diff options
419 files changed, 3772 insertions, 2500 deletions
@@ -1637,6 +1637,10 @@ S: Panoramastrasse 18 S: D-69126 Heidelberg S: Germany +N: Simon Horman +M: horms@verge.net.au +D: Renesas ARM/ARM64 SoC maintainer + N: Christopher Horn E: chorn@warwick.net D: Miscellaneous sysctl hacks diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 0fa8c0e615c2..5361ebec3361 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -615,8 +615,8 @@ on an IO device and is an example of this type. Protections ----------- -A cgroup is protected to be allocated upto the configured amount of -the resource if the usages of all its ancestors are under their +A cgroup is protected upto the configured amount of the resource +as long as the usages of all its ancestors are under their protected levels. Protections can be hard guarantees or best effort soft boundaries. Protections can also be over-committed in which case only upto the amount available to the parent is protected among @@ -1096,7 +1096,10 @@ PAGE_SIZE multiple when read back. is within its effective min boundary, the cgroup's memory won't be reclaimed under any conditions. If there is no unprotected reclaimable memory available, OOM killer - is invoked. + is invoked. Above the effective min boundary (or + effective low boundary if it is higher), pages are reclaimed + proportionally to the overage, reducing reclaim pressure for + smaller overages. Effective min boundary is limited by memory.min values of all ancestor cgroups. If there is memory.min overcommitment @@ -1118,7 +1121,10 @@ PAGE_SIZE multiple when read back. Best-effort memory protection. If the memory usage of a cgroup is within its effective low boundary, the cgroup's memory won't be reclaimed unless memory can be reclaimed - from unprotected cgroups. + from unprotected cgroups. Above the effective low boundary (or + effective min boundary if it is higher), pages are reclaimed + proportionally to the overage, reducing reclaim pressure for + smaller overages. Effective low boundary is limited by memory.low values of all ancestor cgroups. If there is memory.low overcommitment @@ -2482,8 +2488,10 @@ system performance due to overreclaim, to the point where the feature becomes self-defeating. The memory.low boundary on the other hand is a top-down allocated -reserve. A cgroup enjoys reclaim protection when it's within its low, -which makes delegation of subtrees possible. +reserve. A cgroup enjoys reclaim protection when it's within its +effective low, which makes delegation of subtrees possible. It also +enjoys having reclaim pressure proportional to its overage when +above its effective low. The original high boundary, the hard limit, is defined as a strict limit that can not budge, even if the OOM killer has to be called. diff --git a/Documentation/arm64/memory.rst b/Documentation/arm64/memory.rst index b040909e45f8..02e02175e6f5 100644 --- a/Documentation/arm64/memory.rst +++ b/Documentation/arm64/memory.rst @@ -154,11 +154,18 @@ return virtual addresses to userspace from a 48-bit range. Software can "opt-in" to receiving VAs from a 52-bit space by specifying an mmap hint parameter that is larger than 48-bit. + For example: - maybe_high_address = mmap(~0UL, size, prot, flags,...); + +.. code-block:: c + + maybe_high_address = mmap(~0UL, size, prot, flags,...); It is also possible to build a debug kernel that returns addresses from a 52-bit space by enabling the following kernel config options: + +.. code-block:: sh + CONFIG_EXPERT=y && CONFIG_ARM64_FORCE_52BIT=y Note that this option is only intended for debugging applications diff --git a/Documentation/core-api/memory-allocation.rst b/Documentation/core-api/memory-allocation.rst index 7744aa3bf2e0..939e3dfc86e9 100644 --- a/Documentation/core-api/memory-allocation.rst +++ b/Documentation/core-api/memory-allocation.rst @@ -98,6 +98,10 @@ limited. The actual limit depends on the hardware and the kernel configuration, but it is a good practice to use `kmalloc` for objects smaller than page size. +The address of a chunk allocated with `kmalloc` is aligned to at least +ARCH_KMALLOC_MINALIGN bytes. For sizes which are a power of two, the +alignment is also guaranteed to be at least the respective size. + For large allocations you can use :c:func:`vmalloc` and :c:func:`vzalloc`, or directly request pages from the page allocator. The memory allocated by `vmalloc` and related functions is diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst index 25604904fa6e..ecdfdc9d4b03 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -89,6 +89,22 @@ To build, save output files in a separate directory with KBUILD_OUTPUT :: $ export KBUILD_OUTPUT=/tmp/kselftest; make TARGETS="size timers" kselftest +Additionally you can use the "SKIP_TARGETS" variable on the make command +line to specify one or more targets to exclude from the TARGETS list. + +To run all tests but a single subsystem:: + + $ make -C tools/testing/selftests SKIP_TARGETS=ptrace run_tests + +You can specify multiple tests to skip:: + + $ make SKIP_TARGETS="size timers" kselftest + +You can also specify a restricted list of tests to run together with a +dedicated skiplist:: + + $ make TARGETS="bpf breakpoints size timers" SKIP_TARGETS=bpf kselftest + See the top-level tools/testing/selftests/Makefile for the list of all possible targets. diff --git a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml index 3248595dc93c..f04870d84542 100644 --- a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml +++ b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml @@ -85,4 +85,5 @@ examples: <&pd IMX_SC_R_DSP_RAM>; mbox-names = "txdb0", "txdb1", "rxdb0", "rxdb1"; mboxes = <&lsio_mu13 2 0>, <&lsio_mu13 2 1>, <&lsio_mu13 3 0>, <&lsio_mu13 3 1>; + memory-region = <&dsp_reserved>; }; diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml index 676ec42e1438..567a33a83dce 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml @@ -43,13 +43,9 @@ properties: dvdd-supply: description: DVdd voltage supply - items: - - const: dvdd avdd-supply: description: AVdd voltage supply - items: - - const: avdd adi,rejection-60-Hz-enable: description: | @@ -99,6 +95,9 @@ required: examples: - | spi0 { + #address-cells = <1>; + #size-cells = <0>; + adc@0 { compatible = "adi,ad7192"; reg = <0>; diff --git a/Documentation/devicetree/bindings/media/rc.yaml b/Documentation/devicetree/bindings/media/rc.yaml index 3d5c154fd230..9054555e6608 100644 --- a/Documentation/devicetree/bindings/media/rc.yaml +++ b/Documentation/devicetree/bindings/media/rc.yaml @@ -73,7 +73,6 @@ properties: - rc-genius-tvgo-a11mce - rc-gotview7135 - rc-hauppauge - - rc-hauppauge - rc-hisi-poplar - rc-hisi-tv-demo - rc-imon-mce diff --git a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml index 8a56a8526cef..a97482179cf5 100644 --- a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml @@ -37,7 +37,7 @@ properties: - description: exclusive PHY reset line - description: shared reset line between the PCIe PHY and PCIe controller - resets-names: + reset-names: items: - const: phy - const: pcie diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 6ba9d5365ff3..b89c88168d6a 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -954,11 +954,6 @@ When kbuild executes, the following steps are followed (roughly): From commandline LDFLAGS_MODULE shall be used (see kbuild.txt). - KBUILD_ARFLAGS Options for $(AR) when creating archives - - $(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic - mode) if this option is supported by $(AR). - KBUILD_LDS The linker script with full path. Assigned by the top-level Makefile. diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index d2ae799237fd..774a998dcf37 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -498,10 +498,11 @@ build. will be written containing all exported symbols that were not defined in the kernel. ---- 6.3 Symbols From Another External Module +6.3 Symbols From Another External Module +---------------------------------------- Sometimes, an external module uses exported symbols from - another external module. kbuild needs to have full knowledge of + another external module. Kbuild needs to have full knowledge of all symbols to avoid spitting out warnings about undefined symbols. Three solutions exist for this situation. @@ -521,7 +522,7 @@ build. The top-level kbuild file would then look like:: #./Kbuild (or ./Makefile): - obj-y := foo/ bar/ + obj-m := foo/ bar/ And executing:: diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index ab92e98c89c8..503393854e2e 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -16,16 +16,21 @@ the kernel may be unreproducible, and how to avoid them. Timestamps ---------- -The kernel embeds a timestamp in two places: +The kernel embeds timestamps in three places: * The version string exposed by ``uname()`` and included in ``/proc/version`` * File timestamps in the embedded initramfs -By default the timestamp is the current time. This must be overridden -using the `KBUILD_BUILD_TIMESTAMP`_ variable. If you are building -from a git commit, you could use its commit date. +* If enabled via ``CONFIG_IKHEADERS``, file timestamps of kernel + headers embedded in the kernel or respective module, + exposed via ``/sys/kernel/kheaders.tar.xz`` + +By default the timestamp is the current time and in the case of +``kheaders`` the various files' modification times. This must +be overridden using the `KBUILD_BUILD_TIMESTAMP`_ variable. +If you are building from a git commit, you could use its commit date. The kernel does *not* use the ``__DATE__`` and ``__TIME__`` macros, and enables warnings if they are used. If you incorporate external diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst index f51f92571e39..c1f7f75e5fd9 100644 --- a/Documentation/networking/device_drivers/index.rst +++ b/Documentation/networking/device_drivers/index.rst @@ -23,6 +23,7 @@ Contents: intel/ice google/gve mellanox/mlx5 + netronome/nfp pensando/ionic .. only:: subproject and html diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index ce7e7a044e08..dc60b13fcd09 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -272,7 +272,7 @@ supported flags are: * MSG_DONTWAIT, i.e. non-blocking operation. recvmsg(2) -^^^^^^^^^ +^^^^^^^^^^ In most cases recvmsg(2) is needed if you want to extract more information than recvfrom(2) can provide. For example package priority and timestamp. The diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index f4a2198187f9..ada573b7d703 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -56,7 +56,7 @@ instead of ``double-indenting`` the ``case`` labels. E.g.: case 'K': case 'k': mem <<= 10; - /* fall through */ + fallthrough; default: break; } diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 053b24a6dd38..179f2a5625a0 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -122,14 +122,27 @@ memory adjacent to the stack (when built without `CONFIG_VMAP_STACK=y`) Implicit switch case fall-through --------------------------------- -The C language allows switch cases to "fall through" when -a "break" statement is missing at the end of a case. This, -however, introduces ambiguity in the code, as it's not always -clear if the missing break is intentional or a bug. As there -have been a long list of flaws `due to missing "break" statements +The C language allows switch cases to "fall-through" when a "break" statement +is missing at the end of a case. This, however, introduces ambiguity in the +code, as it's not always clear if the missing break is intentional or a bug. + +As there have been a long list of flaws `due to missing "break" statements <https://cwe.mitre.org/data/definitions/484.html>`_, we no longer allow -"implicit fall-through". In order to identify an intentional fall-through -case, we have adopted the marking used by static analyzers: a comment -saying `/* Fall through */`. Once the C++17 `__attribute__((fallthrough))` -is more widely handled by C compilers, static analyzers, and IDEs, we can -switch to using that instead. +"implicit fall-through". + +In order to identify intentional fall-through cases, we have adopted a +pseudo-keyword macro 'fallthrough' which expands to gcc's extension +__attribute__((__fallthrough__)). `Statement Attributes +<https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html>`_ + +When the C17/C18 [[fallthrough]] syntax is more commonly supported by +C compilers, static analyzers, and IDEs, we can switch to using that syntax +for the macro pseudo-keyword. + +All switch/case blocks must end in one of: + + break; + fallthrough; + continue; + goto <label>; + return [expression]; diff --git a/MAINTAINERS b/MAINTAINERS index 3dec8d53c34b..e9b0a4100a29 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2165,12 +2165,10 @@ F: arch/arm64/boot/dts/realtek/ F: Documentation/devicetree/bindings/arm/realtek.yaml ARM/RENESAS ARM64 ARCHITECTURE -M: Simon Horman <horms@verge.net.au> M: Geert Uytterhoeven <geert+renesas@glider.be> M: Magnus Damm <magnus.damm@gmail.com> L: linux-renesas-soc@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next S: Supported F: arch/arm64/boot/dts/renesas/ @@ -2282,12 +2280,10 @@ S: Maintained F: drivers/media/platform/s5p-mfc/ ARM/SHMOBILE ARM ARCHITECTURE -M: Simon Horman <horms@verge.net.au> M: Geert Uytterhoeven <geert+renesas@glider.be> M: Magnus Damm <magnus.damm@gmail.com> L: linux-renesas-soc@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next S: Supported F: arch/arm/boot/dts/emev2* @@ -6112,7 +6108,10 @@ M: Gao Xiang <gaoxiang25@huawei.com> M: Chao Yu <yuchao0@huawei.com> L: linux-erofs@lists.ozlabs.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git +F: Documentation/filesystems/erofs.txt F: fs/erofs/ +F: include/trace/events/erofs.h ERRSEQ ERROR TRACKING INFRASTRUCTURE M: Jeff Layton <jlayton@kernel.org> @@ -9075,6 +9074,7 @@ F: security/keys/ KGDB / KDB /debug_core M: Jason Wessel <jason.wessel@windriver.com> M: Daniel Thompson <daniel.thompson@linaro.org> +R: Douglas Anderson <dianders@chromium.org> W: http://kgdb.wiki.kernel.org/ L: kgdb-bugreport@lists.sourceforge.net T: git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git @@ -9183,6 +9183,7 @@ M: Pavel Machek <pavel@ucw.cz> R: Dan Murphy <dmurphy@ti.com> L: linux-leds@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux-leds.git S: Maintained F: Documentation/devicetree/bindings/leds/ F: drivers/leds/ @@ -2,8 +2,8 @@ VERSION = 5 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc1 -NAME = Bobtail Squid +EXTRAVERSION = -rc2 +NAME = Nesting Opossum # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -206,24 +206,8 @@ ifndef KBUILD_CHECKSRC KBUILD_CHECKSRC = 0 endif -# Use make M=dir to specify directory of external module to build -# Old syntax make ... SUBDIRS=$PWD is still supported -# Setting the environment variable KBUILD_EXTMOD take precedence -ifdef SUBDIRS - $(warning ================= WARNING ================) - $(warning 'SUBDIRS' will be removed after Linux 5.3) - $(warning ) - $(warning If you are building an individual subdirectory) - $(warning in the kernel tree, you can do like this:) - $(warning $$ make path/to/dir/you/want/to/build/) - $(warning (Do not forget the trailing slash)) - $(warning ) - $(warning If you are building an external module,) - $(warning Please use 'M=' or 'KBUILD_EXTMOD' instead) - $(warning ==========================================) - KBUILD_EXTMOD ?= $(SUBDIRS) -endif - +# Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the +# directory of external module to build. Setting M= takes precedence. ifeq ("$(origin M)", "command line") KBUILD_EXTMOD := $(M) endif @@ -498,7 +482,6 @@ export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL -export KBUILD_ARFLAGS # Files to ignore in find ... statements @@ -914,9 +897,6 @@ ifdef CONFIG_RETPOLINE KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif -# use the deterministic mode of AR if available -KBUILD_ARFLAGS := $(call ar-option,D) - include scripts/Makefile.kasan include scripts/Makefile.extrawarn include scripts/Makefile.ubsan @@ -1237,9 +1217,8 @@ PHONY += kselftest kselftest: $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests -PHONY += kselftest-clean -kselftest-clean: - $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean +kselftest-%: FORCE + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests $* PHONY += kselftest-merge kselftest-merge: diff --git a/arch/arm/boot/dts/am335x-icev2.dts b/arch/arm/boot/dts/am335x-icev2.dts index 18f70b35da4c..204bccfcc110 100644 --- a/arch/arm/boot/dts/am335x-icev2.dts +++ b/arch/arm/boot/dts/am335x-icev2.dts @@ -432,7 +432,7 @@ pinctrl-0 = <&mmc0_pins_default>; }; -&gpio0 { +&gpio0_target { /* Do not idle the GPIO used for holding the VTT regulator */ ti,no-reset-on-init; ti,no-idle-on-init; diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 9915c891e05f..7a9eb2b0d45b 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -127,7 +127,7 @@ ranges = <0x0 0x5000 0x1000>; }; - target-module@7000 { /* 0x44e07000, ap 14 20.0 */ + gpio0_target: target-module@7000 { /* 0x44e07000, ap 14 20.0 */ compatible = "ti,sysc-omap2", "ti,sysc"; ti,hwmods = "gpio1"; reg = <0x7000 0x4>, @@ -2038,7 +2038,9 @@ reg = <0xe000 0x4>, <0xe054 0x4>; reg-names = "rev", "sysc"; - ti,sysc-midle ; + ti,sysc-midle = <SYSC_IDLE_FORCE>, + <SYSC_IDLE_NO>, + <SYSC_IDLE_SMART>; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 848e2a8884e2..14bbc438055f 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -337,6 +337,8 @@ ti,hwmods = "dss_dispc"; clocks = <&disp_clk>; clock-names = "fck"; + + max-memory-bandwidth = <230000000>; }; rfbi: rfbi@4832a800 { diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index ea0e7c19eb4e..5cac2dd58241 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -2732,7 +2732,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 129 1>, <&edma_xbar 128 1>; dma-names = "tx", "rx"; - clocks = <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 22>, + clocks = <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 0>, <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 24>, <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 28>; clock-names = "fck", "ahclkx", "ahclkr"; @@ -2768,8 +2768,8 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 131 1>, <&edma_xbar 130 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 22>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 24>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 0>, + <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 24>, <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 28>; clock-names = "fck", "ahclkx", "ahclkr"; status = "disabled"; @@ -2786,9 +2786,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x68000 0x2000>, @@ -2804,7 +2803,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 133 1>, <&edma_xbar 132 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2821,9 +2820,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x6c000 0x2000>, @@ -2839,7 +2837,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 135 1>, <&edma_xbar 134 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2856,9 +2854,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x70000 0x2000>, @@ -2874,7 +2871,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 137 1>, <&edma_xbar 136 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2891,9 +2888,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x74000 0x2000>, @@ -2909,7 +2905,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 139 1>, <&edma_xbar 138 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2926,9 +2922,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x78000 0x2000>, @@ -2944,7 +2939,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 141 1>, <&edma_xbar 140 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2961,9 +2956,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x7c000 0x2000>, @@ -2979,7 +2973,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 143 1>, <&edma_xbar 142 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index d01fc8744fd7..b6ef1a7ac8a4 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -124,6 +124,7 @@ spi-max-frequency = <100000>; spi-cpol; spi-cpha; + spi-cs-high; backlight= <&backlight>; label = "lcd"; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index a53657b83288..bda454d12150 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -8,6 +8,7 @@ #include <dt-bindings/mfd/dbx500-prcmu.h> #include <dt-bindings/arm/ux500_pm_domains.h> #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/thermal/thermal.h> / { #address-cells = <1>; @@ -59,8 +60,12 @@ * cooling. */ cpu_thermal: cpu-thermal { - polling-delay-passive = <0>; - polling-delay = <1000>; + polling-delay-passive = <250>; + /* + * This sensor fires interrupts to update the thermal + * zone, so no polling is needed. + */ + polling-delay = <0>; thermal-sensors = <&thermal>; @@ -79,7 +84,7 @@ cooling-maps { trip = <&cpu_alert>; - cooling-device = <&CPU0 0 2>; + cooling-device = <&CPU0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; contribution = <100>; }; }; diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index b34970ce6b31..01e3c0f4be92 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -228,7 +228,7 @@ CONFIG_RTC_DRV_OMAP=m CONFIG_DMADEVICES=y CONFIG_TI_EDMA=y CONFIG_COMMON_CLK_PWM=m -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_DA8XX_REMOTEPROC=m CONFIG_MEMORY=y CONFIG_TI_AEMIF=m diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 13ba53286901..e4c8def9a0a5 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -415,7 +415,7 @@ CONFIG_SPI_SH_MSIOF=m CONFIG_SPI_SH_HSPI=y CONFIG_SPI_SIRF=y CONFIG_SPI_STM32=m -CONFIG_SPI_STM32_QSPI=m +CONFIG_SPI_STM32_QSPI=y CONFIG_SPI_SUN4I=y CONFIG_SPI_SUN6I=y CONFIG_SPI_TEGRA114=y @@ -933,7 +933,7 @@ CONFIG_BCM2835_MBOX=y CONFIG_ROCKCHIP_IOMMU=y CONFIG_TEGRA_IOMMU_GART=y CONFIG_TEGRA_IOMMU_SMMU=y -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_ST_REMOTEPROC=m CONFIG_RPMSG_VIRTIO=m CONFIG_ASPEED_LPC_CTRL=m diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 64eb896907bf..d3f50971e451 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -364,6 +364,7 @@ CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m CONFIG_DRM_TILCDC=m CONFIG_DRM_PANEL_SIMPLE=m +CONFIG_DRM_TI_TFP410=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MODE_HELPERS=y @@ -423,6 +424,7 @@ CONFIG_USB_SERIAL_GENERIC=y CONFIG_USB_SERIAL_SIMPLE=m CONFIG_USB_SERIAL_FTDI_SIO=m CONFIG_USB_SERIAL_PL2303=m +CONFIG_USB_SERIAL_OPTION=m CONFIG_USB_TEST=m CONFIG_NOP_USB_XCEIV=m CONFIG_AM335X_PHY_USB=m @@ -460,6 +462,7 @@ CONFIG_MMC_SDHCI_OMAP=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=m CONFIG_LEDS_CPCAP=m +CONFIG_LEDS_LM3532=m CONFIG_LEDS_GPIO=m CONFIG_LEDS_PCA963X=m CONFIG_LEDS_PWM=m @@ -481,7 +484,7 @@ CONFIG_RTC_DRV_OMAP=m CONFIG_RTC_DRV_CPCAP=m CONFIG_DMADEVICES=y CONFIG_OMAP_IOMMU=y -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_OMAP_REMOTEPROC=m CONFIG_WKUP_M3_RPROC=m CONFIG_SOC_TI=y diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index b24df84a1d7a..043b0b18bf7e 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -98,6 +98,7 @@ config CRYPTO_AES_ARM_CE tristate "Accelerated AES using ARMv8 Crypto Extensions" depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER + select CRYPTO_LIB_AES select CRYPTO_SIMD help Use an implementation of AES in CBC, CTR and XTS modes that uses diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S index b978cdf133af..4d1707388d94 100644 --- a/arch/arm/crypto/aes-ce-core.S +++ b/arch/arm/crypto/aes-ce-core.S @@ -9,6 +9,7 @@ #include <asm/assembler.h> .text + .arch armv8-a .fpu crypto-neon-fp-armv8 .align 3 diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h deleted file mode 100644 index ec154e719b11..000000000000 --- a/arch/arm/include/asm/xen/xen-ops.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_XEN_OPS_H -#define _ASM_XEN_OPS_H - -void xen_efi_runtime_setup(void); - -#endif /* _ASM_XEN_OPS_H */ diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c index dd939e1325c6..29fd13684a68 100644 --- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c @@ -763,7 +763,8 @@ static struct omap_hwmod_class_sysconfig am33xx_timer_sysc = { .rev_offs = 0x0000, .sysc_offs = 0x0010, .syss_offs = 0x0014, - .sysc_flags = (SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET), + .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET | + SYSC_HAS_RESET_STATUS, .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | SIDLE_SMART_WKUP), .sysc_fields = &omap_hwmod_sysc_type2, diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c index 2bcb6345b873..54524775f278 100644 --- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c @@ -231,8 +231,9 @@ static struct omap_hwmod am33xx_control_hwmod = { static struct omap_hwmod_class_sysconfig lcdc_sysc = { .rev_offs = 0x0, .sysc_offs = 0x54, - .sysc_flags = (SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE), - .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), + .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE, + .idlemodes = SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | + MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART, .sysc_fields = &omap_hwmod_sysc_type2, }; diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 1fde1bf53fb6..7ac9af56762d 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -74,83 +74,6 @@ int omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused) return 0; } -/* - * This API is to be called during init to set the various voltage - * domains to the voltage as per the opp table. Typically we boot up - * at the nominal voltage. So this function finds out the rate of - * the clock associated with the voltage domain, finds out the correct - * opp entry and sets the voltage domain to the voltage specified - * in the opp entry - */ -static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name, - const char *oh_name) -{ - struct voltagedomain *voltdm; - struct clk *clk; - struct dev_pm_opp *opp; - unsigned long freq, bootup_volt; - struct device *dev; - - if (!vdd_name || !clk_name || !oh_name) { - pr_err("%s: invalid parameters\n", __func__); - goto exit; - } - - if (!strncmp(oh_name, "mpu", 3)) - /* - * All current OMAPs share voltage rail and clock - * source, so CPU0 is used to represent the MPU-SS. - */ - dev = get_cpu_device(0); - else - dev = omap_device_get_by_hwmod_name(oh_name); - - if (IS_ERR(dev)) { - pr_err("%s: Unable to get dev pointer for hwmod %s\n", - __func__, oh_name); - goto exit; - } - - voltdm = voltdm_lookup(vdd_name); - if (!voltdm) { - pr_err("%s: unable to get vdd pointer for vdd_%s\n", - __func__, vdd_name); - goto exit; - } - - clk = clk_get(NULL, clk_name); - if (IS_ERR(clk)) { - pr_err("%s: unable to get clk %s\n", __func__, clk_name); - goto exit; - } - - freq = clk_get_rate(clk); - clk_put(clk); - - opp = dev_pm_opp_find_freq_ceil(dev, &freq); - if (IS_ERR(opp)) { - pr_err("%s: unable to find boot up OPP for vdd_%s\n", - __func__, vdd_name); - goto exit; - } - - bootup_volt = dev_pm_opp_get_voltage(opp); - dev_pm_opp_put(opp); - - if (!bootup_volt) { - pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n", - __func__, vdd_name); - goto exit; - } - - voltdm_scale(voltdm, bootup_volt); - return 0; - -exit: - pr_err("%s: unable to set vdd_%s\n", __func__, vdd_name); - return -EINVAL; -} - #ifdef CONFIG_SUSPEND static int omap_pm_enter(suspend_state_t suspend_state) { @@ -208,25 +131,6 @@ void omap_common_suspend_init(void *pm_suspend) } #endif /* CONFIG_SUSPEND */ -static void __init omap3_init_voltages(void) -{ - if (!soc_is_omap34xx()) - return; - - omap2_set_init_voltage("mpu_iva", "dpll1_ck", "mpu"); - omap2_set_init_voltage("core", "l3_ick", "l3_main"); -} - -static void __init omap4_init_voltages(void) -{ - if (!soc_is_omap44xx()) - return; - - omap2_set_init_voltage("mpu", "dpll_mpu_ck", "mpu"); - omap2_set_init_voltage("core", "l3_div_ck", "l3_main_1"); - omap2_set_init_voltage("iva", "dpll_iva_m5x2_ck", "iva"); -} - int __maybe_unused omap_pm_nop_init(void) { return 0; @@ -246,10 +150,6 @@ int __init omap2_common_pm_late_init(void) omap4_twl_init(); omap_voltage_late_init(); - /* Initialize the voltages */ - omap3_init_voltages(); - omap4_init_voltages(); - /* Smartreflex device init */ omap_devinit_smartreflex(); diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile index 7ed28982c4c3..c32d04713ba0 100644 --- a/arch/arm/xen/Makefile +++ b/arch/arm/xen/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o -obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c deleted file mode 100644 index d687a73044bf..000000000000 --- a/arch/arm/xen/efi.c +++ /dev/null @@ -1,28 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2015, Linaro Limited, Shannon Zhao - */ - -#include <linux/efi.h> -#include <xen/xen-ops.h> -#include <asm/xen/xen-ops.h> - -/* Set XEN EFI runtime services function pointers. Other fields of struct efi, - * e.g. efi.systab, will be set like normal EFI. - */ -void __init xen_efi_runtime_setup(void) -{ - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; -} -EXPORT_SYMBOL_GPL(xen_efi_runtime_setup); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 1e57692552d9..dd6804a64f1a 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -15,7 +15,6 @@ #include <xen/xen-ops.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> -#include <asm/xen/xen-ops.h> #include <asm/system_misc.h> #include <asm/efi.h> #include <linux/interrupt.h> @@ -437,7 +436,7 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); -EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw); EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist); EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 2b2c208408bb..38fa917c8585 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -28,7 +28,10 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order) for_each_memblock(memory, reg) { if (reg->base < (phys_addr_t)0xffffffff) { - flags |= __GFP_DMA; + if (IS_ENABLED(CONFIG_ZONE_DMA32)) + flags |= __GFP_DMA32; + else + flags |= __GFP_DMA; break; } } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 41a9b4257b72..950a56b71ff0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -110,7 +110,6 @@ config ARM64 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY - select GENERIC_COMPAT_VDSO if (!CPU_BIG_ENDIAN && COMPAT) select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND select HAVE_PCI @@ -1159,7 +1158,7 @@ menuconfig COMPAT if COMPAT config KUSER_HELPERS - bool "Enable kuser helpers page for 32 bit applications" + bool "Enable kuser helpers page for 32-bit applications" default y help Warning: disabling this option may break 32-bit user programs. @@ -1185,6 +1184,18 @@ config KUSER_HELPERS Say N here only if you are absolutely certain that you do not need these helpers; otherwise, the safe option is to say Y. +config COMPAT_VDSO + bool "Enable vDSO for 32-bit applications" + depends on !CPU_BIG_ENDIAN && "$(CROSS_COMPILE_COMPAT)" != "" + select GENERIC_COMPAT_VDSO + default y + help + Place in the process address space of 32-bit applications an + ELF shared object providing fast implementations of gettimeofday + and clock_gettime. + + You must have a 32-bit build of glibc 2.22 or later for programs + to seamlessly take advantage of this. menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 84a3d502c5a5..2c0238ce0551 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -53,22 +53,6 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable) endif endif -ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y) - CROSS_COMPILE_COMPAT ?= $(CONFIG_CROSS_COMPILE_COMPAT_VDSO:"%"=%) - - ifeq ($(CONFIG_CC_IS_CLANG), y) - $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built) - else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),) - $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built) - else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),) - $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT) - else - export CROSS_COMPILE_COMPAT - export CONFIG_COMPAT_VDSO := y - compat_vdso := -DCONFIG_COMPAT_VDSO=1 - endif -endif - KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst) \ $(compat_vdso) $(cc_has_k_constraint) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 8e05c39eab08..c9a867ac32d4 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -723,7 +723,7 @@ CONFIG_TEGRA_IOMMU_SMMU=y CONFIG_ARM_SMMU=y CONFIG_ARM_SMMU_V3=y CONFIG_QCOM_IOMMU=y -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_QCOM_Q6V5_MSS=m CONFIG_QCOM_Q6V5_PAS=m CONFIG_QCOM_SYSMON=m diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index c6bd87d2915b..574808b9df4c 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -321,7 +321,8 @@ static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) } #define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ -static inline u##sz __lse__cmpxchg_case_##name##sz(volatile void *ptr, \ +static __always_inline u##sz \ +__lse__cmpxchg_case_##name##sz(volatile void *ptr, \ u##sz old, \ u##sz new) \ { \ @@ -362,7 +363,8 @@ __CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __CMPXCHG_CASE #define __CMPXCHG_DBL(name, mb, cl...) \ -static inline long __lse__cmpxchg_double##name(unsigned long old1, \ +static __always_inline long \ +__lse__cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ unsigned long new2, \ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 86825aa20852..97f21cc66657 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -47,30 +47,6 @@ #define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) #define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) -/** - * hyp_alternate_select - Generates patchable code sequences that are - * used to switch between two implementations of a function, depending - * on the availability of a feature. - * - * @fname: a symbol name that will be defined as a function returning a - * function pointer whose type will match @orig and @alt - * @orig: A pointer to the default function, as returned by @fname when - * @cond doesn't hold - * @alt: A pointer to the alternate function, as returned by @fname - * when @cond holds - * @cond: a CPU feature (as described in asm/cpufeature.h) - */ -#define hyp_alternate_select(fname, orig, alt, cond) \ -typeof(orig) * __hyp_text fname(void) \ -{ \ - typeof(alt) *val = orig; \ - asm volatile(ALTERNATIVE("nop \n", \ - "mov %0, %1 \n", \ - cond) \ - : "+r" (val) : "r" (alt)); \ - return val; \ -} - int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/vdso/compat_barrier.h b/arch/arm64/include/asm/vdso/compat_barrier.h index fb60a88b5ed4..3fd8fd6d8fc2 100644 --- a/arch/arm64/include/asm/vdso/compat_barrier.h +++ b/arch/arm64/include/asm/vdso/compat_barrier.h @@ -20,7 +20,7 @@ #define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory") -#if __LINUX_ARM_ARCH__ >= 8 +#if __LINUX_ARM_ARCH__ >= 8 && defined(CONFIG_AS_DMB_ISHLD) #define aarch32_smp_mb() dmb(ish) #define aarch32_smp_rmb() dmb(ishld) #define aarch32_smp_wmb() dmb(ishst) diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h deleted file mode 100644 index 1f38bf330a6e..000000000000 --- a/arch/arm64/include/asm/vdso_datapage.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 ARM Limited - */ -#ifndef __ASM_VDSO_DATAPAGE_H -#define __ASM_VDSO_DATAPAGE_H - -#ifndef __ASSEMBLY__ - -struct vdso_data { - __u64 cs_cycle_last; /* Timebase at clocksource init */ - __u64 raw_time_sec; /* Raw time */ - __u64 raw_time_nsec; - __u64 xtime_clock_sec; /* Kernel time */ - __u64 xtime_clock_nsec; - __u64 xtime_coarse_sec; /* Coarse time */ - __u64 xtime_coarse_nsec; - __u64 wtm_clock_sec; /* Wall to monotonic time */ - __u64 wtm_clock_nsec; - __u32 tb_seq_count; /* Timebase sequence counter */ - /* cs_* members must be adjacent and in this order (ldp accesses) */ - __u32 cs_mono_mult; /* NTP-adjusted clocksource multiplier */ - __u32 cs_shift; /* Clocksource shift (mono = raw) */ - __u32 cs_raw_mult; /* Raw clocksource multiplier */ - __u32 tz_minuteswest; /* Whacky timezone stuff */ - __u32 tz_dsttime; - __u32 use_syscall; - __u32 hrtimer_res; -}; - -#endif /* !__ASSEMBLY__ */ - -#endif /* __ASM_VDSO_DATAPAGE_H */ diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h deleted file mode 100644 index e6e784051932..000000000000 --- a/arch/arm64/include/asm/xen/xen-ops.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_XEN_OPS_H -#define _ASM_XEN_OPS_H - -void xen_efi_runtime_setup(void); - -#endif /* _ASM_XEN_OPS_H */ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 2ec09debc2bb..ca158be21f83 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -174,6 +174,9 @@ static void __init register_insn_emulation(struct insn_emulation_ops *ops) struct insn_emulation *insn; insn = kzalloc(sizeof(*insn), GFP_KERNEL); + if (!insn) + return; + insn->ops = ops; insn->min = INSN_UNDEF; @@ -233,6 +236,8 @@ static void __init register_insn_emulation_sysctl(void) insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl), GFP_KERNEL); + if (!insns_sysctl) + return; raw_spin_lock_irqsave(&insn_emulation_lock, flags); list_for_each_entry(insn, &insn_emulation, node) { diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 1e43ba5c79b7..f593f4cffc0d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -128,8 +128,8 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, int cpu, slot = -1; /* - * enable_smccc_arch_workaround_1() passes NULL for the hyp_vecs - * start/end if we're a guest. Skip the hyp-vectors work. + * detect_harden_bp_fw() passes NULL for the hyp_vecs start/end if + * we're a guest. Skip the hyp-vectors work. */ if (!hyp_vecs_start) { __this_cpu_write(bp_hardening_data.fn, fn); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 9323bcc40a58..cabebf1a7976 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -136,6 +136,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPI_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 84a822748c84..e304fe04b098 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -775,6 +775,7 @@ el0_sync_compat: b.ge el0_dbg b el0_inv el0_svc_compat: + gic_prio_kentry_setup tmp=x1 mov x0, sp bl el0_svc_compat_handler b ret_to_user diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 171773257974..06e56b470315 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -121,10 +121,16 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) /* * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. + * fetch before we patch in the branch. Although the + * architecture doesn't require an IPI in this case, + * Neoverse-N1 erratum #1542419 does require one + * if the TLB maintenance in module_enable_ro() is + * skipped due to rodata_enabled. It doesn't seem worth + * it to make it conditional given that this is + * certainly not a fast-path. */ - __flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + flush_icache_range((unsigned long)&dst[0], + (unsigned long)&dst[1]); } addr = (unsigned long)dst; #else /* CONFIG_ARM64_MODULE_PLTS */ diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index a47462def04b..1fb2819fc048 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -332,22 +332,27 @@ void arch_release_task_struct(struct task_struct *tsk) fpsimd_release_task(tsk); } -/* - * src and dst may temporarily have aliased sve_state after task_struct - * is copied. We cannot fix this properly here, because src may have - * live SVE state and dst's thread_info may not exist yet, so tweaking - * either src's or dst's TIF_SVE is not safe. - * - * The unaliasing is done in copy_thread() instead. This works because - * dst is not schedulable or traceable until both of these functions - * have been called. - */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { if (current->mm) fpsimd_preserve_current_state(); *dst = *src; + /* We rely on the above assignment to initialize dst's thread_flags: */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK)); + + /* + * Detach src's sve_state (if any) from dst so that it does not + * get erroneously used or freed prematurely. dst's sve_state + * will be allocated on demand later on if dst uses SVE. + * For consistency, also clear TIF_SVE here: this could be done + * later in copy_process(), but to avoid tripping up future + * maintainers it is best not to leave TIF_SVE and sve_state in + * an inconsistent state, even temporarily. + */ + dst->thread.sve_state = NULL; + clear_tsk_thread_flag(dst, TIF_SVE); + return 0; } @@ -361,13 +366,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); /* - * Unalias p->thread.sve_state (if any) from the parent task - * and disable discard SVE state for p: - */ - clear_tsk_thread_flag(p, TIF_SVE); - p->thread.sve_state = NULL; - - /* * In case p was allocated the same task_struct pointer as some * other recently-exited task, make sure p is disassociated from * any cpu that may have run that now-exited task recently. diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ /dev/null diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 1fba0776ed40..76b327f88fbb 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -8,15 +8,21 @@ ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32 include $(srctree)/lib/vdso/Makefile -COMPATCC := $(CROSS_COMPILE_COMPAT)gcc +# Same as cc-*option, but using CC_COMPAT instead of CC +ifeq ($(CONFIG_CC_IS_CLANG), y) +CC_COMPAT ?= $(CC) +else +CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc +endif -# Same as cc-*option, but using COMPATCC instead of CC cc32-option = $(call try-run,\ - $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) + $(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) cc32-disable-warning = $(call try-run,\ - $(COMPATCC) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) + $(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) cc32-ldoption = $(call try-run,\ - $(COMPATCC) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2)) + $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2)) +cc32-as-instr = $(call try-run,\ + printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3)) # We cannot use the global flags to compile the vDSO files, the main reason # being that the 32-bit compiler may be older than the main (64-bit) compiler @@ -25,22 +31,21 @@ cc32-ldoption = $(call try-run,\ # arm64 one. # As a result we set our own flags here. -# From top-level Makefile -# NOSTDINC_FLAGS -VDSO_CPPFLAGS := -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include) +# KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile +VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include) VDSO_CPPFLAGS += $(LINUXINCLUDE) -VDSO_CPPFLAGS += $(KBUILD_CPPFLAGS) # Common C and assembly flags # From top-level Makefile VDSO_CAFLAGS := $(VDSO_CPPFLAGS) +ifneq ($(shell $(CC_COMPAT) --version 2>&1 | head -n 1 | grep clang),) +VDSO_CAFLAGS += --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%)) +endif + VDSO_CAFLAGS += $(call cc32-option,-fno-PIE) ifdef CONFIG_DEBUG_INFO VDSO_CAFLAGS += -g endif -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(COMPATCC)), y) -VDSO_CAFLAGS += -DCC_HAVE_ASM_GOTO -endif # From arm Makefile VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm) @@ -55,6 +60,7 @@ endif VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING + # Try to compile for ARMv8. If the compiler is too old and doesn't support it, # fall back to v7. There is no easy way to check for what architecture the code # is being compiled, so define a macro specifying that (see arch/arm/Makefile). @@ -91,6 +97,12 @@ VDSO_CFLAGS += -Wno-int-to-pointer-cast VDSO_AFLAGS := $(VDSO_CAFLAGS) VDSO_AFLAGS += -D__ASSEMBLY__ +# Check for binutils support for dmb ishld +dmbinstr := $(call cc32-as-instr,dmb ishld,-DCONFIG_AS_DMB_ISHLD=1) + +VDSO_CFLAGS += $(dmbinstr) +VDSO_AFLAGS += $(dmbinstr) + VDSO_LDFLAGS := $(VDSO_CPPFLAGS) # From arm vDSO Makefile VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 @@ -159,14 +171,14 @@ quiet_cmd_vdsold_and_vdso_check = LD32 $@ cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) quiet_cmd_vdsold = LD32 $@ - cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ + cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ quiet_cmd_vdsocc = CC32 $@ - cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< + cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< quiet_cmd_vdsocc_gettimeofday = CC32 $@ - cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< + cmd_vdsocc_gettimeofday = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< quiet_cmd_vdsoas = AS32 $@ - cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< + cmd_vdsoas = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< quiet_cmd_vdsomunge = MUNGE $@ cmd_vdsomunge = $(obj)/$(munge) $< $@ diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index bd978ad71936..3d3815020e36 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -229,20 +229,6 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) } } -static bool __hyp_text __true_value(void) -{ - return true; -} - -static bool __hyp_text __false_value(void) -{ - return false; -} - -static hyp_alternate_select(__check_arm_834220, - __false_value, __true_value, - ARM64_WORKAROUND_834220); - static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) { u64 par, tmp; @@ -298,7 +284,8 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) * resolve the IPA using the AT instruction. */ if (!(esr & ESR_ELx_S1PTW) && - (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + (cpus_have_const_cap(ARM64_WORKAROUND_834220) || + (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { if (!__translate_far_to_hpfar(far, &hpfar)) return false; } else { diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index c466060b76d6..eb0efc5557f3 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -67,10 +67,14 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, isb(); } -static hyp_alternate_select(__tlb_switch_to_guest, - __tlb_switch_to_guest_nvhe, - __tlb_switch_to_guest_vhe, - ARM64_HAS_VIRT_HOST_EXTN); +static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm, + struct tlb_inv_context *cxt) +{ + if (has_vhe()) + __tlb_switch_to_guest_vhe(kvm, cxt); + else + __tlb_switch_to_guest_nvhe(kvm, cxt); +} static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, struct tlb_inv_context *cxt) @@ -98,10 +102,14 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, write_sysreg(0, vttbr_el2); } -static hyp_alternate_select(__tlb_switch_to_host, - __tlb_switch_to_host_nvhe, - __tlb_switch_to_host_vhe, - ARM64_HAS_VIRT_HOST_EXTN); +static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, + struct tlb_inv_context *cxt) +{ + if (has_vhe()) + __tlb_switch_to_host_vhe(kvm, cxt); + else + __tlb_switch_to_host_nvhe(kvm, cxt); +} void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { @@ -111,7 +119,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); /* * We could do so much better if we had the VA as well. @@ -154,7 +162,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) if (!has_vhe() && icache_is_vpipt()) __flush_icache_all(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) @@ -165,13 +173,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); __tlbi(vmalls12e1is); dsb(ish); isb(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) @@ -180,13 +188,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) struct tlb_inv_context cxt; /* Switch to requested VMID */ - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); __tlbi(vmalle1); dsb(nsh); isb(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_flush_vm_context(void) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 115d7a0e4b08..855f2a7954e6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -113,6 +113,15 @@ static inline bool is_ttbr1_addr(unsigned long addr) return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; } +static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) +{ + /* Either init_pg_dir or swapper_pg_dir */ + if (mm == &init_mm) + return __pa_symbol(mm->pgd); + + return (unsigned long)virt_to_phys(mm->pgd); +} + /* * Dump out the page tables associated with 'addr' in the currently active mm. */ @@ -141,7 +150,7 @@ static void show_pte(unsigned long addr) pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - vabits_actual, (unsigned long)virt_to_phys(mm->pgd)); + vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -266,7 +275,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ - dfsc = FIELD_PREP(SYS_PAR_EL1_FST, par); + dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT; } diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile index a4fc65f3928d..b66215e8658e 100644 --- a/arch/arm64/xen/Makefile +++ b/arch/arm64/xen/Makefile @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o) obj-y := xen-arm.o hypercall.o -obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o) diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi index 63a9f33aa43e..5cfc9d347826 100644 --- a/arch/mips/boot/dts/qca/ar9331.dtsi +++ b/arch/mips/boot/dts/qca/ar9331.dtsi @@ -99,7 +99,7 @@ miscintc: interrupt-controller@18060010 { compatible = "qca,ar7240-misc-intc"; - reg = <0x18060010 0x4>; + reg = <0x18060010 0x8>; interrupt-parent = <&cpuintc>; interrupts = <6>; diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index af44b35d79a1..b4328b3b5288 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -160,7 +160,6 @@ void __init prom_meminit(void) void __init prom_free_prom_memory(void) { - unsigned long addr; int i; if (prom_flags & PROM_FLAG_DONT_FREE_TEMP) diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h index cbdc14b77435..adab7b54c3b4 100644 --- a/arch/mips/include/asm/octeon/cvmx-ipd.h +++ b/arch/mips/include/asm/octeon/cvmx-ipd.h @@ -36,6 +36,7 @@ #include <asm/octeon/octeon-feature.h> #include <asm/octeon/cvmx-ipd-defs.h> +#include <asm/octeon/cvmx-pip-defs.h> enum cvmx_ipd_mode { CVMX_IPD_OPC_MODE_STT = 0LL, /* All blocks DRAM, not cached in L2 */ diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 071053ece677..5d70babfc9ee 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -52,6 +52,7 @@ # endif #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 /* whitelists for checksyscalls */ #define __IGNORE_fadvise64_64 diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c index fa62cd1dff93..6a7afe7ef4d3 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/cpu-bugs64.c @@ -24,7 +24,8 @@ static char r4kwar[] __initdata = static char daddiwar[] __initdata = "Enable CPU_DADDI_WORKAROUNDS to rectify."; -static inline void align_mod(const int align, const int mod) +static __always_inline __init +void align_mod(const int align, const int mod) { asm volatile( ".set push\n\t" @@ -38,8 +39,9 @@ static inline void align_mod(const int align, const int mod) : "n"(align), "n"(mod)); } -static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w, - const int align, const int mod) +static __always_inline __init +void mult_sh_align_mod(long *v1, long *v2, long *w, + const int align, const int mod) { unsigned long flags; int m1, m2; @@ -113,7 +115,7 @@ static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w, *w = lw; } -static inline void check_mult_sh(void) +static __always_inline __init void check_mult_sh(void) { long v1[8], v2[8], w[8]; int bug, fix, i; @@ -176,7 +178,7 @@ asmlinkage void __init do_daddi_ov(struct pt_regs *regs) exception_exit(prev_state); } -static inline void check_daddi(void) +static __init void check_daddi(void) { extern asmlinkage void handle_daddi_ov(void); unsigned long flags; @@ -242,7 +244,7 @@ static inline void check_daddi(void) int daddiu_bug = IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1; -static inline void check_daddiu(void) +static __init void check_daddiu(void) { long v, w, tmp; diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index b8249c233754..5eec13b8d222 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -108,6 +108,9 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type) return; } + if (start < PHYS_OFFSET) + return; + memblock_add(start, size); /* Reserve any memory except the ordinary RAM ranges. */ switch (type) { @@ -321,7 +324,7 @@ static void __init bootmem_init(void) * Reserve any memory between the start of RAM and PHYS_OFFSET */ if (ramstart > PHYS_OFFSET) - memblock_reserve(PHYS_OFFSET, PFN_UP(ramstart) - PHYS_OFFSET); + memblock_reserve(PHYS_OFFSET, ramstart - PHYS_OFFSET); if (PFN_UP(ramstart) > ARCH_PFN_OFFSET) { pr_info("Wasting %lu bytes for tracking %lu unused pages\n", diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index b0e25e913bdb..3f16f3823031 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -80,6 +80,7 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len, save_static_function(sys_fork); save_static_function(sys_clone); +save_static_function(sys_clone3); SYSCALL_DEFINE1(set_thread_area, unsigned long, addr) { diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index c9c879ec9b6d..e7c5ab38e403 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -373,4 +373,4 @@ 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick 434 n32 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 n32 clone3 __sys_clone3 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index bbce9159caa1..13cd66581f3b 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -349,4 +349,4 @@ 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick 434 n64 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 n64 clone3 __sys_clone3 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 9653591428ec..353539ea4140 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -422,4 +422,4 @@ 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick 434 o32 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 o32 clone3 __sys_clone3 diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c index 4abb92e0fc39..4254ac4ec616 100644 --- a/arch/mips/loongson64/common/mem.c +++ b/arch/mips/loongson64/common/mem.c @@ -3,6 +3,7 @@ */ #include <linux/fs.h> #include <linux/fcntl.