diff options
1098 files changed, 16181 insertions, 6004 deletions
diff --git a/.gitignore b/.gitignore index 87b9dd8a163b..d5f4804ed07c 100644 --- a/.gitignore +++ b/.gitignore @@ -143,6 +143,9 @@ x509.genkey /allrandom.config /allyes.config +# Kconfig savedefconfig output +/defconfig + # Kdevelop4 *.kdev4 @@ -90,11 +90,16 @@ Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com> Frank Zago <fzago@systemfabricworks.com> Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com> Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com> +Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com> +Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com> +Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com> Greg Kroah-Hartman <greg@echidna.(none)> Greg Kroah-Hartman <gregkh@suse.de> Greg Kroah-Hartman <greg@kroah.com> Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com> Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org> +Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com> +Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com> Henk Vergonet <Henk.Vergonet@gmail.com> Henrik Kretzschmar <henne@nachtwindheim.de> Henrik Rydberg <rydberg@bitmath.org> diff --git a/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg b/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg index 151c59578db4..f58cfb06b160 100644 --- a/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg +++ b/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg @@ -1,6 +1,6 @@ What: /sys/bus/platform/devices/ci_hdrc.0/inputs/a_bus_req Date: Feb 2014 -Contact: Li Jun <b47624@freescale.com> +Contact: Li Jun <jun.li@nxp.com> Description: Can be set and read. Set a_bus_req(A-device bus request) input to be 1 if @@ -17,7 +17,7 @@ Description: What: /sys/bus/platform/devices/ci_hdrc.0/inputs/a_bus_drop Date: Feb 2014 -Contact: Li Jun <b47624@freescale.com> +Contact: Li Jun <jun.li@nxp.com> Description: Can be set and read The a_bus_drop(A-device bus drop) input is 1 when the @@ -32,7 +32,7 @@ Description: What: /sys/bus/platform/devices/ci_hdrc.0/inputs/b_bus_req Date: Feb 2014 -Contact: Li Jun <b47624@freescale.com> +Contact: Li Jun <jun.li@nxp.com> Description: Can be set and read. The b_bus_req(B-device bus request) input is 1 during the time @@ -47,7 +47,7 @@ Description: What: /sys/bus/platform/devices/ci_hdrc.0/inputs/a_clr_err Date: Feb 2014 -Contact: Li Jun <b47624@freescale.com> +Contact: Li Jun <jun.li@nxp.com> Description: Only can be set. The a_clr_err(A-device Vbus error clear) input is used to clear diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 5fb526900023..5aad534233cd 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -258,7 +258,7 @@ Configuring the kernel Compiling the kernel -------------------- - - Make sure you have at least gcc 4.6 available. + - Make sure you have at least gcc 4.9 available. For more information, refer to :ref:`Documentation/process/changes.rst <changes>`. Please note that you can still run a.out user programs with this kernel. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index ce3e05e41724..d09471aa7443 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1356,8 +1356,8 @@ PAGE_SIZE multiple when read back. thp_fault_alloc Number of transparent hugepages which were allocated to satisfy - a page fault, including COW faults. This counter is not present - when CONFIG_TRANSPARENT_HUGEPAGE is not set. + a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE + is not set. thp_collapse_alloc Number of transparent hugepages which were allocated to allow diff --git a/Documentation/admin-guide/device-mapper/index.rst b/Documentation/admin-guide/device-mapper/index.rst index ec62fcc8eece..6cf8adc86fa8 100644 --- a/Documentation/admin-guide/device-mapper/index.rst +++ b/Documentation/admin-guide/device-mapper/index.rst @@ -11,6 +11,7 @@ Device Mapper dm-clone dm-crypt dm-dust + dm-ebs dm-flakey dm-init dm-integrity diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 6a233e42be08..b2acd0d395ca 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -305,8 +305,7 @@ monitor how successfully the system is providing huge pages for use. thp_fault_alloc is incremented every time a huge page is successfully - allocated to handle a page fault. This applies to both the - first time a page is faulted and for COW faults. + allocated to handle a page fault. thp_collapse_alloc is incremented by khugepaged when it has found diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 314fa5bc2655..f28853f80089 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -171,6 +171,7 @@ infrastructure: 3) ID_AA64PFR1_EL1 - Processor Feature Register 1 + +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ @@ -181,6 +182,7 @@ infrastructure: 4) MIDR_EL1 - Main ID Register + +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 936cf2a59ca4..3f7c3a7e8a2b 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -147,6 +147,14 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Falkor v{1,2} | E1041 | QCOM_FALKOR_ERRATUM_1041 | +----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Gold | N/A | ARM64_ERRATUM_1463225 | ++----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Gold | N/A | ARM64_ERRATUM_1418040 | ++----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Silver | N/A | ARM64_ERRATUM_1530923 | ++----------------+-----------------+-----------------+-----------------------------+ +| Qualcomm Tech. | Kryo4xx Silver | N/A | ARM64_ERRATUM_1024718 | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/block/bfq-iosched.rst b/Documentation/block/bfq-iosched.rst index 0d237d402860..19d4d1570cee 100644 --- a/Documentation/block/bfq-iosched.rst +++ b/Documentation/block/bfq-iosched.rst @@ -492,13 +492,6 @@ set max_budget to higher values than those to which BFQ would have set it with auto-tuning. An alternative way to achieve this goal is to just increase the value of timeout_sync, leaving max_budget equal to 0. -weights -------- - -Read-only parameter, used to show the weights of the currently active -BFQ queues. - - 4. Group scheduling with BFQ ============================ @@ -566,7 +559,7 @@ Parameters to set For each group, there is only the following parameter to set. weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the -group inside its parent. Available values: 1..10000 (default 100). The +group inside its parent. Available values: 1..1000 (default 100). The linear mapping between ioprio and weights, described at the beginning of the tunable section, is still valid, but all weights higher than IOPRIO_BE_NR*10 are mapped to ioprio 0. diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 2d8d2fed7317..f41620439ef3 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -206,6 +206,14 @@ others should not be larger than the returned value. :: + bool + dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +Returns %true if dma_sync_single_for_{device,cpu} calls are required to +transfer memory ownership. Returns %false if those calls can be skipped. + +:: + unsigned long dma_get_merge_boundary(struct device *dev); diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index 6068266dd303..7ca8c7bac650 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -33,7 +33,7 @@ all combinations of get*(), pin*(), FOLL_LONGTERM, and more. Also, the pin_user_pages*() APIs are clearly distinct from the get_user_pages*() APIs, so that's a natural dividing line, and a good point to make separate wrapper calls. In other words, use pin_user_pages*() for DMA-pinned pages, and -get_user_pages*() for other cases. There are four cases described later on in +get_user_pages*() for other cases. There are five cases described later on in this document, to further clarify that concept. FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However, diff --git a/Documentation/dev-tools/kcsan.rst b/Documentation/dev-tools/kcsan.rst index ce4bbd918648..b38379f06194 100644 --- a/Documentation/dev-tools/kcsan.rst +++ b/Documentation/dev-tools/kcsan.rst @@ -114,12 +114,6 @@ the below options are available: To dynamically limit for which functions to generate reports, see the `DebugFS interface`_ blacklist/whitelist feature. - For ``__always_inline`` functions, replace ``__always_inline`` with - ``__no_kcsan_or_inline`` (which implies ``__always_inline``):: - - static __no_kcsan_or_inline void foo(void) { - ... - * To disable data race detection for a particular compilation unit, add to the ``Makefile``:: diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst index ea55b2467653..1628862e7024 100644 --- a/Documentation/dev-tools/kunit/faq.rst +++ b/Documentation/dev-tools/kunit/faq.rst @@ -61,3 +61,43 @@ test, or an end-to-end test. kernel by installing a production configuration of the kernel on production hardware with a production userspace and then trying to exercise some behavior that depends on interactions between the hardware, the kernel, and userspace. + +KUnit isn't working, what should I do? +====================================== + +Unfortunately, there are a number of things which can break, but here are some +things to try. + +1. Try running ``./tools/testing/kunit/kunit.py run`` with the ``--raw_output`` + parameter. This might show details or error messages hidden by the kunit_tool + parser. +2. Instead of running ``kunit.py run``, try running ``kunit.py config``, + ``kunit.py build``, and ``kunit.py exec`` independently. This can help track + down where an issue is occurring. (If you think the parser is at fault, you + can run it manually against stdin or a file with ``kunit.py parse``.) +3. Running the UML kernel directly can often reveal issues or error messages + kunit_tool ignores. This should be as simple as running ``./vmlinux`` after + building the UML kernel (e.g., by using ``kunit.py build``). Note that UML + has some unusual requirements (such as the host having a tmpfs filesystem + mounted), and has had issues in the past when built statically and the host + has KASLR enabled. (On older host kernels, you may need to run ``setarch + `uname -m` -R ./vmlinux`` to disable KASLR.) +4. Make sure the kernel .config has ``CONFIG_KUNIT=y`` and at least one test + (e.g. ``CONFIG_KUNIT_EXAMPLE_TEST=y``). kunit_tool will keep its .config + around, so you can see what config was used after running ``kunit.py run``. + It also preserves any config changes you might make, so you can + enable/disable things with ``make ARCH=um menuconfig`` or similar, and then + re-run kunit_tool. +5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This + may help clean up any residual config items which could be causing problems. +6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be + built into any kernel, or can be built as a module and loaded at runtime. + Doing so should allow you to determine if UML is causing the issue you're + seeing. When tests are built-in, they will execute when the kernel boots, and + modules will automatically execute associated tests when loaded. Test results + can be collected from ``/sys/kernel/debug/kunit/<test suite>/results``, and + can be parsed with ``kunit.py parse``. For more details, see "KUnit on + non-UML architectures" in :doc:`usage`. + +If none of the above tricks help, you are always welcome to email any issues to +kunit-dev@googlegroups.com. diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index a63898954068..91c4d00e96d3 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -2,7 +2,6 @@ DT_DOC_CHECKER ?= dt-doc-validate DT_EXTRACT_EX ?= dt-extract-example DT_MK_SCHEMA ?= dt-mk-schema -DT_MK_SCHEMA_USERONLY_FLAG := $(if $(DT_SCHEMA_FILES), -u) DT_SCHEMA_MIN_VERSION = 2020.5 @@ -35,21 +34,40 @@ quiet_cmd_mk_schema = SCHEMA $@ DT_DOCS = $(shell $(find_cmd) | sed -e 's|^$(srctree)/||') -DT_SCHEMA_FILES ?= $(DT_DOCS) - -extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) -extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES)) -extra-$(CHECK_DT_BINDING) += processed-schema-examples.yaml - override DTC_FLAGS := \ -Wno-avoid_unnecessary_addr_size \ - -Wno-graph_child_address + -Wno-graph_child_address \ + -Wno-interrupt_provider $(obj)/processed-schema-examples.yaml: $(DT_DOCS) check_dtschema_version FORCE $(call if_changed,mk_schema) -$(obj)/processed-schema.yaml: DT_MK_SCHEMA_FLAGS := $(DT_MK_SCHEMA_USERONLY_FLAG) +ifeq ($(DT_SCHEMA_FILES),) + +# Unless DT_SCHEMA_FILES is specified, use the full schema for dtbs_check too. +# Just copy processed-schema-examples.yaml + +$(obj)/processed-schema.yaml: $(obj)/processed-schema-examples.yaml FORCE + $(call if_changed,copy) + +DT_SCHEMA_FILES = $(DT_DOCS) + +else + +# If DT_SCHEMA_FILES is specified, use it for processed-schema.yaml + +$(obj)/processed-schema.yaml: DT_MK_SCHEMA_FLAGS := -u $(obj)/processed-schema.yaml: $(DT_SCHEMA_FILES) check_dtschema_version FORCE $(call if_changed,mk_schema) -extra-y += processed-schema.yaml +endif + +extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) +extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES)) +extra-$(CHECK_DT_BINDING) += processed-schema-examples.yaml +extra-$(CHECK_DTBS) += processed-schema.yaml + +# Hack: avoid 'Argument list too long' error for 'make clean'. Remove most of +# build artifacts here before they are processed by scripts/Makefile.clean +clean-files = $(shell find $(obj) \( -name '*.example.dts' -o \ + -name '*.example.dt.yaml' \) -delete 2>/dev/null) diff --git a/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt b/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt index 715047444391..10b8459e49f8 100644 --- a/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt +++ b/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt @@ -47,7 +47,7 @@ Required properties: &lsio_mu1 1 2 &lsio_mu1 1 3 &lsio_mu1 3 3>; - See Documentation/devicetree/bindings/mailbox/fsl,mu.txt + See Documentation/devicetree/bindings/mailbox/fsl,mu.yaml for detailed mailbox binding. Note: Each mu which supports general interrupt should have an alias correctly diff --git a/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml b/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml index c4c9119e4a20..a0c6c5d2b70f 100644 --- a/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml +++ b/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml @@ -80,14 +80,14 @@ examples: ranges = <1 0x00000000 0x42000000 0x02000000>, <5 0x00000000 0x46000000 0x01000000>; - ethernet@1,01f00000 { + ethernet@1,1f00000 { compatible = "smsc,lan9115"; reg = <1 0x01f00000 0x1000>; interrupts = <0 48 4>; phy-mode = "mii"; }; - uart@5,00200000 { + serial@5,200000 { compatible = "ns16550a"; reg = <5 0x00200000 0x20>; interrupts = <0 49 4>; diff --git a/Documentation/devicetree/bindings/clock/imx27-clock.yaml b/Documentation/devicetree/bindings/clock/imx27-clock.yaml index b5f3ed084ea0..a75365453dbc 100644 --- a/Documentation/devicetree/bindings/clock/imx27-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx27-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX27 maintainers: - - Fabio Estevam <fabio.estevam@freescale.com> + - Fabio Estevam <fabio.estevam@nxp.com> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/clock/imx31-clock.yaml b/Documentation/devicetree/bindings/clock/imx31-clock.yaml index 1b6f75d3928a..a25a374b3b2a 100644 --- a/Documentation/devicetree/bindings/clock/imx31-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx31-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX31 maintainers: - - Fabio Estevam <fabio.estevam@freescale.com> + - Fabio Estevam <fabio.estevam@nxp.com> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml index f5c2b3d7a910..4d9e7c73dce9 100644 --- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX5 maintainers: - - Fabio Estevam <fabio.estevam@freescale.com> + - Fabio Estevam <fabio.estevam@nxp.com> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/display/bridge/sii902x.txt b/Documentation/devicetree/bindings/display/bridge/sii902x.txt index 6e14e087c0d0..0d1db3f9da84 100644 --- a/Documentation/devicetree/bindings/display/bridge/sii902x.txt +++ b/Documentation/devicetree/bindings/display/bridge/sii902x.txt @@ -37,7 +37,7 @@ Optional properties: simple-card or audio-graph-card binding. See their binding documents on how to describe the way the sii902x device is connected to the rest of the audio system: - Documentation/devicetree/bindings/sound/simple-card.txt + Documentation/devicetree/bindings/sound/simple-card.yaml Documentation/devicetree/bindings/sound/audio-graph-card.txt Note: In case of the audio-graph-card binding the used port index should be 3. diff --git a/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt b/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt index 5bf77f6dd19d..5a99490c17b9 100644 --- a/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt +++ b/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt @@ -68,7 +68,7 @@ Required properties: datasheet - clocks : phandle to the PRE axi clock input, as described in Documentation/devicetree/bindings/clock/clock-bindings.txt and - Documentation/devicetree/bindings/clock/imx6q-clock.txt. + Documentation/devicetree/bindings/clock/imx6q-clock.yaml. - clock-names: should be "axi" - interrupts: should contain the PRE interrupt - fsl,iram: phandle pointing to the mmio-sram device node, that should be @@ -94,7 +94,7 @@ Required properties: datasheet - clocks : phandles to the PRG ipg and axi clock inputs, as described in Documentation/devicetree/bindings/clock/clock-bindings.txt and - Documentation/devicetree/bindings/clock/imx6q-clock.txt. + Documentation/devicetree/bindings/clock/imx6q-clock.yaml. - clock-names: should be "ipg" and "axi" - fsl,pres: phandles to the PRE units attached to this PRG, with the fixed PRE as the first entry and the muxable PREs following. diff --git a/Documentation/devicetree/bindings/display/imx/ldb.txt b/Documentation/devicetree/bindings/display/imx/ldb.txt index 38c637fa39dd..8e6e7d797943 100644 --- a/Documentation/devicetree/bindings/display/imx/ldb.txt +++ b/Documentation/devicetree/bindings/display/imx/ldb.txt @@ -30,8 +30,8 @@ Required properties: "di2_sel" - IPU2 DI0 mux "di3_sel" - IPU2 DI1 mux The needed clock numbers for each are documented in - Documentation/devicetree/bindings/clock/imx5-clock.txt, and in - Documentation/devicetree/bindings/clock/imx6q-clock.txt. + Documentation/devicetree/bindings/clock/imx5-clock.yaml, and in + Documentation/devicetree/bindings/clock/imx6q-clock.yaml. Optional properties: - pinctrl-names : should be "default" on i.MX53, not used on i.MX6q diff --git a/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml b/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml index 41fd5713c156..be69e0cc50fc 100644 --- a/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml +++ b/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml @@ -33,7 +33,7 @@ additionalProperties: false examples: - | - sysreg { + sysreg@0 { compatible = "arm,versatile-sysreg", "syscon", "simple-mfd"; reg = <0x00000 0x1000>; diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml index ec8ae742d4da..7204da5eb4c5 100644 --- a/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml +++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml @@ -24,7 +24,7 @@ properties: description: | Should contain a list of phandles pointing to display interface port of vop devices. vop definitions as defined in - Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt + Documentation/devicetree/bindings/display/rockchip/rockchip-vop.yaml required: - compatible diff --git a/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt b/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt index ba455589f869..e1c49b660d3a 100644 --- a/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt +++ b/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt @@ -12,7 +12,7 @@ Required properties for the top level node: Only the GPIO_ACTIVE_HIGH and GPIO_ACTIVE_LOW flags are supported. - #interrupt-cells : Specifies the number of cells needed to encode an interrupt. Should be 2. The first cell defines the interrupt number, - the second encodes the triger flags encoded as described in + the second encodes the trigger flags encoded as described in Documentation/devicetree/bindings/interrupt-controller/interrupts.txt - compatible: - "mediatek,mt7621-gpio" for Mediatek controllers diff --git a/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt b/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt index e13405355166..e6bbcae4d07f 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt @@ -10,7 +10,7 @@ Interrupt number definition: 16-31 : private irq, and we use 16 as the co-processor timer. 31-1024: common irq for soc ip. -Interrupt triger mode: (Defined in dt-bindings/interrupt-controller/irq.h) +Interrupt trigger mode: (Defined in dt-bindings/interrupt-controller/irq.h) IRQ_TYPE_LEVEL_HIGH (default) IRQ_TYPE_LEVEL_LOW IRQ_TYPE_EDGE_RISING diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt index 4438432bfe9b..ad76edccf881 100644 --- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt +++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt @@ -87,7 +87,7 @@ Example: ranges; /* APU<->RPU0 IPI mailbox controller */ - ipi_mailbox_rpu0: mailbox@ff90400 { + ipi_mailbox_rpu0: mailbox@ff990400 { reg = <0xff990400 0x20>, <0xff990420 0x20>, <0xff990080 0x20>, diff --git a/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt b/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt index 8c4d649cdd8f..2d7cdf19a0d0 100644 --- a/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt +++ b/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt @@ -8,7 +8,7 @@ The embedded controller requires the SPI controller driver to signal readiness to receive a transfer (that is, when TX FIFO contains the response data) by strobing the ACK pin with the ready signal. See the "ready-gpios" property of the SSP binding as documented in: -<Documentation/devicetree/bindings/spi/spi-pxa2xx.txt>. +<Documentation/devicetree/bindings/spi/marvell,mmp2-ssp.yaml>. Example: &ssp3 { diff --git a/Documentation/devicetree/bindings/net/dsa/ocelot.txt b/Documentation/devicetree/bindings/net/dsa/ocelot.txt index 66a129fea705..7a271d070b72 100644 --- a/Documentation/devicetree/bindings/net/dsa/ocelot.txt +++ b/Documentation/devicetree/bindings/net/dsa/ocelot.txt @@ -4,10 +4,15 @@ Microchip Ocelot switch driver family Felix ----- -The VSC9959 core is currently the only switch supported by the driver, and is -found in the NXP LS1028A. It is a PCI device, part of the larger ENETC root -complex. As a result, the ethernet-switch node is a sub-node of the PCIe root -complex node and its "reg" property conforms to the parent node bindings: +Currently the switches supported by the felix driver are: + +- VSC9959 (Felix) +- VSC9953 (Seville) + +The VSC9959 switch is found in the NXP LS1028A. It is a PCI device, part of the +larger ENETC root complex. As a result, the ethernet-switch node is a sub-node +of the PCIe root complex node and its "reg" property conforms to the parent +node bindings: * reg: Specifies PCIe Device Number and Function Number of the endpoint device, in this case for the Ethernet L2Switch it is PF5 (of device 0, bus 0). @@ -114,3 +119,95 @@ Example: }; }; }; + +The VSC9953 switch is found inside NXP T1040. It is a platform device with the +following required properties: + +- compatible: + Must be "mscc,vsc9953-switch". + +Supported PHY interface types (appropriate SerDes protocol setting changes are +needed in the RCW binary): + +* phy_mode = "internal": on ports 8 and 9 +* phy_mode = "sgmii": on ports 0, 1, 2, 3, 4, 5, 6, 7 +* phy_mode = "qsgmii": on ports 0, 1, 2, 3, 4, 5, 6, 7 + +Example: + +&soc { + ethernet-switch@800000 { + #address-cells = <0x1>; + #size-cells = <0x0>; + compatible = "mscc,vsc9953-switch"; + little-endian; + reg = <0x800000 0x290000>; + + ports { + #address-cells = <0x1>; + #size-cells = <0x0>; + + port@0 { + reg = <0x0>; + label = "swp0"; + }; + + port@1 { + reg = <0x1>; + label = "swp1"; + }; + + port@2 { + reg = <0x2>; + label = "swp2"; + }; + + port@3 { + reg = <0x3>; + label = "swp3"; + }; + + port@4 { + reg = <0x4>; + label = "swp4"; + }; + + port@5 { + reg = <0x5>; + label = "swp5"; + }; + + port@6 { + reg = <0x6>; + label = "swp6"; + }; + + port@7 { + reg = <0x7>; + label = "swp7"; + }; + + port@8 { + reg = <0x8>; + phy-mode = "internal"; + ethernet = <&enet0>; + + fixed-link { + speed = <2500>; + full-duplex; + }; + }; + + port@9 { + reg = <0x9>; + phy-mode = "internal"; + status = "disabled"; + + fixed-link { + speed = <2500>; + full-duplex; + }; + }; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt b/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt index 219bcbd0d344..9ef5bacda8c1 100644 --- a/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt +++ b/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt @@ -3,7 +3,7 @@ MediaTek SoC built-in Bluetooth Devices This device is a serial attached device to BTIF device and thus it must be a child node of the serial node with BTIF. The dt-bindings details for BTIF -device can be known via Documentation/devicetree/bindings/serial/8250.txt. +device can be known via Documentation/devicetree/bindings/serial/8250.yaml. Required properties: diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.yaml b/Documentation/devicetree/bindings/net/ti,dp83867.yaml index 554dcd7a40a9..c6716ac6cbcc 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83867.yaml +++ b/Documentation/devicetree/bindings/net/ti,dp83867.yaml @@ -24,7 +24,7 @@ description: | IEEE 802.3 Standard Media Independent Interface (MII), the IEEE 802.3 Gigabit Media Independent Interface (GMII) or Reduced GMII (RGMII). - Specifications about the charger can be found at: + Specifications about the Ethernet PHY can be found at: https://www.ti.com/lit/gpn/dp83867ir properties: diff --git a/Documentation/devicetree/bindings/net/ti,dp83869.yaml b/Documentation/devicetree/bindings/net/ti,dp83869.yaml index 71e90a3e4652..cf40b469c719 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83869.yaml +++ b/Documentation/devicetree/bindings/net/ti,dp83869.yaml @@ -24,7 +24,7 @@ description: | conversions. The DP83869HM can also support Bridge Conversion from RGMII to SGMII and SGMII to RGMII. - Specifications about the charger can be found at: + Specifications about the Ethernet PHY can be found at: http://www.ti.com/lit/ds/symlink/dp83869hm.pdf properties: diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt index b68613188c19..1b8e8b4a6379 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt @@ -114,7 +114,7 @@ with values derived from the SoC user manual. [flags]> On other mach-shmobile platforms GPIO is handled by the gpio-rcar driver. -Please refer to Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt +Please refer to Documentation/devicetree/bindings/gpio/renesas,rcar-gpio.yaml for documentation of the GPIO device tree bindings on those platforms. diff --git a/Documentation/devicetree/bindings/sound/audio-graph-card.txt b/Documentation/devicetree/bindings/sound/audio-graph-card.txt index 269682619a70..d5f6919a2d69 100644 --- a/Documentation/devicetree/bindings/sound/audio-graph-card.txt +++ b/Documentation/devicetree/bindings/sound/audio-graph-card.txt @@ -5,7 +5,7 @@ It is based on common bindings for device graphs. see ${LINUX}/Documentation/devicetree/bindings/graph.txt Basically, Audio Graph Card property is same as Simple Card. -see ${LINUX}/Documentation/devicetree/bindings/sound/simple-card.txt +see ${LINUX}/Documentation/devicetree/bindings/sound/simple-card.yaml Below are same as Simple-Card. diff --git a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt index 4d51f3f5ea98..a6ffcdec6f6a 100644 --- a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt +++ b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt @@ -5,7 +5,7 @@ codec or external codecs. sti sound drivers allows to expose sti SoC audio interface through the generic ASoC simple card. For details about sound card declaration please refer to -Documentation/devicetree/bindings/sound/simple-card.txt. +Documentation/devicetree/bindings/sound/simple-card.yaml. 1) sti-uniperiph-dai: audio dai device. --------------------------------------- diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt b/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt index 790311a42bf1..c8c1e913f4e7 100644 --- a/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt +++ b/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt @@ -19,7 +19,7 @@ Required properties: SPI Controller nodes must be child of GENI based Qualcomm Universal Peripharal. Please refer GENI based QUP wrapper controller node bindings -described in Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt. +described in Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.yaml. SPI slave nodes must be children of the SPI master node and conform to SPI bus binding as described in Documentation/devicetree/bindings/spi/spi-bus.txt. diff --git a/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml b/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml index fcd25a0af38c..727d04550324 100644 --- a/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml +++ b/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml @@ -41,7 +41,7 @@ examples: #include <dt-bindings/interrupt-controller/arm-gic.h> // Example 1: SDM845 TSENS - soc: soc@0 { + soc: soc { #address-cells = <2>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml index b8515d3eeaa2..3ec9cc87ec50 100644 --- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml +++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml @@ -224,7 +224,7 @@ examples: #include <dt-bindings/thermal/thermal.h> // Example 1: SDM845 TSENS - soc: soc@0 { + soc { #address-cells = <2>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml b/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml index 25b9209c2e5d..ea14de80ec75 100644 --- a/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml @@ -35,7 +35,7 @@ examples: #include <dt-bindings/soc/ti,sci_pm_domain.h> vtm: thermal@42050000 { compatible = "ti,am654-vtm"; - reg = <0x0 0x42050000 0x0 0x25c>; + reg = <0x42050000 0x25c>; power-domains = <&k3_pds 80 TI_SCI_PD_EXCLUSIVE>; #thermal-sensor-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/timer/csky,mptimer.txt b/Documentation/devicetree/bindings/timer/csky,mptimer.txt index 15cfec08fbb8..f5c7e99cf52b 100644 --- a/Documentation/devicetree/bindings/timer/csky,mptimer.txt +++ b/Documentation/devicetree/bindings/timer/csky,mptimer.txt @@ -8,7 +8,7 @@ regs is accessed by cpu co-processor 4 registers with mtcr/mfcr. - PTIM_CTLR "cr<0, 14>" Control reg to start reset timer. - PTIM_TSR "cr<1, 14>" Interrupt cleanup status reg. - PTIM_CCVR "cr<3, 14>" Current counter value reg. - - PTIM_LVR "cr<6, 14>" Window value reg to triger next event. + - PTIM_LVR "cr<6, 14>" Window value reg to trigger next event. ============================== timer node bindings definition diff --git a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml index e4e83d3971ac..8b019ac05bbe 100644 --- a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml +++ b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml @@ -127,8 +127,8 @@ examples: #address-cells = <1>; #size-cells = <0>; - string@0409 { - reg = <0x0409>; + string@409 { + reg = <0x409>; manufacturer = "ASPEED"; product = "USB Virtual Hub"; serial-number = "0000"; diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst index 220cf464ed77..8c74a99f95e2 100644 --- a/Documentation/devicetree/writing-schema.rst +++ b/Documentation/devicetree/writing-schema.rst @@ -1,4 +1,4 @@ -:orphan: +.. SPDX-License-Identifier: GPL-2.0 Writing DeviceTree Bindings in json-schema ========================================== @@ -124,9 +124,12 @@ dtc must also be built with YAML output support enabled. This requires that libyaml and its headers be installed on the host system. For some distributions that involves installing the development package, such as: -Debian: +Debian:: + apt-get install libyaml-dev -Fedora: + +Fedora:: + dnf -y install libyaml-devel Running checks diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst index 1da7a4b7383d..728ab57a611a 100644 --- a/Documentation/filesystems/debugfs.rst +++ b/Documentation/filesystems/debugfs.rst @@ -185,13 +185,17 @@ byte offsets over a base for the register block. If you want to dump an u32 array in debugfs, you can create file with:: + struct debugfs_u32_array { + u32 *array; + u32 n_elements; + }; + void debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, - u32 *array, u32 elements); + struct debugfs_u32_array *array); -The "array" argument provides data, and the "elements" argument is -the number of elements in the array. Note: Once array is created its -size can not be changed. +The "array" argument wraps a pointer to the array's data and the number +of its elements. Note: Once array is created its size can not be changed. There is a helper function to create device related seq_file:: diff --git a/Documentation/i2c/slave-eeprom-backend.rst b/Documentation/i2c/slave-eeprom-backend.rst index 0b8cd83698e0..38d951f10302 100644 --- a/Documentation/i2c/slave-eeprom-backend.rst +++ b/Documentation/i2c/slave-eeprom-backend.rst @@ -1,14 +1,26 @@ ============================== -Linux I2C slave eeprom backend +Linux I2C slave EEPROM backend ============================== -by Wolfram Sang <wsa@sang-engineering.com> in 2014-15 +by Wolfram Sang <wsa@sang-engineering.com> in 2014-20 -This is a proof-of-concept backend which acts like an EEPROM on the connected -I2C bus. The memory contents can be modified from userspace via this file -located in sysfs:: +This backend simulates an EEPROM on the connected I2C bus. Its memory contents +can be accessed from userspace via this file located in sysfs:: /sys/bus/i2c/devices/<device-directory>/slave-eeprom +The following types are available: 24c02, 24c32, 24c64, and 24c512. Read-only +variants are also supported. The name needed for instantiating has the form +'slave-<type>[ro]'. Examples follow: + +24c02, read/write, address 0x64: + # echo slave-24c02 0x1064 > /sys/bus/i2c/devices/i2c-1/new_device + +24c512, read-only, address 0x42: + # echo slave-24c512ro 0x1042 > /sys/bus/i2c/devices/i2c-1/new_device + +You can also preload data during boot if a device-property named +'firmware-name' contains a valid filename (DT or ACPI only). + As of 2015, Linux doesn't support poll on binary sysfs files, so there is no notification when another master changed the content. diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index a45cccff467d..85ccc878895e 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -182,7 +182,8 @@ module 8123.ko, which is built from the following files:: 8123_pci.c 8123_bin.o_shipped <= Binary blob ---- 3.1 Shared Makefile +3.1 Shared Makefile +------------------- An external module always includes a wrapper makefile that supports building the module using "make" with no arguments. @@ -470,9 +471,9 @@ build. The syntax of the Module.symvers file is:: - <CRC> <Symbol> <Module> <Export Type> <Namespace> + <CRC> <Symbol> <Module> <Export Type> <Namespace> - 0xe1cc2a05 usb_stor_suspend drivers/usb/storage/usb-storage EXPORT_SYMBOL_GPL USB_STORAGE + 0xe1cc2a05 usb_stor_suspend drivers/usb/storage/usb-storage EXPORT_SYMBOL_GPL USB_STORAGE The fields are separated by tabs and values may be empty (e.g. if no namespace is defined for an exported symbol). diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index 503393854e2e..3b25655e441b 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -101,7 +101,7 @@ Structure randomisation If you enable ``CONFIG_GCC_PLUGIN_RANDSTRUCT``, you will need to pre-generate the random seed in -``scripts/gcc-plgins/randomize_layout_seed.h`` so the same value +``scripts/gcc-plugins/randomize_layout_seed.h`` so the same value is used in rebuilds. Debug info conflicts diff --git a/Documentation/mips/ingenic-tcu.rst b/Documentation/mips/ingenic-tcu.rst index c5a646b14450..2b75760619b4 100644 --- a/Documentation/mips/ingenic-tcu.rst +++ b/Documentation/mips/ingenic-tcu.rst @@ -68,4 +68,4 @@ and frameworks can be controlled from the same registers, all of these drivers access their registers through the same regmap. For more information regarding the devicetree bindings of the TCU drivers, -have a look at Documentation/devicetree/bindings/timer/ingenic,tcu.txt. +have a look at Documentation/devicetree/bindings/timer/ingenic,tcu.yaml. diff --git a/Documentation/networking/arcnet.rst b/Documentation/networking/arcnet.rst index e93d9820f0f1..82fce606c0f0 100644 --- a/Documentation/networking/arcnet.rst +++ b/Documentation/networking/arcnet.rst @@ -434,7 +434,7 @@ can set up your network then: ifconfig arc0 insight route add insight arc0 route add freedom arc0 /* I would use the subnet here (like I said - to to in "single protocol" above), + to in "single protocol" above), but the rest of the subnet unfortunately lies across the PPP link on freedom, which confuses diff --git a/Documentation/networking/ax25.rst b/Documentation/networking/ax25.rst index 824afd7002db..f060cfb1445a 100644 --- a/Documentation/networking/ax25.rst +++ b/Documentation/networking/ax25.rst @@ -6,7 +6,7 @@ AX.25 To use the amateur radio protocols within Linux you will need to get a suitable copy of the AX.25 Utilities. More detailed information about -AX.25, NET/ROM and ROSE, associated programs and and utilities can be +AX.25, NET/ROM and ROSE, associated programs and utilities can be found on http://www.linux-ax25.org. There is an active mailing list for discussing Linux amateur radio matters diff --git a/Documentation/networking/can_ucan_protocol.rst b/Documentation/networking/can_ucan_protocol.rst index 4cef88d24fc7..638ac1ee7914 100644 --- a/Documentation/networking/can_ucan_protocol.rst +++ b/Documentation/networking/can_ucan_protocol.rst @@ -144,7 +144,7 @@ UCAN_COMMAND_SET_BITTIMING *Host2Dev; mandatory* -Setup bittiming by sending the the structure +Setup bittiming by sending the structure ``ucan_ctl_payload_t.cmd_set_bittiming`` (see ``struct bittiming`` for details) @@ -232,7 +232,7 @@ UCAN_IN_TX_COMPLETE zero The CAN device has sent a message to the CAN bus. It answers with a -list of of tuples <echo-ids, flags>. +list of tuples <echo-ids, flags>. The echo-id identifies the frame from (echos the id from a previous UCAN_OUT_TX message). The flag indicates the result of the diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 563d56c6a25c..a8d15dd2b42b 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -95,7 +95,7 @@ Ethernet switch. Networking stack hooks ---------------------- -When a master netdev is used with DSA, a small hook is placed in in the +When a master netdev is used with DSA, a small hook is placed in the networking stack is in order to have the DSA subsystem process the Ethernet switch specific tagging protocol. DSA accomplishes this by registering a specific (and fake) Ethernet type (later becoming ``skb->protocol``) with the diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 396390f4936b..7d75f1e32152 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -506,13 +506,13 @@ Link extended states: power required from cable or module ``ETHTOOL_LINK_EXT_STATE_OVERHEAT`` The module is overheated - ================================================= ============================================ + ================================================ ============================================ Link extended substates: Autoneg substates: - ============================================================== ================================ + =============================================================== ================================ ``ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED`` Peer side is down ``ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED`` Ack not received from peer side @@ -527,11 +527,11 @@ Link extended substates: in both sides are mismatched ``ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD`` No Highest Common Denominator - ============================================================== ================================ + =============================================================== ================================ Link training substates: - ========================================================================== ==================== + =========================================================================== ==================== ``ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED`` Frames were not recognized, the lock failed @@ -547,11 +547,11 @@ Link extended substates: ``ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT`` Remote side is not ready yet - ========================================================================== ==================== + =========================================================================== ==================== Link logical mismatch substates: - =============================================================== =============================== + ================================================================ =============================== ``ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK`` Physical coding sublayer was not locked in first phase - block lock @@ -568,7 +568,7 @@ Link extended substates: ``ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED`` RS forward error correction is not locked - =============================================================== =============================== + ================================================================ =============================== Bad signal integrity substates: @@ -585,11 +585,11 @@ Link extended substates: Cable issue substates: - ================================================== ============================================ + =================================================== ============================================ ``ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE`` Unsupported cable ``ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE`` Cable test failure - ================================================== ============================================ + =================================================== ============================================ DEBUG_GET ========= @@ -1230,6 +1230,39 @@ used to report the amplitude of the reflection for a given pair. | | | ``ETHTOOL_A_CABLE_AMPLITUDE_mV`` | s16 | Reflection amplitude | +-+-+-----------------------------------------+--------+----------------------+ +TUNNEL_INFO +=========== + +Gets information about the tunnel state NIC is aware of. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_TUNNEL_INFO_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + +---------------------------------------------+--------+---------------------+ + | ``ETHTOOL_A_TUNNEL_INFO_HEADER`` | nested | reply header | + +---------------------------------------------+--------+---------------------+ + | ``ETHTOOL_A_TUNNEL_INFO_UDP_PORTS`` | nested | all UDP port tables | + +-+-------------------------------------------+--------+---------------------+ + | | ``ETHTOOL_A_TUNNEL_UDP_TABLE`` | nested | one UDP port table | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE`` | u32 | max size of the | + | | | | | table | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES`` | bitset | tunnel types which | + | | | | | table can hold | + +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY`` | nested | offloaded UDP port | + +-+-+-+---------------------------------------+--------+---------------------+ + | | | | ``ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT`` | be16 | UDP port | + +-+-+-+---------------------------------------+--------+---------------------+ + | | | | ``ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE`` | u32 | tunnel type | + +-+-+-+---------------------------------------+--------+---------------------+ + Request translation =================== diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b72f89d5694c..837d51f9e1fa 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -741,7 +741,7 @@ tcp_fastopen - INTEGER Default: 0x1 - Note that that additional client or server features are only + Note that additional client or server features are only effective if the basic support (0x1 and 0x2) are enabled respectively. tcp_fastopen_blackhole_timeout_sec - INTEGER diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index be36c4600e8f..2afccc63856e 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -114,7 +114,7 @@ drop_entry - INTEGER modes (when there is no enough available memory, the strategy is enabled and the variable is automatically set to 2, otherwise the strategy is disabled and the variable is set to - 1), and 3 means that that the strategy is always enabled. + 1), and 3 means that the strategy is always enabled. drop_packet - INTEGER - 0 - disabled (default) diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst index 68552b92dc44..39c2249c7aa7 100644 --- a/Documentation/networking/rxrpc.rst +++ b/Documentation/networking/rxrpc.rst @@ -186,7 +186,7 @@ About the AF_RXRPC driver: time [tunable] after the last connection using it discarded, in case a new connection is made that could use it. - (#) A client-side connection is only shared between calls if they have have + (#) A client-side connection is only shared between calls if they have the same key struct describing their security (and assuming the calls would otherwise share the connection). Non-secured calls would also be able to share connections with each other. diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 5cfb54c2aaa6..8f68e728ae6b 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -29,7 +29,7 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== Program Minimal version Command to check the version ====================== =============== ======================================== -GNU C 4.8 gcc --version +GNU C 4.9 gcc --version GNU make 3.81 make --version binutils 2.23 ld -v flex 2.5.35 flex --version diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index 2657a55c6f12..1bee6f8affdb 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -319,6 +319,26 @@ If you are afraid to mix up your local variable names, you have another problem, which is called the function-growth-hormone-imbalance syndrome. See chapter 6 (Functions). +For symbol names and documentation, avoid introducing new usage of +'master / slave' (or 'slave' independent of 'master') and 'blacklist / +whitelist'. + +Recommended replacements for 'master / slave' are: + '{primary,main} / {secondary,replica,subordinate}' + '{initiator,requester} / {target,responder}' + '{controller,host} / {device,worker,proxy}' + 'leader / follower' + 'director / performer' + +Recommended replacements for 'blacklist/whitelist' are: + 'denylist / allowlist' + 'blocklist / passlist' + +Exceptions for introducing new usage is to maintain a userspace ABI/API, +or when updating code for an existing (as of 2020) hardware or protocol +specification that mandates those terms. For new specifications +translate specification usage of the terminology to the kernel coding +standard where possible. 5) Typedefs ----------- diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 426f94582b7a..320788f81a05 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4339,14 +4339,15 @@ Errors: #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 struct kvm_vmx_nested_state_hdr { - __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; - __u64 preemption_timer_deadline; struct { __u16 flags; } smm; + + __u32 flags; + __u64 preemption_timer_deadline; }; struct kvm_vmx_nested_state_data { diff --git a/MAINTAINERS b/MAINTAINERS index e5a1da603924..b325ed166228 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2929,6 +2929,7 @@ F: include/uapi/linux/atm* ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre <nicolas.ferre@microchip.com> +M: Claudiu Beznea <claudiu.beznea@microchip.com> S: Supported F: drivers/net/ethernet/cadence/ @@ -3306,7 +3307,7 @@ X: arch/riscv/net/bpf_jit_comp32.c BPF JIT for S390 M: Ilya Leoshkevich <iii@linux.ibm.com> -M: Heiko Carstens <heiko.carstens@de.ibm.com> +M: Heiko Carstens <hca@linux.ibm.com> M: Vasily Gorbik <gor@linux.ibm.com> L: netdev@vger.kernel.org L: bpf@vger.kernel.org @@ -3946,7 +3947,7 @@ L: linux-crypto@vger.kernel.org S: Supported F: drivers/char/hw_random/cctrng.c F: drivers/char/hw_random/cctrng.h -F: Documentation/devicetree/bindings/rng/arm-cctrng.txt +F: Documentation/devicetree/bindings/rng/arm-cctrng.yaml W: https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family CEC FRAMEWORK @@ -5490,7 +5491,7 @@ F: include/uapi/drm/r128_drm.h DRM DRIVER FOR RAYDIUM RM67191 PANELS M: Robert Chiras <robert.chiras@nxp.com> S: Maintained -F: Documentation/devicetree/bindings/display/panel/raydium,rm67191.txt +F: Documentation/devicetree/bindings/display/panel/raydium,rm67191.yaml F: drivers/gpu/drm/panel/panel-raydium-rm67191.c DRM DRIVER FOR ROCKTECH JH057N00900 PANELS @@ -12684,13 +12685,13 @@ F: arch/mips/boot/dts/ralink/omega2p.dts OP-TEE DRIVER M: Jens Wiklander <jens.wiklander@linaro.org> -L: tee-dev@lists.linaro.org +L: op-tee@lists.trustedfirmware.org S: Maintained F: drivers/tee/optee/ OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER M: Sumit Garg <sumit.garg@linaro.org> -L: tee-dev@lists.linaro.org +L: op-tee@lists.trustedfirmware.org S: Maintained F: drivers/char/hw_random/optee-rng.c @@ -14563,8 +14564,8 @@ RENESAS R-CAR THERMAL DRIVERS M: Niklas Söderlund <niklas.soderlund@ragnatech.se> L: linux-renesas-soc@vger.kernel.org S: Supported -F: Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.txt -F: Documentation/devicetree/bindings/thermal/rcar-thermal.txt +F: Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml +F: Documentation/devicetree/bindings/thermal/rcar-thermal.yaml F: drivers/thermal/rcar_gen3_thermal.c F: drivers/thermal/rcar_thermal.c @@ -14820,7 +14821,7 @@ S: Maintained F: drivers/video/fbdev/savage/ S390 -M: Heiko Carstens <heiko.carstens@de.ibm.com> +M: Heiko Carstens <hca@linux.ibm.com> M: Vasily Gorbik <gor@linux.ibm.com> M: Christian Borntraeger <borntraeger@de.ibm.com> L: linux-s390@vger.kernel.org @@ -14851,7 +14852,7 @@ F: drivers/s390/block/dasd* F: include/linux/dasd_mod.h S390 IOMMU (PCI) -M: Gerald Schaefer <gerald.schaefer@de.ibm.com> +M: Gerald Schaefer <gerald.schaefer@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -14879,7 +14880,7 @@ F: drivers/s390/net/ S390 PCI SUBSYSTEM M: Niklas Schnelle <schnelle@linux.ibm.com> -M: Gerald Schaefer <gerald.schaefer@de.ibm.com> +M: Gerald Schaefer <gerald.schaefer@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -16047,8 +16048,10 @@ SPARSE CHECKER M: "Luc Van Oostenryck" <luc.vanoostenryck@gmail.com> L: linux-sparse@vger.kernel.org S: Maintained -W: https://sparse.wiki.kernel.org/ +W: https://sparse.docs.kernel.org/ T: git git://git.kernel.org/pub/scm/devel/sparse/sparse.git +Q: https://patchwork.kernel.org/project/linux-sparse/list/ +B: https://bugzilla.kernel.org/enter_bug.cgi?component=Sparse&product=Tools F: include/linux/compiler.h SPEAR CLOCK FRAMEWORK SUPPORT @@ -16761,7 +16764,7 @@ F: include/media/i2c/tw9910.h TEE SUBSYSTEM M: Jens Wiklander <jens.wiklander@linaro.org> -L: tee-dev@lists.linaro.org +L: op-tee@lists.trustedfirmware.org S: Maintained F: Documentation/tee.txt F: drivers/tee/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc4 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -971,8 +971,8 @@ LDFLAGS_vmlinux += --pack-dyn-relocs=relr endif # Align the bit size of userspace programs with the kernel -KBUILD_USERCFLAGS += $(filter -m32 -m64, $(KBUILD_CFLAGS)) -KBUILD_USERLDFLAGS += $(filter -m32 -m64, $(KBUILD_CFLAGS)) +KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) +KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) # make the checker run with the right architecture CHECKFLAGS += --arch=$(ARCH) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index fddc70029727..197896cfbd23 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -170,6 +170,15 @@ config ARC_CPU_HS endchoice +config ARC_TUNE_MCPU + string "Override default -mcpu compiler flag" + default "" + help + Override default -mcpu=xxx compiler flag (which is set depending on + the ISA version) with the specified value. + NOTE: If specified flag isn't supported by current compiler the + ISA default value will be used as a fallback. + config CPU_BIG_ENDIAN bool "Enable Big Endian Mode" help @@ -465,6 +474,12 @@ config ARC_IRQ_NO_AUTOSAVE This is programmable and can be optionally disabled in which case software INTERRUPT_PROLOGUE/EPILGUE do the needed work +config ARC_LPB_DISABLE + bool "Disable loop buffer (LPB)" + help + On HS cores, loop buffer (LPB) is programmable in runtime and can + be optionally disabled. + endif # ISA_ARCV2 endmenu # "ARC CPU Configuration" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 20e9ab6cc521..d00f8b8afd08 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -10,8 +10,25 @@ CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) endif cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ -cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 -cflags-$(CONFIG_ISA_ARCV2) += -mcpu=hs38 + +tune-mcpu-def-$(CONFIG_ISA_ARCOMPACT) := -mcpu=arc700 +tune-mcpu-def-$(CONFIG_ISA_ARCV2) := -mcpu=hs38 + +ifeq ($(CONFIG_ARC_TUNE_MCPU),"") +cflags-y += $(tune-mcpu-def-y) +else +tune-mcpu := $(shell echo $(CONFIG_ARC_TUNE_MCPU)) +tune-mcpu-ok := $(call cc-option-yn, $(tune-mcpu)) +ifeq ($(tune-mcpu-ok),y) +cflags-y += $(tune-mcpu) +else +# The flag provided by 'CONFIG_ARC_TUNE_MCPU' option isn't known by this compiler +# (probably the compiler is too old). Use ISA default mcpu flag instead as a safe option. +$(warning ** WARNING ** CONFIG_ARC_TUNE_MCPU flag '$(tune-mcpu)' is unknown, fallback to '$(tune-mcpu-def-y)') +cflags-y += $(tune-mcpu-def-y) +endif +endif + ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h index c77a0e3671ac..0284ace0e1ab 100644 --- a/arch/arc/include/asm/elf.h +++ b/arch/arc/include/asm/elf.h @@ -19,7 +19,7 @@ #define R_ARC_32_PCREL 0x31 /*to set parameters in the core dumps */ -#define ELF_ARCH EM_ARCOMPACT +#define ELF_ARCH EM_ARC_INUSE #define ELF_CLASS ELFCLASS32 #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index 7fc73fef5e29..863d63ad18d6 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -90,6 +90,9 @@ static inline void arch_local_irq_restore(unsigned long flags) /* * Unconditionally Enable IRQs */ +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS +extern void arch_local_irq_enable(void); +#else static inline void arch_local_irq_enable(void) { unsigned long temp; @@ -102,7 +105,7 @@ static inline void arch_local_irq_enable(void) : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) : "cc", "memory"); } - +#endif /* * Unconditionally Disable IRQs diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 60406ec62eb8..ea00c8a17f07 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -165,7 +165,6 @@ END(EV_Extension) tracesys: ; save EFA in case tracer wants the PC of traced task ; using ERET won't work since next-PC has already committed - lr r12, [efa] GET_CURR_TASK_FIELD_PTR TASK_THREAD, r11 st r12, [r11, THREAD_FAULT_ADDR] ; thread.fault_address @@ -208,15 +207,9 @@ tracesys_exit: ; Breakpoint TRAP ; --------------------------------------------- trap_with_param: - - ; stop_pc info by gdb needs this info - lr r0, [efa] + mov r0, r12 ; EFA in case ptracer/gdb wants stop_pc mov r1, sp - ; Now that we have read EFA, it is safe to do "fake" rtie - ; and get out of CPU exception mode - FAKE_RET_FROM_EXCPN - ; Save callee regs in case gdb wants to have a look ; SP will grow up by size of CALLEE Reg-File ; NOTE: clobbers r12 @@ -243,6 +236,10 @@ ENTRY(EV_Trap) EXCEPTION_PROLOGUE + lr r12, [efa] + + FAKE_RET_FROM_EXCPN + ;============ TRAP 1 :breakpoints ; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR) bmsk.f 0, r10, 7 @@ -250,9 +247,6 @@ ENTRY(EV_Trap) ;============ TRAP (no param): syscall top level - ; First return from Exception to pure K mode (Exception/IRQs renabled) - FAKE_RET_FROM_EXCPN - ; If syscall tracing ongoing, invoke pre-post-hooks GET_CURR_THR_INFO_FLAGS r10 btst r10, TIF_SYSCALL_TRACE diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 6eb23f1545ee..17fd1ed700cc 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -59,6 +59,14 @@ bclr r5, r5, STATUS_AD_BIT #endif kflag r5 + +#ifdef CONFIG_ARC_LPB_DISABLE + lr r5, [ARC_REG_LPB_BUILD] + breq r5, 0, 1f ; LPB doesn't exist + mov r5, 1 + sr r5, [ARC_REG_LPB_CTRL] +1: +#endif /* CONFIG_ARC_LPB_DISABLE */ #endif ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index dad8a656a2f1..41f07b3e594e 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -58,10 +58,12 @@ static const struct id_to_str arc_legacy_rel[] = { { 0x00, NULL } }; -static const struct id_to_str arc_cpu_rel[] = { +static const struct id_to_str arc_hs_ver54_rel[] = { /* UARCH.MAJOR, Release */ { 0, "R3.10a"}, { 1, "R3.50a"}, + { 2, "R3.60a"}, + { 3, "R4.00a"}, { 0xFF, NULL } }; @@ -117,12 +119,6 @@ static void decode_arc_core(struct cpuinfo_arc *cpu) struct bcr_uarch_build_arcv2 uarch; const struct id_to_str *tbl; - /* - * Up until (including) the first core4 release (0x54) things were - * simple: AUX IDENTITY.ARCVER was sufficient to identify arc family - * and release: 0x50 to 0x53 was HS38, 0x54 was HS48 (dual issue) - */ - if (cpu->core.family < 0x54) { /* includes arc700 */ for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) { @@ -143,11 +139,10 @@ static void decode_arc_core(struct cpuinfo_arc *cpu) } /* - * However the subsequent HS release (same 0x54) allow HS38 or HS48 - * configurations and encode this info in a different BCR. - * The BCR was introduced in 0x54 so can't be read unconditionally. + * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until + * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent + * releases only update it. */ - READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch); if (uarch.prod == 4) { @@ -158,7 +153,7 @@ static void decode_arc_core(struct cpuinfo_arc *cpu) cpu->name = "HS38"; } - for (tbl = &arc_cpu_rel[0]; tbl->id != 0xFF; tbl++) { + for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) { if (uarch.maj == tbl->id) { cpu->release = tbl->str; break; diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi index 05e7b5d4a95b..04f0b1227efe 100644 --- a/arch/arm/boot/dts/am335x-baltos.dtsi +++ b/arch/arm/boot/dts/am335x-baltos.dtsi @@ -369,7 +369,7 @@ &mmc2 { status = "okay"; vmmc-supply = <&wl12xx_vmmc>; - ti,non-removable; + non-removable; bus-width = <4>; cap-power-off-card; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi index 91f93bc89716..dd932220a8bf 100644 --- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi +++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi @@ -22,6 +22,7 @@ pinctrl-0 = <&emmc_pins>; bus-width = <8>; status = "okay"; + non-removable; }; &am33xx_pinmux { diff --git a/arch/arm/boot/dts/am335x-boneblack-wireless.dts b/arch/arm/boot/dts/am335x-boneblack-wireless.dts index 3124d94c0b3c..e07dd7979586 100644 --- a/arch/arm/boot/dts/am335x-boneblack-wireless.dts +++ b/arch/arm/boot/dts/am335x-boneblack-wireless.dts @@ -75,7 +75,6 @@ bus-width = <4>; non-removable; cap-power-off-card; - ti,needs-special-hs-handling; keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wl18xx_pins>; diff --git a/arch/arm/boot/dts/am335x-boneblue.dts b/arch/arm/boot/dts/am335x-boneblue.dts index 5811fb8d4fdf..83f9452c9cd3 100644 --- a/arch/arm/boot/dts/am335x-boneblue.dts +++ b/arch/arm/boot/dts/am335x-boneblue.dts @@ -367,7 +367,6 @@ bus-width = <4>; non-removable; cap-power-off-card; - ti,needs-special-hs-handling; keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wl18xx_pins>; diff --git a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts index 4092cd193b8a..609c8db687ec 100644 --- a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts +++ b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts @@ -75,7 +75,6 @@ bus-width = <4>; non-removable; cap-power-off-card; - ti,needs-special-hs-handling; keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wl18xx_pins>; diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index 68252dab32c3..a4fc6b168a85 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -743,8 +743,7 @@ bus-width = <4>; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wlan_pins>; - ti,non-removable; - ti,needs-special-hs-handling; + non-removable; cap-power-off-card; keep-power-in-suspend; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 32f515a295ee..78b6e1f594c9 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -655,7 +655,7 @@ &mmc2 { status = "okay"; vmmc-supply = <&wl12xx_vmmc>; - ti,non-removable; + non-removable; bus-width = <4>; cap-power-off-card; keep-power-in-suspend; diff --git a/arch/arm/boot/dts/am335x-lxm.dts b/arch/arm/boot/dts/am335x-lxm.dts index fef582852820..dbedf729205c 100644 --- a/arch/arm/boot/dts/am335x-lxm.dts +++ b/arch/arm/boot/dts/am335x-lxm.dts @@ -339,7 +339,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&vmmcsd_fixed>; bus-width = <8>; - ti,non-removable; + non-removable; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi index 6495a125c01f..4e90f9c23d2e 100644 --- a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi +++ b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi @@ -159,7 +159,7 @@ vmmc-supply = <&vmmcsd_fixed>; bus-width = <8>; pinctrl-0 = <&mmc1_pins_default>; - ti,non-removable; + non-removable; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts index 244df9c5a537..f03e72cada41 100644 --- a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts +++ b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts @@ -451,7 +451,7 @@ vmmc-supply = <&vmmcsd_fixed>; bus-width = <8>; pinctrl-0 = <&mmc2_pins_default>; - ti,non-removable; + non-removable; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts index 6d7608d9377b..f9a027b47962 100644 --- a/arch/arm/boot/dts/am335x-pepper.dts +++ b/arch/arm/boot/dts/am335x-pepper.dts @@ -341,7 +341,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&ldo3_reg>; bus-width = <8>; - ti,non-removable; + non-removable; }; &mmc3 { @@ -351,7 +351,7 @@ pinctrl-0 = <&wireless_pins>; vmmmc-supply = <&v3v3c_reg>; bus-width = <4>; - ti,non-removable; + non-removable; dmas = <&edma_xbar 12 0 1 &edma_xbar 13 0 2>; dma-names = "tx", "rx"; diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi index 3d0672b53d77..7e46b4c02709 100644 --- a/arch/arm/boot/dts/am335x-phycore-som.dtsi +++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi @@ -69,7 +69,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&vmmc_reg>; bus-width = <8>; - ti,non-removable; + non-removable; status = "disabled"; }; diff --git a/arch/arm/boot/dts/am335x-pocketbeagle.dts b/arch/arm/boot/dts/am335x-pocketbeagle.dts index 4da719098028..f0b222201b86 100644 --- a/arch/arm/boot/dts/am335x-pocketbeagle.dts +++ b/arch/arm/boot/dts/am335x-pocketbeagle.dts @@ -88,7 +88,6 @@ AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0) AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0) AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0) - AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4) /* (B12) mcasp0_aclkr.mmc0_sdwp */ >; }; diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 7ff11d6bf0f2..a9cbefc80c0c 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -1335,10 +1335,8 @@ ranges = <0x0 0x60000 0x1000>; mmc1: mmc@0 { - compatible = "ti,omap4-hsmmc"; - ti,dual-volt; + compatible = "ti,am335-sdhci"; ti,needs-special-reset; - ti,needs-special-hs-handling; dmas = <&edma_xbar 24 0 0 &edma_xbar 25 0 0>; dma-names = "tx", "rx"; @@ -1816,7 +1814,7 @@ ranges = <0x0 0xd8000 0x1000>; mmc2: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am335-sdhci"; ti,needs-special-reset; dmas = <&edma 2 0 &edma 3 0>; diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 3b177c9c4412..5fdce106edbb 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -322,10 +322,11 @@ ranges = <0x0 0x47810000 0x1000>; mmc3: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am335-sdhci"; ti,needs-special-reset; interrupts = <29>; reg = <0x0 0x1000>; + status = "disabled"; }; }; @@ -335,7 +336,7 @@ <0x47400010 0x4>; reg-names = "rev", "sysc"; ti,sysc-mask = <(SYSC_OMAP4_FREEEMU | - SYSC_OMAP2_SOFTRESET)>; + SYSC_OMAP4_SOFTRESET)>; ti,sysc-midle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; @@ -347,7 +348,7 @@ clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; - ranges = <0x0 0x47400000 0x5000>; + ranges = <0x0 0x47400000 0x8000>; usb0_phy: usb-phy@1300 { compatible = "ti,am335x-usb-phy"; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index b4861f70f178..51ad9e881a62 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -316,10 +316,11 @@ ranges = <0x0 0x47810000 0x1000>; mmc3: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am437-sdhci"; ti,needs-special-reset; interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>; reg = <0x0 0x1000>; + status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts index 063113a5da2d..a6b4fca8626a 100644 --- a/arch/arm/boot/dts/am437x-cm-t43.dts +++ b/arch/arm/boot/dts/am437x-cm-t43.dts @@ -291,7 +291,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&vmmc_3v3>; bus-width = <8>; - ti,non-removable; + non-removable; }; &spi0 { diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts index d692e3b2812a..77378630e5ec 100644 --- a/arch/arm/boot/dts/am437x-gp-evm.dts +++ b/arch/arm/boot/dts/am437x-gp-evm.dts @@ -91,22 +91,6 @@ backlight = <&lcd_bl>; - panel-timing { - clock-frequency = <33000000>; - hactive = <800>; - vactive = <480>; - hfront-porch = <210>; - hback-porch = <16>; - hsync-len = <30>; - vback-porch = <10>; - vfront-porch = <22>; - vsync-len = <13>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; - port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; @@ -869,7 +853,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <&emmc_pins_default>; pinctrl-1 = <&emmc_pins_sleep>; - ti,non-removable; + non-removable; }; &mmc3 { @@ -886,7 +870,7 @@ pinctrl-1 = <&mmc3_pins_sleep>; cap-power-off-card; keep-power-in-suspend; - ti,non-removable; + non-removable; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index 0d0f9fe4a882..7d19395e30c8 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -1083,9 +1083,8 @@ ranges = <0x0 0x60000 0x1000>; mmc1: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am437-sdhci"; reg = <0x0 0x1000>; - ti,dual-volt; ti,needs-special-reset; dmas = <&edma 24 0>, <&edma 25 0>; @@ -1598,7 +1597,7 @@ ranges = <0x0 0xd8000 0x1000>; mmc2: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am437-sdhci"; reg = <0x0 0x1000>; ti,needs-special-reset; dmas = <&edma 2 0>, diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index 4d5a7ca2e25d..08eabf0f3cbd 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -134,22 +134,6 @@ enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>; - panel-timing { - clock-frequency = <9000000>; - hactive = <480>; - vactive = <272>; - hfront-porch = <2>; - hback-porch = <2>; - hsync-len = <41>; - vfront-porch = <2>; - vback-porch = <2>; - vsync-len = <10>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; - port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; @@ -719,7 +703,7 @@ pinctrl-1 = <&mmc3_pins_sleep>; cap-power-off-card; keep-power-in-suspend; - ti,non-removable; + non-removable; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 27259fd6f741..7d4e0dffde7a 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -47,22 +47,6 @@ backlight = <&lcd_bl>; - panel-timing { - clock-frequency = <33000000>; - hactive = <800>; - vactive = <480>; - hfront-porch = <210>; - hback-porch = <16>; - hsync-len = <30>; - vback-porch = <10>; - vfront-porch = <22>; - vsync-len = <13>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; - port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; diff --git a/arch/arm/boot/dts/am5729-beagleboneai.dts b/arch/arm/boot/dts/am5729-beagleboneai.dts index 9877d7709d41..4c51c6b05e64 100644 --- a/arch/arm/boot/dts/am5729-beagleboneai.dts +++ b/arch/arm/boot/dts/am5729-beagleboneai.dts @@ -505,7 +505,7 @@ &cpsw_emac0 { phy-handle = <&phy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; }; &ocp { diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index da6d70f09ef1..3175266ede64 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -200,7 +200,7 @@ status = "disabled"; }; - dma@20000 { + dma: dma@20000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x20000 0x1000>; interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>, @@ -215,6 +215,8 @@ clocks = <&iprocslow>; clock-names = "apb_pclk"; #dma-cells = <1>; + dma-coherent; + status = "disabled"; }; sdio: sdhci@21000 { @@ -257,10 +259,10 @@ status = "disabled"; }; - mailbox: mailbox@25000 { + mailbox: mailbox@25c00 { compatible = "brcm,iproc-fa2-mbox"; - reg = <0x25000 0x445>; - interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>; + reg = <0x25c00 0x400>; + interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>; #mbox-cells = <1>; brcm,rx-status-len = <32>; brcm,use-bcm-hdr; diff --git a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts index 334325390aed..29bbecd36f65 100644 --- a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts +++ b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts @@ -17,6 +17,7 @@ }; memory { + device_type = "memory"; reg = <0x00000000 0x08000000 0x88000000 0x18000000>; }; diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts index 8c388eb8a08f..7be4c4e628e0 100644 --- a/arch/arm/boot/dts/bcm958522er.dts +++ b/arch/arm/boot/dts/bcm958522er.dts @@ -58,6 +58,10 @@ /* USB 3 support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts index c339771bb22e..e58ed7e95346 100644 --- a/arch/arm/boot/dts/bcm958525er.dts +++ b/arch/arm/boot/dts/bcm958525er.dts @@ -58,6 +58,10 @@ /* USB 3 support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts index 1c72ec8288de..716da62f5788 100644 --- a/arch/arm/boot/dts/bcm958525xmc.dts +++ b/arch/arm/boot/dts/bcm958525xmc.dts @@ -58,6 +58,10 @@ /* XHCI support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts index 96a021cebd97..a49c2fd21f4a 100644 --- a/arch/arm/boot/dts/bcm958622hr.dts +++ b/arch/arm/boot/dts/bcm958622hr.dts @@ -58,6 +58,10 @@ /* USB 3 and SLIC support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts index b2c7f21d471e..dd6dff6452b8 100644 --- a/arch/arm/boot/dts/bcm958623hr.dts +++ b/arch/arm/boot/dts/bcm958623hr.dts @@ -58,6 +58,10 @@ /* USB 3 and SLIC support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 536fb24f38bb..a71371b4065e 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -69,6 +69,10 @@ status = "okay"; }; +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts index 3fcca12d83c2..7b84b54436ed 100644 --- a/arch/arm/boot/dts/bcm958625k.dts +++ b/arch/arm/boot/dts/bcm958625k.dts @@ -48,6 +48,10 @@ }; }; +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi index f89a64cbcd53..2cf6a529d4ad 100644 --- a/arch/arm/boot/dts/dra7-evm-common.dtsi +++ b/arch/arm/boot/dts/dra7-evm-common.dtsi @@ -245,26 +245,6 @@ rx-num-evt = <32>; }; -&mailbox5 { - status = "okay"; - mbox_ipu1_ipc3x: mbox_ipu1_ipc3x { - status = "okay"; - }; - mbox_dsp1_ipc3x: mbox_dsp1_ipc3x { - status = "okay"; - }; -}; - -&mailbox6 { - status = "okay"; - mbox_ipu2_ipc3x: mbox_ipu2_ipc3x { - status = "okay"; - }; - mbox_dsp2_ipc3x: mbox_dsp2_ipc3x { - status = "okay"; - }; -}; - &pcie1_rc { status = "okay"; }; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index 62ca89551219..0c6f26605506 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -1207,9 +1207,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; /* Domains (P, C): l4per_pwrdm, l4per_clkdm */ - clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>, - <&timer_sys_clk_div>; - clock-names = "fck", "timer_sys_ck"; + clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>; + clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x36000 0x1000>; @@ -3352,8 +3351,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; /* Domains (P, C): ipu_pwrdm, ipu_clkdm */ - clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>, <&timer_sys_clk_div>; - clock-names = "fck", "timer_sys_ck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>; + clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x20000 0x1000>; @@ -3361,8 +3360,8 @@ timer5: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -3379,9 +3378,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; /* Domains (P, C): ipu_pwrdm, ipu_clkdm */ - clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>, - <&timer_sys_clk_div>; - clock-names = "fck", "timer_sys_ck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>; + clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x22000 0x1000>; @@ -3389,8 +3387,8 @@ timer6: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -3498,8 +3496,8 @@ timer14: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>; ti,timer-pwm; }; @@ -3526,8 +3524,8 @@ timer15: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>; ti,timer-pwm; }; @@ -3554,8 +3552,8 @@ timer16: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>; ti,timer-pwm; }; diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi index f05e91841202..53a25fba34f6 100644 --- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi +++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi @@ -232,13 +232,6 @@ status = "okay"; }; -&wdog1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_wdog>; - fsl,ext-reset-output; - status = "okay"; -}; - &iomuxc { pinctrl-0 = <&pinctrl_reset_out &pinctrl_gpio>; @@ -409,10 +402,4 @@ MX6UL_PAD_NAND_DATA03__USDHC2_DATA3 0x170f9 >; }; - - pinctrl_wdog: wdoggrp { - fsl,pins = < - MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x30b0 - >; - }; }; diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi index a17af4d9bfdf..61ba21a605a8 100644 --- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi +++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi @@ -57,6 +57,13 @@ status = "okay"; }; +&wdog1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; + status = "okay"; +}; + &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reset_out>; @@ -106,4 +113,10 @@ MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09 0x1b0b0 >; }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x18b0 + >; + }; }; diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index e39eee628afd..08a7d3ce383f 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -13,8 +13,10 @@ #interrupt-cells = <2>; #address-cells = <1>; #size-cells = <0>; - spi-max-frequency = <3000000>; + spi-max-frequency = <9600000>; spi-cs-high; + spi-cpol; + spi-cpha; cpcap_adc: adc { compatible = "motorola,mapphone-cpcap-adc"; diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index 8047e8cdb3af..4548d87534e3 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -139,7 +139,7 @@ ethernet@gpmc { reg = <5 0 0xff>; interrupt-parent = <&gpio2>; - interrupts = <12 IRQ_TYPE_EDGE_FALLING>; /* gpio_44 */ + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; /* gpio_44 */ phy-mode = "mii"; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 6c2b07f0704d..4400f5f8e099 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -662,6 +662,6 @@ ti,no-idle; timer@0 { assigned-clocks = <&l4_wkup_clkctrl OMAP4_TIMER1_CLKCTRL 24>; - assigned-clock-parents = <&sys_clkin_ck>; + assigned-clock-parents = <&sys_32k_ck>; }; }; diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi index e6308fb76183..a88ee5294d35 100644 --- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi @@ -100,79 +100,6 @@ }; }; - mcc { - compatible = "arm,vexpress,config-bus"; - arm,vexpress,config-bridge = <&v2m_sysreg>; - - oscclk0 { - /* MCC static memory clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 0>; - freq-range = <25000000 60000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk0"; - }; - - v2m_oscclk1: oscclk1 { - /* CLCD clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 1>; - freq-range = <23750000 65000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk1"; - }; - - v2m_oscclk2: oscclk2 { - /* IO FPGA peripheral clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 2>; - freq-range = <24000000 24000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk2"; - }; - - volt-vio { - /* Logic level voltage */ - compatible = "arm,vexpress-volt"; - arm,vexpress-sysreg,func = <2 0>; - regulator-name = "VIO"; - regulator-always-on; - label = "VIO"; - }; - - temp-mcc { - /* MCC internal operating temperature */ - compatible = "arm,vexpress-temp"; - arm,vexpress-sysreg,func = <4 0>; - label = "MCC"; - }; - - reset { - compatible = "arm,vexpress-reset"; - arm,vexpress-sysreg,func = <5 0>; - }; - - muxfpga { - compatible = "arm,vexpress-muxfpga"; - arm,vexpress-sysreg,func = <7 0>; - }; - - shutdown { - compatible = "arm,vexpress-shutdown"; - arm,vexpress-sysreg,func = <8 0>; - }; - - reboot { - compatible = "arm,vexpress-reboot"; - arm,vexpress-sysreg,func = <9 0>; - }; - - dvimode { - compatible = "arm,vexpress-dvimode"; - arm,vexpress-sysreg,func = <11 0>; - }; - }; - bus@8000000 { motherboard-bus { model = "V2M-P1"; @@ -435,6 +362,79 @@ }; }; }; + + mcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + oscclk0 { + /* MCC static memory clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <25000000 60000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk0"; + }; + + v2m_oscclk1: oscclk1 { + /* CLCD clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <23750000 65000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk1"; + }; + + v2m_oscclk2: oscclk2 { + /* IO FPGA peripheral clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <24000000 24000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk2"; + }; + + volt-vio { + /* Logic level voltage */ + compatible = "arm,vexpress-volt"; + arm,vexpress-sysreg,func = <2 0>; + regulator-name = "VIO"; + regulator-always-on; + label = "VIO"; + }; + + temp-mcc { + /* MCC internal operating temperature */ + compatible = "arm,vexpress-temp"; + arm,vexpress-sysreg,func = <4 0>; + label = "MCC"; + }; + + reset { + compatible = "arm,vexpress-reset"; + arm,vexpress-sysreg,func = <5 0>; + }; + + muxfpga { + compatible = "arm,vexpress-muxfpga"; + arm,vexpress-sysreg,func = <7 0>; + }; + + shutdown { + compatible = "arm,vexpress-shutdown"; + arm,vexpress-sysreg,func = <8 0>; + }; + + reboot { + compatible = "arm,vexpress-reboot"; + arm,vexpress-sysreg,func = <9 0>; + }; + + dvimode { + compatible = "arm,vexpress-dvimode"; + arm,vexpress-sysreg,func = <11 0>; + }; + }; }; }; }; diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 84dc0ba822f5..5dcf3c6011b7 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -87,4 +87,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, return dram_base + SZ_512M; } +struct efi_arm_entry_state { + u32 cpsr_before_ebs; + u32 sctlr_before_ebs; + u32 cpsr_after_ebs; + u32 sctlr_after_ebs; +}; + #endif /* _ASM_ARM_EFI_H */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index c036a4a2f8e2..a1570c8bab25 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -31,15 +31,6 @@ #if defined(__APCS_26__) #error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32 #endif -/* - * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854 - * miscompiles find_get_entry(), and can result in EXT3 and EXT4 - * filesystem corruption (possibly other FS too). - */ -#if defined(GCC_VERSION) && GCC_VERSION >= 40800 && GCC_VERSION < 40803 -#error Your compiler is too buggy; it is known to miscompile kernels -#error and result in filesystem corruption and oopses. -#endif int main(void) { diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index 6aa938b949db..1df0ee01ee02 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -53,6 +53,7 @@ config ARCH_BCM_NSP select ARM_ERRATA_754322 select ARM_ERRATA_775420 select ARM_ERRATA_764369 if SMP + select ARM_TIMER_SP804 select THERMAL select THERMAL_OF help diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c index f057df813f83..e9962b48e30c 100644 --- a/arch/arm/mach-imx/pm-imx5.c +++ b/arch/arm/mach-imx/pm-imx5.c @@ -295,14 +295,14 @@ static int __init imx_suspend_alloc_ocram( if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, size); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } phys = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -312,6 +312,8 @@ static int __init imx_suspend_alloc_ocram( if (virt_out) *virt_out = virt; +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index dd34dff13762..40c74b4c4d73 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -493,14 +493,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -523,7 +523,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat); if (ret) { pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret); - goto put_node; + goto put_device; } ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat); @@ -570,7 +570,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) &imx6_suspend, MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info)); - goto put_node; + goto put_device; pl310_cache_map_failed: iounmap(pm_info->gpc_base.vbase); @@ -580,6 +580,8 @@ iomuxc_map_failed: iounmap(pm_info->src_base.vbase); src_map_failed: iounmap(pm_info->mmdc_base.vbase); +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 82706af307de..c630457bb228 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -3489,7 +3489,7 @@ static const struct omap_hwmod_reset dra7_reset_quirks[] = { }; static const struct omap_hwmod_reset omap_reset_quirks[] = { - { .match = "dss", .len = 3, .reset = omap_dss_reset, }, + { .match = "dss_core", .len = 8, .reset = omap_dss_reset, }, { .match = "hdq1w", .len = 5, .reset = omap_hdq1w_reset, }, { .match = "i2c", .len = 3, .reset = omap_i2c_reset, }, { .match = "wd_timer", .len = 8, .reset = omap2_wd_timer_reset, }, diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c index dcb98937fcf5..ffecbf29646f 100644 --- a/arch/arm/mach-sti/board-dt.c +++ b/arch/arm/mach-sti/board-dt.c @@ -20,14 +20,6 @@ static const char *const stih41x_dt_match[] __initconst = { NULL }; -static void sti_l2_write_sec(unsigned long val, unsigned reg) -{ - /* - * We can't write to secure registers as we are in non-secure - * mode, until we have some SMI service available. - */ -} - DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree") .dt_compat = stih41x_dt_match, .l2c_aux_val = L2C_AUX_CTRL_SHARED_OVERRIDE | @@ -36,5 +28,4 @@ DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree") L2C_AUX_CTRL_WAY_SIZE(4), .l2c_aux_mask = 0xc0000fff, .smp = smp_ops(sti_smp_ops), - .l2c_write_sec = sti_l2_write_sec, MACHINE_END diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index fd4e1ce1daf9..e93145d72c26 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -241,7 +241,6 @@ static int __init fdt_find_hyper_node(unsigned long node, const char *uname, * see Documentation/devicetree/bindings/arm/xen.txt for the * documentation of the Xen Device Tree format. */ -#define GRANT_TABLE_PHYSADDR 0 void __init xen_early_init(void) { of_scan_flat_dt(fdt_find_hyper_node, NULL); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a4a094bedcb2..66dc41fd49f2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1518,9 +1518,9 @@ config ARM64_PTR_AUTH default y depends on !KVM || ARM64_VHE depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC - # GCC 9.1 and later inserts a .note.gnu.property section note for PAC + # Modern compilers insert a .note.gnu.property section note for PAC # which is only understood by binutils starting with version 2.33.1. - depends on !CC_IS_GCC || GCC_VERSION < 90100 || LD_VERSION >= 233010000 + depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100) depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index fb0137a8611c..94911b1707ef 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -136,7 +136,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -144,7 +144,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts index e5ec8322796d..0f1d7f8aeac4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts @@ -208,7 +208,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -216,7 +216,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index d07e0e6a00cc..a1e5483dbbbe 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -113,7 +113,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -121,7 +121,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 5e5dc05d63a0..12f0eb56a1cc 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -73,11 +73,11 @@ static inline void apply_alternatives_module(void *start, size_t length) { } ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature) \ ".popsection\n" \ - ".pushsection .altinstr_replacement, \"a\"\n" \ + ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".popsection\n\t" \ + ".previous\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n" \ ".endif\n" @@ -117,9 +117,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 663: \insn2 -664: .popsection +664: .previous .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .endif @@ -160,7 +160,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm @@ -179,9 +179,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_else 662: .if .Lasm_alt_mode==0 - .pushsection .altinstr_replacement, "ax" + .subsection 1 .else - .popsection + .previous .endif 663: .endm @@ -192,7 +192,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_endif 664: .if .Lasm_alt_mode==0 - .popsection + .previous .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index a358e97572c1..6647ae4f0231 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void) return read_sysreg_s(SYS_ICC_PMR_EL1); } -static inline void gic_write_pmr(u32 val) +static __always_inline void gic_write_pmr(u32 val) { write_sysreg_s(val, SYS_ICC_PMR_EL1); } diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index 7ae54d7d333a..9f0ec21d6327 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -58,6 +58,7 @@ struct arch_timer_erratum_workaround { u64 (*read_cntvct_el0)(void); int (*set_next_event_phys)(unsigned long, struct clock_event_device *); int (*set_next_event_virt)(unsigned long, struct clock_event_device *); + bool disable_compat_vdso; }; DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *, diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 5d1f4ae42799..f7c3d1ff091d 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -675,7 +675,7 @@ static inline bool system_supports_generic_auth(void) cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH); } -static inline bool system_uses_irq_prio_masking(void) +static __always_inline bool system_uses_irq_prio_masking(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index a87a93f67671..7219cddeba66 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,7 @@ #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 +#define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 #define NVIDIA_CPU_PART_DENVER 0x003 @@ -114,6 +115,7 @@ #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) +#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 81fefd2a1d02..ba89a9af820a 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -12,7 +12,6 @@ * instead. */ #define BTI_C hint 34 ; -#define BTI_J hint 36 ; /* * When using in-kernel BTI we need to ensure that PCS-conformant assembly @@ -43,11 +42,6 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \ BTI_C -#define SYM_INNER_LABEL(name, linkage) \ - .type name SYM_T_NONE ASM_NL \ - SYM_ENTRY(name, linkage, SYM_A_NONE) \ - BTI_J - #endif /* diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 68140fdd89d6..8444df000181 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -19,6 +19,9 @@ typedef struct { atomic64_t id; +#ifdef CONFIG_COMPAT + void *sigpage; +#endif void *vdso; unsigned long flags; } mm_context_t; diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 2e7e0f452301..4d867c6446c4 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -67,7 +67,7 @@ extern bool arm64_use_ng_mappings; #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) -#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) +#define PAGE_HYP_DEVICE __pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN) #define PAGE_S2_MEMATTR(attr) \ ({ \ diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h index df6ea65c1dec..b054d9febfb5 100644 --- a/arch/arm64/include/asm/vdso/clocksource.h +++ b/arch/arm64/include/asm/vdso/clocksource.h @@ -2,7 +2,10 @@ #ifndef __ASM_VDSOCLOCKSOURCE_H #define __ASM_VDSOCLOCKSOURCE_H -#define VDSO_ARCH_CLOCKMODES \ - VDSO_CLOCKMODE_ARCHTIMER +#define VDSO_ARCH_CLOCKMODES \ + /* vdso clocksource for both 32 and 64bit tasks */ \ + VDSO_CLOCKMODE_ARCHTIMER, \ + /* vdso clocksource for 64bit tasks only */ \ + VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT #endif diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index b6907ae78e53..9a625e8947ff 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -111,7 +111,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) * update. Return something. Core will do another round and then * see the mode change and fallback to the syscall. */ - if (clock_mode == VDSO_CLOCKMODE_NONE) + if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER) return 0; /* @@ -152,6 +152,12 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) return ret; } +static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +{ + return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER; +} +#define vdso_clocksource_ok vdso_clocksource_ok + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 151f28521f1e..a561cbb91d4d 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -29,9 +29,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o -ifneq ($(CONFIG_COMPAT_VDSO), y) obj-$(CONFIG_COMPAT) += sigreturn32.o -endif obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index d1757ef1b1e7..73039949b5ce 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature) */ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { - unsigned long replptr; - - if (kernel_text_address(pc)) - return true; - - replptr = (unsigned long)ALT_REPL_PTR(alt); - if (pc >= replptr && pc <= (replptr + alt->alt_len)) - return false; - - /* - * Branching into *another* alternate sequence is doomed, and - * we're not even trying to fix it up. - */ - BUG(); + unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); + return !(pc >= replptr && pc <= (replptr + alt->alt_len)); } #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ad06d6802d2e..79728bfb5351 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -460,6 +460,8 @@ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), {}, }; @@ -470,12 +472,7 @@ static bool has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry, int scope) { - u32 midr = read_cpuid_id(); - /* Cortex-A76 r0p0 - r3p1 */ - struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1); - - WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); - return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode(); + return is_affected_midr_range_list(entry, scope) && is_kernel_in_hyp_mode(); } #endif @@ -726,6 +723,8 @@ static const struct midr_range erratum_1418040_list[] = { MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1), /* Neoverse-N1 r0p0 to r3p1 */ MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1), + /* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */ + MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf), {}, }; #endif @@ -770,11 +769,23 @@ static const struct midr_range erratum_speculative_at_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1530923 /* Cortex A55 r0p0 to r2p0 */ MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0), + /* Kryo4xx Silver (rdpe => r1p0) */ + MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif {}, }; #endif +#ifdef CONFIG_ARM64_ERRATUM_1463225 +static const struct midr_range erratum_1463225[] = { + /* Cortex-A76 r0p0 - r3p1 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1), + /* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */ + MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf), + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -914,6 +925,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_WORKAROUND_1463225, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = has_cortex_a76_erratum_1463225, + .midr_range_list = erratum_1463225, }, #endif #ifdef CONFIG_CAVIUM_TX2_ERRATUM_219 diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4ae41670c2e6..9fae0efc80c1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1290,6 +1290,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; char const *str = "kpti command line option"; @@ -1406,6 +1408,8 @@ static bool cpu_has_broken_dbm(void) static const struct midr_range cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_1024718 MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0), // A55 r0p0 -r1p0 + /* Kryo4xx Silver (rdpe => r1p0) */ + MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif {}, }; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 3dbdf9752b11..d3be9dbf5490 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -57,7 +57,7 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) /* * The CPU masked interrupts, and we are leaving them masked during * do_debug_exception(). Update PMR as if we had called - * local_mask_daif(). + * local_daif_mask(). */ if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 5304d193c79d..35de8ba60e3d 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -126,8 +126,10 @@ alternative_else_nop_endif add \dst, \dst, #(\sym - .entry.tramp.text) .endm - // This macro corrupts x0-x3. It is the caller's duty - // to save/restore them if required. + /* + * This macro corrupts x0-x3. It is the caller's duty to save/restore + * them if required. + */ .macro apply_ssbd, state, tmp1, tmp2 #ifdef CONFIG_ARM64_SSBD alternative_cb arm64_enable_wa2_handling @@ -167,13 +169,28 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 + .if \regsize == 32 + /* + * If we're returning from a 32-bit task on a system affected by + * 1418040 then re-enable userspace access to the virtual counter. + */ +#ifdef CONFIG_ARM64_ERRATUM_1418040 +alternative_if ARM64_WORKAROUND_1418040 + mrs x0, cntkctl_el1 + orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN + msr cntkctl_el1, x0 +alternative_else_nop_endif +#endif + .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 msr sp_el0, tsk - // Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions - // when scheduling. + /* + * Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions + * when scheduling. + */ ldr x19, [tsk, #TSK_TI_FLAGS] disable_step_tsk x19, x20 @@ -320,6 +337,14 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f +#ifdef CONFIG_ARM64_ERRATUM_1418040 +alternative_if ARM64_WORKAROUND_1418040 + mrs x0, cntkctl_el1 + bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN + msr cntkctl_el1, x0 +alternative_else_nop_endif +#endif + #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR @@ -331,21 +356,6 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if_not ARM64_WORKAROUND_1418040 - b 4f -alternative_else_nop_endif - /* - * if (x22.mode32 == cntkctl_el1.el0vcten) - * cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten - */ - mrs x1, cntkctl_el1 - eon x0, x1, x22, lsr #3 - tbz x0, #1, 4f - eor x1, x1, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x1 -4: -#endif scs_save tsk, x0 /* No kernel C function calls after this as user keys are set. */ @@ -377,11 +387,11 @@ alternative_else_nop_endif .