mode) -{ - return 0; -} - static inline gfp_t balloon_mapping_gfp_mask(void) { return GFP_HIGHUSER; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f2ad8ed8f777..652cd05b0924 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -95,7 +95,10 @@ struct blkcg_gq { spinlock_t async_bio_lock; struct bio_list async_bios; - struct work_struct async_bio_work; + union { + struct work_struct async_bio_work; + struct work_struct free_work; + }; atomic_t use_delay; atomic64_t delay_nsec; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dd0763a1c674..1973ef9bd40f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -85,8 +85,10 @@ struct block_device { */ #if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) typedef u32 __bitwise blk_status_t; +typedef u32 blk_short_t; #else typedef u8 __bitwise blk_status_t; +typedef u16 blk_short_t; #endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h index cf32123b39f5..57c8ec44ab4e 100644 --- a/include/linux/clk/sunxi-ng.h +++ b/include/linux/clk/sunxi-ng.h @@ -9,4 +9,6 @@ int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); +int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg); + #endif diff --git a/include/linux/cma.h b/include/linux/cma.h index 90fd742fd1ef..a6f637342740 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -12,10 +12,6 @@ */ #ifdef CONFIG_CMA_AREAS #define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) - -#else -#define MAX_CMA_AREAS (0) - #endif #define CMA_MAX_NAME 64 diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index fec374f69e12..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence) return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10d51bcdf7b7..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..77e335a1bcac --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-array.h> + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +/* Internal helper to start new array iteration, don't use directly */ +static inline struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +static inline struct dma_fence * +dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +static inline struct dma_fence * +dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 183160872133..bbde95387a23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,7 +275,6 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ #define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct * helper code (eg buffer layer) * to clear GFP_FS from alloc */ @@ -338,28 +337,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) return kiocb->ki_complete == NULL; } -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user *buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, - unsigned long, unsigned long); - struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); @@ -370,12 +347,6 @@ struct address_space_operations { /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); - /* - * Reads in the requested pages. Unlike ->readpage(), this is - * PURELY used for read-ahead!. - */ - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, @@ -3027,7 +2998,7 @@ extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); -extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); +ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index d44ff747a657..e25539072463 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -457,6 +457,20 @@ int fscache_begin_read_operation(struct netfs_cache_resources *cres, } /** + * fscache_end_operation - End the read operation for the netfs lib + * @cres: The cache resources for the read operation + * + * Clean up the resources at the end of the read request. + */ +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + +/** * fscache_read - Start a read from the cache. * @cres: The cache resources to use * @start_pos: The beginning file offset in the cache file @@ -559,7 +573,6 @@ int fscache_write(struct netfs_cache_resources *cres, /** * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages - * @cookie: The cookie representing the cache object * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to unlock @@ -568,8 +581,7 @@ int fscache_write(struct netfs_cache_resources *cres, * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's * waiting. */ -static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, +static inline void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) { diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index b568b3c7d095..a7afc800bd8d 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -221,7 +221,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) * * This checks whether ->i_verity_info has been set. * - * Filesystems call this from ->readpages() to check whether the pages need to + * Filesystems call this from ->readahead() to check whether the pages need to * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ed8cf433a46a..4816b7e11047 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -9,6 +9,7 @@ #include <linux/trace_recursion.h> #include <linux/trace_clock.h> +#include <linux/jump_label.h> #include <linux/kallsyms.h> #include <linux/linkage.h> #include <linux/bitops.h> @@ -1018,7 +1019,20 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, extern int register_ftrace_graph(struct fgraph_ops *ops); extern void unregister_ftrace_graph(struct fgraph_ops *ops); -extern bool ftrace_graph_is_dead(void); +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +DECLARE_STATIC_KEY_FALSE(kill_ftrace_graph); + +static inline bool ftrace_graph_is_dead(void) +{ + return static_branch_unlikely(&kill_ftrace_graph); +} + extern void ftrace_graph_stop(void); /* The current handlers in use */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0fa17fb85de5..3e3d36fc2109 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -264,9 +264,7 @@ struct vm_area_struct; #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (24 + \ - 3 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ - IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -615,9 +613,11 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, +struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, true) #else @@ -629,8 +629,10 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..e71f6e1bfafe 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -688,7 +688,7 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ @@ -705,6 +705,12 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } +static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, + char *label) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b0728c8ad90c..874aabd270c9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -168,13 +168,16 @@ struct gpio_irq_chip { /** * @parent_handler_data: + * + * If @per_parent_data is false, @parent_handler_data is a single + * pointer used as the data associated with every parent interrupt. + * * @parent_handler_data_array: * - * Data associated, and passed to, the handler for the parent - * interrupt. Can either be a single pointer if @per_parent_data - * is false, or an array of @num_parents pointers otherwise. If - * @per_parent_data is true, @parent_handler_data_array cannot be - * NULL. + * If @per_parent_data is true, @parent_handler_data_array is + * an array of @num_parents pointers, and is used to associate + * different data for each parent. This cannot be NULL if + * @per_parent_data is true. */ union { void *parent_handler_data; @@ -219,6 +222,15 @@ struct gpio_irq_chip { bool per_parent_data; /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers diff --git a/include/linux/input.h b/include/linux/input.h index 0354b298d874..49790c1bd2c4 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -475,6 +475,8 @@ static inline void input_set_events_per_packet(struct input_dev *dev, int n_even void input_alloc_absinfo(struct input_dev *dev); void input_set_abs_params(struct input_dev *dev, unsigned int axis, int min, int max, int fuzz, int flat); +void input_copy_abs(struct input_dev *dst, unsigned int dst_axis, + const struct input_dev *src, unsigned int src_axis); #define INPUT_GENERATE_ABS_ACCESSORS(_suffix, _item) \ static inline int input_abs_get_##_suffix(struct input_dev *dev, \ diff --git a/include/linux/input/vivaldi-fmap.h b/include/linux/input/vivaldi-fmap.h new file mode 100644 index 000000000000..7e4b7023bf04 --- /dev/null +++ b/include/linux/input/vivaldi-fmap.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _VIVALDI_FMAP_H +#define _VIVALDI_FMAP_H + +#include <linux/types.h> + +#define VIVALDI_MAX_FUNCTION_ROW_KEYS 24 + +/** + * struct vivaldi_data - Function row map data for ChromeOS Vivaldi keyboards + * @function_row_physmap: An array of scancodes or their equivalent (HID usage + * codes, encoded rows/columns, etc) for the top + * row function keys, in an order from left to right + * @num_function_row_keys: The number of top row keys in a custom keyboard + * + * This structure is supposed to be used by ChromeOS keyboards using + * the Vivaldi keyboard function row design. + */ +struct vivaldi_data { + u32 function_row_physmap[VIVALDI_MAX_FUNCTION_ROW_KEYS]; + unsigned int num_function_row_keys; +}; + +ssize_t vivaldi_function_row_physmap_show(const struct vivaldi_data *data, + char *buf); + +#endif /* _VIVALDI_FMAP_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 08ba5995aa8b..a890428bcc1a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,15 +64,6 @@ ) /** - * lower_48_bits() - return bits 0-47 of a number - * @n: the number we're accessing - */ -static inline u64 lower_48_bits(u64 n) -{ - return n & ((1ull << 48) - 1); -} - -/** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing * diff --git a/include/linux/kfence.h b/include/linux/kfence.h index f49e64222628..726857a4b680 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -204,6 +204,22 @@ static __always_inline __must_check bool kfence_free(void *addr) */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +#endif + #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } @@ -221,6 +237,14 @@ static inline bool __must_check kfence_handle_page_fault(unsigned long addr, boo return false; } +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + return false; +} +#endif + #endif #endif /* _LINUX_KFENCE_H */ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c7b47399b36a..57fb972fea05 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -120,7 +120,6 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; - struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9536ffa0473b..3f9b22c4983a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -148,6 +148,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) +#define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members * Bits 4-7 are reserved for more arch-independent bits. @@ -156,9 +157,18 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_GPC_INVALIDATE (5 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 +/* + * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to + * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" + * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing + * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous + * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no + * guarantee the vCPU received an IPI and has actually exited guest mode. + */ +#define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) + #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ @@ -1221,27 +1231,27 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * @gpc: struct gfn_to_pfn_cache object. * @vcpu: vCPU to be used for marking pages dirty and to be woken on * invalidation. - * @guest_uses_pa: indicates that the resulting host physical PFN is used while - * @vcpu is IN_GUEST_MODE so invalidations should wake it. - * @kernel_map: requests a kernel virtual mapping (kmap / memremap). + * @usage: indicates if the resulting host physical PFN is used while + * the @vcpu is IN_GUEST_MODE (in which case invalidation of + * the cache from MMU notifiers---but not for KVM memslot + * changes!---will also force @vcpu to exit the guest and + * refresh the cache); and/or if the PFN used directly + * by KVM (and thus needs a kernel virtual mapping). * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. - * @dirty: mark the cache dirty immediately. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This primes a gfn_to_pfn_cache and links it into the @kvm's list for - * invalidations to be processed. Invalidation callbacks to @vcpu using - * %KVM_REQ_GPC_INVALIDATE will occur only for MMU notifiers, not for KVM - * memslot changes. Callers are required to use kvm_gfn_to_pfn_cache_check() - * to ensure that the cache is valid before accessing the target page. + * invalidations to be processed. Callers are required to use + * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before + * accessing the target page. */ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, bool guest_uses_pa, - bool kernel_map, gpa_t gpa, unsigned long len, - bool dirty); + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. @@ -1250,7 +1260,6 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * @gpc: struct gfn_to_pfn_cache object. * @gpa: current guest physical address to map. * @len: sanity check; the range being access must fit a single page. - * @dirty: mark the cache dirty immediately. * * @return: %true if the cache is still valid and the address matches. * %false if the cache is not valid. @@ -1272,7 +1281,6 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * @gpc: struct gfn_to_pfn_cache object. * @gpa: updated guest physical address to map. * @len: sanity check; the range being access must fit a single page. - * @dirty: mark the cache dirty immediately. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. @@ -1285,7 +1293,7 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * with the lock still held to permit access. */ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - gpa_t gpa, unsigned long len, bool dirty); + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache. @@ -1293,10 +1301,9 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. * - * This unmaps the referenced page and marks it dirty, if appropriate. The - * cache is left in the invalid state but at least the mapping from GPA to - * userspace HVA will remain cached and can be reused on a subsequent - * refresh. + * This unmaps the referenced page. The cache is left in the invalid state + * but at least the mapping from GPA to userspace HVA will remain cached + * and can be reused on a subsequent refresh. */ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); @@ -1984,7 +1991,7 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) void kvm_arch_irq_routing_update(struct kvm *kvm); -static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's @@ -1994,6 +2001,19 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } +static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +{ + /* + * Request that don't require vCPU action should never be logged in + * vcpu->requests. The vCPU won't clear the request, so it will stay + * logged indefinitely and prevent the vCPU from entering the guest. + */ + BUILD_BUG_ON(!__builtin_constant_p(req) || + (req & KVM_REQUEST_NO_ACTION)); + + __kvm_make_request(req, vcpu); +} + static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index dceac12c1ce5..ac1ebb37a0ff 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -18,6 +18,7 @@ struct kvm_memslots; enum kvm_mr_change; +#include <linux/bits.h> #include <linux/types.h> #include <linux/spinlock_types.h> @@ -46,6 +47,12 @@ typedef u64 hfn_t; typedef hfn_t kvm_pfn_t; +enum pfn_cache_usage { + KVM_GUEST_USES_PFN = BIT(0), + KVM_HOST_USES_PFN = BIT(1), + KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN, +}; + struct gfn_to_hva_cache { u64 generation; gpa_t gpa; @@ -64,11 +71,9 @@ struct gfn_to_pfn_cache { rwlock_t lock; void *khva; kvm_pfn_t pfn; + enum pfn_cache_usage usage; bool active; bool valid; - bool dirty; - bool kernel_map; - bool guest_uses_pa; }; #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 6d635e8306d6..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 808bb4cee230..b0da04fe087b 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -86,6 +86,8 @@ struct cmos_rtc_board_info { /* 2 values for divider stage reset, others for "testing purposes only" */ # define RTC_DIV_RESET1 0x60 # define RTC_DIV_RESET2 0x70 + /* In AMD BKDG bit 5 and 6 are reserved, bit 4 is for select dv0 bank */ +# define RTC_AMD_BANK_SELECT 0x10 /* Periodic intr. / Square wave rate select. 0=none, 1=32.8kHz,... 15=2Hz */ # define RTC_RATE_SELECT 0x0F diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..de5c64bbdb72 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,7 +175,7 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 962b14d403e8..46ffab808f03 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1397,13 +1397,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); diff --git a/include/linux/net.h b/include/linux/net.h index ba736b457a06..12093f4db50c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -125,6 +125,25 @@ struct socket { struct socket_wq wq; }; +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + struct vm_area_struct; struct page; struct sockaddr; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..b1fbe21650bb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -199,10 +199,10 @@ struct net_device_stats { * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { - local_t rx_dropped; - local_t tx_dropped; - local_t rx_nohandler; -} __aligned(4 * sizeof(local_t)); + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; +} __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> @@ -3843,15 +3843,15 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); -static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); if (likely(p)) - return this_cpu_ptr(p); + return p; return netdev_core_stats_alloc(dev); } @@ -3859,14 +3859,11 @@ static inline struct net_device_core_stats *dev_core_stats(struct net_device *de #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats *p; \ + struct net_device_core_stats __percpu *p; \ \ - preempt_disable(); \ p = dev_core_stats(dev); \ - \ if (p) \ - local_inc(&p->FIELD); \ - preempt_enable(); \ + this_cpu_inc(p->FIELD); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 614f22213e21..c7bf1eaf51d5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -18,6 +18,8 @@ #include <linux/fs.h> #include <linux/pagemap.h> +enum netfs_sreq_ref_trace; + /* * Overload PG_private_2 to give us PG_fscache - this is used to indicate that * a page is currently backed by a local disk cache @@ -106,7 +108,7 @@ static inline int wait_on_page_fscache_killable(struct page *page) return folio_wait_private_2_killable(page_folio(page)); } -enum netfs_read_source { +enum netfs_io_source { NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, @@ -117,6 +119,17 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); /* + * Per-inode description. This must be directly after the inode struct. + */ +struct netfs_i_context { + const struct netfs_request_ops *ops; +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cache; +#endif + loff_t remote_i_size; /* Size of the remote file */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -130,69 +143,75 @@ struct netfs_cache_resources { /* * Descriptor for a single component subrequest. */ -struct netfs_read_subrequest { - struct netfs_read_request *rreq; /* Supervising read request */ +struct netfs_io_subrequest { + struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ - refcount_t usage; + refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - enum netfs_read_source source; /* Where to read from */ + enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; -#define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ +#define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_READ 2 /* Set if there was a short read from the cache */ +#define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ }; +enum netfs_io_origin { + NETFS_READAHEAD, /* This read was triggered by readahead */ + NETFS_READPAGE, /* This read is a synchronous read */ + NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ +} __mode(byte); + /* - * Descriptor for a read helper request. This is used to make multiple I/O - * requests on a variety of sources and then stitch the result together. + * Descriptor for an I/O helper request. This is used to make multiple I/O + * operations to a variety of data stores and then stitch the result together. */ -struct netfs_read_request { +struct netfs_io_request { struct work_struct work; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct netfs_cache_resources cache_resources; - struct list_head subrequests; /* Requests to fetch I/O from disk or net */ + struct list_head subrequests; /* Contributory I/O operations */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - atomic_t nr_rd_ops; /* Number of read ops in progress */ - atomic_t nr_wr_ops; /* Number of write ops in progress */ + atomic_t nr_outstanding; /* Number of ops in progress */ + atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ + enum netfs_io_origin origin; /* Origin of the request */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ - refcount_t usage; + refcount_t ref; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ -#define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ - const struct netfs_read_request_ops *netfs_ops; + const struct netfs_request_ops *netfs_ops; }; /* * Operations the network filesystem can/must provide to the helpers. */ -struct netfs_read_request_ops { - bool (*is_cache_enabled)(struct inode *inode); - void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); - int (*begin_cache_operation)(struct netfs_read_request *rreq); - void (*expand_readahead)(struct netfs_read_request *rreq); - bool (*clamp_length)(struct netfs_read_subrequest *subreq); - void (*issue_op)(struct netfs_read_subrequest *subreq); - bool (*is_still_valid)(struct netfs_read_request *rreq); +struct netfs_request_ops { + int (*init_request)(struct netfs_io_request *rreq, struct file *file); + int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); + bool (*clamp_length)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); + bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); - void (*done)(struct netfs_read_request *rreq); + void (*done)(struct netfs_io_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; @@ -235,7 +254,7 @@ struct netfs_cache_ops { /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ - enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq, + enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, loff_t i_size); /* Prepare a write operation, working out what part of the write we can @@ -254,20 +273,89 @@ struct netfs_cache_ops { }; struct readahead_control; -extern void netfs_readahead(struct readahead_control *, - const struct netfs_read_request_ops *, - void *); -extern int netfs_readpage(struct file *, - struct folio *, - const struct netfs_read_request_ops *, - void *); +extern void netfs_readahead(struct readahead_control *); +extern int netfs_readpage(struct file *, struct page *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, unsigned int, struct folio **, - void **, - const struct netfs_read_request_ops *, - void *); + void **); -extern void netfs_subreq_terminated(struct netfs_read_subrequest *, ssize_t, bool); +extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); +extern void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what); +extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, + bool was_async, enum netfs_sreq_ref_trace what); extern void netfs_stats_show(struct seq_file *); +/** + * netfs_i_context - Get the netfs inode context from the inode + * @inode: The inode to query + * + * Get the netfs lib inode context from the network filesystem's inode. The + * context struct is expected to directly follow on from the VFS inode struct. + */ +static inline struct netfs_i_context *netfs_i_context(struct inode *inode) +{ + return (struct netfs_i_context *)(inode + 1); +} + +/** + * netfs_inode - Get the netfs inode from the inode context + * @ctx: The context to query + * + * Get the netfs inode from the netfs library's inode context. The VFS inode + * is expected to directly precede the context struct. + */ +static inline struct inode *netfs_inode(struct netfs_i_context *ctx) +{ + return ((struct inode *)ctx) - 1; +} + +/** + * netfs_i_context_init - Initialise a netfs lib context + * @inode: The inode with which the context is associated + * @ops: The netfs's operations list + * + * Initialise the netfs library context struct. This is expected to follow on + * directly from the VFS inode struct. + */ +static inline void netfs_i_context_init(struct inode *inode, + const struct netfs_request_ops *ops) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + memset(ctx, 0, sizeof(*ctx)); + ctx->ops = ops; + ctx->remote_i_size = i_size_read(inode); +} + +/** + * netfs_resize_file - Note that a file got resized + * @inode: The inode being resized + * @new_i_size: The new file size + * + * Inform the netfs lib that a file got resized so that it can adjust its state. + */ +static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + ctx->remote_i_size = new_i_size; +} + +/** + * netfs_i_cookie - Get the cache cookie from the inode + * @inode: The inode to query + * + * Get the caching cookie (if enabled) from the network filesystem's inode. + */ +static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct netfs_i_context *ctx = netfs_i_context(inode); + return ctx->cache; +#else + return NULL; +#endif +} + #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 49ba486aea5f..2863e5a69c6a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1694,6 +1694,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4f44f83817a9..f626a445d1a8 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -346,6 +346,7 @@ enum { NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, + NVME_CTRL_OACS_NS_MNGT_SUPP = 1 << 3, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a8d0b327b066..993994cd943a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -752,8 +752,6 @@ struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -extern int read_cache_pages(struct address_space *mapping, - struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, struct file *file) diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h deleted file mode 100644 index 249d4d7fbf18..000000000000 --- a/include/linux/pci-dma-compat.h +++ /dev/null @@ -1,129 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include this file if the platform implements the dma_ DMA Mapping API - * and wants to provide the pci_ DMA Mapping API in terms of it */ - -#ifndef _ASM_GENERIC_PCI_DMA_COMPAT_H -#define _ASM_GENERIC_PCI_DMA_COMPAT_H - -#include <linux/dma-mapping.h> - -/* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL DMA_BIDIRECTIONAL -#define PCI_DMA_TODEVICE DMA_TO_DEVICE -#define PCI_DMA_FROMDEVICE DMA_FROM_DEVICE -#define PCI_DMA_NONE DMA_NONE - -static inline void * -pci_alloc_consistent(struct pci_dev *hwdev, size_t size, - dma_addr_t *dma_handle) -{ - return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); -} - -static inline void * -pci_zalloc_consistent(struct pci_dev *hwdev, size_t size, - dma_addr_t *dma_handle) -{ - return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); -} - -static inline void -pci_free_consistent(struct pci_dev *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - dma_free_coherent(&hwdev->dev, size, vaddr, dma_handle); -} - -static inline dma_addr_t -pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction) -{ - return dma_map_single(&hwdev->dev, ptr, size, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, - size_t size, int direction) -{ - dma_unmap_single(&hwdev->dev, dma_addr, size, (enum dma_data_direction)direction); -} - -static inline dma_addr_t -pci_map_page(struct pci_dev *hwdev, struct page *page, - unsigned long offset, size_t size, int direction) -{ - return dma_map_page(&hwdev->dev, page, offset, size, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address, - size_t size, int direction) -{ - dma_unmap_page(&hwdev->dev, dma_address, size, (enum dma_data_direction)direction); -} - -static inline int -pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) -{ - return dma_map_sg(&hwdev->dev, sg, nents, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) -{ - dma_unmap_sg(&hwdev->dev, sg, nents, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) -{ - dma_sync_single_for_cpu(&hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) -{ - dma_sync_single_for_device(&hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) -{ - dma_sync_sg_for_cpu(&hwdev->dev, sg, nelems, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) -{ - dma_sync_sg_for_device(&hwdev->dev, sg, nelems, (enum dma_data_direction)direction); -} - -static inline int -pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr) -{ - return dma_mapping_error(&pdev->dev, dma_addr); -} - -#ifdef CONFIG_PCI -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_mask(&dev->dev, mask); -} - -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_coherent_mask(&dev->dev, mask); -} -#else -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -#endif - -#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index b957eeb89c7a..60adf42460ab 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2473,8 +2473,7 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif -/* Provide the legacy pci_dma_* API */ -#include <linux/pci-dma-compat.h> +#include <linux/dma-mapping.h> #define pci_printk(level, pdev, fmt, arg...) \ dev_printk(level, &(pdev)->dev, fmt, ##arg) diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..1766e1de6956 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size) #ifdef CONFIG_FS_POSIX_ACL void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); #else static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 47fd1c2d3a57..1fd9c6a21ebe 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -110,8 +110,6 @@ struct rtc_device { struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ int pie_enabled; struct work_struct irqwork; - /* Some hardware can't support UIE mode */ - int uie_unsupported; /* * This offset specifies the update timing of the RTC. diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 67ee9d20cc5a..5a41c3bbcbe3 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -46,7 +46,6 @@ struct ds1685_priv { u32 regstep; int irq_num; bool bcd_mode; - bool no_irq; u8 (*read)(struct ds1685_priv *, int); void (*write)(struct ds1685_priv *, int, u8); void (*prepare_poweroff)(void); diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index dffeb8281c2d..8f5a86e210b9 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -174,7 +174,7 @@ static inline unsigned int __map_depth(const struct sbitmap *sb, int index) static inline void sbitmap_free(struct sbitmap *sb) { free_percpu(sb->alloc_hint); - kfree(sb->map); + kvfree(sb->map); sb->map = NULL; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a6fdd2a679f..d5e3c00b74e1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1090,9 +1090,6 @@ struct task_struct { /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; -#ifdef CONFIG_RT_DELAYED_SIGNALS - struct kernel_siginfo forced_info; -#endif unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 88cc16444b43..60820ab511d2 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -162,6 +162,7 @@ int seq_dentry(struct seq_file *, struct dentry *, const char *); int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc); +void *single_start(struct seq_file *, loff_t *); int single_open(struct file *, int (*)(struct seq_file *, void *), void *); int single_open_size(struct file *, int (*)(struct seq_file *, void *), void *, size_t); int single_release(struct inode *, struct file *); diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -217,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -248,10 +262,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -281,11 +292,14 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) static inline void __static_call_nop(void) { } @@ -327,10 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a5dda4987e8b..217711fc9cac 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -395,6 +395,7 @@ struct svc_deferred_req { size_t addrlen; struct sockaddr_storage daddr; /* where reply must come from */ size_t daddrlen; + void *xprt_ctxt; struct cache_deferred_req handle; size_t xprt_hlen; int argslen; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 45a9530d3839..522bbf937957 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -144,7 +144,7 @@ struct rpc_xprt_ops { unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -358,10 +358,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index a4b1af581f69..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -59,6 +59,15 @@ struct crc64_pi_tuple { __u8 ref_tag[6]; }; +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); diff --git a/include/linux/timex.h b/include/linux/timex.h index 059b18eb1f1f..5745c90c8800 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -75,7 +75,7 @@ * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. */ -#define random_get_entropy() get_cycles() +#define random_get_entropy() ((unsigned long)get_cycles()) #endif /* diff --git a/include/uapi/linux/user_events.h b/include/linux/user_events.h index e570840571e1..736e05603463 100644 --- a/include/uapi/linux/user_events.h +++ b/include/linux/user_events.h @@ -32,9 +32,6 @@ /* Create dynamic location entry within a 32-bit value */ #define DYN_LOC(offset, size) ((size) << 16 | (offset)) -/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */ -#define FLAG_BPF_ITER (1 << 0) - /* * Describes an event registration and stores the results of the registration. * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum @@ -63,54 +60,4 @@ struct user_reg { /* Requests to delete a user_event */ #define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) -/* Data type that was passed to the BPF program */ -enum { - /* Data resides in kernel space */ - USER_BPF_DATA_KERNEL, - - /* Data resides in user space */ - USER_BPF_DATA_USER, - - /* Data is a pointer to a user_bpf_iter structure */ - USER_BPF_DATA_ITER, -}; - -/* - * Describes an iovec iterator that BPF programs can use to access data for - * a given user_event write() / writev() call. - */ -struct user_bpf_iter { - - /* Offset of the data within the first iovec */ - __u32 iov_offset; - - /* Number of iovec structures */ - __u32 nr_segs; - - /* Pointer to iovec structures */ - const struct iovec *iov; -}; - -/* Context that BPF programs receive when attached to a user_event */ -struct user_bpf_context { - - /* Data type being passed (see union below) */ - __u32 data_type; - - /* Length of the data */ - __u32 data_len; - - /* Pointer to data, varies by data type */ - union { - /* Kernel data (data_type == USER_BPF_DATA_KERNEL) */ - void *kdata; - - /* User data (data_type == USER_BPF_DATA_USER) */ - void *udata; - - /* Direct iovec (data_type == USER_BPF_DATA_ITER) */ - struct user_bpf_iter *iter; - }; -}; - #endif /* _UAPI_LINUX_USER_EVENTS_H */ diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 721089bb4c84..8943a209202e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -83,7 +83,7 @@ struct vdpa_device { unsigned int index; bool features_valid; bool use_va; - int nvqs; + u32 nvqs; struct vdpa_mgmt_dev *mdev; }; @@ -207,7 +207,8 @@ struct vdpa_map_file { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) - * @get_config_size: Get the size of the configuration space + * @get_config_size: Get the size of the configuration space includes + * fields that are conditional on feature bits. * @vdev: vdpa device * Returns size_t: configuration size * @get_config: Read from device specific configuration space @@ -337,10 +338,10 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, dev_struct, member)), name, use_va), \ dev_struct, member) -int vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void vdpa_unregister_device(struct vdpa_device *vdev); -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 74a4a0f17b28..48f2dd3c568c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -133,6 +133,8 @@ struct vfio_pci_core_device { struct mutex ioeventfds_lock; struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; + struct list_head sriov_pfs_item; + struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct mutex vma_lock; struct list_head vma_list; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index dafdc7f48c01..b341dd62aa4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -78,7 +76,6 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3b1df7da402d..b159c2789961 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,7 +26,7 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -153,7 +153,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); diff --git a/include/linux/xarray.h b/include/linux/xarray.h index bb52b786be1b..72feab5ea8d4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -9,6 +9,7 @@ * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/gfp.h> diff --git a/include/net/esp.h b/include/net/esp.h index 90cd02ff77ef..9c5637d41d95 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,8 +4,6 @@ #include <linux/skbuff.h> -#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) - struct ip_esp_hdr; static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index aa33e1092e2c..9f65f1bfbd24 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -59,6 +59,8 @@ struct flow_dissector_key_vlan { __be16 vlan_tci; }; __be16 vlan_tpid; + __be16 vlan_eth_type; + u16 padding; }; struct flow_dissector_mpls_lse { diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0219fe907b26..