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <asm/bootinfo.h> @@ -64,24 +65,22 @@ void __init prom_init_memory(void) node_id = loongson_memmap->map[i].node_id; mem_type = loongson_memmap->map[i].mem_type; - if (node_id == 0) { - switch (mem_type) { - case SYSTEM_RAM_LOW: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RAM); - break; - case SYSTEM_RAM_HIGH: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RAM); - break; - case SYSTEM_RAM_RESERVED: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RESERVED); - break; - } + if (node_id != 0) + continue; + + switch (mem_type) { + case SYSTEM_RAM_LOW: + memblock_add(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; + case SYSTEM_RAM_HIGH: + memblock_add(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; + case SYSTEM_RAM_RESERVED: + memblock_reserve(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; } } } diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c index ffefc1cb2612..98c3a7feb10f 100644 --- a/arch/mips/loongson64/common/serial.c +++ b/arch/mips/loongson64/common/serial.c @@ -110,7 +110,7 @@ static int __init serial_init(void) } module_init(serial_init); -static void __init serial_exit(void) +static void __exit serial_exit(void) { platform_device_unregister(&uart8250_device); } diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index 414e97de5dc0..8f20d2cb3767 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -142,8 +142,6 @@ static void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RAM); memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; @@ -156,16 +154,12 @@ static void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RAM); memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", (u32)node_id, mem_type, mem_start, mem_size); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RESERVED); memblock_reserve(((node_id << 44) + mem_start), mem_size << 20); break; @@ -191,8 +185,6 @@ static void __init node_mem_init(unsigned int node) NODE_DATA(node)->node_start_pfn = start_pfn; NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn; - free_bootmem_with_active_regions(node, end_pfn); - if (node == 0) { /* kernel end address */ unsigned long kernel_end_pfn = PFN_UP(__pa_symbol(&_end)); @@ -209,8 +201,6 @@ static void __init node_mem_init(unsigned int node) memblock_reserve((node_addrspace_offset | 0xfe000000), 32 << 20); } - - sparse_memory_present_with_active_regions(node); } static __init void prom_meminit(void) @@ -227,6 +217,7 @@ static __init void prom_meminit(void) cpumask_clear(&__node_data[(node)]->cpumask); } } + memblocks_present(); max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) { diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c index dfb527961a27..800a21b8b8b0 100644 --- a/arch/mips/pmcs-msp71xx/msp_prom.c +++ b/arch/mips/pmcs-msp71xx/msp_prom.c @@ -61,6 +61,7 @@ int init_debug = 1; /* memory blocks */ struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS]; +#define MAX_PROM_MEM 5 static phys_addr_t prom_mem_base[MAX_PROM_MEM] __initdata; static phys_addr_t prom_mem_size[MAX_PROM_MEM] __initdata; static unsigned int nr_prom_mem __initdata; @@ -358,7 +359,7 @@ void __init prom_meminit(void) p++; if (type == BOOT_MEM_ROM_DATA) { - if (nr_prom_mem >= 5) { + if (nr_prom_mem >= MAX_PROM_MEM) { pr_err("Too many ROM DATA regions"); continue; } @@ -377,7 +378,6 @@ void __init prom_free_prom_memory(void) char *ptr; int len = 0; int i; - unsigned long addr; /* * preserve environment variables and command line from pmon/bbload diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 69cfa0a5339e..807f0f782f75 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -59,7 +59,7 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO endif endif diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c deleted file mode 100644 index e8243c7fd5b5..000000000000 --- a/arch/mips/vdso/gettimeofday.c +++ /dev/null @@ -1,269 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2015 Imagination Technologies - * Author: Alex Smith <alex.smith@imgtec.com> - */ - -#include "vdso.h" - -#include <linux/compiler.h> -#include <linux/time.h> - -#include <asm/clocksource.h> -#include <asm/io.h> -#include <asm/unistd.h> -#include <asm/vdso.h> - -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - -static __always_inline long gettimeofday_fallback(struct timeval *_tv, - struct timezone *_tz) -{ - register struct timezone *tz asm("a1") = _tz; - register struct timeval *tv asm("a0") = _tv; - register long ret asm("v0"); - register long nr asm("v0") = __NR_gettimeofday; - register long error asm("a3"); - - asm volatile( - " syscall\n" - : "=r" (ret), "=r" (error) - : "r" (tv), "r" (tz), "r" (nr) - : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); - - return error ? -ret : ret; -} - -#endif - -static __always_inline long clock_gettime_fallback(clockid_t _clkid, - struct timespec *_ts) -{ - register struct timespec *ts asm("a1") = _ts; - register clockid_t clkid asm("a0") = _clkid; - register long ret asm("v0"); - register long nr asm("v0") = __NR_clock_gettime; - register long error asm("a3"); - - asm volatile( - " syscall\n" - : "=r" (ret), "=r" (error) - : "r" (clkid), "r" (ts), "r" (nr) - : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); - - return error ? -ret : ret; -} - -static __always_inline int do_realtime_coarse(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - - do { - start_seq = vdso_data_read_begin(data); - - ts->tv_sec = data->xtime_sec; - ts->tv_nsec = data->xtime_nsec >> data->cs_shift; - } while (vdso_data_read_retry(data, start_seq)); - - return 0; -} - -static __always_inline int do_monotonic_coarse(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 to_mono_sec; - u64 to_mono_nsec; - - do { - start_seq = vdso_data_read_begin(data); - - ts->tv_sec = data->xtime_sec; - ts->tv_nsec = data->xtime_nsec >> data->cs_shift; - - to_mono_sec = data->wall_to_mono_sec; - to_mono_nsec = data->wall_to_mono_nsec; - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_sec += to_mono_sec; - timespec_add_ns(ts, to_mono_nsec); - - return 0; -} - -#ifdef CONFIG_CSRC_R4K - -static __always_inline u64 read_r4k_count(void) -{ - unsigned int count; - - __asm__ __volatile__( - " .set push\n" - " .set mips32r2\n" - " rdhwr %0, $2\n" - " .set pop\n" - : "=r" (count)); - - return count; -} - -#endif - -#ifdef CONFIG_CLKSRC_MIPS_GIC - -static __always_inline u64 read_gic_count(const union mips_vdso_data *data) -{ - void __iomem *gic = get_gic(data); - u32 hi, hi2, lo; - - do { - hi = __raw_readl(gic + sizeof(lo)); - lo = __raw_readl(gic); - hi2 = __raw_readl(gic + sizeof(lo)); - } while (hi2 != hi); - - return (((u64)hi) << 32) + lo; -} - -#endif - -static __always_inline u64 get_ns(const union mips_vdso_data *data) -{ - u64 cycle_now, delta, nsec; - - switch (data->clock_mode) { -#ifdef CONFIG_CSRC_R4K - case VDSO_CLOCK_R4K: - cycle_now = read_r4k_count(); - break; -#endif -#ifdef CONFIG_CLKSRC_MIPS_GIC - case VDSO_CLOCK_GIC: - cycle_now = read_gic_count(data); - break; -#endif - default: - return 0; - } - - delta = (cycle_now - data->cs_cycle_last) & data->cs_mask; - - nsec = (delta * data->cs_mult) + data->xtime_nsec; - nsec >>= data->cs_shift; - - return nsec; -} - -static __always_inline int do_realtime(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 ns; - - do { - start_seq = vdso_data_read_begin(data); - - if (data->clock_mode == VDSO_CLOCK_NONE) - return -ENOSYS; - - ts->tv_sec = data->xtime_sec; - ns = get_ns(data); - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_nsec = 0; - timespec_add_ns(ts, ns); - - return 0; -} - -static __always_inline int do_monotonic(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 ns; - u64 to_mono_sec; - u64 to_mono_nsec; - - do { - start_seq = vdso_data_read_begin(data); - - if (data->clock_mode == VDSO_CLOCK_NONE) - return -ENOSYS; - - ts->tv_sec = data->xtime_sec; - ns = get_ns(data); - - to_mono_sec = data->wall_to_mono_sec; - to_mono_nsec = data->wall_to_mono_nsec; - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_sec += to_mono_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, ns + to_mono_nsec); - - return 0; -} - -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - -/* - * This is behind the ifdef so that we don't provide the symbol when there's no - * possibility of there being a usable clocksource, because there's nothing we - * can do without it. When libc fails the symbol lookup it should fall back on - * the standard syscall path. - */ -int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) -{ - const union mips_vdso_data *data = get_vdso_data(); - struct timespec ts; - int ret; - - ret = do_realtime(&ts, data); - if (ret) - return gettimeofday_fallback(tv, tz); - - if (tv) { - tv->tv_sec = ts.tv_sec; - tv->tv_usec = ts.tv_nsec / 1000; - } - - if (tz) { - tz->tz_minuteswest = data->tz_minuteswest; - tz->tz_dsttime = data->tz_dsttime; - } - - return 0; -} - -#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ - -int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) -{ - const union mips_vdso_data *data = get_vdso_data(); - int ret = -1; - - switch (clkid) { - case CLOCK_REALTIME_COARSE: - ret = do_realtime_coarse(ts, data); - break; - case CLOCK_MONOTONIC_COARSE: - ret = do_monotonic_coarse(ts, data); - break; - case CLOCK_REALTIME: - ret = do_realtime(ts, data); - break; - case CLOCK_MONOTONIC: - ret = do_monotonic(ts, data); - break; - default: - break; - } - - if (ret) - ret = clock_gettime_fallback(clkid, ts); - - return ret; -} diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6841bd52738b..dfbd7f22eef5 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -50,7 +50,7 @@ endif BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc -BOOTARFLAGS := -cr$(KBUILD_ARFLAGS) +BOOTARFLAGS := -crD ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d7fcdfa7fee4..ec2547cc5ecb 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -36,8 +36,8 @@ #include "book3s.h" #include "trace.h" -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ /* #define EXIT_DEBUG */ @@ -69,8 +69,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "pthru_all", VCPU_STAT(pthru_all) }, { "pthru_host", VCPU_STAT(pthru_host) }, { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, - { "largepages_2M", VM_STAT(num_2M_pages) }, - { "largepages_1G", VM_STAT(num_1G_pages) }, + { "largepages_2M", VM_STAT(num_2M_pages, .mode = 0444) }, + { "largepages_1G", VM_STAT(num_1G_pages, .mode = 0444) }, { NULL } }; diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 5a02b7d50940..9c992a88d858 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -22,6 +22,7 @@ #define REG_L __REG_SEL(ld, lw) #define REG_S __REG_SEL(sd, sw) +#define REG_SC __REG_SEL(sc.d, sc.w) #define SZREG __REG_SEL(8, 4) #define LGREG __REG_SEL(3, 2) diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index da7aa88113c2..2d592da1e776 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -98,7 +98,26 @@ _save_context: */ .macro RESTORE_ALL REG_L a0, PT_SSTATUS(sp) - REG_L a2, PT_SEPC(sp) + /* + * The current load reservation is effectively part of the processor's + * state, in the sense that load reservations cannot be shared between + * different hart contexts. We can't actually save and restore a load + * reservation, so instead here we clear any existing reservation -- + * it's always legal for implementations to clear load reservations at + * any point (as long as the forward progress guarantee is kept, but + * we'll ignore that here). + * + * Dangling load reservations can be the result of taking a trap in the + * middle of an LR/SC sequence, but can also be the result of a taken + * forward branch around an SC -- which is how we implement CAS. As a + * result we need to clear reservations between the last CAS and the + * jump back to the new context. While it is unlikely the store + * completes, implementations are allowed to expand reservations to be + * arbitrarily large. + */ + REG_L a2, PT_SEPC(sp) + REG_SC x0, a2, PT_SEPC(sp) + csrw CSR_SSTATUS, a0 csrw CSR_SEPC, a2 diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f0ba71304b6e..83f7d12042fb 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -11,6 +11,7 @@ #include <linux/swap.h> #include <linux/sizes.h> #include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> @@ -82,6 +83,8 @@ disable: } #endif /* CONFIG_BLK_DEV_INITRD */ +static phys_addr_t dtb_early_pa __initdata; + void __init setup_bootmem(void) { struct memblock_region *reg; @@ -117,7 +120,12 @@ void __init setup_bootmem(void) setup_initrd(); #endif /* CONFIG_BLK_DEV_INITRD */ - early_init_fdt_reserve_self(); + /* + * Avoid using early_init_fdt_reserve_self() since __pa() does + * not work for DTB pointers that are fixmap addresses + */ + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + early_init_fdt_scan_reserved_mem(); memblock_allow_resize(); memblock_dump_all(); @@ -393,6 +401,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) /* Save pointer to DTB for early FDT parsing */ dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK); + /* Save physical address for memblock reservation */ + dtb_early_pa = dtb_pa; } static void __init setup_vm_final(void) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 347f48702edb..38d64030aacf 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -44,6 +44,7 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -69,12 +70,13 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -370,6 +372,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y @@ -424,6 +427,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -435,6 +439,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_NETDEVICES=y CONFIG_BONDING=m @@ -489,6 +494,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -538,15 +544,16 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m +CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m @@ -580,6 +587,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -589,6 +598,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -648,12 +658,15 @@ CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m @@ -664,10 +677,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -739,7 +748,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8514b8b9500f..25f799849582 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -44,6 +44,7 @@ CONFIG_NUMA=y # CONFIG_NUMA_EMU is not set CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -66,11 +67,12 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -363,6 +365,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -418,6 +421,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -429,6 +433,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m CONFIG_NETDEVICES=y @@ -484,6 +489,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -533,16 +539,16 @@ CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m +CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m @@ -573,6 +579,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -581,6 +589,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -639,12 +648,15 @@ CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -656,10 +668,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m @@ -727,7 +735,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index be09a208b608..20c51e5d9353 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -61,7 +61,7 @@ CONFIG_RAW_DRIVER=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -# CONFIG_DIMLIB is not set +CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index d3f09526ee19..61467b9eecc7 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -41,7 +41,7 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg") #undef __ATOMIC_OP #define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier) \ -static inline void op_name(op_type val, op_type *ptr) \ +static __always_inline void op_name(op_type val, op_type *ptr) \ { \ asm volatile( \ op_string " %[ptr],%[val]\n" \ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index b8833ac983fa..eb7eed43e780 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr) return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -77,7 +77,7 @@ static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_or(mask, (long *)addr); } -static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -98,8 +98,8 @@ static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_and(mask, (long *)addr); } -static inline void arch_change_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline void arch_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index a092f63aac6a..c0f3bfeddcbe 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -171,7 +171,7 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t; * * Returns 1 if @func is available for @opcode, 0 otherwise */ -static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) mask; diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index ceeb552d3472..819803a97c2b 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -28,6 +28,8 @@ asm(".include \"asm/cpu_mf-insn.h\"\n"); CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA| \ CPU_MF_INT_SF_LSDA) +#define CPU_MF_SF_RIBM_NOTAV 0x1 /* Sampling unavailable */ + /* CPU measurement facility support */ static inline int cpum_cf_avail(void) { @@ -69,7 +71,8 @@ struct hws_qsi_info_block { /* Bit(s) */ unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/ unsigned long tear; /* 24-31: TEAR contents */ unsigned long dear; /* 32-39: DEAR contents */ - unsigned int rsvrd0; /* 40-43: reserved */ + unsigned int rsvrd0:24; /* 40-42: reserved */ + unsigned int ribm:8; /* 43: Reserved by IBM */ unsigned int cpu_speed; /* 44-47: CPU speed */ unsigned long long rsvrd1; /* 48-55: reserved */ unsigned long long rsvrd2; /* 56-63: reserved */ @@ -220,7 +223,8 @@ enum stcctm_ctr_set { MT_DIAG = 5, MT_DIAG_CLEARING = 9, /* clears loss-of-MT-ctr-data alert */ }; -static inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) + +static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) { int cc; diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index bb59dd964590..de8f0bf5f238 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -12,8 +12,6 @@ #include <asm/page.h> #include <asm/pgtable.h> - -#define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range free_pgd_range #define hugepages_supported() (MACHINE_HAS_EDAT1) @@ -23,6 +21,13 @@ pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +static inline bool is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + return false; +} + /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index e548ec1ec12c..39f747d63758 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -20,7 +20,7 @@ * We use a brcl 0,2 instruction for jump labels at compile time so it * can be easily distinguished from a hotpatch generated instruction. */ -static inline bool arch_static_branch(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n" ".pushsection __jump_table,\"aw\"\n" @@ -34,7 +34,7 @@ label: return true; } -static inline bool arch_static_branch_jump(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 36c578c0ff96..5ff98d76a66c 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -997,9 +997,9 @@ static inline pte_t pte_mkhuge(pte_t pte) #define IPTE_NODAT 0x400 #define IPTE_GUEST_ASCE 0x800 -static inline void __ptep_ipte(unsigned long address, pte_t *ptep, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, + unsigned long opt, unsigned long asce, + int local) { unsigned long pto = (unsigned long) ptep; @@ -1020,8 +1020,8 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep, : [r1] "a" (pto), [m4] "i" (local) : "memory"); } -static inline void __ptep_ipte_range(unsigned long address, int nr, - pte_t *ptep, int local) +static __always_inline void __ptep_ipte_range(unsigned long address, int nr, + pte_t *ptep, int local) { unsigned long pto = (unsigned long) ptep; @@ -1269,7 +1269,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) #define pte_offset_kernel(pmd, address) pte_offset(pmd, address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) -#define pte_unmap(pte) do { } while (0) + +static inline void pte_unmap(pte_t *pte) { } static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { @@ -1435,9 +1436,9 @@ static inline void __pmdp_csp(pmd_t *pmdp) #define IDTE_NODAT 0x1000 #define IDTE_GUEST_ASCE 0x2000 -static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, + unsigned long opt, unsigned long asce, + int local) { unsigned long sto; @@ -1461,9 +1462,9 @@ static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, } } -static inline void __pudp_idte(unsigned long addr, pud_t *pudp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp, + unsigned long opt, unsigned long asce, + int local) { unsigned long r3o; diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 78e8a888306d..e3f238e8c611 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -111,7 +111,7 @@ struct qib { /* private: */ u8 res[88]; /* public: */ - u8 parm[QDIO_MAX_BUFFERS_PER_Q]; + u8 parm[128]; } __attribute__ ((packed, aligned(256))); /** diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index 5f1fd1581330..2654e348801a 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -390,7 +390,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset, debug_sprintf_event(cf_diag_dbg, 6, "%s ctrset %d ctrset_size %zu cfvn %d csvn %d" - " need %zd rc:%d\n", + " need %zd rc %d\n", __func__, ctrset, ctrset_size, cpuhw->info.cfvn, cpuhw->info.csvn, need, rc); return need; @@ -567,7 +567,7 @@ static int cf_diag_add(struct perf_event *event, int flags) int err = 0; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d flags %#x cpuhw:%p\n", + "%s event %p cpu %d flags %#x cpuhw %p\n", __func__, event, event->cpu, flags, cpuhw); if (cpuhw->flags & PMU_F_IN_USE) { diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 544a02e944c6..3d8b12a9a6ff 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -803,6 +803,12 @@ static int __hw_perf_event_init(struct perf_event *event) goto out; } + if (si.ribm & CPU_MF_SF_RIBM_NOTAV) { + pr_warn("CPU Measurement Facility sampling is temporarily not available\n"); + err = -EBUSY; + goto out; + } + /* Always enable basic sampling */ SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE; @@ -895,7 +901,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event) /* Check online status of the CPU to which the event is pinned */ if (event->cpu >= 0 && !cpu_online(event->cpu)) - return -ENODEV; + return -ENODEV; /* Force reset of idle/hv excludes regardless of what the * user requested. diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f6db0f1bc867..d047e846e1b9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -332,7 +332,7 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static inline void __insn32_query(unsigned int opcode, u8 query[32]) +static __always_inline void __insn32_query(unsigned int opcode, u8 *query) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) query; @@ -340,9 +340,9 @@ static inline void __insn32_query(unsigned int opcode, u8 query[32]) asm volatile( /* Parameter regs are ignored */ " .insn rrf,%[opc] << 16,2,4,6,0\n" - : "=m" (*query) + : : "d" (r0), "a" (r1), [opc] "i" (opcode) - : "cc"); + : "cc", "memory"); } #define INSN_SORTL 0xb938 diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9bdff4defef1..e585a62d6530 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -66,7 +66,7 @@ static inline int clp_get_ilp(unsigned long *ilp) /* * Call Logical Processor with c=0, the give constant lps and an lpcb request. */ -static inline int clp_req(void *data, unsigned int lps) +static __always_inline int clp_req(void *data, unsigned int lps) { struct { u8 _[CLP_BLK_SIZE]; } *req = data; u64 ignored; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 23edf56cf577..50eb430b0ad8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -219,13 +219,6 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) -/* - * The mask used to denote special SPTEs, which can be either MMIO SPTEs or - * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting - * with the SVE bit in EPT PTEs. - */ -#define SPTE_SPECIAL_MASK (1ULL << 62) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 35c225ede0e4..61d93f062a36 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -734,5 +734,28 @@ do { \ if (unlikely(__gu_err)) goto err_label; \ } while (0) +/* + * We want the unsafe accessors to always be inlined and use + * the error labels - thus the macro games. + */ +#define unsafe_copy_loop(dst, src, len, type, label) \ + while (len >= sizeof(type)) { \ + unsafe_put_user(*(type *)src,(type __user *)dst,label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +#define unsafe_copy_to_user(_dst,_src,_len,label) \ +do { \ + char __user *__ucu_dst = (_dst); \ + const char *__ucu_src = (_src); \ + size_t __ucu_len = (_len); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ +} while (0) + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 63316036f85a..9c5029cf6f3f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -485,6 +485,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); @@ -618,16 +619,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, */ case 0x1f: case 0xb: { - int i, level_type; + int i; - /* read more entries until level_type is zero */ - for (i = 1; ; ++i) { + /* + * We filled in entry[0] for CPUID(EAX=<function>, + * ECX=00H) above. If its level type (ECX[15:8]) is + * zero, then the leaf is unimplemented, and we're + * done. Otherwise, continue to populate entries + * until the level type (ECX[15:8]) of the previously + * added entry is zero. + */ + for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { if (*nent >= maxnent) goto out; - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; do_host_cpuid(&entry[i], function, i); ++*nent; } @@ -969,53 +974,66 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. + * If the basic or extended CPUID leaf requested is higher than the + * maximum supported basic or extended leaf, respectively, then it is + * out of range. */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) +static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) { - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); + struct kvm_cpuid_entry2 *max; + + max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + return max && function <= max->eax; } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) { u32 function = *eax, index = *ecx; - struct kvm_cpuid_entry2 *best; - bool entry_found = true; - - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) { - entry_found = false; - if (!check_limit) - goto out; + struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *max; + bool found; - best = check_cpuid_limit(vcpu, function, index); + entry = kvm_find_cpuid_entry(vcpu, function, index); + found = entry; + /* + * Intel CPUID semantics treats any query for an out-of-range + * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were + * requested. AMD CPUID semantics returns all zeroes for any + * undefined leaf, whether or not the leaf is in range. + */ + if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && + !cpuid_function_in_range(vcpu, function)) { + max = kvm_find_cpuid_entry(vcpu, 0, 0); + if (max) { + function = max->eax; + entry = kvm_find_cpuid_entry(vcpu, function, index); + } } - -out: - if (best) { - *eax = best->eax; - *ebx = best->ebx; - *ecx = best->ecx; - *edx = best->edx; - } else + if (entry) { + *eax = entry->eax; + *ebx = entry->ebx; + *ecx = entry->ecx; + *edx = entry->edx; + } else { *eax = *ebx = *ecx = *edx = 0; - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found); - return entry_found; + /* + * When leaf 0BH or 1FH is defined, CL is pass-through + * and EDX is always the x2APIC ID, even for undefined + * subleaves. Index 1 will exist iff the leaf is + * implemented, so we pass through CL iff leaf 1 + * exists. EDX can be copied from any existing index. + */ + if (function == 0xb || function == 0x1f) { + entry = kvm_find_cpuid_entry(vcpu, function, 1); + if (entry) { + *ecx = index & 0xff; + *edx = entry->edx; + } + } + } + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); + return found; } EXPORT_SYMBOL_GPL(kvm_cpuid); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3a3a6854dcca..87b0fcc23ef8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -66,9 +66,10 @@ #define X2APIC_BROADCAST 0xFFFFFFFFul static bool lapic_timer_advance_dynamic __read_mostly; -#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 -#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 5000 -#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000 +#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_NS_INIT 1000 +#define LAPIC_TIMER_ADVANCE_NS_MAX 5000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -1504,8 +1505,8 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } - if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_ADJUST_MAX)) - timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX)) + timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; apic->lapic_timer.timer_advance_ns = timer_advance_ns; } @@ -2302,7 +2303,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) HRTIMER_MODE_ABS_HARD); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { - apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; lapic_timer_advance_dynamic = true; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5269aa057dfa..24c23c66b226 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -83,7 +83,17 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 #define PT_FIRST_AVAIL_BITS_SHIFT 10 -#define PT64_SECOND_AVAIL_BITS_SHIFT 52 +#define PT64_SECOND_AVAIL_BITS_SHIFT 54 + +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. + */ +#define SPTE_SPECIAL_MASK (3ULL << 52) +#define SPTE_AD_ENABLED_MASK (0ULL << 52) +#define SPTE_AD_DISABLED_MASK (1ULL << 52) +#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52) +#define SPTE_MMIO_MASK (3ULL << 52) #define PT64_LEVEL_BITS 9 @@ -219,12 +229,11 @@ static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; /* - * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. - * Non-present SPTEs with shadow_acc_track_value set are in place for access - * tracking. + * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK; + * shadow_acc_track_mask is the set of bits to be cleared in non-accessed + * pages. */ static u64 __read_mostly shadow_acc_track_mask; -static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; /* * The mask/shift to use for saving the original R/X bits when marking the PTE @@ -304,7 +313,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); - shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; + shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; shadow_mmio_access_mask = access_mask; } @@ -320,10 +329,27 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) return sp->role.ad_disabled; } +static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +{ + /* + * When using the EPT page-modification log, the GPAs in the log + * would come from L2 rather than L1. Therefore, we need to rely + * on write protection to record dirty pages. This also bypasses + * PML, since writes now result in a vmexit. + */ + return vcpu->arch.mmu == &vcpu->arch.guest_mmu; +} + static inline bool spte_ad_enabled(u64 spte) { MMU_WARN_ON(is_mmio_spte(spte)); - return !(spte & shadow_acc_track_value); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK; +} + +static inline bool spte_ad_need_write_protect(u64 spte) +{ + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; } static inline u64 spte_shadow_accessed_mask(u64 spte) @@ -461,7 +487,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); - BUG_ON(acc_track_mask & shadow_acc_track_value); + BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -1589,16 +1615,16 @@ static bool spte_clear_dirty(u64 *sptep) rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; - return mmu_spte_update(sptep, spte); } -static bool wrprot_ad_disabled_spte(u64 *sptep) +static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable) + if (was_writable && !spte_ad_enabled(*sptep)) kvm_set_pfn_dirty(spte_to_pfn(*sptep)); return was_writable; @@ -1617,10 +1643,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_clear_dirty(sptep); + if (spte_ad_need_write_protect(*sptep)) + flush |= spte_wrprot_for_clear_dirty(sptep); else - flush |= wrprot_ad_disabled_spte(sptep); + flush |= spte_clear_dirty(sptep); return flush; } @@ -1631,6 +1657,11 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); + /* + * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * do not bother adding back write access to pages marked + * SPTE_AD_WRPROT_ONLY_MASK. + */ spte |= shadow_dirty_mask; return mmu_spte_update(sptep, spte); @@ -2622,7 +2653,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; else spte |= shadow_accessed_mask; @@ -2968,7 +2999,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, sp = page_header(__pa(sptep)); if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; + else if (kvm_vcpu_ad_need_write_protect(vcpu)) + spte |= SPTE_AD_WRPROT_ONLY_MASK; /* * For the EPT case, shadow_present_mask is 0 if hardware diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 41abc62c9a8a..e76eb4f07f6c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2610,7 +2610,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, /* VM-entry exception error code */ if (CC(has_error_code && - vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))) + vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))) return -EINVAL; /* VM-entry interruption-info field: reserved bits */ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 4dea0e0e7e39..3e9c059099e9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -262,6 +262,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; union cpuid10_edx edx; @@ -283,8 +284,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (!pmu->version) return; + perf_get_x86_pmu_capability(&x86_pmu); + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -294,7 +297,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) } else { pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d4575ffb3cec..e7970a2e8eae 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -209,6 +209,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) struct page *page; unsigned int i; + if (!boot_cpu_has_bug(X86_BUG_L1TF)) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; + } + if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; @@ -7995,12 +8000,10 @@ static int __init vmx_init(void) * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ - if (boot_cpu_has(X86_BUG_L1TF)) { - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + if (r) { + vmx_exit(); + return r; } #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ed07d8d2caa..661e2bf38526 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -212,7 +212,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - if (cr4 & CR4_RESERVED_BITS) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + return -EINVAL; + + return 0; +} + +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + + if (kvm_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { @@ -1161,13 +1169,6 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, - MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19, - MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21, - MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23, - MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25, - MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27, - MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29, - MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, @@ -1177,13 +1178,6 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, - MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19, - MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21, - MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23, - MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25, - MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27, - MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29, - MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31, }; static unsigned num_msrs_to_save; @@ -5097,13 +5091,14 @@ out: static void kvm_init_msr_list(void) { + struct x86_pmu_capability x86_pmu; u32 dummy[2]; unsigned i, j; BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, "Please update the fixed PMCs in msrs_to_save[]"); - BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32, - "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]"); + + perf_get_x86_pmu_capability(&x86_pmu); for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) @@ -5145,6 +5140,15 @@ static void kvm_init_msr_list(void) intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; } default: break; @@ -8714,10 +8718,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in @@ -8736,7 +8736,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return -EINVAL; } - return 0; + return kvm_valid_cr4(vcpu, sregs->cr4); } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 0d3365cb64de..a04551ee5568 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -57,19 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void) return NULL; /* Here we know that Xen runs on EFI platform. */ - - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; + xen_efi_runtime_setup(); efi_systab_xen.tables = info->cfg.addr; efi_systab_xen.nr_tables = info->cfg.nent; diff --git a/block/blk-mq.c b/block/blk-mq.c index 6e3b15f70cd7..ec791156e9cc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1992,10 +1992,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) /* bypass scheduler for flush rq */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); - } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) { + } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs || + !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as * we know the driver uses bd->last in a smart fashion. + * + * Use normal plugging if this disk is slow HDD, as sequential + * IO may benefit a lot from plug merging. */ unsigned int request_count = plug->rq_count; struct request *last = NULL; @@ -2012,6 +2016,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) } blk_add_rq_to_plug(plug, rq); + } else if (q->elevator) { + blk_mq_sched_insert_request(rq, false, true, true); } else if (plug && !blk_queue_nomerges(q)) { /* * We do limited plugging. If the bio can be merged, do that. @@ -2035,8 +2041,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_try_issue_directly(data.hctx, same_queue_rq, &cookie); } - } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator && - !data.hctx->dispatch_busy)) { + } else if ((q->nr_hw_queues > 1 && is_sync) || + !data.hctx->dispatch_busy) { blk_mq_try_issue_directly(data.hctx, rq, &cookie); } else { blk_mq_sched_insert_request(rq, false, true, true); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 61b635bc2a31..656460636ad3 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -160,24 +160,27 @@ bool rq_depth_calc_max_depth(struct rq_depth *rqd) return ret; } -void rq_depth_scale_up(struct rq_depth *rqd) +/* Returns true on success and false if scaling up wasn't possible */ +bool rq_depth_scale_up(struct rq_depth *rqd) { /* * Hit max in previous round, stop here */ if (rqd->scaled_max) - return; + return false; rqd->scale_step--; rqd->scaled_max = rq_depth_calc_max_depth(rqd); + return true; } /* * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we - * had a latency violation. + * had a latency violation. Returns true on success and returns false if + * scaling down wasn't possible. */ -void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) +bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) { /* * Stop scaling down when we've hit the limit. This also prevents @@ -185,7 +188,7 @@ void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) * keep up. */ if (rqd->max_depth == 1) - return; + return false; if (rqd->scale_step < 0 && hard_throttle) rqd->scale_step = 0; @@ -194,6 +197,7 @@ void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) rqd->scaled_max = false; rq_depth_calc_max_depth(rqd); + return true; } struct rq_qos_wait_data { diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 08a09dbe0f4b..e8cb68f6958a 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -130,8 +130,8 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, acquire_inflight_cb_t *acquire_inflight_cb, cleanup_cb_t *cleanup_cb); bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit); -void rq_depth_scale_up(struct rq_depth *rqd); -void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle); +bool rq_depth_scale_up(struct rq_depth *rqd); +bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle); bool rq_depth_calc_max_depth(struct rq_depth *rqd); void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 8af553a0ba00..8641ba9793c5 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -308,7 +308,8 @@ static void calc_wb_limits(struct rq_wb *rwb) static void scale_up(struct rq_wb *rwb) { - rq_depth_scale_up(&rwb->rq_depth); + if (!rq_depth_scale_up(&rwb->rq_depth)) + return; calc_wb_limits(rwb); rwb->unknown_cnt = 0; rwb_wake_all(rwb); @@ -317,7 +318,8 @@ static void scale_up(struct rq_wb *rwb) static void scale_down(struct rq_wb *rwb, bool hard_throttle) { - rq_depth_scale_down(&rwb->rq_depth, hard_throttle); + if (!rq_depth_scale_down(&rwb->rq_depth, hard_throttle)) + return; calc_wb_limits(rwb); rwb->unknown_cnt = 0; rwb_trace_step(rwb, "scale down"); diff --git a/block/sed-opal.c b/block/sed-opal.c index 4e95a9792162..b4c761973ac1 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -129,7 +129,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = { { 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 }, /* tables */ - [OPAL_TABLE_TABLE] + [OPAL_TABLE_TABLE] = { 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 }, [OPAL_LOCKINGRANGE_GLOBAL] = { 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 }, @@ -372,8 +372,8 @@ static void check_geometry(struct opal_dev *dev, const void *data) { const struct d0_geometry_features *geo = data; - dev->align = geo->alignment_granularity; - dev->lowest_lba = geo->lowest_aligned_lba; + dev->align = be64_to_cpu(geo->alignment_granularity); + dev->lowest_lba = be64_to_cpu(geo->lowest_aligned_lba); } static int execute_step(struct opal_dev *dev, diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 76d0f9de767b..58e09ffe8b9c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4791,27 +4791,6 @@ void ata_scsi_hotplug(struct work_struct *work) return; } - /* - * XXX - UGLY HACK - * - * The block layer suspend/resume path is fundamentally broken due - * to freezable kthreads and workqueue and may deadlock if a block - * device gets removed while resume is in progress. I don't know - * what the solution is short of removing freezable kthreads and - * workqueues altogether. - * - * The following is an ugly hack to avoid kicking off device - * removal while freezer is active. This is a joke but does avoid - * this particular deadlock scenario. - * - * https://bugzilla.kernel.org/show_bug.cgi?id=62801 - * http://marc.info/?l=linux-kernel&m=138695698516487 - */ -#ifdef CONFIG_FREEZER - while (pm_freezing) - msleep(10); -#endif - DPRINTK("ENTER\n"); mutex_lock(&ap->scsi_scan_mutex); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1410fa893653..f6f77eaa7217 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -994,6 +994,16 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); + if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) { + /* In case of direct I/O, match underlying block size */ + unsigned short bsize = bdev_logical_block_size( + inode->i_sb->s_bdev); + + blk_queue_logical_block_size(lo->lo_queue, bsize); + blk_queue_physical_block_size(lo->lo_queue, bsize); + blk_queue_io_min(lo->lo_queue, bsize); + } + loop_update_rotational(lo); loop_update_dio(lo); set_capacity(lo->lo_disk, size); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index ac07e8c94c79..478aa86fc1f2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -248,8 +248,8 @@ static void nbd_put(struct nbd_device *nbd) if (refcount_dec_and_mutex_lock(&nbd->refs, &nbd_index_mutex)) { idr_remove(&nbd_index_idr, nbd->index); - mutex_unlock(&nbd_index_mutex); nbd_dev_remove(nbd); + mutex_unlock(&nbd_index_mutex); } } diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index eabc116832a7..3d7fdea872f8 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -142,8 +142,7 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector) zone->wp = zone->start; break; default: - cmd->error = BLK_STS_NOTSUPP; - break; + return BLK_STS_NOTSUPP; } return BLK_STS_OK; } diff --git a/drivers/char/random.c b/drivers/char/random.c index c2f7de9dc543..de434feb873a 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -2520,4 +2520,4 @@ void add_bootloader_randomness(const void *buf, unsigned int size) else add_device_randomness(buf, size); } -EXPORT_SYMBOL_GPL(add_bootloader_randomness);