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - bne 5f + bne 4f msr far_el1, x30 tramp_alias x30, tramp_exit_native br x30 -5: +4: tramp_alias x30, tramp_exit_compat br x30 #endif diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 43119922341f..1a157ca33262 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) if (!kgdb_single_step) return DBG_HOOK_ERROR; - kgdb_handle_exception(1, SIGTRAP, 0, regs); + kgdb_handle_exception(0, SIGTRAP, 0, regs); return DBG_HOOK_HANDLED; } NOKPROBE_SYMBOL(kgdb_step_brk_fn); diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 0bbac612146e..666b225aeb3a 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; /* - * Compat (i.e. 32 bit) mode: - * - PC has been set in the pt_regs struct in kernel_entry, - * - Handle SP and LR here. + * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but + * we're stuck with it for ABI compatability reasons. + * + * For a 32-bit consumer inspecting a 32-bit task, then it will look at + * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). + * These correspond directly to a prefix of the registers saved in our + * 'struct pt_regs', with the exception of the PC, so we copy that down + * (x15 corresponds to SP_hyp in the architecture). + * + * So far, so good. + * + * The oddity arises when a 64-bit consumer looks at a 32-bit task and + * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return + * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and + * PC registers would normally live. The initial idea was to allow a + * 64-bit unwinder to unwind a 32-bit task and, although it's not clear + * how well that works in practice, somebody might be relying on it. + * + * At the time we make a sample, we don't know whether the consumer is + * 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode(regs)) { if ((u32)idx == PERF_REG_ARM64_SP) return regs->compat_sp; if ((u32)idx == PERF_REG_ARM64_LR) return regs->compat_lr; + if (idx == 15) + return regs->pc; } if ((u32)idx == PERF_REG_ARM64_SP) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d1c95dcf1d78..5290f17a4d80 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -120,15 +120,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) void *alloc_insn_page(void) { - void *page; - - page = vmalloc_exec(PAGE_SIZE); - if (page) { - set_memory_ro((unsigned long)page, 1); - set_vm_flush_reset_perms(page); - } - - return page; + return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } /* arm kprobe: install breakpoint in text */ diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 82feca6f7052..2f507f565c48 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -342,38 +342,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, retcode = ptr_to_compat(ka->sa.sa_restorer); } else { /* Set up sigreturn pointer */ -#ifdef CONFIG_COMPAT_VDSO - void *vdso_base = current->mm->context.vdso; - void *vdso_trampoline; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_arm); - } - } else { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_arm); - } - } - - retcode = ptr_to_compat(vdso_trampoline) + thumb; -#else unsigned int idx = thumb << 1; if (ka->sa.sa_flags & SA_SIGINFO) idx += 3; - retcode = (unsigned long)current->mm->context.vdso + + retcode = (unsigned long)current->mm->context.sigpage + (idx << 2) + thumb; -#endif } regs->regs[0] = usig; diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 4e016574bd91..e546df0efefb 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -191,15 +191,12 @@ enum aarch32_map { #ifdef CONFIG_COMPAT_VDSO AA32_MAP_VVAR, AA32_MAP_VDSO, -#else - AA32_MAP_SIGPAGE #endif + AA32_MAP_SIGPAGE }; static struct page *aarch32_vectors_page __ro_after_init; -#ifndef CONFIG_COMPAT_VDSO static struct page *aarch32_sig_page __ro_after_init; -#endif static struct vm_special_mapping aarch32_vdso_maps[] = { [AA32_MAP_VECTORS] = { @@ -214,12 +211,11 @@ static struct vm_special_mapping aarch32_vdso_maps[] = { .name = "[vdso]", .mremap = aarch32_vdso_mremap, }, -#else +#endif /* CONFIG_COMPAT_VDSO */ [AA32_MAP_SIGPAGE] = { .name = "[sigpage]", /* ABI */ .pages = &aarch32_sig_page, }, -#endif /* CONFIG_COMPAT_VDSO */ }; static int aarch32_alloc_kuser_vdso_page(void) @@ -242,27 +238,11 @@ static int aarch32_alloc_kuser_vdso_page(void) return 0; } -#ifdef CONFIG_COMPAT_VDSO -static int __aarch32_alloc_vdso_pages(void) -{ - int ret; - - vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; - vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - - ret = __vdso_init(VDSO_ABI_AA32); - if (ret) - return ret; - - return aarch32_alloc_kuser_vdso_page(); -} -#else -static int __aarch32_alloc_vdso_pages(void) +static int aarch32_alloc_sigpage(void) { extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; unsigned long sigpage; - int ret; sigpage = get_zeroed_page(GFP_ATOMIC); if (!sigpage) @@ -271,18 +251,34 @@ static int __aarch32_alloc_vdso_pages(void) memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz); aarch32_sig_page = virt_to_page(sigpage); flush_dcache_page(aarch32_sig_page); + return 0; +} - ret = aarch32_alloc_kuser_vdso_page(); - if (ret) - free_page(sigpage); +#ifdef CONFIG_COMPAT_VDSO +static int __aarch32_alloc_vdso_pages(void) +{ + vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; + vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - return ret; + return __vdso_init(VDSO_ABI_AA32); } #endif /* CONFIG_COMPAT_VDSO */ static int __init aarch32_alloc_vdso_pages(void) { - return __aarch32_alloc_vdso_pages(); + int ret; + +#ifdef CONFIG_COMPAT_VDSO + ret = __aarch32_alloc_vdso_pages(); + if (ret) + return ret; +#endif + + ret = aarch32_alloc_sigpage(); + if (ret) + return ret; + + return aarch32_alloc_kuser_vdso_page(); } arch_initcall(aarch32_alloc_vdso_pages); @@ -305,7 +301,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm) return PTR_ERR_OR_ZERO(ret); } -#ifndef CONFIG_COMPAT_VDSO static int aarch32_sigreturn_setup(struct mm_struct *mm) { unsigned long addr; @@ -328,12 +323,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm) if (IS_ERR(ret)) goto out; - mm->context.vdso = (void *)addr; + mm->context.sigpage = (void *)addr; out: return PTR_ERR_OR_ZERO(ret); } -#endif /* !CONFIG_COMPAT_VDSO */ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { @@ -352,10 +346,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) mm, bprm, uses_interp); -#else - ret = aarch32_sigreturn_setup(mm); + if (ret) + goto out; #endif /* CONFIG_COMPAT_VDSO */ + ret = aarch32_sigreturn_setup(mm); out: mmap_write_unlock(mm); return ret; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 556d424c6f52..45d5cfe46429 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,13 +23,14 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # potential future proofing if we end up with internal calls to the exported # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ - -Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n \ + $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S index 620a3ef837b7..0e18729abc3b 100644 --- a/arch/arm64/kernel/vdso/sigreturn.S +++ b/arch/arm64/kernel/vdso/sigreturn.S @@ -18,29 +18,40 @@ .text +/* + * NOTE!!! You may notice that all of the .cfi directives in this file have + * been commented out. This is because they have been shown to trigger segfaults + * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread + * cleanup handlers during the thread cancellation dance. By omitting the + * directives, we trigger an arm64-specific fallback path in the unwinder which + * recognises the signal frame and restores many of the registers directly from + * the sigcontext. Re-enabling the cfi directives here therefore needs to be + * much more comprehensive to reduce the risk of further regressions. + */ + /* Ensure that the mysterious NOP can be associated with a function. */ - .cfi_startproc +// .cfi_startproc /* - * .cfi_signal_frame causes the corresponding Frame Description Entry in the - * .eh_frame section to be annotated as a signal frame. This allows DWARF - * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits - * unwinding out of the signal trampoline without the need for the mysterious - * NOP. + * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in + * the .eh_frame section to be annotated as a signal frame. This allows DWARF + * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify + * the next frame using the unmodified return address instead of subtracting 1, + * which may yield the wrong FDE. */ - .cfi_signal_frame +// .cfi_signal_frame /* * Tell the unwinder where to locate the frame record linking back to the - * interrupted context. We don't provide unwind info for registers other - * than the frame pointer and the link register here; in practice, this - * is sufficient for unwinding in C/C++ based runtimes and the values in - * the sigcontext may have been modified by this point anyway. Debuggers + * interrupted context. We don't provide unwind info for registers other than + * the frame pointer and the link register here; in practice, this is likely to + * be insufficient for unwinding in C/C++ based runtimes, especially without a + * means to restore the stack pointer. Thankfully, unwinders and debuggers * already have baked-in strategies for attempting to unwind out of signals. */ - .cfi_def_cfa x29, 0 - .cfi_offset x29, 0 * 8 - .cfi_offset x30, 1 * 8 +// .cfi_def_cfa x29, 0 +// .cfi_offset x29, 0 * 8 +// .cfi_offset x30, 1 * 8 /* * This mysterious NOP is required for some unwinders (e.g. libc++) that @@ -51,16 +62,19 @@ nop // Mysterious NOP /* - * GDB relies on being able to identify the sigreturn instruction sequence to - * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START() - * here, as it will emit a BTI C instruction and break the unwinder. Thankfully, - * this function is only ever called from a RET and so omitting the landing pad - * is perfectly fine. + * GDB, libgcc and libunwind rely on being able to identify the sigreturn + * instruction sequence to unwind from signal handlers. We cannot, therefore, + * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the + * unwinder. Thankfully, this function is only ever called from a RET and so + * omitting the landing pad is perfectly fine. */ SYM_CODE_START(__kernel_rt_sigreturn) +// PLEASE DO NOT MODIFY mov x8, #__NR_rt_sigreturn +// PLEASE DO NOT MODIFY svc #0 - .cfi_endproc +// PLEASE DO NOT MODIFY +// .cfi_endproc SYM_CODE_END(__kernel_rt_sigreturn) emit_aarch64_feature_1_and diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 7ea1e827e505..d88148bef6b0 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -140,7 +140,6 @@ hostprogs := $(munge) c-obj-vdso := note.o c-obj-vdso-gettimeofday := vgettimeofday.o -asm-obj-vdso := sigreturn.o ifneq ($(c-gettimeofday-y),) VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y) diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S deleted file mode 100644 index b0091064c3d6..000000000000 --- a/arch/arm64/kernel/vdso32/sigreturn.S +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This file provides both A32 and T32 versions, in accordance with the - * arm sigreturn code. - * - * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to - * understand some of the craziness in here. - * - * Copyright (C) 2018 ARM Limited - */ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> - - .text - - .arm - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_arm) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_arm) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_arm) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_arm) - - .thumb - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_thumb) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_thumb) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_thumb) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_thumb) diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S index a3944927eaeb..337d03522048 100644 --- a/arch/arm64/kernel/vdso32/vdso.lds.S +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -64,19 +64,7 @@ VERSION __vdso_clock_gettime; __vdso_gettimeofday; __vdso_clock_getres; - __kernel_sigreturn_arm; - __kernel_sigreturn_thumb; - __kernel_rt_sigreturn_arm; - __kernel_rt_sigreturn_thumb; __vdso_clock_gettime64; local: *; }; } - -/* - * Make the sigreturn code visible to the kernel. - */ -VDSO_compat_sigreturn_arm = __kernel_sigreturn_arm; -VDSO_compat_sigreturn_thumb = __kernel_sigreturn_thumb; -VDSO_compat_rt_sigreturn_arm = __kernel_rt_sigreturn_arm; -VDSO_compat_rt_sigreturn_thumb = __kernel_rt_sigreturn_thumb; diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 6827da7f3aa5..5423ffe0a987 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -165,9 +165,6 @@ SECTIONS *(.altinstructions) __alt_instructions_end = .; } - .altinstr_replacement : { - *(.altinstr_replacement) - } . = ALIGN(SEGMENT_ALIGN); __inittext_end = .; diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 6e6ed5581eed..e76c0e89d48e 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -136,11 +136,15 @@ SYM_CODE_START(__kvm_handle_stub_hvc) 1: cmp x0, #HVC_RESET_VECTORS b.ne 1f -reset: + /* - * Reset kvm back to the hyp stub. Do not clobber x0-x4 in - * case we coming via HVC_SOFT_RESTART. + * Set the HVC_RESET_VECTORS return code before entering the common + * path so that we do not clobber x0-x2 in case we are coming via + * HVC_SOFT_RESTART. */ + mov x0, xzr +reset: + /* Reset kvm back to the hyp stub. */ mrs x5, sctlr_el2 mov_q x6, SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc @@ -151,7 +155,6 @@ reset: /* Install stub vectors */ adr_l x5, __hyp_stub_vectors msr vbar_el2, x5 - mov x0, xzr eret 1: /* Bad stub call */ diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index b5ae3a5d509e..3c224162b3dd 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -159,7 +159,10 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events) } /* - * On VHE ensure that only guest events have EL0 counting enabled + * On VHE ensure that only guest events have EL0 counting enabled. + * This is called from both vcpu_{load,put} and the sysreg handling. + * Since the latter is preemptible, special care must be taken to + * disable preemption. */ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { @@ -169,12 +172,14 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) if (!has_vhe()) return; + preempt_disable(); host = this_cpu_ptr(&kvm_host_data); events_guest = host->pmu_events.events_guest; events_host = host->pmu_events.events_host; kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); + preempt_enable(); } /* diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index 1e0f4c284888..f7b52ce1557e 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -3,6 +3,7 @@ #include <linux/arm-smccc.h> #include <linux/kvm_host.h> +#include <linux/sched/stat.h> #include <asm/kvm_mmu.h> #include <asm/pvclock-abi.h> @@ -73,6 +74,11 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) return base; } +static bool kvm_arm_pvtime_supported(void) +{ + return !!sched_info_on(); +} + int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -82,7 +88,8 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, int ret = 0; int idx; - if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + if (!kvm_arm_pvtime_supported() || + attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; if (get_user(ipa, user)) @@ -110,7 +117,8 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, u64 __user *user = (u64 __user *)attr->addr; u64 ipa; - if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + if (!kvm_arm_pvtime_supported() || + attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; ipa = vcpu->arch.steal.base; @@ -125,7 +133,8 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, { switch (attr->attr) { case KVM_ARM_VCPU_PVTIME_IPA: - return 0; + if (kvm_arm_pvtime_supported()) + return 0; } return -ENXIO; } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index d3b209023727..6ed36be51b4b 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { - int ret = -EINVAL; + int ret; bool loaded; u32 pstate; @@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) { - if (kvm_vcpu_enable_ptrauth(vcpu)) + if (kvm_vcpu_enable_ptrauth(vcpu)) { + ret = -EINVAL; goto out; + } } switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) { + ret = -EINVAL; goto out; + } pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 27ac833e5ec7..b5fa73c9fd35 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -90,7 +90,15 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) disable_irq_nosync(irq); + /* + * The v4.1 doorbell can fire concurrently with the vPE being + * made non-resident. Ensure we only update pending_last + * *after* the non-residency sequence has completed. + */ + raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; + raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index e779b19e0193..f66f4b1d062e 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -138,7 +138,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); - memblock_add(memory_start, memory_end - memory_start); + memblock_add(_rambase, memory_end - _rambase); + memblock_reserve(_rambase, memory_start - _rambase); /* Keep a copy of command line */ *cmdline_p = &command_line[0]; diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 29f47923aa46..7d04210d34f0 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -174,7 +174,7 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/mips/boot/dts/ingenic/gcw0.dts b/arch/mips/boot/dts/ingenic/gcw0.dts index 8d22828787d8..bc72304a2440 100644 --- a/arch/mips/boot/dts/ingenic/gcw0.dts +++ b/arch/mips/boot/dts/ingenic/gcw0.dts @@ -92,7 +92,7 @@ "MIC1N", "Built-in Mic"; simple-audio-card,pin-switches = "Speaker", "Headphones"; - simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_HIGH>; + simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_LOW>; simple-audio-card,aux-devs = <&speaker_amp>, <&headphones_amp>; simple-audio-card,bitclock-master = <&dai_codec>; diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h index c628747d4ecd..7dd4a80e05d6 100644 --- a/arch/mips/include/asm/unroll.h +++ b/arch/mips/include/asm/unroll.h @@ -19,15 +19,13 @@ \ /* \ * We can't unroll if the number of iterations isn't \ - * compile-time constant. Unfortunately GCC versions \ - * up until 4.6 tend to miss obvious constants & cause \ + * compile-time constant. Unfortunately clang versions \ + * up until 8.0 tend to miss obvious constants & cause \ * this check to fail, even though they go on to \ * generate reasonable code for the switch statement, \ * so we skip the sanity check for those compilers. \ */ \ - BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 || \ - CONFIG_CLANG_VERSION >= 80000) && \ - !__builtin_constant_p(times)); \ + BUILD_BUG_ON(!__builtin_constant_p(times)); \ \ switch (times) { \ case 32: fn(__VA_ARGS__); /* fall through */ \ diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 7c32c956156a..f655af68176c 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -723,12 +723,14 @@ static int simulate_loongson3_cpucfg(struct pt_regs *regs, perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); /* Do not emulate on unsupported core models. */ - if (!loongson3_cpucfg_emulation_enabled(¤t_cpu_data)) + preempt_disable(); + if (!loongson3_cpucfg_emulation_enabled(¤t_cpu_data)) { + preempt_enable(); return -1; - + } regs->regs[rd] = loongson3_cpucfg_read_synthesized( ¤t_cpu_data, sel); - + preempt_enable(); return 0; } @@ -2169,6 +2171,7 @@ static void configure_status(void) change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX, status_set); + back_to_back_c0_hazard(); } unsigned int hwrena; diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 5ae82d925197..d242300cacc0 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1722,6 +1722,7 @@ enum emulation_result kvm_mips_emulate_store(union mips_instruction inst, vcpu->arch.gprs[rt], *(u32 *)data); break; +#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ) case sdl_op: run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa( vcpu->arch.host_cp0_badvaddr) & (~0x7); @@ -1815,6 +1816,7 @@ enum emulation_result kvm_mips_emulate_store(union mips_instruction inst, vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr, vcpu->arch.gprs[rt], *(u64 *)data); break; +#endif #ifdef CONFIG_CPU_LOONGSON64 case sdc2_op: @@ -2002,6 +2004,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst, } break; +#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ) case ldl_op: run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa( vcpu->arch.host_cp0_badvaddr) & (~0x7); @@ -2073,6 +2076,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst, break; } break; +#endif #ifdef CONFIG_CPU_LOONGSON64 case ldc2_op: diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index aa37545ebe8f..b10342018d19 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -514,8 +514,8 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP | PMU_PPE_TC); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); - clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); @@ -538,8 +538,8 @@ void __init ltq_soc_init(void) PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM | PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 | PMU_PPE_QSB | PMU_PPE_TOP); - clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); - clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index c152a68811dd..345727638d52 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,8 +74,11 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ + mmap_read_lock(&init_mm); error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, NULL); + mmap_read_unlock(&init_mm); + if (error) return ERR_PTR(error); return cpu_addr; @@ -85,9 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; + mmap_read_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ WARN_ON(walk_page_range(&init_mm, va, va + size, &clear_nocache_walk_ops, NULL)); + mmap_read_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e738ea652192..6a73714759ba 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -40,7 +40,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, /* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */ if (kvmhv_on_pseries()) return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr, - __pa(to), __pa(from), n); + (to != NULL) ? __pa(to): 0, + (from != NULL) ? __pa(from): 0, n); quadrant = 1; if (!pid) diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 1199fc2bfaec..ca5fcb4bff32 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -353,9 +353,6 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) int pkey_shift; u64 amr; - if (!is_pkey_enabled(pkey)) - return true; - pkey_shift = pkeyshift(pkey); if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift))) return true; diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 4a75f2d9bf0e..bce0e5349978 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -14,6 +14,7 @@ #include <linux/memblock.h> #include <linux/libfdt.h> #include <linux/crash_core.h> +#include <asm/cacheflush.h> #include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/kdump.h> diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 38ba55b0eb9d..e4c7c2c8a02f 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -17,7 +17,7 @@ vdso-syms += flush_icache obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) endif # Build rules @@ -27,6 +27,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) obj-y += vdso.o vdso-syms.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +# Disable -pg to prevent insert call site +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os + # Disable gcov profiling for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c index d264943e2e47..cc0d80699c31 100644 --- a/arch/riscv/kernel/vdso/vgettimeofday.c +++ b/arch/riscv/kernel/vdso/vgettimeofday.c @@ -9,16 +9,22 @@ #include <linux/time.h> #include <linux/types.h> +extern +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { return __cvdso_clock_gettime(clock, ts); } +extern +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +extern +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res); int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { return __cvdso_clock_getres(clock_id, res); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 46038bc58c9e..0cf9a82326a8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -1,5 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y @@ -14,7 +15,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y -CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y @@ -31,9 +31,9 @@ CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y -CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_BPF_LSM=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -51,14 +51,11 @@ CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m +CONFIG_S390_UNWIND_SELFTEST=y CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -77,6 +74,8 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -96,7 +95,6 @@ CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y @@ -130,6 +128,7 @@ CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m +CONFIG_INET_ESPINTCP=y CONFIG_INET_IPCOMP=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m @@ -144,6 +143,7 @@ CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m +CONFIG_INET6_ESPINTCP=y CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m CONFIG_IPV6_VTI=m @@ -151,7 +151,10 @@ CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_SUBTREES=y +CONFIG_IPV6_RPL_LWTUNNEL=y +CONFIG_MPTCP=y CONFIG_NETFILTER=y +CONFIG_BRIDGE_NETFILTER=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y @@ -317,6 +320,7 @@ CONFIG_L2TP_V3=y CONFIG_L2TP_IP=m CONFIG_L2TP_ETH=m CONFIG_BRIDGE=m +CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y CONFIG_NET_SCHED=y @@ -341,6 +345,7 @@ CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m @@ -364,6 +369,7 @@ CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_GATE=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m @@ -374,6 +380,7 @@ CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m # CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y +# CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -435,6 +442,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_MULTIPATH_HST=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m @@ -448,6 +456,8 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_BAREUDP=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -481,7 +491,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -# CONFIG_MLXFW is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -514,6 +523,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_XILINX is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -561,6 +571,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -608,6 +620,7 @@ CONFIG_ZISOFS=y CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m +CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y @@ -650,8 +663,8 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_FORTIFY_SOURCE=y @@ -675,8 +688,11 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m +CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -685,6 +701,7 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -701,6 +718,7 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_DES=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m @@ -719,6 +737,9 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y +CONFIG_CRYPTO_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -774,6 +795,7 @@ CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y +CONFIG_TEST_LOCKUP=m CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y @@ -786,7 +808,9 @@ CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 +# CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y +CONFIG_BOOTTIME_TRACING=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y CONFIG_IRQSOFF_TRACER=y @@ -808,10 +832,12 @@ CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y +CONFIG_TEST_MIN_HEAP=y CONFIG_TEST_SORT=y CONFIG_KPROBES_SANITY_TEST=y CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y +CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 7cd0648c1f4e..5df9759e8ff6 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -1,5 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y @@ -13,7 +14,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y -CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y @@ -30,9 +30,9 @@ CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y -CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_BPF_LSM=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -41,7 +41,6 @@ CONFIG_LIVEPATCH=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y -# CONFIG_NUMA_EMU is not set CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y @@ -51,14 +50,11 @@ CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m +CONFIG_S390_UNWIND_SELFTEST=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -74,6 +70,8 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -91,7 +89,6 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y @@ -125,6 +122,7 @@ CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m +CONFIG_INET_ESPINTCP=y CONFIG_INET_IPCOMP=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m @@ -139,6 +137,7 @@ CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m +CONFIG_INET6_ESPINTCP=y CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m CONFIG_IPV6_VTI=m @@ -146,7 +145,10 @@ CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_SUBTREES=y +CONFIG_IPV6_RPL_LWTUNNEL=y +CONFIG_MPTCP=y CONFIG_NETFILTER=y +CONFIG_BRIDGE_NETFILTER=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y @@ -311,6 +313,7 @@ CONFIG_L2TP_V3=y CONFIG_L2TP_IP=m CONFIG_L2TP_ETH=m CONFIG_BRIDGE=m +CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y CONFIG_NET_SCHED=y @@ -335,6 +338,7 @@ CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m @@ -358,6 +362,7 @@ CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_GATE=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m @@ -368,6 +373,7 @@ CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m # CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y +# CONFIG_PCIEASPM is not set CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y @@ -430,6 +436,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_MULTIPATH_HST=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m @@ -444,6 +451,8 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_BAREUDP=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -477,7 +486,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -# CONFIG_MLXFW is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -510,6 +518,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_XILINX is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -557,6 +566,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -600,6 +611,7 @@ CONFIG_ZISOFS=y CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m +CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y @@ -642,8 +654,8 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y @@ -667,8 +679,11 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m +CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m @@ -678,6 +693,7 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -694,6 +710,7 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_DES=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m @@ -712,6 +729,9 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y +CONFIG_CRYPTO_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -725,6 +745,7 @@ CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y CONFIG_CORDIC=m +CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m @@ -739,10 +760,12 @@ CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y +CONFIG_TEST_LOCKUP=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y +CONFIG_BOOTTIME_TRACING=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 20c51e5d9353..4091c50449cd 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -30,6 +30,7 @@ CONFIG_IBM_PARTITION=y # CONFIG_BOUNCE is not set CONFIG_NET=y # CONFIG_IUCV is not set +# CONFIG_ETHTOOL_NETLINK is not set CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_RAM=y # CONFIG_BLK_DEV_XPRAM is not set @@ -55,6 +56,8 @@ CONFIG_RAW_DRIVER=y # CONFIG_MONWRITER is not set # CONFIG_S390_VMUR is not set # CONFIG_HID is not set +# CONFIG_VIRTIO_MENU is not set +# CONFIG_VHOST_MENU is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set @@ -62,7 +65,9 @@ CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +# CONFIG_ZLIB_DFLTCC is not set CONFIG_PRINTK_TIME=y +# CONFIG_SYMBOLIC_ERRNAME is not set CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index cee3cb6455a2..6ea0820e7c7f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -31,12 +31,12 @@ #define KVM_USER_MEM_SLOTS 32 /* - * These seem to be used for allocating ->chip in the routing table, - * which we don't use. 4096 is an out-of-thin-air value. If we need - * to look at ->chip later on, we'll need to revisit this. + * These seem to be used for allocating ->chip in the routing table, which we + * don't use. 1 is as small as we can get to reduce the needed memory. If we + * need to look at ->chip later on, we'll need to revisit this. */ #define KVM_NR_IRQCHIPS 1 -#define KVM_IRQCHIP_NUM_PINS 4096 +#define KVM_IRQCHIP_NUM_PINS 1 #define KVM_HALT_POLL_NS_DEFAULT 50000 /* s390-specific vcpu->requests bit members */ diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 85a711d783eb..4f9e4626df55 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -881,12 +881,21 @@ out: return err; } +static bool is_callchain_event(struct perf_event *event) +{ + u64 sample_type = event->attr.sample_type; + + return sample_type & (PERF_SAMPLE_CALLCHAIN | PERF_SAMPLE_REGS_USER | + PERF_SAMPLE_STACK_USER); +} + static int cpumsf_pmu_event_init(struct perf_event *event) { int err; /* No support for taken branch sampling */ - if (has_branch_stack(event)) + /* No support for callchain, stacks and registers */ + if (has_branch_stack(event) || is_callchain_event(event)) return -EOPNOTSUPP; switch (event->attr.type) { diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 5853c9872dfe..07aa15ba43b3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1100,6 +1100,7 @@ void __init setup_arch(char **cmdline_p) if (IS_ENABLED(CONFIG_EXPOLINE_AUTO)) nospec_auto_detect(); + jump_label_init(); parse_early_param(); #ifdef CONFIG_CRASH_DUMP /* Deactivate elfcorehdr= kernel parameter */ diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 82df06d720e8..3b5a4d25ca9b 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -117,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste) _PAGE_YOUNG); #ifdef CONFIG_MEM_SOFT_DIRTY pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY, - _PAGE_DIRTY); + _PAGE_SOFT_DIRTY); #endif pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC, _PAGE_NOEXEC); diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 22a0be655f27..1d17413b319a 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -62,11 +62,15 @@ notrace void *s390_kernel_write(void *dst, const void *src, size_t size) long copied; spin_lock_irqsave(&s390_kernel_write_lock, flags); - while (size) { - copied = s390_kernel_write_odd(tmp, src, size); - tmp += copied; - src += copied; - size -= copied; + if (!(flags & PSW_MASK_DAT)) { + memcpy(dst, src, size); + } else { + while (size) { + copied = s390_kernel_write_odd(tmp, src, size); + tmp += copied; + src += copied; + size -= copied; + } } spin_unlock_irqrestore(&s390_kernel_write_lock, flags); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 08e1d619398e..fdebd286f402 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -94,7 +94,18 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) } zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; - zpci_create_device(zdev); + ret = zpci_enable_device(zdev); + if (ret) + break; + + pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn); + if (!pdev) + break; + + pci_bus_add_device(pdev); + pci_lock_rescan_remove(); + pci_bus_add_devices(zdev->zbus->bus); + pci_unlock_rescan_remove(); break; case 0x0302: /* Reserved -> Standby */ if (!zdev) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a0cc524882d..883da0abf779 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -67,7 +67,7 @@ config X86 select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL - select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_KCOV if X86_64 && STACK_VALIDATION select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index e821a7d7d5c4..97d37f0a34f5 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -213,7 +213,6 @@ SYM_FUNC_START(startup_32) * We place all of the values on our mini stack so lret can * used to perform that far jump. */ - pushl $__KERNEL_CS leal startup_64(%ebp), %eax #ifdef CONFIG_EFI_MIXED movl efi32_boot_args(%ebp), %edi @@ -224,11 +223,20 @@ SYM_FUNC_START(startup_32) movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer cmpl $0, %edx jnz 1f + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + subl $40, %esp leal efi_pe_entry(%ebp), %eax movl %edi, %ecx // MS calling convention movl %esi, %edx 1: #endif + pushl $__KERNEL_CS pushl %eax /* Enter paged protected Mode, activating Long Mode */ @@ -784,6 +792,7 @@ SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 + .balign 16 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index bd3f14175193..e83b3f14897c 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -45,6 +45,32 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +/* Check that the stack and regs on entry from user mode are sane. */ +static void check_user_regs(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) { + /* + * Make sure that the entry code gave us a sensible EFLAGS + * register. Native because we want to check the actual CPU + * state, not the interrupt state as imagined by Xen. + */ + unsigned long flags = native_save_fl(); + WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF | + X86_EFLAGS_NT)); + + /* We think we came from user mode. Make sure pt_regs agrees. */ + WARN_ON_ONCE(!user_mode(regs)); + + /* + * All entries from user mode (except #DF) should be on the + * normal thread stack and should have user pt_regs in the + * correct location. + */ + WARN_ON_ONCE(!on_thread_stack()); + WARN_ON_ONCE(regs != task_pt_regs(current)); + } +} + #ifdef CONFIG_CONTEXT_TRACKING /** * enter_from_user_mode - Establish state when coming from user mode @@ -127,9 +153,6 @@ static long syscall_trace_enter(struct pt_regs *regs) unsigned long ret = 0; u32 work; - if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) - BUG_ON(regs != task_pt_regs(current)); - work = READ_ONCE(ti->flags); if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) { @@ -346,6 +369,8 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) { struct thread_info *ti; + check_user_regs(regs); + enter_from_user_mode(); instrumentation_begin(); @@ -409,6 +434,8 @@ static void do_syscall_32_irqs_on(struct pt_regs *regs) /* Handles int $0x80 */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { + check_user_regs(regs); + enter_from_user_mode(); instrumentation_begin(); @@ -460,6 +487,8 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) vdso_image_32.sym_int80_landing_pad; bool success; + check_user_regs(regs); + /* * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward * so that 'regs->ip -= 2' lands back on an int $0x80 instruction. @@ -510,6 +539,18 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; #endif } + +/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ +__visible noinstr long do_SYSENTER_32(struct pt_regs *regs) +{ + /* SYSENTER loses RSP, but the vDSO saved it in RBP. */ + regs->sp = regs->bp; + + /* SYSENTER clobbers EFLAGS.IF. Assume it was set in usermode. */ + regs->flags |= X86_EFLAGS_IF; + + return do_fast_syscall_32(regs); +} #endif SYSCALL_DEFINE0(ni_syscall) @@ -553,6 +594,7 @@ SYSCALL_DEFINE0(ni_syscall) bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs) { if (user_mode(regs)) { + check_user_regs(regs); enter_from_user_mode(); return false; } @@ -686,6 +728,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit) */ void noinstr idtentry_enter_user(struct pt_regs *regs) { + check_user_regs(regs); enter_from_user_mode(); } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 024d7d276cd4..2d0bd5d5f032 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -933,9 +933,8 @@ SYM_FUNC_START(entry_SYSENTER_32) .Lsysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ebp /* pt_regs->sp (stashed in bp) */ + pushl $0 /* pt_regs->sp (placeholder) */ pushfl /* pt_regs->flags (except IF = 0) */ - orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ pushl %eax /* pt_regs->orig_ax */ @@ -965,7 +964,7 @@ SYM_FUNC_START(entry_SYSENTER_32) .Lsysenter_flags_fixed: movl %esp, %eax - call do_fast_syscall_32 + call do_SYSENTER_32 /* XEN PV guests always use IRET path */ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 0f974ae01e62..541fdaf64045 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -57,29 +57,30 @@ SYM_CODE_START(entry_SYSENTER_compat) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - /* - * User tracing code (ptrace or signal handlers) might assume that - * the saved RAX contains a 32-bit number when we're invoking a 32-bit - * syscall. Just in case the high bits are nonzero, zero-extend - * the syscall number. (This could almost certainly be deleted - * with no ill effects.) - */ - movl %eax, %eax - /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rbp /* pt_regs->sp (stashed in bp) */ + pushq $0 /* pt_regs->sp = 0 (placeholder) */ /* * Push flags. This is nasty. First, interrupts are currently - * off, but we need pt_regs->flags to have IF set. Second, even - * if TF was set when SYSENTER started, it's clear by now. We fix - * that later using TIF_SINGLESTEP. + * off, but we need pt_regs->flags to have IF set. Second, if TS + * was set in usermode, it's still set, and we're singlestepping + * through this code. do_SYSENTER_32() will fix up IF. */ pushfq /* pt_regs->flags (except IF = 0) */ - orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ pushq $__USER32_CS /* pt_regs->cs */ pushq $0 /* pt_regs->ip = 0 (placeholder) */ +SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) + + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ + movl %eax, %eax + pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -135,7 +136,7 @@ SYM_CODE_START(entry_SYSENTER_compat) .Lsysenter_flags_fixed: movq %rsp, %rdi - call do_fast_syscall_32 + call do_SYSENTER_32 /* XEN PV guests always use IRET path */ ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 12c42eba77ec..9933c0e8e97a 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += core.o probe.o -obj-$(PERF_EVENTS_INTEL_RAPL) += rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += rapl.o obj-y += amd/ obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a54c6a401581..6035df1b49e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -375,7 +375,10 @@ void __init hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); - hv_hypercall_pg = vmalloc_exec(PAGE_SIZE); + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, + VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, + __builtin_return_address(0)); if (hv_hypercall_pg == NULL) { wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); goto remove_cpuhp_state; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 35460fef39b8..0367efdc5b7a 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr) return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } -static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { - /* - * Because this is a plain access, we need to disable KCSAN here to - * avoid double instrumentation via instrumented bitops. - */ return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index fb34ff641e0a..028189575560 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -75,6 +75,12 @@ do { \ unreachable(); \ } while (0) +/* + * This instrumentation_begin() is strictly speaking incorrect; but it + * suppresses the complaints from WARN()s in noinstr code. If such a WARN() + * were to trigger, we'd rather wreck the machine in an attempt to get the + * message out than not know about it. + */ #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index dd17c2da1af5..da78ccbd493b 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip) return false; } #endif +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#else +static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} +#endif #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index 6722ffcef2e6..3afa990d756b 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); +/* + * NMI and MCE exceptions need cpu_is_offline() _really_ early, + * provide an arch_ special for them to avoid instrumentation. + */ +#if NR_CPUS > 1 +static __always_inline bool arch_cpu_online(int cpu) +{ + return arch_test_bit(cpu, cpumask_bits(cpu_online_mask)); +} +#else +static __always_inline bool arch_cpu_online(int cpu) +{ + return cpu == 0; +} +#endif + +#define arch_cpu_is_offline(cpu) unlikely(!arch_cpu_online(cpu)) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 42159f45bf9c..845e7481ab77 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -623,6 +623,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * MXCSR and XCR definitions: */ +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + extern unsigned int mxcsr_feature_mask; #define XCR_XFEATURE_ENABLED_MASK 0x00000000 diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index cf51c50eb356..eeac6dc2adaa 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -353,10 +353,6 @@ static __always_inline void __##func(struct pt_regs *regs) #else /* CONFIG_X86_64 */ -/* Maps to a regular IDTENTRY on 32bit for now */ -# define DECLARE_IDTENTRY_IST DECLARE_IDTENTRY -# define DEFINE_IDTENTRY_IST DEFINE_IDTENTRY - /** * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant * @vector: Vector number (ignored for C) @@ -387,28 +383,18 @@ __visible noinstr void func(struct pt_regs *regs, \ #endif /* !CONFIG_X86_64 */ /* C-Code mapping */ +#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW +#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW + +#ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST -#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW -#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW - #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST - -/** - * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points - * @vector: Vector number (ignored for C) - * @func: Function name of the entry point - * - * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM - * indirection magic. - */ -#define DECLARE_IDTENTRY_XEN(vector, func) \ - asmlinkage void xen_asm_exc_xen##func(void); \ - asmlinkage void asm_exc_xen##func(void) +#endif #else /* !__ASSEMBLY__ */ @@ -455,9 +441,6 @@ __visible noinstr void func(struct pt_regs *regs, \ # define DECLARE_IDTENTRY_MCE(vector, func) \ DECLARE_IDTENTRY(vector, func) -# define DECLARE_IDTENTRY_DEBUG(vector, func) \ - DECLARE_IDTENTRY(vector, func) - /* No ASM emitted for DF as this goes through a C shim */ # define DECLARE_IDTENTRY_DF(vector, func) @@ -469,10 +452,6 @@ __visible noinstr void func(struct pt_regs *regs, \ /* No ASM code emitted for NMI */ #define DECLARE_IDTENTRY_NMI(vector, func) -/* XEN NMI and DB wrapper */ -#define DECLARE_IDTENTRY_XEN(vector, func) \ - idtentry vector asm_exc_xen##func exc_##func has_error_code=0 - /* * ASM code to emit the common vector entry stubs where each stub is * packed into 8 bytes. @@ -565,16 +544,28 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); #ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_64 DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_MC, exc_machine_check); +#endif #endif /* NMI */ DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); -DECLARE_IDTENTRY_XEN(X86_TRAP_NMI, nmi); +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi); +#endif /* #DB */ +#ifdef CONFIG_X86_64 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB, exc_debug); -DECLARE_IDTENTRY_XEN(X86_TRAP_DB, debug); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, exc_debug); +#endif +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); +#endif /* #DF */ DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 2da1f95b88d7..816b31c68550 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -194,6 +194,7 @@ enum page_cache_mode { #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) #define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) #define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) @@ -219,6 +220,7 @@ enum page_cache_mode { #define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) #define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) #define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) #define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) #define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 42cd333616c4..03b7c4ca425a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -370,7 +370,7 @@ struct x86_hw_tss { #define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 17c5a038f42d..0780f97c1850 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data { }; struct kvm_vmx_nested_state_hdr { - __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; - __u64 preemption_timer_deadline; struct { __u16 flags; } smm; + + __u32 flags; + __u64 preemption_timer_deadline; }; struct kvm_svm_nested_state_data { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 426792565d86..c5cf336e5077 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -3,6 +3,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 043d93cdcaad..95c090a45b4b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -347,6 +347,9 @@ out: cr4_clear_bits(X86_CR4_UMIP); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0); void native_write_cr4(unsigned long val) { - unsigned long bits_missing = 0; + unsigned long bits_changed = 0; set_register: asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); if (static_branch_likely(&cr_pinning)) { - if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) { - bits_missing = ~val & cr4_pinned_bits; - val |= bits_missing; + if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; goto set_register; } - /* Warn after we've set the missing bits. */ - WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n", - bits_missing); + /* Warn after we've corrected the changed bits. */ + WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n", + bits_changed); } } #if IS_MODULE(CONFIG_LKDTM) @@ -419,7 +422,7 @@ void cr4_init(void) if (boot_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; if (static_branch_likely(&cr_pinning)) - cr4 |= cr4_pinned_bits; + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits; __write_cr4(cr4); @@ -434,10 +437,7 @@ void cr4_init(void) */ static void __init setup_cr_pinning(void) { - unsigned long mask; - - mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP); - cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask; + cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask; static_key_enable(&cr_pinning.key); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index fb538fccd24c..9d033693519a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -81,8 +81,4 @@ extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); -#ifdef CONFIG_IA32_FEAT_CTL -void init_ia32_feat_ctl(struct cpuinfo_x86 *c); -#endif - #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c25a67a34bd3..0ab48f1cdf84 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -50,6 +50,13 @@ static enum split_lock_detect_state sld_state __ro_after_init = sld_off; static u64 msr_test_ctrl_cache __ro_after_init; /* + * With a name like MSR_TEST_CTL it should go without saying, but don't touch + * MSR_TEST_CTL unless the CPU is one of the whitelisted models. Writing it + * on CPUs that do not support SLD can cause fireworks, even when writing '0'. + */ +static bool cpu_model_supports_sld __ro_after_init; + +/* * Processors which have self-snooping capability can handle conflicting * memory type across CPUs by snooping its own cache. However, there exists * CPU models in which having conflicting memory types still leads to @@ -1071,7 +1078,8 @@ static void sld_update_msr(bool on) static void split_lock_init(void) { - split_lock_verify_msr(sld_state != sld_off); + if (cpu_model_supports_sld) + split_lock_verify_msr(sld_state != sld_off); } static void split_lock_warn(unsigned long ip) @@ -1177,5 +1185,6 @@ void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) return; } + cpu_model_supports_sld = true; split_lock_setup(); } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index ce9120c4f740..14e4b4d17ee5 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void) { unsigned int cpu = smp_processor_id(); - if (cpu_is_offline(cpu) || + if (arch_cpu_is_offline(cpu) || (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; @@ -1901,6 +1901,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { + WARN_ON_ONCE(user_mode(regs)); + /* * Only required when from kernel mode. See * mce_check_crashing_cpu() for details. @@ -1954,7 +1956,7 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check) } #else /* 32bit unified entry point */ -DEFINE_IDTENTRY_MCE(exc_machine_check) +DEFINE_IDTENTRY_RAW(exc_machine_check) { unsigned long dr7; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 12f967c6b603..6a9df71c1b9e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; - if (c->x86_vendor == X86_VENDOR_INTEL) - c->x86_cache_mbm_width_offset = eax & 0xff; - else - c->x86_cache_mbm_width_offset = -1; + c->x86_cache_mbm_width_offset = eax & 0xff; + + if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index f20a47d120b1..5ffa32256b3b 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -37,6 +37,7 @@ #define MBA_IS_LINEAR 0x4 #define MBA_MAX_MBPS U32_MAX #define MAX_MBA_BW_AMD 0x800 +#define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 23b4b61319d3..3f844f14fc0a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index df1358ba622b..05fa4ef63490 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -2,6 +2,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include "cpu.h" diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 06c818967bb6..15247b96c6ea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -101,6 +101,12 @@ void kernel_fpu_begin(void) copy_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); + + if (boot_cpu_has(X86_FEATURE_XMM)) + ldmxcsr(MXCSR_DEFAULT); + + if (boot_cpu_has(X86_FEATURE_FPU)) + asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 8748321c4486..b8aee71840ae 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -29,6 +29,8 @@ #include <asm/mmu_context.h> #include <asm/pgtable_areas.h> +#include <xen/xen.h> + /* This is a multiple of PAGE_SIZE. */ #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) @@ -543,6 +545,28 @@ static int read_default_ldt(void __user *ptr, unsigned long bytecount) return bytecount; } +static bool allow_16bit_segments(void) +{ + if (!IS_ENABLED(CONFIG_X86_16BIT)) + return false; + +#ifdef CONFIG_XEN_PV + /* + * Xen PV does not implement ESPFIX64, which means that 16-bit + * segments will not work correctly. Until either Xen PV implements + * ESPFIX64 and can signal this fact to the guest or unless someone + * provides compelling evidence that allowing broken 16-bit segments + * is worthwhile, disallow 16-bit segments under Xen PV. + */ + if (xen_pv_domain()) { + pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n"); + return false; + } +#endif + + return true; +} + static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; @@ -574,7 +598,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) /* The user wants to clear the entry. */ memset(&ldt, 0, sizeof(ldt)); } else { - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + if (!ldt_info.seg_32bit && !allow_16bit_segments()) { error = -EINVAL; goto out; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2de365f15684..d7c5e44b26f7 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -478,7 +478,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { - if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f9727b96961f..b038695f36c5 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } -int is_valid_bugaddr(unsigned long addr) +__always_inline int is_valid_bugaddr(unsigned long addr) { - unsigned short ud; - if (addr < TASK_SIZE_MAX) return 0; - if (get_kernel_nofault(ud, (unsigned short *)addr)) - return 0; - - return ud == INSN_UD0 || ud == INSN_UD2; + /* + * We got #UD, if the text isn't readable we'd have gotten + * a different exception. + */ + return *(unsigned short *)addr == INSN_UD2; } static nokprobe_inline int @@ -216,40 +215,45 @@ static inline void handle_invalid_op(struct pt_regs *regs) ILL_ILLOPN, error_get_trap_addr(regs)); } -DEFINE_IDTENTRY_RAW(exc_invalid_op) +static noinstr bool handle_bug(struct pt_regs *regs) { - bool rcu_exit; + bool handled = false; + + if (!is_valid_bugaddr(regs->ip)) + return handled; /* - * Handle BUG/WARN like NMIs instead of like normal idtentries: - * if we bugged/warned in a bad RCU context, for example, the last - * thing we want is to BUG/WARN again in the idtentry code, ad - * infinitum. + * All lies, just get the WARN/BUG out. + */ + instrumentation_begin(); + /* + * Since we're emulating a CALL with exceptions, restore the interrupt + * state to what it was at the exception site. */ - if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) { - enum bug_trap_type type; + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_enable(); + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_disable(); + instrumentation_end(); - nmi_enter(); - instrumentation_begin(); - trace_hardirqs_off_finish(); - type = report_bug(regs->ip, regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); - instrumentation_end(); - nmi_exit(); + return handled; +} - if (type == BUG_TRAP_TYPE_WARN) { - /* Skip the ud2. */ - regs->ip += LEN_UD2; - return; - } +DEFINE_IDTENTRY_RAW(exc_invalid_op) +{ + bool rcu_exit; - /* - * Else, if this was a BUG and report_bug returns or if this - * was just a normal #UD, we want to continue onward and - * crash. - */ - } + /* + * We use UD2 as a short encoding for 'CALL __WARN', as such + * handle it before exception entry to avoid recursive WARN + * in case exception entry is the one triggering WARNs. + */ + if (!user_mode(regs) && handle_bug(regs)) + return; rcu_exit = idtentry_enter_cond_rcu(regs); instrumentation_begin(); @@ -691,13 +695,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); /* Update the entry stack */ - memcpy(new_stack, &tmp, sizeof(tmp)); + __memcpy(new_stack, &tmp, sizeof(tmp)); BUG_ON(!user_mode(&new_stack->regs)); return new_stack; @@ -866,6 +870,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, trace_hardirqs_off_finish(); /* + * If something gets miswired and we end up here for a user mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(user_mode(regs)); + + /* * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. */ @@ -883,6 +893,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, static __always_inline void exc_debug_user(struct pt_regs *regs, unsigned long dr6) { + /* + * If something gets miswired and we end up here for a kernel mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(!user_mode(regs)); + idtentry_enter_user(regs); instrumentation_begin(); @@ -913,7 +929,7 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) } #else /* 32 bit does not have separate entry points. */ -DEFINE_IDTENTRY_DEBUG(exc_debug) +DEFINE_IDTENTRY_RAW(exc_debug) { unsigned long dr6, dr7; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index ff2d0e9ca3bc..cfe83d4ae625 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE) + | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 76817d13c86e..6d6a0ae7800c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4449,7 +4449,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d1af20b050a8..d4a4cec034d0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4109,7 +4109,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4259,7 +4259,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); @@ -6176,6 +6176,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; } + vmx->nested.has_preemption_timer_deadline = false; if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) { vmx->nested.has_preemption_timer_deadline = true; vmx->nested.preemption_timer_deadline = diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index cb22f33bf1d8..13745f2a5ecd 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -133,9 +133,6 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \ X86_CR0_WP | X86_CR0_PG | X86_CR0_PE) -#define KVM_CR4_GUEST_OWNED_BITS \ - (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD) #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) @@ -4034,9 +4031,9 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { - vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; - if (enable_ept) - vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; + vmx->vcpu.arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS; + if (!enable_ept) + vmx->vcpu.arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; if (is_guest_mode(&vmx->vcpu)) vmx->vcpu.arch.cr4_guest_owned_bits &= ~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask; @@ -4333,8 +4330,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; - vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); + vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3b92db412335..88c593f83b28 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + if ((cr4 ^ old_cr4) & X86_CR4_LA57) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, @@ -2693,6 +2695,9 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) if (data & 0x30) return 1; + if (!lapic_in_kernel(vcpu)) + return 1; + vcpu->arch.apf.msr_en_val = data; if (!kvm_pv_async_pf_enabled(vcpu)) { diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 56b243b14c3a..bbcc05bcefad 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include <asm/alternative-asm.h> #include <asm/export.h> +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index fff28c6f73a2..b0dfac3d3df7 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" + " .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n" diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 7c65102debaf..db1378c6ff26 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -193,6 +193,8 @@ static void fix_processor_context(void) */ static void notrace __restore_processor_state(struct saved_context *ctxt) { + struct cpuinfo_x86 *c; + if (ctxt->misc_enable_saved) wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* @@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) mtrr_bp_restore(); perf_restore_debug_store(); msr_restore_context(ctxt); + + c = &cpu_data(smp_processor_id()); + if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) + init_ia32_feat_ctl(c); } /* Needed by apm.c */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index acc49fa6a097..0d68948c82ad 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -598,6 +598,26 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, } #ifdef CONFIG_X86_64 +void noist_exc_debug(struct pt_regs *regs); + +DEFINE_IDTENTRY_RAW(xenpv_exc_nmi) +{ + /* On Xen PV, NMI doesn't use IST. The C part is the sane as native. */ + exc_nmi(regs); +} + +DEFINE_IDTENTRY_RAW(xenpv_exc_debug) +{ + /* + * There's no IST on Xen PV, but we still need to dispatch + * to the correct handler. + */ + if (user_mode(regs)) + noist_exc_debug(regs); + else + exc_debug(regs); +} + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -609,18 +629,18 @@ struct trap_array_entry { .xen = xen_asm_##func, \ .ist_okay = ist_ok } -#define TRAP_ENTRY_REDIR(func, xenfunc, ist_ok) { \ +#define TRAP_ENTRY_REDIR(func, ist_ok) { \ .orig = asm_##func, \ - .xen = xen_asm_##xenfunc, \ + .xen = xen_asm_xenpv_##func, \ .ist_okay = ist_ok } static struct trap_array_entry trap_array[] = { - TRAP_ENTRY_REDIR(exc_debug, exc_xendebug, true ), + TRAP_ENTRY_REDIR(exc_debug, true ), TRAP_ENTRY(exc_double_fault, true ), #ifdef CONFIG_X86_MCE TRAP_ENTRY(exc_machine_check, true ), #endif - TRAP_ENTRY_REDIR(exc_nmi, exc_xennmi, true ), + TRAP_ENTRY_REDIR(exc_nmi, true ), TRAP_ENTRY(exc_int3, false ), TRAP_ENTRY(exc_overflow, false ), #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 5d252aaeade8..aab1d99b2b48 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -29,10 +29,9 @@ _ASM_NOKPROBE(xen_\name) .endm xen_pv_trap asm_exc_divide_error -xen_pv_trap asm_exc_debug -xen_pv_trap asm_exc_xendebug +xen_pv_trap asm_xenpv_exc_debug xen_pv_trap asm_exc_int3 -xen_pv_trap asm_exc_xennmi +xen_pv_trap asm_xenpv_exc_nmi xen_pv_trap asm_exc_overflow xen_pv_trap asm_exc_bounds xen_pv_trap asm_exc_invalid_op @@ -161,10 +160,22 @@ SYM_FUNC_END(xen_syscall32_target) /* 32-bit compat sysenter target */ SYM_FUNC_START(xen_sysenter_target) - mov 0*8(%rsp), %rcx - mov 1*8(%rsp), %r11 - mov 5*8(%rsp), %rsp - jmp entry_SYSENTER_compat + /* + * NB: Xen is polite and clears TF from EFLAGS for us. This means + * that we don't need to guard against single step exceptions here. + */ + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER32_DS, 4*8(%rsp) + movq $__USER32_CS, 1*8(%rsp) + + jmp entry_SYSENTER_compat_after_hwframe SYM_FUNC_END(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 23632a33ed39..9ffd7e289554 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -24,6 +24,19 @@ void blk_flush_integrity(void) flush_workqueue(kintegrityd_wq); } +static void __bio_integrity_free(struct bio_set *bs, + struct bio_integrity_payload *bip) +{ + if (bs && mempool_initialized(&bs->bio_integrity_pool)) { + if (bip->bip_vec) + bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, + bip->bip_slab); + mempool_free(bip, &bs->bio_integrity_pool); + } else { + kfree(bip); + } +} + /** * bio_integrity_alloc - Allocate integrity payload and attach it to bio * @bio: bio to attach integrity metadata to @@ -78,7 +91,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, return bip; err: - mempool_free(bip, &bs->bio_integrity_pool); + __bio_integrity_free(bs, bip); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(bio_integrity_alloc); @@ -99,14 +112,7 @@ void bio_integrity_free(struct bio *bio) kfree(page_address(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset); - if (bs && mempool_initialized(&bs->bio_integrity_pool)) { - bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab); - - mempool_free(bip, &bs->bio_integrity_pool); - } else { - kfree(bip); - } - + __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; bio->bi_opf &= ~REQ_INTEGRITY; } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 15df3a36e9fa..e0b2bc131bf5 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -125,6 +125,9 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(REGISTERED), QUEUE_FLAG_NAME(SCSI_PASSTHROUGH), QUEUE_FLAG_NAME(QUIESCED), + QUEUE_FLAG_NAME(PCI_P2PDMA), + QUEUE_FLAG_NAME(ZONE_RESETALL), + QUEUE_FLAG_NAME(RQ_ALLOC_TIME), }; #undef QUEUE_FLAG_NAME diff --git a/block/blk-mq.c b/block/blk-mq.c index a9aa6d1e44cf..4e0d173beaa3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -828,10 +828,10 @@ static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { /* - * If we find a request that is inflight and the queue matches, + * If we find a request that isn't idle and the queue matches, * we know the queue is busy. Return false to stop the iteration. */ - if (rq->state == MQ_RQ_IN_FLIGHT && rq->q == hctx->queue) { + if (blk_mq_request_started(rq) && rq->q == hctx->queue) { bool *busy = priv; *busy = true; diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index c2ef41b3147b..35abcb1ec051 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -374,8 +374,7 @@ void blk_ksm_destroy(struct blk_keyslot_manager *ksm) if (!ksm) return; kvfree(ksm->slot_hashtable); - memzero_explicit(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots); - kvfree(ksm->slots); + kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots); memzero_explicit(ksm, sizeof(*ksm)); } EXPORT_SYMBOL_GPL(blk_ksm_destroy); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index b1cd3535c525..28fc323e3fe3 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -128,21 +128,15 @@ EXPORT_SYMBOL_GPL(af_alg_release); void af_alg_release_parent(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); - unsigned int nokey = ask->nokey_refcnt; - bool last = nokey && !ask->refcnt; + unsigned int nokey = atomic_read(&ask->nokey_refcnt); sk = ask->parent; ask = alg_sk(sk); - local_bh_disable(); - bh_lock_sock(sk); - ask->nokey_refcnt -= nokey; - if (!last) - last = !--ask->refcnt; - bh_unlock_sock(sk); - local_bh_enable(); + if (nokey) + atomic_dec(&ask->nokey_refcnt); - if (last) + if (atomic_dec_and_test(&ask->refcnt)) sock_put(sk); } EXPORT_SYMBOL_GPL(af_alg_release_parent); @@ -187,7 +181,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = -EBUSY; lock_sock(sk); - if (ask->refcnt | ask->nokey_refcnt) + if (atomic_read(&ask->refcnt)) goto unlock; swap(ask->type, type); @@ -236,7 +230,7 @@ static int alg_setsockopt(struct socket *sock, int level, int optname, int err = -EBUSY; lock_sock(sk); - if (ask->refcnt) + if (atomic_read(&ask->refcnt) != atomic_read(&ask->nokey_refcnt)) goto unlock; type = ask->type; @@ -301,12 +295,14 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern) if (err) goto unlock; - if (nokey || !ask->refcnt++) + if (atomic_inc_return_relaxed(&ask->refcnt) == 1) sock_hold(sk); - ask->nokey_refcnt += nokey; + if (nokey) { + atomic_inc(&ask->nokey_refcnt); + atomic_set(&alg_sk(sk2)->nokey_refcnt, 1); + } alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; - alg_sk(sk2)->nokey_refcnt = nokey; newsock->ops = type->ops; newsock->state = SS_CONNECTED; diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index eb1910b6d434..0ae000a61c7f 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -384,7 +384,7 @@ static int aead_check_key(struct socket *sock) struct alg_sock *ask = alg_sk(sk); lock_sock(sk); - if (ask->refcnt) + if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; @@ -396,11 +396,8 @@ static int aead_check_key(struct socket *sock) if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY) goto unlock; - if (!pask->refcnt++) - sock_hold(psk); - - ask->refcnt = 1; - sock_put(psk); + atomic_dec(&pask->nokey_refcnt); + atomic_set(&ask->nokey_refcnt, 0); err = 0; diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index da1ffa4f7f8d..e71727c25a7d 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -301,7 +301,7 @@ static int hash_check_key(struct socket *sock) struct alg_sock *ask = alg_sk(sk); lock_sock(sk); - if (ask->refcnt) + if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; @@ -313,11 +313,8 @@ static int hash_check_key(struct socket *sock) if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) goto unlock; - if (!pask->refcnt++) - sock_hold(psk); - - ask->refcnt = 1; - sock_put(psk); + atomic_dec(&pask->nokey_refcnt); + atomic_set(&ask->nokey_refcnt, 0); err = 0; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 4c3bdffe0c3a..ec5567c87a6d 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -211,7 +211,7 @@ static int skcipher_check_key(struct socket *sock) struct alg_sock *ask = alg_sk(sk); lock_sock(sk); - if (ask->refcnt) + if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; @@ -223,11 +223,8 @@ static int skcipher_check_key(struct socket *sock) if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) goto unlock; - if (!pask->refcnt++) - sock_hold(psk); - - ask->refcnt = 1; - sock_put(psk); + atomic_dec(&pask->nokey_refcnt); + atomic_set(&ask->nokey_refcnt, 0); err = 0; diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c index ece8c1a921cc..88c8af455ea3 100644 --- a/drivers/acpi/acpi_configfs.c +++ b/drivers/acpi/acpi_configfs.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/configfs.h> #include <linux/acpi.h> +#include <linux/security.h> #include "acpica/accommon.h" #include "acpica/actables.h" @@ -28,7 +29,10 @@ static ssize_t acpi_table_aml_write(struct config_item *cfg, { const struct acpi_table_header *header = data; struct acpi_table *table; - int ret; + int ret = security_locked_down(LOCKDOWN_ACPI_TABLES); + + if (ret) + return ret; table = container_of(cfg, struct acpi_table, cfg); diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c index 5fab7e350db8..92b996a564d0 100644 --- a/drivers/acpi/dptf/dptf_power.c +++ b/drivers/acpi/dptf/dptf_power.c @@ -228,6 +228,7 @@ static const struct acpi_device_id int3407_device_ids[] = { {"INT3407", 0}, {"INT3532", 0}, {"INTC1047", 0}, + {"INTC1050", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, int3407_device_ids); diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 873e039ad4b7..62873388b24f 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -25,8 +25,8 @@ static int acpi_fan_remove(struct platform_device *pdev); static const struct acpi_device_id fan_device_ids[] = { {"PNP0C0B", 0}, - {"INT1044", 0}, {"INT3404", 0}, + {"INTC1044", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, fan_device_ids); diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 3a89909b50a6..76c668c05fa0 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -938,13 +938,13 @@ static void __exit interrupt_stats_exit(void) } static ssize_t -acpi_show_profile(struct device *dev, struct device_attribute *attr, +acpi_show_profile(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", acpi_gbl_FADT.preferred_profile); } -static const struct device_attribute pm_profile_attr = +static const struct kobj_attribute pm_profile_attr = __ATTR(pm_profile, S_IRUGO, acpi_show_profile, NULL); static ssize_t hotplug_enabled_show(struct kobject *kobj, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index e47c8a4c83db..f50c5f182bb5 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4686,8 +4686,15 @@ static struct binder_thread *binder_get_thread(struct binder_proc *proc) static void binder_free_proc(struct binder_proc *proc) { + struct binder_device *device; + BUG_ON(!list_empty(&proc->todo)); BUG_ON(!list_empty(&proc->delivered_death)); + device = container_of(proc->context, struct binder_device, context); + if (refcount_dec_and_test(&device->ref)) { + kfree(proc->context->name); + kfree(device); + } binder_alloc_deferred_release(&proc->alloc); put_task_struct(proc->tsk); binder_stats_deleted(BINDER_STAT_PROC); @@ -5406,7 +5413,6 @@ static int binder_node_release(struct binder_node *node, int refs) static void binder_deferred_release(struct binder_proc *proc) { struct binder_context *context = proc->context; - struct binder_device *device; struct rb_node *n; int threads, nodes, incoming_refs, outgoing_refs, active_transactions; @@ -5423,12 +5429,6 @@ static void binder_deferred_release(struct binder_proc *proc) context->binder_context_mgr_node = NULL; } mutex_unlock(&context->context_mgr_node_lock); - device = container_of(proc->context, struct binder_device, context); - if (refcount_dec_and_test(&device->ref)) { - kfree(context->name); - kfree(device); - } - proc->context = NULL; binder_inner_proc_lock(proc); /* * Make sure proc stays alive after we diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index c32f7dd9879a..b7646ae55942 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Driver for the Solos PCI ADSL2+ card, designed to support Linux by - * Traverse Technologies -- http://www.traverse.com.au/ + * Traverse Technologies -- https://www.traverse.com.au/ * Xrio Limited -- http://www.xrio.com/ * * Copyright © 2008 Traverse Technologies diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 977d27bd1a22..a97f33d0c59f 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -265,14 +265,14 @@ static struct notifier_block pm_trace_nb = { .notifier_call = pm_trace_notify, }; -static int early_resume_init(void) +static int __init early_resume_init(void) { hash_value_early_read = read_magic_time(); register_pm_notifier(&pm_trace_nb); return 0; } -static int late_resume_init(void) +static int __init late_resume_init(void) { unsigned int val = hash_value_early_read; unsigned int user, file, dev; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 43cff01a5a67..ce7e9f223b20 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1033,25 +1033,26 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, test_bit(NBD_RT_BOUND, &config->runtime_flags))) { dev_err(disk_to_dev(nbd->disk), "Device being setup by another task"); - sockfd_put(sock); - return -EBUSY; + err = -EBUSY; + goto put_socket; + } + + nsock = kzalloc(sizeof(*nsock), GFP_KERNEL); + if (!nsock) { + err = -ENOMEM; + goto put_socket; } socks = krealloc(config->socks, (config->num_connections + 1) * sizeof(struct nbd_sock *), GFP_KERNEL); if (!socks) { - sockfd_put(sock); - return -ENOMEM; + kfree(nsock); + err = -ENOMEM; + goto put_socket; } config->socks = socks; - nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL); - if (!nsock) { - sockfd_put(sock); - return -ENOMEM; - } - nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); @@ -1063,6 +1064,10 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, atomic_inc(&config->live_connections); return 0; + +put_socket: + sockfd_put(sock); + return err; } static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 9d21bf0f155e..980df853ee49 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -878,6 +878,7 @@ out_put_disk: put_disk(vblk->disk); out_free_vq: vdev->config->del_vqs(vdev); + kfree(vblk->vqs); out_free_vblk: kfree(vblk); out_free_index: diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 3affd180baac..bb54fb514e40 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -221,6 +221,35 @@ static u32 sysc_read_sysstatus(struct sysc *ddata) return sysc_read(ddata, offset); } +/* Poll on reset status */ +static int sysc_wait_softreset(struct sysc *ddata) +{ + u32 sysc_mask, syss_done, rstval; + int syss_offset, error = 0; + + syss_offset = ddata->offsets[SYSC_SYSSTATUS]; + sysc_mask = BIT(ddata->cap->regbits->srst_shift); + + if (ddata->cfg.quirks & SYSS_QUIRK_RESETDONE_INVERTED) + syss_done = 0; + else + syss_done = ddata->cfg.syss_mask; + + if (syss_offset >= 0) { + error = readx_poll_timeout(sysc_read_sysstatus, ddata, rstval, + (rstval & ddata->cfg.syss_mask) == + syss_done, + 100, MAX_MODULE_SOFTRESET_WAIT); + + } else if (ddata->cfg.quirks & SYSC_QUIRK_RESET_STATUS) { + error = readx_poll_timeout(sysc_read_sysconfig, ddata, rstval, + !(rstval & sysc_mask), + 100, MAX_MODULE_SOFTRESET_WAIT); + } + + return error; +} + static int sysc_add_named_clock_from_child(struct sysc *ddata, const char *name, const char *optfck_name) @@ -925,18 +954,47 @@ static int sysc_enable_module(struct device *dev) struct sysc *ddata; const struct sysc_regbits *regbits; u32 reg, idlemodes, best_mode; + int error; ddata = dev_get_drvdata(dev); + + /* + * Some modules like DSS reset automatically on idle. Enable optional + * reset clocks and wait for OCP softreset to complete. + */ + if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) { + error = sysc_enable_opt_clocks(ddata); + if (error) { + dev_err(ddata->dev, + "Optional clocks failed for enable: %i\n", + error); + return error; + } + } + error = sysc_wait_softreset(ddata); + if (error) + dev_warn(ddata->dev, "OCP softreset timed out\n"); + if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) + sysc_disable_opt_clocks(ddata); + + /* + * Some subsystem private interconnects, like DSS top level module, + * need only the automatic OCP softreset handling with no sysconfig + * register bits to configure. + */ if (ddata->offsets[SYSC_SYSCONFIG] == -ENODEV) return 0; regbits = ddata->cap->regbits; reg = sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]); - /* Set CLOCKACTIVITY, we only use it for ick */ + /* + * Set CLOCKACTIVITY, we only use it for ick. And we only configure it + * based on the SYSC_QUIRK_USE_CLOCKACT flag, not based on the hardware + * capabilities. See the old HWMOD_SET_DEFAULT_CLOCKACT flag. + */ if (regbits->clkact_shift >= 0 && - (ddata->cfg.quirks & SYSC_QUIRK_USE_CLOCKACT || - ddata->cfg.sysc_val & BIT(regbits->clkact_shift))) + (ddata->cfg.quirks & SYSC_QUIRK_USE_CLOCKACT)) reg |= SYSC_CLOCACT_ICK << regbits->clkact_shift; /* Set SIDLE mode */ @@ -991,6 +1049,9 @@ set_autoidle: sysc_write_sysconfig(ddata, reg); } + /* Flush posted write */ + sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]); + if (ddata->module_enable_quirk) ddata->module_enable_quirk(ddata); @@ -1071,6 +1132,9 @@ set_sidle: reg |= 1 << regbits->autoidle_shift; sysc_write_sysconfig(ddata, reg); + /* Flush posted write */ + sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]); + return 0; } @@ -1488,7 +1552,7 @@ static u32 sysc_quirk_dispc(struct sysc *ddata, int dispc_offset, bool lcd_en, digit_en, lcd2_en = false, lcd3_en = false; const int lcd_en_mask = BIT(0), digit_en_mask = BIT(1); int manager_count; - bool framedonetv_irq; + bool framedonetv_irq = true; u32 val, irq_mask = 0; switch (sysc_soc->soc) { @@ -1505,6 +1569,7 @@ static u32 sysc_quirk_dispc(struct sysc *ddata, int dispc_offset, break; case SOC_AM4: manager_count = 1; + framedonetv_irq = false; break; case SOC_UNKNOWN: default: @@ -1822,11 +1887,10 @@ static int sysc_legacy_init(struct sysc *ddata) */ static int sysc_reset(struct sysc *ddata) { - int sysc_offset, syss_offset, sysc_val, rstval, error = 0; - u32 sysc_mask, syss_done; + int sysc_offset, sysc_val, error; + u32 sysc_mask; sysc_offset = ddata->offsets[SYSC_SYSCONFIG]; - syss_offset = ddata->offsets[SYSC_SYSSTATUS]; if (ddata->legacy_mode || ddata->cap->regbits->srst_shift < 0 || @@ -1835,11 +1899,6 @@ static int sysc_reset(struct sysc *ddata) sysc_mask = BIT(ddata->cap->regbits->srst_shift); - if (ddata->cfg.quirks & SYSS_QUIRK_RESETDONE_INVERTED) - syss_done = 0; - else - syss_done = ddata->cfg.syss_mask; - if (ddata->pre_reset_quirk) ddata->pre_reset_quirk(ddata); @@ -1856,18 +1915,9 @@ static int sysc_reset(struct sysc *ddata) if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); - /* Poll on reset status */ - if (syss_offset >= 0) { - error = readx_poll_timeout(sysc_read_sysstatus, ddata, rstval, - (rstval & ddata->cfg.syss_mask) == - syss_done, - 100, MAX_MODULE_SOFTRESET_WAIT); - - } else if (ddata->cfg.quirks & SYSC_QUIRK_RESET_STATUS) { - error = readx_poll_timeout(sysc_read_sysconfig, ddata, rstval, - !(rstval & sysc_mask), - 100, MAX_MODULE_SOFTRESET_WAIT); - } + error = sysc_wait_softreset(ddata); + if (error) + dev_warn(ddata->dev, "OCP softreset timed out\n"); if (ddata->reset_done_quirk) ddata->reset_done_quirk(ddata); diff --git a/drivers/char/tpm/st33zp24/i2c.c b/drivers/char/tpm/st33zp24/i2c.c index 35333b65acd1..7c617edff4ca 100644 --- a/drivers/char/tpm/st33zp24/i2c.c +++ b/drivers/char/tpm/st33zp24/i2c.c @@ -210,7 +210,7 @@ static int st33zp24_i2c_request_resources(struct i2c_client *client) /* * st33zp24_i2c_probe initialize the TPM device - * @param: client, the i2c_client drescription (TPM I2C description). + * @param: client, the i2c_client description (TPM I2C description). * @param: id, the i2c_device_id struct. * @return: 0 in case of success. * -1 in other case. diff --git a/drivers/char/tpm/st33zp24/spi.c b/drivers/char/tpm/st33zp24/spi.c index 26e09de50f1e..a75dafd39445 100644 --- a/drivers/char/tpm/st33zp24/spi.c +++ b/drivers/char/tpm/st33zp24/spi.c @@ -329,7 +329,7 @@ static int st33zp24_spi_request_resources(struct spi_device *dev) /* * st33zp24_spi_probe initialize the TPM device - * @param: dev, the spi_device drescription (TPM SPI description). + * @param: dev, the spi_device description (TPM SPI description). * @return: 0 in case of success. * or a negative value describing the error. */ @@ -378,7 +378,7 @@ static int st33zp24_spi_probe(struct spi_device *dev) /* * st33zp24_spi_remove remove the TPM device - * @param: client, the spi_device drescription (TPM SPI description). + * @param: client, the spi_device description (TPM SPI description). * @return: 0 in case of success. */ static int st33zp24_spi_remove(struct spi_device *dev) diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c index 37bb13f516be..4ec10ab5e576 100644 --- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -502,7 +502,7 @@ static const struct tpm_class_ops st33zp24_tpm = { /* * st33zp24_probe initialize the TPM device - * @param: client, the i2c_client drescription (TPM I2C description). + * @param: client, the i2c_client description (TPM I2C description). * @param: id, the i2c_device_id struct. * @return: 0 in case of success. * -1 in other case. diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 87f449340202..1784530b8387 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -189,15 +189,6 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, goto out; } - /* atomic tpm command send and result receive. We only hold the ops - * lock during this period so that the tpm can be unregistered even if - * the char dev is held open. - */ - if (tpm_try_get_ops(priv->chip)) { - ret = -EPIPE; - goto out; - } - priv->response_length = 0; priv->response_read = false; *off = 0; @@ -211,11 +202,19 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, if (file->f_flags & O_NONBLOCK) { priv->command_enqueued = true; queue_work(tpm_dev_wq, &priv->async_work); - tpm_put_ops(priv->chip); mutex_unlock(&priv->buffer_mutex); return size; } + /* atomic tpm command send and result receive. We only hold the ops + * lock during this period so that the tpm can be unregistered even if + * the char dev is held open. + */ + if (tpm_try_get_ops(priv->chip)) { + ret = -EPIPE; + goto out; + } + ret = tpm_dev_transmit(priv->chip, priv->space, priv->data_buffer, sizeof(priv->data_buffer)); tpm_put_ops(priv->chip); diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index 09fe45246b8c..994385bf37c0 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -683,13 +683,6 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, if (rc) goto init_irq_cleanup; - if (!strcmp(id->compat, "IBM,vtpm20")) { - chip->flags |= TPM_CHIP_FLAG_TPM2; - rc = tpm2_get_cc_attrs_tbl(chip); - if (rc) - goto init_irq_cleanup; - } - if (!wait_event_timeout(ibmvtpm->crq_queue.wq, ibmvtpm->rtce_buf != NULL, HZ)) { @@ -697,6 +690,13 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, goto init_irq_cleanup; } + if (!strcmp(id->compat, "IBM,vtpm20")) { + chip->flags |= TPM_CHIP_FLAG_TPM2; + rc = tpm2_get_cc_attrs_tbl(chip); + if (rc) + goto init_irq_cleanup; + } + return tpm_chip_register(chip); init_irq_cleanup: do { diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index e7df342a317d..0b214963539d 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -235,6 +235,13 @@ static int tpm_tis_pnp_init(struct pnp_dev *pnp_dev, return tpm_tis_init(&pnp_dev->dev, &tpm_info); } +/* + * There is a known bug caused by 93e1b7d42e1e ("[PATCH] tpm: add HID module + * parameter"). This commit added IFX0102 device ID, which is also used by + * tpm_infineon but ignored to add quirks to probe which driver ought to be + * used. + */ + static struct pnp_device_id tpm_pnp_tbl[] = { {"PNP0C31", 0}, /* TPM */ {"ATM1200", 0}, /* Atmel */ diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 2435216bd10a..65ab1b027949 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1085,7 +1085,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, return 0; out_err: - if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL)) + if (chip->ops->clk_enable != NULL) chip->ops->clk_enable(chip, false); tpm_tis_remove(chip); diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index d96755935529..3856f6ebcb34 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -53,8 +53,6 @@ static int tpm_tis_spi_flow_control(struct tpm_tis_spi_phy *phy, if ((phy->iobuf[3] & 0x01) == 0) { // handle SPI wait states - phy->iobuf[0] = 0; - for (i = 0; i < TPM_RETRY; i++) { spi_xfer->len = 1; spi_message_init(&m); @@ -104,6 +102,8 @@ int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, if (ret < 0) goto exit; + /* Flow control transfers are receive only */ + spi_xfer.tx_buf = NULL; ret = phy->flow_control(phy, &spi_xfer); if (ret < 0) goto exit; @@ -113,9 +113,8 @@ int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, spi_xfer.delay.value = 5; spi_xfer.delay.unit = SPI_DELAY_UNIT_USECS; - if (in) { - spi_xfer.tx_buf = NULL; - } else if (out) { + if (out) { + spi_xfer.tx_buf = phy->iobuf; spi_xfer.rx_buf = NULL; memcpy(phy->iobuf, out, transfer_len); out += transfer_len; @@ -288,6 +287,7 @@ static struct spi_driver tpm_tis_spi_driver = { .pm = &tpm_tis_pm, .of_match_table = of_match_ptr(of_tis_spi_match), .acpi_match_table = ACPI_PTR(acpi_tis_spi_match), + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, .probe = tpm_tis_spi_driver_probe, .remove = tpm_tis_spi_remove, diff --git a/drivers/clk/sifive/fu540-prci.c b/drivers/clk/sifive/fu540-prci.c index 6282ee2f361c..a8901f90a61a 100644 --- a/drivers/clk/sifive/fu540-prci.c +++ b/drivers/clk/sifive/fu540-prci.c @@ -586,7 +586,10 @@ static int sifive_fu540_prci_probe(struct platform_device *pdev) struct __prci_data *pd; int r; - pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL); + pd = devm_kzalloc(dev, + struct_size(pd, hw_clks.hws, + ARRAY_SIZE(__prci_init_clocks)), + GFP_KERNEL); if (!pd) return -ENOMEM; diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index ecf7b7db2d05..6c3e84180146 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -480,6 +480,14 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = { .set_next_event_virt = erratum_set_next_event_tval_virt, }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1418040 + { + .match_type = ate_match_local_cap_id, + .id = (void *)ARM64_WORKAROUND_1418040, + .desc = "ARM erratum 1418040", + .disable_compat_vdso = true, + }, +#endif }; typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *, @@ -566,6 +574,9 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa if (wa->read_cntvct_el0) { clocksource_counter.vdso_clock_mode = VDSO_CLOCKMODE_NONE; vdso_default = VDSO_CLOCKMODE_NONE; + } else if (wa->disable_compat_vdso && vdso_default != VDSO_CLOCKMODE_NONE) { + vdso_default = VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT; + clocksource_counter.vdso_clock_mode = vdso_default; } } diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 8e23a698ce04..e771e8b4f99f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2677,6 +2677,8 @@ static struct acpi_platform_list plat_info[] __initdata = { { } /* End */ }; +#define BITMASK_OOB (BIT(8) | BIT(18)) + static bool __init intel_pstate_platform_pwr_mgmt_exists(void) { const struct x86_cpu_id *id; @@ -2686,8 +2688,9 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) id = x86_match_cpu(intel_pstate_cpu_oob_ids); if (id) { rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr); - if (misc_pwr & (1 << 8)) { - pr_debug("Bit 8 in the MISC_PWR_MGMT MSR set\n"); + if (misc_pwr & BITMASK_OOB) { + pr_debug("Bit 8 or 18 in the MISC_PWR_MGMT MSR set\n"); + pr_debug("P states are controlled in Out of Band mode by the firmware/hardware\n"); return true; } } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index c149d9e20dfd..87197319ab06 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -186,9 +186,10 @@ int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) * be frozen safely. */ index = find_deepest_state(drv, dev, U64_MAX, 0, true); - if (index > 0) + if (index > 0) { enter_s2idle_proper(drv, dev, index); - + local_irq_enable(); + } return index; } #endif /* CONFIG_SUSPEND */ diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 01ce125f8e8d..412629601ad3 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -54,37 +54,11 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) dentry->d_name.name, ret > 0 ? name : ""); } -static const struct dentry_operations dma_buf_dentry_ops = { - .d_dname = dmabuffs_dname, -}; - -static struct vfsmount *dma_buf_mnt; - -static int dma_buf_fs_init_context(struct fs_context *fc) -{ - struct pseudo_fs_context *ctx; - - ctx = init_pseudo(fc, DMA_BUF_MAGIC); - if (!ctx) - return -ENOMEM; - ctx->dops = &dma_buf_dentry_ops; - return 0; -} - -static struct file_system_type dma_buf_fs_type = { - .name = "dmabuf", - .init_fs_context = dma_buf_fs_init_context, - .kill_sb = kill_anon_super, -}; - -static int dma_buf_release(struct inode *inode, struct file *file) +static void dma_buf_release(struct dentry *dentry) { struct dma_buf *dmabuf; - if (!is_dma_buf_file(file)) - return -EINVAL; - - dmabuf = file->private_data; + dmabuf = dentry->d_fsdata; BUG_ON(dmabuf->vmapping_counter); @@ -110,9 +84,32 @@ static int dma_buf_release(struct inode *inode, struct file *file) module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); +} + +static const struct dentry_operations dma_buf_dentry_ops = { + .d_dname = dmabuffs_dname, + .d_release = dma_buf_release, +}; + +static struct vfsmount *dma_buf_mnt; + +static int dma_buf_fs_init_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, DMA_BUF_MAGIC); + if (!ctx) + return -ENOMEM; + ctx->dops = &dma_buf_dentry_ops; return 0; } +static struct file_system_type dma_buf_fs_type = { + .name = "dmabuf", + .init_fs_context = dma_buf_fs_init_context, + .kill_sb = kill_anon_super, +}; + static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) { struct dma_buf *dmabuf; @@ -412,7 +409,6 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file) } static const struct file_operations dma_buf_fops = { - .release = dma_buf_release, .mmap = dma_buf_mmap_internal, .llseek = dma_buf_llseek, .poll = dma_buf_poll, diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ef90070a9194..6262f6370c5d 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -269,6 +269,8 @@ static int get_scrub_rate(struct mem_ctl_info *mci) if (pvt->model == 0x60) amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval); + else + amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval); } else { amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval); } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index e6fc022bc87e..3939699e62fe 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -278,3 +278,14 @@ config EFI_EARLYCON depends on SERIAL_EARLYCON && !ARM && !IA64 select FONT_SUPPORT select ARCH_USE_MEMREMAP_PROT + +config EFI_CUSTOM_SSDT_OVERLAYS + bool "Load custom ACPI SSDT overlay from an EFI variable" + depends on EFI_VARS && ACPI + default ACPI_TABLE_UPGRADE + help + Allow loading of an ACPI SSDT overlay from an EFI variable specified + by a kernel command line option. + + See Documentation/admin-guide/acpi/ssdt-overlays.rst for more + information. diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c index c697e70ca7e7..71c445d20258 100644 --- a/drivers/firmware/efi/arm-init.c +++ b/drivers/firmware/efi/arm-init.c @@ -52,9 +52,11 @@ static phys_addr_t __init efi_to_phys(unsigned long addr) } static __initdata unsigned long screen_info_table = EFI_INVALID_TABLE_ADDR; +static __initdata unsigned long cpu_state_table = EFI_INVALID_TABLE_ADDR; static const efi_config_table_type_t arch_tables[] __initconst = { {LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table}, + {LINUX_EFI_ARM_CPU_STATE_TABLE_GUID, &cpu_state_table}, {} }; @@ -62,7 +64,8 @@ static void __init init_screen_info(void) { struct screen_info *si; - if (screen_info_table != EFI_INVALID_TABLE_ADDR) { + if (IS_ENABLED(CONFIG_ARM) && + screen_info_table != EFI_INVALID_TABLE_ADDR) { si = early_memremap_ro(screen_info_table, sizeof(*si)); if (!si) { pr_err("Could not map screen_info config table\n"); @@ -116,7 +119,8 @@ static int __init uefi_init(u64 efi_system_table) goto out; } retval = efi_config_parse_tables(config_tables, systab->nr_tables, - arch_tables); + IS_ENABLED(CONFIG_ARM) ? arch_tables + : NULL); early_memunmap(config_tables, table_size); out: @@ -238,9 +242,37 @@ void __init efi_init(void) init_screen_info(); +#ifdef CONFIG_ARM /* ARM does not permit early mappings to persist across paging_init() */ - if (IS_ENABLED(CONFIG_ARM)) - efi_memmap_unmap(); + efi_memmap_unmap(); + + if (cpu_state_table != EFI_INVALID_TABLE_ADDR) { + struct efi_arm_entry_state *state; + bool dump_state = true; + + state = early_memremap_ro(cpu_state_table, + sizeof(struct efi_arm_entry_state)); + if (state == NULL) { + pr_warn("Unable to map CPU entry state table.\n"); + return; + } + + if ((state->sctlr_before_ebs & 1) == 0) + pr_warn(FW_BUG "EFI stub was entered with MMU and Dcache disabled, please fix your firmware!\n"); + else if ((state->sctlr_after_ebs & 1) == 0) + pr_warn(FW_BUG "ExitBootServices() returned with MMU and Dcache disabled, please fix your firmware!\n"); + else + dump_state = false; + + if (dump_state || efi_enabled(EFI_DBG)) { + pr_info("CPSR at EFI stub entry : 0x%08x\n", state->cpsr_before_ebs); + pr_info("SCTLR at EFI stub entry : 0x%08x\n", state->sctlr_before_ebs); + pr_info("CPSR after ExitBootServices() : 0x%08x\n", state->cpsr_after_ebs); + pr_info("SCTLR after ExitBootServices(): 0x%08x\n", state->sctlr_after_ebs); + } + early_memunmap(state, sizeof(struct efi_arm_entry_state)); + } +#endif } static bool efifb_overlaps_pci_range(const struct of_pci_range *range) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 7f1657b6c30d..5114cae4ec97 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -189,7 +189,7 @@ static void generic_ops_unregister(void) efivars_unregister(&generic_efivars); } -#if IS_ENABLED(CONFIG_ACPI) +#ifdef CONFIG_EFI_CUSTOM_SSDT_OVERLAYS #define EFIVAR_SSDT_NAME_MAX 16 static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata; static int __init efivar_ssdt_setup(char *str) @@ -622,7 +622,8 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, rsv = (void *)(p + prsv % PAGE_SIZE); /* reserve the entry itself */ - memblock_reserve(prsv, EFI_MEMRESERVE_SIZE(rsv->size)); + memblock_reserve(prsv, + struct_size(rsv, entry, rsv->size)); for (i = 0; i < atomic_read(&rsv->count); i++) { memblock_reserve(rsv->entry[i].base, diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c index e3d692696583..d5915272141f 100644 --- a/drivers/firmware/efi/esrt.c +++ b/drivers/firmware/efi/esrt.c @@ -181,7 +181,7 @@ static int esre_create_sysfs_entry(void *esre, int entry_num) rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL, "entry%d", entry_num); if (rc) { - kfree(entry); + kobject_put(&entry->kobj); return rc; } } diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 75daaf20374e..4cce372edaf4 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -6,7 +6,8 @@ # enabled, even if doing so doesn't break the build. # cflags-$(CONFIG_X86_32) := -march=i386 -cflags-$(CONFIG_X86_64) := -mcmodel=small +cflags-$(CONFIG_X86_64) := -mcmodel=small \ + $(call cc-option,-maccumulate-outgoing-args) cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \ -fPIC -fno-strict-aliasing -mno-red-zone \ -mno-mmx -mno-sse -fshort-wchar \ diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c index 40243f524556..d08e5d55838c 100644 --- a/drivers/firmware/efi/libstub/arm32-stub.c +++ b/drivers/firmware/efi/libstub/arm32-stub.c @@ -7,10 +7,49 @@ #include "efistub.h" +static efi_guid_t cpu_state_guid = LINUX_EFI_ARM_CPU_STATE_TABLE_GUID; + +struct efi_arm_entry_state *efi_entry_state; + +static void get_cpu_state(u32 *cpsr, u32 *sctlr) +{ + asm("mrs %0, cpsr" : "=r"(*cpsr)); + if ((*cpsr & MODE_MASK) == HYP_MODE) + asm("mrc p15, 4, %0, c1, c0, 0" : "=r"(*sctlr)); + else + asm("mrc p15, 0, %0, c1, c0, 0" : "=r"(*sctlr)); +} + efi_status_t check_platform_features(void) { + efi_status_t status; + u32 cpsr, sctlr; int block; + get_cpu_state(&cpsr, &sctlr); + + efi_info("Entering in %s mode with MMU %sabled\n", + ((cpsr & MODE_MASK) == HYP_MODE) ? "HYP" : "SVC", + (sctlr & 1) ? "en" : "dis"); + + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + sizeof(*efi_entry_state), + (void **)&efi_entry_state); + if (status != EFI_SUCCESS) { + efi_err("allocate_pool() failed\n"); + return status; + } + + efi_entry_state->cpsr_before_ebs = cpsr; + efi_entry_state->sctlr_before_ebs = sctlr; + + status = efi_bs_call(install_configuration_table, &cpu_state_guid, + efi_entry_state); + if (status != EFI_SUCCESS) { + efi_err("install_configuration_table() failed\n"); + goto free_state; + } + /* non-LPAE kernels can run anywhere */ if (!IS_ENABLED(CONFIG_ARM_LPAE)) return EFI_SUCCESS; @@ -19,9 +58,22 @@ efi_status_t check_platform_features(void) block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0); if (block < 5) { efi_err("This LPAE kernel is not supported by your CPU\n"); - return EFI_UNSUPPORTED; + status = EFI_UNSUPPORTED; + goto drop_table; } return EFI_SUCCESS; + +drop_table: + efi_bs_call(install_configuration_table, &cpu_state_guid, NULL); +free_state: + efi_bs_call(free_pool, efi_entry_state); + return status; +} + +void efi_handle_post_ebs_state(void) +{ + get_cpu_state(&efi_entry_state->cpsr_after_ebs, + &efi_entry_state->sctlr_after_ebs); } static efi_guid_t screen_info_guid = LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID; diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 89f075275300..d40fd68c6bb2 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -32,6 +32,10 @@ bool __pure __efi_soft_reserve_enabled(void) return !efi_nosoftreserve; } +/** + * efi_char16_puts() - Write a UCS-2 encoded string to the console + * @str: UCS-2 encoded string + */ void efi_char16_puts(efi_char16_t *str) { efi_call_proto(efi_table_attr(efi_system_table, con_out), @@ -83,6 +87,10 @@ u32 utf8_to_utf32(const u8 **s8) return c32; } +/** + * efi_puts() - Write a UTF-8 encoded string to the console + * @str: UTF-8 encoded string + */ void efi_puts(const char *str) { efi_char16_t buf[128]; @@ -113,6 +121,16 @@ void efi_puts(const char *str) } } +/** + * efi_printk() - Print a kernel message + * @fmt: format string + * + * The first letter of the format string is used to determine the logging level + * of the message. If the level is less then the current EFI logging level, the + * message is suppressed. The message will be truncated to 255 bytes. + * + * Return: number of printed characters + */ int efi_printk(const char *fmt, ...) { char printf_buf[256]; @@ -154,13 +172,18 @@ int efi_printk(const char *fmt, ...) return printed; } -/* - * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi= +/** + * efi_parse_options() - Parse EFI command line options + * @cmdline: kernel command line + * + * Parse the ASCII string @cmdline for EFI options, denoted by the efi= * option, e.g. efi=nochunk. * * It should be noted that efi= is parsed in two very different * environments, first in the early boot environment of the EFI boot * stub, and subsequently during the kernel boot. + * + * Return: status code */ efi_status_t efi_parse_options(char const *cmdline) { @@ -286,13 +309,21 @@ char *efi_convert_cmdline(efi_loaded_image_t *image, int *cmd_line_len) return (char *)cmdline_addr; } -/* +/** + * efi_exit_boot_services() - Exit boot services + * @handle: handle of the exiting image + * @map: pointer to receive the memory map + * @priv: argument to be passed to @priv_func + * @priv_func: function to process the memory map before exiting boot services + * * Handle calling ExitBootServices according to the requirements set out by the * spec. Obtains the current memory map, and returns that info after calling * ExitBootServices. The client must specify a function to perform any * processing of the memory map data prior to ExitBootServices. A client * specific structure may be passed to the function via priv. The client * function may be called multiple times. + * + * Return: status code */ efi_status_t efi_exit_boot_services(void *handle, struct efi_boot_memmap *map, @@ -361,6 +392,11 @@ fail: return status; } +/** + * get_efi_config_table() - retrieve UEFI configuration table + * @guid: GUID of the configuration table to be retrieved + * Return: pointer to the configuration table or NULL + */ void *get_efi_config_table(efi_guid_t guid) { unsigned long tables = efi_table_attr(efi_system_table, tables); @@ -408,17 +444,18 @@ static const struct { }; /** - * efi_load_initrd_dev_path - load the initrd from the Linux initrd device path + * efi_load_initrd_dev_path() - load the initrd from the Linux initrd device path * @load_addr: pointer to store the address where the initrd was loaded * @load_size: pointer to store the size of the loaded initrd * @max: upper limit for the initrd memory allocation - * @return: %EFI_SUCCESS if the initrd was loaded successfully, in which - * case @load_addr and @load_size are assigned accordingly - * %EFI_NOT_FOUND if no LoadFile2 protocol exists on the initrd - * device path - * %EFI_INVALID_PARAMETER if load_addr == NULL or load_size == NULL - * %EFI_OUT_OF_RESOURCES if memory allocation failed - * %EFI_LOAD_ERROR in all other cases + * + * Return: + * * %EFI_SUCCESS if the initrd was loaded successfully, in which + * case @load_addr and @load_size are assigned accordingly + * * %EFI_NOT_FOUND if no LoadFile2 protocol exists on the initrd device path + * * %EFI_INVALID_PARAMETER if load_addr == NULL or load_size == NULL + * * %EFI_OUT_OF_RESOURCES if memory allocation failed + * * %EFI_LOAD_ERROR in all other cases */ static efi_status_t efi_load_initrd_dev_path(unsigned long *load_addr, @@ -481,6 +518,16 @@ efi_status_t efi_load_initrd_cmdline(efi_loaded_image_t *image, load_addr, load_size); } +/** + * efi_load_initrd() - Load initial RAM disk + * @image: EFI loaded image protocol + * @load_addr: pointer to loaded initrd + * @load_size: size of loaded initrd + * @soft_limit: preferred size of allocated memory for loading the initrd + * @hard_limit: minimum size of allocated memory + * + * Return: status code + */ efi_status_t efi_load_initrd(efi_loaded_image_t *image, unsigned long *load_addr, unsigned long *load_size, @@ -505,6 +552,15 @@ efi_status_t efi_load_initrd(efi_loaded_image_t *image, return status; } +/** + * efi_wait_for_key() - Wait for key stroke + * @usec: number of microseconds to wait for key stroke + * @key: key entered + * + * Wait for up to @usec microseconds for a key stroke. + * + * Return: status code, EFI_SUCCESS if key received + */ efi_status_t efi_wait_for_key(unsigned long usec, efi_input_key_t *key) { efi_event_t events[2], timer; diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c index e97370bdfdb0..3318ec3f8e5b 100644 --- a/drivers/firmware/efi/libstub/efi-stub.c +++ b/drivers/firmware/efi/libstub/efi-stub.c @@ -329,6 +329,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, if (status != EFI_SUCCESS) goto fail_free_initrd; + if (IS_ENABLED(CONFIG_ARM)) + efi_handle_post_ebs_state(); + efi_enter_kernel(image_addr, fdt_addr, fdt_totalsize((void *)fdt_addr)); /* not reached */ diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index bcd8c0a785f0..2c9d42264c29 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -157,8 +157,14 @@ typedef void (__efiapi *efi_event_notify_t)(efi_event_t, void *); #define EFI_EVT_NOTIFY_WAIT 0x00000100U #define EFI_EVT_NOTIFY_SIGNAL 0x00000200U -/* - * boottime->wait_for_event takes an array of events as input. +/** + * efi_set_event_at() - add event to events array + * + * @events: array of UEFI events + * @ids: index where to put the event in the array + * @event: event to add to the aray + * + * boottime->wait_for_event() takes an array of events as input. * Provide a helper to set it up correctly for mixed mode. */ static inline @@ -771,4 +777,6 @@ efi_status_t efi_load_initrd(efi_loaded_image_t *image, unsigned long soft_limit, unsigned long hard_limit); +void efi_handle_post_ebs_state(void); + #endif diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c index 2005e33b33d5..630caa6b1f4c 100644 --- a/drivers/firmware/efi/libstub/file.c +++ b/drivers/firmware/efi/libstub/file.c @@ -102,12 +102,20 @@ static int find_file_option(const efi_char16_t *cmdline, int cmdline_len, if (!found) return 0; + /* Skip any leading slashes */ + while (cmdline[i] == L'/' || cmdline[i] == L'\\') + i++; + while (--result_len > 0 && i < cmdline_len) { - if (cmdline[i] == L'\0' || - cmdline[i] == L'\n' || - cmdline[i] == L' ') + efi_char16_t c = cmdline[i++]; + + if (c == L'\0' || c == L'\n' || c == L' ') break; - *result++ = cmdline[i++]; + else if (c == L'/') + /* Replace UNIX dir separators with EFI standard ones */ + *result++ = L'\\'; + else + *result++ = c; } *result = L'\0'; return i; diff --git a/drivers/firmware/efi/libstub/skip_spaces.c b/drivers/firmware/efi/libstub/skip_spaces.c index a700b3c7f7d0..159fb4e456c6 100644 --- a/drivers/firmware/efi/libstub/skip_spaces.c +++ b/drivers/firmware/efi/libstub/skip_spaces.