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ @@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, + __be32 key, __u8 tos, + struct net *net, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; + + if (oif) { + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + /* Legacy VRF/l3mdev use case */ + fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; + } + fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3d83b64471d3..b4af4837d80b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -75,8 +75,8 @@ struct netns_ipv6 { struct list_head fib6_walkers; rwlock_t fib6_walker_lock; spinlock_t fib6_gc_lock; - unsigned int ip6_rt_gc_expire; - unsigned long ip6_rt_last_gc; + atomic_t ip6_rt_gc_expire; + unsigned long ip6_rt_last_gc; unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES @@ -620,6 +621,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1042,6 +1044,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ @@ -1164,6 +1167,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index e76c94697c1b..d0a24779c52d 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -53,8 +53,10 @@ enum { #define ISID_SIZE 6 -/* Connection suspend "bit" */ -#define ISCSI_SUSPEND_BIT 1 +/* Connection flags */ +#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) +#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) +#define ISCSI_CONN_FLAG_BOUND BIT(2) #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 @@ -211,8 +213,7 @@ struct iscsi_conn { struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ struct work_struct xmitwork; /* per-conn. xmit workqueue */ - unsigned long suspend_tx; /* suspend Tx */ - unsigned long suspend_rx; /* suspend Rx */ + unsigned long flags; /* ISCSI_CONN_FLAGs */ /* negotiated params */ unsigned max_recv_dlength; /* initiator_max_recv_dsl*/ diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 38e4a67f5922..9acb8422f680 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -211,6 +211,8 @@ struct iscsi_cls_conn { struct mutex ep_mutex; struct iscsi_endpoint *ep; + /* Used when accessing flags and queueing work. */ + spinlock_t lock; unsigned long flags; struct work_struct cleanup_work; @@ -295,7 +297,7 @@ extern void iscsi_host_for_each_session(struct Scsi_Host *shost, struct iscsi_endpoint { void *dd_data; /* LLD private data */ struct device dev; - uint64_t id; + int id; struct iscsi_cls_conn *conn; }; diff --git a/include/sound/core.h b/include/sound/core.h index b7e9b58d3c78..6d4cc49584c6 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -284,6 +284,7 @@ int snd_card_disconnect(struct snd_card *card); void snd_card_disconnect_sync(struct snd_card *card); int snd_card_free(struct snd_card *card); int snd_card_free_when_closed(struct snd_card *card); +int snd_card_free_on_error(struct device *dev, int ret); void snd_card_set_id(struct snd_card *card, const char *id); int snd_card_register(struct snd_card *card); int snd_card_info_init(void); diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index 653dfffb3ac8..8d79cebf95f3 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -51,6 +51,11 @@ struct snd_dma_device { #define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_DEV /* no SG-buf support */ #define SNDRV_DMA_TYPE_DEV_WC_SG SNDRV_DMA_TYPE_DEV_WC #endif +/* fallback types, don't use those directly */ +#ifdef CONFIG_SND_DMA_SGBUF +#define SNDRV_DMA_TYPE_DEV_SG_FALLBACK 10 +#define SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK 11 +#endif /* * info for buffer allocation diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 314f2779cab5..6b99310b5b88 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -402,6 +402,7 @@ struct snd_pcm_runtime { struct fasync_struct *fasync; bool stop_operating; /* sync_stop will be called */ struct mutex buffer_mutex; /* protect for buffer changes */ + atomic_t buffer_accessing; /* >0: in r/w operation, <0: blocked */ /* -- private section -- */ void *private_data; diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 2c530637e10a..311c14a20e70 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -426,8 +426,8 @@ TRACE_EVENT(cachefiles_vol_coherency, ); TRACE_EVENT(cachefiles_prep_read, - TP_PROTO(struct netfs_read_subrequest *sreq, - enum netfs_read_source source, + TP_PROTO(struct netfs_io_subrequest *sreq, + enum netfs_io_source source, enum cachefiles_prepare_read_trace why, ino_t cache_inode), @@ -437,7 +437,7 @@ TRACE_EVENT(cachefiles_prep_read, __field(unsigned int, rreq ) __field(unsigned short, index ) __field(unsigned short, flags ) - __field(enum netfs_read_source, source ) + __field(enum netfs_io_source, source ) __field(enum cachefiles_prepare_read_trace, why ) __field(size_t, len ) __field(loff_t, start ) diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index e6f4ebbb4c69..beec534cbaab 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -15,63 +15,25 @@ /* * Define enums for tracing information. */ -#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY -#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY - -enum netfs_read_trace { - netfs_read_trace_expanded, - netfs_read_trace_readahead, - netfs_read_trace_readpage, - netfs_read_trace_write_begin, -}; - -enum netfs_rreq_trace { - netfs_rreq_trace_assess, - netfs_rreq_trace_done, - netfs_rreq_trace_free, - netfs_rreq_trace_resubmit, - netfs_rreq_trace_unlock, - netfs_rreq_trace_unmark, - netfs_rreq_trace_write, -}; - -enum netfs_sreq_trace { - netfs_sreq_trace_download_instead, - netfs_sreq_trace_free, - netfs_sreq_trace_prepare, - netfs_sreq_trace_resubmit_short, - netfs_sreq_trace_submit, - netfs_sreq_trace_terminated, - netfs_sreq_trace_write, - netfs_sreq_trace_write_skip, - netfs_sreq_trace_write_term, -}; - -enum netfs_failure { - netfs_fail_check_write_begin, - netfs_fail_copy_to_cache, - netfs_fail_read, - netfs_fail_short_readpage, - netfs_fail_short_write_begin, - netfs_fail_prepare_write, -}; - -#endif - #define netfs_read_traces \ EM(netfs_read_trace_expanded, "EXPANDED ") \ EM(netfs_read_trace_readahead, "READAHEAD") \ EM(netfs_read_trace_readpage, "READPAGE ") \ E_(netfs_read_trace_write_begin, "WRITEBEGN") +#define netfs_rreq_origins \ + EM(NETFS_READAHEAD, "RA") \ + EM(NETFS_READPAGE, "RP") \ + E_(NETFS_READ_FOR_WRITE, "RW") + #define netfs_rreq_traces \ - EM(netfs_rreq_trace_assess, "ASSESS") \ - EM(netfs_rreq_trace_done, "DONE ") \ - EM(netfs_rreq_trace_free, "FREE ") \ - EM(netfs_rreq_trace_resubmit, "RESUBM") \ - EM(netfs_rreq_trace_unlock, "UNLOCK") \ - EM(netfs_rreq_trace_unmark, "UNMARK") \ - E_(netfs_rreq_trace_write, "WRITE ") + EM(netfs_rreq_trace_assess, "ASSESS ") \ + EM(netfs_rreq_trace_copy, "COPY ") \ + EM(netfs_rreq_trace_done, "DONE ") \ + EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_resubmit, "RESUBMT") \ + EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + E_(netfs_rreq_trace_unmark, "UNMARK ") #define netfs_sreq_sources \ EM(NETFS_FILL_WITH_ZEROES, "ZERO") \ @@ -94,10 +56,47 @@ enum netfs_failure { EM(netfs_fail_check_write_begin, "check-write-begin") \ EM(netfs_fail_copy_to_cache, "copy-to-cache") \ EM(netfs_fail_read, "read") \ - EM(netfs_fail_short_readpage, "short-readpage") \ - EM(netfs_fail_short_write_begin, "short-write-begin") \ + EM(netfs_fail_short_read, "short-read") \ E_(netfs_fail_prepare_write, "prep-write") +#define netfs_rreq_ref_traces \ + EM(netfs_rreq_trace_get_hold, "GET HOLD ") \ + EM(netfs_rreq_trace_get_subreq, "GET SUBREQ ") \ + EM(netfs_rreq_trace_put_complete, "PUT COMPLT ") \ + EM(netfs_rreq_trace_put_discard, "PUT DISCARD") \ + EM(netfs_rreq_trace_put_failed, "PUT FAILED ") \ + EM(netfs_rreq_trace_put_hold, "PUT HOLD ") \ + EM(netfs_rreq_trace_put_subreq, "PUT SUBREQ ") \ + EM(netfs_rreq_trace_put_zero_len, "PUT ZEROLEN") \ + E_(netfs_rreq_trace_new, "NEW ") + +#define netfs_sreq_ref_traces \ + EM(netfs_sreq_trace_get_copy_to_cache, "GET COPY2C ") \ + EM(netfs_sreq_trace_get_resubmit, "GET RESUBMIT") \ + EM(netfs_sreq_trace_get_short_read, "GET SHORTRD") \ + EM(netfs_sreq_trace_new, "NEW ") \ + EM(netfs_sreq_trace_put_clear, "PUT CLEAR ") \ + EM(netfs_sreq_trace_put_failed, "PUT FAILED ") \ + EM(netfs_sreq_trace_put_merged, "PUT MERGED ") \ + EM(netfs_sreq_trace_put_no_copy, "PUT NO COPY") \ + E_(netfs_sreq_trace_put_terminated, "PUT TERM ") + +#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#undef EM +#undef E_ +#define EM(a, b) a, +#define E_(a, b) a + +enum netfs_read_trace { netfs_read_traces } __mode(byte); +enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte); +enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte); +enum netfs_failure { netfs_failures } __mode(byte); +enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte); +enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); + +#endif /* * Export enum symbols via userspace. @@ -108,10 +107,13 @@ enum netfs_failure { #define E_(a, b) TRACE_DEFINE_ENUM(a); netfs_read_traces; +netfs_rreq_origins; netfs_rreq_traces; netfs_sreq_sources; netfs_sreq_traces; netfs_failures; +netfs_rreq_ref_traces; +netfs_sreq_ref_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -123,7 +125,7 @@ netfs_failures; #define E_(a, b) { a, b } TRACE_EVENT(netfs_read, - TP_PROTO(struct netfs_read_request *rreq, + TP_PROTO(struct netfs_io_request *rreq, loff_t start, size_t len, enum netfs_read_trace what), @@ -156,31 +158,34 @@ TRACE_EVENT(netfs_read, ); TRACE_EVENT(netfs_rreq, - TP_PROTO(struct netfs_read_request *rreq, + TP_PROTO(struct netfs_io_request *rreq, enum netfs_rreq_trace what), TP_ARGS(rreq, what), TP_STRUCT__entry( __field(unsigned int, rreq ) - __field(unsigned short, flags ) + __field(unsigned int, flags ) + __field(enum netfs_io_origin, origin ) __field(enum netfs_rreq_trace, what ) ), TP_fast_assign( __entry->rreq = rreq->debug_id; __entry->flags = rreq->flags; + __entry->origin = rreq->origin; __entry->what = what; ), - TP_printk("R=%08x %s f=%02x", + TP_printk("R=%08x %s %s f=%02x", __entry->rreq, + __print_symbolic(__entry->origin, netfs_rreq_origins), __print_symbolic(__entry->what, netfs_rreq_traces), __entry->flags) ); TRACE_EVENT(netfs_sreq, - TP_PROTO(struct netfs_read_subrequest *sreq, + TP_PROTO(struct netfs_io_subrequest *sreq, enum netfs_sreq_trace what), TP_ARGS(sreq, what), @@ -190,7 +195,7 @@ TRACE_EVENT(netfs_sreq, __field(unsigned short, index ) __field(short, error ) __field(unsigned short, flags ) - __field(enum netfs_read_source, source ) + __field(enum netfs_io_source, source ) __field(enum netfs_sreq_trace, what ) __field(size_t, len ) __field(size_t, transferred ) @@ -211,26 +216,26 @@ TRACE_EVENT(netfs_sreq, TP_printk("R=%08x[%u] %s %s f=%02x s=%llx %zx/%zx e=%d", __entry->rreq, __entry->index, - __print_symbolic(__entry->what, netfs_sreq_traces), __print_symbolic(__entry->source, netfs_sreq_sources), + __print_symbolic(__entry->what, netfs_sreq_traces), __entry->flags, __entry->start, __entry->transferred, __entry->len, __entry->error) ); TRACE_EVENT(netfs_failure, - TP_PROTO(struct netfs_read_request *rreq, - struct netfs_read_subrequest *sreq, + TP_PROTO(struct netfs_io_request *rreq, + struct netfs_io_subrequest *sreq, int error, enum netfs_failure what), TP_ARGS(rreq, sreq, error, what), TP_STRUCT__entry( __field(unsigned int, rreq ) - __field(unsigned short, index ) + __field(short, index ) __field(short, error ) __field(unsigned short, flags ) - __field(enum netfs_read_source, source ) + __field(enum netfs_io_source, source ) __field(enum netfs_failure, what ) __field(size_t, len ) __field(size_t, transferred ) @@ -239,17 +244,17 @@ TRACE_EVENT(netfs_failure, TP_fast_assign( __entry->rreq = rreq->debug_id; - __entry->index = sreq ? sreq->debug_index : 0; + __entry->index = sreq ? sreq->debug_index : -1; __entry->error = error; __entry->flags = sreq ? sreq->flags : 0; __entry->source = sreq ? sreq->source : NETFS_INVALID_READ; __entry->what = what; - __entry->len = sreq ? sreq->len : 0; + __entry->len = sreq ? sreq->len : rreq->len; __entry->transferred = sreq ? sreq->transferred : 0; __entry->start = sreq ? sreq->start : 0; ), - TP_printk("R=%08x[%u] %s f=%02x s=%llx %zx/%zx %s e=%d", + TP_printk("R=%08x[%d] %s f=%02x s=%llx %zx/%zx %s e=%d", __entry->rreq, __entry->index, __print_symbolic(__entry->source, netfs_sreq_sources), __entry->flags, @@ -258,6 +263,59 @@ TRACE_EVENT(netfs_failure, __entry->error) ); +TRACE_EVENT(netfs_rreq_ref, + TP_PROTO(unsigned int rreq_debug_id, int ref, + enum netfs_rreq_ref_trace what), + + TP_ARGS(rreq_debug_id, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, rreq ) + __field(int, ref ) + __field(enum netfs_rreq_ref_trace, what ) + ), + + TP_fast_assign( + __entry->rreq = rreq_debug_id; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("R=%08x %s r=%u", + __entry->rreq, + __print_symbolic(__entry->what, netfs_rreq_ref_traces), + __entry->ref) + ); + +TRACE_EVENT(netfs_sreq_ref, + TP_PROTO(unsigned int rreq_debug_id, unsigned int subreq_debug_index, + int ref, enum netfs_sreq_ref_trace what), + + TP_ARGS(rreq_debug_id, subreq_debug_index, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, rreq ) + __field(unsigned int, subreq ) + __field(int, ref ) + __field(enum netfs_sreq_ref_trace, what ) + ), + + TP_fast_assign( + __entry->rreq = rreq_debug_id; + __entry->subreq = subreq_debug_index; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("R=%08x[%x] %s r=%u", + __entry->rreq, + __entry->subreq, + __print_symbolic(__entry->what, netfs_sreq_ref_traces), + __entry->ref) + ); + +#undef EM +#undef E_ #endif /* _TRACE_NETFS_H */ /* This part must be outside protection */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0f34f13ebd55..3995c58a1c51 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); DECLARE_EVENT_CLASS(rpc_xprt_event, @@ -2016,17 +2015,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __string(addr, dr->xprt->xpt_remotebuf) + __array(__u8, addr, INET6_ADDRSTRLEN + 10) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - __assign_str(addr, dr->xprt->xpt_remotebuf); + snprintf(__entry->addr, sizeof(__entry->addr) - 1, + "%pISpc", (struct sockaddr *)&dr->addr); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __get_str(addr), __entry->dr, + TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, __entry->xid) ); diff --git a/include/trace/stages/stage1_defines.h b/include/trace/stages/stage1_struct_define.h index a16783419687..a16783419687 100644 --- a/include/trace/stages/stage1_defines.h +++ b/include/trace/stages/stage1_struct_define.h diff --git a/include/trace/stages/stage2_defines.h b/include/trace/stages/stage2_data_offsets.h index 42fd1e8813ec..42fd1e8813ec 100644 --- a/include/trace/stages/stage2_defines.h +++ b/include/trace/stages/stage2_data_offsets.h diff --git a/include/trace/stages/stage3_defines.h b/include/trace/stages/stage3_trace_output.h index e3b183e9d18e..e3b183e9d18e 100644 --- a/include/trace/stages/stage3_defines.h +++ b/include/trace/stages/stage3_trace_output.h diff --git a/include/trace/stages/stage4_defines.h b/include/trace/stages/stage4_event_fields.h index e80cdc397a43..e80cdc397a43 100644 --- a/include/trace/stages/stage4_defines.h +++ b/include/trace/stages/stage4_event_fields.h diff --git a/include/trace/stages/stage5_defines.h b/include/trace/stages/stage5_get_offsets.h index 7ee5931300e6..7ee5931300e6 100644 --- a/include/trace/stages/stage5_defines.h +++ b/include/trace/stages/stage5_get_offsets.h diff --git a/include/trace/stages/stage6_defines.h b/include/trace/stages/stage6_event_callback.h index e1724f73594b..e1724f73594b 100644 --- a/include/trace/stages/stage6_defines.h +++ b/include/trace/stages/stage6_event_callback.h diff --git a/include/trace/stages/stage7_defines.h b/include/trace/stages/stage7_class_define.h index 8a7ec24c246d..8a7ec24c246d 100644 --- a/include/trace/stages/stage7_defines.h +++ b/include/trace/stages/stage7_class_define.h diff --git a/include/trace/trace_custom_events.h b/include/trace/trace_custom_events.h index b567c7202339..6e492dba96bf 100644 --- a/include/trace/trace_custom_events.h +++ b/include/trace/trace_custom_events.h @@ -35,7 +35,7 @@ /* Stage 1 creates the structure of the recorded event layout */ -#include "stages/stage1_defines.h" +#include "stages/stage1_struct_define.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ @@ -56,7 +56,7 @@ /* Stage 2 creates the custom class */ -#include "stages/stage2_defines.h" +#include "stages/stage2_data_offsets.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -71,7 +71,7 @@ /* Stage 3 create the way to print the custom event */ -#include "stages/stage3_defines.h" +#include "stages/stage3_trace_output.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -102,7 +102,7 @@ static struct trace_event_functions trace_custom_event_type_funcs_##call = { \ /* Stage 4 creates the offset layout for the fields */ -#include "stages/stage4_defines.h" +#include "stages/stage4_event_fields.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, func, print) \ @@ -114,7 +114,7 @@ static struct trace_event_fields trace_custom_event_fields_##call[] = { \ /* Stage 5 creates the helper function for dynamic fields */ -#include "stages/stage5_defines.h" +#include "stages/stage5_get_offsets.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -134,7 +134,7 @@ static inline notrace int trace_custom_event_get_offsets_##call( \ /* Stage 6 creates the probe function that records the event */ -#include "stages/stage6_defines.h" +#include "stages/stage6_event_callback.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -182,7 +182,7 @@ static inline void ftrace_test_custom_probe_##call(void) \ /* Stage 7 creates the actual class and event structure for the custom event */ -#include "stages/stage7_defines.h" +#include "stages/stage7_class_define.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 8a8cd66cc6d5..c2f9cabf154d 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -45,7 +45,7 @@ PARAMS(print)); \ DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); -#include "stages/stage1_defines.h" +#include "stages/stage1_struct_define.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ @@ -109,7 +109,7 @@ * The size of an array is also encoded, in the higher 16 bits of <item>. */ -#include "stages/stage2_defines.h" +#include "stages/stage2_data_offsets.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -181,7 +181,7 @@ * in binary. */ -#include "stages/stage3_defines.h" +#include "stages/stage3_trace_output.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -236,7 +236,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#include "stages/stage4_defines.h" +#include "stages/stage4_event_fields.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ @@ -249,7 +249,7 @@ static struct trace_event_fields trace_event_fields_##call[] = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#include "stages/stage5_defines.h" +#include "stages/stage5_get_offsets.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -372,7 +372,7 @@ static inline notrace int trace_event_get_offsets_##call( \ #define _TRACE_PERF_INIT(call) #endif /* CONFIG_PERF_EVENTS */ -#include "stages/stage6_defines.h" +#include "stages/stage6_event_callback.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -418,7 +418,7 @@ static inline void ftrace_test_probe_##call(void) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#include "stages/stage7_defines.h" +#include "stages/stage7_class_define.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d2be4eb22008..1845cf7c80ba 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -201,11 +201,9 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries - * IORING_CQE_F_MSG If set, CQE was generated with IORING_OP_MSG_RING */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) -#define IORING_CQE_F_MSG (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -298,6 +296,7 @@ struct io_uring_params { #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) #define IORING_FEAT_CQE_SKIP (1U << 11) +#define IORING_FEAT_LINKED_FILE (1U << 12) /* * io_uring_register(2) opcodes and arguments diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 24a1c45bd1ae..98e60801195e 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -45,7 +45,7 @@ struct loop_info { unsigned long lo_inode; /* ioctl r/o */ __kernel_old_dev_t lo_rdevice; /* ioctl r/o */ int lo_offset; - int lo_encrypt_type; + int lo_encrypt_type; /* obsolete, ignored */ int lo_encrypt_key_size; /* ioctl w/o */ int lo_flags; char lo_name[LO_NAME_SIZE]; @@ -61,7 +61,7 @@ struct loop_info64 { __u64 lo_offset; __u64 lo_sizelimit;/* bytes, 0 == max available */ __u32 lo_number; /* ioctl r/o */ - __u32 lo_encrypt_type; + __u32 lo_encrypt_type; /* obsolete, ignored */ __u32 lo_encrypt_key_size; /* ioctl w/o */ __u32 lo_flags; __u8 lo_file_name[LO_NAME_SIZE]; diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 03e5b776e597..97aca4503a6a 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -133,7 +133,8 @@ struct rtc_param { #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CORRECTION 5 #define RTC_FEATURE_BACKUP_SWITCH_MODE 6 -#define RTC_FEATURE_CNT 7 +#define RTC_FEATURE_ALARM_WAKEUP_ONLY 7 +#define RTC_FEATURE_CNT 8 /* parameter list */ #define RTC_PARAM_FEATURES 0 diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 3021ea25a284..7837ba4fe728 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_STDDEF_H +#define _UAPI_LINUX_STDDEF_H + #include <linux/compiler_types.h> #ifndef __always_inline @@ -41,3 +44,4 @@ struct { } __empty_ ## NAME; \ TYPE NAME[]; \ } +#endif diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index c998860d7bbc..5d99e7c242a2 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -150,4 +150,11 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index b5eda06f0d57..f0fb0ae021c0 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -83,6 +83,12 @@ #define VIRTIO_F_RING_PACKED 34 /* + * Inorder feature indicates that all buffers are used by the device + * in the same order in which they have been made available. + */ +#define VIRTIO_F_IN_ORDER 35 + +/* * This feature indicates that memory accesses by the driver and the * device are ordered in a way described by the platform. */ diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h index a03932f10565..71a54a6849ca 100644 --- a/include/uapi/linux/virtio_crypto.h +++ b/include/uapi/linux/virtio_crypto.h @@ -37,6 +37,7 @@ #define VIRTIO_CRYPTO_SERVICE_HASH 1 #define VIRTIO_CRYPTO_SERVICE_MAC 2 #define VIRTIO_CRYPTO_SERVICE_AEAD 3 +#define VIRTIO_CRYPTO_SERVICE_AKCIPHER 4 #define VIRTIO_CRYPTO_OPCODE(service, op) (((service) << 8) | (op)) @@ -57,6 +58,10 @@ struct virtio_crypto_ctrl_header { VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x02) #define VIRTIO_CRYPTO_AEAD_DESTROY_SESSION \ VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x03) +#define VIRTIO_CRYPTO_AKCIPHER_CREATE_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x04) +#define VIRTIO_CRYPTO_AKCIPHER_DESTROY_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x05) __le32 opcode; __le32 algo; __le32 flag; @@ -180,6 +185,58 @@ struct virtio_crypto_aead_create_session_req { __u8 padding[32]; }; +struct virtio_crypto_rsa_session_para { +#define VIRTIO_CRYPTO_RSA_RAW_PADDING 0 +#define VIRTIO_CRYPTO_RSA_PKCS1_PADDING 1 + __le32 padding_algo; + +#define VIRTIO_CRYPTO_RSA_NO_HASH 0 +#define VIRTIO_CRYPTO_RSA_MD2 1 +#define VIRTIO_CRYPTO_RSA_MD3 2 +#define VIRTIO_CRYPTO_RSA_MD4 3 +#define VIRTIO_CRYPTO_RSA_MD5 4 +#define VIRTIO_CRYPTO_RSA_SHA1 5 +#define VIRTIO_CRYPTO_RSA_SHA256 6 +#define VIRTIO_CRYPTO_RSA_SHA384 7 +#define VIRTIO_CRYPTO_RSA_SHA512 8 +#define VIRTIO_CRYPTO_RSA_SHA224 9 + __le32 hash_algo; +}; + +struct virtio_crypto_ecdsa_session_para { +#define VIRTIO_CRYPTO_CURVE_UNKNOWN 0 +#define VIRTIO_CRYPTO_CURVE_NIST_P192 1 +#define VIRTIO_CRYPTO_CURVE_NIST_P224 2 +#define VIRTIO_CRYPTO_CURVE_NIST_P256 3 +#define VIRTIO_CRYPTO_CURVE_NIST_P384 4 +#define VIRTIO_CRYPTO_CURVE_NIST_P521 5 + __le32 curve_id; + __le32 padding; +}; + +struct virtio_crypto_akcipher_session_para { +#define VIRTIO_CRYPTO_NO_AKCIPHER 0 +#define VIRTIO_CRYPTO_AKCIPHER_RSA 1 +#define VIRTIO_CRYPTO_AKCIPHER_DSA 2 +#define VIRTIO_CRYPTO_AKCIPHER_ECDSA 3 + __le32 algo; + +#define VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PUBLIC 1 +#define VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PRIVATE 2 + __le32 keytype; + __le32 keylen; + + union { + struct virtio_crypto_rsa_session_para rsa; + struct virtio_crypto_ecdsa_session_para ecdsa; + } u; +}; + +struct virtio_crypto_akcipher_create_session_req { + struct virtio_crypto_akcipher_session_para para; + __u8 padding[36]; +}; + struct virtio_crypto_alg_chain_session_para { #define VIRTIO_CRYPTO_SYM_ALG_CHAIN_ORDER_HASH_THEN_CIPHER 1 #define VIRTIO_CRYPTO_SYM_ALG_CHAIN_ORDER_CIPHER_THEN_HASH 2 @@ -247,6 +304,8 @@ struct virtio_crypto_op_ctrl_req { mac_create_session; struct virtio_crypto_aead_create_session_req aead_create_session; + struct virtio_crypto_akcipher_create_session_req + akcipher_create_session; struct virtio_crypto_destroy_session_req destroy_session; __u8 padding[56]; @@ -266,6 +325,14 @@ struct virtio_crypto_op_header { VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x00) #define VIRTIO_CRYPTO_AEAD_DECRYPT \ VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x01) +#define VIRTIO_CRYPTO_AKCIPHER_ENCRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x00) +#define VIRTIO_CRYPTO_AKCIPHER_DECRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x01) +#define VIRTIO_CRYPTO_AKCIPHER_SIGN \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x02) +#define VIRTIO_CRYPTO_AKCIPHER_VERIFY \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x03) __le32 opcode; /* algo should be service-specific algorithms */ __le32 algo; @@ -390,6 +457,16 @@ struct virtio_crypto_aead_data_req { __u8 padding[32]; }; +struct virtio_crypto_akcipher_para { + __le32 src_data_len; + __le32 dst_data_len; +}; + +struct virtio_crypto_akcipher_data_req { + struct virtio_crypto_akcipher_para para; + __u8 padding[40]; +}; + /* The request of the data virtqueue's packet */ struct virtio_crypto_op_data_req { struct virtio_crypto_op_header header; @@ -399,6 +476,7 @@ struct virtio_crypto_op_data_req { struct virtio_crypto_hash_data_req hash_req; struct virtio_crypto_mac_data_req mac_req; struct virtio_crypto_aead_data_req aead_req; + struct virtio_crypto_akcipher_data_req akcipher_req; __u8 padding[48]; } u; }; @@ -408,6 +486,8 @@ struct virtio_crypto_op_data_req { #define VIRTIO_CRYPTO_BADMSG 2 #define VIRTIO_CRYPTO_NOTSUPP 3 #define VIRTIO_CRYPTO_INVSESS 4 /* Invalid session id */ +#define VIRTIO_CRYPTO_NOSPC 5 /* no free session ID */ +#define VIRTIO_CRYPTO_KEY_REJECTED 6 /* Signature verification failed */ /* The accelerator hardware is ready */ #define VIRTIO_CRYPTO_S_HW_READY (1 << 0) @@ -438,7 +518,7 @@ struct virtio_crypto_config { __le32 max_cipher_key_len; /* Maximum length of authenticated key */ __le32 max_auth_key_len; - __le32 reserve; + __le32 akcipher_algo; /* Maximum size of each crypto request's content */ __le64 max_size; }; diff --git a/init/Kconfig b/init/Kconfig index 97463a33baa7..ddcbefe535e9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -62,13 +62,13 @@ config LLD_VERSION config CC_CAN_LINK bool - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag)) if 64BIT - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m32-flag)) + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag)) config CC_CAN_LINK_STATIC bool - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag) -static) if 64BIT - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m32-flag) -static) + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag) -static) if 64BIT + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag) -static) config CC_HAS_ASM_GOTO def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC)) diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 8c6de5a9ecc4..c2f1fd95a821 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -133,14 +133,4 @@ config SCHED_CORE which is the likely usage by Linux distributions, there should be no measurable impact on performance. -config ARCH_WANTS_RT_DELAYED_SIGNALS - bool - help - This option is selected by architectures where raising signals - can happen in atomic contexts on PREEMPT_RT enabled kernels. This - option delays raising the signal until the return to user space - loop where it is also delivered. X86 requires this to deliver - signals from trap handlers which run on IST stacks. - -config RT_DELAYED_SIGNALS - def_bool PREEMPT_RT && ARCH_WANTS_RT_DELAYED_SIGNALS + diff --git a/kernel/Makefile b/kernel/Makefile index 471d71935e90..847a82bfe0e3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/cpu.c b/kernel/cpu.c index 5797c2a7a93f..d0a9aa0b42e8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -71,7 +71,6 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - int cpu; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -475,7 +474,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state -cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; @@ -486,14 +485,15 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) st->target = target; st->single = false; st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); return prev_state; } static inline void -cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state prev_state) { bool bringup = !st->bringup; @@ -520,8 +520,8 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) } st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ @@ -541,15 +541,16 @@ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) wait_for_ap_thread(st, st->bringup); } -static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } @@ -581,7 +582,7 @@ static int bringup_wait_for_ap(unsigned int cpu) if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; - return cpuhp_kick_ap(st, st->target); + return cpuhp_kick_ap(cpu, st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -704,7 +705,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); @@ -721,7 +722,6 @@ static void cpuhp_create(unsigned int cpu) init_completion(&st->done_up); init_completion(&st->done_down); - st->cpu = cpu; } static int cpuhp_should_run(unsigned int cpu) @@ -875,7 +875,7 @@ static int cpuhp_kick_ap_work(unsigned int cpu) cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); - ret = cpuhp_kick_ap(st, st->target); + ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; @@ -1107,7 +1107,7 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, @@ -1134,7 +1134,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. @@ -1165,7 +1165,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); @@ -1352,7 +1352,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - cpuhp_set_state(st, target); + cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 35a1d29d6a2e..9743c6ccce1a 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -277,12 +277,16 @@ void *dma_direct_alloc(struct device *dev, size_t size, } if (remap) { + pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs); + + if (force_dma_unencrypted(dev)) + prot = pgprot_decrypted(prot); + /* remove any dirty cache lines on the kernel alias */ arch_dma_prep_coherent(page, size); /* create a coherent mapping */ - ret = dma_common_contiguous_remap(page, size, - dma_pgprot(dev, PAGE_KERNEL, attrs), + ret = dma_common_contiguous_remap(page, size, prot, __builtin_return_address(0)); if (!ret) goto out_free_pages; @@ -535,6 +539,8 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, int ret = -ENXIO; vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); + if (force_dma_unencrypted(dev)) + vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 4632b0f4f72e..8a6cd53dbe8c 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -114,6 +114,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(dev, phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); } #endif /* _KERNEL_DMA_DIRECT_H */ diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 559461a826ba..db7244291b74 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -407,8 +407,6 @@ EXPORT_SYMBOL(dma_get_sgtable_attrs); */ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { - if (force_dma_unencrypted(dev)) - prot = pgprot_decrypted(prot); if (dev_is_dma_coherent(dev)) return prot; #ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE diff --git a/kernel/entry/common.c b/kernel/entry/common.c index ef8d94a98b7e..93c3b86e781c 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -142,18 +142,6 @@ void noinstr exit_to_user_mode(void) /* Workaround to allow gradual conversion of architecture code */ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { } -#ifdef CONFIG_RT_DELAYED_SIGNALS -static inline void raise_delayed_signal(void) -{ - if (unlikely(current->forced_info.si_signo)) { - force_sig_info(¤t->forced_info); - current->forced_info.si_signo = 0; - } -} -#else -static inline void raise_delayed_signal(void) { } -#endif - static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work) { @@ -168,8 +156,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & _TIF_NEED_RESCHED) schedule(); - raise_delayed_signal(); - if (ti_work & _TIF_UPROBE) uprobe_notify_resume(regs); @@ -406,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_irqentry_exit_cond_resched(void) { - if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) return; raw_irqentry_exit_cond_resched(); } diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..23bb19716ad3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); @@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; - struct perf_cgroup *cgrp; /* * ensure we access cgroup data only when needed and @@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current, event->ctx); + info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { - info = this_cpu_ptr(event->cgrp->info); + if (info->active) __update_cgrp_time(info, perf_clock(), true); - } } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp; + struct perf_event_context *ctx = &cpuctx->ctx; + struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; @@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task, * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ - if (!task || !ctx->nr_cgroups) + if (!cgrp) return; - cgrp = perf_cgroup_from_task(task, ctx); + WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); @@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); -#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ -#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ - /* * reschedule events based on the cgroup constraint of task. - * - * mode SWOUT : schedule out everything - * mode SWIN : schedule in based on cgroup for next */ -static void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task) { + struct perf_cgroup *cgrp; struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) */ local_irq_save(flags); + cgrp = perf_cgroup_from_task(task, NULL); + list = this_cpu_ptr(&cgrp_cpuctx_list); list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + if (READ_ONCE(cpuctx->cgrp) == cgrp) + continue; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to update_cgrp_time_from_cpuctx() in + * ctx_sched_out() + */ + cpuctx->cgrp = cgrp; + /* + * set cgrp before ctxsw in to allow + * perf_cgroup_set_timestamp() in ctx_sched_in() + * to not have to pass task around + */ + cpu_ctx_sched_in(cpuctx, EVENT_ALL); - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, - &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } @@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(next, NULL); - - /* - * only schedule out current cgroup events if we know - * that we are switching to a different cgroup. Otherwise, - * do no touch the cgroup events. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); - - rcu_read_unlock(); -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(prev, NULL); - - /* - * only need to schedule in cgroup events if we are changing - * cgroup during ctxsw. Cgroup events were not scheduled - * out of ctxsw out if that was not the case. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWIN); - - rcu_read_unlock(); -} - static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { @@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); - /* - * Since setting cpuctx->cgrp is conditional on the current @cgrp - * matching the event's cgroup, we must do this for every new event, - * because if the first would mismatch, the second would not try again - * and we would leave cpuctx->cgrp unset. - */ - if (ctx->is_active && !cpuctx->cgrp) { - struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); - - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - cpuctx->cgrp = cgrp; - } - if (ctx->nr_cgroups++) return; + cpuctx->cgrp = perf_cgroup_from_task(current, ctx); list_add(&cpuctx->cgrp_cpuctx_entry, per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); } @@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c if (--ctx->nr_cgroups) return; - if (ctx->is_active && cpuctx->cgrp) - cpuctx->cgrp = NULL; - + cpuctx->cgrp = NULL; list_del(&cpuctx->cgrp_cpuctx_entry); } @@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, { } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ -} - static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) @@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) -{ -} - -static inline void -perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } @@ -1147,6 +1052,10 @@ static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } + +static void perf_cgroup_switch(struct task_struct *task) +{ +} #endif /* @@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, @@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - struct task_struct *task) + struct perf_event_context *ctx) { - cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); } /* @@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, else if (ctx_event_type & EVENT_PINNED) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event, return; if (!event_filter_match(event)) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_out(task, next); + perf_cgroup_switch(next); } /* @@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { int is_active = ctx->is_active; @@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (is_active ^ EVENT_TIME) { /* start ctx time */ __update_context_time(ctx, false); - perf_cgroup_set_timestamp(task, ctx); + perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() @@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx, } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type, task); + ctx_sched_in(ctx, cpuctx, event_type); } static void perf_event_context_sched_in(struct perf_event_context *ctx, @@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, ctx, task); + perf_event_sched_in(cpuctx, ctx); if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(cpuctx->task_ctx, true); @@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; - /* - * If cgroup events exist on this CPU, then we need to check if we have - * to switch in PMU state; cgroup event are system-wide mode only. - * - * Since cgroup events are CPU events, we must schedule these in before - * we schedule in the task events. - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); - for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) if (cpu_event) rotate_ctx(&cpuctx->ctx, cpu_event); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn) clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); @@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); @@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info) { struct task_struct *task = info; rcu_read_lock(); - perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + perf_cgroup_switch(task); rcu_read_unlock(); return 0; } diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..fdf170404650 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec, */ if (numvecs <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, - node_to_cpumask[n]); + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); if (++curvec == last_affv) curvec = firstvec; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index f7df715ec28e..7afa40fe5cc4 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -137,7 +137,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (!irq_work_claim(work)) return false; - kasan_record_aux_stack(work); + kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..51efaabac3e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq) extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); +static void queue_core_balance(struct rq *rq); + static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } rq->core_pick = NULL; - return next; + goto out; } put_prev_task_balance(rq, prev, rf); @@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ WARN_ON_ONCE(fi_before); task_vruntime_update(rq, next, false); - goto done; + goto out_set_next; } } @@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) resched_curr(rq_i); } -done: +out_set_next: set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + return next; } @@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) @@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq) static DEFINE_PER_CPU(struct callback_head, core_balance_head); -void queue_core_balance(struct rq *rq) +static void queue_core_balance(struct rq *rq) { if (!sched_core_enabled(rq)) return; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f8b5020e76a..ecb0d7052877 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir { update_idle_core(rq); schedstat_inc(rq->sched_goidle); - queue_core_balance(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..8dccb34eb190 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq, return false; } -extern void queue_core_balance(struct rq *rq); - static inline bool sched_core_enqueued(struct task_struct *p) { return !RB_EMPTY_NODE(&p->core_node); @@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -static inline void queue_core_balance(struct rq *rq) -{ -} - static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p) { return true; diff --git a/kernel/signal.c b/kernel/signal.c index 368a34c25bbf..30cd1ca43bcd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1308,43 +1308,6 @@ enum sig_handler { }; /* - * On some archictectures, PREEMPT_RT has to delay sending a signal from a - * trap since it cannot enable preemption, and the signal code's - * spin_locks turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME - * which will send the signal on exit of the trap. - */ -#ifdef CONFIG_RT_DELAYED_SIGNALS -static inline bool force_sig_delayed(struct kernel_siginfo *info, - struct task_struct *t) -{ - if (!in_atomic()) - return false; - - if (WARN_ON_ONCE(t->forced_info.si_signo)) - return true; - - if (is_si_special(info)) { - WARN_ON_ONCE(info != SEND_SIG_PRIV); - t->forced_info.si_signo = info->si_signo; - t->forced_info.si_errno = 0; - t->forced_info.si_code = SI_KERNEL; - t->forced_info.si_pid = 0; - t->forced_info.si_uid = 0; - } else { - t->forced_info = *info; - } - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); - return true; -} -#else -static inline bool force_sig_delayed(struct kernel_siginfo *info, - struct task_struct *t) -{ - return false; -} -#endif - -/* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. * @@ -1364,9 +1327,6 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, struct k_sigaction *action; int sig = info->si_signo; - if (force_sig_delayed(info, t)) - return 0; - spin_lock_irqsave(&t->sighand->siglock, flags); action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; diff --git a/kernel/smp.c b/kernel/smp.c index 01a7c1706a58..65a630f62363 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -579,7 +579,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && - !warned && !llist_empty(head))) { + !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); diff --git a/kernel/static_call.c b/kernel/static_call.c index f2b8baea35d2..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,549 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } EXPORT_SYMBOL_GPL(__static_call_return0); - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2d76c91b85de..d257721c68b8 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -188,7 +188,7 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) */ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL - WARN_ON(tick_nohz_full_running); + WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } @@ -1538,7 +1538,7 @@ void tick_cancel_sched_timer(int cpu) } #endif -/** +/* * Async notification about clocksource changes */ void tick_clock_notify(void) @@ -1559,7 +1559,7 @@ void tick_oneshot_notify(void) set_bit(0, &ts->check_clocks); } -/** +/* * Check, if a change happened, which makes oneshot possible. * * Called cyclic from the hrtimer softirq (driven by the timer diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 85f1021ad459..9dd2a39cb3b0 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1722,11 +1722,14 @@ static inline void __run_timers(struct timer_base *base) time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* - * The only possible reason for not finding any expired - * timer at this clk is that all matching timers have been - * dequeued. + * The two possible reasons for not finding any expired + * timer at this clk are that all matching timers have been + * dequeued or no timer has been queued since + * base::next_expiry was set to base::clk + + * NEXT_TIMER_MAX_DELTA. */ - WARN_ON_ONCE(!levels && !base->next_expiry_recalc); + WARN_ON_ONCE(!levels && !base->next_expiry_recalc + && base->timers_pending); base->clk++; base->next_expiry = __next_timer_interrupt(base); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9bb54c0b3b2d..2c43e327a619 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -767,6 +767,7 @@ config USER_EVENTS bool "User trace events" select TRACING select DYNAMIC_EVENTS + depends on BROKEN || COMPILE_TEST # API needs to be straighten out help User trace events are user-defined trace events that can be used like an existing kernel trace event. User trace diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 19028e072cdb..8f4fb328133a 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -7,6 +7,7 @@ * * Highly modified by Steven Rostedt (VMware). */ +#include <linux/jump_label.h> #include <linux/suspend.h> #include <linux/ftrace.h> #include <linux/slab.h> @@ -23,25 +24,13 @@ #define ASSIGN_OPS_HASH(opsname, val) #endif -static bool kill_ftrace_graph; +DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph); int ftrace_graph_active; /* Both enabled by default (can be cleared by function_graph tracer flags */ static bool fgraph_sleep_time = true; /** - * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called - * - * ftrace_graph_stop() is called when a severe error is detected in - * the function graph tracing. This function is called by the critical - * paths of function graph to keep those paths from doing any more harm. - */ -bool ftrace_graph_is_dead(void) -{ - return kill_ftrace_graph; -} - -/** * ftrace_graph_stop - set to permanently disable function graph tracing * * In case of an error int function graph tracing, this is called @@ -51,7 +40,7 @@ bool ftrace_graph_is_dead(void) */ void ftrace_graph_stop(void) { - kill_ftrace_graph = true; + static_branch_enable(&kill_ftrace_graph); } /* Add a function return address to the trace stack on thread info.