\ No newline at end of file +EXPORT_SYMBOL_GPL(add_bootloader_randomness); diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c index b57fe09b428b..9dd6185a4b4e 100644 --- a/drivers/clk/ti/clk-7xx.c +++ b/drivers/clk/ti/clk-7xx.c @@ -683,7 +683,7 @@ static const struct omap_clkctrl_reg_data dra7_l4per2_clkctrl_regs[] __initconst { DRA7_L4PER2_MCASP2_CLKCTRL, dra7_mcasp2_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:0154:22" }, { DRA7_L4PER2_MCASP3_CLKCTRL, dra7_mcasp3_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:015c:22" }, { DRA7_L4PER2_MCASP5_CLKCTRL, dra7_mcasp5_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:016c:22" }, - { DRA7_L4PER2_MCASP8_CLKCTRL, dra7_mcasp8_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:0184:24" }, + { DRA7_L4PER2_MCASP8_CLKCTRL, dra7_mcasp8_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:0184:22" }, { DRA7_L4PER2_MCASP4_CLKCTRL, dra7_mcasp4_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:018c:22" }, { DRA7_L4PER2_UART7_CLKCTRL, dra7_uart7_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:01c4:24" }, { DRA7_L4PER2_UART8_CLKCTRL, dra7_uart8_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:01d4:24" }, @@ -828,8 +828,8 @@ static struct ti_dt_clk dra7xx_clks[] = { DT_CLK(NULL, "mcasp6_aux_gfclk_mux", "l4per2-clkctrl:01f8:22"), DT_CLK(NULL, "mcasp7_ahclkx_mux", "l4per2-clkctrl:01fc:24"), DT_CLK(NULL, "mcasp7_aux_gfclk_mux", "l4per2-clkctrl:01fc:22"), - DT_CLK(NULL, "mcasp8_ahclkx_mux", "l4per2-clkctrl:0184:22"), - DT_CLK(NULL, "mcasp8_aux_gfclk_mux", "l4per2-clkctrl:0184:24"), + DT_CLK(NULL, "mcasp8_ahclkx_mux", "l4per2-clkctrl:0184:24"), + DT_CLK(NULL, "mcasp8_aux_gfclk_mux", "l4per2-clkctrl:0184:22"), DT_CLK(NULL, "mmc1_clk32k", "l3init-clkctrl:0008:8"), DT_CLK(NULL, "mmc1_fclk_div", "l3init-clkctrl:0008:25"), DT_CLK(NULL, "mmc1_fclk_mux", "l3init-clkctrl:0008:24"), diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index d8c2bd4391d0..11ff701ff4bb 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -25,7 +25,9 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq) struct clock_event_device *clkevt = &to->clkevt; - of_irq->percpu ? free_percpu_irq(of_irq->irq, clkevt) : + if (of_irq->percpu) + free_percpu_irq(of_irq->irq, clkevt); + else free_irq(of_irq->irq, clkevt); } diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index fe7a73f52329..bb287f35cf40 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -530,11 +530,12 @@ static void sprd_eic_handle_one_type(struct gpio_chip *chip) } for_each_set_bit(n, ®, SPRD_EIC_PER_BANK_NR) { - girq = irq_find_mapping(chip->irq.domain, - bank * SPRD_EIC_PER_BANK_NR + n); + u32 offset = bank * SPRD_EIC_PER_BANK_NR + n; + + girq = irq_find_mapping(chip->irq.domain, offset); generic_handle_irq(girq); - sprd_eic_toggle_trigger(chip, girq, n); + sprd_eic_toggle_trigger(chip, girq, offset); } } } diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c index 47d05e357e61..faf86ea9c51a 100644 --- a/drivers/gpio/gpio-max77620.c +++ b/drivers/gpio/gpio-max77620.c @@ -192,13 +192,13 @@ static int max77620_gpio_set_debounce(struct max77620_gpio *mgpio, case 0: val = MAX77620_CNFG_GPIO_DBNC_None; break; - case 1 ... 8: + case 1000 ... 8000: val = MAX77620_CNFG_GPIO_DBNC_8ms; break; - case 9 ... 16: + case 9000 ... 16000: val = MAX77620_CNFG_GPIO_DBNC_16ms; break; - case 17 ... 32: + case 17000 ... 32000: val = MAX77620_CNFG_GPIO_DBNC_32ms; break; default: diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 1eea2c6c2e1d..80ea49f570f4 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -317,7 +317,7 @@ struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, transitory = flags & OF_GPIO_TRANSITORY; ret = gpiod_request(desc, label); - if (ret == -EBUSY && (flags & GPIOD_FLAGS_BIT_NONEXCLUSIVE)) + if (ret == -EBUSY && (dflags & GPIOD_FLAGS_BIT_NONEXCLUSIVE)) return desc; if (ret) return ERR_PTR(ret); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index bdbc1649eafa..5833e4f380d6 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -3070,8 +3070,10 @@ int gpiod_direction_output(struct gpio_desc *desc, int value) if (!ret) goto set_output_value; /* Emulate open drain by not actively driving the line high */ - if (value) - return gpiod_direction_input(desc); + if (value) { + ret = gpiod_direction_input(desc); + goto set_output_flag; + } } else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) { ret = gpio_set_config(gc, gpio_chip_hwgpio(desc), @@ -3079,8 +3081,10 @@ int gpiod_direction_output(struct gpio_desc *desc, int value) if (!ret) goto set_output_value; /* Emulate open source by not actively driving the line low */ - if (!value) - return gpiod_direction_input(desc); + if (!value) { + ret = gpiod_direction_input(desc); + goto set_output_flag; + } } else { gpio_set_config(gc, gpio_chip_hwgpio(desc), PIN_CONFIG_DRIVE_PUSH_PULL); @@ -3088,6 +3092,17 @@ int gpiod_direction_output(struct gpio_desc *desc, int value) set_output_value: return gpiod_direction_output_raw_commit(desc, value); + +set_output_flag: + /* + * When emulating open-source or open-drain functionalities by not + * actively driving the line (setting mode to input) we still need to + * set the IS_OUT flag or otherwise we won't be able to set the line + * value anymore. + */ + if (ret == 0) + set_bit(FLAG_IS_OUT, &desc->flags); + return ret; } EXPORT_SYMBOL_GPL(gpiod_direction_output); @@ -3448,8 +3463,6 @@ static void gpio_set_open_drain_value_commit(struct gpio_desc *desc, bool value) if (value) { ret = chip->direction_input(chip, offset); - if (!ret) - clear_bit(FLAG_IS_OUT, &desc->flags); } else { ret = chip->direction_output(chip, offset, 0); if (!ret) @@ -3479,8 +3492,6 @@ static void gpio_set_open_source_value_commit(struct gpio_desc *desc, bool value set_bit(FLAG_IS_OUT, &desc->flags); } else { ret = chip->direction_input(chip, offset); - if (!ret) - clear_bit(FLAG_IS_OUT, &desc->flags); } trace_gpio_direction(desc_to_gpio(desc), !value, ret); if (ret < 0) diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 42e2c1f57152..00962a659009 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -54,7 +54,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \ amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \ amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \ - amdgpu_vm_sdma.o amdgpu_pmu.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o + amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index eba42c752bca..82155ac3288a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -189,7 +189,7 @@ static int acp_hw_init(void *handle) u32 val = 0; u32 count = 0; struct device *dev; - struct i2s_platform_data *i2s_pdata; + struct i2s_platform_data *i2s_pdata = NULL; struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -231,20 +231,21 @@ static int acp_hw_init(void *handle) adev->acp.acp_cell = kcalloc(ACP_DEVS, sizeof(struct mfd_cell), GFP_KERNEL); - if (adev->acp.acp_cell == NULL) - return -ENOMEM; + if (adev->acp.acp_cell == NULL) { + r = -ENOMEM; + goto failure; + } adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL); if (adev->acp.acp_res == NULL) { - kfree(adev->acp.acp_cell); - return -ENOMEM; + r = -ENOMEM; + goto failure; } i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL); if (i2s_pdata == NULL) { - kfree(adev->acp.acp_res); - kfree(adev->acp.acp_cell); - return -ENOMEM; + r = -ENOMEM; + goto failure; } switch (adev->asic_type) { @@ -341,14 +342,14 @@ static int acp_hw_init(void *handle) r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell, ACP_DEVS); if (r) - return r; + goto failure; for (i = 0; i < ACP_DEVS ; i++) { dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i); r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev); if (r) { dev_err(dev, "Failed to add dev to genpd\n"); - return r; + goto failure; } } @@ -367,7 +368,8 @@ static int acp_hw_init(void *handle) break; if (--count == 0) { dev_err(&adev->pdev->dev, "Failed to reset ACP\n"); - return -ETIMEDOUT; + r = -ETIMEDOUT; + goto failure; } udelay(100); } @@ -384,7 +386,8 @@ static int acp_hw_init(void *handle) break; if (--count == 0) { dev_err(&adev->pdev->dev, "Failed to reset ACP\n"); - return -ETIMEDOUT; + r = -ETIMEDOUT; + goto failure; } udelay(100); } @@ -393,6 +396,13 @@ static int acp_hw_init(void *handle) val &= ~ACP_SOFT_RESET__SoftResetAud_MASK; cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val); return 0; + +failure: + kfree(i2s_pdata); + kfree(adev->acp.acp_res); + kfree(adev->acp.acp_cell); + kfree(adev->acp.acp_genpd); + return r; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 7bcf86c61999..61e38e43ad1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -270,7 +270,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, r = amdgpu_bo_create_list_entry_array(&args->in, &info); if (r) - goto error_free; + return r; switch (args->in.operation) { case AMDGPU_BO_LIST_OP_CREATE: @@ -283,8 +283,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL); mutex_unlock(&fpriv->bo_list_lock); if (r < 0) { - amdgpu_bo_list_put(list); - return r; + goto error_put_list; } handle = r; @@ -306,9 +305,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, mutex_unlock(&fpriv->bo_list_lock); if (IS_ERR(old)) { - amdgpu_bo_list_put(list); r = PTR_ERR(old); - goto error_free; + goto error_put_list; } amdgpu_bo_list_put(old); @@ -325,8 +323,10 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data, return 0; +error_put_list: + amdgpu_bo_list_put(list); + error_free: - if (info) - kvfree(info); + kvfree(info); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 264677ab248a..6f8aaf655a9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -81,9 +81,10 @@ * - 3.32.0 - Add syncobj timeline support to AMDGPU_CS. * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS. * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches + * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 34 +#define KMS_DRIVER_MINOR 35 #define KMS_DRIVER_PATCHLEVEL 0 #define AMDGPU_MAX_TIMEOUT_PARAM_LENTH 256 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 554a59b3c4a6..6ee4021910e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -165,6 +165,7 @@ struct amdgpu_gfx_config { uint32_t num_sc_per_sh; uint32_t num_packer_per_sc; uint32_t pa_sc_tile_steering_override; + uint64_t tcc_disabled_mask; }; struct amdgpu_cu_info { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index f6147528be64..f2c097983f48 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -787,6 +787,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file dev_info.pa_sc_tile_steering_override = adev->gfx.config.pa_sc_tile_steering_override; + dev_info.tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask; + return copy_to_user(out, &dev_info, min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index e2fb141ff2e5..5251352f5922 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -603,14 +603,12 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct ttm_bo_global *glob = adev->mman.bdev.glob; struct amdgpu_vm_bo_base *bo_base; -#if 0 if (vm->bulk_moveable) { spin_lock(&glob->lru_lock); ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move); spin_unlock(&glob->lru_lock); return; } -#endif memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move)); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 638c821611ab..957811b73672 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1691,6 +1691,17 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev) } } +static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev) +{ + /* TCCs are global (not instanced). */ + uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) | + RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE); + + adev->gfx.config.tcc_disabled_mask = + REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) | + (REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, HI_TCC_DISABLE) << 16); +} + static void gfx_v10_0_constants_init(struct amdgpu_device *adev) { u32 tmp; @@ -1702,6 +1713,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev) gfx_v10_0_setup_rb(adev); gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info); + gfx_v10_0_get_tcc_info(adev); adev->gfx.config.pa_sc_tile_steering_override = gfx_v10_0_init_pa_sc_tile_steering_override(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 85393a99a848..de9b995b65b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -317,10 +317,12 @@ static int nv_asic_reset(struct amdgpu_device *adev) struct smu_context *smu = &adev->smu; if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); ret = smu_baco_reset(smu); } else { - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); ret = nv_asic_mode1_reset(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index f70658a536a9..f8ab80c8801b 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -558,12 +558,14 @@ static int soc15_asic_reset(struct amdgpu_device *adev) { switch (soc15_asic_reset_method(adev)) { case AMD_RESET_METHOD_BACO: - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); return soc15_asic_baco_reset(adev); case AMD_RESET_METHOD_MODE2: return soc15_mode2_reset(adev); default: - amdgpu_inc_vram_lost(adev); + if (!adev->in_suspend) + amdgpu_inc_vram_lost(adev); return soc15_asic_mode1_reset(adev); } } @@ -771,8 +773,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev) #if defined(CONFIG_DRM_AMD_DC) else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); -#else -# warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15." #endif amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); break; 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 8cab6da512a0..a52f0b13a2c8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2385,8 +2385,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY) dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true; - if (adev->asic_type == CHIP_RENOIR) - dm->dc->debug.disable_stutter = true; return 0; fail: @@ -6019,7 +6017,9 @@ static void amdgpu_dm_enable_crtc_interrupts(struct drm_device *dev, struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state, *new_crtc_state; int i; +#ifdef CONFIG_DEBUG_FS enum amdgpu_dm_pipe_crc_source source; +#endif for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c index 1787b9bf800a..76d54885374a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c @@ -668,6 +668,7 @@ struct clock_source *dce100_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index 318e9c2e2ca8..89620adc81d8 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -714,6 +714,7 @@ struct clock_source *dce110_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c index 83e1878161c9..21a657e79306 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c @@ -687,6 +687,7 @@ struct clock_source *dce112_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 8b85e5274bba..7c52f7f9196c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -500,6 +500,7 @@ static struct clock_source *dce120_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index 4625df9f9fd2..643ccb0ade00 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -701,6 +701,7 @@ struct clock_source *dce80_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 59305e411a66..1599bb971111 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -786,6 +786,7 @@ struct clock_source *dcn10_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } 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 b4e3ce22ed52..5a2763daff4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1077,6 +1077,7 @@ struct clock_source *dcn20_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile index 8cd9de8b1a7a..ef673bffc241 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile @@ -3,7 +3,17 @@ DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o -CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4 +ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) + cc_stack_align := -mpreferred-stack-boundary=4 +else ifneq ($(call cc-option, -mstack-alignment=16),) + cc_stack_align := -mstack-alignment=16 +endif + +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align) + +ifdef CONFIG_CC_IS_CLANG +CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2 +endif AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21)) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index 456cd0e3289c..3b6ed60dcd35 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -39,9 +39,6 @@ * ways. Unless there is something clearly wrong with it the code should * remain as-is as it provides us with a guarantee from HW that it is correct. */ - -typedef unsigned int uint; - typedef struct { double DPPCLK; double DISPCLK; @@ -4774,7 +4771,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0; mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - uint m; + unsigned int m; locals->cursor_bw[k] = 0; locals->cursor_bw_pre[k] = 0; @@ -5285,7 +5282,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank; double FullDETBufferingTimeYStutterCriticalPlane = 0; double TimeToFinishSwathTransferStutterCriticalPlane = 0; - uint k, j; + unsigned int k, j; mode_lib->vba.TotalActiveDPP = 0; mode_lib->vba.TotalDCCActiveDPP = 0; @@ -5507,7 +5504,7 @@ static void CalculateDCFCLKDeepSleep( double DPPCLK[], double *DCFCLKDeepSleep) { - uint k; + unsigned int k; double DisplayPipeLineDeliveryTimeLuma; double DisplayPipeLineDeliveryTimeChroma; //double DCFCLKDeepSleepPerPlane[DC__NUM_DPP__MAX]; @@ -5727,7 +5724,7 @@ static void CalculatePixelDeliveryTimes( double DisplayPipeRequestDeliveryTimeChromaPrefetch[]) { double req_per_swath_ub; - uint k; + unsigned int k; for (k = 0; k < NumberOfActivePlanes; ++k) { if (VRatio[k] <= 1) { @@ -5869,7 +5866,7 @@ static void CalculateMetaAndPTETimes( unsigned int dpte_groups_per_row_chroma_ub; unsigned int num_group_per_lower_vm_stage; unsigned int num_req_per_lower_vm_stage; - uint k; + unsigned int k; for (k = 0; k < NumberOfActivePlanes; ++k) { if (GPUVMEnable == true) { diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 33960fb38a5d..4acf139ea014 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -843,6 +843,8 @@ static int smu_sw_init(void *handle) smu->smu_baco.state = SMU_BACO_STATE_EXIT; smu->smu_baco.platform_support = false; + mutex_init(&smu->sensor_lock); + smu->watermarks_bitmap = 0; smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index f1f072012fac..d493a3f8c07a 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu, if (!data || !size) return -EINVAL; + mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_MAX_FAN_RPM: *(uint32_t *)data = pptable->FanMaximumRpm; @@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu, default: ret = smu_smc_read_sensor(smu, sensor, data, size); } + mutex_unlock(&smu->sensor_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 6109815a0401..23171a4d9a31 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -344,6 +344,7 @@ struct smu_context const struct smu_funcs *funcs; const struct pptable_funcs *ppt_funcs; struct mutex mutex; + struct mutex sensor_lock; uint64_t pool_size; struct smu_table_context smu_table; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 12c0e469bf35..0b461404af6b 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -547,7 +547,7 @@ static int navi10_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; - if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) { + if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { @@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu, if(!data || !size) return -EINVAL; + mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_MAX_FAN_RPM: *(uint32_t *)data = pptable->FanMaximumRpm; @@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu, default: ret = smu_smc_read_sensor(smu, sensor, data, size); } + mutex_unlock(&smu->sensor_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index 64386ee3f878..bbd8ebd58434 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu, if(!data || !size) return -EINVAL; + mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_MAX_FAN_RPM: *(uint32_t *)data = pptable->FanMaximumRpm; @@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu, default: ret = smu_smc_read_sensor(smu, sensor, data, size); } + mutex_unlock(&smu->sensor_lock); return ret; } diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c index 2851cac94d86..b72840c06ab7 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c @@ -43,9 +43,8 @@ komeda_wb_encoder_atomic_check(struct drm_encoder *encoder, struct komeda_data_flow_cfg dflow; int err; - if (!writeback_job || !writeback_job->fb) { + if (!writeback_job) return 0; - } if (!crtc_st->active) { DRM_DEBUG_ATOMIC("Cannot write the composition result out on a inactive CRTC.\n"); @@ -166,8 +165,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms, &komeda_wb_encoder_helper_funcs, formats, n_formats); komeda_put_fourcc_list(formats); - if (err) + if (err) { + kfree(kwb_conn); return err; + } drm_connector_helper_add(&wb_conn->base, &komeda_wb_conn_helper_funcs); diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index 22c0847986df..875a3a9eabfa 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -131,7 +131,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder, struct drm_framebuffer *fb; int i, n_planes; - if (!conn_state->writeback_job || !conn_state->writeback_job->fb) + if (!conn_state->writeback_job) return 0; fb = conn_state->writeback_job->fb; @@ -248,7 +248,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm, mw_state = to_mw_state(conn_state); - if (conn_state->writeback_job && conn_state->writeback_job->fb) { + if (conn_state->writeback_job) { struct drm_framebuffer *fb = conn_state->writeback_job->fb; DRM_DEV_DEBUG_DRIVER(drm->dev, diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index cebc8e620820..8a8d605021f0 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -728,6 +728,8 @@ static int tc_set_video_mode(struct tc_data *tc, int lower_margin = mode->vsync_start - mode->vdisplay; int vsync_len = mode->vsync_end - mode->vsync_start; u32 dp0_syncval; + u32 bits_per_pixel = 24; + u32 in_bw, out_bw; /* * Recommended maximum number of symbols transferred in a transfer unit: @@ -735,7 +737,10 @@ static int tc_set_video_mode(struct tc_data *tc, * (output active video bandwidth in bytes)) * Must be less than tu_size. */ - max_tu_symbol = TU_SIZE_RECOMMENDED - 1; + + in_bw = mode->clock * bits_per_pixel / 8; + out_bw = tc->link.base.num_lanes * tc->link.base.rate; + max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw); dev_dbg(tc->dev, "set mode %dx%d\n", mode->hdisplay, mode->vdisplay); diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 419381abbdd1..14aeaf736321 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -430,10 +430,15 @@ static int drm_atomic_connector_check(struct drm_connector *connector, return -EINVAL; } - if (writeback_job->out_fence && !writeback_job->fb) { - DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n", - connector->base.id, connector->name); - return -EINVAL; + if (!writeback_job->fb) { + if (writeback_job->out_fence) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n", + connector->base.id, connector->name); + return -EINVAL; + } + + drm_writeback_cleanup_job(writeback_job); + state->writeback_job = NULL; } return 0; diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index ff138b6ec48b..43d9e3bb3a94 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -324,6 +324,9 @@ void drm_writeback_cleanup_job(struct drm_writeback_job *job) if (job->fb) drm_framebuffer_put(job->fb); + if (job->out_fence) + dma_fence_put(job->out_fence); + kfree(job); } EXPORT_SYMBOL(drm_writeback_cleanup_job); @@ -366,25 +369,29 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector, { unsigned long flags; struct drm_writeback_job *job; + struct dma_fence *out_fence; spin_lock_irqsave(&wb_connector->job_lock, flags); job = list_first_entry_or_null(&wb_connector->job_queue, struct drm_writeback_job, list_entry); - if (job) { + if (job) list_del(&job->list_entry); - if (job->out_fence) { - if (status) - dma_fence_set_error(job->out_fence, status); - dma_fence_signal(job->out_fence); - dma_fence_put(job->out_fence); - } - } + spin_unlock_irqrestore(&wb_connector->job_lock, flags); if (WARN_ON(!job)) return; + out_fence = job->out_fence; + if (out_fence) { + if (status) + dma_fence_set_error(out_fence, status); + dma_fence_signal(out_fence); + dma_fence_put(out_fence); + job->out_fence = NULL; + } + INIT_WORK(&job->cleanup_work, cleanup_work); queue_work(system_long_wq, &job->cleanup_work); } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index b51d1ceb8739..aa54bb22796d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -3280,7 +3280,20 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb, switch (fb->modifier) { case DRM_FORMAT_MOD_LINEAR: case I915_FORMAT_MOD_X_TILED: - return 4096; + /* + * Validated limit is 4k, but has 5k should + * work apart from the following features: + * - Ytile (already limited to 4k) + * - FP16 (already limited to 4k) + * - render compression (already limited to 4k) + * - KVMR sprite and cursor (don't care) + * - horizontal panning (TODO verify this) + * - pipe and plane scaling (TODO verify this) + */ + if (cpp == 8) + return 4096; + else + return 5120; case I915_FORMAT_MOD_Y_TILED_CCS: case I915_FORMAT_MOD_Yf_TILED_CCS: /* FIXME AUX plane? */ @@ -7261,7 +7274,7 @@ retry: pipe_config->fdi_lanes = lane; intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock, - link_bw, &pipe_config->fdi_m_n, false); + link_bw, &pipe_config->fdi_m_n, false, false); ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config); if (ret == -EDEADLK) @@ -7508,11 +7521,15 @@ void intel_link_compute_m_n(u16 bits_per_pixel, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, - bool constant_n) + bool constant_n, bool fec_enable) { - m_n->tu = 64; + u32 data_clock = bits_per_pixel * pixel_clock; - compute_m_n(bits_per_pixel * pixel_clock, + if (fec_enable) + data_clock = intel_dp_mode_to_fec_clock(data_clock); + + m_n->tu = 64; + compute_m_n(data_clock, link_clock * nlanes * 8, &m_n->gmch_m, &m_n->gmch_n, constant_n); diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index e57e6969051d..01fa87ad3270 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -414,7 +414,7 @@ enum phy_fia { void intel_link_compute_m_n(u16 bpp, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, - bool constant_n); + bool constant_n, bool fec_enable); bool is_ccs_modifier(u64 modifier); void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv); u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 921ad0a2f7ba..57e9f0ba331b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -78,8 +78,8 @@ #define DP_DSC_MAX_ENC_THROUGHPUT_0 340000 #define DP_DSC_MAX_ENC_THROUGHPUT_1 400000 -/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */ -#define DP_DSC_FEC_OVERHEAD_FACTOR 976 +/* DP DSC FEC Overhead factor = 1/(0.972261) */ +#define DP_DSC_FEC_OVERHEAD_FACTOR 972261 /* Compliance test status bits */ #define INTEL_DP_RESOLUTION_SHIFT_MASK 0 @@ -494,6 +494,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, return 0; } +u32 intel_dp_mode_to_fec_clock(u32 mode_clock) +{ + return div_u64(mul_u32_u32(mode_clock, 1000000U), + DP_DSC_FEC_OVERHEAD_FACTOR); +} + +static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count, + u32 mode_clock, u32 mode_hdisplay) +{ + u32 bits_per_pixel, max_bpp_small_joiner_ram; + int i; + + /* + * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)* + * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP) + * for SST -> TimeSlotsPerMTP is 1, + * for MST -> TimeSlotsPerMTP has to be calculated + */ + bits_per_pixel = (link_clock * lane_count * 8) / + intel_dp_mode_to_fec_clock(mode_clock); + DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel); + + /* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */ + max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay; + DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram); + + /* + * Greatest allowed DSC BPP = MIN (output BPP from available Link BW + * check, output bpp from small joiner RAM check) + */ + bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram); + + /* Error out if the max bpp is less than smallest allowed valid bpp */ + if (bits_per_pixel < valid_dsc_bpp[0]) { + DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n", + bits_per_pixel, valid_dsc_bpp[0]); + return 0; + } + + /* Find the nearest match in the array of known BPPs from VESA */ + for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) { + if (bits_per_pixel < valid_dsc_bpp[i + 1]) + break; + } + bits_per_pixel = valid_dsc_bpp[i]; + + /* + * Compressed BPP in U6.4 format so multiply by 16, for Gen 11, + * fractional part is 0 + */ + return bits_per_pixel << 4; +} + +static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, + int mode_clock, int mode_hdisplay) +{ + u8 min_slice_count, i; + int max_slice_width; + + if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE) + min_slice_count = DIV_ROUND_UP(mode_clock, + DP_DSC_MAX_ENC_THROUGHPUT_0); + else + min_slice_count = DIV_ROUND_UP(mode_clock, + DP_DSC_MAX_ENC_THROUGHPUT_1); + + max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd); + if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) { + DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n", + max_slice_width); + return 0; + } + /* Also take into account max slice width */ + min_slice_count = min_t(u8, min_slice_count, + DIV_ROUND_UP(mode_hdisplay, + max_slice_width)); + + /* Find the closest match to the valid slice count values */ + for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) { + if (valid_dsc_slicecount[i] > + drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, + false)) + break; + if (min_slice_count <= valid_dsc_slicecount[i]) + return valid_dsc_slicecount[i]; + } + + DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count); + return 0; +} + static enum drm_mode_status intel_dp_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) @@ -2226,7 +2317,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, adjusted_mode->crtc_clock, pipe_config->port_clock, &pipe_config->dp_m_n, - constant_n); + constant_n, pipe_config->fec_enable); if (intel_connector->panel.downclock_mode != NULL && dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) { @@ -2236,7 +2327,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_connector->panel.downclock_mode->clock, pipe_config->port_clock, &pipe_config->dp_m2_n2, - constant_n); + constant_n, pipe_config->fec_enable); } if (!HAS_DDI(dev_priv)) @@ -4323,91 +4414,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector) DP_DPRX_ESI_LEN; } -u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count, - int mode_clock, int mode_hdisplay) -{ - u16 bits_per_pixel, max_bpp_small_joiner_ram; - int i; - - /* - * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)* - * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP) - * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1, - * for MST -> TimeSlotsPerMTP has to be calculated - */ - bits_per_pixel = (link_clock * lane_count * 8 * - DP_DSC_FEC_OVERHEAD_FACTOR) / - mode_clock; - - /* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */ - max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / - mode_hdisplay; - - /* - * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW - * check, output bpp from small joiner RAM check) - */ - bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram); - - /* Error out if the max bpp is less than smallest allowed valid bpp */ - if (bits_per_pixel < valid_dsc_bpp[0]) { - DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel); - return 0; - } - - /* Find the nearest match in the array of known BPPs from VESA */ - for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) { - if (bits_per_pixel < valid_dsc_bpp[i + 1]) - break; - } - bits_per_pixel = valid_dsc_bpp[i]; - - /* - * Compressed BPP in U6.4 format so multiply by 16, for Gen 11, - * fractional part is 0 - */ - return bits_per_pixel << 4; -} - -u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, - int mode_clock, - int mode_hdisplay) -{ - u8 min_slice_count, i; - int max_slice_width; - - if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE) - min_slice_count = DIV_ROUND_UP(mode_clock, - DP_DSC_MAX_ENC_THROUGHPUT_0); - else - min_slice_count = DIV_ROUND_UP(mode_clock, - DP_DSC_MAX_ENC_THROUGHPUT_1); - - max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd); - if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) { - DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n", - max_slice_width); - return 0; - } - /* Also take into account max slice width */ - min_slice_count = min_t(u8, min_slice_count, - DIV_ROUND_UP(mode_hdisplay, - max_slice_width)); - - /* Find the closest match to the valid slice count values */ - for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) { - if (valid_dsc_slicecount[i] > - drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, - false)) - break; - if (min_slice_count <= valid_dsc_slicecount[i]) - return valid_dsc_slicecount[i]; - } - - DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count); - return 0; -} - static void intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index 657bbb1f5ed0..00981fb9414b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -102,10 +102,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp); bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp); bool intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status); -u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count, - int mode_clock, int mode_hdisplay); -u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock, - int mode_hdisplay); bool intel_dp_read_dpcd(struct intel_dp *intel_dp); bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp); @@ -118,4 +114,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count) return ~((1 << lane_count) - 1) & 0xf; } +u32 intel_dp_mode_to_fec_clock(u32 mode_clock); + #endif /* __INTEL_DP_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 6df240a01b8c..600873c796d0 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, adjusted_mode->crtc_clock, crtc_state->port_clock, &crtc_state->dp_m_n, - constant_n); + constant_n, crtc_state->fec_enable); crtc_state->dp_m_n.tu = slots; return 0; @@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum intel_encoder->type = INTEL_OUTPUT_DP_MST; intel_encoder->power_domain = intel_dig_port->base.power_domain; intel_encoder->port = intel_dig_port->base.port; - intel_encoder->crtc_mask = BIT(pipe); + intel_encoder->crtc_mask = 0x7; intel_encoder->cloneable = 0; intel_encoder->compute_config = intel_dp_mst_compute_config; diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index dea63be1964f..cae25e493128 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -1528,6 +1528,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state, int src_x, src_w, src_h, crtc_w, crtc_h; const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode; + unsigned int stride = plane_state->color_plane[0].stride; unsigned int cpp = fb->format->cpp[0]; unsigned int width_bytes; int min_width, min_height; @@ -1569,9 +1570,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state, return -EINVAL; } - if (width_bytes > 4096 || fb->pitches[0] > 4096) { + if (stride > 4096) { DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n", - fb->pitches[0], 4096); + stride, 4096); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 261c9bd83f51..91051e178021 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -245,11 +245,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) wakeref = intel_runtime_pm_get(rpm); - srcu = intel_gt_reset_trylock(ggtt->vm.gt); - if (srcu < 0) { - ret = srcu; + ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu); + if (ret) goto err_rpm; - } ret = i915_mutex_lock_interruptible(dev); if (ret) @@ -318,7 +316,11 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) intel_wakeref_auto(&i915->ggtt.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); - i915_vma_set_ggtt_write(vma); + if (write) { + GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); + i915_vma_set_ggtt_write(vma); + obj->mm.dirty = true; + } err_fence: i915_vma_unpin_fence(vma); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 92e53c25424c..ad2a63dbcac2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -241,9 +241,6 @@ void i915_gem_resume(struct drm_i915_private *i915) mutex_lock(&i915->drm.struct_mutex); intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL); - i915_gem_restore_gtt_mappings(i915); - i915_gem_restore_fences(i915); - if (i915_gem_init_hw(i915)) goto err_wedged; diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index d3c6993f4f46..22aab8593abf 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -136,6 +136,20 @@ execlists_active(const struct intel_engine_execlists *execlists) return READ_ONCE(*execlists->active); } +static inline void +execlists_active_lock_bh(struct intel_engine_execlists *execlists) +{ + local_bh_disable(); /* prevent local softirq and lock recursion */ + tasklet_lock(&execlists->tasklet); +} + +static inline void +execlists_active_unlock_bh(struct intel_engine_execlists *execlists) +{ + tasklet_unlock(&execlists->tasklet); + local_bh_enable(); /* restore softirq, and kick ksoftirqd! */ +} + struct i915_request * execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 82630db0394b..4ce8626b140e 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1197,9 +1197,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, struct drm_printer *m) { struct drm_i915_private *dev_priv = engine->i915; - const struct intel_engine_execlists * const execlists = - &engine->execlists; - unsigned long flags; + struct intel_engine_execlists * const execlists = &engine->execlists; u64 addr; if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7)) @@ -1281,7 +1279,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, idx, hws[idx * 2], hws[idx * 2 + 1]); } - spin_lock_irqsave(&engine->active.lock, flags); + execlists_active_lock_bh(execlists); for (port = execlists->active; (rq = *port); port++) { char hdr[80]; int len; @@ -1309,7 +1307,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, hwsp_seqno(rq)); print_request(m, rq, hdr); } - spin_unlock_irqrestore(&engine->active.lock, flags); + execlists_active_unlock_bh(execlists); } else if (INTEL_GEN(dev_priv) > 6) { drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n", ENGINE_READ(engine, RING_PP_DIR_BASE)); @@ -1440,8 +1438,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) if (!intel_engine_supports_stats(engine)) return -ENODEV; - spin_lock_irqsave(&engine->active.lock, flags); - write_seqlock(&engine->stats.lock); + execlists_active_lock_bh(execlists); + write_seqlock_irqsave(&engine->stats.lock, flags); if (unlikely(engine->stats.enabled == ~0)) { err = -EBUSY; @@ -1469,8 +1467,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) } unlock: - write_sequnlock(&engine->stats.lock); - spin_unlock_irqrestore(&engine->active.lock, flags); + write_sequnlock_irqrestore(&engine->stats.lock, flags); + execlists_active_unlock_bh(execlists); return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index d42584439f51..bdfcc7bdadbf 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -631,7 +631,6 @@ execlists_schedule_out(struct i915_request *rq) struct intel_engine_cs *cur, *old; trace_i915_request_out(rq); - GEM_BUG_ON(intel_context_inflight(ce) != rq->engine); old = READ_ONCE(ce->inflight); do @@ -797,6 +796,17 @@ static bool can_merge_rq(const struct i915_request *prev, GEM_BUG_ON(prev == next); GEM_BUG_ON(!assert_priority_queue(prev, next)); + /* + * We do not submit known completed requests. Therefore if the next + * request is already completed, we can pretend to merge it in + * with the previous context (and we will skip updating the ELSP + * and tracking). Thus hopefully keeping the ELSP full with active + * contexts, despite the best efforts of preempt-to-busy to confuse + * us. + */ + if (i915_request_completed(next)) + return true; + if (!can_merge_ctx(prev->hw_context, next->hw_context)) return false; @@ -893,7 +903,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve, static struct i915_request * last_active(const struct intel_engine_execlists *execlists) { - struct i915_request * const *last = execlists->active; + struct i915_request * const *last = READ_ONCE(execlists->active); while (*last && i915_request_completed(*last)) last++; @@ -1172,21 +1182,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) continue; } - if (i915_request_completed(rq)) { - ve->request = NULL; - ve->base.execlists.queue_priority_hint = INT_MIN; - rb_erase_cached(rb, &execlists->virtual); - RB_CLEAR_NODE(rb); - - rq->engine = engine; - __i915_request_submit(rq); - - spin_unlock(&ve->base.active.lock); - - rb = rb_first_cached(&execlists->virtual); - continue; - } - if (last && !can_merge_rq(last, rq)) { spin_unlock(&ve->base.active.lock); return; /* leave this for another */ @@ -1237,11 +1232,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine) GEM_BUG_ON(ve->siblings[0] != engine); } - __i915_request_submit(rq); - if (!i915_request_completed(rq)) { + if (__i915_request_submit(rq)) { submit = true; last = rq; } + + /* + * Hmm, we have a bunch of virtual engine requests, + * but the first one was already completed (thanks + * preempt-to-busy!). Keep looking at the veng queue + * until we have no more relevant requests (i.e. + * the normal submit queue has higher priority). + */ + if (!submit) { + spin_unlock(&ve->base.active.lock); + rb = rb_first_cached(&execlists->virtual); + continue; + } } spin_unlock(&ve->base.active.lock); @@ -1254,8 +1261,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) int i; priolist_for_each_request_consume(rq, rn, p, i) { - if (i915_request_completed(rq)) - goto skip; + bool merge = true; /* * Can we combine this request with the current port? @@ -1296,14 +1302,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine) ctx_single_port_submission(rq->hw_context)) goto done; - *port = execlists_schedule_in(last, port - execlists->pending); - port++; + merge = false; } - last = rq; - submit = true; -skip: - __i915_request_submit(rq); + if (__i915_request_submit(rq)) { + if (!merge) { + *port = execlists_schedule_in(last, port - execlists->pending); + port++; + last = NULL; + } + + GEM_BUG_ON(last && + !can_merge_ctx(last->hw_context, + rq->hw_context)); + + submit = true; + last = rq; + } } rb_erase_cached(&p->node, &execlists->queue); @@ -1593,8 +1608,11 @@ static void process_csb(struct intel_engine_cs *engine) static void __execlists_submission_tasklet(struct intel_engine_cs *const engine) { lockdep_assert_held(&engine->active.lock); - if (!engine->execlists.pending[0]) + if (!engine->execlists.pending[0]) { + rcu_read_lock(); /* protect peeking at execlists->active */ execlists_dequeue(engine); + rcu_read_unlock(); + } } /* @@ -2399,10 +2417,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine) static struct i915_request *active_request(struct i915_request *rq) { - const struct list_head * const list = &rq->timeline->requests; const struct intel_context * const ce = rq->hw_context; struct i915_request *active = NULL; + struct list_head *list; + + if (!i915_request_is_active(rq)) /* unwound, but incomplete! */ + return rq; + list = &rq->timeline->requests; list_for_each_entry_from_reverse(rq, list, link) { if (i915_request_completed(rq)) break; @@ -2565,7 +2587,6 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) int i; priolist_for_each_request_consume(rq, rn, p, i) { - list_del_init(&rq->sched.link); __i915_request_submit(rq); dma_fence_set_error(&rq->fence, -EIO); i915_request_mark_complete(rq); @@ -3631,18 +3652,22 @@ static void virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal) { struct virtual_engine *ve = to_virtual_engine(rq->engine); + intel_engine_mask_t allowed, exec; struct ve_bond *bond; + allowed = ~to_request(signal)->engine->mask; + bond = virtual_find_bond(ve, to_request(signal)->engine); - if (bond) { - intel_engine_mask_t old, new, cmp; + if (bond) + allowed &= bond->sibling_mask; - cmp = READ_ONCE(rq->execution_mask); - do { - old = cmp; - new = cmp & bond->sibling_mask; - } while ((cmp = cmpxchg(&rq->execution_mask, old, new)) != old); - } + /* Restrict the bonded request to run on only the available engines */ + exec = READ_ONCE(rq->execution_mask); + while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed)) + ; + + /* Prevent the master from being re-run on the bonded engines */ + to_request(signal)->execution_mask &= ~allowed; } struct intel_context * diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index b9d84d52e986..8cea42379dd7 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -42,11 +42,10 @@ static void engine_skip_context(struct i915_request *rq) struct intel_engine_cs *engine = rq->engine; struct i915_gem_context *hung_ctx = rq->gem_context; - lockdep_assert_held(&engine->active.lock); - if (!i915_request_is_active(rq)) return; + lockdep_assert_held(&engine->active.lock); list_for_each_entry_continue(rq, &engine->active.requests, sched.link) if (rq->gem_context == hung_ctx) i915_request_skip(rq, -EIO); @@ -123,7 +122,6 @@ void __i915_request_reset(struct i915_request *rq, bool guilty) rq->fence.seqno, yesno(guilty)); - lockdep_assert_held(&rq->engine->active.lock); GEM_BUG_ON(i915_request_completed(rq)); if (guilty) { @@ -1214,10 +1212,8 @@ out: intel_runtime_pm_put(>->i915->runtime_pm, wakeref); } -int intel_gt_reset_trylock(struct intel_gt *gt) +int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu) { - int srcu; - might_lock(>->reset.backoff_srcu); might_sleep(); @@ -1232,10 +1228,10 @@ int intel_gt_reset_trylock(struct intel_gt *gt) rcu_read_lock(); } - srcu = srcu_read_lock(>->reset.backoff_srcu); + *srcu = srcu_read_lock(>->reset.backoff_srcu); rcu_read_unlock(); - return srcu; + return 0; } void intel_gt_reset_unlock(struct intel_gt *gt, int tag) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index 37a987b17108..52c00199e069 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -38,7 +38,7 @@ int intel_engine_reset(struct intel_engine_cs *engine, void __i915_request_reset(struct i915_request *rq, bool guilty); -int __must_check intel_gt_reset_trylock(struct intel_gt *gt); +int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu); void intel_gt_reset_unlock(struct intel_gt *gt, int tag); void intel_gt_set_wedged(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c index 601c16239fdf..bacaa7bb8c9a 100644 --- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c @@ -1573,7 +1573,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) struct intel_engine_cs *engine = rq->engine; enum intel_engine_id id; const int num_engines = - IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0; + IS_HASWELL(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0; bool force_restore = false; int len; u32 *cs; diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 45481eb1fa3c..5f6ec2fd29a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1063,6 +1063,9 @@ static void gen9_whitelist_build(struct i915_wa_list *w) /* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */ whitelist_reg(w, GEN8_HDC_CHICKEN1); + + /* WaSendPushConstantsFromMMIO:skl,bxt */ + whitelist_reg(w, COMMON_SLICE_CHICKEN2); } static void skl_whitelist_build(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 020696726f9e..bb6f86c7067a 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1924,6 +1924,11 @@ static int i915_drm_resume(struct drm_device *dev) if (ret) DRM_ERROR("failed to re-enable GGTT\n"); + mutex_lock(&dev_priv->drm.struct_mutex); + i915_gem_restore_gtt_mappings(dev_priv); + i915_gem_restore_fences(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); + intel_csr_ucode_resume(dev_priv); i915_restore_state(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h index 167a7b56ed5b..6795f1daa3d5 100644 --- a/drivers/gpu/drm/i915/i915_gem.h +++ b/drivers/gpu/drm/i915/i915_gem.h @@ -77,6 +77,12 @@ struct drm_i915_private; #define I915_GEM_IDLE_TIMEOUT (HZ / 5) +static inline void tasklet_lock(struct tasklet_struct *t) +{ + while (!tasklet_trylock(t)) + cpu_relax(); +} + static inline void __tasklet_disable_sync_once(struct tasklet_struct *t) { if (!atomic_fetch_inc(&t->count)) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index a53777dd371c..1c5506822dc7 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -194,6 +194,27 @@ static void free_capture_list(struct i915_request *request) } } +static void remove_from_engine(struct i915_request *rq) +{ + struct intel_engine_cs *engine, *locked; + + /* + * Virtual engines complicate acquiring the engine timeline lock, + * as their rq->engine pointer is not stable until under that + * engine lock. The simple ploy we use is to take the lock then + * check that the rq still belongs to the newly locked engine. + */ + locked = READ_ONCE(rq->engine); + spin_lock(&locked->active.lock); + while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) { + spin_unlock(&locked->active.lock); + spin_lock(&engine->active.lock); + locked = engine; + } + list_del(&rq->sched.link); + spin_unlock(&locked->active.lock); +} + static bool i915_request_retire(struct i915_request *rq) { struct i915_active_request *active, *next; @@ -259,9 +280,7 @@ static bool i915_request_retire(struct i915_request *rq) * request that we have removed from the HW and put back on a run * queue. */ - spin_lock(&rq->engine->active.lock); - list_del(&rq->sched.link); - spin_unlock(&rq->engine->active.lock); + remove_from_engine(rq); spin_lock(&rq->lock); i915_request_mark_complete(rq); @@ -358,9 +377,10 @@ __i915_request_await_execution(struct i915_request *rq, return 0; } -void __i915_request_submit(struct i915_request *request) +bool __i915_request_submit(struct i915_request *request) { struct intel_engine_cs *engine = request->engine; + bool result = false; GEM_TRACE("%s fence %llx:%lld, current %d\n", engine->name, @@ -370,6 +390,25 @@ void __i915_request_submit(struct i915_request *request) GEM_BUG_ON(!irqs_disabled()); lockdep_assert_held(&engine->active.lock); + /* + * With the advent of preempt-to-busy, we frequently encounter + * requests that we have unsubmitted from HW, but left running + * until the next ack and so have completed in the meantime. On + * resubmission of that completed request, we can skip + * updating the payload, and execlists can even skip submitting + * the request. + * + * We must remove the request from the caller's priority queue, + * and the caller must only call us when the request is in their + * priority queue, under the active.lock. This ensures that the + * request has *not* yet been retired and we can safely move + * the request into the engine->active.list where it will be + * dropped upon retiring. (Otherwise if resubmit a *retired* + * request, this would be a horrible use-after-free.) + */ + if (i915_request_completed(request)) + goto xfer; + if (i915_gem_context_is_banned(request->gem_context)) i915_request_skip(request, -EIO); @@ -393,13 +432,18 @@ void __i915_request_submit(struct i915_request *request) i915_sw_fence_signaled(&request->semaphore)) engine->saturated |= request->sched.semaphores; - /* We may be recursing from the signal callback of another i915 fence */ - spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); + engine->emit_fini_breadcrumb(request, + request->ring->vaddr + request->postfix); - list_move_tail(&request->sched.link, &engine->active.requests); + trace_i915_request_execute(request); + engine->serial++; + result = true; + +xfer: /* We may be recursing from the signal callback of another i915 fence */ + spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING); - GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)); - set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags); + if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) + list_move_tail(&request->sched.link, &engine->active.requests); if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) && @@ -410,12 +454,7 @@ void __i915_request_submit(struct i915_request *request) spin_unlock(&request->lock); - engine->emit_fini_breadcrumb(request, - request->ring->vaddr + request->postfix); - - engine->serial++; - - trace_i915_request_execute(request); + return result; } void i915_request_submit(struct i915_request *request) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 8ac6e1226a56..e4dd013761e8 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -292,7 +292,7 @@ int i915_request_await_execution(struct i915_request *rq, void i915_request_add(struct i915_request *rq); -void __i915_request_submit(struct i915_request *request); +bool __i915_request_submit(struct i915_request *request); void i915_request_submit(struct i915_request *request); void i915_request_skip(struct i915_request *request, int error); diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c index fa864d8f2b73..15f8bff141f9 100644 --- a/drivers/gpu/drm/i915/intel_pch.c +++ b/drivers/gpu/drm/i915/intel_pch.c @@ -69,6 +69,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv)); return PCH_CNP; case INTEL_PCH_CMP_DEVICE_ID_TYPE: + case INTEL_PCH_CMP2_DEVICE_ID_TYPE: DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n"); WARN_ON(!IS_COFFEELAKE(dev_priv)); /* CometPoint is CNP Compatible */ diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h index e6a2d65f19c6..c29c81ec7971 100644 --- a/drivers/gpu/drm/i915/intel_pch.h +++ b/drivers/gpu/drm/i915/intel_pch.h @@ -41,6 +41,7 @@ enum intel_pch { #define INTEL_PCH_CNP_DEVICE_ID_TYPE 0xA300 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE 0x9D80 #define INTEL_PCH_CMP_DEVICE_ID_TYPE 0x0280 +#define INTEL_PCH_CMP2_DEVICE_ID_TYPE 0x0680 #define INTEL_PCH_ICP_DEVICE_ID_TYPE 0x3480 #define INTEL_PCH_MCC_DEVICE_ID_TYPE 0x4B00 #define INTEL_PCH_MCC2_DEVICE_ID_TYPE 0x3880 diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index bb6dd54a6ff3..37593831b539 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -118,6 +118,12 @@ static void pm_resume(struct drm_i915_private *i915) with_intel_runtime_pm(&i915->runtime_pm, wakeref) { intel_gt_sanitize(&i915->gt, false); i915_gem_sanitize(i915); + + mutex_lock(&i915->drm.struct_mutex); + i915_gem_restore_gtt_mappings(i915); + i915_gem_restore_fences(i915); + mutex_unlock(&i915->drm.struct_mutex); + i915_gem_resume(i915); } } diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index e226324adb69..4bdd63b57100 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1083,7 +1083,7 @@ static const struct dss_features omap34xx_dss_feats = { static const struct dss_features omap3630_dss_feats = { .model = DSS_MODEL_OMAP3, - .fck_div_max = 32, + .fck_div_max = 31, .fck_freq_max = 173000000, .dss_fck_multiplier = 1, .parent_clk_name = "dpll4_ck", diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c index fc82a525b071..ee4379729a5b 100644 --- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c +++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c @@ -220,9 +220,17 @@ static const struct of_device_id lb035q02_of_match[] = { MODULE_DEVICE_TABLE(of, lb035q02_of_match); +static const struct spi_device_id lb035q02_ids[] = { + { "lb035q02", 0 }, + { /* sentinel */ } +}; + +MODULE_DEVICE_TABLE(spi, lb035q02_ids); + static struct spi_driver lb035q02_driver = { .probe = lb035q02_probe, .remove = lb035q02_remove, + .id_table = lb035q02_ids, .driver = { .name = "panel-lg-lb035q02", .of_match_table = lb035q02_of_match, @@ -231,7 +239,6 @@ static struct spi_driver lb035q02_driver = { module_spi_driver(lb035q02_driver); -MODULE_ALIAS("spi:lgphilips,lb035q02"); MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>"); MODULE_DESCRIPTION("LG.Philips LB035Q02 LCD Panel driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c index 299b217c83e1..20f17e46e65d 100644 --- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c +++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c @@ -230,9 +230,17 @@ static const struct of_device_id nl8048_of_match[] = { MODULE_DEVICE_TABLE(of, nl8048_of_match); +static const struct spi_device_id nl8048_ids[] = { + { "nl8048hl11", 0 }, + { /* sentinel */ } +}; + +MODULE_DEVICE_TABLE(spi, nl8048_ids); + static struct spi_driver nl8048_driver = { .probe = nl8048_probe, .remove = nl8048_remove, + .id_table = nl8048_ids, .driver = { .name = "panel-nec-nl8048hl11", .pm = &nl8048_pm_ops, @@ -242,7 +250,6 @@ static struct spi_driver nl8048_driver = { module_spi_driver(nl8048_driver); -MODULE_ALIAS("spi:nec,nl8048hl11"); MODULE_AUTHOR("Erik Gilling <konkers@android.com>"); MODULE_DESCRIPTION("NEC-NL8048HL11 Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c index 305259b58767..3d5b9c4f68d9 100644 --- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c +++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c @@ -684,9 +684,17 @@ static const struct of_device_id acx565akm_of_match[] = { MODULE_DEVICE_TABLE(of, acx565akm_of_match); +static const struct spi_device_id acx565akm_ids[] = { + { "acx565akm", 0 }, + { /* sentinel */ } +}; + +MODULE_DEVICE_TABLE(spi, acx565akm_ids); + static struct spi_driver acx565akm_driver = { .probe = acx565akm_probe, .remove = acx565akm_remove, + .id_table = acx565akm_ids, .driver = { .name = "panel-sony-acx565akm", .of_match_table = acx565akm_of_match, @@ -695,7 +703,6 @@ static struct spi_driver acx565akm_driver = { module_spi_driver(acx565akm_driver); -MODULE_ALIAS("spi:sony,acx565akm"); MODULE_AUTHOR("Nokia Corporation"); MODULE_DESCRIPTION("Sony ACX565AKM LCD Panel Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c index d7b2e34626ef..f2baff827f50 100644 --- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c +++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c @@ -375,8 +375,7 @@ static const struct of_device_id td028ttec1_of_match[] = { MODULE_DEVICE_TABLE(of, td028ttec1_of_match); static const struct spi_device_id td028ttec1_ids[] = { - { "tpo,td028ttec1", 0}, - { "toppoly,td028ttec1", 0 }, + { "td028ttec1", 0 }, { /* sentinel */ } }; diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c index 84370562910f..ba163c779084 100644 --- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c +++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c @@ -491,9 +491,17 @@ static const struct of_device_id td043mtea1_of_match[] = { MODULE_DEVICE_TABLE(of, td043mtea1_of_match); +static const struct spi_device_id td043mtea1_ids[] = { + { "td043mtea1", 0 }, + { /* sentinel */ } +}; + +MODULE_DEVICE_TABLE(spi, td043mtea1_ids); + static struct spi_driver td043mtea1_driver = { .probe = td043mtea1_probe, .remove = td043mtea1_remove, + .id_table = td043mtea1_ids, .driver = { .name = "panel-tpo-td043mtea1", .pm = &td043mtea1_pm_ops, @@ -503,7 +511,6 @@ static struct spi_driver td043mtea1_driver = { module_spi_driver(td043mtea1_driver); -MODULE_ALIAS("spi:tpo,td043mtea1"); MODULE_AUTHOR("Gražvydas Ignotas <notasas@gmail.com>"); MODULE_DESCRIPTION("TPO TD043MTEA1 Panel Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c index ae07290bba6a..04efa78d70b6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c @@ -147,7 +147,7 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder, struct drm_device *dev = encoder->dev; struct drm_framebuffer *fb; - if (!conn_state->writeback_job || !conn_state->writeback_job->fb) + if (!conn_state->writeback_job) return 0; fb = conn_state->writeback_job->fb; @@ -221,7 +221,7 @@ void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc, unsigned int i; state = rcrtc->writeback.base.state; - if (!state || !state->writeback_job || !state->writeback_job->fb) + if (!state || !state->writeback_job) return; fb = state->writeback_job->fb; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c index 525dc1c0f1c1..530edb3b51cc 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c @@ -7,6 +7,7 @@ #include <linux/gpio.h> #include <linux/mod_devicetable.h> #include <linux/of_gpio.h> +#include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> #include <drm/drm_atomic_helper.h> diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c index 1ce4d7142b6e..bf720206727f 100644 --- a/drivers/gpu/drm/vc4/vc4_txp.c +++ b/drivers/gpu/drm/vc4/vc4_txp.c @@ -231,7 +231,7 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn, int i; conn_state = drm_atomic_get_new_connector_state(state, conn); - if (!conn_state->writeback_job || !conn_state->writeback_job->fb) + if (!conn_state->writeback_job) return 0; crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); @@ -271,8 +271,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn, u32 ctrl; int i; - if (WARN_ON(!conn_state->writeback_job || - !conn_state->writeback_job->fb)) + if (WARN_ON(!conn_state->writeback_job)) return; mode = &conn_state->crtc->state->adjusted_mode; diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index cc5b09b87ab0..79a28fc91521 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -314,60 +314,24 @@ static void mousevsc_on_receive(struct hv_device *device, static void mousevsc_on_channel_callback(void *context) { - const int packet_size = 0x100; - int ret; struct hv_device *device = context; - u32 bytes_recvd; - u64 req_id; struct vmpacket_descriptor *desc; - unsigned char *buffer; - int bufferlen = packet_size; - - buffer = kmalloc(bufferlen, GFP_ATOMIC); - if (!buffer) - return; - - do { - ret = vmbus_recvpacket_raw(device->channel, buffer, - bufferlen, &bytes_recvd, &req_id); - - switch (ret) { - case 0: - if (bytes_recvd <= 0) { - kfree(buffer); - return; - } - desc = (struct vmpacket_descriptor *)buffer; - - switch (desc->type) { - case VM_PKT_COMP: - break; - - case VM_PKT_DATA_INBAND: - mousevsc_on_receive(device, desc); - break; - - default: - pr_err("unhandled packet type %d, tid %llx len %d\n", - desc->type, req_id, bytes_recvd); - break; - } + foreach_vmbus_pkt(desc, device->channel) { + switch (desc->type) { + case VM_PKT_COMP: break; - case -ENOBUFS: - kfree(buffer); - /* Handle large packet */ - bufferlen = bytes_recvd; - buffer = kmalloc(bytes_recvd, GFP_ATOMIC); - - if (!buffer) - return; + case VM_PKT_DATA_INBAND: + mousevsc_on_receive(device, desc); + break; + default: + pr_err("Unhandled packet type %d, tid %llx len %d\n", + desc->type, desc->trans_id, desc->len8 * 8); break; } - } while (1); - + } } static int mousevsc_connect_to_vsp(struct hv_device *device) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 391f0b225c9a..53a60c81e220 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -912,6 +912,7 @@ static void vmbus_shutdown(struct device *child_device) drv->shutdown(dev); } +#ifdef CONFIG_PM_SLEEP /* * vmbus_suspend - Suspend a vmbus device */ @@ -949,6 +950,7 @@ static int vmbus_resume(struct device *child_device) return drv->resume(dev); } +#endif /* CONFIG_PM_SLEEP */ /* * vmbus_device_release - Final callback release of the vmbus child device @@ -1070,6 +1072,7 @@ msg_handled: vmbus_signal_eom(msg, message_type); } +#ifdef CONFIG_PM_SLEEP /* * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for * hibernation, because hv_sock connections can not persist across hibernation. @@ -1105,6 +1108,7 @@ static void vmbus_force_channel_rescinded(struct vmbus_channel *channel) vmbus_connection.work_queue, &ctx->work); } +#endif /* CONFIG_PM_SLEEP */ /* * Direct callback for channels using other deferred processing @@ -2125,6 +2129,7 @@ acpi_walk_err: return ret_val; } +#ifdef CONFIG_PM_SLEEP static int vmbus_bus_suspend(struct device *dev) { struct vmbus_channel *channel, *sc; @@ -2247,6 +2252,7 @@ static int vmbus_bus_resume(struct device *dev) return 0; } +#endif /* CONFIG_PM_SLEEP */ static const struct acpi_device_id vmbus_acpi_device_ids[] = { {"VMBUS", 0}, diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index da10e6ccb43c..5920c0085d35 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -4399,6 +4399,7 @@ error2: error1: port_modify.set_port_cap_mask = 0; port_modify.clr_port_cap_mask = IB_PORT_CM_SUP; + kfree(port); while (--i) { if (!rdma_cap_ib_cm(ib_device, i)) continue; @@ -4407,6 +4408,7 @@ error1: ib_modify_port(ib_device, port->port_num, 0, &port_modify); ib_unregister_mad_agent(port->mad_agent); cm_remove_port_fs(port); + kfree(port); } free: kfree(cm_dev); @@ -4460,6 +4462,7 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data) spin_unlock_irq(&cm.state_lock); ib_unregister_mad_agent(cur_mad_agent); cm_remove_port_fs(port); + kfree(port); } kfree(cm_dev); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 0e3cf3461999..d78f67623f24 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2396,9 +2396,10 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, conn_id->cm_id.iw = NULL; cma_exch(conn_id, RDMA_CM_DESTROYING); mutex_unlock(&conn_id->handler_mutex); + mutex_unlock(&listen_id->handler_mutex); cma_deref_id(conn_id); rdma_destroy_id(&conn_id->id); - goto out; + return ret; } mutex_unlock(&conn_id->handler_mutex); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 99c4a55545cf..2dd2cfe9b561 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1987,8 +1987,6 @@ static int iw_query_port(struct ib_device *device, if (!netdev) return -ENODEV; - dev_put(netdev); - port_attr->max_mtu = IB_MTU_4096; port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu); @@ -1996,19 +1994,22 @@ static int iw_query_port(struct ib_device *device, port_attr->state = IB_PORT_DOWN; port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; } else { - inetdev = in_dev_get(netdev); + rcu_read_lock(); + inetdev = __in_dev_get_rcu(netdev); if (inetdev && inetdev->ifa_list) { port_attr->state = IB_PORT_ACTIVE; port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; - in_dev_put(inetdev); } else { port_attr->state = IB_PORT_INIT; port_attr->phys_state = IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING; } + + rcu_read_unlock(); } + dev_put(netdev); err = device->ops.query_port(device, port_num, port_attr); if (err) return err; diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 7a7474000100..65b36548bc17 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1230,7 +1230,7 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh, msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; - goto err; + goto err_get; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, @@ -1787,10 +1787,6 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh, cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]); qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]); - ret = rdma_counter_unbind_qpn(device, port, qpn, cntn); - if (ret) - goto err_unbind; - if (fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) || @@ -1799,13 +1795,15 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh, goto err_fill; } + ret = rdma_counter_unbind_qpn(device, port, qpn, cntn); + if (ret) + goto err_fill; + nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_fill: - rdma_counter_bind_qpn(device, port, qpn, cntn); -err_unbind: nlmsg_free(msg); err: ib_device_put(device); diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index 1ab423b19f77..6eb6d2717ca5 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -426,7 +426,7 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) int ret; rdma_for_each_port (dev, i) { - is_ib = rdma_protocol_ib(dev, i++); + is_ib = rdma_protocol_ib(dev, i); if (is_ib) break; } diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index f67a30fda1ed..163ff7ba92b7 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -451,8 +451,10 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp) * that the hardware will not attempt to access the MR any more. */ if (!umem_odp->is_implicit_odp) { + mutex_lock(&umem_odp->umem_mutex); ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp), ib_umem_end(umem_odp)); + mutex_unlock(&umem_odp->umem_mutex); kvfree(umem_odp->dma_list); kvfree(umem_odp->page_list); } @@ -719,6 +721,8 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt, u64 addr; struct ib_device *dev = umem_odp->umem.ibdev; + lockdep_assert_held(&umem_odp->umem_mutex); + virt = max_t(u64, virt, ib_umem_start(umem_odp)); bound = min_t(u64, bound, ib_umem_end(umem_odp)); /* Note that during the run of this function, the @@ -726,7 +730,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt, * faults from completion. We might be racing with other * invalidations, so we must make sure we free each page only * once. */ - mutex_lock(&umem_odp->umem_mutex); for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) { idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift; if (umem_odp->page_list[idx]) { @@ -757,7 +760,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt, umem_odp->npages--; } } - mutex_unlock(&umem_odp->umem_mutex); } EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages); diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index a8b9548bd1a2..599340c1f0b8 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -242,10 +242,13 @@ static void set_ep_sin6_addrs(struct c4iw_ep *ep, } } -static int dump_qp(struct c4iw_qp *qp, struct c4iw_debugfs_data *qpd) +static int dump_qp(unsigned long id, struct c4iw_qp *qp, + struct c4iw_debugfs_data *qpd) { int space; int cc; + if (id != qp->wq.sq.qid) + return 0; space = qpd->bufsize - qpd->pos - 1; if (space == 0) @@ -350,7 +353,7 @@ static int qp_open(struct inode *inode, struct file *file) xa_lock_irq(&qpd->devp->qps); xa_for_each(&qpd->devp->qps, index, qp) - dump_qp(qp, qpd); + dump_qp(index, qp, qpd); xa_unlock_irq(&qpd->devp->qps); qpd->buf[qpd->pos++] = 0; diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index aa772ee0706f..35c284af574d 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -275,13 +275,17 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, struct sk_buff *skb, struct c4iw_wr_wait *wr_waitp) { int err; - struct fw_ri_tpte tpt; + struct fw_ri_tpte *tpt; u32 stag_idx; static atomic_t key; if (c4iw_fatal_error(rdev)) return -EIO; + tpt = kmalloc(sizeof(*tpt), GFP_KERNEL); + if (!tpt) + return -ENOMEM; + stag_state = stag_state > 0; stag_idx = (*stag) >> 8; @@ -291,6 +295,7 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, mutex_lock(&rdev->stats.lock); rdev->stats.stag.fail++; mutex_unlock(&rdev->stats.lock); + kfree(tpt); return -ENOMEM; } mutex_lock(&rdev->stats.lock); @@ -305,28 +310,28 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, /* write TPT entry */ if (reset_tpt_entry) - memset(&tpt, 0, sizeof(tpt)); + memset(tpt, 0, sizeof(*tpt)); else { - tpt.valid_to_pdid = cpu_to_be32(FW_RI_TPTE_VALID_F | + tpt->valid_to_pdid = cpu_to_be32(FW_RI_TPTE_VALID_F | FW_RI_TPTE_STAGKEY_V((*stag & FW_RI_TPTE_STAGKEY_M)) | FW_RI_TPTE_STAGSTATE_V(stag_state) | FW_RI_TPTE_STAGTYPE_V(type) | FW_RI_TPTE_PDID_V(pdid)); - tpt.locread_to_qpid = cpu_to_be32(FW_RI_TPTE_PERM_V(perm) | + tpt->locread_to_qpid = cpu_to_be32(FW_RI_TPTE_PERM_V(perm) | (bind_enabled ? FW_RI_TPTE_MWBINDEN_F : 0) | FW_RI_TPTE_ADDRTYPE_V((zbva ? FW_RI_ZERO_BASED_TO : FW_RI_VA_BASED_TO))| FW_RI_TPTE_PS_V(page_size)); - tpt.nosnoop_pbladdr = !pbl_size ? 0 : cpu_to_be32( + tpt->nosnoop_pbladdr = !pbl_size ? 0 : cpu_to_be32( FW_RI_TPTE_PBLADDR_V(PBL_OFF(rdev, pbl_addr)>>3)); - tpt.len_lo = cpu_to_be32((u32)(len & 0xffffffffUL)); - tpt.va_hi = cpu_to_be32((u32)(to >> 32)); - tpt.va_lo_fbo = cpu_to_be32((u32)(to & 0xffffffffUL)); - tpt.dca_mwbcnt_pstag = cpu_to_be32(0); - tpt.len_hi = cpu_to_be32((u32)(len >> 32)); + tpt->len_lo = cpu_to_be32((u32)(len & 0xffffffffUL)); + tpt->va_hi = cpu_to_be32((u32)(to >> 32)); + tpt->va_lo_fbo = cpu_to_be32((u32)(to & 0xffffffffUL)); + tpt->dca_mwbcnt_pstag = cpu_to_be32(0); + tpt->len_hi = cpu_to_be32((u32)(len >> 32)); } err = write_adapter_mem(rdev, stag_idx + (rdev->lldi.vr->stag.start >> 5), - sizeof(tpt), &tpt, skb, wr_waitp); + sizeof(*tpt), tpt, skb, wr_waitp); if (reset_tpt_entry) { c4iw_put_resource(&rdev->resource.tpt_table, stag_idx); @@ -334,6 +339,7 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry, rdev->stats.stag.cur -= 32; mutex_unlock(&rdev->stats.lock); } + kfree(tpt); return err; } diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index eb9368be28c1..bbcac539777a 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -2737,15 +2737,11 @@ int c4iw_create_srq(struct ib_srq *ib_srq, struct ib_srq_init_attr *attrs, if (CHELSIO_CHIP_VERSION(rhp->rdev.lldi.adapter_type) > CHELSIO_T6) srq->flags = T4_SRQ_LIMIT_SUPPORT; - ret = xa_insert_irq(&rhp->qps, srq->wq.qid, srq, GFP_KERNEL); - if (ret) - goto err_free_queue; - if (udata) { srq_key_mm = kmalloc(sizeof(*srq_key_mm), GFP_KERNEL); if (!srq_key_mm) { ret = -ENOMEM; - goto err_remove_handle; + goto err_free_queue; } srq_db_key_mm = kmalloc(sizeof(*srq_db_key_mm), GFP_KERNEL); if (!srq_db_key_mm) { @@ -2789,8 +2785,6 @@ err_free_srq_db_key_mm: kfree(srq_db_key_mm); err_free_srq_key_mm: kfree(srq_key_mm); -err_remove_handle: - xa_erase_irq(&rhp->qps, srq->wq.qid); err_free_queue: free_srq_queue(srq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx, srq->wr_waitp); @@ -2813,8 +2807,6 @@ void c4iw_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata) rhp = srq->rhp; pr_debug("%s id %d\n", __func__, srq->wq.qid); - - xa_erase_irq(&rhp->qps, srq->wq.qid); ucontext = rdma_udata_to_drv_context(udata, struct c4iw_ucontext, ibucontext); free_srq_queue(srq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx, diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 2395fd4233a7..2ed7bfd5feea 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1526,8 +1526,11 @@ int sdma_init(struct hfi1_devdata *dd, u8 port) } ret = rhashtable_init(tmp_sdma_rht, &sdma_rht_params); - if (ret < 0) + if (ret < 0) { + kfree(tmp_sdma_rht); goto bail; + } + dd->sdma_rht = tmp_sdma_rht; dd_dev_info(dd, "SDMA num_sdma: %u\n", dd->num_sdma); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 8056930bbe2c..cd9ee1664a69 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -2773,6 +2773,10 @@ int i40iw_register_rdma_device(struct i40iw_device *iwdev) return -ENOMEM; iwibdev = iwdev->iwibdev; rdma_set_device_sysfs_group(&iwibdev->ibdev, &i40iw_attr_group); + ret = ib_device_set_netdev(&iwibdev->ibdev, iwdev->netdev, 1); + if (ret) + goto error; + ret = ib_register_device(&iwibdev->ibdev, "i40iw%d"); if (ret) goto error; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 59022b744144..d609f4659afb 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1298,29 +1298,6 @@ static int devx_handle_mkey_create(struct mlx5_ib_dev *dev, return 0; } -static void devx_free_indirect_mkey(struct rcu_head *rcu) -{ - kfree(container_of(rcu, struct devx_obj, devx_mr.rcu)); -} - -/* This function to delete from the radix tree needs to be called before - * destroying the underlying mkey. Otherwise a race might occur in case that - * other thread will get the same mkey before this one will be deleted, - * in that case it will fail via inserting to the tree its own data. - * - * Note: - * An error in the destroy is not expected unless there is some other indirect - * mkey which points to this one. In a kernel cleanup flow it will be just - * destroyed in the iterative destruction call. In a user flow, in case - * the application didn't close in the expected order it's its own problem, - * the mkey won't be part of the tree, in both cases the kernel is safe. - */ -static void devx_cleanup_mkey(struct devx_obj *obj) -{ - xa_erase(&obj->ib_dev->mdev->priv.mkey_table, - mlx5_base_mkey(obj->devx_mr.mmkey.key)); -} - static void devx_cleanup_subscription(struct mlx5_ib_dev *dev, struct devx_event_subscription *sub) { @@ -1362,8 +1339,16 @@ static int devx_obj_cleanup(struct ib_uobject *uobject, int ret; dev = mlx5_udata_to_mdev(&attrs->driver_udata); - if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) - devx_cleanup_mkey(obj); + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { + /* + * The pagefault_single_data_segment() does commands against + * the mmkey, we must wait for that to stop before freeing the + * mkey, as another allocation could get the same mkey #. + */ + xa_erase(&obj->ib_dev->mdev->priv.mkey_table, + mlx5_base_mkey(obj->devx_mr.mmkey.key)); + synchronize_srcu(&dev->mr_srcu); + } if (obj->flags & DEVX_OBJ_FLAGS_DCT) ret = mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct); @@ -1382,12 +1367,6 @@ static int devx_obj_cleanup(struct ib_uobject *uobject, devx_cleanup_subscription(dev, sub_entry); mutex_unlock(&devx_event_table->event_xa_lock); - if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { - call_srcu(&dev->mr_srcu, &obj->devx_mr.rcu, - devx_free_indirect_mkey); - return ret; - } - kfree(obj); return ret; } @@ -1491,26 +1470,21 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( &obj_id); WARN_ON(obj->dinlen > MLX5_MAX_DESTROY_INBOX_SIZE_DW * sizeof(u32)); - if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { - err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out); - if (err) - goto obj_destroy; - } - err = uverbs_copy_to(attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_CMD_OUT, cmd_out, cmd_out_len); if (err) - goto err_copy; + goto obj_destroy; if (opcode == MLX5_CMD_OP_CREATE_GENERAL_OBJECT) obj_type = MLX5_GET(general_obj_in_cmd_hdr, cmd_in, obj_type); - obj->obj_id = get_enc_obj_id(opcode | obj_type << 16, obj_id); + if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) { + err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out); + if (err) + goto obj_destroy; + } return 0; -err_copy: - if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) - devx_cleanup_mkey(obj); obj_destroy: if (obj->flags & DEVX_OBJ_FLAGS_DCT) mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 2ceaef3ea3fb..1a98ee2e01c4 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -606,7 +606,7 @@ struct mlx5_ib_mr { struct mlx5_ib_dev *dev; u32 out[MLX5_ST_SZ_DW(create_mkey_out)]; struct mlx5_core_sig_ctx *sig; - int live; + unsigned int live; void *descs_alloc; int access_flags; /* Needed for rereg MR */ @@ -639,7 +639,6 @@ struct mlx5_ib_mw { struct mlx5_ib_devx_mr { struct mlx5_core_mkey mmkey; int ndescs; - struct rcu_head rcu; }; struct mlx5_ib_umr_context { diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 1eff031ef048..630599311586 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -84,32 +84,6 @@ static bool use_umr_mtt_update(struct mlx5_ib_mr *mr, u64 start, u64 length) length + (start & (MLX5_ADAPTER_PAGE_SIZE - 1)); } -static void update_odp_mr(struct mlx5_ib_mr *mr) -{ - if (is_odp_mr(mr)) { - /* - * This barrier prevents the compiler from moving the - * setting of umem->odp_data->private to point to our - * MR, before reg_umr finished, to ensure that the MR - * initialization have finished before starting to - * handle invalidations. - */ - smp_wmb(); - to_ib_umem_odp(mr->umem)->private = mr; - /* - * Make sure we will see the new - * umem->odp_data->private value in the invalidation - * routines, before we can get page faults on the - * MR. Page faults can happen once we put the MR in - * the tree, below this line. Without the barrier, - * there can be a fault handling and an invalidation - * before umem->odp_data->private == mr is visible to - * the invalidation handler. - */ - smp_wmb(); - } -} - static void reg_mr_callback(int status, struct mlx5_async_work *context) { struct mlx5_ib_mr *mr = @@ -1346,8 +1320,6 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mr->umem = umem; set_mr_fields(dev, mr, npages, length, access_flags); - update_odp_mr(mr); - if (use_umr) { int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE; @@ -1363,10 +1335,12 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, } } - if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { - mr->live = 1; + if (is_odp_mr(mr)) { + to_ib_umem_odp(mr->umem)->private = mr; atomic_set(&mr->num_pending_prefetch, 0); } + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) + smp_store_release(&mr->live, 1); return &mr->ibmr; error: @@ -1441,6 +1415,9 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (!mr->umem) return -EINVAL; + if (is_odp_mr(mr)) + return -EOPNOTSUPP; + if (flags & IB_MR_REREG_TRANS) { addr = virt_addr; len = length; @@ -1486,8 +1463,6 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, } mr->allocated_from_cache = 0; - if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) - mr->live = 1; } else { /* * Send a UMR WQE @@ -1516,7 +1491,6 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, set_mr_fields(dev, mr, npages, len, access_flags); - update_odp_mr(mr); return 0; err: @@ -1607,15 +1581,16 @@ static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) /* Prevent new page faults and * prefetch requests from succeeding */ - mr->live = 0; + WRITE_ONCE(mr->live, 0); + + /* Wait for all running page-fault handlers to finish. */ + synchronize_srcu(&dev->mr_srcu); /* dequeue pending prefetch requests for the mr */ if (atomic_read(&mr->num_pending_prefetch)) flush_workqueue(system_unbound_wq); WARN_ON(atomic_read(&mr->num_pending_prefetch)); - /* Wait for all running page-fault handlers to finish. */ - synchronize_srcu(&dev->mr_srcu); /* Destroy all page mappings */ if (!umem_odp->is_implicit_odp) mlx5_ib_invalidate_range(umem_odp, @@ -1987,14 +1962,25 @@ free: int mlx5_ib_dealloc_mw(struct ib_mw *mw) { + struct mlx5_ib_dev *dev = to_mdev(mw->device); struct mlx5_ib_mw *mmw = to_mmw(mw); int err; - err = mlx5_core_destroy_mkey((to_mdev(mw->device))->mdev, - &mmw->mmkey); - if (!err) - kfree(mmw); - return err; + if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { + xa_erase(&dev->mdev->priv.mkey_table, + mlx5_base_mkey(mmw->mmkey.key)); + /* + * pagefault_single_data_segment() may be accessing mmw under + * SRCU if the user bound an ODP MR to this MW. + */ + synchronize_srcu(&dev->mr_srcu); + } + + err = mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey); + if (err) + return err; + kfree(mmw); + return 0; } int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask, diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 2e9b43061797..3f9478d19376 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -178,6 +178,29 @@ void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset, return; } + /* + * The locking here is pretty subtle. Ideally the implicit children + * list would be protected by the umem_mutex, however that is not + * possible. Instead this uses a weaker update-then-lock pattern: + * + * srcu_read_lock() + * <change children list> + * mutex_lock(umem_mutex) + * mlx5_ib_update_xlt() + * mutex_unlock(umem_mutex) + * destroy lkey + * + * ie any change the children list must be followed by the locked + * update_xlt before destroying. + * + * The umem_mutex provides the acquire/release semantic needed to make + * the children list visible to a racing thread. While SRCU is not + * technically required, using it gives consistent use of the SRCU + * locking around the children list. + */ + lockdep_assert_held(&to_ib_umem_odp(mr->umem)->umem_mutex); + lockdep_assert_held(&mr->dev->mr_srcu); + odp = odp_lookup(offset * MLX5_IMR_MTT_SIZE, nentries * MLX5_IMR_MTT_SIZE, mr); @@ -202,15 +225,22 @@ static void mr_leaf_free_action(struct work_struct *work) struct ib_umem_odp *odp = container_of(work, struct ib_umem_odp, work); int idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT; struct mlx5_ib_mr *mr = odp->private, *imr = mr->parent; + struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem); + int srcu_key; mr->parent = NULL; synchronize_srcu(&mr->dev->mr_srcu); - ib_umem_odp_release(odp); - if (imr->live) + if (smp_load_acquire(&imr->live)) { + srcu_key = srcu_read_lock(&mr->dev->mr_srcu); + mutex_lock(&odp_imr->umem_mutex); mlx5_ib_update_xlt(imr, idx, 1, 0, MLX5_IB_UPD_XLT_INDIRECT | MLX5_IB_UPD_XLT_ATOMIC); + mutex_unlock(&odp_imr->umem_mutex); + srcu_read_unlock(&mr->dev->mr_srcu, srcu_key); + } + ib_umem_odp_release(odp); mlx5_mr_cache_free(mr->dev, mr); if (atomic_dec_and_test(&imr->num_leaf_free)) @@ -278,7 +308,6 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start, idx - blk_start_idx + 1, 0, MLX5_IB_UPD_XLT_ZAP | MLX5_IB_UPD_XLT_ATOMIC); - mutex_unlock(&umem_odp->umem_mutex); /* * We are now sure that the device will not access the * memory. We can safely unmap it, and mark it as dirty if @@ -289,10 +318,12 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start, if (unlikely(!umem_odp->npages && mr->parent && !umem_odp->dying)) { - WRITE_ONCE(umem_odp->dying, 1); + WRITE_ONCE(mr->live, 0); + umem_odp->dying = 1; atomic_inc(&mr->parent->num_leaf_free); schedule_work(&umem_odp->work); } + mutex_unlock(&umem_odp->umem_mutex); } void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev) @@ -429,8 +460,6 @@ static struct mlx5_ib_mr *implicit_mr_alloc(struct ib_pd *pd, mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; - mr->live = 1; - mlx5_ib_dbg(dev, "key %x dev %p mr %p\n", mr->mmkey.key, dev->mdev, mr); @@ -484,6 +513,8 @@ next_mr: mtt->parent = mr; INIT_WORK(&odp->work, mr_leaf_free_action); + smp_store_release(&mtt->live, 1); + if (!nentries) start_idx = addr >> MLX5_IMR_MTT_SHIFT; nentries++; @@ -536,6 +567,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, init_waitqueue_head(&imr->q_leaf_free); atomic_set(&imr->num_leaf_free, 0); atomic_set(&imr->num_pending_prefetch, 0); + smp_store_release(&imr->live, 1); return imr; } @@ -555,15 +587,19 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) if (mr->parent != imr) continue; + mutex_lock(&umem_odp->umem_mutex); ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp), ib_umem_end(umem_odp)); - if (umem_odp->dying) + if (umem_odp->dying) { + mutex_unlock(&umem_odp->umem_mutex); continue; + } - WRITE_ONCE(umem_odp->dying, 1); + umem_odp->dying = 1; atomic_inc(&imr->num_leaf_free); schedule_work(&umem_odp->work); + mutex_unlock(&umem_odp->umem_mutex); } up_read(&per_mm->umem_rwsem); @@ -773,7 +809,7 @@ next_mr: switch (mmkey->type) { case MLX5_MKEY_MR: mr = container_of(mmkey, struct mlx5_ib_mr, mmkey); - if (!mr->live || !mr->ibmr.pd) { + if (!smp_load_acquire(&mr->live) || !mr->ibmr.pd) { mlx5_ib_dbg(dev, "got dead MR\n"); ret = -EFAULT; goto srcu_unlock; @@ -1641,12 +1677,12 @@ static bool num_pending_prefetch_inc(struct ib_pd *pd, mr = container_of(mmkey, struct mlx5_ib_mr, mmkey); - if (mr->ibmr.pd != pd) { + if (!smp_load_acquire(&mr->live)) { ret = false; break; } - if (!mr->live) { + if (mr->ibmr.pd != pd) { ret = false; break; } diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c index 6cac0c88cf39..36cdfbdbd325 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c @@ -230,8 +230,6 @@ static void pvrdma_free_srq(struct pvrdma_dev *dev, struct pvrdma_srq *srq) pvrdma_page_dir_cleanup(dev, &srq->pdir); - kfree(srq); - atomic_dec(&dev->num_srqs); } diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index 430314c8abd9..52d402f39df9 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -182,12 +182,19 @@ void siw_qp_llp_close(struct siw_qp *qp) */ void siw_qp_llp_write_space(struct sock *sk) { - struct siw_cep *cep = sk_to_cep(sk); + struct siw_cep *cep; - cep->sk_write_space(sk); + read_lock(&sk->sk_callback_lock); + + cep = sk_to_cep(sk); + if (cep) { + cep->sk_write_space(sk); - if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) - (void)siw_sq_start(cep->qp); + if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) + (void)siw_sq_start(cep->qp); + } + + read_unlock(&sk->sk_callback_lock); } static int siw_qp_readq_init(struct siw_qp *qp, int irq_size, int orq_size) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 684aa51684db..b00274caae4f 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -705,7 +705,7 @@ qca8k_setup(struct dsa_switch *ds) BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); /* Setup connection between CPU port & user ports */ - for (i = 0; i < DSA_MAX_PORTS; i++) { + for (i = 0; i < QCA8K_NUM_PORTS; i++) { /* CPU port gets connected to all user ports of the switch */ if (dsa_is_cpu_port(ds, i)) { qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT), @@ -1077,7 +1077,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev) if (id != QCA8K_ID_QCA8337) return -ENODEV; - priv->ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS); + priv->ds = dsa_switch_alloc(&mdiodev->dev, QCA8K_NUM_PORTS); if (!priv->ds) return -ENOMEM; diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index ca3d17e43ed8..ac88caca5ad4 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -339,10 +339,12 @@ int rtl8366_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { struct realtek_smi *smi = ds->priv; + u16 vid; int ret; - if (!smi->ops->is_vlan_valid(smi, port)) - return -EINVAL; + for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++) + if (!smi->ops->is_vlan_valid(smi, vid)) + return -EINVAL; dev_info(smi->dev, "prepare VLANs %04x..%04x\n", vlan->vid_begin, vlan->vid_end); @@ -370,8 +372,9 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, u16 vid; int ret; - if (!smi->ops->is_vlan_valid(smi, port)) - return; + for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++) + if (!smi->ops->is_vlan_valid(smi, vid)) + return; dev_info(smi->dev, "add VLAN on port %d, %s, %s\n", port, diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index a268085ffad2..f5cc8b0a7c74 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -507,7 +507,8 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) irq = of_irq_get(intc, 0); if (irq <= 0) { dev_err(smi->dev, "failed to get parent IRQ\n"); - return irq ? irq : -EINVAL; + ret = irq ? irq : -EINVAL; + goto out_put_node; } /* This clears the IRQ status register */ @@ -515,7 +516,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) &val); if (ret) { dev_err(smi->dev, "can't read interrupt status\n"); - return ret; + goto out_put_node; } /* Fetch IRQ edge information from the descriptor */ @@ -537,7 +538,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) val); if (ret) { dev_err(smi->dev, "could not configure IRQ polarity\n"); - return ret; + goto out_put_node; } ret = devm_request_threaded_irq(smi->dev, irq, NULL, @@ -545,7 +546,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) "RTL8366RB", smi); if (ret) { dev_err(smi->dev, "unable to request irq: %d\n", ret); - return ret; + goto out_put_node; } smi->irqdomain = irq_domain_add_linear(intc, RTL8366RB_NUM_INTERRUPT, @@ -553,12 +554,15 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) smi); if (!smi->irqdomain) { dev_err(smi->dev, "failed to create IRQ domain\n"); - return -EINVAL; + ret = -EINVAL; + goto out_put_node; } for (i = 0; i < smi->num_ports; i++) irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq); - return 0; +out_put_node: + of_node_put(intc); + return ret; } static int rtl8366rb_set_addr(struct realtek_smi *smi) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index b9def744bcb3..7687ddcae159 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1897,7 +1897,9 @@ static int sja1105_set_ageing_time(struct dsa_switch *ds, return sja1105_static_config_reload(priv); } -/* Caller must hold priv->tagger_data.meta_lock */ +/* Must be called only with priv->tagger_data.state bit + * SJA1105_HWTS_RX_EN cleared + */ static int sja1105_change_rxtstamping(struct sja1105_private *priv, bool on) { @@ -1954,16 +1956,17 @@ static int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, break; } - if (rx_on != priv->tagger_data.hwts_rx_en) { - spin_lock(&priv->tagger_data.meta_lock); + if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) { + clear_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); + rc = sja1105_change_rxtstamping(priv, rx_on); - spin_unlock(&priv->tagger_data.meta_lock); if (rc < 0) { dev_err(ds->dev, "Failed to change RX timestamping: %d\n", rc); - return -EFAULT; + return rc; } - priv->tagger_data.hwts_rx_en = rx_on; + if (rx_on) + set_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); } if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) @@ -1982,7 +1985,7 @@ static int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, config.tx_type = HWTSTAMP_TX_ON; else config.tx_type = HWTSTAMP_TX_OFF; - if (priv->tagger_data.hwts_rx_en) + if (test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; else config.rx_filter = HWTSTAMP_FILTER_NONE; @@ -2005,12 +2008,12 @@ static void sja1105_rxtstamp_work(struct work_struct *work) mutex_lock(&priv->ptp_lock); - now = priv->tstamp_cc.read(&priv->tstamp_cc); - while ((skb = skb_dequeue(&data->skb_rxtstamp_queue)) != NULL) { struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb); u64 ts; + now = priv->tstamp_cc.read(&priv->tstamp_cc); + *shwt = (struct skb_shared_hwtstamps) {0}; ts = SJA1105_SKB_CB(skb)->meta_tstamp; @@ -2031,7 +2034,7 @@ static bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, struct sja1105_private *priv = ds->priv; struct sja1105_tagger_data *data = &priv->tagger_data; - if (!data->hwts_rx_en) + if (!test_bit(SJA1105_HWTS_RX_EN, &data->state)) return false; /* We need to read the full PTP clock to reconstruct the Rx @@ -2201,6 +2204,7 @@ static int sja1105_probe(struct spi_device *spi) tagger_data = &priv->tagger_data; skb_queue_head_init(&tagger_data->skb_rxtstamp_queue); INIT_WORK(&tagger_data->rxtstamp_work, sja1105_rxtstamp_work); + spin_lock_init(&tagger_data->meta_lock); /* Connections between dsa_port and sja1105_port */ for (i = 0; i < SJA1105_NUM_PORTS; i++) { diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index 84dc603138cf..58dd37ecde17 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -409,7 +409,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv) rc = static_config_buf_prepare_for_upload(priv, config_buf, buf_len); if (rc < 0) { dev_err(dev, "Invalid config, cannot upload\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } /* Prevent PHY jabbering during switch reset by inhibiting * Tx on all ports and waiting for current packet to drain. @@ -418,7 +419,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv) rc = sja1105_inhibit_tx(priv, port_bitmap, true); if (rc < 0) { dev_err(dev, "Failed to inhibit Tx on ports\n"); - return -ENXIO; + rc = -ENXIO; + goto out; } /* Wait for an eventual egress packet to finish transmission * (reach IFG). It is guaranteed that a second one will not diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 7548247455d7..1b1a09095c0d 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -526,7 +526,7 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) struct device *dev = &ag->pdev->dev; struct net_device *ndev = ag->ndev; static struct mii_bus *mii_bus; - struct device_node *np; + struct device_node *np, *mnp; int err; np = dev->of_node; @@ -571,7 +571,9 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) msleep(200); } - err = of_mdiobus_register(mii_bus, np); + mnp = of_get_child_by_name(np, "mdio"); + err = of_mdiobus_register(mii_bus, mnp); + of_node_put(mnp); if (err) goto mdio_err_put_clk; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index 5b602243d573..a4dead4ab0ed 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -137,13 +137,12 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp, static int alloc_uld_rxqs(struct adapter *adap, struct sge_uld_rxq_info *rxq_info, bool lro) { - struct sge *s = &adap->sge; unsigned int nq = rxq_info->nrxq + rxq_info->nciq; + int i, err, msi_idx, que_idx = 0, bmap_idx = 0; struct sge_ofld_rxq *q = rxq_info->uldrxq; unsigned short *ids = rxq_info->rspq_id; - unsigned int bmap_idx = 0; + struct sge *s = &adap->sge; unsigned int per_chan; - int i, err, msi_idx, que_idx = 0; per_chan = rxq_info->nrxq / adap->params.nports; @@ -161,6 +160,10 @@ static int alloc_uld_rxqs(struct adapter *adap, if (msi_idx >= 0) { bmap_idx = get_msix_idx_from_bmap(adap); + if (bmap_idx < 0) { + err = -ENOSPC; + goto freeout; + } msi_idx = adap->msix_info_ulds[bmap_idx].idx; } err = t4_sge_alloc_rxq(adap, &q->rspq, false, diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 3e863a71c513..7df5d7d211d4 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -148,11 +148,15 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev, { u32 time_cnt; u32 reg_value; + int ret; regmap_write(mdio_dev->subctrl_vbase, cfg_reg, set_val); for (time_cnt = MDIO_TIMEOUT; time_cnt; time_cnt--) { - regmap_read(mdio_dev->subctrl_vbase, st_reg, ®_value); + ret = regmap_read(mdio_dev->subctrl_vbase, st_reg, ®_value); + if (ret) + return ret; + reg_value &= st_msk; if ((!!check_st) == (!!reg_value)) break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 9231b39d18b2..c501bf2a0252 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -112,17 +112,11 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 out[MLX5_ST_SZ_DW(destroy_mkey_out)] = {0}; u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {0}; struct xarray *mkeys = &dev->priv.mkey_table; - struct mlx5_core_mkey *deleted_mkey; unsigned long flags; xa_lock_irqsave(mkeys, flags); - deleted_mkey = __xa_erase(mkeys, mlx5_base_mkey(mkey->key)); + __xa_erase(mkeys, mlx5_base_mkey(mkey->key)); xa_unlock_irqrestore(mkeys, flags); - if (!deleted_mkey) { - mlx5_core_dbg(dev, "failed xarray delete of mkey 0x%x\n", - mlx5_base_mkey(mkey->key)); - return -ENOENT; - } MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY); MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index 913f1e5aaaf2..d7c7467e2d53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -137,7 +137,8 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool, icm_mr->icm_start_addr = icm_mr->dm.addr; - align_diff = icm_mr->icm_start_addr % align_base; + /* align_base is always a power of 2 */ + align_diff = icm_mr->icm_start_addr & (align_base - 1); if (align_diff) icm_mr->used_length = align_base - align_diff; diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index b063eb78fa0c..aac115136720 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -388,13 +388,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev) continue; phy = of_phy_find_device(phy_node); + of_node_put(phy_node); if (!phy) continue; err = ocelot_probe_port(ocelot, port, regs, phy); if (err) { of_node_put(portnp); - return err; + goto out_put_ports; } phy_mode = of_get_phy_mode(portnp); @@ -422,7 +423,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) "invalid phy mode for port%d, (Q)SGMII only\n", port); of_node_put(portnp); - return -EINVAL; + err = -EINVAL; + goto out_put_ports; } serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); @@ -435,7 +437,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) "missing SerDes phys for port%d\n", port); - goto err_probe_ports; + of_node_put(portnp); + goto out_put_ports; } ocelot->ports[port]->serdes = serdes; @@ -447,9 +450,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) dev_info(&pdev->dev, "Ocelot switch probed\n"); - return 0; - -err_probe_ports: +out_put_ports: + of_node_put(ports); return err; } diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig index bd0583e409df..d25b88f53de4 100644 --- a/drivers/net/ethernet/pensando/Kconfig +++ b/drivers/net/ethernet/pensando/Kconfig @@ -20,6 +20,7 @@ if NET_VENDOR_PENSANDO config IONIC tristate "Pensando Ethernet IONIC Support" depends on 64BIT && PCI + select NET_DEVLINK help This enables the support for the Pensando family of Ethernet adapters. More specific information on this driver can be diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 457444894d80..b4b8ba00ee01 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2787,6 +2787,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) netdev_err(qdev->ndev, "PCI mapping failed with error: %d\n", err); + dev_kfree_skb_irq(skb); ql_free_large_buffers(qdev); return -ENOMEM; } diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 55db7fbd43cc..f9e6744d8fd6 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -282,7 +282,6 @@ struct netsec_desc_ring { void *vaddr; u16 head, tail; u16 xdp_xmit; /* netsec_xdp_xmit packets */ - bool is_xdp; struct page_pool *page_pool; struct xdp_rxq_info xdp_rxq; spinlock_t lock; /* XDP tx queue locking */ @@ -634,8 +633,7 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv) unsigned int bytes; int cnt = 0; - if (dring->is_xdp) - spin_lock(&dring->lock); + spin_lock(&dring->lock); bytes = 0; entry = dring->vaddr + DESC_SZ * tail; @@ -682,8 +680,8 @@ next: entry = dring->vaddr + DESC_SZ * tail; cnt++; } - if (dring->is_xdp) - spin_unlock(&dring->lock); + + spin_unlock(&dring->lock); if (!cnt) return false; @@ -799,9 +797,6 @@ static void netsec_set_tx_de(struct netsec_priv *priv, de->data_buf_addr_lw = lower_32_bits(desc->dma_addr); de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len; de->attr = attr; - /* under spin_lock if using XDP */ - if (!dring->is_xdp) - dma_wmb(); dring->desc[idx] = *desc; if (desc->buf_type == TYPE_NETSEC_SKB) @@ -1123,12 +1118,10 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, u16 tso_seg_len = 0; int filled; - if (dring->is_xdp) - spin_lock_bh(&dring->lock); + spin_lock_bh(&dring->lock); filled = netsec_desc_used(dring); if (netsec_check_stop_tx(priv, filled)) { - if (dring->is_xdp) - spin_unlock_bh(&dring->lock); + spin_unlock_bh(&dring->lock); net_warn_ratelimited("%s %s Tx queue full\n", dev_name(priv->dev), ndev->name); return NETDEV_TX_BUSY; @@ -1161,8 +1154,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, tx_desc.dma_addr = dma_map_single(priv->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); if (dma_mapping_error(priv->dev, tx_desc.dma_addr)) { - if (dring->is_xdp) - spin_unlock_bh(&dring->lock); + spin_unlock_bh(&dring->lock); netif_err(priv, drv, priv->ndev, "%s: DMA mapping failed\n", __func__); ndev->stats.tx_dropped++; @@ -1177,8 +1169,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, netdev_sent_queue(priv->ndev, skb->len); netsec_set_tx_de(priv, dring, &tx_ctrl, &tx_desc, skb); - if (dring->is_xdp) - spin_unlock_bh(&dring->lock); + spin_unlock_bh(&dring->lock); netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */ return NETDEV_TX_OK; @@ -1262,7 +1253,6 @@ err: static void netsec_setup_tx_dring(struct netsec_priv *priv) { struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX]; - struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog); int i; for (i = 0; i < DESC_NUM; i++) { @@ -1275,12 +1265,6 @@ static void netsec_setup_tx_dring(struct netsec_priv *priv) */ de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD; } - - if (xdp_prog) - dring->is_xdp = true; - else - dring->is_xdp = false; - } static int netsec_setup_rx_dring(struct netsec_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 9b4b5f69fc02..2cb9c53f93b8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -401,8 +401,11 @@ static void dwmac4_set_filter(struct mac_device_info *hw, int numhashregs = (hw->multicast_filter_bins >> 5); int mcbitslog2 = hw->mcast_bits_log2; unsigned int value; + u32 mc_filter[8]; int i; + memset(mc_filter, 0, sizeof(mc_filter)); + value = readl(ioaddr + GMAC_PACKET_FILTER); value &= ~GMAC_PACKET_FILTER_HMC; value &= ~GMAC_PACKET_FILTER_HPF; @@ -416,16 +419,13 @@ static void dwmac4_set_filter(struct mac_device_info *hw, /* Pass all multi */ value |= GMAC_PACKET_FILTER_PM; /* Set all the bits of the HASH tab */ - for (i = 0; i < numhashregs; i++) - writel(0xffffffff, ioaddr + GMAC_HASH_TAB(i)); + memset(mc_filter, 0xff, sizeof(mc_filter)); } else if (!netdev_mc_empty(dev)) { struct netdev_hw_addr *ha; - u32 mc_filter[8]; /* Hash filter for multicast */ value |= GMAC_PACKET_FILTER_HMC; - memset(mc_filter, 0, sizeof(mc_filter)); netdev_for_each_mc_addr(ha, dev) { /* The upper n bits of the calculated CRC are used to * index the contents of the hash table. The number of @@ -440,10 +440,11 @@ static void dwmac4_set_filter(struct mac_device_info *hw, */ mc_filter[bit_nr >> 5] |= (1 << (bit_nr & 0x1f)); } - for (i = 0; i < numhashregs; i++) - writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i)); } + for (i = 0; i < numhashregs; i++) + writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i)); + value |= GMAC_PACKET_FILTER_HPF; /* Handle multiple unicast addresses */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 5923ca62d793..99037386080a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -84,7 +84,7 @@ #define XGMAC_TSIE BIT(12) #define XGMAC_LPIIE BIT(5) #define XGMAC_PMTIE BIT(4) -#define XGMAC_INT_DEFAULT_EN (XGMAC_LPIIE | XGMAC_PMTIE | XGMAC_TSIE) +#define XGMAC_INT_DEFAULT_EN (XGMAC_LPIIE | XGMAC_PMTIE) #define XGMAC_Qx_TX_FLOW_CTRL(x) (0x00000070 + (x) * 4) #define XGMAC_PT GENMASK(31, 16) #define XGMAC_PT_SHIFT 16 @@ -122,6 +122,7 @@ #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 #define XGMAC_HWFEAT_L3L4FNUM GENMASK(30, 27) +#define XGMAC_HWFEAT_HASHTBLSZ GENMASK(25, 24) #define XGMAC_HWFEAT_RSSEN BIT(20) #define XGMAC_HWFEAT_TSOEN BIT(18) #define XGMAC_HWFEAT_SPHEN BIT(17) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 2b277b2c586b..5031398e612c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -472,7 +472,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw, dwxgmac2_set_mchash(ioaddr, mc_filter, mcbitslog2); /* Handle multiple unicast addresses */ - if (netdev_uc_count(dev) > XGMAC_ADDR_MAX) { + if (netdev_uc_count(dev) > hw->unicast_filter_entries) { value |= XGMAC_FILTER_PR; } else { struct netdev_hw_addr *ha; @@ -523,8 +523,8 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw, struct stmmac_rss *cfg, u32 num_rxq) { void __iomem *ioaddr = hw->pcsr; + u32 value, *key; int i, ret; - u32 value; value = readl(ioaddr + XGMAC_RSS_CTRL); if (!cfg || !cfg->enable) { @@ -533,8 +533,9 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw, return 0; } - for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) { - ret = dwxgmac2_rss_write_reg(ioaddr, true, i, cfg->key[i]); + key = (u32 *)cfg->key; + for (i = 0; i < (ARRAY_SIZE(cfg->key) / sizeof(u32)); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, true, i, key[i]); if (ret) return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 53c4a40d8386..965cbe3e6f51 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -380,6 +380,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, /* MAC HW feature 1 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1); dma_cap->l3l4fnum = (hw_cap & XGMAC_HWFEAT_L3L4FNUM) >> 27; + dma_cap->hash_tb_sz = (hw_cap & XGMAC_HWFEAT_HASHTBLSZ) >> 24; dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20; dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18; dma_cap->sphen = (hw_cap & XGMAC_HWFEAT_SPHEN) >> 17; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3232738fb25..c76a1336a451 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -629,6 +629,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; snap_type_sel = PTP_TCR_SNAPTYPSEL_1; + ts_event_en = PTP_TCR_TSEVNTENA; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; ptp_over_ethernet = PTP_TCR_TSIPENA; @@ -4715,11 +4716,9 @@ int stmmac_suspend(struct device *dev) if (!ndev || !netif_running(ndev)) return 0; - mutex_lock(&priv->lock); + phylink_mac_change(priv->phylink, false); - rtnl_lock(); - phylink_stop(priv->phylink); - rtnl_unlock(); + mutex_lock(&priv->lock); netif_device_detach(ndev); stmmac_stop_all_queues(priv); @@ -4734,6 +4733,12 @@ int stmmac_suspend(struct device *dev) stmmac_pmt(priv, priv->hw, priv->wolopts); priv->irq_wake = 1; } else { + mutex_unlock(&priv->lock); + rtnl_lock(); + phylink_stop(priv->phylink); + rtnl_unlock(); + mutex_lock(&priv->lock); + stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); /* Disable clock in case of PWM is off */ @@ -4824,12 +4829,16 @@ int stmmac_resume(struct device *dev) stmmac_start_all_queues(priv); - rtnl_lock(); - phylink_start(priv->phylink); - rtnl_unlock(); - mutex_unlock(&priv->lock); + if (!device_may_wakeup(priv->device)) { + rtnl_lock(); + phylink_start(priv->phylink); + rtnl_unlock(); + } + + phylink_mac_change(priv->phylink, true); + return 0; } EXPORT_SYMBOL_GPL(stmmac_resume); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index 5f66f6161629..cc76a42c7466 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1564,10 +1564,6 @@ static int __stmmac_test_jumbo(struct stmmac_priv *priv, u16 queue) struct stmmac_packet_attrs attr = { }; int size = priv->dma_buf_sz; - /* Only XGMAC has SW support for multiple RX descs in same packet */ - if (priv->plat->has_xgmac) - size = priv->dev->max_mtu; - attr.dst = priv->dev->dev_addr; attr.max_size = size - ETH_FCS_LEN; attr.queue_mapping = queue; diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index ceddb424f887..0dd0ba915ab9 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -1137,10 +1137,11 @@ static void atusb_disconnect(struct usb_interface *interface) ieee802154_unregister_hw(atusb->hw); + usb_put_dev(atusb->usb_dev); + ieee802154_free_hw(atusb->hw); usb_set_intfdata(interface, NULL); - usb_put_dev(atusb->usb_dev); pr_debug("%s done\n", __func__); } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 11402dc347db..430c93786153 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -3145,12 +3145,12 @@ static int ca8210_probe(struct spi_device *spi_device) goto error; } + priv->spi->dev.platform_data = pdata; ret = ca8210_get_platform_data(priv->spi, pdata); if (ret) { dev_crit(&spi_device->dev, "ca8210_get_platform_data failed\n"); goto error; } - priv->spi->dev.platform_data = pdata; ret = ca8210_dev_com_init(priv); if (ret) { diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 17f2300e63ee..8dc04e2590b1 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -800,7 +800,7 @@ mcr20a_handle_rx_read_buf_complete(void *context) if (!skb) return; - memcpy(skb_put(skb, len), lp->rx_buf, len); + __skb_put_data(skb, lp->rx_buf, len); ieee802154_rx_irqsafe(lp->hw, skb, lp->rx_lqi[0]); print_hex_dump_debug("mcr20a rx: ", DUMP_PREFIX_OFFSET, 16, 1, diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 2aa7b2e60046..1eb5d4fb8925 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -15,6 +15,15 @@ #include <linux/of_gpio.h> #include <linux/gpio/consumer.h> +#define AT803X_SPECIFIC_STATUS 0x11 +#define AT803X_SS_SPEED_MASK (3 << 14) +#define AT803X_SS_SPEED_1000 (2 << 14) +#define AT803X_SS_SPEED_100 (1 << 14) +#define AT803X_SS_SPEED_10 (0 << 14) +#define AT803X_SS_DUPLEX BIT(13) +#define AT803X_SS_SPEED_DUPLEX_RESOLVED BIT(11) +#define AT803X_SS_MDIX BIT(6) + #define AT803X_INTR_ENABLE 0x12 #define AT803X_INTR_ENABLE_AUTONEG_ERR BIT(15) #define AT803X_INTR_ENABLE_SPEED_CHANGED BIT(14) @@ -357,6 +366,64 @@ static int at803x_aneg_done(struct phy_device *phydev) return aneg_done; } +static int at803x_read_status(struct phy_device *phydev) +{ + int ss, err, old_link = phydev->link; + + /* Update the link, but return if there was an error */ + err = genphy_update_link(phydev); + if (err) + return err; + + /* why bother the PHY if nothing can have changed */ + if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) + return 0; + + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + phydev->pause = 0; + phydev->asym_pause = 0; + + err = genphy_read_lpa(phydev); + if (err < 0) + return err; + + /* Read the AT8035 PHY-Specific Status register, which indicates the + * speed and duplex that the PHY is actually using, irrespective of + * whether we are in autoneg mode or not. + */ + ss = phy_read(phydev, AT803X_SPECIFIC_STATUS); + if (ss < 0) + return ss; + + if (ss & AT803X_SS_SPEED_DUPLEX_RESOLVED) { + switch (ss & AT803X_SS_SPEED_MASK) { + case AT803X_SS_SPEED_10: + phydev->speed = SPEED_10; + break; + case AT803X_SS_SPEED_100: + phydev->speed = SPEED_100; + break; + case AT803X_SS_SPEED_1000: + phydev->speed = SPEED_1000; + break; + } + if (ss & AT803X_SS_DUPLEX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + if (ss & AT803X_SS_MDIX) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + } + + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) + phy_resolve_aneg_pause(phydev); + + return 0; +} + static struct phy_driver at803x_driver[] = { { /* ATHEROS 8035 */ @@ -370,6 +437,7 @@ static struct phy_driver at803x_driver[] = { .