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/ctype.h> +#include <linux/string.h> #include <linux/types.h> char *skip_spaces(const char *str) diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c index 873841af8d57..3d6ba425dbb9 100644 --- a/drivers/firmware/psci/psci_checker.c +++ b/drivers/firmware/psci/psci_checker.c @@ -157,8 +157,10 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups) cpu_groups = kcalloc(nb_available_cpus, sizeof(cpu_groups), GFP_KERNEL); - if (!cpu_groups) + if (!cpu_groups) { + free_cpumask_var(tmp); return -ENOMEM; + } cpumask_copy(tmp, cpu_online_mask); @@ -167,6 +169,7 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups) topology_core_cpumask(cpumask_any(tmp)); if (!alloc_cpumask_var(&cpu_groups[num_groups], GFP_KERNEL)) { + free_cpumask_var(tmp); free_cpu_groups(num_groups, &cpu_groups); return -ENOMEM; } @@ -196,13 +199,12 @@ static int hotplug_tests(void) if (!page_buf) goto out_free_cpu_groups; - err = 0; /* * Of course the last CPU cannot be powered down and cpu_down() should * refuse doing that. */ pr_info("Trying to turn off and on again all CPUs\n"); - err += down_and_up_cpus(cpu_online_mask, offlined_cpus); + err = down_and_up_cpus(cpu_online_mask, offlined_cpus); /* * Take down CPUs by cpu group this time. When the last CPU is turned diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c index ef8098856a47..625c8fdceabf 100644 --- a/drivers/firmware/raspberrypi.c +++ b/drivers/firmware/raspberrypi.c @@ -181,6 +181,7 @@ EXPORT_SYMBOL_GPL(rpi_firmware_property); static void rpi_firmware_print_firmware_revision(struct rpi_firmware *fw) { + time64_t date_and_time; u32 packet; int ret = rpi_firmware_property(fw, RPI_FIRMWARE_GET_FIRMWARE_REVISION, @@ -189,7 +190,9 @@ rpi_firmware_print_firmware_revision(struct rpi_firmware *fw) if (ret) return; - dev_info(fw->cl.dev, "Attached to firmware from %ptT\n", &packet); + /* This is not compatible with y2038 */ + date_and_time = packet; + dev_info(fw->cl.dev, "Attached to firmware from %ptT\n", &date_and_time); } static void diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index b2408a710662..7cd5a29fc437 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -208,7 +208,7 @@ config FPGA_DFL_PCI config FPGA_MGR_ZYNQMP_FPGA tristate "Xilinx ZynqMP FPGA" - depends on ARCH_ZYNQMP || COMPILE_TEST + depends on ZYNQMP_FIRMWARE || (!ZYNQMP_FIRMWARE && COMPILE_TEST) help FPGA manager driver support for Xilinx ZynqMP FPGAs. This driver uses the processor configuration port(PCAP) diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index 5640efe5e750..5bda38e0780f 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -64,6 +64,7 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset) ret = pm_runtime_get_sync(chip->parent); if (ret < 0) { dev_err(chip->parent, "Failed to resume: %d\n", ret); + pm_runtime_put_autosuspend(chip->parent); return ret; } @@ -72,12 +73,15 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset) if (ret < 0) { dev_err(chip->parent, "Failed to drop cache: %d\n", ret); + pm_runtime_put_autosuspend(chip->parent); return ret; } ret = regmap_read(arizona->regmap, reg, &val); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_autosuspend(chip->parent); return ret; + } pm_runtime_mark_last_busy(chip->parent); pm_runtime_put_autosuspend(chip->parent); @@ -106,6 +110,7 @@ static int arizona_gpio_direction_out(struct gpio_chip *chip, ret = pm_runtime_get_sync(chip->parent); if (ret < 0) { dev_err(chip->parent, "Failed to resume: %d\n", ret); + pm_runtime_put(chip->parent); return ret; } } diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 1fca8dd7824f..a3b9bdedbe44 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -107,6 +107,84 @@ static const struct i2c_device_id pca953x_id[] = { }; MODULE_DEVICE_TABLE(i2c, pca953x_id); +#ifdef CONFIG_GPIO_PCA953X_IRQ + +#include <linux/dmi.h> +#include <linux/gpio.h> +#include <linux/list.h> + +static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = { + { + /* + * On Intel Galileo Gen 2 board the IRQ pin of one of + * the I²C GPIO expanders, which has GpioInt() resource, + * is provided as an absolute number instead of being + * relative. Since first controller (gpio-sch.c) and + * second (gpio-dwapb.c) are at the fixed bases, we may + * safely refer to the number in the global space to get + * an IRQ out of it. + */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_NAME, "GalileoGen2"), + }, + }, + {} +}; + +#ifdef CONFIG_ACPI +static int pca953x_acpi_get_pin(struct acpi_resource *ares, void *data) +{ + struct acpi_resource_gpio *agpio; + int *pin = data; + + if (acpi_gpio_get_irq_resource(ares, &agpio)) + *pin = agpio->pin_table[0]; + return 1; +} + +static int pca953x_acpi_find_pin(struct device *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(dev); + int pin = -ENOENT, ret; + LIST_HEAD(r); + + ret = acpi_dev_get_resources(adev, &r, pca953x_acpi_get_pin, &pin); + acpi_dev_free_resource_list(&r); + if (ret < 0) + return ret; + + return pin; +} +#else +static inline int pca953x_acpi_find_pin(struct device *dev) { return -ENXIO; } +#endif + +static int pca953x_acpi_get_irq(struct device *dev) +{ + int pin, ret; + + pin = pca953x_acpi_find_pin(dev); + if (pin < 0) + return pin; + + dev_info(dev, "Applying ACPI interrupt quirk (GPIO %d)\n", pin); + + if (!gpio_is_valid(pin)) + return -EINVAL; + + ret = gpio_request(pin, "pca953x interrupt"); + if (ret) + return ret; + + ret = gpio_to_irq(pin); + + /* When pin is used as an IRQ, no need to keep it requested */ + gpio_free(pin); + + return ret; +} +#endif + static const struct acpi_device_id pca953x_acpi_ids[] = { { "INT3491", 16 | PCA953X_TYPE | PCA_LATCH_INT, }, { } @@ -322,6 +400,7 @@ static const struct regmap_config pca953x_ai_i2c_regmap = { .writeable_reg = pca953x_writeable_register, .volatile_reg = pca953x_volatile_register, + .disable_locking = true, .cache_type = REGCACHE_RBTREE, .max_register = 0x7f, }; @@ -623,8 +702,6 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d) DECLARE_BITMAP(reg_direction, MAX_LINE); int level; - pca953x_read_regs(chip, chip->regs->direction, reg_direction); - if (chip->driver_data & PCA_PCAL) { /* Enable latch on interrupt-enabled inputs */ pca953x_write_regs(chip, PCAL953X_IN_LATCH, chip->irq_mask); @@ -635,7 +712,11 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d) pca953x_write_regs(chip, PCAL953X_INT_MASK, irq_mask); } + /* Switch direction to input if needed */ + pca953x_read_regs(chip, chip->regs->direction, reg_direction); + bitmap_or(irq_mask, chip->irq_trig_fall, chip->irq_trig_raise, gc->ngpio); + bitmap_complement(reg_direction, reg_direction, gc->ngpio); bitmap_and(irq_mask, irq_mask, reg_direction, gc->ngpio); /* Look for any newly setup interrupt */ @@ -734,14 +815,16 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid) struct gpio_chip *gc = &chip->gpio_chip; DECLARE_BITMAP(pending, MAX_LINE); int level; + bool ret; - if (!pca953x_irq_pending(chip, pending)) - return IRQ_NONE; + mutex_lock(&chip->i2c_lock); + ret = pca953x_irq_pending(chip, pending); + mutex_unlock(&chip->i2c_lock); for_each_set_bit(level, pending, gc->ngpio) handle_nested_irq(irq_find_mapping(gc->irq.domain, level)); - return IRQ_HANDLED; + return IRQ_RETVAL(ret); } static int pca953x_irq_setup(struct pca953x_chip *chip, int irq_base) @@ -752,6 +835,12 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, int irq_base) DECLARE_BITMAP(irq_stat, MAX_LINE); int ret; + if (dmi_first_match(pca953x_dmi_acpi_irq_info)) { + ret = pca953x_acpi_get_irq(&client->dev); + if (ret > 0) + client->irq = ret; + } + if (!client->irq) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 58f9d8c3a17a..44f927641b89 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -204,6 +204,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, (mode_info->atom_context->bios + data_offset); switch (crev) { case 11: + case 12: mem_channel_number = igp_info->v11.umachannelnumber; /* channel width is 64 */ if (vram_width) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 47207188c569..4fb4c3b69687 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -37,7 +37,8 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) memset(&ti, 0, sizeof(struct amdgpu_task_info)); - if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { + if (amdgpu_gpu_recovery && + amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", s_job->sched->name); return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 16596a9ccabe..02e6f8c4dde0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -2784,7 +2784,7 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000); + return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev, @@ -2819,7 +2819,7 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000); + return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 7301fdcfb8bc..ef3269c43d4f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -372,6 +372,52 @@ static int psp_tmr_load(struct psp_context *psp) return ret; } +static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp, + struct psp_gfx_cmd_resp *cmd) +{ + if (amdgpu_sriov_vf(psp->adev)) + cmd->cmd_id = GFX_CMD_ID_DESTROY_VMR; + else + cmd->cmd_id = GFX_CMD_ID_DESTROY_TMR; +} + +static int psp_tmr_unload(struct psp_context *psp) +{ + int ret; + struct psp_gfx_cmd_resp *cmd; + + cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + psp_prep_tmr_unload_cmd_buf(psp, cmd); + DRM_INFO("free PSP TMR buffer\n"); + + ret = psp_cmd_submit_buf(psp, NULL, cmd, + psp->fence_buf_mc_addr); + + kfree(cmd); + + return ret; +} + +static int psp_tmr_terminate(struct psp_context *psp) +{ + int ret; + void *tmr_buf; + void **pptr; + + ret = psp_tmr_unload(psp); + if (ret) + return ret; + + /* free TMR memory buffer */ + pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; + amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr); + + return 0; +} + static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd, uint64_t asd_mc, uint32_t size) { @@ -1779,8 +1825,6 @@ static int psp_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct psp_context *psp = &adev->psp; - void *tmr_buf; - void **pptr; if (psp->adev->psp.ta_fw) { psp_ras_terminate(psp); @@ -1790,10 +1834,9 @@ static int psp_hw_fini(void *handle) psp_asd_unload(psp); + psp_tmr_terminate(psp); psp_ring_destroy(psp, PSP_RING_TYPE__KM); - pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL; - amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr); amdgpu_bo_free_kernel(&psp->fw_pri_bo, &psp->fw_pri_mc_addr, &psp->fw_pri_buf); amdgpu_bo_free_kernel(&psp->fence_buf_bo, @@ -1840,6 +1883,18 @@ static int psp_suspend(void *handle) } } + ret = psp_asd_unload(psp); + if (ret) { + DRM_ERROR("Failed to unload asd\n"); + return ret; + } + + ret = psp_tmr_terminate(psp); + if (ret) { + DRM_ERROR("Falied to terminate tmr\n"); + return ret; + } + ret = psp_ring_stop(psp, PSP_RING_TYPE__KM); if (ret) { DRM_ERROR("PSP ring stop failed\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index b544baf306f2..5d71c23e2640 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1298,8 +1298,12 @@ static int sdma_v5_0_sw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - for (i = 0; i < adev->sdma.num_instances; i++) + for (i = 0; i < adev->sdma.num_instances; i++) { + if (adev->sdma.instance[i].fw != NULL) + release_firmware(adev->sdma.instance[i].fw); + amdgpu_ring_fini(&adev->sdma.instance[i].ring); + } return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index d27221ddcdeb..0e0c42e9f6a3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -428,6 +428,7 @@ struct kfd_process *kfd_create_process(struct file *filep) (int)process->lead_thread->pid); if (ret) { pr_warn("Creating procfs pid directory failed"); + kobject_put(process->kobj); goto out; } 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 7ced9f87be97..db5e0bb0d935 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1358,7 +1358,7 @@ static int dm_late_init(void *handle) struct dmcu *dmcu = NULL; bool ret; - if (!adev->dm.fw_dmcu) + if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw) return detect_mst_link_for_all_connectors(adev->ddev); dmcu = adev->dm.dc->res_pool->dmcu; @@ -5024,7 +5024,8 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector, struct drm_connector *connector = &aconnector->base; struct amdgpu_device *adev = connector->dev->dev_private; struct dc_stream_state *stream; - int requested_bpc = connector->state ? connector->state->max_requested_bpc : 8; + const struct drm_connector_state *drm_state = dm_state ? &dm_state->base : NULL; + int requested_bpc = drm_state ? drm_state->max_requested_bpc : 8; enum dc_status dc_result = DC_OK; do { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 076af267b488..1d692f4f42f3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1058,7 +1058,6 @@ static const struct { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, {"test_pattern", &dp_phy_test_pattern_fops}, - {"output_bpc", &output_bpc_fops}, {"vrr_range", &vrr_range_fops}, #ifdef CONFIG_DRM_AMD_DC_HDCP {"hdcp_sink_capability", &hdcp_sink_capability_fops}, @@ -1142,6 +1141,9 @@ void connector_debugfs_init(struct amdgpu_dm_connector *connector) debugfs_create_file_unsafe("force_yuv420_output", 0644, dir, connector, &force_yuv420_output_fops); + debugfs_create_file("output_bpc", 0644, dir, connector, + &output_bpc_fops); + connector->debugfs_dpcd_address = 0; connector->debugfs_dpcd_size = 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index dcf84a61de37..949d10ef8304 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -510,8 +510,10 @@ static ssize_t srm_data_read(struct file *filp, struct kobject *kobj, struct bin srm = psp_get_srm(work->hdcp.config.psp.handle, &srm_version, &srm_size); - if (!srm) - return -EINVAL; + if (!srm) { + ret = -EINVAL; + goto ret; + } if (pos >= srm_size) ret = 0; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 6f93a6ca4cf0..d016f50e187c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2538,10 +2538,12 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_stream_update_to_stream(dc, context, stream, stream_update); - if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { - DC_ERROR("Mode validation failed for stream update!\n"); - dc_release_state(context); - return; + if (update_type > UPDATE_TYPE_FAST) { + if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { + DC_ERROR("Mode validation failed for stream update!\n"); + dc_release_state(context); + return; + } } commit_planes_for_stream( diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c index 2fb97554134f..c2e0fbbccf56 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c @@ -522,9 +522,11 @@ static int vega20_smu_init(struct pp_hwmgr *hwmgr) priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].version = 0x01; priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size = sizeof(DpmActivityMonitorCoeffInt_t); - ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c); - if (ret) - goto err4; + if (adev->psp.ras.ras) { + ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c); + if (ret) + goto err4; + } return 0; @@ -560,7 +562,8 @@ static int vega20_smu_fini(struct pp_hwmgr *hwmgr) (struct vega20_smumgr *)(hwmgr->smu_backend); struct amdgpu_device *adev = hwmgr->adev; - smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c); + if (adev->psp.ras.ras) + smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c); if (priv) { amdgpu_bo_free_kernel(&priv->smu_tables.entry[TABLE_PPTABLE].handle, diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 170aa7689110..5609e164805f 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -227,18 +227,9 @@ int drm_fb_helper_debug_leave(struct fb_info *info) } EXPORT_SYMBOL(drm_fb_helper_debug_leave); -/** - * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration - * @fb_helper: driver-allocated fbdev helper, can be NULL - * - * This should be called from driver's drm &drm_driver.lastclose callback - * when implementing an fbcon on top of kms using this helper. This ensures that - * the user isn't greeted with a black screen when e.g. X dies. - * - * RETURNS: - * Zero if everything went ok, negative error code otherwise. - */ -int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) +static int +__drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, + bool force) { bool do_delayed; int ret; @@ -250,7 +241,16 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) return 0; mutex_lock(&fb_helper->lock); - ret = drm_client_modeset_commit(&fb_helper->client); + if (force) { + /* + * Yes this is the _locked version which expects the master lock + * to be held. But for forced restores we're intentionally + * racing here, see drm_fb_helper_set_par(). + */ + ret = drm_client_modeset_commit_locked(&fb_helper->client); + } else { + ret = drm_client_modeset_commit(&fb_helper->client); + } do_delayed = fb_helper->delayed_hotplug; if (do_delayed) @@ -262,6 +262,22 @@ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) return ret; } + +/** + * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration + * @fb_helper: driver-allocated fbdev helper, can be NULL + * + * This should be called from driver's drm &drm_driver.lastclose callback + * when implementing an fbcon on top of kms using this helper. This ensures that + * the user isn't greeted with a black screen when e.g. X dies. + * + * RETURNS: + * Zero if everything went ok, negative error code otherwise. + */ +int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) +{ + return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false); +} EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); #ifdef CONFIG_MAGIC_SYSRQ @@ -1318,6 +1334,7 @@ int drm_fb_helper_set_par(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct fb_var_screeninfo *var = &info->var; + bool force; if (oops_in_progress) return -EBUSY; @@ -1327,7 +1344,25 @@ int drm_fb_helper_set_par(struct fb_info *info) return -EINVAL; } - drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); + /* + * Normally we want to make sure that a kms master takes precedence over + * fbdev, to avoid fbdev flickering and occasionally stealing the + * display status. But Xorg first sets the vt back to text mode using + * the KDSET IOCTL with KD_TEXT, and only after that drops the master + * status when exiting. + * + * In the past this was caught by drm_fb_helper_lastclose(), but on + * modern systems where logind always keeps a drm fd open to orchestrate + * the vt switching, this doesn't work. + * + * To not break the userspace ABI we have this special case here, which + * is only used for the above case. Everything else uses the normal + * commit function, which ensures that we never steal the display from + * an active drm master. + */ + force = var->activate & FB_ACTIVATE_KD_TEXT; + + __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force); return 0; } diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index ffd95bfeaa94..d00ea384dcbf 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -30,12 +30,6 @@ struct drm_dmi_panel_orientation_data { int orientation; }; -static const struct drm_dmi_panel_orientation_data acer_s1003 = { - .width = 800, - .height = 1280, - .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, -}; - static const struct drm_dmi_panel_orientation_data asus_t100ha = { .width = 800, .height = 1280, @@ -114,13 +108,19 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, - .driver_data = (void *)&acer_s1003, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Asus T100HA */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"), }, .driver_data = (void *)&asus_t100ha, + }, { /* Asus T101HA */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* GPD MicroPC (generic strings, also match on bios date) */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"), diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index 619f81435c1b..58b89ec11b0e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -61,7 +61,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; - int ret; + int ret = 0; if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) { DRM_DEV_ERROR(subdrv_dev, "Device %s lacks support for IOMMU\n", @@ -92,7 +92,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, if (ret) clear_dma_max_seg_size(subdrv_dev); - return 0; + return ret; } /* diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index fcee33a43aca..03be31427181 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1498,7 +1498,6 @@ static int g2d_probe(struct platform_device *pdev) g2d->irq = platform_get_irq(pdev, 0); if (g2d->irq < 0) { - dev_err(dev, "failed to get irq\n"); ret = g2d->irq; goto err_put_clk; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index a86abc173605..3821ea76a703 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -269,8 +269,10 @@ static void mic_pre_enable(struct drm_bridge *bridge) goto unlock; ret = pm_runtime_get_sync(mic->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(mic->dev); goto unlock; + } mic_set_path(mic, 1); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index a6fd0c29e5b8..544b9993c99e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -307,8 +307,6 @@ static int hibmc_load(struct drm_device *dev) /* reset all the states of crtc/plane/encoder/connector */ drm_mode_config_reset(dev); - drm_fbdev_generic_setup(dev, dev->mode_config.preferred_depth); - return 0; err: @@ -355,6 +353,9 @@ static int hibmc_pci_probe(struct pci_dev *pdev, ret); goto err_unload; } + + drm_fbdev_generic_setup(dev, dev->mode_config.preferred_depth); + return 0; err_unload: diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 9ea1a397d1b5..26996e1839e2 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -3822,6 +3822,17 @@ skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state, return true; } +unsigned int +intel_plane_fence_y_offset(const struct intel_plane_state *plane_state) +{ + int x = 0, y = 0; + + intel_plane_adjust_aligned_offset(&x, &y, plane_state, 0, + plane_state->color_plane[0].offset, 0); + + return y; +} + static int skl_check_main_surface(struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev); diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index efb4da205ea2..3a06f72c9859 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -608,6 +608,7 @@ unsigned int i9xx_plane_max_stride(struct intel_plane *plane, u32 pixel_format, u64 modifier, unsigned int rotation); int bdw_get_pipemisc_bpp(struct intel_crtc *crtc); +unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state); struct intel_display_error_state * intel_display_capture_error_state(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 1c26673acb2d..a65d9d8b79a7 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -48,19 +48,6 @@ #include "intel_frontbuffer.h" /* - * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the - * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's - * origin so the x and y offsets can actually fit the registers. As a - * consequence, the fence doesn't really start exactly at the display plane - * address we program because it starts at the real start of the buffer, so we - * have to take this into consideration here. - */ -static unsigned int get_crtc_fence_y_offset(struct intel_fbc *fbc) -{ - return fbc->state_cache.plane.y - fbc->state_cache.plane.adjusted_y; -} - -/* * For SKL+, the plane source size used by the hardware is based on the value we * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value * we wrote to PIPESRC. @@ -141,7 +128,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv) fbc_ctl2 |= FBC_CTL_CPU_FENCE; intel_de_write(dev_priv, FBC_CONTROL2, fbc_ctl2); intel_de_write(dev_priv, FBC_FENCE_OFF, - params->crtc.fence_y_offset); + params->fence_y_offset); } /* enable it... */ @@ -175,7 +162,7 @@ static void g4x_fbc_activate(struct drm_i915_private *dev_priv) if (params->fence_id >= 0) { dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id; intel_de_write(dev_priv, DPFC_FENCE_YOFF, - params->crtc.fence_y_offset); + params->fence_y_offset); } else { intel_de_write(dev_priv, DPFC_FENCE_YOFF, 0); } @@ -243,7 +230,7 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv) intel_de_write(dev_priv, SNB_DPFC_CTL_SA, SNB_CPU_FENCE_ENABLE | params->fence_id); intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, - params->crtc.fence_y_offset); + params->fence_y_offset); } } else { if (IS_GEN(dev_priv, 6)) { @@ -253,7 +240,7 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv) } intel_de_write(dev_priv, ILK_DPFC_FENCE_YOFF, - params->crtc.fence_y_offset); + params->fence_y_offset); /* enable it... */ intel_de_write(dev_priv, ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN); @@ -320,7 +307,7 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv) intel_de_write(dev_priv, SNB_DPFC_CTL_SA, SNB_CPU_FENCE_ENABLE | params->fence_id); intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, - params->crtc.fence_y_offset); + params->fence_y_offset); } else if (dev_priv->ggtt.num_fences) { intel_de_write(dev_priv, SNB_DPFC_CTL_SA, 0); intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, 0); @@ -631,8 +618,8 @@ static bool rotation_is_valid(struct drm_i915_private *dev_priv, /* * For some reason, the hardware tracking starts looking at whatever we * programmed as the display plane base address register. It does not look at - * the X and Y offset registers. That's why we look at the crtc->adjusted{x,y} - * variables instead of just looking at the pipe/plane size. + * the X and Y offset registers. That's why we include the src x/y offsets + * instead of just looking at the plane size. */ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) { @@ -705,7 +692,6 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc, cache->plane.src_h = drm_rect_height(&plane_state->uapi.src) >> 16; cache->plane.adjusted_x = plane_state->color_plane[0].x; cache->plane.adjusted_y = plane_state->color_plane[0].y; - cache->plane.y = plane_state->uapi.src.y1 >> 16; cache->plane.pixel_blend_mode = plane_state->hw.pixel_blend_mode; @@ -713,6 +699,8 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc, cache->fb.stride = fb->pitches[0]; cache->fb.modifier = fb->modifier; + cache->fence_y_offset = intel_plane_fence_y_offset(plane_state); + drm_WARN_ON(&dev_priv->drm, plane_state->flags & PLANE_HAS_FENCE && !plane_state->vma->fence); @@ -883,10 +871,10 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc, memset(params, 0, sizeof(*params)); params->fence_id = cache->fence_id; + params->fence_y_offset = cache->fence_y_offset; params->crtc.pipe = crtc->pipe; params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane; - params->crtc.fence_y_offset = get_crtc_fence_y_offset(fbc); params->fb.format = cache->fb.format; params->fb.stride = cache->fb.stride; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index e4aece20bc80..52db2bde44a3 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -204,25 +204,25 @@ static int __ring_active(struct intel_ring *ring) { int err; - err = i915_active_acquire(&ring->vma->active); + err = intel_ring_pin(ring); if (err) return err; - err = intel_ring_pin(ring); + err = i915_active_acquire(&ring->vma->active); if (err) - goto err_active; + goto err_pin; return 0; -err_active: - i915_active_release(&ring->vma->active); +err_pin: + intel_ring_unpin(ring); return err; } static void __ring_retire(struct intel_ring *ring) { - intel_ring_unpin(ring); i915_active_release(&ring->vma->active); + intel_ring_unpin(ring); } __i915_active_call diff --git a/drivers/gpu/drm/i915/gt/shaders/README b/drivers/gpu/drm/i915/gt/shaders/README new file mode 100644 index 000000000000..e7e96d7073c7 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/shaders/README @@ -0,0 +1,46 @@ +ASM sources for auto generated shaders +====================================== + +The i915/gt/hsw_clear_kernel.c and i915/gt/ivb_clear_kernel.c files contain +pre-compiled batch chunks that will clear any residual render cache during +context switch. + +They are generated from their respective platform ASM files present on +i915/gt/shaders/clear_kernel directory. + +The generated .c files should never be modified directly. Instead, any modification +needs to be done on the on their respective ASM files and build instructions below +needes to be followed. + +Building +======== + +Environment +----------- + +IGT GPU tool scripts and the Mesa's i965 instruction assembler tool are used +on building. + +Please make sure your Mesa tool is compiled with "-Dtools=intel" and +"-Ddri-drivers=i965", and run this script from IGT source root directory" + +The instructions bellow assume: + * IGT gpu tools source code is located on your home directory (~) as ~/igt + * Mesa source code is located on your home directory (~) as ~/mesa + and built under the ~/mesa/build directory + * Linux kernel source code is under your home directory (~) as ~/linux + +Instructions +------------ + +~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm \ + ~/igt/lib/i915/shaders/clear_kernel/ivb.asm +~ $ cd ~/igt +igt $ ./scripts/generate_clear_kernel.sh -g ivb \ + -m ~/mesa/build/src/intel/tools/i965_asm + +~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm \ + ~/igt/lib/i915/shaders/clear_kernel/hsw.asm +~ $ cd ~/igt +igt $ ./scripts/generate_clear_kernel.sh -g hsw \ + -m ~/mesa/build/src/intel/tools/i965_asm
\ No newline at end of file diff --git a/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm new file mode 100644 index 000000000000..5fdf384bb621 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +/* + * Kernel for PAVP buffer clear. + * + * 1. Clear all 64 GRF registers assigned to the kernel with designated value; + * 2. Write 32x16 block of all "0" to render target buffer which indirectly clears + * 512 bytes of Render Cache. + */ + +/* Store designated "clear GRF" value */ +mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N }; + +/** + * Curbe Format + * + * DW 1.0 - Block Offset to write Render Cache + * DW 1.1 [15:0] - Clear Word + * DW 1.2 - Delay iterations + * DW 1.3 - Enable Instrumentation (only for debug) + * DW 1.4 - Rsvd (intended for context ID) + * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount + * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count) + * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count) + * + * Binding Table + * + * BTI 0: 2D Surface to help clear L3 (Render/Data Cache) + * BTI 1: Wait/Instrumentation Buffer + * Size : (SliceCount * SubSliceCount * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT) + * Expected to be initialized to 0 by driver/another kernel + * Layout: + * RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS] + * Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N + */ +add(1) g1.2<1>UD g1.2<0,1,0>UD 0x00000001UD { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */ +cmp.z.f0.0(1) null<1>UD g1.3<0,1,0>UD 0x00000000UD { align1 1N }; +(+f0.0) jmpi(1) 352D { align1 WE_all 1N }; + +/** + * State Register has info on where this thread is running + * IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID + * HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID + */ +mov(8) g3<1>UD 0x00000000UD { align1 1Q }; +shr(1) g3<1>D sr0<0,1,0>D 12D { align1 1N }; +and(1) g3<1>D g3<0,1,0>D 1D { align1 1N }; /* g3 has HSID */ +shr(1) g3.1<1>D sr0<0,1,0>D 13D { align1 1N }; +and(1) g3.1<1>D g3.1<0,1,0>D 3D { align1 1N }; /* g3.1 has sliceID */ +mul(1) g3.5<1>D g3.1<0,1,0>D g1.10<0,1,0>UW { align1 1N }; +add(1) g3<1>D g3<0,1,0>D g3.5<0,1,0>D { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */ +shr(1) g3.2<1>D sr0<0,1,0>D 8D { align1 1N }; +and(1) g3.2<1>D g3.2<0,1,0>D 15D { align1 1N }; /* g3.2 = EUID */ +mul(1) g3.4<1>D g3<0,1,0>D 16D { align1 1N }; +add(1) g3.2<1>D g3.2<0,1,0>D g3.4<0,1,0>D { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address ) in instrumentation surf */ + +mov(8) g5<1>UD 0x00000000UD { align1 1Q }; +and(1) g3.3<1>D sr0<0,1,0>D 7D { align1 1N }; +mul(1) g3.3<1>D g3.3<0,1,0>D 4D { align1 1N }; + +mov(8) g4<1>UD g0<8,8,1>UD { align1 1Q }; /* Initialize message header with g0 */ +mov(1) g4<1>UD g3.3<0,1,0>UD { align1 1N }; /* Block offset */ +mov(1) g4.1<1>UD g3.2<0,1,0>UD { align1 1N }; /* Block offset */ +mov(1) g4.2<1>UD 0x00000003UD { align1 1N }; /* Block size (1 row x 4 bytes) */ +and(1) g4.3<1>UD g4.3<0,1,0>UW 0xffffffffUD { align1 1N }; + +/* Media block read to fetch current value at specified location in instrumentation buffer */ +sendc(8) g5<1>UD g4<8,8,1>F 0x02190001 + + render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q }; +add(1) g5<1>D g5<0,1,0>D 1D { align1 1N }; + +/* Media block write for updated value at specified location in instrumentation buffer */ +sendc(8) g5<1>UD g4<8,8,1>F 0x040a8001 + render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q }; + +/* Delay thread for specified parameter */ +add.nz.f0.0(1) g1.2<1>UD g1.2<0,1,0>UD -1D { align1 1N }; +(+f0.0) jmpi(1) -32D { align1 WE_all 1N }; + +/* Store designated "clear GRF" value */ +mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N }; + +/* Initialize looping parameters */ +mov(1) a0<1>D 0D { align1 1N }; /* Initialize a0.0:w=0 */ +mov(1) a0.4<1>W 127W { align1 1N }; /* Loop count. Each loop contains 16 GRF's */ + +/* Write 32x16 all "0" block */ +mov(8) g2<1>UD g0<8,8,1>UD { align1 1Q }; +mov(8) g127<1>UD g0<8,8,1>UD { align1 1Q }; +mov(2) g2<1>UD g1<2,2,1>UW { align1 1N }; +mov(1) g2.2<1>UD 0x000f000fUD { align1 1N }; /* Block size (16x16) */ +and(1) g2.3<1>UD g2.3<0,1,0>UW 0xffffffefUD { align1 1N }; +mov(16) g3<1>UD 0x00000000UD { align1 1H }; +mov(16) g4<1>UD 0x00000000UD { align1 1H }; +mov(16) g5<1>UD 0x00000000UD { align1 1H }; +mov(16) g6<1>UD 0x00000000UD { align1 1H }; +mov(16) g7<1>UD 0x00000000UD { align1 1H }; +mov(16) g8<1>UD 0x00000000UD { align1 1H }; +mov(16) g9<1>UD 0x00000000UD { align1 1H }; +mov(16) g10<1>UD 0x00000000UD { align1 1H }; +sendc(8) null<1>UD g2<8,8,1>F 0x120a8000 + render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q }; +add(1) g2<1>UD g1<0,1,0>UW 0x0010UW { align1 1N }; +sendc(8) null<1>UD g2<8,8,1>F 0x120a8000 + render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q }; + +/* Now, clear all GRF registers */ +add.nz.f0.0(1) a0.4<1>W a0.4<0,1,0>W -1W { align1 1N }; +mov(16) g[a0]<1>UW f0.1<0,1,0>UW { align1 1H }; +add(1) a0<1>D a0<0,1,0>D 32D { align1 1N }; +(+f0.0) jmpi(1) -64D { align1 WE_all 1N }; + +/* Terminante the thread */ +sendc(8) null<1>UD g127<8,8,1>F 0x82000010 + thread_spawner MsgDesc: mlen 1 rlen 0 { align1 1Q EOT }; diff --git a/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm new file mode 100644 index 000000000000..97c7ac9e3854 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2020 Intel Corporation + */ + +/* + * Kernel for PAVP buffer clear. + * + * 1. Clear all 64 GRF registers assigned to the kernel with designated value; + * 2. Write 32x16 block of all "0" to render target buffer which indirectly clears + * 512 bytes of Render Cache. + */ + +/* Store designated "clear GRF" value */ +mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N }; + +/** + * Curbe Format + * + * DW 1.0 - Block Offset to write Render Cache + * DW 1.1 [15:0] - Clear Word + * DW 1.2 - Delay iterations + * DW 1.3 - Enable Instrumentation (only for debug) + * DW 1.4 - Rsvd (intended for context ID) + * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount + * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count) + * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count) + * + * Binding Table + * + * BTI 0: 2D Surface to help clear L3 (Render/Data Cache) + * BTI 1: Wait/Instrumentation Buffer + * Size : (SliceCount * SubSliceCount * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT) + * Expected to be initialized to 0 by driver/another kernel + * Layout : + * RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS] + * Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N + */ +add(1) g1.2<1>UD g1.2<0,1,0>UD 0x00000001UD { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */ +cmp.z.f0.0(1) null<1>UD g1.3<0,1,0>UD 0x00000000UD { align1 1N }; +(+f0.0) jmpi(1) 44D { align1 WE_all 1N }; + +/** + * State Register has info on where this thread is running + * IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID + * HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID + */ +mov(8) g3<1>UD 0x00000000UD { align1 1Q }; +shr(1) g3<1>D sr0<0,1,0>D 12D { align1 1N }; +and(1) g3<1>D g3<0,1,0>D 1D { align1 1N }; /* g3 has HSID */ +shr(1) g3.1<1>D sr0<0,1,0>D 13D { align1 1N }; +and(1) g3.1<1>D g3.1<0,1,0>D 3D { align1 1N }; /* g3.1 has sliceID */ +mul(1) g3.5<1>D g3.1<0,1,0>D g1.10<0,1,0>UW { align1 1N }; +add(1) g3<1>D g3<0,1,0>D g3.5<0,1,0>D { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */ +shr(1) g3.2<1>D sr0<0,1,0>D 8D { align1 1N }; +and(1) g3.2<1>D g3.2<0,1,0>D 15D { align1 1N }; /* g3.2 = EUID */ +mul(1) g3.4<1>D g3<0,1,0>D 16D { align1 1N }; +add(1) g3.2<1>D g3.2<0,1,0>D g3.4<0,1,0>D { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address ) in instrumentation surf */ + +mov(8) g5<1>UD 0x00000000UD { align1 1Q }; +and(1) g3.3<1>D sr0<0,1,0>D 7D { align1 1N }; +mul(1) g3.3<1>D g3.3<0,1,0>D 4D { align1 1N }; + +mov(8) g4<1>UD g0<8,8,1>UD { align1 1Q }; /* Initialize message header with g0 */ +mov(1) g4<1>UD g3.3<0,1,0>UD { align1 1N }; /* Block offset */ +mov(1) g4.1<1>UD g3.2<0,1,0>UD { align1 1N }; /* Block offset */ +mov(1) g4.2<1>UD 0x00000003UD { align1 1N }; /* Block size (1 row x 4 bytes) */ +and(1) g4.3<1>UD g4.3<0,1,0>UW 0xffffffffUD { align1 1N }; + +/* Media block read to fetch current value at specified location in instrumentation buffer */ +sendc(8) g5<1>UD g4<8,8,1>F 0x02190001 + render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q }; +add(1) g5<1>D g5<0,1,0>D 1D { align1 1N }; + +/* Media block write for updated value at specified location in instrumentation buffer */ +sendc(8) g5<1>UD g4<8,8,1>F 0x040a8001 + render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q }; +/* Delay thread for specified parameter */ +add.nz.f0.0(1) g1.2<1>UD g1.2<0,1,0>UD -1D { align1 1N }; +(+f0.0) jmpi(1) -4D { align1 WE_all 1N }; + +/* Store designated "clear GRF" value */ +mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N }; + +/* Initialize looping parameters */ +mov(1) a0<1>D 0D { align1 1N }; /* Initialize a0.0:w=0 */ +mov(1) a0.4<1>W 127W { align1 1N }; /* Loop count. Each loop contains 16 GRF's */ + +/* Write 32x16 all "0" block */ +mov(8) g2<1>UD g0<8,8,1>UD { align1 1Q }; +mov(8) g127<1>UD g0<8,8,1>UD { align1 1Q }; +mov(2) g2<1>UD g1<2,2,1>UW { align1 1N }; +mov(1) g2.2<1>UD 0x000f000fUD { align1 1N }; /* Block size (16x16) */ +and(1) g2.3<1>UD g2.3<0,1,0>UW 0xffffffefUD { align1 1N }; +mov(16) g3<1>UD 0x00000000UD { align1 1H }; +mov(16) g4<1>UD 0x00000000UD { align1 1H }; +mov(16) g5<1>UD 0x00000000UD { align1 1H }; +mov(16) g6<1>UD 0x00000000UD { align1 1H }; +mov(16) g7<1>UD 0x00000000UD { align1 1H }; +mov(16) g8<1>UD 0x00000000UD { align1 1H }; +mov(16) g9<1>UD 0x00000000UD { align1 1H }; +mov(16) g10<1>UD 0x00000000UD { align1 1H }; +sendc(8) null<1>UD g2<8,8,1>F 0x120a8000 + render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q }; +add(1) g2<1>UD g1<0,1,0>UW 0x0010UW { align1 1N }; +sendc(8) null<1>UD g2<8,8,1>F 0x120a8000 + render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q }; + +/* Now, clear all GRF registers */ +add.nz.f0.0(1) a0.4<1>W a0.4<0,1,0>W -1W { align1 1N }; +mov(16) g[a0]<1>UW f0.1<0,1,0>UW { align1 1H }; +add(1) a0<1>D a0<0,1,0>D 32D { align1 1N }; +(+f0.0) jmpi(1) -8D { align1 WE_all 1N }; + +/* Terminante the thread */ +sendc(8) null<1>UD g127<8,8,1>F 0x82000010 + thread_spawner MsgDesc: mlen 1 rlen 0 { align1 1Q EOT }; diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index ec47d4114554..62e6a14ad58e 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -66,7 +66,7 @@ static inline int mmio_diff_handler(struct intel_gvt *gvt, vreg = vgpu_vreg(param->vgpu, offset); if (preg != vreg) { - node = kmalloc(sizeof(*node), GFP_KERNEL); + node = kmalloc(sizeof(*node), GFP_ATOMIC); if (!node) return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 3e88e3b5c43a..fadd2adb8030 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1726,13 +1726,13 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, (*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(2); write_vreg(vgpu, offset, p_data, bytes); - if (data & _MASKED_BIT_ENABLE(1)) { + if (IS_MASKED_BITS_ENABLED(data, 1)) { enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST); return 0; } if (IS_COFFEELAKE(vgpu->gvt->gt->i915) && - data & _MASKED_BIT_ENABLE(2)) { + IS_MASKED_BITS_ENABLED(data, 2)) { enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST); return 0; } @@ -1741,14 +1741,14 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, * pvinfo, if not, we will treat this guest as non-gvtg-aware * guest, and stop emulating its cfg space, mmio, gtt, etc. */ - if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) || - (data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))) - && !vgpu->pv_notified) { + if ((IS_MASKED_BITS_ENABLED(data, GFX_PPGTT_ENABLE) || + IS_MASKED_BITS_ENABLED(data, GFX_RUN_LIST_ENABLE)) && + !vgpu->pv_notified) { enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST); return 0; } - if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)) - || (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) { + if (IS_MASKED_BITS_ENABLED(data, GFX_RUN_LIST_ENABLE) || + IS_MASKED_BITS_DISABLED(data, GFX_RUN_LIST_ENABLE)) { enable_execlist = !!(data & GFX_RUN_LIST_ENABLE); gvt_dbg_core("EXECLIST %s on ring %s\n", @@ -1809,7 +1809,7 @@ static int ring_reset_ctl_write(struct intel_vgpu *vgpu, write_vreg(vgpu, offset, p_data, bytes); data = vgpu_vreg(vgpu, offset); - if (data & _MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET)) + if (IS_MASKED_BITS_ENABLED(data, RESET_CTL_REQUEST_RESET)) data |= RESET_CTL_READY_TO_RESET; else if (data & _MASKED_BIT_DISABLE(RESET_CTL_REQUEST_RESET)) data &= ~RESET_CTL_READY_TO_RESET; @@ -1827,7 +1827,8 @@ static int csfe_chicken1_mmio_write(struct intel_vgpu *vgpu, (*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(0x18); write_vreg(vgpu, offset, p_data, bytes); - if (data & _MASKED_BIT_ENABLE(0x10) || data & _MASKED_BIT_ENABLE(0x8)) + if (IS_MASKED_BITS_ENABLED(data, 0x10) || + IS_MASKED_BITS_ENABLED(data, 0x8)) enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST); return 0; @@ -3055,6 +3056,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_MMIO(0x72380), D_SKL_PLUS); MMIO_D(_MMIO(0x7239c), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_SURF_3_A), D_SKL_PLUS); + MMIO_D(_MMIO(_PLANE_SURF_3_B), D_SKL_PLUS); MMIO_D(CSR_SSP_BASE, D_SKL_PLUS); MMIO_D(CSR_HTP_SKL, D_SKL_PLUS); @@ -3131,8 +3133,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_D(GAMT_CHKN_BIT_REG, D_KBL); - MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL); + MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL); + MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.h b/drivers/gpu/drm/i915/gvt/mmio_context.h index 970704b18f23..3b25e7fe32f6 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.h +++ b/drivers/gpu/drm/i915/gvt/mmio_context.h @@ -54,8 +54,8 @@ bool is_inhibit_context(struct intel_context *ce); int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu, struct i915_request *req); -#define IS_RESTORE_INHIBIT(a) \ - (_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) == \ - ((a) & _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT))) + +#define IS_RESTORE_INHIBIT(a) \ + IS_MASKED_BITS_ENABLED(a, CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) #endif diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h index 5b66e14c5b7b..b88e033cbed4 100644 --- a/drivers/gpu/drm/i915/gvt/reg.h +++ b/drivers/gpu/drm/i915/gvt/reg.h @@ -94,6 +94,11 @@ #define GFX_MODE_BIT_SET_IN_MASK(val, bit) \ ((((bit) & 0xffff0000) == 0) && !!((val) & (((bit) << 16)))) +#define IS_MASKED_BITS_ENABLED(_val, _b) \ + (((_val) & _MASKED_BIT_ENABLE(_b)) == _MASKED_BIT_ENABLE(_b)) +#define IS_MASKED_BITS_DISABLED(_val, _b) \ + ((_val) & _MASKED_BIT_DISABLE(_b)) + #define FORCEWAKE_RENDER_GEN9_REG 0xa278 #define FORCEWAKE_ACK_RENDER_GEN9_REG 0x0D84 #define FORCEWAKE_BLITTER_GEN9_REG 0xa188 diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index bca036ac6621..e7532e7d74e9 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -230,7 +230,7 @@ static int per_file_stats(int id, void *ptr, void *data) struct file_stats *stats = data; struct i915_vma *vma; - if (!kref_get_unless_zero(&obj->base.refcount)) + if (IS_ERR_OR_NULL(obj) || !kref_get_unless_zero(&obj->base.refcount)) return 0; stats->count++; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index adb9bf34cf97..f79f118bf192 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -410,8 +410,6 @@ struct intel_fbc { int adjusted_x; int adjusted_y; - int y; - u16 pixel_blend_mode; } plane; @@ -420,6 +418,8 @@ struct intel_fbc { unsigned int stride; u64 modifier; } fb; + + unsigned int fence_y_offset; u16 gen9_wa_cfb_stride; s8 fence_id; } state_cache; @@ -435,7 +435,6 @@ struct intel_fbc { struct { enum pipe pipe; enum i9xx_plane_id i9xx_plane; - unsigned int fence_y_offset; } crtc; struct { @@ -444,6 +443,7 @@ struct intel_fbc { } fb; int cfb_size; + unsigned int fence_y_offset; u16 gen9_wa_cfb_stride; s8 fence_id; bool plane_visible; diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index fc14ebf9a0b7..1f9cd33b35cb 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -104,6 +104,7 @@ vma_create(struct drm_i915_gem_object *obj, struct i915_address_space *vm, const struct i915_ggtt_view *view) { + struct i915_vma *pos = ERR_PTR(-E2BIG); struct i915_vma *vma; struct rb_node *rb, **p; @@ -184,7 +185,6 @@ vma_create(struct drm_i915_gem_object *obj, rb = NULL; p = &obj->vma.tree.rb_node; while (*p) { - struct i915_vma *pos; long cmp; rb = *p; @@ -196,16 +196,12 @@ vma_create(struct drm_i915_gem_object *obj, * and dispose of ours. */ cmp = i915_vma_compare(pos, vm, view); - if (cmp == 0) { - spin_unlock(&obj->vma.lock); - i915_vma_free(vma); - return pos; - } - if (cmp < 0) p = &rb->rb_right; - else + else if (cmp > 0) p = &rb->rb_left; + else + goto err_unlock; } rb_link_node(&vma->obj_node, rb, p); rb_insert_color(&vma->obj_node, &obj->vma.tree); @@ -228,8 +224,9 @@ vma_create(struct drm_i915_gem_object *obj, err_unlock: spin_unlock(&obj->vma.lock); err_vma: + i915_vm_put(vm); i915_vma_free(vma); - return ERR_PTR(-E2BIG); + return pos; } static struct i915_vma * diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 04e1d38d41f7..08802e5177f6 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -812,7 +812,7 @@ static void mcde_display_enable(struct drm_simple_display_pipe *pipe, struct drm_crtc *crtc = &pipe->crtc; struct drm_plane *plane = &pipe->plane; struct drm_device *drm = crtc->dev; - struct mcde *mcde = drm->dev_private; + struct mcde *mcde = to_mcde(drm); const struct drm_display_mode *mode = &cstate->mode; struct drm_framebuffer *fb = plane->state->fb; u32 format = fb->format->format; diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index 84f3e2dbd77b..80082d6dce3a 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -209,7 +209,6 @@ static int mcde_modeset_init(struct drm_device *drm) drm_mode_config_reset(drm); drm_kms_helper_poll_init(drm); - drm_fbdev_generic_setup(drm, 32); return 0; } @@ -264,6 +263,8 @@ static int mcde_drm_bind(struct device *dev) if (ret < 0) goto unbind; + drm_fbdev_generic_setup(drm, 32); + return 0; unbind: diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index c420f5a3d33b..aa74aac3cbcc 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -6,12 +6,12 @@ config DRM_MEDIATEK depends on COMMON_CLK depends on HAVE_ARM_SMCCC depends on OF + depends on MTK_MMSYS select DRM_GEM_CMA_HELPER select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL select MEMORY - select MTK_MMSYS select MTK_SMI select VIDEOMODE_HELPERS help diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index fe46c4bac64d..7cd8f415fd02 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -193,7 +193,6 @@ static int mtk_crtc_ddp_clk_enable(struct mtk_drm_crtc *mtk_crtc) int ret; int i; - DRM_DEBUG_DRIVER("%s\n", __func__); for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) { ret = clk_prepare_enable(mtk_crtc->ddp_comp[i]->clk); if (ret) { @@ -213,7 +212,6 @@ static void mtk_crtc_ddp_clk_disable(struct mtk_drm_crtc *mtk_crtc) { int i; - DRM_DEBUG_DRIVER("%s\n", __func__); for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) clk_disable_unprepare(mtk_crtc->ddp_comp[i]->clk); } @@ -258,7 +256,6 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc) int ret; int i; - DRM_DEBUG_DRIVER("%s\n", __func__); if (WARN_ON(!crtc->state)) return -EINVAL; @@ -299,7 +296,6 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc) goto err_mutex_unprepare; } - DRM_DEBUG_DRIVER("mediatek_ddp_ddp_path_setup\n"); for (i = 0; i < mtk_crtc->ddp_comp_nr - 1; i++) { mtk_mmsys_ddp_connect(mtk_crtc->mmsys_dev, mtk_crtc->ddp_comp[i]->id, @@ -349,7 +345,6 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc) struct drm_crtc *crtc = &mtk_crtc->base; int i; - DRM_DEBUG_DRIVER("%s\n", __func__); for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) { mtk_ddp_comp_stop(mtk_crtc->ddp_comp[i]); if (i == 1) @@ -831,7 +826,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, #if IS_REACHABLE(CONFIG_MTK_CMDQ) mtk_crtc->cmdq_client = - cmdq_mbox_create(dev, drm_crtc_index(&mtk_crtc->base), + cmdq_mbox_create(mtk_crtc->mmsys_dev, + drm_crtc_index(&mtk_crtc->base), 2000); if (IS_ERR(mtk_crtc->cmdq_client)) { dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n", diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 6bd369434d9d..040a8f393fe2 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -444,7 +444,6 @@ static int mtk_drm_probe(struct platform_device *pdev) if (!private) return -ENOMEM; - private->data = of_device_get_match_data(dev); private->mmsys_dev = dev->parent; if (!private->mmsys_dev) { dev_err(dev, "Failed to get MMSYS device\n"); @@ -514,7 +513,8 @@ static int mtk_drm_probe(struct platform_device *pdev) goto err_node; } - ret = mtk_ddp_comp_init(dev, node, comp, comp_id, NULL); + ret = mtk_ddp_comp_init(dev->parent, node, comp, + comp_id, NULL); if (ret) { of_node_put(node); goto err_node; @@ -571,7 +571,6 @@ static int mtk_drm_sys_suspend(struct device *dev) int ret; ret = drm_mode_config_helper_suspend(drm); - DRM_DEBUG_DRIVER("mtk_drm_sys_suspend\n"); return ret; } @@ -583,7 +582,6 @@ static int mtk_drm_sys_resume(struct device *dev) int ret; ret = drm_mode_config_helper_resume(drm); - DRM_DEBUG_DRIVER("mtk_drm_sys_resume\n"); return ret; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index c2bd683a87c8..92141a19681b 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -164,6 +164,16 @@ static int mtk_plane_atomic_check(struct drm_plane *plane, true, true); } +static void mtk_plane_atomic_disable(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct mtk_plane_state *state = to_mtk_plane_state(plane->state); + + state->pending.enable = false; + wmb(); /* Make sure the above parameter is set before update */ + state->pending.dirty = true; +} + static void mtk_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *old_state) { @@ -178,6 +188,11 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, if (!crtc || WARN_ON(!fb)) return; + if (!plane->state->visible) { + mtk_plane_atomic_disable(plane, old_state); + return; + } + gem = fb->obj[0]; mtk_gem = to_mtk_gem_obj(gem); addr = mtk_gem->dma_addr; @@ -200,16 +215,6 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, state->pending.dirty = true; } -static void mtk_plane_atomic_disable(struct drm_plane *plane, - struct drm_plane_state *old_state) -{ - struct mtk_plane_state *state = to_mtk_plane_state(plane->state); - - state->pending.enable = false; - wmb(); /* Make sure the above parameter is set before update */ - state->pending.dirty = true; -} - static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = { .prepare_fb = drm_gem_fb_prepare_fb, .atomic_check = mtk_plane_atomic_check, diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 270bf22c98fe..02ac55c13a80 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -316,10 +316,7 @@ static void mtk_dsi_lane0_ulp_mode_leave(struct mtk_dsi *dsi) static bool mtk_dsi_clk_hs_state(struct mtk_dsi *dsi) { - u32 tmp_reg1; - - tmp_reg1 = readl(dsi->regs + DSI_PHY_LCCON); - return ((tmp_reg1 & LC_HS_TX_EN) == 1) ? true : false; + return readl(dsi->regs + DSI_PHY_LCCON) & LC_HS_TX_EN; } static void mtk_dsi_clk_hs_mode(struct mtk_dsi *dsi, bool enter) diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 5feb760617cb..1eebe310470a 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1630,8 +1630,6 @@ static int mtk_hdmi_audio_startup(struct device *dev, void *data) { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - dev_dbg(dev, "%s\n", __func__); - mtk_hdmi_audio_enable(hdmi); return 0; @@ -1641,8 +1639,6 @@ static void mtk_hdmi_audio_shutdown(struct device *dev, void *data) { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - dev_dbg(dev, "%s\n", __func__); - mtk_hdmi_audio_disable(hdmi); } @@ -1651,8 +1647,6 @@ mtk_hdmi_audio_digital_mute(struct device *dev, void *data, bool enable) { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - dev_dbg(dev, "%s(%d)\n", __func__, enable); - if (enable) mtk_hdmi_hw_aud_mute(hdmi); else @@ -1665,8 +1659,6 @@ static int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, { struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - dev_dbg(dev, "%s\n", __func__); - memcpy(buf, hdmi->conn.eld, min(sizeof(hdmi->conn.eld), len)); return 0; @@ -1766,7 +1758,6 @@ static int mtk_drm_hdmi_probe(struct platform_device *pdev) goto err_bridge_remove; } - dev_dbg(dev, "mediatek hdmi probe success\n"); return 0; err_bridge_remove: @@ -1789,7 +1780,7 @@ static int mtk_hdmi_suspend(struct device *dev) struct mtk_hdmi *hdmi = dev_get_drvdata(dev); mtk_hdmi_clk_disable_audio(hdmi); - dev_dbg(dev, "hdmi suspend success!\n"); + return 0; } @@ -1804,7 +1795,6 @@ static int mtk_hdmi_resume(struct device *dev) return ret; } - dev_dbg(dev, "hdmi resume success!\n"); return 0; } #endif diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c index b55f51675205..827b93786fac 100644 --- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c +++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c @@ -107,60 +107,10 @@ #define RGS_HDMITX_5T1_EDG (0xf << 4) #define RGS_HDMITX_PLUG_TST BIT(0) -static const u8 PREDIV[3][4] = { - {0x0, 0x0, 0x0, 0x0}, /* 27Mhz */ - {0x1, 0x1, 0x1, 0x1}, /* 74Mhz */ - {0x1, 0x1, 0x1, 0x1} /* 148Mhz */ -}; - -static const u8 TXDIV[3][4] = { - {0x3, 0x3, 0x3, 0x2}, /* 27Mhz */ - {0x2, 0x1, 0x1, 0x1}, /* 74Mhz */ - {0x1, 0x0, 0x0, 0x0} /* 148Mhz */ -}; - -static const u8 FBKSEL[3][4] = { - {0x1, 0x1, 0x1, 0x1}, /* 27Mhz */ - {0x1, 0x0, 0x1, 0x1}, /* 74Mhz */ - {0x1, 0x0, 0x1, 0x1} /* 148Mhz */ -}; - -static const u8 FBKDIV[3][4] = { - {19, 24, 29, 19}, /* 27Mhz */ - {19, 24, 14, 19}, /* 74Mhz */ - {19, 24, 14, 19} /* 148Mhz */ -}; - -static const u8 DIVEN[3][4] = { - {0x2, 0x1, 0x1, 0x2}, /* 27Mhz */ - {0x2, 0x2, 0x2, 0x2}, /* 74Mhz */ - {0x2, 0x2, 0x2, 0x2} /* 148Mhz */ -}; - -static const u8 HTPLLBP[3][4] = { - {0xc, 0xc, 0x8, 0xc}, /* 27Mhz */ - {0xc, 0xf, 0xf, 0xc}, /* 74Mhz */ - {0xc, 0xf, 0xf, 0xc} /* 148Mhz */ -}; - -static const u8 HTPLLBC[3][4] = { - {0x2, 0x3, 0x3, 0x2}, /* 27Mhz */ - {0x2, 0x3, 0x3, 0x2}, /* 74Mhz */ - {0x2, 0x3, 0x3, 0x2} /* 148Mhz */ -}; - -static const u8 HTPLLBR[3][4] = { - {0x1, 0x1, 0x0, 0x1}, /* 27Mhz */ - {0x1, 0x2, 0x2, 0x1}, /* 74Mhz */ - {0x1, 0x2, 0x2, 0x1} /* 148Mhz */ -}; - static int mtk_hdmi_pll_prepare(struct clk_hw *hw) { struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - dev_dbg(hdmi_phy->dev, "%s\n", __func__); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_AUTOK_EN); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_MHLCK_EN); @@ -178,8 +128,6 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) { struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - dev_dbg(hdmi_phy->dev, "%s\n", __func__); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_TXDIV_EN); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_LPF_EN); usleep_range(100, 150); diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h index 8ea00546cd4e..049c4bfe2a3a 100644 --- a/drivers/gpu/drm/meson/meson_registers.h +++ b/drivers/gpu/drm/meson/meson_registers.h @@ -261,6 +261,12 @@ #define VIU_OSD_FIFO_DEPTH_VAL(val) ((val & 0x7f) << 12) #define VIU_OSD_WORDS_PER_BURST(words) (((words & 0x4) >> 1) << 22) #define VIU_OSD_FIFO_LIMITS(size) ((size & 0xf) << 24) +#define VIU_OSD_BURST_LENGTH_24 (0x0 << 31 | 0x0 << 10) +#define VIU_OSD_BURST_LENGTH_32 (0x0 << 31 | 0x1 << 10) +#define VIU_OSD_BURST_LENGTH_48 (0x0 << 31 | 0x2 << 10) +#define VIU_OSD_BURST_LENGTH_64 (0x0 << 31 | 0x3 << 10) +#define VIU_OSD_BURST_LENGTH_96 (0x1 << 31 | 0x0 << 10) +#define VIU_OSD_BURST_LENGTH_128 (0x1 << 31 | 0x1 << 10) #define VD1_IF0_GEN_REG 0x1a50 #define VD1_IF0_CANVAS0 0x1a51 diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index 304f8ff1339c..aede0c67a57f 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -411,13 +411,6 @@ void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv) priv->io_base + _REG(VIU_MISC_CTRL1)); } -static inline uint32_t meson_viu_osd_burst_length_reg(uint32_t length) -{ - uint32_t val = (((length & 0x80) % 24) / 12); - - return (((val & 0x3) << 10) | (((val & 0x4) >> 2) << 31)); -} - void meson_viu_init(struct meson_drm *priv) { uint32_t reg; @@ -444,9 +437,9 @@ void meson_viu_init(struct meson_drm *priv) VIU_OSD_FIFO_LIMITS(2); /* fifo_lim: 2*16=32 */ if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) - reg |= meson_viu_osd_burst_length_reg(32); + reg |= VIU_OSD_BURST_LENGTH_32; else - reg |= meson_viu_osd_burst_length_reg(64); + reg |= VIU_OSD_BURST_LENGTH_64; writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT)); writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT)); diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 60f6472a3e58..6021f8d9efd1 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -408,7 +408,7 @@ a2xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) struct msm_gem_address_space *aspace; aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M, - SZ_16M + 0xfff * SZ_64K); + 0xfff * SZ_64K); if (IS_ERR(aspace) && !IS_ERR(mmu)) mmu->funcs->destroy(mmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 096be97ce9f9..21e77d67151f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -1121,7 +1121,7 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) return -ENODEV; mmu = msm_iommu_new(gmu->dev, domain); - gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x7fffffff); + gmu->aspace = msm_gem_address_space_create(mmu, "gmu", 0x0, 0x80000000); if (IS_ERR(gmu->aspace)) { iommu_domain_free(domain); return PTR_ERR(gmu->aspace); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index a1589e040c57..7768557cdfb2 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -893,8 +893,8 @@ static const struct adreno_gpu_funcs funcs = { #if defined(CONFIG_DRM_MSM_GPU_STATE) .gpu_state_get = a6xx_gpu_state_get, .gpu_state_put = a6xx_gpu_state_put, - .create_address_space = adreno_iommu_create_address_space, #endif + .create_address_space = adreno_iommu_create_address_space, }, .get_timestamp = a6xx_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 89673c7ed473..5db06b590943 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -194,7 +194,7 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu, struct msm_gem_address_space *aspace; aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M, - 0xfffffff); + 0xffffffff - SZ_16M); if (IS_ERR(aspace) && !IS_ERR(mmu)) mmu->funcs->destroy(mmu); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 63976dcd2ac8..0946a86b37b2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -521,7 +521,7 @@ static struct msm_display_topology dpu_encoder_get_topology( struct dpu_kms *dpu_kms, struct drm_display_mode *mode) { - struct msm_display_topology topology; + struct msm_display_topology topology = {0}; int i, intf_count = 0; for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++) @@ -537,7 +537,8 @@ static struct msm_display_topology dpu_encoder_get_topology( * 1 LM, 1 INTF * 2 LM, 1 INTF (stream merge to support high resolution interfaces) * - * Adding color blocks only to primary interface + * Adding color blocks only to primary interface if available in + * sufficient number */ if (intf_count == 2) topology.num_lm = 2; @@ -546,8 +547,11 @@ static struct msm_display_topology dpu_encoder_get_topology( else topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; - if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI) - topology.num_dspp = topology.num_lm; + if (dpu_enc->disp_info.intf_type == DRM_MODE_ENCODER_DSI) { + if (dpu_kms->catalog->dspp && + (dpu_kms->catalog->dspp_count >= topology.num_lm)) + topology.num_dspp = topology.num_lm; + } topology.num_enc = 0; topology.num_intf = intf_count; @@ -2136,7 +2140,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, dpu_enc = to_dpu_encoder_virt(enc); - mutex_init(&dpu_enc->enc_lock); ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info); if (ret) goto fail; @@ -2151,7 +2154,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, 0); - mutex_init(&dpu_enc->rc_lock); INIT_DELAYED_WORK(&dpu_enc->delayed_off_work, dpu_encoder_off_work); dpu_enc->idle_timeout = IDLE_TIMEOUT; @@ -2183,7 +2185,7 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev, dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL); if (!dpu_enc) - return ERR_PTR(ENOMEM); + return ERR_PTR(-ENOMEM); rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs, drm_enc_mode, NULL); @@ -2196,6 +2198,8 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev, spin_lock_init(&dpu_enc->enc_spinlock); dpu_enc->enabled = false; + mutex_init(&dpu_enc->enc_lock); + mutex_init(&dpu_enc->rc_lock); return &dpu_enc->base; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index b8615d4fe8a3..680527e28d09 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -780,7 +780,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms) mmu = msm_iommu_new(dpu_kms->dev->dev, domain); aspace = msm_gem_address_space_create(mmu, "dpu1", - 0x1000, 0xfffffff); + 0x1000, 0x100000000 - 0x1000); if (IS_ERR(aspace)) { mmu->funcs->destroy(mmu); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 08897184b1d9..fc6a3f8134c7 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -514,7 +514,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev) config->iommu); aspace = msm_gem_address_space_create(mmu, - "mdp4", 0x1000, 0xffffffff); + "mdp4", 0x1000, 0x100000000 - 0x1000); if (IS_ERR(aspace)) { if (!IS_ERR(mmu)) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 19ec48695ffb..e193865ce9a2 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -633,7 +633,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) mmu = msm_iommu_new(iommu_dev, config->platform.iommu); aspace = msm_gem_address_space_create(mmu, "mdp5", - 0x1000, 0xffffffff); + 0x1000, 0x100000000 - 0x1000); if (IS_ERR(aspace)) { if (!IS_ERR(mmu)) diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 001fbf537440..a1d94be7883a 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -71,8 +71,10 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, queue->flags = flags; if (priv->gpu) { - if (prio >= priv->gpu->nr_rings) + if (prio >= priv->gpu->nr_rings) { + kfree(queue); return -EINVAL; + } queue->prio = prio; } diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index d472942102f5..519f99868e35 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -601,6 +601,9 @@ nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc) (0x0100 << nv_crtc->index), }; + if (!nv_encoder->audio) + return; + nv_encoder->audio = false; nvif_mthd(&disp->disp->object, 0, &args, sizeof(args)); diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index e5c230d9ae24..cc9993837508 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -550,7 +550,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) goto out_free_page; - if (drm->dmem->migrate.copy_func(drm, page_size(spage), + if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST, *dma_addr)) goto out_dma_unmap; } else { diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index ba9f9359c30e..6586d9d39874 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -562,6 +562,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, .end = notifier->notifier.interval_tree.last + 1, .pfn_flags_mask = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE, .hmm_pfns = hmm_pfns, + .dev_private_owner = drm->dev, }; struct mm_struct *mm = notifier->notifier.mm; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c index c8ab1b5741a3..db7769cb33eb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c @@ -118,10 +118,10 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry, if (retries) udelay(400); - /* transaction request, wait up to 1ms for it to complete */ + /* transaction request, wait up to 2ms for it to complete */ nvkm_wr32(device, 0x00e4e4 + base, 0x00010000 | ctrl); - timeout = 1000; + timeout = 2000; do { ctrl = nvkm_rd32(device, 0x00e4e4 + base); udelay(1); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c index 7ef60895f43a..edb6148cbca0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c @@ -118,10 +118,10 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry, if (retries) udelay(400); - /* transaction request, wait up to 1ms for it to complete */ + /* transaction request, wait up to 2ms for it to complete */ nvkm_wr32(device, 0x00d954 + base, 0x00010000 | ctrl); - timeout = 1000; + timeout = 2000; do { ctrl = nvkm_rd32(device, 0x00d954 + base); udelay(1); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b6ecd1552132..5178f87d6574 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2495,6 +2495,7 @@ static const struct panel_desc logicpd_type_28 = { .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct panel_desc mitsubishi_aa070mc01 = { @@ -2663,6 +2664,7 @@ static const struct panel_desc newhaven_nhd_43_480272ef_atxl = { .bus_format = MEDIA_BUS_FMT_RGB888_1X24, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE | DRM_BUS_FLAG_SYNC_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct display_timing nlt_nl192108ac18_02d_timing = { diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 134aa2b01f90..f434efdeca44 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -5563,6 +5563,7 @@ static int ci_parse_power_table(struct radeon_device *rdev) if (!rdev->pm.dpm.ps) return -ENOMEM; power_state_offset = (u8 *)state_array->states; + rdev->pm.dpm.num_ps = 0; for (i = 0; i < state_array->ucNumEntries; i++) { u8 *idx; power_state = (union pplib_power_state *)power_state_offset; @@ -5572,10 +5573,8 @@ static int ci_parse_power_table(struct radeon_device *rdev) if (!rdev->pm.power_state[i].clock_info) return -EINVAL; ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL); - if (ps == NULL) { - kfree(rdev->pm.dpm.ps); + if (ps == NULL) return -ENOMEM; - } rdev->pm.dpm.ps[i].ps_priv = ps; ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i], non_clock_info, @@ -5597,8 +5596,8 @@ static int ci_parse_power_table(struct radeon_device *rdev) k++; } power_state_offset += 2 + power_state->v2.ucNumDPMLevels; + rdev->pm.dpm.num_ps = i + 1; } - rdev->pm.dpm.num_ps = state_array->ucNumEntries; /* fill in the vce power states */ for (i = 0; i < RADEON_MAX_VCE_LEVELS; i++) { diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index b57c37ddd164..c7fbb7932f37 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -2127,7 +2127,7 @@ static int ni_init_smc_spll_table(struct radeon_device *rdev) if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT)) ret = -EINVAL; - if (clk_s & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKS_SHIFT)) + if (fb_div & ~(SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_FBDIV_SHIFT)) ret = -EINVAL; if (clk_v & ~(SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_MASK >> SMC_NISLANDS_SPLL_DIV_TABLE_CLKV_SHIFT)) diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig index 0919f1f159a4..f65d1489dc50 100644 --- a/drivers/gpu/drm/rcar-du/Kconfig +++ b/drivers/gpu/drm/rcar-du/Kconfig @@ -31,6 +31,7 @@ config DRM_RCAR_DW_HDMI config DRM_RCAR_LVDS tristate "R-Car DU LVDS Encoder Support" depends on DRM && DRM_BRIDGE && OF + select DRM_KMS_HELPER select DRM_PANEL select OF_FLATTREE select OF_OVERLAY diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index ce07ddc3e058..557cbe5ab35f 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -259,9 +259,8 @@ sun4i_hdmi_connector_detect(struct drm_connector *connector, bool force) struct sun4i_hdmi *hdmi = drm_connector_to_sun4i_hdmi(connector); unsigned long reg; - if (readl_poll_timeout(hdmi->base + SUN4I_HDMI_HPD_REG, reg, - reg & SUN4I_HDMI_HPD_HIGH, - 0, 500000)) { + reg = readl(hdmi->base + SUN4I_HDMI_HPD_REG); + if (reg & SUN4I_HDMI_HPD_HIGH) { cec_phys_addr_invalidate(hdmi->cec_adap); return connector_status_disconnected; } diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index 56cc037fd312..cc4fb916318f 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -363,6 +363,19 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master, mixer->engine.ops = &sun8i_engine_ops; mixer->engine.node = dev->of_node; + if (of_find_property(dev->of_node, "iommus", NULL)) { + /* + * This assume we have the same DMA constraints for + * all our the mixers in our pipeline. This sounds + * bad, but it has always been the case for us, and + * DRM doesn't do per-device allocation either, so we + * would need to fix DRM first... + */ + ret = of_dma_configure(drm->dev, dev->of_node, true); + if (ret) + return ret; + } + /* * While this function can fail, we shouldn't do anything * if this happens. Some early DE2 DT entries don't provide diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 83f31c6e891c..04d6848d19fc 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -957,6 +957,7 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, } drm_plane_helper_add(&plane->base, &tegra_cursor_plane_helper_funcs); + drm_plane_create_zpos_immutable_property(&plane->base, 255); return &plane->base; } diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index 8183e617bf6b..22a03f7ffdc1 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -149,7 +149,9 @@ int tegra_display_hub_prepare(struct tegra_display_hub *hub) for (i = 0; i < hub->soc->num_wgrps; i++) { struct tegra_windowgroup *wgrp = &hub->wgrps[i]; - tegra_windowgroup_enable(wgrp); + /* Skip orphaned window group whose parent DC is disabled */ + if (wgrp->parent) + tegra_windowgroup_enable(wgrp); } return 0; @@ -166,7 +168,9 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub) for (i = 0; i < hub->soc->num_wgrps; i++) { struct tegra_windowgroup *wgrp = &hub->wgrps[i]; - tegra_windowgroup_disable(wgrp); + /* Skip orphaned window group whose parent DC is disabled */ + if (wgrp->parent) + tegra_windowgroup_disable(wgrp); } } @@ -944,6 +948,15 @@ static int tegra_display_hub_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to register host1x client: %d\n", err); + err = devm_of_platform_populate(&pdev->dev); + if (err < 0) + goto unregister; + + return err; + +unregister: + host1x_client_unregister(&hub->client); + pm_runtime_disable(&pdev->dev); return err; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index f73b81c2576e..0f20e14a4cfd 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -883,8 +883,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, if (!fence) return 0; - if (no_wait_gpu) + if (no_wait_gpu) { + dma_fence_put(fence); return -EBUSY; + } dma_resv_add_shared_fence(bo->base.resv, fence); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index a43aa7275f12..fa03fab02076 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -300,8 +300,10 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, break; case -EBUSY: case -ERESTARTSYS: + dma_fence_put(moving); return VM_FAULT_NOPAGE; default: + dma_fence_put(moving); return VM_FAULT_SIGBUS; } diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 6a995db51d6d..e201f62d62c0 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -686,8 +686,17 @@ EXPORT_SYMBOL(host1x_driver_register_full); */ void host1x_driver_unregister(struct host1x_driver *driver) { + struct host1x *host1x; + driver_unregister(&driver->driver); + mutex_lock(&devices_lock); + + list_for_each_entry(host1x, &devices, list) + host1x_detach_driver(host1x, driver); + + mutex_unlock(&devices_lock); + mutex_lock(&drivers_lock); list_del_init(&driver->list); mutex_unlock(&drivers_lock); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index d24344e91922..d0ebb70e2fdd 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -468,11 +468,18 @@ static int host1x_probe(struct platform_device *pdev) err = host1x_register(host); if (err < 0) - goto deinit_intr; + goto deinit_debugfs; + + err = devm_of_platform_populate(&pdev->dev); + if (err < 0) + goto unregister; return 0; -deinit_intr: +unregister: + host1x_unregister(host); +deinit_debugfs: + host1x_debug_deinit(host); host1x_intr_deinit(host); deinit_syncpt: host1x_syncpt_deinit(host); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 9147ee9d5f7d..d69f4efa3719 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1368,7 +1368,7 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, * Write dump contents to the page. No need to synchronize; panic should * be single-threaded. */ - kmsg_dump_get_buffer(dumper, true, hv_panic_page, HV_HYP_PAGE_SIZE, + kmsg_dump_get_buffer(dumper, false, hv_panic_page, HV_HYP_PAGE_SIZE, &bytes_written); if (bytes_written) hyperv_report_panic_msg(panic_pa, bytes_written); diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 0db8ef4fd6e1..a270b975e90b 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -883,7 +883,7 @@ static int acpi_power_meter_add(struct acpi_device *device) res = setup_attrs(resource); if (res) - goto exit_free; + goto exit_free_capability; resource->hwmon_dev = hwmon_device_register(&device->dev); if (IS_ERR(resource->hwmon_dev)) { @@ -896,6 +896,8 @@ static int acpi_power_meter_add(struct acpi_device *device) exit_remove: remove_attrs(resource); +exit_free_capability: + free_capabilities(resource); exit_free: kfree(resource); exit: diff --git a/drivers/hwmon/bt1-pvt.c b/drivers/hwmon/bt1-pvt.c index 1a9772fb1f73..94698cae0497 100644 --- a/drivers/hwmon/bt1-pvt.c +++ b/drivers/hwmon/bt1-pvt.c @@ -64,7 +64,7 @@ static const struct pvt_sensor_info pvt_info[] = { * 48380, * where T = [-48380, 147438] mC and N = [0, 1023]. */ -static const struct pvt_poly poly_temp_to_N = { +static const struct pvt_poly __maybe_unused poly_temp_to_N = { .total_divider = 10000, .terms = { {4, 18322, 10000, 10000}, @@ -96,7 +96,7 @@ static const struct pvt_poly poly_N_to_temp = { * N = (18658e-3*V - 11572) / 10, * V = N * 10^5 / 18658 + 11572 * 10^4 / 18658. */ -static const struct pvt_poly poly_volt_to_N = { +static const struct pvt_poly __maybe_unused poly_volt_to_N = { .total_divider = 10, .terms = { {1, 18658, 1000, 1}, @@ -300,12 +300,12 @@ static irqreturn_t pvt_soft_isr(int irq, void *data) return IRQ_HANDLED; } -inline umode_t pvt_limit_is_visible(enum pvt_sensor_type type) +static inline umode_t pvt_limit_is_visible(enum pvt_sensor_type type) { return 0644; } -inline umode_t pvt_alarm_is_visible(enum pvt_sensor_type type) +static inline umode_t pvt_alarm_is_visible(enum pvt_sensor_type type) { return 0444; } @@ -462,12 +462,12 @@ static irqreturn_t pvt_hard_isr(int irq, void *data) #define pvt_soft_isr NULL -inline umode_t pvt_limit_is_visible(enum pvt_sensor_type type) +static inline umode_t pvt_limit_is_visible(enum pvt_sensor_type type) { return 0; } -inline umode_t pvt_alarm_is_visible(enum pvt_sensor_type type) +static inline umode_t pvt_alarm_is_visible(enum pvt_sensor_type type) { return 0; } diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c index 743752a2467a..64122eb38060 100644 --- a/drivers/hwmon/max6697.c +++ b/drivers/hwmon/max6697.c @@ -38,8 +38,9 @@ static const u8 MAX6697_REG_CRIT[] = { * Map device tree / platform data register bit map to chip bit map. * Applies to alert register and over-temperature register. */ -#define MAX6697_MAP_BITS(reg) ((((reg) & 0x7e) >> 1) | \ +#define MAX6697_ALERT_MAP_BITS(reg) ((((reg) & 0x7e) >> 1) | \ (((reg) & 0x01) << 6) | ((reg) & 0x80)) +#define MAX6697_OVERT_MAP_BITS(reg) (((reg) >> 1) | (((reg) & 0x01) << 7)) #define MAX6697_REG_STAT(n) (0x44 + (n)) @@ -562,12 +563,12 @@ static int max6697_init_chip(struct max6697_data *data, return ret; ret = i2c_smbus_write_byte_data(client, MAX6697_REG_ALERT_MASK, - MAX6697_MAP_BITS(pdata->alert_mask)); + MAX6697_ALERT_MAP_BITS(pdata->alert_mask)); if (ret < 0) return ret; ret = i2c_smbus_write_byte_data(client, MAX6697_REG_OVERT_MASK, - MAX6697_MAP_BITS(pdata->over_temperature_mask)); + MAX6697_OVERT_MAP_BITS(pdata->over_temperature_mask)); if (ret < 0) return ret; diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig index a337195b1c39..ea516cec1d35 100644 --- a/drivers/hwmon/pmbus/Kconfig +++ b/drivers/hwmon/pmbus/Kconfig @@ -71,7 +71,7 @@ config SENSORS_IR35221 Infineon IR35221 controller. This driver can also be built as a module. If so, the module will - be called ir35521. + be called ir35221. config SENSORS_IR38064 tristate "Infineon IR38064" diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index a420877ba533..2191575a448b 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -1869,7 +1869,7 @@ static int pmbus_add_fan_ctrl(struct i2c_client *client, struct pmbus_sensor *sensor; sensor = pmbus_add_sensor(data, "fan", "target", index, page, - PMBUS_VIRT_FAN_TARGET_1 + id, 0xff, PSC_FAN, + 0xff, PMBUS_VIRT_FAN_TARGET_1 + id, PSC_FAN, false, false, true); if (!sensor) @@ -1880,14 +1880,14 @@ static int pmbus_add_fan_ctrl(struct i2c_client *client, return 0; sensor = pmbus_add_sensor(data, "pwm", NULL, index, page, - PMBUS_VIRT_PWM_1 + id, 0xff, PSC_PWM, + 0xff, PMBUS_VIRT_PWM_1 + id, PSC_PWM, false, false, true); if (!sensor) return -ENOMEM; sensor = pmbus_add_sensor(data, "pwm", "enable", index, page, - PMBUS_VIRT_PWM_ENABLE_1 + id, 0xff, PSC_PWM, + 0xff, PMBUS_VIRT_PWM_ENABLE_1 + id, PSC_PWM, true, false, false); if (!sensor) @@ -1929,7 +1929,7 @@ static int pmbus_add_fan_attributes(struct i2c_client *client, continue; if (pmbus_add_sensor(data, "fan", "input", index, - page, pmbus_fan_registers[f], 0xff, + page, 0xff, pmbus_fan_registers[f], PSC_FAN, true, true, true) == NULL) return -ENOMEM; diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig index ef39c83aaf33..bae1dc08ec9a 100644 --- a/drivers/i2c/Kconfig +++ b/drivers/i2c/Kconfig @@ -113,11 +113,18 @@ config I2C_STUB config I2C_SLAVE bool "I2C slave support" + help + This enables Linux to act as an I2C slave device. Note that your I2C + bus master driver also needs to support this functionality. Please + read Documentation/i2c/slave-interface.rst for further details. if I2C_SLAVE config I2C_SLAVE_EEPROM tristate "I2C eeprom slave driver" + help + This backend makes Linux behave like an I2C EEPROM. Please read + Documentation/i2c/slave-eeprom-backend.rst for further details. endif diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c index 7f10312d1b88..388978775be0 100644 --- a/drivers/i2c/algos/i2c-algo-pca.c +++ b/drivers/i2c/algos/i2c-algo-pca.c @@ -314,7 +314,8 @@ static int pca_xfer(struct i2c_adapter *i2c_adap, DEB2("BUS ERROR - SDA Stuck low\n"); pca_reset(adap); goto out; - case 0x90: /* Bus error - SCL stuck low */ + case 0x78: /* Bus error - SCL stuck low (PCA9665) */ + case 0x90: /* Bus error - SCL stuck low (PCA9564) */ DEB2("BUS ERROR - SCL Stuck low\n"); pca_reset(adap); goto out; diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index e3a8640db7da..3c19aada4b30 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -286,10 +286,8 @@ int i2c_dw_acpi_configure(struct device *device) } EXPORT_SYMBOL_GPL(i2c_dw_acpi_configure); -void i2c_dw_acpi_adjust_bus_speed(struct device *device) +static u32 i2c_dw_acpi_round_bus_speed(struct device *device) { - struct dw_i2c_dev *dev = dev_get_drvdata(device); - struct i2c_timings *t = &dev->timings; u32 acpi_speed; int i; @@ -300,9 +298,22 @@ void i2c_dw_acpi_adjust_bus_speed(struct device *device) */ for (i = 0; i < ARRAY_SIZE(supported_speeds); i++) { if (acpi_speed >= supported_speeds[i]) - break; + return supported_speeds[i]; } - acpi_speed = i < ARRAY_SIZE(supported_speeds) ? supported_speeds[i] : 0; + + return 0; +} + +#else /* CONFIG_ACPI */ + +static inline u32 i2c_dw_acpi_round_bus_speed(struct device *device) { return 0; } + +#endif /* CONFIG_ACPI */ + +void i2c_dw_adjust_bus_speed(struct dw_i2c_dev *dev) +{ + u32 acpi_speed = i2c_dw_acpi_round_bus_speed(dev->dev); + struct i2c_timings *t = &dev->timings; /* * Find bus speed from the "clock-frequency" device property, ACPI @@ -315,9 +326,7 @@ void i2c_dw_acpi_adjust_bus_speed(struct device *device) else t->bus_freq_hz = I2C_MAX_FAST_MODE_FREQ; } -EXPORT_SYMBOL_GPL(i2c_dw_acpi_adjust_bus_speed); - -#endif /* CONFIG_ACPI */ +EXPORT_SYMBOL_GPL(i2c_dw_adjust_bus_speed); u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) { diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 556673a1f61b..eb5ef4d0f463 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -361,11 +361,10 @@ static inline int i2c_dw_probe_lock_support(struct dw_i2c_dev *dev) { return 0; #endif int i2c_dw_validate_speed(struct dw_i2c_dev *dev); +void i2c_dw_adjust_bus_speed(struct dw_i2c_dev *dev); #if IS_ENABLED(CONFIG_ACPI) int i2c_dw_acpi_configure(struct device *device); -void i2c_dw_acpi_adjust_bus_speed(struct device *device); #else static inline int i2c_dw_acpi_configure(struct device *device) { return -ENODEV; } -static inline void i2c_dw_acpi_adjust_bus_speed(struct device *device) {} #endif diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index 947c096f86e3..8522134f9ea9 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -240,7 +240,7 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev, } } - i2c_dw_acpi_adjust_bus_speed(&pdev->dev); + i2c_dw_adjust_bus_speed(dev); if (has_acpi_companion(&pdev->dev)) i2c_dw_acpi_configure(&pdev->dev); diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 0de4e302fc6a..a71bc58fc03c 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -12,6 +12,7 @@ #include <linux/clk-provider.h> #include <linux/clk.h> #include <linux/delay.h> +#include <linux/dmi.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/i2c.h> @@ -191,6 +192,17 @@ static int dw_i2c_plat_request_regs(struct dw_i2c_dev *dev) return ret; } +static const struct dmi_system_id dw_i2c_hwmon_class_dmi[] = { + { + .ident = "Qtechnology QT5222", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Qtechnology"), + DMI_MATCH(DMI_PRODUCT_NAME, "QT5222"), + }, + }, + { } /* terminate list */ +}; + static int dw_i2c_plat_probe(struct platform_device *pdev) { struct dw_i2c_platform_data *pdata = dev_get_platdata(&pdev->dev); @@ -228,7 +240,7 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) else i2c_parse_fw_timings(&pdev->dev, t, false); - i2c_dw_acpi_adjust_bus_speed(&pdev->dev); + i2c_dw_adjust_bus_speed(dev); if (pdev->dev.of_node) dw_i2c_of_configure(pdev); @@ -267,7 +279,8 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) adap = &dev->adapter; adap->owner = THIS_MODULE; - adap->class = I2C_CLASS_DEPRECATED; + adap->class = dmi_check_system(dw_i2c_hwmon_class_dmi) ? + I2C_CLASS_HWMON : I2C_CLASS_DEPRECATED; ACPI_COMPANION_SET(&adap->dev, ACPI_COMPANION(&pdev->dev)); adap->dev.of_node = pdev->dev.of_node; adap->nr = -1; diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index bb810dee8fb5..73f139690e4e 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -180,6 +180,7 @@ static const struct pci_device_id pch_pcidev_id[] = { { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7831_I2C), 1, }, {0,} }; +MODULE_DEVICE_TABLE(pci, pch_pcidev_id); static irqreturn_t pch_i2c_handler(int irq, void *pData); diff --git a/drivers/i2c/busses/i2c-fsi.c b/drivers/i2c/busses/i2c-fsi.c index e0c256922d4f..977d6f524649 100644 --- a/drivers/i2c/busses/i2c-fsi.c +++ b/drivers/i2c/busses/i2c-fsi.c @@ -98,7 +98,7 @@ #define I2C_STAT_DAT_REQ BIT(25) #define I2C_STAT_CMD_COMP BIT(24) #define I2C_STAT_STOP_ERR BIT(23) -#define I2C_STAT_MAX_PORT GENMASK(19, 16) +#define I2C_STAT_MAX_PORT GENMASK(22, 16) #define I2C_STAT_ANY_INT BIT(15) #define I2C_STAT_SCL_IN BIT(11) #define I2C_STAT_SDA_IN BIT(10) diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 2fd717d8dd30..71d7bae2cbca 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -337,9 +337,9 @@ static int mlxcpld_i2c_wait_for_tc(struct mlxcpld_i2c_priv *priv) if (priv->smbus_block && (val & MLXCPLD_I2C_SMBUS_BLK_BIT)) { mlxcpld_i2c_read_comm(priv, MLXCPLD_LPCI2C_NUM_DAT_REG, &datalen, 1); - if (unlikely(datalen > (I2C_SMBUS_BLOCK_MAX + 1))) { + if (unlikely(datalen > I2C_SMBUS_BLOCK_MAX)) { dev_err(priv->dev, "Incorrect smbus block read message len\n"); - return -E2BIG; + return -EPROTO; } } else { datalen = priv->xfer.data_len; diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index 56bb840142e3..f5c9787992e9 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -495,6 +495,13 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_BLOCK_PROC_CALL: + if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) { + dev_err(&adapter->dev, + "Invalid block size returned: %d\n", + msg[1].buf[0]); + status = -EPROTO; + goto cleanup; + } for (i = 0; i < msg[1].buf[0] + 1; i++) data->block[i] = msg[1].buf[i]; break; diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index a2ed09a3c714..8c930bf1df89 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -829,13 +829,20 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask) return len; } -static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask) +static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask) { struct sk_buff *skb = NULL; struct nlmsghdr *nlh; void *data; struct ib_sa_mad *mad; int len; + unsigned long flags; + unsigned long delay; + gfp_t gfp_flag; + int ret; + + INIT_LIST_HEAD(&query->list); + query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq); mad = query->mad_buf->mad; len = ib_nl_get_path_rec_attrs_len(mad->sa_hdr.comp_mask); @@ -860,36 +867,25 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask) /* Repair the nlmsg header length */ nlmsg_end(skb, nlh); - return rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_mask); -} + gfp_flag = ((gfp_mask & GFP_ATOMIC) == GFP_ATOMIC) ? GFP_ATOMIC : + GFP_NOWAIT; -static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask) -{ - unsigned long flags; - unsigned long delay; - int ret; + spin_lock_irqsave(&ib_nl_request_lock, flags); + ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_flag); - INIT_LIST_HEAD(&query->list); - query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq); + if (ret) + goto out; - /* Put the request on the list first.*/ - spin_lock_irqsave(&ib_nl_request_lock, flags); + /* Put the request on the list.*/ delay = msecs_to_jiffies(sa_local_svc_timeout_ms); query->timeout = delay + jiffies; list_add_tail(&query->list, &ib_nl_request_list); /* Start the timeout if this is the only request */ if (ib_nl_request_list.next == &query->list) queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay); - spin_unlock_irqrestore(&ib_nl_request_lock, flags); - ret = ib_nl_send_msg(query, gfp_mask); - if (ret) { - ret = -EIO; - /* Remove the request */ - spin_lock_irqsave(&ib_nl_request_lock, flags); - list_del(&query->list); - spin_unlock_irqrestore(&ib_nl_request_lock, flags); - } +out: + spin_unlock_irqrestore(&ib_nl_request_lock, flags); return ret; } diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 5eed4360695f..cb7ad1288821 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -831,6 +831,29 @@ wq_error: } /** + * destroy_workqueues - destroy per port workqueues + * @dd: the hfi1_ib device + */ +static void destroy_workqueues(struct hfi1_devdata *dd) +{ + int pidx; + struct hfi1_pportdata *ppd; + + for (pidx = 0; pidx < dd->num_pports; ++pidx) { + ppd = dd->pport + pidx; + + if (ppd->hfi1_wq) { + destroy_workqueue(ppd->hfi1_wq); + ppd->hfi1_wq = NULL; + } + if (ppd->link_wq) { + destroy_workqueue(ppd->link_wq); + ppd->link_wq = NULL; + } + } +} + +/** * enable_general_intr() - Enable the IRQs that will be handled by the * general interrupt handler. * @dd: valid devdata @@ -1103,15 +1126,10 @@ static void shutdown_device(struct hfi1_devdata *dd) * We can't count on interrupts since we are stopping. */ hfi1_quiet_serdes(ppd); - - if (ppd->hfi1_wq) { - destroy_workqueue(ppd->hfi1_wq); - ppd->hfi1_wq = NULL; - } - if (ppd->link_wq) { - destroy_workqueue(ppd->link_wq); - ppd->link_wq = NULL; - } + if (ppd->hfi1_wq) + flush_workqueue(ppd->hfi1_wq); + if (ppd->link_wq) + flush_workqueue(ppd->link_wq); } sdma_exit(dd); } @@ -1756,6 +1774,7 @@ static void remove_one(struct pci_dev *pdev) * clear dma engines, etc. */ shutdown_device(dd); + destroy_workqueues(dd); stop_timers(dd); diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 0c2ae9f7b3e8..be62284e42d9 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -195,7 +195,7 @@ static inline int verbs_mtu_enum_to_int(struct ib_device *dev, enum ib_mtu mtu) { /* Constraining 10KB packets to 8KB packets */ if (mtu == (enum ib_mtu)OPA_MTU_10240) - mtu = OPA_MTU_8192; + mtu = (enum ib_mtu)OPA_MTU_8192; return opa_mtu_enum_to_int((enum opa_mtu)mtu); } @@ -367,7 +367,10 @@ bool _hfi1_schedule_send(struct rvt_qp *qp) struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device); + struct hfi1_devdata *dd = ppd->dd; + + if (dd->flags & HFI1_SHUTDOWN) + return true; return iowait_schedule(&priv->s_iowait, ppd->hfi1_wq, priv->s_sde ? diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 243b4ba0b6f6..facff133139a 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -5406,7 +5406,10 @@ static bool _hfi1_schedule_tid_send(struct rvt_qp *qp) struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device); + struct hfi1_devdata *dd = ppd->dd; + + if ((dd->flags & HFI1_SHUTDOWN)) + return true; return iowait_tid_schedule(&priv->s_iowait, ppd->hfi1_wq, priv->s_sde ? diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 343a8b8361e7..6f99ed03d88e 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -511,7 +511,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, mdev_port_num); if (err) goto out; - ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet); + ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability); eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); props->active_width = IB_WIDTH_4X; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index f939c9b769f0..e050eade97a1 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -2668,6 +2668,10 @@ static int process_create_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (qp_type == IB_QPT_RAW_PACKET && attr->rwq_ind_tbl) return (create_flags) ? -EINVAL : 0; + process_create_flag(dev, &create_flags, IB_QP_CREATE_NETIF_QP, + mlx5_get_flow_namespace(dev->mdev, + MLX5_FLOW_NAMESPACE_BYPASS), + qp); process_create_flag(dev, &create_flags, IB_QP_CREATE_INTEGRITY_EN, MLX5_CAP_GEN(mdev, sho), qp); @@ -3001,11 +3005,12 @@ destroy_qp: mlx5_ib_destroy_dct(qp); } else { /* - * The two lines below are temp solution till QP allocation + * These lines below are temp solution till QP allocation * will be moved to be under IB/core responsiblity. */ qp->ibqp.send_cq = attr->send_cq; qp->ibqp.recv_cq = attr->recv_cq; + qp->ibqp.pd = pd; destroy_qp_common(dev, qp, udata); } diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index a0b8cc643c5c..ed60c9e4643e 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -67,12 +67,13 @@ static int siw_device_register(struct siw_device *sdev, const char *name) static int dev_id = 1; int rv; + sdev->vendor_part_id = dev_id++; + rv = ib_register_device(base_dev, name); if (rv) { pr_warn("siw: device registration error %d\n", rv); return rv; } - sdev->vendor_part_id = dev_id++; siw_dbg(base_dev, "HWaddr=%pM\n", sdev->netdev->dev_addr); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index b510f67dfa49..6dc49ed8377a 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -211,7 +211,7 @@ config INTEL_IOMMU_DEBUGFS config INTEL_IOMMU_SVM bool "Support for Shared Virtual Memory with Intel IOMMU" - depends on INTEL_IOMMU && X86 + depends on INTEL_IOMMU && X86_64 select PCI_PASID select PCI_PRI select MMU_NOTIFIER diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index cc46dff98fa0..683b812c5c47 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -898,7 +898,8 @@ int __init detect_intel_iommu(void) if (!ret) ret = dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl, &validate_drhd_cb); - if (!ret && !no_iommu && !iommu_detected && !dmar_disabled) { + if (!ret && !no_iommu && !iommu_detected && + (!dmar_disabled || dmar_platform_optin())) { iommu_detected = 1; /* Make sure ACS will be enabled */ pci_request_acs(); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9129663a7406..d759e7234e98 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -612,6 +612,12 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) return g_iommus[iommu_id]; } +static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu) +{ + return sm_supported(iommu) ? + ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap); +} + static void domain_update_iommu_coherency(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; @@ -623,7 +629,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) for_each_domain_iommu(i, domain) { found = true; - if (!ecap_coherent(g_iommus[i]->ecap)) { + if (!iommu_paging_structure_coherency(g_iommus[i])) { domain->iommu_coherency = 0; break; } @@ -634,7 +640,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) /* No hardware attached; use lowest common denominator */ rcu_read_lock(); for_each_active_iommu(iommu, drhd) { - if (!ecap_coherent(iommu->ecap)) { + if (!iommu_paging_structure_coherency(iommu)) { domain->iommu_coherency = 0; break; } @@ -921,7 +927,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; if (domain_use_first_level(domain)) - pteval |= DMA_FL_PTE_XD; + pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US; if (cmpxchg64(&pte->val, 0ULL, pteval)) /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); @@ -1951,7 +1957,6 @@ static inline void context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) { context->hi |= pasid & ((1 << 20) - 1); - context->hi |= (1 << 20); } /* @@ -2095,7 +2100,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain, context_set_fault_enable(context); context_set_present(context); - domain_flush_cache(domain, context, sizeof(*context)); + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(context, sizeof(*context)); /* * It's a non-present to present mapping. If hardware doesn't cache @@ -2243,7 +2249,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP); if (domain_use_first_level(domain)) - attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD; + attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD | DMA_FL_PTE_US; if (!sg) { sg_res = nr_pages; @@ -2695,7 +2701,9 @@ static int __init si_domain_init(int hw) end >> agaw_to_width(si_domain->agaw))) continue; - ret = iommu_domain_identity_map(si_domain, start, end); + ret = iommu_domain_identity_map(si_domain, + mm_to_dma_pfn(start >> PAGE_SHIFT), + mm_to_dma_pfn(end >> PAGE_SHIFT)); if (ret) return ret; } @@ -6021,6 +6029,23 @@ intel_iommu_domain_set_attr(struct iommu_domain *domain, return ret; } +/* + * Check that the device does not live on an external facing PCI port that is + * marked as untrusted. Such devices should not be able to apply quirks and + * thus not be able to bypass the IOMMU restrictions. + */ +static bool risky_device(struct pci_dev *pdev) +{ + if (pdev->untrusted) { + pci_info(pdev, + "Skipping IOMMU quirk for dev [%04X:%04X] on untrusted PCI link\n", + pdev->vendor, pdev->device); + pci_info(pdev, "Please check with your BIOS/Platform vendor about this\n"); + return true; + } + return false; +} + const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, .domain_alloc = intel_iommu_domain_alloc, @@ -6060,6 +6085,9 @@ const struct iommu_ops intel_iommu_ops = { static void quirk_iommu_igfx(struct pci_dev *dev) { + if (risky_device(dev)) + return; + pci_info(dev, "Disabling IOMMU for graphics on this chipset\n"); dmar_map_gfx = 0; } @@ -6101,6 +6129,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx); static void quirk_iommu_rwbf(struct pci_dev *dev) { + if (risky_device(dev)) + return; + /* * Mobile 4 Series Chipset neglects to set RWBF capability, * but needs it. Same seems to hold for the desktop versions. @@ -6131,6 +6162,9 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev) { unsigned short ggc; + if (risky_device(dev)) + return; + if (pci_read_config_word(dev, GGC, &ggc)) return; @@ -6164,6 +6198,12 @@ static void __init check_tylersburg_isoch(void) pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL); if (!pdev) return; + + if (risky_device(pdev)) { + pci_dev_put(pdev); + return; + } + pci_dev_put(pdev); /* System Management Registers. Might be hidden, in which case @@ -6173,6 +6213,11 @@ static void __init check_tylersburg_isoch(void) if (!pdev) return; + if (risky_device(pdev)) { + pci_dev_put(pdev); + return; + } + if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) { pci_dev_put(pdev); return; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 29fead208cad..216b3b8392b5 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -563,7 +563,7 @@ config LOONGSON_PCH_PIC Support for the Loongson PCH PIC Controller. config LOONGSON_PCH_MSI - bool "Loongson PCH PIC Controller" + bool "Loongson PCH MSI Controller" depends on MACH_LOONGSON64 || COMPILE_TEST depends on PCI default MACH_LOONGSON64 diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cd685f521c77..beac4caefad9 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3797,10 +3797,10 @@ static void its_wait_vpt_parse_complete(void) if (!gic_rdists->has_vpend_valid_dirty) return; - WARN_ON_ONCE(readq_relaxed_poll_timeout(vlpi_base + GICR_VPENDBASER, - val, - !(val & GICR_VPENDBASER_Dirty), - 10, 500)); + WARN_ON_ONCE(readq_relaxed_poll_timeout_atomic(vlpi_base + GICR_VPENDBASER, + val, + !(val & GICR_VPENDBASER_Dirty), + 10, 500)); } static void its_vpe_schedule(struct its_vpe *vpe) @@ -4054,16 +4054,24 @@ static void its_vpe_4_1_deschedule(struct its_vpe *vpe, u64 val; if (info->req_db) { + unsigned long flags; + /* * vPE is going to block: make the vPE non-resident with * PendingLast clear and DB set. The GIC guarantees that if * we read-back PendingLast clear, then a doorbell will be * delivered when an interrupt comes. + * + * Note the locking to deal with the concurrent update of + * pending_last from the doorbell interrupt handler that can + * run concurrently. */ + raw_spin_lock_irqsave(&vpe->vpe_lock, flags); val = its_clear_vpend_valid(vlpi_base, GICR_VPENDBASER_PendingLast, GICR_VPENDBASER_4_1_DB); vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast); + raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags); } else { /* * We're not blocking, so just make the vPE non-resident diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 00de05abd3c3..c17fabd6741e 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -329,10 +329,8 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { - void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3); - unsigned int cpu, shift = (gic_irq(d) % 4) * 8; - u32 val, mask, bit; - unsigned long flags; + void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d); + unsigned int cpu; if (!force) cpu = cpumask_any_and(mask_val, cpu_online_mask); @@ -342,13 +340,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids) return -EINVAL; - gic_lock_irqsave(flags); - mask = 0xff << shift; - bit = gic_cpu_map[cpu] << shift; - val = readl_relaxed(reg) & ~mask; - writel_relaxed(val | bit, reg); - gic_unlock_irqrestore(flags); - + writeb_relaxed(gic_cpu_map[cpu], reg); irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK_DONE; diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index a6f97fa6ff69..8017f6d32d52 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -99,7 +99,7 @@ static int __init riscv_intc_init(struct device_node *node, hartid = riscv_of_parent_hartid(node); if (hartid < 0) { - pr_warn("unable to fine hart id for %pOF\n", node); + pr_warn("unable to find hart id for %pOF\n", node); return 0; } diff --git a/drivers/isdn/capi/Kconfig b/drivers/isdn/capi/Kconfig index cc408ad9aafb..fdb43a632215 100644 --- a/drivers/isdn/capi/Kconfig +++ b/drivers/isdn/capi/Kconfig @@ -5,7 +5,7 @@ config ISDN_CAPI This provides CAPI (the Common ISDN Application Programming Interface) Version 2.0, a standard making it easy for programs to access ISDN hardware in a device independent way. (For details see - <http://www.capi.org/>.) CAPI supports making and accepting voice + <https://www.capi.org/>.) CAPI supports making and accepting voice and data connections, controlling call options and protocols, as well as ISDN supplementary services like call forwarding or three-party conferences (if supported by the specific hardware diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index ac83f5002ce5..489935d5f22d 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1471,7 +1471,7 @@ static void retrieve_deps(struct dm_table *table, /* * Check we have enough space. */ - needed = sizeof(*deps) + (sizeof(*deps->dev) * count); + needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; return; diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index f60c02512121..85e0daabad49 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -146,10 +146,6 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig) */ static void rq_completed(struct mapped_device *md) { - /* nudge anyone waiting on suspend queue */ - if (unlikely(wq_has_sleeper(&md->wait))) - wake_up(&md->wait); - /* * dm_put() must be at the end of this function. See the comment above */ diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 74f3c506f084..5358894bb9fd 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -282,6 +282,8 @@ static int persistent_memory_claim(struct dm_writecache *wc) while (daa-- && i < p) { pages[i++] = pfn_t_to_page(pfn); pfn.val++; + if (!