*/ diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 8b3d241a31c2..706e1686b5eb 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -18,7 +18,12 @@ #include <linux/tracefs.h> #include <linux/types.h> #include <linux/uaccess.h> +/* Reminder to move to uapi when everything works */ +#ifdef CONFIG_COMPILE_TEST +#include <linux/user_events.h> +#else #include <uapi/linux/user_events.h> +#endif #include "trace.h" #include "trace_dynevent.h" @@ -42,9 +47,6 @@ #define MAX_FIELD_ARRAY_SIZE 1024 #define MAX_FIELD_ARG_NAME 256 -#define MAX_BPF_COPY_SIZE PAGE_SIZE -#define MAX_STACK_BPF_DATA 512 - static char *register_page_data; static DEFINE_MUTEX(reg_mutex); @@ -405,19 +407,6 @@ parse: type[0] != 'u', FILTER_OTHER); } -static void user_event_parse_flags(struct user_event *user, char *flags) -{ - char *flag; - - if (flags == NULL) - return; - - while ((flag = strsep(&flags, ",")) != NULL) { - if (strcmp(flag, "BPF_ITER") == 0) - user->flags |= FLAG_BPF_ITER; - } -} - static int user_event_parse_fields(struct user_event *user, char *args) { char *field; @@ -713,64 +702,14 @@ discard: } #ifdef CONFIG_PERF_EVENTS -static void user_event_bpf(struct user_event *user, struct iov_iter *i) -{ - struct user_bpf_context context; - struct user_bpf_iter bpf_i; - char fast_data[MAX_STACK_BPF_DATA]; - void *temp = NULL; - - if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) { - /* Raw iterator */ - context.data_type = USER_BPF_DATA_ITER; - context.data_len = i->count; - context.iter = &bpf_i; - - bpf_i.iov_offset = i->iov_offset; - bpf_i.iov = i->iov; - bpf_i.nr_segs = i->nr_segs; - } else if (i->nr_segs == 1 && iter_is_iovec(i)) { - /* Single buffer from user */ - context.data_type = USER_BPF_DATA_USER; - context.data_len = i->count; - context.udata = i->iov->iov_base + i->iov_offset; - } else { - /* Multi buffer from user */ - struct iov_iter copy = *i; - size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE); - - context.data_type = USER_BPF_DATA_KERNEL; - context.kdata = fast_data; - - if (unlikely(copy_size > sizeof(fast_data))) { - temp = kmalloc(copy_size, GFP_NOWAIT); - - if (temp) - context.kdata = temp; - else - copy_size = sizeof(fast_data); - } - - context.data_len = copy_nofault(context.kdata, - copy_size, ©); - } - - trace_call_bpf(&user->call, &context); - - kfree(temp); -} - /* - * Writes the user supplied payload out to perf ring buffer or eBPF program. + * Writes the user supplied payload out to perf ring buffer. */ static void user_event_perf(struct user_event *user, struct iov_iter *i, void *tpdata, bool *faulted) { struct hlist_head *perf_head; - if (bpf_prog_array_valid(&user->call)) - user_event_bpf(user, i); - perf_head = this_cpu_ptr(user->call.perf_events); if (perf_head && !hlist_empty(perf_head)) { @@ -1136,8 +1075,6 @@ static int user_event_parse(char *name, char *args, char *flags, user->tracepoint.name = name; - user_event_parse_flags(user, flags); - ret = user_event_parse_fields(user, args); if (ret) @@ -1165,11 +1102,11 @@ static int user_event_parse(char *name, char *args, char *flags, #endif mutex_lock(&event_mutex); + ret = user_event_trace_register(user); - mutex_unlock(&event_mutex); if (ret) - goto put_user; + goto put_user_lock; user->index = index; @@ -1181,8 +1118,12 @@ static int user_event_parse(char *name, char *args, char *flags, set_bit(user->index, page_bitmap); hash_add(register_table, &user->node, key); + mutex_unlock(&event_mutex); + *newuser = user; return 0; +put_user_lock: + mutex_unlock(&event_mutex); put_user: user_event_destroy_fields(user); user_event_destroy_validators(user); @@ -1575,9 +1516,6 @@ static int user_seq_show(struct seq_file *m, void *p) busy++; } - if (flags & FLAG_BPF_ITER) - seq_puts(m, " FLAG:BPF_ITER"); - seq_puts(m, "\n"); active++; } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 3990e4df3d7b..230038d4f908 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -370,6 +370,7 @@ static void __put_watch_queue(struct kref *kref) for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); + kfree(wqueue->notes); bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); diff --git a/lib/kobject.c b/lib/kobject.c index 56fa037501b5..5f0e71ab292c 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -54,32 +54,6 @@ void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) kobj->ktype->get_ownership(kobj, uid, gid); } -/* - * populate_dir - populate directory with attributes. - * @kobj: object we're working on. - * - * Most subsystems have a set of default attributes that are associated - * with an object that registers with them. This is a helper called during - * object registration that loops through the default attributes of the - * subsystem and creates attributes files for them in sysfs. - */ -static int populate_dir(struct kobject *kobj) -{ - const struct kobj_type *t = get_ktype(kobj); - struct attribute *attr; - int error = 0; - int i; - - if (t && t->default_attrs) { - for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) { - error = sysfs_create_file(kobj, attr); - if (error) - break; - } - } - return error; -} - static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); @@ -90,12 +64,6 @@ static int create_dir(struct kobject *kobj) if (error) return error; - error = populate_dir(kobj); - if (error) { - sysfs_remove_dir(kobj); - return error; - } - if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { diff --git a/lib/logic_iomem.c b/lib/logic_iomem.c index 8c3365f26e51..b247d412ddef 100644 --- a/lib/logic_iomem.c +++ b/lib/logic_iomem.c @@ -68,7 +68,7 @@ int logic_iomem_add_region(struct resource *resource, } EXPORT_SYMBOL(logic_iomem_add_region); -#ifndef CONFIG_LOGIC_IOMEM_FALLBACK +#ifndef CONFIG_INDIRECT_IOMEM_FALLBACK static void __iomem *real_ioremap(phys_addr_t offset, size_t size) { WARN(1, "invalid ioremap(0x%llx, 0x%zx)\n", @@ -81,7 +81,7 @@ static void real_iounmap(volatile void __iomem *addr) WARN(1, "invalid iounmap for addr 0x%llx\n", (unsigned long long)(uintptr_t __force)addr); } -#endif /* CONFIG_LOGIC_IOMEM_FALLBACK */ +#endif /* CONFIG_INDIRECT_IOMEM_FALLBACK */ void __iomem *ioremap(phys_addr_t offset, size_t size) { @@ -168,7 +168,7 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); -#ifndef CONFIG_LOGIC_IOMEM_FALLBACK +#ifndef CONFIG_INDIRECT_IOMEM_FALLBACK #define MAKE_FALLBACK(op, sz) \ static u##sz real_raw_read ## op(const volatile void __iomem *addr) \ { \ @@ -213,7 +213,7 @@ static void real_memcpy_toio(volatile void __iomem *addr, const void *buffer, WARN(1, "Invalid memcpy_toio at address 0x%llx\n", (unsigned long long)(uintptr_t __force)addr); } -#endif /* CONFIG_LOGIC_IOMEM_FALLBACK */ +#endif /* CONFIG_INDIRECT_IOMEM_FALLBACK */ #define MAKE_OP(op, sz) \ u##sz __raw_read ## op(const volatile void __iomem *addr) \ diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 926f4823d5ea..fd1728d94bab 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -271,8 +271,12 @@ static FORCE_INLINE int LZ4_decompress_generic( ip += length; op += length; - /* Necessarily EOF, due to parsing restrictions */ - if (!partialDecoding || (cpy == oend)) + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2))) break; } else { /* may overwrite up to WILDCOPYLENGTH beyond cpy */ diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 2eb3de18ded3..ae4fd4de9ebe 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -110,7 +110,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, sb->alloc_hint = NULL; } - sb->map = kcalloc_node(sb->map_nr, sizeof(*sb->map), flags, node); + sb->map = kvzalloc_node(sb->map_nr * sizeof(*sb->map), flags, node); if (!sb->map) { free_percpu(sb->alloc_hint); return -ENOMEM; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 8b1c318189ce..e77d4856442c 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1463,6 +1463,25 @@ unlock: XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_create_range_5(struct xarray *xa, + unsigned long index, unsigned int order) +{ + XA_STATE_ORDER(xas, xa, index, order); + unsigned int i; + + xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL); + + for (i = 0; i < order + 10; i++) { + do { + xas_lock(&xas); + xas_create_range(&xas); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + } + + xa_destroy(xa); +} + static noinline void check_create_range(struct xarray *xa) { unsigned int order; @@ -1490,6 +1509,9 @@ static noinline void check_create_range(struct xarray *xa) check_create_range_4(xa, (3U << order) + 1, order); check_create_range_4(xa, (3U << order) - 1, order); check_create_range_4(xa, (1U << 24) + 1, order); + + check_create_range_5(xa, 0, order); + check_create_range_5(xa, (1U << order), order); } check_create_range_3(); diff --git a/lib/xarray.c b/lib/xarray.c index b95e92598b9c..4acc88ea7c21 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -722,6 +722,8 @@ void xas_create_range(struct xa_state *xas) for (;;) { struct xa_node *node = xas->xa_node; + if (node->shift >= shift) + break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) @@ -1079,6 +1081,7 @@ void xas_split(struct xa_state *xas, void *entry, unsigned int order) xa_mk_node(child)); if (xa_is_value(curr)) values--; + xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; @@ -1093,6 +1096,7 @@ void xas_split(struct xa_state *xas, void *entry, unsigned int order) } while (offset-- > xas->xa_offset); node->nr_values += values; + xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 907fefde2572..4b8eab4b3f45 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -203,7 +203,7 @@ EXPORT_SYMBOL_GPL(balloon_page_dequeue); #ifdef CONFIG_BALLOON_COMPACTION -bool balloon_page_isolate(struct page *page, isolate_mode_t mode) +static bool balloon_page_isolate(struct page *page, isolate_mode_t mode) { struct balloon_dev_info *b_dev_info = balloon_page_device(page); @@ -217,7 +217,7 @@ bool balloon_page_isolate(struct page *page, isolate_mode_t mode) return true; } -void balloon_page_putback(struct page *page) +static void balloon_page_putback(struct page *page) { struct balloon_dev_info *b_dev_info = balloon_page_device(page); unsigned long flags; @@ -230,7 +230,7 @@ void balloon_page_putback(struct page *page) /* move_to_new_page() counterpart for a ballooned page */ -int balloon_page_migrate(struct address_space *mapping, +static int balloon_page_migrate(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { diff --git a/mm/compaction.c b/mm/compaction.c index c3e37aa9ff9e..fe915db6149b 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -26,6 +26,11 @@ #include "internal.h" #ifdef CONFIG_COMPACTION +/* + * Fragmentation score check interval for proactive compaction purposes. + */ +#define HPAGE_FRAG_CHECK_INTERVAL_MSEC (500) + static inline void count_compact_event(enum vm_event_item item) { count_vm_event(item); @@ -51,11 +56,6 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order) /* - * Fragmentation score check interval for proactive compaction purposes. - */ -static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500; - -/* * Page order with-respect-to which proactive compaction * calculates external fragmentation, which is used as * the "fragmentation score" of a node/zone. diff --git a/mm/damon/core.c b/mm/damon/core.c index c1e0fed4e877..5ce8d7c867f0 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1019,12 +1019,15 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) struct damos *s; unsigned long wait_time; unsigned long min_wait_time = 0; + bool init_wait_time = false; while (!kdamond_need_stop(ctx)) { damon_for_each_scheme(s, ctx) { wait_time = damos_wmark_wait_us(s); - if (!min_wait_time || wait_time < min_wait_time) + if (!init_wait_time || wait_time < min_wait_time) { + init_wait_time = true; min_wait_time = wait_time; + } } if (!min_wait_time) return 0; diff --git a/mm/filemap.c b/mm/filemap.c index 647d72bf23b6..9a1eef6c5d35 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1063,12 +1063,6 @@ void __init pagecache_init(void) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); - - /* - * tmpfs uses the ZERO_PAGE for reading holes: it is up-to-date, - * and splice's page_cache_pipe_buf_confirm() needs to see that. - */ - SetPageUptodate(ZERO_PAGE(0)); } /* @@ -2538,7 +2532,7 @@ static int filemap_create_folio(struct file *file, * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate - * pages or ->readpages() that need to hold invalidate_lock + * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ @@ -3752,9 +3746,10 @@ out: } EXPORT_SYMBOL(generic_file_direct_write); -ssize_t generic_perform_write(struct file *file, - struct iov_iter *i, loff_t pos) +ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { + struct file *file = iocb->ki_filp; + loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; @@ -3884,7 +3879,8 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; - status = generic_perform_write(file, from, pos = iocb->ki_pos); + pos = iocb->ki_pos; + status = generic_perform_write(iocb, from); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were @@ -3916,7 +3912,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) */ } } else { - written = generic_perform_write(file, from, iocb->ki_pos); + written = generic_perform_write(iocb, from); if (likely(written > 0)) iocb->ki_pos += written; } @@ -1404,6 +1404,7 @@ long populate_vma_page_range(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; + long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); @@ -1438,8 +1439,10 @@ long populate_vma_page_range(struct vm_area_struct *vma, * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ - return __get_user_pages(mm, start, nr_pages, gup_flags, + ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); + lru_add_drain(); + return ret; } /* @@ -1471,6 +1474,7 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; + long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); @@ -1498,8 +1502,10 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, if (check_vma_flags(vma, gup_flags)) return -EINVAL; - return __get_user_pages(mm, start, nr_pages, gup_flags, + ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); + lru_add_drain(); + return ret; } /* diff --git a/mm/highmem.c b/mm/highmem.c index 0cc0c4da7ed9..1a692997fac4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -624,7 +624,7 @@ void __kmap_local_sched_out(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) @@ -661,7 +661,7 @@ void __kmap_local_sched_in(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fe38212e07c..c468fee595ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2145,15 +2145,14 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); - if (folio) { - VM_WARN_ON_ONCE(!folio_test_locked(folio)); - if (folio != page_folio(pmd_page(*pmd))) - goto out; - } + VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) + is_pmd_migration_entry(*pmd)) { + if (folio && folio != page_folio(pmd_page(*pmd))) + goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); + } out: spin_unlock(ptl); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b34f50156f7e..f8ca7cca3c1a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3475,7 +3475,6 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) { int nr_nodes, node; struct page *page; - int rc = 0; lockdep_assert_held(&hugetlb_lock); @@ -3486,15 +3485,19 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) } for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { - if (!list_empty(&h->hugepage_freelists[node])) { - page = list_entry(h->hugepage_freelists[node].next, - struct page, lru); - rc = demote_free_huge_page(h, page); - break; + list_for_each_entry(page, &h->hugepage_freelists[node], lru) { + if (PageHWPoison(page)) + continue; + + return demote_free_huge_page(h, page); } } - return rc; + /* + * Only way to get here is if all pages on free lists are poisoned. + * Return -EBUSY so that caller will not retry. + */ + return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ diff --git a/mm/internal.h b/mm/internal.h index 58dc6adc19c5..cf16280ce132 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -456,7 +456,8 @@ static inline void munlock_vma_page(struct page *page, } void mlock_new_page(struct page *page); bool need_mlock_page_drain(int cpu); -void mlock_page_drain(int cpu); +void mlock_page_drain_local(void); +void mlock_page_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); @@ -539,7 +540,8 @@ static inline void munlock_vma_page(struct page *page, struct vm_area_struct *vma, bool compound) { } static inline void mlock_new_page(struct page *page) { } static inline bool need_mlock_page_drain(int cpu) { return false; } -static inline void mlock_page_drain(int cpu) { } +static inline void mlock_page_drain_local(void) { } +static inline void mlock_page_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 07a76c46daa5..9e1b6544bfa8 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -336,8 +336,6 @@ void __kasan_poison_vmalloc(const void *start, unsigned long size) #endif -#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) - void kasan_enable_tagging(void) { if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC) @@ -347,6 +345,9 @@ void kasan_enable_tagging(void) else hw_enable_tagging_sync(); } + +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) + EXPORT_SYMBOL_GPL(kasan_enable_tagging); void kasan_force_async_fault(void) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index d79b83d673b1..b01b4bbe0409 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -355,25 +355,27 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_set_mem_tag_range(addr, size, tag, init) \ arch_set_mem_tag_range((addr), (size), (tag), (init)) +void kasan_enable_tagging(void); + #else /* CONFIG_KASAN_HW_TAGS */ #define hw_enable_tagging_sync() #define hw_enable_tagging_async() #define hw_enable_tagging_asymm() +static inline void kasan_enable_tagging(void) { } + #endif /* CONFIG_KASAN_HW_TAGS */ #if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -void kasan_enable_tagging(void); void kasan_force_async_fault(void); -#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ +#else /* CONFIG_KASAN_HW_TAGS && CONFIG_KASAN_KUNIT_TEST */ -static inline void kasan_enable_tagging(void) { } static inline void kasan_force_async_fault(void) { } -#endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ +#endif /* CONFIG_KASAN_HW_TAGS && CONFIG_KASAN_KUNIT_TEST */ #ifdef CONFIG_KASAN_SW_TAGS u8 kasan_random_tag(void); diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 2f9fdfde1941..9b2b5f56f4ae 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -231,27 +231,6 @@ static bool kfence_unprotect(unsigned long addr) return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); } -static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) -{ - long index; - - /* The checks do not affect performance; only called from slow-paths. */ - - if (!is_kfence_address((void *)addr)) - return NULL; - - /* - * May be an invalid index if called with an address at the edge of - * __kfence_pool, in which case we would report an "invalid access" - * error. - */ - index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; - if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) - return NULL; - - return &kfence_metadata[index]; -} - static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) { unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; @@ -566,6 +545,8 @@ static unsigned long kfence_init_pool(void) * enters __slab_free() slow-path. */ for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { + struct slab *slab = page_slab(&pages[i]); + if (!i || (i % 2)) continue; @@ -573,7 +554,11 @@ static unsigned long kfence_init_pool(void) if (WARN_ON(compound_head(&pages[i]) != &pages[i])) return addr; - __SetPageSlab(&pages[i]); + __folio_set_slab(slab_folio(slab)); +#ifdef CONFIG_MEMCG + slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg | + MEMCG_DATA_OBJCGS; +#endif } /* @@ -1033,6 +1018,9 @@ void __kfence_free(void *addr) { struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); +#ifdef CONFIG_MEMCG + KFENCE_WARN_ON(meta->objcg); +#endif /* * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing * the object, as the object page may be recycled for other-typed diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2a2d5de9d379..600f2e2431d6 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -89,10 +89,34 @@ struct kfence_metadata { struct kfence_track free_track; /* For updating alloc_covered on frees. */ u32 alloc_stack_hash; +#ifdef CONFIG_MEMCG + struct obj_cgroup *objcg; +#endif }; extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + /* KFENCE error types for report generation. */ enum kfence_error_type { KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c index f93a7b2a338b..f5a6d8ba3e21 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -273,3 +273,50 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r /* We encountered a memory safety error, taint the kernel! */ add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); } + +#ifdef CONFIG_PRINTK +static void kfence_to_kp_stack(const struct kfence_track *track, void **kp_stack) +{ + int i, j; + + i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + for (j = 0; i < track->num_stack_entries && j < KS_ADDRS_COUNT; ++i, ++j) + kp_stack[j] = (void *)track->stack_entries[i]; + if (j < KS_ADDRS_COUNT) + kp_stack[j] = NULL; +} + +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)object); + unsigned long flags; + + if (!meta) + return false; + + /* + * If state is UNUSED at least show the pointer requested; the rest + * would be garbage data. + */ + kpp->kp_ptr = object; + + /* Requesting info an a never-used object is almost certainly a bug. */ + if (WARN_ON(meta->state == KFENCE_OBJECT_UNUSED)) + return true; + + raw_spin_lock_irqsave(&meta->lock, flags); + + kpp->kp_slab = slab; + kpp->kp_slab_cache = meta->cache; + kpp->kp_objp = (void *)meta->addr; + kfence_to_kp_stack(&meta->alloc_track, kpp->kp_stack); + if (meta->state == KFENCE_OBJECT_FREED) + kfence_to_kp_stack(&meta->free_track, kpp->kp_free_stack); + /* get_stack_skipnr() ensures the first entry is outside allocator. */ + kpp->kp_ret = kpp->kp_stack[0]; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + return true; +} +#endif diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 7580baa76af1..a182f5ddaf68 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -796,6 +796,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) unsigned long flags; struct kmemleak_object *object; struct kmemleak_scan_area *area = NULL; + unsigned long untagged_ptr; + unsigned long untagged_objp; object = find_and_get_object(ptr, 1); if (!object) { @@ -804,6 +806,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) return; } + untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); + untagged_objp = (unsigned long)kasan_reset_tag((void *)object->pointer); + if (scan_area_cache) area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp)); @@ -815,8 +820,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) goto out_unlock; } if (size == SIZE_MAX) { - size = object->pointer + object->size - ptr; - } else if (ptr + size > object->pointer + object->size) { + size = untagged_objp + object->size - untagged_ptr; + } else if (untagged_ptr + size > untagged_objp + object->size) { kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr); dump_object_info(object); kmem_cache_free(scan_area_cache, area); @@ -1127,7 +1132,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, gfp_t gfp) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_alloc(__va(phys), size, min_count, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1141,7 +1146,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_free_part(__va(phys), size); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1153,7 +1158,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_not_leak_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_not_leak(__va(phys)); } EXPORT_SYMBOL(kmemleak_not_leak_phys); @@ -1165,7 +1170,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_ignore(__va(phys)); } EXPORT_SYMBOL(kmemleak_ignore_phys); diff --git a/mm/list_lru.c b/mm/list_lru.c index c669d87001a6..ba76428ceece 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -395,12 +395,6 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, struct list_lru_one *src, *dst; /* - * If there is no lru entry in this nlru, we can skip it immediately. - */ - if (!READ_ONCE(nlru->nr_items)) - return; - - /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ diff --git a/mm/madvise.c b/mm/madvise.c index b41858ee937b..1873616a37d2 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1464,16 +1464,9 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, while (iov_iter_count(&iter)) { iovec = iov_iter_iovec(&iter); - /* - * do_madvise returns ENOMEM if unmapped holes are present - * in the passed VMA. process_madvise() is expected to skip - * unmapped holes passed to it in the 'struct iovec' list - * and not fail because of them. Thus treat -ENOMEM return - * from do_madvise as valid and continue processing. - */ ret = do_madvise(mm, (unsigned long)iovec.iov_base, iovec.iov_len, behavior); - if (ret < 0 && ret != -ENOMEM) + if (ret < 0) break; iov_iter_advance(&iter, iovec.iov_len); } diff --git a/mm/memory.c b/mm/memory.c index be44d0b36b18..76e3af9639d9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3918,14 +3918,18 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) return ret; if (unlikely(PageHWPoison(vmf->page))) { + struct page *page = vmf->page; vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { + if (page_mapped(page)) + unmap_mapping_pages(page_mapping(page), + page->index, 1, false); /* Retry if a clean page was removed from the cache. */ - if (invalidate_inode_page(vmf->page)) - poisonret = 0; - unlock_page(vmf->page); + if (invalidate_inode_page(page)) + poisonret = VM_FAULT_NOPAGE; + unlock_page(page); } - put_page(vmf->page); + put_page(page); vmf->page = NULL; return poisonret; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a2516d31db6c..8c74107a2b15 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1191,8 +1191,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, */ static struct page *new_page(struct page *page, unsigned long start) { + struct folio *dst, *src = page_folio(page); struct vm_area_struct *vma; unsigned long address; + gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL; vma = find_vma(current->mm, start); while (vma) { @@ -1202,24 +1204,19 @@ static struct page *new_page(struct page *page, unsigned long start) vma = vma->vm_next; } - if (PageHuge(page)) { - return alloc_huge_page_vma(page_hstate(compound_head(page)), + if (folio_test_hugetlb(src)) + return alloc_huge_page_vma(page_hstate(&src->page), vma, address); - } else if (PageTransHuge(page)) { - struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } + if (folio_test_large(src)) + gfp = GFP_TRANSHUGE; + /* - * if !vma, alloc_page_vma() will use task or system default policy + * if !vma, vma_alloc_folio() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, - vma, address); + dst = vma_alloc_folio(gfp, folio_order(src), vma, address, + folio_test_large(src)); + return &dst->page; } #else @@ -2227,6 +2224,19 @@ out: } EXPORT_SYMBOL(alloc_pages_vma); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage) +{ + struct folio *folio; + + folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr, + hugepage); + if (folio && order > 1) + prep_transhuge_page(&folio->page); + + return folio; +} + /** * alloc_pages - Allocate pages. * @gfp: GFP flags. @@ -2733,6 +2743,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index 3d60823afd2d..6c31ee1e1c9b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -246,7 +246,7 @@ static bool remove_migration_pte(struct folio *folio, set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } if (vma->vm_flags & VM_LOCKED) - mlock_page_drain(smp_processor_id()); + mlock_page_drain_local(); trace_remove_migration_pte(pvmw.address, pte_val(pte), compound_order(new)); @@ -1520,10 +1520,11 @@ out: struct page *alloc_migration_target(struct page *page, unsigned long private) { + struct folio *folio = page_folio(page); struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; - struct page *new_page = NULL; + struct folio *new_folio = NULL; int nid; int zidx; @@ -1531,34 +1532,31 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) - nid = page_to_nid(page); + nid = folio_nid(folio); - if (PageHuge(page)) { - struct hstate *h = page_hstate(compound_head(page)); + if (folio_test_hugetlb(folio)) { + struct hstate *h = page_hstate(&folio->page); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); } - if (PageTransHuge(page)) { + if (folio_test_large(folio)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; + order = folio_order(folio); } - zidx = zone_idx(page_zone(page)); + zidx = zone_idx(folio_zone(folio)); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; - new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); + new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask); - return new_page; + return &new_folio->page; } #ifdef CONFIG_NUMA @@ -1999,32 +1997,20 @@ static struct page *alloc_misplaced_dst_page(struct page *page, unsigned long data) { int nid = (int) data; - struct page *newpage; - - newpage = __alloc_pages_node(nid, - (GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE | __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_NOWARN) & - ~__GFP_RECLAIM, 0); - - return newpage; -} - -static struct page *alloc_misplaced_dst_page_thp(struct page *page, - unsigned long data) -{ - int nid = (int) data; - struct page *newpage; - - newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!newpage) - goto out; - - prep_transhuge_page(newpage); + int order = compound_order(page); + gfp_t gfp = __GFP_THISNODE; + struct folio *new; + + if (order > 0) + gfp |= GFP_TRANSHUGE_LIGHT; + else { + gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN; + gfp &= ~__GFP_RECLAIM; + } + new = __folio_alloc_node(gfp, order, nid); -out: - return newpage; + return &new->page; } static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) @@ -2082,23 +2068,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - new_page_t *new; - bool compound; int nr_pages = thp_nr_pages(page); /* - * PTE mapped THP or HugeTLB page can't reach here so the page could - * be either base page or THP. And it must be head page if it is - * THP. - */ - compound = PageTransHuge(page); - - if (compound) - new = alloc_misplaced_dst_page_thp; - else - new = alloc_misplaced_dst_page; - - /* * Don't migrate file pages that are mapped in multiple processes * with execute permissions as they are probably shared libraries. */ @@ -2118,9 +2090,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, - &nr_succeeded); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mlock.c b/mm/mlock.c index 529fbc1f27c8..716caf851043 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -28,7 +28,14 @@ #include "internal.h" -static DEFINE_PER_CPU(struct pagevec, mlock_pvec); +struct mlock_pvec { + local_lock_t lock; + struct pagevec vec; +}; + +static DEFINE_PER_CPU(struct mlock_pvec, mlock_pvec) = { + .lock = INIT_LOCAL_LOCK(lock), +}; bool can_do_mlock(void) { @@ -203,18 +210,30 @@ static void mlock_pagevec(struct pagevec *pvec) pagevec_reinit(pvec); } -void mlock_page_drain(int cpu) +void mlock_page_drain_local(void) +{ + struct pagevec *pvec; + + local_lock(&mlock_pvec.lock); + pvec = this_cpu_ptr(&mlock_pvec.vec); + if (pagevec_count(pvec)) + mlock_pagevec(pvec); + local_unlock(&mlock_pvec.lock); +} + +void mlock_page_drain_remote(int cpu) { struct pagevec *pvec; - pvec = &per_cpu(mlock_pvec, cpu); + WARN_ON_ONCE(cpu_online(cpu)); + pvec = &per_cpu(mlock_pvec.vec, cpu); if (pagevec_count(pvec)) mlock_pagevec(pvec); } bool need_mlock_page_drain(int cpu) { - return pagevec_count(&per_cpu(mlock_pvec, cpu)); + return pagevec_count(&per_cpu(mlock_pvec.vec, cpu)); } /** @@ -223,7 +242,10 @@ bool need_mlock_page_drain(int cpu) */ void mlock_folio(struct folio *folio) { - struct pagevec *pvec = &get_cpu_var(mlock_pvec); + struct pagevec *pvec; + + local_lock(&mlock_pvec.lock); + pvec = this_cpu_ptr(&mlock_pvec.vec); if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); @@ -236,7 +258,7 @@ void mlock_folio(struct folio *folio) if (!pagevec_add(pvec, mlock_lru(&folio->page)) || folio_test_large(folio) || lru_cache_disabled()) mlock_pagevec(pvec); - put_cpu_var(mlock_pvec); + local_unlock(&mlock_pvec.lock); } /** @@ -245,9 +267,11 @@ void mlock_folio(struct folio *folio) */ void mlock_new_page(struct page *page) { - struct pagevec *pvec = &get_cpu_var(mlock_pvec); + struct pagevec *pvec; int nr_pages = thp_nr_pages(page); + local_lock(&mlock_pvec.lock); + pvec = this_cpu_ptr(&mlock_pvec.vec); SetPageMlocked(page); mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); @@ -256,7 +280,7 @@ void mlock_new_page(struct page *page) if (!pagevec_add(pvec, mlock_new(page)) || PageHead(page) || lru_cache_disabled()) mlock_pagevec(pvec); - put_cpu_var(mlock_pvec); + local_unlock(&mlock_pvec.lock); } /** @@ -265,8 +289,10 @@ void mlock_new_page(struct page *page) */ void munlock_page(struct page *page) { - struct pagevec *pvec = &get_cpu_var(mlock_pvec); + struct pagevec *pvec; + local_lock(&mlock_pvec.lock); + pvec = this_cpu_ptr(&mlock_pvec.vec); /* * TestClearPageMlocked(page) must be left to __munlock_page(), * which will check whether the page is multiply mlocked. @@ -276,7 +302,7 @@ void munlock_page(struct page *page) if (!pagevec_add(pvec, page) || PageHead(page) || lru_cache_disabled()) mlock_pagevec(pvec); - put_cpu_var(mlock_pvec); + local_unlock(&mlock_pvec.lock); } static int mlock_pte_range(pmd_t *pmd, unsigned long addr, diff --git a/mm/mremap.c b/mm/mremap.c index 9d76da79594d..303d3290b938 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, pmd_t *old_pmd, *new_pmd; pud_t *old_pud, *new_pud; + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6c6af8658775..33ca8cab21e6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -128,7 +128,7 @@ static DEFINE_MUTEX(pcp_batch_high_lock); struct pagesets { local_lock_t lock; }; -static DEFINE_PER_CPU(struct pagesets, pagesets) __maybe_unused = { +static DEFINE_PER_CPU(struct pagesets, pagesets) = { .lock = INIT_LOCAL_LOCK(lock), }; @@ -6131,7 +6131,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) do { zone_type--; zone = pgdat->node_zones + zone_type; - if (managed_zone(zone)) { + if (populated_zone(zone)) { zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } @@ -8367,6 +8367,7 @@ static int page_alloc_cpu_dead(unsigned int cpu) struct zone *zone; lru_add_drain_cpu(cpu); + mlock_page_drain_remote(cpu); drain_pages(cpu); /* diff --git a/mm/page_io.c b/mm/page_io.c index b417f000b49e..89fbf3cae30f 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -51,54 +51,6 @@ void end_swap_bio_write(struct bio *bio) bio_put(bio); } -static void swap_slot_free_notify(struct page *page) -{ - struct swap_info_struct *sis; - struct gendisk *disk; - swp_entry_t entry; - - /* - * There is no guarantee that the page is in swap cache - the software - * suspend code (at least) uses end_swap_bio_read() against a non- - * swapcache page. So we must check PG_swapcache before proceeding with - * this optimization. - */ - if (unlikely(!PageSwapCache(page))) - return; - - sis = page_swap_info(page); - if (data_race(!