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_GBIT_FEATURES */ + .read_status = at803x_read_status, .ack_interrupt = at803x_ack_interrupt, .config_intr = at803x_config_intr, }, { @@ -399,6 +467,7 @@ static struct phy_driver at803x_driver[] = { .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_GBIT_FEATURES */ + .read_status = at803x_read_status, .aneg_done = at803x_aneg_done, .ack_interrupt = &at803x_ack_interrupt, .config_intr = &at803x_config_intr, diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index e282600bd83e..c1d345c3cab3 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -121,7 +121,7 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value) return; if (mdiodev->reset_gpio) - gpiod_set_value(mdiodev->reset_gpio, value); + gpiod_set_value_cansleep(mdiodev->reset_gpio, value); if (mdiodev->reset_ctrl) { if (value) diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 369903d9b6ec..9412669b579c 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -283,6 +283,18 @@ void of_set_phy_eee_broken(struct phy_device *phydev) phydev->eee_broken_modes = broken; } +void phy_resolve_aneg_pause(struct phy_device *phydev) +{ + if (phydev->duplex == DUPLEX_FULL) { + phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + phydev->lp_advertising); + phydev->asym_pause = linkmode_test_bit( + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + phydev->lp_advertising); + } +} +EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause); + /** * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings * @phydev: The phy_device struct @@ -305,13 +317,7 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev) break; } - if (phydev->duplex == DUPLEX_FULL) { - phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->lp_advertising); - phydev->asym_pause = linkmode_test_bit( - ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->lp_advertising); - } + phy_resolve_aneg_pause(phydev); } EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 7c92afd36bbe..119e6f466056 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -457,6 +457,11 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) val); change_autoneg = true; break; + case MII_CTRL1000: + mii_ctrl1000_mod_linkmode_adv_t(phydev->advertising, + val); + change_autoneg = true; + break; default: /* do nothing */ break; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d347ddcac45b..9d2bbb13293e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1783,32 +1783,9 @@ done: } EXPORT_SYMBOL(genphy_update_link); -/** - * genphy_read_status - check the link status and update current link state - * @phydev: target phy_device struct - * - * Description: Check the link, then figure out the current state - * by comparing what we advertise with what the link partner - * advertises. Start by checking the gigabit possibilities, - * then move on to 10/100. - */ -int genphy_read_status(struct phy_device *phydev) +int genphy_read_lpa(struct phy_device *phydev) { - int lpa, lpagb, err, old_link = phydev->link; - - /* Update the link, but return if there was an error */ - err = genphy_update_link(phydev); - if (err) - return err; - - /* why bother the PHY if nothing can have changed */ - if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) - return 0; - - phydev->speed = SPEED_UNKNOWN; - phydev->duplex = DUPLEX_UNKNOWN; - phydev->pause = 0; - phydev->asym_pause = 0; + int lpa, lpagb; if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { if (phydev->is_gigabit_capable) { @@ -1838,6 +1815,44 @@ int genphy_read_status(struct phy_device *phydev) return lpa; mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa); + } + + return 0; +} +EXPORT_SYMBOL(genphy_read_lpa); + +/** + * genphy_read_status - check the link status and update current link state + * @phydev: target phy_device struct + * + * Description: Check the link, then figure out the current state + * by comparing what we advertise with what the link partner + * advertises. Start by checking the gigabit possibilities, + * then move on to 10/100. + */ +int genphy_read_status(struct phy_device *phydev) +{ + int err, old_link = phydev->link; + + /* Update the link, but return if there was an error */ + err = genphy_update_link(phydev); + if (err) + return err; + + /* why bother the PHY if nothing can have changed */ + if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) + return 0; + + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + phydev->pause = 0; + phydev->asym_pause = 0; + + err = genphy_read_lpa(phydev); + if (err < 0) + return err; + + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { phy_resolve_aneg_linkmode(phydev); } else if (phydev->autoneg == AUTONEG_DISABLE) { int bmcr = phy_read(phydev, MII_BMCR); diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 734de7de03f7..e1fabb3e3246 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -238,7 +238,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); - nf_reset(skb); + nf_reset_ct(skb); skb->ip_summed = CHECKSUM_NONE; ip_select_ident(net, skb, NULL); @@ -358,7 +358,7 @@ static int pptp_rcv(struct sk_buff *skb) po = lookup_chan(htons(header->call_id), iph->saddr); if (po) { skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); return sk_receive_skb(sk_pppox(po), skb, 0); } drop: diff --git a/drivers/net/tun.c b/drivers/net/tun.c index aab0be40d443..812dc3a65efb 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1104,7 +1104,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) */ skb_orphan(skb); - nf_reset(skb); + nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) goto drop; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index ce78714f536f..a505b2ab88b8 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2620,14 +2620,18 @@ static struct hso_device *hso_create_bulk_serial_device( */ if (serial->tiocmget) { tiocmget = serial->tiocmget; + tiocmget->endp = hso_get_ep(interface, + USB_ENDPOINT_XFER_INT, + USB_DIR_IN); + if (!tiocmget->endp) { + dev_err(&interface->dev, "Failed to find INT IN ep\n"); + goto exit; + } + tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL); if (tiocmget->urb) { mutex_init(&tiocmget->mutex); init_waitqueue_head(&tiocmget->waitq); - tiocmget->endp = hso_get_ep( - interface, - USB_ENDPOINT_XFER_INT, - USB_DIR_IN); } else hso_free_tiomget(serial); } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index b6dc5d714b5e..3d77cd402ba9 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1350,6 +1350,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1e2d, 0x0082, 4)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 5)}, /* Cinterion PHxx,PXxx (2 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0083, 4)}, /* Cinterion PHxx,PXxx (1 RmNet + USB Audio)*/ + {QMI_QUIRK_SET_DTR(0x1e2d, 0x00b0, 4)}, /* Cinterion CLS8 */ {QMI_FIXED_INTF(0x413c, 0x81a2, 8)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a3, 8)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 08726090570e..cee9fef925cd 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4799,10 +4799,9 @@ static int rtl8152_reset_resume(struct usb_interface *intf) struct r8152 *tp = usb_get_intfdata(intf); clear_bit(SELECTIVE_SUSPEND, &tp->flags); - mutex_lock(&tp->control); tp->rtl_ops.init(tp); queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0); - mutex_unlock(&tp->control); + set_ethernet_addr(tp); return rtl8152_resume(intf); } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ba98e0971b84..5a635f028bdc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1585,7 +1585,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) /* Don't wait up for transmitted skbs to be freed. */ if (!use_napi) { skb_orphan(skb); - nf_reset(skb); + nf_reset_ct(skb); } /* If running out of space, stop queue to avoid getting packets that we diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index a4b38a980c3c..ee52bde058df 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -366,7 +366,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, struct neighbour *neigh; int ret; - nf_reset(skb); + nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -459,7 +459,7 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, /* reset skb device */ if (likely(err == 1)) - nf_reset(skb); + nf_reset_ct(skb); else skb = NULL; @@ -560,7 +560,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s bool is_v6gw = false; int ret = -EINVAL; - nf_reset(skb); + nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { @@ -670,7 +670,7 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, /* reset skb device */ if (likely(err == 1)) - nf_reset(skb); + nf_reset_ct(skb); else skb = NULL; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 635956024e88..45c73a6f09a1 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1261,8 +1261,8 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw, skb_orphan(skb); skb_dst_drop(skb); skb->mark = 0; - secpath_reset(skb); - nf_reset(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); /* * Get absolute mactime here so all HWs RX at the "same time", and diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e14ec75b61d6..482c6c8b0fb7 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -887,9 +887,9 @@ static int xennet_set_skb_gso(struct sk_buff *skb, return 0; } -static RING_IDX xennet_fill_frags(struct netfront_queue *queue, - struct sk_buff *skb, - struct sk_buff_head *list) +static int xennet_fill_frags(struct netfront_queue *queue, + struct sk_buff *skb, + struct sk_buff_head *list) { RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb; @@ -908,7 +908,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { queue->rx.rsp_cons = ++cons + skb_queue_len(list); kfree_skb(nskb); - return ~0U; + return -ENOENT; } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, @@ -919,7 +919,9 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, kfree_skb(nskb); } - return cons; + queue->rx.rsp_cons = cons; + + return 0; } static int checksum_setup(struct net_device *dev, struct sk_buff *skb) @@ -1045,8 +1047,7 @@ err: skb->data_len = rx->status; skb->len += rx->status; - i = xennet_fill_frags(queue, skb, &tmpq); - if (unlikely(i == ~0U)) + if (unlikely(xennet_fill_frags(queue, skb, &tmpq))) goto err; if (rx->flags & XEN_NETRXF_csum_blank) @@ -1056,7 +1057,7 @@ err: __skb_queue_tail(&rxq, skb); - queue->rx.rsp_cons = ++i; + i = ++queue->rx.rsp_cons; work_done++; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 108f60b46804..fd7dea36c3b6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns) */ if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) return; - revalidate_disk(ns->disk); blk_set_queue_dying(ns->queue); /* Forcibly unquiesce queues to avoid blocking dispatch */ blk_mq_unquiesce_queue(ns->queue); + /* + * Revalidate after unblocking dispatchers that may be holding bd_butex + */ + revalidate_disk(ns->disk); } static void nvme_queue_scan(struct nvme_ctrl *ctrl) @@ -847,7 +850,7 @@ out: static int nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, void __user *ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, u32 *result, unsigned timeout) + u32 meta_seed, u64 *result, unsigned timeout) { bool write = nvme_is_write(cmd); struct nvme_ns *ns = q->queuedata; @@ -888,7 +891,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, else ret = nvme_req(req)->status; if (result) - *result = le32_to_cpu(nvme_req(req)->result.u32); + *result = le64_to_cpu(nvme_req(req)->result.u64); if (meta && !ret && !write) { if (copy_to_user(meta_buffer, meta, meta_len)) ret = -EFAULT; @@ -1335,6 +1338,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_command c; unsigned timeout = 0; u32 effects; + u64 result; + int status; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + if (copy_from_user(&cmd, ucmd, sizeof(cmd))) + return -EFAULT; + if (cmd.flags) + return -EINVAL; + + memset(&c, 0, sizeof(c)); + c.common.opcode = cmd.opcode; + c.common.flags = cmd.flags; + c.common.nsid = cpu_to_le32(cmd.nsid); + c.common.cdw2[0] = cpu_to_le32(cmd.cdw2); + c.common.cdw2[1] = cpu_to_le32(cmd.cdw3); + c.common.cdw10 = cpu_to_le32(cmd.cdw10); + c.common.cdw11 = cpu_to_le32(cmd.cdw11); + c.common.cdw12 = cpu_to_le32(cmd.cdw12); + c.common.cdw13 = cpu_to_le32(cmd.cdw13); + c.common.cdw14 = cpu_to_le32(cmd.cdw14); + c.common.cdw15 = cpu_to_le32(cmd.cdw15); + + if (cmd.timeout_ms) + timeout = msecs_to_jiffies(cmd.timeout_ms); + + effects = nvme_passthru_start(ctrl, ns, cmd.opcode); + status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, + (void __user *)(uintptr_t)cmd.addr, cmd.data_len, + (void __user *)(uintptr_t)cmd.metadata, + cmd.metadata_len, 0, &result, timeout); + nvme_passthru_end(ctrl, effects); + + if (status >= 0) { + if (put_user(result, &ucmd->result)) + return -EFAULT; + } + + return status; +} + +static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, + struct nvme_passthru_cmd64 __user *ucmd) +{ + struct nvme_passthru_cmd64 cmd; + struct nvme_command c; + unsigned timeout = 0; + u32 effects; int status; if (!capable(CAP_SYS_ADMIN)) @@ -1405,6 +1456,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx) srcu_read_unlock(&head->srcu, idx); } +static bool is_ctrl_ioctl(unsigned int cmd) +{ + if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD) + return true; + if (is_sed_ioctl(cmd)) + return true; + return false; +} + +static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, + void __user *argp, + struct nvme_ns_head *head, + int srcu_idx) +{ + struct nvme_ctrl *ctrl = ns->ctrl; + int ret; + + nvme_get_ctrl(ns->ctrl); + nvme_put_ns_from_disk(head, srcu_idx); + + switch (cmd) { + case NVME_IOCTL_ADMIN_CMD: + ret = nvme_user_cmd(ctrl, NULL, argp); + break; + case NVME_IOCTL_ADMIN64_CMD: + ret = nvme_user_cmd64(ctrl, NULL, argp); + break; + default: + ret = sed_ioctl(ctrl->opal_dev, cmd, argp); + break; + } + nvme_put_ctrl(ctrl); + return ret; +} + static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1422,20 +1508,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, * seperately and drop the ns SRCU reference early. This avoids a * deadlock when deleting namespaces using the passthrough interface. */ - if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) { - struct nvme_ctrl *ctrl = ns->ctrl; - - nvme_get_ctrl(ns->ctrl); - nvme_put_ns_from_disk(head, srcu_idx); - - if (cmd == NVME_IOCTL_ADMIN_CMD) - ret = nvme_user_cmd(ctrl, NULL, argp); - else - ret = sed_ioctl(ctrl->opal_dev, cmd, argp); - - nvme_put_ctrl(ctrl); - return ret; - } + if (is_ctrl_ioctl(cmd)) + return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx); switch (cmd) { case NVME_IOCTL_ID: @@ -1448,6 +1522,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, case NVME_IOCTL_SUBMIT_IO: ret = nvme_submit_io(ns, argp); break; + case NVME_IOCTL_IO64_CMD: + ret = nvme_user_cmd64(ns->ctrl, ns, argp); + break; default: if (ns->ndev) ret = nvme_nvm_ioctl(ns, cmd, arg); @@ -2289,6 +2366,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = { .vid = 0x14a4, .fr = "22301111", .quirks = NVME_QUIRK_SIMPLE_SUSPEND, + }, + { + /* + * This Kingston E8FK11.T firmware version has no interrupt + * after resume with actions related to suspend to idle + * https://bugzilla.kernel.org/show_bug.cgi?id=204887 + */ + .vid = 0x2646, + .fr = "E8FK11.T", + .quirks = NVME_QUIRK_SIMPLE_SUSPEND, } }; @@ -2540,8 +2627,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) list_add_tail(&subsys->entry, &nvme_subsystems); } - if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj, - dev_name(ctrl->device))) { + ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj, + dev_name(ctrl->device)); + if (ret) { dev_err(ctrl->device, "failed to create sysfs link from subsystem.\n"); goto out_put_subsystem; @@ -2838,6 +2926,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case NVME_IOCTL_ADMIN_CMD: return nvme_user_cmd(ctrl, NULL, argp); + case NVME_IOCTL_ADMIN64_CMD: + return nvme_user_cmd64(ctrl, NULL, argp); case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: @@ -3045,6 +3135,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); nvme_show_int_function(cntlid); nvme_show_int_function(numa_node); +nvme_show_int_function(queue_count); +nvme_show_int_function(sqsize); static ssize_t nvme_sysfs_delete(struct device *dev, struct device_attribute *attr, const char *buf, @@ -3125,6 +3217,8 @@ static struct attribute *nvme_dev_attrs[] = { &dev_attr_address.attr, &dev_attr_state.attr, &dev_attr_numa_node.attr, + &dev_attr_queue_count.attr, + &dev_attr_sqsize.attr, NULL }; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index b5013c101b35..38a83ef5bcd3 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -221,6 +221,7 @@ struct nvme_ctrl { u16 oacs; u16 nssa; u16 nr_streams; + u16 sqsize; u32 max_namespaces; atomic_t abort_limit; u8 vwc; @@ -269,7 +270,6 @@ struct nvme_ctrl { u16 hmmaxd; /* Fabrics only */ - u16 sqsize; u32 ioccsz; u32 iorcsz; u16 icdoff; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c0808f9eb8ab..bb88681f4dc3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2946,11 +2946,21 @@ static int nvme_suspend(struct device *dev) if (ret < 0) goto unfreeze; + /* + * A saved state prevents pci pm from generically controlling the + * device's power. If we're using protocol specific settings, we don't + * want pci interfering. + */ + pci_save_state(pdev); + ret = nvme_set_power_state(ctrl, ctrl->npss); if (ret < 0) goto unfreeze; if (ret) { + /* discard the saved state */ + pci_load_saved_state(pdev, NULL); + /* * Clearing npss forces a controller reset on resume. The * correct value will be resdicovered then. @@ -2958,14 +2968,7 @@ static int nvme_suspend(struct device *dev) nvme_dev_disable(ndev, true); ctrl->npss = 0; ret = 0; - goto unfreeze; } - /* - * A saved state prevents pci pm from generically controlling the - * device's power. If we're using protocol specific settings, we don't - * want pci interfering. - */ - pci_save_state(pdev); unfreeze: nvme_unfreeze(ctrl); return ret; @@ -3090,6 +3093,9 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_LIGHTNVM, }, { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index dfa07bb9dfeb..4d280160dd3f 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue) static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev) { return min_t(u32, NVME_RDMA_MAX_SEGMENTS, - ibdev->attrs.max_fast_reg_page_list_len); + ibdev->attrs.max_fast_reg_page_list_len - 1); } static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) @@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) const int cq_factor = send_wr_factor + 1; /* + RECV */ int comp_vector, idx = nvme_rdma_queue_idx(queue); enum ib_poll_context poll_ctx; - int ret; + int ret, pages_per_mr; queue->device = nvme_rdma_find_get_device(queue->cm_id); if (!queue->device) { @@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) goto out_destroy_qp; } + /* + * Currently we don't use SG_GAPS MR's so if the first entry is + * misaligned we'll end up using two entries for a single data page, + * so one additional entry is required. + */ + pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1; ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs, queue->queue_size, IB_MR_TYPE_MEM_REG, - nvme_rdma_get_max_fr_pages(ibdev), 0); + pages_per_mr, 0); if (ret) { dev_err(queue->ctrl->ctrl.device, "failed to initialize MR pool sized %d for QID %d\n", @@ -614,7 +620,8 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx) if (!ret) { set_bit(NVME_RDMA_Q_LIVE, &queue->flags); } else { - __nvme_rdma_stop_queue(queue); + if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) + __nvme_rdma_stop_queue(queue); dev_info(ctrl->ctrl.device, "failed to connect queue: %d ret=%d\n", idx, ret); } @@ -820,8 +827,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, if (error) goto out_stop_queue; - ctrl->ctrl.max_hw_sectors = - (ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9); + ctrl->ctrl.max_segments = ctrl->max_fr_pages; + ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9); blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 4ffd5957637a..385a5212c10f 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w) { struct nvme_tcp_queue *queue = container_of(w, struct nvme_tcp_queue, io_work); - unsigned long start = jiffies + msecs_to_jiffies(1); + unsigned long deadline = jiffies + msecs_to_jiffies(1); do { bool pending = false; @@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w) if (!pending) return; - } while (time_after(jiffies, start)); /* quota is exhausted */ + } while (!time_after(jiffies, deadline)); /* quota is exhausted */ queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); } diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index de0bff70ebb6..32008d85172b 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -11,10 +11,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) { const struct queue_limits *ql = &bdev_get_queue(bdev)->limits; - /* Number of physical blocks per logical block. */ - const u32 ppl = ql->physical_block_size / ql->logical_block_size; - /* Physical blocks per logical block, 0's based. */ - const __le16 ppl0b = to0based(ppl); + /* Number of logical blocks per physical block. */ + const u32 lpp = ql->physical_block_size / ql->logical_block_size; + /* Logical blocks per physical block, 0's based. */ + const __le16 lpp0b = to0based(lpp); /* * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN, @@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) * field from the identify controller data structure should be used. */ id->nsfeat |= 1 << 1; - id->nawun = ppl0b; - id->nawupf = ppl0b; - id->nacwu = ppl0b; + id->nawun = lpp0b; + id->nawupf = lpp0b; + id->nacwu = lpp0b; /* * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and @@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) */ id->nsfeat |= 1 << 4; /* NPWG = Namespace Preferred Write Granularity. 0's based */ - id->npwg = ppl0b; + id->npwg = lpp0b; /* NPWA = Namespace Preferred Write Alignment. 0's based */ id->npwa = id->npwg; /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index bf4f03474e89..d535080b781f 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -348,8 +348,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd) return 0; err: - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); return NVME_SC_INTERNAL; } @@ -554,8 +553,7 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) if (queue->nvme_sq.sqhd_disabled) { kfree(cmd->iov); - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); } return 1; @@ -586,8 +584,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd, return -EAGAIN; kfree(cmd->iov); - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); cmd->queue->snd_cmd = NULL; nvmet_tcp_put_cmd(cmd); return 1; @@ -1310,8 +1307,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd) nvmet_req_uninit(&cmd->req); nvmet_tcp_unmap_pdu_iovec(cmd); kfree(cmd->iov); - if (cmd->req.sg_cnt) - sgl_free(cmd->req.sg); + sgl_free(cmd->req.sg); } static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index c61f00b72e15..a577218d1ab7 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -507,6 +507,8 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base, ptp_qoriq->regs.etts_regs = base + ETTS_REGS_OFFSET; } + spin_lock_init(&ptp_qoriq->lock); + ktime_get_real_ts64(&now); ptp_qoriq_settime(&ptp_qoriq->caps, &now); @@ -514,7 +516,6 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base, (ptp_qoriq->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT | (ptp_qoriq->cksel & CKSEL_MASK) << CKSEL_SHIFT; - spin_lock_init(&ptp_qoriq->lock); spin_lock_irqsave(&ptp_qoriq->lock, flags); regs = &ptp_qoriq->regs; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index fc53e1e221f0..c94184d080f8 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1553,8 +1553,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device) if (rc == 0) { memcpy(&private->vsq, vsq, sizeof(*vsq)); } else { - dev_warn(&device->cdev->dev, - "Reading the volume storage information failed with rc=%d\n", rc); + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "Reading the volume storage information failed with rc=%d", rc); } if (useglobal) @@ -1737,8 +1737,8 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device) if (rc == 0) { dasd_eckd_cpy_ext_pool_data(device, lcq); } else { - dev_warn(&device->cdev->dev, - "Reading the logical configuration failed with rc=%d\n", rc); + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "Reading the logical configuration failed with rc=%d", rc); } dasd_sfree_request(cqr, cqr->memdev); @@ -2020,14 +2020,10 @@ dasd_eckd_check_characteristics(struct dasd_device *device) dasd_eckd_read_features(device); /* Read Volume Information */ - rc = dasd_eckd_read_vol_info(device); - if (rc) - goto out_err3; + dasd_eckd_read_vol_info(device); /* Read Extent Pool Information */ - rc = dasd_eckd_read_ext_pool_info(device); - if (rc) - goto out_err3; + dasd_eckd_read_ext_pool_info(device); /* Read Device Characteristics */ rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, @@ -2059,9 +2055,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device) if (readonly) set_bit(DASD_FLAG_DEVICE_RO, &device->flags); - if (dasd_eckd_is_ese(device)) - dasd_set_feature(device->cdev, DASD_FEATURE_DISCARD, 1); - dev_info(&device->cdev->dev, "New DASD %04X/%02X (CU %04X/%02X) " "with %d cylinders, %d heads, %d sectors%s\n", private->rdc_data.dev_type, @@ -3695,14 +3688,6 @@ static int dasd_eckd_release_space(struct dasd_device *device, return -EINVAL; } -static struct dasd_ccw_req * -dasd_eckd_build_cp_discard(struct dasd_device *device, struct dasd_block *block, - struct request *req, sector_t first_trk, - sector_t last_trk) -{ - return dasd_eckd_dso_ras(device, block, req, first_trk, last_trk, 1); -} - static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single( struct dasd_device *startdev, struct dasd_block *block, @@ -4447,10 +4432,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev, cmdwtd = private->features.feature[12] & 0x40; use_prefix = private->features.feature[8] & 0x01; - if (req_op(req) == REQ_OP_DISCARD) - return dasd_eckd_build_cp_discard(startdev, block, req, - first_trk, last_trk); - cqr = NULL; if (cdlspecial || dasd_page_cache) { /* do nothing, just fall through to the cmd mode single case */ @@ -4729,14 +4710,12 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base, struct dasd_block *block, struct request *req) { - struct dasd_device *startdev = NULL; struct dasd_eckd_private *private; - struct dasd_ccw_req *cqr; + struct dasd_device *startdev; unsigned long flags; + struct dasd_ccw_req *cqr; - /* Discard requests can only be processed on base devices */ - if (req_op(req) != REQ_OP_DISCARD) - startdev = dasd_alias_get_start_dev(base); + startdev = dasd_alias_get_start_dev(base); if (!startdev) startdev = base; private = startdev->private; @@ -5663,14 +5642,10 @@ static int dasd_eckd_restore_device(struct dasd_device *device) dasd_eckd_read_features(device); /* Read Volume Information */ - rc = dasd_eckd_read_vol_info(device); - if (rc) - goto out_err2; + dasd_eckd_read_vol_info(device); /* Read Extent Pool Information */ - rc = dasd_eckd_read_ext_pool_info(device); - if (rc) - goto out_err2; + dasd_eckd_read_ext_pool_info(device); /* Read Device Characteristics */ rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, @@ -6521,20 +6496,8 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block) unsigned int logical_block_size = block->bp_block; struct request_queue *q = block->request_queue; struct dasd_device *device = block->base; - struct dasd_eckd_private *private; - unsigned int max_discard_sectors; - unsigned int max_bytes; - unsigned int ext_bytes; /* Extent Size in Bytes */ - int recs_per_trk; - int trks_per_cyl; - int ext_limit; - int ext_size; /* Extent Size in Cylinders */ int max; - private = device->private; - trks_per_cyl = private->rdc_data.trk_per_cyl; - recs_per_trk = recs_per_track(&private->rdc_data, 0, logical_block_size); - if (device->features & DASD_FEATURE_USERAW) { /* * the max_blocks value for raw_track access is 256 @@ -6555,28 +6518,6 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block) /* With page sized segments each segment can be translated into one idaw/tidaw */ blk_queue_max_segment_size(q, PAGE_SIZE); blk_queue_segment_boundary(q, PAGE_SIZE - 1); - - if (dasd_eckd_is_ese(device)) { - /* - * Depending on the extent size, up to UINT_MAX bytes can be - * accepted. However, neither DASD_ECKD_RAS_EXTS_MAX nor the - * device limits should be exceeded. - */ - ext_size = dasd_eckd_ext_size(device); - ext_limit = min(private->real_cyl / ext_size, DASD_ECKD_RAS_EXTS_MAX); - ext_bytes = ext_size * trks_per_cyl * recs_per_trk * - logical_block_size; - max_bytes = UINT_MAX - (UINT_MAX % ext_bytes); - if (max_bytes / ext_bytes > ext_limit) - max_bytes = ext_bytes * ext_limit; - - max_discard_sectors = max_bytes / 512; - - blk_queue_max_discard_sectors(q, max_discard_sectors); - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - q->limits.discard_granularity = ext_bytes; - q->limits.discard_alignment = ext_bytes; - } } static struct ccw_driver dasd_eckd_driver = { diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index f4ca1d29d61b..cd164886132f 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -113,7 +113,7 @@ static void set_impl_params(struct qdio_irq *irq_ptr, irq_ptr->qib.pfmt = qib_param_field_format; if (qib_param_field) memcpy(irq_ptr->qib.parm, qib_param_field, - QDIO_MAX_BUFFERS_PER_Q); + sizeof(irq_ptr->qib.parm)); if (!input_slib_elements) goto output; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a7868c8133ee..dda274351c21 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4715,8 +4715,7 @@ static int qeth_qdio_establish(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "qdioest"); - qib_param_field = kzalloc(QDIO_MAX_BUFFERS_PER_Q, - GFP_KERNEL); + qib_param_field = kzalloc(FIELD_SIZEOF(struct qib, parm), GFP_KERNEL); if (!qib_param_field) { rc = -ENOMEM; goto out_free_nothing; diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index da00ca5fa5dc..401743e2b429 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -1923,6 +1923,7 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, struct fcoe_fcp_rsp_payload *fcp_rsp; struct bnx2fc_rport *tgt = io_req->tgt; struct scsi_cmnd *sc_cmd; + u16 scope = 0, qualifier = 0; /* scsi_cmd_cmpl is called with tgt lock held */ @@ -1990,12 +1991,30 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req, if (io_req->cdb_status == SAM_STAT_TASK_SET_FULL || io_req->cdb_status == SAM_STAT_BUSY) { - /* Set the jiffies + retry_delay_timer * 100ms - for the rport/tgt */ - tgt->retry_delay_timestamp = jiffies + - fcp_rsp->retry_delay_timer * HZ / 10; + /* Newer array firmware with BUSY or + * TASK_SET_FULL may return a status that needs + * the scope bits masked. + * Or a huge delay timestamp up to 27 minutes + * can result. + */ + if (fcp_rsp->retry_delay_timer) { + /* Upper 2 bits */ + scope = fcp_rsp->retry_delay_timer + & 0xC000; + /* Lower 14 bits */ + qualifier = fcp_rsp->retry_delay_timer + & 0x3FFF; + } + if (scope > 0 && qualifier > 0 && + qualifier <= 0x3FEF) { + /* Set the jiffies + + * retry_delay_timer * 100ms + * for the rport/tgt + */ + tgt->retry_delay_timestamp = jiffies + + (qualifier * HZ / 10); + } } - } if (io_req->fcp_resid) scsi_set_resid(sc_cmd, io_req->fcp_resid); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index d1513fdf1e00..0847e682797b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -3683,7 +3683,7 @@ void hisi_sas_debugfs_work_handler(struct work_struct *work) } EXPORT_SYMBOL_GPL(hisi_sas_debugfs_work_handler); -void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba) +static void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba) { struct device *dev = hisi_hba->dev; int i; @@ -3705,7 +3705,7 @@ void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba) devm_kfree(dev, hisi_hba->debugfs_port_reg[i]); } -int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba) +static int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba) { const struct hisi_sas_hw *hw = hisi_hba->hw; struct device *dev = hisi_hba->dev; @@ -3796,7 +3796,7 @@ fail: return -ENOMEM; } -void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba) +static void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba) { hisi_hba->debugfs_bist_dentry = debugfs_create_dir("bist", hisi_hba->debugfs_dir); diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 45a66048801b..ff6d4aa92421 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -4183,11 +4183,11 @@ megaraid_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) */ if (pdev->subsystem_vendor == PCI_VENDOR_ID_COMPAQ && pdev->subsystem_device == 0xC000) - return -ENODEV; + goto out_disable_device; /* Now check the magic signature byte */ pci_read_config_word(pdev, PCI_CONF_AMISIG, &magic); if (magic != HBA_SIGNATURE_471 && magic != HBA_SIGNATURE) - return -ENODEV; + goto out_disable_device; /* Ok it is probably a megaraid */ } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 1659d35cd37b..59ca98f12afd 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -596,7 +596,7 @@ static void qedf_dcbx_handler(void *dev, struct qed_dcbx_get *get, u32 mib_type) tmp_prio = get->operational.app_prio.fcoe; if (qedf_default_prio > -1) qedf->prio = qedf_default_prio; - else if (tmp_prio < 0 || tmp_prio > 7) { + else if (tmp_prio > 7) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, "FIP/FCoE prio %d out of range, setting to %d.\n", tmp_prio, QEDF_DEFAULT_PRIO); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 8190c2a27584..30bafd9d21e9 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2920,6 +2920,8 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) struct qla_hw_data *ha = vha->hw; uint16_t id = vha->vp_idx; + set_bit(VPORT_DELETE, &vha->dpc_flags); + while (test_bit(LOOP_RESYNC_ACTIVE, &vha->dpc_flags) || test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags)) msleep(1000); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 873a6aef1c5c..6ffa9877c28b 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -2396,6 +2396,7 @@ typedef struct fc_port { unsigned int query:1; unsigned int id_changed:1; unsigned int scan_needed:1; + unsigned int n2n_flag:1; struct completion nvme_del_done; uint32_t nvme_prli_service_param; @@ -2446,7 +2447,6 @@ typedef struct fc_port { uint8_t fc4_type; uint8_t fc4f_nvme; uint8_t scan_state; - uint8_t n2n_flag; unsigned long last_queue_full; unsigned long last_ramp_up; @@ -3036,6 +3036,7 @@ enum scan_flags_t { enum fc4type_t { FS_FC4TYPE_FCP = BIT_0, FS_FC4TYPE_NVME = BIT_1, + FS_FCP_IS_N2N = BIT_7, }; struct fab_scan_rp { @@ -4394,6 +4395,7 @@ typedef struct scsi_qla_host { #define IOCB_WORK_ACTIVE 31 #define SET_ZIO_THRESHOLD_NEEDED 32 #define ISP_ABORT_TO_ROM 33 +#define VPORT_DELETE 34 unsigned long pci_flags; #define PFLG_DISCONNECTED 0 /* PCI device removed */ diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index dc0e36676313..5298ed10059f 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3102,7 +3102,8 @@ int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id) { struct qla_work_evt *e; - if (test_bit(UNLOADING, &vha->dpc_flags)) + if (test_bit(UNLOADING, &vha->dpc_flags) || + (vha->vp_idx && test_bit(VPORT_DELETE, &vha->dpc_flags))) return 0; e = qla2x00_alloc_work(vha, QLA_EVT_GPNID); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 643d2324082e..1d041313ec52 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -746,12 +746,15 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, break; default: if ((id.b24 != fcport->d_id.b24 && - fcport->d_id.b24) || + fcport->d_id.b24 && + fcport->loop_id != FC_NO_LOOP_ID) || (fcport->loop_id != FC_NO_LOOP_ID && fcport->loop_id != loop_id)) { ql_dbg(ql_dbg_disc, vha, 0x20e3, "%s %d %8phC post del sess\n", __func__, __LINE__, fcport->port_name); + if (fcport->n2n_flag) + fcport->d_id.b24 = 0; qlt_schedule_sess_for_deletion(fcport); return; } @@ -759,6 +762,8 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, } fcport->loop_id = loop_id; + if (fcport->n2n_flag) + fcport->d_id.b24 = id.b24; wwn = wwn_to_u64(fcport->port_name); qlt_find_sess_invalidate_other(vha, wwn, @@ -972,7 +977,7 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res) wwn = wwn_to_u64(e->port_name); ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x20e8, - "%s %8phC %02x:%02x:%02x state %d/%d lid %x \n", + "%s %8phC %02x:%02x:%02x CLS %x/%x lid %x \n", __func__, (void *)&wwn, e->port_id[2], e->port_id[1], e->port_id[0], e->current_login_state, e->last_login_state, (loop_id & 0x7fff)); @@ -1499,7 +1504,8 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) (fcport->fw_login_state == DSC_LS_PRLI_PEND))) return 0; - if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) { + if (fcport->fw_login_state == DSC_LS_PLOGI_COMP && + !N2N_TOPO(vha->hw)) { if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline)) { set_bit(RELOGIN_NEEDED, &vha->dpc_flags); return 0; @@ -1570,8 +1576,9 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) qla24xx_post_gpdb_work(vha, fcport, 0); } else { ql_dbg(ql_dbg_disc, vha, 0x2118, - "%s %d %8phC post NVMe PRLI\n", - __func__, __LINE__, fcport->port_name); + "%s %d %8phC post %s PRLI\n", + __func__, __LINE__, fcport->port_name, + fcport->fc4f_nvme ? "NVME" : "FC"); qla24xx_post_prli_work(vha, fcport); } break; @@ -1853,17 +1860,38 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea) break; } - if (ea->fcport->n2n_flag) { + if (ea->fcport->fc4f_nvme) { ql_dbg(ql_dbg_disc, vha, 0x2118, "%s %d %8phC post fc4 prli\n", __func__, __LINE__, ea->fcport->port_name); ea->fcport->fc4f_nvme = 0; - ea->fcport->n2n_flag = 0; qla24xx_post_prli_work(vha, ea->fcport); + return; + } + + /* at this point both PRLI NVME & PRLI FCP failed */ + if (N2N_TOPO(vha->hw)) { + if (ea->fcport->n2n_link_reset_cnt < 3) { + ea->fcport->n2n_link_reset_cnt++; + /* + * remote port is not sending Plogi. Reset + * link to kick start his state machine + */ + set_bit(N2N_LINK_RESET, &vha->dpc_flags); + } else { + ql_log(ql_log_warn, vha, 0x2119, + "%s %d %8phC Unable to reconnect\n", + __func__, __LINE__, ea->fcport->port_name); + } + } else { + /* + * switch connect. login failed. Take connection + * down and allow relogin to retrigger + */ + ea->fcport->flags &= ~FCF_ASYNC_SENT; + ea->fcport->keep_nport_handle = 0; + qlt_schedule_sess_for_deletion(ea->fcport); } - ql_dbg(ql_dbg_disc, vha, 0x2119, - "%s %d %8phC unhandle event of %x\n", - __func__, __LINE__, ea->fcport->port_name, ea->data[0]); break; } } @@ -3190,7 +3218,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) for (j = 0; j < 2; j++, fwdt++) { if (!fwdt->template) { - ql_log(ql_log_warn, vha, 0x00ba, + ql_dbg(ql_dbg_init, vha, 0x00ba, "-> fwdt%u no template\n", j); continue; } @@ -4986,28 +5014,47 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) unsigned long flags; /* Inititae N2N login. */ - if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) { - /* borrowing */ - u32 *bp, i, sz; - - memset(ha->init_cb, 0, ha->init_cb_size); - sz = min_t(int, sizeof(struct els_plogi_payload), - ha->init_cb_size); - rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma, - (void *)ha->init_cb, sz); - if (rval == QLA_SUCCESS) { - bp = (uint32_t *)ha->init_cb; - for (i = 0; i < sz/4 ; i++, bp++) - *bp = cpu_to_be32(*bp); + if (N2N_TOPO(ha)) { + if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) { + /* borrowing */ + u32 *bp, i, sz; + + memset(ha->init_cb, 0, ha->init_cb_size); + sz = min_t(int, sizeof(struct els_plogi_payload), + ha->init_cb_size); + rval = qla24xx_get_port_login_templ(vha, + ha->init_cb_dma, (void *)ha->init_cb, sz); + if (rval == QLA_SUCCESS) { + bp = (uint32_t *)ha->init_cb; + for (i = 0; i < sz/4 ; i++, bp++) + *bp = cpu_to_be32(*bp); - memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb, - sizeof(ha->plogi_els_payld.data)); - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - } else { - ql_dbg(ql_dbg_init, vha, 0x00d1, - "PLOGI ELS param read fail.\n"); + memcpy(&ha->plogi_els_payld.data, + (void *)ha->init_cb, + sizeof(ha->plogi_els_payld.data)); + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + } else { + ql_dbg(ql_dbg_init, vha, 0x00d1, + "PLOGI ELS param read fail.\n"); + goto skip_login; + } + } + + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->n2n_flag) { + qla24xx_fcport_handle_login(vha, fcport); + return QLA_SUCCESS; + } + } +skip_login: + spin_lock_irqsave(&vha->work_lock, flags); + vha->scan.scan_retry++; + spin_unlock_irqrestore(&vha->work_lock, flags); + + if (vha->scan.scan_retry < MAX_SCAN_RETRIES) { + set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); + set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); } - return QLA_SUCCESS; } found_devs = 0; diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index e92e52aa6e9b..518eb954cf42 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2656,9 +2656,10 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) els_iocb->port_id[0] = sp->fcport->d_id.b.al_pa; els_iocb->port_id[1] = sp->fcport->d_id.b.area; els_iocb->port_id[2] = sp->fcport->d_id.b.domain; - els_iocb->s_id[0] = vha->d_id.b.al_pa; - els_iocb->s_id[1] = vha->d_id.b.area; - els_iocb->s_id[2] = vha->d_id.b.domain; + /* For SID the byte order is different than DID */ + els_iocb->s_id[1] = vha->d_id.b.al_pa; + els_iocb->s_id[2] = vha->d_id.b.area; + els_iocb->s_id[0] = vha->d_id.b.domain; if (elsio->u.els_logo.els_cmd == ELS_DCMD_PLOGI) { els_iocb->control_flags = 0; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4c858e2d0ea8..1cc6913f76c4 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -2249,7 +2249,7 @@ qla2x00_lip_reset(scsi_qla_host_t *vha) mbx_cmd_t mc; mbx_cmd_t *mcp = &mc; - ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x105a, + ql_dbg(ql_dbg_disc, vha, 0x105a, "Entered %s.\n", __func__); if (IS_CNA_CAPABLE(vha->hw)) { @@ -3883,14 +3883,24 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, case TOPO_N2N: ha->current_topology = ISP_CFG_N; spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + list_for_each_entry(fcport, &vha->vp_fcports, list) { + fcport->scan_state = QLA_FCPORT_SCAN; + fcport->n2n_flag = 0; + } + fcport = qla2x00_find_fcport_by_wwpn(vha, rptid_entry->u.f1.port_name, 1); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); if (fcport) { fcport->plogi_nack_done_deadline = jiffies + HZ; - fcport->dm_login_expire = jiffies + 3*HZ; + fcport->dm_login_expire = jiffies + 2*HZ; fcport->scan_state = QLA_FCPORT_FOUND; + fcport->n2n_flag = 1; + fcport->keep_nport_handle = 1; + if (vha->flags.nvme_enabled) + fcport->fc4f_nvme = 1; + switch (fcport->disc_state) { case DSC_DELETED: set_bit(RELOGIN_NEEDED, @@ -3924,7 +3934,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, rptid_entry->u.f1.port_name, rptid_entry->u.f1.node_name, NULL, - FC4_TYPE_UNKNOWN); + FS_FCP_IS_N2N); } /* if our portname is higher then initiate N2N login */ @@ -4023,6 +4033,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, list_for_each_entry(fcport, &vha->vp_fcports, list) { fcport->scan_state = QLA_FCPORT_SCAN; + fcport->n2n_flag = 0; } fcport = qla2x00_find_fcport_by_wwpn(vha, @@ -4032,6 +4043,14 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, fcport->login_retry = vha->hw->login_retry_count; fcport->plogi_nack_done_deadline = jiffies + HZ; fcport->scan_state = QLA_FCPORT_FOUND; + fcport->keep_nport_handle = 1; + fcport->n2n_flag = 1; + fcport->d_id.b.domain = + rptid_entry->u.f2.remote_nport_id[2]; + fcport->d_id.b.area = + rptid_entry->u.f2.remote_nport_id[1]; + fcport->d_id.b.al_pa = + rptid_entry->u.f2.remote_nport_id[0]; } } } diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index 1a9a11ae7285..6afad68e5ba2 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -66,6 +66,7 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha) uint16_t vp_id; struct qla_hw_data *ha = vha->hw; unsigned long flags = 0; + u8 i; mutex_lock(&ha->vport_lock); /* @@ -75,8 +76,9 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha) * ensures no active vp_list traversal while the vport is removed * from the queue) */ - wait_event_timeout(vha->vref_waitq, !atomic_read(&vha->vref_count), - 10*HZ); + for (i = 0; i < 10 && atomic_read(&vha->vref_count); i++) + wait_event_timeout(vha->vref_waitq, + atomic_read(&vha->vref_count), HZ); spin_lock_irqsave(&ha->vport_slock, flags); if (atomic_read(&vha->vref_count)) { @@ -262,6 +264,9 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb) spin_lock_irqsave(&ha->vport_slock, flags); list_for_each_entry(vha, &ha->vp_list, list) { if (vha->vp_idx) { + if (test_bit(VPORT_DELETE, &vha->dpc_flags)) + continue; + atomic_inc(&vha->vref_count); spin_unlock_irqrestore(&ha->vport_slock, flags); @@ -300,6 +305,20 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb) int qla2x00_vp_abort_isp(scsi_qla_host_t *vha) { + fc_port_t *fcport; + + /* + * To exclusively reset vport, we need to log it out first. + * Note: This control_vp can fail if ISP reset is already + * issued, this is expected, as the vp would be already + * logged out due to ISP reset. + */ + if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) { + qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); + list_for_each_entry(fcport, &vha->vp_fcports, list) + fcport->logout_on_delete = 0; + } + /* * Physical port will do most of the abort and recovery work. We can * just treat it as a loop down @@ -312,16 +331,9 @@ qla2x00_vp_abort_isp(scsi_qla_host_t *vha) atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); } - /* - * To exclusively reset vport, we need to log it out first. Note: this - * control_vp can fail if ISP reset is already issued, this is - * expected, as the vp would be already logged out due to ISP reset. - */ - if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) - qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); - ql_dbg(ql_dbg_taskm, vha, 0x801d, "Scheduling enable of Vport %d.\n", vha->vp_idx); + return qla24xx_enable_vp(vha); } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 73db01e3b4e4..3568031c6504 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1115,9 +1115,15 @@ static inline int test_fcport_count(scsi_qla_host_t *vha) void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) { + u8 i; + qla2x00_mark_all_devices_lost(vha, 0); - wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), 10*HZ); + for (i = 0; i < 10; i++) + wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), + HZ); + + flush_workqueue(vha->hw->wq); } /* @@ -5036,6 +5042,10 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) memcpy(fcport->port_name, e->u.new_sess.port_name, WWN_SIZE); + + if (e->u.new_sess.fc4_type & FS_FCP_IS_N2N) + fcport->n2n_flag = 1; + } else { ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %8phC mem alloc fail.