(i & 15)) + cond_resched(); } } while (i < p); wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL); @@ -849,10 +851,14 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_ if (likely(!e->write_in_progress)) { if (!discarded_something) { - writecache_wait_for_ios(wc, READ); - writecache_wait_for_ios(wc, WRITE); + if (!WC_MODE_PMEM(wc)) { + writecache_wait_for_ios(wc, READ); + writecache_wait_for_ios(wc, WRITE); + } discarded_something = true; } + if (!writecache_entry_is_committed(wc, e)) + wc->uncommitted_blocks--; writecache_free_entry(wc, e); } @@ -2260,6 +2266,12 @@ invalid_optional: } if (WC_MODE_PMEM(wc)) { + if (!dax_synchronous(wc->ssd_dev->dax_dev)) { + r = -EOPNOTSUPP; + ti->error = "Asynchronous persistent memory not supported as pmem cache"; + goto bad; + } + r = persistent_memory_claim(wc); if (r) { ti->error = "Unable to map persistent memory for cache"; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 130b5a6d9f12..b298fefb022e 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1078,7 +1078,8 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb, nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + zmd->zone_nr_blocks - 1) >> zmd->zone_nr_blocks_shift; if (!nr_meta_zones || - nr_meta_zones >= zmd->nr_rnd_zones) { + (zmd->nr_devs <= 1 && nr_meta_zones >= zmd->nr_rnd_zones) || + (zmd->nr_devs > 1 && nr_meta_zones >= zmd->nr_cache_zones)) { dmz_dev_err(dev, "Invalid number of metadata blocks"); return -ENXIO; } @@ -1949,7 +1950,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd, unsigned int idx, bool idle) { struct dm_zone *dzone = NULL; - struct dm_zone *zone, *last = NULL; + struct dm_zone *zone, *maxw_z = NULL; struct list_head *zone_list; /* If we have cache zones select from the cache zone list */ @@ -1961,18 +1962,37 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd, } else zone_list = &zmd->dev[idx].map_rnd_list; + /* + * Find the buffer zone with the heaviest weight or the first (oldest) + * data zone that can be reclaimed. + */ list_for_each_entry(zone, zone_list, link) { if (dmz_is_buf(zone)) { dzone = zone->bzone; - if (dzone->dev->dev_idx != idx) - continue; - if (!last) { - last = dzone; + if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx) continue; - } - if (last->weight < dzone->weight) + if (!maxw_z || maxw_z->weight < dzone->weight) + maxw_z = dzone; + } else { + dzone = zone; + if (dmz_lock_zone_reclaim(dzone)) + return dzone; + } + } + + if (maxw_z && dmz_lock_zone_reclaim(maxw_z)) + return maxw_z; + + /* + * If we come here, none of the zones inspected could be locked for + * reclaim. Try again, being more aggressive, that is, find the + * first zone that can be reclaimed regardless of its weitght. + */ + list_for_each_entry(zone, zone_list, link) { + if (dmz_is_buf(zone)) { + dzone = zone->bzone; + if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx) continue; - dzone = last; } else dzone = zone; if (dmz_lock_zone_reclaim(dzone)) @@ -2006,7 +2026,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd, struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd, unsigned int dev_idx, bool idle) { - struct dm_zone *zone; + struct dm_zone *zone = NULL; /* * Search for a zone candidate to reclaim: 2 cases are possible. @@ -2019,7 +2039,7 @@ struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd, dmz_lock_map(zmd); if (list_empty(&zmd->reserved_seq_zones_list)) zone = dmz_get_seq_zone_for_reclaim(zmd, dev_idx); - else + if (!zone) zone = dmz_get_rnd_zone_for_reclaim(zmd, dev_idx, idle); dmz_unlock_map(zmd); @@ -2197,8 +2217,15 @@ struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned int dev_idx, { struct list_head *list; struct dm_zone *zone; - int i = 0; + int i; + + /* Schedule reclaim to ensure free zones are available */ + if (!(flags & DMZ_ALLOC_RECLAIM)) { + for (i = 0; i < zmd->nr_devs; i++) + dmz_schedule_reclaim(zmd->dev[i].reclaim); + } + i = 0; again: if (flags & DMZ_ALLOC_CACHE) list = &zmd->unmap_cache_list; diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index 2261b4dd60b7..9c0ecc9568a4 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -377,6 +377,7 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) dmz_metadata_label(zmd), zrc->dev_idx); return -EBUSY; } + rzone = dzone; start = jiffies; if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) { @@ -391,8 +392,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) */ ret = dmz_reclaim_rnd_data(zrc, dzone); } - rzone = dzone; - } else { struct dm_zone *bzone = dzone->bzone; sector_t chunk_block = 0; @@ -415,7 +414,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) * be later reclaimed. */ ret = dmz_reclaim_seq_data(zrc, dzone); - rzone = dzone; } } out: @@ -458,6 +456,8 @@ static unsigned int dmz_reclaim_percentage(struct dmz_reclaim *zrc) nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx); nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx); } + if (nr_unmap <= 1) + return 0; return nr_unmap * 100 / nr_zones; } @@ -503,7 +503,7 @@ static void dmz_reclaim_work(struct work_struct *work) { struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work); struct dmz_metadata *zmd = zrc->metadata; - unsigned int p_unmap, nr_unmap_rnd = 0, nr_rnd = 0; + unsigned int p_unmap; int ret; if (dmz_dev_is_dying(zmd)) @@ -529,9 +529,6 @@ static void dmz_reclaim_work(struct work_struct *work) zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2); } - nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx); - nr_rnd = dmz_nr_rnd_zones(zmd, zrc->dev_idx); - DMDEBUG("(%s/%u): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u random)", dmz_metadata_label(zmd), zrc->dev_idx, zrc->kc_throttle.throttle, diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index a907a9446c0b..42aa5139df7c 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -400,15 +400,7 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); struct dmz_metadata *zmd = dmz->metadata; struct dm_zone *zone; - int i, ret; - - /* - * Write may trigger a zone allocation. So make sure the - * allocation can succeed. - */ - if (bio_op(bio) == REQ_OP_WRITE) - for (i = 0; i < dmz->nr_ddevs; i++) - dmz_schedule_reclaim(dmz->dev[i].reclaim); + int ret; dmz_lock_metadata(zmd); @@ -890,7 +882,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) } /* Set target (no write same support) */ - ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata) << 9; + ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata); ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_write_zeroes_bios = 1; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 109e81f33edb..52449afd58eb 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/blkpg.h> #include <linux/bio.h> @@ -654,28 +655,6 @@ static void free_tio(struct dm_target_io *tio) bio_put(&tio->clone); } -static bool md_in_flight_bios(struct mapped_device *md) -{ - int cpu; - struct hd_struct *part = &dm_disk(md)->part0; - long sum = 0; - - for_each_possible_cpu(cpu) { - sum += part_stat_local_read_cpu(part, in_flight[0], cpu); - sum += part_stat_local_read_cpu(part, in_flight[1], cpu); - } - - return sum != 0; -} - -static bool md_in_flight(struct mapped_device *md) -{ - if (queue_is_mq(md->queue)) - return blk_mq_queue_inflight(md->queue); - else - return md_in_flight_bios(md); -} - u64 dm_start_time_ns_from_clone(struct bio *bio) { struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); @@ -1009,6 +988,7 @@ static void clone_endio(struct bio *bio) struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; + struct bio *orig_bio = io->orig_bio; if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) { if (bio_op(bio) == REQ_OP_DISCARD && @@ -1022,6 +1002,18 @@ static void clone_endio(struct bio *bio) disable_write_zeroes(md); } + /* + * For zone-append bios get offset in zone of the written + * sector and add that to the original bio sector pos. + */ + if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) { + sector_t written_sector = bio->bi_iter.bi_sector; + struct request_queue *q = orig_bio->bi_disk->queue; + u64 mask = (u64)blk_queue_zone_sectors(q) - 1; + + orig_bio->bi_iter.bi_sector += written_sector & mask; + } + if (endio) { int r = endio(tio->ti, bio, &error); switch (r) { @@ -1452,9 +1444,6 @@ static int __send_empty_flush(struct clone_info *ci) BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); - - bio_disassociate_blkg(ci->bio); - return 0; } @@ -1642,6 +1631,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.bio = &flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); + bio_uninit(ci.bio); /* dec_pending submits any data associated with flush */ } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; @@ -1716,6 +1706,7 @@ static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map, ci.bio = &flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); + bio_uninit(ci.bio); /* dec_pending submits any data associated with flush */ } else { struct dm_target_io *tio; @@ -2457,15 +2448,29 @@ void dm_put(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_put); -static int dm_wait_for_completion(struct mapped_device *md, long task_state) +static bool md_in_flight_bios(struct mapped_device *md) +{ + int cpu; + struct hd_struct *part = &dm_disk(md)->part0; + long sum = 0; + + for_each_possible_cpu(cpu) { + sum += part_stat_local_read_cpu(part, in_flight[0], cpu); + sum += part_stat_local_read_cpu(part, in_flight[1], cpu); + } + + return sum != 0; +} + +static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state) { int r = 0; DEFINE_WAIT(wait); - while (1) { + while (true) { prepare_to_wait(&md->wait, &wait, task_state); - if (!md_in_flight(md)) + if (!md_in_flight_bios(md)) break; if (signal_pending_state(task_state, current)) { @@ -2480,6 +2485,28 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state) return r; } +static int dm_wait_for_completion(struct mapped_device *md, long task_state) +{ + int r = 0; + + if (!queue_is_mq(md->queue)) + return dm_wait_for_bios_completion(md, task_state); + + while (true) { + if (!blk_mq_queue_inflight(md->queue)) + break; + + if (signal_pending_state(task_state, current)) { + r = -EINTR; + break; + } + + msleep(5); + } + + return r; +} + /* * Process the deferred bios */ @@ -2913,17 +2940,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast); int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned cookie) { + int r; + unsigned noio_flag; char udev_cookie[DM_COOKIE_LENGTH]; char *envp[] = { udev_cookie, NULL }; + noio_flag = memalloc_noio_save(); + if (!cookie) - return kobject_uevent(&disk_to_dev(md->disk)->kobj, action); + r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action); else { snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u", DM_COOKIE_ENV_VAR_NAME, cookie); - return kobject_uevent_env(&disk_to_dev(md->disk)->kobj, - action, envp); + r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj, + action, envp); } + + memalloc_noio_restore(noio_flag); + + return r; } uint32_t dm_next_uevent_seq(struct mapped_device *md) diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c index a4ee6b86663e..b91e472ee764 100644 --- a/drivers/media/platform/omap3isp/isp.c +++ b/drivers/media/platform/omap3isp/isp.c @@ -39,8 +39,6 @@ * Troy Laramy <t-laramy@ti.com> */ -#include <asm/cacheflush.h> - #include <linux/clk.h> #include <linux/clkdev.h> #include <linux/delay.h> diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c index 10c214bd0903..1ac9aef70dff 100644 --- a/drivers/media/platform/omap3isp/ispvideo.c +++ b/drivers/media/platform/omap3isp/ispvideo.c @@ -18,7 +18,6 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> -#include <asm/cacheflush.h> #include <media/v4l2-dev.h> #include <media/v4l2-ioctl.h> diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index 68aea22f2b89..5216487db4fb 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -1324,13 +1324,13 @@ mpt_host_page_alloc(MPT_ADAPTER *ioc, pIOCInit_t ioc_init) return 0; /* fw doesn't need any host buffers */ /* spin till we get enough memory */ - while(host_page_buffer_sz > 0) { - - if((ioc->HostPageBuffer = pci_alloc_consistent( - ioc->pcidev, - host_page_buffer_sz, - &ioc->HostPageBuffer_dma)) != NULL) { - + while (host_page_buffer_sz > 0) { + ioc->HostPageBuffer = + dma_alloc_coherent(&ioc->pcidev->dev, + host_page_buffer_sz, + &ioc->HostPageBuffer_dma, + GFP_KERNEL); + if (ioc->HostPageBuffer) { dinitprintk(ioc, printk(MYIOC_s_DEBUG_FMT "host_page_buffer @ %p, dma @ %x, sz=%d bytes\n", ioc->name, ioc->HostPageBuffer, @@ -2741,8 +2741,8 @@ mpt_adapter_disable(MPT_ADAPTER *ioc) sz = ioc->alloc_sz; dexitprintk(ioc, printk(MYIOC_s_INFO_FMT "free @ %p, sz=%d bytes\n", ioc->name, ioc->alloc, ioc->alloc_sz)); - pci_free_consistent(ioc->pcidev, sz, - ioc->alloc, ioc->alloc_dma); + dma_free_coherent(&ioc->pcidev->dev, sz, ioc->alloc, + ioc->alloc_dma); ioc->reply_frames = NULL; ioc->req_frames = NULL; ioc->alloc = NULL; @@ -2751,8 +2751,8 @@ mpt_adapter_disable(MPT_ADAPTER *ioc) if (ioc->sense_buf_pool != NULL) { sz = (ioc->req_depth * MPT_SENSE_BUFFER_ALLOC); - pci_free_consistent(ioc->pcidev, sz, - ioc->sense_buf_pool, ioc->sense_buf_pool_dma); + dma_free_coherent(&ioc->pcidev->dev, sz, ioc->sense_buf_pool, + ioc->sense_buf_pool_dma); ioc->sense_buf_pool = NULL; ioc->alloc_total -= sz; } @@ -2802,7 +2802,7 @@ mpt_adapter_disable(MPT_ADAPTER *ioc) "HostPageBuffer free @ %p, sz=%d bytes\n", ioc->name, ioc->HostPageBuffer, ioc->HostPageBuffer_sz)); - pci_free_consistent(ioc->pcidev, ioc->HostPageBuffer_sz, + dma_free_coherent(&ioc->pcidev->dev, ioc->HostPageBuffer_sz, ioc->HostPageBuffer, ioc->HostPageBuffer_dma); ioc->HostPageBuffer = NULL; ioc->HostPageBuffer_sz = 0; @@ -4497,7 +4497,8 @@ PrimeIocFifos(MPT_ADAPTER *ioc) ioc->name, sz, sz, num_chain)); total_size += sz; - mem = pci_alloc_consistent(ioc->pcidev, total_size, &alloc_dma); + mem = dma_alloc_coherent(&ioc->pcidev->dev, total_size, + &alloc_dma, GFP_KERNEL); if (mem == NULL) { printk(MYIOC_s_ERR_FMT "Unable to allocate Reply, Request, Chain Buffers!\n", ioc->name); @@ -4574,8 +4575,8 @@ PrimeIocFifos(MPT_ADAPTER *ioc) spin_unlock_irqrestore(&ioc->FreeQlock, flags); sz = (ioc->req_depth * MPT_SENSE_BUFFER_ALLOC); - ioc->sense_buf_pool = - pci_alloc_consistent(ioc->pcidev, sz, &ioc->sense_buf_pool_dma); + ioc->sense_buf_pool = dma_alloc_coherent(&ioc->pcidev->dev, sz, + &ioc->sense_buf_pool_dma, GFP_KERNEL); if (ioc->sense_buf_pool == NULL) { printk(MYIOC_s_ERR_FMT "Unable to allocate Sense Buffers!\n", ioc->name); @@ -4613,18 +4614,16 @@ out_fail: if (ioc->alloc != NULL) { sz = ioc->alloc_sz; - pci_free_consistent(ioc->pcidev, - sz, - ioc->alloc, ioc->alloc_dma); + dma_free_coherent(&ioc->pcidev->dev, sz, ioc->alloc, + ioc->alloc_dma); ioc->reply_frames = NULL; ioc->req_frames = NULL; ioc->alloc_total -= sz; } if (ioc->sense_buf_pool != NULL) { sz = (ioc->req_depth * MPT_SENSE_BUFFER_ALLOC); - pci_free_consistent(ioc->pcidev, - sz, - ioc->sense_buf_pool, ioc->sense_buf_pool_dma); + dma_free_coherent(&ioc->pcidev->dev, sz, ioc->sense_buf_pool, + ioc->sense_buf_pool_dma); ioc->sense_buf_pool = NULL; } diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c index f0737c57ed5f..1491561d2e5c 100644 --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -118,8 +118,6 @@ int mptscsih_suspend(struct pci_dev *pdev, pm_message_t state); int mptscsih_resume(struct pci_dev *pdev); #endif -#define SNS_LEN(scp) SCSI_SENSE_BUFFERSIZE - /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/ /* @@ -2422,7 +2420,7 @@ mptscsih_copy_sense_data(struct scsi_cmnd *sc, MPT_SCSI_HOST *hd, MPT_FRAME_HDR /* Copy the sense received into the scsi command block. */ req_index = le16_to_cpu(mf->u.frame.hwhdr.msgctxu.fld.req_idx); sense_data = ((u8 *)ioc->sense_buf_pool + (req_index * MPT_SENSE_BUFFER_ALLOC)); - memcpy(sc->sense_buffer, sense_data, SNS_LEN(sc)); + memcpy(sc->sense_buffer, sense_data, MPT_SENSE_BUFFER_ALLOC); /* Log SMART data (asc = 0x5D, non-IM case only) if required. */ diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index f82974a916c3..b0f62cbbdc87 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -62,6 +62,12 @@ static void hl_fence_release(struct dma_fence *fence) container_of(fence, struct hl_cs_compl, base_fence); struct hl_device *hdev = hl_cs_cmpl->hdev; + /* EBUSY means the CS was never submitted and hence we don't have + * an attached hw_sob object that we should handle here + */ + if (fence->error == -EBUSY) + goto free; + if ((hl_cs_cmpl->type == CS_TYPE_SIGNAL) || (hl_cs_cmpl->type == CS_TYPE_WAIT)) { @@ -92,6 +98,7 @@ static void hl_fence_release(struct dma_fence *fence) kref_put(&hl_cs_cmpl->hw_sob->kref, hl_sob_reset); } +free: kfree_rcu(hl_cs_cmpl, base_fence.rcu); } @@ -328,10 +335,16 @@ static void cs_do_release(struct kref *ref) hl_ctx_put(cs->ctx); + /* We need to mark an error for not submitted because in that case + * the dma fence release flow is different. Mainly, we don't need + * to handle hw_sob for signal/wait + */ if (cs->timedout) dma_fence_set_error(cs->fence, -ETIMEDOUT); else if (cs->aborted) dma_fence_set_error(cs->fence, -EIO); + else if (!cs->submitted) + dma_fence_set_error(cs->fence, -EBUSY); dma_fence_signal(cs->fence); dma_fence_put(cs->fence); diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index 3c8dcdfba20c..fc4372c18ce2 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -480,7 +480,7 @@ out: return 0; } -static ssize_t mmu_write(struct file *file, const char __user *buf, +static ssize_t mmu_asid_va_write(struct file *file, const char __user *buf, size_t count, loff_t *f_pos) { struct seq_file *s = file->private_data; @@ -1125,7 +1125,7 @@ static const struct hl_info_list hl_debugfs_list[] = { {"command_submission_jobs", command_submission_jobs_show, NULL}, {"userptr", userptr_show, NULL}, {"vm", vm_show, NULL}, - {"mmu", mmu_show, mmu_write}, + {"mmu", mmu_show, mmu_asid_va_write}, {"engines", engines_show, NULL} }; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 61f88e9884ce..834470d10b46 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -96,7 +96,7 @@ #define GAUDI_NUM_OF_QM_ARB_ERR_CAUSE 3 -#define GAUDI_ARB_WDT_TIMEOUT 0x400000 +#define GAUDI_ARB_WDT_TIMEOUT 0x1000000 static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { "gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3", @@ -1893,6 +1893,8 @@ static void gaudi_init_pci_dma_qman(struct hl_device *hdev, int dma_id, WREG32(mmDMA0_QM_CP_MSG_BASE3_ADDR_LO_0 + q_off, so_base_ws_lo); WREG32(mmDMA0_QM_CP_MSG_BASE3_ADDR_HI_0 + q_off, so_base_ws_hi); + WREG32(mmDMA0_QM_CP_BARRIER_CFG_0 + q_off, 0x100); + /* The following configuration is needed only once per QMAN */ if (qman_id == 0) { /* Configure RAZWI IRQ */ @@ -2725,6 +2727,12 @@ static int gaudi_mmu_init(struct hl_device *hdev) WREG32(mmSTLB_HOP_CONFIGURATION, hdev->mmu_huge_page_opt ? 0x30440 : 0x40440); + /* + * The H/W expects the first PI after init to be 1. After wraparound + * we'll write 0. + */ + gaudi->mmu_cache_inv_pi = 1; + gaudi->hw_cap_initialized |= HW_CAP_MMU; return 0; @@ -3790,6 +3798,25 @@ static int gaudi_validate_dma_pkt_no_mmu(struct hl_device *hdev, src_in_host); } +static int gaudi_validate_load_and_exe_pkt(struct hl_device *hdev, + struct hl_cs_parser *parser, + struct packet_load_and_exe *user_pkt) +{ + u32 cfg; + + cfg = le32_to_cpu(user_pkt->cfg); + + if (cfg & GAUDI_PKT_LOAD_AND_EXE_CFG_DST_MASK) { + dev_err(hdev->dev, + "User not allowed to use Load and Execute\n"); + return -EPERM; + } + + parser->patched_cb_size += sizeof(struct packet_load_and_exe); + + return 0; +} + static int gaudi_validate_cb(struct hl_device *hdev, struct hl_cs_parser *parser, bool is_mmu) { @@ -3838,6 +3865,11 @@ static int gaudi_validate_cb(struct hl_device *hdev, rc = -EPERM; break; + case PACKET_LOAD_AND_EXE: + rc = gaudi_validate_load_and_exe_pkt(hdev, parser, + (struct packet_load_and_exe *) user_pkt); + break; + case PACKET_LIN_DMA: parser->contains_dma_pkt = true; if (is_mmu) @@ -3855,7 +3887,6 @@ static int gaudi_validate_cb(struct hl_device *hdev, case PACKET_FENCE: case PACKET_NOP: case PACKET_ARB_POINT: - case PACKET_LOAD_AND_EXE: parser->patched_cb_size += pkt_size; break; @@ -5994,6 +6025,8 @@ static int gaudi_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard, mutex_lock(&hdev->mmu_cache_lock); /* L0 & L1 invalidation */ + WREG32(mmSTLB_INV_PS, 3); + WREG32(mmSTLB_CACHE_INV, gaudi->mmu_cache_inv_pi++); WREG32(mmSTLB_INV_PS, 2); rc = hl_poll_timeout( diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h index a46530d375fa..41a8d9bff6bf 100644 --- a/drivers/misc/habanalabs/gaudi/gaudiP.h +++ b/drivers/misc/habanalabs/gaudi/gaudiP.h @@ -229,6 +229,8 @@ struct gaudi_internal_qman_info { * @multi_msi_mode: whether we are working in multi MSI single MSI mode. * Multi MSI is possible only with IOMMU enabled. * @ext_queue_idx: helper index for external queues initialization. + * @mmu_cache_inv_pi: PI for MMU cache invalidation flow. The H/W expects an + * 8-bit value so use u8. */ struct gaudi_device { int (*armcp_info_get)(struct hl_device *hdev); @@ -248,6 +250,7 @@ struct gaudi_device { u32 hw_cap_initialized; u8 multi_msi_mode; u8 ext_queue_idx; + u8 mmu_cache_inv_pi; }; void gaudi_init_security(struct hl_device *hdev); diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h b/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h index 9a5800b0086b..0f0cd067bb43 100644 --- a/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h +++ b/drivers/misc/habanalabs/include/gaudi/gaudi_packets.h @@ -197,6 +197,9 @@ struct packet_wait { __le32 ctl; }; +#define GAUDI_PKT_LOAD_AND_EXE_CFG_DST_SHIFT 0 +#define GAUDI_PKT_LOAD_AND_EXE_CFG_DST_MASK 0x00000001 + struct packet_load_and_exe { __le32 cfg; __le32 ctl; diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 9392934e3a06..7becfc768bbc 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -94,6 +94,7 @@ #define MEI_DEV_ID_JSP_N 0x4DE0 /* Jasper Lake Point N */ #define MEI_DEV_ID_TGP_LP 0xA0E0 /* Tiger Lake Point LP */ +#define MEI_DEV_ID_TGP_H 0x43E0 /* Tiger Lake Point H */ #define MEI_DEV_ID_MCC 0x4B70 /* Mule Creek Canyon (EHL) */ #define MEI_DEV_ID_MCC_4 0x4B75 /* Mule Creek Canyon 4 (EHL) */ @@ -107,6 +108,8 @@ # define PCI_CFG_HFS_1_D0I3_MSK 0x80000000 #define PCI_CFG_HFS_2 0x48 #define PCI_CFG_HFS_3 0x60 +# define PCI_CFG_HFS_3_FW_SKU_MSK 0x00000070 +# define PCI_CFG_HFS_3_FW_SKU_SPS 0x00000060 #define PCI_CFG_HFS_4 0x64 #define PCI_CFG_HFS_5 0x68 #define PCI_CFG_HFS_6 0x6C diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index f620442addf5..7649710a2ab9 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1366,7 +1366,7 @@ static bool mei_me_fw_type_nm(struct pci_dev *pdev) #define MEI_CFG_FW_NM \ .quirk_probe = mei_me_fw_type_nm -static bool mei_me_fw_type_sps(struct pci_dev *pdev) +static bool mei_me_fw_type_sps_4(struct pci_dev *pdev) { u32 reg; unsigned int devfn; @@ -1382,7 +1382,36 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev) return (reg & 0xf0000) == 0xf0000; } -#define MEI_CFG_FW_SPS \ +#define MEI_CFG_FW_SPS_4 \ + .quirk_probe = mei_me_fw_type_sps_4 + +/** + * mei_me_fw_sku_sps() - check for sps sku + * + * Read ME FW Status register to check for SPS Firmware. + * The SPS FW is only signaled in pci function 0 + * + * @pdev: pci device + * + * Return: true in case of SPS firmware + */ +static bool mei_me_fw_type_sps(struct pci_dev *pdev) +{ + u32 reg; + u32 fw_type; + unsigned int devfn; + + devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), 0); + pci_bus_read_config_dword(pdev->bus, devfn, PCI_CFG_HFS_3, ®); + trace_mei_pci_cfg_read(&pdev->dev, "PCI_CFG_HFS_3", PCI_CFG_HFS_3, reg); + fw_type = (reg & PCI_CFG_HFS_3_FW_SKU_MSK); + + dev_dbg(&pdev->dev, "fw type is %d\n", fw_type); + + return fw_type == PCI_CFG_HFS_3_FW_SKU_SPS; +} + +#define MEI_CFG_FW_SPS \ .quirk_probe = mei_me_fw_type_sps #define MEI_CFG_FW_VER_SUPP \ @@ -1452,10 +1481,17 @@ static const struct mei_cfg mei_me_pch8_cfg = { }; /* PCH8 Lynx Point with quirk for SPS Firmware exclusion */ -static const struct mei_cfg mei_me_pch8_sps_cfg = { +static const struct mei_cfg mei_me_pch8_sps_4_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_VER_SUPP, - MEI_CFG_FW_SPS, + MEI_CFG_FW_SPS_4, +}; + +/* LBG with quirk for SPS (4.0) Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_4_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS_4, }; /* Cannon Lake and newer devices */ @@ -1465,10 +1501,20 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, }; -/* LBG with quirk for SPS Firmware exclusion */ +/* Cannon Lake with quirk for SPS 5.0 and newer Firmware exclusion */ static const struct mei_cfg mei_me_pch12_sps_cfg = { MEI_CFG_PCH8_HFS, MEI_CFG_FW_VER_SUPP, + MEI_CFG_DMA_128, + MEI_CFG_FW_SPS, +}; + +/* Cannon Lake with quirk for SPS 5.0 and newer Firmware exclusion + * w/o DMA support + */ +static const struct mei_cfg mei_me_pch12_nodma_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, MEI_CFG_FW_SPS, }; @@ -1480,6 +1526,15 @@ static const struct mei_cfg mei_me_pch15_cfg = { MEI_CFG_TRC, }; +/* Tiger Lake with quirk for SPS 5.0 and newer Firmware exclusion */ +static const struct mei_cfg mei_me_pch15_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_DMA_128, + MEI_CFG_TRC, + MEI_CFG_FW_SPS, +}; + /* * mei_cfg_list - A list of platform platform specific configurations. * Note: has to be synchronized with enum mei_cfg_idx. @@ -1492,10 +1547,13 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH7_CFG] = &mei_me_pch7_cfg, [MEI_ME_PCH_CPT_PBG_CFG] = &mei_me_pch_cpt_pbg_cfg, [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, - [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, + [MEI_ME_PCH8_SPS_4_CFG] = &mei_me_pch8_sps_4_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_4_CFG] = &mei_me_pch12_sps_4_cfg, [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, + [MEI_ME_PCH12_SPS_NODMA_CFG] = &mei_me_pch12_nodma_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, + [MEI_ME_PCH15_SPS_CFG] = &mei_me_pch15_sps_cfg, }; const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx) diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index b6b94e211464..6a8973649c49 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (c) 2012-2019, Intel Corporation. All rights reserved. + * Copyright (c) 2012-2020, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver */ @@ -76,14 +76,20 @@ struct mei_me_hw { * with quirk for Node Manager exclusion. * @MEI_ME_PCH8_CFG: Platform Controller Hub Gen8 and newer * client platforms. - * @MEI_ME_PCH8_SPS_CFG: Platform Controller Hub Gen8 and newer + * @MEI_ME_PCH8_SPS_4_CFG: Platform Controller Hub Gen8 and newer * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer - * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_4_CFG:Platform Controller Hub Gen12 up to 4.0 + * servers platforms with quirk for + * SPS firmware exclusion. + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 5.0 and newer * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer + * @MEI_ME_PCH15_SPS_CFG: Platform Controller Hub Gen15 and newer + * servers platforms with quirk for + * SPS firmware exclusion. * @MEI_ME_NUM_CFG: Upper Sentinel. */ enum mei_cfg_idx { @@ -94,10 +100,13 @@ enum mei_cfg_idx { MEI_ME_PCH7_CFG, MEI_ME_PCH_CPT_PBG_CFG, MEI_ME_PCH8_CFG, - MEI_ME_PCH8_SPS_CFG, + MEI_ME_PCH8_SPS_4_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_4_CFG, MEI_ME_PCH12_SPS_CFG, + MEI_ME_PCH12_SPS_NODMA_CFG, MEI_ME_PCH15_CFG, + MEI_ME_PCH15_SPS_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 71f795b510ce..2a3f2fd5df50 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -59,18 +59,18 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, MEI_ME_PCH7_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, MEI_ME_PCH7_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, MEI_ME_PCH7_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_LP, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LPT_HR, MEI_ME_PCH8_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_WPT_LP_2, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_4_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_4_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, @@ -84,8 +84,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_LP_3, MEI_ME_PCH8_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_3, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_SPS_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_3, MEI_ME_PCH12_SPS_NODMA_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)}, @@ -96,6 +96,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_H, MEI_ME_PCH15_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_JSP_N, MEI_ME_PCH15_CFG)}, diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 7eb38d7482c6..08a3b1c05acb 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1146,9 +1146,11 @@ static int meson_mmc_probe(struct platform_device *pdev) mmc->caps |= MMC_CAP_CMD23; if (host->dram_access_quirk) { + /* Limit segments to 1 due to low available sram memory */ + mmc->max_segs = 1; /* Limit to the available sram memory */ - mmc->max_segs = SD_EMMC_SRAM_DATA_BUF_LEN / mmc->max_blk_size; - mmc->max_blk_count = mmc->max_segs; + mmc->max_blk_count = SD_EMMC_SRAM_DATA_BUF_LEN / + mmc->max_blk_size; } else { mmc->max_blk_count = CMD_CFG_LENGTH_MASK; mmc->max_segs = SD_EMMC_DESC_BUF_LEN / diff --git a/drivers/mmc/host/owl-mmc.c b/drivers/mmc/host/owl-mmc.c index 5e20c099fe03..df43f42855e2 100644 --- a/drivers/mmc/host/owl-mmc.c +++ b/drivers/mmc/host/owl-mmc.c @@ -689,7 +689,7 @@ MODULE_DEVICE_TABLE(of, owl_mmc_of_match); static struct platform_driver owl_mmc_driver = { .driver = { .name = "owl_mmc", - .of_match_table = of_match_ptr(owl_mmc_of_match), + .of_match_table = owl_mmc_of_match, }, .probe = owl_mmc_probe, .remove = owl_mmc_remove, diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index b277dd7fbdb5..c0d58e9fcc33 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -618,8 +618,9 @@ static int msm_init_cm_dll(struct sdhci_host *host) config &= ~CORE_CLK_PWRSAVE; writel_relaxed(config, host->ioaddr + msm_offset->core_vendor_spec); - config = msm_host->dll_config; - writel_relaxed(config, host->ioaddr + msm_offset->core_dll_config); + if (msm_host->dll_config) + writel_relaxed(msm_host->dll_config, + host->ioaddr + msm_offset->core_dll_config); if (msm_host->use_14lpp_dll_reset) { config = readl_relaxed(host->ioaddr + diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 76d832a88e0c..7d930569a7df 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -1273,8 +1273,8 @@ int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, return -EROFS; if (!len) return 0; - if (!mtd->oops_panic_write) - mtd->oops_panic_write = true; + if (!master->oops_panic_write) + master->oops_panic_write = true; return master->_panic_write(master, mtd_get_master_ofs(mtd, to), len, retlen, buf); diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index 0a5cb77966cc..f5a53aac3c5f 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -1761,7 +1761,7 @@ static void ns_switch_state(struct nandsim *ns) NS_DBG("switch_state: operation is unknown, try to find it\n"); - if (!ns_find_operation(ns, 0)) + if (ns_find_operation(ns, 0)) return; if ((ns->state & ACTION_MASK) && diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index 94bfba994326..29255476afdb 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -224,7 +224,7 @@ static int xway_nand_remove(struct platform_device *pdev) struct nand_chip *chip = &data->chip; int ret; - ret = mtd_device_unregister(mtd); + ret = mtd_device_unregister(nand_to_mtd(chip)); WARN_ON(ret); nand_cleanup(chip); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2adf6ce20a38..e2d491c4378c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -383,9 +383,14 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, static int bond_ipsec_add_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; - struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave = rtnl_dereference(bond->curr_active_slave); + struct bonding *bond; + struct slave *slave; + if (!bond_dev) + return -EINVAL; + + bond = netdev_priv(bond_dev); + slave = rcu_dereference(bond->curr_active_slave); xs->xso.real_dev = slave->dev; bond->xs = xs; @@ -405,8 +410,14 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs) static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; - struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave = rtnl_dereference(bond->curr_active_slave); + struct bonding *bond; + struct slave *slave; + + if (!bond_dev) + return; + + bond = netdev_priv(bond_dev); + slave = rcu_dereference(bond->curr_active_slave); if (!slave) return; @@ -431,7 +442,7 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct bonding *bond = netdev_priv(bond_dev); - struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); + struct slave *curr_active = rcu_dereference(bond->curr_active_slave); struct net_device *slave_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) @@ -960,12 +971,12 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (old_active == new_active) return; - if (new_active) { #ifdef CONFIG_XFRM_OFFLOAD - if ((BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) && bond->xs) - bond_ipsec_del_sa(bond->xs); + if (old_active && bond->xs) + bond_ipsec_del_sa(bond->xs); #endif /* CONFIG_XFRM_OFFLOAD */ + if (new_active) { new_active->last_link_up = jiffies; if (new_active->link == BOND_LINK_BACK) { @@ -1028,13 +1039,6 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) bond_should_notify_peers(bond); } -#ifdef CONFIG_XFRM_OFFLOAD - if (old_active && bond->xs) { - xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true); - bond_ipsec_add_sa(bond->xs); - } -#endif /* CONFIG_XFRM_OFFLOAD */ - call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); if (should_notify_peers) { bond->send_peer_notif--; @@ -1044,6 +1048,13 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) } } +#ifdef CONFIG_XFRM_OFFLOAD + if (new_active && bond->xs) { + xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true); + bond_ipsec_add_sa(bond->xs); + } +#endif /* CONFIG_XFRM_OFFLOAD */ + /* resend IGMP joins since active slave has changed or * all were sent on curr_active_slave. * resend only if bond is brought up with the affected diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index d0024cb30a7b..468b3c4273c5 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -70,6 +70,7 @@ config NET_DSA_QCA8K config NET_DSA_REALTEK_SMI tristate "Realtek SMI Ethernet switch family support" depends on NET_DSA + select NET_DSA_TAG_RTL4_A select FIXED_PHY select IRQ_DOMAIN select REALTEK_PHY diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 400207c5c7de..f8bc85a6e670 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -280,13 +280,11 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) struct dsa_loop_pdata *pdata = mdiodev->dev.platform_data; struct dsa_loop_priv *ps; struct dsa_switch *ds; + int ret; if (!pdata) return -ENODEV; - dev_info(&mdiodev->dev, "%s: 0x%0x\n", - pdata->name, pdata->enabled_ports); - ds = devm_kzalloc(&mdiodev->dev, sizeof(*ds), GFP_KERNEL); if (!ds) return -ENOMEM; @@ -311,7 +309,12 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) dev_set_drvdata(&mdiodev->dev, ds); - return dsa_register_switch(ds); + ret = dsa_register_switch(ds); + if (!ret) + dev_info(&mdiodev->dev, "%s: 0x%0x\n", + pdata->name, pdata->enabled_ports); + + return ret; } static void dsa_loop_drv_remove(struct mdio_device *mdiodev) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 4202411627f1..8f1d15ea15d9 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1251,6 +1251,9 @@ static int ksz8795_switch_init(struct ksz_device *dev) return -ENOMEM; } + /* set the real number of ports */ + dev->ds->num_ports = dev->port_cnt; + return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index b939e0b82aa0..687d442f3bc7 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1570,6 +1570,9 @@ static int ksz9477_switch_init(struct ksz_device *dev) return -ENOMEM; } + /* set the real number of ports */ + dev->ds->num_ports = dev->port_cnt; + return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 7d050fab0889..7951f52d860d 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -79,6 +79,7 @@ MODULE_DEVICE_TABLE(i2c, ksz9477_i2c_id); static const struct of_device_id ksz9477_dt_ids[] = { { .compatible = "microchip,ksz9477" }, { .compatible = "microchip,ksz9897" }, + { .compatible = "microchip,ksz9893" }, { .compatible = "microchip,ksz9567" }, {}, }; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d995f5bf0d40..6f019955ae42 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2693,6 +2693,31 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_DEFAULT_VLAN, 0); } +static int mv88e6xxx_get_max_mtu(struct dsa_switch *ds, int port) +{ + struct mv88e6xxx_chip *chip = ds->priv; + + if (chip->info->ops->port_set_jumbo_size) + return 10240; + return 1522; +} + +static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int ret = 0; + + mv88e6xxx_reg_lock(chip); + if (chip->info->ops->port_set_jumbo_size) + ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu); + else + if (new_mtu > 1522) + ret = -EINVAL; + mv88e6xxx_reg_unlock(chip); + + return ret; +} + static int mv88e6xxx_port_enable(struct dsa_switch *ds, int port, struct phy_device *phydev) { @@ -5525,6 +5550,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .get_sset_count = mv88e6xxx_get_sset_count, .port_enable = mv88e6xxx_port_enable, .port_disable = mv88e6xxx_port_disable, + .port_max_mtu = mv88e6xxx_get_max_mtu, + .port_change_mtu = mv88e6xxx_change_mtu, .get_mac_eee = mv88e6xxx_get_mac_eee, .set_mac_eee = mv88e6xxx_set_mac_eee, .get_eeprom_len = mv88e6xxx_get_eeprom_len, diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 3d3c2a6fb0c0..5b23bf6ba848 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -10,7 +10,11 @@ config NET_DSA_MSCC_FELIX select NET_DSA_TAG_OCELOT select FSL_ENETC_MDIO help - This driver supports the VSC9959 network switch, which is a member of - the Vitesse / Microsemi / Microchip Ocelot family of switching cores. - It is embedded as a PCIe function of the NXP LS1028A ENETC integrated - endpoint. + This driver supports network switches from the the Vitesse / + Microsemi / Microchip Ocelot family of switching cores that are + connected to their host CPU via Ethernet. + The following switches are supported: + - VSC9959 (Felix): embedded as a PCIe function of the NXP LS1028A + ENETC integrated endpoint. + - VSC9953 (Seville): embedded as a platform device on the + NXP T1040 SoC. diff --git a/drivers/net/dsa/ocelot/Makefile b/drivers/net/dsa/ocelot/Makefile index 37ad403e0b2a..ec57a5a12330 100644 --- a/drivers/net/dsa/ocelot/Makefile +++ b/drivers/net/dsa/ocelot/Makefile @@ -3,4 +3,5 @@ obj-$(CONFIG_NET_DSA_MSCC_FELIX) += mscc_felix.o mscc_felix-objs := \ felix.o \ - felix_vsc9959.o + felix_vsc9959.o \ + seville_vsc9953.o diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 75652ed99b24..c69d9592a2b7 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1,5 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright 2019 NXP Semiconductors + * + * This is an umbrella module for all network switches that are + * register-compatible with Ocelot and that perform I/O to their host CPU + * through an NPI (Node Processor Interface) Ethernet port. */ #include <uapi/linux/if_bridge.h> #include <soc/mscc/ocelot_vcap.h> @@ -9,6 +13,7 @@ #include <soc/mscc/ocelot_ana.h> #include <soc/mscc/ocelot_ptp.h> #include <soc/mscc/ocelot.h> +#include <linux/platform_device.h> #include <linux/packing.h> #include <linux/module.h> #include <linux/of_net.h> @@ -185,37 +190,10 @@ static void felix_phylink_validate(struct dsa_switch *ds, int port, struct phylink_link_state *state) { struct ocelot *ocelot = ds->priv; - struct ocelot_port *ocelot_port = ocelot->ports[port]; - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != ocelot_port->phy_mode) { - bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); - return; - } - - phylink_set_port_modes(mask); - phylink_set(mask, Autoneg); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - phylink_set(mask, 1000baseT_Half); - phylink_set(mask, 1000baseT_Full); - - if (state->interface == PHY_INTERFACE_MODE_INTERNAL || - state->interface == PHY_INTERFACE_MODE_2500BASEX || - state->interface == PHY_INTERFACE_MODE_USXGMII) { - phylink_set(mask, 2500baseT_Full); - phylink_set(mask, 2500baseX_Full); - } + struct felix *felix = ocelot_to_felix(ocelot); - bitmap_and(supported, supported, mask, - __ETHTOOL_LINK_MODE_MASK_NBITS); - bitmap_and(state->advertising, state->advertising, mask, - __ETHTOOL_LINK_MODE_MASK_NBITS); + if (felix->info->phylink_validate) + felix->info->phylink_validate(ocelot, port, supported, state); } static int felix_phylink_mac_pcs_get_state(struct dsa_switch *ds, int port, @@ -249,8 +227,7 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, struct ocelot_port *ocelot_port = ocelot->ports[port]; ocelot_port_writel(ocelot_port, 0, DEV_MAC_ENA_CFG); - ocelot_rmw_rix(ocelot, 0, QSYS_SWITCH_PORT_MODE_PORT_ENA, - QSYS_SWITCH_PORT_MODE, port); + ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 0); } static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, @@ -326,10 +303,8 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, ANA_PORT_PORT_CFG, port); /* Core: Enable port for frame transfer */ - ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE | - QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) | - QSYS_SWITCH_PORT_MODE_PORT_ENA, - QSYS_SWITCH_PORT_MODE, port); + ocelot_fields_write(ocelot, port, + QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); if (felix->info->pcs_link_up) felix->info->pcs_link_up(ocelot, port, link_an_mode, interface, @@ -459,7 +434,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) { struct ocelot *ocelot = &felix->ocelot; phy_interface_t *port_phy_modes; - resource_size_t switch_base; struct resource res; int port, i, err; @@ -490,9 +464,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return err; } - switch_base = pci_resource_start(felix->pdev, - felix->info->switch_pci_bar); - for (i = 0; i < TARGET_MAX; i++) { struct regmap *target; @@ -501,8 +472,8 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) memcpy(&res, &felix->info->target_io_res[i], sizeof(res)); res.flags = IORESOURCE_MEM; - res.start += switch_base; - res.end += switch_base; + res.start += felix->switch_base; + res.end += felix->switch_base; target = ocelot_regmap_init(ocelot, &res); if (IS_ERR(target)) { @@ -524,7 +495,8 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) for (port = 0; port < num_phys_ports; port++) { struct ocelot_port *ocelot_port; - void __iomem *port_regs; + struct regmap *target; + u8 *template; ocelot_port = devm_kzalloc(ocelot->dev, sizeof(struct ocelot_port), @@ -538,21 +510,34 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) memcpy(&res, &felix->info->port_io_res[port], sizeof(res)); res.flags = IORESOURCE_MEM; - res.start += switch_base; - res.end += switch_base; + res.start += felix->switch_base; + res.end += felix->switch_base; - port_regs = devm_ioremap_resource(ocelot->dev, &res); - if (IS_ERR(port_regs)) { + target = ocelot_regmap_init(ocelot, &res); + if (IS_ERR(target)) { dev_err(ocelot->dev, - "failed to map registers for port %d\n", port); + "Failed to map memory space for port %d\n", + port); kfree(port_phy_modes); - return PTR_ERR(port_regs); + return PTR_ERR(target); + } + + template = devm_kzalloc(ocelot->dev, OCELOT_TAG_LEN, + GFP_KERNEL); + if (!template) { + dev_err(ocelot->dev, + "Failed to allocate memory for DSA tag\n"); + kfree(port_phy_modes); + return -ENOMEM; } ocelot_port->phy_mode = port_phy_modes[port]; ocelot_port->ocelot = ocelot; - ocelot_port->regs = port_regs; + ocelot_port->target = target; + ocelot_port->xmit_template = template; ocelot->ports[port] = ocelot_port; + + felix->info->xmit_template_populate(ocelot, port); } kfree(port_phy_modes); @@ -791,7 +776,7 @@ static int felix_port_setup_tc(struct dsa_switch *ds, int port, return -EOPNOTSUPP; } -static const struct dsa_switch_ops felix_switch_ops = { +const struct dsa_switch_ops felix_switch_ops = { .get_tag_protocol = felix_get_tag_protocol, .setup = felix_setup, .teardown = felix_teardown, @@ -834,149 +819,28 @@ static const struct dsa_switch_ops felix_switch_ops = { .port_setup_tc = felix_port_setup_tc, }; -static struct felix_info *felix_instance_tbl[] = { - [FELIX_INSTANCE_VSC9959] = &felix_info_vsc9959, -}; - -static irqreturn_t felix_irq_handler(int irq, void *data) -{ - struct ocelot *ocelot = (struct ocelot *)data; - - /* The INTB interrupt is used for both PTP TX timestamp interrupt - * and preemption status change interrupt on each port. - * - * - Get txtstamp if have - * - TODO: handle preemption. Without handling it, driver may get - * interrupt storm. - */ - - ocelot_get_txtstamp(ocelot); - - return IRQ_HANDLED; -} - -static int felix_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) +static int __init felix_init(void) { - enum felix_instance instance = id->driver_data; - struct dsa_switch *ds; - struct ocelot *ocelot; - struct felix *felix; int err; - if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) { - dev_info(&pdev->dev, "device is disabled, skipping\n"); - return -ENODEV; - } - - err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "device enable failed\n"); - goto err_pci_enable; - } - - /* set up for high or low dma */ - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } - } - - felix = kzalloc(sizeof(struct felix), GFP_KERNEL); - if (!felix) { - err = -ENOMEM; - dev_err(&pdev->dev, "Failed to allocate driver memory\n"); - goto err_alloc_felix; - } - - pci_set_drvdata(pdev, felix); - ocelot = &felix->ocelot; - ocelot->dev = &pdev->dev; - felix->pdev = pdev; - felix->info = felix_instance_tbl[instance]; - - pci_set_master(pdev); - - err = devm_request_threaded_irq(&pdev->dev, pdev->irq, NULL, - &felix_irq_handler, IRQF_ONESHOT, - "felix-intb", ocelot); - if (err) { - dev_err(&pdev->dev, "Failed to request irq\n"); - goto err_alloc_irq; - } - - ocelot->ptp = 1; - - ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL); - if (!ds) { - err = -ENOMEM; - dev_err(&pdev->dev, "Failed to allocate DSA switch\n"); - goto err_alloc_ds; - } - - ds->dev = &pdev->dev; - ds->num_ports = felix->info->num_ports; - ds->num_tx_queues = felix->info->num_tx_queues; - ds->ops = &felix_switch_ops; - ds->priv = ocelot; - felix->ds = ds; + err = pci_register_driver(&felix_vsc9959_pci_driver); + if (err) + return err; - err = dsa_register_switch(ds); - if (err) { - dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err); - goto err_register_ds; - } + err = platform_driver_register(&seville_vsc9953_driver); + if (err) + return err; return 0; - -err_register_ds: - kfree(ds); -err_alloc_ds: -err_alloc_irq: -err_alloc_felix: - kfree(felix); -err_dma: - pci_disable_device(pdev); -err_pci_enable: - return err; } +module_init(felix_init); -static void felix_pci_remove(struct pci_dev *pdev) +static void __exit felix_exit(void) { - struct felix *felix; - - felix = pci_get_drvdata(pdev); - - dsa_unregister_switch(felix->ds); - - kfree(felix->ds); - kfree(felix); - - pci_disable_device(pdev); + pci_unregister_driver(&felix_vsc9959_pci_driver); + platform_driver_unregister(&seville_vsc9953_driver); } - -static struct pci_device_id felix_ids[] = { - { - /* NXP LS1028A */ - PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, 0xEEF0), - .driver_data = FELIX_INSTANCE_VSC9959, - }, - { 0, } -}; -MODULE_DEVICE_TABLE(pci, felix_ids); - -static struct pci_driver felix_pci_driver = { - .name = KBUILD_MODNAME, - .id_table = felix_ids, - .probe = felix_pci_probe, - .remove = felix_pci_remove, -}; - -module_pci_driver(felix_pci_driver); +module_exit(felix_exit); MODULE_DESCRIPTION("Felix Switch driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 00137b64132b..98f14621ac23 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -37,28 +37,42 @@ struct felix_info { int speed, int duplex); void (*pcs_link_state)(struct ocelot *ocelot, int port, struct phylink_link_state *state); + void (*phylink_validate)(struct ocelot *ocelot, int port, + unsigned long *supported, + struct phylink_link_state *state); int (*prevalidate_phy_mode)(struct ocelot *ocelot, int port, phy_interface_t phy_mode); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); void (*port_sched_speed_set)(struct ocelot *ocelot, int port, u32 speed); + void (*xmit_template_populate)(struct ocelot *ocelot, int port); }; -extern struct felix_info felix_info_vsc9959; - -enum felix_instance { - FELIX_INSTANCE_VSC9959 = 0, -}; +extern const struct dsa_switch_ops felix_switch_ops; +extern struct pci_driver felix_vsc9959_pci_driver; +extern struct platform_driver seville_vsc9953_driver; /* DSA glue / front-end for struct ocelot */ struct felix { struct dsa_switch *ds; - struct pci_dev *pdev; - struct felix_info *info; + const struct felix_info *info; struct ocelot ocelot; struct mii_bus *imdio; struct phy_device **pcs; + resource_size_t switch_base; + resource_size_t imdio_base; }; +void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, + struct phylink_link_state *state); +void vsc9959_pcs_config(struct ocelot *ocelot, int port, + unsigned int link_an_mode, + const struct phylink_link_state *state); +void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, + unsigned int link_an_mode, + phy_interface_t interface, + int speed, int duplex); +void vsc9959_mdio_bus_free(struct ocelot *ocelot); + #endif diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 19614537b1ba..1bdf74fd8be4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -8,6 +8,7 @@ #include <soc/mscc/ocelot_ptp.h> #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot.h> +#include <linux/packing.h> #include <net/pkt_sched.h> #include <linux/iopoll.h> #include <linux/pci.h> @@ -329,7 +330,49 @@ static const u32 vsc9959_gcb_regmap[] = { REG(GCB_SOFT_RST, 0x000004), }; -static const u32 *vsc9959_regmap[] = { +static const u32 vsc9959_dev_gmii_regmap[] = { + REG(DEV_CLOCK_CFG, 0x0), + REG(DEV_PORT_MISC, 0x4), + REG(DEV_EVENTS, 0x8), + REG(DEV_EEE_CFG, 0xc), + REG(DEV_RX_PATH_DELAY, 0x10), + REG(DEV_TX_PATH_DELAY, 0x14), + REG(DEV_PTP_PREDICT_CFG, 0x18), + REG(DEV_MAC_ENA_CFG, 0x1c), + REG(DEV_MAC_MODE_CFG, 0x20), + REG(DEV_MAC_MAXLEN_CFG, 0x24), + REG(DEV_MAC_TAGS_CFG, 0x28), + REG(DEV_MAC_ADV_CHK_CFG, 0x2c), + REG(DEV_MAC_IFG_CFG, 0x30), + REG(DEV_MAC_HDX_CFG, 0x34), + REG(DEV_MAC_DBG_CFG, 0x38), + REG(DEV_MAC_FC_MAC_LOW_CFG, 0x3c), + REG(DEV_MAC_FC_MAC_HIGH_CFG, 0x40), + REG(DEV_MAC_STICKY, 0x44), + REG_RESERVED(PCS1G_CFG), + REG_RESERVED(PCS1G_MODE_CFG), + REG_RESERVED(PCS1G_SD_CFG), + REG_RESERVED(PCS1G_ANEG_CFG), + REG_RESERVED(PCS1G_ANEG_NP_CFG), + REG_RESERVED(PCS1G_LB_CFG), + REG_RESERVED(PCS1G_DBG_CFG), + REG_RESERVED(PCS1G_CDET_CFG), + REG_RESERVED(PCS1G_ANEG_STATUS), + REG_RESERVED(PCS1G_ANEG_NP_STATUS), + REG_RESERVED(PCS1G_LINK_STATUS), + REG_RESERVED(PCS1G_LINK_DOWN_CNT), + REG_RESERVED(PCS1G_STICKY), + REG_RESERVED(PCS1G_DEBUG_STATUS), + REG_RESERVED(PCS1G_LPI_CFG), + REG_RESERVED(PCS1G_LPI_WAKE_ERROR_CNT), + REG_RESERVED(PCS1G_LPI_STATUS), + REG_RESERVED(PCS1G_TSTPAT_MODE_CFG), + REG_RESERVED(PCS1G_TSTPAT_STATUS), + REG_RESERVED(DEV_PCS_FX100_CFG), + REG_RESERVED(DEV_PCS_FX100_STATUS), +}; + +static const u32 *vsc9959_regmap[TARGET_MAX] = { [ANA] = vsc9959_ana_regmap, [QS] = vsc9959_qs_regmap, [QSYS] = vsc9959_qsys_regmap, @@ -338,10 +381,11 @@ static const u32 *vsc9959_regmap[] = { [S2] = vsc9959_s2_regmap, [PTP] = vsc9959_ptp_regmap, [GCB] = vsc9959_gcb_regmap, + [DEV_GMII] = vsc9959_dev_gmii_regmap, }; /* Addresses are relative to the PCI device's base address */ -static const struct resource vsc9959_target_io_res[] = { +static const struct resource vsc9959_target_io_res[TARGET_MAX] = { [ANA] = { .start = 0x0280000, .end = 0x028ffff, @@ -426,7 +470,7 @@ static const struct resource vsc9959_imdio_res = { .name = "imdio", }; -static const struct reg_field vsc9959_regfields[] = { +static const struct reg_field vsc9959_regfields[REGFIELD_MAX] = { [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 6, 6), [ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 5), [ANA_ANEVENTS_FLOOD_DISCARD] = REG_FIELD(ANA_ANEVENTS, 30, 30), @@ -460,6 +504,20 @@ static const struct reg_field vsc9959_regfields[] = { [ANA_TABLES_MACTINDX_M_INDEX] = REG_FIELD(ANA_TABLES_MACTINDX, 0, 10), [SYS_RESET_CFG_CORE_ENA] = REG_FIELD(SYS_RESET_CFG, 0, 0), [GCB_SOFT_RST_SWC_RST] = REG_FIELD(GCB_SOFT_RST, 0, 0), + /* Replicated per number of ports (7), register size 4 per port */ + [QSYS_SWITCH_PORT_MODE_PORT_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 14, 14, 7, 4), + [QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 11, 13, 7, 4), + [QSYS_SWITCH_PORT_MODE_YEL_RSRVD] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 10, 10, 7, 4), + [QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 9, 9, 7, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 1, 8, 7, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 0, 0, 7, 4), + [SYS_PORT_MODE_DATA_WO_TS] = REG_FIELD_ID(SYS_PORT_MODE, 5, 6, 7, 4), + [SYS_PORT_MODE_INCL_INJ_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 3, 4, 7, 4), + [SYS_PORT_MODE_INCL_XTR_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 1, 2, 7, 4), + [SYS_PORT_MODE_INCL_HDR_ERR] = REG_FIELD_ID(SYS_PORT_MODE, 0, 0, 7, 4), + [SYS_PAUSE_CFG_PAUSE_START] = REG_FIELD_ID(SYS_PAUSE_CFG, 10, 18, 7, 4), + [SYS_PAUSE_CFG_PAUSE_STOP] = REG_FIELD_ID(SYS_PAUSE_CFG, 1, 9, 7, 4), + [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 7, 4), }; static const struct ocelot_stat_layout vsc9959_stats_layout[] = { @@ -794,9 +852,9 @@ static void vsc9959_pcs_config_usxgmii(struct phy_device *pcs, USXGMII_ADVERTISE_FDX); } -static void vsc9959_pcs_config(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state) +void vsc9959_pcs_config(struct ocelot *ocelot, int port, + unsigned int link_an_mode, + const struct phylink_link_state *state) { struct felix *felix = ocelot_to_felix(ocelot); struct phy_device *pcs = felix->pcs[port]; @@ -907,10 +965,10 @@ static void vsc9959_pcs_link_up_2500basex(struct phy_device *pcs, phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE); } -static void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex) +void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, + unsigned int link_an_mode, + phy_interface_t interface, + int speed, int duplex) { struct felix *felix = ocelot_to_felix(ocelot); struct phy_device *pcs = felix->pcs[port]; @@ -1038,8 +1096,8 @@ static void vsc9959_pcs_link_state_usxgmii(struct phy_device *pcs, pcs->duplex = DUPLEX_HALF; } -static void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, - struct phylink_link_state *state) +void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, + struct phylink_link_state *state) { struct felix *felix = ocelot_to_felix(ocelot); struct phy_device *pcs = felix->pcs[port]; @@ -1070,6 +1128,43 @@ static void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, vsc9959_pcs_link_state_resolve(pcs, state); } +static void vsc9959_phylink_validate(struct ocelot *ocelot, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + if (state->interface != PHY_INTERFACE_MODE_NA && + state->interface != ocelot_port->phy_mode) { + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + return; + } + + phylink_set_port_modes(mask); + phylink_set(mask, Autoneg); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + phylink_set(mask, 1000baseT_Half); + phylink_set(mask, 1000baseT_Full); + + if (state->interface == PHY_INTERFACE_MODE_INTERNAL || + state->interface == PHY_INTERFACE_MODE_2500BASEX || + state->interface == PHY_INTERFACE_MODE_USXGMII) { + phylink_set(mask, 2500baseT_Full); + phylink_set(mask, 2500baseX_Full); + } + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port, phy_interface_t phy_mode) { @@ -1091,8 +1186,21 @@ static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port, } } +/* Watermark encode + * Bit 8: Unit; 0:1, 1:16 + * Bit 7-0: Value to be multiplied with unit + */ +static u16 vsc9959_wm_enc(u16 value) +{ + if (value >= BIT(8)) + return BIT(8) | (value / 16); + + return value; +} + static const struct ocelot_ops vsc9959_ops = { .reset = vsc9959_reset, + .wm_enc = vsc9959_wm_enc, }; static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) @@ -1100,7 +1208,6 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) struct felix *felix = ocelot_to_felix(ocelot); struct enetc_mdio_priv *mdio_priv; struct device *dev = ocelot->dev; - resource_size_t imdio_base; void __iomem *imdio_regs; struct resource res; struct enetc_hw *hw; @@ -1116,13 +1223,10 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) return -ENOMEM; } - imdio_base = pci_resource_start(felix->pdev, - felix->info->imdio_pci_bar); - memcpy(&res, felix->info->imdio_res, sizeof(res)); res.flags = IORESOURCE_MEM; - res.start += imdio_base; - res.end += imdio_base; + res.start += felix->imdio_base; + res.end += felix->imdio_base; imdio_regs = devm_ioremap_resource(dev, &res); if (IS_ERR(imdio_regs)) { @@ -1182,7 +1286,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) return 0; } -static void vsc9959_mdio_bus_free(struct ocelot *ocelot) +void vsc9959_mdio_bus_free(struct ocelot *ocelot) { struct felix *felix = ocelot_to_felix(ocelot); int port; @@ -1378,7 +1482,25 @@ static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port, } } -struct felix_info felix_info_vsc9959 = { +static void vsc9959_xmit_template_populate(struct ocelot *ocelot, int port) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u8 *template = ocelot_port->xmit_template; + u64 bypass, dest, src; + + /* Set the source port as the CPU port module and not the + * NPI port + */ + src = ocelot->num_phys_ports; + dest = BIT(port); + bypass = true; + + packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0); + packing(template, &dest, 68, 56, OCELOT_TAG_LEN, PACK, 0); + packing(template, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0); +} + +static const struct felix_info felix_info_vsc9959 = { .target_io_res = vsc9959_target_io_res, .port_io_res = vsc9959_port_io_res, .imdio_res = &vsc9959_imdio_res, @@ -1401,7 +1523,148 @@ struct felix_info felix_info_vsc9959 = { .pcs_config = vsc9959_pcs_config, .pcs_link_up = vsc9959_pcs_link_up, .pcs_link_state = vsc9959_pcs_link_state, + .phylink_validate = vsc9959_phylink_validate, .prevalidate_phy_mode = vsc9959_prevalidate_phy_mode, .port_setup_tc = vsc9959_port_setup_tc, .port_sched_speed_set = vsc9959_sched_speed_set, + .xmit_template_populate = vsc9959_xmit_template_populate, +}; + +static irqreturn_t felix_irq_handler(int irq, void *data) +{ + struct ocelot *ocelot = (struct ocelot *)data; + + /* The INTB interrupt is used for both PTP TX timestamp interrupt + * and preemption status change interrupt on each port. + * + * - Get txtstamp if have + * - TODO: handle preemption. Without handling it, driver may get + * interrupt storm. + */ + + ocelot_get_txtstamp(ocelot); + + return IRQ_HANDLED; +} + +static int felix_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct dsa_switch *ds; + struct ocelot *ocelot; + struct felix *felix; + int err; + + if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) { + dev_info(&pdev->dev, "device is disabled, skipping\n"); + return -ENODEV; + } + + err = pci_enable_device(pdev); + if (err) { + dev_err(&pdev->dev, "device enable failed\n"); + goto err_pci_enable; + } + + /* set up for high or low dma */ + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; + } + } + + felix = kzalloc(sizeof(struct felix), GFP_KERNEL); + if (!felix) { + err = -ENOMEM; + dev_err(&pdev->dev, "Failed to allocate driver memory\n"); + goto err_alloc_felix; + } + + pci_set_drvdata(pdev, felix); + ocelot = &felix->ocelot; + ocelot->dev = &pdev->dev; + felix->info = &felix_info_vsc9959; + felix->switch_base = pci_resource_start(pdev, + felix->info->switch_pci_bar); + felix->imdio_base = pci_resource_start(pdev, + felix->info->imdio_pci_bar); + + pci_set_master(pdev); + + err = devm_request_threaded_irq(&pdev->dev, pdev->irq, NULL, + &felix_irq_handler, IRQF_ONESHOT, + "felix-intb", ocelot); + if (err) { + dev_err(&pdev->dev, "Failed to request irq\n"); + goto err_alloc_irq; + } + + ocelot->ptp = 1; + + ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL); + if (!ds) { + err = -ENOMEM; + dev_err(&pdev->dev, "Failed to allocate DSA switch\n"); + goto err_alloc_ds; + } + + ds->dev = &pdev->dev; + ds->num_ports = felix->info->num_ports; + ds->num_tx_queues = felix->info->num_tx_queues; + ds->ops = &felix_switch_ops; + ds->priv = ocelot; + felix->ds = ds; + + err = dsa_register_switch(ds); + if (err) { + dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err); + goto err_register_ds; + } + + return 0; + +err_register_ds: + kfree(ds); +err_alloc_ds: +err_alloc_irq: +err_alloc_felix: + kfree(felix); +err_dma: + pci_disable_device(pdev); +err_pci_enable: + return err; +} + +static void felix_pci_remove(struct pci_dev *pdev) +{ + struct felix *felix; + + felix = pci_get_drvdata(pdev); + + dsa_unregister_switch(felix->ds); + + kfree(felix->ds); + kfree(felix); + + pci_disable_device(pdev); +} + +static struct pci_device_id felix_ids[] = { + { + /* NXP LS1028A */ + PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, 0xEEF0), + }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, felix_ids); + +struct pci_driver felix_vsc9959_pci_driver = { + .name = "mscc_felix", + .id_table = felix_ids, + .probe = felix_pci_probe, + .remove = felix_pci_remove, }; diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c new file mode 100644 index 000000000000..625b1891d955 --- /dev/null +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -0,0 +1,1104 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Distributed Switch Architecture VSC9953 driver + * Copyright (C) 2020, Maxim Kochetkov <fido_max@inbox.ru> + */ +#include <linux/types.h> +#include <soc/mscc/ocelot_vcap.h> +#include <soc/mscc/ocelot_sys.h> +#include <soc/mscc/ocelot.h> +#include <linux/of_platform.h> +#include <linux/packing.h> +#include <linux/iopoll.h> +#include "felix.h" + +#define VSC9953_VCAP_IS2_CNT 1024 +#define VSC9953_VCAP_IS2_ENTRY_WIDTH 376 +#define VSC9953_VCAP_PORT_CNT 10 + +#define MSCC_MIIM_REG_STATUS 0x0 +#define MSCC_MIIM_STATUS_STAT_BUSY BIT(3) +#define MSCC_MIIM_REG_CMD 0x8 +#define MSCC_MIIM_CMD_OPR_WRITE BIT(1) +#define MSCC_MIIM_CMD_OPR_READ BIT(2) +#define MSCC_MIIM_CMD_WRDATA_SHIFT 4 +#define MSCC_MIIM_CMD_REGAD_SHIFT 20 +#define MSCC_MIIM_CMD_PHYAD_SHIFT 25 +#define MSCC_MIIM_CMD_VLD BIT(31) +#define MSCC_MIIM_REG_DATA 0xC +#define MSCC_MIIM_DATA_ERROR (BIT(16) | BIT(17)) + +#define MSCC_PHY_REG_PHY_CFG 0x0 +#define PHY_CFG_PHY_ENA (BIT(0) | BIT(1) | BIT(2) | BIT(3)) +#define PHY_CFG_PHY_COMMON_RESET BIT(4) +#define PHY_CFG_PHY_RESET (BIT(5) | BIT(6) | BIT(7) | BIT(8)) +#define MSCC_PHY_REG_PHY_STATUS 0x4 + +static const u32 vsc9953_ana_regmap[] = { + REG(ANA_ADVLEARN, 0x00b500), + REG(ANA_VLANMASK, 0x00b504), + REG_RESERVED(ANA_PORT_B_DOMAIN), + REG(ANA_ANAGEFIL, 0x00b50c), + REG(ANA_ANEVENTS, 0x00b510), + REG(ANA_STORMLIMIT_BURST, 0x00b514), + REG(ANA_STORMLIMIT_CFG, 0x00b518), + REG(ANA_ISOLATED_PORTS, 0x00b528), + REG(ANA_COMMUNITY_PORTS, 0x00b52c), + REG(ANA_AUTOAGE, 0x00b530), + REG(ANA_MACTOPTIONS, 0x00b534), + REG(ANA_LEARNDISC, 0x00b538), + REG(ANA_AGENCTRL, 0x00b53c), + REG(ANA_MIRRORPORTS, 0x00b540), + REG(ANA_EMIRRORPORTS, 0x00b544), + REG(ANA_FLOODING, 0x00b548), + REG(ANA_FLOODING_IPMC, 0x00b54c), + REG(ANA_SFLOW_CFG, 0x00b550), + REG(ANA_PORT_MODE, 0x00b57c), + REG_RESERVED(ANA_CUT_THRU_CFG), + REG(ANA_PGID_PGID, 0x00b600), + REG(ANA_TABLES_ANMOVED, 0x00b4ac), + REG(ANA_TABLES_MACHDATA, 0x00b4b0), + REG(ANA_TABLES_MACLDATA, 0x00b4b4), + REG_RESERVED(ANA_TABLES_STREAMDATA), + REG(ANA_TABLES_MACACCESS, 0x00b4b8), + REG(ANA_TABLES_MACTINDX, 0x00b4bc), + REG(ANA_TABLES_VLANACCESS, 0x00b4c0), + REG(ANA_TABLES_VLANTIDX, 0x00b4c4), + REG_RESERVED(ANA_TABLES_ISDXACCESS), + REG_RESERVED(ANA_TABLES_ISDXTIDX), + REG(ANA_TABLES_ENTRYLIM, 0x00b480), + REG_RESERVED(ANA_TABLES_PTP_ID_HIGH), + REG_RESERVED(ANA_TABLES_PTP_ID_LOW), + REG_RESERVED(ANA_TABLES_STREAMACCESS), + REG_RESERVED(ANA_TABLES_STREAMTIDX), + REG_RESERVED(ANA_TABLES_SEQ_HISTORY), + REG_RESERVED(ANA_TABLES_SEQ_MASK), + REG_RESERVED(ANA_TABLES_SFID_MASK), + REG_RESERVED(ANA_TABLES_SFIDACCESS), + REG_RESERVED(ANA_TABLES_SFIDTIDX), + REG_RESERVED(ANA_MSTI_STATE), + REG_RESERVED(ANA_OAM_UPM_LM_CNT), + REG_RESERVED(ANA_SG_ACCESS_CTRL), + REG_RESERVED(ANA_SG_CONFIG_REG_1), + REG_RESERVED(ANA_SG_CONFIG_REG_2), + REG_RESERVED(ANA_SG_CONFIG_REG_3), + REG_RESERVED(ANA_SG_CONFIG_REG_4), + REG_RESERVED(ANA_SG_CONFIG_REG_5), + REG_RESERVED(ANA_SG_GCL_GS_CONFIG), + REG_RESERVED(ANA_SG_GCL_TI_CONFIG), + REG_RESERVED(ANA_SG_STATUS_REG_1), + REG_RESERVED(ANA_SG_STATUS_REG_2), + REG_RESERVED(ANA_SG_STATUS_REG_3), + REG(ANA_PORT_VLAN_CFG, 0x000000), + REG(ANA_PORT_DROP_CFG, 0x000004), + REG(ANA_PORT_QOS_CFG, 0x000008), + REG(ANA_PORT_VCAP_CFG, 0x00000c), + REG(ANA_PORT_VCAP_S1_KEY_CFG, 0x000010), + REG(ANA_PORT_VCAP_S2_CFG, 0x00001c), + REG(ANA_PORT_PCP_DEI_MAP, 0x000020), + REG(ANA_PORT_CPU_FWD_CFG, 0x000060), + REG(ANA_PORT_CPU_FWD_BPDU_CFG, 0x000064), + REG(ANA_PORT_CPU_FWD_GARP_CFG, 0x000068), + REG(ANA_PORT_CPU_FWD_CCM_CFG, 0x00006c), + REG(ANA_PORT_PORT_CFG, 0x000070), + REG(ANA_PORT_POL_CFG, 0x000074), + REG_RESERVED(ANA_PORT_PTP_CFG), + REG_RESERVED(ANA_PORT_PTP_DLY1_CFG), + REG_RESERVED(ANA_PORT_PTP_DLY2_CFG), + REG_RESERVED(ANA_PORT_SFID_CFG), + REG(ANA_PFC_PFC_CFG, 0x00c000), + REG_RESERVED(ANA_PFC_PFC_TIMER), + REG_RESERVED(ANA_IPT_OAM_MEP_CFG), + REG_RESERVED(ANA_IPT_IPT), + REG_RESERVED(ANA_PPT_PPT), + REG_RESERVED(ANA_FID_MAP_FID_MAP), + REG(ANA_AGGR_CFG, 0x00c600), + REG(ANA_CPUQ_CFG, 0x00c604), + REG_RESERVED(ANA_CPUQ_CFG2), + REG(ANA_CPUQ_8021_CFG, 0x00c60c), + REG(ANA_DSCP_CFG, 0x00c64c), + REG(ANA_DSCP_REWR_CFG, 0x00c74c), + REG(ANA_VCAP_RNG_TYPE_CFG, 0x00c78c), + REG(ANA_VCAP_RNG_VAL_CFG, 0x00c7ac), + REG_RESERVED(ANA_VRAP_CFG), + REG_RESERVED(ANA_VRAP_HDR_DATA), + REG_RESERVED(ANA_VRAP_HDR_MASK), + REG(ANA_DISCARD_CFG, 0x00c7d8), + REG(ANA_FID_CFG, 0x00c7dc), + REG(ANA_POL_PIR_CFG, 0x00a000), + REG(ANA_POL_CIR_CFG, 0x00a004), + REG(ANA_POL_MODE_CFG, 0x00a008), + REG(ANA_POL_PIR_STATE, 0x00a00c), + REG(ANA_POL_CIR_STATE, 0x00a010), + REG_RESERVED(ANA_POL_STATE), + REG(ANA_POL_FLOWC, 0x00c280), + REG(ANA_POL_HYST, 0x00c2ec), + REG_RESERVED(ANA_POL_MISC_CFG), +}; + +static const u32 vsc9953_qs_regmap[] = { + REG(QS_XTR_GRP_CFG, 0x000000), + REG(QS_XTR_RD, 0x000008), + REG(QS_XTR_FRM_PRUNING, 0x000010), + REG(QS_XTR_FLUSH, 0x000018), + REG(QS_XTR_DATA_PRESENT, 0x00001c), + REG(QS_XTR_CFG, 0x000020), + REG(QS_INJ_GRP_CFG, 0x000024), + REG(QS_INJ_WR, 0x00002c), + REG(QS_INJ_CTRL, 0x000034), + REG(QS_INJ_STATUS, 0x00003c), + REG(QS_INJ_ERR, 0x000040), + REG_RESERVED(QS_INH_DBG), +}; + +static const u32 vsc9953_s2_regmap[] = { + REG(S2_CORE_UPDATE_CTRL, 0x000000), + REG(S2_CORE_MV_CFG, 0x000004), + REG(S2_CACHE_ENTRY_DAT, 0x000008), + REG(S2_CACHE_MASK_DAT, 0x000108), + REG(S2_CACHE_ACTION_DAT, 0x000208), + REG(S2_CACHE_CNT_DAT, 0x000308), + REG(S2_CACHE_TG_DAT, 0x000388), +}; + +static const u32 vsc9953_qsys_regmap[] = { + REG(QSYS_PORT_MODE, 0x003600), + REG(QSYS_SWITCH_PORT_MODE, 0x003630), + REG(QSYS_STAT_CNT_CFG, 0x00365c), + REG(QSYS_EEE_CFG, 0x003660), + REG(QSYS_EEE_THRES, 0x003688), + REG(QSYS_IGR_NO_SHARING, 0x00368c), + REG(QSYS_EGR_NO_SHARING, 0x003690), + REG(QSYS_SW_STATUS, 0x003694), + REG(QSYS_EXT_CPU_CFG, 0x0036c0), + REG_RESERVED(QSYS_PAD_CFG), + REG(QSYS_CPU_GROUP_MAP, 0x0036c8), + REG_RESERVED(QSYS_QMAP), + REG_RESERVED(QSYS_ISDX_SGRP), + REG_RESERVED(QSYS_TIMED_FRAME_ENTRY), + REG_RESERVED(QSYS_TFRM_MISC), + REG_RESERVED(QSYS_TFRM_PORT_DLY), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_1), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_2), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_3), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_4), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_5), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_6), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_7), + REG_RESERVED(QSYS_TFRM_TIMER_CFG_8), + REG(QSYS_RED_PROFILE, 0x003724), + REG(QSYS_RES_QOS_MODE, 0x003764), + REG(QSYS_RES_CFG, 0x004000), + REG(QSYS_RES_STAT, 0x004004), + REG(QSYS_EGR_DROP_MODE, 0x003768), + REG(QSYS_EQ_CTRL, 0x00376c), + REG_RESERVED(QSYS_EVENTS_CORE), + REG_RESERVED(QSYS_QMAXSDU_CFG_0), + REG_RESERVED(QSYS_QMAXSDU_CFG_1), + REG_RESERVED(QSYS_QMAXSDU_CFG_2), + REG_RESERVED(QSYS_QMAXSDU_CFG_3), + REG_RESERVED(QSYS_QMAXSDU_CFG_4), + REG_RESERVED(QSYS_QMAXSDU_CFG_5), + REG_RESERVED(QSYS_QMAXSDU_CFG_6), + REG_RESERVED(QSYS_QMAXSDU_CFG_7), + REG_RESERVED(QSYS_PREEMPTION_CFG), + REG(QSYS_CIR_CFG, 0x000000), + REG_RESERVED(QSYS_EIR_CFG), + REG(QSYS_SE_CFG, 0x000008), + REG(QSYS_SE_DWRR_CFG, 0x00000c), + REG_RESERVED(QSYS_SE_CONNECT), + REG_RESERVED(QSYS_SE_DLB_SENSE), + REG(QSYS_CIR_STATE, 0x000044), + REG_RESERVED(QSYS_EIR_STATE), + REG_RESERVED(QSYS_SE_STATE), + REG(QSYS_HSCH_MISC_CFG, 0x003774), + REG_RESERVED(QSYS_TAG_CONFIG), + REG_RESERVED(QSYS_TAS_PARAM_CFG_CTRL), + REG_RESERVED(QSYS_PORT_MAX_SDU), + REG_RESERVED(QSYS_PARAM_CFG_REG_1), + REG_RESERVED(QSYS_PARAM_CFG_REG_2), + REG_RESERVED(QSYS_PARAM_CFG_REG_3), + REG_RESERVED(QSYS_PARAM_CFG_REG_4), + REG_RESERVED(QSYS_PARAM_CFG_REG_5), + REG_RESERVED(QSYS_GCL_CFG_REG_1), + REG_RESERVED(QSYS_GCL_CFG_REG_2), + REG_RESERVED(QSYS_PARAM_STATUS_REG_1), + REG_RESERVED(QSYS_PARAM_STATUS_REG_2), + REG_RESERVED(QSYS_PARAM_STATUS_REG_3), + REG_RESERVED(QSYS_PARAM_STATUS_REG_4), + REG_RESERVED(QSYS_PARAM_STATUS_REG_5), + REG_RESERVED(QSYS_PARAM_STATUS_REG_6), + REG_RESERVED(QSYS_PARAM_STATUS_REG_7), + REG_RESERVED(QSYS_PARAM_STATUS_REG_8), + REG_RESERVED(QSYS_PARAM_STATUS_REG_9), + REG_RESERVED(QSYS_GCL_STATUS_REG_1), + REG_RESERVED(QSYS_GCL_STATUS_REG_2), +}; + +static const u32 vsc9953_rew_regmap[] = { + REG(REW_PORT_VLAN_CFG, 0x000000), + REG(REW_TAG_CFG, 0x000004), + REG(REW_PORT_CFG, 0x000008), + REG(REW_DSCP_CFG, 0x00000c), + REG(REW_PCP_DEI_QOS_MAP_CFG, 0x000010), + REG_RESERVED(REW_PTP_CFG), + REG_RESERVED(REW_PTP_DLY1_CFG), + REG_RESERVED(REW_RED_TAG_CFG), + REG(REW_DSCP_REMAP_DP1_CFG, 0x000610), + REG(REW_DSCP_REMAP_CFG, 0x000710), + REG_RESERVED(REW_STAT_CFG), + REG_RESERVED(REW_REW_STICKY), + REG_RESERVED(REW_PPT), +}; + +static const u32 vsc9953_sys_regmap[] = { + REG(SYS_COUNT_RX_OCTETS, 0x000000), + REG(SYS_COUNT_RX_MULTICAST, 0x000008), + REG(SYS_COUNT_RX_SHORTS, 0x000010), + REG(SYS_COUNT_RX_FRAGMENTS, 0x000014), + REG(SYS_COUNT_RX_JABBERS, 0x000018), + REG(SYS_COUNT_RX_64, 0x000024), + REG(SYS_COUNT_RX_65_127, 0x000028), + REG(SYS_COUNT_RX_128_255, 0x00002c), + REG(SYS_COUNT_RX_256_1023, 0x000030), + REG(SYS_COUNT_RX_1024_1526, 0x000034), + REG(SYS_COUNT_RX_1527_MAX, 0x000038), + REG(SYS_COUNT_RX_LONGS, 0x000048), + REG(SYS_COUNT_TX_OCTETS, 0x000100), + REG(SYS_COUNT_TX_COLLISION, 0x000110), + REG(SYS_COUNT_TX_DROPS, 0x000114), + REG(SYS_COUNT_TX_64, 0x00011c), + REG(SYS_COUNT_TX_65_127, 0x000120), + REG(SYS_COUNT_TX_128_511, 0x000124), + REG(SYS_COUNT_TX_512_1023, 0x000128), + REG(SYS_COUNT_TX_1024_1526, 0x00012c), + REG(SYS_COUNT_TX_1527_MAX, 0x000130), + REG(SYS_COUNT_TX_AGING, 0x000178), + REG(SYS_RESET_CFG, 0x000318), + REG_RESERVED(SYS_SR_ETYPE_CFG), + REG(SYS_VLAN_ETYPE_CFG, 0x000320), + REG(SYS_PORT_MODE, 0x000324), + REG(SYS_FRONT_PORT_MODE, 0x000354), + REG(SYS_FRM_AGING, 0x00037c), + REG(SYS_STAT_CFG, 0x000380), + REG_RESERVED(SYS_SW_STATUS), + REG_RESERVED(SYS_MISC_CFG), + REG_RESERVED(SYS_REW_MAC_HIGH_CFG), + REG_RESERVED(SYS_REW_MAC_LOW_CFG), + REG_RESERVED(SYS_TIMESTAMP_OFFSET), + REG(SYS_PAUSE_CFG, 0x00044c), + REG(SYS_PAUSE_TOT_CFG, 0x000478), + REG(SYS_ATOP, 0x00047c), + REG(SYS_ATOP_TOT_CFG, 0x0004a8), + REG(SYS_MAC_FC_CFG, 0x0004ac), + REG(SYS_MMGT, 0x0004d4), + REG_RESERVED(SYS_MMGT_FAST), + REG_RESERVED(SYS_EVENTS_DIF), + REG_RESERVED(SYS_EVENTS_CORE), + REG_RESERVED(SYS_CNT), + REG_RESERVED(SYS_PTP_STATUS), + REG_RESERVED(SYS_PTP_TXSTAMP), + REG_RESERVED(SYS_PTP_NXT), + REG_RESERVED(SYS_PTP_CFG), + REG_RESERVED(SYS_RAM_INIT), + REG_RESERVED(SYS_CM_ADDR), + REG_RESERVED(SYS_CM_DATA_WR), + REG_RESERVED(SYS_CM_DATA_RD), + REG_RESERVED(SYS_CM_OP), + REG_RESERVED(SYS_CM_DATA), +}; + +static const u32 vsc9953_gcb_regmap[] = { + REG(GCB_SOFT_RST, 0x000008), + REG(GCB_MIIM_MII_STATUS, 0x0000ac), + REG(GCB_MIIM_MII_CMD, 0x0000b4), + REG(GCB_MIIM_MII_DATA, 0x0000b8), +}; + +static const u32 vsc9953_dev_gmii_regmap[] = { + REG(DEV_CLOCK_CFG, 0x0), + REG(DEV_PORT_MISC, 0x4), + REG_RESERVED(DEV_EVENTS), + REG(DEV_EEE_CFG, 0xc), + REG_RESERVED(DEV_RX_PATH_DELAY), + REG_RESERVED(DEV_TX_PATH_DELAY), + REG_RESERVED(DEV_PTP_PREDICT_CFG), + REG(DEV_MAC_ENA_CFG, 0x10), + REG(DEV_MAC_MODE_CFG, 0x14), + REG(DEV_MAC_MAXLEN_CFG, 0x18), + REG(DEV_MAC_TAGS_CFG, 0x1c), + REG(DEV_MAC_ADV_CHK_CFG, 0x20), + REG(DEV_MAC_IFG_CFG, 0x24), + REG(DEV_MAC_HDX_CFG, 0x28), + REG_RESERVED(DEV_MAC_DBG_CFG), + REG(DEV_MAC_FC_MAC_LOW_CFG, 0x30), + REG(DEV_MAC_FC_MAC_HIGH_CFG, 0x34), + REG(DEV_MAC_STICKY, 0x38), + REG_RESERVED(PCS1G_CFG), + REG_RESERVED(PCS1G_MODE_CFG), + REG_RESERVED(PCS1G_SD_CFG), + REG_RESERVED(PCS1G_ANEG_CFG), + REG_RESERVED(PCS1G_ANEG_NP_CFG), + REG_RESERVED(PCS1G_LB_CFG), + REG_RESERVED(PCS1G_DBG_CFG), + REG_RESERVED(PCS1G_CDET_CFG), + REG_RESERVED(PCS1G_ANEG_STATUS), + REG_RESERVED(PCS1G_ANEG_NP_STATUS), + REG_RESERVED(PCS1G_LINK_STATUS), + REG_RESERVED(PCS1G_LINK_DOWN_CNT), + REG_RESERVED(PCS1G_STICKY), + REG_RESERVED(PCS1G_DEBUG_STATUS), + REG_RESERVED(PCS1G_LPI_CFG), + REG_RESERVED(PCS1G_LPI_WAKE_ERROR_CNT), + REG_RESERVED(PCS1G_LPI_STATUS), + REG_RESERVED(PCS1G_TSTPAT_MODE_CFG), + REG_RESERVED(PCS1G_TSTPAT_STATUS), + REG_RESERVED(DEV_PCS_FX100_CFG), + REG_RESERVED(DEV_PCS_FX100_STATUS), +}; + +static const u32 *vsc9953_regmap[TARGET_MAX] = { + [ANA] = vsc9953_ana_regmap, + [QS] = vsc9953_qs_regmap, + [QSYS] = vsc9953_qsys_regmap, + [REW] = vsc9953_rew_regmap, + [SYS] = vsc9953_sys_regmap, + [S2] = vsc9953_s2_regmap, + [GCB] = vsc9953_gcb_regmap, + [DEV_GMII] = vsc9953_dev_gmii_regmap, +}; + +/* Addresses are relative to the device's base address */ +static const struct resource vsc9953_target_io_res[TARGET_MAX] = { + [ANA] = { + .start = 0x0280000, + .end = 0x028ffff, + .name = "ana", + }, + [QS] = { + .start = 0x0080000, + .end = 0x00800ff, + .name = "qs", + }, + [QSYS] = { + .start = 0x0200000, + .end = 0x021ffff, + .name = "qsys", + }, + [REW] = { + .start = 0x0030000, + .end = 0x003ffff, + .name = "rew", + }, + [SYS] = { + .start = 0x0010000, + .end = 0x001ffff, + .name = "sys", + }, + [S2] = { + .start = 0x0060000, + .end = 0x00603ff, + .name = "s2", + }, + [PTP] = { + .start = 0x0090000, + .end = 0x00900cb, + .name = "ptp", + }, + [GCB] = { + .start = 0x0070000, + .end = 0x00701ff, + .name = "devcpu_gcb", + }, +}; + +static const struct resource vsc9953_port_io_res[] = { + { + .start = 0x0100000, + .end = 0x010ffff, + .name = "port0", + }, + { + .start = 0x0110000, + .end = 0x011ffff, + .name = "port1", + }, + { + .start = 0x0120000, + .end = 0x012ffff, + .name = "port2", + }, + { + .start = 0x0130000, + .end = 0x013ffff, + .name = "port3", + }, + { + .start = 0x0140000, + .end = 0x014ffff, + .name = "port4", + }, + { + .start = 0x0150000, + .end = 0x015ffff, + .name = "port5", + }, + { + .start = 0x0160000, + .end = 0x016ffff, + .name = "port6", + }, + { + .start = 0x0170000, + .end = 0x017ffff, + .name = "port7", + }, + { + .start = 0x0180000, + .end = 0x018ffff, + .name = "port8", + }, + { + .start = 0x0190000, + .end = 0x019ffff, + .name = "port9", + }, +}; + +static const struct reg_field vsc9953_regfields[REGFIELD_MAX] = { + [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 10, 10), + [ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 9), + [ANA_ANEVENTS_AUTOAGE] = REG_FIELD(ANA_ANEVENTS, 24, 24), + [ANA_ANEVENTS_STORM_DROP] = REG_FIELD(ANA_ANEVENTS, 22, 22), + [ANA_ANEVENTS_LEARN_DROP] = REG_FIELD(ANA_ANEVENTS, 21, 21), + [ANA_ANEVENTS_AGED_ENTRY] = REG_FIELD(ANA_ANEVENTS, 20, 20), + [ANA_ANEVENTS_CPU_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 19, 19), + [ANA_ANEVENTS_AUTO_LEARN_FAILED] = REG_FIELD(ANA_ANEVENTS, 18, 18), + [ANA_ANEVENTS_LEARN_REMOVE] = REG_FIELD(ANA_ANEVENTS, 17, 17), + [ANA_ANEVENTS_AUTO_LEARNED] = REG_FIELD(ANA_ANEVENTS, 16, 16), + [ANA_ANEVENTS_AUTO_MOVED] = REG_FIELD(ANA_ANEVENTS, 15, 15), + [ANA_ANEVENTS_CLASSIFIED_DROP] = REG_FIELD(ANA_ANEVENTS, 13, 13), + [ANA_ANEVENTS_CLASSIFIED_COPY] = REG_FIELD(ANA_ANEVENTS, 12, 12), + [ANA_ANEVENTS_VLAN_DISCARD] = REG_FIELD(ANA_ANEVENTS, 11, 11), + [ANA_ANEVENTS_FWD_DISCARD] = REG_FIELD(ANA_ANEVENTS, 10, 10), + [ANA_ANEVENTS_MULTICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 9, 9), + [ANA_ANEVENTS_UNICAST_FLOOD] = REG_FIELD(ANA_ANEVENTS, 8, 8), + [ANA_ANEVENTS_DEST_KNOWN] = REG_FIELD(ANA_ANEVENTS, 7, 7), + [ANA_ANEVENTS_BUCKET3_MATCH] = REG_FIELD(ANA_ANEVENTS, 6, 6), + [ANA_ANEVENTS_BUCKET2_MATCH] = REG_FIELD(ANA_ANEVENTS, 5, 5), + [ANA_ANEVENTS_BUCKET1_MATCH] = REG_FIELD(ANA_ANEVENTS, 4, 4), + [ANA_ANEVENTS_BUCKET0_MATCH] = REG_FIELD(ANA_ANEVENTS, 3, 3), + [ANA_ANEVENTS_CPU_OPERATION] = REG_FIELD(ANA_ANEVENTS, 2, 2), + [ANA_ANEVENTS_DMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 1, 1), + [ANA_ANEVENTS_SMAC_LOOKUP] = REG_FIELD(ANA_ANEVENTS, 0, 0), + [ANA_TABLES_MACACCESS_B_DOM] = REG_FIELD(ANA_TABLES_MACACCESS, 16, 16), + [ANA_TABLES_MACTINDX_BUCKET] = REG_FIELD(ANA_TABLES_MACTINDX, 11, 12), + [ANA_TABLES_MACTINDX_M_INDEX] = REG_FIELD(ANA_TABLES_MACTINDX, 0, 10), + [SYS_RESET_CFG_CORE_ENA] = REG_FIELD(SYS_RESET_CFG, 7, 7), + [SYS_RESET_CFG_MEM_ENA] = REG_FIELD(SYS_RESET_CFG, 6, 6), + [SYS_RESET_CFG_MEM_INIT] = REG_FIELD(SYS_RESET_CFG, 5, 5), + [GCB_SOFT_RST_SWC_RST] = REG_FIELD(GCB_SOFT_RST, 0, 0), + [GCB_MIIM_MII_STATUS_PENDING] = REG_FIELD(GCB_MIIM_MII_STATUS, 2, 2), + [GCB_MIIM_MII_STATUS_BUSY] = REG_FIELD(GCB_MIIM_MII_STATUS, 3, 3), + /* Replicated per number of ports (11), register size 4 per port */ + [QSYS_SWITCH_PORT_MODE_PORT_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 13, 13, 11, 4), + [QSYS_SWITCH_PORT_MODE_YEL_RSRVD] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 10, 10, 11, 4), + [QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 9, 9, 11, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 1, 8, 11, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 0, 0, 11, 4), + [SYS_PORT_MODE_INCL_INJ_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 4, 5, 11, 4), + [SYS_PORT_MODE_INCL_XTR_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 2, 3, 11, 4), + [SYS_PORT_MODE_INCL_HDR_ERR] = REG_FIELD_ID(SYS_PORT_MODE, 0, 0, 11, 4), + [SYS_PAUSE_CFG_PAUSE_START] = REG_FIELD_ID(SYS_PAUSE_CFG, 11, 20, 11, 4), + [SYS_PAUSE_CFG_PAUSE_STOP] = REG_FIELD_ID(SYS_PAUSE_CFG, 1, 10, 11, 4), + [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 11, 4), +}; + +static const struct ocelot_stat_layout vsc9953_stats_layout[] = { + { .offset = 0x00, .name = "rx_octets", }, + { .offset = 0x01, .name = "rx_unicast", }, + { .offset = 0x02, .name = "rx_multicast", }, + { .offset = 0x03, .name = "rx_broadcast", }, + { .offset = 0x04, .name = "rx_shorts", }, + { .offset = 0x05, .name = "rx_fragments", }, + { .offset = 0x06, .name = "rx_jabbers", }, + { .offset = 0x07, .name = "rx_crc_align_errs", }, + { .offset = 0x08, .name = "rx_sym_errs", }, + { .offset = 0x09, .name = "rx_frames_below_65_octets", }, + { .offset = 0x0A, .name = "rx_frames_65_to_127_octets", }, + { .offset = 0x0B, .name = "rx_frames_128_to_255_octets", }, + { .offset = 0x0C, .name = "rx_frames_256_to_511_octets", }, + { .offset = 0x0D, .name = "rx_frames_512_to_1023_octets", }, + { .offset = 0x0E, .name = "rx_frames_1024_to_1526_octets", }, + { .offset = 0x0F, .name = "rx_frames_over_1526_octets", }, + { .offset = 0x10, .name = "rx_pause", }, + { .offset = 0x11, .name = "rx_control", }, + { .offset = 0x12, .name = "rx_longs", }, + { .offset = 0x13, .name = "rx_classified_drops", }, + { .offset = 0x14, .name = "rx_red_prio_0", }, + { .offset = 0x15, .name = "rx_red_prio_1", }, + { .offset = 0x16, .name = "rx_red_prio_2", }, + { .offset = 0x17, .name = "rx_red_prio_3", }, + { .offset = 0x18, .name = "rx_red_prio_4", }, + { .offset = 0x19, .name = "rx_red_prio_5", }, + { .offset = 0x1A, .name = "rx_red_prio_6", }, + { .offset = 0x1B, .name = "rx_red_prio_7", }, + { .offset = 0x1C, .name = "rx_yellow_prio_0", }, + { .offset = 0x1D, .name = "rx_yellow_prio_1", }, + { .offset = 0x1E, .name = "rx_yellow_prio_2", }, + { .offset = 0x1F, .name = "rx_yellow_prio_3", }, + { .offset = 0x20, .name = "rx_yellow_prio_4", }, + { .offset = 0x21, .name = "rx_yellow_prio_5", }, + { .offset = 0x22, .name = "rx_yellow_prio_6", }, + { .offset = 0x23, .name = "rx_yellow_prio_7", }, + { .offset = 0x24, .name = "rx_green_prio_0", }, + { .offset = 0x25, .name = "rx_green_prio_1", }, + { .offset = 0x26, .name = "rx_green_prio_2", }, + { .offset = 0x27, .name = "rx_green_prio_3", }, + { .offset = 0x28, .name = "rx_green_prio_4", }, + { .offset = 0x29, .name = "rx_green_prio_5", }, + { .offset = 0x2A, .name = "rx_green_prio_6", }, + { .offset = 0x2B, .name = "rx_green_prio_7", }, + { .offset = 0x40, .name = "tx_octets", }, + { .offset = 0x41, .name = "tx_unicast", }, + { .offset = 0x42, .name = "tx_multicast", }, + { .offset = 0x43, .name = "tx_broadcast", }, + { .offset = 0x44, .name = "tx_collision", }, + { .offset = 0x45, .name = "tx_drops", }, + { .offset = 0x46, .name = "tx_pause", }, + { .offset = 0x47, .name = "tx_frames_below_65_octets", }, + { .offset = 0x48, .name = "tx_frames_65_to_127_octets", }, + { .offset = 0x49, .name = "tx_frames_128_255_octets", }, + { .offset = 0x4A, .name = "tx_frames_256_511_octets", }, + { .offset = 0x4B, .name = "tx_frames_512_1023_octets", }, + { .offset = 0x4C, .name = "tx_frames_1024_1526_octets", }, + { .offset = 0x4D, .name = "tx_frames_over_1526_octets", }, + { .offset = 0x4E, .name = "tx_yellow_prio_0", }, + { .offset = 0x4F, .name = "tx_yellow_prio_1", }, + { .offset = 0x50, .name = "tx_yellow_prio_2", }, + { .offset = 0x51, .name = "tx_yellow_prio_3", }, + { .offset = 0x52, .name = "tx_yellow_prio_4", }, + { .offset = 0x53, .name = "tx_yellow_prio_5", }, + { .offset = 0x54, .name = "tx_yellow_prio_6", }, + { .offset = 0x55, .name = "tx_yellow_prio_7", }, + { .offset = 0x56, .name = "tx_green_prio_0", }, + { .offset = 0x57, .name = "tx_green_prio_1", }, + { .offset = 0x58, .name = "tx_green_prio_2", }, + { .offset = 0x59, .name = "tx_green_prio_3", }, + { .offset = 0x5A, .name = "tx_green_prio_4", }, + { .offset = 0x5B, .name = "tx_green_prio_5", }, + { .offset = 0x5C, .name = "tx_green_prio_6", }, + { .offset = 0x5D, .name = "tx_green_prio_7", }, + { .offset = 0x5E, .name = "tx_aged", }, + { .offset = 0x80, .name = "drop_local", }, + { .offset = 0x81, .name = "drop_tail", }, + { .offset = 0x82, .name = "drop_yellow_prio_0", }, + { .offset = 0x83, .name = "drop_yellow_prio_1", }, + { .offset = 0x84, .name = "drop_yellow_prio_2", }, + { .offset = 0x85, .name = "drop_yellow_prio_3", }, + { .offset = 0x86, .name = "drop_yellow_prio_4", }, + { .offset = 0x87, .name = "drop_yellow_prio_5", }, + { .offset = 0x88, .name = "drop_yellow_prio_6", }, + { .offset = 0x89, .name = "drop_yellow_prio_7", }, + { .offset = 0x8A, .name = "drop_green_prio_0", }, + { .offset = 0x8B, .name = "drop_green_prio_1", }, + { .offset = 0x8C, .name = "drop_green_prio_2", }, + { .offset = 0x8D, .name = "drop_green_prio_3", }, + { .offset = 0x8E, .name = "drop_green_prio_4", }, + { .offset = 0x8F, .name = "drop_green_prio_5", }, + { .offset = 0x90, .name = "drop_green_prio_6", }, + { .offset = 0x91, .name = "drop_green_prio_7", }, +}; + +static struct vcap_field vsc9953_vcap_is2_keys[] = { + /* Common: 41 bits */ + [VCAP_IS2_TYPE] = { 0, 4}, + [VCAP_IS2_HK_FIRST] = { 4, 1}, + [VCAP_IS2_HK_PAG] = { 5, 8}, + [VCAP_IS2_HK_IGR_PORT_MASK] = { 13, 11}, + [VCAP_IS2_HK_RSV2] = { 24, 1}, + [VCAP_IS2_HK_HOST_MATCH] = { 25, 1}, + [VCAP_IS2_HK_L2_MC] = { 26, 1}, + [VCAP_IS2_HK_L2_BC] = { 27, 1}, + [VCAP_IS2_HK_VLAN_TAGGED] = { 28, 1}, + [VCAP_IS2_HK_VID] = { 29, 12}, + [VCAP_IS2_HK_DEI] = { 41, 1}, + [VCAP_IS2_HK_PCP] = { 42, 3}, + /* MAC_ETYPE / MAC_LLC / MAC_SNAP / OAM common */ + [VCAP_IS2_HK_L2_DMAC] = { 45, 48}, + [VCAP_IS2_HK_L2_SMAC] = { 93, 48}, + /* MAC_ETYPE (TYPE=000) */ + [VCAP_IS2_HK_MAC_ETYPE_ETYPE] = {141, 16}, + [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0] = {157, 16}, + [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1] = {173, 8}, + [VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2] = {181, 3}, + /* MAC_LLC (TYPE=001) */ + [VCAP_IS2_HK_MAC_LLC_L2_LLC] = {141, 40}, + /* MAC_SNAP (TYPE=010) */ + [VCAP_IS2_HK_MAC_SNAP_L2_SNAP] = {141, 40}, + /* MAC_ARP (TYPE=011) */ + [VCAP_IS2_HK_MAC_ARP_SMAC] = { 45, 48}, + [VCAP_IS2_HK_MAC_ARP_ADDR_SPACE_OK] = { 93, 1}, + [VCAP_IS2_HK_MAC_ARP_PROTO_SPACE_OK] = { 94, 1}, + [VCAP_IS2_HK_MAC_ARP_LEN_OK] = { 95, 1}, + [VCAP_IS2_HK_MAC_ARP_TARGET_MATCH] = { 96, 1}, + [VCAP_IS2_HK_MAC_ARP_SENDER_MATCH] = { 97, 1}, + [VCAP_IS2_HK_MAC_ARP_OPCODE_UNKNOWN] = { 98, 1}, + [VCAP_IS2_HK_MAC_ARP_OPCODE] = { 99, 2}, + [VCAP_IS2_HK_MAC_ARP_L3_IP4_DIP] = {101, 32}, + [VCAP_IS2_HK_MAC_ARP_L3_IP4_SIP] = {133, 32}, + [VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP] = {165, 1}, + /* IP4_TCP_UDP / IP4_OTHER common */ + [VCAP_IS2_HK_IP4] = { 45, 1}, + [VCAP_IS2_HK_L3_FRAGMENT] = { 46, 1}, + [VCAP_IS2_HK_L3_FRAG_OFS_GT0] = { 47, 1}, + [VCAP_IS2_HK_L3_OPTIONS] = { 48, 1}, + [VCAP_IS2_HK_IP4_L3_TTL_GT0] = { 49, 1}, + [VCAP_IS2_HK_L3_TOS] = { 50, 8}, + [VCAP_IS2_HK_L3_IP4_DIP] = { 58, 32}, + [VCAP_IS2_HK_L3_IP4_SIP] = { 90, 32}, + [VCAP_IS2_HK_DIP_EQ_SIP] = {122, 1}, + /* IP4_TCP_UDP (TYPE=100) */ + [VCAP_IS2_HK_TCP] = {123, 1}, + [VCAP_IS2_HK_L4_SPORT] = {124, 16}, + [VCAP_IS2_HK_L4_DPORT] = {140, 16}, + [VCAP_IS2_HK_L4_RNG] = {156, 8}, + [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {164, 1}, + [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {165, 1}, + [VCAP_IS2_HK_L4_URG] = {166, 1}, + [VCAP_IS2_HK_L4_ACK] = {167, 1}, + [VCAP_IS2_HK_L4_PSH] = {168, 1}, + [VCAP_IS2_HK_L4_RST] = {169, 1}, + [VCAP_IS2_HK_L4_SYN] = {170, 1}, + [VCAP_IS2_HK_L4_FIN] = {171, 1}, + /* IP4_OTHER (TYPE=101) */ + [VCAP_IS2_HK_IP4_L3_PROTO] = {123, 8}, + [VCAP_IS2_HK_L3_PAYLOAD] = {131, 56}, + /* IP6_STD (TYPE=110) */ + [VCAP_IS2_HK_IP6_L3_TTL_GT0] = { 45, 1}, + [VCAP_IS2_HK_L3_IP6_SIP] = { 46, 128}, + [VCAP_IS2_HK_IP6_L3_PROTO] = {174, 8}, +}; + +static struct vcap_field vsc9953_vcap_is2_actions[] = { + [VCAP_IS2_ACT_HIT_ME_ONCE] = { 0, 1}, + [VCAP_IS2_ACT_CPU_COPY_ENA] = { 1, 1}, + [VCAP_IS2_ACT_CPU_QU_NUM] = { 2, 3}, + [VCAP_IS2_ACT_MASK_MODE] = { 5, 2}, + [VCAP_IS2_ACT_MIRROR_ENA] = { 7, 1}, + [VCAP_IS2_ACT_LRN_DIS] = { 8, 1}, + [VCAP_IS2_ACT_POLICE_ENA] = { 9, 1}, + [VCAP_IS2_ACT_POLICE_IDX] = { 10, 8}, + [VCAP_IS2_ACT_POLICE_VCAP_ONLY] = { 21, 1}, + [VCAP_IS2_ACT_PORT_MASK] = { 22, 10}, + [VCAP_IS2_ACT_ACL_ID] = { 44, 6}, + [VCAP_IS2_ACT_HIT_CNT] = { 50, 32}, +}; + +static const struct vcap_props vsc9953_vcap_props[] = { + [VCAP_IS2] = { + .tg_width = 2, + .sw_count = 4, + .entry_count = VSC9953_VCAP_IS2_CNT, + .entry_width = VSC9953_VCAP_IS2_ENTRY_WIDTH, + .action_count = VSC9953_VCAP_IS2_CNT + + VSC9953_VCAP_PORT_CNT + 2, + .action_width = 101, + .action_type_width = 1, + .action_table = { + [IS2_ACTION_TYPE_NORMAL] = { + .width = 44, + .count = 2 + }, + [IS2_ACTION_TYPE_SMAC_SIP] = { + .width = 6, + .count = 4 + }, + }, + .counter_words = 4, + .counter_width = 32, + }, +}; + +#define VSC9953_INIT_TIMEOUT 50000 +#define VSC9953_GCB_RST_SLEEP 100 +#define VSC9953_SYS_RAMINIT_SLEEP 80 +#define VCS9953_MII_TIMEOUT 10000 + +static int vsc9953_gcb_soft_rst_status(struct ocelot *ocelot) +{ + int val; + + ocelot_field_read(ocelot, GCB_SOFT_RST_SWC_RST, &val); + + return val; +} + +static int vsc9953_sys_ram_init_status(struct ocelot *ocelot) +{ + int val; + + ocelot_field_read(ocelot, SYS_RESET_CFG_MEM_INIT, &val); + + return val; +} + +static int vsc9953_gcb_miim_pending_status(struct ocelot *ocelot) +{ + int val; + + ocelot_field_read(ocelot, GCB_MIIM_MII_STATUS_PENDING, &val); + + return val; +} + +static int vsc9953_gcb_miim_busy_status(struct ocelot *ocelot) +{ + int val; + + ocelot_field_read(ocelot, GCB_MIIM_MII_STATUS_BUSY, &val); + + return val; +} + +static int vsc9953_mdio_write(struct mii_bus *bus, int phy_id, int regnum, + u16 value) +{ + struct ocelot *ocelot = bus->priv; + int err, cmd, val; + + /* Wait while MIIM controller becomes idle */ + err = readx_poll_timeout(vsc9953_gcb_miim_pending_status, ocelot, + val, !val, 10, VCS9953_MII_TIMEOUT); + if (err) { + dev_err(ocelot->dev, "MDIO write: pending timeout\n"); + goto out; + } + + cmd = MSCC_MIIM_CMD_VLD | (phy_id << MSCC_MIIM_CMD_PHYAD_SHIFT) | + (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | + (value << MSCC_MIIM_CMD_WRDATA_SHIFT) | + MSCC_MIIM_CMD_OPR_WRITE; + + ocelot_write(ocelot, cmd, GCB_MIIM_MII_CMD); + +out: + return err; +} + +static int vsc9953_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +{ + struct ocelot *ocelot = bus->priv; + int err, cmd, val; + + /* Wait until MIIM controller becomes idle */ + err = readx_poll_timeout(vsc9953_gcb_miim_pending_status, ocelot, + val, !val, 10, VCS9953_MII_TIMEOUT); + if (err) { + dev_err(ocelot->dev, "MDIO read: pending timeout\n"); + goto out; + } + + /* Write the MIIM COMMAND register */ + cmd = MSCC_MIIM_CMD_VLD | (phy_id << MSCC_MIIM_CMD_PHYAD_SHIFT) | + (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | MSCC_MIIM_CMD_OPR_READ; + + ocelot_write(ocelot, cmd, GCB_MIIM_MII_CMD); + + /* Wait while read operation via the MIIM controller is in progress */ + err = readx_poll_timeout(vsc9953_gcb_miim_busy_status, ocelot, + val, !val, 10, VCS9953_MII_TIMEOUT); + if (err) { + dev_err(ocelot->dev, "MDIO read: busy timeout\n"); + goto out; + } + + val = ocelot_read(ocelot, GCB_MIIM_MII_DATA); + + err = val & 0xFFFF; +out: + return err; +} + +static int vsc9953_reset(struct ocelot *ocelot) +{ + int val, err; + + /* soft-reset the switch core */ + ocelot_field_write(ocelot, GCB_SOFT_RST_SWC_RST, 1); + + err = readx_poll_timeout(vsc9953_gcb_soft_rst_status, ocelot, val, !val, + VSC9953_GCB_RST_SLEEP, VSC9953_INIT_TIMEOUT); + if (err) { + dev_err(ocelot->dev, "timeout: switch core reset\n"); + return err; + } + + /* initialize switch mem ~40us */ + ocelot_field_write(ocelot, SYS_RESET_CFG_MEM_INIT, 1); + ocelot_field_write(ocelot, SYS_RESET_CFG_MEM_ENA, 1); + + err = readx_poll_timeout(vsc9953_sys_ram_init_status, ocelot, val, !val, + VSC9953_SYS_RAMINIT_SLEEP, + VSC9953_INIT_TIMEOUT); + if (err) { + dev_err(ocelot->dev, "timeout: switch sram init\n"); + return err; + } + + /* enable switch core */ + ocelot_field_write(ocelot, SYS_RESET_CFG_MEM_ENA, 1); + ocelot_field_write(ocelot, SYS_RESET_CFG_CORE_ENA, 1); + + return 0; +} + +static void vsc9953_phylink_validate(struct ocelot *ocelot, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + if (state->interface != PHY_INTERFACE_MODE_NA && + state->interface != ocelot_port->phy_mode) { + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + return; + } + + phylink_set_port_modes(mask); + phylink_set(mask, Autoneg); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 100baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 1000baseT_Full); + + if (state->interface == PHY_INTERFACE_MODE_INTERNAL) { + phylink_set(mask, 2500baseT_Full); + phylink_set(mask, 2500baseX_Full); + } + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static int vsc9953_prevalidate_phy_mode(struct ocelot *ocelot, int port, + phy_interface_t phy_mode) +{ + switch (phy_mode) { + case PHY_INTERFACE_MODE_INTERNAL: + if (port != 8 && port != 9) + return -ENOTSUPP; + return 0; + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + /* Not supported on internal to-CPU ports */ + if (port == 8 || port == 9) + return -ENOTSUPP; + return 0; + default: + return -ENOTSUPP; + } +} + +/* Watermark encode + * Bit 9: Unit; 0:1, 1:16 + * Bit 8-0: Value to be multiplied with unit + */ +static u16 vsc9953_wm_enc(u16 value) +{ + if (value >= BIT(9)) + return BIT(9) | (value / 16); + + return value; +} + +static const struct ocelot_ops vsc9953_ops = { + .reset = vsc9953_reset, + .wm_enc = vsc9953_wm_enc, +}; + +static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) +{ + struct felix *felix = ocelot_to_felix(ocelot); + struct device *dev = ocelot->dev; + struct mii_bus *bus; + int port; + int rc; + + felix->pcs = devm_kcalloc(dev, felix->info->num_ports, + sizeof(struct phy_device *), + GFP_KERNEL); + if (!felix->pcs) { + dev_err(dev, "failed to allocate array for PCS PHYs\n"); + return -ENOMEM; + } + + bus = devm_mdiobus_alloc(dev); + if (!bus) + return -ENOMEM; + + bus->name = "VSC9953 internal MDIO bus"; + bus->read = vsc9953_mdio_read; + bus->write = vsc9953_mdio_write; + bus->parent = dev; + bus->priv = ocelot; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev)); + + /* Needed in order to initialize the bus mutex lock */ + rc = mdiobus_register(bus); + if (rc < 0) { + dev_err(dev, "failed to register MDIO bus\n"); + return rc; + } + + felix->imdio = bus; + + for (port = 0; port < felix->info->num_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct phy_device *pcs; + int addr = port + 4; + + if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) + continue; + + pcs = get_phy_device(felix->imdio, addr, false); + if (IS_ERR(pcs)) + continue; + + pcs->interface = ocelot_port->phy_mode; + felix->pcs[port] = pcs; + + dev_info(dev, "Found PCS at internal MDIO address %d\n", addr); + } + + return 0; +} + +static void vsc9953_xmit_template_populate(struct ocelot *ocelot, int port) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u8 *template = ocelot_port->xmit_template; + u64 bypass, dest, src; + + /* Set the source port as the CPU port module and not the + * NPI port + */ + src = ocelot->num_phys_ports; + dest = BIT(port); + bypass = true; + + packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0); + packing(template, &dest, 67, 57, OCELOT_TAG_LEN, PACK, 0); + packing(template, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0); +} + +static const struct felix_info seville_info_vsc9953 = { + .target_io_res = vsc9953_target_io_res, + .port_io_res = vsc9953_port_io_res, + .regfields = vsc9953_regfields, + .map = vsc9953_regmap, + .ops = &vsc9953_ops, + .stats_layout = vsc9953_stats_layout, + .num_stats = ARRAY_SIZE(vsc9953_stats_layout), + .vcap_is2_keys = vsc9953_vcap_is2_keys, + .vcap_is2_actions = vsc9953_vcap_is2_actions, + .vcap = vsc9953_vcap_props, + .shared_queue_sz = 128 * 1024, + .num_mact_rows = 2048, + .num_ports = 10, + .mdio_bus_alloc = vsc9953_mdio_bus_alloc, + .mdio_bus_free = vsc9959_mdio_bus_free, + .pcs_config = vsc9959_pcs_config, + .pcs_link_up = vsc9959_pcs_link_up, + .pcs_link_state = vsc9959_pcs_link_state, + .phylink_validate = vsc9953_phylink_validate, + .prevalidate_phy_mode = vsc9953_prevalidate_phy_mode, + .xmit_template_populate = vsc9953_xmit_template_populate, +}; + +static int seville_probe(struct platform_device *pdev) +{ + struct dsa_switch *ds; + struct ocelot *ocelot; + struct resource *res; + struct felix *felix; + int err; + + felix = kzalloc(sizeof(struct felix), GFP_KERNEL); + if (!felix) { + err = -ENOMEM; + dev_err(&pdev->dev, "Failed to allocate driver memory\n"); + goto err_alloc_felix; + } + + platform_set_drvdata(pdev, felix); + + ocelot = &felix->ocelot; + ocelot->dev = &pdev->dev; + felix->info = &seville_info_vsc9953; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + felix->switch_base = res->start; + + ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL); + if (!ds) { + err = -ENOMEM; + dev_err(&pdev->dev, "Failed to allocate DSA switch\n"); + goto err_alloc_ds; + } + + ds->dev = &pdev->dev; + ds->num_ports = felix->info->num_ports; + ds->ops = &felix_switch_ops; + ds->priv = ocelot; + felix->ds = ds; + + err = dsa_register_switch(ds); + if (err) { + dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err); + goto err_register_ds; + } + + return 0; + +err_register_ds: + kfree(ds); +err_alloc_ds: +err_alloc_felix: + kfree(felix); + return err; +} + +static int seville_remove(struct platform_device *pdev) +{ + struct felix *felix; + + felix = platform_get_drvdata(pdev); + + dsa_unregister_switch(felix->ds); + + kfree(felix->ds); + kfree(felix); + + return 0; +} + +static const struct of_device_id seville_of_match[] = { + { .compatible = "mscc,vsc9953-switch" }, + { }, +}; +MODULE_DEVICE_TABLE(of, seville_of_match); + +struct platform_driver seville_vsc9953_driver = { + .probe = seville_probe, + .remove = seville_remove, + .driver = { + .name = "mscc_seville", + .of_match_table = of_match_ptr(seville_of_match), + }, +}; diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index fd1977590cb4..48f1ff746799 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -109,8 +109,8 @@ /* CPU port control reg */ #define RTL8368RB_CPU_CTRL_REG 0x0061 #define RTL8368RB_CPU_PORTS_MSK 0x00FF -/* Enables inserting custom tag length/type 0x8899 */ -#define RTL8368RB_CPU_INSTAG BIT(15) +/* Disables inserting custom tag length/type 0x8899 */ +#define RTL8368RB_CPU_NO_TAG BIT(15) #define RTL8366RB_SMAR0 0x0070 /* bits 0..15 */ #define RTL8366RB_SMAR1 0x0071 /* bits 16..31 */ @@ -844,16 +844,14 @@ static int rtl8366rb_setup(struct dsa_switch *ds) if (ret) return ret; - /* Enable CPU port and enable inserting CPU tag + /* Enable CPU port with custom DSA tag 8899. * - * Disabling RTL8368RB_CPU_INSTAG here will change the behaviour - * of the switch totally and it will start talking Realtek RRCP - * internally. It is probably possible to experiment with this, - * but then the kernel needs to understand and handle RRCP first. + * If you set RTL8368RB_CPU_NO_TAG (bit 15) in this registers + * the custom tag is turned off. */ ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG, 0xFFFF, - RTL8368RB_CPU_INSTAG | BIT(smi->cpu_port)); + BIT(smi->cpu_port)); if (ret) return ret; @@ -967,21 +965,8 @@ static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) { - /* For now, the RTL switches are handled without any custom tags. - * - * It is possible to turn on "custom tags" by removing the - * RTL8368RB_CPU_INSTAG flag when enabling the port but what it - * does is unfamiliar to DSA: ethernet frames of type 8899, the Realtek - * Remote Control Protocol (RRCP) start to appear on the CPU port of - * the device. So this is not the ordinary few extra bytes in the - * frame. Instead it appears that the switch starts to talk Realtek - * RRCP internally which means a pretty complex RRCP implementation - * decoding and responding the RRCP protocol is needed to exploit this. - * - * The OpenRRCP project (dormant since 2009) have reverse-egineered - * parts of the protocol. - */ - return DSA_TAG_PROTO_NONE; + /* This switch uses the 4 byte protocol A Realtek DSA tag */ + return DSA_TAG_PROTO_RTL4_A; } static void rtl8366rb_adjust_link(struct dsa_switch *ds, int port, diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index bf546118dbc6..9c5891bbfe61 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -8,7 +8,7 @@ * available in the GRLIB VHDL IP core library. * * Full documentation of both cores can be found here: - * http://www.gaisler.com/products/grlib/grip.pdf + * https://www.gaisler.com/products/grlib/grip.pdf * * The Gigabit version supports scatter/gather DMA, any alignment of * buffers and checksum offloading. diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 5d389a984394..b6c43b58ed3d 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -226,7 +226,9 @@ static int amd8111e_free_skbs(struct net_device *dev) /* Freeing transmit skbs */ for(i = 0; i < NUM_TX_BUFFERS; i++){ if(lp->tx_skbuff[i]){ - pci_unmap_single(lp->pci_dev,lp->tx_dma_addr[i], lp->tx_skbuff[i]->len,PCI_DMA_TODEVICE); + dma_unmap_single(&lp->pci_dev->dev, + lp->tx_dma_addr[i], + lp->tx_skbuff[i]->len, DMA_TO_DEVICE); dev_kfree_skb (lp->tx_skbuff[i]); lp->tx_skbuff[i] = NULL; lp->tx_dma_addr[i] = 0; @@ -236,8 +238,9 @@ static int amd8111e_free_skbs(struct net_device *dev) for (i = 0; i < NUM_RX_BUFFERS; i++){ rx_skbuff = lp->rx_skbuff[i]; if(rx_skbuff != NULL){ - pci_unmap_single(lp->pci_dev,lp->rx_dma_addr[i], - lp->rx_buff_len - 2,PCI_DMA_FROMDEVICE); + dma_unmap_single(&lp->pci_dev->dev, + lp->rx_dma_addr[i], + lp->rx_buff_len - 2, DMA_FROM_DEVICE); dev_kfree_skb(lp->rx_skbuff[i]); lp->rx_skbuff[i] = NULL; lp->rx_dma_addr[i] = 0; @@ -287,20 +290,20 @@ static int amd8111e_init_ring(struct net_device *dev) amd8111e_free_skbs(dev); else{ - /* allocate the tx and rx descriptors */ - if((lp->tx_ring = pci_alloc_consistent(lp->pci_dev, - sizeof(struct amd8111e_tx_dr)*NUM_TX_RING_DR, - &lp->tx_ring_dma_addr)) == NULL) - + /* allocate the tx and rx descriptors */ + lp->tx_ring = dma_alloc_coherent(&lp->pci_dev->dev, + sizeof(struct amd8111e_tx_dr) * NUM_TX_RING_DR, + &lp->tx_ring_dma_addr, GFP_ATOMIC); + if (!lp->tx_ring) goto err_no_mem; - if((lp->rx_ring = pci_alloc_consistent(lp->pci_dev, - sizeof(struct amd8111e_rx_dr)*NUM_RX_RING_DR, - &lp->rx_ring_dma_addr)) == NULL) - + lp->rx_ring = dma_alloc_coherent(&lp->pci_dev->dev, + sizeof(struct amd8111e_rx_dr) * NUM_RX_RING_DR, + &lp->rx_ring_dma_addr, GFP_ATOMIC); + if (!lp->rx_ring) goto err_free_tx_ring; - } + /* Set new receive buff size */ amd8111e_set_rx_buff_len(dev); @@ -318,8 +321,10 @@ static int amd8111e_init_ring(struct net_device *dev) } /* Initilaizing receive descriptors */ for (i = 0; i < NUM_RX_BUFFERS; i++) { - lp->rx_dma_addr[i] = pci_map_single(lp->pci_dev, - lp->rx_skbuff[i]->data,lp->rx_buff_len-2, PCI_DMA_FROMDEVICE); + lp->rx_dma_addr[i] = dma_map_single(&lp->pci_dev->dev, + lp->rx_skbuff[i]->data, + lp->rx_buff_len - 2, + DMA_FROM_DEVICE); lp->rx_ring[i].buff_phy_addr = cpu_to_le32(lp->rx_dma_addr[i]); lp->rx_ring[i].buff_count = cpu_to_le16(lp->rx_buff_len-2); @@ -338,15 +343,15 @@ static int amd8111e_init_ring(struct net_device *dev) err_free_rx_ring: - pci_free_consistent(lp->pci_dev, - sizeof(struct amd8111e_rx_dr)*NUM_RX_RING_DR,lp->rx_ring, - lp->rx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct amd8111e_rx_dr) * NUM_RX_RING_DR, + lp->rx_ring, lp->rx_ring_dma_addr); err_free_tx_ring: - pci_free_consistent(lp->pci_dev, - sizeof(struct amd8111e_tx_dr)*NUM_TX_RING_DR,lp->tx_ring, - lp->tx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct amd8111e_tx_dr) * NUM_TX_RING_DR, + lp->tx_ring, lp->tx_ring_dma_addr); err_no_mem: return -ENOMEM; @@ -612,16 +617,16 @@ static void amd8111e_free_ring(struct amd8111e_priv *lp) { /* Free transmit and receive descriptor rings */ if(lp->rx_ring){ - pci_free_consistent(lp->pci_dev, - sizeof(struct amd8111e_rx_dr)*NUM_RX_RING_DR, - lp->rx_ring, lp->rx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct amd8111e_rx_dr) * NUM_RX_RING_DR, + lp->rx_ring, lp->rx_ring_dma_addr); lp->rx_ring = NULL; } if(lp->tx_ring){ - pci_free_consistent(lp->pci_dev, - sizeof(struct amd8111e_tx_dr)*NUM_TX_RING_DR, - lp->tx_ring, lp->tx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct amd8111e_tx_dr) * NUM_TX_RING_DR, + lp->tx_ring, lp->tx_ring_dma_addr); lp->tx_ring = NULL; } @@ -649,9 +654,10 @@ static int amd8111e_tx(struct net_device *dev) /* We must free the original skb */ if (lp->tx_skbuff[tx_index]) { - pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[tx_index], - lp->tx_skbuff[tx_index]->len, - PCI_DMA_TODEVICE); + dma_unmap_single(&lp->pci_dev->dev, + lp->tx_dma_addr[tx_index], + lp->tx_skbuff[tx_index]->len, + DMA_TO_DEVICE); dev_consume_skb_irq(lp->tx_skbuff[tx_index]); lp->tx_skbuff[tx_index] = NULL; lp->tx_dma_addr[tx_index] = 0; @@ -737,14 +743,14 @@ static int amd8111e_rx_poll(struct napi_struct *napi, int budget) skb_reserve(new_skb, 2); skb = lp->rx_skbuff[rx_index]; - pci_unmap_single(lp->pci_dev,lp->rx_dma_addr[rx_index], - lp->rx_buff_len-2, PCI_DMA_FROMDEVICE); + dma_unmap_single(&lp->pci_dev->dev, lp->rx_dma_addr[rx_index], + lp->rx_buff_len - 2, DMA_FROM_DEVICE); skb_put(skb, pkt_len); lp->rx_skbuff[rx_index] = new_skb; - lp->rx_dma_addr[rx_index] = pci_map_single(lp->pci_dev, + lp->rx_dma_addr[rx_index] = dma_map_single(&lp->pci_dev->dev, new_skb->data, - lp->rx_buff_len-2, - PCI_DMA_FROMDEVICE); + lp->rx_buff_len - 2, + DMA_FROM_DEVICE); skb->protocol = eth_type_trans(skb, dev); @@ -1270,7 +1276,8 @@ static netdev_tx_t amd8111e_start_xmit(struct sk_buff *skb, } #endif lp->tx_dma_addr[tx_index] = - pci_map_single(lp->pci_dev, skb->data, skb->len, PCI_DMA_TODEVICE); + dma_map_single(&lp->pci_dev->dev, skb->data, skb->len, + DMA_TO_DEVICE); lp->tx_ring[tx_index].buff_phy_addr = cpu_to_le32(lp->tx_dma_addr[tx_index]); @@ -1773,7 +1780,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev, } /* Initialize DMA */ - if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) < 0) { + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) < 0) { dev_err(&pdev->dev, "DMA not supported\n"); err = -ENODEV; goto err_free_reg; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index f47140391f67..187b0b9a6e1d 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -250,7 +250,7 @@ struct pcnet32_access { /* * The first field of pcnet32_private is read by the ethernet device - * so the structure should be allocated using pci_alloc_consistent(). + * so the structure should be allocated using dma_alloc_coherent(). */ struct pcnet32_private { struct pcnet32_init_block *init_block; @@ -258,7 +258,7 @@ struct pcnet32_private { struct pcnet32_rx_head *rx_ring; struct pcnet32_tx_head *tx_ring; dma_addr_t init_dma_addr;/* DMA address of beginning of the init block, - returned by pci_alloc_consistent */ + returned by dma_alloc_coherent */ struct pci_dev *pci_dev; const char *name; /* The saved address of a sent-in-place packet/buffer, for skfree(). */ @@ -485,9 +485,9 @@ static void pcnet32_realloc_tx_ring(struct net_device *dev, pcnet32_purge_tx_ring(dev); new_tx_ring = - pci_zalloc_consistent(lp->pci_dev, - sizeof(struct pcnet32_tx_head) * entries, - &new_ring_dma_addr); + dma_alloc_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_tx_head) * entries, + &new_ring_dma_addr, GFP_ATOMIC); if (new_tx_ring == NULL) return; @@ -501,9 +501,9 @@ static void pcnet32_realloc_tx_ring(struct net_device *dev, kfree(lp->tx_skbuff); kfree(lp->tx_dma_addr); - pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_tx_head) * lp->tx_ring_size, - lp->tx_ring, lp->tx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_tx_head) * lp->tx_ring_size, + lp->tx_ring, lp->tx_ring_dma_addr); lp->tx_ring_size = entries; lp->tx_mod_mask = lp->tx_ring_size - 1; @@ -517,10 +517,9 @@ static void pcnet32_realloc_tx_ring(struct net_device *dev, free_new_lists: kfree(new_dma_addr_list); free_new_tx_ring: - pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_tx_head) * entries, - new_tx_ring, - new_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_tx_head) * entries, + new_tx_ring, new_ring_dma_addr); } /* @@ -545,9 +544,9 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, unsigned int entries = BIT(size); new_rx_ring = - pci_zalloc_consistent(lp->pci_dev, - sizeof(struct pcnet32_rx_head) * entries, - &new_ring_dma_addr); + dma_alloc_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_rx_head) * entries, + &new_ring_dma_addr, GFP_ATOMIC); if (new_rx_ring == NULL) return; @@ -580,10 +579,9 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, skb_reserve(rx_skbuff, NET_IP_ALIGN); new_dma_addr_list[new] = - pci_map_single(lp->pci_dev, rx_skbuff->data, - PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(lp->pci_dev, - new_dma_addr_list[new])) { + dma_map_single(&lp->pci_dev->dev, rx_skbuff->data, + PKT_BUF_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(&lp->pci_dev->dev, new_dma_addr_list[new])) { netif_err(lp, drv, dev, "%s dma mapping failed\n", __func__); dev_kfree_skb(new_skb_list[new]); @@ -596,22 +594,20 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, /* and free any unneeded buffers */ for (; new < lp->rx_ring_size; new++) { if (lp->rx_skbuff[new]) { - if (!pci_dma_mapping_error(lp->pci_dev, - lp->rx_dma_addr[new])) - pci_unmap_single(lp->pci_dev, + if (!dma_mapping_error(&lp->pci_dev->dev, lp->rx_dma_addr[new])) + dma_unmap_single(&lp->pci_dev->dev, lp->rx_dma_addr[new], PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); dev_kfree_skb(lp->rx_skbuff[new]); } } kfree(lp->rx_skbuff); kfree(lp->rx_dma_addr); - pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_rx_head) * - lp->rx_ring_size, lp->rx_ring, - lp->rx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_rx_head) * lp->rx_ring_size, + lp->rx_ring, lp->rx_ring_dma_addr); lp->rx_ring_size = entries; lp->rx_mod_mask = lp->rx_ring_size - 1; @@ -625,12 +621,11 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, free_all_new: while (--new >= lp->rx_ring_size) { if (new_skb_list[new]) { - if (!pci_dma_mapping_error(lp->pci_dev, - new_dma_addr_list[new])) - pci_unmap_single(lp->pci_dev, + if (!dma_mapping_error(&lp->pci_dev->dev, new_dma_addr_list[new])) + dma_unmap_single(&lp->pci_dev->dev, new_dma_addr_list[new], PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); dev_kfree_skb(new_skb_list[new]); } } @@ -638,10 +633,9 @@ free_all_new: free_new_lists: kfree(new_dma_addr_list); free_new_rx_ring: - pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_rx_head) * entries, - new_rx_ring, - new_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_rx_head) * entries, + new_rx_ring, new_ring_dma_addr); } static void pcnet32_purge_rx_ring(struct net_device *dev) @@ -654,12 +648,11 @@ static void pcnet32_purge_rx_ring(struct net_device *dev) lp->rx_ring[i].status = 0; /* CPU owns buffer */ wmb(); /* Make sure adapter sees owner change */ if (lp->rx_skbuff[i]) { - if (!pci_dma_mapping_error(lp->pci_dev, - lp->rx_dma_addr[i])) - pci_unmap_single(lp->pci_dev, + if (!dma_mapping_error(&lp->pci_dev->dev, lp->rx_dma_addr[i])) + dma_unmap_single(&lp->pci_dev->dev, lp->rx_dma_addr[i], PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); dev_kfree_skb_any(lp->rx_skbuff[i]); } lp->rx_skbuff[i] = NULL; @@ -1036,9 +1029,9 @@ static int pcnet32_loopback_test(struct net_device *dev, uint64_t * data1) *packet++ = i; lp->tx_dma_addr[x] = - pci_map_single(lp->pci_dev, skb->data, skb->len, - PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(lp->pci_dev, lp->tx_dma_addr[x])) { + dma_map_single(&lp->pci_dev->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&lp->pci_dev->dev, lp->tx_dma_addr[x])) { netif_printk(lp, hw, KERN_DEBUG, dev, "DMA mapping error at line: %d!