(sis->flags & SWP_BLKDEV))) - return; - - /* - * The swap subsystem performs lazy swap slot freeing, - * expecting that the page will be swapped out again. - * So we can avoid an unnecessary write if the page - * isn't redirtied. - * This is good for real swap storage because we can - * reduce unnecessary I/O and enhance wear-leveling - * if an SSD is used as the as swap device. - * But if in-memory swap device (eg zram) is used, - * this causes a duplicated copy between uncompressed - * data in VM-owned memory and compressed data in - * zram-owned memory. So let's free zram-owned memory - * and make the VM-owned decompressed page *dirty*, - * so the page should be swapped out somewhere again if - * we again wish to reclaim it. - */ - disk = sis->bdev->bd_disk; - entry.val = page_private(page); - if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { - unsigned long offset; - - offset = swp_offset(entry); - - SetPageDirty(page); - disk->fops->swap_slot_free_notify(sis->bdev, - offset); - } -} - static void end_swap_bio_read(struct bio *bio) { struct page *page = bio_first_page_all(bio); @@ -114,7 +66,6 @@ static void end_swap_bio_read(struct bio *bio) } SetPageUptodate(page); - swap_slot_free_notify(page); out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); @@ -394,11 +345,6 @@ int swap_readpage(struct page *page, bool synchronous) if (sis->flags & SWP_SYNCHRONOUS_IO) { ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - if (trylock_page(page)) { - swap_slot_free_notify(page); - unlock_page(page); - } - count_vm_event(PSWPIN); goto out; } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 1187f9c1ec5b..14a5cda73dee 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -163,7 +163,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { - unsigned long size = pvmw->nr_pages * PAGE_SIZE; + struct hstate *hstate = hstate_vma(vma); + unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); @@ -173,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm, - pvmw->pte); + pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); diff --git a/mm/readahead.c b/mm/readahead.c index d3a47546d17d..8e3775829513 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -13,29 +13,29 @@ * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever - * attempts to read pages that are not yet in the page cache. If a - * page is present but not up-to-date, readahead will not try to read + * attempts to read folios that are not yet in the page cache. If a + * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->readpage() will be requested. * * Readahead is triggered when an application read request (whether a - * systemcall or a page fault) finds that the requested page is not in + * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the - * %PG_readahead flag set. This flag indicates that the page was loaded - * as part of a previous read-ahead request and now that it has been - * accessed, it is time for the next read-ahead. + * readahead flag set. This flag indicates that the folio was read + * as part of a previous readahead request and now that it has been + * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async - * read-ahead. This is reflected in the struct file_ra_state which - * contains ->size being to total number of pages, and ->async_size - * which is the number of pages in the async section. The first page in - * this async section will have %PG_readahead set as a trigger for a - * subsequent read ahead. Once a series of sequential reads has been + * readahead. This is reflected in the struct file_ra_state which + * contains ->size being the total number of pages, and ->async_size + * which is the number of pages in the async section. The readahead + * flag will be set on the first folio in this async section to trigger + * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and - * all read ahead request will be fully asynchronous. + * all readahead request will be fully asynchronous. * - * When either of the triggers causes a readahead, three numbers need to - * be determined: the start of the region, the size of the region, and - * the size of the async tail. + * When either of the triggers causes a readahead, three numbers need + * to be determined: the start of the region to read, the size of the + * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page @@ -45,14 +45,14 @@ * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED - * PAGE. + * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead - * was triggered by the %PG_readahead flag, the size of the previous + * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new @@ -65,52 +65,52 @@ * larger than the current request, and it is not scaled up, unless it * is at the start of file. * - * In general read ahead is accelerated at the start of the file, as + * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor - * adjustments to the read ahead size in various special cases and these + * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * - * The above calculation determines the readahead, to which any requested - * read size may be added. + * The above calculation, based on the previous readahead size, + * determines the size of the readahead, to which any requested read + * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all - * pages, but may fail to read any or all pages without causing an IO + * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->readpage() request - * for any page which ->readahead() does not provided, and only an error + * for any folio which ->readahead() did not read, and only an error * from this will be final. * - * ->readahead() will generally call readahead_page() repeatedly to get - * each page from those prepared for read ahead. It may fail to read a - * page by: + * ->readahead() will generally call readahead_folio() repeatedly to get + * each folio from those prepared for readahead. It may fail to read a + * folio by: * - * * not calling readahead_page() sufficiently many times, effectively - * ignoring some pages, as might be appropriate if the path to + * * not calling readahead_folio() sufficiently many times, effectively + * ignoring some folios, as might be appropriate if the path to * storage is congested. * - * * failing to actually submit a read request for a given page, + * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * - * In the last two cases, the page should be unlocked to indicate that - * the read attempt has failed. In the first case the page will be - * unlocked by the caller. + * In the last two cases, the folio should be unlocked by the filesystem + * to indicate that the read attempt has failed. In the first case the + * folio will be unlocked by the VFS. * - * Those pages not in the final ``async_size`` of the request should be + * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to - * become available. Pages in the final ``async_size`` may be + * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. - * In this case it is best to use delete_from_page_cache() to remove the - * pages from the page cache as is automatically done for pages that - * were not fetched with readahead_page(). This will allow a - * subsequent synchronous read ahead request to try them again. If they + * In this case it is best to use filemap_remove_folio() to remove the + * folios from the page cache as is automatically done for folios that + * were not fetched with readahead_folio(). This will allow a + * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using - * ->readpage(). - * + * ->readpage() which may be less efficient. */ #include <linux/kernel.h> @@ -142,91 +142,14 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) } EXPORT_SYMBOL_GPL(file_ra_state_init); -/* - * see if a page needs releasing upon read_cache_pages() failure - * - the caller of read_cache_pages() may have set PG_private or PG_fscache - * before calling, such as the NFS fs marking pages that are cached locally - * on disk, thus we need to give the fs a chance to clean up in the event of - * an error - */ -static void read_cache_pages_invalidate_page(struct address_space *mapping, - struct page *page) -{ - if (page_has_private(page)) { - if (!trylock_page(page)) - BUG(); - page->mapping = mapping; - folio_invalidate(page_folio(page), 0, PAGE_SIZE); - page->mapping = NULL; - unlock_page(page); - } - put_page(page); -} - -/* - * release a list of pages, invalidating them first if need be - */ -static void read_cache_pages_invalidate_pages(struct address_space *mapping, - struct list_head *pages) -{ - struct page *victim; - - while (!list_empty(pages)) { - victim = lru_to_page(pages); - list_del(&victim->lru); - read_cache_pages_invalidate_page(mapping, victim); - } -} - -/** - * read_cache_pages - populate an address space with some pages & start reads against them - * @mapping: the address_space - * @pages: The address of a list_head which contains the target pages. These - * pages have their ->index populated and are otherwise uninitialised. - * @filler: callback routine for filling a single page. - * @data: private data for the callback routine. - * - * Hides the details of the LRU cache etc from the filesystems. - * - * Returns: %0 on success, error return by @filler otherwise - */ -int read_cache_pages(struct address_space *mapping, struct list_head *pages, - int (*filler)(void *, struct page *), void *data) -{ - struct page *page; - int ret = 0; - - while (!list_empty(pages)) { - page = lru_to_page(pages); - list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, page->index, - readahead_gfp_mask(mapping))) { - read_cache_pages_invalidate_page(mapping, page); - continue; - } - put_page(page); - - ret = filler(data, page); - if (unlikely(ret)) { - read_cache_pages_invalidate_pages(mapping, pages); - break; - } - task_io_account_read(PAGE_SIZE); - } - return ret; -} - -EXPORT_SYMBOL(read_cache_pages); - -static void read_pages(struct readahead_control *rac, struct list_head *pages, - bool skip_page) +static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct page *page; struct blk_plug plug; if (!readahead_count(rac)) - goto out; + return; blk_start_plug(&plug); @@ -234,7 +157,7 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages, aops->readahead(rac); /* * Clean up the remaining pages. The sizes in ->ra - * maybe be used to size next read-ahead, so make sure + * may be used to size the next readahead, so make sure * they accurately reflect what happened. */ while ((page = readahead_page(rac))) { @@ -246,13 +169,6 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages, unlock_page(page); put_page(page); } - } else if (aops->readpages) { - aops->readpages(rac->file, rac->mapping, pages, - readahead_count(rac)); - /* Clean up the remaining pages */ - put_pages_list(pages); - rac->_index += rac->_nr_pages; - rac->_nr_pages = 0; } else { while ((page = readahead_page(rac))) { aops->readpage(rac->file, page); @@ -262,12 +178,7 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages, blk_finish_plug(&plug); - BUG_ON(pages && !list_empty(pages)); BUG_ON(readahead_count(rac)); - -out: - if (skip_page) - rac->_index++; } /** @@ -289,7 +200,6 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); - LIST_HEAD(page_pool); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long i; @@ -321,7 +231,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * have a stable reference to this page, and it's * not worth getting one just for that. */ - read_pages(ractl, &page_pool, true); + read_pages(ractl); + ractl->_index++; i = ractl->_index + ractl->_nr_pages - index - 1; continue; } @@ -329,13 +240,11 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, folio = filemap_alloc_folio(gfp_mask, 0); if (!folio) break; - if (mapping->a_ops->readpages) { - folio->index = index + i; - list_add(&folio->lru, &page_pool); - } else if (filemap_add_folio(mapping, folio, index + i, + if (filemap_add_folio(mapping, folio, index + i, gfp_mask) < 0) { folio_put(folio); - read_pages(ractl, &page_pool, true); + read_pages(ractl); + ractl->_index++; i = ractl->_index + ractl->_nr_pages - index - 1; continue; } @@ -349,7 +258,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * uptodate then the caller will launch readpage again, and * will then handle the error. */ - read_pages(ractl, &page_pool, false); + read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } @@ -394,8 +303,7 @@ void force_page_cache_ra(struct readahead_control *ractl, struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages, index; - if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages && - !mapping->a_ops->readahead)) + if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readahead)) return; /* @@ -512,7 +420,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, } /* - * page cache context based read-ahead + * page cache context based readahead */ static int try_context_readahead(struct address_space *mapping, struct file_ra_state *ra, @@ -624,7 +532,7 @@ void page_cache_ra_order(struct readahead_control *ractl, ra->async_size += index - limit - 1; } - read_pages(ractl, NULL, false); + read_pages(ractl); /* * If there were already pages in the page cache, then we may have @@ -763,9 +671,9 @@ void page_cache_sync_ra(struct readahead_control *ractl, bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); /* - * Even if read-ahead is disabled, issue this request as read-ahead + * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced - * read-ahead will do the right thing and limit the read to just the + * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ractl->ra->ra_pages || blk_cgroup_congested()) { @@ -781,7 +689,6 @@ void page_cache_sync_ra(struct readahead_control *ractl, return; } - /* do read-ahead */ ondemand_readahead(ractl, NULL, req_count); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); @@ -789,7 +696,7 @@ EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { - /* no read-ahead */ + /* no readahead */ if (!ractl->ra->ra_pages) return; @@ -804,7 +711,6 @@ void page_cache_async_ra(struct readahead_control *ractl, if (blk_cgroup_congested()) return; - /* do read-ahead */ ondemand_readahead(ractl, folio, req_count); } EXPORT_SYMBOL_GPL(page_cache_async_ra); diff --git a/mm/rmap.c b/mm/rmap.c index 5cb970d51f0a..fedb82371efe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1683,7 +1683,7 @@ discard: */ page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); if (vma->vm_flags & VM_LOCKED) - mlock_page_drain(smp_processor_id()); + mlock_page_drain_local(); folio_put(folio); } @@ -1961,7 +1961,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, */ page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); if (vma->vm_flags & VM_LOCKED) - mlock_page_drain(smp_processor_id()); + mlock_page_drain_local(); folio_put(folio); } diff --git a/mm/secretmem.c b/mm/secretmem.c index 098638d3b8a4..3b3cf2892b6a 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -158,6 +158,22 @@ const struct address_space_operations secretmem_aops = { .isolate_page = secretmem_isolate_page, }; +static int secretmem_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + unsigned int ia_valid = iattr->ia_valid; + + if ((ia_valid & ATTR_SIZE) && inode->i_size) + return -EINVAL; + + return simple_setattr(mnt_userns, dentry, iattr); +} + +static const struct inode_operations secretmem_iops = { + .setattr = secretmem_setattr, +}; + static struct vfsmount *secretmem_mnt; static struct file *secretmem_file_create(unsigned long flags) @@ -177,6 +193,7 @@ static struct file *secretmem_file_create(unsigned long flags) mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); + inode->i_op = &secretmem_iops; inode->i_mapping->a_ops = &secretmem_aops; /* pretend we are a normal file with zero size */ diff --git a/mm/shmem.c b/mm/shmem.c index 529c9ad3e926..4b2fea33158e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2513,7 +2513,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) pgoff_t end_index; unsigned long nr, ret; loff_t i_size = i_size_read(inode); - bool got_page; end_index = i_size >> PAGE_SHIFT; if (index > end_index) @@ -2570,24 +2569,34 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) */ if (!offset) mark_page_accessed(page); - got_page = true; + /* + * Ok, we have the page, and it's up-to-date, so + * now we can copy it to user space... + */ + ret = copy_page_to_iter(page, offset, nr, to); + put_page(page); + + } else if (iter_is_iovec(to)) { + /* + * Copy to user tends to be so well optimized, but + * clear_user() not so much, that it is noticeably + * faster to copy the zero page instead of clearing. + */ + ret = copy_page_to_iter(ZERO_PAGE(0), offset, nr, to); } else { - page = ZERO_PAGE(0); - got_page = false; + /* + * But submitting the same page twice in a row to + * splice() - or others? - can result in confusion: + * so don't attempt that optimization on pipes etc. + */ + ret = iov_iter_zero(nr, to); } - /* - * Ok, we have the page, and it's up-to-date, so - * now we can copy it to user space... - */ - ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; - if (got_page) - put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { diff --git a/mm/slab.c b/mm/slab.c index b04e40078bdf..0edb474edef1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3665,7 +3665,7 @@ EXPORT_SYMBOL(__kmalloc_node_track_caller); #endif /* CONFIG_NUMA */ #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { struct kmem_cache *cachep; unsigned int objnr; diff --git a/mm/slab.h b/mm/slab.h index fd7ae2024897..95eb34174c1b 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -868,7 +868,7 @@ struct kmem_obj_info { void *kp_stack[KS_ADDRS_COUNT]; void *kp_free_stack[KS_ADDRS_COUNT]; }; -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR diff --git a/mm/slab_common.c b/mm/slab_common.c index 6ee64d6208b3..2b3206a2c3b5 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -555,6 +555,13 @@ bool kmem_valid_obj(void *object) } EXPORT_SYMBOL_GPL(kmem_valid_obj); +static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + if (__kfence_obj_info(kpp, object, slab)) + return; + __kmem_obj_info(kpp, object, slab); +} + /** * kmem_dump_obj - Print available slab provenance information * @object: slab object for which to find provenance information. @@ -590,6 +597,8 @@ void kmem_dump_obj(void *object) pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name); else pr_cont(" slab%s", cp); + if (is_kfence_address(object)) + pr_cont(" (kfence)"); if (kp.kp_objp) pr_cont(" start %px", kp.kp_objp); if (kp.kp_data_offset) diff --git a/mm/slob.c b/mm/slob.c index dfa6808dff36..40ea6e2d4ccd 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -463,7 +463,7 @@ out: } #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { kpp->kp_ptr = object; kpp->kp_slab = slab; diff --git a/mm/slub.c b/mm/slub.c index 74d92aa4a3a2..ed5c2c03a47a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4312,7 +4312,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s) } #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { void *base; int __maybe_unused i; diff --git a/mm/swap.c b/mm/swap.c index bceff0cb559c..7e320ec08c6a 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -624,7 +624,6 @@ void lru_add_drain_cpu(int cpu) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); - mlock_page_drain(cpu); } /** @@ -706,6 +705,7 @@ void lru_add_drain(void) local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); + mlock_page_drain_local(); } /* @@ -720,6 +720,7 @@ static void lru_add_and_bh_lrus_drain(void) lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); invalidate_bh_lrus_cpu(); + mlock_page_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) @@ -728,6 +729,7 @@ void lru_add_drain_cpu_zone(struct zone *zone) lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&lru_pvecs.lock); + mlock_page_drain_local(); } #ifdef CONFIG_SMP diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e163372d3967..07da85ae825b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1671,17 +1671,6 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); -#ifdef CONFIG_X86_64 -/* - * called before a call to iounmap() if the caller wants vm_area_struct's - * immediately freed. - */ -void set_iounmap_nonlazy(void) -{ - atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); -} -#endif /* CONFIG_X86_64 */ - /* * Purges all lazily-freed vmap areas. */ @@ -3106,7 +3095,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return NULL; } - if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) { + if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { unsigned long size_per_node; /* @@ -3273,21 +3262,24 @@ void *vmalloc(unsigned long size) EXPORT_SYMBOL(vmalloc); /** - * vmalloc_no_huge - allocate virtually contiguous memory using small pages - * @size: allocation size + * vmalloc_huge - allocate virtually contiguous memory, allow huge pages + * @size: allocation size + * @gfp_mask: flags for the page level allocator * - * Allocate enough non-huge pages to cover @size from the page level + * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. + * If @size is greater than or equal to PMD_SIZE, allow using + * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_no_huge(unsigned long size) +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL, VM_NO_HUGE_VMAP, + gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_no_huge); +EXPORT_SYMBOL_GPL(vmalloc_huge); /** * vzalloc - allocate virtually contiguous memory with zero fill diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8cc44c367231..18affda2b522 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -353,6 +353,8 @@ static int br_switchdev_vlan_attr_replay(struct net_device *br_dev, attr.orig_dev = br_dev; vg = br_vlan_group(br); + if (!vg) + return 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti) { diff --git a/net/can/isotp.c b/net/can/isotp.c index bafb0fb5f0e0..ff5d7870294e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -906,6 +906,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; + s64 hrtimer_sec = 0; int off; int err; @@ -1004,7 +1005,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) isotp_create_fframe(cf, so, ae); /* start timeout for FC */ - hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + hrtimer_sec = 1; + hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + HRTIMER_MODE_REL_SOFT); } /* send the first or only CAN frame */ @@ -1017,6 +1020,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); + + /* no transmission -> no timeout monitoring */ + if (hrtimer_sec) + hrtimer_cancel(&so->txtimer); + goto err_out_drop; } diff --git a/net/core/dev.c b/net/core/dev.c index 8c6c08446556..1461c2d9dec8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10304,7 +10304,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; @@ -10315,11 +10315,7 @@ struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ - p = READ_ONCE(dev->core_stats); - if (!p) - return NULL; - - return this_cpu_ptr(p); + return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); @@ -10356,9 +10352,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); - storage->rx_dropped += local_read(&core_stats->rx_dropped); - storage->tx_dropped += local_read(&core_stats->tx_dropped); - storage->rx_nohandler += local_read(&core_stats->rx_nohandler); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); } } return storage; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 03b6e649c428..6f7ec72016dc 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1032,7 +1032,7 @@ bool __skb_flow_dissect(const struct net *net, key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); - memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); + memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } proto_again: @@ -1183,6 +1183,7 @@ proto_again: VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; + key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 159c9c61e6af..d1381ea6d52e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5242,6 +5242,8 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, *prividx = attr_id_l3_stats; size_l3 = rtnl_offload_xstats_get_size_stats(dev, t_l3); + if (!size_l3) + goto skip_l3_stats; attr = nla_reserve_64bit(skb, attr_id_l3_stats, size_l3, IFLA_OFFLOAD_XSTATS_UNSPEC); if (!attr) @@ -5253,6 +5255,7 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, return err; have_data = true; +skip_l3_stats: *prividx = 0; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index ca6af86964bc..cf933225df32 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -562,7 +562,6 @@ static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; struct dsa_switch *ds = dp->ds; - struct net_device *slave; if (!dp->setup) return; @@ -584,11 +583,9 @@ static void dsa_port_teardown(struct dsa_port *dp) dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - slave = dp->slave; - - if (slave) { + if (dp->slave) { + dsa_slave_destroy(dp->slave); dp->slave = NULL; - dsa_slave_destroy(slave); } break; } @@ -1147,17 +1144,17 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_cpu_ports; - err = dsa_tree_setup_master(dst); + err = dsa_tree_setup_ports(dst); if (err) goto teardown_switches; - err = dsa_tree_setup_ports(dst); + err = dsa_tree_setup_master(dst); if (err) - goto teardown_master; + goto teardown_ports; err = dsa_tree_setup_lags(dst); if (err) - goto teardown_ports; + goto teardown_master; dst->setup = true; @@ -1165,10 +1162,10 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) return 0; -teardown_ports: - dsa_tree_teardown_ports(dst); teardown_master: dsa_tree_teardown_master(dst); +teardown_ports: + dsa_tree_teardown_ports(dst); teardown_switches: dsa_tree_teardown_switches(dst); teardown_cpu_ports: @@ -1186,10 +1183,10 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_lags(dst); - dsa_tree_teardown_ports(dst); - dsa_tree_teardown_master(dst); + dsa_tree_teardown_ports(dst); + dsa_tree_teardown_switches(dst); dsa_tree_teardown_cpu_ports(dst); diff --git a/net/dsa/port.c b/net/dsa/port.c index 32d472a82241..cdc56ba11f52 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1620,8 +1620,10 @@ int dsa_port_link_register_of(struct dsa_port *dp) if (ds->ops->phylink_mac_link_down) ds->ops->phylink_mac_link_down(ds, port, MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + of_node_put(phy_np); return dsa_port_phylink_register(dp); } + of_node_put(phy_np); return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 41c69a6e7854..8022d50584db 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -285,7 +285,7 @@ static void dsa_port_manage_cpu_flood(struct dsa_port *dp) if (other_dp->slave->flags & IFF_ALLMULTI) flags.val |= BR_MCAST_FLOOD; if (other_dp->slave->flags & IFF_PROMISC) - flags.val |= BR_FLOOD; + flags.val |= BR_FLOOD | BR_MCAST_FLOOD; } err = dsa_port_pre_bridge_flags(dp, flags, NULL); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index f64b805303cd..eb204ad36eee 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 *tag; + /* Calculate checksums (if required) before adding the trailer tag to + * avoid including it in calculations. That would lead to wrong + * checksums after the switch strips the tag. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, HELLCREEK_TAG_LEN); *tag = BIT(dp->index); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 70e6c87fbe3d..d747166bb291 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { @@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 99db2e41ed10..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -504,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -581,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -605,8 +603,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - key->tos & ~INET_ECN_MASK, 0, skb->mark, - skb_get_hash(skb)); + key->tos & ~INET_ECN_MASK, dev_net(dev), 0, + skb->mark, skb_get_hash(skb)); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 5a473319d3a5..94017a8c3994 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark, 0); + RT_TOS(iph->tos), dev_net(dev), + tunnel->parms.link, tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - 0, skb->mark, skb_get_hash(skb)); + dev_net(dev), 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; @@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->parms.o_key, RT_TOS(tos), + dev_net(dev), tunnel->parms.link, tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ /dev/null diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2088f93fa37b..48f607522860 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5454,7 +5454,17 @@ static void tcp_new_space(struct sock *sk) INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6366df7aaf2a..6854bb1fb32b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9ede847f4199..1ca2f28c9981 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index fbab921670cc..9a8e014d9b5b 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently - * sent skb, i.e., the skb with the highest prior_delivered count. + * sent skb, i.e., the skb with the most recently sent time and the highest + * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; + tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || - after(scb->tx.delivered, rs->prior_delivered)) { + tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, + scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); + tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 55d604c9b3b3..f2120e92caf1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -482,7 +482,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; if (x->encap) { int err = esp6_output_encap(x, skb, esp); @@ -491,8 +490,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 8753e9cec326..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -724,6 +724,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -733,16 +734,13 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) - return -ENOMEM; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; + int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); if (IS_ERR(tun_info) || @@ -760,21 +758,27 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, dsfield = key->tos; flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); - tunnel->tun_hlen = gre_calc_hlen(flags); + tun_hlen = gre_calc_hlen(flags); - gre_build_header(skb, tunnel->tun_hlen, + if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) + return -ENOMEM; + + gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + + flags = tunnel->parms.o_flags; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1052,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e23f058166af..fa63ef2bd99c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -485,7 +485,7 @@ int ip6_forward(struct sk_buff *skb) goto drop; if (!net->ipv6.devconf_all->disable_policy && - !idev->cnf.disable_policy && + (!idev || !idev->cnf.disable_policy) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1da332450d98..8ce60ab89015 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,14 +24,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { - .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, @@ -39,6 +38,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + if (sk && sk->sk_bound_dev_if) + fl6.flowi6_oif = sk->sk_bound_dev_if; + else if (strict) + fl6.flowi6_oif = dev->ifindex; + else + fl6.flowi6_oif = l3mdev_master_ifindex(dev); + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 169e9df6d172..c4b6ce017d5e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3292,6 +3292,7 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + unsigned int val; int entries; entries = dst_entries_get_fast(ops); @@ -3302,13 +3303,13 @@ static int ip6_dst_gc(struct dst_ops *ops) entries <= rt_max_size) goto out; - net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) - net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; + atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: - net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + val = atomic_read(&net->ipv6.ip6_rt_gc_expire); + atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); return entries > rt_max_size; } @@ -6509,7 +6510,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; - net->ipv6.ip6_rt_gc_expire = 30*HZ; + atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 4eb8892fb2ff..ca10916340b0 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -147,7 +147,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) dev = dev_get_by_index_rcu(net, ifindex); while (dev && !netif_is_l3_master(dev)) - dev = netdev_master_upper_dev_get(dev); + dev = netdev_master_upper_dev_get_rcu(dev); return dev ? dev->ifindex : 0; } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 9479f2787ea7..88d9cc945a21 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -441,7 +441,7 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, #define PRINT_HT_CAP(_cond, _str) \ do { \ if (_cond) \ - p += scnprintf(p, sizeof(buf)+buf-p, "\t" _str "\n"); \ + p += scnprintf(p, bufsz + buf - p, "\t" _str "\n"); \ } while (0) char *buf, *p; int i; diff --git a/net/mctp/device.c b/net/mctp/device.c index f49be882e98e..99a3bda8852f 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -313,6 +313,7 @@ void mctp_dev_hold(struct mctp_dev *mdev) void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { + kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } @@ -441,7 +442,6 @@ static void mctp_unregister(struct net_device *dev) mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); - kfree(mdev->addrs); mctp_dev_put(mdev); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 2c467c422dc6..fb67f1ca2495 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,7 +1495,7 @@ int __init ip_vs_conn_init(void) pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(struct list_head))/1024); + (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 128ee3b300d6..16c3a39689f4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9363,7 +9363,7 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -static unsigned int nft_parse_register(const struct nlattr *attr, u32 *preg) +static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index d600a566da32..7325bee7d144 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -349,7 +349,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, *ext = &rbe->ext; return -EEXIST; } else { - p = &parent->rb_left; + overlap = false; + if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; } } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index bd3792f080ed..6d9e8e0a3a7d 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -37,12 +37,11 @@ static void nft_socket_wildcard(const struct nft_pktinfo *pkt, #ifdef CONFIG_SOCK_CGROUP_DATA static noinline bool -nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level) +nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level) { - struct sock *sk = skb_to_full_sk(pkt->skb); struct cgroup *cgrp; - if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk))) + if (!sk_fullsock(sk)) return false; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); @@ -109,7 +108,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; #ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: - if (!nft_sock_get_eval_cgroupv2(dest, pkt, priv->level)) { + if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 47a876ccd288..05a3795eac8e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2263,6 +2263,13 @@ static int netlink_dump(struct sock *sk) * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); + + /* Make sure malicious BPF programs can not read unitialized memory + * from skb->head -> skb->data + */ + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index d2537383a3e8..6a193cce2a75 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -560,6 +560,10 @@ static int nci_close_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { + /* Need to flush the cmd wq in case + * there is a queued/running cmd_work + */ + flush_workqueue(ndev->cmd_wq); del_timer_sync(&ndev->cmd_timer); del_timer_sync(&ndev->data_timer); mutex_unlock(&ndev->req_lock); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7176156d3844..4c09cf8a0ab2 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2465,7 +2465,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c39c09899fd0..002d2b9c69dd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2858,8 +2858,9 @@ tpacket_error: status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -3060,8 +3061,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->no_fcs = 1; err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + } dev_put(dev); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index f15d6942da45..cc7e30733feb 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -113,7 +113,9 @@ static __net_exit void rxrpc_exit_net(struct net *net) struct rxrpc_net *rxnet = rxrpc_net(net); rxnet->live = false; + del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + /* Remove the timer again as the worker may have restarted it. */ del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2957f8f5cea7..f0699f39afdb 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1672,10 +1672,10 @@ static int tcf_chain_tp_insert(struct tcf_chain *chain, if (chain->flushing) return -EAGAIN; + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); if (*chain_info->pprev == chain->filter_chain) tcf_chain0_head_change(chain, tp); tcf_proto_get(tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); return 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c80fc49c0da1..ed5e6f08e74a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1013,6 +1013,7 @@ static int fl_set_key_mpls(struct nlattr **tb, static void fl_set_key_vlan(struct nlattr **tb, __be16 ethertype, int vlan_id_key, int vlan_prio_key, + int vlan_next_eth_type_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { @@ -1031,6 +1032,11 @@ static void fl_set_key_vlan(struct nlattr **tb, } key_val->vlan_tpid = ethertype; key_mask->vlan_tpid = cpu_to_be16(~0); + if (tb[vlan_next_eth_type_key]) { + key_val->vlan_eth_type = + nla_get_be16(tb[vlan_next_eth_type_key]); + key_mask->vlan_eth_type = cpu_to_be16(~0); + } } static void fl_set_key_flag(u32 flower_key, u32 flower_mask, @@ -1602,8 +1608,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (eth_type_vlan(ethertype)) { fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, - TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, - &mask->vlan); + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &key->vlan, &mask->vlan); if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) { ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]); @@ -1611,6 +1618,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_CVLAN_ID, TCA_FLOWER_KEY_CVLAN_PRIO, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, &key->cvlan, &mask->cvlan); fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, @@ -3002,13 +3010,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (mask->basic.n_proto) { - if (mask->cvlan.vlan_tpid) { + if (mask->cvlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, key->basic.n_proto)) goto nla_put_failure; - } else if (mask->vlan.vlan_tpid) { + } else if (mask->vlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, - key->basic.n_proto)) + key->vlan.vlan_eth_type)) goto nla_put_failure; } } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index cf5649292ee0..4d27300c287c 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -386,14 +386,19 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) +static void __u32_destroy_key(struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - tcf_exts_put_net(&n->exts); if (ht && --ht->refcnt == 0) kfree(ht); + kfree(n); +} + +static void u32_destroy_key(struct tc_u_knode *n, bool free_pf) +{ + tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -402,8 +407,7 @@ static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) if (free_pf) free_percpu(n->pcpu_success); #endif - kfree(n); - return 0; + __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied @@ -811,10 +815,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); - /* bump reference count as long as we hold pointer to structure */ - if (ht) - ht->refcnt++; - #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed @@ -836,6 +836,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, return NULL; } + /* bump reference count as long as we hold pointer to structure */ + if (ht) + ht->refcnt++; + return new; } @@ -900,13 +904,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 377f896bdedc..b9c71a304d39 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -417,7 +417,8 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, { struct taprio_sched *q = qdisc_priv(sch); - if (skb->sk && sock_flag(skb->sk, SOCK_TXTIME)) { + /* sk_flags are only safe to use on full sockets. */ + if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) return qdisc_drop(skb, sch, to_free); } else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b3815b568e8e..463c4a58d2c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -458,6 +458,10 @@ void sctp_generate_reconf_event(struct timer_list *t) goto out_unlock; } + /* This happens when the response arrives after the timer is triggered. */ + if (!asoc->strreset_chunk) + goto out_unlock; + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7f342bc12735..52edee1322fc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -781,7 +781,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, } } - if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } @@ -932,7 +932,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, /* Set peer label for connection. */ if (security_sctp_assoc_established((struct sctp_association *)asoc, - chunk->skb)) + chunk->head_skb ?: chunk->skb)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Verify that the chunk length for the COOKIE-ACK is OK. @@ -2262,7 +2262,7 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3e1a9600be5e..7b0427658056 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5636,7 +5636,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) * Set the daddr and initialize id to something more random and also * copy over any ip options. */ - sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk); + sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f0d118e9f155..fce16b9d6e1a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -121,6 +121,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, bool *own_req) { struct smc_sock *smc; + struct sock *child; smc = smc_clcsock_user_data(sk); @@ -134,8 +135,17 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, } /* passthrough to original syn recv sock fct */ - return smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, - own_req); + child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, + own_req); + /* child must not inherit smc or its ops */ + if (child) { + rcu_assign_sk_user_data(child, NULL); + + /* v4-mapped sockets don't inherit parent ops. Don't restore. */ + if (inet_csk(child)->icsk_af_ops == inet_csk(sk)->icsk_af_ops) + inet_csk(child)->icsk_af_ops = smc->ori_af_ops; + } + return child; drop: dst_release(dst); @@ -233,11 +243,27 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_fback_restore_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = NULL; + + smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change); + smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready); + smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space); + smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); +} + static void smc_restore_fallback_changes(struct smc_sock *smc) { if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ smc->clcsock->file->private_data = smc->sk.sk_socket; smc->clcsock->file = NULL; + smc_fback_restore_callbacks(smc); } } @@ -363,6 +389,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); mutex_init(&smc->clcsock_release_lock); + smc_init_saved_callbacks(smc); return sk; } @@ -734,47 +761,73 @@ out: static void smc_fback_state_change(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_state_change); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_data_ready(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_data_ready); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_write_space(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_write_space); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_error_report(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_error_report); + read_unlock_bh(&clcsk->sk_callback_lock); +} + +static void smc_fback_replace_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change, + &smc->clcsk_state_change); + smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready, + &smc->clcsk_data_ready); + smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space, + &smc->clcsk_write_space); + smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report, + &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); } static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { - struct sock *clcsk; int rc = 0; mutex_lock(&smc->clcsock_release_lock); @@ -782,10 +835,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) rc = -EBADF; goto out; } - clcsk = smc->clcsock->sk; - if (smc->use_fallback) - goto out; smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -800,18 +850,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * in smc sk->sk_wq and they should be woken up * as clcsock's wait queue is woken up. */ - smc->clcsk_state_change = clcsk->sk_state_change; - smc->clcsk_data_ready = clcsk->sk_data_ready; - smc->clcsk_write_space = clcsk->sk_write_space; - smc->clcsk_error_report = clcsk->sk_error_report; - - clcsk->sk_state_change = smc_fback_state_change; - clcsk->sk_data_ready = smc_fback_data_ready; - clcsk->sk_write_space = smc_fback_write_space; - clcsk->sk_error_report = smc_fback_error_report; - - smc->clcsock->sk->sk_user_data = - (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_fback_replace_callbacks(smc); } out: mutex_unlock(&smc->clcsock_release_lock); @@ -1465,6 +1504,8 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_state = SMC_CLOSED; if (rc == -EPIPE || rc == -EAGAIN) smc->sk.sk_err = EPIPE; + else if (rc == -ECONNREFUSED) + smc->sk.sk_err = ECONNREFUSED; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); sock_put(&smc->sk); /* passive closing */ @@ -1584,6 +1625,19 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) * function; switch it back to the original sk_data_ready function */ new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; + + /* if new clcsock has also inherited the fallback-specific callback + * functions, switch them back to the original ones. + */ + if (lsmc->use_fallback) { + if (lsmc->clcsk_state_change) + new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change; + if (lsmc->clcsk_write_space) + new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space; + if (lsmc->clcsk_error_report) + new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report; + } + (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -2343,17 +2397,20 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc = - smc_clcsock_user_data(listen_clcsock); + struct smc_sock *lsmc; + read_lock_bh(&listen_clcsock->sk_callback_lock); + lsmc = smc_clcsock_user_data(listen_clcsock); if (!lsmc) - return; + goto out; lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } +out: + read_unlock_bh(&listen_clcsock->sk_callback_lock); } static int smc_listen(struct socket *sock, int backlog) @@ -2385,10 +2442,12 @@ static int smc_listen(struct socket *sock, int backlog) /* save original sk_data_ready function and establish * smc-specific sk_data_ready function */ - smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; - smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready, + smc_clcsock_data_ready, &smc->clcsk_data_ready); + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); /* save original ops */ smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; @@ -2403,7 +2462,11 @@ static int smc_listen(struct socket *sock, int backlog) rc = kernel_listen(smc->clcsock, backlog); if (rc) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); + smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); goto out; } sk->sk_max_ack_backlog = backlog; @@ -2664,8 +2727,10 @@ static int smc_shutdown(struct socket *sock, int how) if (smc->use_fallback) { rc = kernel_sock_shutdown(smc->clcsock, how); sk->sk_shutdown = smc->clcsock->sk->sk_shutdown; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (sk->sk_shutdown == SHUTDOWN_MASK) { sk->sk_state = SMC_CLOSED; + sock_put(sk); + } goto out; } switch (how) { diff --git a/net/smc/smc.h b/net/smc/smc.h index ea0620529ebe..5ed765ea0c73 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -288,12 +288,41 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline void smc_init_saved_callbacks(struct smc_sock *smc) +{ + smc->clcsk_state_change = NULL; + smc->clcsk_data_ready = NULL; + smc->clcsk_write_space = NULL; + smc->clcsk_error_report = NULL; +} + static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk) { return (struct smc_sock *) ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); } +/* save target_cb in saved_cb, and replace target_cb with new_cb */ +static inline void smc_clcsock_replace_cb(void (**target_cb)(struct sock *), + void (*new_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + /* only save once */ + if (!