\n", @@ -5134,11 +5144,9 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) if (dfcp) qlt_schedule_sess_for_deletion(tfcp); - - if (N2N_TOPO(vha->hw)) - fcport->flags &= ~FCF_FABRIC_DEVICE; - if (N2N_TOPO(vha->hw)) { + fcport->flags &= ~FCF_FABRIC_DEVICE; + fcport->keep_nport_handle = 1; if (vha->flags.nvme_enabled) { fcport->fc4f_nvme = 1; fcport->n2n_flag = 1; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0ffda6171614..a06e56224a55 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -953,7 +953,7 @@ void qlt_free_session_done(struct work_struct *work) struct qla_hw_data *ha = vha->hw; unsigned long flags; bool logout_started = false; - scsi_qla_host_t *base_vha; + scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev); struct qlt_plogi_ack_t *own = sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN]; @@ -1020,6 +1020,7 @@ void qlt_free_session_done(struct work_struct *work) if (logout_started) { bool traced = false; + u16 cnt = 0; while (!READ_ONCE(sess->logout_completed)) { if (!traced) { @@ -1029,6 +1030,9 @@ void qlt_free_session_done(struct work_struct *work) traced = true; } msleep(100); + cnt++; + if (cnt > 200) + break; } ql_dbg(ql_dbg_disc, vha, 0xf087, @@ -1101,6 +1105,7 @@ void qlt_free_session_done(struct work_struct *work) } spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + sess->free_pending = 0; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001, "Unregistration of sess %p %8phC finished fcp_cnt %d\n", @@ -1109,17 +1114,9 @@ void qlt_free_session_done(struct work_struct *work) if (tgt && (tgt->sess_count == 0)) wake_up_all(&tgt->waitQ); - if (vha->fcport_count == 0) - wake_up_all(&vha->fcport_waitQ); - - base_vha = pci_get_drvdata(ha->pdev); - - sess->free_pending = 0; - - if (test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags)) - return; - - if ((!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) { + if (!test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags) && + !(vha->vp_idx && test_bit(VPORT_DELETE, &vha->dpc_flags)) && + (!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) { switch (vha->host->active_mode) { case MODE_INITIATOR: case MODE_DUAL: @@ -1132,6 +1129,9 @@ void qlt_free_session_done(struct work_struct *work) break; } } + + if (vha->fcport_count == 0) + wake_up_all(&vha->fcport_waitQ); } /* ha->tgt.sess_lock supposed to be held on entry */ @@ -1161,7 +1161,7 @@ void qlt_unreg_sess(struct fc_port *sess) sess->last_login_gen = sess->login_gen; INIT_WORK(&sess->free_work, qlt_free_session_done); - schedule_work(&sess->free_work); + queue_work(sess->vha->hw->wq, &sess->free_work); } EXPORT_SYMBOL(qlt_unreg_sess); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index ed8b9ac805e6..542d2bac2922 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1837,8 +1837,7 @@ static int storvsc_probe(struct hv_device *device, /* * Set the number of HW queues we are supporting. */ - if (stor_device->num_sc != 0) - host->nr_hw_queues = stor_device->num_sc + 1; + host->nr_hw_queues = num_present_cpus(); /* * Set the error handler work queue. diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 034dd9cb9ec8..11a87f51c442 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8143,6 +8143,9 @@ int ufshcd_shutdown(struct ufs_hba *hba) { int ret = 0; + if (!hba->is_powered) + goto out; + if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba)) goto out; diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index c64728fc21f2..a62057555d1b 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -349,10 +349,8 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) */ dst_release(skb_dst(skb)); skb_dst_set(skb, NULL); -#ifdef CONFIG_XFRM - secpath_reset(skb); -#endif - nf_reset(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); #ifdef CONFIG_NET_SCHED skb->tc_index = 0; diff --git a/drivers/video/logo/Makefile b/drivers/video/logo/Makefile index 228a89b9bdd1..16f60c1e1766 100644 --- a/drivers/video/logo/Makefile +++ b/drivers/video/logo/Makefile @@ -18,23 +18,6 @@ obj-$(CONFIG_SPU_BASE) += logo_spe_clut224.o # How to generate logo's -# Use logo-cfiles to retrieve list of .c files to be built -logo-cfiles = $(notdir $(patsubst %.$(2), %.c, \ - $(wildcard $(srctree)/$(src)/*$(1).$(2)))) - - -# Mono logos -extra-y += $(call logo-cfiles,_mono,pbm) - -# VGA16 logos -extra-y += $(call logo-cfiles,_vga16,ppm) - -# 224 Logos -extra-y += $(call logo-cfiles,_clut224,ppm) - -# Gray 256 -extra-y += $(call logo-cfiles,_gray256,pgm) - pnmtologo := scripts/pnmtologo # Create commands like "pnmtologo -t mono -n logo_mac_mono -o ..." @@ -55,5 +38,5 @@ $(obj)/%_clut224.c: $(src)/%_clut224.ppm $(pnmtologo) FORCE $(obj)/%_gray256.c: $(src)/%_gray256.pgm $(pnmtologo) FORCE $(call if_changed,logo) -# Files generated that shall be removed upon make clean -clean-files := *.o *_mono.c *_vga16.c *_clut224.c *_gray256.c +# generated C files +targets += *_mono.c *_vga16.c *_clut224.c *_gray256.c diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 4e11de6cde81..5bae515c8e25 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -156,8 +156,10 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); (GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC) /* balloon_append: add the given page to the balloon. */ -static void __balloon_append(struct page *page) +static void balloon_append(struct page *page) { + __SetPageOffline(page); + /* Lowmem is re-populated first, so highmem pages go at list tail. */ if (PageHighMem(page)) { list_add_tail(&page->lru, &ballooned_pages); @@ -169,11 +171,6 @@ static void __balloon_append(struct page *page) wake_up(&balloon_wq); } -static void balloon_append(struct page *page) -{ - __balloon_append(page); -} - /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */ static struct page *balloon_retrieve(bool require_lowmem) { @@ -192,6 +189,7 @@ static struct page *balloon_retrieve(bool require_lowmem) else balloon_stats.balloon_low--; + __ClearPageOffline(page); return page; } @@ -377,8 +375,7 @@ static void xen_online_page(struct page *page, unsigned int order) for (i = 0; i < size; i++) { p = pfn_to_page(start_pfn + i); __online_page_set_limits(p); - __SetPageOffline(p); - __balloon_append(p); + balloon_append(p); } mutex_unlock(&balloon_mutex); } @@ -444,7 +441,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages) xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]); /* Relinquish the page back to the allocator. */ - __ClearPageOffline(page); free_reserved_page(page); } @@ -471,7 +467,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) state = BP_EAGAIN; break; } - __SetPageOffline(page); adjust_managed_page_count(page, -1); xenmem_reservation_scrub_page(page); list_add(&page->lru, &pages); @@ -611,7 +606,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) while (pgno < nr_pages) { page = balloon_retrieve(true); if (page) { - __ClearPageOffline(page); pages[pgno++] = page; #ifdef CONFIG_XEN_HAVE_PVMMU /* @@ -653,10 +647,8 @@ void free_xenballooned_pages(int nr_pages, struct page **pages) mutex_lock(&balloon_mutex); for (i = 0; i < nr_pages; i++) { - if (pages[i]) { - __SetPageOffline(pages[i]); + if (pages[i]) balloon_append(pages[i]); - } } balloon_stats.target_unpopulated -= nr_pages; @@ -674,7 +666,6 @@ static void __init balloon_add_region(unsigned long start_pfn, unsigned long pages) { unsigned long pfn, extra_pfn_end; - struct page *page; /* * If the amount of usable memory has been limited (e.g., with @@ -684,11 +675,10 @@ static void __init balloon_add_region(unsigned long start_pfn, extra_pfn_end = min(max_pfn, start_pfn + pages); for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { - page = pfn_to_page(pfn); /* totalram_pages and totalhigh_pages do not include the boot-time balloon extension, so don't subtract from it. */ - __balloon_append(page); + balloon_append(pfn_to_page(pfn)); } balloon_stats.total_pages += extra_pfn_end - start_pfn; diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c index 89d60f8e3c18..d1ff2186ebb4 100644 --- a/drivers/xen/efi.c +++ b/drivers/xen/efi.c @@ -40,7 +40,7 @@ #define efi_data(op) (op.u.efi_runtime_call) -efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) +static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { struct xen_platform_op op = INIT_EFI_OP(get_time); @@ -61,9 +61,8 @@ efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_time); -efi_status_t xen_efi_set_time(efi_time_t *tm) +static efi_status_t xen_efi_set_time(efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(set_time); @@ -75,10 +74,10 @@ efi_status_t xen_efi_set_time(efi_time_t *tm) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_time); -efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, - efi_time_t *tm) +static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, + efi_bool_t *pending, + efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time); @@ -98,9 +97,8 @@ efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_wakeup_time); -efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time); @@ -117,11 +115,10 @@ efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_wakeup_time); -efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 *attr, unsigned long *data_size, - void *data) +static efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *data_size, + void *data) { struct xen_platform_op op = INIT_EFI_OP(get_variable); @@ -141,11 +138,10 @@ efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_variable); -efi_status_t xen_efi_get_next_variable(unsigned long *name_size, - efi_char16_t *name, - efi_guid_t *vendor) +static efi_status_t xen_efi_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) { struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name); @@ -165,11 +161,10 @@ efi_status_t xen_efi_get_next_variable(unsigned long *name_size, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_next_variable); -efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, - void *data) +static efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data) { struct xen_platform_op op = INIT_EFI_OP(set_variable); @@ -186,11 +181,10 @@ efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_variable); -efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, - u64 *remaining_space, - u64 *max_variable_size) +static efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) { struct xen_platform_op op = INIT_EFI_OP(query_variable_info); @@ -208,9 +202,8 @@ efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_query_variable_info); -efi_status_t xen_efi_get_next_high_mono_count(u32 *count) +static efi_status_t xen_efi_get_next_high_mono_count(u32 *count) { struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count); @@ -221,10 +214,9 @@ efi_status_t xen_efi_get_next_high_mono_count(u32 *count) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_next_high_mono_count); -efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, - unsigned long count, unsigned long sg_list) +static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, unsigned long sg_list) { struct xen_platform_op op = INIT_EFI_OP(update_capsule); @@ -241,11 +233,9 @@ efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_update_capsule); -efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, - unsigned long count, u64 *max_size, - int *reset_type) +static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, u64 *max_size, int *reset_type) { struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities); @@ -264,10 +254,9 @@ efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_query_capsule_caps); -void xen_efi_reset_system(int reset_type, efi_status_t status, - unsigned long data_size, efi_char16_t *data) +static void xen_efi_reset_system(int reset_type, efi_status_t status, + unsigned long data_size, efi_char16_t *data) { switch (reset_type) { case EFI_RESET_COLD: @@ -281,4 +270,25 @@ void xen_efi_reset_system(int reset_type, efi_status_t status, BUG(); } } -EXPORT_SYMBOL_GPL(xen_efi_reset_system); + +/* + * Set XEN EFI runtime services function pointers. Other fields of struct efi, + * e.g. efi.systab, will be set like normal EFI. + */ +void __init xen_efi_runtime_setup(void) +{ + efi.get_time = xen_efi_get_time; + efi.set_time = xen_efi_set_time; + efi.get_wakeup_time = xen_efi_get_wakeup_time; + efi.set_wakeup_time = xen_efi_set_wakeup_time; + efi.get_variable = xen_efi_get_variable; + efi.get_next_variable = xen_efi_get_next_variable; + efi.set_variable = xen_efi_set_variable; + efi.set_variable_nonblocking = xen_efi_set_variable; + efi.query_variable_info = xen_efi_query_variable_info; + efi.query_variable_info_nonblocking = xen_efi_query_variable_info; + efi.update_capsule = xen_efi_update_capsule; + efi.query_capsule_caps = xen_efi_query_capsule_caps; + efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; + efi.reset_system = xen_efi_reset_system; +} diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 08adc590f631..597af455a522 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -55,6 +55,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/miscdevice.h> +#include <linux/workqueue.h> #include <xen/xenbus.h> #include <xen/xen.h> @@ -116,6 +117,8 @@ struct xenbus_file_priv { wait_queue_head_t read_waitq; struct kref kref; + + struct work_struct wq; }; /* Read out any raw xenbus messages queued up. */ @@ -300,14 +303,14 @@ static void watch_fired(struct xenbus_watch *watch, mutex_unlock(&adap->dev_data->reply_mutex); } -static void xenbus_file_free(struct kref *kref) +static void xenbus_worker(struct work_struct *wq) { struct xenbus_file_priv *u; struct xenbus_transaction_holder *trans, *tmp; struct watch_adapter *watch, *tmp_watch; struct read_buffer *rb, *tmp_rb; - u = container_of(kref, struct xenbus_file_priv, kref); + u = container_of(wq, struct xenbus_file_priv, wq); /* * No need for locking here because there are no other users, @@ -333,6 +336,18 @@ static void xenbus_file_free(struct kref *kref) kfree(u); } +static void xenbus_file_free(struct kref *kref) +{ + struct xenbus_file_priv *u; + + /* + * We might be called in xenbus_thread(). + * Use workqueue to avoid deadlock. + */ + u = container_of(kref, struct xenbus_file_priv, kref); + schedule_work(&u->wq); +} + static struct xenbus_transaction_holder *xenbus_get_transaction( struct xenbus_file_priv *u, uint32_t tx_id) { @@ -650,6 +665,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp) INIT_LIST_HEAD(&u->watches); INIT_LIST_HEAD(&u->read_buffers); init_waitqueue_head(&u->read_waitq); + INIT_WORK(&u->wq, xenbus_worker); mutex_init(&u->reply_mutex); mutex_init(&u->msgbuffer_mutex); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index ad4c6b1d5074..c5642bcb6b46 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -879,7 +879,7 @@ out_free_interp: the correct location in memory. */ for(i = 0, elf_ppnt = elf_phdata; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { - int elf_prot, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; + int elf_prot, elf_flags; unsigned long k, vaddr; unsigned long total_size = 0; @@ -911,13 +911,6 @@ out_free_interp: */ } } - - /* - * Some binaries have overlapping elf segments and then - * we have to forcefully map over an existing mapping - * e.g. over this newly established brk mapping. - */ - elf_fixed = MAP_FIXED; } elf_prot = make_prot(elf_ppnt->p_flags); @@ -930,7 +923,7 @@ out_free_interp: * the ET_DYN load_addr calculations, proceed normally. */ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) { - elf_flags |= elf_fixed; + elf_flags |= MAP_FIXED; } else if (loc->elf_ex.e_type == ET_DYN) { /* * This logic is run once for the first LOAD Program @@ -966,7 +959,7 @@ out_free_interp: load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); - elf_flags |= elf_fixed; + elf_flags |= MAP_FIXED; } else load_bias = 0; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 8fe4eb7e5045..27e5b269e729 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1591,7 +1591,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; - struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; u64 lockstart; @@ -1611,6 +1610,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, return -ENOMEM; while (iov_iter_count(i) > 0) { + struct extent_state *cached_state = NULL; size_t offset = offset_in_page(pos); size_t sector_offset; size_t write_bytes = min(iov_iter_count(i), @@ -1758,9 +1758,20 @@ again: if (copied > 0) ret = btrfs_dirty_pages(inode, pages, dirty_pages, pos, copied, &cached_state); + + /* + * If we have not locked the extent range, because the range's + * start offset is >= i_size, we might still have a non-NULL + * cached extent state, acquired while marking the extent range + * as delalloc through btrfs_dirty_pages(). Therefore free any + * possible cached extent state to avoid a memory leak. + */ if (extents_locked) unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state); + else + free_extent_state(cached_state); + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes, true); if (ret) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a0546401bc0a..0f2754eaa05b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6305,13 +6305,16 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, u32 sizes[2]; int nitems = name ? 2 : 1; unsigned long ptr; + unsigned int nofs_flag; int ret; path = btrfs_alloc_path(); if (!path) return ERR_PTR(-ENOMEM); + nofs_flag = memalloc_nofs_save(); inode = new_inode(fs_info->sb); + memalloc_nofs_restore(nofs_flag); if (!inode) { btrfs_free_path(path); return ERR_PTR(-ENOMEM); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index e87cbdad02a3..b57f3618e58e 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -500,7 +500,7 @@ static int process_leaf(struct btrfs_root *root, struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; u32 count; - int i = 0, tree_block_level = 0, ret; + int i = 0, tree_block_level = 0, ret = 0; struct btrfs_key key; int nritems = btrfs_header_nritems(leaf); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index f3215028235c..123ac54af071 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5085,7 +5085,7 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *path; struct btrfs_key key; int ret; - u64 clone_src_i_size; + u64 clone_src_i_size = 0; /* * Prevent cloning from a zero offset with a length matching the sector diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 29b82a795522..8a6cc600bf18 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2932,7 +2932,8 @@ out: * in the tree of log roots */ static int update_log_root(struct btrfs_trans_handle *trans, - struct btrfs_root *log) + struct btrfs_root *log, + struct btrfs_root_item *root_item) { struct btrfs_fs_info *fs_info = log->fs_info; int ret; @@ -2940,10 +2941,10 @@ static int update_log_root(struct btrfs_trans_handle *trans, if (log->log_transid == 1) { /* insert root item on the first sync */ ret = btrfs_insert_root(trans, fs_info->log_root_tree, - &log->root_key, &log->root_item); + &log->root_key, root_item); } else { ret = btrfs_update_root(trans, fs_info->log_root_tree, - &log->root_key, &log->root_item); + &log->root_key, root_item); } return ret; } @@ -3041,6 +3042,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log = root->log_root; struct btrfs_root *log_root_tree = fs_info->log_root_tree; + struct btrfs_root_item new_root_item; int log_transid = 0; struct btrfs_log_ctx root_log_ctx; struct blk_plug plug; @@ -3104,18 +3106,26 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, goto out; } + /* + * We _must_ update under the root->log_mutex in order to make sure we + * have a consistent view of the log root we are trying to commit at + * this moment. + * + * We _must_ copy this into a local copy, because we are not holding the + * log_root_tree->log_mutex yet. This is important because when we + * commit the log_root_tree we must have a consistent view of the + * log_root_tree when we update the super block to point at the + * log_root_tree bytenr. If we update the log_root_tree here we'll race + * with the commit and possibly point at the new block which we may not + * have written out. + */ btrfs_set_root_node(&log->root_item, log->node); + memcpy(&new_root_item, &log->root_item, sizeof(new_root_item)); root->log_transid++; log->log_transid = root->log_transid; root->log_start_pid = 0; /* - * Update or create log root item under the root's log_mutex to prevent - * races with concurrent log syncs that can lead to failure to update - * log root item because it was not created yet. - */ - ret = update_log_root(trans, log); - /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. @@ -3135,6 +3145,14 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&log_root_tree->log_mutex); mutex_lock(&log_root_tree->log_mutex); + + /* + * Now we are safe to update the log_root_tree because we're under the + * log_mutex, and we're a current writer so we're holding the commit + * open until we drop the log_mutex. + */ + ret = update_log_root(trans, log, &new_root_item); + if (atomic_dec_and_test(&log_root_tree->log_writers)) { /* atomic_dec_and_test implies a barrier */ cond_wake_up_nomb(&log_root_tree->log_writer_wait); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cdd7af424033..bdfe4493e43a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3845,7 +3845,11 @@ static int alloc_profile_is_valid(u64 flags, int extended) return !extended; /* "0" is valid for usual profiles */ /* true if exactly one bit set */ - return is_power_of_2(flags); + /* + * Don't use is_power_of_2(unsigned long) because it won't work + * for the single profile (1ULL << 48) on 32-bit CPUs. + */ + return flags != 0 && (flags & (flags - 1)) == 0; } static inline int balance_need_close(struct btrfs_fs_info *fs_info) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 8a9fcbd0e8ac..fc3a8d8064f8 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -34,11 +34,15 @@ static void erofs_readendio(struct bio *bio) struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr) { - struct inode *const bd_inode = sb->s_bdev->bd_inode; - struct address_space *const mapping = bd_inode->i_mapping; + struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping; + struct page *page; - return read_cache_page_gfp(mapping, blkaddr, + page = read_cache_page_gfp(mapping, blkaddr, mapping_gfp_constraint(mapping, ~__GFP_FS)); + /* should already be PageUptodate */ + if (!IS_ERR(page)) + lock_page(page); + return page; } static int erofs_map_blocks_flatmode(struct inode *inode, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index caf9a95173b0..0e369494f2f2 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -105,9 +105,9 @@ static int erofs_read_superblock(struct super_block *sb) int ret; page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL); - if (!page) { + if (IS_ERR(page)) { erofs_err(sb, "cannot read erofs superblock"); - return -EIO; + return PTR_ERR(page); } sbi = EROFS_SB(sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 96e34c90f814..fad80c97d247 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -575,7 +575,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, struct erofs_map_blocks *const map = &fe->map; struct z_erofs_collector *const clt = &fe->clt; const loff_t offset = page_offset(page); - bool tight = (clt->mode >= COLLECT_PRIMARY_HOOKED); + bool tight = true; enum z_erofs_cache_alloctype cache_strategy; enum z_erofs_page_type page_type; @@ -628,8 +628,16 @@ restart_now: preload_compressed_pages(clt, MNGD_MAPPING(sbi), cache_strategy, pagepool); - tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED); hitted: + /* + * Ensure the current partial page belongs to this submit chain rather + * than other concurrent submit chains or the noio(bypass) chain since + * those chains are handled asynchronously thus the page cannot be used + * for inplace I/O or pagevec (should be processed in strict order.) + */ + tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED && + clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE); + cur = end - min_t(unsigned int, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8aaa7eec7b74..e88421d9a48d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -164,8 +164,13 @@ static void finish_writeback_work(struct bdi_writeback *wb, if (work->auto_free) kfree(work); - if (done && atomic_dec_and_test(&done->cnt)) - wake_up_all(done->waitq); + if (done) { + wait_queue_head_t *waitq = done->waitq; + + /* @done can't be accessed after the following dec */ + if (atomic_dec_and_test(&done->cnt)) + wake_up_all(waitq); + } } static void wb_queue_work(struct bdi_writeback *wb, diff --git a/fs/io_uring.c b/fs/io_uring.c index aa8ac557493c..92972b5c1d00 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -591,14 +591,6 @@ static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, io_cqring_ev_posted(ctx); } -static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) -{ - percpu_ref_put_many(&ctx->refs, refs); - - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); -} - static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, struct io_submit_state *state) { @@ -646,7 +638,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, req->result = 0; return req; out: - io_ring_drop_ctx_refs(ctx, 1); + percpu_ref_put(&ctx->refs); return NULL; } @@ -654,7 +646,7 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) { if (*nr) { kmem_cache_free_bulk(req_cachep, *nr, reqs); - io_ring_drop_ctx_refs(ctx, *nr); + percpu_ref_put_many(&ctx->refs, *nr); *nr = 0; } } @@ -663,7 +655,7 @@ static void __io_free_req(struct io_kiocb *req) { if (req->file && !(req->flags & REQ_F_FIXED_FILE)) fput(req->file); - io_ring_drop_ctx_refs(req->ctx, 1); + percpu_ref_put(&req->ctx->refs); kmem_cache_free(req_cachep, req); } @@ -1892,15 +1884,15 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) unsigned count, req_dist, tail_index; struct io_ring_ctx *ctx = req->ctx; struct list_head *entry; - struct timespec ts; + struct timespec64 ts; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags || sqe->len != 1) return -EINVAL; - if (copy_from_user(&ts, (void __user *) (unsigned long) sqe->addr, - sizeof(ts))) + + if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; /* @@ -1934,7 +1926,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); req->timeout.timer.function = io_timeout_fn; - hrtimer_start(&req->timeout.timer, timespec_to_ktime(ts), + hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts), HRTIMER_MODE_REL); return 0; } @@ -2761,7 +2753,7 @@ out: if (link) io_queue_link_head(ctx, link, &link->submit, shadow_req, - block_for_last); + !block_for_last); if (statep) io_submit_state_end(statep); @@ -2920,8 +2912,12 @@ static void io_finish_async(struct io_ring_ctx *ctx) static void io_destruct_skb(struct sk_buff *skb) { struct io_ring_ctx *ctx = skb->sk->sk_user_data; + int i; + + for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++) + if (ctx->sqo_wq[i]) + flush_workqueue(ctx->sqo_wq[i]); - io_finish_async(ctx); unix_destruct_scm(skb); } @@ -3630,7 +3626,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } } - io_ring_drop_ctx_refs(ctx, 1); + percpu_ref_put(&ctx->refs); out_fput: fdput(f); return submitted ? submitted : ret; diff --git a/fs/libfs.c b/fs/libfs.c index c9b2850c0f7c..540611b99b9a 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -89,58 +89,45 @@ int dcache_dir_close(struct inode *inode, struct file *file) EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ -static struct dentry *next_positive(struct dentry *parent, - struct list_head *from, - int count) +/* + * Returns an element of siblings' list. + * We are looking for <count>th positive after <p>; if + * found, dentry is grabbed and returned to caller. + * If no such element exists, NULL is returned. + */ +static struct dentry *scan_positives(struct dentry *cursor, + struct list_head *p, + loff_t count, + struct dentry *last) { - unsigned *seq = &parent->d_inode->i_dir_seq, n; - struct dentry *res; - struct list_head *p; - bool skipped; - int i; + struct dentry *dentry = cursor->d_parent, *found = NULL; -retry: - i = count; - skipped = false; - n = smp_load_acquire(seq) & ~1; - res = NULL; - rcu_read_lock(); - for (p = from->next; p != &parent->d_subdirs; p = p->next) { + spin_lock(&dentry->d_lock); + while ((p = p->next) != &dentry->d_subdirs) { struct dentry *d = list_entry(p, struct dentry, d_child); - if (!simple_positive(d)) { - skipped = true; - } else if (!--i) { - res = d; - break; + // we must at least skip cursors, to avoid livelocks + if (d->d_flags & DCACHE_DENTRY_CURSOR) + continue; + if (simple_positive(d) && !--count) { + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(d)) + found = dget_dlock(d); + spin_unlock(&d->d_lock); + if (likely(found)) + break; + count = 1; + } + if (need_resched()) { + list_move(&cursor->d_child, p); + p = &cursor->d_child; + spin_unlock(&dentry->d_lock); + cond_resched(); + spin_lock(&dentry->d_lock); } } - rcu_read_unlock(); - if (skipped) { - smp_rmb(); - if (unlikely(*seq != n)) - goto retry; - } - return res; -} - -static void move_cursor(struct dentry *cursor, struct list_head *after) -{ - struct dentry *parent = cursor->d_parent; - unsigned n, *seq = &parent->d_inode->i_dir_seq; - spin_lock(&parent->d_lock); - for (;;) { - n = *seq; - if (!(n & 1) && cmpxchg(seq, n, n + 1) == n) - break; - cpu_relax(); - } - __list_del(cursor->d_child.prev, cursor->d_child.next); - if (after) - list_add(&cursor->d_child, after); - else - list_add_tail(&cursor->d_child, &parent->d_subdirs); - smp_store_release(seq, n + 2); - spin_unlock(&parent->d_lock); + spin_unlock(&dentry->d_lock); + dput(last); + return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) @@ -158,17 +145,25 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) return -EINVAL; } if (offset != file->f_pos) { + struct dentry *cursor = file->private_data; + struct dentry *to = NULL; + + inode_lock_shared(dentry->d_inode); + + if (offset > 2) + to = scan_positives(cursor, &dentry->d_subdirs, + offset - 2, NULL); + spin_lock(&dentry->d_lock); + if (to) + list_move(&cursor->d_child, &to->d_child); + else + list_del_init(&cursor->d_child); + spin_unlock(&dentry->d_lock); + dput(to); + file->f_pos = offset; - if (file->f_pos >= 2) { - struct dentry *cursor = file->private_data; - struct dentry *to; - loff_t n = file->f_pos - 2; - - inode_lock_shared(dentry->d_inode); - to = next_positive(dentry, &dentry->d_subdirs, n); - move_cursor(cursor, to ? &to->d_child : NULL); - inode_unlock_shared(dentry->d_inode); - } + + inode_unlock_shared(dentry->d_inode); } return offset; } @@ -190,25 +185,35 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p = &cursor->d_child; - struct dentry *next; - bool moved = false; + struct list_head *anchor = &dentry->d_subdirs; + struct dentry *next = NULL; + struct list_head *p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) - p = &dentry->d_subdirs; - while ((next = next_positive(dentry, p, 1)) != NULL) { + p = anchor; + else if (!list_empty(&cursor->d_child)) + p = &cursor->d_child; + else + return 0; + + while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, dt_type(d_inode(next)))) break; - moved = true; - p = &next->d_child; ctx->pos++; + p = &next->d_child; } - if (moved) - move_cursor(cursor, p); + spin_lock(&dentry->d_lock); + if (next) + list_move_tail(&cursor->d_child, &next->d_child); + else + list_del_init(&cursor->d_child); + spin_unlock(&dentry->d_lock); + dput(next); + return 0; } EXPORT_SYMBOL(dcache_readdir); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 8de1c9d644f6..9cd0a6815933 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2049,7 +2049,8 @@ out_write_size: inode->i_mtime = inode->i_ctime = current_time(inode); di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); - ocfs2_update_inode_fsync_trans(handle, inode, 1); + if (handle) + ocfs2_update_inode_fsync_trans(handle, inode, 1); } if (handle) ocfs2_journal_dirty(handle, wc->w_di_bh); @@ -2146,13 +2147,30 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct ocfs2_dio_write_ctxt *dwc = NULL; struct buffer_head *di_bh = NULL; u64 p_blkno; - loff_t pos = iblock << inode->i_sb->s_blocksize_bits; + unsigned int i_blkbits = inode->i_sb->s_blocksize_bits; + loff_t pos = iblock << i_blkbits; + sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits; unsigned len, total_len = bh_result->b_size; int ret = 0, first_get_block = 0; len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); len = min(total_len, len); + /* + * bh_result->b_size is count in get_more_blocks according to write + * "pos" and "end", we need map twice to return different buffer state: + * 1. area in file size, not set NEW; + * 2. area out file size, set NEW. + * + * iblock endblk + * |--------|---------|---------|--------- + * |<-------area in file------->| + */ + + if ((iblock <= endblk) && + ((iblock + ((len - 1) >> i_blkbits)) > endblk)) + len = (endblk - iblock + 1) << i_blkbits; + mlog(0, "get block of %lu at %llu:%u req %u\n", inode->i_ino, pos, len, total_len); @@ -2236,6 +2254,9 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, if (desc->c_needs_zero) set_buffer_new(bh_result); + if (iblock > endblk) + set_buffer_new(bh_result); + /* May sleep in end_io. It should not happen in a irq context. So defer * it to dio work queue. */ set_buffer_defer_completion(bh_result); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index d6f7b299eb23..efeea208fdeb 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -283,7 +283,7 @@ static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb, if (inode_alloc) inode_lock(inode_alloc); - if (o2info_coherent(&fi->ifi_req)) { + if (inode_alloc && o2info_coherent(&fi->ifi_req)) { status = ocfs2_inode_lock(inode_alloc, &bh, 0); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 90c830e3758e..d8507972ee13 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1490,18 +1490,6 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc, return loc->xl_ops->xlo_check_space(loc, xi); } -static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash) -{ - loc->xl_ops->xlo_add_entry(loc, name_hash); - loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash); - /* - * We can't leave the new entry's xe_name_offset at zero or - * add_namevalue() will go nuts. We set it to the size of our - * storage so that it can never be less than any other entry. - */ - loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size); -} - static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc, struct ocfs2_xattr_info *xi) { @@ -2133,29 +2121,31 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc, if (rc) goto out; - if (loc->xl_entry) { - if (ocfs2_xa_can_reuse_entry(loc, xi)) { - orig_value_size = loc->xl_entry->xe_value_size; - rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); - if (rc) - goto out; - goto alloc_value; - } + if (!loc->xl_entry) { + rc = -EINVAL; + goto out; + } - if (!ocfs2_xattr_is_local(loc->xl_entry)) { - orig_clusters = ocfs2_xa_value_clusters(loc); - rc = ocfs2_xa_value_truncate(loc, 0, ctxt); - if (rc) { - mlog_errno(rc); - ocfs2_xa_cleanup_value_truncate(loc, - "overwriting", - orig_clusters); - goto out; - } + if (ocfs2_xa_can_reuse_entry(loc, xi)) { + orig_value_size = loc->xl_entry->xe_value_size; + rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); + if (rc) + goto out; + goto alloc_value; + } + + if (!ocfs2_xattr_is_local(loc->xl_entry)) { + orig_clusters = ocfs2_xa_value_clusters(loc); + rc = ocfs2_xa_value_truncate(loc, 0, ctxt); + if (rc) { + mlog_errno(rc); + ocfs2_xa_cleanup_value_truncate(loc, + "overwriting", + orig_clusters); + goto out; } - ocfs2_xa_wipe_namevalue(loc); - } else - ocfs2_xa_add_entry(loc, name_hash); + } + ocfs2_xa_wipe_namevalue(loc); /* * If we get here, we have a blank entry. Fill it. We grow our diff --git a/fs/readdir.c b/fs/readdir.c index 2f6a4534e0df..6e2623e57b2e 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -20,9 +20,23 @@ #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/compat.h> - #include <linux/uaccess.h> +#include <asm/unaligned.h> + +/* + * Note the "unsafe_put_user() semantics: we goto a + * label for errors. + */ +#define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \ + char __user *dst = (_dst); \ + const char *src = (_src); \ + size_t len = (_len); \ + unsafe_put_user(0, dst+len, label); \ + unsafe_copy_to_user(dst, src, len, label); \ +} while (0) + + int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); @@ -65,6 +79,40 @@ out: EXPORT_SYMBOL(iterate_dir); /* + * POSIX says that a dirent name cannot contain NULL or a '/'. + * + * It's not 100% clear what we should really do in this case. + * The filesystem is clearly corrupted, but returning a hard + * error means that you now don't see any of the other names + * either, so that isn't a perfect alternative. + * + * And if you return an error, what error do you use? Several + * filesystems seem to have decided on EUCLEAN being the error + * code for EFSCORRUPTED, and that may be the error to use. Or + * just EIO, which is perhaps more obvious to users. + * + * In order to see the other file names in the directory, the + * caller might want to make this a "soft" error: skip the + * entry, and return the error at the end instead. + * + * Note that this should likely do a "memchr(name, 0, len)" + * check too, since that would be filesystem corruption as + * well. However, that case can't actually confuse user space, + * which has to do a strlen() on the name anyway to find the + * filename length, and the above "soft error" worry means + * that it's probably better left alone until we have that + * issue clarified. + */ +static int verify_dirent_name(const char *name, int len) +{ + if (WARN_ON_ONCE(!len)) + return -EIO; + if (WARN_ON_ONCE(memchr(name, '/', len))) + return -EIO; + return 0; +} + +/* * Traditional linux readdir() handling.. * * "count=1" is a special case, meaning that the buffer is one @@ -173,6 +221,9 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return buf->error; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; @@ -182,28 +233,31 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, return -EOVERFLOW; } dirent = buf->previous; - if (dirent) { - if (signal_pending(current)) - return -EINTR; - if (__put_user(offset, &dirent->d_off)) - goto efault; - } - dirent = buf->current_dir; - if (__put_user(d_ino, &dirent->d_ino)) - goto efault; - if (__put_user(reclen, &dirent->d_reclen)) - goto efault; - if (copy_to_user(dirent->d_name, name, namlen)) - goto efault; - if (__put_user(0, dirent->d_name + namlen)) - goto efault; - if (__put_user(d_type, (char __user *) dirent + reclen - 1)) + if (dirent && signal_pending(current)) + return -EINTR; + + /* + * Note! This range-checks 'previous' (which may be NULL). + * The real range was checked in getdents + */ + if (!user_access_begin(dirent, sizeof(*dirent))) goto efault; + if (dirent) + unsafe_put_user(offset, &dirent->d_off, efault_end); + dirent = buf->current_dir; + unsafe_put_user(d_ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_access_end(); + buf->previous = dirent; dirent = (void __user *)dirent + reclen; buf->current_dir = dirent; buf->count -= reclen; return 0; +efault_end: + user_access_end(); efault: buf->error = -EFAULT; return -EFAULT; @@ -259,34 +313,38 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return buf->error; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; dirent = buf->previous; - if (dirent) { - if (signal_pending(current)) - return -EINTR; - if (__put_user(offset, &dirent->d_off)) - goto efault; - } - dirent = buf->current_dir; - if (__put_user(ino, &dirent->d_ino)) - goto efault; - if (__put_user(0, &dirent->d_off)) - goto efault; - if (__put_user(reclen, &dirent->d_reclen)) - goto efault; - if (__put_user(d_type, &dirent->d_type)) - goto efault; - if (copy_to_user(dirent->d_name, name, namlen)) - goto efault; - if (__put_user(0, dirent->d_name + namlen)) + if (dirent && signal_pending(current)) + return -EINTR; + + /* + * Note! This range-checks 'previous' (which may be NULL). + * The real range was checked in getdents + */ + if (!user_access_begin(dirent, sizeof(*dirent))) goto efault; + if (dirent) + unsafe_put_user(offset, &dirent->d_off, efault_end); + dirent = buf->current_dir; + unsafe_put_user(ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, &dirent->d_type, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_access_end(); + buf->previous = dirent; dirent = (void __user *)dirent + reclen; buf->current_dir = dirent; buf->count -= reclen; return 0; +efault_end: + user_access_end(); efault: buf->error = -EFAULT; return -EFAULT; diff --git a/fs/statfs.c b/fs/statfs.c index eea7af6f2f22..2616424012ea 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -318,19 +318,10 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) { struct compat_statfs64 buf; - if (sizeof(ubuf->f_bsize) == 4) { - if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen | - kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL) - return -EOVERFLOW; - /* f_files and f_ffree may be -1; it's okay - * to stuff that into 32 bits */ - if (kbuf->f_files != 0xffffffffffffffffULL - && (kbuf->f_files & 0xffffffff00000000ULL)) - return -EOVERFLOW; - if (kbuf->f_ffree != 0xffffffffffffffffULL - && (kbuf->f_ffree & 0xffffffff00000000ULL)) - return -EOVERFLOW; - } + + if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) + return -EOVERFLOW; + memset(&buf, 0, sizeof(struct compat_statfs64)); buf.f_type = kbuf->f_type; buf.f_bsize = kbuf->f_bsize; diff --git a/fs/super.c b/fs/super.c index f627b7c53d2b..cfadab2cbf35 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1300,6 +1300,7 @@ int get_tree_bdev(struct fs_context *fc, mutex_lock(&bdev->bd_fsfreeze_mutex); if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); + blkdev_put(bdev, mode); warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); return -EBUSY; } @@ -1308,8 +1309,10 @@ int get_tree_bdev(struct fs_context *fc, fc->sget_key = bdev; s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc); mutex_unlock(&bdev->bd_fsfreeze_mutex); - if (IS_ERR(s)) + if (IS_ERR(s)) { + blkdev_put(bdev, mode); return PTR_ERR(s); + } if (s->s_root) { /* Don't summarily change the RO/RW state. */ diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 5de296b34ab1..14fbdf22b7e7 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -28,12 +28,11 @@ xfs_get_aghdr_buf( struct xfs_mount *mp, xfs_daddr_t blkno, size_t numblks, - int flags, const struct xfs_buf_ops *ops) { struct xfs_buf *bp; - bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags); + bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0); if (!bp) return NULL; @@ -345,7 +344,7 @@ xfs_ag_init_hdr( { struct xfs_buf *bp; - bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, 0, ops); + bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, ops); if (!bp) return -ENOMEM; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index b9f019603d0b..f0089e862216 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -826,32 +826,17 @@ xfs_attr_shortform_to_leaf( sf = (xfs_attr_shortform_t *)tmpbuffer; xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); - xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK); + xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK); bp = NULL; error = xfs_da_grow_inode(args, &blkno); - if (error) { - /* - * If we hit an IO error middle of the transaction inside - * grow_inode(), we may have inconsistent data. Bail out. - */ - if (error == -EIO) - goto out; - xfs_idata_realloc(dp, size, XFS_ATTR_FORK); /* try to put */ - memcpy(ifp->if_u1.if_data, tmpbuffer, size); /* it back */ + if (error) goto out; - } ASSERT(blkno == 0); error = xfs_attr3_leaf_create(args, blkno, &bp); - if (error) { - /* xfs_attr3_leaf_create may not have instantiated a block */ - if (bp && (xfs_da_shrink_inode(args, 0, bp) != 0)) - goto out; - xfs_idata_realloc(dp, size, XFS_ATTR_FORK); /* try to put */ - memcpy(ifp->if_u1.if_data, tmpbuffer, size); /* it back */ + if (error) goto out; - } memset((char *)&nargs, 0, sizeof(nargs)); nargs.dp = dp; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 4edc25a2ba80..02469d59c787 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -792,6 +792,7 @@ out_root_realloc: */ void xfs_bmap_local_to_extents_empty( + struct xfs_trans *tp, struct xfs_inode *ip, int whichfork) { @@ -808,6 +809,7 @@ xfs_bmap_local_to_extents_empty( ifp->if_u1.if_root = NULL; ifp->if_height = 0; XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } @@ -840,7 +842,7 @@ xfs_bmap_local_to_extents( ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); if (!ifp->if_bytes) { - xfs_bmap_local_to_extents_empty(ip, whichfork); + xfs_bmap_local_to_extents_empty(tp, ip, whichfork); flags = XFS_ILOG_CORE; goto done; } @@ -887,7 +889,7 @@ xfs_bmap_local_to_extents( /* account for the change in fork size */ xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); - xfs_bmap_local_to_extents_empty(ip, whichfork); + xfs_bmap_local_to_extents_empty(tp, ip, whichfork); flags |= XFS_ILOG_CORE; ifp->if_u1.if_root = NULL; diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 5bb446d80542..e2798c6f3a5f 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -182,7 +182,8 @@ void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); int xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version); -void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); +void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp, + struct xfs_inode *ip, int whichfork); void __xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, bool skip_discard); diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index 9595ced393dc..49e4bc39e7bb 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -1096,7 +1096,7 @@ xfs_dir2_sf_to_block( memcpy(sfp, oldsfp, ifp->if_bytes); xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK); - xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK); + xfs_bmap_local_to_extents_empty(tp, dp, XFS_DATA_FORK); dp->i_d.di_size = 0; /* diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 93b3793bc5b3..0cab11a5d390 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -341,7 +341,6 @@ xchk_refcountbt_rec( xfs_extlen_t len; xfs_nlink_t refcount; bool has_cowflag; - int error = 0; bno = be32_to_cpu(rec->refc.rc_startblock); len = be32_to_cpu(rec->refc.rc_blockcount); @@ -366,7 +365,7 @@ xchk_refcountbt_rec( xchk_refcountbt_xref(bs->sc, bno, len, refcount); - return error; + return 0; } /* Make sure we have as many refc blocks as the rmap says. */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 0910cb75b65d..4f443703065e 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -864,6 +864,7 @@ xfs_alloc_file_space( xfs_filblks_t allocatesize_fsb; xfs_extlen_t extsz, temp; xfs_fileoff_t startoffset_fsb; + xfs_fileoff_t endoffset_fsb; int nimaps; int quota_flag; int rt; @@ -891,7 +892,8 @@ xfs_alloc_file_space( imapp = &imaps[0]; nimaps = 1; startoffset_fsb = XFS_B_TO_FSBT(mp, offset); - allocatesize_fsb = XFS_B_TO_FSB(mp, count); + endoffset_fsb = XFS_B_TO_FSB(mp, offset + count); + allocatesize_fsb = endoffset_fsb - startoffset_fsb; /* * Allocate file space until done or until there is an error diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 21c243622a79..0abba171aa89 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -345,6 +345,15 @@ xfs_buf_allocate_memory( unsigned short page_count, i; xfs_off_t start, end; int error; + xfs_km_flags_t kmflag_mask = 0; + + /* + * assure zeroed buffer for non-read cases. + */ + if (!(flags & XBF_READ)) { + kmflag_mask |= KM_ZERO; + gfp_mask |= __GFP_ZERO; + } /* * for buffers that are contained within a single page, just allocate @@ -354,7 +363,8 @@ xfs_buf_allocate_memory( size = BBTOB(bp->b_length); if (size < PAGE_SIZE) { int align_mask = xfs_buftarg_dma_alignment(bp->b_target); - bp->b_addr = kmem_alloc_io(size, align_mask, KM_NOFS); + bp->b_addr = kmem_alloc_io(size, align_mask, + KM_NOFS | kmflag_mask); if (!bp->b_addr) { /* low memory - use alloc_page loop instead */ goto use_alloc_page; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a2beee9f74da..641d07f30a27 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1443,7 +1443,7 @@ xlog_alloc_log( prev_iclog = iclog; iclog->ic_data = kmem_alloc_io(log->l_iclog_size, align_mask, - KM_MAYFAIL); + KM_MAYFAIL | KM_ZERO); if (!iclog->ic_data) goto out_free_iclog; #ifdef DEBUG diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 508319039dce..c1a514ffff55 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -127,7 +127,7 @@ xlog_alloc_buffer( if (nbblks > 1 && log->l_sectBBsize > 1) nbblks += log->l_sectBBsize; nbblks = round_up(nbblks, log->l_sectBBsize); - return kmem_alloc_io(BBTOB(nbblks), align_mask, KM_MAYFAIL); + return kmem_alloc_io(BBTOB(nbblks), align_mask, KM_MAYFAIL | KM_ZERO); } /* diff --git a/include/linux/bitops.h b/include/linux/bitops.h index cf074bce3eb3..c94a9ff9f082 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,6 +4,13 @@ #include <asm/types.h> #include <linux/bits.h> +/* Set bits in the first 'n' bytes when loaded from memory */ +#ifdef __LITTLE_ENDIAN +# define aligned_byte_mask(n) ((1UL << 8*(n))-1) +#else +# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) +#endif + #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b318efd8a74..cdf016596659 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -40,6 +40,7 @@ # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +# define __GCC4_has_attribute___fallthrough__ 0 #endif /* @@ -186,6 +187,22 @@ #endif /* + * Add the pseudo keyword 'fallthrough' so case statement blocks + * must end with any of these keywords: + * break; + * fallthrough; + * goto <label>; + * return [expression]; + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html#Statement-Attributes + */ +#if __has_attribute(__fallthrough__) +# define fallthrough __attribute__((__fallthrough__)) +#else +# define fallthrough do {} while (0) /* fallthrough */ +#endif + +/* * Note the missing underscores. * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noinline-function-attribute diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 79435cfc20eb..897e799dbcb9 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -31,6 +31,8 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull +#define SJA1105_HWTS_RX_EN 0 + /* Global tagger data: each struct sja1105_port has a reference to * the structure defined in struct sja1105_private. */ @@ -42,7 +44,7 @@ struct sja1105_tagger_data { * from taggers running on multiple ports on SMP systems */ spinlock_t meta_lock; - bool hwts_rx_en; + unsigned long state; }; struct sja1105_skb_cb { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fcb46b3374c6..719fc3e15ea4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1090,6 +1090,7 @@ enum kvm_stat_kind { struct kvm_stat_data { int offset; + int mode; struct kvm *kvm; }; @@ -1097,6 +1098,7 @@ struct kvm_stats_debugfs_item { const char *name; int offset; enum kvm_stat_kind kind; + int mode; }; extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/leds.h b/include/linux/leds.h index b8df71193329..efb309dba914 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -247,7 +247,7 @@ extern void led_set_brightness(struct led_classdev *led_cdev, /** * led_set_brightness_sync - set LED brightness synchronously * @led_cdev: the LED to set - * @brightness: the brightness to set it to + * @value: the brightness to set it to * * Set an LED's brightness immediately. This function will block * the caller for the time required for accessing device registers, @@ -301,8 +301,7 @@ extern void led_sysfs_enable(struct led_classdev *led_cdev); /** * led_compose_name - compose LED class device name * @dev: LED controller device object - * @child: child fwnode_handle describing a LED or a group of synchronized LEDs; - * it must be provided only for fwnode based LEDs + * @init_data: the LED class device initialization data * @led_classdev_name: composed LED class device name * * Create LED class device name basing on the provided init_data argument. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9b60863429cc..ae703ea3ef48 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -356,6 +356,19 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, + bool in_low_reclaim) +{ + if (mem_cgroup_disabled()) + return 0; + + if (in_low_reclaim) + return READ_ONCE(memcg->memory.emin); + + return max(READ_ONCE(memcg->memory.emin), + READ_ONCE(memcg->memory.elow)); +} + enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); @@ -537,6 +550,8 @@ void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); +unsigned long mem_cgroup_size(struct mem_cgroup *memcg); + void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); @@ -829,6 +844,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, + bool in_low_reclaim) +{ + return 0; +} + static inline enum mem_cgroup_protection mem_cgroup_protected( struct mem_cgroup *root, struct mem_cgroup *memcg) { @@ -968,6 +989,11 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) return 0; } +static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) +{ + return 0; +} + static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { @@ -1264,6 +1290,9 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { + if (mem_cgroup_disabled()) + return; + if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } diff --git a/include/linux/mii.h b/include/linux/mii.h index 5cd824c1c0ca..4ce8901a1af6 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -455,6 +455,15 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising, lp_advertising, lpa & LPA_LPACK); } +static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, + u32 ctrl1000) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, advertising, + ctrl1000 & ADVERTISE_1000HALF); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, advertising, + ctrl1000 & ADVERTISE_1000FULL); +} + /** * linkmode_adv_to_lcl_adv_t * @advertising:pointer to linkmode advertising diff --git a/include/linux/phy.h b/include/linux/phy.h index a7ecbe0e55aa..9a0e981df502 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -678,6 +678,7 @@ static inline bool phy_is_started(struct phy_device *phydev) return phydev->state >= PHY_UP; } +void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); /** @@ -1076,6 +1077,7 @@ int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); +int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e7d3b1a513ef..4351577b14d7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4160,15 +4160,12 @@ static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} #endif /* CONFIG_SKB_EXTENSIONS */ -static inline void nf_reset(struct sk_buff *skb) +static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - skb_ext_del(skb, SKB_EXT_BRIDGE_NF); -#endif } static inline void nf_reset_trace(struct sk_buff *skb) diff --git a/include/linux/slab.h b/include/linux/slab.h index ab2b98ad76e1..4d2a2fa55ed5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -493,6 +493,10 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * + * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN + * bytes. For @size of power of two bytes, the alignment is also guaranteed + * to be at least to the size. + * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 70bbdc38dc37..d4ee6e942562 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, #endif /* ARCH_HAS_NOCACHE_UACCESS */ +extern __must_check int check_zeroed_user(const void __user *from, size_t size); + +/** + * copy_struct_from_user: copy a struct from userspace + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @src: Source address, in userspace. + * @usize: (Alleged) size of @src struct. + * + * Copies a struct from userspace to kernel space, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) + * { + * int err; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + * if (err) + * return err; + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the userspace has passed an old struct to a + * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) + * are to be zero-filled. + * * If @usize > @ksize, then the userspace has passed a new struct to an + * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) + * are checked to ensure they are zeroed, otherwise -E2BIG is returned. + * + * Returns (in all cases, some data may have been copied): + * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_from_user(void *dst, size_t ksize, const void __user *src, + size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Deal with trailing bytes. */ + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + int ret = check_zeroed_user(src + size, rest); + if (ret <= 0) + return ret ?: -E2BIG; + } + /* Copy the interoperable parts of the struct. */ + if (copy_from_user(dst, src, size)) + return -EFAULT; + return 0; +} + /* * probe_kernel_read(): safely attempt to read from a location * @dst: pointer to the buffer that shall take the data @@ -285,8 +355,10 @@ extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) -#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) +#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) +#define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) +#define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) +#define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a13a62db3565..edc5c887a44c 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1068,7 +1068,7 @@ TRACE_EVENT(rxrpc_recvmsg, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call ? call->debug_id : 0; __entry->why = why; __entry->seq = seq; __entry->offset = offset; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index c99b4f2482c6..4fe35d600ab8 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1003,6 +1003,8 @@ struct drm_amdgpu_info_device { __u64 high_va_max; /* gfx10 pa_sc_tile_steering_override */ __u32 pa_sc_tile_steering_override; + /* disabled TCCs */ + __u64 tcc_disabled_mask; }; struct drm_amdgpu_info_hw_ip { diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 1c215ea1798e..e168dc59e9a0 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -45,6 +45,27 @@ struct nvme_passthru_cmd { __u32 result; }; +struct nvme_passthru_cmd64 { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u64 result; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -54,5 +75,7 @@ struct nvme_passthru_cmd { #define NVME_IOCTL_RESET _IO('N', 0x44) #define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45) #define NVME_IOCTL_RESCAN _IO('N', 0x46) +#define NVME_IOCTL_ADMIN64_CMD _IOWR('N', 0x47, struct nvme_passthru_cmd64) +#define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h index 364c350e85cd..62b6f69bd9fb 100644 --- a/include/uapi/linux/pg.h +++ b/include/uapi/linux/pg.h @@ -35,6 +35,9 @@ */ +#ifndef _UAPI_LINUX_PG_H +#define _UAPI_LINUX_PG_H + #define PG_MAGIC 'P' #define PG_RESET 'Z' #define PG_COMMAND 'C' @@ -61,4 +64,4 @@ struct pg_read_hdr { }; -/* end of pg.h */ +#endif /* _UAPI_LINUX_PG_H */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index b3105ac1381a..99335e1f4a27 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -33,8 +33,31 @@ #define CLONE_NEWNET 0x40000000 /* New network namespace */ #define CLONE_IO 0x80000000 /* Clone io context */ -/* - * Arguments for the clone3 syscall +#ifndef __ASSEMBLY__ +/** + * struct clone_args - arguments for the clone3 syscall + * @flags: Flags for the new process as listed above. + * All flags are valid except for CSIGNAL and + * CLONE_DETACHED. + * @pidfd: If CLONE_PIDFD is set, a pidfd will be + * returned in this argument. + * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the + * child process will be returned in the child's + * memory. + * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of + * the child process will be returned in the + * parent's memory. + * @exit_signal: The exit_signal the parent process will be + * sent when the child exits. + * @stack: Specify the location of the stack for the + * child process. + * @stack_size: The size of the stack for the child process. + * @tls: If CLONE_SETTLS is set, the tls descriptor + * is set to tls. + * + * The structure is versioned by size and thus extensible. + * New struct members must go at the end of the struct and + * must be properly 64bit aligned. */ struct clone_args { __aligned_u64 flags; @@ -46,6 +69,9 @@ struct clone_args { __aligned_u64 stack_size; __aligned_u64 tls; }; +#endif + +#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ /* * Scheduling policies diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 98b30c1613b2..d89969aa9942 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -212,30 +212,7 @@ int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr, bool xen_running_on_version_or_later(unsigned int major, unsigned int minor); -efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc); -efi_status_t xen_efi_set_time(efi_time_t *tm); -efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, - efi_time_t *tm); -efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm); -efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 *attr, unsigned long *data_size, - void *data); -efi_status_t xen_efi_get_next_variable(unsigned long *name_size, - efi_char16_t *name, efi_guid_t *vendor); -efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, - void *data); -efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, - u64 *remaining_space, - u64 *max_variable_size); -efi_status_t xen_efi_get_next_high_mono_count(u32 *count); -efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, - unsigned long count, unsigned long sg_list); -efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, - unsigned long count, u64 *max_size, - int *reset_type); -void xen_efi_reset_system(int reset_type, efi_status_t status, - unsigned long data_size, efi_char16_t *data); +void xen_efi_runtime_setup(void); #ifdef CONFIG_PREEMPT diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index ca4e5d44b571..c00b9258fa6a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -87,9 +87,9 @@ void *dma_common_contiguous_remap(struct page *page, size_t size, */ void dma_common_free_remap(void *cpu_addr, size_t size) { - struct page **pages = dma_common_find_pages(cpu_addr); + struct vm_struct *area = find_vm_area(cpu_addr); - if (!pages) { + if (!area || area->flags != VM_DMA_COHERENT) { WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); return; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 4655adbbae10..3f0cb82e4fbc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10586,55 +10586,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, u32 size; int ret; - if (!access_ok(uattr, PERF_ATTR_SIZE_VER0)) - return -EFAULT; - - /* - * zero the full structure, so that a short copy will be nice. - */ + /* Zero the full structure, so that a short copy will be nice. */ memset(attr, 0, sizeof(*attr)); ret = get_user(size, &uattr->size); if (ret) return ret; - if (size > PAGE_SIZE) /* silly large */ - goto err_size; - - if (!size) /* abi compat */ + /* ABI compatibility quirk: */ + if (!size) size = PERF_ATTR_SIZE_VER0; - - if (size < PERF_ATTR_SIZE_VER0) + if (size < PERF_ATTR_SIZE_VER0 || size > PAGE_SIZE) goto err_size; - /* - * If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ - if (size > sizeof(*attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(*attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - ret = get_user(val, addr); - if (ret) - return ret; - if (val) - goto err_size; - } - size = sizeof(*attr); + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; } - ret = copy_from_user(attr, uattr, size); - if (ret) - return -EFAULT; - attr->size = size; if (attr->__reserved_1) diff --git a/kernel/fork.c b/kernel/fork.c index f9572f416126..bcdf53125210 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2525,39 +2525,19 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, - size_t size) + size_t usize) { + int err; struct clone_args args; - if (unlikely(size > PAGE_SIZE)) + if (unlikely(usize > PAGE_SIZE)) return -E2BIG; - - if (unlikely(size < sizeof(struct clone_args))) + if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; - if (unlikely(!access_ok(uargs, size))) - return -EFAULT; - - if (size > sizeof(struct clone_args)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uargs + sizeof(struct clone_args); - end = (void __user *)uargs + size; - - for (; addr < end; addr++) { - if (get_user(val, addr)) - return -EFAULT; - if (val) - return -E2BIG; - } - - size = sizeof(struct clone_args); - } - - if (copy_from_user(&args, uargs, size)) - return -EFAULT; + err = copy_struct_from_user(&args, sizeof(args), uargs, usize); + if (err) + return err; /* * Verify that higher 32bits of exit_signal are unset and that @@ -2604,6 +2584,17 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs) return true; } +/** + * clone3 - create a new process with specific properties + * @uargs: argument structure + * @size: size of @uargs + * + * clone3() is the extensible successor to clone()/clone2(). + * It takes a struct as argument that is versioned by its size. + * + * Return: On success, a positive PID for the child process. + * On error, a negative errno number. + */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; @@ -2934,7 +2925,7 @@ int sysctl_max_threads(struct ctl_table *table, int write, struct ctl_table t; int ret; int threads = max_threads; - int min = MIN_THREADS; + int min = 1; int max = MAX_THREADS; t = *table; @@ -2946,7 +2937,7 @@ int sysctl_max_threads(struct ctl_table *table, int write, if (ret || !write) return ret; - set_max_threads(threads); + max_threads = threads; return 0; } diff --git a/kernel/freezer.c b/kernel/freezer.c index c0738424bb43..dc520f01f99d 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -22,12 +22,6 @@ EXPORT_SYMBOL(system_freezing_cnt); bool pm_freezing; bool pm_nosig_freezing; -/* - * Temporary export for the deadlock workaround in ata_scsi_hotplug(). - * Remove once the hack becomes unnecessary. - */ -EXPORT_SYMBOL_GPL(pm_freezing); - /* protects freezing and frozen transitions */ static DEFINE_SPINLOCK(freezer_lock); diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 9ff449888d9c..aff79e461fc9 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -71,7 +71,10 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 find $cpio_dir -type f -print0 | xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' -tar -Jcf $tarfile -C $cpio_dir/ . > /dev/null +# Create archive and try to normalize metadata for reproducibility +tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --owner=0 --group=0 --sort=name --numeric-owner \ + -Jcf $tarfile -C $cpio_dir/ . > /dev/null echo "$src_files_md5" > kernel/kheaders.md5 echo "$obj_files_md5" >> kernel/kheaders.md5 diff --git a/kernel/panic.c b/kernel/panic.c index 47e8ebccc22b..f470a038b05b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -180,6 +180,7 @@ void panic(const char *fmt, ...) * after setting panic_cpu) from invoking panic() again. */ local_irq_disable(); + preempt_disable_notrace(); /* * It's possible to come here directly from a panic-assertion and diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7880f4f64d0e..dd05a378631a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5106,9 +5106,6 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a u32 size; int ret; - if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0)) - return -EFAULT; - /* Zero the full structure, so that a short copy will be nice: */ memset(attr, 0, sizeof(*attr)); @@ -5116,45 +5113,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a if (ret) return ret; - /* Bail out on silly large: */ - if (size > PAGE_SIZE) - goto err_size; - /* ABI compatibility quirk: */ if (!size) size = SCHED_ATTR_SIZE_VER0; - - if (size < SCHED_ATTR_SIZE_VER0) + if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) goto err_size; - /* - * If we're handed a bigger struct than we know of, - * ensure all the unknown bits are 0 - i.e. new - * user-space does not rely on any kernel feature - * extensions we dont know about yet. - */ - if (size > sizeof(*attr)) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - - addr = (void __user *)uattr + sizeof(*attr); - end = (void __user *)uattr + size; - - for (; addr < end; addr++) { - ret = get_user(val, addr); - if (ret) - return ret; - if (val) - goto err_size; - } - size = sizeof(*attr); + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; } - ret = copy_from_user(attr, uattr, size); - if (ret) - return -EFAULT; - if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && size < SCHED_ATTR_SIZE_VER1) return -EINVAL; @@ -5354,7 +5325,7 @@ sched_attr_copy_to_user(struct sched_attr __user *uattr, * sys_sched_getattr - similar to sched_getparam, but with sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. - * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility. + * @usize: sizeof(attr) for fwd/bwd comp. * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a39bed2c784f..168479a7d61b 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags) */ if (cpu == raw_smp_processor_id()) continue; - rcu_read_lock(); p = rcu_dereference(cpu_rq(cpu)->curr); if (p && p->mm == mm) __cpumask_set_cpu(cpu, tmpmask); diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index c1f5bb590b5e..b5a65e212df2 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt) */ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) { - int bc_moved; /* - * We try to cancel the timer first. If the callback is on - * flight on some other cpu then we let it handle it. If we - * were able to cancel the timer nothing can rearm it as we - * own broadcast_lock. + * This is called either from enter/exit idle code or from the + * broadcast handler. In all cases tick_broadcast_lock is held. * - * However we can also be called from the event handler of - * ce_broadcast_hrtimer itself when it expires. We cannot - * restart the timer because we are in the callback, but we - * can set the expiry time and let the callback return - * HRTIMER_RESTART. + * hrtimer_cancel() cannot be called here neither from the + * broadcast handler nor from the enter/exit idle code. The idle + * code can run into the problem described in bc_shutdown() and the + * broadcast handler cannot wait for itself to complete for obvious + * reasons. * - * Since we are in the idle loop at this point and because - * hrtimer_{start/cancel} functions call into tracing, - * calls to these functions must be bound within RCU_NONIDLE. + * Each caller tries to arm the hrtimer on its own CPU, but if the + * hrtimer callbback function is currently running, then + * hrtimer_start() cannot move it and the timer stays on the CPU on + * which it is assigned at the moment. + * + * As this can be called from idle code, the hrtimer_start() + * invocation has to be wrapped with RCU_NONIDLE() as + * hrtimer_start() can call into tracing. */ - RCU_NONIDLE( - { - bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0; - if (bc_moved) { - hrtimer_start(&bctimer, expires, - HRTIMER_MODE_ABS_PINNED_HARD); - } - } - ); - - if (bc_moved) { - /* Bind the "device" to the cpu */ - bc->bound_on = smp_processor_id(); - } else if (bc->bound_on == smp_processor_id()) { - hrtimer_set_expires(&bctimer, expires); - } + RCU_NONIDLE( { + hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD); + /* + * The core tick broadcast mode expects bc->bound_on to be set + * correctly to prevent a CPU which has the broadcast hrtimer + * armed from going deep idle. + * + * As tick_broadcast_lock is held, nothing can change the cpu + * base which was just established in hrtimer_start() above. So + * the below access is safe even without holding the hrtimer + * base lock. + */ + bc->bound_on = bctimer.base->cpu_base->cpu; + } ); return 0; } @@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) { ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); - if (clockevent_state_oneshot(&ce_broadcast_hrtimer)) - if (ce_broadcast_hrtimer.next_event != KTIME_MAX) - return HRTIMER_RESTART; - return HRTIMER_NORESTART; } diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 28ff554a1be8..6c0005d5dd5c 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -3,16 +3,10 @@ #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> +#include <linux/bitops.h> #include <asm/word-at-a-time.h> -/* Set bits in the first 'n' bytes when loaded from memory */ -#ifdef __LITTLE_ENDIAN -# define aligned_byte_mask(n) ((1ul << 8*(n))-1) -#else -# define aligned_byte_mask(n) (~0xfful << (BITS_PER_LONG - 8 - 8*(n))) -#endif - /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c index 67bcd5dfd847..e365ace06538 100644 --- a/lib/test_user_copy.c +++ b/lib/test_user_copy.c @@ -31,14 +31,133 @@ # define TEST_U64 #endif -#define test(condition, msg) \ -({ \ - int cond = (condition); \ - if (cond) \ - pr_warn("%s\n", msg); \ - cond; \ +#define test(condition, msg, ...) \ +({ \ + int cond = (condition); \ + if (cond) \ + pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__); \ + cond; \ }) +static bool is_zeroed(void *from, size_t size) +{ + return memchr_inv(from, 0x0, size) == NULL; +} + +static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size) +{ + int ret = 0; + size_t start, end, i; + size_t zero_start = size / 4; + size_t zero_end = size - zero_start; + + /* + * We conduct a series of check_nonzero_user() tests on a block of memory + * with the following byte-pattern (trying every possible [start,end] + * pair): + * + * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] + * + * And we verify that check_nonzero_user() acts identically to memchr_inv(). + */ + + memset(kmem, 0x0, size); + for (i = 1; i < zero_start; i += 2) + kmem[i] = 0xff; + for (i = zero_end; i < size; i += 2) + kmem[i] = 0xff; + + ret |= test(copy_to_user(umem, kmem, size), + "legitimate copy_to_user failed"); + + for (start = 0; start <= size; start++) { + for (end = start; end <= size; end++) { + size_t len = end - start; + int retval = check_zeroed_user(umem + start, len); + int expected = is_zeroed(kmem + start, len); + + ret |= test(retval != expected, + "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)", + retval, expected, start, end); + } + } + + return ret; +} + +static int test_copy_struct_from_user(char *kmem, char __user *umem, + size_t size) +{ + int ret = 0; + char *umem_src = NULL, *expected = NULL; + size_t ksize, usize; + + umem_src = kmalloc(size, GFP_KERNEL); + if ((ret |= test(umem_src == NULL, "kmalloc failed"))) + goto out_free; + + expected = kmalloc(size, GFP_KERNEL); + if ((ret |= test(expected == NULL, "kmalloc failed"))) + goto out_free; + + /* Fill umem with a fixed byte pattern. */ + memset(umem_src, 0x3e, size); + ret |= test(copy_to_user(umem, umem_src, size), + "legitimate copy_to_user failed"); + + /* Check basic case -- (usize == ksize). */ + ksize = size; + usize = size; + + memcpy(expected, umem_src, ksize); + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), + "copy_struct_from_user(usize == ksize) failed"); + ret |= test(memcmp(kmem, expected, ksize), + "copy_struct_from_user(usize == ksize) gives unexpected copy"); + + /* Old userspace case -- (usize < ksize). */ + ksize = size; + usize = size / 2; + + memcpy(expected, umem_src, usize); + memset(expected + usize, 0x0, ksize - usize); + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), + "copy_struct_from_user(usize < ksize) failed"); + ret |= test(memcmp(kmem, expected, ksize), + "copy_struct_from_user(usize < ksize) gives unexpected copy"); + + /* New userspace (-E2BIG) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize) != -E2BIG, + "copy_struct_from_user(usize > ksize) didn't give E2BIG"); + + /* New userspace (success) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memcpy(expected, umem_src, ksize); + ret |= test(clear_user(umem + ksize, usize - ksize), + "legitimate clear_user failed"); + + memset(kmem, 0x0, size); + ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), + "copy_struct_from_user(usize > ksize) failed"); + ret |= test(memcmp(kmem, expected, ksize), + "copy_struct_from_user(usize > ksize) gives unexpected copy"); + +out_free: + kfree(expected); + kfree(umem_src); + return ret; +} + static int __init test_user_copy_init(void) { int ret = 0; @@ -106,6 +225,11 @@ static int __init test_user_copy_init(void) #endif #undef test_legit + /* Test usage of check_nonzero_user(). */ + ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE); + /* Test usage of copy_struct_from_user(). */ + ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE); + /* * Invalid usage: none of these copies should succeed. */ diff --git a/lib/textsearch.c b/lib/textsearch.c index 4f16eec5d554..f68dea8806be 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -89,9 +89,9 @@ * goto errout; * } * - * pos = textsearch_find_continuous(conf, \&state, example, strlen(example)); + * pos = textsearch_find_continuous(conf, &state, example, strlen(example)); * if (pos != UINT_MAX) - * panic("Oh my god, dancing chickens at \%d\n", pos); + * panic("Oh my god, dancing chickens at %d\n", pos); * * textsearch_destroy(conf); */ diff --git a/lib/usercopy.c b/lib/usercopy.c index c2bfbcaeb3dc..cbb4d9ec00f2 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/uaccess.h> +#include <linux/bitops.h> /* out-of-line parts */ @@ -31,3 +32,57 @@ unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) } EXPORT_SYMBOL(_copy_to_user); #endif + +/** + * check_zeroed_user: check if a userspace buffer only contains zero bytes + * @from: Source address, in userspace. + * @size: Size of buffer. + * + * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for + * userspace addresses (and is more efficient because we don't care where the + * first non-zero byte is). + * + * Returns: + * * 0: There were non-zero bytes present in the buffer. + * * 1: The buffer was full of zero bytes. + * * -EFAULT: access to userspace failed. + */ +int check_zeroed_user(const void __user *from, size_t size) +{ + unsigned long val; + uintptr_t align = (uintptr_t) from % sizeof(unsigned long); + + if (unlikely(size == 0)) + return 1; + + from -= align; + size += align; + + if (!user_access_begin(from, size)) + return -EFAULT; + + unsafe_get_user(val, (unsigned long __user *) from, err_fault); + if (align) + val &= ~aligned_byte_mask(align); + + while (size > sizeof(unsigned long)) { + if (unlikely(val)) + goto done; + + from += sizeof(unsigned long); + size -= sizeof(unsigned long); + + unsafe_get_user(val, (unsigned long __user *) from, err_fault); + } + + if (size < sizeof(unsigned long)) + val &= aligned_byte_mask(size); + +done: + user_access_end(); + return (val == 0); +err_fault: + user_access_end(); + return -EFAULT; +} +EXPORT_SYMBOL(check_zeroed_user); diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index cc00364bd2c2..9fe698ff62ec 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -24,13 +24,4 @@ config GENERIC_COMPAT_VDSO help This config option enables the compat VDSO layer. -config CROSS_COMPILE_COMPAT_VDSO - string "32 bit Toolchain prefix for compat vDSO" - default "" - depends on GENERIC_COMPAT_VDSO - help - Defines the cross-compiler prefix for compiling compat vDSO. - If a 64 bit compiler (i.e. x86_64) can compile the VDSO for - 32 bit, it does not need to define this parameter. - endif diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d9daa3e422d0..c360f6a6c844 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -239,8 +239,8 @@ static int __init default_bdi_init(void) { int err; - bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE | - WQ_UNBOUND | WQ_SYSFS, 0); + bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | + WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c313c49074ca..bdac56009a38 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1567,6 +1567,11 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) return max; } +unsigned long mem_cgroup_size(struct mem_cgroup *memcg) +{ + return page_counter_read(&memcg->memory); +} + static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { diff --git a/mm/memremap.c b/mm/memremap.c index 32c79b51af86..68204912cc0a 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -13,8 +13,6 @@ #include <linux/xarray.h> static DEFINE_XARRAY(pgmap_array); -#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) -#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 15c2050c629b..c0b2e0306720 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1175,11 +1175,17 @@ static __always_inline bool free_pages_prepare(struct page *page, debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } - arch_free_page(page, order); if (want_init_on_free()) kernel_init_free_pages(page, 1 << order); kernel_poison_pages(page, 1 << order, 0); + /* + * arch_free_page() can make the page's contents inaccessible. s390 + * does this. So nothing which can access the page's contents should + * happen after this. + */ + arch_free_page(page, order); + if (debug_pagealloc_enabled()) kernel_map_pages(page, 1 << order, 0); diff --git a/mm/shmem.c b/mm/shmem.c index cd570cc79c76..220be9fa2c41 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3482,6 +3482,12 @@ static int shmem_parse_options(struct fs_context *fc, void *data) { char *options = data; + if (options) { + int err = security_sb_eat_lsm_opts(options, &fc->security); + if (err) + return err; + } + while (options != NULL) { char *this_char = options; for (;;) { diff --git a/mm/shuffle.c b/mm/shuffle.c index 3ce12481b1dc..b3fe97fd6654 100644 --- a/mm/shuffle.c +++ b/mm/shuffle.c @@ -33,7 +33,7 @@ __meminit void page_alloc_shuffle(enum mm_shuffle_ctl ctl) } static bool shuffle_param; -extern int shuffle_show(char *buffer, const struct kernel_param *kp) +static int shuffle_show(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%c\n", test_bit(SHUFFLE_ENABLE, &shuffle_state) ? 'Y' : 'N'); diff --git a/mm/slab_common.c b/mm/slab_common.c index 6491c3a41805..c29f03adca91 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1030,10 +1030,19 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, unsigned int useroffset, unsigned int usersize) { int err; + unsigned int align = ARCH_KMALLOC_MINALIGN; s->name = name; s->size = s->object_size = size; - s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size); + + /* + * For power of two sizes, guarantee natural alignment for kmalloc + * caches, regardless of SL*B debugging options. + */ + if (is_power_of_2(size)) + align = max(align, size); + s->align = calculate_alignment(flags, align, size); + s->useroffset = useroffset; s->usersize = usersize; @@ -1287,12 +1296,16 @@ void __init create_kmalloc_caches(slab_flags_t flags) */ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) { - void *ret; + void *ret = NULL; struct page *page; flags |= __GFP_COMP; page = alloc_pages(flags, order); - ret = page ? page_address(page) : NULL; + if (likely(page)) { + ret = page_address(page); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); + } ret = kasan_kmalloc_large(ret, size, flags); /* As ret might get tagged, call kmemleak hook after KASAN. */ kmemleak_alloc(ret, size, 1, flags); diff --git a/mm/slob.c b/mm/slob.c index cf377beab962..fa53e9f73893 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -190,7 +190,7 @@ static int slob_last(slob_t *s) static void *slob_new_pages(gfp_t gfp, int order, int node) { - void *page; + struct page *page; #ifdef CONFIG_NUMA if (node != NUMA_NO_NODE) @@ -202,14 +202,21 @@ static void *slob_new_pages(gfp_t gfp, int order, int node) if (!page) return NULL; + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); return page_address(page); } static void slob_free_pages(void *b, int order) { + struct page *sp = virt_to_page(b); + if (current->reclaim_state) current->reclaim_state->reclaimed_slab += 1 << order; - free_pages((unsigned long)b, order); + + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(sp, order); } /* @@ -217,6 +224,7 @@ static void slob_free_pages(void *b, int order) * @sp: Page to look in. * @size: Size of the allocation. * @align: Allocation alignment. + * @align_offset: Offset in the allocated block that will be aligned. * @page_removed_from_list: Return parameter. * * Tries to find a chunk of memory at least @size bytes big within @page. @@ -227,7 +235,7 @@ static void slob_free_pages(void *b, int order) * true (set to false otherwise). */ static void *slob_page_alloc(struct page *sp, size_t size, int align, - bool *page_removed_from_list) + int align_offset, bool *page_removed_from_list) { slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); @@ -236,8 +244,17 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align, for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) { slobidx_t avail = slob_units(cur); + /* + * 'aligned' will hold the address of the slob block so that the + * address 'aligned'+'align_offset' is aligned according to the + * 'align' parameter. This is for kmalloc() which prepends the + * allocated block with its size, so that the block itself is + * aligned when needed. + */ if (align) { - aligned = (slob_t *)ALIGN((unsigned long)cur, align); + aligned = (slob_t *) + (ALIGN((unsigned long)cur + align_offset, align) + - align_offset); delta = aligned - cur; } if (avail >= units + delta) { /* room enough? */ @@ -281,7 +298,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align, /* * slob_alloc: entry point into the slob allocator. */ -static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) +static void *slob_alloc(size_t size, gfp_t gfp, int align, int node, + int align_offset) { struct page *sp; struct list_head *slob_list; @@ -312,7 +330,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) if (sp->units < SLOB_UNITS(size)) continue; - b = slob_page_alloc(sp, size, align, &page_removed_from_list); + b = slob_page_alloc(sp, size, align, align_offset, &page_removed_from_list); if (!b) continue; @@ -349,7 +367,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) INIT_LIST_HEAD(&sp->slab_list); set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); set_slob_page_free(sp, slob_list); - b = slob_page_alloc(sp, size, align, &_unused); + b = slob_page_alloc(sp, size, align, align_offset, &_unused); BUG_ON(!b); spin_unlock_irqrestore(&slob_lock, flags); } @@ -451,7 +469,7 @@ static __always_inline void * __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) { unsigned int *m; - int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); void *ret; gfp &= gfp_allowed_mask; @@ -459,19 +477,28 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) fs_reclaim_acquire(gfp); fs_reclaim_release(gfp); - if (size < PAGE_SIZE - align) { + if (size < PAGE_SIZE - minalign) { + int align = minalign; + + /* + * For power of two sizes, guarantee natural alignment for + * kmalloc()'d objects. + */ + if (is_power_of_2(size)) + align = max(minalign, (int) size); + if (!size) return ZERO_SIZE_PTR; - m = slob_alloc(size + align, gfp, align, node); + m = slob_alloc(size + minalign, gfp, align, node, minalign); if (!m) return NULL; *m = size; - ret = (void *)m + align; + ret = (void *)m + minalign; trace_kmalloc_node(caller, ret, - size, size + align, gfp, node); + size, size + minalign, gfp, node); } else { unsigned int order = get_order(size); @@ -521,8 +548,13 @@ void kfree(const void *block) int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); - } else - __free_pages(sp, compound_order(sp)); + } else { + unsigned int order = compound_order(sp); + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(sp, order); + + } } EXPORT_SYMBOL(kfree); @@ -567,7 +599,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) fs_reclaim_release(flags); if (c->size < PAGE_SIZE) { - b = slob_alloc(c->size, flags, c->align, node); + b = slob_alloc(c->size, flags, c->align, node, 0); trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size, SLOB_UNITS(c->size) * SLOB_UNIT, flags, node); diff --git a/mm/slub.c b/mm/slub.c index 42c1b3af3c98..3d63ae320d31 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3821,11 +3821,15 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) { struct page *page; void *ptr = NULL; + unsigned int order = get_order(size); flags |= __GFP_COMP; - page = alloc_pages_node(node, flags, get_order(size)); - if (page) + page = alloc_pages_node(node, flags, order); + if (page) { ptr = page_address(page); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); + } return kmalloc_large_node_hook(ptr, size, flags); } @@ -3951,9 +3955,13 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { + unsigned int order = compound_order(page); + BUG_ON(!PageCompound(page)); kfree_hook(object); - __free_pages(page, compound_order(page)); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(page, order); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); diff --git a/mm/sparse.c b/mm/sparse.c index bf32de9e666b..f6891c1992b1 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -219,7 +219,7 @@ static inline unsigned long first_present_section_nr(void) return next_present_section_nr(-1); } -void subsection_mask_set(unsigned long *map, unsigned long pfn, +static void subsection_mask_set(unsigned long *map, unsigned long pfn, unsigned long nr_pages) { int idx = subsection_map_index(pfn); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index f3b50811497a..4bac22fe1aa2 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -355,6 +355,9 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * "hierarchy" or "local"). * * To be used as memcg event method. + * + * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could + * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) @@ -362,7 +365,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg, struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; - enum vmpressure_levels level = -1; + enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; @@ -375,20 +378,18 @@ int vmpressure_register_event(struct mem_cgroup *memcg, /* Find required level */ token = strsep(&spec, ","); - level = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); - if (level < 0) { - ret = level; + ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); + if (ret < 0) goto out; - } + level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { - mode = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); - if (mode < 0) { - ret = mode; + ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); + if (ret < 0) goto out; - } + mode = ret; } ev = kzalloc(sizeof(*ev), GFP_KERNEL); @@ -404,6 +405,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg, mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); + ret = 0; out: kfree(spec_orig); return ret; diff --git a/mm/vmscan.c b/mm/vmscan.c index e5d52d6a24af..c6659bb758a4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2459,17 +2459,70 @@ out: *lru_pages = 0; for_each_evictable_lru(lru) { int file = is_file_lru(lru); - unsigned long size; + unsigned long lruvec_size; unsigned long scan; + unsigned long protection; + + lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); + protection = mem_cgroup_protection(memcg, + sc->memcg_low_reclaim); + + if (protection) { + /* + * Scale a cgroup's reclaim pressure by proportioning + * its current usage to its memory.low or memory.min + * setting. + * + * This is important, as otherwise scanning aggression + * becomes extremely binary -- from nothing as we + * approach the memory protection threshold, to totally + * nominal as we exceed it. This results in requiring + * setting extremely liberal protection thresholds. It + * also means we simply get no protection at all if we + * set it too low, which is not ideal. + * + * If there is any protection in place, we reduce scan + * pressure by how much of the total memory used is + * within protection thresholds. + * + * There is one special case: in the first reclaim pass, + * we skip over all groups that are within their low + * protection. If that fails to reclaim enough pages to + * satisfy the reclaim goal, we come back and override + * the best-effort low protection. However, we still + * ideally want to honor how well-behaved groups are in + * that case instead of simply punishing them all + * equally. As such, we reclaim them based on how much + * memory they are using, reducing the scan pressure + * again by how much of the total memory used is under + * hard protection. + */ + unsigned long cgroup_size = mem_cgroup_size(memcg); + + /* Avoid TOCTOU with earlier protection check */ + cgroup_size = max(cgroup_size, protection); + + scan = lruvec_size - lruvec_size * protection / + cgroup_size; + + /* + * Minimally target SWAP_CLUSTER_MAX pages to keep + * reclaim moving forwards, avoiding decremeting + * sc->priority further than desirable. + */ + scan = max(scan, SWAP_CLUSTER_MAX); + } else { + scan = lruvec_size; + } + + scan >>= sc->priority; - size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - scan = size >> sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) - scan = min(size, SWAP_CLUSTER_MAX); + scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: @@ -2489,7 +2542,7 @@ out: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) { - size = 0; + lruvec_size = 0; scan = 0; } break; @@ -2498,7 +2551,7 @@ out: BUG(); } - *lru_pages += size; + *lru_pages += lruvec_size; nr[lru] = scan; } } @@ -2742,6 +2795,13 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) memcg_memory_event(memcg, MEMCG_LOW); break; case MEMCG_PROT_NONE: + /* + * All protection thresholds breached. We may + * still choose to vary the scan pressure + * applied based on by how much the cgroup in + * question has exceeded its protection + * thresholds (see get_scan_count). + */ break; } diff --git a/mm/z3fold.c b/mm/z3fold.c index 05bdf90646e7..6d3d3f698ebb 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -998,9 +998,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) struct z3fold_header *zhdr; struct page *page; enum buddy bud; + bool page_claimed; zhdr = handle_to_z3fold_header(handle); page = virt_to_page(zhdr); + page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private); if (test_bit(PAGE_HEADLESS, &page->private)) { /* if a headless page is under reclaim, just leave. @@ -1008,7 +1010,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) * has not been set before, we release this page * immediately so we don't care about its value any more. */ - if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) { + if (!page_claimed) { spin_lock(&pool->lock); list_del(&page->lru); spin_unlock(&pool->lock); @@ -1044,13 +1046,15 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } - if (test_bit(PAGE_CLAIMED, &page->private)) { + if (page_claimed) { + /* the page has not been claimed by us */ z3fold_page_unlock(zhdr); return; } if (unlikely(PageIsolated(page)) || test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); return; } if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { @@ -1060,10 +1064,12 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) zhdr->cpu = -1; kref_get(&zhdr->refcount); do_compact_page(zhdr, true); + clear_bit(PAGE_CLAIMED, &page->private); return; } kref_get(&zhdr->refcount); queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); + clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a1146cb10919..9cbed6f5a85a 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -436,7 +436,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* clean the netfilter state now that the batman-adv header has been * removed */ - nf_reset(skb); + nf_reset_ct(skb); if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) goto dropped; diff --git a/net/core/devlink.c b/net/core/devlink.c index e48680efe54a..f80151eeaf51 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3172,7 +3172,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { + if (err && err != -EOPNOTSUPP) { mutex_unlock(&devlink->lock); goto out; } @@ -3432,7 +3432,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { + if (err && err != -EOPNOTSUPP) { mutex_unlock(&devlink->lock); goto out; } @@ -4088,7 +4088,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); mutex_unlock(&devlink->lock); - if (err) + if (err && err != -EOPNOTSUPP) break; idx++; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 01d65206f4fb..529133611ea2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5120,7 +5120,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); - nf_reset(skb); + nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV diff --git a/net/core/sock.c b/net/core/sock.c index 07863edbe6fc..fac2b4d80de5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1700,8 +1700,6 @@ static void __sk_destruct(struct rcu_head *head) sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } - if (rcu_access_pointer(sk->sk_reuseport_cb)) - reuseport_detach_sock(sk); sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); @@ -1728,7 +1726,14 @@ static void __sk_destruct(struct rcu_head *head) void sk_destruct(struct sock *sk) { - if (sock_flag(sk, SOCK_RCU_FREE)) + bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); + + if (rcu_access_pointer(sk->sk_reuseport_cb)) { + reuseport_detach_sock(sk); + use_call_rcu = true; + } + + if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); @@ -3492,7 +3497,7 @@ static long sock_prot_memory_allocated(struct proto *proto) return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } -static char *sock_prot_memory_pressure(struct proto *proto) +static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b685bc82f8d0..d9b4200ed12d 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -871,7 +871,7 @@ lookup: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - nf_reset(skb); + nf_reset_ct(skb); return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9c9aff3e52cf..63ef2a14c934 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -156,7 +156,11 @@ static struct sk_buff /* Step 1: A timestampable frame was received. * Buffer it until we get its meta frame. */ - if (is_link_local && sp->data->hwts_rx_en) { + if (is_link_local) { + if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + /* Do normal processing. */ + return skb; + spin_lock(&sp->data->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? @@ -187,6 +191,12 @@ static struct sk_buff } else if (is_meta) { struct sk_buff *stampable_skb; + /* Drop the meta frame if we're not in the right state + * to process it. + */ + if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + return NULL; + spin_lock(&sp->data->meta_lock); stampable_skb = sp->data->stampable_skb; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a53a543fe055..52690bb3e40f 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1446,6 +1446,7 @@ static void erspan_setup(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1e2392b7c64e..c59a78a267c3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -199,7 +199,7 @@ resubmit: kfree_skb(skb); return; } - nf_reset(skb); + nf_reset_ct(skb); } ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv, skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 313470f6bb14..716d5472c022 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1794,7 +1794,7 @@ static void ip_encap(struct net *net, struct sk_buff *skb, ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - nf_reset(skb); + nf_reset_ct(skb); } static inline int ipmr_forward_finish(struct net *net, struct sock *sk, @@ -2140,7 +2140,7 @@ int ip_mr_input(struct sk_buff *skb) mroute_sk = rcu_dereference(mrt->mroute_sk); if (mroute_sk) { - nf_reset(skb); + nf_reset_ct(skb); raw_rcv(mroute_sk, skb); return 0; } diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index af3fbf76dbd3..6cc5743c553a 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -65,7 +65,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Avoid counting cloned packets towards the original connection. */ - nf_reset(skb); + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); #endif /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 80da5a66d5d7..3183413ebc6c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -332,7 +332,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - nf_reset(skb); + nf_reset_ct(skb); skb_push(skb, skb->data - skb_network_header(skb)); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7dcce724c78b..14654876127e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -916,16 +916,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (peer->rate_tokens == 0 || time_after(jiffies, (peer->rate_last + - (ip_rt_redirect_load << peer->rate_tokens)))) { + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; - ++peer->rate_tokens; ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number) + peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 79c325a07ba5..f98a1882e537 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1798,13 +1798,11 @@ static int tcp_zerocopy_receive(struct sock *sk, } if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; - int size = skb_frag_size(frags); - while (remaining && (size != PAGE_SIZE || + while (remaining && (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags))) { - remaining -= size; + remaining -= skb_frag_size(frags); frags++; - size = skb_frag_size(frags); } zc->recv_skip_hint -= remaining; break; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2ee45e3755e9..bf124b1742df 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1916,7 +1916,7 @@ process: if (tcp_v4_inbound_md5_hash(sk, skb)) goto discard_and_relse; - nf_reset(skb); + nf_reset_ct(skb); if (tcp_filter(sk, skb)) goto discard_and_relse; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 40de2d2364a1..05be564414e9 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -198,8 +198,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (likely(timeout == 0)) - timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN); + if (likely(timeout == 0)) { + unsigned int rto_base = TCP_RTO_MIN; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + timeout = tcp_model_timeout(sk, boundary, rto_base); + } return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cf755156a684..14bc654b6842 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -821,6 +821,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); __wsum csum = 0; /* @@ -854,10 +855,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, return -EIO; } - skb_shinfo(skb)->gso_size = cork->gso_size; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh), - cork->gso_size); + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + } goto csum_partial; } @@ -1969,7 +1972,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) */ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); @@ -2298,7 +2301,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_lib_checksum_complete(skb)) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a576ff92c39..34ccef18b40e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5964,13 +5964,20 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: /* - * If the address was optimistic - * we inserted the route at the start of - * our DAD process, so we don't need - * to do it again + * If the address was optimistic we inserted the route at the + * start of our DAD process, so we don't need to do it again. + * If the device was taken down in the middle of the DAD + * cycle there is a race where we could get here without a + * host route, so nothing to insert. That will be fixed when + * the device is brought up. */ - if (!rcu_access_pointer(ifp->rt->fib6_node)) + if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) { ip6_ins_rt(net, ifp->rt); + } else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) { + pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n", + &ifp->addr, ifp->idev->dev->name); + } + if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index d432d0011c16..3d71c7d6102c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -223,6 +223,16 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; + /* While