\n", __LINE__); @@ -1226,21 +1219,21 @@ static void pcnet32_rx_entry(struct net_device *dev, */ if (newskb) { skb_reserve(newskb, NET_IP_ALIGN); - new_dma_addr = pci_map_single(lp->pci_dev, + new_dma_addr = dma_map_single(&lp->pci_dev->dev, newskb->data, PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(lp->pci_dev, new_dma_addr)) { + DMA_FROM_DEVICE); + if (dma_mapping_error(&lp->pci_dev->dev, new_dma_addr)) { netif_err(lp, rx_err, dev, "DMA mapping error.\n"); dev_kfree_skb(newskb); skb = NULL; } else { skb = lp->rx_skbuff[entry]; - pci_unmap_single(lp->pci_dev, + dma_unmap_single(&lp->pci_dev->dev, lp->rx_dma_addr[entry], PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); skb_put(skb, pkt_len); lp->rx_skbuff[entry] = newskb; lp->rx_dma_addr[entry] = new_dma_addr; @@ -1259,17 +1252,15 @@ static void pcnet32_rx_entry(struct net_device *dev, if (!rx_in_place) { skb_reserve(skb, NET_IP_ALIGN); skb_put(skb, pkt_len); /* Make room */ - pci_dma_sync_single_for_cpu(lp->pci_dev, - lp->rx_dma_addr[entry], - pkt_len, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&lp->pci_dev->dev, + lp->rx_dma_addr[entry], pkt_len, + DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, (unsigned char *)(lp->rx_skbuff[entry]->data), pkt_len); - pci_dma_sync_single_for_device(lp->pci_dev, - lp->rx_dma_addr[entry], - pkt_len, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&lp->pci_dev->dev, + lp->rx_dma_addr[entry], pkt_len, + DMA_FROM_DEVICE); } dev->stats.rx_bytes += skb->len; skb->protocol = eth_type_trans(skb, dev); @@ -1358,10 +1349,10 @@ static int pcnet32_tx(struct net_device *dev) /* We must free the original skb */ if (lp->tx_skbuff[entry]) { - pci_unmap_single(lp->pci_dev, + dma_unmap_single(&lp->pci_dev->dev, lp->tx_dma_addr[entry], - lp->tx_skbuff[entry]-> - len, PCI_DMA_TODEVICE); + lp->tx_skbuff[entry]->len, + DMA_TO_DEVICE); dev_kfree_skb_any(lp->tx_skbuff[entry]); lp->tx_skbuff[entry] = NULL; lp->tx_dma_addr[entry] = 0; @@ -1551,7 +1542,7 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_disable_dev; } - err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK); + err = dma_set_mask(&pdev->dev, PCNET32_DMA_MASK); if (err) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("architecture does not support 32bit PCI busmaster DMA\n"); @@ -1834,12 +1825,13 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) dev->base_addr = ioaddr; lp = netdev_priv(dev); - /* pci_alloc_consistent returns page-aligned memory, so we do not have to check the alignment */ - lp->init_block = pci_alloc_consistent(pdev, sizeof(*lp->init_block), - &lp->init_dma_addr); + /* dma_alloc_coherent returns page-aligned memory, so we do not have to check the alignment */ + lp->init_block = dma_alloc_coherent(&pdev->dev, + sizeof(*lp->init_block), + &lp->init_dma_addr, GFP_KERNEL); if (!lp->init_block) { if (pcnet32_debug & NETIF_MSG_PROBE) - pr_err("Consistent memory allocation failed\n"); + pr_err("Coherent memory allocation failed\n"); ret = -ENOMEM; goto err_free_netdev; } @@ -1998,8 +1990,8 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) err_free_ring: pcnet32_free_ring(dev); - pci_free_consistent(lp->pci_dev, sizeof(*lp->init_block), - lp->init_block, lp->init_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, sizeof(*lp->init_block), + lp->init_block, lp->init_dma_addr); err_free_netdev: free_netdev(dev); err_release_region: @@ -2012,21 +2004,19 @@ static int pcnet32_alloc_ring(struct net_device *dev, const char *name) { struct pcnet32_private *lp = netdev_priv(dev); - lp->tx_ring = pci_alloc_consistent(lp->pci_dev, - sizeof(struct pcnet32_tx_head) * - lp->tx_ring_size, - &lp->tx_ring_dma_addr); + lp->tx_ring = dma_alloc_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_tx_head) * lp->tx_ring_size, + &lp->tx_ring_dma_addr, GFP_KERNEL); if (lp->tx_ring == NULL) { - netif_err(lp, drv, dev, "Consistent memory allocation failed\n"); + netif_err(lp, drv, dev, "Coherent memory allocation failed\n"); return -ENOMEM; } - lp->rx_ring = pci_alloc_consistent(lp->pci_dev, - sizeof(struct pcnet32_rx_head) * - lp->rx_ring_size, - &lp->rx_ring_dma_addr); + lp->rx_ring = dma_alloc_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_rx_head) * lp->rx_ring_size, + &lp->rx_ring_dma_addr, GFP_KERNEL); if (lp->rx_ring == NULL) { - netif_err(lp, drv, dev, "Consistent memory allocation failed\n"); + netif_err(lp, drv, dev, "Coherent memory allocation failed\n"); return -ENOMEM; } @@ -2070,18 +2060,16 @@ static void pcnet32_free_ring(struct net_device *dev) lp->rx_dma_addr = NULL; if (lp->tx_ring) { - pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_tx_head) * - lp->tx_ring_size, lp->tx_ring, - lp->tx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_tx_head) * lp->tx_ring_size, + lp->tx_ring, lp->tx_ring_dma_addr); lp->tx_ring = NULL; } if (lp->rx_ring) { - pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_rx_head) * - lp->rx_ring_size, lp->rx_ring, - lp->rx_ring_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, + sizeof(struct pcnet32_rx_head) * lp->rx_ring_size, + lp->rx_ring, lp->rx_ring_dma_addr); lp->rx_ring = NULL; } } @@ -2342,12 +2330,11 @@ static void pcnet32_purge_tx_ring(struct net_device *dev) lp->tx_ring[i].status = 0; /* CPU owns buffer */ wmb(); /* Make sure adapter sees owner change */ if (lp->tx_skbuff[i]) { - if (!pci_dma_mapping_error(lp->pci_dev, - lp->tx_dma_addr[i])) - pci_unmap_single(lp->pci_dev, + if (!dma_mapping_error(&lp->pci_dev->dev, lp->tx_dma_addr[i])) + dma_unmap_single(&lp->pci_dev->dev, lp->tx_dma_addr[i], lp->tx_skbuff[i]->len, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); dev_kfree_skb_any(lp->tx_skbuff[i]); } lp->tx_skbuff[i] = NULL; @@ -2382,10 +2369,9 @@ static int pcnet32_init_ring(struct net_device *dev) rmb(); if (lp->rx_dma_addr[i] == 0) { lp->rx_dma_addr[i] = - pci_map_single(lp->pci_dev, rx_skbuff->data, - PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(lp->pci_dev, - lp->rx_dma_addr[i])) { + dma_map_single(&lp->pci_dev->dev, rx_skbuff->data, + PKT_BUF_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(&lp->pci_dev->dev, lp->rx_dma_addr[i])) { /* there is not much we can do at this point */ netif_err(lp, drv, dev, "%s pci dma mapping error\n", @@ -2523,8 +2509,9 @@ static netdev_tx_t pcnet32_start_xmit(struct sk_buff *skb, lp->tx_ring[entry].misc = 0x00000000; lp->tx_dma_addr[entry] = - pci_map_single(lp->pci_dev, skb->data, skb->len, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(lp->pci_dev, lp->tx_dma_addr[entry])) { + dma_map_single(&lp->pci_dev->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&lp->pci_dev->dev, lp->tx_dma_addr[entry])) { dev_kfree_skb_any(skb); dev->stats.tx_dropped++; goto drop_packet; @@ -2947,8 +2934,8 @@ static void pcnet32_remove_one(struct pci_dev *pdev) unregister_netdev(dev); pcnet32_free_ring(dev); release_region(dev->base_addr, PCNET32_TOTAL_SIZE); - pci_free_consistent(lp->pci_dev, sizeof(*lp->init_block), - lp->init_block, lp->init_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, sizeof(*lp->init_block), + lp->init_block, lp->init_dma_addr); free_netdev(dev); pci_disable_device(pdev); } @@ -3030,8 +3017,8 @@ static void __exit pcnet32_cleanup_module(void) unregister_netdev(pcnet32_dev); pcnet32_free_ring(pcnet32_dev); release_region(pcnet32_dev->base_addr, PCNET32_TOTAL_SIZE); - pci_free_consistent(lp->pci_dev, sizeof(*lp->init_block), - lp->init_block, lp->init_dma_addr); + dma_free_coherent(&lp->pci_dev->dev, sizeof(*lp->init_block), + lp->init_block, lp->init_dma_addr); free_netdev(pcnet32_dev); pcnet32_dev = next_dev; } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index 3c8e8047ea1e..d775b23025c1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -1700,7 +1700,7 @@ void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location, for (i = 0; i < 4; ++i) aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_SRCA_ADR(location + i), - ipv6_src[i]); + ipv6_src[3 - i]); } void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location, @@ -1711,7 +1711,7 @@ void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location, for (i = 0; i < 4; ++i) aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_DSTA_ADR(location + i), - ipv6_dest[i]); + ipv6_dest[3 - i]); } u32 hw_atl_sem_ram_get(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 06220792daf1..7430ff025134 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -1360,7 +1360,7 @@ */ /* Register address for bitfield pif_rpf_l3_da0_i[31:0] */ -#define HW_ATL_RPF_L3_DSTA_ADR(filter) (0x000053B0 + (filter) * 0x4) +#define HW_ATL_RPF_L3_DSTA_ADR(filter) (0x000053D0 + (filter) * 0x4) /* Bitmask for bitfield l3_da0[1F:0] */ #define HW_ATL_RPF_L3_DSTA_MSK 0xFFFFFFFFu /* Inverted bitmask for bitfield l3_da0[1F:0] */ diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b470551bae4f..dfed9ade6950 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1250,8 +1250,7 @@ static struct sk_buff *bcm_sysport_insert_tsb(struct sk_buff *skb, memset(tsb, 0, sizeof(*tsb)); if (skb_vlan_tag_present(skb)) { - tsb->pcp_dei_vid = (skb_vlan_tag_get_prio(skb) >> - VLAN_PRIO_SHIFT & PCP_DEI_MASK); + tsb->pcp_dei_vid = skb_vlan_tag_get_prio(skb) & PCP_DEI_MASK; tsb->pcp_dei_vid |= (u32)skb_vlan_tag_get_id(skb) << VID_SHIFT; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_self_test.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_self_test.c index 48f63ef2e6ea..3f8bdad3351c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_self_test.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_self_test.c @@ -2218,31 +2218,31 @@ static struct st_record st_database[ST_DB_LINES] = { /*line 352*/{(0x1E), 1, MISC_REG_AEU_SYS_KILL_OCCURRED, NA, NA, NA, pneq, NA, IDLE_CHK_ERROR, - "MISC: system kill occurd;", + "MISC: system kill occurred;", {NA, NA, 0, NA, NA, NA} }, /*line 353*/{(0x1E), 1, MISC_REG_AEU_SYS_KILL_STATUS_0, NA, NA, NA, pneq, NA, IDLE_CHK_ERROR, - "MISC: system kill occurd; status_0 register", + "MISC: system kill occurred; status_0 register", {NA, NA, 0, NA, NA, NA} }, /*line 354*/{(0x1E), 1, MISC_REG_AEU_SYS_KILL_STATUS_1, NA, NA, NA, pneq, NA, IDLE_CHK_ERROR, - "MISC: system kill occurd; status_1 register", + "MISC: system kill occurred; status_1 register", {NA, NA, 0, NA, NA, NA} }, /*line 355*/{(0x1E), 1, MISC_REG_AEU_SYS_KILL_STATUS_2, NA, NA, NA, pneq, NA, IDLE_CHK_ERROR, - "MISC: system kill occurd; status_2 register", + "MISC: system kill occurred; status_2 register", {NA, NA, 0, NA, NA, NA} }, /*line 356*/{(0x1E), 1, MISC_REG_AEU_SYS_KILL_STATUS_3, NA, NA, NA, pneq, NA, IDLE_CHK_ERROR, - "MISC: system kill occurd; status_3 register", + "MISC: system kill occurred; status_3 register", {NA, NA, 0, NA, NA, NA} }, /*line 357*/{(0x1E), 1, MISC_REG_PCIE_HOT_RESET, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6a884df44612..0911eb3b8007 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1614,7 +1614,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type); if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) && - (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { + (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) { u16 vlan_proto = tpa_info->metadata >> RX_CMP_FLAGS2_METADATA_TPID_SFT; u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK; @@ -1832,7 +1832,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if ((rxcmp1->rx_cmp_flags2 & cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) && - (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { + (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) { u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data); u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK; u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT; @@ -3538,7 +3538,7 @@ static void bnxt_free_vnic_attributes(struct bnxt *bp) } if (vnic->rss_table) { - dma_free_coherent(&pdev->dev, PAGE_SIZE, + dma_free_coherent(&pdev->dev, vnic->rss_table_size, vnic->rss_table, vnic->rss_table_dma_addr); vnic->rss_table = NULL; @@ -3603,7 +3603,13 @@ vnic_skip_grps: continue; /* Allocate rss table and hash key */ - vnic->rss_table = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, + size = L1_CACHE_ALIGN(HW_HASH_INDEX_SIZE * sizeof(u16)); + if (bp->flags & BNXT_FLAG_CHIP_P5) + size = L1_CACHE_ALIGN(BNXT_MAX_RSS_TABLE_SIZE_P5); + + vnic->rss_table_size = size + HW_HASH_KEY_SIZE; + vnic->rss_table = dma_alloc_coherent(&pdev->dev, + vnic->rss_table_size, &vnic->rss_table_dma_addr, GFP_KERNEL); if (!vnic->rss_table) { @@ -3611,8 +3617,6 @@ vnic_skip_grps: goto out; } - size = L1_CACHE_ALIGN(HW_HASH_INDEX_SIZE * sizeof(u16)); - vnic->rss_hash_key = ((void *)vnic->rss_table) + size; vnic->rss_hash_key_dma_addr = vnic->rss_table_dma_addr + size; } @@ -4505,10 +4509,12 @@ static int bnxt_hwrm_tunnel_dst_port_free(struct bnxt *bp, u8 tunnel_type) switch (tunnel_type) { case TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN: - req.tunnel_dst_port_id = bp->vxlan_fw_dst_port_id; + req.tunnel_dst_port_id = cpu_to_le16(bp->vxlan_fw_dst_port_id); + bp->vxlan_fw_dst_port_id = INVALID_HW_RING_ID; break; case TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE: - req.tunnel_dst_port_id = bp->nge_fw_dst_port_id; + req.tunnel_dst_port_id = cpu_to_le16(bp->nge_fw_dst_port_id); + bp->nge_fw_dst_port_id = INVALID_HW_RING_ID; break; default: break; @@ -4543,10 +4549,11 @@ static int bnxt_hwrm_tunnel_dst_port_alloc(struct bnxt *bp, __be16 port, switch (tunnel_type) { case TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN: - bp->vxlan_fw_dst_port_id = resp->tunnel_dst_port_id; + bp->vxlan_fw_dst_port_id = + le16_to_cpu(resp->tunnel_dst_port_id); break; case TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE: - bp->nge_fw_dst_port_id = resp->tunnel_dst_port_id; + bp->nge_fw_dst_port_id = le16_to_cpu(resp->tunnel_dst_port_id); break; default: break; @@ -4826,9 +4833,112 @@ static u16 bnxt_cp_ring_for_tx(struct bnxt *bp, struct bnxt_tx_ring_info *txr) } } +static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp) +{ + int entries; + + if (bp->flags & BNXT_FLAG_CHIP_P5) + entries = BNXT_MAX_RSS_TABLE_ENTRIES_P5; + else + entries = HW_HASH_INDEX_SIZE; + + bp->rss_indir_tbl_entries = entries; + bp->rss_indir_tbl = kmalloc_array(entries, sizeof(*bp->rss_indir_tbl), + GFP_KERNEL); + if (!bp->rss_indir_tbl) + return -ENOMEM; + return 0; +} + +static void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp) +{ + u16 max_rings, max_entries, pad, i; + + if (!bp->rx_nr_rings) + return; + + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + max_rings = bp->rx_nr_rings - 1; + else + max_rings = bp->rx_nr_rings; + + max_entries = bnxt_get_rxfh_indir_size(bp->dev); + + for (i = 0; i < max_entries; i++) + bp->rss_indir_tbl[i] = ethtool_rxfh_indir_default(i, max_rings); + + pad = bp->rss_indir_tbl_entries - max_entries; + if (pad) + memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16)); +} + +static u16 bnxt_get_max_rss_ring(struct bnxt *bp) +{ + u16 i, tbl_size, max_ring = 0; + + if (!bp->rss_indir_tbl) + return 0; + + tbl_size = bnxt_get_rxfh_indir_size(bp->dev); + for (i = 0; i < tbl_size; i++) + max_ring = max(max_ring, bp->rss_indir_tbl[i]); + return max_ring; +} + +int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) +{ + if (bp->flags & BNXT_FLAG_CHIP_P5) + return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5); + if (BNXT_CHIP_TYPE_NITRO_A0(bp)) + return 2; + return 1; +} + +static void __bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) +{ + bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG); + u16 i, j; + + /* Fill the RSS indirection table with ring group ids */ + for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++) { + if (!no_rss) + j = bp->rss_indir_tbl[i]; + vnic->rss_table[i] = cpu_to_le16(vnic->fw_grp_ids[j]); + } +} + +static void __bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, + struct bnxt_vnic_info *vnic) +{ + __le16 *ring_tbl = vnic->rss_table; + struct bnxt_rx_ring_info *rxr; + u16 tbl_size, i; + + tbl_size = bnxt_get_rxfh_indir_size(bp->dev); + + for (i = 0; i < tbl_size; i++) { + u16 ring_id, j; + + j = bp->rss_indir_tbl[i]; + rxr = &bp->rx_ring[j]; + + ring_id = rxr->rx_ring_struct.fw_ring_id; + *ring_tbl++ = cpu_to_le16(ring_id); + ring_id = bnxt_cp_ring_for_rx(bp, rxr); + *ring_tbl++ = cpu_to_le16(ring_id); + } +} + +static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) +{ + if (bp->flags & BNXT_FLAG_CHIP_P5) + __bnxt_fill_hw_rss_tbl_p5(bp, vnic); + else + __bnxt_fill_hw_rss_tbl(bp, vnic); +} + static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) { - u32 i, j, max_rings; struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; struct hwrm_vnic_rss_cfg_input req = {0}; @@ -4838,24 +4948,9 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1); if (set_rss) { + bnxt_fill_hw_rss_tbl(bp, vnic); req.hash_type = cpu_to_le32(bp->rss_hash_cfg); req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; - if (vnic->flags & BNXT_VNIC_RSS_FLAG) { - if (BNXT_CHIP_TYPE_NITRO_A0(bp)) - max_rings = bp->rx_nr_rings - 1; - else - max_rings = bp->rx_nr_rings; - } else { - max_rings = 1; - } - - /* Fill the RSS indirection table with ring group ids */ - for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++, j++) { - if (j == max_rings) - j = 0; - vnic->rss_table[i] = cpu_to_le16(vnic->fw_grp_ids[j]); - } - req.ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr); req.hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); @@ -4867,9 +4962,9 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss) { struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; - u32 i, j, k, nr_ctxs, max_rings = bp->rx_nr_rings; - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0]; struct hwrm_vnic_rss_cfg_input req = {0}; + dma_addr_t ring_tbl_map; + u32 i, nr_ctxs; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1); req.vnic_id = cpu_to_le16(vnic->fw_vnic_id); @@ -4877,31 +4972,18 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss) hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); return 0; } + bnxt_fill_hw_rss_tbl(bp, vnic); req.hash_type = cpu_to_le32(bp->rss_hash_cfg); req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; - req.ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr); req.hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); - nr_ctxs = DIV_ROUND_UP(bp->rx_nr_rings, 64); - for (i = 0, k = 0; i < nr_ctxs; i++) { - __le16 *ring_tbl = vnic->rss_table; + ring_tbl_map = vnic->rss_table_dma_addr; + nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings); + for (i = 0; i < nr_ctxs; ring_tbl_map += BNXT_RSS_TABLE_SIZE_P5, i++) { int rc; + req.ring_grp_tbl_addr = cpu_to_le64(ring_tbl_map); req.ring_table_pair_index = i; req.rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[i]); - for (j = 0; j < 64; j++) { - u16 ring_id; - - ring_id = rxr->rx_ring_struct.fw_ring_id; - *ring_tbl++ = cpu_to_le16(ring_id); - ring_id = bnxt_cp_ring_for_rx(bp, rxr); - *ring_tbl++ = cpu_to_le16(ring_id); - rxr++; - k++; - if (k == max_rings) { - k = 0; - rxr = &bp->rx_ring[0]; - } - } rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) return rc; @@ -5139,6 +5221,14 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) if (flags & VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP) bp->flags |= BNXT_FLAG_ROCE_MIRROR_CAP; + + /* Older P5 fw before EXT_HW_STATS support did not set + * VLAN_STRIP_CAP properly. + */ + if ((flags & VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP) || + ((bp->flags & BNXT_FLAG_CHIP_P5) && + !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED))) + bp->fw_cap |= BNXT_FW_CAP_VLAN_RX_STRIP; bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported); if (bp->max_tpa_v2) bp->hw_ring_stats_size = @@ -5992,6 +6082,21 @@ static int __bnxt_reserve_rings(struct bnxt *bp) rx = rx_rings << 1; cp = sh ? max_t(int, tx, rx_rings) : tx + rx_rings; bp->tx_nr_rings = tx; + + /* If we cannot reserve all the RX rings, reset the RSS map only + * if absolutely necessary + */ + if (rx_rings != bp->rx_nr_rings) { + netdev_warn(bp->dev, "Able to reserve only %d out of %d requested RX rings\n", + rx_rings, bp->rx_nr_rings); + if ((bp->dev->priv_flags & IFF_RXFH_CONFIGURED) && + (bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) != + bnxt_get_nr_rss_ctxs(bp, rx_rings) || + bnxt_get_max_rss_ring(bp) >= rx_rings)) { + netdev_warn(bp->dev, "RSS table entries reverting to default\n"); + bp->dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + } + } bp->rx_nr_rings = rx_rings; bp->cp_nr_rings = cp; @@ -6955,7 +7060,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) struct hwrm_func_qcaps_input req = {0}; struct hwrm_func_qcaps_output *resp = bp->hwrm_cmd_resp_addr; struct bnxt_hw_resc *hw_resc = &bp->hw_resc; - u32 flags; + u32 flags, flags_ext; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCAPS, -1, -1); req.fid = cpu_to_le16(0xffff); @@ -6980,6 +7085,12 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_ERROR_RECOVERY; if (flags & FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD) bp->fw_cap |= BNXT_FW_CAP_ERR_RECOVER_RELOAD; + if (!(flags & FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED)) + bp->fw_cap |= BNXT_FW_CAP_VLAN_TX_INSERT; + + flags_ext = le32_to_cpu(resp->flags_ext); + if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED; bp->tx_push_thresh = 0; if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) && @@ -7470,16 +7581,12 @@ static int bnxt_hwrm_pcie_qstats(struct bnxt *bp) static void bnxt_hwrm_free_tunnel_ports(struct bnxt *bp) { - if (bp->vxlan_port_cnt) { + if (bp->vxlan_fw_dst_port_id != INVALID_HW_RING_ID) bnxt_hwrm_tunnel_dst_port_free( bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN); - } - bp->vxlan_port_cnt = 0; - if (bp->nge_port_cnt) { + if (bp->nge_fw_dst_port_id != INVALID_HW_RING_ID) bnxt_hwrm_tunnel_dst_port_free( bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE); - } - bp->nge_port_cnt = 0; } static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) @@ -7634,7 +7741,7 @@ static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id) { int rc, i, nr_ctxs; - nr_ctxs = DIV_ROUND_UP(bp->rx_nr_rings, 64); + nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings); for (i = 0; i < nr_ctxs; i++) { rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, i); if (rc) { @@ -8196,6 +8303,9 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) rc = bnxt_init_int_mode(bp); bnxt_ulp_irq_restart(bp, rc); } + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + if (rc) { netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; @@ -9194,7 +9304,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } if (irq_re_init) - udp_tunnel_get_rx_info(bp->dev); + udp_tunnel_nic_reset_ntf(bp->dev); set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); @@ -9835,24 +9945,16 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, /* Both CTAG and STAG VLAN accelaration on the RX side have to be * turned on or off together. */ - vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_STAG_RX); - if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_STAG_RX)) { - if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) - features &= ~(NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_STAG_RX); + vlan_features = features & BNXT_HW_FEATURE_VLAN_ALL_RX; + if (vlan_features != BNXT_HW_FEATURE_VLAN_ALL_RX) { + if (dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX) + features &= ~BNXT_HW_FEATURE_VLAN_ALL_RX; else if (vlan_features) - features |= NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_STAG_RX; + features |= BNXT_HW_FEATURE_VLAN_ALL_RX; } #ifdef CONFIG_BNXT_SRIOV - if (BNXT_VF(bp)) { - if (bp->vf.vlan) { - features &= ~(NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_STAG_RX); - } - } + if (BNXT_VF(bp) && bp->vf.vlan) + features &= ~BNXT_HW_FEATURE_VLAN_ALL_RX; #endif return features; } @@ -9875,7 +9977,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (bp->flags & BNXT_FLAG_NO_AGG_RINGS) flags &= ~BNXT_FLAG_TPA; - if (features & NETIF_F_HW_VLAN_CTAG_RX) + if (features & BNXT_HW_FEATURE_VLAN_ALL_RX) flags |= BNXT_FLAG_STRIP_VLAN; if (features & NETIF_F_NTUPLE) @@ -10353,24 +10455,6 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_cfg_ntp_filters(bp); if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); - if (test_and_clear_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event)) { - bnxt_hwrm_tunnel_dst_port_alloc( - bp, bp->vxlan_port, - TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN); - } - if (test_and_clear_bit(BNXT_VXLAN_DEL_PORT_SP_EVENT, &bp->sp_event)) { - bnxt_hwrm_tunnel_dst_port_free( - bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN); - } - if (test_and_clear_bit(BNXT_GENEVE_ADD_PORT_SP_EVENT, &bp->sp_event)) { - bnxt_hwrm_tunnel_dst_port_alloc( - bp, bp->nge_port, - TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE); - } - if (test_and_clear_bit(BNXT_GENEVE_DEL_PORT_SP_EVENT, &bp->sp_event)) { - bnxt_hwrm_tunnel_dst_port_free( - bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE); - } if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) { bnxt_hwrm_port_qstats(bp); bnxt_hwrm_port_qstats_ext(bp); @@ -10967,6 +11051,9 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) timer_setup(&bp->timer, bnxt_timer, 0); bp->current_interval = BNXT_TIMER_INTERVAL; + bp->vxlan_fw_dst_port_id = INVALID_HW_RING_ID; + bp->nge_fw_dst_port_id = INVALID_HW_RING_ID; + clear_bit(BNXT_STATE_OPEN, &bp->state); return 0; @@ -11294,84 +11381,33 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) #endif /* CONFIG_RFS_ACCEL */ -static void bnxt_udp_tunnel_add(struct net_device *dev, - struct udp_tunnel_info *ti) +static int bnxt_udp_tunnel_sync(struct net_device *netdev, unsigned int table) { - struct bnxt *bp = netdev_priv(dev); - - if (ti->sa_family != AF_INET6 && ti->sa_family != AF_INET) - return; - - if (!netif_running(dev)) - return; + struct bnxt *bp = netdev_priv(netdev); + struct udp_tunnel_info ti; + unsigned int cmd; - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (bp->vxlan_port_cnt && bp->vxlan_port != ti->port) - return; + udp_tunnel_nic_get_port(netdev, table, 0, &ti); + if (ti.type == UDP_TUNNEL_TYPE_VXLAN) + cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN; + else + cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE; - bp->vxlan_port_cnt++; - if (bp->vxlan_port_cnt == 1) { - bp->vxlan_port = ti->port; - set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event); - bnxt_queue_sp_work(bp); - } - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (bp->nge_port_cnt && bp->nge_port != ti->port) - return; + if (ti.port) + return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti.port, cmd); - bp->nge_port_cnt++; - if (bp->nge_port_cnt == 1) { - bp->nge_port = ti->port; - set_bit(BNXT_GENEVE_ADD_PORT_SP_EVENT, &bp->sp_event); - } - break; - default: - return; - } - - bnxt_queue_sp_work(bp); + return bnxt_hwrm_tunnel_dst_port_free(bp, cmd); } -static void bnxt_udp_tunnel_del(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct bnxt *bp = netdev_priv(dev); - - if (ti->sa_family != AF_INET6 && ti->sa_family != AF_INET) - return; - - if (!netif_running(dev)) - return; - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (!bp->vxlan_port_cnt || bp->vxlan_port != ti->port) - return; - bp->vxlan_port_cnt--; - - if (bp->vxlan_port_cnt != 0) - return; - - set_bit(BNXT_VXLAN_DEL_PORT_SP_EVENT, &bp->sp_event); - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (!bp->nge_port_cnt || bp->nge_port != ti->port) - return; - bp->nge_port_cnt--; - - if (bp->nge_port_cnt != 0) - return; - - set_bit(BNXT_GENEVE_DEL_PORT_SP_EVENT, &bp->sp_event); - break; - default: - return; - } - - bnxt_queue_sp_work(bp); -} +static const struct udp_tunnel_nic_info bnxt_udp_tunnels = { + .sync_table = bnxt_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | + UDP_TUNNEL_NIC_INFO_OPEN_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, + }, +}; static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, @@ -11469,8 +11505,8 @@ static const struct net_device_ops bnxt_netdev_ops = { #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = bnxt_rx_flow_steer, #endif - .ndo_udp_tunnel_add = bnxt_udp_tunnel_add, - .ndo_udp_tunnel_del = bnxt_udp_tunnel_del, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_bpf = bnxt_xdp, .ndo_xdp_xmit = bnxt_xdp_xmit, .ndo_bridge_getlink = bnxt_bridge_getlink, @@ -11510,6 +11546,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) bnxt_free_ctx_mem(bp); kfree(bp->ctx); bp->ctx = NULL; + kfree(bp->rss_indir_tbl); + bp->rss_indir_tbl = NULL; bnxt_free_port_stats(bp); free_netdev(dev); } @@ -11958,11 +11996,15 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_PARTIAL; + dev->udp_tunnel_nic_info = &bnxt_udp_tunnels; + dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM; dev->vlan_features = dev->hw_features | NETIF_F_HIGHDMA; - dev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX; + if (bp->fw_cap & BNXT_FW_CAP_VLAN_RX_STRIP) + dev->hw_features |= BNXT_HW_FEATURE_VLAN_ALL_RX; + if (bp->fw_cap & BNXT_FW_CAP_VLAN_TX_INSERT) + dev->hw_features |= BNXT_HW_FEATURE_VLAN_ALL_TX; if (BNXT_SUPPORTS_TPA(bp)) dev->hw_features |= NETIF_F_GRO_HW; dev->features |= dev->hw_features | NETIF_F_HIGHDMA; @@ -12018,7 +12060,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_fw_init_one_p3(bp); - if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX) + if (dev->hw_features & BNXT_HW_FEATURE_VLAN_ALL_RX) bp->flags |= BNXT_FLAG_STRIP_VLAN; rc = bnxt_init_int_mode(bp); @@ -12030,6 +12072,11 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + rc = bnxt_alloc_rss_indir_tbl(bp); + if (rc) + goto init_err_pci_clean; + bnxt_set_dflt_rss_indir_tbl(bp); + if (BNXT_PF(bp)) { if (!bnxt_pf_wq) { bnxt_pf_wq = @@ -12074,6 +12121,8 @@ init_err_pci_clean: bnxt_free_ctx_mem(bp); kfree(bp->ctx); bp->ctx = NULL; + kfree(bp->rss_indir_tbl); + bp->rss_indir_tbl = NULL; init_err_free: free_netdev(dev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 78e2fd63ac3d..2acd7f958246 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1017,6 +1017,15 @@ struct bnxt_vnic_info { __le16 *rss_table; dma_addr_t rss_hash_key_dma_addr; u64 *rss_hash_key; + int rss_table_size; +#define BNXT_RSS_TABLE_ENTRIES_P5 64 +#define BNXT_RSS_TABLE_SIZE_P5 (BNXT_RSS_TABLE_ENTRIES_P5 * 4) +#define BNXT_RSS_TABLE_MAX_TBL_P5 8 +#define BNXT_MAX_RSS_TABLE_SIZE_P5 \ + (BNXT_RSS_TABLE_SIZE_P5 * BNXT_RSS_TABLE_MAX_TBL_P5) +#define BNXT_MAX_RSS_TABLE_ENTRIES_P5 \ + (BNXT_RSS_TABLE_ENTRIES_P5 * BNXT_RSS_TABLE_MAX_TBL_P5) + u32 rx_mask; u8 *mc_list; @@ -1648,6 +1657,8 @@ struct bnxt { struct bnxt_ring_grp_info *grp_info; struct bnxt_vnic_info *vnic_info; int nr_vnics; + u16 *rss_indir_tbl; + u16 rss_indir_tbl_entries; u32 rss_hash_cfg; u16 max_mtu; @@ -1705,6 +1716,9 @@ struct bnxt { #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 #define BNXT_FW_CAP_HOT_RESET 0x00200000 #define BNXT_FW_CAP_SHARED_PORT_CFG 0x00400000 + #define BNXT_FW_CAP_VLAN_RX_STRIP 0x01000000 + #define BNXT_FW_CAP_VLAN_TX_INSERT 0x02000000 + #define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED 0x04000000 #define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; @@ -1751,12 +1765,8 @@ struct bnxt { ((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv)) #define BNXT_FW_MAJ(bp) ((bp)->fw_ver_code >> 48) - __be16 vxlan_port; - u8 vxlan_port_cnt; - __le16 vxlan_fw_dst_port_id; - __be16 nge_port; - u8 nge_port_cnt; - __le16 nge_fw_dst_port_id; + u16 vxlan_fw_dst_port_id; + u16 nge_fw_dst_port_id; u8 port_partition_type; u8 port_count; u16 br_mode; @@ -1776,16 +1786,12 @@ struct bnxt { #define BNXT_RX_NTP_FLTR_SP_EVENT 1 #define BNXT_LINK_CHNG_SP_EVENT 2 #define BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT 3 -#define BNXT_VXLAN_ADD_PORT_SP_EVENT 4 -#define BNXT_VXLAN_DEL_PORT_SP_EVENT 5 #define BNXT_RESET_TASK_SP_EVENT 6 #define BNXT_RST_RING_SP_EVENT 7 #define BNXT_HWRM_PF_UNLOAD_SP_EVENT 8 #define BNXT_PERIODIC_STATS_SP_EVENT 9 #define BNXT_HWRM_PORT_MODULE_SP_EVENT 10 #define BNXT_RESET_TASK_SILENT_SP_EVENT 11 -#define BNXT_GENEVE_ADD_PORT_SP_EVENT 12 -#define BNXT_GENEVE_DEL_PORT_SP_EVENT 13 #define BNXT_LINK_SPEED_CHNG_SP_EVENT 14 #define BNXT_FLOW_STATS_SP_EVENT 15 #define BNXT_UPDATE_PHY_SP_EVENT 16 @@ -1895,6 +1901,11 @@ struct bnxt { #define BNXT_PCIE_STATS_OFFSET(counter) \ (offsetof(struct pcie_ctx_hw_stats, counter) / 8) +#define BNXT_HW_FEATURE_VLAN_ALL_RX \ + (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX) +#define BNXT_HW_FEATURE_VLAN_ALL_TX \ + (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX) + #define I2C_DEV_ADDR_A0 0xa0 #define I2C_DEV_ADDR_A2 0xa2 #define SFF_DIAG_SUPPORT_OFFSET 0x5c @@ -2028,6 +2039,7 @@ int hwrm_send_message(struct bnxt *, void *, u32, int); int hwrm_send_message_silent(struct bnxt *, void *, u32, int); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, bool async_only); +int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings); int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id); int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings); int bnxt_nq_rings_in_use(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 2bd610fafc58..3a854195d5b0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -691,6 +691,7 @@ static void bnxt_dl_params_unregister(struct bnxt *bp) int bnxt_dl_register(struct bnxt *bp) { + struct devlink_port_attrs attrs = {}; struct devlink *dl; int rc; @@ -719,9 +720,11 @@ int bnxt_dl_register(struct bnxt *bp) if (!BNXT_PF(bp)) return 0; - devlink_port_attrs_set(&bp->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - bp->pf.port_id, false, 0, bp->dsn, - sizeof(bp->dsn)); + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = bp->pf.port_id; + memcpy(attrs.switch_id.id, bp->dsn, sizeof(bp->dsn)); + attrs.switch_id.id_len = sizeof(bp->dsn); + devlink_port_attrs_set(&bp->dl_port, &attrs); rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id); if (rc) { netdev_err(bp->dev, "devlink_port_register failed\n"); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6b88143af5ea..538c976200f7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -926,6 +926,13 @@ static int bnxt_set_channels(struct net_device *dev, return rc; } + if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != + bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && + (dev->priv_flags & IFF_RXFH_CONFIGURED)) { + netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n"); + return -EINVAL; + } + if (netif_running(dev)) { if (BNXT_PF(bp)) { /* TODO CHIMP_FW: Send message to all VF's @@ -1273,8 +1280,12 @@ static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return rc; } -static u32 bnxt_get_rxfh_indir_size(struct net_device *dev) +u32 bnxt_get_rxfh_indir_size(struct net_device *dev) { + struct bnxt *bp = netdev_priv(dev); + + if (bp->flags & BNXT_FLAG_CHIP_P5) + return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5); return HW_HASH_INDEX_SIZE; } @@ -1288,7 +1299,7 @@ static int bnxt_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, { struct bnxt *bp = netdev_priv(dev); struct bnxt_vnic_info *vnic; - int i = 0; + u32 i, tbl_size; if (hfunc) *hfunc = ETH_RSS_HASH_TOP; @@ -1297,9 +1308,10 @@ static int bnxt_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, return 0; vnic = &bp->vnic_info[0]; - if (indir && vnic->rss_table) { - for (i = 0; i < HW_HASH_INDEX_SIZE; i++) - indir[i] = le16_to_cpu(vnic->rss_table[i]); + if (indir && bp->rss_indir_tbl) { + tbl_size = bnxt_get_rxfh_indir_size(dev); + for (i = 0; i < tbl_size; i++) + indir[i] = bp->rss_indir_tbl[i]; } if (key && vnic->rss_hash_key) @@ -1308,6 +1320,35 @@ static int bnxt_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, return 0; } +static int bnxt_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct bnxt *bp = netdev_priv(dev); + int rc = 0; + + if (hfunc && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + if (key) + return -EOPNOTSUPP; + + if (indir) { + u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(dev); + + for (i = 0; i < tbl_size; i++) + bp->rss_indir_tbl[i] = indir[i]; + pad = bp->rss_indir_tbl_entries - tbl_size; + if (pad) + memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16)); + } + + if (netif_running(bp->dev)) { + bnxt_close_nic(bp, false, false); + rc = bnxt_open_nic(bp, false, false); + } + return rc; +} + static void bnxt_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { @@ -3614,6 +3655,7 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_rxfh_indir_size = bnxt_get_rxfh_indir_size, .get_rxfh_key_size = bnxt_get_rxfh_key_size, .get_rxfh = bnxt_get_rxfh, + .set_rxfh = bnxt_set_rxfh, .flash_device = bnxt_flash_device, .get_eeprom_len = bnxt_get_eeprom_len, .get_eeprom = bnxt_get_eeprom, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index ce7585ff9e4d..dddbca1d052c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -86,6 +86,7 @@ struct hwrm_dbg_cmn_output { extern const struct ethtool_ops bnxt_ethtool_ops; +u32 bnxt_get_rxfh_indir_size(struct net_device *dev); u32 _bnxt_fw_to_ethtool_adv_spds(u16, u8); u32 bnxt_fw_to_ethtool_speed(u16); u16 bnxt_get_fw_auto_link_speeds(u32); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 3a9a51f7063a..392e32c7122a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -396,6 +396,7 @@ static void bnxt_free_vf_resources(struct bnxt *bp) } } + bp->pf.active_vfs = 0; kfree(bp->pf.vf); bp->pf.vf = NULL; } @@ -835,7 +836,6 @@ void bnxt_sriov_disable(struct bnxt *bp) bnxt_free_vf_resources(bp); - bp->pf.active_vfs = 0; /* Reclaim all resources for the PF. */ rtnl_lock(); bnxt_restore_pf_fw_resources(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 0a9a4467d7c7..e82e5cf64d61 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1888,7 +1888,7 @@ static void bnxt_tc_setup_indr_rel(void *cb_priv) kfree(priv); } -static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp, +static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct Qdisc *sch, struct bnxt *bp, struct flow_block_offload *f, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) { @@ -1911,7 +1911,7 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp, block_cb = flow_indr_block_cb_alloc(bnxt_tc_setup_indr_block_cb, cb_priv, cb_priv, bnxt_tc_setup_indr_rel, f, - netdev, data, bp, cleanup); + netdev, sch, data, bp, cleanup); if (IS_ERR(block_cb)) { list_del(&cb_priv->list); kfree(cb_priv); @@ -1946,7 +1946,7 @@ static bool bnxt_is_netdev_indr_offload(struct net_device *netdev) return netif_is_vxlan(netdev); } -static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv, +static int bnxt_tc_setup_indr_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) @@ -1956,8 +1956,7 @@ static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv, switch (type) { case TC_SETUP_BLOCK: - return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data, data, - cleanup); + return bnxt_tc_setup_indr_block(netdev, sch, cb_priv, type_data, data, cleanup); default: break; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6c99a519ab06..e5e37aa81b02 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2819,11 +2819,13 @@ static void macb_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct macb *bp = netdev_priv(netdev); - wol->supported = 0; - wol->wolopts = 0; - - if (bp->wol & MACB_WOL_HAS_MAGIC_PACKET) + if (bp->wol & MACB_WOL_HAS_MAGIC_PACKET) { phylink_ethtool_get_wol(bp->phylink, wol); + wol->supported |= WAKE_MAGIC; + + if (bp->wol & MACB_WOL_ENABLED) + wol->wolopts |= WAKE_MAGIC; + } } static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) @@ -2831,9 +2833,13 @@ static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) struct macb *bp = netdev_priv(netdev); int ret; + /* Pass the order to phylink layer */ ret = phylink_ethtool_set_wol(bp->phylink, wol); - if (!ret) - return 0; + /* Don't manage WoL on MAC if handled by the PHY + * or if there's a failure in talking to the PHY + */ + if (!ret || ret != -EOPNOTSUPP) + return ret; if (!(bp->wol & MACB_WOL_HAS_MAGIC_PACKET) || (wol->wolopts & ~WAKE_MAGIC)) @@ -4413,7 +4419,7 @@ static int macb_probe(struct platform_device *pdev) bp->wol = 0; if (of_get_property(np, "magic-packet", NULL)) bp->wol |= MACB_WOL_HAS_MAGIC_PACKET; - device_init_wakeup(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET); + device_set_wakeup_capable(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET); spin_lock_init(&bp->lock); @@ -4589,10 +4595,10 @@ static int __maybe_unused macb_suspend(struct device *dev) bp->pm_data.scrt2 = gem_readl_n(bp, ETHT, SCRT2_ETHT); } - netif_carrier_off(netdev); if (bp->ptp_info) bp->ptp_info->ptp_remove(netdev); - pm_runtime_force_suspend(dev); + if (!device_may_wakeup(dev)) + pm_runtime_force_suspend(dev); return 0; } @@ -4607,7 +4613,8 @@ static int __maybe_unused macb_resume(struct device *dev) if (!netif_running(netdev)) return 0; - pm_runtime_force_resume(dev); + if (!device_may_wakeup(dev)) + pm_runtime_force_resume(dev); if (bp->wol & MACB_WOL_ENABLED) { macb_writel(bp, IDR, MACB_BIT(WOL)); @@ -4645,7 +4652,7 @@ static int __maybe_unused macb_runtime_suspend(struct device *dev) struct net_device *netdev = dev_get_drvdata(dev); struct macb *bp = netdev_priv(netdev); - if (!(device_may_wakeup(&bp->dev->dev))) { + if (!(device_may_wakeup(dev))) { clk_disable_unprepare(bp->tx_clk); clk_disable_unprepare(bp->hclk); clk_disable_unprepare(bp->pclk); @@ -4661,7 +4668,7 @@ static int __maybe_unused macb_runtime_resume(struct device *dev) struct net_device *netdev = dev_get_drvdata(dev); struct macb *bp = netdev_priv(netdev); - if (!(device_may_wakeup(&bp->dev->dev))) { + if (!(device_may_wakeup(dev))) { clk_prepare_enable(bp->pclk); clk_prepare_enable(bp->hclk); clk_prepare_enable(bp->tx_clk); diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index 617b3b728dd0..cd7d0332cba3 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -2,7 +2,7 @@ /** * Cadence GEM PCI wrapper. * - * Copyright (C) 2016 Cadence Design Systems - http://www.cadence.com + * Copyright (C) 2016 Cadence Design Systems - https://www.cadence.com * * Authors: Rafal Ozieblo <rafalo@cadence.com> * Bartosz Folta <bfolta@cadence.com> diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 43a3f0dbf857..31ebf3ee7ec0 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -2,7 +2,7 @@ /** * 1588 PTP support for Cadence GEM device. * - * Copyright (C) 2017 Cadence Design Systems - http://www.cadence.com + * Copyright (C) 2017 Cadence Design Systems - https://www.cadence.com * * Authors: Rafal Ozieblo <rafalo@cadence.com> * Bartosz Folta <bfolta@cadence.com> diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 482b633f7679..650db92cb11c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1112,16 +1112,16 @@ static bool is_addr_all_mask(u8 *ipmask, int family) struct in_addr *addr; addr = (struct in_addr *)ipmask; - if (ntohl(addr->s_addr) == 0xffffffff) + if (addr->s_addr == htonl(0xffffffff)) return true; } else if (family == AF_INET6) { struct in6_addr *addr6; addr6 = (struct in6_addr *)ipmask; - if (ntohl(addr6->s6_addr32[0]) == 0xffffffff && - ntohl(addr6->s6_addr32[1]) == 0xffffffff && - ntohl(addr6->s6_addr32[2]) == 0xffffffff && - ntohl(addr6->s6_addr32[3]) == 0xffffffff) + if (addr6->s6_addr32[0] == htonl(0xffffffff) && + addr6->s6_addr32[1] == htonl(0xffffffff) && + addr6->s6_addr32[2] == htonl(0xffffffff) && + addr6->s6_addr32[3] == htonl(0xffffffff)) return true; } return false; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 0af5ee9975df..8a56491bb034 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3493,7 +3493,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, drv_fw = &fw_info->fw_hdr; /* Read the header of the firmware on the card */ - ret = -t4_read_flash(adap, FLASH_FW_START, + ret = t4_read_flash(adap, FLASH_FW_START, sizeof(*card_fw) / sizeof(uint32_t), (uint32_t *)card_fw, 1); if (ret == 0) { @@ -3522,8 +3522,8 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, should_install_fs_fw(adap, card_fw_usable, be32_to_cpu(fs_fw->fw_ver), be32_to_cpu(card_fw->fw_ver))) { - ret = -t4_fw_upgrade(adap, adap->mbox, fw_data, - fw_size, 0); + ret = t4_fw_upgrade(adap, adap->mbox, fw_data, + fw_size, 0); if (ret != 0) { dev_err(adap->pdev_dev, "failed to install firmware: %d\n", ret); @@ -3554,7 +3554,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c), FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k), FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k)); - ret = EINVAL; + ret = -EINVAL; goto bye; } diff --git a/drivers/net/ethernet/cortina/Kconfig b/drivers/net/ethernet/cortina/Kconfig index ac8cb5744a87..aaf9e294b70b 100644 --- a/drivers/net/ethernet/cortina/Kconfig +++ b/drivers/net/ethernet/cortina/Kconfig @@ -7,7 +7,7 @@ config NET_VENDOR_CORTINA help If you have a network (Ethernet) card belonging to this class, say Y and read the Ethernet-HOWTO, available from - <http://www.tldp.org/docs.html#howto>. + <https://www.tldp.org/docs.html#howto>. if NET_VENDOR_CORTINA diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index ad261e67f5a8..3f32b85ba2cf 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -266,7 +266,7 @@ static irqreturn_t enetc_msix(int irq, void *data) /* disable interrupts */ enetc_wr_reg(v->rbier, 0); - for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings) + for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0); napi_schedule_irqoff(&v->napi); @@ -302,7 +302,7 @@ static int enetc_poll(struct napi_struct *napi, int budget) /* enable interrupts */ enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE); - for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings) + for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS) enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), ENETC_TBIER_TXTIE); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index b8b336179d82..a9939550fa8f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -511,7 +511,7 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, cbd.addr[0] = lower_32_bits(dma); cbd.addr[1] = upper_32_bits(dma); - memset(si_data->dmac, 0xff, ETH_ALEN); + eth_broadcast_addr(si_data->dmac); si_data->vid_vidm_tg = cpu_to_le16(ENETC_CBDR_SID_VID_MASK + ((0x3 << 14) | ENETC_CBDR_SID_VIDM)); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index a6cdd5b61921..d8d76da51c5e 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -525,11 +525,6 @@ struct fec_enet_private { unsigned int total_tx_ring_size; unsigned int total_rx_ring_size; - unsigned long work_tx; - unsigned long work_rx; - unsigned long work_ts; - unsigned long work_mdio; - struct platform_device *pdev; int dev_id; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 9f80a33c5b16..a93381284f08 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -75,8 +75,6 @@ static void fec_enet_itr_coal_init(struct net_device *ndev); #define DRIVER_NAME "fec" -#define FEC_ENET_GET_QUQUE(_x) ((_x == 0) ? 1 : ((_x == 1) ? 2 : 0)) - /* Pause frame feild and FIFO threshold */ #define FEC_ENET_FCE (1 << 5) #define FEC_ENET_RSEM_V 0x84 @@ -1247,8 +1245,6 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) fep = netdev_priv(ndev); - queue_id = FEC_ENET_GET_QUQUE(queue_id); - txq = fep->tx_queue[queue_id]; /* get next bdp of dirty_tx */ nq = netdev_get_tx_queue(ndev, queue_id); @@ -1339,17 +1335,14 @@ skb_done: writel(0, txq->bd.reg_desc_active); } -static void -fec_enet_tx(struct net_device *ndev) +static void fec_enet_tx(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); - u16 queue_id; - /* First process class A queue, then Class B and Best Effort queue */ - for_each_set_bit(queue_id, &fep->work_tx, FEC_ENET_MAX_TX_QS) { - clear_bit(queue_id, &fep->work_tx); - fec_enet_tx_queue(ndev, queue_id); - } - return; + int i; + + /* Make sure that AVB queues are processed first. */ + for (i = fep->num_tx_queues - 1; i >= 0; i--) + fec_enet_tx_queue(ndev, i); } static int @@ -1425,7 +1418,6 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) #ifdef CONFIG_M532x flush_cache_all(); #endif - queue_id = FEC_ENET_GET_QUQUE(queue_id); rxq = fep->rx_queue[queue_id]; /* First, grab all of the stats for the incoming packet. @@ -1549,6 +1541,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) htons(ETH_P_8021Q), vlan_tag); + skb_record_rx_queue(skb, queue_id); napi_gro_receive(&fep->napi, skb); if (is_copybreak) { @@ -1594,48 +1587,30 @@ rx_processing_done: return pkt_received; } -static int -fec_enet_rx(struct net_device *ndev, int budget) +static int fec_enet_rx(struct net_device *ndev, int budget) { - int pkt_received = 0; - u16 queue_id; struct fec_enet_private *fep = netdev_priv(ndev); + int i, done = 0; - for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) { - int ret; - - ret = fec_enet_rx_queue(ndev, - budget - pkt_received, queue_id); + /* Make sure that AVB queues are processed first. */ + for (i = fep->num_rx_queues - 1; i >= 0; i--) + done += fec_enet_rx_queue(ndev, budget - done, i); - if (ret < budget - pkt_received) - clear_bit(queue_id, &fep->work_rx); - - pkt_received += ret; - } - return pkt_received; + return done; } -static bool -fec_enet_collect_events(struct fec_enet_private *fep, uint int_events) +static bool fec_enet_collect_events(struct fec_enet_private *fep) { - if (int_events == 0) - return false; + uint int_events; - if (int_events & FEC_ENET_RXF_0) - fep->work_rx |= (1 << 2); - if (int_events & FEC_ENET_RXF_1) - fep->work_rx |= (1 << 0); - if (int_events & FEC_ENET_RXF_2) - fep->work_rx |= (1 << 1); + int_events = readl(fep->hwp + FEC_IEVENT); - if (int_events & FEC_ENET_TXF_0) - fep->work_tx |= (1 << 2); - if (int_events & FEC_ENET_TXF_1) - fep->work_tx |= (1 << 0); - if (int_events & FEC_ENET_TXF_2) - fep->work_tx |= (1 << 1); + /* Don't clear MDIO events, we poll for those */ + int_events &= ~FEC_ENET_MII; - return true; + writel(int_events, fep->hwp + FEC_IEVENT); + + return int_events != 0; } static irqreturn_t @@ -1643,18 +1618,9 @@ fec_enet_interrupt(int irq, void *dev_id) { struct net_device *ndev = dev_id; struct fec_enet_private *fep = netdev_priv(ndev); - uint int_events; irqreturn_t ret = IRQ_NONE; - int_events = readl(fep->hwp + FEC_IEVENT); - - /* Don't clear MDIO events, we poll for those */ - int_events &= ~FEC_ENET_MII; - - writel(int_events, fep->hwp + FEC_IEVENT); - fec_enet_collect_events(fep, int_events); - - if ((fep->work_tx || fep->work_rx) && fep->link) { + if (fec_enet_collect_events(fep) && fep->link) { ret = IRQ_HANDLED; if (napi_schedule_prep(&fep->napi)) { @@ -1671,17 +1637,19 @@ static int fec_enet_rx_napi(struct napi_struct *napi, int budget) { struct net_device *ndev = napi->dev; struct fec_enet_private *fep = netdev_priv(ndev); - int pkts; - - pkts = fec_enet_rx(ndev, budget); + int done = 0; - fec_enet_tx(ndev); + do { + done += fec_enet_rx(ndev, budget - done); + fec_enet_tx(ndev); + } while ((done < budget) && fec_enet_collect_events(fep)); - if (pkts < budget) { - napi_complete_done(napi, pkts); + if (done < budget) { + napi_complete_done(napi, done); writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); } - return pkts; + + return done; } /* ------------------------------------------------------------------------- */ @@ -3710,6 +3678,8 @@ fec_probe(struct platform_device *pdev) fec_enet_clk_enable(ndev, false); pinctrl_pm_select_sleep_state(&pdev->dev); + ndev->max_mtu = PKT_MAXBUF_SIZE - ETH_HLEN - ETH_FCS_LEN; + ret = register_netdev(ndev); if (ret) goto failed_register; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b319a766889f..fe7d57aeffd8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4140,9 +4140,8 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) hns3_put_ring_config(priv); - hns3_dbg_uninit(handle); - out_netdev_free: + hns3_dbg_uninit(handle); free_netdev(netdev); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 6b1545f982aa..2622e04e8eed 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -180,18 +180,21 @@ static void hns3_lb_check_skb_data(struct hns3_enet_ring *ring, { struct hns3_enet_tqp_vector *tqp_vector = ring->tqp_vector; unsigned char *packet = skb->data; + u32 len = skb_headlen(skb); u32 i; - for (i = 0; i < skb->len; i++) + len = min_t(u32, len, HNS3_NIC_LB_TEST_PACKET_SIZE); + + for (i = 0; i < len; i++) if (packet[i] != (unsigned char)(i & 0xff)) break; /* The packet is correctly received */ - if (i == skb->len) + if (i == HNS3_NIC_LB_TEST_PACKET_SIZE) tqp_vector->rx_group.total_packets++; else print_hex_dump(KERN_ERR, "selftest:", DUMP_PREFIX_OFFSET, 16, 1, - skb->data, skb->len, true); + skb->data, len, true); dev_kfree_skb_any(skb); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 96bfad52630d..d6bfdc6520df 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9859,7 +9859,7 @@ retry: set_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); hdev->reset_type = HNAE3_FLR_RESET; ret = hclge_reset_prepare(hdev); - if (ret) { + if (ret || hdev->reset_pending) { dev_err(&hdev->pdev->dev, "fail to prepare FLR, ret=%d\n", ret); if (hdev->reset_pending || diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 1b9578d0bd80..a10b022d1951 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1793,6 +1793,11 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) if (hdev->reset_type == HNAE3_VF_FUNC_RESET) { hclgevf_build_send_msg(&send_msg, HCLGE_MBX_RESET, 0); ret = hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to assert VF reset, ret = %d\n", ret); + return ret; + } hdev->rst_stats.vf_func_rst_cnt++; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 45c137827a16..47c60d9752e4 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -880,6 +880,8 @@ err_aeqs_init: err_init_msix: err_pfhwdev_alloc: hinic_free_hwif(hwif); + if (err > 0) + err = -EIO; return ERR_PTR(err); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index c33eb1147055..e0f5a81d8620 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -370,48 +370,89 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, MSG_NOT_RESP, timeout); } -/** - * mgmt_recv_msg_handler - handler for message from mgmt cpu - * @pf_to_mgmt: PF to MGMT channel - * @recv_msg: received message details - **/ -static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt, - struct hinic_recv_msg *recv_msg) +static void recv_mgmt_msg_work_handler(struct work_struct *work) { - struct hinic_hwif *hwif = pf_to_mgmt->hwif; - struct pci_dev *pdev = hwif->pdev; - u8 *buf_out = recv_msg->buf_out; + struct hinic_mgmt_msg_handle_work *mgmt_work = + container_of(work, struct hinic_mgmt_msg_handle_work, work); + struct hinic_pf_to_mgmt *pf_to_mgmt = mgmt_work->pf_to_mgmt; + struct pci_dev *pdev = pf_to_mgmt->hwif->pdev; + u8 *buf_out = pf_to_mgmt->mgmt_ack_buf; struct hinic_mgmt_cb *mgmt_cb; unsigned long cb_state; u16 out_size = 0; - if (recv_msg->mod >= HINIC_MOD_MAX) { + memset(buf_out, 0, MAX_PF_MGMT_BUF_SIZE); + + if (mgmt_work->mod >= HINIC_MOD_MAX) { dev_err(&pdev->dev, "Unknown MGMT MSG module = %d\n", - recv_msg->mod); + mgmt_work->mod); + kfree(mgmt_work->msg); + kfree(mgmt_work); return; } - mgmt_cb = &pf_to_mgmt->mgmt_cb[recv_msg->mod]; + mgmt_cb = &pf_to_mgmt->mgmt_cb[mgmt_work->mod]; cb_state = cmpxchg(&mgmt_cb->state, HINIC_MGMT_CB_ENABLED, HINIC_MGMT_CB_ENABLED | HINIC_MGMT_CB_RUNNING); if ((cb_state == HINIC_MGMT_CB_ENABLED) && (mgmt_cb->cb)) - mgmt_cb->cb(mgmt_cb->handle, recv_msg->cmd, - recv_msg->msg, recv_msg->msg_len, + mgmt_cb->cb(mgmt_cb->handle, mgmt_work->cmd, + mgmt_work->msg, mgmt_work->msg_len, buf_out, &out_size); else dev_err(&pdev->dev, "No MGMT msg handler, mod: %d, cmd: %d\n", - recv_msg->mod, recv_msg->cmd); + mgmt_work->mod, mgmt_work->cmd); mgmt_cb->state &= ~HINIC_MGMT_CB_RUNNING; - if (!recv_msg->async_mgmt_to_pf) + if (!mgmt_work->async_mgmt_to_pf) /* MGMT sent sync msg, send the response */ - msg_to_mgmt_async(pf_to_mgmt, recv_msg->mod, recv_msg->cmd, + msg_to_mgmt_async(pf_to_mgmt, mgmt_work->mod, mgmt_work->cmd, buf_out, out_size, MGMT_RESP, - recv_msg->msg_id); + mgmt_work->msg_id); + + kfree(mgmt_work->msg); + kfree(mgmt_work); +} + +/** + * mgmt_recv_msg_handler - handler for message from mgmt cpu + * @pf_to_mgmt: PF to MGMT channel + * @recv_msg: received message details + **/ +static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt, + struct hinic_recv_msg *recv_msg) +{ + struct hinic_mgmt_msg_handle_work *mgmt_work = NULL; + struct pci_dev *pdev = pf_to_mgmt->hwif->pdev; + + mgmt_work = kzalloc(sizeof(*mgmt_work), GFP_KERNEL); + if (!mgmt_work) { + dev_err(&pdev->dev, "Allocate mgmt work memory failed\n"); + return; + } + + if (recv_msg->msg_len) { + mgmt_work->msg = kzalloc(recv_msg->msg_len, GFP_KERNEL); + if (!mgmt_work->msg) { + dev_err(&pdev->dev, "Allocate mgmt msg memory failed\n"); + kfree(mgmt_work); + return; + } + } + + mgmt_work->pf_to_mgmt = pf_to_mgmt; + mgmt_work->msg_len = recv_msg->msg_len; + memcpy(mgmt_work->msg, recv_msg->msg, recv_msg->msg_len); + mgmt_work->msg_id = recv_msg->msg_id; + mgmt_work->mod = recv_msg->mod; + mgmt_work->cmd = recv_msg->cmd; + mgmt_work->async_mgmt_to_pf = recv_msg->async_mgmt_to_pf; + + INIT_WORK(&mgmt_work->work, recv_mgmt_msg_work_handler); + queue_work(pf_to_mgmt->workq, &mgmt_work->work); } /** @@ -546,6 +587,12 @@ static int alloc_msg_buf(struct hinic_pf_to_mgmt *pf_to_mgmt) if (!pf_to_mgmt->sync_msg_buf) return -ENOMEM; + pf_to_mgmt->mgmt_ack_buf = devm_kzalloc(&pdev->dev, + MAX_PF_MGMT_BUF_SIZE, + GFP_KERNEL); + if (!pf_to_mgmt->mgmt_ack_buf) + return -ENOMEM; + return 0; } @@ -571,6 +618,11 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt, return 0; sema_init(&pf_to_mgmt->sync_msg_lock, 1); + pf_to_mgmt->workq = create_singlethread_workqueue("hinic_mgmt"); + if (!pf_to_mgmt->workq) { + dev_err(&pdev->dev, "Failed to initialize MGMT workqueue\n"); + return -ENOMEM; + } pf_to_mgmt->sync_msg_id = 0; err = alloc_msg_buf(pf_to_mgmt); @@ -605,4 +657,5 @@ void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt) hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU); hinic_api_cmd_free(pf_to_mgmt->cmd_chain); + destroy_workqueue(pf_to_mgmt->workq); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h index 919d2c6ffc35..e8a55b53c855 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h @@ -124,6 +124,7 @@ struct hinic_pf_to_mgmt { struct semaphore sync_msg_lock; u16 sync_msg_id; u8 *sync_msg_buf; + void *mgmt_ack_buf; struct hinic_recv_msg recv_resp_msg_from_mgmt; struct hinic_recv_msg recv_msg_from_mgmt; @@ -131,6 +132,21 @@ struct hinic_pf_to_mgmt { struct hinic_api_cmd_chain *cmd_chain[HINIC_API_CMD_MAX]; struct hinic_mgmt_cb mgmt_cb[HINIC_MOD_MAX]; + + struct workqueue_struct *workq; +}; + +struct hinic_mgmt_msg_handle_work { + struct work_struct work; + struct hinic_pf_to_mgmt *pf_to_mgmt; + + void *msg; + u16 msg_len; + + enum hinic_mod_type mod; + u8 cmd; + u16 msg_id; + int async_mgmt_to_pf; }; void hinic_register_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt, diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 3ea470e8cfa2..43da2dcb0cbc 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -312,6 +312,7 @@ int ice_devlink_create_port(struct ice_pf *pf) struct devlink *devlink = priv_to_devlink(pf); struct ice_vsi *vsi = ice_get_main_vsi(pf); struct device *dev = ice_pf_to_dev(pf); + struct devlink_port_attrs attrs = {}; int err; if (!vsi) { @@ -319,8 +320,9 @@ int ice_devlink_create_port(struct ice_pf *pf) return -EIO; } - devlink_port_attrs_set(&pf->devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - pf->hw.pf_id, false, 0, NULL, 0); + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = pf->hw.pf_id; + devlink_port_attrs_set(&pf->devlink_port, &attrs); err = devlink_port_register(devlink, &pf->devlink_port, pf->hw.pf_id); if (err) { dev_err(dev, "devlink_port_register failed: %d\n", err); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index debbcf216134..1e8a809233a0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -588,11 +588,9 @@ struct ixgbe_adapter { #define IXGBE_FLAG_FCOE_ENABLED BIT(21) #define IXGBE_FLAG_SRIOV_CAPABLE BIT(22) #define IXGBE_FLAG_SRIOV_ENABLED BIT(23) -#define IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE BIT(24) #define IXGBE_FLAG_RX_HWTSTAMP_ENABLED BIT(25) #define IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER BIT(26) #define IXGBE_FLAG_DCB_CAPABLE BIT(27) -#define IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE BIT(28) u32 flags2; #define IXGBE_FLAG2_RSC_CAPABLE BIT(0) @@ -606,7 +604,6 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP BIT(9) #define IXGBE_FLAG2_PTP_PPS_ENABLED BIT(10) #define IXGBE_FLAG2_PHY_INTERRUPT BIT(11) -#define IXGBE_FLAG2_UDP_TUN_REREG_NEEDED BIT(12) #define IXGBE_FLAG2_VLAN_PROMISC BIT(13) #define IXGBE_FLAG2_EEE_CAPABLE BIT(14) #define IXGBE_FLAG2_EEE_ENABLED BIT(15) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f5d3d6230786..4d898ff21a46 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4994,24 +4994,41 @@ static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) napi_disable(&adapter->q_vector[q_idx]->napi); } -static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) +static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table) { + struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; - u32 vxlanctrl; + struct udp_tunnel_info ti; - if (!(adapter->flags & (IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE | - IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))) - return; + udp_tunnel_nic_get_port(dev, table, 0, &ti); + if (ti.type == UDP_TUNNEL_TYPE_VXLAN) + adapter->vxlan_port = ti.port; + else + adapter->geneve_port = ti.port; - vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask; - IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl); + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, + ntohs(adapter->vxlan_port) | + ntohs(adapter->geneve_port) << + IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT); + return 0; +} - if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK) - adapter->vxlan_port = 0; +static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550 = { + .sync_table = ixgbe_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + }, +}; - if (mask & IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK) - adapter->geneve_port = 0; -} +static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550em_a = { + .sync_table = ixgbe_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, + }, +}; #ifdef CONFIG_IXGBE_DCB /** @@ -6332,7 +6349,6 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; break; case ixgbe_mac_x550em_a: - adapter->flags |= IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE; switch (hw->device_id) { case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: @@ -6359,7 +6375,6 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, #ifdef CONFIG_IXGBE_DCA adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE; #endif - adapter->flags |= IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE; break; default: break; @@ -6798,8 +6813,7 @@ int ixgbe_open(struct net_device *netdev) ixgbe_up_complete(adapter); - ixgbe_clear_udp_tunnel_port(adapter, IXGBE_VXLANCTRL_ALL_UDPPORT_MASK); - udp_tunnel_get_rx_info(netdev); + udp_tunnel_nic_reset_ntf(netdev); return 0; @@ -7921,12 +7935,6 @@ static void ixgbe_service_task(struct work_struct *work) ixgbe_service_event_complete(adapter); return; } - if (adapter->flags2 & IXGBE_FLAG2_UDP_TUN_REREG_NEEDED) { - rtnl_lock(); - adapter->flags2 &= ~IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; - udp_tunnel_get_rx_info(adapter->netdev); - rtnl_unlock(); - } ixgbe_reset_subtask(adapter); ixgbe_phy_interrupt_subtask(adapter); ixgbe_sfp_detection_subtask(adapter); @@ -9784,26 +9792,6 @@ static int ixgbe_set_features(struct net_device *netdev, netdev->features = features; - if ((adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) { - if (features & NETIF_F_RXCSUM) { - adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; - } else { - u32 port_mask = IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK; - - ixgbe_clear_udp_tunnel_port(adapter, port_mask); - } - } - - if ((adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) { - if (features & NETIF_F_RXCSUM) { - adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; - } else { - u32 port_mask = IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK; - - ixgbe_clear_udp_tunnel_port(adapter, port_mask); - } - } - if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1) ixgbe_reset_l2fw_offload(adapter); else if (need_reset) @@ -9815,118 +9803,6 @@ static int ixgbe_set_features(struct net_device *netdev, return 1; } -/** - * ixgbe_add_udp_tunnel_port - Get notifications about adding UDP tunnel ports - * @dev: The port's netdev - * @ti: Tunnel endpoint information - **/ -static void ixgbe_add_udp_tunnel_port(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct ixgbe_adapter *adapter = netdev_priv(dev); - struct ixgbe_hw *hw = &adapter->hw; - __be16 port = ti->port; - u32 port_shift = 0; - u32 reg; - - if (ti->sa_family != AF_INET) - return; - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) - return; - - if (adapter->vxlan_port == port) - return; - - if (adapter->vxlan_port) { - netdev_info(dev, - "VXLAN port %d set, not adding port %d\n", - ntohs(adapter->vxlan_port), - ntohs(port)); - return; - } - - adapter->vxlan_port = port; - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (!(adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) - return; - - if (adapter->geneve_port == port) - return; - - if (adapter->geneve_port) { - netdev_info(dev, - "GENEVE port %d set, not adding port %d\n", - ntohs(adapter->geneve_port), - ntohs(port)); - return; - } - - port_shift = IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT; - adapter->geneve_port = port; - break; - default: - return; - } - - reg = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) | ntohs(port) << port_shift; - IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, reg); -} - -/** - * ixgbe_del_udp_tunnel_port - Get notifications about removing UDP tunnel ports - * @dev: The port's netdev - * @ti: Tunnel endpoint information - **/ -static void ixgbe_del_udp_tunnel_port(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct ixgbe_adapter *adapter = netdev_priv(dev); - u32 port_mask; - - if (ti->type != UDP_TUNNEL_TYPE_VXLAN && - ti->type != UDP_TUNNEL_TYPE_GENEVE) - return; - - if (ti->sa_family != AF_INET) - return; - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) - return; - - if (adapter->vxlan_port != ti->port) { - netdev_info(dev, "VXLAN port %d not found\n", - ntohs(ti->port)); - return; - } - - port_mask = IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK; - break; - case UDP_TUNNEL_TYPE_GENEVE: - if (!(adapter->flags & IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE)) - return; - - if (adapter->geneve_port != ti->port) { - netdev_info(dev, "GENEVE port %d not found\n", - ntohs(ti->port)); - return; - } - - port_mask = IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK; - break; - default: - return; - } - - ixgbe_clear_udp_tunnel_port(adapter, port_mask); - adapter->flags2 |= IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; -} - static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, @@ -10416,8 +10292,8 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, .ndo_dfwd_add_station = ixgbe_fwd_add, .ndo_dfwd_del_station = ixgbe_fwd_del, - .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port, - .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_features_check = ixgbe_features_check, .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, @@ -10862,6 +10738,18 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550; + break; + case ixgbe_mac_x550em_a: + netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550em_a; + break; + default: + break; + } + /* Make sure the SWFW semaphore is in a valid state */ if (hw->mac.ops.init_swfw_sync) hw->mac.ops.init_swfw_sync(hw); diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index c97c74164c73..ddc757680089 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -3,7 +3,7 @@ * JMicron JMC2x0 series PCIe Ethernet Linux Device Driver * * Copyright 2008 JMicron Technology Corporation - * http://www.jmicron.com/ + * https://www.jmicron.com/ * Copyright (c) 2009 - 2010 Guo-Fu Tseng <cooldavid@cooldavid.org> * * Author: Guo-Fu Tseng <cooldavid@cooldavid.org> diff --git a/drivers/net/ethernet/jme.h b/drivers/net/ethernet/jme.h index 2bba5ce20289..a2c3b00d939d 100644 --- a/drivers/net/ethernet/jme.h +++ b/drivers/net/ethernet/jme.h @@ -3,7 +3,7 @@ * JMicron JMC2x0 series PCIe Ethernet Linux Device Driver * * Copyright 2008 JMicron Technology Corporation - * http://www.jmicron.com/ + * https://www.jmicron.com/ * Copyright (c) 2009 - 2010 Guo-Fu Tseng <cooldavid@cooldavid.org> * * Author: Guo-Fu Tseng <cooldavid@cooldavid.org> diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 37b9c75a5a60..7191902f6cfe 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3965,7 +3965,7 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, /* When at 2.5G, the link partner can send frames with shortened * preambles. */ - if (state->speed == SPEED_2500) + if (state->interface == PHY_INTERFACE_MODE_2500BASEX) new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE; if (pp->phy_interface != state->interface) { diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 3c89206f18a7..b792f6306a64 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -939,10 +939,10 @@ static int skge_rx_setup(struct skge_port *skge, struct skge_element *e, struct skge_rx_desc *rd = e->desc; dma_addr_t map; - map = pci_map_single(skge->hw->pdev, skb->data, bufsize, - PCI_DMA_FROMDEVICE); + map = dma_map_single(&skge->hw->pdev->dev, skb->data, bufsize, + DMA_FROM_DEVICE); - if (pci_dma_mapping_error(skge->hw->pdev, map)) + if (dma_mapping_error(&skge->hw->pdev->dev, map)) return -1; rd->dma_lo = lower_32_bits(map); @@ -990,10 +990,10 @@ static void skge_rx_clean(struct skge_port *skge) struct skge_rx_desc *rd = e->desc; rd->control = 0; if (e->skb) { - pci_unmap_single(hw->pdev, + dma_unmap_single(&hw->pdev->dev, dma_unmap_addr(e, mapaddr), dma_unmap_len(e, maplen), - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); dev_kfree_skb(e->skb); e->skb = NULL; } @@ -2547,14 +2547,15 @@ static int skge_up(struct net_device *dev) rx_size = skge->rx_ring.count * sizeof(struct skge_rx_desc); tx_size = skge->tx_ring.count * sizeof(struct skge_tx_desc); skge->mem_size = tx_size + rx_size; - skge->mem = pci_alloc_consistent(hw->pdev, skge->mem_size, &skge->dma); + skge->mem = dma_alloc_coherent(&hw->pdev->dev, skge->mem_size, + &skge->dma, GFP_KERNEL); if (!skge->mem) return -ENOMEM; BUG_ON(skge->dma & 7); if (upper_32_bits(skge->dma) != upper_32_bits(skge->dma + skge->mem_size)) { - dev_err(&hw->pdev->dev, "pci_alloc_consistent region crosses 4G boundary\n"); + dev_err(&hw->pdev->dev, "dma_alloc_coherent region crosses 4G boundary\n"); err = -EINVAL; goto free_pci_mem; } @@ -2625,7 +2626,8 @@ static int skge_up(struct net_device *dev) skge_rx_clean(skge); kfree(skge->rx_ring.start); free_pci_mem: - pci_free_consistent(hw->pdev, skge->mem_size, skge->mem, skge->dma); + dma_free_coherent(&hw->pdev->dev, skge->mem_size, skge->mem, + skge->dma); skge->mem = NULL; return err; @@ -2715,7 +2717,8 @@ static int skge_down(struct net_device *dev) kfree(skge->rx_ring.start); kfree(skge->tx_ring.start); - pci_free_consistent(hw->pdev, skge->mem_size, skge->mem, skge->dma); + dma_free_coherent(&hw->pdev->dev, skge->mem_size, skge->mem, + skge->dma); skge->mem = NULL; return 0; } @@ -2749,8 +2752,8 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb, BUG_ON(td->control & BMU_OWN); e->skb = skb; len = skb_headlen(skb); - map = pci_map_single(hw->pdev, skb->data, len, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(hw->pdev, map)) + map = dma_map_single(&hw->pdev->dev, skb->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(&hw->pdev->dev, map)) goto mapping_error; dma_unmap_addr_set(e, mapaddr, map); @@ -2830,16 +2833,12 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb, mapping_unwind: e = skge->tx_ring.to_use; - pci_unmap_single(hw->pdev, - dma_unmap_addr(e, mapaddr), - dma_unmap_len(e, maplen), - PCI_DMA_TODEVICE); + dma_unmap_single(&hw->pdev->dev, dma_unmap_addr(e, mapaddr), + dma_unmap_len(e, maplen), DMA_TO_DEVICE); while (i-- > 0) { e = e->next; - pci_unmap_page(hw->pdev, - dma_unmap_addr(e, mapaddr), - dma_unmap_len(e, maplen), - PCI_DMA_TODEVICE); + dma_unmap_page(&hw->pdev->dev, dma_unmap_addr(e, mapaddr), + dma_unmap_len(e, maplen), DMA_TO_DEVICE); } mapping_error: @@ -2856,13 +2855,11 @@ static inline void skge_tx_unmap(struct pci_dev *pdev, struct skge_element *e, { /* skb header vs. fragment */ if (control & BMU_STF) - pci_unmap_single(pdev, dma_unmap_addr(e, mapaddr), - dma_unmap_len(e, maplen), - PCI_DMA_TODEVICE); + dma_unmap_single(&pdev->dev, dma_unmap_addr(e, mapaddr), + dma_unmap_len(e, maplen), DMA_TO_DEVICE); else - pci_unmap_page(pdev, dma_unmap_addr(e, mapaddr), - dma_unmap_len(e, maplen), - PCI_DMA_TODEVICE); + dma_unmap_page(&pdev->dev, dma_unmap_addr(e, mapaddr), + dma_unmap_len(e, maplen), DMA_TO_DEVICE); } /* Free all buffers in transmit ring */ @@ -3072,15 +3069,15 @@ static struct sk_buff *skge_rx_get(struct net_device *dev, if (!skb) goto resubmit; - pci_dma_sync_single_for_cpu(skge->hw->pdev, - dma_unmap_addr(e, mapaddr), - dma_unmap_len(e, maplen), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&skge->hw->pdev->dev, + dma_unmap_addr(e, mapaddr), + dma_unmap_len(e, maplen), + DMA_FROM_DEVICE); skb_copy_from_linear_data(e->skb, skb->data, len); - pci_dma_sync_single_for_device(skge->hw->pdev, - dma_unmap_addr(e, mapaddr), - dma_unmap_len(e, maplen), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&skge->hw->pdev->dev, + dma_unmap_addr(e, mapaddr), + dma_unmap_len(e, maplen), + DMA_FROM_DEVICE); skge_rx_reuse(e, skge->rx_buf_size); } else { struct skge_element ee; @@ -3100,10 +3097,9 @@ static struct sk_buff *skge_rx_get(struct net_device *dev, goto resubmit; } - pci_unmap_single(skge->hw->pdev, + dma_unmap_single(&skge->hw->pdev->dev, dma_unmap_addr(&ee, mapaddr), - dma_unmap_len(&ee, maplen), - PCI_DMA_FROMDEVICE); + dma_unmap_len(&ee, maplen), DMA_FROM_DEVICE); } skb_put(skb, len); @@ -3895,12 +3891,12 @@ static int skge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - if (!only_32bit_dma && !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!only_32bit_dma && !dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) { using_dac = 1; - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - } else if (!(err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) { + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); + } else if (!(err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)))) { using_dac = 0; - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); } if (err) { diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 241f00716979..cec8124301c7 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -203,7 +203,7 @@ io_error: static inline u16 gm_phy_read(struct sky2_hw *hw, unsigned port, u16 reg) { - u16 v; + u16 v = 0; __gm_phy_read(hw, port, reg, &v); return v; } @@ -1209,8 +1209,9 @@ static int sky2_rx_map_skb(struct pci_dev *pdev, struct rx_ring_info *re, struct sk_buff *skb = re->skb; int i; - re->data_addr = pci_map_single(pdev, skb->data, size, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(pdev, re->data_addr)) + re->data_addr = dma_map_single(&pdev->dev, skb->data, size, + DMA_FROM_DEVICE); + if (dma_mapping_error(&pdev->dev, re->data_addr)) goto mapping_error; dma_unmap_len_set(re, data_size, size); @@ -1229,13 +1230,13 @@ static int sky2_rx_map_skb(struct pci_dev *pdev, struct rx_ring_info *re, map_page_error: while (--i >= 0) { - pci_unmap_page(pdev, re->frag_addr[i], + dma_unmap_page(&pdev->dev, re->frag_addr[i], skb_frag_size(&skb_shinfo(skb)->frags[i]), - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); } - pci_unmap_single(pdev, re->data_addr, dma_unmap_len(re, data_size), - PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, re->data_addr, + dma_unmap_len(re, data_size), DMA_FROM_DEVICE); mapping_error: if (net_ratelimit()) @@ -1249,13 +1250,13 @@ static void sky2_rx_unmap_skb(struct pci_dev *pdev, struct rx_ring_info *re) struct sk_buff *skb = re->skb; int i; - pci_unmap_single(pdev, re->data_addr, dma_unmap_len(re, data_size), - PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, re->data_addr, + dma_unmap_len(re, data_size), DMA_FROM_DEVICE); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - pci_unmap_page(pdev, re->frag_addr[i], + dma_unmap_page(&pdev->dev, re->frag_addr[i], skb_frag_size(&skb_shinfo(skb)->frags[i]), - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); } /* Tell chip where to start receive checksum. @@ -1592,10 +1593,9 @@ static int sky2_alloc_buffers(struct sky2_port *sky2) struct sky2_hw *hw = sky2->hw; /* must be power of 2 */ - sky2->tx_le = pci_alloc_consistent(hw->pdev, - sky2->tx_ring_size * - sizeof(struct sky2_tx_le), - &sky2->tx_le_map); + sky2->tx_le = dma_alloc_coherent(&hw->pdev->dev, + sky2->tx_ring_size * sizeof(struct sky2_tx_le), + &sky2->tx_le_map, GFP_KERNEL); if (!sky2->tx_le) goto nomem; @@ -1604,8 +1604,8 @@ static int sky2_alloc_buffers(struct sky2_port *sky2) if (!sky2->tx_ring) goto nomem; - sky2->rx_le = pci_zalloc_consistent(hw->pdev, RX_LE_BYTES, - &sky2->rx_le_map); + sky2->rx_le = dma_alloc_coherent(&hw->pdev->dev, RX_LE_BYTES, + &sky2->rx_le_map, GFP_KERNEL); if (!sky2->rx_le) goto nomem; @@ -1626,14 +1626,14 @@ static void sky2_free_buffers(struct sky2_port *sky2) sky2_rx_clean(sky2); if (sky2->rx_le) { - pci_free_consistent(hw->pdev, RX_LE_BYTES, - sky2->rx_le, sky2->rx_le_map); + dma_free_coherent(&hw->pdev->dev, RX_LE_BYTES, sky2->rx_le, + sky2->rx_le_map); sky2->rx_le = NULL; } if (sky2->tx_le) { - pci_free_consistent(hw->pdev, - sky2->tx_ring_size * sizeof(struct sky2_tx_le), - sky2->tx_le, sky2->tx_le_map); + dma_free_coherent(&hw->pdev->dev, + sky2->tx_ring_size * sizeof(struct sky2_tx_le), + sky2->tx_le, sky2->tx_le_map); sky2->tx_le = NULL; } kfree(sky2->tx_ring); @@ -1806,13 +1806,11 @@ static unsigned tx_le_req(const struct sk_buff *skb) static void sky2_tx_unmap(struct pci_dev *pdev, struct tx_ring_info *re) { if (re->flags & TX_MAP_SINGLE) - pci_unmap_single(pdev, dma_unmap_addr(re, mapaddr), - dma_unmap_len(re, maplen), - PCI_DMA_TODEVICE); + dma_unmap_single(&pdev->dev, dma_unmap_addr(re, mapaddr), + dma_unmap_len(re, maplen), DMA_TO_DEVICE); else if (re->flags & TX_MAP_PAGE) - pci_unmap_page(pdev, dma_unmap_addr(re, mapaddr), - dma_unmap_len(re, maplen), - PCI_DMA_TODEVICE); + dma_unmap_page(&pdev->dev, dma_unmap_addr(re, mapaddr), + dma_unmap_len(re, maplen), DMA_TO_DEVICE); re->flags = 0; } @@ -1840,9 +1838,10 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb, return NETDEV_TX_BUSY; len = skb_headlen(skb); - mapping = pci_map_single(hw->pdev, skb->data, len, PCI_DMA_TODEVICE); + mapping = dma_map_single(&hw->pdev->dev, skb->data, len, + DMA_TO_DEVICE); - if (pci_dma_mapping_error(hw->pdev, mapping)) + if (dma_mapping_error(&hw->pdev->dev, mapping)) goto mapping_error; slot = sky2->tx_prod; @@ -2464,16 +2463,17 @@ static struct sk_buff *receive_copy(struct sky2_port *sky2, skb = netdev_alloc_skb_ip_align(sky2->netdev, length); if (likely(skb)) { - pci_dma_sync_single_for_cpu(sky2->hw->pdev, re->data_addr, - length, PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&sky2->hw->pdev->dev, re->data_addr, + length, DMA_FROM_DEVICE); skb_copy_from_linear_data(re->skb, skb->data, length); skb->ip_summed = re->skb->ip_summed; skb->csum = re->skb->csum; skb_copy_hash(skb, re->skb); __vlan_hwaccel_copy_tag(skb, re->skb); - pci_dma_sync_single_for_device(sky2->hw->pdev, re->data_addr, - length, PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&sky2->hw->pdev->dev, + re->data_addr, length, + DMA_FROM_DEVICE); __vlan_hwaccel_clear_tag(re->skb); skb_clear_hash(re->skb); re->skb->ip_summed = CHECKSUM_NONE; @@ -4985,16 +4985,16 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); if (sizeof(dma_addr_t) > sizeof(u32) && - !(err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)))) { + !(err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)))) { using_dac = 1; - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); if (err < 0) { dev_err(&pdev->dev, "unable to obtain 64 bit DMA " "for consistent allocations\n"); goto err_out_free_regions; } } else { - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "no usable DMA configuration\n"); goto err_out_free_regions; @@ -5038,8 +5038,9 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* ring for status responses */ hw->st_size = hw->ports * roundup_pow_of_two(3*RX_MAX_PENDING + TX_MAX_PENDING); - hw->st_le = pci_alloc_consistent(pdev, hw->st_size * sizeof(struct sky2_status_le), - &hw->st_dma); + hw->st_le = dma_alloc_coherent(&pdev->dev, + hw->st_size * sizeof(struct sky2_status_le), + &hw->st_dma, GFP_KERNEL); if (!hw->st_le) { err = -ENOMEM; goto err_out_reset; @@ -5119,8 +5120,9 @@ err_out_free_netdev: pci_disable_msi(pdev); free_netdev(dev); err_out_free_pci: - pci_free_consistent(pdev, hw->st_size * sizeof(struct sky2_status_le), - hw->st_le, hw->st_dma); + dma_free_coherent(&pdev->dev, + hw->st_size * sizeof(struct sky2_status_le), + hw->st_le, hw->st_dma); err_out_reset: sky2_write8(hw, B0_CTST, CS_RST_SET); err_out_iounmap: @@ -5164,8 +5166,9 @@ static void sky2_remove(struct pci_dev *pdev) if (hw->flags & SKY2_HW_USE_MSI) pci_disable_msi(pdev); - pci_free_consistent(pdev, hw->st_size * sizeof(struct sky2_status_le), - hw->st_le, hw->st_dma); + dma_free_coherent(&pdev->dev, + hw->st_size * sizeof(struct sky2_status_le), + hw->st_le, hw->st_dma); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 5bd3cd37d50f..2b8608f8f0a9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1816,7 +1816,7 @@ int mlx4_en_start_port(struct net_device *dev) queue_work(mdev->workqueue, &priv->rx_mode_task); if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) - udp_tunnel_get_rx_info(dev); + udp_tunnel_nic_reset_ntf(dev); priv->port_up = true; @@ -2628,89 +2628,32 @@ static int mlx4_en_get_phys_port_id(struct net_device *dev, return 0; } -static void mlx4_en_add_vxlan_offloads(struct work_struct *work) +static int mlx4_udp_tunnel_sync(struct net_device *dev, unsigned int table) { + struct mlx4_en_priv *priv = netdev_priv(dev); + struct udp_tunnel_info ti; int ret; - struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, - vxlan_add_task); - ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port); - if (ret) - goto out; + udp_tunnel_nic_get_port(dev, table, 0, &ti); + priv->vxlan_port = ti.port; - ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, - VXLAN_STEER_BY_OUTER_MAC, 1); -out: - if (ret) { - en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret); - return; - } -} - -static void mlx4_en_del_vxlan_offloads(struct work_struct *work) -{ - int ret; - struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, - vxlan_del_task); - ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, - VXLAN_STEER_BY_OUTER_MAC, 0); + ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port); if (ret) - en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret); + return ret; - priv->vxlan_port = 0; + return mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, + VXLAN_STEER_BY_OUTER_MAC, + !!priv->vxlan_port); } -static void mlx4_en_add_vxlan_port(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct mlx4_en_priv *priv = netdev_priv(dev); - __be16 port = ti->port; - __be16 current_port; - - if (ti->type != UDP_TUNNEL_TYPE_VXLAN) - return; - - if (ti->sa_family != AF_INET) - return; - - if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) - return; - - current_port = priv->vxlan_port; - if (current_port && current_port != port) { - en_warn(priv, "vxlan port %d configured, can't add port %d\n", - ntohs(current_port), ntohs(port)); - return; - } - - priv->vxlan_port = port; - queue_work(priv->mdev->workqueue, &priv->vxlan_add_task); -} - -static void mlx4_en_del_vxlan_port(struct net_device *dev, - struct udp_tunnel_info *ti) -{ - struct mlx4_en_priv *priv = netdev_priv(dev); - __be16 port = ti->port; - __be16 current_port; - - if (ti->type != UDP_TUNNEL_TYPE_VXLAN) - return; - - if (ti->sa_family != AF_INET) - return; - - if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) - return; - - current_port = priv->vxlan_port; - if (current_port != port) { - en_dbg(DRV, priv, "vxlan port %d isn't configured, ignoring\n", ntohs(port)); - return; - } - - queue_work(priv->mdev->workqueue, &priv->vxlan_del_task); -} +static const struct udp_tunnel_nic_info mlx4_udp_tunnels = { + .sync_table = mlx4_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | + UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + }, +}; static netdev_features_t mlx4_en_features_check(struct sk_buff *skb, struct net_device *dev, @@ -2914,8 +2857,8 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif .ndo_get_phys_port_id = mlx4_en_get_phys_port_id, - .ndo_udp_tunnel_add = mlx4_en_add_vxlan_port, - .ndo_udp_tunnel_del = mlx4_en_del_vxlan_port, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, .ndo_bpf = mlx4_xdp, @@ -2948,8 +2891,8 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif .ndo_get_phys_port_id = mlx4_en_get_phys_port_id, - .ndo_udp_tunnel_add = mlx4_en_add_vxlan_port, - .ndo_udp_tunnel_del = mlx4_en_del_vxlan_port, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, .ndo_bpf = mlx4_xdp, @@ -3250,8 +3193,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); - INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads); - INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads); #ifdef CONFIG_RFS_ACCEL INIT_LIST_HEAD(&priv->filters); spin_lock_init(&priv->filters_lock); @@ -3406,6 +3347,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_PARTIAL; + + dev->udp_tunnel_nic_info = &mlx4_udp_tunnels; } dev->vlan_features = dev->hw_features; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 9f5603612960..a46efe37cfa9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -599,8 +599,6 @@ struct mlx4_en_priv { struct work_struct linkstate_task; struct delayed_work stats_task; struct delayed_work service_task; - struct work_struct vxlan_add_task; - struct work_struct vxlan_del_task; struct mlx4_en_perf_stats pstats; struct mlx4_en_pkt_stats pkstats; struct mlx4_en_counter_stats pf_stats; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 1e7c7f10db6e..124caec65a34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o mlx5_core-$(CONFIG_MLX5_ESWITCH) += lag_mp.o lib/geneve.o lib/port_tun.o \ - en_rep.o en/rep/bond.o + en_rep.o en/rep/bond.o en/mod_hdr.o mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en_tc.o en/rep/tc.o en/rep/neigh.o \ en/mapping.o esw/chains.o en/tc_tun.o \ en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h index 7be6b2d36b60..9976de8b9047 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h @@ -29,6 +29,7 @@ struct mlx5e_dcbx { bool manual_buffer; u32 cable_len; u32 xoff; + u16 port_buff_cell_sz; }; #define MLX5E_MAX_DSCP (64) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index f8b2de4b04be..a69c62d72d16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -6,17 +6,16 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) { struct devlink *devlink = priv_to_devlink(priv->mdev); + struct devlink_port_attrs attrs = {}; - if (mlx5_core_is_pf(priv->mdev)) - devlink_port_attrs_set(&priv->dl_port, - DEVLINK_PORT_FLAVOUR_PHYSICAL, - PCI_FUNC(priv->mdev->pdev->devfn), - false, 0, - NULL, 0); - else - devlink_port_attrs_set(&priv->dl_port, - DEVLINK_PORT_FLAVOUR_VIRTUAL, - 0, false, 0, NULL, 0); + if (mlx5_core_is_pf(priv->mdev)) { + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = PCI_FUNC(priv->mdev->pdev->devfn); + } else { + attrs.flavour = DEVLINK_PORT_FLAVOUR_VIRTUAL; + } + + devlink_port_attrs_set(&priv->dl_port, &attrs); return devlink_port_register(devlink, &priv->dl_port, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 385cbff1caf1..6f4767324044 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -4,6 +4,8 @@ #ifndef __MLX5E_FLOW_STEER_H__ #define __MLX5E_FLOW_STEER_H__ +#include "mod_hdr.h" + enum { MLX5E_TC_FT_LEVEL = 0, MLX5E_TC_TTC_FT_LEVEL, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c new file mode 100644 index 000000000000..7edde4d536fd --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2020 Mellanox Technologies + +#include <linux/jhash.h> +#include "mod_hdr.h" + +#define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) + +struct mod_hdr_key { + int num_actions; + void *actions; +}; + +struct mlx5e_mod_hdr_handle { + /* a node of a hash table which keeps all the mod_hdr entries */ + struct hlist_node mod_hdr_hlist; + + struct mod_hdr_key key; + + struct mlx5_modify_hdr *modify_hdr; + + refcount_t refcnt; + struct completion res_ready; + int compl_result; +}; + +static u32 hash_mod_hdr_info(struct mod_hdr_key *key) +{ + return jhash(key->actions, + key->num_actions * MLX5_MH_ACT_SZ, 0); +} + +static int cmp_mod_hdr_info(struct mod_hdr_key *a, struct mod_hdr_key *b) +{ + if (a->num_actions != b->num_actions) + return 1; + + return memcmp(a->actions, b->actions, + a->num_actions * MLX5_MH_ACT_SZ); +} + +void mlx5e_mod_hdr_tbl_init(struct mod_hdr_tbl *tbl) +{ + mutex_init(&tbl->lock); + hash_init(tbl->hlist); +} + +void mlx5e_mod_hdr_tbl_destroy(struct mod_hdr_tbl *tbl) +{ + mutex_destroy(&tbl->lock); +} + +static struct mlx5e_mod_hdr_handle *mod_hdr_get(struct mod_hdr_tbl *tbl, + struct mod_hdr_key *key, + u32 hash_key) +{ + struct mlx5e_mod_hdr_handle *mh, *found = NULL; + + hash_for_each_possible(tbl->hlist, mh, mod_hdr_hlist, hash_key) { + if (!cmp_mod_hdr_info(&mh->key, key)) { + refcount_inc(&mh->refcnt); + found = mh; + break; + } + } + + return found; +} + +struct mlx5e_mod_hdr_handle * +mlx5e_mod_hdr_attach(struct mlx5_core_dev *mdev, + struct mod_hdr_tbl *tbl, + enum mlx5_flow_namespace_type namespace, + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts) +{ + int num_actions, actions_size, err; + struct mlx5e_mod_hdr_handle *mh; + struct mod_hdr_key key; + u32 hash_key; + + num_actions = mod_hdr_acts->num_actions; + actions_size = MLX5_MH_ACT_SZ * num_actions; + + key.actions = mod_hdr_acts->actions; + key.num_actions = num_actions; + + hash_key = hash_mod_hdr_info(&key); + + mutex_lock(&tbl->lock); + mh = mod_hdr_get(tbl, &key, hash_key); + if (mh) { + mutex_unlock(&tbl->lock); + wait_for_completion(&mh->res_ready); + + if (mh->compl_result < 0) { + err = -EREMOTEIO; + goto attach_header_err; + } + goto attach_header; + } + + mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); + if (!mh) { + mutex_unlock(&tbl->lock); + return ERR_PTR(-ENOMEM); + } + + mh->key.actions = (void *)mh + sizeof(*mh); + memcpy(mh->key.actions, key.actions, actions_size); + mh->key.num_actions = num_actions; + refcount_set(&mh->refcnt, 1); + init_completion(&mh->res_ready); + + hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); + mutex_unlock(&tbl->lock); + + mh->modify_hdr = mlx5_modify_header_alloc(mdev, namespace, + mh->key.num_actions, + mh->key.actions); + if (IS_ERR(mh->modify_hdr)) { + err = PTR_ERR(mh->modify_hdr); + mh->compl_result = err; + goto alloc_header_err; + } + mh->compl_result = 1; + complete_all(&mh->res_ready); + +attach_header: + return mh; + +alloc_header_err: + complete_all(&mh->res_ready); +attach_header_err: + mlx5e_mod_hdr_detach(mdev, tbl, mh); + return ERR_PTR(err); +} + +void mlx5e_mod_hdr_detach(struct mlx5_core_dev *mdev, + struct mod_hdr_tbl *tbl, + struct mlx5e_mod_hdr_handle *mh) +{ + if (!refcount_dec_and_mutex_lock(&mh->refcnt, &tbl->lock)) + return; + hash_del(&mh->mod_hdr_hlist); + mutex_unlock(&tbl->lock); + + if (mh->compl_result > 0) + mlx5_modify_header_dealloc(mdev, mh->modify_hdr); + + kfree(mh); +} + +struct mlx5_modify_hdr *mlx5e_mod_hdr_get(struct mlx5e_mod_hdr_handle *mh) +{ + return mh->modify_hdr; +} + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.h b/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.h new file mode 100644 index 000000000000..33b23d8f9182 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mod_hdr.