*saved_cb) + *saved_cb = *target_cb; + *target_cb = new_cb; +} + +/* restore target_cb to saved_cb, and reset saved_cb to NULL */ +static inline void smc_clcsock_restore_cb(void (**target_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + if (!*saved_cb) + return; + *target_cb = *saved_cb; + *saved_cb = NULL; +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index ce27399b38b1..f9f3f59c79de 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -191,7 +191,8 @@ static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, flags, SMC_NETLINK_DUMP_UEID); if (!hdr) return -ENOMEM; - snprintf(ueid_str, sizeof(ueid_str), "%s", ueid); + memcpy(ueid_str, ueid, SMC_MAX_EID_LEN); + ueid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; @@ -252,7 +253,8 @@ int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) goto end; smc_ism_get_system_eid(&seid); - snprintf(seid_str, sizeof(seid_str), "%s", seid); + memcpy(seid_str, seid, SMC_MAX_EID_LEN); + seid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) goto err; read_lock(&smc_clc_eid_table.lock); diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 676cb2333d3c..31db7438857c 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -214,8 +214,11 @@ again: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7984f8883472..7055ed10e316 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -311,8 +311,9 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || - !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, - IB_DEVICE_NAME_MAX - 1)) { + (ibdev->ibdev->dev.parent && + !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, + IB_DEVICE_NAME_MAX - 1))) { goto out; } } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8bf2af8546d2..af0174d7ce5a 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1127,6 +1127,8 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data) struct rpc_task *task; task = rpc_new_task(task_setup_data); + if (IS_ERR(task)) + return task; if (!RPC_IS_ASYNC(task)) task->tk_flags |= RPC_TASK_CRED_NOREF; @@ -1227,6 +1229,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); + if (IS_ERR(task)) { + xprt_free_bc_request(req); + return task; + } + xprt_init_bc_request(req, task); task->tk_action = call_bc_encode; @@ -1858,6 +1865,9 @@ call_encode(struct rpc_task *task) xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); + /* Add task to reply queue before transmission to avoid races */ + if (task->tk_status == 0 && rpc_reply_expected(task)) + task->tk_status = xprt_request_enqueue_receive(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ @@ -1881,9 +1891,6 @@ call_encode(struct rpc_task *task) return; } - /* Add task to reply queue before transmission to avoid races */ - if (rpc_reply_expected(task)) - xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: task->tk_action = call_transmit; @@ -2200,6 +2207,7 @@ call_transmit_status(struct rpc_task *task) * socket just returned a connection error, * then hold onto the transport lock. */ + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2283,6 +2291,7 @@ call_bc_transmit_status(struct rpc_task *task) case -ENOTCONN: case -EPIPE: break; + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2365,6 +2374,11 @@ call_status(struct rpc_task *task) case -EPIPE: case -EAGAIN: break; + case -ENFILE: + case -ENOBUFS: + case -ENOMEM: + rpc_delay(task, HZ>>2); + break; case -EIO: /* shutdown or soft timeout */ goto out_exit; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b258b87a3ec2..7f70c1e608b7 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -1128,6 +1128,11 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) if (task == NULL) { task = rpc_alloc_task(); + if (task == NULL) { + rpc_release_calldata(setup_data->callback_ops, + setup_data->callback_data); + return ERR_PTR(-ENOMEM); + } flags = RPC_TASK_DYNAMIC; } diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 05b38bf68316..71ba4cf513bc 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -221,12 +221,6 @@ static int xprt_send_kvec(struct socket *sock, struct msghdr *msg, static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) { - int err; - - err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); - if (err < 0) - return err; - iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, xdr_buf_pagecount(xdr), xdr->page_len + xdr->page_base); return xprt_sendmsg(sock, msg, base + xdr->page_base); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 297c49855038..5b59e2103526 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1231,6 +1231,8 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; dr->xprt_hlen = rqstp->rq_xprt_hlen; + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; + rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; @@ -1269,6 +1271,7 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_xprt_hlen = dr->xprt_hlen; rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_xprt_ctxt = dr->xprt_ctxt; svc_xprt_received(rqstp->rq_xprt); return (dr->argslen<<2) - dr->xprt_hlen; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 478f857cdaed..cc35ec433400 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -579,15 +579,18 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) if (svc_xprt_is_dead(xprt)) goto out_notconn; + err = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (err < 0) + goto out_unlock; + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); } + xdr_free_bvec(xdr); trace_svcsock_udp_send(xprt, err); - +out_unlock: mutex_unlock(&xprt->xpt_mutex); if (err < 0) return err; @@ -1096,7 +1099,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr, int ret; *sentp = 0; - xdr_alloc_bvec(xdr, GFP_KERNEL); + ret = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (ret < 0) + return ret; ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len); if (ret < 0) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 515501f79290..86d62cffba0d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -69,10 +69,11 @@ /* * Local functions */ -static void xprt_init(struct rpc_xprt *xprt, struct net *net); +static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_destroy(struct rpc_xprt *xprt); -static void xprt_request_init(struct rpc_task *task); +static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); +static int xprt_request_prepare(struct rpc_rqst *req); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -929,12 +930,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_lock_write(xprt, task)) return; - if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - trace_xprt_disconnect_cleanup(xprt); - xprt->ops->close(xprt); - } - - if (!xprt_connected(xprt)) { + if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on_timeout(&xprt->pending, task, NULL, xprt_request_timeout(task->tk_rqstp)); @@ -1143,16 +1139,19 @@ xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req) * @task: RPC task * */ -void +int xprt_request_enqueue_receive(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + int ret; if (!xprt_request_need_enqueue_receive(task, req)) - return; + return 0; - xprt_request_prepare(task->tk_rqstp); + ret = xprt_request_prepare(task->tk_rqstp); + if (ret) + return ret; spin_lock(&xprt->queue_lock); /* Update the softirq receive buffer */ @@ -1166,6 +1165,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); + return 0; } /** @@ -1452,14 +1452,16 @@ xprt_request_dequeue_xprt(struct rpc_task *task) * * Calls into the transport layer to do whatever is needed to prepare * the request for transmission or receive. + * Returns error, or zero. */ -void +static int xprt_request_prepare(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; if (xprt->ops->prepare_request) - xprt->ops->prepare_request(req); + return xprt->ops->prepare_request(req); + return 0; } /** diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cf76a6ad127b..864131a9fc6e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -831,7 +831,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_err; if (ret == 0) goto out_drop; - rqstp->rq_xprt_hlen = ret; + rqstp->rq_xprt_hlen = 0; if (svc_rdma_is_reverse_direction_reply(xprt, ctxt)) goto out_backchannel; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 78af7518f263..8ab64ea46870 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,12 +822,17 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) return ret; } -static void +static int xs_stream_prepare_request(struct rpc_rqst *req) { + gfp_t gfp = rpc_task_gfp_mask(); + int ret; + + ret = xdr_alloc_bvec(&req->rq_snd_buf, gfp); + if (ret < 0) + return ret; xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec( - &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + return xdr_alloc_bvec(&req->rq_rcv_buf, gfp); } /* @@ -879,7 +884,7 @@ static int xs_local_send_request(struct rpc_rqst *req) /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; } @@ -915,7 +920,7 @@ static int xs_local_send_request(struct rpc_rqst *req) -status); fallthrough; case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; } @@ -956,6 +961,9 @@ static int xs_udp_send_request(struct rpc_rqst *req) if (!xprt_request_get_cong(xprt, req)) return -EBADSLT; + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (status < 0) + return status; req->rq_xtime = ktime_get(); status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent); @@ -1185,6 +1193,16 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + } if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1208,7 +1226,7 @@ static void xs_reset_transport(struct sock_xprt *transport) mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp); xprt_disconnect_done(xprt); } @@ -2544,6 +2562,9 @@ static int bc_sendto(struct rpc_rqst *req) int err; req->rq_xtime = ktime_get(); + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (err < 0) + return err; err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); if (err < 0 || sent != (xdr->len + sizeof(marker))) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ee1c2b6b6971..21e808fcb676 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = IEEE80211_MAX_MESH_ID_LEN }, [NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT, - [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, + /* allow 3 for NUL-termination, we used to declare this NLA_STRING */ + [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3), [NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED }, [NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 }, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b2fdac96bab0..4a6d86432910 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2018,11 +2018,13 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, /* this is a nontransmitting bss, we need to add it to * transmitting bss' list if it is not there */ + spin_lock_bh(&rdev->bss_lock); if (cfg80211_add_nontrans_list(non_tx_data->tx_bss, &res->pub)) { if (__cfg80211_unlink_bss(rdev, res)) rdev->bss_generation++; } + spin_unlock_bh(&rdev->bss_lock); } trace_cfg80211_return_bss(&res->pub); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 19aa994f5d2c..00bd0ecff5a1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2593,12 +2593,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; + int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; - dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, + oif = fl->flowi_oif ? : fl->flowi_l3mdev; + dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2173a6729f30..9717e6f6fb31 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -40,8 +40,7 @@ include $(srctree)/scripts/Makefile.compiler # The filename Kbuild has precedence over Makefile kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src)) -kbuild-file := $(if $(wildcard $(kbuild-dir)/Kbuild),$(kbuild-dir)/Kbuild,$(kbuild-dir)/Makefile) -include $(kbuild-file) +include $(or $(wildcard $(kbuild-dir)/Kbuild),$(kbuild-dir)/Makefile) include $(srctree)/scripts/Makefile.lib diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index fd6175322470..74cb1c5c3658 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -12,7 +12,7 @@ include $(srctree)/scripts/Kbuild.include # The filename Kbuild has precedence over Makefile kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src)) -include $(if $(wildcard $(kbuild-dir)/Kbuild), $(kbuild-dir)/Kbuild, $(kbuild-dir)/Makefile) +include $(or $(wildcard $(kbuild-dir)/Kbuild),$(kbuild-dir)/Makefile) # Figure out what we need to build from the various variables # ========================================================================== diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index c593475d4a93..9f69ecdd7977 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -106,7 +106,7 @@ subdir-ym := $(addprefix $(obj)/,$(subdir-ym)) modname-multi = $(sort $(foreach m,$(multi-obj-ym),\ $(if $(filter $*.o, $(call suffix-search, $m, .o, -objs -y -m)),$(m:.o=)))) -__modname = $(if $(modname-multi),$(modname-multi),$(basetarget)) +__modname = $(or $(modname-multi),$(basetarget)) modname = $(subst $(space),:,$(__modname)) modfile = $(addprefix $(obj)/,$(__modname)) @@ -241,20 +241,16 @@ $(foreach m, $(notdir $1), \ $(addprefix $(obj)/, $(foreach s, $3, $($(m:%$(strip $2)=%$(s))))))) endef -quiet_cmd_copy = COPY $@ - cmd_copy = cp $< $@ - -# Shipped files +# Copy a file # =========================================================================== # 'cp' preserves permissions. If you use it to copy a file in read-only srctree, # the copy would be read-only as well, leading to an error when executing the # rule next time. Use 'cat' instead in order to generate a writable file. - -quiet_cmd_shipped = SHIPPED $@ -cmd_shipped = cat $< > $@ +quiet_cmd_copy = COPY $@ + cmd_copy = cat $< > $@ $(obj)/%: $(src)/%_shipped - $(call cmd,shipped) + $(call cmd,copy) # Commands useful for building a boot image # =========================================================================== @@ -431,7 +427,7 @@ MKIMAGE := $(srctree)/scripts/mkuboot.sh # SRCARCH just happens to match slightly more than ARCH (on sparc), so reduces # the number of overrides in arch makefiles UIMAGE_ARCH ?= $(SRCARCH) -UIMAGE_COMPRESSION ?= $(if $(2),$(2),none) +UIMAGE_COMPRESSION ?= $(or $(2),none) UIMAGE_OPTS-y ?= UIMAGE_TYPE ?= kernel UIMAGE_LOADADDR ?= arch_must_set_this diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index 44e887cff49b..2328f9a641da 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -105,25 +105,6 @@ static void usage(void) exit(1); } -/* - * In the intended usage of this program, the stdout is redirected to .*.cmd - * files. The return value of printf() must be checked to catch any error, - * e.g. "No space left on device". - */ -static void xprintf(const char *format, ...) -{ - va_list ap; - int ret; - - va_start(ap, format); - ret = vprintf(format, ap); - if (ret < 0) { - perror("fixdep"); - exit(1); - } - va_end(ap); -} - struct item { struct item *next; unsigned int len; @@ -189,7 +170,7 @@ static void use_config(const char *m, int slen) define_config(m, slen, hash); /* Print out a dependency path from a symbol name. */ - xprintf(" $(wildcard include/config/%.*s) \\\n", slen, m); + printf(" $(wildcard include/config/%.*s) \\\n", slen, m); } /* test if s ends in sub */ @@ -318,13 +299,13 @@ static void parse_dep_file(char *m, const char *target) */ if (!saw_any_target) { saw_any_target = 1; - xprintf("source_%s := %s\n\n", - target, m); - xprintf("deps_%s := \\\n", target); + printf("source_%s := %s\n\n", + target, m); + printf("deps_%s := \\\n", target); } is_first_dep = 0; } else { - xprintf(" %s \\\n", m); + printf(" %s \\\n", m); } buf = read_file(m); @@ -347,8 +328,8 @@ static void parse_dep_file(char *m, const char *target) exit(1); } - xprintf("\n%s: $(deps_%s)\n\n", target, target); - xprintf("$(deps_%s):\n", target); + printf("\n%s: $(deps_%s)\n\n", target, target); + printf("$(deps_%s):\n", target); } int main(int argc, char *argv[]) @@ -363,11 +344,22 @@ int main(int argc, char *argv[]) target = argv[2]; cmdline = argv[3]; - xprintf("cmd_%s := %s\n\n", target, cmdline); + printf("cmd_%s := %s\n\n", target, cmdline); buf = read_file(depfile); parse_dep_file(buf, target); free(buf); + fflush(stdout); + + /* + * In the intended usage, the stdout is redirected to .*.cmd files. + * Call ferror() to catch errors such as "No space left on device". + */ + if (ferror(stdout)) { + fprintf(stderr, "fixdep: not all data was written to the output\n"); + exit(1); + } + return 0; } diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c index 589454bce930..8425da41de0d 100644 --- a/scripts/gcc-plugins/latent_entropy_plugin.c +++ b/scripts/gcc-plugins/latent_entropy_plugin.c @@ -86,25 +86,31 @@ static struct plugin_info latent_entropy_plugin_info = { .help = "disable\tturn off latent entropy instrumentation\n", }; -static unsigned HOST_WIDE_INT seed; -/* - * get_random_seed() (this is a GCC function) generates the seed. - * This is a simple random generator without any cryptographic security because - * the entropy doesn't come from here. - */ +static unsigned HOST_WIDE_INT deterministic_seed; +static unsigned HOST_WIDE_INT rnd_buf[32]; +static size_t rnd_idx = ARRAY_SIZE(rnd_buf); +static int urandom_fd = -1; + static unsigned HOST_WIDE_INT get_random_const(void) { - unsigned int i; - unsigned HOST_WIDE_INT ret = 0; - - for (i = 0; i < 8 * sizeof(ret); i++) { - ret = (ret << 1) | (seed & 1); - seed >>= 1; - if (ret & 1) - seed ^= 0xD800000000000000ULL; + if (deterministic_seed) { + unsigned HOST_WIDE_INT w = deterministic_seed; + w ^= w << 13; + w ^= w >> 7; + w ^= w << 17; + deterministic_seed = w; + return deterministic_seed; } - return ret; + if (urandom_fd < 0) { + urandom_fd = open("/dev/urandom", O_RDONLY); + gcc_assert(urandom_fd >= 0); + } + if (rnd_idx >= ARRAY_SIZE(rnd_buf)) { + gcc_assert(read(urandom_fd, rnd_buf, sizeof(rnd_buf)) == sizeof(rnd_buf)); + rnd_idx = 0; + } + return rnd_buf[rnd_idx++]; } static tree tree_get_random_const(tree type) @@ -537,8 +543,6 @@ static void latent_entropy_start_unit(void *gcc_data __unused, tree type, id; int quals; - seed = get_random_seed(false); - if (in_lto_p) return; @@ -573,6 +577,12 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, const struct plugin_argument * const argv = plugin_info->argv; int i; + /* + * Call get_random_seed() with noinit=true, so that this returns + * 0 in the case where no seed has been passed via -frandom-seed. + */ + deterministic_seed = get_random_seed(true); + static const struct ggc_root_tab gt_ggc_r_gt_latent_entropy[] = { { .base = &latent_entropy_decl, diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl index 7437e19ba3ac..1389db76cff3 100755 --- a/scripts/get_abi.pl +++ b/scripts/get_abi.pl @@ -327,7 +327,7 @@ sub output_rest { my @filepath = split / /, $data{$what}->{filepath}; if ($enable_lineno) { - printf "#define LINENO %s%s#%s\n\n", + printf ".. LINENO %s%s#%s\n\n", $prefix, $file[0], $data{$what}->{line_no}; } @@ -1023,7 +1023,7 @@ logic (B<--no-rst-source>). =item B<--enable-lineno> -Enable output of #define LINENO lines. +Enable output of .. LINENO lines. =item B<--debug> I<debug level> diff --git a/scripts/get_feat.pl b/scripts/get_feat.pl index 457712355676..76cfb96b59b6 100755 --- a/scripts/get_feat.pl +++ b/scripts/get_feat.pl @@ -13,6 +13,7 @@ my $man; my $debug; my $arch; my $feat; +my $enable_fname; my $basename = abs_path($0); $basename =~ s,/[^/]+$,/,; @@ -31,6 +32,7 @@ GetOptions( 'arch=s' => \$arch, 'feat=s' => \$feat, 'feature=s' => \$feat, + "enable-fname" => \$enable_fname, man => \$man ) or pod2usage(2); @@ -95,6 +97,10 @@ sub parse_feat { return if ($file =~ m,($prefix)/arch-support.txt,); return if (!($file =~ m,arch-support.txt$,)); + if ($enable_fname) { + printf ".. FILE %s\n", abs_path($file); + } + my $subsys = ""; $subsys = $2 if ( m,.*($prefix)/([^/]+).*,); @@ -580,6 +586,11 @@ Output features for a single specific feature. Changes the location of the Feature files. By default, it uses the Documentation/features directory. +=item B<--enable-fname> + +Prints the file name of the feature files. This can be used in order to +track dependencies during documentation build. + =item B<--debug> Put the script in verbose mode, useful for debugging. Can be called multiple diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 54ad86d13784..8caabddf817c 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -108,7 +108,7 @@ static bool is_ignored_symbol(const char *name, char type) /* Symbol names that begin with the following are ignored.*/ static const char * const ignored_prefixes[] = { "$", /* local symbols for ARM, MIPS, etc. */ - ".LASANPC", /* s390 kasan local symbols */ + ".L", /* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */ "__crc_", /* modversions */ "__efistub_", /* arm64 EFI stub namespace */ "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index d3c3a61308ad..c4340c90e172 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -658,13 +658,6 @@ static char *escape_string_value(const char *in) return out; } -/* - * Kconfig configuration printer - * - * This printer is used when generating the resulting configuration after - * kconfig invocation and `defconfig' files. Unset symbol might be omitted by - * passing a non-NULL argument to the printer. - */ enum output_n { OUTPUT_N, OUTPUT_N_AS_UNSET, OUTPUT_N_NONE }; static void __print_symbol(FILE *fp, struct symbol *sym, enum output_n output_n, @@ -903,19 +896,20 @@ next: menu = menu->list; continue; } - if (menu->next) + +end_check: + if (!menu->sym && menu_is_visible(menu) && menu != &rootmenu && + menu->prompt->type == P_MENU) { + fprintf(out, "# end of %s\n", menu_get_prompt(menu)); + need_newline = true; + } + + if (menu->next) { menu = menu->next; - else while ((menu = menu->parent)) { - if (!menu->sym && menu_is_visible(menu) && - menu != &rootmenu) { - str = menu_get_prompt(menu); - fprintf(out, "# end of %s\n", str); - need_newline = true; - } - if (menu->next) { - menu = menu->next; - break; - } + } else { + menu = menu->parent; + if (menu) + goto end_check; } } fclose(out); @@ -979,6 +973,7 @@ static int conf_write_autoconf_cmd(const char *autoconf_name) fprintf(out, "\n$(deps_config): ;\n"); + fflush(out); ret = ferror(out); /* error check for all fprintf() calls */ fclose(out); if (ret) @@ -1097,6 +1092,7 @@ static int __conf_write_autoconf(const char *filename, if ((sym->flags & SYMBOL_WRITE) && sym->name) print_symbol(file, sym); + fflush(file); /* check possible errors in conf_write_heading() and print_symbol() */ ret = ferror(file); fclose(file); diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 9c084a2ba3b0..7516949bb049 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -424,7 +424,7 @@ sub get_kernel_version() { sub print_lineno { my $lineno = shift; if ($enable_lineno && defined($lineno)) { - print "#define LINENO " . $lineno . "\n"; + print ".. LINENO " . $lineno . "\n"; } } ## @@ -2478,7 +2478,7 @@ May be specified multiple times. =item -enable-lineno -Enable output of #define LINENO lines. +Enable output of .. LINENO lines. =back diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f704034ebbe6..20f44504a644 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -50,7 +50,7 @@ gen_initcalls() { info GEN .tmp_initcalls.lds - ${PYTHON} ${srctree}/scripts/jobserver-exec \ + ${PYTHON3} ${srctree}/scripts/jobserver-exec \ ${PERL} ${srctree}/scripts/generate_initcall_order.pl \ ${KBUILD_VMLINUX_OBJS} ${KBUILD_VMLINUX_LIBS} \ > .tmp_initcalls.lds diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index d10f93aac1c8..ed9d056d2108 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -674,7 +674,7 @@ static void handle_modversion(const struct module *mod, unsigned int crc; if (sym->st_shndx == SHN_UNDEF) { - warn("EXPORT symbol \"%s\" [%s%s] version ...\n" + warn("EXPORT symbol \"%s\" [%s%s] version generation failed, symbol will not be versioned.\n" "Is \"%s\" prototyped in <asm/asm-prototypes.h>?\n", symname, mod->name, mod->is_vmlinux ? "" : ".ko", symname); diff --git a/security/Kconfig b/security/Kconfig index 1d2d71cc1f36..9b2c4925585a 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -166,7 +166,7 @@ config HARDENED_USERCOPY config HARDENED_USERCOPY_PAGESPAN bool "Refuse to copy allocations that span multiple pages" depends on HARDENED_USERCOPY - depends on EXPERT + depends on BROKEN help When a multi-page allocation is done without __GFP_COMP, hardened usercopy will reject attempts to copy it. There are, diff --git a/sound/core/init.c b/sound/core/init.c index 31ba7024e3ad..726a8353201f 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -209,6 +209,12 @@ static void __snd_card_release(struct device *dev, void *data) * snd_card_register(), the very first devres action to call snd_card_free() * is added automatically. In that way, the resource disconnection is assured * at first, then released in the expected order. + * + * If an error happens at the probe before snd_card_register() is called and + * there have been other devres resources, you'd need to free the card manually + * via snd_card_free() call in the error; otherwise it may lead to UAF due to + * devres call orders. You can use snd_card_free_on_error() helper for + * handling it more easily. */ int snd_devm_card_new(struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size, @@ -235,6 +241,28 @@ int snd_devm_card_new(struct device *parent, int idx, const char *xid, } EXPORT_SYMBOL_GPL(snd_devm_card_new); +/** + * snd_card_free_on_error - a small helper for handling devm probe errors + * @dev: the managed device object + * @ret: the return code from the probe callback + * + * This function handles the explicit snd_card_free() call at the error from + * the probe callback. It's just a small helper for simplifying the error + * handling with the managed devices. + */ +int snd_card_free_on_error(struct device *dev, int ret) +{ + struct snd_card *card; + + if (!ret) + return 0; + card = devres_find(dev, __snd_card_release, NULL, NULL); + if (card) + snd_card_free(card); + return ret; +} +EXPORT_SYMBOL_GPL(snd_card_free_on_error); + static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size) diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 6fd763d4d15b..15dc7160ba34 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -499,6 +499,10 @@ static const struct snd_malloc_ops snd_dma_wc_ops = { }; #endif /* CONFIG_X86 */ +#ifdef CONFIG_SND_DMA_SGBUF +static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size); +#endif + /* * Non-contiguous pages allocator */ @@ -509,8 +513,18 @@ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); - if (!sgt) + if (!sgt) { +#ifdef CONFIG_SND_DMA_SGBUF + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; + else + dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + return snd_dma_sg_fallback_alloc(dmab, size); +#else return NULL; +#endif + } + dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); @@ -633,6 +647,8 @@ static void *snd_dma_sg_wc_alloc(struct snd_dma_buffer *dmab, size_t size) if (!p) return NULL; + if (dmab->dev.type != SNDRV_DMA_TYPE_DEV_WC_SG) + return p; for_each_sgtable_page(sgt, &iter, 0) set_memory_wc(sg_wc_address(&iter), 1); return p; @@ -665,6 +681,95 @@ static const struct snd_malloc_ops snd_dma_sg_wc_ops = { .get_page = snd_dma_noncontig_get_page, .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; + +/* Fallback SG-buffer allocations for x86 */ +struct snd_dma_sg_fallback { + size_t count; + struct page **pages; + dma_addr_t *addrs; +}; + +static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, + struct snd_dma_sg_fallback *sgbuf) +{ + size_t i; + + if (sgbuf->count && dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wb(sgbuf->pages, sgbuf->count); + for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++) + dma_free_coherent(dmab->dev.dev, PAGE_SIZE, + page_address(sgbuf->pages[i]), + sgbuf->addrs[i]); + kvfree(sgbuf->pages); + kvfree(sgbuf->addrs); + kfree(sgbuf); +} + +static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) +{ + struct snd_dma_sg_fallback *sgbuf; + struct page **pages; + size_t i, count; + void *p; + + sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); + if (!sgbuf) + return NULL; + count = PAGE_ALIGN(size) >> PAGE_SHIFT; + pages = kvcalloc(count, sizeof(*pages), GFP_KERNEL); + if (!pages) + goto error; + sgbuf->pages = pages; + sgbuf->addrs = kvcalloc(count, sizeof(*sgbuf->addrs), GFP_KERNEL); + if (!sgbuf->addrs) + goto error; + + for (i = 0; i < count; sgbuf->count++, i++) { + p = dma_alloc_coherent(dmab->dev.dev, PAGE_SIZE, + &sgbuf->addrs[i], DEFAULT_GFP); + if (!p) + goto error; + sgbuf->pages[i] = virt_to_page(p); + } + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wc(pages, count); + p = vmap(pages, count, VM_MAP, PAGE_KERNEL); + if (!p) + goto error; + dmab->private_data = sgbuf; + return p; + + error: + __snd_dma_sg_fallback_free(dmab, sgbuf); + return NULL; +} + +static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) +{ + vunmap(dmab->area); + __snd_dma_sg_fallback_free(dmab, dmab->private_data); +} + +static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, + struct vm_area_struct *area) +{ + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); + return vm_map_pages(area, sgbuf->pages, sgbuf->count); +} + +static const struct snd_malloc_ops snd_dma_sg_fallback_ops = { + .alloc = snd_dma_sg_fallback_alloc, + .free = snd_dma_sg_fallback_free, + .mmap = snd_dma_sg_fallback_mmap, + /* reuse vmalloc helpers */ + .get_addr = snd_dma_vmalloc_get_addr, + .get_page = snd_dma_vmalloc_get_page, + .get_chunk_size = snd_dma_vmalloc_get_chunk_size, +}; #endif /* CONFIG_SND_DMA_SGBUF */ /* @@ -736,6 +841,10 @@ static const struct snd_malloc_ops *dma_ops[] = { #ifdef CONFIG_GENERIC_ALLOCATOR [SNDRV_DMA_TYPE_DEV_IRAM] = &snd_dma_iram_ops, #endif /* CONFIG_GENERIC_ALLOCATOR */ +#ifdef CONFIG_SND_DMA_SGBUF + [SNDRV_DMA_TYPE_DEV_SG_FALLBACK] = &snd_dma_sg_fallback_ops, + [SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK] = &snd_dma_sg_fallback_ops, +#endif #endif /* CONFIG_HAS_DMA */ }; diff --git a/sound/core/pcm.c b/sound/core/pcm.c index edd9849210f2..977d54320a5c 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -970,6 +970,7 @@ int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, runtime->status->state = SNDRV_PCM_STATE_OPEN; mutex_init(&runtime->buffer_mutex); + atomic_set(&runtime->buffer_accessing, 0); substream->runtime = runtime; substream->private_data = pcm->private_data; diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index a40a35e51fad..1fc7c50ffa62 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1906,11 +1906,9 @@ static int wait_for_avail(struct snd_pcm_substream *substream, if (avail >= runtime->twake) break; snd_pcm_stream_unlock_irq(substream); - mutex_unlock(&runtime->buffer_mutex); tout = schedule_timeout(wait_time); - mutex_lock(&runtime->buffer_mutex); snd_pcm_stream_lock_irq(substream); set_current_state(TASK_INTERRUPTIBLE); switch (runtime->status->state) { @@ -2221,7 +2219,6 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, nonblock = !!(substream->f_flags & O_NONBLOCK); - mutex_lock(&runtime->buffer_mutex); snd_pcm_stream_lock_irq(substream); err = pcm_accessible_state(runtime); if (err < 0) @@ -2276,6 +2273,10 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, err = -EINVAL; goto _end_unlock; } + if (!atomic_inc_unless_negative(&runtime->buffer_accessing)) { + err = -EBUSY; + goto _end_unlock; + } snd_pcm_stream_unlock_irq(substream); if (!is_playback) snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_CPU); @@ -2284,6 +2285,7 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, if (is_playback) snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); snd_pcm_stream_lock_irq(substream); + atomic_dec(&runtime->buffer_accessing); if (err < 0) goto _end_unlock; err = pcm_accessible_state(runtime); @@ -2313,7 +2315,6 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, if (xfer > 0 && err >= 0) snd_pcm_update_state(substream, runtime); snd_pcm_stream_unlock_irq(substream); - mutex_unlock(&runtime->buffer_mutex); return xfer > 0 ? (snd_pcm_sframes_t)xfer : err; } EXPORT_SYMBOL(__snd_pcm_lib_xfer); diff --git a/sound/core/pcm_misc.c b/sound/core/pcm_misc.c index 4866aed97aac..5588b6a1ee8b 100644 --- a/sound/core/pcm_misc.c +++ b/sound/core/pcm_misc.c @@ -433,7 +433,7 @@ int snd_pcm_format_set_silence(snd_pcm_format_t format, void *data, unsigned int return 0; width = pcm_formats[(INT)format].phys; /* physical width */ pat = pcm_formats[(INT)format].silence; - if (! width) + if (!width || !pat) return -EINVAL; /* signed or 1 byte data */ if (pcm_formats[(INT)format].signd == 1 || width <= 8) { diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 704fdc9ebf91..4adaee62ef33 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -685,6 +685,24 @@ static int snd_pcm_hw_params_choose(struct snd_pcm_substream *pcm, return 0; } +/* acquire buffer_mutex; if it's in r/w operation, return -EBUSY, otherwise + * block the further r/w operations + */ +static int snd_pcm_buffer_access_lock(struct snd_pcm_runtime *runtime) +{ + if (!atomic_dec_unless_positive(&runtime->buffer_accessing)) + return -EBUSY; + mutex_lock(&runtime->buffer_mutex); + return 0; /* keep buffer_mutex, unlocked by below */ +} + +/* release buffer_mutex and clear r/w access flag */ +static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) +{ + mutex_unlock(&runtime->buffer_mutex); + atomic_inc(&runtime->buffer_accessing); +} + #if IS_ENABLED(CONFIG_SND_PCM_OSS) #define is_oss_stream(substream) ((substream)->oss.oss) #else @@ -695,14 +713,16 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_runtime *runtime; - int err = 0, usecs; + int err, usecs; unsigned int bits; snd_pcm_uframes_t frames; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; - mutex_lock(&runtime->buffer_mutex); + err = snd_pcm_buffer_access_lock(runtime); + if (err < 0) + return err; snd_pcm_stream_lock_irq(substream); switch (runtime->status->state) { case SNDRV_PCM_STATE_OPEN: @@ -820,7 +840,7 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream, snd_pcm_lib_free_pages(substream); } unlock: - mutex_unlock(&runtime->buffer_mutex); + snd_pcm_buffer_access_unlock(runtime); return err; } @@ -865,7 +885,9 @@ static int snd_pcm_hw_free(struct snd_pcm_substream *substream) if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; - mutex_lock(&runtime->buffer_mutex); + result = snd_pcm_buffer_access_lock(runtime); + if (result < 0) + return result; snd_pcm_stream_lock_irq(substream); switch (runtime->status->state) { case SNDRV_PCM_STATE_SETUP: @@ -884,7 +906,7 @@ static int snd_pcm_hw_free(struct snd_pcm_substream *substream) snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); unlock: - mutex_unlock(&runtime->buffer_mutex); + snd_pcm_buffer_access_unlock(runtime); return result; } @@ -1369,12 +1391,15 @@ static int snd_pcm_action_nonatomic(const struct action_ops *ops, /* Guarantee the group members won't change during non-atomic action */ down_read(&snd_pcm_link_rwsem); - mutex_lock(&substream->runtime->buffer_mutex); + res = snd_pcm_buffer_access_lock(substream->runtime); + if (res < 0) + goto unlock; if (snd_pcm_stream_linked(substream)) res = snd_pcm_action_group(ops, substream, state, false); else res = snd_pcm_action_single(ops, substream, state); - mutex_unlock(&substream->runtime->buffer_mutex); + snd_pcm_buffer_access_unlock(substream->runtime); + unlock: up_read(&snd_pcm_link_rwsem); return res; } diff --git a/sound/drivers/mtpav.c b/sound/drivers/mtpav.c index 11235baaf6fa..f212f233ea61 100644 --- a/sound/drivers/mtpav.c +++ b/sound/drivers/mtpav.c @@ -693,8 +693,6 @@ static int snd_mtpav_probe(struct platform_device *dev) mtp_card->outmidihwport = 0xffffffff; timer_setup(&mtp_card->timer, snd_mtpav_output_timer, 0); - card->private_free = snd_mtpav_free; - err = snd_mtpav_get_RAWMIDI(mtp_card); if (err < 0) return err; @@ -716,6 +714,8 @@ static int snd_mtpav_probe(struct platform_device *dev) if (err < 0) return err; + card->private_free = snd_mtpav_free; + platform_set_drvdata(dev, card); printk(KERN_INFO "Motu MidiTimePiece on parallel port irq: %d ioport: 0x%lx\n", irq, port); return 0; diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index efe810af28c5..48b8ed752b69 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -116,16 +116,25 @@ static int i915_component_master_match(struct device *dev, int subcomponent, return 0; } -/* check whether intel graphics is present */ -static bool i915_gfx_present(void) +/* check whether Intel graphics is present and reachable */ +static int i915_gfx_present(struct pci_dev *hdac_pci) { - static const struct pci_device_id ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_ANY_ID), - .class = PCI_BASE_CLASS_DISPLAY << 16, - .class_mask = 0xff << 16 }, - {} - }; - return pci_dev_present(ids); + unsigned int class = PCI_BASE_CLASS_DISPLAY << 16; + struct pci_dev *display_dev = NULL; + bool match = false; + + do { + display_dev = pci_get_class(class, display_dev); + + if (display_dev && display_dev->vendor == PCI_VENDOR_ID_INTEL && + connectivity_check(display_dev, hdac_pci)) + match = true; + + pci_dev_put(display_dev); + + } while (!match && display_dev); + + return match; } /** @@ -145,7 +154,7 @@ int snd_hdac_i915_init(struct hdac_bus *bus) struct drm_audio_component *acomp; int err; - if (!i915_gfx_present()) + if (!i915_gfx_present(to_pci_dev(bus->dev))) return -ENODEV; err = snd_hdac_acomp_init(bus, NULL, diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 70fd8b13938e..8b0a16ba27d3 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -390,22 +390,36 @@ static const struct config_entry config_table[] = { /* Alder Lake */ #if IS_ENABLED(CONFIG_SND_SOC_SOF_ALDERLAKE) + /* Alderlake-S */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x7ad0, }, + /* RaptorLake-S */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, - .device = 0x51c8, + .device = 0x7a50, }, + /* Alderlake-P */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, - .device = 0x51cc, + .device = 0x51c8, }, { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x51cd, }, + /* Alderlake-PS */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51c9, + }, + /* Alderlake-M */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cc, + }, + /* Alderlake-N */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x54c8, diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c index b6bdebd9ef27..10112e1bb25d 100644 --- a/sound/isa/cs423x/cs4236.c +++ b/sound/isa/cs423x/cs4236.c @@ -494,7 +494,7 @@ static int snd_cs423x_pnpbios_detect(struct pnp_dev *pdev, static int dev; int err; struct snd_card *card; - struct pnp_dev *cdev; + struct pnp_dev *cdev, *iter; char cid[PNP_ID_LEN]; if (pnp_device_is_isapnp(pdev)) @@ -510,9 +510,11 @@ static int snd_cs423x_pnpbios_detect(struct pnp_dev *pdev, strcpy(cid, pdev->id[0].id); cid[5] = '1'; cdev = NULL; - list_for_each_entry(cdev, &(pdev->protocol->devices), protocol_list) { - if (!strcmp(cdev->id[0].id, cid)) + list_for_each_entry(iter, &(pdev->protocol->devices), protocol_list) { + if (!strcmp(iter->id[0].id, cid)) { + cdev = iter; break; + } } err = snd_cs423x_card_new(&pdev->dev, dev, &card); if (err < 0) diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c index ea001c80149d..3164eb8510fa 100644 --- a/sound/isa/galaxy/galaxy.c +++ b/sound/isa/galaxy/galaxy.c @@ -478,7 +478,7 @@ static void snd_galaxy_free(struct snd_card *card) galaxy_set_config(galaxy, galaxy->config); } -static int snd_galaxy_probe(struct device *dev, unsigned int n) +static int __snd_galaxy_probe(struct device *dev, unsigned int n) { struct snd_galaxy *galaxy; struct snd_wss *chip; @@ -598,6 +598,11 @@ static int snd_galaxy_probe(struct device *dev, unsigned int n) return 0; } +static int snd_galaxy_probe(struct device *dev, unsigned int n) +{ + return snd_card_free_on_error(dev, __snd_galaxy_probe(dev, n)); +} + static struct isa_driver snd_galaxy_driver = { .match = snd_galaxy_match, .probe = snd_galaxy_probe, diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c index 26ab7ff80768..60398fced046 100644 --- a/sound/isa/sc6000.c +++ b/sound/isa/sc6000.c @@ -537,7 +537,7 @@ static void