RFC4291 is not explicit about v4mapped addresses + * in IPv6 headers, it seems clear linux dual-stack + * model can not deal properly with these. + * Security models could be fooled by ::ffff:127.0.0.1 for example. + * + * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02 + */ + if (ipv6_addr_v4mapped(&hdr->saddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); @@ -371,7 +381,7 @@ resubmit_final: /* Free reference early: we don't need it any more, and it may hold ip_conntrack module loaded indefinitely. */ - nf_reset(skb); + nf_reset_ct(skb); skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index e6c9da9866b1..a0a2de30be3e 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -54,7 +54,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, return; #if IS_ENABLED(CONFIG_NF_CONNTRACK) - nf_reset(skb); + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); #endif if (hooknum == NF_INET_PRE_ROUTING || diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 6e1888ee4036..a77f6b7d3a7c 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -215,7 +215,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) /* Not releasing hash table! */ if (clone) { - nf_reset(clone); + nf_reset_ct(clone); rawv6_rcv(sk, clone); } } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index aae4938f3dea..6324d3a8cb53 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1109,6 +1109,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, __wsum csum = 0; int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); /* * Create a UDP header @@ -1141,8 +1142,12 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, return -EIO; } - skb_shinfo(skb)->gso_size = cork->gso_size; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + } goto csum_partial; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 105e5a7092e7..f82ea12bac37 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1078,7 +1078,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); - nf_reset(skb); + nf_reset_ct(skb); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index bd3f39349d40..fd5ac2788e45 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -151,7 +151,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, skb->ip_summed = CHECKSUM_NONE; skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); rcu_read_lock(); dev = rcu_dereference(spriv->dev); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 622833317dcb..0d7c887a2b75 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -193,7 +193,7 @@ pass_up: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; - nf_reset(skb); + nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 687e23a8b326..802f19aba7e3 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -206,7 +206,7 @@ pass_up: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; - nf_reset(skb); + nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index b1438fd4d876..64b544ae9966 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -487,9 +487,14 @@ static ssize_t ieee80211_if_fmt_aqm( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { struct ieee80211_local *local = sdata->local; - struct txq_info *txqi = to_txq_info(sdata->vif.txq); + struct txq_info *txqi; int len; + if (!sdata->vif.txq) + return 0; + + txqi = to_txq_info(sdata->vif.txq); + spin_lock_bh(&local->fq.lock); rcu_read_lock(); @@ -658,7 +663,9 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); - if (sdata->local->ops->wake_tx_queue) + if (sdata->local->ops->wake_tx_queue && + sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && + sdata->vif.type != NL80211_IFTYPE_NAN) DEBUGFS_ADD(aqm); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 051a02ddcb85..32a7a53833c0 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -247,7 +247,8 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) struct sta_info *sta; int i; - spin_lock_bh(&fq->lock); + local_bh_disable(); + spin_lock(&fq->lock); if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; @@ -273,9 +274,9 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) &txqi->flags)) continue; - spin_unlock_bh(&fq->lock); + spin_unlock(&fq->lock); drv_wake_tx_queue(local, txqi); - spin_lock_bh(&fq->lock); + spin_lock(&fq->lock); } } @@ -288,12 +289,14 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac) goto out; - spin_unlock_bh(&fq->lock); + spin_unlock(&fq->lock); drv_wake_tx_queue(local, txqi); + local_bh_enable(); return; out: - spin_unlock_bh(&fq->lock); + spin_unlock(&fq->lock); + local_bh_enable(); } static void diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9c464d24beec..888d3068a492 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -613,7 +613,7 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (unlikely(cp->flags & IP_VS_CONN_F_NFCT)) ret = ip_vs_confirm_conntrack(skb); if (ret == NF_ACCEPT) { - nf_reset(skb); + nf_reset_ct(skb); skb_forward_csum(skb); } return ret; diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index af1497ab9464..69d6173f91e2 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -218,8 +218,13 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); + bool ret; - return nf_conncount_gc_list(net, &priv->list); + local_bh_disable(); + ret = nf_conncount_gc_list(net, &priv->list); + local_bh_enable(); + + return ret; } static struct nft_expr_type nft_connlimit_type; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 8dfea26536c9..ccdd790e163a 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -107,9 +107,14 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) llcp_sock->service_name = kmemdup(llcp_addr.service_name, llcp_sock->service_name_len, GFP_KERNEL); - + if (!llcp_sock->service_name) { + ret = -ENOMEM; + goto put_dev; + } llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); if (llcp_sock->ssap == LLCP_SAP_MAX) { + kfree(llcp_sock->service_name); + llcp_sock->service_name = NULL; ret = -EADDRINUSE; goto put_dev; } diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index d2437b5b2f6a..21c90d3a7ebf 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -237,7 +237,7 @@ static netdev_tx_t internal_dev_recv(struct sk_buff *skb) } skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); secpath_reset(skb); skb->pkt_type = PACKET_HOST; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e2742b006d25..82a50e850245 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1821,7 +1821,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); /* drop conntrack reference */ - nf_reset(skb); + nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; @@ -2121,7 +2121,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); /* drop conntrack reference */ - nf_reset(skb); + nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; diff --git a/net/rds/ib.c b/net/rds/ib.c index 45acab2de0cf..9de2ae22d583 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -143,6 +143,9 @@ static void rds_ib_add_one(struct ib_device *device) refcount_set(&rds_ibdev->refcount, 1); INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); + INIT_LIST_HEAD(&rds_ibdev->ipaddr_list); + INIT_LIST_HEAD(&rds_ibdev->conn_list); + rds_ibdev->max_wrs = device->attrs.max_qp_wr; rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE); @@ -203,9 +206,6 @@ static void rds_ib_add_one(struct ib_device *device) device->name, rds_ibdev->use_fastreg ? "FRMR" : "FMR"); - INIT_LIST_HEAD(&rds_ibdev->ipaddr_list); - INIT_LIST_HEAD(&rds_ibdev->conn_list); - down_write(&rds_ib_devices_lock); list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices); up_write(&rds_ib_devices_lock); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 06c7a2da21bc..39b427dc7512 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1127,6 +1127,33 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, }; +static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], + struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, + cbq_policy, extack); + if (err < 0) + return err; + + if (tb[TCA_CBQ_WRROPT]) { + const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); + + if (wrr->priority > TC_CBQ_MAXPRIO) { + NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); + err = -EINVAL; + } + } + return err; +} + static int cbq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1139,13 +1166,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt, hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); q->delay_timer.function = cbq_undelay; - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy, - extack); + err = cbq_opt_parse(tb, opt, extack); if (err < 0) return err; @@ -1464,13 +1485,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t struct cbq_class *parent; struct qdisc_rate_table *rtab = NULL; - if (!opt) { - NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy, - extack); + err = cbq_opt_parse(tb, opt, extack); if (err < 0) return err; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 1bef152c5721..b2905b03a432 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -306,7 +306,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) if (err < 0) goto skip; - if (ecmd.base.speed != SPEED_UNKNOWN) + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index bad1cbe59a56..05605b30bef3 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -361,6 +361,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, goto errout; err = -EINVAL; + if (!tb[TCA_DSMARK_INDICES]) + goto errout; indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); if (hweight32(indices) != 1) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 2f7b34205c82..68b543f85a96 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1044,12 +1044,11 @@ static void taprio_set_picos_per_byte(struct net_device *dev, if (err < 0) goto skip; - if (ecmd.base.speed != SPEED_UNKNOWN) + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: - picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - speed * 1000 * 1000); + picos_per_byte = (USEC_PER_SEC * 8) / speed; atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", diff --git a/net/sctp/input.c b/net/sctp/input.c index 1008cdc44dd6..5a070fb5b278 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -201,7 +201,7 @@ int sctp_rcv(struct sk_buff *skb) if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family)) goto discard_release; - nf_reset(skb); + nf_reset_ct(skb); if (sk_filter(sk, skb)) goto discard_release; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e41ed2e0ae7d..48d63956a68c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2155,7 +2155,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_SET_PRIMARY: if (ep->asconf_enable) break; - goto fallthrough; + goto unhandled; case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ @@ -2166,11 +2166,11 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_FWD_TSN_SUPPORT: if (ep->prsctp_enable) break; - goto fallthrough; + goto unhandled; case SCTP_PARAM_RANDOM: if (!ep->auth_enable) - goto fallthrough; + goto unhandled; /* SCTP-AUTH: Secion 6.1 * If the random number is not 32 byte long the association @@ -2187,7 +2187,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_CHUNKS: if (!ep->auth_enable) - goto fallthrough; + goto unhandled; /* SCTP-AUTH: Section 3.2 * The CHUNKS parameter MUST be included once in the INIT or @@ -2203,7 +2203,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_HMAC_ALGO: if (!ep->auth_enable) - goto fallthrough; + goto unhandled; hmacs = (struct sctp_hmac_algo_param *)param.p; n_elt = (ntohs(param.p->length) - @@ -2226,7 +2226,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, retval = SCTP_IERROR_ABORT; } break; -fallthrough: +unhandled: default: pr_debug("%s: unrecognized param:%d for chunk:%d\n", __func__, ntohs(param.p->type), cid); diff --git a/net/tipc/link.c b/net/tipc/link.c index 6cc75ffd9e2c..999eab592de8 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -160,6 +160,7 @@ struct tipc_link { struct { u16 len; u16 limit; + struct sk_buff *target_bskb; } backlog[5]; u16 snd_nxt; u16 window; @@ -880,6 +881,7 @@ static void link_prepare_wakeup(struct tipc_link *l) void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; + u32 imp; __skb_queue_head_init(&list); @@ -901,11 +903,10 @@ void tipc_link_reset(struct tipc_link *l) __skb_queue_purge(&l->deferdq); __skb_queue_purge(&l->backlogq); __skb_queue_purge(&l->failover_deferdq); - l->backlog[TIPC_LOW_IMPORTANCE].len = 0; - l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; - l->backlog[TIPC_HIGH_IMPORTANCE].len = 0; - l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; - l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; + for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) { + l->backlog[imp].len = 0; + l->backlog[imp].target_bskb = NULL; + } kfree_skb(l->reasm_buf); kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); @@ -947,7 +948,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; struct sk_buff_head *transmq = &l->transmq; struct sk_buff_head *backlogq = &l->backlogq; - struct sk_buff *skb, *_skb, *bskb; + struct sk_buff *skb, *_skb, **tskb; int pkt_cnt = skb_queue_len(list); int rc = 0; @@ -999,19 +1000,21 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, seqno++; continue; } - if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) { + tskb = &l->backlog[imp].target_bskb; + if (tipc_msg_bundle(*tskb, hdr, mtu)) { kfree_skb(__skb_dequeue(list)); l->stats.sent_bundled++; continue; } - if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) { + if (tipc_msg_make_bundle(tskb, hdr, mtu, l->addr)) { kfree_skb(__skb_dequeue(list)); - __skb_queue_tail(backlogq, bskb); - l->backlog[msg_importance(buf_msg(bskb))].len++; + __skb_queue_tail(backlogq, *tskb); + l->backlog[imp].len++; l->stats.sent_bundled++; l->stats.sent_bundles++; continue; } + l->backlog[imp].target_bskb = NULL; l->backlog[imp].len += skb_queue_len(list); skb_queue_splice_tail_init(list, backlogq); } @@ -1027,6 +1030,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l, u16 seqno = l->snd_nxt; u16 ack = l->rcv_nxt - 1; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u32 imp; while (skb_queue_len(&l->transmq) < l->window) { skb = skb_peek(&l->backlogq); @@ -1037,7 +1041,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l, break; __skb_dequeue(&l->backlogq); hdr = buf_msg(skb); - l->backlog[msg_importance(hdr)].len--; + imp = msg_importance(hdr); + l->backlog[imp].len--; + if (unlikely(skb == l->backlog[imp].target_bskb)) + l->backlog[imp].target_bskb = NULL; __skb_queue_tail(&l->transmq, skb); /* next retransmit attempt */ if (link_is_bc_sndlink(l)) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index e6d49cdc61b4..922d262e153f 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -543,10 +543,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, bmsg = buf_msg(_skb); tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode); - if (msg_isdata(msg)) - msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE); - else - msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE); + msg_set_importance(bmsg, msg_importance(msg)); msg_set_seqno(bmsg, msg_seqno(msg)); msg_set_ack(bmsg, msg_ack(msg)); msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ab47bf3ab66e..2ab43b2bba31 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -638,7 +638,7 @@ struct sock *__vsock_create(struct net *net, } EXPORT_SYMBOL_GPL(__vsock_create); -static void __vsock_release(struct sock *sk) +static void __vsock_release(struct sock *sk, int level) { if (sk) { struct sk_buff *skb; @@ -648,9 +648,17 @@ static void __vsock_release(struct sock *sk) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ + /* The release call is supposed to use lock_sock_nested() + * rather than lock_sock(), if a sock lock should be acquired. + */ transport->release(vsk); - lock_sock(sk); + /* When "level" is SINGLE_DEPTH_NESTING, use the nested + * version to avoid the warning "possible recursive locking + * detected". When "level" is 0, lock_sock_nested(sk, level) + * is the same as lock_sock(sk). + */ + lock_sock_nested(sk, level); sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; @@ -659,7 +667,7 @@ static void __vsock_release(struct sock *sk) /* Clean up any sockets that never were accepted. */ while ((pending = vsock_dequeue_accept(sk)) != NULL) { - __vsock_release(pending); + __vsock_release(pending, SINGLE_DEPTH_NESTING); sock_put(pending); } @@ -708,7 +716,7 @@ EXPORT_SYMBOL_GPL(vsock_stream_has_space); static int vsock_release(struct socket *sock) { - __vsock_release(sock->sk); + __vsock_release(sock->sk, 0); sock->sk = NULL; sock->state = SS_FREE; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 261521d286d6..c443db7af8d4 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -559,7 +559,7 @@ static void hvs_release(struct vsock_sock *vsk) struct sock *sk = sk_vsock(vsk); bool remove_sock; - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); remove_sock = hvs_close_lock_held(vsk); release_sock(sk); if (remove_sock) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 5bb70c692b1e..a666ef8fc54e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -820,7 +820,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d21b1581a665..141cdb171665 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -201,6 +201,38 @@ cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info) return __cfg80211_rdev_from_attrs(netns, info->attrs); } +static int validate_beacon_head(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + const u8 *data = nla_data(attr); + unsigned int len = nla_len(attr); + const struct element *elem; + const struct ieee80211_mgmt *mgmt = (void *)data; + unsigned int fixedlen = offsetof(struct ieee80211_mgmt, + u.beacon.variable); + + if (len < fixedlen) + goto err; + + if (ieee80211_hdrlen(mgmt->frame_control) != + offsetof(struct ieee80211_mgmt, u.beacon)) + goto err; + + data += fixedlen; + len -= fixedlen; + + for_each_element(elem, data, len) { + /* nothing */ + } + + if (for_each_element_completed(elem, data, len)) + return 0; + +err: + NL_SET_ERR_MSG_ATTR(extack, attr, "malformed beacon head"); + return -EINVAL; +} + static int validate_ie_attr(const struct nlattr *attr, struct netlink_ext_ack *extack) { @@ -338,8 +370,9 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BEACON_INTERVAL] = { .type = NLA_U32 }, [NL80211_ATTR_DTIM_PERIOD] = { .type = NLA_U32 }, - [NL80211_ATTR_BEACON_HEAD] = { .type = NLA_BINARY, - .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_BEACON_HEAD] = + NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_beacon_head, + IEEE80211_MAX_DATA_LEN), [NL80211_ATTR_BEACON_TAIL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_ie_attr, IEEE80211_MAX_DATA_LEN), @@ -2636,6 +2669,8 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, control_freq = nla_get_u32(attrs[NL80211_ATTR_WIPHY_FREQ]); + memset(chandef, 0, sizeof(*chandef)); + chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq); chandef->width = NL80211_CHAN_WIDTH_20_NOHT; chandef->center_freq1 = control_freq; @@ -3176,7 +3211,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag if (rdev->ops->get_channel) { int ret; - struct cfg80211_chan_def chandef; + struct cfg80211_chan_def chandef = {}; ret = rdev_get_channel(rdev, wdev, &chandef); if (ret == 0) { @@ -6270,6 +6305,9 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->del_mpath) return -EOPNOTSUPP; + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + return rdev_del_mpath(rdev, dev, dst); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5311d0ae2454..420c4207ab59 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2108,7 +2108,7 @@ static void reg_call_notifier(struct wiphy *wiphy, static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) { - struct cfg80211_chan_def chandef; + struct cfg80211_chan_def chandef = {}; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); enum nl80211_iftype iftype; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d313c9befa23..ff1016607f0b 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1723,7 +1723,12 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, return; new_ie_len -= trans_ssid[1]; mbssid = cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen); - if (!mbssid) + /* + * It's not valid to have the MBSSID element before SSID + * ignore if that happens - the code below assumes it is + * after (while copying things inbetween). + */ + if (!mbssid || mbssid < trans_ssid) return; new_ie_len -= mbssid[1]; rcu_read_lock(); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 7b6529d81c61..cac9e28d852b 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -798,7 +798,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - struct cfg80211_chan_def chandef; + struct cfg80211_chan_def chandef = {}; int ret; switch (wdev->iftype) { diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 6088bc2dc11e..9b599ed66d97 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -706,7 +706,7 @@ resume: if (err) goto drop; - nf_reset(skb); + nf_reset_ct(skb); if (decaps) { sp = skb_sec_path(skb); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 2ab4859df55a..0f5131bc3342 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -185,7 +185,7 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - nf_reset(skb); + nf_reset_ct(skb); nf_reset_trace(skb); if (!xnet) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9499b35feb92..b1db55b50ba1 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -502,7 +502,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) struct net *net = xs_net(skb_dst(skb)->xfrm); while (likely((err = xfrm_output_one(skb, err)) == 0)) { - nf_reset(skb); + nf_reset_ct(skb); err = skb_dst(skb)->ops->local_out(net, skb->sk, skb); if (unlikely(err != 1)) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 21e939235b39..f2d1e573ea55 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2808,7 +2808,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) continue; } - nf_reset(skb); + nf_reset_ct(skb); skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 4b0432e095ae..10ba926ae292 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -143,11 +143,6 @@ cc-ifversion = $(shell [ $(CONFIG_GCC_VERSION)0 $(1) $(2)000 ] && echo $(3) || e # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y) ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) -# ar-option -# Usage: KBUILD_ARFLAGS := $(call ar-option,D) -# Important: no spaces around options -ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2)) - # ld-version # Note this is mainly for HJ Lu's 3 number binutil versions ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index f72aba64d611..a9e47953ca53 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -389,7 +389,7 @@ $(sort $(subdir-obj-y)): $(subdir-ym) ; ifdef builtin-target quiet_cmd_ar_builtin = AR $@ - cmd_ar_builtin = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) $@ $(real-prereqs) + cmd_ar_builtin = rm -f $@; $(AR) cDPrST $@ $(real-prereqs) $(builtin-target): $(real-obj-y) FORCE $(call if_changed,ar_builtin) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 4a0cdd6f5909..179d55af5852 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -232,7 +232,7 @@ quiet_cmd_ld = LD $@ # --------------------------------------------------------------------------- quiet_cmd_ar = AR $@ - cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(real-prereqs) + cmd_ar = rm -f $@; $(AR) cDPrsT $@ $(real-prereqs) # Objcopy # --------------------------------------------------------------------------- diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 4d2cdb4d71e3..936d3ad23c83 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2653,15 +2653,20 @@ int main(int argc, char **argv) fatal("modpost: Section mismatches detected.\n" "Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them.\n"); for (n = 0; n < SYMBOL_HASH_SIZE; n++) { - struct symbol *s = symbolhash[n]; + struct symbol *s; + + for (s = symbolhash[n]; s; s = s->next) { + /* + * Do not check "vmlinux". This avoids the same warnings + * shown twice, and false-positives for ARCH=um. + */ + if (is_vmlinux(s->module->name) && !s->module->is_dot_o) + continue; - while (s) { if (s->is_static) warn("\"%s\" [%s] is a static %s\n", s->name, s->module->name, export_str(s->export)); - - s = s->next; } } diff --git a/scripts/namespace.pl b/scripts/namespace.pl index 6135574a6f39..1da7bca201a4 100755 --- a/scripts/namespace.pl +++ b/scripts/namespace.pl @@ -65,13 +65,14 @@ use warnings; use strict; use File::Find; +use File::Spec; my $nm = ($ENV{'NM'} || "nm") . " -p"; my $objdump = ($ENV{'OBJDUMP'} || "objdump") . " -s -j .comment"; -my $srctree = ""; -my $objtree = ""; -$srctree = "$ENV{'srctree'}/" if (exists($ENV{'srctree'})); -$objtree = "$ENV{'objtree'}/" if (exists($ENV{'objtree'})); +my $srctree = File::Spec->curdir(); +my $objtree = File::Spec->curdir(); +$srctree = File::Spec->rel2abs($ENV{'srctree'}) if (exists($ENV{'srctree'})); +$objtree = File::Spec->rel2abs($ENV{'objtree'}) if (exists($ENV{'objtree'})); if ($#ARGV != -1) { print STDERR "usage: $0 takes no parameters\n"; @@ -231,9 +232,9 @@ sub do_nm } ($source = $basename) =~ s/\.o$//; if (-e "$source.c" || -e "$source.S") { - $source = "$objtree$File::Find::dir/$source"; + $source = File::Spec->catfile($objtree, $File::Find::dir, $source) } else { - $source = "$srctree$File::Find::dir/$source"; + $source = File::Spec->catfile($srctree, $File::Find::dir, $source) } if (! -e "$source.c" && ! -e "$source.S") { # No obvious source, exclude the object if it is conglomerate diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 365b3c2b8f43..220dae0db3f1 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -126,7 +126,7 @@ scm_version() collect_files() { - local file res + local file res= for file; do case "$file" in diff --git a/security/integrity/Makefile b/security/integrity/Makefile index 19faace69644..35e6ca773734 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -13,9 +13,6 @@ integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyrin integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \ platform_certs/load_uefi.o integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o -$(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar -subdir-$(CONFIG_IMA) += ima obj-$(CONFIG_IMA) += ima/ -subdir-$(CONFIG_EVM) += evm obj-$(CONFIG_EVM) += evm/ diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 3a29e7c24ba9..a5813c7629c1 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -1946,7 +1946,14 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) rc = string_to_context_struct(args->newp, NULL, s, newc, SECSID_NULL); if (rc == -EINVAL) { - /* Retain string representation for later mapping. */ + /* + * Retain string representation for later mapping. + * + * IMPORTANT: We need to copy the contents of oldc->str + * back into s again because string_to_context_struct() + * may have garbled it. + */ + memcpy(s, oldc->str, oldc->len); context_init(newc); newc->str = s; newc->len = oldc->len; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c3feccb99ff5..4cdbae6f4e61 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -63,6 +63,13 @@ TARGETS += zram TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug +# User can optionally provide a TARGETS skiplist. +SKIP_TARGETS ?= +ifneq ($(SKIP_TARGETS),) + TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS)) + override TARGETS := $(TMP) +endif + # Clear LDFLAGS and MAKEFLAGS if called from main # Makefile to avoid test build failures when test # Makefile doesn't have explicit build rules. @@ -171,9 +178,12 @@ run_pstore_crash: # 1. output_dir=kernel_src # 2. a separate output directory is specified using O= KBUILD_OUTPUT # 3. a separate output directory is specified using KBUILD_OUTPUT +# Avoid conflict with INSTALL_PATH set by the main Makefile # -INSTALL_PATH ?= $(BUILD)/install -INSTALL_PATH := $(abspath $(INSTALL_PATH)) +KSFT_INSTALL_PATH ?= $(BUILD)/kselftest_install +KSFT_INSTALL_PATH := $(abspath $(KSFT_INSTALL_PATH)) +# Avoid changing the rest of the logic here and lib.mk. +INSTALL_PATH := $(KSFT_INSTALL_PATH) ALL_SCRIPT := $(INSTALL_PATH)/run_kselftest.sh install: all @@ -198,11 +208,16 @@ ifdef INSTALL_PATH echo " cat /dev/null > \$$logfile" >> $(ALL_SCRIPT) echo "fi" >> $(ALL_SCRIPT) + @# While building run_kselftest.sh skip also non-existent TARGET dirs: + @# they could be the result of a build failure and should NOT be + @# included in the generated runlist. for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ + [ ! -d $$INSTALL_PATH/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \ echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \ echo "cd $$TARGET" >> $(ALL_SCRIPT); \ echo -n "run_many" >> $(ALL_SCRIPT); \ + echo -n "Emit Tests for $$TARGET\n"; \ $(MAKE) -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ echo "" >> $(ALL_SCRIPT); \ echo "cd \$$ROOT" >> $(ALL_SCRIPT); \ diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 00c9020bdda8..84de7bc74f2c 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -3,9 +3,14 @@ # # Runs a set of tests in a given subdirectory. export skip_rc=4 +export timeout_rc=124 export logfile=/dev/stdout export per_test_logging= +# Defaults for "settings" file fields: +# "timeout" how many seconds to let each test run before failing. +export kselftest_default_timeout=45 + # There isn't a shell-agnostic way to find the path of a sourced file, # so we must rely on BASE_DIR being set to find other tools. if [ -z "$BASE_DIR" ]; then @@ -24,6 +29,16 @@ tap_prefix() fi } +tap_timeout() +{ + # Make sure tests will time out if utility is available. + if [ -x /usr/bin/timeout ] ; then + /usr/bin/timeout "$kselftest_timeout" "$1" + else + "$1" + fi +} + run_one() { DIR="$1" @@ -32,6 +47,18 @@ run_one() BASENAME_TEST=$(basename $TEST) + # Reset any "settings"-file variables. + export kselftest_timeout="$kselftest_default_timeout" + # Load per-test-directory kselftest "settings" file. + settings="$BASE_DIR/$DIR/settings" + if [ -r "$settings" ] ; then + while read line ; do + field=$(echo "$line" | cut -d= -f1) + value=$(echo "$line" | cut -d= -f2-) + eval "kselftest_$field"="$value" + done < "$settings" + fi + TEST_HDR_MSG="selftests: $DIR: $BASENAME_TEST" echo "# $TEST_HDR_MSG" if [ ! -x "$TEST" ]; then @@ -44,14 +71,17 @@ run_one() echo "not ok $test_num $TEST_HDR_MSG" else cd `dirname $TEST` > /dev/null - (((((./$BASENAME_TEST 2>&1; echo $? >&3) | + ((((( tap_timeout ./$BASENAME_TEST 2>&1; echo $? >&3) | tap_prefix >&4) 3>&1) | (read xs; exit $xs)) 4>>"$logfile" && echo "ok $test_num $TEST_HDR_MSG") || - (if [ $? -eq $skip_rc ]; then \ + (rc=$?; \ + if [ $rc -eq $skip_rc ]; then \ echo "not ok $test_num $TEST_HDR_MSG # SKIP" + elif [ $rc -eq $timeout_rc ]; then \ + echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" else - echo "not ok $test_num $TEST_HDR_MSG" + echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" fi) cd - >/dev/null fi diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh index ec304463883c..e2e1911d62d5 100755 --- a/tools/testing/selftests/kselftest_install.sh +++ b/tools/testing/selftests/kselftest_install.sh @@ -24,12 +24,12 @@ main() echo "$0: Installing in specified location - $install_loc ..." fi - install_dir=$install_loc/kselftest + install_dir=$install_loc/kselftest_install # Create install directory mkdir -p $install_dir # Build tests - INSTALL_PATH=$install_dir make install + KSFT_INSTALL_PATH=$install_dir make install } main "$@" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 62c591f87dab..c5ec868fa1e5 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -22,6 +22,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test @@ -48,7 +49,7 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ - $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) + $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) # On s390, build the testcases KVM-enabled pgste-option = $(call try-run, echo 'int main() { return 0; }' | \ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 0c17f2ee685e..ff234018219c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -1083,6 +1083,9 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); #define VMX_BASIC_MEM_TYPE_WB 6LLU #define VMX_BASIC_INOUT 0x0040000000000000LLU +/* VMX_EPT_VPID_CAP bits */ +#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) + /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 69b17055f63d..6ae5a47fe067 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -569,6 +569,10 @@ struct vmx_pages { void *enlightened_vmcs_hva; uint64_t enlightened_vmcs_gpa; void *enlightened_vmcs; + + void *eptp_hva; + uint64_t eptp_gpa; + void *eptp; }; struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva); @@ -576,4 +580,14 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx); void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp); bool load_vmcs(struct vmx_pages *vmx); +void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot); +void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint64_t size, + uint32_t eptp_memslot); +void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t memslot, uint32_t eptp_memslot); +void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t eptp_memslot); + #endif /* SELFTEST_KVM_VMX_H */ diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 80a338b5403c..41cf45416060 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -705,7 +705,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, * on error (e.g. currently no memory region using memslot as a KVM * memory slot ID). */ -static struct userspace_mem_region * +struct userspace_mem_region * memslot2region(struct kvm_vm *vm, uint32_t memslot) { struct userspace_mem_region *region; diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index f36262e0f655..ac50c42750cf 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -68,4 +68,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent); void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent); +struct userspace_mem_region * +memslot2region(struct kvm_vm *vm, uint32_t memslot); + #endif /* SELFTEST_KVM_UTIL_INTERNAL_H */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c53dbc6bc568..6698cb741e10 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1085,7 +1085,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) for (i = 0; i < nmsrs; i++) state->msrs.entries[i].index = list->indices[i]; r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs); - TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)", + TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)", r, r == nmsrs ? -1 : list->indices[r]); r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 9cef0455b819..fab8f6b0bf52 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -7,11 +7,39 @@ #include "test_util.h" #include "kvm_util.h" +#include "../kvm_util_internal.h" #include "processor.h" #include "vmx.h" +#define PAGE_SHIFT_4K 12 + +#define KVM_EPT_PAGE_TABLE_MIN_PADDR 0x1c0000 + bool enable_evmcs; +struct eptPageTableEntry { + uint64_t readable:1; + uint64_t writable:1; + uint64_t executable:1; + uint64_t memory_type:3; + uint64_t ignore_pat:1; + uint64_t page_size:1; + uint64_t accessed:1; + uint64_t dirty:1; + uint64_t ignored_11_10:2; + uint64_t address:40; + uint64_t ignored_62_52:11; + uint64_t suppress_ve:1; +}; + +struct eptPageTablePointer { + uint64_t memory_type:3; + uint64_t page_walk_length:3; + uint64_t ad_enabled:1; + uint64_t reserved_11_07:5; + uint64_t address:40; + uint64_t reserved_63_52:12; +}; int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id) { uint16_t evmcs_ver; @@ -174,15 +202,35 @@ bool load_vmcs(struct vmx_pages *vmx) */ static inline void init_vmcs_control_fields(struct vmx_pages *vmx) { + uint32_t sec_exec_ctl = 0; + vmwrite(VIRTUAL_PROCESSOR_ID, 0); vmwrite(POSTED_INTR_NV, 0); vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS)); - if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0)) + + if (vmx->eptp_gpa) { + uint64_t ept_paddr; + struct eptPageTablePointer eptp = { + .memory_type = VMX_BASIC_MEM_TYPE_WB, + .page_walk_length = 3, /* + 1 */ + .ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS), + .address = vmx->eptp_gpa >> PAGE_SHIFT_4K, + }; + + memcpy(&ept_paddr, &eptp, sizeof(ept_paddr)); + vmwrite(EPT_POINTER, ept_paddr); + sec_exec_ctl |= SECONDARY_EXEC_ENABLE_EPT; + } + + if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, sec_exec_ctl)) vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS); - else + else { vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS)); + GUEST_ASSERT(!sec_exec_ctl); + } + vmwrite(EXCEPTION_BITMAP, 0); vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0); vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */ @@ -327,3 +375,152 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp) init_vmcs_host_state(); init_vmcs_guest_state(guest_rip, guest_rsp); } + +void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot) +{ + uint16_t index[4]; + struct eptPageTableEntry *pml4e; + + TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " + "unknown or unsupported guest mode, mode: 0x%x", vm->mode); + + TEST_ASSERT((nested_paddr % vm->page_size) == 0, + "Nested physical address not on page boundary,\n" + " nested_paddr: 0x%lx vm->page_size: 0x%x", + nested_paddr, vm->page_size); + TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + TEST_ASSERT((paddr % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", + paddr, vm->page_size); + TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + paddr, vm->max_gfn, vm->page_size); + + index[0] = (nested_paddr >> 12) & 0x1ffu; + index[1] = (nested_paddr >> 21) & 0x1ffu; + index[2] = (nested_paddr >> 30) & 0x1ffu; + index[3] = (nested_paddr >> 39) & 0x1ffu; + + /* Allocate page directory pointer table if not present. */ + pml4e = vmx->eptp_hva; + if (!pml4e[index[3]].readable) { + pml4e[index[3]].address = vm_phy_page_alloc(vm, + KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) + >> vm->page_shift; + pml4e[index[3]].writable = true; + pml4e[index[3]].readable = true; + pml4e[index[3]].executable = true; + } + + /* Allocate page directory table if not present. */ + struct eptPageTableEntry *pdpe; + pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size); + if (!pdpe[index[2]].readable) { + pdpe[index[2]].address = vm_phy_page_alloc(vm, + KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) + >> vm->page_shift; + pdpe[index[2]].writable = true; + pdpe[index[2]].readable = true; + pdpe[index[2]].executable = true; + } + + /* Allocate page table if not present. */ + struct eptPageTableEntry *pde; + pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size); + if (!pde[index[1]].readable) { + pde[index[1]].address = vm_phy_page_alloc(vm, + KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot) + >> vm->page_shift; + pde[index[1]].writable = true; + pde[index[1]].readable = true; + pde[index[1]].executable = true; + } + + /* Fill in page table entry. */ + struct eptPageTableEntry *pte; + pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size); + pte[index[0]].address = paddr >> vm->page_shift; + pte[index[0]].writable = true; + pte[index[0]].readable = true; + pte[index[0]].executable = true; + + /* + * For now mark these as accessed and dirty because the only + * testcase we have needs that. Can be reconsidered later. + */ + pte[index[0]].accessed = true; + pte[index[0]].dirty = true; +} + +/* + * Map a range of EPT guest physical addresses to the VM's physical address + * + * Input Args: + * vm - Virtual Machine + * nested_paddr - Nested guest physical address to map + * paddr - VM Physical Address + * size - The size of the range to map + * eptp_memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within the VM given by vm, creates a nested guest translation for the + * page range starting at nested_paddr to the page range starting at paddr. + */ +void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm, + uint64_t nested_paddr, uint64_t paddr, uint64_t size, + uint32_t eptp_memslot) +{ + size_t page_size = vm->page_size; + size_t npages = size / page_size; + + TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow"); + TEST_ASSERT(paddr + size > paddr, "Paddr overflow"); + + while (npages--) { + nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot); + nested_paddr += page_size; + paddr += page_size; + } +} + +/* Prepare an identity extended page table that maps all the + * physical pages in VM. + */ +void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t memslot, uint32_t eptp_memslot) +{ + sparsebit_idx_t i, last; + struct userspace_mem_region *region = + memslot2region(vm, memslot); + + i = (region->region.guest_phys_addr >> vm->page_shift) - 1; + last = i + (region->region.memory_size >> vm->page_shift); + for (;;) { + i = sparsebit_next_clear(region->unused_phy_pages, i); + if (i > last) + break; + + nested_map(vmx, vm, + (uint64_t)i << vm->page_shift, + (uint64_t)i << vm->page_shift, + 1 << vm->page_shift, + eptp_memslot); + } +} + +void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, + uint32_t eptp_memslot) +{ + vmx->eptp = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0); + vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp); + vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp); +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c new file mode 100644 index 000000000000..0bca1cfe2c1e --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging test + * + * Copyright (C) 2018, Red Hat, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#define VCPU_ID 1 + +/* The memory slot index to track dirty pages */ +#define TEST_MEM_SLOT_INDEX 1 +#define TEST_MEM_SIZE 3 + +/* L1 guest test virtual memory offset */ +#define GUEST_TEST_MEM 0xc0000000 + +/* L2 guest test virtual memory offset */ +#define NESTED_TEST_MEM1 0xc0001000 +#define NESTED_TEST_MEM2 0xc0002000 + +static void l2_guest_code(void) +{ + *(volatile uint64_t *)NESTED_TEST_MEM1; + *(volatile uint64_t *)NESTED_TEST_MEM1 = 1; + GUEST_SYNC(true); + GUEST_SYNC(false); + + *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + GUEST_SYNC(true); + *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + GUEST_SYNC(true); + GUEST_SYNC(false); + + /* Exit to L1 and never come back. */ + vmcall(); +} + +void l1_guest_code(struct vmx_pages *vmx) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT(vmx->vmcs_gpa); + GUEST_ASSERT(prepare_for_vmx_operation(vmx)); + GUEST_ASSERT(load_vmcs(vmx)); + + prepare_vmcs(vmx, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_SYNC(false); + GUEST_ASSERT(!vmlaunch()); + GUEST_SYNC(false); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t vmx_pages_gva = 0; + struct vmx_pages *vmx; + unsigned long *bmap; + uint64_t *host_test_mem; + + struct kvm_vm *vm; + struct kvm_run *run; + struct ucall uc; + bool done = false; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + run = vcpu_state(vm, VCPU_ID); + + /* Add an extra memory slot for testing dirty logging */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + GUEST_TEST_MEM, + TEST_MEM_SLOT_INDEX, + TEST_MEM_SIZE, + KVM_MEM_LOG_DIRTY_PAGES); + + /* + * Add an identity map for GVA range [0xc0000000, 0xc0002000). This + * affects both L1 and L2. However... + */ + virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM, + TEST_MEM_SIZE * 4096, 0); + + /* + * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to + * 0xc0000000. + * + * Note that prepare_eptp should be called only L1's GPA map is done, + * meaning after the last call to virt_map. + */ + prepare_eptp(vmx, vm, 0); + nested_map_memslot(vmx, vm, 0, 0); + nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0); + nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0); + + bmap = bitmap_alloc(TEST_MEM_SIZE); + host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); + + while (!done) { + memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096); + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], + __FILE__, uc.args[1]); + /* NOT REACHED */ + case UCALL_SYNC: + /* + * The nested guest wrote at offset 0x1000 in the memslot, but the + * dirty bitmap must be filled in according to L1 GPA, not L2. + */ + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + if (uc.args[1]) { + TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n"); + TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n"); + } else { + TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n"); + TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n"); + } + + TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n"); + TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n"); + TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n"); + TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n"); + break; + case UCALL_DONE: + done = true; + break; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + } + } +} diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c7cced739c34..8aefd81fbc86 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -21,3 +21,4 @@ ipv6_flowlabel ipv6_flowlabel_mgr so_txtime tcp_fastopen_backup_key +nettest diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index b8265ee9923f..614b31aad168 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -89,12 +89,9 @@ struct testcase testcases_v4[] = { .tfail = true, }, { - /* send a single MSS: will fail with GSO, because the segment - * logic in udp4_ufo_fragment demands a gso skb to be > MTU - */ + /* send a single MSS: will fall back to no GSO */ .tlen = CONST_MSS_V4, .gso_len = CONST_MSS_V4, - .tfail = true, .r_num_mss = 1, }, { @@ -139,10 +136,9 @@ struct testcase testcases_v4[] = { .tfail = true, }, { - /* send a single 1B MSS: will fail, see single MSS above */ + /* send a single 1B MSS: will fall back to no GSO */ .tlen = 1, .gso_len = 1, - .tfail = true, .r_num_mss = 1, }, { @@ -196,12 +192,9 @@ struct testcase testcases_v6[] = { .tfail = true, }, { - /* send a single MSS: will fail with GSO, because the segment - * logic in udp4_ufo_fragment demands a gso skb to be > MTU - */ + /* send a single MSS: will fall back to no GSO */ .tlen = CONST_MSS_V6, .gso_len = CONST_MSS_V6, - .tfail = true, .r_num_mss = 1, }, { @@ -246,10 +239,9 @@ struct testcase testcases_v6[] = { .tfail = true, }, { - /* send a single 1B MSS: will fail, see single MSS above */ + /* send a single 1B MSS: will fall back to no GSO */ .tlen = 1, .gso_len = 1, - .tfail = true, .r_num_mss = 1, }, { diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 464c9b76148f..7550f08822a3 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ -lpthread +CFLAGS += -g -I../../../../usr/include/ -pthread TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/rtc/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index afff120c7be6..f45e510500c0 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -19,7 +19,7 @@ int fd; const char v = 'V'; -static const char sopts[] = "bdehp:t:Tn:NLf:"; +static const char sopts[] = "bdehp:t:Tn:NLf:i"; static const struct option lopts[] = { {"bootstatus", no_argument, NULL, 'b'}, {"disable", no_argument, NULL, 'd'}, @@ -32,6 +32,7 @@ static const struct option lopts[] = { {"getpretimeout", no_argument, NULL, 'N'}, {"gettimeleft", no_argument, NULL, 'L'}, {"file", required_argument, NULL, 'f'}, + {"info", no_argument, NULL, 'i'}, {NULL, no_argument, NULL, 0x0} }; @@ -72,6 +73,7 @@ static void usage(char *progname) printf("Usage: %s [options]\n", progname); printf(" -f, --file\t\tOpen watchdog device file\n"); printf("\t\t\tDefault is /dev/watchdog\n"); + printf(" -i, --info\t\tShow watchdog_info\n"); printf(" -b, --bootstatus\tGet last boot status (Watchdog/POR)\n"); printf(" -d, --disable\t\tTurn off the watchdog timer\n"); printf(" -e, --enable\t\tTurn on the watchdog timer\n"); @@ -97,6 +99,7 @@ int main(int argc, char *argv[]) int c; int oneshot = 0; char *file = "/dev/watchdog"; + struct watchdog_info info; setbuf(stdout, NULL); @@ -118,6 +121,16 @@ int main(int argc, char *argv[]) exit(-1); } + /* + * Validate that `file` is a watchdog device + */ + ret = ioctl(fd, WDIOC_GETSUPPORT, &info); + if (ret) { + printf("WDIOC_GETSUPPORT error '%s'\n", strerror(errno)); + close(fd); + exit(ret); + } + optind = 0; while ((c = getopt_long(argc, argv, sopts, lopts, NULL)) != -1) { @@ -205,6 +218,18 @@ int main(int argc, char *argv[]) case 'f': /* Handled above */ break; + case 'i': + /* + * watchdog_info was obtained as part of file open + * validation. So we just show it here. + */ + oneshot = 1; + printf("watchdog_info:\n"); + printf(" identity:\t\t%s\n", info.identity); + printf(" firmware_version:\t%u\n", + info.firmware_version); + printf(" options:\t\t%08x\n", info.options); + break; default: usage(argv[0]); diff --git a/usr/include/Makefile b/usr/include/Makefile index c9449aaf438d..57b20f7b6729 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -29,13 +29,11 @@ header-test- += linux/android/binderfs.h header-test-$(CONFIG_CPU_BIG_ENDIAN) += linux/byteorder/big_endian.h header-test-$(CONFIG_CPU_LITTLE_ENDIAN) += linux/byteorder/little_endian.h header-test- += linux/coda.h -header-test- += linux/coda_psdev.h header-test- += linux/elfcore.h header-test- += linux/errqueue.h header-test- += linux/fsmap.h header-test- += linux/hdlc/ioctl.h header-test- += linux/ivtv.h -header-test- += linux/jffs2.h header-test- += linux/kexec.h header-test- += linux/matroxfb.h header-test- += linux/netfilter_ipv4/ipt_LOG.h @@ -55,20 +53,12 @@ header-test- += linux/v4l2-mediabus.h header-test- += linux/v4l2-subdev.h header-test- += linux/videodev2.h header-test- += linux/vm_sockets.h -header-test- += scsi/scsi_bsg_fc.h -header-test- += scsi/scsi_netlink.h -header-test- += scsi/scsi_netlink_fc.h header-test- += sound/asequencer.h header-test- += sound/asoc.h header-test- += sound/asound.h header-test- += sound/compress_offload.h header-test- += sound/emu10k1.h header-test- += sound/sfnt_info.h -header-test- += sound/sof/eq.h -header-test- += sound/sof/fw.h -header-test- += sound/sof/header.h -header-test- += sound/sof/manifest.h -header-test- += sound/sof/trace.h header-test- += xen/evtchn.h header-test- += xen/gntdev.h header-test- += xen/privcmd.h diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h index 55fed77a9f73..4fd4f6db181b 100644 --- a/virt/kvm/arm/vgic/trace.h +++ b/virt/kvm/arm/vgic/trace.h @@ -30,7 +30,7 @@ TRACE_EVENT(vgic_update_irq_pending, #endif /* _TRACE_VGIC_H */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic +#define TRACE_INCLUDE_PATH ../../virt/kvm/arm/vgic #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e6de3159e682..fd68fbe0a75d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -617,8 +617,9 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) stat_data->kvm = kvm; stat_data->offset = p->offset; + stat_data->mode = p->mode ? p->mode : 0644; kvm->debugfs_stat_data[p - debugfs_entries] = stat_data; - debugfs_create_file(p->name, 0644, kvm->debugfs_dentry, + debugfs_create_file(p->name, stat_data->mode, kvm->debugfs_dentry, stat_data, stat_fops_per_vm[p->kind]); } return 0; @@ -3929,7 +3930,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, if (!refcount_inc_not_zero(&stat_data->kvm->users_count)) return -ENOENT; - if (simple_attr_open(inode, file, get, set, fmt)) { + if (simple_attr_open(inode, file, get, + stat_data->mode & S_IWUGO ? set : NULL, + fmt)) { kvm_put_kvm(stat_data->kvm); return -ENOMEM; } @@ -4177,7 +4180,8 @@ static void kvm_init_debug(void) kvm_debugfs_num_entries = 0; for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) { - debugfs_create_file(p->name, 0644, kvm_debugfs_dir, + int mode = p->mode ? p->mode : 0644; + debugfs_create_file(p->name, mode, kvm_debugfs_dir, (void *)(long)p->offset, stat_fops[p->kind]); } |