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies */ + +#ifndef __MLX5E_EN_MOD_HDR_H__ +#define __MLX5E_EN_MOD_HDR_H__ + +#include <linux/hashtable.h> +#include <linux/mlx5/fs.h> + +struct mlx5e_mod_hdr_handle; + +struct mlx5e_tc_mod_hdr_acts { + int num_actions; + int max_actions; + void *actions; +}; + +struct mlx5e_mod_hdr_handle * +mlx5e_mod_hdr_attach(struct mlx5_core_dev *mdev, + struct mod_hdr_tbl *tbl, + enum mlx5_flow_namespace_type namespace, + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts); +void mlx5e_mod_hdr_detach(struct mlx5_core_dev *mdev, + struct mod_hdr_tbl *tbl, + struct mlx5e_mod_hdr_handle *mh); +struct mlx5_modify_hdr *mlx5e_mod_hdr_get(struct mlx5e_mod_hdr_handle *mh); + +void mlx5e_mod_hdr_tbl_init(struct mod_hdr_tbl *tbl); +void mlx5e_mod_hdr_tbl_destroy(struct mod_hdr_tbl *tbl); + +#endif /* __MLX5E_EN_MOD_HDR_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 2a8950b3056f..5de1cb9f5330 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -76,13 +76,31 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { [MLX5E_100GAUI_2_100GBASE_CR2_KR2] = 100000, [MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000, [MLX5E_400GAUI_8] = 400000, + [MLX5E_100GAUI_1_100GBASE_CR_KR] = 100000, + [MLX5E_200GAUI_2_200GBASE_CR2_KR2] = 200000, + [MLX5E_400GAUI_4_400GBASE_CR4_KR4] = 400000, }; +bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev) +{ + struct mlx5e_port_eth_proto eproto; + int err; + + if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet)) + return true; + + err = mlx5_port_query_eth_proto(mdev, 1, true, &eproto); + if (err) + return false; + + return !!eproto.cap; +} + static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev, const u32 **arr, u32 *size, bool force_legacy) { - bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + bool ext = force_legacy ? false : mlx5e_ptys_ext_supported(mdev); *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) : ARRAY_SIZE(mlx5e_link_speed); @@ -177,7 +195,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) bool ext; int err; - ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + ext = mlx5e_ptys_ext_supported(mdev); err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) goto out; @@ -205,7 +223,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) int err; int i; - ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + ext = mlx5e_ptys_ext_supported(mdev); err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index a2ddd446dd59..7a7defe60792 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -54,7 +54,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, bool force_legacy); - +bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index ae99fac08b53..673f1c82d381 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -34,6 +34,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, struct mlx5e_port_buffer *port_buffer) { + u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; struct mlx5_core_dev *mdev = priv->mdev; int sz = MLX5_ST_SZ_BYTES(pbmc_reg); u32 total_used = 0; @@ -57,11 +58,11 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, port_buffer->buffer[i].epsb = MLX5_GET(bufferx_reg, buffer, epsb); port_buffer->buffer[i].size = - MLX5_GET(bufferx_reg, buffer, size) << MLX5E_BUFFER_CELL_SHIFT; + MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz; port_buffer->buffer[i].xon = - MLX5_GET(bufferx_reg, buffer, xon_threshold) << MLX5E_BUFFER_CELL_SHIFT; + MLX5_GET(bufferx_reg, buffer, xon_threshold) * port_buff_cell_sz; port_buffer->buffer[i].xoff = - MLX5_GET(bufferx_reg, buffer, xoff_threshold) << MLX5E_BUFFER_CELL_SHIFT; + MLX5_GET(bufferx_reg, buffer, xoff_threshold) * port_buff_cell_sz; total_used += port_buffer->buffer[i].size; mlx5e_dbg(HW, priv, "buffer %d: size=%d, xon=%d, xoff=%d, epsb=%d, lossy=%d\n", i, @@ -73,7 +74,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, } port_buffer->port_buffer_size = - MLX5_GET(pbmc_reg, out, port_buffer_size) << MLX5E_BUFFER_CELL_SHIFT; + MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz; port_buffer->spare_buffer_size = port_buffer->port_buffer_size - total_used; @@ -88,9 +89,9 @@ out: static int port_set_buffer(struct mlx5e_priv *priv, struct mlx5e_port_buffer *port_buffer) { + u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; struct mlx5_core_dev *mdev = priv->mdev; int sz = MLX5_ST_SZ_BYTES(pbmc_reg); - void *buffer; void *in; int err; int i; @@ -104,16 +105,18 @@ static int port_set_buffer(struct mlx5e_priv *priv, goto out; for (i = 0; i < MLX5E_MAX_BUFFER; i++) { - buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); - - MLX5_SET(bufferx_reg, buffer, size, - port_buffer->buffer[i].size >> MLX5E_BUFFER_CELL_SHIFT); - MLX5_SET(bufferx_reg, buffer, lossy, - port_buffer->buffer[i].lossy); - MLX5_SET(bufferx_reg, buffer, xoff_threshold, - port_buffer->buffer[i].xoff >> MLX5E_BUFFER_CELL_SHIFT); - MLX5_SET(bufferx_reg, buffer, xon_threshold, - port_buffer->buffer[i].xon >> MLX5E_BUFFER_CELL_SHIFT); + void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); + u64 size = port_buffer->buffer[i].size; + u64 xoff = port_buffer->buffer[i].xoff; + u64 xon = port_buffer->buffer[i].xon; + + do_div(size, port_buff_cell_sz); + do_div(xoff, port_buff_cell_sz); + do_div(xon, port_buff_cell_sz); + MLX5_SET(bufferx_reg, buffer, size, size); + MLX5_SET(bufferx_reg, buffer, lossy, port_buffer->buffer[i].lossy); + MLX5_SET(bufferx_reg, buffer, xoff_threshold, xoff); + MLX5_SET(bufferx_reg, buffer, xon_threshold, xon); } err = mlx5e_port_set_pbmc(mdev, in); @@ -143,7 +146,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) } static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, - u32 xoff, unsigned int max_mtu) + u32 xoff, unsigned int max_mtu, u16 port_buff_cell_sz) { int i; @@ -155,7 +158,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, } if (port_buffer->buffer[i].size < - (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) { + (xoff + max_mtu + port_buff_cell_sz)) { pr_err("buffer_size[%d]=%d is not enough for lossless buffer\n", i, port_buffer->buffer[i].size); return -ENOMEM; @@ -175,6 +178,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * @pfc_en: <input> current pfc configuration * @buffer: <input> current prio to buffer mapping * @xoff: <input> xoff value + * @port_buff_cell_sz: <input> port buffer cell_size * @port_buffer: <output> port receive buffer configuration * @change: <output> * @@ -189,7 +193,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * sets change to true if buffer configuration was modified. */ static int update_buffer_lossy(unsigned int max_mtu, - u8 pfc_en, u8 *buffer, u32 xoff, + u8 pfc_en, u8 *buffer, u32 xoff, u16 port_buff_cell_sz, struct mlx5e_port_buffer *port_buffer, bool *change) { @@ -225,7 +229,7 @@ static int update_buffer_lossy(unsigned int max_mtu, } if (changed) { - err = update_xoff_threshold(port_buffer, xoff, max_mtu); + err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; @@ -262,6 +266,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, u32 *buffer_size, u8 *prio2buffer) { + u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; struct mlx5e_port_buffer port_buffer; u32 xoff = calculate_xoff(priv, mtu); bool update_prio2buffer = false; @@ -282,7 +287,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_CABLE_LEN) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, max_mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; } @@ -292,7 +297,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err; - err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, + err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, port_buff_cell_sz, &port_buffer, &update_buffer); if (err) return err; @@ -304,7 +309,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err; - err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, + err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, port_buff_cell_sz, xoff, &port_buffer, &update_buffer); if (err) return err; @@ -329,7 +334,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, return -EINVAL; update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, max_mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; } @@ -337,7 +342,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, /* Need to update buffer configuration if xoff value is changed */ if (!update_buffer && xoff != priv->dcbx.xoff) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, max_mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h index 34f55b81a0de..80af7a5ac604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h @@ -36,7 +36,6 @@ #include "port.h" #define MLX5E_MAX_BUFFER 8 -#define MLX5E_BUFFER_CELL_SHIFT 7 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */ #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index a0913836c973..906292035088 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -6,7 +6,6 @@ #include <linux/rculist.h> #include <linux/rtnetlink.h> #include <linux/workqueue.h> -#include <linux/rwlock.h> #include <linux/spinlock.h> #include <linux/notifier.h> #include <net/netevent.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index eefeb1cdc2ee..f8af109d34cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -404,7 +404,7 @@ static void mlx5e_rep_indr_block_unbind(void *cb_priv) static LIST_HEAD(mlx5e_block_cb_list); static int -mlx5e_rep_indr_setup_block(struct net_device *netdev, +mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, struct mlx5e_rep_priv *rpriv, struct flow_block_offload *f, flow_setup_cb_t *setup_cb, @@ -442,7 +442,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, block_cb = flow_indr_block_cb_alloc(setup_cb, indr_priv, indr_priv, mlx5e_rep_indr_block_unbind, - f, netdev, data, rpriv, + f, netdev, sch, data, rpriv, cleanup); if (IS_ERR(block_cb)) { list_del(&indr_priv->list); @@ -472,18 +472,18 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, } static -int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv, +int mlx5e_rep_indr_setup_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) { switch (type) { case TC_SETUP_BLOCK: - return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data, + return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data, mlx5e_rep_indr_setup_tc_cb, data, cleanup); case TC_SETUP_FT: - return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data, + return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data, mlx5e_rep_indr_setup_ft_cb, data, cleanup); default: @@ -594,7 +594,7 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, struct mlx5e_tc_update_priv *tc_priv) { #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - u32 chain = 0, reg_c0, reg_c1, tunnel_id, tuple_id; + u32 chain = 0, reg_c0, reg_c1, tunnel_id, zone_restore_id; struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; struct tc_skb_ext *tc_skb_ext; @@ -631,11 +631,12 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe, tc_skb_ext->chain = chain; - tuple_id = reg_c1 & TUPLE_ID_MAX; + zone_restore_id = reg_c1 & ZONE_RESTORE_MAX; uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &uplink_rpriv->uplink_priv; - if (!mlx5e_tc_ct_restore_flow(uplink_priv, skb, tuple_id)) + if (!mlx5e_tc_ct_restore_flow(uplink_priv, skb, + zone_restore_id)) return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 32ed1067e6dc..9913647a1faf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -611,13 +611,10 @@ static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = { void mlx5e_reporter_rx_create(struct mlx5e_priv *priv) { - struct devlink *devlink = priv_to_devlink(priv->mdev); struct devlink_health_reporter *reporter; - reporter = devlink_health_reporter_create(devlink, - &mlx5_rx_reporter_ops, - MLX5E_REPORTER_RX_GRACEFUL_PERIOD, - priv); + reporter = devlink_port_health_reporter_create(&priv->dl_port, &mlx5_rx_reporter_ops, + MLX5E_REPORTER_RX_GRACEFUL_PERIOD, priv); if (IS_ERR(reporter)) { netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n", PTR_ERR(reporter)); @@ -631,5 +628,5 @@ void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv) if (!priv->rx_reporter) return; - devlink_health_reporter_destroy(priv->rx_reporter); + devlink_port_health_reporter_destroy(priv->rx_reporter); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 826584380216..8be6eaa3eeb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -440,14 +440,9 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { void mlx5e_reporter_tx_create(struct mlx5e_priv *priv) { struct devlink_health_reporter *reporter; - struct mlx5_core_dev *mdev = priv->mdev; - struct devlink *devlink; - - devlink = priv_to_devlink(mdev); - reporter = - devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, - MLX5_REPORTER_TX_GRACEFUL_PERIOD, - priv); + + reporter = devlink_port_health_reporter_create(&priv->dl_port, &mlx5_tx_reporter_ops, + MLX5_REPORTER_TX_GRACEFUL_PERIOD, priv); if (IS_ERR(reporter)) { netdev_warn(priv->netdev, "Failed to create tx reporter, err = %ld\n", @@ -462,5 +457,5 @@ void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv) if (!priv->tx_reporter) return; - devlink_health_reporter_destroy(priv->tx_reporter); + devlink_port_health_reporter_destroy(priv->tx_reporter); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c7107da03212..4c65677feaab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -16,6 +16,8 @@ #include "esw/chains.h" #include "en/tc_ct.h" +#include "en/mod_hdr.h" +#include "en/mapping.h" #include "en.h" #include "en_tc.h" #include "en_rep.h" @@ -39,10 +41,13 @@ struct mlx5_tc_ct_priv { struct idr fte_ids; struct xarray tuple_ids; struct rhashtable zone_ht; + struct rhashtable ct_tuples_ht; + struct rhashtable ct_tuples_nat_ht; struct mlx5_flow_table *ct; struct mlx5_flow_table *ct_nat; struct mlx5_flow_table *post_ct; struct mutex control_lock; /* guards parallel adds/dels */ + struct mapping_ctx *zone_mapping; }; struct mlx5_ct_flow { @@ -57,8 +62,8 @@ struct mlx5_ct_flow { struct mlx5_ct_zone_rule { struct mlx5_flow_handle *rule; + struct mlx5e_mod_hdr_handle *mh; struct mlx5_esw_flow_attr attr; - int tupleid; bool nat; }; @@ -74,6 +79,7 @@ struct mlx5_tc_ct_pre { struct mlx5_ct_ft { struct rhash_head node; u16 zone; + u32 zone_restore_id; refcount_t refcount; struct nf_flowtable *nf_ft; struct mlx5_tc_ct_priv *ct_priv; @@ -82,12 +88,37 @@ struct mlx5_ct_ft { struct mlx5_tc_ct_pre pre_ct_nat; }; -struct mlx5_ct_entry { +struct mlx5_ct_tuple { + u16 addr_type; + __be16 n_proto; + u8 ip_proto; + struct { + union { + __be32 src_v4; + struct in6_addr src_v6; + }; + union { + __be32 dst_v4; + struct in6_addr dst_v6; + }; + } ip; + struct { + __be16 src; + __be16 dst; + } port; + u16 zone; +}; + +struct mlx5_ct_entry { struct rhash_head node; + struct rhash_head tuple_node; + struct rhash_head tuple_nat_node; struct mlx5_fc *counter; unsigned long cookie; unsigned long restore_cookie; + struct mlx5_ct_tuple tuple; + struct mlx5_ct_tuple tuple_nat; struct mlx5_ct_zone_rule zone_rules[2]; }; @@ -106,6 +137,22 @@ static const struct rhashtable_params zone_params = { .automatic_shrinking = true, }; +static const struct rhashtable_params tuples_ht_params = { + .head_offset = offsetof(struct mlx5_ct_entry, tuple_node), + .key_offset = offsetof(struct mlx5_ct_entry, tuple), + .key_len = sizeof(((struct mlx5_ct_entry *)0)->tuple), + .automatic_shrinking = true, + .min_size = 16 * 1024, +}; + +static const struct rhashtable_params tuples_nat_ht_params = { + .head_offset = offsetof(struct mlx5_ct_entry, tuple_nat_node), + .key_offset = offsetof(struct mlx5_ct_entry, tuple_nat), + .key_len = sizeof(((struct mlx5_ct_entry *)0)->tuple_nat), + .automatic_shrinking = true, + .min_size = 16 * 1024, +}; + static struct mlx5_tc_ct_priv * mlx5_tc_ct_get_ct_priv(struct mlx5e_priv *priv) { @@ -119,6 +166,115 @@ mlx5_tc_ct_get_ct_priv(struct mlx5e_priv *priv) } static int +mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule) +{ + struct flow_match_control control; + struct flow_match_basic basic; + + flow_rule_match_basic(rule, &basic); + flow_rule_match_control(rule, &control); + + tuple->n_proto = basic.key->n_proto; + tuple->ip_proto = basic.key->ip_proto; + tuple->addr_type = control.key->addr_type; + + if (tuple->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + tuple->ip.src_v4 = match.key->src; + tuple->ip.dst_v4 = match.key->dst; + } else if (tuple->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); + tuple->ip.src_v6 = match.key->src; + tuple->ip.dst_v6 = match.key->dst; + } else { + return -EOPNOTSUPP; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + switch (tuple->ip_proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + tuple->port.src = match.key->src; + tuple->port.dst = match.key->dst; + break; + default: + return -EOPNOTSUPP; + } + } else { + return -EOPNOTSUPP; + } + + return 0; +} + +static int +mlx5_tc_ct_rule_to_tuple_nat(struct mlx5_ct_tuple *tuple, + struct flow_rule *rule) +{ + struct flow_action *flow_action = &rule->action; + struct flow_action_entry *act; + u32 offset, val, ip6_offset; + int i; + + flow_action_for_each(i, act, flow_action) { + if (act->id != FLOW_ACTION_MANGLE) + continue; + + offset = act->mangle.offset; + val = act->mangle.val; + switch (act->mangle.htype) { + case FLOW_ACT_MANGLE_HDR_TYPE_IP4: + if (offset == offsetof(struct iphdr, saddr)) + tuple->ip.src_v4 = cpu_to_be32(val); + else if (offset == offsetof(struct iphdr, daddr)) + tuple->ip.dst_v4 = cpu_to_be32(val); + else + return -EOPNOTSUPP; + break; + + case FLOW_ACT_MANGLE_HDR_TYPE_IP6: + ip6_offset = (offset - offsetof(struct ipv6hdr, saddr)); + ip6_offset /= 4; + if (ip6_offset < 8) + tuple->ip.src_v6.s6_addr32[ip6_offset] = cpu_to_be32(val); + else + return -EOPNOTSUPP; + break; + + case FLOW_ACT_MANGLE_HDR_TYPE_TCP: + if (offset == offsetof(struct tcphdr, source)) + tuple->port.src = cpu_to_be16(val); + else if (offset == offsetof(struct tcphdr, dest)) + tuple->port.dst = cpu_to_be16(val); + else + return -EOPNOTSUPP; + break; + + case FLOW_ACT_MANGLE_HDR_TYPE_UDP: + if (offset == offsetof(struct udphdr, source)) + tuple->port.src = cpu_to_be16(val); + else if (offset == offsetof(struct udphdr, dest)) + tuple->port.dst = cpu_to_be16(val); + else + return -EOPNOTSUPP; + break; + + default: + return -EOPNOTSUPP; + } + } + + return 0; +} + +static int mlx5_tc_ct_set_tuple_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct flow_rule *rule) { @@ -243,11 +399,11 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_esw_flow_attr *attr = &zone_rule->attr; struct mlx5_eswitch *esw = ct_priv->esw; - ct_dbg("Deleting ct entry rule in zone %d", entry->zone); + ct_dbg("Deleting ct entry rule in zone %d", entry->tuple.zone); mlx5_eswitch_del_offloaded_rule(esw, zone_rule->rule, attr); - mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr); - xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid); + mlx5e_mod_hdr_detach(ct_priv->esw->dev, + &esw->offloads.mod_hdr, zone_rule->mh); } static void @@ -281,7 +437,7 @@ mlx5_tc_ct_entry_set_registers(struct mlx5_tc_ct_priv *ct_priv, u8 ct_state, u32 mark, u32 label, - u32 tupleid) + u8 zone_restore_id) { struct mlx5_eswitch *esw = ct_priv->esw; int err; @@ -302,7 +458,7 @@ mlx5_tc_ct_entry_set_registers(struct mlx5_tc_ct_priv *ct_priv, return err; err = mlx5e_tc_match_to_reg_set(esw->dev, mod_acts, - TUPLEID_TO_REG, tupleid); + ZONE_RESTORE_TO_REG, zone_restore_id); if (err) return err; @@ -429,12 +585,10 @@ static int mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_esw_flow_attr *attr, struct flow_rule *flow_rule, - u32 tupleid, - bool nat) + struct mlx5e_mod_hdr_handle **mh, + u8 zone_restore_id, bool nat) { struct mlx5e_tc_mod_hdr_acts mod_acts = {}; - struct mlx5_eswitch *esw = ct_priv->esw; - struct mlx5_modify_hdr *mod_hdr; struct flow_action_entry *meta; u16 ct_state = 0; int err; @@ -464,18 +618,19 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, ct_state, meta->ct_metadata.mark, meta->ct_metadata.labels[0], - tupleid); + zone_restore_id); if (err) goto err_mapping; - mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, - mod_acts.num_actions, - mod_acts.actions); - if (IS_ERR(mod_hdr)) { - err = PTR_ERR(mod_hdr); + *mh = mlx5e_mod_hdr_attach(ct_priv->esw->dev, + &ct_priv->esw->offloads.mod_hdr, + MLX5_FLOW_NAMESPACE_FDB, + &mod_acts); + if (IS_ERR(*mh)) { + err = PTR_ERR(*mh); goto err_mapping; } - attr->modify_hdr = mod_hdr; + attr->modify_hdr = mlx5e_mod_hdr_get(*mh); dealloc_mod_hdr_actions(&mod_acts); return 0; @@ -489,13 +644,12 @@ static int mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, struct flow_rule *flow_rule, struct mlx5_ct_entry *entry, - bool nat) + bool nat, u8 zone_restore_id) { struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat]; struct mlx5_esw_flow_attr *attr = &zone_rule->attr; struct mlx5_eswitch *esw = ct_priv->esw; struct mlx5_flow_spec *spec = NULL; - u32 tupleid; int err; zone_rule->nat = nat; @@ -504,18 +658,9 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, if (!spec) return -ENOMEM; - /* Get tuple unique id */ - err = xa_alloc(&ct_priv->tuple_ids, &tupleid, zone_rule, - XA_LIMIT(1, TUPLE_ID_MAX), GFP_KERNEL); - if (err) { - netdev_warn(ct_priv->netdev, - "Failed to allocate tuple id, err: %d\n", err); - goto err_xa_alloc; - } - zone_rule->tupleid = tupleid; - err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule, - tupleid, nat); + &zone_rule->mh, + zone_restore_id, nat); if (err) { ct_dbg("Failed to create ct entry mod hdr"); goto err_mod_hdr; @@ -533,7 +678,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule); mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG, - entry->zone & MLX5_CT_ZONE_MASK, + entry->tuple.zone & MLX5_CT_ZONE_MASK, MLX5_CT_ZONE_MASK); zone_rule->rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); @@ -544,15 +689,14 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, } kfree(spec); - ct_dbg("Offloaded ct entry rule in zone %d", entry->zone); + ct_dbg("Offloaded ct entry rule in zone %d", entry->tuple.zone); return 0; err_rule: - mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr); + mlx5e_mod_hdr_detach(ct_priv->esw->dev, + &esw->offloads.mod_hdr, zone_rule->mh); err_mod_hdr: - xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid); -err_xa_alloc: kfree(spec); return err; } @@ -560,7 +704,8 @@ err_xa_alloc: static int mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv, struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry) + struct mlx5_ct_entry *entry, + u8 zone_restore_id) { struct mlx5_eswitch *esw = ct_priv->esw; int err; @@ -572,11 +717,13 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv, return err; } - err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, false); + err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, false, + zone_restore_id); if (err) goto err_orig; - err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, true); + err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, true, + zone_restore_id); if (err) goto err_nat; @@ -613,11 +760,35 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, if (!entry) return -ENOMEM; - entry->zone = ft->zone; + entry->tuple.zone = ft->zone; entry->cookie = flow->cookie; entry->restore_cookie = meta_action->ct_metadata.cookie; - err = mlx5_tc_ct_entry_add_rules(ct_priv, flow_rule, entry); + err = mlx5_tc_ct_rule_to_tuple(&entry->tuple, flow_rule); + if (err) + goto err_set; + + memcpy(&entry->tuple_nat, &entry->tuple, sizeof(entry->tuple)); + err = mlx5_tc_ct_rule_to_tuple_nat(&entry->tuple_nat, flow_rule); + if (err) + goto err_set; + + err = rhashtable_insert_fast(&ct_priv->ct_tuples_ht, + &entry->tuple_node, + tuples_ht_params); + if (err) + goto err_tuple; + + if (memcmp(&entry->tuple, &entry->tuple_nat, sizeof(entry->tuple))) { + err = rhashtable_insert_fast(&ct_priv->ct_tuples_nat_ht, + &entry->tuple_nat_node, + tuples_nat_ht_params); + if (err) + goto err_tuple_nat; + } + + err = mlx5_tc_ct_entry_add_rules(ct_priv, flow_rule, entry, + ft->zone_restore_id); if (err) goto err_rules; @@ -631,12 +802,34 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, err_insert: mlx5_tc_ct_entry_del_rules(ct_priv, entry); err_rules: + rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht, + &entry->tuple_nat_node, tuples_nat_ht_params); +err_tuple_nat: + if (entry->tuple_node.next) + rhashtable_remove_fast(&ct_priv->ct_tuples_ht, + &entry->tuple_node, + tuples_ht_params); +err_tuple: +err_set: kfree(entry); netdev_warn(ct_priv->netdev, "Failed to offload ct entry, err: %d\n", err); return err; } +static void +mlx5_tc_ct_del_ft_entry(struct mlx5_tc_ct_priv *ct_priv, + struct mlx5_ct_entry *entry) +{ + mlx5_tc_ct_entry_del_rules(ct_priv, entry); + if (entry->tuple_node.next) + rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht, + &entry->tuple_nat_node, + tuples_nat_ht_params); + rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node, + tuples_ht_params); +} + static int mlx5_tc_ct_block_flow_offload_del(struct mlx5_ct_ft *ft, struct flow_cls_offload *flow) @@ -649,7 +842,7 @@ mlx5_tc_ct_block_flow_offload_del(struct mlx5_ct_ft *ft, if (!entry) return -ENOENT; - mlx5_tc_ct_entry_del_rules(ft->ct_priv, entry); + mlx5_tc_ct_del_ft_entry(ft->ct_priv, entry); WARN_ON(rhashtable_remove_fast(&ft->ct_entries_ht, &entry->node, cts_ht_params)); @@ -702,6 +895,66 @@ mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data, return -EOPNOTSUPP; } +static bool +mlx5_tc_ct_skb_to_tuple(struct sk_buff *skb, struct mlx5_ct_tuple *tuple, + u16 zone) +{ + struct flow_keys flow_keys; + + skb_reset_network_header(skb); + skb_flow_dissect_flow_keys(skb, &flow_keys, 0); + + tuple->zone = zone; + + if (flow_keys.basic.ip_proto != IPPROTO_TCP && + flow_keys.basic.ip_proto != IPPROTO_UDP) + return false; + + tuple->port.src = flow_keys.ports.src; + tuple->port.dst = flow_keys.ports.dst; + tuple->n_proto = flow_keys.basic.n_proto; + tuple->ip_proto = flow_keys.basic.ip_proto; + + switch (flow_keys.basic.n_proto) { + case htons(ETH_P_IP): + tuple->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + tuple->ip.src_v4 = flow_keys.addrs.v4addrs.src; + tuple->ip.dst_v4 = flow_keys.addrs.v4addrs.dst; + break; + + case htons(ETH_P_IPV6): + tuple->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + tuple->ip.src_v6 = flow_keys.addrs.v6addrs.src; + tuple->ip.dst_v6 = flow_keys.addrs.v6addrs.dst; + break; + default: + goto out; + } + + return true; + +out: + return false; +} + +int +mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec) +{ + u32 ctstate = 0, ctstate_mask = 0; + + mlx5e_tc_match_to_reg_get_match(spec, CTSTATE_TO_REG, + &ctstate, &ctstate_mask); + if (ctstate_mask) + return -EOPNOTSUPP; + + ctstate_mask |= MLX5_CT_STATE_TRK_BIT; + mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG, + ctstate, ctstate_mask); + + return 0; +} + int mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, @@ -1054,6 +1307,10 @@ mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone, if (!ft) return ERR_PTR(-ENOMEM); + err = mapping_add(ct_priv->zone_mapping, &zone, &ft->zone_restore_id); + if (err) + goto err_mapping; + ft->zone = zone; ft->nf_ft = nf_ft; ft->ct_priv = ct_priv; @@ -1086,6 +1343,8 @@ err_insert: err_init: mlx5_tc_ct_free_pre_ct_tables(ft); err_alloc_pre_ct: + mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id); +err_mapping: kfree(ft); return ERR_PTR(err); } @@ -1096,7 +1355,8 @@ mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg) struct mlx5_tc_ct_priv *ct_priv = arg; struct mlx5_ct_entry *entry = ptr; - mlx5_tc_ct_entry_del_rules(ct_priv, entry); + mlx5_tc_ct_del_ft_entry(ct_priv, entry); + kfree(entry); } static void @@ -1112,6 +1372,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) mlx5_tc_ct_flush_ft_entry, ct_priv); mlx5_tc_ct_free_pre_ct_tables(ft); + mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id); kfree(ft); } @@ -1139,6 +1400,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) * | set mark * | set label * | set established + * | set zone_restore * | do nat (if needed) * v * +--------------+ @@ -1146,12 +1408,11 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) * + fte_id match +------------------------> * +--------------+ */ -static int +static struct mlx5_flow_handle * __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *orig_spec, - struct mlx5_esw_flow_attr *attr, - struct mlx5_flow_handle **flow_rule) + struct mlx5_esw_flow_attr *attr) { struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); bool nat = attr->ct_attr.ct_action & TCA_CT_ACT_NAT; @@ -1171,7 +1432,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv, if (!post_ct_spec || !ct_flow) { kfree(post_ct_spec); kfree(ct_flow); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } /* Register for CT established events */ @@ -1292,11 +1553,10 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv, } attr->ct_attr.ct_flow = ct_flow; - *flow_rule = ct_flow->post_ct_rule; dealloc_mod_hdr_actions(&pre_mod_acts); kfree(post_ct_spec); - return 0; + return rule; err_insert_orig: mlx5_eswitch_del_offloaded_rule(ct_priv->esw, ct_flow->post_ct_rule, @@ -1314,16 +1574,14 @@ err_ft: kfree(post_ct_spec); kfree(ct_flow); netdev_warn(priv->netdev, "Failed to offload ct flow, err %d\n", err); - return err; + return ERR_PTR(err); } -static int +static struct mlx5_flow_handle * __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *orig_spec, struct mlx5_esw_flow_attr *attr, - struct mlx5e_tc_mod_hdr_acts *mod_acts, - struct mlx5_flow_handle **flow_rule) + struct mlx5e_tc_mod_hdr_acts *mod_acts) { struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); struct mlx5_eswitch *esw = ct_priv->esw; @@ -1335,7 +1593,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv, ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL); if (!ct_flow) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* Base esw attributes on original rule attribute */ pre_ct_attr = &ct_flow->pre_ct_attr; @@ -1370,16 +1628,14 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv, attr->ct_attr.ct_flow = ct_flow; ct_flow->pre_ct_rule = rule; - *flow_rule = rule; - - return 0; + return rule; err_insert: mlx5_modify_header_dealloc(priv->mdev, mod_hdr); err_set_registers: netdev_warn(priv->netdev, "Failed to offload ct clear flow, err %d\n", err); - return err; + return ERR_PTR(err); } struct mlx5_flow_handle * @@ -1391,22 +1647,18 @@ mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv, { bool clear_action = attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); - struct mlx5_flow_handle *rule = ERR_PTR(-EINVAL); - int err; + struct mlx5_flow_handle *rule; if (!ct_priv) return ERR_PTR(-EOPNOTSUPP); mutex_lock(&ct_priv->control_lock); + if (clear_action) - err = __mlx5_tc_ct_flow_offload_clear(priv, flow, spec, attr, - mod_hdr_acts, &rule); + rule = __mlx5_tc_ct_flow_offload_clear(priv, spec, attr, mod_hdr_acts); else - err = __mlx5_tc_ct_flow_offload(priv, flow, spec, attr, - &rule); + rule = __mlx5_tc_ct_flow_offload(priv, flow, spec, attr); mutex_unlock(&ct_priv->control_lock); - if (err) - return ERR_PTR(err); return rule; } @@ -1534,6 +1786,12 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv) goto err_alloc; } + ct_priv->zone_mapping = mapping_create(sizeof(u16), 0, true); + if (IS_ERR(ct_priv->zone_mapping)) { + err = PTR_ERR(ct_priv->zone_mapping); + goto err_mapping; + } + ct_priv->esw = esw; ct_priv->netdev = rpriv->netdev; ct_priv->ct = mlx5_esw_chains_create_global_table(esw); @@ -1560,9 +1818,10 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv) } idr_init(&ct_priv->fte_ids); - xa_init_flags(&ct_priv->tuple_ids, XA_FLAGS_ALLOC1); mutex_init(&ct_priv->control_lock); rhashtable_init(&ct_priv->zone_ht, &zone_params); + rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params); + rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params); /* Done, set ct_priv to know it initializted */ uplink_priv->ct_priv = ct_priv; @@ -1574,6 +1833,8 @@ err_post_ct_tbl: err_ct_nat_tbl: mlx5_esw_chains_destroy_global_table(esw, ct_priv->ct); err_ct_tbl: + mapping_destroy(ct_priv->zone_mapping); +err_mapping: kfree(ct_priv); err_alloc: err_support: @@ -1592,10 +1853,12 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->post_ct); mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->ct_nat); mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->ct); + mapping_destroy(ct_priv->zone_mapping); + rhashtable_destroy(&ct_priv->ct_tuples_ht); + rhashtable_destroy(&ct_priv->ct_tuples_nat_ht); rhashtable_destroy(&ct_priv->zone_ht); mutex_destroy(&ct_priv->control_lock); - xa_destroy(&ct_priv->tuple_ids); idr_destroy(&ct_priv->fte_ids); kfree(ct_priv); @@ -1604,22 +1867,30 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) bool mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv, - struct sk_buff *skb, u32 tupleid) + struct sk_buff *skb, u8 zone_restore_id) { struct mlx5_tc_ct_priv *ct_priv = uplink_priv->ct_priv; - struct mlx5_ct_zone_rule *zone_rule; + struct mlx5_ct_tuple tuple = {}; struct mlx5_ct_entry *entry; + u16 zone; - if (!ct_priv || !tupleid) + if (!ct_priv || !zone_restore_id) return true; - zone_rule = xa_load(&ct_priv->tuple_ids, tupleid); - if (!zone_rule) + if (mapping_find(ct_priv->zone_mapping, zone_restore_id, &zone)) return false; - entry = container_of(zone_rule, struct mlx5_ct_entry, - zone_rules[zone_rule->nat]); - tcf_ct_flow_table_restore_skb(skb, entry->restore_cookie); + if (!mlx5_tc_ct_skb_to_tuple(skb, &tuple, zone)) + return false; + entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, &tuple, + tuples_ht_params); + if (!entry) + entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_nat_ht, + &tuple, tuples_nat_ht_params); + if (!entry) + return false; + + tcf_ct_flow_table_restore_skb(skb, entry->restore_cookie); return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 626f6c04882e..5e10a72f5f24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -67,16 +67,17 @@ struct mlx5_ct_attr { misc_parameters_2.metadata_reg_c_5),\ } -#define tupleid_to_reg_ct {\ +#define zone_restore_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1,\ .moffset = 0,\ - .mlen = 3,\ + .mlen = 1,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ - misc_parameters_2.metadata_reg_c_1),\ + misc_parameters_2.metadata_reg_c_1) + 3,\ } -#define TUPLE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[TUPLEID_TO_REG].mlen * 8) -#define TUPLE_ID_MAX GENMASK(TUPLE_ID_BITS - 1, 0) +#define REG_MAPPING_MLEN(reg) (mlx5e_tc_attr_to_reg_mappings[reg].mlen) +#define ZONE_RESTORE_BITS (REG_MAPPING_MLEN(ZONE_RESTORE_TO_REG) * 8) +#define ZONE_RESTORE_MAX GENMASK(ZONE_RESTORE_BITS - 1, 0) #if IS_ENABLED(CONFIG_MLX5_TC_CT) @@ -91,6 +92,9 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, struct flow_cls_offload *f, struct netlink_ext_ack *extack); int +mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec); +int mlx5_tc_ct_parse_action(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr, const struct flow_action_entry *act, @@ -109,7 +113,7 @@ mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv, bool mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv, - struct sk_buff *skb, u32 tupleid); + struct sk_buff *skb, u8 zone_restore_id); #else /* CONFIG_MLX5_TC_CT */ @@ -141,6 +145,13 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, } static inline int +mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec) +{ + return 0; +} + +static inline int mlx5_tc_ct_parse_action(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr, const struct flow_action_entry *act, @@ -170,10 +181,10 @@ mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv, static inline bool mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv, - struct sk_buff *skb, u32 tupleid) + struct sk_buff *skb, u8 zone_restore_id) { - if (!tupleid) - return true; + if (!zone_restore_id) + return true; return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index bc102d094bbd..d20243d6a032 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1217,6 +1217,24 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) return 0; } +#define MLX5E_BUFFER_CELL_SHIFT 7 + +static u16 mlx5e_query_port_buffers_cell_size(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u32 out[MLX5_ST_SZ_DW(sbcam_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(sbcam_reg)] = {}; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return (1 << MLX5E_BUFFER_CELL_SHIFT); + + if (mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), + MLX5_REG_SBCAM, 0, 0)) + return (1 << MLX5E_BUFFER_CELL_SHIFT); + + return MLX5_GET(sbcam_reg, out, cap_cell_size); +} + void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) { struct mlx5e_dcbx *dcbx = &priv->dcbx; @@ -1234,6 +1252,7 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) if (priv->dcbx.mode == MLX5E_DCBX_PARAM_VER_OPER_HOST) priv->dcbx.cap |= DCB_CAP_DCBX_HOST; + priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv); priv->dcbx.manual_buffer = false; priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index ec5658bbe3c5..af849bc83c30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -194,13 +194,31 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_1_100GBASE_CR_KR, ext, + ETHTOOL_LINK_MODE_100000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT, + ETHTOOL_LINK_MODE_100000baseDR_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_2_200GBASE_CR2_KR2, ext, + ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT, + ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT, + ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_4_400GBASE_CR4_KR4, ext, + ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT, + ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT, + ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT); } static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev, struct ptys2ethtool_config **arr, u32 *size) { - bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + bool ext = mlx5e_ptys_ext_supported(mdev); *arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table; *size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) : @@ -883,7 +901,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp, struct ethtool_link_ksettings *link_ksettings) { unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising; - bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + bool ext = mlx5e_ptys_ext_supported(mdev); ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext); } @@ -913,7 +931,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, __func__, err); goto err_query_regs; } - ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability); eth_proto_cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_capability); eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, @@ -1012,7 +1030,8 @@ static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes) unsigned long modes[2]; for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) { - if (*ptys2ext_ethtool_table[i].advertised == 0) + if (ptys2ext_ethtool_table[i].advertised[0] == 0 && + ptys2ext_ethtool_table[i].advertised[1] == 0) continue; memset(modes, 0, sizeof(modes)); bitmap_and(modes, ptys2ext_ethtool_table[i].advertised, @@ -1066,7 +1085,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, autoneg = link_ksettings->base.autoneg; speed = link_ksettings->base.speed; - ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + ext_supported = mlx5e_ptys_ext_supported(mdev); ext = ext_requested(autoneg, adver, ext_supported); if (!ext_supported && ext) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b04c8572adea..4e5d83f6334a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3138,9 +3138,6 @@ int mlx5e_open(struct net_device *netdev) mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); - if (mlx5_vxlan_allowed(priv->mdev->vxlan)) - udp_tunnel_get_rx_info(netdev); - return err; } @@ -5086,6 +5083,9 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, if (err) mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_build_nic_netdev(netdev); + err = mlx5e_devlink_port_register(priv); + if (err) + mlx5_core_err(mdev, "mlx5e_devlink_port_register failed, %d\n", err); mlx5e_health_create_reporters(priv); return 0; @@ -5094,6 +5094,7 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { mlx5e_health_destroy_reporters(priv); + mlx5e_devlink_port_unregister(priv); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); mlx5e_netdev_cleanup(priv->netdev, priv); @@ -5150,6 +5151,10 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) if (err) goto err_tc_nic_cleanup; +#ifdef CONFIG_MLX5_EN_ARFS + priv->netdev->rx_cpu_rmap = mlx5_eq_table_get_rmap(priv->mdev); +#endif + return 0; err_tc_nic_cleanup: @@ -5234,6 +5239,8 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) rtnl_lock(); if (netif_running(netdev)) mlx5e_open(netdev); + if (mlx5_vxlan_allowed(priv->mdev->vxlan)) + udp_tunnel_get_rx_info(netdev); netif_device_attach(netdev); rtnl_unlock(); } @@ -5248,6 +5255,8 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) rtnl_lock(); if (netif_running(priv->netdev)) mlx5e_close(priv->netdev); + if (mlx5_vxlan_allowed(priv->mdev->vxlan)) + udp_tunnel_drop_rx_info(priv->netdev); netif_device_detach(priv->netdev); rtnl_unlock(); @@ -5320,10 +5329,6 @@ int mlx5e_netdev_init(struct net_device *netdev, /* netdev init */ netif_carrier_off(netdev); -#ifdef CONFIG_MLX5_EN_ARFS - netdev->rx_cpu_rmap = mlx5_eq_table_get_rmap(mdev); -#endif - return 0; err_free_cpumask: @@ -5526,16 +5531,10 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) goto err_destroy_netdev; } - err = mlx5e_devlink_port_register(priv); - if (err) { - mlx5_core_err(mdev, "mlx5e_devlink_port_register failed, %d\n", err); - goto err_detach; - } - err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); - goto err_devlink_port_unregister; + goto err_detach; } mlx5e_devlink_port_type_eth_set(priv); @@ -5543,8 +5542,6 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) mlx5e_dcbnl_init_app(priv); return priv; -err_devlink_port_unregister: - mlx5e_devlink_port_unregister(priv); err_detach: mlx5e_detach(mdev, priv); err_destroy_netdev: @@ -5565,7 +5562,6 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) priv = vpriv; mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); - mlx5e_devlink_port_unregister(priv); mlx5e_detach(mdev, vpriv); mlx5e_destroy_netdev(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ed2430677b12..0a69f10ac30c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1185,6 +1185,7 @@ static int register_devlink_port(struct mlx5_core_dev *dev, { struct devlink *devlink = priv_to_devlink(dev); struct mlx5_eswitch_rep *rep = rpriv->rep; + struct devlink_port_attrs attrs = {}; struct netdev_phys_item_id ppid = {}; unsigned int dl_port_index = 0; u16 pfnum; @@ -1195,19 +1196,16 @@ static int register_devlink_port(struct mlx5_core_dev *dev, mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, rep->vport); pfnum = PCI_FUNC(dev->pdev->devfn); - + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = pfnum; + memcpy(attrs.switch_id.id, &ppid.id[0], ppid.id_len); + attrs.switch_id.id_len = ppid.id_len; if (rep->vport == MLX5_VPORT_UPLINK) - devlink_port_attrs_set(&rpriv->dl_port, - DEVLINK_PORT_FLAVOUR_PHYSICAL, - pfnum, false, 0, - &ppid.id[0], ppid.id_len); + devlink_port_attrs_set(&rpriv->dl_port, &attrs); else if (rep->vport == MLX5_VPORT_PF) - devlink_port_attrs_pci_pf_set(&rpriv->dl_port, - &ppid.id[0], ppid.id_len, - pfnum); + devlink_port_attrs_pci_pf_set(&rpriv->dl_port, pfnum); else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) devlink_port_attrs_pci_vf_set(&rpriv->dl_port, - &ppid.id[0], ppid.id_len, pfnum, rep->vport - 1); return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index bc9c0ac15f99..b366c46a5604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -63,6 +63,7 @@ #include "en/tc_tun.h" #include "en/mapping.h" #include "en/tc_ct.h" +#include "en/mod_hdr.h" #include "lib/devcom.h" #include "lib/geneve.h" #include "diag/en_tc_tracepoint.h" @@ -140,8 +141,7 @@ struct mlx5e_tc_flow { */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; - struct mlx5e_mod_hdr_entry *mh; /* attached mod header instance */ - struct list_head mod_hdr; /* flows sharing the same mod hdr ID */ + struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */ struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ struct list_head peer; /* flows with peer flow */ @@ -180,17 +180,17 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { }, [TUNNEL_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1, - .moffset = 3, - .mlen = 1, + .moffset = 1, + .mlen = 3, .soffset = MLX5_BYTE_OFF(fte_match_param, misc_parameters_2.metadata_reg_c_1), }, [ZONE_TO_REG] = zone_to_reg_ct, + [ZONE_RESTORE_TO_REG] = zone_restore_to_reg_ct, [CTSTATE_TO_REG] = ctstate_to_reg_ct, [MARK_TO_REG] = mark_to_reg_ct, [LABELS_TO_REG] = labels_to_reg_ct, [FTEID_TO_REG] = fteid_to_reg_ct, - [TUPLEID_TO_REG] = tupleid_to_reg_ct, }; static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); @@ -219,6 +219,28 @@ mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; } +void +mlx5e_tc_match_to_reg_get_match(struct mlx5_flow_spec *spec, + enum mlx5e_tc_attr_to_reg type, + u32 *data, + u32 *mask) +{ + int soffset = mlx5e_tc_attr_to_reg_mappings[type].soffset; + int match_len = mlx5e_tc_attr_to_reg_mappings[type].mlen; + void *headers_c = spec->match_criteria; + void *headers_v = spec->match_value; + void *fmask, *fval; + + fmask = headers_c + soffset; + fval = headers_v + soffset; + + memcpy(mask, fmask, match_len); + memcpy(data, fval, match_len); + + *mask = be32_to_cpu((__force __be32)(*mask << (32 - (match_len * 8)))); + *data = be32_to_cpu((__force __be32)(*data << (32 - (match_len * 8)))); +} + int mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, @@ -287,29 +309,6 @@ struct mlx5e_hairpin_entry { struct completion res_ready; }; -struct mod_hdr_key { - int num_actions; - void *actions; -}; - -struct mlx5e_mod_hdr_entry { - /* a node of a hash table which keeps all the mod_hdr entries */ - struct hlist_node mod_hdr_hlist; - - /* protects flows list */ - spinlock_t flows_lock; - /* flows sharing the same mod_hdr entry */ - struct list_head flows; - - struct mod_hdr_key key; - - struct mlx5_modify_hdr *modify_hdr; - - refcount_t refcnt; - struct completion res_ready; - int compl_result; -}; - static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); @@ -386,148 +385,43 @@ static bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) return flow_flag_test(flow, OFFLOADED); } -static inline u32 hash_mod_hdr_info(struct mod_hdr_key *key) -{ - return jhash(key->actions, - key->num_actions * MLX5_MH_ACT_SZ, 0); -} - -static inline int cmp_mod_hdr_info(struct mod_hdr_key *a, - struct mod_hdr_key *b) +static int get_flow_name_space(struct mlx5e_tc_flow *flow) { - if (a->num_actions != b->num_actions) - return 1; - - return memcmp(a->actions, b->actions, a->num_actions * MLX5_MH_ACT_SZ); + return mlx5e_is_eswitch_flow(flow) ? + MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; } static struct mod_hdr_tbl * -get_mod_hdr_table(struct mlx5e_priv *priv, int namespace) +get_mod_hdr_table(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - return namespace == MLX5_FLOW_NAMESPACE_FDB ? &esw->offloads.mod_hdr : + return get_flow_name_space(flow) == MLX5_FLOW_NAMESPACE_FDB ? + &esw->offloads.mod_hdr : &priv->fs.tc.mod_hdr; } -static struct mlx5e_mod_hdr_entry * -mlx5e_mod_hdr_get(struct mod_hdr_tbl *tbl, struct mod_hdr_key *key, u32 hash_key) -{ - struct mlx5e_mod_hdr_entry *mh, *found = NULL; - - hash_for_each_possible(tbl->hlist, mh, mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, key)) { - refcount_inc(&mh->refcnt); - found = mh; - break; - } - } - - return found; -} - -static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, - struct mlx5e_mod_hdr_entry *mh, - int namespace) -{ - struct mod_hdr_tbl *tbl = get_mod_hdr_table(priv, namespace); - - if (!refcount_dec_and_mutex_lock(&mh->refcnt, &tbl->lock)) - return; - hash_del(&mh->mod_hdr_hlist); - mutex_unlock(&tbl->lock); - - WARN_ON(!list_empty(&mh->flows)); - if (mh->compl_result > 0) - mlx5_modify_header_dealloc(priv->mdev, mh->modify_hdr); - - kfree(mh); -} - -static int get_flow_name_space(struct mlx5e_tc_flow *flow) -{ - return mlx5e_is_eswitch_flow(flow) ? - MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; -} static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr) { - int num_actions, actions_size, namespace, err; - struct mlx5e_mod_hdr_entry *mh; - struct mod_hdr_tbl *tbl; - struct mod_hdr_key key; - u32 hash_key; - - num_actions = parse_attr->mod_hdr_acts.num_actions; - actions_size = MLX5_MH_ACT_SZ * num_actions; - - key.actions = parse_attr->mod_hdr_acts.actions; - key.num_actions = num_actions; - - hash_key = hash_mod_hdr_info(&key); - - namespace = get_flow_name_space(flow); - tbl = get_mod_hdr_table(priv, namespace); - - mutex_lock(&tbl->lock); - mh = mlx5e_mod_hdr_get(tbl, &key, hash_key); - if (mh) { - mutex_unlock(&tbl->lock); - wait_for_completion(&mh->res_ready); - - if (mh->compl_result < 0) { - err = -EREMOTEIO; - goto attach_header_err; - } - goto attach_flow; - } - - mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); - if (!mh) { - mutex_unlock(&tbl->lock); - return -ENOMEM; - } - - mh->key.actions = (void *)mh + sizeof(*mh); - memcpy(mh->key.actions, key.actions, actions_size); - mh->key.num_actions = num_actions; - spin_lock_init(&mh->flows_lock); - INIT_LIST_HEAD(&mh->flows); - refcount_set(&mh->refcnt, 1); - init_completion(&mh->res_ready); - - hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); - mutex_unlock(&tbl->lock); + struct mlx5_modify_hdr *modify_hdr; + struct mlx5e_mod_hdr_handle *mh; - mh->modify_hdr = mlx5_modify_header_alloc(priv->mdev, namespace, - mh->key.num_actions, - mh->key.actions); - if (IS_ERR(mh->modify_hdr)) { - err = PTR_ERR(mh->modify_hdr); - mh->compl_result = err; - goto alloc_header_err; - } - mh->compl_result = 1; - complete_all(&mh->res_ready); + mh = mlx5e_mod_hdr_attach(priv->mdev, get_mod_hdr_table(priv, flow), + get_flow_name_space(flow), + &parse_attr->mod_hdr_acts); + if (IS_ERR(mh)) + return PTR_ERR(mh); -attach_flow: - flow->mh = mh; - spin_lock(&mh->flows_lock); - list_add(&flow->mod_hdr, &mh->flows); - spin_unlock(&mh->flows_lock); + modify_hdr = mlx5e_mod_hdr_get(mh); if (mlx5e_is_eswitch_flow(flow)) - flow->esw_attr->modify_hdr = mh->modify_hdr; + flow->esw_attr->modify_hdr = modify_hdr; else - flow->nic_attr->modify_hdr = mh->modify_hdr; + flow->nic_attr->modify_hdr = modify_hdr; + flow->mh = mh; return 0; - -alloc_header_err: - complete_all(&mh->res_ready); -attach_header_err: - mlx5e_mod_hdr_put(priv, mh, namespace); - return err; } static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, @@ -537,11 +431,8 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, if (!flow->mh) return; - spin_lock(&flow->mh->flows_lock); - list_del(&flow->mod_hdr); - spin_unlock(&flow->mh->flows_lock); - - mlx5e_mod_hdr_put(priv, flow->mh, get_flow_name_space(flow)); + mlx5e_mod_hdr_detach(priv->mdev, get_mod_hdr_table(priv, flow), + flow->mh); flow->mh = NULL; } @@ -3086,6 +2977,7 @@ struct ipv6_hoplimit_word { static int is_action_keys_supported(const struct flow_action_entry *act, bool ct_flow, bool *modify_ip_header, + bool *modify_tuple, struct netlink_ext_ack *extack) { u32 mask, offset; @@ -3108,7 +3000,10 @@ static int is_action_keys_supported(const struct flow_action_entry *act, *modify_ip_header = true; } - if (ct_flow && offset >= offsetof(struct iphdr, saddr)) { + if (offset >= offsetof(struct iphdr, saddr)) + *modify_tuple = true; + + if (ct_flow && *modify_tuple) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of ipv4 address with action ct"); return -EOPNOTSUPP; @@ -3123,28 +3018,36 @@ static int is_action_keys_supported(const struct flow_action_entry *act, *modify_ip_header = true; } - if (ct_flow && offset >= offsetof(struct ipv6hdr, saddr)) { + if (ct_flow && offset >= offsetof(struct ipv6hdr, saddr)) + *modify_tuple = true; + + if (ct_flow && *modify_tuple) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of ipv6 address with action ct"); return -EOPNOTSUPP; } - } else if (ct_flow && (htype == FLOW_ACT_MANGLE_HDR_TYPE_TCP || - htype == FLOW_ACT_MANGLE_HDR_TYPE_UDP)) { - NL_SET_ERR_MSG_MOD(extack, - "can't offload re-write of transport header ports with action ct"); - return -EOPNOTSUPP; + } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_TCP || + htype == FLOW_ACT_MANGLE_HDR_TYPE_UDP) { + *modify_tuple = true; + if (ct_flow) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload re-write of transport header ports with action ct"); + return -EOPNOTSUPP; + } } return 0; } -static bool modify_header_match_supported(struct mlx5_flow_spec *spec, +static bool modify_header_match_supported(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, struct flow_action *flow_action, u32 actions, bool ct_flow, + bool ct_clear, struct netlink_ext_ack *extack) { const struct flow_action_entry *act; - bool modify_ip_header; + bool modify_ip_header, modify_tuple; void *headers_c; void *headers_v; u16 ethertype; @@ -3161,23 +3064,39 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, goto out_ok; modify_ip_header = false; + modify_tuple = false; flow_action_for_each(i, act, flow_action) { if (act->id != FLOW_ACTION_MANGLE && act->id != FLOW_ACTION_ADD) continue; err = is_action_keys_supported(act, ct_flow, - &modify_ip_header, extack); + &modify_ip_header, + &modify_tuple, extack); if (err) return err; } + /* Add ct_state=-trk match so it will be offloaded for non ct flows + * (or after clear action), as otherwise, since the tuple is changed, + * we can't restore ct state + */ + if (!ct_clear && modify_tuple && + mlx5_tc_ct_add_no_trk_match(priv, spec)) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload tuple modify header with ct matches"); + netdev_info(priv->netdev, + "can't offload tuple modify header with ct matches"); + return false; + } + ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of non TCP/UDP"); - pr_info("can't offload re-write of ip proto %d\n", ip_proto); + netdev_info(priv->netdev, "can't offload re-write of ip proto %d\n", + ip_proto); return false; } @@ -3191,13 +3110,14 @@ static bool actions_match_supported(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { - bool ct_flow; + bool ct_flow = false, ct_clear = false; u32 actions; - ct_flow = flow_flag_test(flow, CT); if (mlx5e_is_eswitch_flow(flow)) { actions = flow->esw_attr->action; - + ct_clear = flow->esw_attr->ct_attr.ct_action & + TCA_CT_ACT_CLEAR; + ct_flow = flow_flag_test(flow, CT) && !ct_clear; if (flow->esw_attr->split_count && ct_flow) { /* All registers used by ct are cleared when using * split rules. @@ -3211,9 +3131,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv, } if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - return modify_header_match_supported(&parse_attr->spec, + return modify_header_match_supported(priv, &parse_attr->spec, flow_action, actions, - ct_flow, extack); + ct_flow, ct_clear, + extack); return true; } @@ -4408,7 +4329,6 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, flow->priv = priv; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) INIT_LIST_HEAD(&flow->encaps[out_index].list); - INIT_LIST_HEAD(&flow->mod_hdr); INIT_LIST_HEAD(&flow->hairpin); INIT_LIST_HEAD(&flow->l3_to_l2_reformat); refcount_set(&flow->refcnt, 1); @@ -4480,11 +4400,12 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_free; - err = parse_tc_fdb_actions(priv, &rule->action, flow, extack, filter_dev); + /* actions validation depends on parsing the ct matches first */ + err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f, extack); if (err) goto err_free; - err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f, extack); + err = parse_tc_fdb_actions(priv, &rule->action, flow, extack, filter_dev); if (err) goto err_free; @@ -4670,9 +4591,10 @@ static bool is_flow_rule_duplicate_allowed(struct net_device *dev, struct mlx5e_rep_priv *rpriv) { /* Offloaded flow rule is allowed to duplicate on non-uplink representor - * sharing tc block with other slaves of a lag device. + * sharing tc block with other slaves of a lag device. Rpriv can be NULL if this + * function is called from NIC mode. */ - return netif_is_lag_port(dev) && rpriv->rep->vport != MLX5_VPORT_UPLINK; + return netif_is_lag_port(dev) && rpriv && rpriv->rep->vport != MLX5_VPORT_UPLINK; } int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, @@ -4686,13 +4608,12 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, rcu_read_lock(); flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params); - rcu_read_unlock(); if (flow) { /* Same flow rule offloaded to non-uplink representor sharing tc block, * just return 0. */ if (is_flow_rule_duplicate_allowed(dev, rpriv) && flow->orig_dev != dev) - goto out; + goto rcu_unlock; NL_SET_ERR_MSG_MOD(extack, "flow cookie already exists, ignoring"); @@ -4700,8 +4621,12 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, "flow cookie %lx already exists, ignoring\n", f->cookie); err = -EEXIST; - goto out; + goto rcu_unlock; } +rcu_unlock: + rcu_read_unlock(); + if (flow) + goto out; trace_mlx5e_configure_flower(f); err = mlx5e_tc_add_flow(priv, f, flags, dev, &flow); @@ -5011,9 +4936,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) struct mlx5e_tc_table *tc = &priv->fs.tc; int err; + mlx5e_mod_hdr_tbl_init(&tc->mod_hdr); mutex_init(&tc->t_lock); - mutex_init(&tc->mod_hdr.lock); - hash_init(tc->mod_hdr.hlist); mutex_init(&tc->hairpin_tbl_lock); hash_init(tc->hairpin_tbl); @@ -5051,7 +4975,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) &tc->netdevice_nb, &tc->netdevice_nn); - mutex_destroy(&tc->mod_hdr.lock); + mlx5e_mod_hdr_tbl_destroy(&tc->mod_hdr); mutex_destroy(&tc->hairpin_tbl_lock); rhashtable_destroy(&tc->ht); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 1561eaa89ffd..437f680728fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -70,9 +70,9 @@ struct tunnel_match_enc_opts { * Upper TUNNEL_INFO_BITS for general tunnel info. * Lower ENC_OPTS_BITS bits for enc_opts. */ -#define TUNNEL_INFO_BITS 6 +#define TUNNEL_INFO_BITS 12 #define TUNNEL_INFO_BITS_MASK GENMASK(TUNNEL_INFO_BITS - 1, 0) -#define ENC_OPTS_BITS 2 +#define ENC_OPTS_BITS 12 #define ENC_OPTS_BITS_MASK GENMASK(ENC_OPTS_BITS - 1, 0) #define TUNNEL_ID_BITS (TUNNEL_INFO_BITS + ENC_OPTS_BITS) #define TUNNEL_ID_MASK GENMASK(TUNNEL_ID_BITS - 1, 0) @@ -129,10 +129,10 @@ enum mlx5e_tc_attr_to_reg { TUNNEL_TO_REG, CTSTATE_TO_REG, ZONE_TO_REG, + ZONE_RESTORE_TO_REG, MARK_TO_REG, LABELS_TO_REG, FTEID_TO_REG, - TUPLEID_TO_REG, }; struct mlx5e_tc_attr_to_reg_mapping { @@ -148,12 +148,6 @@ extern struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[]; bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv, struct net_device *out_dev); -struct mlx5e_tc_mod_hdr_acts { - int num_actions; - int max_actions; - void *actions; -}; - int mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, enum mlx5e_tc_attr_to_reg type, @@ -164,6 +158,11 @@ void mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec, u32 data, u32 mask); +void mlx5e_tc_match_to_reg_get_match(struct mlx5_flow_spec *spec, + enum mlx5e_tc_attr_to_reg type, + u32 *data, + u32 *mask); + int alloc_mod_hdr_actions(struct mlx5_core_dev *mdev, int namespace, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c index 5dc335e621c5..b68976b378b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c @@ -217,7 +217,6 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw, } /* Create ingress allow rule */ - memset(spec, 0, sizeof(*spec)); spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index c656c9f081c1..c181f6b63f59 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -42,6 +42,7 @@ #include "fs_core.h" #include "devlink.h" #include "ecpf.h" +#include "en/mod_hdr.h" enum { MLX5_ACTION_NONE = 0, @@ -69,7 +70,7 @@ static int mlx5_eswitch_check(const struct mlx5_core_dev *dev) return -EOPNOTSUPP; if (!MLX5_ESWITCH_MANAGER(dev)) - return -EPERM; + return -EOPNOTSUPP; return 0; } @@ -1748,10 +1749,9 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) mutex_init(&esw->offloads.encap_tbl_lock); hash_init(esw->offloads.encap_tbl); - mutex_init(&esw->offloads.mod_hdr.lock); - hash_init(esw->offloads.mod_hdr.hlist); mutex_init(&esw->offloads.decap_tbl_lock); hash_init(esw->offloads.decap_tbl); + mlx5e_mod_hdr_tbl_init(&esw->offloads.mod_hdr); atomic64_set(&esw->offloads.num_flows, 0); ida_init(&esw->offloads.vport_metadata_ida); mutex_init(&esw->state_lock); @@ -1793,7 +1793,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) mutex_destroy(&esw->mode_lock); mutex_destroy(&esw->state_lock); ida_destroy(&esw->offloads.vport_metadata_ida); - mutex_destroy(&esw->offloads.mod_hdr.lock); + mlx5e_mod_hdr_tbl_destroy(&esw->offloads.mod_hdr); mutex_destroy(&esw->offloads.encap_tbl_lock); mutex_destroy(&esw->offloads.decap_tbl_lock); kfree(esw->vports); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 9f829e68fc73..e4186e84b3ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -293,7 +293,40 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num) return 0; } -static int mlx5_eeprom_page(int offset) +static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num, + u8 *module_id) +{ + u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {}; + u32 out[MLX5_ST_SZ_DW(mcia_reg)]; + int err, status; + u8 *ptr; + + MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW); + MLX5_SET(mcia_reg, in, module, module_num); + MLX5_SET(mcia_reg, in, device_address, 0); + MLX5_SET(mcia_reg, in, page_number, 0); + MLX5_SET(mcia_reg, in, size, 1); + MLX5_SET(mcia_reg, in, l, 0); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_MCIA, 0, 0); + if (err) + return err; + + status = MLX5_GET(mcia_reg, out, status); + if (status) { + mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n", + status); + return -EIO; + } + ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); + + *module_id = ptr[0]; + + return 0; +} + +static int mlx5_qsfp_eeprom_page(u16 offset) { if (offset < MLX5_EEPROM_PAGE_LENGTH) /* Addresses between 0-255 - page 00 */ @@ -307,7 +340,7 @@ static int mlx5_eeprom_page(int offset) MLX5_EEPROM_HIGH_PAGE_LENGTH); } -static int mlx5_eeprom_high_page_offset(int page_num) +static int mlx5_qsfp_eeprom_high_page_offset(int page_num) { if (!page_num) /* Page 0 always start from low page */ return 0; @@ -316,35 +349,62 @@ static int mlx5_eeprom_high_page_offset(int page_num) return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH; } +static void mlx5_qsfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset) +{ + *i2c_addr = MLX5_I2C_ADDR_LOW; + *page_num = mlx5_qsfp_eeprom_page(*offset); + *offset -= mlx5_qsfp_eeprom_high_page_offset(*page_num); +} + +static void mlx5_sfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset) +{ + *i2c_addr = MLX5_I2C_ADDR_LOW; + *page_num = 0; + + if (*offset < MLX5_EEPROM_PAGE_LENGTH) + return; + + *i2c_addr = MLX5_I2C_ADDR_HIGH; + *offset -= MLX5_EEPROM_PAGE_LENGTH; +} + int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, u16 offset, u16 size, u8 *data) { - int module_num, page_num, status, err; + int module_num, status, err, page_num = 0; + u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {}; u32 out[MLX5_ST_SZ_DW(mcia_reg)]; - u32 in[MLX5_ST_SZ_DW(mcia_reg)]; - u16 i2c_addr; - void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); + u16 i2c_addr = 0; + u8 module_id; + void *ptr; err = mlx5_query_module_num(dev, &module_num); if (err) return err; - memset(in, 0, sizeof(in)); - size = min_t(int, size, MLX5_EEPROM_MAX_BYTES); - - /* Get the page number related to the given offset */ - page_num = mlx5_eeprom_page(offset); + err = mlx5_query_module_id(dev, module_num, &module_id); + if (err) + return err; - /* Set the right offset according to the page number, - * For page_num > 0, relative offset is always >= 128 (high page). - */ - offset -= mlx5_eeprom_high_page_offset(page_num); + switch (module_id) { + case MLX5_MODULE_ID_SFP: + mlx5_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + case MLX5_MODULE_ID_QSFP: + case MLX5_MODULE_ID_QSFP_PLUS: + case MLX5_MODULE_ID_QSFP28: + mlx5_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset); + break; + default: + mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id); + return -EINVAL; + } if (offset + size > MLX5_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; - i2c_addr = MLX5_I2C_ADDR_LOW; + size = min_t(int, size, MLX5_EEPROM_MAX_BYTES); MLX5_SET(mcia_reg, in, l, 0); MLX5_SET(mcia_reg, in, module, module_num); @@ -365,6 +425,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, return -EIO; } + ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); memcpy(data, ptr, size); return size; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e9ccd333f61d..8b3791d73c99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -2122,6 +2122,7 @@ static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, enum devlink_port_flavour flavour, u32 port_number, bool split, u32 split_port_subnumber, + bool splittable, u32 lanes, const unsigned char *switch_id, unsigned char switch_id_len) { @@ -2129,12 +2130,19 @@ static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, struct mlxsw_core_port *mlxsw_core_port = &mlxsw_core->ports[local_port]; struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; + struct devlink_port_attrs attrs = {}; int err; + attrs.split = split; + attrs.lanes = lanes; + attrs.splittable = splittable; + attrs.flavour = flavour; + attrs.phys.port_number = port_number; + attrs.phys.split_subport_number = split_port_subnumber; + memcpy(attrs.switch_id.id, switch_id, switch_id_len); + attrs.switch_id.id_len = switch_id_len; mlxsw_core_port->local_port = local_port; - devlink_port_attrs_set(devlink_port, flavour, port_number, - split, split_port_subnumber, - switch_id, switch_id_len); + devlink_port_attrs_set(devlink_port, &attrs); err = devlink_port_register(devlink, devlink_port, local_port); if (err) memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port)); @@ -2154,12 +2162,14 @@ static void __mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port) int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, u32 port_number, bool split, u32 split_port_subnumber, + bool splittable, u32 lanes, const unsigned char *switch_id, unsigned char switch_id_len) { return __mlxsw_core_port_init(mlxsw_core, local_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, port_number, split, split_port_subnumber, + splittable, lanes, switch_id, switch_id_len); } EXPORT_SYMBOL(mlxsw_core_port_init); @@ -2181,7 +2191,7 @@ int mlxsw_core_cpu_port_init(struct mlxsw_core *mlxsw_core, err = __mlxsw_core_port_init(mlxsw_core, MLXSW_PORT_CPU_PORT, DEVLINK_PORT_FLAVOUR_CPU, - 0, false, 0, + 0, false, 0, false, 0, switch_id, switch_id_len); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 22b0dfa7cfae..7d6b0a232789 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -191,8 +191,8 @@ void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core, void *mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port); int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, - u32 port_number, bool split, - u32 split_port_subnumber, + u32 port_number, bool split, u32 split_port_subnumber, + bool splittable, u32 lanes, const unsigned char *switch_id, unsigned char switch_id_len); void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index c4caeeadcba9..c010db2c9dba 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -164,8 +164,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module) int err; err = mlxsw_core_port_init(mlxsw_m->core, local_port, - module + 1, false, 0, - mlxsw_m->base_mac, + module + 1, false, 0, false, + 0, mlxsw_m->base_mac, sizeof(mlxsw_m->base_mac)); if (err) { dev_err(mlxsw_m->bus_info->dev, "Port %d: Failed to init core port\n", diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index fd0e97de44e7..c04ec1a92826 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1414,23 +1414,12 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, u16 num_pages; int err; - mutex_init(&mlxsw_pci->cmd.lock); - init_waitqueue_head(&mlxsw_pci->cmd.wait); - mlxsw_pci->core = mlxsw_core; mbox = mlxsw_cmd_mbox_alloc(); if (!mbox) return -ENOMEM; - err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); - if (err) - goto mbox_put; - - err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); - if (err) - goto err_out_mbox_alloc; - err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id); if (err) goto err_sw_reset; @@ -1537,9 +1526,6 @@ err_query_fw: mlxsw_pci_free_irq_vectors(mlxsw_pci); err_alloc_irq: err_sw_reset: - mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); -err_out_mbox_alloc: - mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); mbox_put: mlxsw_cmd_mbox_free(mbox); return err; @@ -1553,8 +1539,6 @@ static void mlxsw_pci_fini(void *bus_priv) mlxsw_pci_aqs_fini(mlxsw_pci); mlxsw_pci_fw_area_fini(mlxsw_pci); mlxsw_pci_free_irq_vectors(mlxsw_pci); - mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); - mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); } static struct mlxsw_pci_queue * @@ -1776,6 +1760,37 @@ static const struct mlxsw_bus mlxsw_pci_bus = { .features = MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET, }; +static int mlxsw_pci_cmd_init(struct mlxsw_pci *mlxsw_pci) +{ + int err; + + mutex_init(&mlxsw_pci->cmd.lock); + init_waitqueue_head(&mlxsw_pci->cmd.wait); + + err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); + if (err) + goto err_in_mbox_alloc; + + err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); + if (err) + goto err_out_mbox_alloc; + + return 0; + +err_out_mbox_alloc: + mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); +err_in_mbox_alloc: + mutex_destroy(&mlxsw_pci->cmd.lock); + return err; +} + +static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci) +{ + mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); + mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); + mutex_destroy(&mlxsw_pci->cmd.lock); +} + static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { const char *driver_name = pdev->driver->name; @@ -1831,6 +1846,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mlxsw_pci->pdev = pdev; pci_set_drvdata(pdev, mlxsw_pci); + err = mlxsw_pci_cmd_init(mlxsw_pci); + if (err) + goto err_pci_cmd_init; + mlxsw_pci->bus_info.device_kind = driver_name; mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev); mlxsw_pci->bus_info.dev = &pdev->dev; @@ -1848,6 +1867,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; err_bus_device_register: + mlxsw_pci_cmd_fini(mlxsw_pci); +err_pci_cmd_init: iounmap(mlxsw_pci->hw_addr); err_ioremap: err_pci_resource_len_check: @@ -1865,6 +1886,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev) struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev); mlxsw_core_bus_device_unregister(mlxsw_pci->core, false); + mlxsw_pci_cmd_fini(mlxsw_pci); iounmap(mlxsw_pci->hw_addr); pci_release_regions(mlxsw_pci->pdev); pci_disable_device(mlxsw_pci->pdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index b76c839223b5..76f61bef03f8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -9502,6 +9502,106 @@ MLXSW_ITEM32(reg, mogcr, ptp_iftc, 0x00, 1, 1); */ MLXSW_ITEM32(reg, mogcr, ptp_eftc, 0x00, 0, 1); +/* MPAGR - Monitoring Port Analyzer Global Register + * ------------------------------------------------ + * This register is used for global port analyzer configurations. + * Note: This register is not supported by current FW versions for Spectrum-1. + */ +#define MLXSW_REG_MPAGR_ID 0x9089 +#define MLXSW_REG_MPAGR_LEN 0x0C + +MLXSW_REG_DEFINE(mpagr, MLXSW_REG_MPAGR_ID, MLXSW_REG_MPAGR_LEN); + +enum mlxsw_reg_mpagr_trigger { + MLXSW_REG_MPAGR_TRIGGER_EGRESS, + MLXSW_REG_MPAGR_TRIGGER_INGRESS, + MLXSW_REG_MPAGR_TRIGGER_INGRESS_WRED, + MLXSW_REG_MPAGR_TRIGGER_INGRESS_SHARED_BUFFER, + MLXSW_REG_MPAGR_TRIGGER_INGRESS_ING_CONG, + MLXSW_REG_MPAGR_TRIGGER_INGRESS_EGR_CONG, + MLXSW_REG_MPAGR_TRIGGER_EGRESS_ECN, + MLXSW_REG_MPAGR_TRIGGER_EGRESS_HIGH_LATENCY, +}; + +/* reg_mpagr_trigger + * Mirror trigger. + * Access: Index + */ +MLXSW_ITEM32(reg, mpagr, trigger, 0x00, 0, 4); + +/* reg_mpagr_pa_id + * Port analyzer ID. + * Access: RW + */ +MLXSW_ITEM32(reg, mpagr, pa_id, 0x04, 0, 4); + +/* reg_mpagr_probability_rate + * Sampling rate. + * Valid values are: 1 to 3.5*10^9 + * Value of 1 means "sample all". Default is 1. + * Access: RW + */ +MLXSW_ITEM32(reg, mpagr, probability_rate, 0x08, 0, 32); + +static inline void mlxsw_reg_mpagr_pack(char *payload, + enum mlxsw_reg_mpagr_trigger trigger, + u8 pa_id, u32 probability_rate) +{ + MLXSW_REG_ZERO(mpagr, payload); + mlxsw_reg_mpagr_trigger_set(payload, trigger); + mlxsw_reg_mpagr_pa_id_set(payload, pa_id); + mlxsw_reg_mpagr_probability_rate_set(payload, probability_rate); +} + +/* MOMTE - Monitoring Mirror Trigger Enable Register + * ------------------------------------------------- + * This register is used to configure the mirror enable for different mirror + * reasons. + */ +#define MLXSW_REG_MOMTE_ID 0x908D +#define MLXSW_REG_MOMTE_LEN 0x10 + +MLXSW_REG_DEFINE(momte, MLXSW_REG_MOMTE_ID, MLXSW_REG_MOMTE_LEN); + +/* reg_momte_local_port + * Local port number. + * Access: Index + */ +MLXSW_ITEM32(reg, momte, local_port, 0x00, 16, 8); + +enum mlxsw_reg_momte_type { + MLXSW_REG_MOMTE_TYPE_WRED = 0x20, + MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_TCLASS = 0x31, + MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_TCLASS_DESCRIPTORS = 0x32, + MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_EGRESS_PORT = 0x33, + MLXSW_REG_MOMTE_TYPE_ING_CONG = 0x40, + MLXSW_REG_MOMTE_TYPE_EGR_CONG = 0x50, + MLXSW_REG_MOMTE_TYPE_ECN = 0x60, + MLXSW_REG_MOMTE_TYPE_HIGH_LATENCY = 0x70, +}; + +/* reg_momte_type + * Type of mirroring. + * Access: Index + */ +MLXSW_ITEM32(reg, momte, type, 0x04, 0, 8); + +/* reg_momte_tclass_en + * TClass/PG mirror enable. Each bit represents corresponding tclass. + * 0: disable (default) + * 1: enable + * Access: RW + */ +MLXSW_ITEM_BIT_ARRAY(reg, momte, tclass_en, 0x08, 0x08, 1); + +static inline void mlxsw_reg_momte_pack(char *payload, u8 local_port, + enum mlxsw_reg_momte_type type) +{ + MLXSW_REG_ZERO(momte, payload); + mlxsw_reg_momte_local_port_set(payload, local_port); + mlxsw_reg_momte_type_set(payload, type); +} + /* MTPPPC - Time Precision Packet Port Configuration * ------------------------------------------------- * This register serves for configuration of which PTP messages should be @@ -10853,6 +10953,8 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mgpc), MLXSW_REG(mprs), MLXSW_REG(mogcr), + MLXSW_REG(mpagr), + MLXSW_REG(momte), MLXSW_REG(mtpppc), MLXSW_REG(mtpptr), MLXSW_REG(mtptpt), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 81bb9ea1479b..4ac634bd3571 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -175,10 +175,6 @@ struct mlxsw_sp_mlxfw_dev { struct mlxsw_sp *mlxsw_sp; }; -struct mlxsw_sp_span_ops { - u32 (*buffsize_get)(int mtu, u32 speed); -}; - static int mlxsw_sp_component_query(struct mlxfw_dev *mlxfw_dev, u16 component_index, u32 *p_max_size, u8 *p_align_bits, u16 *p_max_write_size) @@ -1333,6 +1329,21 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, return 0; } +static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f) +{ + switch (f->binder_type) { + case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS: + return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, true); + case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS: + return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, false); + case FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP: + return mlxsw_sp_setup_tc_block_qevent_early_drop(mlxsw_sp_port, f); + default: + return -EOPNOTSUPP; + } +} + static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -1733,12 +1744,16 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; bool split = !!split_base_local_port; struct mlxsw_sp_port *mlxsw_sp_port; + u32 lanes = port_mapping->width; struct net_device *dev; + bool splittable; int err; + splittable = lanes > 1 && !split; err = mlxsw_core_port_init(mlxsw_sp->core, local_port, port_mapping->module + 1, split, - port_mapping->lane / port_mapping->width, + port_mapping->lane / lanes, + splittable, lanes, mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac)); if (err) { @@ -2232,13 +2247,6 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - /* Split ports cannot be split. */ - if (mlxsw_sp_port->split) { - netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); - NL_SET_ERR_MSG_MOD(extack, "Port cannot be split further"); - return -EINVAL; - } - max_width = mlxsw_core_module_max_width(mlxsw_core, mlxsw_sp_port->mapping.module); if (max_width < 0) { @@ -2247,19 +2255,13 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return max_width; } - /* Split port with non-max and 1 module width cannot be split. */ - if (mlxsw_sp_port->mapping.width != max_width || max_width == 1) { + /* Split port with non-max cannot be split. */ + if (mlxsw_sp_port->mapping.width != max_width) { netdev_err(mlxsw_sp_port->dev, "Port cannot be split\n"); NL_SET_ERR_MSG_MOD(extack, "Port cannot be split"); return -EINVAL; } - if (count == 1 || !is_power_of_2(count) || count > max_width) { - netdev_err(mlxsw_sp_port->dev, "Invalid split count\n"); - NL_SET_ERR_MSG_MOD(extack, "Invalid split count"); - return -EINVAL; - } - offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); if (offset < 0) { netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); @@ -2821,52 +2823,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { .get_stats = mlxsw_sp2_get_stats, }; -static u32 mlxsw_sp1_span_buffsize_get(int mtu, u32 speed) -{ - return mtu * 5 / 2; -} - -static const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops = { - .buffsize_get = mlxsw_sp1_span_buffsize_get, -}; - -#define MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR 38 -#define MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR 50 - -static u32 __mlxsw_sp_span_buffsize_get(int mtu, u32 speed, u32 buffer_factor) -{ - return 3 * mtu + buffer_factor * speed / 1000; -} - -static u32 mlxsw_sp2_span_buffsize_get(int mtu, u32 speed) -{ - int factor = MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR; - - return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); -} - -static const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops = { - .buffsize_get = mlxsw_sp2_span_buffsize_get, -}; - -static u32 mlxsw_sp3_span_buffsize_get(int mtu, u32 speed) -{ - int factor = MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR; - - return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); -} - -static const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops = { - .buffsize_get = mlxsw_sp3_span_buffsize_get, -}; - -u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed) -{ - u32 buffsize = mlxsw_sp->span_ops->buffsize_get(speed, mtu); - - return mlxsw_sp_bytes_cells(mlxsw_sp, buffsize) + 1; -} - static int mlxsw_sp_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 1d6b2bc2774c..c00811178637 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -539,7 +539,6 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int *p_counter_index); void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, unsigned int counter_index); -u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed); bool mlxsw_sp_port_dev_check(const struct net_device *dev); struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev); @@ -711,7 +710,6 @@ struct mlxsw_sp_flow_block { struct mlxsw_sp_flow_block_binding { struct list_head list; - struct net_device *dev; struct mlxsw_sp_port *mlxsw_sp_port; bool ingress; }; @@ -769,8 +767,9 @@ mlxsw_sp_flow_block_is_mixed_bound(const struct mlxsw_sp_flow_block *block) struct mlxsw_sp_flow_block *mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net); void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block); -int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f); +int mlxsw_sp_setup_tc_block_clsact(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + bool ingress); /* spectrum_acl.c */ struct mlxsw_sp_acl_ruleset; @@ -962,6 +961,30 @@ extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops; extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops; /* spectrum_matchall.c */ +enum mlxsw_sp_mall_action_type { + MLXSW_SP_MALL_ACTION_TYPE_MIRROR, + MLXSW_SP_MALL_ACTION_TYPE_SAMPLE, + MLXSW_SP_MALL_ACTION_TYPE_TRAP, +}; + +struct mlxsw_sp_mall_mirror_entry { + const struct net_device *to_dev; + int span_id; +}; + +struct mlxsw_sp_mall_entry { + struct list_head list; + unsigned long cookie; + unsigned int priority; + enum mlxsw_sp_mall_action_type type; + bool ingress; + union { + struct mlxsw_sp_mall_mirror_entry mirror; + struct mlxsw_sp_port_sample sample; + }; + struct rcu_head rcu; +}; + int mlxsw_sp_mall_replace(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_flow_block *block, struct tc_cls_matchall_offload *f); @@ -1008,6 +1031,8 @@ int mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_tbf_qopt_offload *p); int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_fifo_qopt_offload *p); +int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f); /* spectrum_fid.c */ bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c index 47b66f347ff1..0456cda33808 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c @@ -219,8 +219,7 @@ static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_tc_block_release); if (IS_ERR(block_cb)) { mlxsw_sp_flow_block_destroy(flow_block); - err = PTR_ERR(block_cb); - goto err_cb_register; + return PTR_ERR(block_cb); } register_block = true; } else { @@ -247,7 +246,6 @@ static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port, err_block_bind: if (!flow_block_cb_decref(block_cb)) flow_block_cb_free(block_cb); -err_cb_register: return err; } @@ -279,18 +277,10 @@ static void mlxsw_sp_setup_tc_block_unbind(struct mlxsw_sp_port *mlxsw_sp_port, } } -int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f) +int mlxsw_sp_setup_tc_block_clsact(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + bool ingress) { - bool ingress; - - if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) - ingress = true; - else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) - ingress = false; - else - return -EOPNOTSUPP; - f->driver_block_list = &mlxsw_sp_block_cb_list; switch (f->command) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c index f1a44a8eda55..195e28ab8e65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c @@ -10,29 +10,6 @@ #include "spectrum_span.h" #include "reg.h" -enum mlxsw_sp_mall_action_type { - MLXSW_SP_MALL_ACTION_TYPE_MIRROR, - MLXSW_SP_MALL_ACTION_TYPE_SAMPLE, -}; - -struct mlxsw_sp_mall_mirror_entry { - const struct net_device *to_dev; - int span_id; -}; - -struct mlxsw_sp_mall_entry { - struct list_head list; - unsigned long cookie; - unsigned int priority; - enum mlxsw_sp_mall_action_type type; - bool ingress; - union { - struct mlxsw_sp_mall_mirror_entry mirror; - struct mlxsw_sp_port_sample sample; - }; - struct rcu_head rcu; -}; - static struct mlxsw_sp_mall_entry * mlxsw_sp_mall_entry_find(struct mlxsw_sp_flow_block *block, unsigned long cookie) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 670a43fe2a00..901acd87353f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -8,6 +8,7 @@ #include <net/red.h> #include "spectrum.h" +#include "spectrum_span.h" #include "reg.h" #define MLXSW_SP_PRIO_BAND_TO_TCLASS(band) (IEEE_8021QAZ_MAX_TCS - band - 1) @@ -1272,6 +1273,477 @@ int mlxsw_sp_setup_tc_ets(struct mlxsw_sp_port *mlxsw_sp_port, } } +struct mlxsw_sp_qevent_block { + struct list_head binding_list; + struct list_head mall_entry_list; + struct mlxsw_sp *mlxsw_sp; +}; + +struct mlxsw_sp_qevent_binding { + struct list_head list; + struct mlxsw_sp_port *mlxsw_sp_port; + u32 handle; + int tclass_num; + enum mlxsw_sp_span_trigger span_trigger; +}; + +static LIST_HEAD(mlxsw_sp_qevent_block_cb_list); + +static int mlxsw_sp_qevent_mirror_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; + struct mlxsw_sp_span_trigger_parms trigger_parms = {}; + int span_id; + int err; + + err = mlxsw_sp_span_agent_get(mlxsw_sp, mall_entry->mirror.to_dev, &span_id); + if (err) + return err; + + err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, true); + if (err) + goto err_analyzed_port_get; + + trigger_parms.span_id = span_id; + err = mlxsw_sp_span_agent_bind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + &trigger_parms); + if (err) + goto err_agent_bind; + + err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, qevent_binding->span_trigger, + qevent_binding->tclass_num); + if (err) + goto err_trigger_enable; + + mall_entry->mirror.span_id = span_id; + return 0; + +err_trigger_enable: + mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + &trigger_parms); +err_agent_bind: + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); +err_analyzed_port_get: + mlxsw_sp_span_agent_put(mlxsw_sp, span_id); + return err; +} + +static void mlxsw_sp_qevent_mirror_deconfigure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; + struct mlxsw_sp_span_trigger_parms trigger_parms = { + .span_id = mall_entry->mirror.span_id, + }; + + mlxsw_sp_span_trigger_disable(mlxsw_sp_port, qevent_binding->span_trigger, + qevent_binding->tclass_num); + mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + &trigger_parms); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_agent_put(mlxsw_sp, mall_entry->mirror.span_id); +} + +static int mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + switch (mall_entry->type) { + case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: + return mlxsw_sp_qevent_mirror_configure(mlxsw_sp, mall_entry, qevent_binding); + default: + /* This should have been validated away. */ + WARN_ON(1); + return -EOPNOTSUPP; + } +} + +static void mlxsw_sp_qevent_entry_deconfigure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + switch (mall_entry->type) { + case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: + return mlxsw_sp_qevent_mirror_deconfigure(mlxsw_sp, mall_entry, qevent_binding); + default: + WARN_ON(1); + return; + } +} + +static int mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + struct mlxsw_sp_mall_entry *mall_entry; + int err; + + list_for_each_entry(mall_entry, &qevent_block->mall_entry_list, list) { + err = mlxsw_sp_qevent_entry_configure(qevent_block->mlxsw_sp, mall_entry, + qevent_binding); + if (err) + goto err_entry_configure; + } + + return 0; + +err_entry_configure: + list_for_each_entry_continue_reverse(mall_entry, &qevent_block->mall_entry_list, list) + mlxsw_sp_qevent_entry_deconfigure(qevent_block->mlxsw_sp, mall_entry, + qevent_binding); + return err; +} + +static void mlxsw_sp_qevent_binding_deconfigure(struct mlxsw_sp_qevent_block *qevent_block, + struct mlxsw_sp_qevent_binding *qevent_binding) +{ + struct mlxsw_sp_mall_entry *mall_entry; + + list_for_each_entry(mall_entry, &qevent_block->mall_entry_list, list) + mlxsw_sp_qevent_entry_deconfigure(qevent_block->mlxsw_sp, mall_entry, + qevent_binding); +} + +static int mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block) +{ + struct mlxsw_sp_qevent_binding *qevent_binding; + int err; + + list_for_each_entry(qevent_binding, &qevent_block->binding_list, list) { + err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + if (err) + goto err_binding_configure; + } + + return 0; + +err_binding_configure: + list_for_each_entry_continue_reverse(qevent_binding, &qevent_block->binding_list, list) + mlxsw_sp_qevent_binding_deconfigure(qevent_block, qevent_binding); + return err; +} + +static void mlxsw_sp_qevent_block_deconfigure(struct mlxsw_sp_qevent_block *qevent_block) +{ + struct mlxsw_sp_qevent_binding *qevent_binding; + + list_for_each_entry(qevent_binding, &qevent_block->binding_list, list) + mlxsw_sp_qevent_binding_deconfigure(qevent_block, qevent_binding); +} + +static struct mlxsw_sp_mall_entry * +mlxsw_sp_qevent_mall_entry_find(struct mlxsw_sp_qevent_block *block, unsigned long cookie) +{ + struct mlxsw_sp_mall_entry *mall_entry; + + list_for_each_entry(mall_entry, &block->mall_entry_list, list) + if (mall_entry->cookie == cookie) + return mall_entry; + + return NULL; +} + +static int mlxsw_sp_qevent_mall_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_qevent_block *qevent_block, + struct tc_cls_matchall_offload *f) +{ + struct mlxsw_sp_mall_entry *mall_entry; + struct flow_action_entry *act; + int err; + + /* It should not currently be possible to replace a matchall rule. So + * this must be a new rule. + */ + if (!list_empty(&qevent_block->mall_entry_list)) { + NL_SET_ERR_MSG(f->common.extack, "At most one filter supported"); + return -EOPNOTSUPP; + } + if (f->rule->action.num_entries != 1) { + NL_SET_ERR_MSG(f->common.extack, "Only singular actions supported"); + return -EOPNOTSUPP; + } + if (f->common.chain_index) { + NL_SET_ERR_MSG(f->common.extack, "Only chain 0 is supported"); + return -EOPNOTSUPP; + } + if (f->common.protocol != htons(ETH_P_ALL)) { + NL_SET_ERR_MSG(f->common.extack, "Protocol matching not supported"); + return -EOPNOTSUPP; + } + + act = &f->rule->action.entries[0]; + if (!