snd_sc6000_free(struct snd_card *card) sc6000_setup_board(vport, 0); } -static int snd_sc6000_probe(struct device *devptr, unsigned int dev) +static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) { static const int possible_irqs[] = { 5, 7, 9, 10, 11, -1 }; static const int possible_dmas[] = { 1, 3, 0, -1 }; @@ -662,6 +662,11 @@ static int snd_sc6000_probe(struct device *devptr, unsigned int dev) return 0; } +static int snd_sc6000_probe(struct device *devptr, unsigned int dev) +{ + return snd_card_free_on_error(devptr, __snd_sc6000_probe(devptr, dev)); +} + static struct isa_driver snd_sc6000_driver = { .match = snd_sc6000_match, .probe = snd_sc6000_probe, diff --git a/sound/oss/dmasound/dmasound.h b/sound/oss/dmasound/dmasound.h index c1c52b479da2..ad8ce6a1c25c 100644 --- a/sound/oss/dmasound/dmasound.h +++ b/sound/oss/dmasound/dmasound.h @@ -88,11 +88,7 @@ static inline int ioctl_return(int __user *addr, int value) */ extern int dmasound_init(void); -#ifdef MODULE extern void dmasound_deinit(void); -#else -#define dmasound_deinit() do { } while (0) -#endif /* description of the set-up applies to either hard or soft settings */ @@ -114,9 +110,7 @@ typedef struct { void *(*dma_alloc)(unsigned int, gfp_t); void (*dma_free)(void *, unsigned int); int (*irqinit)(void); -#ifdef MODULE void (*irqcleanup)(void); -#endif void (*init)(void); void (*silence)(void); int (*setFormat)(int); diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 0c95828ac0b1..9c48f3a9e3d1 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -206,12 +206,10 @@ module_param(writeBufSize, int, 0); MODULE_LICENSE("GPL"); -#ifdef MODULE static int sq_unit = -1; static int mixer_unit = -1; static int state_unit = -1; static int irq_installed; -#endif /* MODULE */ /* control over who can modify resources shared between play/record */ static fmode_t shared_resource_owner; @@ -391,9 +389,6 @@ static const struct file_operations mixer_fops = static void mixer_init(void) { -#ifndef MODULE - int mixer_unit; -#endif mixer_unit = register_sound_mixer(&mixer_fops, -1); if (mixer_unit < 0) return; @@ -1171,9 +1166,6 @@ static const struct file_operations sq_fops = static int sq_init(void) { const struct file_operations *fops = &sq_fops; -#ifndef MODULE - int sq_unit; -#endif sq_unit = register_sound_dsp(fops, -1); if (sq_unit < 0) { @@ -1366,9 +1358,6 @@ static const struct file_operations state_fops = { static int state_init(void) { -#ifndef MODULE - int state_unit; -#endif state_unit = register_sound_special(&state_fops, SND_DEV_STATUS); if (state_unit < 0) return state_unit ; @@ -1386,10 +1375,9 @@ static int state_init(void) int dmasound_init(void) { int res ; -#ifdef MODULE + if (irq_installed) return -EBUSY; -#endif /* Set up sound queue, /dev/audio and /dev/dsp. */ @@ -1408,9 +1396,7 @@ int dmasound_init(void) printk(KERN_ERR "DMA sound driver: Interrupt initialization failed\n"); return -ENODEV; } -#ifdef MODULE irq_installed = 1; -#endif printk(KERN_INFO "%s DMA sound driver rev %03d installed\n", dmasound.mach.name, (DMASOUND_CORE_REVISION<<4) + @@ -1424,8 +1410,6 @@ int dmasound_init(void) return 0; } -#ifdef MODULE - void dmasound_deinit(void) { if (irq_installed) { @@ -1444,8 +1428,6 @@ void dmasound_deinit(void) unregister_sound_dsp(sq_unit); } -#else /* !MODULE */ - static int dmasound_setup(char *str) { int ints[6], size; @@ -1489,8 +1471,6 @@ static int dmasound_setup(char *str) __setup("dmasound=", dmasound_setup); -#endif /* !MODULE */ - /* * Conversion tables */ @@ -1577,9 +1557,7 @@ char dmasound_alaw2dma8[] = { EXPORT_SYMBOL(dmasound); EXPORT_SYMBOL(dmasound_init); -#ifdef MODULE EXPORT_SYMBOL(dmasound_deinit); -#endif EXPORT_SYMBOL(dmasound_write_sq); EXPORT_SYMBOL(dmasound_catchRadius); #ifdef HAS_8BIT_TABLES diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c index bba4dae8dcc7..50e30704bf6f 100644 --- a/sound/pci/ad1889.c +++ b/sound/pci/ad1889.c @@ -844,8 +844,8 @@ snd_ad1889_create(struct snd_card *card, struct pci_dev *pci) } static int -snd_ad1889_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +__snd_ad1889_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { int err; static int devno; @@ -904,6 +904,12 @@ snd_ad1889_probe(struct pci_dev *pci, return 0; } +static int snd_ad1889_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ad1889_probe(pci, pci_id)); +} + static const struct pci_device_id snd_ad1889_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_ANALOG_DEVICES, PCI_DEVICE_ID_AD1889JS) }, { 0, }, diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c index 92eb59db106d..2378a39abaeb 100644 --- a/sound/pci/ali5451/ali5451.c +++ b/sound/pci/ali5451/ali5451.c @@ -2124,8 +2124,8 @@ static int snd_ali_create(struct snd_card *card, return 0; } -static int snd_ali_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_ali_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct snd_ali *codec; @@ -2170,6 +2170,12 @@ static int snd_ali_probe(struct pci_dev *pci, return 0; } +static int snd_ali_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ali_probe(pci, pci_id)); +} + static struct pci_driver ali5451_driver = { .name = KBUILD_MODNAME, .id_table = snd_ali_ids, diff --git a/sound/pci/als300.c b/sound/pci/als300.c index b86565dcdbe4..c70aff060120 100644 --- a/sound/pci/als300.c +++ b/sound/pci/als300.c @@ -708,7 +708,7 @@ static int snd_als300_probe(struct pci_dev *pci, err = snd_als300_create(card, pci, chip_type); if (err < 0) - return err; + goto error; strcpy(card->driver, "ALS300"); if (chip->chip_type == DEVICE_ALS300_PLUS) @@ -723,11 +723,15 @@ static int snd_als300_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver als300_driver = { diff --git a/sound/pci/als4000.c b/sound/pci/als4000.c index 535eccd124be..f33aeb692a11 100644 --- a/sound/pci/als4000.c +++ b/sound/pci/als4000.c @@ -806,8 +806,8 @@ static void snd_card_als4000_free( struct snd_card *card ) snd_als4000_free_gameport(acard); } -static int snd_card_als4000_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_als4000_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -930,6 +930,12 @@ static int snd_card_als4000_probe(struct pci_dev *pci, return 0; } +static int snd_card_als4000_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_als4000_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_als4000_suspend(struct device *dev) { diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c index b8e035d5930d..43d01f1847ed 100644 --- a/sound/pci/atiixp.c +++ b/sound/pci/atiixp.c @@ -1572,8 +1572,8 @@ static int snd_atiixp_init(struct snd_card *card, struct pci_dev *pci) } -static int snd_atiixp_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct atiixp *chip; @@ -1623,6 +1623,12 @@ static int snd_atiixp_probe(struct pci_dev *pci, return 0; } +static int snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_atiixp_probe(pci, pci_id)); +} + static struct pci_driver atiixp_driver = { .name = KBUILD_MODNAME, .id_table = snd_atiixp_ids, diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c index 178dce8ef1e9..8864c4c3c7e1 100644 --- a/sound/pci/atiixp_modem.c +++ b/sound/pci/atiixp_modem.c @@ -1201,8 +1201,8 @@ static int snd_atiixp_init(struct snd_card *card, struct pci_dev *pci) } -static int snd_atiixp_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct atiixp_modem *chip; @@ -1247,6 +1247,12 @@ static int snd_atiixp_probe(struct pci_dev *pci, return 0; } +static int snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_atiixp_probe(pci, pci_id)); +} + static struct pci_driver atiixp_modem_driver = { .name = KBUILD_MODNAME, .id_table = snd_atiixp_ids, diff --git a/sound/pci/au88x0/au88x0.c b/sound/pci/au88x0/au88x0.c index 342ef2a6655e..eb234153691b 100644 --- a/sound/pci/au88x0/au88x0.c +++ b/sound/pci/au88x0/au88x0.c @@ -193,7 +193,7 @@ snd_vortex_create(struct snd_card *card, struct pci_dev *pci) // constructor -- see "Constructor" sub-section static int -snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -310,6 +310,12 @@ snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_vortex_probe(pci, pci_id)); +} + // pci_driver definition static struct pci_driver vortex_driver = { .name = KBUILD_MODNAME, diff --git a/sound/pci/aw2/aw2-alsa.c b/sound/pci/aw2/aw2-alsa.c index d56f126d6fdd..29a4bcdec237 100644 --- a/sound/pci/aw2/aw2-alsa.c +++ b/sound/pci/aw2/aw2-alsa.c @@ -275,7 +275,7 @@ static int snd_aw2_probe(struct pci_dev *pci, /* (3) Create main component */ err = snd_aw2_create(card, pci); if (err < 0) - return err; + goto error; /* initialize mutex */ mutex_init(&chip->mtx); @@ -294,13 +294,17 @@ static int snd_aw2_probe(struct pci_dev *pci, /* (6) Register card instance */ err = snd_card_register(card); if (err < 0) - return err; + goto error; /* (7) Set PCI driver data */ pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } /* open callback */ diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c index 089050470ff2..7f329dfc5404 100644 --- a/sound/pci/azt3328.c +++ b/sound/pci/azt3328.c @@ -2427,7 +2427,7 @@ snd_azf3328_create(struct snd_card *card, } static int -snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2520,6 +2520,12 @@ snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_azf3328_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static inline void snd_azf3328_suspend_regs(const struct snd_azf3328 *chip, diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c index d23f93163841..621985bfee5d 100644 --- a/sound/pci/bt87x.c +++ b/sound/pci/bt87x.c @@ -805,8 +805,8 @@ static int snd_bt87x_detect_card(struct pci_dev *pci) return SND_BT87X_BOARD_UNKNOWN; } -static int snd_bt87x_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_bt87x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -889,6 +889,12 @@ static int snd_bt87x_probe(struct pci_dev *pci, return 0; } +static int snd_bt87x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_bt87x_probe(pci, pci_id)); +} + /* default entries for all Bt87x cards - it's not exported */ /* driver_data is set to 0 to call detection */ static const struct pci_device_id snd_bt87x_default_ids[] = { diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c index 8577f9fa5ea6..cf1bac7a435f 100644 --- a/sound/pci/ca0106/ca0106_main.c +++ b/sound/pci/ca0106/ca0106_main.c @@ -1725,8 +1725,8 @@ static int snd_ca0106_midi(struct snd_ca0106 *chip, unsigned int channel) } -static int snd_ca0106_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_ca0106_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1786,6 +1786,12 @@ static int snd_ca0106_probe(struct pci_dev *pci, return 0; } +static int snd_ca0106_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ca0106_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_ca0106_suspend(struct device *dev) { diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index dab801d9d3b4..727db6d43391 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -3247,15 +3247,19 @@ static int snd_cmipci_probe(struct pci_dev *pci, err = snd_cmipci_create(card, pci, dev); if (err < 0) - return err; + goto error; err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } #ifdef CONFIG_PM_SLEEP diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c index e7367402b84a..0c9cadf7b3b8 100644 --- a/sound/pci/cs4281.c +++ b/sound/pci/cs4281.c @@ -1827,8 +1827,8 @@ static void snd_cs4281_opl3_command(struct snd_opl3 *opl3, unsigned short cmd, spin_unlock_irqrestore(&opl3->reg_lock, flags); } -static int snd_cs4281_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_cs4281_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1888,6 +1888,12 @@ static int snd_cs4281_probe(struct pci_dev *pci, return 0; } +static int snd_cs4281_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_cs4281_probe(pci, pci_id)); +} + /* * Power Management */ diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c index 499fa0148f9a..440b8f9b40c9 100644 --- a/sound/pci/cs5535audio/cs5535audio.c +++ b/sound/pci/cs5535audio/cs5535audio.c @@ -281,8 +281,8 @@ static int snd_cs5535audio_create(struct snd_card *card, return 0; } -static int snd_cs5535audio_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_cs5535audio_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -331,6 +331,12 @@ static int snd_cs5535audio_probe(struct pci_dev *pci, return 0; } +static int snd_cs5535audio_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_cs5535audio_probe(pci, pci_id)); +} + static struct pci_driver cs5535audio_driver = { .name = KBUILD_MODNAME, .id_table = snd_cs5535audio_ids, diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c index 25b012ef5c3e..c70c3ac4e99a 100644 --- a/sound/pci/echoaudio/echoaudio.c +++ b/sound/pci/echoaudio/echoaudio.c @@ -1970,8 +1970,8 @@ static int snd_echo_create(struct snd_card *card, } /* constructor */ -static int snd_echo_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_echo_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2139,6 +2139,11 @@ static int snd_echo_probe(struct pci_dev *pci, return 0; } +static int snd_echo_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_echo_probe(pci, pci_id)); +} #if defined(CONFIG_PM_SLEEP) diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c index c49c44dc1082..89043392f3ec 100644 --- a/sound/pci/emu10k1/emu10k1x.c +++ b/sound/pci/emu10k1/emu10k1x.c @@ -1491,8 +1491,8 @@ static int snd_emu10k1x_midi(struct emu10k1x *emu) return 0; } -static int snd_emu10k1x_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_emu10k1x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1554,6 +1554,12 @@ static int snd_emu10k1x_probe(struct pci_dev *pci, return 0; } +static int snd_emu10k1x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_emu10k1x_probe(pci, pci_id)); +} + // PCI IDs static const struct pci_device_id snd_emu10k1x_ids[] = { { PCI_VDEVICE(CREATIVE, 0x0006), 0 }, /* Dell OEM version (EMU10K1) */ diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c index 2651f0c64c06..94efe347a97a 100644 --- a/sound/pci/ens1370.c +++ b/sound/pci/ens1370.c @@ -2304,8 +2304,8 @@ static irqreturn_t snd_audiopci_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int snd_audiopci_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_audiopci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2369,6 +2369,12 @@ static int snd_audiopci_probe(struct pci_dev *pci, return 0; } +static int snd_audiopci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_audiopci_probe(pci, pci_id)); +} + static struct pci_driver ens137x_driver = { .name = KBUILD_MODNAME, .id_table = snd_audiopci_ids, diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c index 00b976f42a3d..e34ec6f89e7e 100644 --- a/sound/pci/es1938.c +++ b/sound/pci/es1938.c @@ -1716,8 +1716,8 @@ static int snd_es1938_mixer(struct es1938 *chip) } -static int snd_es1938_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_es1938_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1796,6 +1796,12 @@ static int snd_es1938_probe(struct pci_dev *pci, return 0; } +static int snd_es1938_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_es1938_probe(pci, pci_id)); +} + static struct pci_driver es1938_driver = { .name = KBUILD_MODNAME, .id_table = snd_es1938_ids, diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c index 6a8a02a9ecf4..4a7e20bb11bc 100644 --- a/sound/pci/es1968.c +++ b/sound/pci/es1968.c @@ -2741,8 +2741,8 @@ static int snd_es1968_create(struct snd_card *card, /* */ -static int snd_es1968_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_es1968_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2848,6 +2848,12 @@ static int snd_es1968_probe(struct pci_dev *pci, return 0; } +static int snd_es1968_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_es1968_probe(pci, pci_id)); +} + static struct pci_driver es1968_driver = { .name = KBUILD_MODNAME, .id_table = snd_es1968_ids, diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c index 9c22ff19e56d..62b3cb126c6d 100644 --- a/sound/pci/fm801.c +++ b/sound/pci/fm801.c @@ -1268,8 +1268,8 @@ static int snd_fm801_create(struct snd_card *card, return 0; } -static int snd_card_fm801_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_fm801_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1333,6 +1333,12 @@ static int snd_card_fm801_probe(struct pci_dev *pci, return 0; } +static int snd_card_fm801_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_fm801_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static const unsigned char saved_regs[] = { FM801_PCM_VOL, FM801_I2S_VOL, FM801_FM_VOL, FM801_REC_SRC, diff --git a/sound/pci/hda/patch_cs8409-tables.c b/sound/pci/hda/patch_cs8409-tables.c index 2d1fa706327b..74c50ec040d9 100644 --- a/sound/pci/hda/patch_cs8409-tables.c +++ b/sound/pci/hda/patch_cs8409-tables.c @@ -478,28 +478,29 @@ const struct snd_pci_quirk cs8409_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0A29, "Bullseye", CS8409_BULLSEYE), SND_PCI_QUIRK(0x1028, 0x0A2A, "Bullseye", CS8409_BULLSEYE), SND_PCI_QUIRK(0x1028, 0x0A2B, "Bullseye", CS8409_BULLSEYE), + SND_PCI_QUIRK(0x1028, 0x0A77, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A78, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A79, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A7A, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A7D, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A7E, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A7F, "Cyborg", CS8409_CYBORG), + SND_PCI_QUIRK(0x1028, 0x0A80, "Cyborg", CS8409_CYBORG), SND_PCI_QUIRK(0x1028, 0x0AB0, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0AB2, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0AB1, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0AB3, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0AB4, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0AB5, "Warlock", CS8409_WARLOCK), + SND_PCI_QUIRK(0x1028, 0x0ACF, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0AD0, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0AD1, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0AD2, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0AD3, "Dolphin", CS8409_DOLPHIN), SND_PCI_QUIRK(0x1028, 0x0AD9, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0ADA, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0ADB, "Warlock", CS8409_WARLOCK), SND_PCI_QUIRK(0x1028, 0x0ADC, "Warlock", CS8409_WARLOCK), - SND_PCI_QUIRK(0x1028, 0x0AF4, "Warlock", CS8409_WARLOCK), - SND_PCI_QUIRK(0x1028, 0x0AF5, "Warlock", CS8409_WARLOCK), - SND_PCI_QUIRK(0x1028, 0x0BB5, "Warlock N3 15 TGL-U Nuvoton EC", CS8409_WARLOCK), - SND_PCI_QUIRK(0x1028, 0x0BB6, "Warlock V3 15 TGL-U Nuvoton EC", CS8409_WARLOCK), - SND_PCI_QUIRK(0x1028, 0x0A77, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A78, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A79, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A7A, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A7D, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A7E, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A7F, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0A80, "Cyborg", CS8409_CYBORG), SND_PCI_QUIRK(0x1028, 0x0ADF, "Cyborg", CS8409_CYBORG), SND_PCI_QUIRK(0x1028, 0x0AE0, "Cyborg", CS8409_CYBORG), SND_PCI_QUIRK(0x1028, 0x0AE1, "Cyborg", CS8409_CYBORG), @@ -512,11 +513,30 @@ const struct snd_pci_quirk cs8409_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0AEE, "Cyborg", CS8409_CYBORG), SND_PCI_QUIRK(0x1028, 0x0AEF, "Cyborg", CS8409_CYBORG), SND_PCI_QUIRK(0x1028, 0x0AF0, "Cyborg", CS8409_CYBORG), - SND_PCI_QUIRK(0x1028, 0x0AD0, "Dolphin", CS8409_DOLPHIN), - SND_PCI_QUIRK(0x1028, 0x0AD1, "Dolphin", CS8409_DOLPHIN), - SND_PCI_QUIRK(0x1028, 0x0AD2, "Dolphin", CS8409_DOLPHIN), - SND_PCI_QUIRK(0x1028, 0x0AD3, "Dolphin", CS8409_DOLPHIN), - SND_PCI_QUIRK(0x1028, 0x0ACF, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0AF4, "Warlock", CS8409_WARLOCK), + SND_PCI_QUIRK(0x1028, 0x0AF5, "Warlock", CS8409_WARLOCK), + SND_PCI_QUIRK(0x1028, 0x0B92, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0B93, "Warlock MLK Dual Mic", CS8409_WARLOCK_MLK_DUAL_MIC), + SND_PCI_QUIRK(0x1028, 0x0B94, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0B95, "Warlock MLK Dual Mic", CS8409_WARLOCK_MLK_DUAL_MIC), + SND_PCI_QUIRK(0x1028, 0x0B96, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0B97, "Warlock MLK Dual Mic", CS8409_WARLOCK_MLK_DUAL_MIC), + SND_PCI_QUIRK(0x1028, 0x0BB2, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0BB3, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0BB4, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0BB5, "Warlock N3 15 TGL-U Nuvoton EC", CS8409_WARLOCK), + SND_PCI_QUIRK(0x1028, 0x0BB6, "Warlock V3 15 TGL-U Nuvoton EC", CS8409_WARLOCK), + SND_PCI_QUIRK(0x1028, 0x0BB8, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0BB9, "Warlock MLK Dual Mic", CS8409_WARLOCK_MLK_DUAL_MIC), + SND_PCI_QUIRK(0x1028, 0x0BBA, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0BBB, "Warlock MLK Dual Mic", CS8409_WARLOCK_MLK_DUAL_MIC), + SND_PCI_QUIRK(0x1028, 0x0BBC, "Warlock MLK", CS8409_WARLOCK_MLK), + SND_PCI_QUIRK(0x1028, 0x0BBD, "Warlock MLK Dual Mic", CS8409_WARLOCK_MLK_DUAL_MIC), + SND_PCI_QUIRK(0x1028, 0x0BD4, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0BD5, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0BD6, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0BD7, "Dolphin", CS8409_DOLPHIN), + SND_PCI_QUIRK(0x1028, 0x0BD8, "Dolphin", CS8409_DOLPHIN), {} /* terminator */ }; @@ -524,6 +544,8 @@ const struct snd_pci_quirk cs8409_fixup_tbl[] = { const struct hda_model_fixup cs8409_models[] = { { .id = CS8409_BULLSEYE, .name = "bullseye" }, { .id = CS8409_WARLOCK, .name = "warlock" }, + { .id = CS8409_WARLOCK_MLK, .name = "warlock mlk" }, + { .id = CS8409_WARLOCK_MLK_DUAL_MIC, .name = "warlock mlk dual mic" }, { .id = CS8409_CYBORG, .name = "cyborg" }, { .id = CS8409_DOLPHIN, .name = "dolphin" }, {} @@ -542,6 +564,18 @@ const struct hda_fixup cs8409_fixups[] = { .chained = true, .chain_id = CS8409_FIXUPS, }, + [CS8409_WARLOCK_MLK] = { + .type = HDA_FIXUP_PINS, + .v.pins = cs8409_cs42l42_pincfgs, + .chained = true, + .chain_id = CS8409_FIXUPS, + }, + [CS8409_WARLOCK_MLK_DUAL_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = cs8409_cs42l42_pincfgs, + .chained = true, + .chain_id = CS8409_FIXUPS, + }, [CS8409_CYBORG] = { .type = HDA_FIXUP_PINS, .v.pins = cs8409_cs42l42_pincfgs, diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index aff2b5abb81e..343fabc4387d 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -733,6 +733,7 @@ static void cs42l42_resume(struct sub_codec *cs42l42) { 0x130A, 0x00 }, { 0x130F, 0x00 }, }; + int fsv_old, fsv_new; /* Bring CS42L42 out of Reset */ gpio_data = snd_hda_codec_read(codec, CS8409_PIN_AFG, 0, AC_VERB_GET_GPIO_DATA, 0); @@ -749,8 +750,13 @@ static void cs42l42_resume(struct sub_codec *cs42l42) /* Clear interrupts, by reading interrupt status registers */ cs8409_i2c_bulk_read(cs42l42, irq_regs, ARRAY_SIZE(irq_regs)); - if (cs42l42->full_scale_vol) - cs8409_i2c_write(cs42l42, 0x2001, 0x01); + fsv_old = cs8409_i2c_read(cs42l42, 0x2001); + if (cs42l42->full_scale_vol == CS42L42_FULL_SCALE_VOL_0DB) + fsv_new = fsv_old & ~CS42L42_FULL_SCALE_VOL_MASK; + else + fsv_new = fsv_old & CS42L42_FULL_SCALE_VOL_MASK; + if (fsv_new != fsv_old) + cs8409_i2c_write(cs42l42, 0x2001, fsv_new); /* we have to explicitly allow unsol event handling even during the * resume phase so that the jack event is processed properly @@ -906,9 +912,15 @@ static void cs8409_cs42l42_hw_init(struct hda_codec *codec) cs8409_vendor_coef_set(codec, seq_bullseye->cir, seq_bullseye->coeff); } - /* DMIC1_MO=00b, DMIC1/2_SR=1 */ - if (codec->fixup_id == CS8409_WARLOCK || codec->fixup_id == CS8409_CYBORG) - cs8409_vendor_coef_set(codec, 0x09, 0x0003); + switch (codec->fixup_id) { + case CS8409_CYBORG: + case CS8409_WARLOCK_MLK_DUAL_MIC: + /* DMIC1_MO=00b, DMIC1/2_SR=1 */ + cs8409_vendor_coef_set(codec, CS8409_DMIC_CFG, 0x0003); + break; + default: + break; + } cs42l42_resume(cs42l42); @@ -993,25 +1005,17 @@ void cs8409_cs42l42_fixups(struct hda_codec *codec, const struct hda_fixup *fix, cs8409_fix_caps(codec, CS8409_CS42L42_HP_PIN_NID); cs8409_fix_caps(codec, CS8409_CS42L42_AMIC_PIN_NID); - /* Set TIP_SENSE_EN for analog front-end of tip sense. - * Additionally set HSBIAS_SENSE_EN and Full Scale volume for some variants. - */ + /* Set HSBIAS_SENSE_EN and Full Scale volume for some variants. */ switch (codec->fixup_id) { - case CS8409_WARLOCK: + case CS8409_WARLOCK_MLK: + case CS8409_WARLOCK_MLK_DUAL_MIC: spec->scodecs[CS8409_CODEC0]->hsbias_hiz = 0x0020; - spec->scodecs[CS8409_CODEC0]->full_scale_vol = 1; - break; - case CS8409_BULLSEYE: - spec->scodecs[CS8409_CODEC0]->hsbias_hiz = 0x0020; - spec->scodecs[CS8409_CODEC0]->full_scale_vol = 0; - break; - case CS8409_CYBORG: - spec->scodecs[CS8409_CODEC0]->hsbias_hiz = 0x00a0; - spec->scodecs[CS8409_CODEC0]->full_scale_vol = 1; + spec->scodecs[CS8409_CODEC0]->full_scale_vol = CS42L42_FULL_SCALE_VOL_0DB; break; default: - spec->scodecs[CS8409_CODEC0]->hsbias_hiz = 0x0003; - spec->scodecs[CS8409_CODEC0]->full_scale_vol = 1; + spec->scodecs[CS8409_CODEC0]->hsbias_hiz = 0x0020; + spec->scodecs[CS8409_CODEC0]->full_scale_vol = + CS42L42_FULL_SCALE_VOL_MINUS6DB; break; } @@ -1222,6 +1226,9 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac cs8409_fix_caps(codec, DOLPHIN_LO_PIN_NID); cs8409_fix_caps(codec, DOLPHIN_AMIC_PIN_NID); + spec->scodecs[CS8409_CODEC0]->full_scale_vol = CS42L42_FULL_SCALE_VOL_MINUS6DB; + spec->scodecs[CS8409_CODEC1]->full_scale_vol = CS42L42_FULL_SCALE_VOL_MINUS6DB; + break; case HDA_FIXUP_ACT_PROBE: /* Fix Sample Rate to 48kHz */ diff --git a/sound/pci/hda/patch_cs8409.h b/sound/pci/hda/patch_cs8409.h index d0b725c7285b..7df46bd8d2da 100644 --- a/sound/pci/hda/patch_cs8409.h +++ b/sound/pci/hda/patch_cs8409.h @@ -235,6 +235,9 @@ enum cs8409_coefficient_index_registers { #define CS42L42_I2C_SLEEP_US (2000) #define CS42L42_PDN_TIMEOUT_US (250000) #define CS42L42_PDN_SLEEP_US (2000) +#define CS42L42_FULL_SCALE_VOL_MASK (2) +#define CS42L42_FULL_SCALE_VOL_0DB (1) +#define CS42L42_FULL_SCALE_VOL_MINUS6DB (0) /* Dell BULLSEYE / WARLOCK / CYBORG Specific Definitions */ @@ -264,6 +267,8 @@ enum cs8409_coefficient_index_registers { enum { CS8409_BULLSEYE, CS8409_WARLOCK, + CS8409_WARLOCK_MLK, + CS8409_WARLOCK_MLK_DUAL_MIC, CS8409_CYBORG, CS8409_FIXUPS, CS8409_DOLPHIN, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index c85ed7bc121e..3e086eebf88d 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1625,6 +1625,7 @@ static void hdmi_present_sense_via_verbs(struct hdmi_spec_per_pin *per_pin, struct hda_codec *codec = per_pin->codec; struct hdmi_spec *spec = codec->spec; struct hdmi_eld *eld = &spec->temp_eld; + struct device *dev = hda_codec_dev(codec); hda_nid_t pin_nid = per_pin->pin_nid; int dev_id = per_pin->dev_id; /* @@ -1638,8 +1639,13 @@ static void hdmi_present_sense_via_verbs(struct hdmi_spec_per_pin *per_pin, int present; int ret; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return; +#endif + ret = snd_hda_power_up_pm(codec); - if (ret < 0 && pm_runtime_suspended(hda_codec_dev(codec))) + if (ret < 0 && pm_runtime_suspended(dev)) goto out; present = snd_hda_jack_pin_sense(codec, pin_nid, dev_id); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c78f16944f43..62fbf3772b41 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2619,6 +2619,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65e5, "Clevo PC50D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65f1, "Clevo PC50HS", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65f5, "Clevo PD50PN[NRT]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -3617,8 +3618,8 @@ static void alc256_shutup(struct hda_codec *codec) /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly * when booting with headset plugged. So skip setting it for the codec alc257 */ - if (spec->codec_variant != ALC269_TYPE_ALC257 && - spec->codec_variant != ALC269_TYPE_ALC256) + if (codec->core.vendor_id != 0x10ec0236 && + codec->core.vendor_id != 0x10ec0257) alc_update_coef_idx(codec, 0x46, 0, 3 << 12); if (!spec->no_shutup_pins) @@ -7006,6 +7007,7 @@ enum { ALC287_FIXUP_LEGION_16ACHG6, ALC287_FIXUP_CS35L41_I2C_2, ALC245_FIXUP_CS35L41_SPI_2, + ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_4, ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED, ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED, @@ -8771,6 +8773,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_spi_two, }, + [ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_spi_two, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_LED, + }, [ALC245_FIXUP_CS35L41_SPI_4] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_spi_four, @@ -9026,7 +9034,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89ac, "HP EliteBook 640 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ae, "HP EliteBook 650 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89c3, "Zbook Studio G9", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), @@ -9257,6 +9265,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x505d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x505f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x5062, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x508b, "Thinkpad X12 Gen 1", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), @@ -11140,6 +11149,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), + SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32ca, "Lenovo ThinkCentre M80", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c index f6275868877a..6fab2ad85bbe 100644 --- a/sound/pci/ice1712/ice1724.c +++ b/sound/pci/ice1712/ice1724.c @@ -2519,8 +2519,8 @@ static int snd_vt1724_create(struct snd_card *card, * */ -static int snd_vt1724_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_vt1724_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2662,6 +2662,12 @@ static int snd_vt1724_probe(struct pci_dev *pci, return 0; } +static int snd_vt1724_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_vt1724_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_vt1724_suspend(struct device *dev) { diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index a51032b3ac4d..ae285c0a629c 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -3109,8 +3109,8 @@ static int check_default_spdif_aclink(struct pci_dev *pci) return 0; } -static int snd_intel8x0_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_intel8x0_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct intel8x0 *chip; @@ -3189,6 +3189,12 @@ static int snd_intel8x0_probe(struct pci_dev *pci, return 0; } +static int snd_intel8x0_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_intel8x0_probe(pci, pci_id)); +} + static struct pci_driver intel8x0_driver = { .name = KBUILD_MODNAME, .id_table = snd_intel8x0_ids, diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c index 7de3cb2f17b5..2845cc006d0c 100644 --- a/sound/pci/intel8x0m.c +++ b/sound/pci/intel8x0m.c @@ -1178,8 +1178,8 @@ static struct shortname_table { { 0 }, }; -static int snd_intel8x0m_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_intel8x0m_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct intel8x0m *chip; @@ -1225,6 +1225,12 @@ static int snd_intel8x0m_probe(struct pci_dev *pci, return 0; } +static int snd_intel8x0m_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_intel8x0m_probe(pci, pci_id)); +} + static struct pci_driver intel8x0m_driver = { .name = KBUILD_MODNAME, .id_table = snd_intel8x0m_ids, diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c index 5c9e240ff6a9..33b4f95d65b3 100644 --- a/sound/pci/korg1212/korg1212.c +++ b/sound/pci/korg1212/korg1212.c @@ -2355,7 +2355,7 @@ snd_korg1212_probe(struct pci_dev *pci, err = snd_korg1212_create(card, pci); if (err < 0) - return err; + goto error; strcpy(card->driver, "korg1212"); strcpy(card->shortname, "korg1212"); @@ -2366,10 +2366,14 @@ snd_korg1212_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver korg1212_driver = { diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c index 5269a1d396a5..1aa30e90b86a 100644 --- a/sound/pci/lola/lola.c +++ b/sound/pci/lola/lola.c @@ -637,8 +637,8 @@ static int lola_create(struct snd_card *card, struct pci_dev *pci, int dev) return 0; } -static int lola_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __lola_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -687,6 +687,12 @@ static int lola_probe(struct pci_dev *pci, return 0; } +static int lola_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __lola_probe(pci, pci_id)); +} + /* PCI IDs */ static const struct pci_device_id lola_ids[] = { { PCI_VDEVICE(DIGIGRAM, 0x0001) }, diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c index 168a1084f730..bd9b6148dd6f 100644 --- a/sound/pci/lx6464es/lx6464es.c +++ b/sound/pci/lx6464es/lx6464es.c @@ -1019,7 +1019,7 @@ static int snd_lx6464es_probe(struct pci_dev *pci, err = snd_lx6464es_create(card, pci); if (err < 0) { dev_err(card->dev, "error during snd_lx6464es_create\n"); - return err; + goto error; } strcpy(card->driver, "LX6464ES"); @@ -1036,12 +1036,16 @@ static int snd_lx6464es_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; dev_dbg(chip->card->dev, "initialization successful\n"); pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver lx6464es_driver = { diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c index 056838ead21d..261850775c80 100644 --- a/sound/pci/maestro3.c +++ b/sound/pci/maestro3.c @@ -2637,7 +2637,7 @@ snd_m3_create(struct snd_card *card, struct pci_dev *pci, /* */ static int -snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2702,6 +2702,12 @@ snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_m3_probe(pci, pci_id)); +} + static struct pci_driver m3_driver = { .name = KBUILD_MODNAME, .id_table = snd_m3_ids, diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c index c9c178504959..f99a1e96e923 100644 --- a/sound/pci/nm256/nm256.c +++ b/sound/pci/nm256/nm256.c @@ -1573,7 +1573,6 @@ snd_nm256_create(struct snd_card *card, struct pci_dev *pci) chip->coeffs_current = 0; snd_nm256_init_chip(chip); - card->private_free = snd_nm256_free; // pci_set_master(pci); /* needed? */ return 0; @@ -1680,6 +1679,7 @@ static int snd_nm256_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) return err; + card->private_free = snd_nm256_free; pci_set_drvdata(pci, card); return 0; diff --git a/sound/pci/oxygen/oxygen_lib.c b/sound/pci/oxygen/oxygen_lib.c index 4fb3f2484fdb..92ffe9dc20c5 100644 --- a/sound/pci/oxygen/oxygen_lib.c +++ b/sound/pci/oxygen/oxygen_lib.c @@ -576,7 +576,7 @@ static void oxygen_card_free(struct snd_card *card) mutex_destroy(&chip->mutex); } -int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, +static int __oxygen_pci_probe(struct pci_dev *pci, int index, char *id, struct module *owner, const struct pci_device_id *ids, int (*get_model)(struct oxygen *chip, @@ -701,6 +701,16 @@ int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, pci_set_drvdata(pci, card); return 0; } + +int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, + struct module *owner, + const struct pci_device_id *ids, + int (*get_model)(struct oxygen *chip, + const struct pci_device_id *id)) +{ + return snd_card_free_on_error(&pci->dev, + __oxygen_pci_probe(pci, index, id, owner, ids, get_model)); +} EXPORT_SYMBOL(oxygen_pci_probe); #ifdef CONFIG_PM_SLEEP diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index 5a987c683c41..b37c877c2c16 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -2023,7 +2023,7 @@ static void snd_riptide_joystick_remove(struct pci_dev *pci) #endif static int -snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2124,6 +2124,12 @@ snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_riptide_probe(pci, pci_id)); +} + static struct pci_driver driver = { .name = KBUILD_MODNAME, .id_table = snd_riptide_ids, diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c index 5b6bd9f0b2f7..9c0ac025e143 100644 --- a/sound/pci/rme32.c +++ b/sound/pci/rme32.c @@ -1875,7 +1875,7 @@ static void snd_rme32_card_free(struct snd_card *card) } static int -snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct rme32 *rme32; @@ -1927,6 +1927,12 @@ snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_rme32_probe(pci, pci_id)); +} + static struct pci_driver rme32_driver = { .name = KBUILD_MODNAME, .id_table = snd_rme32_ids, diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c index 8fc811504920..bccb7e0d3d11 100644 --- a/sound/pci/rme96.c +++ b/sound/pci/rme96.c @@ -2430,8 +2430,8 @@ static void snd_rme96_card_free(struct snd_card *card) } static int -snd_rme96_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +__snd_rme96_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct rme96 *rme96; @@ -2498,6 +2498,12 @@ snd_rme96_probe(struct pci_dev *pci, return 0; } +static int snd_rme96_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_rme96_probe(pci, pci_id)); +} + static struct pci_driver rme96_driver = { .name = KBUILD_MODNAME, .id_table = snd_rme96_ids, diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 96c12dfb24cf..3db641318d3a 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -5444,17 +5444,21 @@ static int snd_hdsp_probe(struct pci_dev *pci, hdsp->pci = pci; err = snd_hdsp_create(card, hdsp); if (err) - return err; + goto error; strcpy(card->shortname, "Hammerfall DSP"); sprintf(card->longname, "%s at 0x%lx, irq %d", hdsp->card_name, hdsp->port, hdsp->irq); err = snd_card_register(card); if (err) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver hdsp_driver = { diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index ff06ee82607c..fa1812e7a49d 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -6895,7 +6895,7 @@ static int snd_hdspm_probe(struct pci_dev *pci, err = snd_hdspm_create(card, hdspm); if (err < 0) - return err; + goto error; if (hdspm->io_type != MADIface) { snprintf(card->shortname, sizeof(card->shortname), "%s_%x", @@ -6914,12 +6914,16 @@ static int snd_hdspm_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver hdspm_driver = { diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index 7755e19aa776..1d614fe89a6a 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -2572,7 +2572,7 @@ static int snd_rme9652_probe(struct pci_dev *pci, rme9652->pci = pci; err = snd_rme9652_create(card, rme9652, precise_ptr[dev]); if (err) - return err; + goto error; strcpy(card->shortname, rme9652->card_name); @@ -2580,10 +2580,14 @@ static int snd_rme9652_probe(struct pci_dev *pci, card->shortname, rme9652->port, rme9652->irq); err = snd_card_register(card); if (err) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver rme9652_driver = { diff --git a/sound/pci/sis7019.c b/sound/pci/sis7019.c index 0b722b0e0604..fabe393607f8 100644 --- a/sound/pci/sis7019.c +++ b/sound/pci/sis7019.c @@ -1331,8 +1331,8 @@ static int sis_chip_create(struct snd_card *card, return 0; } -static int snd_sis7019_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_sis7019_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct sis7019 *sis; @@ -1352,8 +1352,8 @@ static int snd_sis7019_probe(struct pci_dev *pci, if (!codecs) codecs = SIS_PRIMARY_CODEC_PRESENT; - rc = snd_card_new(&pci->dev, index, id, THIS_MODULE, - sizeof(*sis), &card); + rc = snd_devm_card_new(&pci->dev, index, id, THIS_MODULE, + sizeof(*sis), &card); if (rc < 0) return rc; @@ -1386,6 +1386,12 @@ static int snd_sis7019_probe(struct pci_dev *pci, return 0; } +static int snd_sis7019_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_sis7019_probe(pci, pci_id)); +} + static struct pci_driver sis7019_driver = { .name = KBUILD_MODNAME, .id_table = snd_sis7019_ids, diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c index c8c49881008f..f91cbf6eeca0 100644 --- a/sound/pci/sonicvibes.c +++ b/sound/pci/sonicvibes.c @@ -1387,8 +1387,8 @@ static int snd_sonicvibes_midi(struct sonicvibes *sonic, return 0; } -static int snd_sonic_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_sonic_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1459,6 +1459,12 @@ static int snd_sonic_probe(struct pci_dev *pci, return 0; } +static int snd_sonic_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_sonic_probe(pci, pci_id)); +} + static struct pci_driver sonicvibes_driver = { .name = KBUILD_MODNAME, .id_table = snd_sonic_ids, diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c index 65514f7e42d7..361b83fd721e 100644 --- a/sound/pci/via82xx.c +++ b/sound/pci/via82xx.c @@ -2458,8 +2458,8 @@ static int check_dxs_list(struct pci_dev *pci, int revision) return VIA_DXS_48K; }; -static int snd_via82xx_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct via82xx *chip; @@ -2569,6 +2569,12 @@ static int snd_via82xx_probe(struct pci_dev *pci, return 0; } +static int snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_via82xx_probe(pci, pci_id)); +} + static struct pci_driver via82xx_driver = { .name = KBUILD_MODNAME, .id_table = snd_via82xx_ids, diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c index 234f7fbed236..ca7f024bf8ec 100644 --- a/sound/pci/via82xx_modem.c +++ b/sound/pci/via82xx_modem.c @@ -1103,8 +1103,8 @@ static int snd_via82xx_create(struct snd_card *card, } -static int snd_via82xx_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct via82xx_modem *chip; @@ -1157,6 +1157,12 @@ static int snd_via82xx_probe(struct pci_dev *pci, return 0; } +static int snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_via82xx_probe(pci, pci_id)); +} + static struct pci_driver via82xx_modem_driver = { .name = KBUILD_MODNAME, .id_table = snd_via82xx_modem_ids, diff --git a/sound/soc/codecs/mt6358.c b/sound/soc/codecs/mt6358.c index 9b263a9a669d..4c7b5d940799 100644 --- a/sound/soc/codecs/mt6358.c +++ b/sound/soc/codecs/mt6358.c @@ -107,6 +107,7 @@ int mt6358_set_mtkaif_protocol(struct snd_soc_component *cmpnt, priv->mtkaif_protocol = mtkaif_protocol; return 0; } +EXPORT_SYMBOL_GPL(mt6358_set_mtkaif_protocol); static void playback_gpio_set(struct mt6358_priv *priv) { @@ -273,6 +274,7 @@ int mt6358_mtkaif_calibration_enable(struct snd_soc_component *cmpnt) 1 << RG_AUD_PAD_TOP_DAT_MISO_LOOPBACK_SFT); return 0; } +EXPORT_SYMBOL_GPL(mt6358_mtkaif_calibration_enable); int mt6358_mtkaif_calibration_disable(struct snd_soc_component *cmpnt) { @@ -296,6 +298,7 @@ int mt6358_mtkaif_calibration_disable(struct snd_soc_component *cmpnt) capture_gpio_reset(priv); return 0; } +EXPORT_SYMBOL_GPL(mt6358_mtkaif_calibration_disable); int mt6358_set_mtkaif_calibration_phase(struct snd_soc_component *cmpnt, int phase_1, int phase_2) @@ -310,6 +313,7 @@ int mt6358_set_mtkaif_calibration_phase(struct snd_soc_component *cmpnt, phase_2 << RG_AUD_PAD_TOP_PHASE_MODE2_SFT); return 0; } +EXPORT_SYMBOL_GPL(mt6358_set_mtkaif_calibration_phase); /* dl pga gain */ enum { diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index 370bc790c6ba..d9a0d4768c4d 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -462,11 +462,9 @@ static int hp_jack_event(struct notifier_block *nb, unsigned long event, if (event & SND_JACK_HEADPHONE) /* Disable speaker if headphone is plugged in */ - snd_soc_dapm_disable_pin(dapm, "Ext Spk"); + return snd_soc_dapm_disable_pin(dapm, "Ext Spk"); else - snd_soc_dapm_enable_pin(dapm, "Ext Spk"); - - return 0; + return snd_soc_dapm_enable_pin(dapm, "Ext Spk"); } static struct notifier_block hp_jack_nb = { @@ -481,11 +479,9 @@ static int mic_jack_event(struct notifier_block *nb, unsigned long event, if (event & SND_JACK_MICROPHONE) /* Disable dmic if microphone is plugged in */ - snd_soc_dapm_disable_pin(dapm, "DMIC"); + return snd_soc_dapm_disable_pin(dapm, "DMIC"); else - snd_soc_dapm_enable_pin(dapm, "DMIC"); - - return 0; + return snd_soc_dapm_enable_pin(dapm, "DMIC"); } static struct notifier_block mic_jack_nb = { diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index d3b710406941..98700e75b82a 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -469,14 +469,14 @@ static int rockchip_i2s_tdm_set_fmt(struct snd_soc_dai *cpu_dai, txcr_val = I2S_TXCR_IBM_NORMAL; rxcr_val = I2S_RXCR_IBM_NORMAL; break; - case SND_SOC_DAIFMT_DSP_A: /* PCM no delay mode */ - txcr_val = I2S_TXCR_TFS_PCM; - rxcr_val = I2S_RXCR_TFS_PCM; - break; - case SND_SOC_DAIFMT_DSP_B: /* PCM delay 1 mode */ + case SND_SOC_DAIFMT_DSP_A: /* PCM delay 1 mode */ txcr_val = I2S_TXCR_TFS_PCM | I2S_TXCR_PBM_MODE(1); rxcr_val = I2S_RXCR_TFS_PCM | I2S_RXCR_PBM_MODE(1); break; + case SND_SOC_DAIFMT_DSP_B: /* PCM no delay mode */ + txcr_val = I2S_TXCR_TFS_PCM; + rxcr_val = I2S_RXCR_TFS_PCM; + break; default: ret = -EINVAL; goto err_pm_put; diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index b53f216d4ecc..172419392b33 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -84,6 +84,7 @@ if SND_SOC_SOF_PCI config SND_SOC_SOF_MERRIFIELD tristate "SOF support for Tangier/Merrifield" default SND_SOC_SOF_PCI + select SND_SOC_SOF_PCI_DEV select SND_SOC_SOF_INTEL_ATOM_HIFI_EP help This adds support for Sound Open Firmware for Intel(R) platforms diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index cec6e91afea2..6d699065e81a 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -669,9 +669,9 @@ static const struct snd_pcm_hardware snd_usb_hardware = SNDRV_PCM_INFO_PAUSE, .channels_min = 1, .channels_max = 256, - .buffer_bytes_max = 1024 * 1024, + .buffer_bytes_max = INT_MAX, /* limited by BUFFER_TIME later */ .period_bytes_min = 64, - .period_bytes_max = 512 * 1024, + .period_bytes_max = INT_MAX, /* limited by PERIOD_TIME later */ .periods_min = 2, .periods_max = 1024, }; @@ -1064,6 +1064,18 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre return err; } + /* set max period and buffer sizes for 1 and 2 seconds, respectively */ + err = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIOD_TIME, + 0, 1000000); + if (err < 0) + return err; + err = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_BUFFER_TIME, + 0, 2000000); + if (err < 0) + return err; + /* additional hw constraints for implicit fb */ err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, hw_rule_format_implicit_fb, subs, diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 167834133b9b..b8359a0aa008 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -8,7 +8,7 @@ */ /* handling of USB vendor/product ID pairs as 32-bit numbers */ -#define USB_ID(vendor, product) (((vendor) << 16) | (product)) +#define USB_ID(vendor, product) (((unsigned int)(vendor) << 16) | (product)) #define USB_ID_VENDOR(id) ((id) >> 16) #define USB_ID_PRODUCT(id) ((u16)(id)) diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index b00634663346..0d828e35b401 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -1652,7 +1652,7 @@ static void hdmi_lpe_audio_free(struct snd_card *card) * This function is called when the i915 driver creates the * hdmi-lpe-audio platform device. */ -static int hdmi_lpe_audio_probe(struct platform_device *pdev) +static int __hdmi_lpe_audio_probe(struct platform_device *pdev) { struct snd_card *card; struct snd_intelhad_card *card_ctx; @@ -1815,6 +1815,11 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) return 0; } +static int hdmi_lpe_audio_probe(struct platform_device *pdev) +{ + return snd_card_free_on_error(&pdev->dev, __hdmi_lpe_audio_probe(pdev)); +} + static const struct dev_pm_ops hdmi_lpe_audio_pm = { SET_SYSTEM_SLEEP_PM_OPS(hdmi_lpe_audio_suspend, hdmi_lpe_audio_resume) }; diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 9afcc6467a09..e09d6908a21d 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 490d489d0ee8..c1b6ddc02d2f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -419,6 +419,16 @@ struct kvm_arm_copy_mte_tags { #define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS #define KVM_PSCI_RET_DENIED PSCI_RET_DENIED +/* arm64-specific kvm_run::system_event flags */ +/* + * Reset caused by a PSCI v1.1 SYSTEM_RESET2 call. + * Valid only when the system event has a type of KVM_SYSTEM_EVENT_RESET. + */ +#define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0) + +/* run->fail_entry.hardware_entry_failure_reason codes. */ +#define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 3edf05e98e58..73e643ae94b6 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -388,6 +388,7 @@ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ #define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ #define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ #define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 0e7f303542bf..ee15311b6be1 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -128,9 +128,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 @@ -205,6 +205,8 @@ #define RTIT_CTL_DISRETC BIT(11) #define RTIT_CTL_PTW_EN BIT(12) #define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_EVENT_EN BIT(31) +#define RTIT_CTL_NOTNT BIT_ULL(55) #define RTIT_CTL_MTC_RANGE_OFFSET 14 #define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) #define RTIT_CTL_CYC_THRESH_OFFSET 19 @@ -360,11 +362,29 @@ #define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c #define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d - #define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 +/* Control-flow Enforcement Technology MSRs */ +#define MSR_IA32_U_CET 0x000006a0 /* user mode cet */ +#define MSR_IA32_S_CET 0x000006a2 /* kernel mode cet */ +#define CET_SHSTK_EN BIT_ULL(0) +#define CET_WRSS_EN BIT_ULL(1) +#define CET_ENDBR_EN BIT_ULL(2) +#define CET_LEG_IW_EN BIT_ULL(3) +#define CET_NO_TRACK_EN BIT_ULL(4) +#define CET_SUPPRESS_DISABLE BIT_ULL(5) +#define CET_RESERVED (BIT_ULL(6) | BIT_ULL(7) | BIT_ULL(8) | BIT_ULL(9)) +#define CET_SUPPRESS BIT_ULL(10) +#define CET_WAIT_ENDBR BIT_ULL(11) + +#define MSR_IA32_PL0_SSP 0x000006a4 /* ring-0 shadow stack pointer */ +#define MSR_IA32_PL1_SSP 0x000006a5 /* ring-1 shadow stack pointer */ +#define MSR_IA32_PL2_SSP 0x000006a6 /* ring-2 shadow stack pointer */ +#define MSR_IA32_PL3_SSP 0x000006a7 /* ring-3 shadow stack pointer */ +#define MSR_IA32_INT_SSP_TAB 0x000006a8 /* exception shadow stack table */ + /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 9800f966fd51..c6d2c77d0252 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -74,7 +74,7 @@ CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS)) CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ - -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(or $(OUTPUT),.) \ -I$(LIBBPF_INCLUDE) \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ @@ -180,7 +180,7 @@ endif $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP) $(QUIET_CLANG)$(CLANG) \ - -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(or $(OUTPUT),.) \ -I$(srctree)/tools/include/uapi/ \ -I$(LIBBPF_BOOTSTRAP_INCLUDE) \ -g -O2 -Wall -target bpf -c $< -o $@ diff --git a/tools/build/Makefile b/tools/build/Makefile index 6f11e6fc9ffe..17cdf01e29a0 100644 --- a/tools/build/Makefile +++ b/tools/build/Makefile @@ -36,7 +36,7 @@ TMP_O := $(if $(OUTPUT),$(OUTPUT)feature/,./) clean: $(call QUIET_CLEAN, fixdep) - $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)rm -f $(OUTPUT)fixdep $(call QUIET_CLEAN, feature-detect) ifneq ($(wildcard $(TMP_O)),) diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 1480910c792e..de66e1cc0734 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1)) PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) +ifeq ($(CC_NO_CLANG), 0) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro +endif + $(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) diff --git a/tools/counter/Makefile b/tools/counter/Makefile index 5ebc195fd9c0..8843f0fa6119 100644 --- a/tools/counter/Makefile +++ b/tools/counter/Makefile @@ -40,7 +40,7 @@ $(OUTPUT)counter_example: $(COUNTER_EXAMPLE) clean: rm -f $(ALL_PROGRAMS) rm -rf $(OUTPUT)include/linux/counter.h - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index 440434027557..d29c9c49e251 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -78,7 +78,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN) clean: rm -f $(ALL_PROGRAMS) rm -f $(OUTPUT)include/linux/gpio.h - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/hv/Makefile b/tools/hv/Makefile index b57143d9459c..fe770e679ae8 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -47,7 +47,7 @@ $(OUTPUT)hv_fcopy_daemon: $(HV_FCOPY_DAEMON_IN) clean: rm -f $(ALL_PROGRAMS) - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(sbindir); \ diff --git a/tools/iio/Makefile b/tools/iio/Makefile index 5d12ac4e7f8f..fa720f062229 100644 --- a/tools/iio/Makefile +++ b/tools/iio/Makefile @@ -58,7 +58,7 @@ $(OUTPUT)iio_generic_buffer: $(IIO_GENERIC_BUFFER_IN) clean: rm -f $(ALL_PROGRAMS) rm -rf $(OUTPUT)include/linux/iio - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 1567a3294c3d..6c1aa92a92e4 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -75,6 +75,8 @@ #define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ #define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 914ebd9290e5..05c3642aaece 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1118,10 +1118,16 @@ struct drm_i915_gem_exec_object2 { /** * When the EXEC_OBJECT_PINNED flag is specified this is populated by * the user with the GTT offset at which this object will be pinned. + * * When the I915_EXEC_NO_RELOC flag is specified this must contain the * presumed_offset of the object. + * * During execbuffer2 the kernel populates it with the value of the * current GTT offset of the object, for future presumed_offset writes. + * + * See struct drm_i915_gem_create_ext for the rules when dealing with + * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with + * minimum page sizes, like DG2. */ __u64 offset; @@ -3144,11 +3150,40 @@ struct drm_i915_gem_create_ext { * * The (page-aligned) allocated size for the object will be returned. * - * Note that for some devices we have might have further minimum - * page-size restrictions(larger than 4K), like for device local-memory. - * However in general the final size here should always reflect any - * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS - * extension to place the object in device local-memory. + * + * DG2 64K min page size implications: + * + * On discrete platforms, starting from DG2, we have to contend with GTT + * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE + * objects. Specifically the hardware only supports 64K or larger GTT + * page sizes for such memory. The kernel will already ensure that all + * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page + * sizes underneath. + * + * Note that the returned size here will always reflect any required + * rounding up done by the kernel, i.e 4K will now become 64K on devices + * such as DG2. + * + * Special DG2 GTT address alignment requirement: + * + * The GTT alignment will also need to be at least 2M for such objects. + * + * Note that due to how the hardware implements 64K GTT page support, we + * have some further complications: + * + * 1) The entire PDE (which covers a 2MB virtual address range), must + * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same + * PDE is forbidden by the hardware. + * + * 2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM + * objects. + * + * To keep things simple for userland, we mandate that any GTT mappings + * must be aligned to and rounded up to 2MB. The kernel will internally + * pad them out to the next 2MB boundary. As this only wastes virtual + * address space and avoids userland having to copy any needlessly + * complicated PDE sharing scheme (coloring) and only affects DG2, this + * is deemed to be a good compromise. */ __u64 size; /** diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index bbc6b7c2dc1b..91a6fe4e02c0 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -562,9 +562,12 @@ struct kvm_s390_mem_op { __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */ union { - __u8 ar; /* the access register number */ + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + }; __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* should be set to 0 */ + __u8 reserved[32]; /* ignored */ }; }; /* types for kvm_s390_mem_op->op */ @@ -572,9 +575,12 @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_LOGICAL_WRITE 1 #define KVM_S390_MEMOP_SIDA_READ 2 #define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) /* for KVM_INTERRUPT */ struct kvm_interrupt { @@ -1137,6 +1143,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_AIL_MODE_3 210 #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 +#define KVM_CAP_DISABLE_QUIRKS2 213 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c998860d7bbc..5d99e7c242a2 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -150,4 +150,11 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index a13e9c7f1fc5..e21e1b40b525 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -60,7 +60,7 @@ $(LIBFILE): $(API_IN) clean: $(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \ - find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) FORCE: diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index b8b37fe76006..064c89e31560 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -60,7 +60,7 @@ ifndef VERBOSE VERBOSE = 0 endif -INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.) \ +INCLUDES = -I$(or $(OUTPUT),.) \ -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi export prefix libdir src obj diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile index 08fe6e3c4089..21df023a2103 100644 --- a/tools/lib/perf/Makefile +++ b/tools/lib/perf/Makefile @@ -153,7 +153,7 @@ $(TESTS_STATIC): $(TESTS_IN) $(LIBPERF_A) $(LIBAPI) $(QUIET_LINK)$(CC) -o $@ $^ $(TESTS_SHARED): $(TESTS_IN) $(LIBAPI) - $(QUIET_LINK)$(CC) -o $@ -L$(if $(OUTPUT),$(OUTPUT),.) $^ -lperf + $(QUIET_LINK)$(CC) -o $@ -L$(or $(OUTPUT),.) $^ -lperf make-tests: libs $(TESTS_SHARED) $(TESTS_STATIC) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index ee66760f1e63..384d5e076ee4 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -319,6 +319,26 @@ struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map) return map->nr > 0 ? map->map[map->nr - 1] : result; } +/** Is 'b' a subset of 'a'. */ +bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b) +{ + if (a == b || !b) + return true; + if (!a || b->nr > a->nr) + return false; + + for (int i = 0, j = 0; i < a->nr; i++) { + if (a->map[i].cpu > b->map[j].cpu) + return false; + if (a->map[i].cpu == b->map[j].cpu) { + j++; + if (j == b->nr) + return true; + } + } + return false; +} + /* * Merge two cpumaps * @@ -335,17 +355,12 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, int i, j, k; struct perf_cpu_map *merged; - if (!orig && !other) - return NULL; - if (!orig) { - perf_cpu_map__get(other); - return other; - } - if (!other) - return orig; - if (orig->nr == other->nr && - !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu))) + if (perf_cpu_map__is_subset(orig, other)) return orig; + if (perf_cpu_map__is_subset(other, orig)) { + perf_cpu_map__put(orig); + return perf_cpu_map__get(other); + } tmp_len = orig->nr + other->nr; tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 9a770bfdc804..a09315538a30 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -41,10 +41,10 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, */ if (!evsel->own_cpus || evlist->has_user_cpus) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->cpus); - } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) { + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); + } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } else if (evsel->cpus != evsel->own_cpus) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evsel->own_cpus); @@ -123,10 +123,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist) void perf_evlist__exit(struct perf_evlist *evlist) { - perf_cpu_map__put(evlist->cpus); + perf_cpu_map__put(evlist->user_requested_cpus); perf_cpu_map__put(evlist->all_cpus); perf_thread_map__put(evlist->threads); - evlist->cpus = NULL; + evlist->user_requested_cpus = NULL; evlist->all_cpus = NULL; evlist->threads = NULL; fdarray__exit(&evlist->pollfd); @@ -155,9 +155,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, * original reference count of 1. If that is not the case it is up to * the caller to increase the reference count. */ - if (cpus != evlist->cpus) { - perf_cpu_map__put(evlist->cpus); - evlist->cpus = perf_cpu_map__get(cpus); + if (cpus != evlist->user_requested_cpus) { + perf_cpu_map__put(evlist->user_requested_cpus); + evlist->user_requested_cpus = perf_cpu_map__get(cpus); } if (threads != evlist->threads) { @@ -294,7 +294,7 @@ add: int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { - int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus); int nr_threads = perf_thread_map__nr(evlist->threads); int nfds = 0; struct perf_evsel *evsel; @@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, int idx, struct perf_mmap_param *mp, int cpu_idx, int thread, int *_output, int *_output_overwrite) { - struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx); struct perf_evsel *evsel; int revent; @@ -536,7 +536,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { int nr_threads = perf_thread_map__nr(evlist->threads); - int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus); int cpu, thread; for (cpu = 0; cpu < nr_cpus; cpu++) { @@ -564,8 +564,8 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) { int nr_mmaps; - nr_mmaps = perf_cpu_map__nr(evlist->cpus); - if (perf_cpu_map__empty(evlist->cpus)) + nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus); + if (perf_cpu_map__empty(evlist->user_requested_cpus)) nr_mmaps = perf_thread_map__nr(evlist->threads); return nr_mmaps; @@ -576,8 +576,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_mmap_param *mp) { struct perf_evsel *evsel; - const struct perf_cpu_map *cpus = evlist->cpus; - const struct perf_thread_map *threads = evlist->threads; + const struct perf_cpu_map *cpus = evlist->user_requested_cpus; if (!ops || !ops->get || !ops->mmap) return -EINVAL; @@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, perf_evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0) return -ENOMEM; } diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 1973a18c096b..35dd29642296 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -25,5 +25,6 @@ struct perf_cpu_map { #endif int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); +bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 4cefade540bd..e3e64f37db7b 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -19,7 +19,12 @@ struct perf_evlist { int nr_entries; int nr_groups; bool has_user_cpus; - struct perf_cpu_map *cpus; + /** + * The cpus passed from the command line or all online CPUs by + * default. + */ + struct perf_cpu_map *user_requested_cpus; + /** The union of all evsel cpu maps. */ struct perf_cpu_map *all_cpus; struct perf_thread_map *threads; int nr_mmaps; diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 1c777a72bb39..8f1a09cdfd17 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -63,7 +63,7 @@ $(LIBFILE): $(SUBCMD_IN) clean: $(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \ - find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) FORCE: diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 92ce4fce7bc7..0dbd397f319d 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -13,7 +13,7 @@ srctree := $(patsubst %/,%,$(dir $(srctree))) endif SUBCMD_SRCDIR = $(srctree)/tools/lib/subcmd/ -LIBSUBCMD_OUTPUT = $(if $(OUTPUT),$(OUTPUT),$(CURDIR)/) +LIBSUBCMD_OUTPUT = $(or $(OUTPUT),$(CURDIR)/) LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcmd.a OBJTOOL := $(OUTPUT)objtool diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6de5085e3e5a..bd0c2c828940 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1155,6 +1155,17 @@ static void annotate_call_site(struct objtool_file *file, : arch_nop_insn(insn->len)); insn->type = sibling ? INSN_RETURN : INSN_NOP; + + if (sibling) { + /* + * We've replaced the tail-call JMP insn by two new + * insn: RET; INT3, except we only have a single struct + * insn here. Mark it retpoline_safe to avoid the SLS + * warning, instead of adding another insn. + */ + insn->retpoline_safe = true; + } + return; } @@ -1239,11 +1250,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2) return insn1->func->pfunc == insn2->func->pfunc; } -static bool is_first_func_insn(struct instruction *insn) +static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn) { - return insn->offset == insn->func->offset || - (insn->type == INSN_ENDBR && - insn->offset == insn->func->offset + insn->len); + if (insn->offset == insn->func->offset) + return true; + + if (ibt) { + struct instruction *prev = prev_insn_same_sym(file, insn); + + if (prev && prev->type == INSN_ENDBR && + insn->offset == insn->func->offset + prev->len) + return true; + } + + return false; } /* @@ -1327,7 +1347,7 @@ static int add_jump_destinations(struct objtool_file *file) insn->jump_dest->func->pfunc = insn->func; } else if (!same_function(insn, insn->jump_dest) && - is_first_func_insn(insn->jump_dest)) { + is_first_func_insn(file, insn->jump_dest)) { /* internal sibling call (without reloc) */ add_call_dest(file, insn, insn->jump_dest->func, true); } diff --git a/tools/pci/Makefile b/tools/pci/Makefile index 4b95a5176355..57744778b518 100644 --- a/tools/pci/Makefile +++ b/tools/pci/Makefile @@ -42,7 +42,7 @@ $(OUTPUT)pcitest: $(PCITEST_IN) clean: rm -f $(ALL_PROGRAMS) rm -rf $(OUTPUT)include/ - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..f3bf9297bcc0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -790,6 +793,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9c935f86d172..69473a836bae 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -691,9 +691,8 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt) $(SCRIPTS) : % : %.sh $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@' -$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD ../../.git/ORIG_HEAD +$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) - $(Q)touch $(OUTPUT)PERF-VERSION-FILE # These can record PERF_VERSION perf.spec $(SCRIPTS) \ @@ -724,7 +723,7 @@ endif # get relative building directory (to $(OUTPUT)) # and '.' if it's $(OUTPUT) itself __build-dir = $(subst $(OUTPUT),,$(dir $@)) -build-dir = $(if $(__build-dir),$(__build-dir),.) +build-dir = $(or $(__build-dir),.) prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \ $(fadvise_advice_array) \ @@ -1090,7 +1089,7 @@ bpf-skel-clean: clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf-iostat $(LANG_BINDINGS) - $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ @@ -1139,21 +1138,12 @@ else @echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP" endif -# -# Trick: if ../../.git does not exist - we are building out of tree for example, -# then force version regeneration: -# -ifeq ($(wildcard ../../.git/HEAD),) - GIT-HEAD-PHONY = ../../.git/HEAD ../../.git/ORIG_HEAD -else - GIT-HEAD-PHONY = -endif FORCE: .PHONY: all install clean config-clean strip install-gtk .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell -.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare +.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope FORCE prepare .PHONY: libtraceevent_plugins archheaders endif # force_fixdep diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index cbc555245959..11c71aa219f7 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -199,7 +199,7 @@ static int cs_etm_set_option(struct auxtrace_record *itr, struct evsel *evsel, u32 option) { int i, err = -EINVAL; - struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus; + struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* Set option of each CPU we have */ @@ -299,7 +299,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; struct evsel *evsel, *cs_etm_evsel = NULL; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); int err = 0; @@ -522,7 +522,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, { int i; int etmv3 = 0, etmv4 = 0, ete = 0; - struct perf_cpu_map *event_cpus = evlist->core.cpus; + struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); /* cpu map is not empty, we have specific CPUs to work with */ @@ -713,7 +713,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, u32 offset; u64 nr_cpu, type; struct perf_cpu_map *cpu_map; - struct perf_cpu_map *event_cpus = session->evlist->core.cpus; + struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus; struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 5860bbaea95a..af4d63af8072 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -144,7 +144,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, container_of(itr, struct arm_spe_recording, itr); struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu; struct evsel *evsel, *arm_spe_evsel = NULL; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; @@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 4a76d49d25d6..d68a0f48e41e 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -110,7 +110,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, container_of(itr, struct intel_bts_recording, itr); struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu; struct evsel *evsel, *intel_bts_evsel = NULL; - const struct perf_cpu_map *cpus = evlist->core.cpus; + const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); if (opts->auxtrace_sample_mode) { diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 8c31578d6f4a..38ec2666ec12 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -382,7 +382,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus); + per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -632,7 +632,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; bool have_timing_info, need_immediate = false; struct evsel *evsel, *intel_pt_evsel = NULL; - const struct perf_cpu_map *cpus = evlist->core.cpus; + const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); u64 tsc_bit; int err; diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c index de56601f69ee..5a27691469ed 100644 --- a/tools/perf/bench/evlist-open-close.c +++ b/tools/perf/bench/evlist-open-close.c @@ -151,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr) init_stats(&time_stats); - printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus)); + printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.user_requested_cpus)); printf(" Number of threads:\t%d\n", evlist->core.threads->nr); printf(" Number of events:\t%d (%d fds)\n", evlist->core.nr_entries, evlist__count_evsel_fds(evlist)); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index f2640179ada9..44e1f8a44087 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -34,6 +34,7 @@ #include <linux/numa.h> #include <linux/zalloc.h> +#include "../util/header.h" #include <numa.h> #include <numaif.h> @@ -54,7 +55,7 @@ struct thread_data { int curr_cpu; - cpu_set_t bind_cpumask; + cpu_set_t *bind_cpumask; int bind_node; u8 *process_data; int process_nr; @@ -266,71 +267,115 @@ static bool node_has_cpus(int node) return ret; } -static cpu_set_t bind_to_cpu(int target_cpu) +static cpu_set_t *bind_to_cpu(int target_cpu) { - cpu_set_t orig_mask, mask; - int ret; + int nrcpus = numa_num_possible_cpus(); + cpu_set_t *orig_mask, *mask; + size_t size; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); + + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; - CPU_ZERO(&mask); + CPU_ZERO_S(size, mask); if (target_cpu == -1) { int cpu; for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { - BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); - CPU_SET(target_cpu, &mask); + if (target_cpu < 0 || target_cpu >= g->p.nr_cpus) + goto err; + + CPU_SET_S(target_cpu, size, mask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); } -static cpu_set_t bind_to_node(int target_node) +static cpu_set_t *bind_to_node(int target_node) { - cpu_set_t orig_mask, mask; + int nrcpus = numa_num_possible_cpus(); + size_t size; + cpu_set_t *orig_mask, *mask; int cpu; - int ret; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); - CPU_ZERO(&mask); + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_node == NUMA_NO_NODE) { for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { struct bitmask *cpumask = numa_allocate_cpumask(); - BUG_ON(!cpumask); + if (!cpumask) + goto err; + if (!numa_node_to_cpus(target_node, cpumask)) { for (cpu = 0; cpu < (int)cpumask->size; cpu++) { if (numa_bitmask_isbitset(cpumask, cpu)) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } } numa_free_cpumask(cpumask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); } -static void bind_to_cpumask(cpu_set_t mask) +static void bind_to_cpumask(cpu_set_t *mask) { int ret; + size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus()); - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + ret = sched_setaffinity(0, size, mask); + if (ret) { + CPU_FREE(mask); + BUG_ON(ret); + } } static void mempol_restore(void) @@ -376,7 +421,7 @@ do { \ static u8 *alloc_data(ssize_t bytes0, int map_flags, int init_zero, int init_cpu0, int thp, int init_random) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask = NULL; ssize_t bytes; u8 *buf; int ret; @@ -434,6 +479,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Restore affinity: */ if (init_cpu0) { bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); mempol_restore(); } @@ -585,10 +631,16 @@ static int parse_setup_cpu_list(void) return -1; } + if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) { + printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n"); + return -1; + } + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus); int i; for (i = 0; i < mul; i++) { @@ -608,10 +660,15 @@ static int parse_setup_cpu_list(void) tprintf("%2d", bind_cpu); } - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(size, td->bind_cpumask); for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { - BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); - CPU_SET(cpu, &td->bind_cpumask); + if (cpu < 0 || cpu >= g->p.nr_cpus) { + CPU_FREE(td->bind_cpumask); + BUG_ON(-1); + } + CPU_SET_S(cpu, size, td->bind_cpumask); } t++; } @@ -752,8 +809,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused, return parse_node_list(arg); } -#define BIT(x) (1ul << x) - static inline uint32_t lfsr_32(uint32_t lfsr) { const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); @@ -1241,7 +1296,7 @@ static void *worker_thread(void *__tdata) * by migrating to CPU#0: */ if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask; int target_cpu; int this_cpu; @@ -1265,6 +1320,7 @@ static void *worker_thread(void *__tdata) printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); } if (details >= 3) { @@ -1398,21 +1454,31 @@ static void init_thread_data(void) for (t = 0; t < g->p.nr_tasks; t++) { struct thread_data *td = g->threads + t; + size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus); int cpu; /* Allow all nodes by default: */ td->bind_node = NUMA_NO_NODE; /* Allow all CPUs by default: */ - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(cpuset_size, td->bind_cpumask); for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &td->bind_cpumask); + CPU_SET_S(cpu, cpuset_size, td->bind_cpumask); } } static void deinit_thread_data(void) { ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + /* Free the bind_cpumask allocated for thread_data */ + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + CPU_FREE(td->bind_cpumask); + } free_data(g->threads, size); } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index ad9ce1bfffa1..7de07bb16d23 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -301,7 +301,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap) static int set_tracing_cpu(struct perf_ftrace *ftrace) { - struct perf_cpu_map *cpumap = ftrace->evlist->core.cpus; + struct perf_cpu_map *cpumap = ftrace->evlist->core.user_requested_cpus; if (!target__has_cpu(&ftrace->target)) return 0; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 0b4abed555d8..069825c48d40 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -987,10 +987,13 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru int m, tm, nr_mmaps = evlist->core.nr_mmaps; struct mmap *mmap = evlist->mmap; struct mmap *overwrite_mmap = evlist->overwrite_mmap; - struct perf_cpu_map *cpus = evlist->core.cpus; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; - thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, - thread_data->mask->maps.nbits); + if (cpu_map__is_dummy(cpus)) + thread_data->nr_mmaps = nr_mmaps; + else + thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, + thread_data->mask->maps.nbits); if (mmap) { thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *)); if (!thread_data->maps) @@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps); for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { - if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { + if (cpu_map__is_dummy(cpus) || + test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { if (thread_data->maps) { thread_data->maps[tm] = &mmap[m]; pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } if (thread_data->overwrite_maps) { thread_data->overwrite_maps[tm] = &overwrite_mmap[m]; pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } tm++; } @@ -1881,7 +1885,7 @@ static int record__synthesize(struct record *rec, bool tail) return err; } - err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.cpus, + err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus, process_synthesized_event, NULL); if (err < 0) { pr_err("Couldn't synthesize cpu map.\n"); @@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c { int c; + if (cpu_map__is_dummy(cpus)) + return; + for (c = 0; c < cpus->nr; c++) set_bit(cpus->map[c].cpu, mask->bits); } @@ -3675,11 +3682,16 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu static int record__init_thread_masks(struct record *rec) { int ret = 0; - struct perf_cpu_map *cpus = rec->evlist->core.cpus; + struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus; if (!record__threads_enabled(rec)) return record__init_thread_default_masks(rec, cpus); + if (cpu_map__is_dummy(cpus)) { + pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n"); + return -EINVAL; + } + switch (rec->opts.threads_spec) { case THREAD_SPEC__CPU: ret = record__init_thread_cpu_masks(rec, cpus); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 4ee40de698a4..a96f106dc93a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -804,7 +804,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (group) evlist__set_leader(evsel_list); - if (!cpu_map__is_dummy(evsel_list->core.cpus)) { + if (!cpu_map__is_dummy(evsel_list->core.user_requested_cpus)) { if (affinity__setup(&saved_affinity) < 0) return -1; affinity = &saved_affinity; @@ -1458,7 +1458,7 @@ static int perf_stat_init_aggr_mode(void) aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode); if (get_id) { - stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, /*data=*/NULL); if (!stat_config.aggr_map) { pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); @@ -1472,7 +1472,10 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - nr = perf_cpu_map__max(evsel_list->core.cpus).cpu; + if (evsel_list->core.user_requested_cpus) + nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu; + else + nr = 0; stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } @@ -1627,7 +1630,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) if (!get_id) return 0; - stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env); + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, env); if (!stat_config.aggr_map) { pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); return -1; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 9b08e44a31d9..fd8fd913c533 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1021,7 +1021,7 @@ static int perf_top__start_counters(struct perf_top *top) evlist__for_each_entry(evlist, counter) { try_again: - if (evsel__open(counter, top->evlist->core.cpus, + if (evsel__open(counter, top->evlist->core.user_requested_cpus, top->evlist->core.threads) < 0) { /* diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py index 461848c7f57d..bba68a6d4515 100755 --- a/tools/perf/python/tracepoint.py +++ b/tools/perf/python/tracepoint.py @@ -34,7 +34,7 @@ def main(): if not isinstance(event, perf.sample_event): continue - print "time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % ( + print("time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % ( event.sample_time, event.prev_comm, event.prev_pid, @@ -42,7 +42,7 @@ def main(): event.prev_state, event.next_comm, event.next_pid, - event.next_prio) + event.next_prio)) if __name__ == '__main__': main() diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..cc6df49a65a1 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -124,8 +131,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +198,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +207,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9e48652662d4..df1c5bbbaa0d 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, mp->idx = idx; if (per_cpu) { - mp->cpu = perf_cpu_map__cpu(evlist->core.cpus, idx); + mp->cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, idx); if (evlist->core.threads) mp->tid = perf_thread_map__pid(evlist->core.threads, 0); else diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 4f4d3aaff37c..7a4297d8fd2c 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -38,7 +38,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { - ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus); + ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus); bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus); } @@ -63,7 +63,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) fd = bpf_map__fd(skel->maps.cpu_filter); for (i = 0; i < ncpus; i++) { - cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu; + cpu = perf_cpu_map__cpu(ftrace->evlist->core.user_requested_cpus, i).cpu; bpf_map_update_elem(fd, &cpu, &val, BPF_ANY); } } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9bb79e049957..52ea004ba01e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -440,7 +440,7 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name) bool has_imm = false; // See explanation in evlist__close() - if (!cpu_map__is_dummy(evlist->core.cpus)) { + if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) { if (affinity__setup(&saved_affinity) < 0) return; affinity = &saved_affinity; @@ -500,7 +500,7 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name) struct affinity saved_affinity, *affinity = NULL; // See explanation in evlist__close() - if (!cpu_map__is_dummy(evlist->core.cpus)) { + if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) { if (affinity__setup(&saved_affinity) < 0) return; affinity = &saved_affinity; @@ -565,7 +565,7 @@ static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread) { int cpu; - int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); + int nr_cpus = perf_cpu_map__nr(evlist->core.user_requested_cpus); if (!evsel->core.fd) return -EINVAL; @@ -580,7 +580,7 @@ static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evse int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx) { - bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus); + bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus); if (per_cpu_mmaps) return evlist__enable_event_cpu(evlist, evsel, idx); @@ -1301,10 +1301,11 @@ void evlist__close(struct evlist *evlist) struct affinity affinity; /* - * With perf record core.cpus is usually NULL. + * With perf record core.user_requested_cpus is usually NULL. * Use the old method to handle this for now. */ - if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) { + if (!evlist->core.user_requested_cpus || + cpu_map__is_dummy(evlist->core.user_requested_cpus)) { evlist__for_each_entry_reverse(evlist, evsel) evsel__close(evsel); return; @@ -1330,7 +1331,6 @@ static int evlist__create_syswide_maps(struct evlist *evlist) { struct perf_cpu_map *cpus; struct perf_thread_map *threads; - int err = -ENOMEM; /* * Try reading /sys/devices/system/cpu/online to get @@ -1355,7 +1355,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist) out_put: perf_cpu_map__put(cpus); out: - return err; + return -ENOMEM; } int evlist__open(struct evlist *evlist) @@ -1367,7 +1367,7 @@ int evlist__open(struct evlist *evlist) * Default: one fd per CPU, all threads, aka systemwide * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL */ - if (evlist->core.threads == NULL && evlist->core.cpus == NULL) { + if (evlist->core.threads == NULL && evlist->core.user_requested_cpus == NULL) { err = evlist__create_syswide_maps(evlist); if (err < 0) goto out_err; diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c index 3c20b126d60d..aeb09c288716 100644 --- a/tools/perf/util/hashmap.c +++ b/tools/perf/util/hashmap.c @@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map) void hashmap__free(struct hashmap *map) { - if (!map) + if (IS_ERR_OR_NULL(map)) return; hashmap__clear(map); @@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key, return true; } - diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d546ff724dbe..a27132e5a5ef 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff, return do_write(ff, &data->dir.version, sizeof(data->dir.version)); } +/* + * Check whether a CPU is online + * + * Returns: + * 1 -> if CPU is online + * 0 -> if CPU is offline + * -1 -> error case + */ +int is_cpu_online(unsigned int cpu) +{ + char *str; + size_t strlen; + char buf[256]; + int status = -1; + struct stat statbuf; + + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d", cpu); + if (stat(buf, &statbuf) != 0) + return 0; + + /* + * Check if /sys/devices/system/cpu/cpux/online file + * exists. Some cases cpu0 won't have online file since + * it is not expected to be turned off generally. + * In kernels without CONFIG_HOTPLUG_CPU, this + * file won't exist + */ + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d/online", cpu); + if (stat(buf, &statbuf) != 0) + return 1; + + /* + * Read online file using sysfs__read_str. + * If read or open fails, return -1. + * If read succeeds, return value from file + * which gets stored in "str" + */ + snprintf(buf, sizeof(buf), + "devices/system/cpu/cpu%d/online", cpu); + + if (sysfs__read_str(buf, &str, &strlen) < 0) + return status; + + status = atoi(str); + + free(str); + return status; +} + #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, struct evlist *evlist __maybe_unused) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index c9e3265832d9..0eb4bc29a5a4 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size); int write_padded(struct feat_fd *fd, const void *bf, size_t count, size_t count_aligned); +int is_cpu_online(unsigned int cpu); /* * arch specific callback */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 24997925ae00..dd84fed698a3 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, bool use_uncore_alias; LIST_HEAD(config_terms); - if (verbose > 1) { + pmu = parse_state->fake_pmu ?: perf_pmu__find(name); + + if (verbose > 1 && !