(act->hw_stats & FLOW_ACTION_HW_STATS_DISABLED)) { + NL_SET_ERR_MSG(f->common.extack, "HW counters not supported on qevents"); + return -EOPNOTSUPP; + } + + mall_entry = kzalloc(sizeof(*mall_entry), GFP_KERNEL); + if (!mall_entry) + return -ENOMEM; + mall_entry->cookie = f->cookie; + + if (act->id == FLOW_ACTION_MIRRED) { + mall_entry->type = MLXSW_SP_MALL_ACTION_TYPE_MIRROR; + mall_entry->mirror.to_dev = act->dev; + } else { + NL_SET_ERR_MSG(f->common.extack, "Unsupported action"); + err = -EOPNOTSUPP; + goto err_unsupported_action; + } + + list_add_tail(&mall_entry->list, &qevent_block->mall_entry_list); + + err = mlxsw_sp_qevent_block_configure(qevent_block); + if (err) + goto err_block_configure; + + return 0; + +err_block_configure: + list_del(&mall_entry->list); +err_unsupported_action: + kfree(mall_entry); + return err; +} + +static void mlxsw_sp_qevent_mall_destroy(struct mlxsw_sp_qevent_block *qevent_block, + struct tc_cls_matchall_offload *f) +{ + struct mlxsw_sp_mall_entry *mall_entry; + + mall_entry = mlxsw_sp_qevent_mall_entry_find(qevent_block, f->cookie); + if (!mall_entry) + return; + + mlxsw_sp_qevent_block_deconfigure(qevent_block); + + list_del(&mall_entry->list); + kfree(mall_entry); +} + +static int mlxsw_sp_qevent_block_mall_cb(struct mlxsw_sp_qevent_block *qevent_block, + struct tc_cls_matchall_offload *f) +{ + struct mlxsw_sp *mlxsw_sp = qevent_block->mlxsw_sp; + + switch (f->command) { + case TC_CLSMATCHALL_REPLACE: + return mlxsw_sp_qevent_mall_replace(mlxsw_sp, qevent_block, f); + case TC_CLSMATCHALL_DESTROY: + mlxsw_sp_qevent_mall_destroy(qevent_block, f); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int mlxsw_sp_qevent_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) +{ + struct mlxsw_sp_qevent_block *qevent_block = cb_priv; + + switch (type) { + case TC_SETUP_CLSMATCHALL: + return mlxsw_sp_qevent_block_mall_cb(qevent_block, type_data); + default: + return -EOPNOTSUPP; + } +} + +static struct mlxsw_sp_qevent_block *mlxsw_sp_qevent_block_create(struct mlxsw_sp *mlxsw_sp, + struct net *net) +{ + struct mlxsw_sp_qevent_block *qevent_block; + + qevent_block = kzalloc(sizeof(*qevent_block), GFP_KERNEL); + if (!qevent_block) + return NULL; + + INIT_LIST_HEAD(&qevent_block->binding_list); + INIT_LIST_HEAD(&qevent_block->mall_entry_list); + qevent_block->mlxsw_sp = mlxsw_sp; + return qevent_block; +} + +static void +mlxsw_sp_qevent_block_destroy(struct mlxsw_sp_qevent_block *qevent_block) +{ + WARN_ON(!list_empty(&qevent_block->binding_list)); + WARN_ON(!list_empty(&qevent_block->mall_entry_list)); + kfree(qevent_block); +} + +static void mlxsw_sp_qevent_block_release(void *cb_priv) +{ + struct mlxsw_sp_qevent_block *qevent_block = cb_priv; + + mlxsw_sp_qevent_block_destroy(qevent_block); +} + +static struct mlxsw_sp_qevent_binding * +mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, int tclass_num, + enum mlxsw_sp_span_trigger span_trigger) +{ + struct mlxsw_sp_qevent_binding *binding; + + binding = kzalloc(sizeof(*binding), GFP_KERNEL); + if (!binding) + return ERR_PTR(-ENOMEM); + + binding->mlxsw_sp_port = mlxsw_sp_port; + binding->handle = handle; + binding->tclass_num = tclass_num; + binding->span_trigger = span_trigger; + return binding; +} + +static void +mlxsw_sp_qevent_binding_destroy(struct mlxsw_sp_qevent_binding *binding) +{ + kfree(binding); +} + +static struct mlxsw_sp_qevent_binding * +mlxsw_sp_qevent_binding_lookup(struct mlxsw_sp_qevent_block *block, + struct mlxsw_sp_port *mlxsw_sp_port, + u32 handle, + enum mlxsw_sp_span_trigger span_trigger) +{ + struct mlxsw_sp_qevent_binding *qevent_binding; + + list_for_each_entry(qevent_binding, &block->binding_list, list) + if (qevent_binding->mlxsw_sp_port == mlxsw_sp_port && + qevent_binding->handle == handle && + qevent_binding->span_trigger == span_trigger) + return qevent_binding; + return NULL; +} + +static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_qevent_binding *qevent_binding; + struct mlxsw_sp_qevent_block *qevent_block; + struct flow_block_cb *block_cb; + struct mlxsw_sp_qdisc *qdisc; + bool register_block = false; + int err; + + block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_qevent_block_cb, mlxsw_sp); + if (!block_cb) { + qevent_block = mlxsw_sp_qevent_block_create(mlxsw_sp, f->net); + if (!qevent_block) + return -ENOMEM; + block_cb = flow_block_cb_alloc(mlxsw_sp_qevent_block_cb, mlxsw_sp, qevent_block, + mlxsw_sp_qevent_block_release); + if (IS_ERR(block_cb)) { + mlxsw_sp_qevent_block_destroy(qevent_block); + return PTR_ERR(block_cb); + } + register_block = true; + } else { + qevent_block = flow_block_cb_priv(block_cb); + } + flow_block_cb_incref(block_cb); + + qdisc = mlxsw_sp_qdisc_find_by_handle(mlxsw_sp_port, f->sch->handle); + if (!qdisc) { + NL_SET_ERR_MSG(f->extack, "Qdisc not offloaded"); + err = -ENOENT; + goto err_find_qdisc; + } + + if (WARN_ON(mlxsw_sp_qevent_binding_lookup(qevent_block, mlxsw_sp_port, f->sch->handle, + span_trigger))) { + err = -EEXIST; + goto err_binding_exists; + } + + qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, f->sch->handle, + qdisc->tclass_num, span_trigger); + if (IS_ERR(qevent_binding)) { + err = PTR_ERR(qevent_binding); + goto err_binding_create; + } + + err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + if (err) + goto err_binding_configure; + + list_add(&qevent_binding->list, &qevent_block->binding_list); + + if (register_block) { + flow_block_cb_add(block_cb, f); + list_add_tail(&block_cb->driver_list, &mlxsw_sp_qevent_block_cb_list); + } + + return 0; + +err_binding_configure: + mlxsw_sp_qevent_binding_destroy(qevent_binding); +err_binding_create: +err_binding_exists: +err_find_qdisc: + if (!flow_block_cb_decref(block_cb)) + flow_block_cb_free(block_cb); + return err; +} + +static void mlxsw_sp_setup_tc_block_qevent_unbind(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_qevent_binding *qevent_binding; + struct mlxsw_sp_qevent_block *qevent_block; + struct flow_block_cb *block_cb; + + block_cb = flow_block_cb_lookup(f->block, mlxsw_sp_qevent_block_cb, mlxsw_sp); + if (!block_cb) + return; + qevent_block = flow_block_cb_priv(block_cb); + + qevent_binding = mlxsw_sp_qevent_binding_lookup(qevent_block, mlxsw_sp_port, f->sch->handle, + span_trigger); + if (!qevent_binding) + return; + + list_del(&qevent_binding->list); + mlxsw_sp_qevent_binding_deconfigure(qevent_block, qevent_binding); + mlxsw_sp_qevent_binding_destroy(qevent_binding); + + if (!flow_block_cb_decref(block_cb)) { + flow_block_cb_remove(block_cb, f); + list_del(&block_cb->driver_list); + } +} + +static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger) +{ + f->driver_block_list = &mlxsw_sp_qevent_block_cb_list; + + switch (f->command) { + case FLOW_BLOCK_BIND: + return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, span_trigger); + case FLOW_BLOCK_UNBIND: + mlxsw_sp_setup_tc_block_qevent_unbind(mlxsw_sp_port, f, span_trigger); + return 0; + default: + return -EOPNOTSUPP; + } +} + +int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f) +{ + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, MLXSW_SP_SPAN_TRIGGER_EARLY_DROP); +} + int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp_qdisc_state *qdisc_state; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 770de0222e7b..019ed503aadf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6262,7 +6262,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, } fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); - if (WARN_ON(!fib_work)) + if (!fib_work) return NOTIFY_BAD; fib_work->mlxsw_sp = router->mlxsw_sp; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 92351a79addc..6374765a112d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -21,6 +21,7 @@ struct mlxsw_sp_span { struct work_struct work; struct mlxsw_sp *mlxsw_sp; + const struct mlxsw_sp_span_trigger_ops **span_trigger_ops_arr; struct list_head analyzed_ports_list; struct mutex analyzed_ports_lock; /* Protects analyzed_ports_list */ struct list_head trigger_entries_list; @@ -38,12 +39,31 @@ struct mlxsw_sp_span_analyzed_port { struct mlxsw_sp_span_trigger_entry { struct list_head list; /* Member of trigger_entries_list */ + struct mlxsw_sp_span *span; + const struct mlxsw_sp_span_trigger_ops *ops; refcount_t ref_count; u8 local_port; enum mlxsw_sp_span_trigger trigger; struct mlxsw_sp_span_trigger_parms parms; }; +enum mlxsw_sp_span_trigger_type { + MLXSW_SP_SPAN_TRIGGER_TYPE_PORT, + MLXSW_SP_SPAN_TRIGGER_TYPE_GLOBAL, +}; + +struct mlxsw_sp_span_trigger_ops { + int (*bind)(struct mlxsw_sp_span_trigger_entry *trigger_entry); + void (*unbind)(struct mlxsw_sp_span_trigger_entry *trigger_entry); + bool (*matches)(struct mlxsw_sp_span_trigger_entry *trigger_entry, + enum mlxsw_sp_span_trigger trigger, + struct mlxsw_sp_port *mlxsw_sp_port); + int (*enable)(struct mlxsw_sp_span_trigger_entry *trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, u8 tc); + void (*disable)(struct mlxsw_sp_span_trigger_entry *trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, u8 tc); +}; + static void mlxsw_sp_span_respin_work(struct work_struct *work); static u64 mlxsw_sp_span_occ_get(void *priv) @@ -57,7 +77,7 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); struct mlxsw_sp_span *span; - int i, entries_count; + int i, entries_count, err; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) return -EIO; @@ -77,11 +97,20 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < mlxsw_sp->span->entries_count; i++) mlxsw_sp->span->entries[i].id = i; + err = mlxsw_sp->span_ops->init(mlxsw_sp); + if (err) + goto err_init; + devlink_resource_occ_get_register(devlink, MLXSW_SP_RESOURCE_SPAN, mlxsw_sp_span_occ_get, mlxsw_sp); INIT_WORK(&span->work, mlxsw_sp_span_respin_work); return 0; + +err_init: + mutex_destroy(&mlxsw_sp->span->analyzed_ports_lock); + kfree(mlxsw_sp->span); + return err; } void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) @@ -766,6 +795,14 @@ static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, return 0; } +static u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, + u32 speed) +{ + u32 buffsize = mlxsw_sp->span_ops->buffsize_get(speed, mtu); + + return mlxsw_sp_bytes_cells(mlxsw_sp, buffsize) + 1; +} + static int mlxsw_sp_span_port_buffer_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) { @@ -1051,9 +1088,9 @@ out_unlock: } static int -__mlxsw_sp_span_trigger_entry_bind(struct mlxsw_sp_span *span, - struct mlxsw_sp_span_trigger_entry * - trigger_entry, bool enable) +__mlxsw_sp_span_trigger_port_bind(struct mlxsw_sp_span *span, + struct mlxsw_sp_span_trigger_entry * + trigger_entry, bool enable) { char mpar_pl[MLXSW_REG_MPAR_LEN]; enum mlxsw_reg_mpar_i_e i_e; @@ -1076,19 +1113,254 @@ __mlxsw_sp_span_trigger_entry_bind(struct mlxsw_sp_span *span, } static int -mlxsw_sp_span_trigger_entry_bind(struct mlxsw_sp_span *span, - struct mlxsw_sp_span_trigger_entry * - trigger_entry) +mlxsw_sp_span_trigger_port_bind(struct mlxsw_sp_span_trigger_entry * + trigger_entry) +{ + return __mlxsw_sp_span_trigger_port_bind(trigger_entry->span, + trigger_entry, true); +} + +static void +mlxsw_sp_span_trigger_port_unbind(struct mlxsw_sp_span_trigger_entry * + trigger_entry) +{ + __mlxsw_sp_span_trigger_port_bind(trigger_entry->span, trigger_entry, + false); +} + +static bool +mlxsw_sp_span_trigger_port_matches(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + enum mlxsw_sp_span_trigger trigger, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + return trigger_entry->trigger == trigger && + trigger_entry->local_port == mlxsw_sp_port->local_port; +} + +static int +mlxsw_sp_span_trigger_port_enable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, u8 tc) +{ + /* Port trigger are enabled during binding. */ + return 0; +} + +static void +mlxsw_sp_span_trigger_port_disable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, u8 tc) +{ +} + +static const struct mlxsw_sp_span_trigger_ops +mlxsw_sp_span_trigger_port_ops = { + .bind = mlxsw_sp_span_trigger_port_bind, + .unbind = mlxsw_sp_span_trigger_port_unbind, + .matches = mlxsw_sp_span_trigger_port_matches, + .enable = mlxsw_sp_span_trigger_port_enable, + .disable = mlxsw_sp_span_trigger_port_disable, +}; + +static int +mlxsw_sp1_span_trigger_global_bind(struct mlxsw_sp_span_trigger_entry * + trigger_entry) +{ + return -EOPNOTSUPP; +} + +static void +mlxsw_sp1_span_trigger_global_unbind(struct mlxsw_sp_span_trigger_entry * + trigger_entry) +{ +} + +static bool +mlxsw_sp1_span_trigger_global_matches(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + enum mlxsw_sp_span_trigger trigger, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + WARN_ON_ONCE(1); + return false; +} + +static int +mlxsw_sp1_span_trigger_global_enable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, + u8 tc) { - return __mlxsw_sp_span_trigger_entry_bind(span, trigger_entry, true); + return -EOPNOTSUPP; } static void -mlxsw_sp_span_trigger_entry_unbind(struct mlxsw_sp_span *span, - struct mlxsw_sp_span_trigger_entry * +mlxsw_sp1_span_trigger_global_disable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, + u8 tc) +{ +} + +static const struct mlxsw_sp_span_trigger_ops +mlxsw_sp1_span_trigger_global_ops = { + .bind = mlxsw_sp1_span_trigger_global_bind, + .unbind = mlxsw_sp1_span_trigger_global_unbind, + .matches = mlxsw_sp1_span_trigger_global_matches, + .enable = mlxsw_sp1_span_trigger_global_enable, + .disable = mlxsw_sp1_span_trigger_global_disable, +}; + +static const struct mlxsw_sp_span_trigger_ops * +mlxsw_sp1_span_trigger_ops_arr[] = { + [MLXSW_SP_SPAN_TRIGGER_TYPE_PORT] = &mlxsw_sp_span_trigger_port_ops, + [MLXSW_SP_SPAN_TRIGGER_TYPE_GLOBAL] = + &mlxsw_sp1_span_trigger_global_ops, +}; + +static int +mlxsw_sp2_span_trigger_global_bind(struct mlxsw_sp_span_trigger_entry * trigger_entry) { - __mlxsw_sp_span_trigger_entry_bind(span, trigger_entry, false); + struct mlxsw_sp *mlxsw_sp = trigger_entry->span->mlxsw_sp; + enum mlxsw_reg_mpagr_trigger trigger; + char mpagr_pl[MLXSW_REG_MPAGR_LEN]; + + switch (trigger_entry->trigger) { + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: + trigger = MLXSW_REG_MPAGR_TRIGGER_INGRESS_SHARED_BUFFER; + break; + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: + trigger = MLXSW_REG_MPAGR_TRIGGER_INGRESS_WRED; + break; + case MLXSW_SP_SPAN_TRIGGER_ECN: + trigger = MLXSW_REG_MPAGR_TRIGGER_EGRESS_ECN; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + mlxsw_reg_mpagr_pack(mpagr_pl, trigger, trigger_entry->parms.span_id, + 1); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpagr), mpagr_pl); +} + +static void +mlxsw_sp2_span_trigger_global_unbind(struct mlxsw_sp_span_trigger_entry * + trigger_entry) +{ + /* There is no unbinding for global triggers. The trigger should be + * disabled on all ports by now. + */ +} + +static bool +mlxsw_sp2_span_trigger_global_matches(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + enum mlxsw_sp_span_trigger trigger, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + return trigger_entry->trigger == trigger; +} + +static int +__mlxsw_sp2_span_trigger_global_enable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, + u8 tc, bool enable) +{ + struct mlxsw_sp *mlxsw_sp = trigger_entry->span->mlxsw_sp; + char momte_pl[MLXSW_REG_MOMTE_LEN]; + enum mlxsw_reg_momte_type type; + int err; + + switch (trigger_entry->trigger) { + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: + type = MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_TCLASS; + break; + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: + type = MLXSW_REG_MOMTE_TYPE_WRED; + break; + case MLXSW_SP_SPAN_TRIGGER_ECN: + type = MLXSW_REG_MOMTE_TYPE_ECN; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + /* Query existing configuration in order to only change the state of + * the specified traffic class. + */ + mlxsw_reg_momte_pack(momte_pl, mlxsw_sp_port->local_port, type); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(momte), momte_pl); + if (err) + return err; + + mlxsw_reg_momte_tclass_en_set(momte_pl, tc, enable); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(momte), momte_pl); +} + +static int +mlxsw_sp2_span_trigger_global_enable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, + u8 tc) +{ + return __mlxsw_sp2_span_trigger_global_enable(trigger_entry, + mlxsw_sp_port, tc, true); +} + +static void +mlxsw_sp2_span_trigger_global_disable(struct mlxsw_sp_span_trigger_entry * + trigger_entry, + struct mlxsw_sp_port *mlxsw_sp_port, + u8 tc) +{ + __mlxsw_sp2_span_trigger_global_enable(trigger_entry, mlxsw_sp_port, tc, + false); +} + +static const struct mlxsw_sp_span_trigger_ops +mlxsw_sp2_span_trigger_global_ops = { + .bind = mlxsw_sp2_span_trigger_global_bind, + .unbind = mlxsw_sp2_span_trigger_global_unbind, + .matches = mlxsw_sp2_span_trigger_global_matches, + .enable = mlxsw_sp2_span_trigger_global_enable, + .disable = mlxsw_sp2_span_trigger_global_disable, +}; + +static const struct mlxsw_sp_span_trigger_ops * +mlxsw_sp2_span_trigger_ops_arr[] = { + [MLXSW_SP_SPAN_TRIGGER_TYPE_PORT] = &mlxsw_sp_span_trigger_port_ops, + [MLXSW_SP_SPAN_TRIGGER_TYPE_GLOBAL] = + &mlxsw_sp2_span_trigger_global_ops, +}; + +static void +mlxsw_sp_span_trigger_ops_set(struct mlxsw_sp_span_trigger_entry *trigger_entry) +{ + struct mlxsw_sp_span *span = trigger_entry->span; + enum mlxsw_sp_span_trigger_type type; + + switch (trigger_entry->trigger) { + case MLXSW_SP_SPAN_TRIGGER_INGRESS: /* fall-through */ + case MLXSW_SP_SPAN_TRIGGER_EGRESS: + type = MLXSW_SP_SPAN_TRIGGER_TYPE_PORT; + break; + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: /* fall-through */ + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: /* fall-through */ + case MLXSW_SP_SPAN_TRIGGER_ECN: + type = MLXSW_SP_SPAN_TRIGGER_TYPE_GLOBAL; + break; + default: + WARN_ON_ONCE(1); + return; + } + + trigger_entry->ops = span->span_trigger_ops_arr[type]; } static struct mlxsw_sp_span_trigger_entry * @@ -1106,12 +1378,15 @@ mlxsw_sp_span_trigger_entry_create(struct mlxsw_sp_span *span, return ERR_PTR(-ENOMEM); refcount_set(&trigger_entry->ref_count, 1); - trigger_entry->local_port = mlxsw_sp_port->local_port; + trigger_entry->local_port = mlxsw_sp_port ? mlxsw_sp_port->local_port : + 0; trigger_entry->trigger = trigger; memcpy(&trigger_entry->parms, parms, sizeof(trigger_entry->parms)); + trigger_entry->span = span; + mlxsw_sp_span_trigger_ops_set(trigger_entry); list_add_tail(&trigger_entry->list, &span->trigger_entries_list); - err = mlxsw_sp_span_trigger_entry_bind(span, trigger_entry); + err = trigger_entry->ops->bind(trigger_entry); if (err) goto err_trigger_entry_bind; @@ -1128,7 +1403,7 @@ mlxsw_sp_span_trigger_entry_destroy(struct mlxsw_sp_span *span, struct mlxsw_sp_span_trigger_entry * trigger_entry) { - mlxsw_sp_span_trigger_entry_unbind(span, trigger_entry); + trigger_entry->ops->unbind(trigger_entry); list_del(&trigger_entry->list); kfree(trigger_entry); } @@ -1141,8 +1416,8 @@ mlxsw_sp_span_trigger_entry_find(struct mlxsw_sp_span *span, struct mlxsw_sp_span_trigger_entry *trigger_entry; list_for_each_entry(trigger_entry, &span->trigger_entries_list, list) { - if (trigger_entry->trigger == trigger && - trigger_entry->local_port == mlxsw_sp_port->local_port) + if (trigger_entry->ops->matches(trigger_entry, trigger, + mlxsw_sp_port)) return trigger_entry; } @@ -1207,3 +1482,93 @@ void mlxsw_sp_span_agent_unbind(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_span_trigger_entry_destroy(mlxsw_sp->span, trigger_entry); } + +int mlxsw_sp_span_trigger_enable(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_sp_span_trigger trigger, u8 tc) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_span_trigger_entry *trigger_entry; + + ASSERT_RTNL(); + + trigger_entry = mlxsw_sp_span_trigger_entry_find(mlxsw_sp->span, + trigger, + mlxsw_sp_port); + if (WARN_ON_ONCE(!trigger_entry)) + return -EINVAL; + + return trigger_entry->ops->enable(trigger_entry, mlxsw_sp_port, tc); +} + +void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_sp_span_trigger trigger, u8 tc) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_span_trigger_entry *trigger_entry; + + ASSERT_RTNL(); + + trigger_entry = mlxsw_sp_span_trigger_entry_find(mlxsw_sp->span, + trigger, + mlxsw_sp_port); + if (WARN_ON_ONCE(!trigger_entry)) + return; + + return trigger_entry->ops->disable(trigger_entry, mlxsw_sp_port, tc); +} + +static int mlxsw_sp1_span_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->span->span_trigger_ops_arr = mlxsw_sp1_span_trigger_ops_arr; + + return 0; +} + +static u32 mlxsw_sp1_span_buffsize_get(int mtu, u32 speed) +{ + return mtu * 5 / 2; +} + +const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops = { + .init = mlxsw_sp1_span_init, + .buffsize_get = mlxsw_sp1_span_buffsize_get, +}; + +static int mlxsw_sp2_span_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->span->span_trigger_ops_arr = mlxsw_sp2_span_trigger_ops_arr; + + return 0; +} + +#define MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR 38 +#define MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR 50 + +static u32 __mlxsw_sp_span_buffsize_get(int mtu, u32 speed, u32 buffer_factor) +{ + return 3 * mtu + buffer_factor * speed / 1000; +} + +static u32 mlxsw_sp2_span_buffsize_get(int mtu, u32 speed) +{ + int factor = MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR; + + return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); +} + +const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops = { + .init = mlxsw_sp2_span_init, + .buffsize_get = mlxsw_sp2_span_buffsize_get, +}; + +static u32 mlxsw_sp3_span_buffsize_get(int mtu, u32 speed) +{ + int factor = MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR; + + return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); +} + +const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops = { + .init = mlxsw_sp2_span_init, + .buffsize_get = mlxsw_sp3_span_buffsize_get, +}; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index 9f6dd2d0f4e6..29b96b222e25 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -26,6 +26,9 @@ struct mlxsw_sp_span_parms { enum mlxsw_sp_span_trigger { MLXSW_SP_SPAN_TRIGGER_INGRESS, MLXSW_SP_SPAN_TRIGGER_EGRESS, + MLXSW_SP_SPAN_TRIGGER_TAIL_DROP, + MLXSW_SP_SPAN_TRIGGER_EARLY_DROP, + MLXSW_SP_SPAN_TRIGGER_ECN, }; struct mlxsw_sp_span_trigger_parms { @@ -34,6 +37,11 @@ struct mlxsw_sp_span_trigger_parms { struct mlxsw_sp_span_entry_ops; +struct mlxsw_sp_span_ops { + int (*init)(struct mlxsw_sp *mlxsw_sp); + u32 (*buffsize_get)(int mtu, u32 speed); +}; + struct mlxsw_sp_span_entry { const struct net_device *to_dev; const struct mlxsw_sp_span_entry_ops *ops; @@ -81,5 +89,13 @@ mlxsw_sp_span_agent_unbind(struct mlxsw_sp *mlxsw_sp, enum mlxsw_sp_span_trigger trigger, struct mlxsw_sp_port *mlxsw_sp_port, const struct mlxsw_sp_span_trigger_parms *parms); +int mlxsw_sp_span_trigger_enable(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_sp_span_trigger trigger, u8 tc); +void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_sp_span_trigger trigger, u8 tc); + +extern const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops; +extern const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops; +extern const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops; #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c index 4ff1e623aa76..1e561132eb1e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c @@ -281,7 +281,7 @@ static int mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port, int err; err = mlxsw_core_port_init(mlxsw_sib->core, local_port, - module + 1, false, 0, + module + 1, false, 0, false, 0, mlxsw_sib->hw_id, sizeof(mlxsw_sib->hw_id)); if (err) { dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to init core port\n", diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index b438f5576e18..6f9a725662fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1107,7 +1107,7 @@ static int mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, int err; err = mlxsw_core_port_init(mlxsw_sx->core, local_port, - module + 1, false, 0, + module + 1, false, 0, false, 0, mlxsw_sx->hw_id, sizeof(mlxsw_sx->hw_id)); if (err) { dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n", diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e815aad8d85e..f2d94b026d88 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -309,18 +309,6 @@ static void ocelot_vlan_init(struct ocelot *ocelot) } } -/* Watermark encode - * Bit 8: Unit; 0:1, 1:16 - * Bit 7-0: Value to be multiplied with unit - */ -static u16 ocelot_wm_enc(u16 value) -{ - if (value >= BIT(8)) - return BIT(8) | (value / 16); - - return value; -} - void ocelot_adjust_link(struct ocelot *ocelot, int port, struct phy_device *phydev) { @@ -389,10 +377,8 @@ void ocelot_adjust_link(struct ocelot *ocelot, int port, ANA_PFC_PFC_CFG, port); /* Core: Enable port for frame transfer */ - ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE | - QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) | - QSYS_SWITCH_PORT_MODE_PORT_ENA, - QSYS_SWITCH_PORT_MODE, port); + ocelot_fields_write(ocelot, port, + QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); /* Flow control */ ocelot_write_rix(ocelot, SYS_MAC_FC_CFG_PAUSE_VAL_CFG(0xffff) | @@ -423,8 +409,7 @@ void ocelot_port_disable(struct ocelot *ocelot, int port) struct ocelot_port *ocelot_port = ocelot->ports[port]; ocelot_port_writel(ocelot_port, 0, DEV_MAC_ENA_CFG); - ocelot_rmw_rix(ocelot, 0, QSYS_SWITCH_PORT_MODE_PORT_ENA, - QSYS_SWITCH_PORT_MODE, port); + ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 0); } EXPORT_SYMBOL(ocelot_port_disable); @@ -1262,6 +1247,7 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) { struct ocelot_port *ocelot_port = ocelot->ports[port]; int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN; + int pause_start, pause_stop; int atop_wm; if (port == ocelot->npi) { @@ -1275,20 +1261,20 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) ocelot_port_writel(ocelot_port, maxlen, DEV_MAC_MAXLEN_CFG); - /* Set Pause WM hysteresis - * 152 = 6 * maxlen / OCELOT_BUFFER_CELL_SZ - * 101 = 4 * maxlen / OCELOT_BUFFER_CELL_SZ - */ - ocelot_write_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA | - SYS_PAUSE_CFG_PAUSE_STOP(101) | - SYS_PAUSE_CFG_PAUSE_START(152), SYS_PAUSE_CFG, port); + /* Set Pause watermark hysteresis */ + pause_start = 6 * maxlen / OCELOT_BUFFER_CELL_SZ; + pause_stop = 4 * maxlen / OCELOT_BUFFER_CELL_SZ; + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_START, + pause_start); + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_STOP, + pause_stop); /* Tail dropping watermark */ atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) / OCELOT_BUFFER_CELL_SZ; - ocelot_write_rix(ocelot, ocelot_wm_enc(9 * maxlen), + ocelot_write_rix(ocelot, ocelot->ops->wm_enc(9 * maxlen), SYS_ATOP, port); - ocelot_write(ocelot, ocelot_wm_enc(atop_wm), SYS_ATOP_TOT_CFG); + ocelot_write(ocelot, ocelot->ops->wm_enc(atop_wm), SYS_ATOP_TOT_CFG); } EXPORT_SYMBOL(ocelot_port_set_maxlen); @@ -1344,6 +1330,9 @@ void ocelot_init_port(struct ocelot *ocelot, int port) ocelot_port_writel(ocelot_port, 0, DEV_MAC_FC_MAC_HIGH_CFG); ocelot_port_writel(ocelot_port, 0, DEV_MAC_FC_MAC_LOW_CFG); + /* Enable transmission of pause frames */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 1); + /* Drop frames with multicast source address */ ocelot_rmw_gix(ocelot, ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA, ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA, @@ -1392,27 +1381,25 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi, QSYS_EXT_CPU_CFG); /* Enable NPI port */ - ocelot_write_rix(ocelot, - QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE | - QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) | - QSYS_SWITCH_PORT_MODE_PORT_ENA, - QSYS_SWITCH_PORT_MODE, npi); + ocelot_fields_write(ocelot, npi, + QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); /* NPI port Injection/Extraction configuration */ - ocelot_write_rix(ocelot, - SYS_PORT_MODE_INCL_XTR_HDR(extraction) | - SYS_PORT_MODE_INCL_INJ_HDR(injection), - SYS_PORT_MODE, npi); + ocelot_fields_write(ocelot, npi, SYS_PORT_MODE_INCL_XTR_HDR, + extraction); + ocelot_fields_write(ocelot, npi, SYS_PORT_MODE_INCL_INJ_HDR, + injection); + + /* Disable transmission of pause frames */ + ocelot_fields_write(ocelot, npi, SYS_PAUSE_CFG_PAUSE_ENA, 0); } /* Enable CPU port module */ - ocelot_write_rix(ocelot, QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE | - QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(1) | - QSYS_SWITCH_PORT_MODE_PORT_ENA, - QSYS_SWITCH_PORT_MODE, cpu); + ocelot_fields_write(ocelot, cpu, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); /* CPU port Injection/Extraction configuration */ - ocelot_write_rix(ocelot, SYS_PORT_MODE_INCL_XTR_HDR(extraction) | - SYS_PORT_MODE_INCL_INJ_HDR(injection), - SYS_PORT_MODE, cpu); + ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_XTR_HDR, + extraction); + ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_INJ_HDR, + injection); /* Configure the CPU port to be VLAN aware */ ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) | diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 394362e23c47..dc29e05103a1 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -102,11 +102,7 @@ void ocelot_port_lag_leave(struct ocelot *ocelot, int port, u32 ocelot_port_readl(struct ocelot_port *port, u32 reg); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg); -#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val)) -#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val)) - -int ocelot_probe_port(struct ocelot *ocelot, u8 port, - void __iomem *regs, +int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, struct phy_device *phy); void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu, @@ -117,7 +113,4 @@ extern struct notifier_block ocelot_netdevice_nb; extern struct notifier_block ocelot_switchdev_nb; extern struct notifier_block ocelot_switchdev_blocking_nb; -#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val)) -#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val)) - #endif diff --git a/drivers/net/ethernet/mscc/ocelot_io.c b/drivers/net/ethernet/mscc/ocelot_io.c index b229b1cb68ef..d22711282183 100644 --- a/drivers/net/ethernet/mscc/ocelot_io.c +++ b/drivers/net/ethernet/mscc/ocelot_io.c @@ -49,13 +49,25 @@ EXPORT_SYMBOL(__ocelot_rmw_ix); u32 ocelot_port_readl(struct ocelot_port *port, u32 reg) { - return readl(port->regs + reg); + struct ocelot *ocelot = port->ocelot; + u16 target = reg >> TARGET_OFFSET; + u32 val; + + WARN_ON(!target); + + regmap_read(port->target, ocelot->map[target][reg & REG_MASK], &val); + return val; } EXPORT_SYMBOL(ocelot_port_readl); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg) { - writel(val, port->regs + reg); + struct ocelot *ocelot = port->ocelot; + u16 target = reg >> TARGET_OFFSET; + + WARN_ON(!target); + + regmap_write(port->target, ocelot->map[target][reg & REG_MASK], val); } EXPORT_SYMBOL(ocelot_port_writel); @@ -77,6 +89,8 @@ int ocelot_regfields_init(struct ocelot *ocelot, regfield.reg = ocelot->map[target][reg & REG_MASK]; regfield.lsb = regfields[i].lsb; regfield.msb = regfields[i].msb; + regfield.id_size = regfields[i].id_size; + regfield.id_offset = regfields[i].id_offset; ocelot->regfields[i] = devm_regmap_field_alloc(ocelot->dev, diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 41a1b5f6df95..0668d23cdbfa 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1005,8 +1005,7 @@ struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = { .notifier_call = ocelot_switchdev_blocking_event, }; -int ocelot_probe_port(struct ocelot *ocelot, u8 port, - void __iomem *regs, +int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, struct phy_device *phy) { struct ocelot_port_private *priv; @@ -1024,7 +1023,7 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port, priv->chip_port = port; ocelot_port = &priv->port; ocelot_port->ocelot = ocelot; - ocelot_port->regs = regs; + ocelot_port->target = target; ocelot->ports[port] = ocelot_port; dev->netdev_ops = &ocelot_port_netdev_ops; diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 43716e8dc0ac..0ead1ef11c6c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -263,7 +263,49 @@ static const u32 ocelot_ptp_regmap[] = { REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), }; -static const u32 *ocelot_regmap[] = { +static const u32 ocelot_dev_gmii_regmap[] = { + REG(DEV_CLOCK_CFG, 0x0), + REG(DEV_PORT_MISC, 0x4), + REG(DEV_EVENTS, 0x8), + REG(DEV_EEE_CFG, 0xc), + REG(DEV_RX_PATH_DELAY, 0x10), + REG(DEV_TX_PATH_DELAY, 0x14), + REG(DEV_PTP_PREDICT_CFG, 0x18), + REG(DEV_MAC_ENA_CFG, 0x1c), + REG(DEV_MAC_MODE_CFG, 0x20), + REG(DEV_MAC_MAXLEN_CFG, 0x24), + REG(DEV_MAC_TAGS_CFG, 0x28), + REG(DEV_MAC_ADV_CHK_CFG, 0x2c), + REG(DEV_MAC_IFG_CFG, 0x30), + REG(DEV_MAC_HDX_CFG, 0x34), + REG(DEV_MAC_DBG_CFG, 0x38), + REG(DEV_MAC_FC_MAC_LOW_CFG, 0x3c), + REG(DEV_MAC_FC_MAC_HIGH_CFG, 0x40), + REG(DEV_MAC_STICKY, 0x44), + REG(PCS1G_CFG, 0x48), + REG(PCS1G_MODE_CFG, 0x4c), + REG(PCS1G_SD_CFG, 0x50), + REG(PCS1G_ANEG_CFG, 0x54), + REG(PCS1G_ANEG_NP_CFG, 0x58), + REG(PCS1G_LB_CFG, 0x5c), + REG(PCS1G_DBG_CFG, 0x60), + REG(PCS1G_CDET_CFG, 0x64), + REG(PCS1G_ANEG_STATUS, 0x68), + REG(PCS1G_ANEG_NP_STATUS, 0x6c), + REG(PCS1G_LINK_STATUS, 0x70), + REG(PCS1G_LINK_DOWN_CNT, 0x74), + REG(PCS1G_STICKY, 0x78), + REG(PCS1G_DEBUG_STATUS, 0x7c), + REG(PCS1G_LPI_CFG, 0x80), + REG(PCS1G_LPI_WAKE_ERROR_CNT, 0x84), + REG(PCS1G_LPI_STATUS, 0x88), + REG(PCS1G_TSTPAT_MODE_CFG, 0x8c), + REG(PCS1G_TSTPAT_STATUS, 0x90), + REG(DEV_PCS_FX100_CFG, 0x94), + REG(DEV_PCS_FX100_STATUS, 0x98), +}; + +static const u32 *ocelot_regmap[TARGET_MAX] = { [ANA] = ocelot_ana_regmap, [QS] = ocelot_qs_regmap, [QSYS] = ocelot_qsys_regmap, @@ -271,9 +313,10 @@ static const u32 *ocelot_regmap[] = { [SYS] = ocelot_sys_regmap, [S2] = ocelot_s2_regmap, [PTP] = ocelot_ptp_regmap, + [DEV_GMII] = ocelot_dev_gmii_regmap, }; -static const struct reg_field ocelot_regfields[] = { +static const struct reg_field ocelot_regfields[REGFIELD_MAX] = { [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 11, 11), [ANA_ADVLEARN_LEARN_MIRROR] = REG_FIELD(ANA_ADVLEARN, 0, 10), [ANA_ANEVENTS_MSTI_DROP] = REG_FIELD(ANA_ANEVENTS, 27, 27), @@ -315,6 +358,20 @@ static const struct reg_field ocelot_regfields[] = { [SYS_RESET_CFG_CORE_ENA] = REG_FIELD(SYS_RESET_CFG, 2, 2), [SYS_RESET_CFG_MEM_ENA] = REG_FIELD(SYS_RESET_CFG, 1, 1), [SYS_RESET_CFG_MEM_INIT] = REG_FIELD(SYS_RESET_CFG, 0, 0), + /* Replicated per number of ports (11), register size 4 per port */ + [QSYS_SWITCH_PORT_MODE_PORT_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 14, 14, 11, 4), + [QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 11, 13, 11, 4), + [QSYS_SWITCH_PORT_MODE_YEL_RSRVD] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 10, 10, 11, 4), + [QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 9, 9, 11, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_ENA] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 1, 8, 11, 4), + [QSYS_SWITCH_PORT_MODE_TX_PFC_MODE] = REG_FIELD_ID(QSYS_SWITCH_PORT_MODE, 0, 0, 11, 4), + [SYS_PORT_MODE_DATA_WO_TS] = REG_FIELD_ID(SYS_PORT_MODE, 5, 6, 11, 4), + [SYS_PORT_MODE_INCL_INJ_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 3, 4, 11, 4), + [SYS_PORT_MODE_INCL_XTR_HDR] = REG_FIELD_ID(SYS_PORT_MODE, 1, 2, 11, 4), + [SYS_PORT_MODE_INCL_HDR_ERR] = REG_FIELD_ID(SYS_PORT_MODE, 0, 0, 11, 4), + [SYS_PAUSE_CFG_PAUSE_START] = REG_FIELD_ID(SYS_PAUSE_CFG, 10, 18, 11, 4), + [SYS_PAUSE_CFG_PAUSE_STOP] = REG_FIELD_ID(SYS_PAUSE_CFG, 1, 9, 11, 4), + [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 11, 4), }; static const struct ocelot_stat_layout ocelot_stats_layout[] = { @@ -682,8 +739,21 @@ static int ocelot_reset(struct ocelot *ocelot) return 0; } +/* Watermark encode + * Bit 8: Unit; 0:1, 1:16 + * Bit 7-0: Value to be multiplied with unit + */ +static u16 ocelot_wm_enc(u16 value) +{ + if (value >= BIT(8)) + return BIT(8) | (value / 16); + + return value; +} + static const struct ocelot_ops ocelot_ops = { .reset = ocelot_reset, + .wm_enc = ocelot_wm_enc, }; static const struct vcap_field vsc7514_vcap_is2_keys[] = { @@ -948,9 +1018,9 @@ static int mscc_ocelot_probe(struct platform_device *pdev) struct device_node *phy_node; phy_interface_t phy_mode; struct phy_device *phy; + struct regmap *target; struct resource *res; struct phy *serdes; - void __iomem *regs; char res_name[8]; u32 port; @@ -961,8 +1031,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, res_name); - regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(regs)) + target = ocelot_regmap_init(ocelot, res); + if (IS_ERR(target)) continue; phy_node = of_parse_phandle(portnp, "phy-handle", 0); @@ -974,7 +1044,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) if (!phy) continue; - err = ocelot_probe_port(ocelot, port, regs, phy); + err = ocelot_probe_port(ocelot, port, target, phy); if (err) { of_node_put(portnp); goto out_put_ports; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 7f54a620acad..3bf9c1afa45e 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -458,7 +458,7 @@ void nfp_flower_qos_cleanup(struct nfp_app *app); int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev, struct tc_cls_matchall_offload *flow); void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb); -int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv, +int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 3af27bb5f4b0..4651fe417b7f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1646,7 +1646,7 @@ void nfp_flower_setup_indr_tc_release(void *cb_priv) } static int -nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, +nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct Qdisc *sch, struct nfp_app *app, struct flow_block_offload *f, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) { @@ -1680,7 +1680,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, block_cb = flow_indr_block_cb_alloc(nfp_flower_setup_indr_block_cb, cb_priv, cb_priv, nfp_flower_setup_indr_tc_release, - f, netdev, data, app, cleanup); + f, netdev, sch, data, app, cleanup); if (IS_ERR(block_cb)) { list_del(&cb_priv->list); kfree(cb_priv); @@ -1711,7 +1711,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, } int -nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv, +nfp_flower_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)) @@ -1721,7 +1721,7 @@ nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv, switch (type) { case TC_SETUP_BLOCK: - return nfp_flower_setup_indr_tc_block(netdev, cb_priv, + return nfp_flower_setup_indr_tc_block(netdev, sch, cb_priv, type_data, data, cleanup); default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 07dbf4d72227..be52510d446b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -70,9 +70,6 @@ nfp_devlink_port_split(struct devlink *devlink, unsigned int port_index, unsigned int lanes; int ret; - if (count < 2) - return -EINVAL; - mutex_lock(&pf->lock); rtnl_lock(); @@ -81,7 +78,7 @@ nfp_devlink_port_split(struct devlink *devlink, unsigned int port_index, if (ret) goto out; - if (eth_port.is_split || eth_port.port_lanes % count) { + if (eth_port.port_lanes % count) { ret = -EINVAL; goto out; } @@ -353,6 +350,7 @@ const struct devlink_ops nfp_devlink_ops = { int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) { + struct devlink_port_attrs attrs = {}; struct nfp_eth_table_port eth_port; struct devlink *devlink; const u8 *serial; @@ -365,10 +363,15 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) if (ret) return ret; + attrs.split = eth_port.is_split; + attrs.splittable = !attrs.split; + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = eth_port.label_port; + attrs.phys.split_subport_number = eth_port.label_subport; serial_len = nfp_cpp_serial(port->app->cpp, &serial); - devlink_port_attrs_set(&port->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - eth_port.label_port, eth_port.is_split, - eth_port.label_subport, serial, serial_len); + memcpy(attrs.switch_id.id, serial, serial_len); + attrs.switch_id.id_len = serial_len; + devlink_port_attrs_set(&port->dl_port, &attrs); devlink = priv_to_devlink(app->pf); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index 2d590e571133..c4f4fd469fe3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -69,6 +69,7 @@ void ionic_devlink_free(struct ionic *ionic) int ionic_devlink_register(struct ionic *ionic) { struct devlink *dl = priv_to_devlink(ionic); + struct devlink_port_attrs attrs = {}; int err; err = devlink_register(dl, ionic->dev); @@ -77,8 +78,8 @@ int ionic_devlink_register(struct ionic *ionic) return err; } - devlink_port_attrs_set(&ionic->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - 0, false, 0, NULL, 0); + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + devlink_port_attrs_set(&ionic->dl_port, &attrs); err = devlink_port_register(dl, &ionic->dl_port, 0); if (err) dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index f7e3ce3de04d..e03ea9b18f95 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -468,12 +468,18 @@ static void ionic_get_ringparam(struct net_device *netdev, ring->rx_pending = lif->nrxq_descs; } +static void ionic_set_ringsize(struct ionic_lif *lif, void *arg) +{ + struct ethtool_ringparam *ring = arg; + + lif->ntxq_descs = ring->tx_pending; + lif->nrxq_descs = ring->rx_pending; +} + static int ionic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { struct ionic_lif *lif = netdev_priv(netdev); - bool running; - int err; if (ring->rx_mini_pending || ring->rx_jumbo_pending) { netdev_info(netdev, "Changing jumbo or mini descriptors not supported\n"); @@ -491,22 +497,7 @@ static int ionic_set_ringparam(struct net_device *netdev, ring->rx_pending == lif->nrxq_descs) return 0; - err = ionic_wait_for_bit(lif, IONIC_LIF_F_QUEUE_RESET); - if (err) - return err; - - running = test_bit(IONIC_LIF_F_UP, lif->state); - if (running) - ionic_stop(netdev); - - lif->ntxq_descs = ring->tx_pending; - lif->nrxq_descs = ring->rx_pending; - - if (running) - ionic_open(netdev); - clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state); - - return 0; + return ionic_reset_queues(lif, ionic_set_ringsize, ring); } static void ionic_get_channels(struct net_device *netdev, @@ -521,12 +512,17 @@ static void ionic_get_channels(struct net_device *netdev, ch->combined_count = lif->nxqs; } +static void ionic_set_queuecount(struct ionic_lif *lif, void *arg) +{ + struct ethtool_channels *ch = arg; + + lif->nxqs = ch->combined_count; +} + static int ionic_set_channels(struct net_device *netdev, struct ethtool_channels *ch) { struct ionic_lif *lif = netdev_priv(netdev); - bool running; - int err; if (!ch->combined_count || ch->other_count || ch->rx_count || ch->tx_count) @@ -535,21 +531,7 @@ static int ionic_set_channels(struct net_device *netdev, if (ch->combined_count == lif->nxqs) return 0; - err = ionic_wait_for_bit(lif, IONIC_LIF_F_QUEUE_RESET); - if (err) - return err; - - running = test_bit(IONIC_LIF_F_UP, lif->state); - if (running) - ionic_stop(netdev); - - lif->nxqs = ch->combined_count; - - if (running) - ionic_open(netdev); - clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state); - - return 0; + return ionic_reset_queues(lif, ionic_set_queuecount, ch); } static u32 ionic_get_priv_flags(struct net_device *netdev) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index aaa00edd9d5b..f49486b6d04d 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1313,7 +1313,7 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) return err; netdev->mtu = new_mtu; - err = ionic_reset_queues(lif); + err = ionic_reset_queues(lif, NULL, NULL); return err; } @@ -1325,7 +1325,7 @@ static void ionic_tx_timeout_work(struct work_struct *ws) netdev_info(lif->netdev, "Tx Timeout recovery\n"); rtnl_lock(); - ionic_reset_queues(lif); + ionic_reset_queues(lif, NULL, NULL); rtnl_unlock(); } @@ -1673,6 +1673,14 @@ int ionic_open(struct net_device *netdev) if (err) goto err_out; + err = netif_set_real_num_tx_queues(netdev, lif->nxqs); + if (err) + goto err_txrx_deinit; + + err = netif_set_real_num_rx_queues(netdev, lif->nxqs); + if (err) + goto err_txrx_deinit; + /* don't start the queues until we have link */ if (netif_carrier_ok(netdev)) { err = ionic_start_queues(lif); @@ -1980,7 +1988,7 @@ static const struct net_device_ops ionic_netdev_ops = { .ndo_get_vf_stats = ionic_get_vf_stats, }; -int ionic_reset_queues(struct ionic_lif *lif) +int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) { bool running; int err = 0; @@ -1993,12 +2001,19 @@ int ionic_reset_queues(struct ionic_lif *lif) if (running) { netif_device_detach(lif->netdev); err = ionic_stop(lif->netdev); + if (err) + goto reset_out; } - if (!err && running) { - ionic_open(lif->netdev); + + if (cb) + cb(lif, arg); + + if (running) { + err = ionic_open(lif->netdev); netif_device_attach(lif->netdev); } +reset_out: clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state); return err; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index c3428034a17b..ed126dd74e01 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -248,6 +248,8 @@ static inline u32 ionic_coal_hw_to_usec(struct ionic *ionic, u32 units) return (units * div) / mult; } +typedef void (*ionic_reset_cb)(struct ionic_lif *lif, void *arg); + void ionic_link_status_check_request(struct ionic_lif *lif); void ionic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *ns); @@ -267,7 +269,7 @@ int ionic_lif_rss_config(struct ionic_lif *lif, u16 types, int ionic_open(struct net_device *netdev); int ionic_stop(struct net_device *netdev); -int ionic_reset_queues(struct ionic_lif *lif); +int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg); static inline void debug_stats_txq_post(struct ionic_qcq *qcq, struct ionic_txq_desc *desc, bool dbell) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 68fe745c9b99..ced805399e4f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -850,6 +850,8 @@ struct qed_dev { struct qed_dbg_feature dbg_features[DBG_FEATURE_NUM]; u8 engine_for_debug; bool disable_ilt_dump; + bool dbg_bin_dump; + DECLARE_HASHTABLE(connections, 10); const struct firmware *firmware; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 41ab23712bbd..6ab3e60d4928 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -7517,6 +7517,12 @@ static enum dbg_status format_feature(struct qed_hwfn *p_hwfn, if (p_hwfn->cdev->print_dbg_data) qed_dbg_print_feature(text_buf, text_size_bytes); + /* Just return the original binary buffer if requested */ + if (p_hwfn->cdev->dbg_bin_dump) { + vfree(text_buf); + return DBG_STATUS_OK; + } + /* Free the old dump_buf and point the dump_buf to the newly allocagted * and formatted text buffer. */ @@ -7742,7 +7748,9 @@ int qed_dbg_mcp_trace_size(struct qed_dev *cdev) #define REGDUMP_HEADER_SIZE_SHIFT 0 #define REGDUMP_HEADER_SIZE_MASK 0xffffff #define REGDUMP_HEADER_FEATURE_SHIFT 24 -#define REGDUMP_HEADER_FEATURE_MASK 0x3f +#define REGDUMP_HEADER_FEATURE_MASK 0x1f +#define REGDUMP_HEADER_BIN_DUMP_SHIFT 29 +#define REGDUMP_HEADER_BIN_DUMP_MASK 0x1 #define REGDUMP_HEADER_OMIT_ENGINE_SHIFT 30 #define REGDUMP_HEADER_OMIT_ENGINE_MASK 0x1 #define REGDUMP_HEADER_ENGINE_SHIFT 31 @@ -7780,6 +7788,7 @@ static u32 qed_calc_regdump_header(struct qed_dev *cdev, feature, feature_size); SET_FIELD(res, REGDUMP_HEADER_FEATURE, feature); + SET_FIELD(res, REGDUMP_HEADER_BIN_DUMP, 1); SET_FIELD(res, REGDUMP_HEADER_OMIT_ENGINE, omit_engine); SET_FIELD(res, REGDUMP_HEADER_ENGINE, engine); @@ -7803,6 +7812,7 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) omit_engine = 1; mutex_lock(&qed_dbg_lock); + cdev->dbg_bin_dump = true; org_engine = qed_get_debug_engine(cdev); for (cur_engine = 0; cur_engine < cdev->num_hwfns; cur_engine++) { @@ -7940,6 +7950,10 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) DP_ERR(cdev, "qed_dbg_mcp_trace failed. rc = %d\n", rc); } + /* Re-populate nvm attribute info */ + qed_mcp_nvm_info_free(p_hwfn); + qed_mcp_nvm_info_populate(p_hwfn); + /* nvm cfg1 */ rc = qed_dbg_nvm_image(cdev, (u8 *)buffer + offset + @@ -8002,6 +8016,7 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) QED_NVM_IMAGE_MDUMP, "QED_NVM_IMAGE_MDUMP", rc); } + cdev->dbg_bin_dump = false; mutex_unlock(&qed_dbg_lock); return 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 74142896b707..491a6dbb5d73 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -4446,12 +4446,6 @@ static int qed_get_dev_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return 0; } -static void qed_nvm_info_free(struct qed_hwfn *p_hwfn) -{ - kfree(p_hwfn->nvm_info.image_att); - p_hwfn->nvm_info.image_att = NULL; -} - static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn, void __iomem *p_regview, void __iomem *p_doorbells, @@ -4536,7 +4530,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn, return rc; err3: if (IS_LEAD_HWFN(p_hwfn)) - qed_nvm_info_free(p_hwfn); + qed_mcp_nvm_info_free(p_hwfn); err2: if (IS_LEAD_HWFN(p_hwfn)) qed_iov_free_hw_info(p_hwfn->cdev); @@ -4597,7 +4591,7 @@ int qed_hw_prepare(struct qed_dev *cdev, if (rc) { if (IS_PF(cdev)) { qed_init_free(p_hwfn); - qed_nvm_info_free(p_hwfn); + qed_mcp_nvm_info_free(p_hwfn); qed_mcp_free(p_hwfn); qed_hw_hwfn_free(p_hwfn); } @@ -4631,7 +4625,7 @@ void qed_hw_remove(struct qed_dev *cdev) qed_iov_free_hw_info(cdev); - qed_nvm_info_free(p_hwfn); + qed_mcp_nvm_info_free(p_hwfn); } static void qed_chain_free_next_ptr(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 25433d162a54..2d12bb27560c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3254,6 +3254,13 @@ err0: return rc; } +void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn) +{ + kfree(p_hwfn->nvm_info.image_att); + p_hwfn->nvm_info.image_att = NULL; + p_hwfn->nvm_info.valid = false; +} + int qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, enum qed_nvm_images image_id, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index d77b4c262cff..63a22a615e94 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -1195,6 +1195,13 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn); /** + * @brief Delete nvm info shadow in the given hardware function + * + * @param p_hwfn + */ +void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn); + +/** * @brief Get the engine affinity configuration. * * @param p_hwfn diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 40efe60eff8d..fcdecddb2812 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -47,15 +47,23 @@ static int rmnet_unregister_real_device(struct net_device *real_dev) return 0; } -static int rmnet_register_real_device(struct net_device *real_dev) +static int rmnet_register_real_device(struct net_device *real_dev, + struct netlink_ext_ack *extack) { struct rmnet_port *port; int rc, entry; ASSERT_RTNL(); - if (rmnet_is_real_dev_registered(real_dev)) + if (rmnet_is_real_dev_registered(real_dev)) { + port = rmnet_get_port_rtnl(real_dev); + if (port->rmnet_mode != RMNET_EPMODE_VND) { + NL_SET_ERR_MSG_MOD(extack, "bridge device already exists"); + return -EINVAL; + } + return 0; + } port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) @@ -133,7 +141,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]); - err = rmnet_register_real_device(real_dev); + err = rmnet_register_real_device(real_dev, extack); if (err) goto err0; @@ -422,7 +430,7 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, } if (port->rmnet_mode != RMNET_EPMODE_VND) { - NL_SET_ERR_MSG_MOD(extack, "bridge device already exists"); + NL_SET_ERR_MSG_MOD(extack, "more than one bridge dev attached"); return -EINVAL; } @@ -433,7 +441,7 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, return -EBUSY; } - err = rmnet_register_real_device(slave_dev); + err = rmnet_register_real_device(slave_dev, extack); if (err) return -EBUSY; diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 61ddee0c2a2e..d950b312c418 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1512,12 +1512,9 @@ static void epic_remove_one(struct pci_dev *pdev) /* pci_power_off(pdev, -1); */ } - -#ifdef CONFIG_PM - -static int epic_suspend (struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused epic_suspend(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(dev_d); struct epic_private *ep = netdev_priv(dev); void __iomem *ioaddr = ep->ioaddr; @@ -1531,9 +1528,9 @@ static int epic_suspend (struct pci_dev *pdev, pm_message_t state) } -static int epic_resume (struct pci_dev *pdev) +static int __maybe_unused epic_resume(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(dev_d); if (!netif_running(dev)) return 0; @@ -1542,18 +1539,14 @@ static int epic_resume (struct pci_dev *pdev) return 0; } -#endif /* CONFIG_PM */ - +static SIMPLE_DEV_PM_OPS(epic_pm_ops, epic_suspend, epic_resume); static struct pci_driver epic_driver = { .name = DRV_NAME, .id_table = epic_pci_tbl, .probe = epic_init_one, .remove = epic_remove_one, -#ifdef CONFIG_PM - .suspend = epic_suspend, - .resume = epic_resume, -#endif /* CONFIG_PM */ + .driver.pm = &epic_pm_ops, }; diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 7312e522c022..42bef04d65ba 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -1422,11 +1422,9 @@ out_0: return result; } -#ifdef CONFIG_PM - -static int smsc9420_suspend(struct pci_dev *pdev, pm_message_t state) +static int __maybe_unused smsc9420_suspend(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(dev_d); struct smsc9420_pdata *pd = netdev_priv(dev); u32 int_cfg; ulong flags; @@ -1451,34 +1449,21 @@ static int smsc9420_suspend(struct pci_dev *pdev, pm_message_t state) netif_device_detach(dev); } - pci_save_state(pdev); - pci_enable_wake(pdev, pci_choose_state(pdev, state), 0); - pci_disable_device(pdev); - pci_set_power_state(pdev, pci_choose_state(pdev, state)); + device_wakeup_disable(dev_d); return 0; } -static int smsc9420_resume(struct pci_dev *pdev) +static int __maybe_unused smsc9420_resume(struct device *dev_d) { - struct net_device *dev = pci_get_drvdata(pdev); - struct smsc9420_pdata *pd = netdev_priv(dev); + struct net_device *dev = dev_get_drvdata(dev_d); int err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - err = pci_enable_device(pdev); - if (err) - return err; + pci_set_master(to_pci_dev(dev_d)); - pci_set_master(pdev); - - err = pci_enable_wake(pdev, PCI_D0, 0); - if (err) - netif_warn(pd, ifup, pd->dev, "pci_enable_wake failed: %d\n", - err); + device_wakeup_disable(dev_d); + err = 0; if (netif_running(dev)) { /* FIXME: gross. It looks like ancient PM relic.*/ err = smsc9420_open(dev); @@ -1487,8 +1472,6 @@ static int smsc9420_resume(struct pci_dev *pdev) return err; } -#endif /* CONFIG_PM */ - static const struct net_device_ops smsc9420_netdev_ops = { .ndo_open = smsc9420_open, .ndo_stop = smsc9420_stop, @@ -1658,15 +1641,14 @@ static void smsc9420_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static SIMPLE_DEV_PM_OPS(smsc9420_pm_ops, smsc9420_suspend, smsc9420_resume); + static struct pci_driver smsc9420_driver = { .name = DRV_NAME, .id_table = smsc9420_id_table, .probe = smsc9420_probe, .remove = smsc9420_remove, -#ifdef CONFIG_PM - .suspend = smsc9420_suspend, - .resume = smsc9420_resume, -#endif /* CONFIG_PM */ + .driver.pm = &smsc9420_pm_ops, }; static int __init smsc9420_init_module(void) diff --git a/drivers/net/fddi/skfp/ess.c b/drivers/net/fddi/skfp/ess.c index a546eaf071f7..afd5ca39f43b 100644 --- a/drivers/net/fddi/skfp/ess.c +++ b/drivers/net/fddi/skfp/ess.c @@ -148,7 +148,7 @@ int ess_raf_received_pack(struct s_smc *smc, SMbuf *mb, struct smt_header *sm, DB_ESSN(2, "fc %x ft %x", sm->smt_class, sm->smt_type); DB_ESSN(2, "ver %x tran %x", sm->smt_version, sm->smt_tid); - DB_ESSN(2, "stn_id %s", addr_to_string(&sm->smt_source)); + DB_ESSN(2, "stn_id %pM", &sm->smt_source); DB_ESSN(2, "infolen %x res %lx", sm->smt_len, msg_res_type); DB_ESSN(2, "sbacmd %x", cmd->sba_cmd); @@ -308,8 +308,8 @@ int ess_raf_received_pack(struct s_smc *smc, SMbuf *mb, struct smt_header *sm, p = (void *) sm_to_para(smc,sm,SMT_P3210) ; overhead = ((struct smt_p_3210 *)p)->mib_overhead ; - DB_ESSN(2, "ESS: Change Request from %s", - addr_to_string(&sm->smt_source)); + DB_ESSN(2, "ESS: Change Request from %pM", + &sm->smt_source); DB_ESSN(2, "payload= %lx overhead= %lx", payload, overhead); @@ -339,8 +339,8 @@ int ess_raf_received_pack(struct s_smc *smc, SMbuf *mb, struct smt_header *sm, return fs; } - DB_ESSN(2, "ESS: Report Request from %s", - addr_to_string(&sm->smt_source)); + DB_ESSN(2, "ESS: Report Request from %pM", + &sm->smt_source); /* * verify that the resource type is sync bw only diff --git a/drivers/net/fddi/skfp/h/cmtdef.h b/drivers/net/fddi/skfp/h/cmtdef.h index 3a1ceb7cb8d2..4dd590d65d76 100644 --- a/drivers/net/fddi/skfp/h/cmtdef.h +++ b/drivers/net/fddi/skfp/h/cmtdef.h @@ -640,7 +640,6 @@ void dump_smt(struct s_smc *smc, struct smt_header *sm, char *text); #define dump_smt(smc,sm,text) #endif -char* addr_to_string(struct fddi_addr *addr); #ifdef DEBUG void dump_hex(char *p, int len); #endif diff --git a/drivers/net/fddi/skfp/smt.c b/drivers/net/fddi/skfp/smt.c index 47c48202a68c..b8c59d803ce6 100644 --- a/drivers/net/fddi/skfp/smt.c +++ b/drivers/net/fddi/skfp/smt.c @@ -520,8 +520,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) * ignore any packet with NSA and A-indicator set */ if ( (fs & A_INDICATOR) && m_fc(mb) == FC_SMT_NSA) { - DB_SMT("SMT : ignoring NSA with A-indicator set from %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT : ignoring NSA with A-indicator set from %pM", + &sm->smt_source); smt_free_mbuf(smc,mb) ; return ; } @@ -552,8 +552,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) break ; } if (illegal) { - DB_SMT("SMT : version = %d, dest = %s", - sm->smt_version, addr_to_string(&sm->smt_source)); + DB_SMT("SMT : version = %d, dest = %pM", + sm->smt_version, &sm->smt_source); smt_send_rdf(smc,mb,m_fc(mb),SMT_RDF_VERSION,local) ; smt_free_mbuf(smc,mb) ; return ; @@ -582,8 +582,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) if (!is_equal( &smc->mib.m[MAC0].fddiMACUpstreamNbr, &sm->smt_source)) { - DB_SMT("SMT : updated my UNA = %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT : updated my UNA = %pM", + &sm->smt_source); if (!is_equal(&smc->mib.m[MAC0]. fddiMACUpstreamNbr,&SMT_Unknown)){ /* Do not update unknown address */ @@ -612,8 +612,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) is_individual(&sm->smt_source) && ((!(fs & A_INDICATOR) && m_fc(mb) == FC_SMT_NSA) || (m_fc(mb) != FC_SMT_NSA))) { - DB_SMT("SMT : replying to NIF request %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT : replying to NIF request %pM", + &sm->smt_source); smt_send_nif(smc,&sm->smt_source, FC_SMT_INFO, sm->smt_tid, @@ -621,8 +621,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) } break ; case SMT_REPLY : - DB_SMT("SMT : received NIF response from %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT : received NIF response from %pM", + &sm->smt_source); if (fs & A_INDICATOR) { smc->sm.pend[SMT_TID_NIF] = 0 ; DB_SMT("SMT : duplicate address"); @@ -682,23 +682,23 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) case SMT_SIF_CONFIG : /* station information */ if (sm->smt_type != SMT_REQUEST) break ; - DB_SMT("SMT : replying to SIF Config request from %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT : replying to SIF Config request from %pM", + &sm->smt_source); smt_send_sif_config(smc,&sm->smt_source,sm->smt_tid,local) ; break ; case SMT_SIF_OPER : /* station information */ if (sm->smt_type != SMT_REQUEST) break ; - DB_SMT("SMT : replying to SIF Operation request from %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT : replying to SIF Operation request from %pM", + &sm->smt_source); smt_send_sif_operation(smc,&sm->smt_source,sm->smt_tid,local) ; break ; case SMT_ECF : /* echo frame */ switch (sm->smt_type) { case SMT_REPLY : smc->mib.priv.fddiPRIVECF_Reply_Rx++ ; - DB_SMT("SMT: received ECF reply from %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT: received ECF reply from %pM", + &sm->smt_source); if (sm_to_para(smc,sm,SMT_P_ECHODATA) == NULL) { DB_SMT("SMT: ECHODATA missing"); break ; @@ -727,8 +727,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) local) ; break ; } - DB_SMT("SMT - sending ECF reply to %s", - addr_to_string(&sm->smt_source)); + DB_SMT("SMT - sending ECF reply to %pM", + &sm->smt_source); /* set destination addr. & reply */ sm->smt_dest = sm->smt_source ; @@ -794,8 +794,8 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs) * we need to send a RDF frame according to 8.1.3.1.1, * only if it is a REQUEST. */ - DB_SMT("SMT : class = %d, send RDF to %s", - sm->smt_class, addr_to_string(&sm->smt_source)); + DB_SMT("SMT : class = %d, send RDF to %pM", + sm->smt_class, &sm->smt_source); smt_send_rdf(smc,mb,m_fc(mb),SMT_RDF_CLASS,local) ; break ; @@ -864,8 +864,8 @@ static void smt_send_rdf(struct s_smc *smc, SMbuf *rej, int fc, int reason, if (sm->smt_type != SMT_REQUEST) return ; - DB_SMT("SMT: sending RDF to %s,reason = 0x%x", - addr_to_string(&sm->smt_source), reason); + DB_SMT("SMT: sending RDF to %pM,reason = 0x%x", + &sm->smt_source, reason); /* @@ -1715,22 +1715,6 @@ void fddi_send_antc(struct s_smc *smc, struct fddi_addr *dest) } #endif -#ifdef DEBUG -char *addr_to_string(struct fddi_addr *addr) -{ - int i ; - static char string[6*3] = "****" ; - - for (i = 0 ; i < 6 ; i++) { - string[i * 3] = hex_asc_hi(addr->a[i]); - string[i * 3 + 1] = hex_asc_lo(addr->a[i]); - string[i * 3 + 2] = ':'; - } - string[5 * 3 + 2] = 0; - return string; -} -#endif - /* * return static mac index */ diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index e3d074008da2..49b00def2eef 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1796,9 +1796,11 @@ static int geneve_netdevice_event(struct notifier_block *unused, event == NETDEV_UDP_TUNNEL_DROP_INFO) { geneve_offload_rx_ports(dev, event == NETDEV_UDP_TUNNEL_PUSH_INFO); } else if (event == NETDEV_UNREGISTER) { - geneve_offload_rx_ports(dev, false); + if (!dev->udp_tunnel_nic_info) + geneve_offload_rx_ports(dev, false); } else if (event == NETDEV_REGISTER) { - geneve_offload_rx_ports(dev, true); + if (!dev->udp_tunnel_nic_info) + geneve_offload_rx_ports(dev, true); } return NOTIFY_DONE; diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index c84b8d92caa9..0e63d35320aa 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -508,6 +508,13 @@ static int gsi_channel_stop_command(struct gsi_channel *channel) int ret; state = gsi_channel_state(channel); + + /* Channel could have entered STOPPED state since last call + * if it timed out. If so, we're done. + */ + if (state == GSI_CHANNEL_STATE_STOPPED) + return 0; + if (state != GSI_CHANNEL_STATE_STARTED && state != GSI_CHANNEL_STATE_STOP_IN_PROC) { dev_err(dev, "bad channel state %u before stop\n", state); @@ -796,20 +803,11 @@ int gsi_channel_start(struct gsi *gsi, u32 channel_id) int gsi_channel_stop(struct gsi *gsi, u32 channel_id) { struct gsi_channel *channel = &gsi->channel[channel_id]; - enum gsi_channel_state state; u32 retries; int ret; gsi_channel_freeze(channel); - /* Channel could have entered STOPPED state since last call if the - * STOP command timed out. We won't stop a channel if stopping it - * was successful previously (so we still want the freeze above). - */ - state = gsi_channel_state(channel); - if (state == GSI_CHANNEL_STATE_STOPPED) - return 0; - /* RX channels might require a little time to enter STOPPED state */ retries = channel->toward_ipa ? 0 : GSI_CHANNEL_STOP_RX_RETRIES; @@ -1365,7 +1363,7 @@ static void gsi_channel_update(struct gsi_channel *channel) * gsi_channel_poll_one() - Return a single completed transaction on a channel * @channel: Channel to be polled * - * @Return: Transaction pointer, or null if none are available + * Return: Transaction pointer, or null if none are available * * This function returns the first entry on a channel's completed transaction * list. If that list is empty, the hardware is consulted to determine @@ -1395,8 +1393,8 @@ static struct gsi_trans *gsi_channel_poll_one(struct gsi_channel *channel) * gsi_channel_poll() - NAPI poll function for a channel * @napi: NAPI structure for the channel * @budget: Budget supplied by NAPI core - - * @Return: Number of items polled (<= budget) + * + * Return: Number of items polled (<= budget) * * Single transactions completed by hardware are polled until either * the budget is exhausted, or there are no more. Each transaction diff --git a/drivers/net/ipa/gsi.h b/drivers/net/ipa/gsi.h index 90a02194e7ad..061312773df0 100644 --- a/drivers/net/ipa/gsi.h +++ b/drivers/net/ipa/gsi.h @@ -167,7 +167,7 @@ struct gsi { * @gsi: Address of GSI structure embedded in an IPA structure * @legacy: Set up for legacy hardware * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code * * Performs initialization that must wait until the GSI hardware is * ready (including firmware loaded). @@ -185,7 +185,7 @@ void gsi_teardown(struct gsi *gsi); * @gsi: GSI pointer * @channel_id: Channel whose limit is to be returned * - * @Return: The maximum number of TREs oustanding on the channel + * Return: The maximum number of TREs oustanding on the channel */ u32 gsi_channel_tre_max(struct gsi *gsi, u32 channel_id); @@ -194,7 +194,7 @@ u32 gsi_channel_tre_max(struct gsi *gsi, u32 channel_id); * @gsi: GSI pointer * @channel_id: Channel whose limit is to be returned * - * @Return: The maximum TRE count per transaction on the channel + * Return: The maximum TRE count per transaction on the channel */ u32 gsi_channel_trans_tre_max(struct gsi *gsi, u32 channel_id); @@ -203,7 +203,7 @@ u32 gsi_channel_trans_tre_max(struct gsi *gsi, u32 channel_id); * @gsi: GSI pointer * @channel_id: Channel to start * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ int gsi_channel_start(struct gsi *gsi, u32 channel_id); @@ -212,7 +212,7 @@ int gsi_channel_start(struct gsi *gsi, u32 channel_id); * @gsi: GSI pointer returned by gsi_setup() * @channel_id: Channel to stop * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ int gsi_channel_stop(struct gsi *gsi, u32 channel_id); @@ -238,7 +238,7 @@ int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start); * @gsi: Address of GSI structure embedded in an IPA structure * @pdev: IPA platform device * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code * * Early stage initialization of the GSI subsystem, performing tasks * that can be done before the GSI hardware is ready to use. diff --git a/drivers/net/ipa/gsi_private.h b/drivers/net/ipa/gsi_private.h index b57d0198ebc1..1785c9d3344d 100644 --- a/drivers/net/ipa/gsi_private.h +++ b/drivers/net/ipa/gsi_private.h @@ -44,7 +44,7 @@ void gsi_trans_complete(struct gsi_trans *trans); * @channel: Channel associated with the transaction * @index: Index of the TRE having a transaction * - * @Return: The GSI transaction pointer associated with the TRE index + * Return: The GSI transaction pointer associated with the TRE index */ struct gsi_trans *gsi_channel_trans_mapped(struct gsi_channel *channel, u32 index); @@ -53,7 +53,7 @@ struct gsi_trans *gsi_channel_trans_mapped(struct gsi_channel *channel, * gsi_channel_trans_complete() - Return a channel's next completed transaction * @channel: Channel whose next transaction is to be returned * - * @Return: The next completed transaction, or NULL if nothing new + * Return: The next completed transaction, or NULL if nothing new */ struct gsi_trans *gsi_channel_trans_complete(struct gsi_channel *channel); @@ -76,7 +76,7 @@ void gsi_channel_trans_cancel_pending(struct gsi_channel *channel); * @gsi: GSI pointer * @channel_id: Channel number * - * @Return: 0 if successful, or -ENOMEM on allocation failure + * Return: 0 if successful, or -ENOMEM on allocation failure * * Creates and sets up information for managing transactions on a channel */ diff --git a/drivers/net/ipa/gsi_trans.h b/drivers/net/ipa/gsi_trans.h index 1477fc15b30a..4d4606b5fa95 100644 --- a/drivers/net/ipa/gsi_trans.h +++ b/drivers/net/ipa/gsi_trans.h @@ -75,7 +75,7 @@ struct gsi_trans { * @count: Minimum number of elements in the pool * @max_alloc: Maximum number of elements allocated at a time from pool * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ int gsi_trans_pool_init(struct gsi_trans_pool *pool, size_t size, u32 count, u32 max_alloc); @@ -85,7 +85,7 @@ int gsi_trans_pool_init(struct gsi_trans_pool *pool, size_t size, u32 count, * @pool: Pool pointer * @count: Number of elements to allocate from the pool * - * @Return: Virtual address of element(s) allocated from the pool + * Return: Virtual address of element(s) allocated from the pool */ void *gsi_trans_pool_alloc(struct gsi_trans_pool *pool, u32 count); @@ -103,7 +103,7 @@ void gsi_trans_pool_exit(struct gsi_trans_pool *pool); * @count: Minimum number of elements in the pool * @max_alloc: Maximum number of elements allocated at a time from pool * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code * * Structures in this pool reside in DMA-coherent memory. */ @@ -115,7 +115,7 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, * @pool: DMA pool pointer * @addr: DMA address "handle" associated with the allocation * - * @Return: Virtual address of element allocated from the pool + * Return: Virtual address of element allocated from the pool * * Only one element at a time may be allocated from a DMA pool. */ @@ -134,7 +134,7 @@ void gsi_trans_pool_exit_dma(struct device *dev, struct gsi_trans_pool *pool); * @tre_count: Number of elements in the transaction * @direction: DMA direction for entire SGL (or DMA_NONE) * - * @Return: A GSI transaction structure, or a null pointer if all + * Return: A GSI transaction structure, or a null pointer if all * available transactions are in use */ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, @@ -175,7 +175,7 @@ int gsi_trans_page_add(struct gsi_trans *trans, struct page *page, u32 size, * @trans: Transaction * @skb: Socket buffer for transfer (outbound) * - * @Return: 0, or -EMSGSIZE if socket data won't fit in transaction. + * Return: 0, or -EMSGSIZE if socket data won't fit in transaction. */ int gsi_trans_skb_add(struct gsi_trans *trans, struct sk_buff *skb); diff --git a/drivers/net/ipa/ipa_clock.c b/drivers/net/ipa/ipa_clock.c index 0fbc8b1bdf41..398f2e47043d 100644 --- a/drivers/net/ipa/ipa_clock.c +++ b/drivers/net/ipa/ipa_clock.c @@ -44,7 +44,7 @@ /** * struct ipa_clock - IPA clocking information * @count: Clocking reference count - * @mutex; Protects clock enable/disable + * @mutex: Protects clock enable/disable * @core: IPA core clock * @memory_path: Memory interconnect * @imem_path: Internal memory interconnect diff --git a/drivers/net/ipa/ipa_clock.h b/drivers/net/ipa/ipa_clock.h index 0f4e2877a6df..1d70f1de3875 100644 --- a/drivers/net/ipa/ipa_clock.h +++ b/drivers/net/ipa/ipa_clock.h @@ -22,7 +22,7 @@ u32 ipa_clock_rate(struct ipa *ipa); * ipa_clock_init() - Initialize IPA clocking * @dev: IPA device * - * @Return: A pointer to an ipa_clock structure, or a pointer-coded error + * Return: A pointer to an ipa_clock structure, or a pointer-coded error */ struct ipa_clock *ipa_clock_init(struct device *dev); diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index c9ab865e7290..d92dd3f09b73 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -586,6 +586,21 @@ u32 ipa_cmd_tag_process_count(void) return 4; } +void ipa_cmd_tag_process(struct ipa *ipa) +{ + u32 count = ipa_cmd_tag_process_count(); + struct gsi_trans *trans; + + trans = ipa_cmd_trans_alloc(ipa, count); + if (trans) { + ipa_cmd_tag_process_add(trans); + gsi_trans_commit_wait(trans); + } else { + dev_err(&ipa->pdev->dev, + "error allocating %u entry tag transaction\n", count); + } +} + static struct ipa_cmd_info * ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count) { diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h index e440aa69c8b5..f7e6f87facf7 100644 --- a/drivers/net/ipa/ipa_cmd.h +++ b/drivers/net/ipa/ipa_cmd.h @@ -61,7 +61,7 @@ struct ipa_cmd_info { * @ipv6: - Whether the table is for IPv6 or IPv4 * @hashed: - Whether the table is hashed or non-hashed * - * @Return: true if region is valid, false otherwise + * Return: true if region is valid, false otherwise */ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem, bool route, bool ipv6, bool hashed); @@ -70,7 +70,7 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem, * ipa_cmd_data_valid() - Validate command-realted configuration is valid * @ipa: - IPA pointer * - * @Return: true if assumptions required for command are valid + * Return: true if assumptions required for command are valid */ bool ipa_cmd_data_valid(struct ipa *ipa); @@ -95,7 +95,7 @@ static inline bool ipa_cmd_data_valid(struct ipa *ipa) * @channel: AP->IPA command TX GSI channel pointer * @tre_count: Number of pool elements to allocate * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ int ipa_cmd_pool_init(struct gsi_channel *gsi_channel, u32 tre_count); @@ -166,17 +166,25 @@ void ipa_cmd_tag_process_add(struct gsi_trans *trans); /** * ipa_cmd_tag_process_add_count() - Number of commands in a tag process * - * @Return: The number of elements to allocate in a transaction + * Return: The number of elements to allocate in a transaction * to hold tag process commands */ u32 ipa_cmd_tag_process_count(void); /** + * ipa_cmd_tag_process() - Perform a tag process + * + * @Return: The number of elements to allocate in a transaction + * to hold tag process commands + */ +void ipa_cmd_tag_process(struct ipa *ipa); + +/** * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint * @ipa: IPA pointer * @tre_count: Number of elements in the transaction * - * @Return: A GSI transaction structure, or a null pointer if all + * Return: A GSI transaction structure, or a null pointer if all * available transactions are in use */ struct gsi_trans *ipa_cmd_trans_alloc(struct ipa *ipa, u32 tre_count); diff --git a/drivers/net/ipa/ipa_data-sdm845.c b/drivers/net/ipa/ipa_data-sdm845.c index 52d4b84e0dac..de2768d71ab5 100644 --- a/drivers/net/ipa/ipa_data-sdm845.c +++ b/drivers/net/ipa/ipa_data-sdm845.c @@ -44,7 +44,6 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_INVALID, .config = { - .checksum = true, .aggregation = true, .status_enable = true, .rx = { diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index d4be12385bcc..b7efd7c95e9c 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -349,7 +349,7 @@ static void ipa_endpoint_force_close(struct ipa_endpoint *endpoint) /** * ipa_endpoint_suspend_aggr() - Emulate suspend interrupt - * @endpoint_id: Endpoint on which to emulate a suspend + * @endpoint: Endpoint on which to emulate a suspend * * Emulate suspend IPA interrupt to unsuspend an endpoint suspended * with an open aggregation frame. This is to work around a hardware @@ -499,6 +499,9 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) } /** + * ipa_endpoint_init_hdr() - Initialize HDR endpoint configuration register + * @endpoint: Endpoint pointer + * * We program QMAP endpoints so each packet received is preceded by a QMAP * header structure. The QMAP header contains a 1-byte mux_id and 2-byte * packet size field, and we have the IPA hardware populate both for each @@ -921,6 +924,8 @@ err_free_pages: /** * ipa_endpoint_replenish() - Replenish the Rx packets cache. + * @endpoint: Endpoint to be replenished + * @count: Number of buffers to send to hardware * * Allocate RX packet wrapper structures with maximal socket buffers * for an endpoint. These are supplied to the hardware, which fills @@ -1231,7 +1236,7 @@ void ipa_endpoint_default_route_clear(struct ipa *ipa) * on its underlying GSI channel, a special sequence of actions must be * taken to ensure the IPA pipeline is properly cleared. * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ static int ipa_endpoint_reset_rx_aggr(struct ipa_endpoint *endpoint) { @@ -1469,6 +1474,8 @@ void ipa_endpoint_suspend(struct ipa *ipa) if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); + ipa_cmd_tag_process(ipa); + ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]); ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]); } diff --git a/drivers/net/ipa/ipa_gsi.c b/drivers/net/ipa/ipa_gsi.c index dc4a5c2196ae..d323adb03383 100644 --- a/drivers/net/ipa/ipa_gsi.c +++ b/drivers/net/ipa/ipa_gsi.c @@ -6,6 +6,7 @@ #include <linux/types.h> +#include "ipa_gsi.h" #include "gsi_trans.h" #include "ipa.h" #include "ipa_endpoint.h" diff --git a/drivers/net/ipa/ipa_gsi.h b/drivers/net/ipa/ipa_gsi.h index 3cf18600c68e..c02cb6f3a2e1 100644 --- a/drivers/net/ipa/ipa_gsi.h +++ b/drivers/net/ipa/ipa_gsi.h @@ -8,7 +8,9 @@ #include <linux/types.h> +struct gsi; struct gsi_trans; +struct ipa_gsi_endpoint_data; /** * ipa_gsi_trans_complete() - GSI transaction completion callback @@ -41,9 +43,9 @@ void ipa_gsi_trans_release(struct gsi_trans *trans); */ void ipa_gsi_channel_tx_queued(struct gsi *gsi, u32 channel_id, u32 count, u32 byte_count); + /** - * ipa_gsi_trans_complete() - GSI transaction completion callback -ipa_gsi_channel_tx_completed() + * ipa_gsi_channel_tx_completed() - GSI transaction completion callback * @gsi: GSI pointer * @channel_id: Channel number * @count: Number of transactions completed since last report @@ -55,6 +57,15 @@ ipa_gsi_channel_tx_completed() void ipa_gsi_channel_tx_completed(struct gsi *gsi, u32 channel_id, u32 count, u32 byte_count); +/* ipa_gsi_endpoint_data_empty() - Empty endpoint config data test + * @data: endpoint configuration data + * + * Determines whether an endpoint configuration data entry is empty, + * meaning it contains no valid configuration information and should + * be ignored. + * + * Return: true if empty; false otherwise + */ bool ipa_gsi_endpoint_data_empty(const struct ipa_gsi_endpoint_data *data); #endif /* _IPA_GSI_TRANS_H_ */ diff --git a/drivers/net/ipa/ipa_interrupt.h b/drivers/net/ipa/ipa_interrupt.h index d4f4c1c9f0b1..727e9c5044d1 100644 --- a/drivers/net/ipa/ipa_interrupt.h +++ b/drivers/net/ipa/ipa_interrupt.h @@ -104,7 +104,7 @@ void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt); * ipa_interrupt_setup() - Set up the IPA interrupt framework * @ipa: IPA pointer * - * @Return: Pointer to IPA SMP2P info, or a pointer-coded error + * Return: Pointer to IPA SMP2P info, or a pointer-coded error */ struct ipa_interrupt *ipa_interrupt_setup(struct ipa *ipa); diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 27a869df3a4b..1fdfec41e442 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -277,6 +277,7 @@ static void ipa_idle_indication_cfg(struct ipa *ipa, /** * ipa_hardware_dcd_config() - Enable dynamic clock division on IPA + * @ipa: IPA pointer * * Configures when the IPA signals it is idle to the global clock * controller, which can respond by scalling down the clock to @@ -495,6 +496,7 @@ static void ipa_resource_deconfig(struct ipa *ipa) /** * ipa_config() - Configure IPA hardware * @ipa: IPA pointer + * @data: IPA configuration data * * Perform initialization requiring IPA clock to be enabled. */ @@ -686,7 +688,7 @@ static void ipa_validate_build(void) * ipa_probe() - IPA platform driver probe function * @pdev: Platform device pointer * - * @Return: 0 if successful, or a negative error code (possibly + * Return: 0 if successful, or a negative error code (possibly * EPROBE_DEFER) * * This is the main entry point for the IPA driver. Initialization proceeds @@ -902,7 +904,7 @@ static int ipa_remove(struct platform_device *pdev) * ipa_suspend() - Power management system suspend callback * @dev: IPA device structure * - * @Return: Zero + * Return: Always returns zero * * Called by the PM framework when a system suspend operation is invoked. */ @@ -920,7 +922,7 @@ static int ipa_suspend(struct device *dev) * ipa_resume() - Power management system resume callback * @dev: IPA device structure * - * @Return: Always returns 0 + * Return: Always returns 0 * * Called by the PM framework when a system resume operation is invoked. */ diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 3ef814119aab..2d45c444a67f 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -41,6 +41,7 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, const struct ipa_mem *mem) /** * ipa_mem_setup() - Set up IPA AP and modem shared memory areas + * @ipa: IPA pointer * * Set up the shared memory regions in IPA local memory. This involves * zero-filling memory regions, and in the case of header memory, telling @@ -52,7 +53,7 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, const struct ipa_mem *mem) * The AP informs the modem where its portions of memory are located * in a QMI exchange that occurs at modem startup. * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ int ipa_mem_setup(struct ipa *ipa) { @@ -137,8 +138,9 @@ static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id) /** * ipa_mem_config() - Configure IPA shared memory + * @ipa: IPA pointer * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code */ int ipa_mem_config(struct ipa *ipa) { @@ -238,6 +240,7 @@ void ipa_mem_deconfig(struct ipa *ipa) /** * ipa_mem_zero_modem() - Zero IPA-local memory regions owned by the modem + * @ipa: IPA pointer * * Zero regions of IPA-local memory used by the modem. These are configured * (and initially zeroed) by ipa_mem_setup(), but if the modem crashes and diff --git a/drivers/net/ipa/ipa_qmi_msg.c b/drivers/net/ipa/ipa_qmi_msg.c index 03a1d0e55964..73413371e3d3 100644 --- a/drivers/net/ipa/ipa_qmi_msg.c +++ b/drivers/net/ipa/ipa_qmi_msg.c @@ -119,7 +119,7 @@ struct qmi_elem_info ipa_driver_init_complete_rsp_ei[] = { sizeof_field(struct ipa_driver_init_complete_rsp, rsp), .tlv_type = 0x02, - .elem_size = offsetof(struct ipa_driver_init_complete_rsp, + .offset = offsetof(struct ipa_driver_init_complete_rsp, rsp), .ei_array = qmi_response_type_v01_ei, }, @@ -137,7 +137,7 @@ struct qmi_elem_info ipa_init_complete_ind_ei[] = { sizeof_field(struct ipa_init_complete_ind, status), .tlv_type = 0x02, - .elem_size = offsetof(struct ipa_init_complete_ind, + .offset = offsetof(struct ipa_init_complete_ind, status), .ei_array = qmi_response_type_v01_ei, }, @@ -218,7 +218,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { sizeof_field(struct ipa_init_modem_driver_req, platform_type_valid), .tlv_type = 0x10, - .elem_size = offsetof(struct ipa_init_modem_driver_req, + .offset = offsetof(struct ipa_init_modem_driver_req, platform_type_valid), }, { diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h index 1f65cdc9d406..bf0e4063cfd9 100644 --- a/drivers/net/ipa/ipa_smp2p.h +++ b/drivers/net/ipa/ipa_smp2p.h @@ -15,7 +15,7 @@ struct ipa; * @ipa: IPA pointer * @modem_init: Whether the modem is responsible for GSI initialization * - * @Return: 0 if successful, or a negative error code + * Return: 0 if successful, or a negative error code * */ int ipa_smp2p_init(struct ipa *ipa, bool modem_init); diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 9df2a3e78c98..2098ca2f2c90 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -505,7 +505,7 @@ void ipa_table_teardown(struct ipa *ipa) /** * ipa_filter_tuple_zero() - Zero an endpoint's hashed filter tuple - * @endpoint_id: Endpoint whose filter hash tuple should be zeroed + * @endpoint: Endpoint whose filter hash tuple should be zeroed * * Endpoint must be for the AP (not modem) and support filtering. Updates * the filter hash values without changing route ones. @@ -560,6 +560,7 @@ static bool ipa_route_id_modem(u32 route_id) /** * ipa_route_tuple_zero() - Zero a hashed route table entry tuple + * @ipa: IPA pointer * @route_id: Route table entry whose hash tuple should be zeroed * * Updates the route hash values without changing filter ones. diff --git a/drivers/net/ipa/ipa_table.h b/drivers/net/ipa/ipa_table.h index 64ea0221441a..78038d14fcea 100644 --- a/drivers/net/ipa/ipa_table.h +++ b/drivers/net/ipa/ipa_table.h @@ -25,7 +25,7 @@ struct ipa; * ipa_table_valid() - Validate route and filter table memory regions * @ipa: IPA pointer - * @Return: true if all regions are valid, false otherwise + * Return: true if all regions are valid, false otherwise */ bool ipa_table_valid(struct ipa *ipa); @@ -33,7 +33,7 @@ bool ipa_table_valid(struct ipa *ipa); * ipa_filter_map_valid() - Validate a filter table endpoint bitmap * @ipa: IPA pointer * - * @Return: true if all regions are valid, false otherwise + * Return: true if all regions are valid, false otherwise */ bool ipa_filter_map_valid(struct ipa *ipa, u32 filter_mask); diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index 9f9980ec2ed3..1a0b04e0ab74 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -41,19 +41,24 @@ /** * struct ipa_uc_mem_area - AP/microcontroller shared memory area * @command: command code (AP->microcontroller) + * @reserved0: reserved bytes; avoid reading or writing * @command_param: low 32 bits of command parameter (AP->microcontroller) * @command_param_hi: high 32 bits of command parameter (AP->microcontroller) * * @response: response code (microcontroller->AP) + * @reserved1: reserved bytes; avoid reading or writing * @response_param: response parameter (microcontroller->AP) * * @event: event code (microcontroller->AP) + * @reserved2: reserved bytes; avoid reading or writing * @event_param: event parameter (microcontroller->AP) * * @first_error_address: address of first error-source on SNOC * @hw_state: state of hardware (including error type information) * @warning_counter: counter of non-fatal hardware errors + * @reserved3: reserved bytes; avoid reading or writing * @interface_version: hardware-reported interface version + * @reserved4: reserved bytes; avoid reading or writing * * A shared memory area at the base of IPA resident memory is used for * communication with the microcontroller. The region is 128 bytes in diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index e56547bfdac9..9159846b8b93 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -4052,9 +4052,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev, return err; netdev_lockdep_set_classes(dev); - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &macsec_netdev_addr_lock_key, - dev->lower_level); + lockdep_set_class(&dev->addr_list_lock, + &macsec_netdev_addr_lock_key); err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 6a6cc9f75307..4942f6112e51 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -880,9 +880,8 @@ static struct lock_class_key macvlan_netdev_addr_lock_key; static void macvlan_set_lockdep_class(struct net_device *dev) { netdev_lockdep_set_classes(dev); - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &macvlan_netdev_addr_lock_key, - dev->lower_level); + lockdep_set_class(&dev->addr_list_lock, + &macvlan_netdev_addr_lock_key); } static int macvlan_init(struct net_device *dev) diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile index f4d8f62f28c2..4dfb389dbfd8 100644 --- a/drivers/net/netdevsim/Makefile +++ b/drivers/net/netdevsim/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_NETDEVSIM) += netdevsim.o netdevsim-objs := \ - netdev.o dev.o fib.o bus.o health.o + netdev.o dev.o fib.o bus.o health.o udp_tunnels.o ifeq ($(CONFIG_BPF_SYSCALL),y) netdevsim-objs += \ diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index ec6b6f7818ac..ce719c830a77 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -225,6 +225,7 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) debugfs_create_bool("fail_trap_policer_counter_get", 0600, nsim_dev->ddir, &nsim_dev->fail_trap_policer_counter_get); + nsim_udp_tunnels_debugfs_create(nsim_dev); return 0; } @@ -889,6 +890,7 @@ static const struct devlink_ops nsim_dev_devlink_ops = { static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, unsigned int port_index) { + struct devlink_port_attrs attrs = {}; struct nsim_dev_port *nsim_dev_port; struct devlink_port *devlink_port; int err; @@ -899,10 +901,11 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, nsim_dev_port->port_index = port_index; devlink_port = &nsim_dev_port->devlink_port; - devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - port_index + 1, 0, 0, - nsim_dev->switch_id.id, - nsim_dev->switch_id.id_len); + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = port_index + 1; + memcpy(attrs.switch_id.id, nsim_dev->switch_id.id, nsim_dev->switch_id.id_len); + attrs.switch_id.id_len = nsim_dev->switch_id.id_len; + devlink_port_attrs_set(devlink_port, &attrs); err = devlink_port_register(priv_to_devlink(nsim_dev), devlink_port, port_index); if (err) diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 2908e0a0d6e1..9d0d18026434 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -22,6 +22,7 @@ #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/rtnetlink.h> +#include <net/udp_tunnel.h> #include "netdevsim.h" @@ -257,6 +258,8 @@ static const struct net_device_ops nsim_netdev_ops = { .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, .ndo_bpf = nsim_bpf, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, .ndo_get_devlink_port = nsim_get_devlink_port, }; @@ -299,10 +302,14 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev); dev->netdev_ops = &nsim_netdev_ops; + err = nsim_udp_tunnels_info_create(nsim_dev, dev); + if (err) + goto err_free_netdev; + rtnl_lock(); err = nsim_bpf_init(ns); if (err) - goto err_free_netdev; + goto err_utn_destroy; nsim_ipsec_init(ns); @@ -317,6 +324,8 @@ err_ipsec_teardown: nsim_ipsec_teardown(ns); nsim_bpf_uninit(ns); rtnl_unlock(); +err_utn_destroy: + nsim_udp_tunnels_info_destroy(dev); err_free_netdev: free_netdev(dev); return ERR_PTR(err); @@ -331,6 +340,7 @@ void nsim_destroy(struct netdevsim *ns) nsim_ipsec_teardown(ns); nsim_bpf_uninit(ns); rtnl_unlock(); + nsim_udp_tunnels_info_destroy(dev); free_netdev(dev); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 4ded54a21e1e..d164052e0393 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -13,6 +13,7 @@ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ +#include <linux/debugfs.h> #include <linux/device.h> #include <linux/kernel.h> #include <linux/list.h> @@ -29,6 +30,7 @@ #define NSIM_IPSEC_MAX_SA_COUNT 33 #define NSIM_IPSEC_VALID BIT(31) +#define NSIM_UDP_TUNNEL_N_PORTS 4 struct nsim_sa { struct xfrm_state *xs; @@ -72,12 +74,23 @@ struct netdevsim { bool bpf_map_accept; struct nsim_ipsec ipsec; + struct { + u32 inject_error; + u32 sleep; + u32 ports[2][NSIM_UDP_TUNNEL_N_PORTS]; + struct debugfs_u32_array dfs_ports[2]; + } udp_ports; }; struct netdevsim * nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port); void nsim_destroy(struct netdevsim *ns); +void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev); +int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, + struct net_device *dev); +void nsim_udp_tunnels_info_destroy(struct net_device *dev); + #ifdef CONFIG_BPF_SYSCALL int nsim_bpf_dev_init(struct nsim_dev *nsim_dev); void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev); @@ -183,6 +196,12 @@ struct nsim_dev { bool fail_trap_group_set; bool fail_trap_policer_set; bool fail_trap_policer_counter_get; + struct { + bool sync_all; + bool open_only; + bool ipv4_only; + u32 sleep; + } udp_ports; }; static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev) diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c new file mode 100644 index 000000000000..22c06a76033c --- /dev/null +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2020 Facebook Inc. + +#include <linux/debugfs.h> +#include <linux/netdevice.h> +#include <linux/slab.h> +#include <net/udp_tunnel.h> + +#include "netdevsim.h" + +static int +nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct netdevsim *ns = netdev_priv(dev); + int ret; + + ret = -ns->udp_ports.inject_error; + ns->udp_ports.inject_error = 0; + + if (ns->udp_ports.sleep) + msleep(ns->udp_ports.sleep); + + if (!ret) { + if (ns->udp_ports.ports[table][entry]) + ret = -EBUSY; + else + ns->udp_ports.ports[table][entry] = + be16_to_cpu(ti->port) << 16 | ti->type; + } + + netdev_info(dev, "set [%d, %d] type %d family %d port %d - %d\n", + table, entry, ti->type, ti->sa_family, ntohs(ti->port), + ret); + return ret; +} + +static int +nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct netdevsim *ns = netdev_priv(dev); + int ret; + + ret = -ns->udp_ports.inject_error; + ns->udp_ports.inject_error = 0; + + if (ns->udp_ports.sleep) + msleep(ns->udp_ports.sleep); + if (!ret) { + u32 val = be16_to_cpu(ti->port) << 16 | ti->type; + + if (val == ns->udp_ports.ports[table][entry]) + ns->udp_ports.ports[table][entry] = 0; + else + ret = -ENOENT; + } + + netdev_info(dev, "unset [%d, %d] type %d family %d port %d - %d\n", + table, entry, ti->type, ti->sa_family, ntohs(ti->port), + ret); + return ret; +} + +static int +nsim_udp_tunnel_sync_table(struct net_device *dev, unsigned int table) +{ + struct netdevsim *ns = netdev_priv(dev); + struct udp_tunnel_info ti; + unsigned int i; + int ret; + + ret = -ns->udp_ports.inject_error; + ns->udp_ports.inject_error = 0; + + for (i = 0; i < NSIM_UDP_TUNNEL_N_PORTS; i++) { + udp_tunnel_nic_get_port(dev, table, i, &ti); + ns->udp_ports.ports[table][i] = + be16_to_cpu(ti.port) << 16 | ti.type; + } + + return ret; +} + +static const struct udp_tunnel_nic_info nsim_udp_tunnel_info = { + .set_port = nsim_udp_tunnel_set_port, + .unset_port = nsim_udp_tunnel_unset_port, + .sync_table = nsim_udp_tunnel_sync_table, + + .tables = { + { + .n_entries = NSIM_UDP_TUNNEL_N_PORTS, + .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, + }, + { + .n_entries = NSIM_UDP_TUNNEL_N_PORTS, + .tunnel_types = UDP_TUNNEL_TYPE_GENEVE | + UDP_TUNNEL_TYPE_VXLAN_GPE, + }, + }, +}; + +static ssize_t +nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct net_device *dev = file->private_data; + struct netdevsim *ns = netdev_priv(dev); + + memset(&ns->udp_ports.ports, 0, sizeof(ns->udp_ports.ports)); + rtnl_lock(); + udp_tunnel_nic_reset_ntf(dev); + rtnl_unlock(); + + return count; +} + +static const struct file_operations nsim_udp_tunnels_info_reset_fops = { + .open = simple_open, + .write = nsim_udp_tunnels_info_reset_write, + .llseek = generic_file_llseek, +}; + +int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, + struct net_device *dev) +{ + struct netdevsim *ns = netdev_priv(dev); + struct udp_tunnel_nic_info *info; + + debugfs_create_u32("udp_ports_inject_error", 0600, + ns->nsim_dev_port->ddir, + &ns->udp_ports.inject_error); + + ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0]; + ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS; + debugfs_create_u32_array("udp_ports_table0", 0400, + ns->nsim_dev_port->ddir, + &ns->udp_ports.dfs_ports[0]); + + ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1]; + ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS; + debugfs_create_u32_array("udp_ports_table1", 0400, + ns->nsim_dev_port->ddir, + &ns->udp_ports.dfs_ports[1]); + + debugfs_create_file("udp_ports_reset", 0200, ns->nsim_dev_port->ddir, + dev, &nsim_udp_tunnels_info_reset_fops); + + /* Note: it's not normal to allocate the info struct like this! + * Drivers are expected to use a static const one, here we're testing. + */ + info = kmemdup(&nsim_udp_tunnel_info, sizeof(nsim_udp_tunnel_info), + GFP_KERNEL); + if (!info) + return -ENOMEM; + ns->udp_ports.sleep = nsim_dev->udp_ports.sleep; + + if (nsim_dev->udp_ports.sync_all) { + info->set_port = NULL; + info->unset_port = NULL; + } else { + info->sync_table = NULL; + } + + if (ns->udp_ports.sleep) + info->flags |= UDP_TUNNEL_NIC_INFO_MAY_SLEEP; + if (nsim_dev->udp_ports.open_only) + info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY; + if (nsim_dev->udp_ports.ipv4_only) + info->flags |= UDP_TUNNEL_NIC_INFO_IPV4_ONLY; + + dev->udp_tunnel_nic_info = info; + return 0; +} + +void nsim_udp_tunnels_info_destroy(struct net_device *dev) +{ + kfree(dev->udp_tunnel_nic_info); + dev->udp_tunnel_nic_info = NULL; +} + +void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev) +{ + debugfs_create_bool("udp_ports_sync_all", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.sync_all); + debugfs_create_bool("udp_ports_open_only", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.open_only); + debugfs_create_bool("udp_ports_ipv4_only", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.ipv4_only); + debugfs_create_u32("udp_ports_sleep", 0600, nsim_dev->ddir, + &nsim_dev->udp_ports.sleep); +} diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index e351d65533aa..dd20c2c27c2f 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -21,6 +21,9 @@ config MDIO_BUS if MDIO_BUS +config MDIO_DEVRES + tristate + config MDIO_ASPEED tristate "ASPEED MDIO bus controller" depends on ARCH_ASPEED || COMPILE_TEST @@ -182,6 +185,7 @@ config MDIO_MOXART config MDIO_MSCC_MIIM tristate "Microsemi MIIM interface support" depends on HAS_IOMEM + select MDIO_DEVRES help This driver supports the MIIM (MDIO) interface found in the network switches of the Microsemi SoCs; it is recommended to switch on @@ -252,6 +256,7 @@ menuconfig PHYLIB tristate "PHY Device support and infrastructure" depends on NETDEVICES select MDIO_DEVICE + select MDIO_DEVRES help Ethernet controllers are usually attached to PHY devices. This option provides infrastructure for diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index c9a9adf194d5..d84bab489a53 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -4,7 +4,6 @@ libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ linkmode.o mdio-bus-y += mdio_bus.o mdio_device.o -mdio-devres-y += mdio_devres.o ifdef CONFIG_MDIO_DEVICE obj-y += mdio-boardinfo.o @@ -18,7 +17,7 @@ libphy-y += $(mdio-bus-y) else obj-$(CONFIG_MDIO_DEVICE) += mdio-bus.o endif -obj-$(CONFIG_MDIO_DEVICE) += mdio-devres.o +obj-$(CONFIG_MDIO_DEVRES) += mdio_devres.o libphy-$(CONFIG_SWPHY) += swphy.o libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index ef3441747348..b97ee79f3cdf 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1494,10 +1494,7 @@ static int __vsc8584_init_ptp(struct phy_device *phydev) vsc8531->ptp->ptp_clock = ptp_clock_register(&vsc8531->ptp->caps, &phydev->mdio.dev); - if (IS_ERR(vsc8531->ptp->ptp_clock)) - return PTR_ERR(vsc8531->ptp->ptp_clock); - - return 0; + return PTR_ERR_OR_ZERO(vsc8531->ptp->ptp_clock); } void vsc8584_config_ts_intr(struct phy_device *phydev) diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 46bd68e9ecfa..ff8e14b01eeb 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -8,7 +8,7 @@ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 75, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 90, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -78,12 +78,22 @@ static const struct phy_setting settings[] = { PHY_SETTING( 400000, FULL, 400000baseLR8_ER8_FR8_Full ), PHY_SETTING( 400000, FULL, 400000baseDR8_Full ), PHY_SETTING( 400000, FULL, 400000baseSR8_Full ), + PHY_SETTING( 400000, FULL, 400000baseCR4_Full ), + PHY_SETTING( 400000, FULL, 400000baseKR4_Full ), + PHY_SETTING( 400000, FULL, 400000baseLR4_ER4_FR4_Full ), + PHY_SETTING( 400000, FULL, 400000baseDR4_Full ), + PHY_SETTING( 400000, FULL, 400000baseSR4_Full ), /* 200G */ PHY_SETTING( 200000, FULL, 200000baseCR4_Full ), PHY_SETTING( 200000, FULL, 200000baseKR4_Full ), PHY_SETTING( 200000, FULL, 200000baseLR4_ER4_FR4_Full ), PHY_SETTING( 200000, FULL, 200000baseDR4_Full ), PHY_SETTING( 200000, FULL, 200000baseSR4_Full ), + PHY_SETTING( 200000, FULL, 200000baseCR2_Full ), + PHY_SETTING( 200000, FULL, 200000baseKR2_Full ), + PHY_SETTING( 200000, FULL, 200000baseLR2_ER2_FR2_Full ), + PHY_SETTING( 200000, FULL, 200000baseDR2_Full ), + PHY_SETTING( 200000, FULL, 200000baseSR2_Full ), /* 100G */ PHY_SETTING( 100000, FULL, 100000baseCR4_Full ), PHY_SETTING( 100000, FULL, 100000baseKR4_Full ), @@ -94,6 +104,11 @@ static const struct phy_setting settings[] = { PHY_SETTING( 100000, FULL, 100000baseLR2_ER2_FR2_Full ), PHY_SETTING( 100000, FULL, 100000baseDR2_Full ), PHY_SETTING( 100000, FULL, 100000baseSR2_Full ), + PHY_SETTING( 100000, FULL, 100000baseCR_Full ), + PHY_SETTING( 100000, FULL, 100000baseKR_Full ), + PHY_SETTING( 100000, FULL, 100000baseLR_ER_FR_Full ), + PHY_SETTING( 100000, FULL, 100000baseDR_Full ), + PHY_SETTING( 100000, FULL, 100000baseSR_Full ), /* 56G */ PHY_SETTING( 56000, FULL, 56000baseCR4_Full ), PHY_SETTING( 56000, FULL, 56000baseKR4_Full ), diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 56cfae950472..79b4f35d151e 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -489,6 +489,54 @@ static void phy_abort_cable_test(struct phy_device *phydev) phydev_err(phydev, "Error while aborting cable test"); } +int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) +{ + if (!phydev->drv) + return -EIO; + + mutex_lock(&phydev->lock); + phydev->drv->get_strings(phydev, data); + mutex_unlock(&phydev->lock); + + return 0; +} +EXPORT_SYMBOL(phy_ethtool_get_strings); + +int phy_ethtool_get_sset_count(struct phy_device *phydev) +{ + int ret; + + if (!phydev->drv) + return -EIO; + + if (phydev->drv->get_sset_count && + phydev->drv->get_strings && + phydev->drv->get_stats) { + mutex_lock(&phydev->lock); + ret = phydev->drv->get_sset_count(phydev); + mutex_unlock(&phydev->lock); + + return ret; + } + + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(phy_ethtool_get_sset_count); + +int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + if (!phydev->drv) + return -EIO; + + mutex_lock(&phydev->lock); + phydev->drv->get_stats(phydev, stats, data); + mutex_unlock(&phydev->lock); + + return 0; +} +EXPORT_SYMBOL(phy_ethtool_get_stats); + int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index cf3505e2f587..7cda95330aea 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3027,6 +3027,14 @@ static struct phy_driver genphy_driver = { .set_loopback = genphy_loopback, }; +static const struct ethtool_phy_ops phy_ethtool_phy_ops = { + .get_sset_count = phy_ethtool_get_sset_count, + .get_strings = phy_ethtool_get_strings, + .get_stats = phy_ethtool_get_stats, + .start_cable_test = phy_start_cable_test, + .start_cable_test_tdr = phy_start_cable_test_tdr, +}; + static int __init phy_init(void) { int rc; @@ -3035,6 +3043,7 @@ static int __init phy_init(void) if (rc) return rc; + ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); features_init(); rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE); @@ -3056,6 +3065,7 @@ static void __exit phy_exit(void) phy_driver_unregister(&genphy_c45_driver); phy_driver_unregister(&genphy_driver); mdio_bus_exit(); + ethtool_set_ethtool_phy_ops(NULL); } subsys_initcall(phy_init); diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 7bdfcde98266..eef458ab0e5b 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -2354,6 +2354,9 @@ static int sfp_probe(struct platform_device *pdev) "%s-%s", dev_name(sfp->dev), gpio_of_names[i]); + if (!sfp_irq_name) + return -ENOMEM; + err = devm_request_threaded_irq(sfp->dev, sfp->gpio_irq[i], NULL, sfp_irq, IRQF_ONESHOT | diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 858b012074bd..7adeb91bd368 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -62,6 +62,7 @@ #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> +#include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> @@ -1351,6 +1352,7 @@ static void tun_net_init(struct net_device *dev) switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 31b1d4b959f6..07c42c0719f5 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1370,6 +1370,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 3cf4dc3433f9..bb4ccbda031a 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1287,11 +1287,14 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) /* Init all registers */ ret = smsc95xx_reset(dev); + if (ret) + goto free_pdata; /* detect device revision as different features may be available */ ret = smsc95xx_read_reg(dev, ID_REV, &val); if (ret < 0) - return ret; + goto free_pdata; + val >>= 16; pdata->chip_id = val; pdata->mdix_ctrl = get_mdix_status(dev->net); @@ -1317,6 +1320,10 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); return 0; + +free_pdata: + kfree(pdata); + return ret; } static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 89d85dcb200e..a43c97b13924 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -4477,10 +4477,12 @@ static int vxlan_netdevice_event(struct notifier_block *unused, struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); if (event == NETDEV_UNREGISTER) { - vxlan_offload_rx_ports(dev, false); + if (!dev->udp_tunnel_nic_info) + vxlan_offload_rx_ports(dev, false); vxlan_handle_lowerdev_unregister(vn, dev); } else if (event == NETDEV_REGISTER) { - vxlan_offload_rx_ports(dev, true); + if (!dev->udp_tunnel_nic_info) + vxlan_offload_rx_ports(dev, true); } else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO || event == NETDEV_UDP_TUNNEL_DROP_INFO) { vxlan_offload_rx_ports(dev, event == NETDEV_UDP_TUNNEL_PUSH_INFO); diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c index cb57f9124ab1..c354a5143e99 100644 --- a/drivers/net/wan/c101.c +++ b/drivers/net/wan/c101.c @@ -4,7 +4,7 @@ * * Copyright (C) 2000-2003 Krzysztof Halasa <khc@pm.waw.pl> * - * For information see <http://www.kernel.org/pub/linux/utils/net/hdlc/> + * For information see <https://www.kernel.org/pub/linux/utils/net/hdlc/> * * Sources of information: * Hitachi HD64570 SCA User's Manual diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 5d6532ad6b78..f8aed0696d77 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -12,7 +12,7 @@ * HARDWARE INFO * * Both cards are developed at the Institute of Computer Science, - * Masaryk University (http://www.ics.muni.cz/). The hardware is + * Masaryk University (https://www.ics.muni.cz/). The hardware is * developed by Jiri Novotny <novotny@ics.muni.cz>. More information * and the photo of both cards is available at * http://www.pavoucek.cz/cosa.html. The card documentation, firmwares @@ -35,7 +35,7 @@ * * SOFTWARE INFO * - * The homepage of the Linux driver is at http://www.fi.muni.cz/~kas/cosa/. + * The homepage of the Linux driver is at https://www.fi.muni.cz/~kas/cosa/. * The CVS tree of Linux driver can be viewed there, as well as the * firmware binaries and user-space utilities for downloading the firmware * into the card and setting up the card. diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 7916efce7188..0196b7fd130d 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -124,7 +124,7 @@ module_param_array(fst_excluded_list, int, NULL, 0); /* The Am186CH/CC processors support a SmartDMA mode using circular pools * of buffer descriptors. The structure is almost identical to that used * in the LANCE Ethernet controllers. Details available as PDF from the - * AMD web site: http://www.amd.com/products/epd/processors/\ + * AMD web site: https://www.amd.com/products/epd/processors/\ * 2.16bitcont/3.am186cxfa/a21914/21914.pdf */ struct txdesc { /* Transmit descriptor */ diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index e30d91a38cfb..284832314f31 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -303,7 +303,6 @@ static void lapbeth_setup(struct net_device *dev) dev->netdev_ops = &lapbeth_netdev_ops; dev->needs_free_netdev = true; dev->type = ARPHRD_X25; - dev->hard_header_len = 3; dev->mtu = 1000; dev->addr_len = 0; } @@ -324,6 +323,14 @@ static int lapbeth_new_device(struct net_device *dev) if (!ndev) goto out; + /* When transmitting data: + * first this driver removes a pseudo header of 1 byte, + * then the lapb module prepends an LAPB header of at most 3 bytes, + * then this driver prepends a length field of 2 bytes, + * then the underlying Ethernet device prepends its own header. + */ + ndev->hard_header_len = -1 + 3 + 2 + dev->hard_header_len; + lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; diff --git a/drivers/net/wan/n2.c b/drivers/net/wan/n2.c index f9e7fc7e9978..5bf4463873b1 100644 --- a/drivers/net/wan/n2.c +++ b/drivers/net/wan/n2.c @@ -4,7 +4,7 @@ * * Copyright (C) 1998-2003 Krzysztof Halasa <khc@pm.waw.pl> * - * For information see <http://www.kernel.org/pub/linux/utils/net/hdlc/> + * For information see <https://www.kernel.org/pub/linux/utils/net/hdlc/> * * Note: integrated CSU/DSU/DDS are not supported by this driver * diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c index 190735604b2e..001fd378d417 100644 --- a/drivers/net/wan/pc300too.c +++ b/drivers/net/wan/pc300too.c @@ -4,7 +4,7 @@ * * Copyright (C) 2000-2008 Krzysztof Halasa <khc@pm.waw.pl> * - * For information see <http://www.kernel.org/pub/linux/utils/net/hdlc/>. + * For information see <https://www.kernel.org/pub/linux/utils/net/hdlc/>. * * Sources of information: * Hitachi HD64572 SCA-II User's Manual diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c index b5f8aaca5f06..d0062224b216 100644 --- a/drivers/net/wan/pci200syn.c +++ b/drivers/net/wan/pci200syn.c @@ -4,7 +4,7 @@ * * Copyright (C) 2002-2008 Krzysztof Halasa <khc@pm.waw.pl> * - * For information see <http://www.kernel.org/pub/linux/utils/net/hdlc/> + * For information see <https://www.kernel.org/pub/linux/utils/net/hdlc/> * * Sources of information: * Hitachi HD64572 SCA-II User's Manual diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index a8f151b1b5fa..c9f65e96ccb0 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -262,6 +262,7 @@ static void wg_setup(struct net_device *dev) max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->hard_header_len = 0; dev->addr_len = 0; dev->needed_headroom = DATA_PACKET_HEAD_ROOM; diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index c58df439dbbe..dfb674e03076 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -11,6 +11,7 @@ #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/ip_tunnels.h> struct wg_device; struct wg_peer; @@ -65,25 +66,9 @@ struct packet_cb { #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) -/* Returns either the correct skb->protocol value, or 0 if invalid. */ -static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb) -{ - if (skb_network_header(skb) >= skb->head && - (skb_network_header(skb) + sizeof(struct iphdr)) <= - skb_tail_pointer(skb) && - ip_hdr(skb)->version == 4) - return htons(ETH_P_IP); - if (skb_network_header(skb) >= skb->head && - (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= - skb_tail_pointer(skb) && - ipv6_hdr(skb)->version == 6) - return htons(ETH_P_IPV6); - return 0; -} - static inline bool wg_check_packet_protocol(struct sk_buff *skb) { - __be16 real_protocol = wg_examine_packet_protocol(skb); + __be16 real_protocol = ip_tunnel_parse_protocol(skb); return real_protocol && skb->protocol == real_protocol; } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 9b2ab6fc91cd..2c9551ea6dc7 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -387,7 +387,7 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, */ skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = ~0; /* All levels */ - skb->protocol = wg_examine_packet_protocol(skb); + skb->protocol = ip_tunnel_parse_protocol(skb); if (skb->protocol == htons(ETH_P_IP)) { len = ntohs(ip_hdr(skb)->tot_len); if (unlikely(len < sizeof(struct iphdr))) diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index 89b85970912d..4cef69bd3c1b 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -95,7 +95,7 @@ static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm, struct encrypted_key_payload *epayload; struct device *dev = &nvdimm->dev; - keyref = lookup_user_key(id, 0, 0); + keyref = lookup_user_key(id, 0, KEY_NEED_SEARCH); if (IS_ERR(keyref)) return NULL; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c2c5bc4fb702..8410d03b940d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1116,10 +1116,16 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, dev_warn(ctrl->device, "Identify Descriptors failed (%d)\n", status); /* - * Don't treat an error as fatal, as we potentially already - * have a NGUID or EUI-64. + * Don't treat non-retryable errors as fatal, as we potentially + * already have a NGUID or EUI-64. If we failed with DNR set, + * we want to silently ignore the error as we can still + * identify the device, but if the status has DNR set, we want + * to propagate the error back specifically for the disk + * revalidation flow to make sure we don't abandon the + * device just because of a temporal retry-able error (such + * as path of transport errors). */ - if (status > 0 && !(status & NVME_SC_DNR)) + if (status > 0 && (status & NVME_SC_DNR)) status = 0; goto free_data; } @@ -1974,7 +1980,6 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); blk_queue_stack_limits(ns->head->disk->queue, ns->queue); - revalidate_disk(ns->head->disk); } #endif return 0; @@ -4174,6 +4179,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->dev = dev; ctrl->ops = ops; ctrl->quirks = quirks; + ctrl->numa_node = NUMA_NO_NODE; INIT_WORK(&ctrl->scan_work, nvme_scan_work); INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index da78e499947a..66509472fe06 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -409,15 +409,14 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) { struct nvme_ns_head *head = ns->head; - lockdep_assert_held(&ns->head->lock); - if (!head->disk) return; - if (!