(pmu && pmu->selectable)) { fprintf(stderr, "Attempting to add event pmu '%s' with '", name); if (head_config) { @@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, fprintf(stderr, "' that may result in non-fatal errors\n"); } - pmu = parse_state->fake_pmu ?: perf_pmu__find(name); if (!pmu) { char *err_str; diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 007a64681416..5b09ecbb05dc 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call if (opts->group) evlist__set_leader(evlist); - if (perf_cpu_map__cpu(evlist->core.cpus, 0).cpu < 0) + if (perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0).cpu < 0) opts->no_inherit = true; use_comm_exec = perf_can_comm_exec(); @@ -244,7 +244,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) evsel = evlist__last(temp_evlist); - if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { + if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) { struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); if (cpus) @@ -252,7 +252,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) perf_cpu_map__put(cpus); } else { - cpu = perf_cpu_map__cpu(evlist->core.cpus, 0); + cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0); } while (1) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..45a30040ec8d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c index 748371ac22be..388846f17bc1 100644 --- a/tools/perf/util/sideband_evlist.c +++ b/tools/perf/util/sideband_evlist.c @@ -114,7 +114,8 @@ int evlist__start_sb_thread(struct evlist *evlist, struct target *target) } evlist__for_each_entry(evlist, counter) { - if (evsel__open(counter, evlist->core.cpus, evlist->core.threads) < 0) + if (evsel__open(counter, evlist->core.user_requested_cpus, + evlist->core.threads) < 0) goto out_delete_evlist; } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 9cbe351b141f..138e3ab9d638 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -929,7 +929,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config, int all_idx; struct perf_cpu cpu; - perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) { + perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) { struct evsel *counter; bool first = true; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ee6f03481215..817a2de264b4 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/err.h> #include <inttypes.h> #include <math.h> #include <string.h> @@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, if (!mask) { mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL); - if (!mask) + if (IS_ERR(mask)) return -ENOMEM; counter->per_pkg_mask = mask; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index b654de0841f8..27acdc5e5723 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2127,7 +2127,7 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p return err; } - err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL); + err = perf_event__synthesize_cpu_map(tool, evlist->core.user_requested_cpus, process, NULL); if (err < 0) { pr_err("Couldn't synthesize thread map.\n"); return err; diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index c1ebfc5d2e0c..b8b32431d2f7 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -95,15 +95,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "", + perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1 + ? "s" : "", target->cpu_list); else { if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", - perf_cpu_map__nr(top->evlist->core.cpus), - perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : ""); + perf_cpu_map__nr(top->evlist->core.user_requested_cpus), + perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1 + ? "s" : ""); } perf_top__reset_sample_counters(top); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile index d2fba1297d96..846f785e278d 100644 --- a/tools/power/x86/intel-speed-select/Makefile +++ b/tools/power/x86/intel-speed-select/Makefile @@ -47,7 +47,7 @@ $(OUTPUT)intel-speed-select: $(ISST_IN) clean: rm -f $(ALL_PROGRAMS) rm -rf $(OUTPUT)include/linux/isst_if.h - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index a2335e402145..0efb8f2b33ce 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -52,11 +52,17 @@ define allow-override endef ifneq ($(LLVM),) -$(call allow-override,CC,clang) -$(call allow-override,AR,llvm-ar) -$(call allow-override,LD,ld.lld) -$(call allow-override,CXX,clang++) -$(call allow-override,STRIP,llvm-strip) +ifneq ($(filter %/,$(LLVM)),) +LLVM_PREFIX := $(LLVM) +else ifneq ($(filter -%,$(LLVM)),) +LLVM_SUFFIX := $(LLVM) +endif + +$(call allow-override,CC,$(LLVM_PREFIX)clang$(LLVM_SUFFIX)) +$(call allow-override,AR,$(LLVM_PREFIX)llvm-ar$(LLVM_SUFFIX)) +$(call allow-override,LD,$(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX)) +$(call allow-override,CXX,$(LLVM_PREFIX)clang++$(LLVM_SUFFIX)) +$(call allow-override,STRIP,$(LLVM_PREFIX)llvm-strip$(LLVM_SUFFIX)) else # Allow setting various cross-compile vars or setting CROSS_COMPILE as a prefix. $(call allow-override,CC,$(CROSS_COMPILE)gcc) @@ -69,9 +75,9 @@ endif CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?) ifneq ($(LLVM),) -HOSTAR ?= llvm-ar -HOSTCC ?= clang -HOSTLD ?= ld.lld +HOSTAR ?= $(LLVM_PREFIX)llvm-ar$(LLVM_SUFFIX) +HOSTCC ?= $(LLVM_PREFIX)clang$(LLVM_SUFFIX) +HOSTLD ?= $(LLVM_PREFIX)ld.lld$(LLVM_SUFFIX) else HOSTAR ?= ar HOSTCC ?= gcc diff --git a/tools/scripts/utilities.mak b/tools/scripts/utilities.mak index c16ce833079c..172e47273b5d 100644 --- a/tools/scripts/utilities.mak +++ b/tools/scripts/utilities.mak @@ -175,5 +175,5 @@ _ge-abspath = $(if $(is-executable),$(1)) define get-executable-or-default $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2))) endef -_ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2))) +_ge_attempt = $(or $(get-executable),$(call _gea_err,$(2))) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) diff --git a/tools/spi/Makefile b/tools/spi/Makefile index 0aa6dbd31fb8..7fccd245a535 100644 --- a/tools/spi/Makefile +++ b/tools/spi/Makefile @@ -53,9 +53,9 @@ $(OUTPUT)spidev_fdx: $(SPIDEV_FDX_IN) clean: rm -f $(ALL_PROGRAMS) rm -rf $(OUTPUT)include/ - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete - find $(if $(OUTPUT),$(OUTPUT),.) -name '\.*.o.d' -delete - find $(if $(OUTPUT),$(OUTPUT),.) -name '\.*.o.cmd' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete + find $(or $(OUTPUT),.) -name '\.*.o.d' -delete + find $(or $(OUTPUT),.) -name '\.*.o.cmd' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 65dbdda3a054..1da76ccde448 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t) return 0; } -static void security_init(struct nfit_test *t) +static void nfit_security_init(struct nfit_test *t) { int i; @@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t) if (nfit_test_dimm_init(t)) return -ENOMEM; smart_init(t); - security_init(t); + nfit_security_init(t); return ars_state_init(&t->pdev.dev, &t->ars_state); } diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh index 429f7ee735cf..fd23c80eba31 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh @@ -159,6 +159,17 @@ flooding_remotes_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + for i in $(eval echo {1..$num_remotes}); do lsb=$((i + 1)) @@ -195,6 +206,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh index fedcb7b35af9..af5ea50ed5c0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh @@ -172,6 +172,17 @@ flooding_filters_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + tc qdisc add dev $rp2 clsact for i in $(eval echo {1..$num_remotes}); do @@ -194,6 +205,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 11779405dc80..25f4d54067c0 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -64,6 +64,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <setjmp.h> #include "kselftest.h" @@ -183,7 +184,10 @@ struct __test_metadata *_metadata, \ struct __fixture_variant_metadata *variant) \ { \ - test_name(_metadata); \ + _metadata->setup_completed = true; \ + if (setjmp(_metadata->env) == 0) \ + test_name(_metadata); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata _##test_name##_object = \ { .name = #test_name, \ @@ -287,7 +291,9 @@ #define FIXTURE_TEARDOWN(fixture_name) \ void fixture_name##_teardown( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) /** * FIXTURE_VARIANT() - Optionally called once per fixture @@ -302,9 +308,9 @@ * ... * }; * - * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F() - * as *variant*. Variants allow the same tests to be run with different - * arguments. + * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and + * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with + * different arguments. */ #define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name @@ -356,10 +362,7 @@ * Defines a test that depends on a fixture (e.g., is part of a test case). * Very similar to TEST() except that *self* is the setup instance of fixture's * datatype exposed for use by the implementation. - * - * Warning: use of ASSERT_* here will skip TEARDOWN. */ -/* TODO(wad) register fixtures on dedicated test lists. */ #define TEST_F(fixture_name, test_name) \ __TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT) @@ -381,12 +384,17 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ - return; \ - fixture_name##_##test_name(_metadata, &self, variant->data); \ - fixture_name##_teardown(_metadata, &self); \ + if (setjmp(_metadata->env) == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (!_metadata->passed) \ + return; \ + _metadata->setup_completed = true; \ + fixture_name##_##test_name(_metadata, &self, variant->data); \ + } \ + if (_metadata->setup_completed) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata \ _##fixture_name##_##test_name##_object = { \ @@ -683,7 +691,7 @@ */ #define OPTIONAL_HANDLER(_assert) \ for (; _metadata->trigger; _metadata->trigger = \ - __bail(_assert, _metadata->no_print, _metadata->step)) + __bail(_assert, _metadata)) #define __INC_STEP(_metadata) \ /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ @@ -830,6 +838,9 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + bool aborted; /* stopped test due to failed ASSERT */ + bool setup_completed; /* did setup finish? */ + jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t) __LIST_APPEND(t->fixture->tests, t); } -static inline int __bail(int for_realz, bool no_print, __u8 step) +static inline int __bail(int for_realz, struct __test_metadata *t) { + /* if this is ASSERT, return immediately. */ if (for_realz) { - if (no_print) - _exit(step); - abort(); + t->aborted = true; + longjmp(t->env, 1); } + /* otherwise, end the for loop and continue. */ return 0; } +static inline void __test_check_assert(struct __test_metadata *t) +{ + if (t->aborted) { + if (t->no_print) + _exit(t->step); + abort(); + } +} + struct __test_metadata *__active_test; static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d1e8f5237469..0b0e4402bba6 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -3,6 +3,7 @@ /aarch64/debug-exceptions /aarch64/get-reg-list /aarch64/psci_cpu_on_test +/aarch64/vcpu_width_config /aarch64/vgic_init /aarch64/vgic_irq /s390x/memop @@ -33,6 +34,7 @@ /x86_64/state_test /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test +/x86_64/tsc_scaling_sync /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/userspace_io_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 21c2dbd21a81..681b173aa87c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -106,6 +106,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test +TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq TEST_GEN_PROGS_aarch64 += demand_paging_test diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index b08d30bf71c5..3b940a101bc0 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -362,11 +362,12 @@ static void test_init_timer_irq(struct kvm_vm *vm) pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq); } +static int gic_fd; + static struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; - int ret; int nr_vcpus = test_args.nr_vcpus; vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); @@ -383,8 +384,8 @@ static struct kvm_vm *test_vm_create(void) ucall_init(vm, NULL); test_init_timer_irq(vm); - ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); - if (ret < 0) { + gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + if (gic_fd < 0) { print_skip("Failed to create vgic-v3"); exit(KSFT_SKIP); } @@ -395,6 +396,12 @@ static struct kvm_vm *test_vm_create(void) return vm; } +static void test_vm_cleanup(struct kvm_vm *vm) +{ + close(gic_fd); + kvm_vm_free(vm); +} + static void test_print_help(char *name) { pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n", @@ -478,7 +485,7 @@ int main(int argc, char *argv[]) vm = test_vm_create(); test_run(vm); - kvm_vm_free(vm); + test_vm_cleanup(vm); return 0; } diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index f12147c43464..0b571f3fe64c 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -503,8 +503,13 @@ static void run_test(struct vcpu_config *c) ++missing_regs; if (new_regs || missing_regs) { + n = 0; + for_each_reg_filtered(i) + ++n; + printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n); - printf("%s: Number registers: %5lld\n", config_name(c), reg_list->n); + printf("%s: Number registers: %5lld (includes %lld filtered registers)\n", + config_name(c), reg_list->n, reg_list->n - n); } if (new_regs) { @@ -683,9 +688,10 @@ static __u64 base_regs[] = { KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), - KVM_REG_ARM_FW_REG(0), - KVM_REG_ARM_FW_REG(1), - KVM_REG_ARM_FW_REG(2), + KVM_REG_ARM_FW_REG(0), /* KVM_REG_ARM_PSCI_VERSION */ + KVM_REG_ARM_FW_REG(1), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */ + KVM_REG_ARM_FW_REG(2), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */ + KVM_REG_ARM_FW_REG(3), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */ ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ ARM64_SYS_REG(3, 3, 14, 0, 2), diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c new file mode 100644 index 000000000000..6e9402679229 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vcpu_width_config - Test KVM_ARM_VCPU_INIT() with KVM_ARM_VCPU_EL1_32BIT. + * + * Copyright (c) 2022 Google LLC. + * + * This is a test that ensures that non-mixed-width vCPUs (all 64bit vCPUs + * or all 32bit vcPUs) can be configured and mixed-width vCPUs cannot be + * configured. + */ + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + + +/* + * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then + * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2. + */ +static int add_init_2vcpus(struct kvm_vcpu_init *init1, + struct kvm_vcpu_init *init2) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + + vm_vcpu_add(vm, 0); + ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1); + if (ret) + goto free_exit; + + vm_vcpu_add(vm, 1); + ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2); + +free_exit: + kvm_vm_free(vm); + return ret; +} + +/* + * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1, + * and run KVM_ARM_VCPU_INIT for another vCPU with @init2. + */ +static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1, + struct kvm_vcpu_init *init2) +{ + struct kvm_vm *vm; + int ret; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + + vm_vcpu_add(vm, 0); + vm_vcpu_add(vm, 1); + + ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1); + if (ret) + goto free_exit; + + ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2); + +free_exit: + kvm_vm_free(vm); + return ret; +} + +/* + * Tests that two 64bit vCPUs can be configured, two 32bit vCPUs can be + * configured, and two mixed-width vCPUs cannot be configured. + * Each of those three cases, configure vCPUs in two different orders. + * The one is running KVM_CREATE_VCPU for 2 vCPUs, and then running + * KVM_ARM_VCPU_INIT for them. + * The other is running KVM_CREATE_VCPU and KVM_ARM_VCPU_INIT for a vCPU, + * and then run those commands for another vCPU. + */ +int main(void) +{ + struct kvm_vcpu_init init1, init2; + struct kvm_vm *vm; + int ret; + + if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) { + print_skip("KVM_CAP_ARM_EL1_32BIT is not supported"); + exit(KSFT_SKIP); + } + + /* Get the preferred target type and copy that to init2 for later use */ + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1); + kvm_vm_free(vm); + init2 = init1; + + /* Test with 64bit vCPUs */ + ret = add_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 64bit EL1 vCPUs failed unexpectedly"); + ret = add_2vcpus_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 64bit EL1 vCPUs failed unexpectedly"); + + /* Test with 32bit vCPUs */ + init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); + ret = add_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 32bit EL1 vCPUs failed unexpectedly"); + ret = add_2vcpus_init_2vcpus(&init1, &init1); + TEST_ASSERT(ret == 0, + "Configuring 32bit EL1 vCPUs failed unexpectedly"); + + /* Test with mixed-width vCPUs */ + init1.features[0] = 0; + init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT); + ret = add_init_2vcpus(&init1, &init2); + TEST_ASSERT(ret != 0, + "Configuring mixed-width vCPUs worked unexpectedly"); + ret = add_2vcpus_init_2vcpus(&init1, &init2); + TEST_ASSERT(ret != 0, + "Configuring mixed-width vCPUs worked unexpectedly"); + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index c9d9e513ca04..7b47ae4f952e 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -18,11 +18,40 @@ #include "test_util.h" #include "perf_test_util.h" #include "guest_modes.h" + #ifdef __aarch64__ #include "aarch64/vgic.h" #define GICD_BASE_GPA 0x8000000ULL #define GICR_BASE_GPA 0x80A0000ULL + +static int gic_fd; + +static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) +{ + /* + * The test can still run even if hardware does not support GICv3, as it + * is only an optimization to reduce guest exits. + */ + gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); +} + +static void arch_cleanup_vm(struct kvm_vm *vm) +{ + if (gic_fd > 0) + close(gic_fd); +} + +#else /* __aarch64__ */ + +static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus) +{ +} + +static void arch_cleanup_vm(struct kvm_vm *vm) +{ +} + #endif /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ @@ -206,9 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } -#ifdef __aarch64__ - vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); -#endif + arch_setup_vm(vm, nr_vcpus); /* Start the iterations */ iteration = 0; @@ -302,6 +329,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) } free_bitmaps(bitmaps, p->slots); + arch_cleanup_vm(vm); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index dc284c6bdbc3..eca5c622efd2 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -101,7 +101,9 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, #define PGTBL_PTE_WRITE_SHIFT 2 #define PGTBL_PTE_READ_MASK 0x0000000000000002ULL #define PGTBL_PTE_READ_SHIFT 1 -#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \ +#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_ACCESSED_MASK | \ + PGTBL_PTE_DIRTY_MASK | \ + PGTBL_PTE_EXECUTE_MASK | \ PGTBL_PTE_WRITE_MASK | \ PGTBL_PTE_READ_MASK) #define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index d377f2603d98..3961487a4870 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -268,7 +268,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6); } -static void guest_hang(void) +static void __aligned(16) guest_hang(void) { while (1) ; diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index a40add31a2e3..2a2d240cdc1b 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -1,7 +1,13 @@ # This mimics the top-level Makefile. We do it explicitly here so that this # Makefile can operate with or without the kbuild infrastructure. ifneq ($(LLVM),) -CC := clang +ifneq ($(filter %/,$(LLVM)),) +LLVM_PREFIX := $(LLVM) +else ifneq ($(filter -%,$(LLVM)),) +LLVM_SUFFIX := $(LLVM) +endif + +CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) else CC := $(CROSS_COMPILE)gcc endif diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c index b019e0b8221c..84fda3b49073 100644 --- a/tools/testing/selftests/mqueue/mq_perf_tests.c +++ b/tools/testing/selftests/mqueue/mq_perf_tests.c @@ -180,6 +180,9 @@ void shutdown(int exit_val, char *err_cause, int line_no) if (in_shutdown++) return; + /* Free the cpu_set allocated using CPU_ALLOC in main function */ + CPU_FREE(cpu_set); + for (i = 0; i < num_cpus_to_pin; i++) if (cpu_threads[i]) { pthread_kill(cpu_threads[i], SIGUSR1); @@ -551,6 +554,12 @@ int main(int argc, char *argv[]) perror("sysconf(_SC_NPROCESSORS_ONLN)"); exit(1); } + + if (getuid() != 0) + ksft_exit_skip("Not running as root, but almost all tests " + "require root in order to modify\nsystem settings. " + "Exiting.\n"); + cpus_online = min(MAX_CPUS, sysconf(_SC_NPROCESSORS_ONLN)); cpu_set = CPU_ALLOC(cpus_online); if (cpu_set == NULL) { @@ -589,7 +598,7 @@ int main(int argc, char *argv[]) cpu_set)) { fprintf(stderr, "Any given CPU may " "only be given once.\n"); - exit(1); + goto err_code; } else CPU_SET_S(cpus_to_pin[cpu], cpu_set_size, cpu_set); @@ -607,7 +616,7 @@ int main(int argc, char *argv[]) queue_path = malloc(strlen(option) + 2); if (!queue_path) { perror("malloc()"); - exit(1); + goto err_code; } queue_path[0] = '/'; queue_path[1] = 0; @@ -622,17 +631,12 @@ int main(int argc, char *argv[]) fprintf(stderr, "Must pass at least one CPU to continuous " "mode.\n"); poptPrintUsage(popt_context, stderr, 0); - exit(1); + goto err_code; } else if (!continuous_mode) { num_cpus_to_pin = 1; cpus_to_pin[0] = cpus_online - 1; } - if (getuid() != 0) - ksft_exit_skip("Not running as root, but almost all tests " - "require root in order to modify\nsystem settings. " - "Exiting.\n"); - max_msgs = fopen(MAX_MSGS, "r+"); max_msgsize = fopen(MAX_MSGSIZE, "r+"); if (!max_msgs) @@ -740,4 +744,9 @@ int main(int argc, char *argv[]) sleep(1); } shutdown(0, "", 0); + +err_code: + CPU_FREE(cpu_set); + exit(1); + } diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index dcaefa224ca0..edafaca1aeb3 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ -TEST_GEN_PROGS := regression_enomem +TEST_GEN_PROGS = regression_enomem -include ../lib.mk +LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h -$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h +include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 17999e082aa7..070c1c876df1 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,7 +95,6 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 18a3bde8bc96..28604c9f805c 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -46,6 +46,8 @@ #include <sys/time.h> #include <sys/resource.h> +#include "../kselftest.h" + static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags) { return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags); @@ -368,7 +370,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } @@ -417,7 +419,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } } diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index c4aea794725a..e691a3cf1491 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "../kselftest.h" static const char **name; @@ -306,10 +307,8 @@ static void test_clock_gettime(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime(-1, "invalid"); @@ -370,10 +369,8 @@ static void test_clock_gettime64(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime64(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime64(-1, "invalid"); diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config index a85025d7206e..a9b4fe795048 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/i686.config +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -1,3 +1,4 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config index 00a1ef4869d5..45dd53a0d760 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -1,3 +1,4 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 53df7d3893d3..0388c4d60af0 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -92,6 +92,10 @@ warn_32bit_failure: echo "If you are using a Fedora-like distribution, try:"; \ echo ""; \ echo " yum install glibc-devel.*i686"; \ + echo ""; \ + echo "If you are using a SUSE-like distribution, try:"; \ + echo ""; \ + echo " zypper install gcc-32bit glibc-devel-static-32bit"; \ exit 0; endif diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c index 3615ef4a48bb..2189f0322d8b 100644 --- a/tools/testing/selftests/x86/amx.c +++ b/tools/testing/selftests/x86/amx.c @@ -368,9 +368,16 @@ static void req_xtiledata_perm(void) static void validate_req_xcomp_perm(enum expected_result exp) { - unsigned long bitmask; + unsigned long bitmask, expected_bitmask; long rc; + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask); + if (rc) { + fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc); + } else if (!(bitmask & XFEATURE_MASK_XTILECFG)) { + fatal_error("ARCH_GET_XCOMP_PERM returns XFEATURE_XTILECFG off."); + } + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); if (exp == FAIL_EXPECTED) { if (rc) { @@ -383,10 +390,15 @@ static void validate_req_xcomp_perm(enum expected_result exp) fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected failure.\n"); } + expected_bitmask = bitmask | XFEATURE_MASK_XTILEDATA; + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask); if (rc) { fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc); - } else if (bitmask & XFEATURE_MASK_XTILE) { + } else if (bitmask != expected_bitmask) { + fatal_error("ARCH_REQ_XCOMP_PERM set a wrong bitmask: %lx, expected: %lx.\n", + bitmask, expected_bitmask); + } else { printf("\tARCH_REQ_XCOMP_PERM is successful.\n"); } } diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 5a1eda617992..11fb417abb42 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -46,7 +46,7 @@ DATADIR := /usr/share DOCDIR := $(DATADIR)/doc MANDIR := $(DATADIR)/man LICDIR := $(DATADIR)/licenses -SRCTREE := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)) +SRCTREE := $(or $(BUILD_SRC),$(CURDIR)) # If running from the tarball, man pages are stored in the Documentation # dir. If running from the kernel source, man pages are stored in diff --git a/tools/usb/Makefile b/tools/usb/Makefile index 1b128e551b2e..c6235667dd46 100644 --- a/tools/usb/Makefile +++ b/tools/usb/Makefile @@ -38,7 +38,7 @@ $(OUTPUT)ffs-test: $(FFS_TEST_IN) clean: rm -f $(ALL_PROGRAMS) - find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.o.cmd' -delete + find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.o.cmd' -delete install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 0d7bbe49359d..1b25cc7c64bb 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -5,7 +5,8 @@ virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h -LDFLAGS += -lpthread +CFLAGS += -pthread +LDFLAGS += -pthread vpath %.c ../../drivers/virtio ../../drivers/vhost mod: ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V} diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 8f41cd6bd5c0..834a90bd3270 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -26,8 +26,8 @@ enum dma_data_direction { #define dma_map_single(d, p, s, dir) (virt_to_phys(p)) #define dma_mapping_error(...) (0) -#define dma_unmap_single(...) do { } while (0) -#define dma_unmap_page(...) do { } while (0) +#define dma_unmap_single(d, a, s, r) do { (void)(d); (void)(a); (void)(s); (void)(r); } while (0) +#define dma_unmap_page(d, a, s, r) do { (void)(d); (void)(a); (void)(s); (void)(r); } while (0) #define dma_max_mapping_size(...) SIZE_MAX diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c index 7679335fce5b..7d98e76c2291 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/vm/page_owner_sort.c @@ -441,7 +441,6 @@ static void usage(void) "-n\t\tSort by task command name.\n" "-a\t\tSort by memory allocate time.\n" "-r\t\tSort by memory release time.\n" - "-c\t\tCull by comparing stacktrace instead of total block.\n" "-f\t\tFilter out the information of blocks whose memory has been released.\n" "--pid <PID>\tSelect by pid. This selects the information of blocks whose process ID number equals to <PID>.\n" "--tgid <TGID>\tSelect by tgid. This selects the information of blocks whose Thread Group ID number equals to <TGID>.\n" @@ -466,14 +465,11 @@ int main(int argc, char **argv) { 0, 0, 0, 0}, }; - while ((opt = getopt_long(argc, argv, "acfmnprstP", longopts, NULL)) != -1) + while ((opt = getopt_long(argc, argv, "afmnprstP", longopts, NULL)) != -1) switch (opt) { case 'a': cmp = compare_ts; break; - case 'c': - cull = cull | CULL_STACKTRACE; - break; case 'f': filter = filter | FILTER_UNRELEASE; break; diff --git a/usr/Makefile b/usr/Makefile index cc0d2824e100..59d9e8b07a01 100644 --- a/usr/Makefile +++ b/usr/Makefile @@ -3,7 +3,7 @@ # kbuild file for usr/ - including initramfs image # -compress-y := shipped +compress-y := copy compress-$(CONFIG_INITRAMFS_COMPRESSION_GZIP) := gzip compress-$(CONFIG_INITRAMFS_COMPRESSION_BZIP2) := bzip2 compress-$(CONFIG_INITRAMFS_COMPRESSION_LZMA) := lzma @@ -37,7 +37,7 @@ endif # .cpio.*, use it directly as an initramfs, and avoid double compression. ifeq ($(words $(subst .cpio.,$(space),$(ramfs-input))),2) cpio-data := $(ramfs-input) -compress-y := shipped +compress-y := copy endif endif diff --git a/usr/include/Makefile b/usr/include/Makefile index 7b283d43f00d..fa9819e022b7 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -10,7 +10,10 @@ UAPI_CFLAGS := -std=c90 -Wall -Werror=implicit-function-declaration # In theory, we do not care -m32 or -m64 for header compile tests. # It is here just because CONFIG_CC_CAN_LINK is tested with -m32 or -m64. -UAPI_CFLAGS += $(filter -m32 -m64, $(KBUILD_CFLAGS)) +UAPI_CFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) + +# USERCFLAGS might contain sysroot location for CC. +UAPI_CFLAGS += $(USERCFLAGS) override c_flags = $(UAPI_CFLAGS) -Wp,-MMD,$(depfile) -I$(objtree)/usr/include @@ -84,7 +87,7 @@ endif # asm-generic/*.h is used by asm/*.h, and should not be included directly no-header-test += asm-generic/% -extra-y := $(patsubst $(obj)/%.h,%.hdrtest, $(shell find $(obj) -name '*.h' 2>/dev/null)) +always-y := $(patsubst $(obj)/%.h,%.hdrtest, $(shell find $(obj) -name '*.h' 2>/dev/null)) # Include the header twice to detect missing include guard. quiet_cmd_hdrtest = HDRTEST $< diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 69c318fdff61..dfb7dabdbc63 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -117,6 +117,8 @@ EXPORT_SYMBOL_GPL(kvm_debugfs_dir); static const struct file_operations stat_fops_per_vm; +static struct file_operations kvm_chardev_ops; + static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #ifdef CONFIG_KVM_COMPAT @@ -251,7 +253,8 @@ static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req, { int cpu; - kvm_make_request(req, vcpu); + if (likely(!(req & KVM_REQUEST_NO_ACTION))) + __kvm_make_request(req, vcpu); if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) return; @@ -431,8 +434,8 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { - kvm_dirty_ring_free(&vcpu->dirty_ring); kvm_arch_vcpu_destroy(vcpu); + kvm_dirty_ring_free(&vcpu->dirty_ring); /* * No need for rcu_read_lock as VCPU_RUN is the only place that changes @@ -929,7 +932,7 @@ static void kvm_destroy_vm_debugfs(struct kvm *kvm) int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; - if (!kvm->debugfs_dentry) + if (IS_ERR(kvm->debugfs_dentry)) return; debugfs_remove_recursive(kvm->debugfs_dentry); @@ -952,6 +955,12 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; + /* + * Force subsequent debugfs file creations to fail if the VM directory + * is not created. + */ + kvm->debugfs_dentry = ERR_PTR(-ENOENT); + if (!debugfs_initialized()) return 0; @@ -1131,6 +1140,16 @@ static struct kvm *kvm_create_vm(unsigned long type) preempt_notifier_inc(); kvm_init_pm_notifier(kvm); + /* + * When the fd passed to this ioctl() is opened it pins the module, + * but try_module_get() also prevents getting a reference if the module + * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait"). + */ + if (!try_module_get(kvm_chardev_ops.owner)) { + r = -ENODEV; + goto out_err; + } + return kvm; out_err: @@ -1220,6 +1239,7 @@ static void kvm_destroy_vm(struct kvm *kvm) preempt_notifier_dec(); hardware_disable_all(); mmdrop(mm); + module_put(kvm_chardev_ops.owner); } void kvm_get_kvm(struct kvm *kvm) @@ -3663,7 +3683,7 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp) return 0; } -static struct file_operations kvm_vcpu_fops = { +static const struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, @@ -4714,7 +4734,7 @@ static long kvm_vm_compat_ioctl(struct file *filp, } #endif -static struct file_operations kvm_vm_fops = { +static const struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, .llseek = noop_llseek, @@ -5465,7 +5485,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) } add_uevent_var(env, "PID=%d", kvm->userspace_pid); - if (kvm->debugfs_dentry) { + if (!IS_ERR(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT); if (p) { @@ -5721,8 +5741,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, goto out_free_5; kvm_chardev_ops.owner = module; - kvm_vm_fops.owner = module; - kvm_vcpu_fops.owner = module; r = misc_register(&kvm_dev); if (r) { diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index ce878f4be4da..dd84676615f1 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -27,7 +27,7 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, { DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); struct gfn_to_pfn_cache *gpc; - bool wake_vcpus = false; + bool evict_vcpus = false; spin_lock(&kvm->gpc_lock); list_for_each_entry(gpc, &kvm->gpc_list, list) { @@ -40,41 +40,32 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, /* * If a guest vCPU could be using the physical address, - * it needs to be woken. + * it needs to be forced out of guest mode. */ - if (gpc->guest_uses_pa) { - if (!wake_vcpus) { - wake_vcpus = true; + if (gpc->usage & KVM_GUEST_USES_PFN) { + if (!evict_vcpus) { + evict_vcpus = true; bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); } __set_bit(gpc->vcpu->vcpu_idx, vcpu_bitmap); } - - /* - * We cannot call mark_page_dirty() from here because - * this physical CPU might not have an active vCPU - * with which to do the KVM dirty tracking. - * - * Neither is there any point in telling the kernel MM - * that the underlying page is dirty. A vCPU in guest - * mode might still be writing to it up to the point - * where we wake them a few lines further down anyway. - * - * So all the dirty marking happens on the unmap. - */ } write_unlock_irq(&gpc->lock); } spin_unlock(&kvm->gpc_lock); - if (wake_vcpus) { - unsigned int req = KVM_REQ_GPC_INVALIDATE; + if (evict_vcpus) { + /* + * KVM needs to ensure the vCPU is fully out of guest context + * before allowing the invalidation to continue. + */ + unsigned int req = KVM_REQ_OUTSIDE_GUEST_MODE; bool called; /* * If the OOM reaper is active, then all vCPUs should have * been stopped already, so perform the request without - * KVM_REQUEST_WAIT and be sad if any needed to be woken. + * KVM_REQUEST_WAIT and be sad if any needed to be IPI'd. */ if (!may_block) req &= ~KVM_REQUEST_WAIT; @@ -104,8 +95,7 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, } EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_check); -static void __release_gpc(struct kvm *kvm, kvm_pfn_t pfn, void *khva, - gpa_t gpa, bool dirty) +static void __release_gpc(struct kvm *kvm, kvm_pfn_t pfn, void *khva, gpa_t gpa) { /* Unmap the old page if it was mapped before, and release it */ if (!is_error_noslot_pfn(pfn)) { @@ -118,9 +108,7 @@ static void __release_gpc(struct kvm *kvm, kvm_pfn_t pfn, void *khva, #endif } - kvm_release_pfn(pfn, dirty); - if (dirty) - mark_page_dirty(kvm, gpa); + kvm_release_pfn(pfn, false); } } @@ -152,7 +140,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, unsigned long uhva) } int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - gpa_t gpa, unsigned long len, bool dirty) + gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); unsigned long page_offset = gpa & ~PAGE_MASK; @@ -160,7 +148,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, unsigned long old_uhva; gpa_t old_gpa; void *old_khva; - bool old_valid, old_dirty; + bool old_valid; int ret = 0; /* @@ -177,20 +165,19 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, old_khva = gpc->khva - offset_in_page(gpc->khva); old_uhva = gpc->uhva; old_valid = gpc->valid; - old_dirty = gpc->dirty; /* If the userspace HVA is invalid, refresh that first */ if (gpc->gpa != gpa || gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva)) { gfn_t gfn = gpa_to_gfn(gpa); - gpc->dirty = false; gpc->gpa = gpa; gpc->generation = slots->generation; gpc->memslot = __gfn_to_memslot(slots, gfn); gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn); if (kvm_is_error_hva(gpc->uhva)) { + gpc->pfn = KVM_PFN_ERR_FAULT; ret = -EFAULT; goto out; } @@ -219,7 +206,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, goto map_done; } - if (gpc->kernel_map) { + if (gpc->usage & KVM_HOST_USES_PFN) { if (new_pfn == old_pfn) { new_khva = old_khva; old_pfn = KVM_PFN_ERR_FAULT; @@ -255,14 +242,9 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, } out: - if (ret) - gpc->dirty = false; - else - gpc->dirty = dirty; - write_unlock_irq(&gpc->lock); - __release_gpc(kvm, old_pfn, old_khva, old_gpa, old_dirty); + __release_gpc(kvm, old_pfn, old_khva, old_gpa); return ret; } @@ -272,7 +254,6 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) { void *old_khva; kvm_pfn_t old_pfn; - bool old_dirty; gpa_t old_gpa; write_lock_irq(&gpc->lock); @@ -280,7 +261,6 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) gpc->valid = false; old_khva = gpc->khva - offset_in_page(gpc->khva); - old_dirty = gpc->dirty; old_gpa = gpc->gpa; old_pfn = gpc->pfn; @@ -293,16 +273,17 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) write_unlock_irq(&gpc->lock); - __release_gpc(kvm, old_pfn, old_khva, old_gpa, old_dirty); + __release_gpc(kvm, old_pfn, old_khva, old_gpa); } EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap); int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, bool guest_uses_pa, - bool kernel_map, gpa_t gpa, unsigned long len, - bool dirty) + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len) { + WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage); + if (!gpc->active) { rwlock_init(&gpc->lock); @@ -310,8 +291,7 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, gpc->pfn = KVM_PFN_ERR_FAULT; gpc->uhva = KVM_HVA_ERR_BAD; gpc->vcpu = vcpu; - gpc->kernel_map = kernel_map; - gpc->guest_uses_pa = guest_uses_pa; + gpc->usage = usage; gpc->valid = false; gpc->active = true; @@ -319,7 +299,7 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, list_add(&gpc->list, &kvm->gpc_list); spin_unlock(&kvm->gpc_lock); } - return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len, dirty); + return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len); } EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_init); |