(head->disk->flags & GENHD_FL_UP)) + if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) device_add_disk(&head->subsys->dev, head->disk, nvme_ns_id_attr_groups); + mutex_lock(&head->lock); if (nvme_path_is_optimized(ns)) { int node, srcu_idx; @@ -426,9 +425,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) __nvme_find_path(head, node); srcu_read_unlock(&head->srcu, srcu_idx); } + mutex_unlock(&head->lock); - synchronize_srcu(&ns->head->srcu); - kblockd_schedule_work(&ns->head->requeue_work); + synchronize_srcu(&head->srcu); + kblockd_schedule_work(&head->requeue_work); } static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, @@ -483,14 +483,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state) static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, struct nvme_ns *ns) { - mutex_lock(&ns->head->lock); ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags); if (nvme_state_is_live(ns->ana_state)) nvme_mpath_set_live(ns); - mutex_unlock(&ns->head->lock); } static int nvme_update_ana_state(struct nvme_ctrl *ctrl, @@ -640,38 +638,45 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr, } DEVICE_ATTR_RO(ana_state); -static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl, +static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *desc, void *data) { - struct nvme_ns *ns = data; + struct nvme_ana_group_desc *dst = data; - if (ns->ana_grpid == le32_to_cpu(desc->grpid)) { - nvme_update_ns_ana_state(desc, ns); - return -ENXIO; /* just break out of the loop */ - } + if (desc->grpid != dst->grpid) + return 0; - return 0; + *dst = *desc; + return -ENXIO; /* just break out of the loop */ } void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) { if (nvme_ctrl_use_ana(ns->ctrl)) { + struct nvme_ana_group_desc desc = { + .grpid = id->anagrpid, + .state = 0, + }; + mutex_lock(&ns->ctrl->ana_lock); ns->ana_grpid = le32_to_cpu(id->anagrpid); - nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state); + nvme_parse_ana_log(ns->ctrl, &desc, nvme_lookup_ana_group_desc); mutex_unlock(&ns->ctrl->ana_lock); + if (desc.state) { + /* found the group desc: update */ + nvme_update_ns_ana_state(&desc, ns); + } } else { - mutex_lock(&ns->head->lock); ns->ana_state = NVME_ANA_OPTIMIZED; nvme_mpath_set_live(ns); - mutex_unlock(&ns->head->lock); } if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) { - struct backing_dev_info *info = - ns->head->disk->queue->backing_dev_info; + struct gendisk *disk = ns->head->disk; - info->capabilities |= BDI_CAP_STABLE_WRITES; + if (disk) + disk->queue->backing_dev_info->capabilities |= + BDI_CAP_STABLE_WRITES; } } @@ -686,6 +691,14 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); blk_cleanup_queue(head->disk->queue); + if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { + /* + * if device_add_disk wasn't called, prevent + * disk release to put a bogus reference on the + * request queue + */ + head->disk->queue = NULL; + } put_disk(head->disk); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index c0f4226d3299..2ef8d501e2a8 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -364,6 +364,8 @@ struct nvme_ns_head { spinlock_t requeue_lock; struct work_struct requeue_work; struct mutex lock; + unsigned long flags; +#define NVME_NSHEAD_DISK_LIVE 0 struct nvme_ns __rcu *current_path[]; #endif }; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index e2bacd369a88..b1d18f0633c7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1593,7 +1593,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH; dev->admin_tagset.timeout = ADMIN_TIMEOUT; - dev->admin_tagset.numa_node = dev_to_node(dev->dev); + dev->admin_tagset.numa_node = dev->ctrl.numa_node; dev->admin_tagset.cmd_size = sizeof(struct nvme_iod); dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; dev->admin_tagset.driver_data = dev; @@ -1669,6 +1669,8 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) if (result) return result; + dev->ctrl.numa_node = dev_to_node(dev->dev); + nvmeq = &dev->queues[0]; aqa = nvmeq->q_depth - 1; aqa |= aqa << 16; @@ -2257,7 +2259,7 @@ static void nvme_dev_add(struct nvme_dev *dev) if (dev->io_queues[HCTX_TYPE_POLL]) dev->tagset.nr_maps++; dev->tagset.timeout = NVME_IO_TIMEOUT; - dev->tagset.numa_node = dev_to_node(dev->dev); + dev->tagset.numa_node = dev->ctrl.numa_node; dev->tagset.queue_depth = min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1; dev->tagset.cmd_size = sizeof(struct nvme_iod); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f8f856dc0c67..13506a87a444 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -470,7 +470,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) * Spread I/O queues completion vectors according their queue index. * Admin queues can always go on completion vector 0. */ - comp_vector = idx == 0 ? idx : idx - 1; + comp_vector = (idx == 0 ? idx : idx - 1) % ibdev->num_comp_vectors; /* Polling queues need direct cq polling context */ if (nvme_rdma_poll_queue(queue)) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 3345ec7efaff..79ef2b8e2b3c 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1532,7 +1532,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->ops = &nvme_tcp_admin_mq_ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; set->reserved_tags = 2; /* connect + keep-alive */ - set->numa_node = NUMA_NO_NODE; + set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_BLOCKING; set->cmd_size = sizeof(struct nvme_tcp_request); set->driver_data = ctrl; @@ -1544,7 +1544,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->ops = &nvme_tcp_mq_ops; set->queue_depth = nctrl->sqsize + 1; set->reserved_tags = 1; /* fabric connect */ - set->numa_node = NUMA_NO_NODE; + set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; set->cmd_size = sizeof(struct nvme_tcp_request); set->driver_data = ctrl; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 0d54e730cbf2..6344e73c9354 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -340,7 +340,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops; ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ - ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; + ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); ctrl->admin_tag_set.driver_data = ctrl; @@ -512,7 +512,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) ctrl->tag_set.ops = &nvme_loop_mq_ops; ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ - ctrl->tag_set.numa_node = NUMA_NO_NODE; + ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 0ff7c55173da..615174a9d1e0 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -800,6 +800,21 @@ static void byt_gpio_disable_free(struct pinctrl_dev *pctl_dev, pm_runtime_put(vg->dev); } +static void byt_gpio_direct_irq_check(struct intel_pinctrl *vg, + unsigned int offset) +{ + void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG); + + /* + * Before making any direction modifications, do a check if gpio is set + * for direct IRQ. On Bay Trail, setting GPIO to output does not make + * sense, so let's at least inform the caller before they shoot + * themselves in the foot. + */ + if (readl(conf_reg) & BYT_DIRECT_IRQ_EN) + dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output"); +} + static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, struct pinctrl_gpio_range *range, unsigned int offset, @@ -807,7 +822,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, { struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev); void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG); - void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG); unsigned long flags; u32 value; @@ -817,14 +831,8 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev, value &= ~BYT_DIR_MASK; if (input) value |= BYT_OUTPUT_EN; - else if (readl(conf_reg) & BYT_DIRECT_IRQ_EN) - /* - * Before making any direction modifications, do a check if gpio - * is set for direct IRQ. On baytrail, setting GPIO to output - * does not make sense, so let's at least inform the caller before - * they shoot themselves in the foot. - */ - dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output"); + else + byt_gpio_direct_irq_check(vg, offset); writel(value, val_reg); @@ -1165,19 +1173,50 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset) { - return pinctrl_gpio_direction_input(chip->base + offset); + struct intel_pinctrl *vg = gpiochip_get_data(chip); + void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG); + unsigned long flags; + u32 reg; + + raw_spin_lock_irqsave(&byt_lock, flags); + + reg = readl(val_reg); + reg &= ~BYT_DIR_MASK; + reg |= BYT_OUTPUT_EN; + writel(reg, val_reg); + + raw_spin_unlock_irqrestore(&byt_lock, flags); + return 0; } +/* + * Note despite the temptation this MUST NOT be converted into a call to + * pinctrl_gpio_direction_output() + byt_gpio_set() that does not work this + * MUST be done as a single BYT_VAL_REG register write. + * See the commit message of the commit adding this comment for details. + */ static int byt_gpio_direction_output(struct gpio_chip *chip, unsigned int offset, int value) { - int ret = pinctrl_gpio_direction_output(chip->base + offset); + struct intel_pinctrl *vg = gpiochip_get_data(chip); + void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG); + unsigned long flags; + u32 reg; - if (ret) - return ret; + raw_spin_lock_irqsave(&byt_lock, flags); + + byt_gpio_direct_irq_check(vg, offset); - byt_gpio_set(chip, offset, value); + reg = readl(val_reg); + reg &= ~BYT_DIR_MASK; + if (value) + reg |= BYT_LEVEL; + else + reg &= ~BYT_LEVEL; + writel(reg, val_reg); + + raw_spin_unlock_irqrestore(&byt_lock, flags); return 0; } diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 3e5760f1a715..d4a192df5fab 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -252,7 +252,7 @@ static const struct amd_pingroup kerncz_groups[] = { { .name = "uart0", .pins = uart0_pins, - .npins = 9, + .npins = 5, }, { .name = "uart1", diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c index a646fc81c872..13b26a1c7988 100644 --- a/drivers/s390/cio/vfio_ccw_chp.c +++ b/drivers/s390/cio/vfio_ccw_chp.c @@ -8,6 +8,7 @@ * Eric Farman <farman@linux.ibm.com> */ +#include <linux/slab.h> #include <linux/vfio.h> #include "vfio_ccw_private.h" diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index db320dab1fee..79f6e8fb03ca 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -577,7 +577,10 @@ static void zfcp_erp_strategy_check_fsfreq(struct zfcp_erp_action *act) ZFCP_STATUS_ERP_TIMEDOUT)) { req->status |= ZFCP_STATUS_FSFREQ_DISMISSED; zfcp_dbf_rec_run("erscf_1", act); - req->erp_action = NULL; + /* lock-free concurrent access with + * zfcp_erp_timeout_handler() + */ + WRITE_ONCE(req->erp_action, NULL); } if (act->status & ZFCP_STATUS_ERP_TIMEDOUT) zfcp_dbf_rec_run("erscf_2", act); @@ -613,8 +616,14 @@ void zfcp_erp_notify(struct zfcp_erp_action *erp_action, unsigned long set_mask) void zfcp_erp_timeout_handler(struct timer_list *t) { struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer); - struct zfcp_erp_action *act = fsf_req->erp_action; + struct zfcp_erp_action *act; + if (fsf_req->status & ZFCP_STATUS_FSFREQ_DISMISSED) + return; + /* lock-free concurrent access with zfcp_erp_strategy_check_fsfreq() */ + act = READ_ONCE(fsf_req->erp_action); + if (!act) + return; zfcp_erp_notify(act, ZFCP_STATUS_ERP_TIMEDOUT); } diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 773c45af9387..278d15ff1c5a 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -133,8 +133,10 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) lockdep_assert_held(&lport->disc.disc_mutex); rdata = fc_rport_lookup(lport, port_id); - if (rdata) + if (rdata) { + kref_put(&rdata->kref, fc_rport_destroy); return rdata; + } if (lport->rport_priv_size > 0) rport_priv_size = lport->rport_priv_size; @@ -481,10 +483,11 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata, fc_rport_state_enter(rdata, RPORT_ST_DELETE); - kref_get(&rdata->kref); - if (rdata->event == RPORT_EV_NONE && - !queue_work(rport_event_queue, &rdata->event_work)) - kref_put(&rdata->kref, fc_rport_destroy); + if (rdata->event == RPORT_EV_NONE) { + kref_get(&rdata->kref); + if (!queue_work(rport_event_queue, &rdata->event_work)) + kref_put(&rdata->kref, fc_rport_destroy); + } rdata->event = event; } diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 69a5249e007a..6637f84a3d1b 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -11878,7 +11878,8 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) lpfc_sli4_xri_exchange_busy_wait(phba); /* per-phba callback de-registration for hotplug event */ - lpfc_cpuhp_remove(phba); + if (phba->pport) + lpfc_cpuhp_remove(phba); /* Disable PCI subsystem interrupt */ lpfc_sli4_disable_intr(phba); diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 42c3ad27f1cb..df670fba2ab8 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3496,7 +3496,9 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp) qla2x00_clear_loop_id(fcport); fcport->flags |= FCF_FABRIC_DEVICE; } else if (fcport->d_id.b24 != rp->id.b24 || - fcport->scan_needed) { + (fcport->scan_needed && + fcport->port_type != FCT_INITIATOR && + fcport->port_type != FCT_NVME_INITIATOR)) { qlt_schedule_sess_for_deletion(fcport); } fcport->d_id.b24 = rp->id.b24; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 4576d3ae9937..2436a17f5cd9 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -5944,7 +5944,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha) break; } - if (NVME_TARGET(vha->hw, fcport)) { + if (found && NVME_TARGET(vha->hw, fcport)) { if (fcport->disc_state == DSC_DELETE_PEND) { qla2x00_set_fcport_disc_state(fcport, DSC_GNL); vha->fcport_count--; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index d66d47a0f958..fa695a4007f8 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -139,11 +139,12 @@ static void qla_nvme_release_fcp_cmd_kref(struct kref *kref) sp->priv = NULL; if (priv->comp_status == QLA_SUCCESS) { fd->rcv_rsplen = le16_to_cpu(nvme->u.nvme.rsp_pyld_len); + fd->status = NVME_SC_SUCCESS; } else { fd->rcv_rsplen = 0; fd->transferred_length = 0; + fd->status = NVME_SC_INTERNAL; } - fd->status = 0; spin_unlock_irqrestore(&priv->cmd_lock, flags); fd->done(fd); diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c index 7b0759adb47d..cc57a384d74d 100644 --- a/drivers/soc/imx/soc-imx8m.c +++ b/drivers/soc/imx/soc-imx8m.c @@ -22,6 +22,8 @@ #define OCOTP_UID_LOW 0x410 #define OCOTP_UID_HIGH 0x420 +#define IMX8MP_OCOTP_UID_OFFSET 0x10 + /* Same as ANADIG_DIGPROG_IMX7D */ #define ANADIG_DIGPROG_IMX8MM 0x800 @@ -87,6 +89,8 @@ static void __init imx8mm_soc_uid(void) { void __iomem *ocotp_base; struct device_node *np; + u32 offset = of_machine_is_compatible("fsl,imx8mp") ? + IMX8MP_OCOTP_UID_OFFSET : 0; np = of_find_compatible_node(NULL, NULL, "fsl,imx8mm-ocotp"); if (!np) @@ -95,9 +99,9 @@ static void __init imx8mm_soc_uid(void) ocotp_base = of_iomap(np, 0); WARN_ON(!ocotp_base); - soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH); + soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH + offset); soc_uid <<= 32; - soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW); + soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW + offset); iounmap(ocotp_base); of_node_put(np); @@ -146,7 +150,7 @@ static const struct imx8_soc_data imx8mp_soc_data = { .soc_revision = imx8mm_soc_revision, }; -static const struct of_device_id imx8_soc_match[] = { +static __maybe_unused const struct of_device_id imx8_soc_match[] = { { .compatible = "fsl,imx8mq", .data = &imx8mq_soc_data, }, { .compatible = "fsl,imx8mm", .data = &imx8mm_soc_data, }, { .compatible = "fsl,imx8mn", .data = &imx8mn_soc_data, }, diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c index 96c6f777519c..c9b3f9ebf0bb 100644 --- a/drivers/soc/ti/omap_prm.c +++ b/drivers/soc/ti/omap_prm.c @@ -256,10 +256,10 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, goto exit; /* wait for the status to be set */ - ret = readl_relaxed_poll_timeout(reset->prm->base + - reset->prm->data->rstst, - v, v & BIT(st_bit), 1, - OMAP_RESET_MAX_WAIT); + ret = readl_relaxed_poll_timeout_atomic(reset->prm->base + + reset->prm->data->rstst, + v, v & BIT(st_bit), 1, + OMAP_RESET_MAX_WAIT); if (ret) pr_err("%s: timedout waiting for %s:%lu\n", __func__, reset->prm->data->name, id); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 58190c94561f..91c6affe139c 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1109,6 +1109,8 @@ static int dspi_suspend(struct device *dev) struct spi_controller *ctlr = dev_get_drvdata(dev); struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); + if (dspi->irq) + disable_irq(dspi->irq); spi_controller_suspend(ctlr); clk_disable_unprepare(dspi->clk); @@ -1129,6 +1131,8 @@ static int dspi_resume(struct device *dev) if (ret) return ret; spi_controller_resume(ctlr); + if (dspi->irq) + enable_irq(dspi->irq); return 0; } @@ -1385,22 +1389,22 @@ static int dspi_probe(struct platform_device *pdev) goto poll_mode; } - ret = devm_request_irq(&pdev->dev, dspi->irq, dspi_interrupt, - IRQF_SHARED, pdev->name, dspi); + init_completion(&dspi->xfer_done); + + ret = request_threaded_irq(dspi->irq, dspi_interrupt, NULL, + IRQF_SHARED, pdev->name, dspi); if (ret < 0) { dev_err(&pdev->dev, "Unable to attach DSPI interrupt\n"); goto out_clk_put; } - init_completion(&dspi->xfer_done); - poll_mode: if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) { ret = dspi_request_dma(dspi, res->start); if (ret < 0) { dev_err(&pdev->dev, "can't get dma channels\n"); - goto out_clk_put; + goto out_free_irq; } } @@ -1415,11 +1419,14 @@ poll_mode: ret = spi_register_controller(ctlr); if (ret != 0) { dev_err(&pdev->dev, "Problem registering DSPI ctlr\n"); - goto out_clk_put; + goto out_free_irq; } return ret; +out_free_irq: + if (dspi->irq) + free_irq(dspi->irq, dspi); out_clk_put: clk_disable_unprepare(dspi->clk); out_ctlr_put: @@ -1434,18 +1441,8 @@ static int dspi_remove(struct platform_device *pdev) struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); /* Disconnect from the SPI framework */ - dspi_release_dma(dspi); - clk_disable_unprepare(dspi->clk); spi_unregister_controller(dspi->ctlr); - return 0; -} - -static void dspi_shutdown(struct platform_device *pdev) -{ - struct spi_controller *ctlr = platform_get_drvdata(pdev); - struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); - /* Disable RX and TX */ regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF, @@ -1455,8 +1452,16 @@ static void dspi_shutdown(struct platform_device *pdev) regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, SPI_MCR_HALT); dspi_release_dma(dspi); + if (dspi->irq) + free_irq(dspi->irq, dspi); clk_disable_unprepare(dspi->clk); - spi_unregister_controller(dspi->ctlr); + + return 0; +} + +static void dspi_shutdown(struct platform_device *pdev) +{ + dspi_remove(pdev); } static struct platform_driver fsl_dspi_driver = { diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 6721910e5f2a..0040362b7162 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1485,6 +1485,11 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = { { PCI_VDEVICE(INTEL, 0x4daa), LPSS_CNL_SSP }, { PCI_VDEVICE(INTEL, 0x4dab), LPSS_CNL_SSP }, { PCI_VDEVICE(INTEL, 0x4dfb), LPSS_CNL_SSP }, + /* TGL-H */ + { PCI_VDEVICE(INTEL, 0x43aa), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x43ab), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x43fb), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0x43fd), LPSS_CNL_SSP }, /* APL */ { PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP }, { PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP }, diff --git a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c index 69bcd172b298..a3ea7ce3e12e 100644 --- a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c @@ -1824,12 +1824,14 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l pIE = (struct ndis_80211_var_ie *)rtw_get_ie(pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len); if (!pIE) return _FAIL; + if (ie_len > sizeof(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates)) + return _FAIL; memcpy(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len); supportRateNum = ie_len; pIE = (struct ndis_80211_var_ie *)rtw_get_ie(pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len); - if (pIE) + if (pIE && (ie_len <= sizeof(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates) - supportRateNum)) memcpy((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len); return _SUCCESS; diff --git a/drivers/staging/wfx/hif_tx.c b/drivers/staging/wfx/hif_tx.c index 893b67f2f792..5110f9b93762 100644 --- a/drivers/staging/wfx/hif_tx.c +++ b/drivers/staging/wfx/hif_tx.c @@ -240,7 +240,7 @@ int hif_write_mib(struct wfx_dev *wdev, int vif_id, u16 mib_id, } int hif_scan(struct wfx_vif *wvif, struct cfg80211_scan_request *req, - int chan_start_idx, int chan_num) + int chan_start_idx, int chan_num, int *timeout) { int ret, i; struct hif_msg *hif; @@ -289,11 +289,13 @@ int hif_scan(struct wfx_vif *wvif, struct cfg80211_scan_request *req, tmo_chan_fg = 512 * USEC_PER_TU + body->probe_delay; tmo_chan_fg *= body->num_of_probe_requests; tmo = chan_num * max(tmo_chan_bg, tmo_chan_fg) + 512 * USEC_PER_TU; + if (timeout) + *timeout = usecs_to_jiffies(tmo); wfx_fill_header(hif, wvif->id, HIF_REQ_ID_START_SCAN, buf_len); ret = wfx_cmd_send(wvif->wdev, hif, NULL, 0, false); kfree(hif); - return ret ? ret : usecs_to_jiffies(tmo); + return ret; } int hif_stop_scan(struct wfx_vif *wvif) diff --git a/drivers/staging/wfx/hif_tx.h b/drivers/staging/wfx/hif_tx.h index e9eca9330178..e1da28aef706 100644 --- a/drivers/staging/wfx/hif_tx.h +++ b/drivers/staging/wfx/hif_tx.h @@ -42,7 +42,7 @@ int hif_read_mib(struct wfx_dev *wdev, int vif_id, u16 mib_id, int hif_write_mib(struct wfx_dev *wdev, int vif_id, u16 mib_id, void *buf, size_t buf_size); int hif_scan(struct wfx_vif *wvif, struct cfg80211_scan_request *req80211, - int chan_start, int chan_num); + int chan_start, int chan_num, int *timeout); int hif_stop_scan(struct wfx_vif *wvif); int hif_join(struct wfx_vif *wvif, const struct ieee80211_bss_conf *conf, struct ieee80211_channel *channel, const u8 *ssid, int ssidlen); diff --git a/drivers/staging/wfx/queue.c b/drivers/staging/wfx/queue.c index 3248ecefda56..93ea2b72febd 100644 --- a/drivers/staging/wfx/queue.c +++ b/drivers/staging/wfx/queue.c @@ -246,7 +246,7 @@ static struct sk_buff *wfx_tx_queues_get_skb(struct wfx_dev *wdev) for (i = 0; i < IEEE80211_NUM_ACS; i++) { sorted_queues[i] = &wdev->tx_queue[i]; for (j = i; j > 0; j--) - if (atomic_read(&sorted_queues[j]->pending_frames) > + if (atomic_read(&sorted_queues[j]->pending_frames) < atomic_read(&sorted_queues[j - 1]->pending_frames)) swap(sorted_queues[j - 1], sorted_queues[j]); } @@ -291,15 +291,12 @@ struct hif_msg *wfx_tx_queues_get(struct wfx_dev *wdev) if (atomic_read(&wdev->tx_lock)) return NULL; - - for (;;) { - skb = wfx_tx_queues_get_skb(wdev); - if (!skb) - return NULL; - skb_queue_tail(&wdev->tx_pending, skb); - wake_up(&wdev->tx_dequeue); - tx_priv = wfx_skb_tx_priv(skb); - tx_priv->xmit_timestamp = ktime_get(); - return (struct hif_msg *)skb->data; - } + skb = wfx_tx_queues_get_skb(wdev); + if (!skb) + return NULL; + skb_queue_tail(&wdev->tx_pending, skb); + wake_up(&wdev->tx_dequeue); + tx_priv = wfx_skb_tx_priv(skb); + tx_priv->xmit_timestamp = ktime_get(); + return (struct hif_msg *)skb->data; } diff --git a/drivers/staging/wfx/scan.c b/drivers/staging/wfx/scan.c index 57ea9997800b..e9de19784865 100644 --- a/drivers/staging/wfx/scan.c +++ b/drivers/staging/wfx/scan.c @@ -56,10 +56,10 @@ static int send_scan_req(struct wfx_vif *wvif, wfx_tx_lock_flush(wvif->wdev); wvif->scan_abort = false; reinit_completion(&wvif->scan_complete); - timeout = hif_scan(wvif, req, start_idx, i - start_idx); - if (timeout < 0) { + ret = hif_scan(wvif, req, start_idx, i - start_idx, &timeout); + if (ret) { wfx_tx_unlock(wvif->wdev); - return timeout; + return -EIO; } ret = wait_for_completion_timeout(&wvif->scan_complete, timeout); if (req->channels[start_idx]->max_power != wvif->vif->bss_conf.txpower) diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index 9e124020519f..6c0e1b053126 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -123,12 +123,12 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, { int i; - for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) { - if (power > cpufreq_cdev->em->table[i].power) + for (i = cpufreq_cdev->max_level; i >= 0; i--) { + if (power >= cpufreq_cdev->em->table[i].power) break; } - return cpufreq_cdev->em->table[i + 1].frequency; + return cpufreq_cdev->em->table[i].frequency; } /** diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index e761c9b42217..1b84ea674edb 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -649,7 +649,7 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match); static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data) { struct device_node *np; - int ret; + int ret = 0; data->policy = cpufreq_cpu_get(0); if (!data->policy) { @@ -664,11 +664,12 @@ static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data) if (IS_ERR(data->cdev)) { ret = PTR_ERR(data->cdev); cpufreq_cpu_put(data->policy); - return ret; } } - return 0; + of_node_put(np); + + return ret; } static void imx_thermal_unregister_legacy_cooling(struct imx_thermal_data *data) diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c index 76e30603d4d5..6b7ef1993d7e 100644 --- a/drivers/thermal/mtk_thermal.c +++ b/drivers/thermal/mtk_thermal.c @@ -211,6 +211,9 @@ enum { /* The total number of temperature sensors in the MT8183 */ #define MT8183_NUM_SENSORS 6 +/* The number of banks in the MT8183 */ +#define MT8183_NUM_ZONES 1 + /* The number of sensing points per bank */ #define MT8183_NUM_SENSORS_PER_ZONE 6 @@ -497,7 +500,7 @@ static const struct mtk_thermal_data mt7622_thermal_data = { */ static const struct mtk_thermal_data mt8183_thermal_data = { .auxadc_channel = MT8183_TEMP_AUXADC_CHANNEL, - .num_banks = MT8183_NUM_SENSORS_PER_ZONE, + .num_banks = MT8183_NUM_ZONES, .num_sensors = MT8183_NUM_SENSORS, .vts_index = mt8183_vts_index, .cali_val = MT8183_CALIBRATION, diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index 8d3e94d2a9ed..39c4462e38f6 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -382,7 +382,7 @@ static inline u32 masked_irq(u32 hw_id, u32 mask, enum tsens_ver ver) * * Return: IRQ_HANDLED */ -irqreturn_t tsens_critical_irq_thread(int irq, void *data) +static irqreturn_t tsens_critical_irq_thread(int irq, void *data) { struct tsens_priv *priv = data; struct tsens_irq_data d; @@ -452,7 +452,7 @@ irqreturn_t tsens_critical_irq_thread(int irq, void *data) * * Return: IRQ_HANDLED */ -irqreturn_t tsens_irq_thread(int irq, void *data) +static irqreturn_t tsens_irq_thread(int irq, void *data) { struct tsens_priv *priv = data; struct tsens_irq_data d; @@ -520,7 +520,7 @@ irqreturn_t tsens_irq_thread(int irq, void *data) return IRQ_HANDLED; } -int tsens_set_trips(void *_sensor, int low, int high) +static int tsens_set_trips(void *_sensor, int low, int high) { struct tsens_sensor *s = _sensor; struct tsens_priv *priv = s->priv; @@ -557,7 +557,7 @@ int tsens_set_trips(void *_sensor, int low, int high) return 0; } -int tsens_enable_irq(struct tsens_priv *priv) +static int tsens_enable_irq(struct tsens_priv *priv) { int ret; int val = tsens_version(priv) > VER_1_X ? 7 : 1; @@ -570,7 +570,7 @@ int tsens_enable_irq(struct tsens_priv *priv) return ret; } -void tsens_disable_irq(struct tsens_priv *priv) +static void tsens_disable_irq(struct tsens_priv *priv) { regmap_field_write(priv->rf[INT_EN], 0); } diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c index 58fe7c1ef00b..c48c5e9b8f20 100644 --- a/drivers/thermal/rcar_gen3_thermal.c +++ b/drivers/thermal/rcar_gen3_thermal.c @@ -167,7 +167,7 @@ static int rcar_gen3_thermal_get_temp(void *devdata, int *temp) { struct rcar_gen3_thermal_tsc *tsc = devdata; int mcelsius, val; - u32 reg; + int reg; /* Read register and convert to mili Celsius */ reg = rcar_gen3_thermal_read(tsc, REG_GEN3_TEMP) & CTEMP_MASK; diff --git a/drivers/thermal/sprd_thermal.c b/drivers/thermal/sprd_thermal.c index a340374e8c51..4cde70dcf655 100644 --- a/drivers/thermal/sprd_thermal.c +++ b/drivers/thermal/sprd_thermal.c @@ -348,8 +348,8 @@ static int sprd_thm_probe(struct platform_device *pdev) thm->var_data = pdata; thm->base = devm_platform_ioremap_resource(pdev, 0); - if (!thm->base) - return -ENOMEM; + if (IS_ERR(thm->base)) + return PTR_ERR(thm->base); thm->nr_sensors = of_get_child_count(np); if (thm->nr_sensors == 0 || thm->nr_sensors > SPRD_THM_MAX_SENSOR) { diff --git a/drivers/tty/serial/kgdb_nmi.c b/drivers/tty/serial/kgdb_nmi.c index 5022447afa23..6004c0c1d173 100644 --- a/drivers/tty/serial/kgdb_nmi.c +++ b/drivers/tty/serial/kgdb_nmi.c @@ -50,7 +50,7 @@ static int kgdb_nmi_console_setup(struct console *co, char *options) * I/O utilities that messages sent to the console will automatically * be displayed on the dbg_io. */ - dbg_io_ops->is_console = true; + dbg_io_ops->cons = co; return 0; } diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 41396982e9e0..84ffede27f23 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -45,7 +45,6 @@ static struct platform_device *kgdboc_pdev; #if IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) static struct kgdb_io kgdboc_earlycon_io_ops; -static struct console *earlycon; static int (*earlycon_orig_exit)(struct console *con); #endif /* IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */ @@ -145,7 +144,7 @@ static void kgdboc_unregister_kbd(void) #if IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) static void cleanup_earlycon(void) { - if (earlycon) + if (kgdboc_earlycon_io_ops.cons) kgdb_unregister_io_module(&kgdboc_earlycon_io_ops); } #else /* !IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */ @@ -178,7 +177,7 @@ static int configure_kgdboc(void) goto noconfig; } - kgdboc_io_ops.is_console = 0; + kgdboc_io_ops.cons = NULL; kgdb_tty_driver = NULL; kgdboc_use_kms = 0; @@ -198,7 +197,7 @@ static int configure_kgdboc(void) int idx; if (cons->device && cons->device(cons, &idx) == p && idx == tty_line) { - kgdboc_io_ops.is_console = 1; + kgdboc_io_ops.cons = cons; break; } } @@ -433,7 +432,8 @@ static int kgdboc_earlycon_get_char(void) { char c; - if (!earlycon->read(earlycon, &c, 1)) + if (!kgdboc_earlycon_io_ops.cons->read(kgdboc_earlycon_io_ops.cons, + &c, 1)) return NO_POLL_CHAR; return c; @@ -441,7 +441,8 @@ static int kgdboc_earlycon_get_char(void) static void kgdboc_earlycon_put_char(u8 chr) { - earlycon->write(earlycon, &chr, 1); + kgdboc_earlycon_io_ops.cons->write(kgdboc_earlycon_io_ops.cons, &chr, + 1); } static void kgdboc_earlycon_pre_exp_handler(void) @@ -461,7 +462,7 @@ static void kgdboc_earlycon_pre_exp_handler(void) * boot if we detect this case. */ for_each_console(con) - if (con == earlycon) + if (con == kgdboc_earlycon_io_ops.cons) return; already_warned = true; @@ -484,25 +485,25 @@ static int kgdboc_earlycon_deferred_exit(struct console *con) static void kgdboc_earlycon_deinit(void) { - if (!earlycon) + if (!kgdboc_earlycon_io_ops.cons) return; - if (earlycon->exit == kgdboc_earlycon_deferred_exit) + if (kgdboc_earlycon_io_ops.cons->exit == kgdboc_earlycon_deferred_exit) /* * kgdboc_earlycon is exiting but original boot console exit * was never called (AKA kgdboc_earlycon_deferred_exit() * didn't ever run). Undo our trap. */ - earlycon->exit = earlycon_orig_exit; - else if (earlycon->exit) + kgdboc_earlycon_io_ops.cons->exit = earlycon_orig_exit; + else if (kgdboc_earlycon_io_ops.cons->exit) /* * We skipped calling the exit() routine so we could try to * keep using the boot console even after it went away. We're * finally done so call the function now. */ - earlycon->exit(earlycon); + kgdboc_earlycon_io_ops.cons->exit(kgdboc_earlycon_io_ops.cons); - earlycon = NULL; + kgdboc_earlycon_io_ops.cons = NULL; } static struct kgdb_io kgdboc_earlycon_io_ops = { @@ -511,7 +512,6 @@ static struct kgdb_io kgdboc_earlycon_io_ops = { .write_char = kgdboc_earlycon_put_char, .pre_exception = kgdboc_earlycon_pre_exp_handler, .deinit = kgdboc_earlycon_deinit, - .is_console = true, }; #define MAX_CONSOLE_NAME_LEN (sizeof((struct console *) 0)->name) @@ -557,10 +557,10 @@ static int __init kgdboc_earlycon_init(char *opt) goto unlock; } - earlycon = con; + kgdboc_earlycon_io_ops.cons = con; pr_info("Going to register kgdb with earlycon '%s'\n", con->name); if (kgdb_register_io_module(&kgdboc_earlycon_io_ops) != 0) { - earlycon = NULL; + kgdboc_earlycon_io_ops.cons = NULL; pr_info("Failed to register kgdb with earlycon\n"); } else { /* Trap exit so we can keep earlycon longer if needed. */ diff --git a/drivers/usb/cdns3/ep0.c b/drivers/usb/cdns3/ep0.c index 82645a2a0f52..61ec5bb2b0ca 100644 --- a/drivers/usb/cdns3/ep0.c +++ b/drivers/usb/cdns3/ep0.c @@ -327,7 +327,8 @@ static int cdns3_ep0_feature_handle_device(struct cdns3_device *priv_dev, if (!set || (tmode & 0xff) != 0) return -EINVAL; - switch (tmode >> 8) { + tmode >>= 8; + switch (tmode) { case TEST_J: case TEST_K: case TEST_SE0_NAK: @@ -704,15 +705,17 @@ static int cdns3_gadget_ep0_queue(struct usb_ep *ep, int ret = 0; u8 zlp = 0; + spin_lock_irqsave(&priv_dev->lock, flags); trace_cdns3_ep0_queue(priv_dev, request); /* cancel the request if controller receive new SETUP packet. */ - if (cdns3_check_new_setup(priv_dev)) + if (cdns3_check_new_setup(priv_dev)) { + spin_unlock_irqrestore(&priv_dev->lock, flags); return -ECONNRESET; + } /* send STATUS stage. Should be called only for SET_CONFIGURATION */ if (priv_dev->ep0_stage == CDNS3_STATUS_STAGE) { - spin_lock_irqsave(&priv_dev->lock, flags); cdns3_select_ep(priv_dev, 0x00); erdy_sent = !priv_dev->hw_configured_flag; @@ -737,7 +740,6 @@ static int cdns3_gadget_ep0_queue(struct usb_ep *ep, return 0; } - spin_lock_irqsave(&priv_dev->lock, flags); if (!list_empty(&priv_ep->pending_req_list)) { dev_err(priv_dev->dev, "can't handle multiple requests for ep0\n"); diff --git a/drivers/usb/cdns3/trace.h b/drivers/usb/cdns3/trace.h index 8d121e207fd8..755c56582257 100644 --- a/drivers/usb/cdns3/trace.h +++ b/drivers/usb/cdns3/trace.h @@ -156,7 +156,7 @@ DECLARE_EVENT_CLASS(cdns3_log_ep0_irq, __dynamic_array(char, str, CDNS3_MSG_MAX) ), TP_fast_assign( - __entry->ep_dir = priv_dev->ep0_data_dir; + __entry->ep_dir = priv_dev->selected_ep; __entry->ep_sts = ep_sts; ), TP_printk("%s", cdns3_decode_ep0_irq(__get_str(str), diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index f67088bb8218..d5187b50fc82 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1689,6 +1689,8 @@ static int acm_pre_reset(struct usb_interface *intf) static const struct usb_device_id acm_ids[] = { /* quirky and broken devices */ + { USB_DEVICE(0x0424, 0x274e), /* Microchip Technology, Inc. (formerly SMSC) */ + .driver_info = DISABLE_ECHO, }, /* DISABLE ECHO in termios flag */ { USB_DEVICE(0x076d, 0x0006), /* Denso Cradle CU-321 */ .driver_info = NO_UNION_NORMAL, },/* has no union descriptor */ { USB_DEVICE(0x17ef, 0x7000), /* Lenovo USB modem */ diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 3e8efe759c3e..e0b77674869c 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -218,11 +218,12 @@ static const struct usb_device_id usb_quirk_list[] = { /* Logitech HD Webcam C270 */ { USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME }, - /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */ + /* Logitech HD Pro Webcams C920, C920-C, C922, C925e and C930e */ { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x046d, 0x085c), .driver_info = USB_QUIRK_DELAY_INIT }, /* Logitech ConferenceCam CC3000e */ { USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 12b98b466287..7faf5f8c056d 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -4920,12 +4920,6 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg) epnum, 0); } - ret = usb_add_gadget_udc(dev, &hsotg->gadget); - if (ret) { - dwc2_hsotg_ep_free_request(&hsotg->eps_out[0]->ep, - hsotg->ctrl_req); - return ret; - } dwc2_hsotg_dump(hsotg); return 0; diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index e571c8ae65ec..c347d93eae64 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -575,6 +575,17 @@ static int dwc2_driver_probe(struct platform_device *dev) if (hsotg->dr_mode == USB_DR_MODE_PERIPHERAL) dwc2_lowlevel_hw_disable(hsotg); +#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \ + IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE) + /* Postponed adding a new gadget to the udc class driver list */ + if (hsotg->gadget_enabled) { + retval = usb_add_gadget_udc(hsotg->dev, &hsotg->gadget); + if (retval) { + dwc2_hsotg_remove(hsotg); + goto error_init; + } + } +#endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */ return 0; error_init: diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 48b68b6f0dc8..90bb022737da 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -162,12 +162,6 @@ static const struct dwc3_exynos_driverdata exynos5250_drvdata = { .suspend_clk_idx = -1, }; -static const struct dwc3_exynos_driverdata exynos5420_drvdata = { - .clk_names = { "usbdrd30", "usbdrd30_susp_clk"}, - .num_clks = 2, - .suspend_clk_idx = 1, -}; - static const struct dwc3_exynos_driverdata exynos5433_drvdata = { .clk_names = { "aclk", "susp_clk", "pipe_pclk", "phyclk" }, .num_clks = 4, @@ -185,9 +179,6 @@ static const struct of_device_id exynos_dwc3_match[] = { .compatible = "samsung,exynos5250-dwusb3", .data = &exynos5250_drvdata, }, { - .compatible = "samsung,exynos5420-dwusb3", - .data = &exynos5420_drvdata, - }, { .compatible = "samsung,exynos5433-dwusb3", .data = &exynos5433_drvdata, }, { diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index b67372737dc9..96c05b121fac 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -206,8 +206,10 @@ static void dwc3_pci_resume_work(struct work_struct *work) int ret; ret = pm_runtime_get_sync(&dwc3->dev); - if (ret) + if (ret) { + pm_runtime_put_sync_autosuspend(&dwc3->dev); return; + } pm_runtime_mark_last_busy(&dwc3->dev); pm_runtime_put_sync_autosuspend(&dwc3->dev); diff --git a/drivers/usb/early/ehci-dbgp.c b/drivers/usb/early/ehci-dbgp.c index ea0d531c63e2..775cf70cfb3e 100644 --- a/drivers/usb/early/ehci-dbgp.c +++ b/drivers/usb/early/ehci-dbgp.c @@ -1058,7 +1058,8 @@ static int __init kgdbdbgp_parse_config(char *str) kgdbdbgp_wait_time = simple_strtoul(ptr, &ptr, 10); } kgdb_register_io_module(&kgdbdbgp_io_ops); - kgdbdbgp_io_ops.is_console = early_dbgp_console.index != -1; + if (early_dbgp_console.index != -1) + kgdbdbgp_io_ops.cons = &early_dbgp_console; return 0; } diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index cafde053788b..80a1b52c656e 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -2313,7 +2313,8 @@ static int mv_udc_probe(struct platform_device *pdev) return 0; err_create_workqueue: - destroy_workqueue(udc->qwork); + if (udc->qwork) + destroy_workqueue(udc->qwork); err_destroy_dma: dma_pool_destroy(udc->dtd_pool); err_free_dma: diff --git a/drivers/usb/host/ehci-exynos.c b/drivers/usb/host/ehci-exynos.c index a4e9abcbdc4f..1a9b7572e17f 100644 --- a/drivers/usb/host/ehci-exynos.c +++ b/drivers/usb/host/ehci-exynos.c @@ -203,9 +203,8 @@ static int exynos_ehci_probe(struct platform_device *pdev) hcd->rsrc_len = resource_size(res); irq = platform_get_irq(pdev, 0); - if (!irq) { - dev_err(&pdev->dev, "Failed to get IRQ\n"); - err = -ENODEV; + if (irq < 0) { + err = irq; goto fail_io; } diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 3c3820ad9092..af3c1b9b38b2 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -216,6 +216,13 @@ static int ehci_pci_setup(struct usb_hcd *hcd) ehci_info(ehci, "applying MosChip frame-index workaround\n"); ehci->frame_index_bug = 1; break; + case PCI_VENDOR_ID_HUAWEI: + /* Synopsys HC bug */ + if (pdev->device == 0xa239) { + ehci_info(ehci, "applying Synopsys HC workaround\n"); + ehci->has_synopsys_hc_bug = 1; + } + break; } /* optional debug port, normally in the first BAR */ diff --git a/drivers/usb/host/ohci-sm501.c b/drivers/usb/host/ohci-sm501.c index cff965240327..b91d50da6127 100644 --- a/drivers/usb/host/ohci-sm501.c +++ b/drivers/usb/host/ohci-sm501.c @@ -191,6 +191,7 @@ static int ohci_hcd_sm501_drv_remove(struct platform_device *pdev) struct resource *mem; usb_remove_hcd(hcd); + iounmap(hcd->regs); release_mem_region(hcd->rsrc_start, hcd->rsrc_len); usb_put_hcd(hcd); mem = platform_get_resource(pdev, IORESOURCE_MEM, 1); diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index bfbdb3ceed29..4311d4c9b68d 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -587,6 +587,9 @@ static int xhci_mtk_remove(struct platform_device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct usb_hcd *shared_hcd = xhci->shared_hcd; + pm_runtime_put_noidle(&dev->dev); + pm_runtime_disable(&dev->dev); + usb_remove_hcd(shared_hcd); xhci->shared_hcd = NULL; device_init_wakeup(&dev->dev, false); @@ -597,8 +600,6 @@ static int xhci_mtk_remove(struct platform_device *dev) xhci_mtk_sch_exit(mtk); xhci_mtk_clks_disable(mtk); xhci_mtk_ldos_disable(mtk); - pm_runtime_put_sync(&dev->dev); - pm_runtime_disable(&dev->dev); return 0; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index bee5deccc83d..ed468eed299c 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1430,6 +1430,7 @@ static int xhci_check_maxpacket(struct xhci_hcd *xhci, unsigned int slot_id, xhci->devs[slot_id]->out_ctx, ep_index); ep_ctx = xhci_get_ep_ctx(xhci, command->in_ctx, ep_index); + ep_ctx->ep_info &= cpu_to_le32(~EP_STATE_MASK);/* must clear */ ep_ctx->ep_info2 &= cpu_to_le32(~MAX_PACKET_MASK); ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet_size)); @@ -4390,6 +4391,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, int hird, exit_latency; int ret; + if (xhci->quirks & XHCI_HW_LPM_DISABLE) + return -EPERM; + if (hcd->speed >= HCD_USB3 || !xhci->hw_lpm_support || !udev->lpm_capable) return -EPERM; @@ -4412,7 +4416,7 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, xhci_dbg(xhci, "%s port %d USB2 hardware LPM\n", enable ? "enable" : "disable", port_num + 1); - if (enable && !(xhci->quirks & XHCI_HW_LPM_DISABLE)) { + if (enable) { /* Host supports BESL timeout instead of HIRD */ if (udev->usb2_hw_lpm_besl_capable) { /* if device doesn't have a preferred BESL value use a @@ -4471,6 +4475,9 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd, mutex_lock(hcd->bandwidth_mutex); xhci_change_max_exit_latency(xhci, udev, 0); mutex_unlock(hcd->bandwidth_mutex); + readl_poll_timeout(ports[port_num]->addr, pm_val, + (pm_val & PORT_PLS_MASK) == XDEV_U0, + 100, 10000); return 0; } } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 2c6c4f8d1ee1..c295e8a7f5ae 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -716,7 +716,7 @@ struct xhci_ep_ctx { * 4 - TRB error * 5-7 - reserved */ -#define EP_STATE_MASK (0xf) +#define EP_STATE_MASK (0x7) #define EP_STATE_DISABLED 0 #define EP_STATE_RUNNING 1 #define EP_STATE_HALTED 2 diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index 98ada1a3425c..bae88893ee8e 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -2873,6 +2873,7 @@ static void usbtest_disconnect(struct usb_interface *intf) usb_set_intfdata(intf, NULL); dev_dbg(&intf->dev, "disconnect\n"); + kfree(dev->buf); kfree(dev); } diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index cffe2aced488..03a333797382 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -1199,11 +1199,7 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) platform_set_drvdata(pdev, tegra_phy); - err = usb_add_phy_dev(&tegra_phy->u_phy); - if (err) - return err; - - return 0; + return usb_add_phy_dev(&tegra_phy->u_phy); } static int tegra_usb_phy_remove(struct platform_device *pdev) diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 01c6a48c41bc..ac9a81ae8216 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -803,7 +803,8 @@ static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map) return info->dma_map_ctrl(chan->device->dev, pkt, map); } -static void usbhsf_dma_complete(void *arg); +static void usbhsf_dma_complete(void *arg, + const struct dmaengine_result *result); static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt) { struct usbhs_pipe *pipe = pkt->pipe; @@ -813,6 +814,7 @@ static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt) struct dma_chan *chan; struct device *dev = usbhs_priv_to_dev(priv); enum dma_transfer_direction dir; + dma_cookie_t cookie; fifo = usbhs_pipe_to_fifo(pipe); if (!fifo) @@ -827,11 +829,11 @@ static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt) if (!desc) return; - desc->callback = usbhsf_dma_complete; - desc->callback_param = pipe; + desc->callback_result = usbhsf_dma_complete; + desc->callback_param = pkt; - pkt->cookie = dmaengine_submit(desc); - if (pkt->cookie < 0) { + cookie = dmaengine_submit(desc); + if (cookie < 0) { dev_err(dev, "Failed to submit dma descriptor\n"); return; } @@ -1152,12 +1154,10 @@ static size_t usbhs_dma_calc_received_size(struct usbhs_pkt *pkt, struct dma_chan *chan, int dtln) { struct usbhs_pipe *pipe = pkt->pipe; - struct dma_tx_state state; size_t received_size; int maxp = usbhs_pipe_get_maxpacket(pipe); - dmaengine_tx_status(chan, pkt->cookie, &state); - received_size = pkt->length - state.residue; + received_size = pkt->length - pkt->dma_result->residue; if (dtln) { received_size -= USBHS_USB_DMAC_XFER_SIZE; @@ -1363,13 +1363,16 @@ static int usbhsf_irq_ready(struct usbhs_priv *priv, return 0; } -static void usbhsf_dma_complete(void *arg) +static void usbhsf_dma_complete(void *arg, + const struct dmaengine_result *result) { - struct usbhs_pipe *pipe = arg; + struct usbhs_pkt *pkt = arg; + struct usbhs_pipe *pipe = pkt->pipe; struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); struct device *dev = usbhs_priv_to_dev(priv); int ret; + pkt->dma_result = result; ret = usbhsf_pkt_handler(pipe, USBHSF_PKT_DMA_DONE); if (ret < 0) dev_err(dev, "dma_complete run_error %d : %d\n", diff --git a/drivers/usb/renesas_usbhs/fifo.h b/drivers/usb/renesas_usbhs/fifo.h index 7d3700bf41d9..039a2b993157 100644 --- a/drivers/usb/renesas_usbhs/fifo.h +++ b/drivers/usb/renesas_usbhs/fifo.h @@ -50,7 +50,7 @@ struct usbhs_pkt { struct usbhs_pkt *pkt); struct work_struct work; dma_addr_t dma; - dma_cookie_t cookie; + const struct dmaengine_result *dma_result; void *buf; int length; int trans; diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index 962bc69a6a59..70ddc9d6d49e 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -148,7 +148,8 @@ pmc_usb_mux_dp_hpd(struct pmc_usb_port *port, struct typec_mux_state *state) msg[0] = PMC_USB_DP_HPD; msg[0] |= port->usb3_port << PMC_USB_MSG_USB3_PORT_SHIFT; - msg[1] = PMC_USB_DP_HPD_IRQ; + if (data->status & DP_STATUS_IRQ_HPD) + msg[1] = PMC_USB_DP_HPD_IRQ; if (data->status & DP_STATUS_HPD_STATE) msg[1] |= PMC_USB_DP_HPD_LVL; @@ -161,6 +162,7 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state) { struct typec_displayport_data *data = state->data; struct altmode_req req = { }; + int ret; if (data->status & DP_STATUS_IRQ_HPD) return pmc_usb_mux_dp_hpd(port, state); @@ -181,7 +183,14 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state) if (data->status & DP_STATUS_HPD_STATE) req.mode_data |= PMC_USB_ALTMODE_HPD_HIGH; - return pmc_usb_command(port, (void *)&req, sizeof(req)); + ret = pmc_usb_command(port, (void *)&req, sizeof(req)); + if (ret) + return ret; + + if (data->status & DP_STATUS_HPD_STATE) + return pmc_usb_mux_dp_hpd(port, state); + + return 0; } static int diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c index 017389021b96..b56a0880a044 100644 --- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c +++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c @@ -179,26 +179,6 @@ out: return tcpci_irq(chip->tcpci); } -static int rt1711h_init_alert(struct rt1711h_chip *chip, - struct i2c_client *client) -{ - int ret; - - /* Disable chip interrupts before requesting irq */ - ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0); - if (ret < 0) - return ret; - - ret = devm_request_threaded_irq(chip->dev, client->irq, NULL, - rt1711h_irq, - IRQF_ONESHOT | IRQF_TRIGGER_LOW, - dev_name(chip->dev), chip); - if (ret < 0) - return ret; - enable_irq_wake(client->irq); - return 0; -} - static int rt1711h_sw_reset(struct rt1711h_chip *chip) { int ret; @@ -260,7 +240,8 @@ static int rt1711h_probe(struct i2c_client *client, if (ret < 0) return ret; - ret = rt1711h_init_alert(chip, client); + /* Disable chip interrupts before requesting irq */ + ret = rt1711h_write16(chip, TCPC_ALERT_MASK, 0); if (ret < 0) return ret; @@ -271,6 +252,14 @@ static int rt1711h_probe(struct i2c_client *client, if (IS_ERR_OR_NULL(chip->tcpci)) return PTR_ERR(chip->tcpci); + ret = devm_request_threaded_irq(chip->dev, client->irq, NULL, + rt1711h_irq, + IRQF_ONESHOT | IRQF_TRIGGER_LOW, + dev_name(chip->dev), chip); + if (ret < 0) + return ret; + enable_irq_wake(client->irq); + return 0; } diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 7c0779018b1b..f634c81998bb 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -521,10 +521,14 @@ static void vfio_pci_release(void *device_data) vfio_pci_vf_token_user_add(vdev, -1); vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_disable(vdev); - if (vdev->err_trigger) + if (vdev->err_trigger) { eventfd_ctx_put(vdev->err_trigger); - if (vdev->req_trigger) + vdev->err_trigger = NULL; + } + if (vdev->req_trigger) { eventfd_ctx_put(vdev->req_trigger); + vdev->req_trigger = NULL; + } } mutex_unlock(&vdev->reflck->lock); diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 8746c943247a..d98843feddce 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -398,9 +398,15 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write) /* Caller should hold memory_lock semaphore */ bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) { + struct pci_dev *pdev = vdev->pdev; u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); - return cmd & PCI_COMMAND_MEMORY; + /* + * SR-IOV VF memory enable is handled by the MSE bit in the + * PF SR-IOV capability, there's therefore no need to trigger + * faults based on the virtual value. + */ + return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY); } /* @@ -1728,6 +1734,15 @@ int vfio_config_init(struct vfio_pci_device *vdev) vconfig[PCI_INTERRUPT_PIN]); vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ + + /* + * VFs do no implement the memory enable bit of the COMMAND + * register therefore we'll not have it set in our initial + * copy of config space after pci_enable_device(). For + * consistency with PFs, set the virtual enable bit here. + */ + *(__le16 *)&vconfig[PCI_COMMAND] |= + cpu_to_le16(PCI_COMMAND_MEMORY); } if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 9d28a8e3328f..e2a490c5ae08 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2402,7 +2402,8 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) ops->graphics = 1; if (!blank) { - var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE; + var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE | + FB_ACTIVATE_KD_TEXT; fb_set_var(info, &var); ops->graphics = 0; ops->var = info->var; diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index bee29aadc646..def14ac0ebe1 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1836,7 +1836,7 @@ static int uvesafb_setup(char *options) else if (!strcmp(this_opt, "noedid")) noedid = true; else if (!strcmp(this_opt, "noblank")) - blank = true; + blank = false; else if (!strncmp(this_opt, "vtotal:", 7)) vram_total = simple_strtoul(this_opt + 7, NULL, 0); else if (!strncmp(this_opt, "vremap:", 7)) diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 040d2a43e8e3..4f168b46fbca 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -69,11 +69,27 @@ struct xenbus_map_node { unsigned int nr_handles; }; +struct map_ring_valloc { + struct xenbus_map_node *node; + + /* Why do we need two arrays? See comment of __xenbus_map_ring */ + union { + unsigned long addrs[XENBUS_MAX_RING_GRANTS]; + pte_t *ptes[XENBUS_MAX_RING_GRANTS]; + }; + phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS]; + + struct gnttab_map_grant_ref map[XENBUS_MAX_RING_GRANTS]; + struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS]; + + unsigned int idx; /* HVM only. */ +}; + static DEFINE_SPINLOCK(xenbus_valloc_lock); static LIST_HEAD(xenbus_valloc_pages); struct xenbus_ring_ops { - int (*map)(struct xenbus_device *dev, + int (*map)(struct xenbus_device *dev, struct map_ring_valloc *info, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr); int (*unmap)(struct xenbus_device *dev, void *vaddr); @@ -440,8 +456,7 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn); * Map @nr_grefs pages of memory into this domain from another * domain's grant table. xenbus_map_ring_valloc allocates @nr_grefs * pages of virtual address space, maps the pages to that address, and - * sets *vaddr to that address. Returns 0 on success, and GNTST_* - * (see xen/include/interface/grant_table.h) or -ENOMEM / -EINVAL on + * sets *vaddr to that address. Returns 0 on success, and -errno on * error. If an error is returned, device will switch to * XenbusStateClosing and the error message will be saved in XenStore. */ @@ -449,12 +464,25 @@ int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr) { int err; + struct map_ring_valloc *info; + + *vaddr = NULL; + + if (nr_grefs > XENBUS_MAX_RING_GRANTS) + return -EINVAL; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; - err = ring_ops->map(dev, gnt_refs, nr_grefs, vaddr); - /* Some hypervisors are buggy and can return 1. */ - if (err > 0) - err = GNTST_general_error; + info->node = kzalloc(sizeof(*info->node), GFP_KERNEL); + if (!info->node) + err = -ENOMEM; + else + err = ring_ops->map(dev, info, gnt_refs, nr_grefs, vaddr); + kfree(info->node); + kfree(info); return err; } EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc); @@ -466,62 +494,57 @@ static int __xenbus_map_ring(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, grant_handle_t *handles, - phys_addr_t *addrs, + struct map_ring_valloc *info, unsigned int flags, bool *leaked) { - struct gnttab_map_grant_ref map[XENBUS_MAX_RING_GRANTS]; - struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS]; int i, j; - int err = GNTST_okay; if (nr_grefs > XENBUS_MAX_RING_GRANTS) return -EINVAL; for (i = 0; i < nr_grefs; i++) { - memset(&map[i], 0, sizeof(map[i])); - gnttab_set_map_op(&map[i], addrs[i], flags, gnt_refs[i], - dev->otherend_id); + gnttab_set_map_op(&info->map[i], info->phys_addrs[i], flags, + gnt_refs[i], dev->otherend_id); handles[i] = INVALID_GRANT_HANDLE; } - gnttab_batch_map(map, i); + gnttab_batch_map(info->map, i); for (i = 0; i < nr_grefs; i++) { - if (map[i].status != GNTST_okay) { - err = map[i].status; - xenbus_dev_fatal(dev, map[i].status, + if (info->map[i].status != GNTST_okay) { + xenbus_dev_fatal(dev, info->map[i].status, "mapping in shared page %d from domain %d", gnt_refs[i], dev->otherend_id); goto fail; } else - handles[i] = map[i].handle; + handles[i] = info->map[i].handle; } - return GNTST_okay; + return 0; fail: for (i = j = 0; i < nr_grefs; i++) { if (handles[i] != INVALID_GRANT_HANDLE) { - memset(&unmap[j], 0, sizeof(unmap[j])); - gnttab_set_unmap_op(&unmap[j], (phys_addr_t)addrs[i], + gnttab_set_unmap_op(&info->unmap[j], + info->phys_addrs[i], GNTMAP_host_map, handles[i]); j++; } } - if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, j)) + if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, info->unmap, j)) BUG(); *leaked = false; for (i = 0; i < j; i++) { - if (unmap[i].status != GNTST_okay) { + if (info->unmap[i].status != GNTST_okay) { *leaked = true; break; } } - return err; + return -ENOENT; } /** @@ -566,21 +589,12 @@ static int xenbus_unmap_ring(struct xenbus_device *dev, grant_handle_t *handles, return err; } -struct map_ring_valloc_hvm -{ - unsigned int idx; - - /* Why do we need two arrays? See comment of __xenbus_map_ring */ - phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS]; - unsigned long addrs[XENBUS_MAX_RING_GRANTS]; -}; - static void xenbus_map_ring_setup_grant_hvm(unsigned long gfn, unsigned int goffset, unsigned int len, void *data) { - struct map_ring_valloc_hvm *info = data; + struct map_ring_valloc *info = data; unsigned long vaddr = (unsigned long)gfn_to_virt(gfn); info->phys_addrs[info->idx] = vaddr; @@ -589,39 +603,28 @@ static void xenbus_map_ring_setup_grant_hvm(unsigned long gfn, info->idx++; } -static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, - grant_ref_t *gnt_ref, - unsigned int nr_grefs, - void **vaddr) +static int xenbus_map_ring_hvm(struct xenbus_device *dev, + struct map_ring_valloc *info, + grant_ref_t *gnt_ref, + unsigned int nr_grefs, + void **vaddr) { - struct xenbus_map_node *node; + struct xenbus_map_node *node = info->node; int err; void *addr; bool leaked = false; - struct map_ring_valloc_hvm info = { - .idx = 0, - }; unsigned int nr_pages = XENBUS_PAGES(nr_grefs); - if (nr_grefs > XENBUS_MAX_RING_GRANTS) - return -EINVAL; - - *vaddr = NULL; - - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return -ENOMEM; - err = alloc_xenballooned_pages(nr_pages, node->hvm.pages); if (err) goto out_err; gnttab_foreach_grant(node->hvm.pages, nr_grefs, xenbus_map_ring_setup_grant_hvm, - &info); + info); err = __xenbus_map_ring(dev, gnt_ref, nr_grefs, node->handles, - info.phys_addrs, GNTMAP_host_map, &leaked); + info, GNTMAP_host_map, &leaked); node->nr_handles = nr_grefs; if (err) @@ -641,11 +644,13 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, spin_unlock(&xenbus_valloc_lock); *vaddr = addr; + info->node = NULL; + return 0; out_xenbus_unmap_ring: if (!leaked) - xenbus_unmap_ring(dev, node->handles, nr_grefs, info.addrs); + xenbus_unmap_ring(dev, node->handles, nr_grefs, info->addrs); else pr_alert("leaking %p size %u page(s)", addr, nr_pages); @@ -653,7 +658,6 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, if (!leaked) free_xenballooned_pages(nr_pages, node->hvm.pages); out_err: - kfree(node); return err; } @@ -676,40 +680,30 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr) EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree); #ifdef CONFIG_XEN_PV -static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev, - grant_ref_t *gnt_refs, - unsigned int nr_grefs, - void **vaddr) +static int xenbus_map_ring_pv(struct xenbus_device *dev, + struct map_ring_valloc *info, + grant_ref_t *gnt_refs, + unsigned int nr_grefs, + void **vaddr) { - struct xenbus_map_node *node; + struct xenbus_map_node *node = info->node; struct vm_struct *area; - pte_t *ptes[XENBUS_MAX_RING_GRANTS]; - phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS]; int err = GNTST_okay; int i; bool leaked; - *vaddr = NULL; - - if (nr_grefs > XENBUS_MAX_RING_GRANTS) - return -EINVAL; - - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return -ENOMEM; - - area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, ptes); + area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, info->ptes); if (!area) { kfree(node); return -ENOMEM; } for (i = 0; i < nr_grefs; i++) - phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr; + info->phys_addrs[i] = + arbitrary_virt_to_machine(info->ptes[i]).maddr; err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles, - phys_addrs, - GNTMAP_host_map | GNTMAP_contains_pte, + info, GNTMAP_host_map | GNTMAP_contains_pte, &leaked); if (err) goto failed; @@ -722,6 +716,8 @@ static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev, spin_unlock(&xenbus_valloc_lock); *vaddr = area->addr; + info->node = NULL; + return 0; failed: @@ -730,11 +726,10 @@ failed: else pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs); - kfree(node); return err; } -static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr) +static int xenbus_unmap_ring_pv(struct xenbus_device *dev, void *vaddr) { struct xenbus_map_node *node; struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS]; @@ -798,12 +793,12 @@ static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr) } static const struct xenbus_ring_ops ring_ops_pv = { - .map = xenbus_map_ring_valloc_pv, - .unmap = xenbus_unmap_ring_vfree_pv, + .map = xenbus_map_ring_pv, + .unmap = xenbus_unmap_ring_pv, }; #endif -struct unmap_ring_vfree_hvm +struct unmap_ring_hvm { unsigned int idx; unsigned long addrs[XENBUS_MAX_RING_GRANTS]; @@ -814,19 +809,19 @@ static void xenbus_unmap_ring_setup_grant_hvm(unsigned long gfn, unsigned int len, void *data) { - struct unmap_ring_vfree_hvm *info = data; + struct unmap_ring_hvm *info = data; info->addrs[info->idx] = (unsigned long)gfn_to_virt(gfn); info->idx++; } -static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) +static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr) { int rv; struct xenbus_map_node *node; void *addr; - struct unmap_ring_vfree_hvm info = { + struct unmap_ring_hvm info = { .idx = 0, }; unsigned int nr_pages; @@ -887,8 +882,8 @@ enum xenbus_state xenbus_read_driver_state(const char *path) EXPORT_SYMBOL_GPL(xenbus_read_driver_state); static const struct xenbus_ring_ops ring_ops_hvm = { - .map = xenbus_map_ring_valloc_hvm, - .unmap = xenbus_unmap_ring_vfree_hvm, + .map = xenbus_map_ring_hvm, + .unmap = xenbus_unmap_ring_hvm, }; void __init xenbus_ring_ops_init(void) diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 005921e3b38d..5b79cdceefa0 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -154,10 +154,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, return ERR_PTR(-ENOMEM); } + cell->name = kmalloc(namelen + 1, GFP_KERNEL); + if (!cell->name) { + kfree(cell); + return ERR_PTR(-ENOMEM); + } + cell->net = net; cell->name_len = namelen; for (i = 0; i < namelen; i++) cell->name[i] = tolower(name[i]); + cell->name[i] = 0; atomic_set(&cell->usage, 2); INIT_WORK(&cell->manager, afs_manage_cell); @@ -207,6 +214,7 @@ parse_failed: if (ret == -EINVAL) printk(KERN_ERR "kAFS: bad VL server IP address\n"); error: + kfree(cell->name); kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -489,6 +497,7 @@ static void afs_cell_destroy(struct rcu_head *rcu) afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers)); afs_put_cell(cell->net, cell->alias_of); key_put(cell->anonymous_key); + kfree(cell->name); kfree(cell); _leave(" [destroyed]"); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index d520535ddb62..792ac711985e 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -388,7 +388,7 @@ struct afs_cell { struct afs_vlserver_list __rcu *vl_servers; u8 name_len; /* Length of name */ - char name[64 + 1]; /* Cell name, case-flattened and NUL-padded */ + char *name; /* Cell name, case-flattened and NUL-padded */ }; /* diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index b04c528b19d3..74c886f7c51c 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -53,7 +53,7 @@ static int autofs_write(struct autofs_sb_info *sbi, mutex_lock(&sbi->pipe_mutex); while (bytes) { - wr = __kernel_write(file, data, bytes, &file->f_pos); + wr = kernel_write(file, data, bytes, &file->f_pos); if (wr <= 0) break; data += wr; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 3a7648bff42c..82ab6e5a386d 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1196,7 +1196,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, switch (tm->op) { case MOD_LOG_KEY_REMOVE_WHILE_FREEING: BUG_ON(tm->slot < n); - /* Fallthrough */ + fallthrough; case MOD_LOG_KEY_REMOVE_WHILE_MOVING: case MOD_LOG_KEY_REMOVE: btrfs_set_node_key(eb, &tm->key, tm->slot); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7c6f0bbb54a5..b1a148058773 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2593,10 +2593,12 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) !extent_buffer_uptodate(tree_root->node)) { handle_error = true; - if (IS_ERR(tree_root->node)) + if (IS_ERR(tree_root->node)) { ret = PTR_ERR(tree_root->node); - else if (!extent_buffer_uptodate(tree_root->node)) + tree_root->node = NULL; + } else if (!extent_buffer_uptodate(tree_root->node)) { ret = -EUCLEAN; + } btrfs_warn(fs_info, "failed to read tree root"); continue; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 68c96057ad2d..608f93438b29 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5058,25 +5058,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, static void check_buffer_tree_ref(struct extent_buffer *eb) { int refs; - /* the ref bit is tricky. We have to make sure it is set - * if we have the buffer dirty. Otherwise the - * code to free a buffer can end up dropping a dirty - * page + /* + * The TREE_REF bit is first set when the extent_buffer is added + * to the radix tree. It is also reset, if unset, when a new reference + * is created by find_extent_buffer. * - * Once the ref bit is set, it won't go away while the - * buffer is dirty or in writeback, and it also won't - * go away while we have the reference count on the - * eb bumped. + * It is only cleared in two cases: freeing the last non-tree + * reference to the extent_buffer when its STALE bit is set or + * calling releasepage when the tree reference is the only reference. * - * We can't just set the ref bit without bumping the - * ref on the eb because free_extent_buffer might - * see the ref bit and try to clear it. If this happens - * free_extent_buffer might end up dropping our original - * ref by mistake and freeing the page before we are able - * to add one more ref. + * In both cases, care is taken to ensure that the extent_buffer's + * pages are not under io. However, releasepage can be concurrently + * called with creating new references, which is prone to race + * conditions between the calls to check_buffer_tree_ref in those + * codepaths and clearing TREE_REF in try_release_extent_buffer. * - * So bump the ref count first, then set the bit. If someone - * beat us to it, drop the ref we added. + * The actual lifetime of the extent_buffer in the radix tree is + * adequately protected by the refcount, but the TREE_REF bit and + * its corresponding reference are not. To protect against this + * class of races, we call check_buffer_tree_ref from the codepaths + * which trigger io after they set eb->io_pages. Note that once io is + * initiated, TREE_REF can no longer be cleared, so that is the + * moment at which any such race is best fixed. */ refs = atomic_read(&eb->refs); if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) @@ -5527,6 +5530,11 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = 0; atomic_set(&eb->io_pages, num_reads); + /* + * It is possible for releasepage to clear the TREE_REF bit before we + * set io_pages. See check_buffer_tree_ref for a more detailed comment. + */ + check_buffer_tree_ref(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 7887317033c9..af92525dbb16 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -509,7 +509,7 @@ static int process_leaf(struct btrfs_root *root, switch (key.type) { case BTRFS_EXTENT_ITEM_KEY: *num_bytes = key.offset; - /* fall through */ + fallthrough; case BTRFS_METADATA_ITEM_KEY: *bytenr = key.objectid; ret = process_extent_item(fs_info, path, &key, i, diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 41ee88633769..c7bd3fdd7792 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -879,8 +879,8 @@ static bool steal_from_global_rsv(struct btrfs_fs_info *fs_info, return false; } global_rsv->reserved -= ticket->bytes; + remove_ticket(space_info, ticket); ticket->bytes = 0; - list_del_init(&ticket->list); wake_up(&ticket->wait); space_info->tickets_id++; if (global_rsv->reserved < global_rsv->size) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index bc73fd670702..c3826ae883f0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -523,7 +523,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_compress_force: case Opt_compress_force_type: compress_force = true; - /* Fallthrough */ + fallthrough; case Opt_compress: case Opt_compress_type: saved_compress_type = btrfs_test_opt(info, @@ -622,7 +622,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, btrfs_set_opt(info->mount_opt, NOSSD); btrfs_clear_and_info(info, SSD, "not using ssd optimizations"); - /* Fallthrough */ + fallthrough; case Opt_nossd_spread: btrfs_clear_and_info(info, SSD_SPREAD, "not using spread ssd allocation scheme"); @@ -793,7 +793,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_recovery: btrfs_warn(info, "'recovery' is deprecated, use 'usebackuproot' instead"); - /* fall through */ + fallthrough; case Opt_usebackuproot: btrfs_info(info, "trying to use backup root at mount time"); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index f067b5934c46..75af2334b2e3 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -408,7 +408,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio) return BTRFS_MAP_WRITE; default: WARN_ON_ONCE(1); - /* fall through */ + fallthrough; case REQ_OP_READ: return BTRFS_MAP_READ; } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index e7726f5f1241..3080cda9e824 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -937,7 +937,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) } data = kmap(page); - ret = __kernel_write(file, data, len, &pos); + ret = kernel_write(file, data, len, &pos); kunmap(page); fput(file); if (ret != len) diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index fc98b97b396a..53588d7517b4 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -399,6 +399,10 @@ skip_rdma: if (ses->sign) seq_puts(m, " signed"); + seq_printf(m, "\n\tUser: %d Cred User: %d", + from_kuid(&init_user_ns, ses->linux_uid), + from_kuid(&init_user_ns, ses->cred_uid)); + if (ses->chan_count > 1) { seq_printf(m, "\n\n\tExtra Channels: %zu\n", ses->chan_count-1); @@ -406,7 +410,7 @@ skip_rdma: cifs_dump_channel(m, j, &ses->chans[j]); } - seq_puts(m, "\n\tShares:"); + seq_puts(m, "\n\n\tShares:"); j = 0; seq_printf(m, "\n\t%d) IPC: ", j); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c7a311d28d3d..99b3180c613a 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -156,5 +156,5 @@ extern int cifs_truncate_page(struct address_space *mapping, loff_t from); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.27" +#define CIFS_VERSION "2.28" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 5fac34f192af..a61abde09ffe 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -5306,9 +5306,15 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) vol_info->nocase = master_tcon->nocase; vol_info->nohandlecache = master_tcon->nohandlecache; vol_info->local_lease = master_tcon->local_lease; + vol_info->no_lease = master_tcon->no_lease; + vol_info->resilient = master_tcon->use_resilient; + vol_info->persistent = master_tcon->use_persistent; + vol_info->handle_timeout = master_tcon->handle_timeout; vol_info->no_linux_ext = !master_tcon->unix_ext; + vol_info->linux_ext = master_tcon->posix_extensions; vol_info->sectype = master_tcon->ses->sectype; vol_info->sign = master_tcon->ses->sign; + vol_info->seal = master_tcon->seal; rc = cifs_set_vol_auth(vol_info, master_tcon->ses); if (rc) { @@ -5334,10 +5340,6 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } - /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */ - if (tcon->posix_extensions) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; - if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, vol_info); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4fe757cfc360..be46fab4c96d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1149,20 +1149,20 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock) /* * Set the byte-range lock (posix style). Returns: - * 1) 0, if we set the lock and don't need to request to the server; - * 2) 1, if we need to request to the server; - * 3) <0, if the error occurs while setting the lock. + * 1) <0, if the error occurs while setting the lock; + * 2) 0, if we set the lock and don't need to request to the server; + * 3) FILE_LOCK_DEFERRED, if we will wait for some other file_lock; + * 4) FILE_LOCK_DEFERRED + 1, if we need to request to the server. */ static int cifs_posix_lock_set(struct file *file, struct file_lock *flock) { struct cifsInodeInfo *cinode = CIFS_I(file_inode(file)); - int rc = 1; + int rc = FILE_LOCK_DEFERRED + 1; if ((flock->fl_flags & FL_POSIX) == 0) return rc; -try_again: cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); @@ -1171,13 +1171,6 @@ try_again: rc = posix_lock_file(file, flock, NULL); up_write(&cinode->lock_sem); - if (rc == FILE_LOCK_DEFERRED) { - rc = wait_event_interruptible(flock->fl_wait, - list_empty(&flock->fl_blocked_member)); - if (!rc) - goto try_again; - locks_delete_block(flock); - } return rc; } @@ -1652,7 +1645,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, int posix_lock_type; rc = cifs_posix_lock_set(file, flock); - if (!rc || rc < 0) + if (rc <= FILE_LOCK_DEFERRED) return rc; if (type & server->vals->shared_lock_type) @@ -4336,7 +4329,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __SetPageLocked(page); - if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { + rc = add_to_page_cache_locked(page, mapping, page->index, gfp); + if (rc) { __ClearPageLocked(page); break; } @@ -4352,6 +4346,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, struct list_head *page_list, unsigned num_pages) { int rc; + int err = 0; struct list_head tmplist; struct cifsFileInfo *open_file = file->private_data; struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); @@ -4396,7 +4391,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, * the order of declining indexes. When we put the pages in * the rdata->pages, then we want them in increasing order. */ - while (!list_empty(page_list)) { + while (!list_empty(page_list) && !err) { unsigned int i, nr_pages, bytes, rsize; loff_t offset; struct page *page, *tpage; @@ -4429,9 +4424,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, return 0; } - rc = readpages_get_pages(mapping, page_list, rsize, &tmplist, + nr_pages = 0; + err = readpages_get_pages(mapping, page_list, rsize, &tmplist, &nr_pages, &offset, &bytes); - if (rc) { + if (!nr_pages) { add_credits_and_wake_if(server, credits, 0); break; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 583f5e4008c2..49c3ea8aa845 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2044,6 +2044,7 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; + bool new_target = d_really_is_negative(target_dentry); if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -2120,8 +2121,13 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, */ unlink_target: - /* Try unlinking the target dentry if it's not negative */ - if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { + /* + * If the target dentry was created during the rename, try + * unlinking it if it's not negative + */ + if (new_target && + d_really_is_positive(target_dentry) && + (rc == -EACCES || rc == -EEXIST)) { if (d_is_dir(target_dentry)) tmprc = cifs_rmdir(target_dir, target_dentry); else @@ -2535,6 +2541,15 @@ set_size_out: if (rc == 0) { cifsInode->server_eof = attrs->ia_size; cifs_setsize(inode, attrs->ia_size); + + /* + * The man page of truncate says if the size changed, + * then the st_ctime and st_mtime fields for the file + * are updated. + */ + attrs->ia_ctime = attrs->ia_mtime = current_time(inode); + attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME; + cifs_truncate_page(inode->i_mapping, inode->i_size); } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 4a73e63c4d43..dcde44ff6cf9 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -169,6 +169,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) unsigned int xid; struct cifsFileInfo *pSMBFile = filep->private_data; struct cifs_tcon *tcon; + struct tcon_link *tlink; struct cifs_sb_info *cifs_sb; __u64 ExtAttrBits = 0; __u64 caps; @@ -307,13 +308,19 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; } cifs_sb = CIFS_SB(inode->i_sb); - tcon = tlink_tcon(cifs_sb_tlink(cifs_sb)); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + break; + } + tcon = tlink_tcon(tlink); if (tcon && tcon->ses->server->ops->notify) { rc = tcon->ses->server->ops->notify(xid, filep, (void __user *)arg); cifs_dbg(FYI, "ioctl notify rc %d\n", rc); } else rc = -EOPNOTSUPP; + cifs_put_tlink(tlink); break; default: cifs_dbg(FYI, "unsupported ioctl\n"); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 56791a692c8b..e44d049142d0 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -844,28 +844,26 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) struct bio_vec *bv = NULL; if (iov_iter_is_kvec(iter)) { - memcpy(&ctx->iter, iter, sizeof(struct iov_iter)); + memcpy(&ctx->iter, iter, sizeof(*iter)); ctx->len = count; iov_iter_advance(iter, count); return 0; } - if (max_pages * sizeof(struct bio_vec) <= CIFS_AIO_KMALLOC_LIMIT) - bv = kmalloc_array(max_pages, sizeof(struct bio_vec), - GFP_KERNEL); + if (array_size(max_pages, sizeof(*bv)) <= CIFS_AIO_KMALLOC_LIMIT) + bv = kmalloc_array(max_pages, sizeof(*bv), GFP_KERNEL); if (!bv) { - bv = vmalloc(array_size(max_pages, sizeof(struct bio_vec))); + bv = vmalloc(array_size(max_pages, sizeof(*bv))); if (!bv) return -ENOMEM; } - if (max_pages * sizeof(struct page *) <= CIFS_AIO_KMALLOC_LIMIT) - pages = kmalloc_array(max_pages, sizeof(struct page *), - GFP_KERNEL); + if (array_size(max_pages, sizeof(*pages)) <= CIFS_AIO_KMALLOC_LIMIT) + pages = kmalloc_array(max_pages, sizeof(*pages), GFP_KERNEL); if (!pages) { - pages = vmalloc(array_size(max_pages, sizeof(struct page *))); + pages = vmalloc(array_size(max_pages, sizeof(*pages))); if (!pages) { kvfree(bv); return -ENOMEM; diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 6a39451973f8..157992864ce7 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -354,9 +354,13 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr) ((struct smb2_ioctl_rsp *)shdr)->OutputCount); break; case SMB2_CHANGE_NOTIFY: + *off = le16_to_cpu( + ((struct smb2_change_notify_rsp *)shdr)->OutputBufferOffset); + *len = le32_to_cpu( + ((struct smb2_change_notify_rsp *)shdr)->OutputBufferLength); + break; default: - /* BB FIXME for unimplemented cases above */ - cifs_dbg(VFS, "no length check for command\n"); + cifs_dbg(VFS, "no length check for command %d\n", le16_to_cpu(shdr->Command)); break; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 736d86b8a910..32f90dc82c84 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -763,6 +763,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, /* close extra handle outside of crit sec */ SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); } + rc = 0; goto oshr_free; } @@ -2147,7 +2148,7 @@ smb3_notify(const unsigned int xid, struct file *pfile, tcon = cifs_sb_master_tcon(cifs_sb); oparms.tcon = tcon; - oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA; oparms.disposition = FILE_OPEN; oparms.create_options = cifs_create_options(cifs_sb, 0); oparms.fid = &fid; @@ -3187,6 +3188,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + /* + * We zero the range through ioctl, so we need remove the page caches + * first, otherwise the data may be inconsistent with the server. + */ + truncate_pagecache_range(inode, offset, offset + len - 1); /* if file not oplocked can't be sure whether asking to extend size */ if (!CIFS_CACHE_READ(cifsi)) @@ -3253,6 +3259,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; } + /* + * We implement the punch hole through ioctl, so we need remove the page + * caches first, otherwise the data may be inconsistent with the server. + */ + truncate_pagecache_range(inode, offset, offset + len - 1); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index d11e31064679..84433d0653f9 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -523,7 +523,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, const int timeout, const int flags, unsigned int *instance) { - int rc; + long rc; int *credits; int optype; long int t; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index ae49a55bda00..d0ed71f37511 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -918,11 +918,6 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode, } EXPORT_SYMBOL_GPL(debugfs_create_blob); -struct array_data { - void *array; - u32 elements; -}; - static size_t u32_format_array(char *buf, size_t bufsize, u32 *array, int array_size) { @@ -943,8 +938,8 @@ static size_t u32_format_array(char *buf, size_t bufsize, static int u32_array_open(struct inode *inode, struct file *file) { - struct array_data *data = inode->i_private; - int size, elements = data->elements; + struct debugfs_u32_array *data = inode->i_private; + int size, elements = data->n_elements; char *buf; /* @@ -959,7 +954,7 @@ static int u32_array_open(struct inode *inode, struct file *file) buf[size] = 0; file->private_data = buf; - u32_format_array(buf, size, data->array, data->elements); + u32_format_array(buf, size, data->array, data->n_elements); return nonseekable_open(inode, file); } @@ -996,8 +991,7 @@ static const struct file_operations u32_array_fops = { * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. - * @array: u32 array that provides data. - * @elements: total number of elements in the array. + * @array: wrapper struct containing data pointer and size of the array. * * This function creates a file in debugfs with the given name that exports * @array as data. If the @mode variable is so set it can be read from. @@ -1005,17 +999,10 @@ static const struct file_operations u32_array_fops = { * Once array is created its size can not be changed. */ void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, u32 elements) + struct dentry *parent, + struct debugfs_u32_array *array) { - struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL); - - if (data == NULL) - return; - - data->array = array; - data->elements = elements; - - debugfs_create_file_unsafe(name, mode, parent, data, &u32_array_fops); + debugfs_create_file_unsafe(name, mode, parent, array, &u32_array_fops); } EXPORT_SYMBOL_GPL(debugfs_create_u32_array); diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index e9e27a271af0..feaa5e182b7b 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -51,6 +51,7 @@ static ssize_t efivarfs_file_write(struct file *file, } else { inode_lock(inode); i_size_write(inode, datasize + sizeof(attributes)); + inode->i_mtime = current_time(inode); inode_unlock(inode); } @@ -72,10 +73,8 @@ static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf, ssize_t size = 0; int err; - while (!__ratelimit(&file->f_cred->user->ratelimit)) { - if (!msleep_interruptible(50)) - return -EINTR; - } + while (!__ratelimit(&file->f_cred->user->ratelimit)) + msleep(50); err = efivar_entry_size(var, &datasize); diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index de43534aa299..91ece649285d 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -309,7 +309,7 @@ const struct file_operations exfat_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate = exfat_iterate, - .fsync = generic_file_fsync, + .fsync = exfat_file_fsync, }; int exfat_alloc_new_dir(struct inode *inode, struct exfat_chain *clu) @@ -425,10 +425,12 @@ static void exfat_init_name_entry(struct exfat_dentry *ep, ep->dentry.name.flags = 0x0; for (i = 0; i < EXFAT_FILE_NAME_LEN; i++) { - ep->dentry.name.unicode_0_14[i] = cpu_to_le16(*uniname); - if (*uniname == 0x0) - break; - uniname++; + if (*uniname != 0x0) { + ep->dentry.name.unicode_0_14[i] = cpu_to_le16(*uniname); + uniname++; + } else { + ep->dentry.name.unicode_0_14[i] = 0x0; + } } } diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 595f3117f492..7579cd3bbadb 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -420,6 +420,7 @@ void exfat_truncate(struct inode *inode, loff_t size); int exfat_setattr(struct dentry *dentry, struct iattr *attr); int exfat_getattr(const struct path *path, struct kstat *stat, unsigned int request_mask, unsigned int query_flags); +int exfat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); /* namei.c */ extern const struct dentry_operations exfat_dentry_ops; diff --git a/fs/exfat/file.c b/fs/exfat/file.c index fce03f318787..3b7fea465fd4 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/cred.h> #include <linux/buffer_head.h> +#include <linux/blkdev.h> #include "exfat_raw.h" #include "exfat_fs.h" @@ -346,12 +347,28 @@ out: return error; } +int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) +{ + struct inode *inode = filp->f_mapping->host; + int err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; + + err = sync_blockdev(inode->i_sb->s_bdev); + if (err) + return err; + + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); +} + const struct file_operations exfat_file_operations = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, - .fsync = generic_file_fsync, + .fsync = exfat_file_fsync, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 5b0f35329d63..2b9e21094a96 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -975,7 +975,6 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) goto unlock; } - exfat_set_vol_flags(sb, VOL_DIRTY); exfat_chain_set(&clu_to_free, ei->start_clu, EXFAT_B_TO_CLU_ROUND_UP(i_size_read(inode), sbi), ei->flags); @@ -1002,6 +1001,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) num_entries++; brelse(bh); + exfat_set_vol_flags(sb, VOL_DIRTY); err = exfat_remove_entries(dir, &cdir, entry, 0, num_entries); if (err) { exfat_err(sb, "failed to exfat_remove_entries : err(%d)", err); @@ -1077,10 +1077,14 @@ static int exfat_rename_file(struct inode *inode, struct exfat_chain *p_dir, epold = exfat_get_dentry(sb, p_dir, oldentry + 1, &old_bh, §or_old); + if (!epold) + return -EIO; epnew = exfat_get_dentry(sb, p_dir, newentry + 1, &new_bh, §or_new); - if (!epold || !epnew) + if (!epnew) { + brelse(old_bh); return -EIO; + } memcpy(epnew, epold, DENTRY_SIZE); exfat_update_bh(sb, new_bh, sync); @@ -1161,10 +1165,14 @@ static int exfat_move_file(struct inode *inode, struct exfat_chain *p_olddir, epmov = exfat_get_dentry(sb, p_olddir, oldentry + 1, &mov_bh, §or_mov); + if (!epmov) + return -EIO; epnew = exfat_get_dentry(sb, p_newdir, newentry + 1, &new_bh, §or_new); - if (!epmov || !epnew) + if (!epnew) { + brelse(mov_bh); return -EIO; + } memcpy(epnew, epmov, DENTRY_SIZE); exfat_update_bh(sb, new_bh, IS_DIRSYNC(inode)); diff --git a/fs/exfat/super.c b/fs/exfat/super.c index e650e65536f8..253a92460d52 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -693,10 +693,20 @@ static void exfat_free(struct fs_context *fc) } } +static int exfat_reconfigure(struct fs_context *fc) +{ + fc->sb_flags |= SB_NODIRATIME; + + /* volume flag will be updated in exfat_sync_fs */ + sync_filesystem(fc->root->d_sb); + return 0; +} + static const struct fs_context_operations exfat_context_ops = { .parse_param = exfat_parse_param, .get_tree = exfat_get_tree, .free = exfat_free, + .reconfigure = exfat_reconfigure, }; static int exfat_init_fs_context(struct fs_context *fc) diff --git a/fs/file_table.c b/fs/file_table.c index 65603502fed6..656647f9575a 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -230,7 +230,7 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(mnt); d_instantiate(path.dentry, inode); - file = alloc_file(&path, flags | FMODE_NONOTIFY, fops); + file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 72c9560f4467..68cd700a2719 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -468,21 +468,10 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) } -/** - * __gfs2_readpage - readpage - * @file: The file to read a page for - * @page: The page to read - * - * This is the core of gfs2's readpage. It's used by the internal file - * reading code as in that case we already hold the glock. Also it's - * called by gfs2_readpage() once the required lock has been granted. - */ - static int __gfs2_readpage(void *file, struct page *page) { struct gfs2_inode *ip = GFS2_I(page->mapping->host); struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host); - int error; if (i_blocksize(page->mapping->host) == PAGE_SIZE && @@ -505,36 +494,11 @@ static int __gfs2_readpage(void *file, struct page *page) * gfs2_readpage - read a page of a file * @file: The file to read * @page: The page of the file - * - * This deals with the locking required. We have to unlock and - * relock the page in order to get the locking in the right - * order. */ static int gfs2_readpage(struct file *file, struct page *page) { - struct address_space *mapping = page->mapping; - struct gfs2_inode *ip = GFS2_I(mapping->host); - struct gfs2_holder gh; - int error; - - unlock_page(page); - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh); - error = gfs2_glock_nq(&gh); - if (unlikely(error)) - goto out; - error = AOP_TRUNCATED_PAGE; - lock_page(page); - if (page->mapping == mapping && !PageUptodate(page)) - error = __gfs2_readpage(file, page); - else - unlock_page(page); - gfs2_glock_dq(&gh); -out: - gfs2_holder_uninit(&gh); - if (error && error != AOP_TRUNCATED_PAGE) - lock_page(page); - return error; + return __gfs2_readpage(file, page); } /** @@ -598,16 +562,9 @@ static void gfs2_readahead(struct readahead_control *rac) { struct inode *inode = rac->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_holder gh; - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh); - if (gfs2_glock_nq(&gh)) - goto out_uninit; if (!gfs2_is_stuffed(ip)) mpage_readahead(rac, gfs2_block_map); - gfs2_glock_dq(&gh); -out_uninit: - gfs2_holder_uninit(&gh); } /** diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index fe305e4bfd37..bebde537ac8c 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -558,8 +558,29 @@ out_uninit: return block_page_mkwrite_return(ret); } +static vm_fault_t gfs2_fault(struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vmf->vma->vm_file); + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + vm_fault_t ret; + int err; + + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh); + err = gfs2_glock_nq(&gh); + if (err) { + ret = block_page_mkwrite_return(err); + goto out_uninit; + } + ret = filemap_fault(vmf); + gfs2_glock_dq(&gh); +out_uninit: + gfs2_holder_uninit(&gh); + return ret; +} + static const struct vm_operations_struct gfs2_vm_ops = { - .fault = filemap_fault, + .fault = gfs2_fault, .map_pages = filemap_map_pages, .page_mkwrite = gfs2_page_mkwrite, }; @@ -824,6 +845,9 @@ out_uninit: static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { + struct gfs2_inode *ip; + struct gfs2_holder gh; + size_t written = 0; ssize_t ret; if (iocb->ki_flags & IOCB_DIRECT) { @@ -832,7 +856,31 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return ret; iocb->ki_flags &= ~IOCB_DIRECT; } - return generic_file_read_iter(iocb, to); + iocb->ki_flags |= IOCB_NOIO; + ret = generic_file_read_iter(iocb, to); + iocb->ki_flags &= ~IOCB_NOIO; + if (ret >= 0) { + if (!iov_iter_count(to)) + return ret; + written = ret; + } else { + if (ret != -EAGAIN) + return ret; + if (iocb->ki_flags & IOCB_NOWAIT) + return ret; + } + ip = GFS2_I(iocb->ki_filp->f_mapping->host); + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh); + ret = gfs2_glock_nq(&gh); + if (ret) + goto out_uninit; + ret = generic_file_read_iter(iocb, to); + if (ret > 0) + written += ret; + gfs2_glock_dq(&gh); +out_uninit: + gfs2_holder_uninit(&gh); + return written ? written : ret; } /** diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 2299dcc417ea..8545024a1401 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1899,7 +1899,10 @@ bool gfs2_delete_work_queued(const struct gfs2_glock *gl) static void flush_delete_work(struct gfs2_glock *gl) { - flush_delayed_work(&gl->gl_delete); + if (cancel_delayed_work(&gl->gl_delete)) { + queue_delayed_work(gfs2_delete_workqueue, + &gl->gl_delete, 0); + } gfs2_glock_queue_work(gl, 0); } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index c84887769b5a..de1d5f1d9ff8 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -531,8 +531,7 @@ static int freeze_go_sync(struct gfs2_glock *gl) int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) && - test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { + if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { @@ -545,8 +544,11 @@ static int freeze_go_sync(struct gfs2_glock *gl) gfs2_assert_withdraw(sdp, 0); } queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work); - gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE | - GFS2_LFC_FREEZE_GO_SYNC); + if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) + gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE | + GFS2_LFC_FREEZE_GO_SYNC); + else /* read-only mounts */ + atomic_set(&sdp->sd_freeze_state, SFS_FROZEN); } return 0; } diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 03ab11fab962..ca2ec02436ec 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -399,7 +399,6 @@ enum { GIF_QD_LOCKED = 1, GIF_ALLOC_FAILED = 2, GIF_SW_PAGED = 3, - GIF_ORDERED = 4, GIF_FREE_VFS_INODE = 5, GIF_GLOP_PENDING = 6, GIF_DEFERRED_DELETE = 7, diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 370c3a4b31ac..6774865f5b5b 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -207,10 +207,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (no_formal_ino && ip->i_no_formal_ino && no_formal_ino != ip->i_no_formal_ino) { + error = -ESTALE; if (inode->i_state & I_NEW) goto fail; iput(inode); - return ERR_PTR(-ESTALE); + return ERR_PTR(error); } if (inode->i_state & I_NEW) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 3e4734431783..a76e55bc28eb 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -613,6 +613,12 @@ static int ip_cmp(void *priv, struct list_head *a, struct list_head *b) return 0; } +static void __ordered_del_inode(struct gfs2_inode *ip) +{ + if (!list_empty(&ip->i_ordered)) + list_del_init(&ip->i_ordered); +} + static void gfs2_ordered_write(struct gfs2_sbd *sdp) { struct gfs2_inode *ip; @@ -623,8 +629,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) while (!list_empty(&sdp->sd_log_ordered)) { ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered); if (ip->i_inode.i_mapping->nrpages == 0) { - test_and_clear_bit(GIF_ORDERED, &ip->i_flags); - list_del(&ip->i_ordered); + __ordered_del_inode(ip); continue; } list_move(&ip->i_ordered, &written); @@ -643,8 +648,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) spin_lock(&sdp->sd_ordered_lock); while (!list_empty(&sdp->sd_log_ordered)) { ip = list_first_entry(&sdp->sd_log_ordered, struct gfs2_inode, i_ordered); - list_del(&ip->i_ordered); - WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags)); + __ordered_del_inode(ip); if (ip->i_inode.i_mapping->nrpages == 0) continue; spin_unlock(&sdp->sd_ordered_lock); @@ -659,8 +663,7 @@ void gfs2_ordered_del_inode(struct gfs2_inode *ip) struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); spin_lock(&sdp->sd_ordered_lock); - if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags)) - list_del(&ip->i_ordered); + __ordered_del_inode(ip); spin_unlock(&sdp->sd_ordered_lock); } @@ -1002,6 +1005,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) out: if (gfs2_withdrawn(sdp)) { + /** + * If the tr_list is empty, we're withdrawing during a log + * flush that targets a transaction, but the transaction was + * never queued onto any of the ail lists. Here we add it to + * ail1 just so that ail_drain() will find and free it. + */ + spin_lock(&sdp->sd_ail_lock); + if (tr && list_empty(&tr->tr_list)) + list_add(&tr->tr_list, &sdp->sd_ail1_list); + spin_unlock(&sdp->sd_ail_lock); ail_drain(sdp); /* frees all transactions */ tr = NULL; } diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index c1cd6ae17659..8965c751a303 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -53,9 +53,9 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip) if (gfs2_is_jdata(ip) || !gfs2_is_ordered(sdp)) return; - if (!test_bit(GIF_ORDERED, &ip->i_flags)) { + if (list_empty(&ip->i_ordered)) { spin_lock(&sdp->sd_ordered_lock); - if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags)) + if (list_empty(&ip->i_ordered)) list_add(&ip->i_ordered, &sdp->sd_log_ordered); spin_unlock(&sdp->sd_ordered_lock); } diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 733470ca6be9..c7393ee9cf68 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -39,6 +39,7 @@ static void gfs2_init_inode_once(void *foo) atomic_set(&ip->i_sizehint, 0); init_rwsem(&ip->i_rw_mutex); INIT_LIST_HEAD(&ip->i_trunc_list); + INIT_LIST_HEAD(&ip->i_ordered); ip->i_qadata = NULL; gfs2_holder_mark_uninitialized(&ip->i_rgd_gh); memset(&ip->i_res, 0, sizeof(ip->i_res)); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 094f5fe7c009..6d18d2c91add 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1136,7 +1136,18 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) goto fail_per_node; } - if (!sb_rdonly(sb)) { + if (sb_rdonly(sb)) { + struct gfs2_holder freeze_gh; + + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, + LM_FLAG_NOEXP | GL_EXACT, + &freeze_gh); + if (error) { + fs_err(sdp, "can't make FS RO: %d\n", error); + goto fail_per_node; + } + gfs2_glock_dq_uninit(&freeze_gh); + } else { error = gfs2_make_fs_rw(sdp); if (error) { fs_err(sdp, "can't make FS RW: %d\n", error); diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 96c345f49273..390ea79d682c 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -364,8 +364,8 @@ void gfs2_recover_func(struct work_struct *work) /* Acquire a shared hold on the freeze lock */ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, - LM_FLAG_NOEXP | LM_FLAG_PRIORITY, - &thaw_gh); + LM_FLAG_NOEXP | LM_FLAG_PRIORITY | + GL_EXACT, &thaw_gh); if (error) goto fail_gunlock_ji; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 32d8d26126a1..47d0ae158b69 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -167,7 +167,8 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) if (error) return error; - error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, + LM_FLAG_NOEXP | GL_EXACT, &freeze_gh); if (error) goto fail_threads; @@ -203,7 +204,6 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) return 0; fail: - freeze_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&freeze_gh); fail_threads: if (sdp->sd_quotad_process) @@ -430,7 +430,7 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp) } error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE, - GL_NOCACHE, &sdp->sd_freeze_gh); + LM_FLAG_NOEXP, &sdp->sd_freeze_gh); if (error) goto out; @@ -613,13 +613,15 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp) !gfs2_glock_is_locked_by_me(sdp->sd_freeze_gl)) { if (!log_write_allowed) { error = gfs2_glock_nq_init(sdp->sd_freeze_gl, - LM_ST_SHARED, GL_NOCACHE | - LM_FLAG_TRY, &freeze_gh); + LM_ST_SHARED, LM_FLAG_TRY | + LM_FLAG_NOEXP | GL_EXACT, + &freeze_gh); if (error == GLR_TRYFAILED) error = 0; } else { error = gfs2_glock_nq_init(sdp->sd_freeze_gl, - LM_ST_SHARED, GL_NOCACHE, + LM_ST_SHARED, + LM_FLAG_NOEXP | GL_EXACT, &freeze_gh); if (error && !gfs2_withdrawn(sdp)) return error; @@ -761,8 +763,8 @@ void gfs2_freeze_func(struct work_struct *work) struct super_block *sb = sdp->sd_vfs; atomic_inc(&sb->s_active); - error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, - &freeze_gh); + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, + LM_FLAG_NOEXP | GL_EXACT, &freeze_gh); if (error) { fs_info(sdp, "GFS2: couldn't get freeze lock : %d\n", error); gfs2_assert_withdraw(sdp, 0); @@ -774,8 +776,6 @@ void gfs2_freeze_func(struct work_struct *work) error); gfs2_assert_withdraw(sdp, 0); } - if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) - freeze_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&freeze_gh); } deactivate_super(sb); diff --git a/fs/io_uring.c b/fs/io_uring.c index a78201b96179..ca8abde48b6c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -890,6 +890,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_files_update *ip, unsigned nr_args); static int io_grab_files(struct io_kiocb *req); +static void io_complete_rw_common(struct kiocb *kiocb, long res); static void io_cleanup_req(struct io_kiocb *req); static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, int fd, struct file **out_file, bool fixed); @@ -1273,6 +1274,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) if (cqe) { clear_bit(0, &ctx->sq_check_overflow); clear_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); @@ -1310,6 +1312,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) if (list_empty(&ctx->cq_overflow_list)) { set_bit(0, &ctx->sq_check_overflow); set_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; } req->flags |= REQ_F_OVERFLOW; refcount_inc(&req->refs); @@ -1749,6 +1752,14 @@ static void io_iopoll_queue(struct list_head *again) do { req = list_first_entry(again, struct io_kiocb, list); list_del(&req->list); + + /* shouldn't happen unless io_uring is dying, cancel reqs */ + if (unlikely(!current->mm)) { + io_complete_rw_common(&req->rw.kiocb, -EAGAIN); + io_put_req(req); + continue; + } + refcount_inc(&req->refs); io_queue_async_work(req); } while (!list_empty(again)); @@ -1994,10 +2005,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) WRITE_ONCE(req->result, res); /* order with io_poll_complete() checking ->result */ - if (res != -EAGAIN) { - smp_wmb(); - WRITE_ONCE(req->iopoll_completed, 1); - } + smp_wmb(); + WRITE_ONCE(req->iopoll_completed, 1); } /* @@ -4065,6 +4074,29 @@ struct io_poll_table { int error; }; +static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb) +{ + struct task_struct *tsk = req->task; + struct io_ring_ctx *ctx = req->ctx; + int ret, notify = TWA_RESUME; + + /* + * SQPOLL kernel thread doesn't need notification, just a wakeup. + * If we're not using an eventfd, then TWA_RESUME is always fine, + * as we won't have dependencies between request completions for + * other kernel wait conditions. + */ + if (ctx->flags & IORING_SETUP_SQPOLL) + notify = 0; + else if (ctx->cq_ev_fd) + notify = TWA_SIGNAL; + + ret = task_work_add(tsk, cb, notify); + if (!ret) + wake_up_process(tsk); + return ret; +} + static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, __poll_t mask, task_work_func_t func) { @@ -4088,13 +4120,13 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, * of executing it. We can't safely execute it anyway, as we may not * have the needed state needed for it anyway. */ - ret = task_work_add(tsk, &req->task_work, true); + ret = io_req_task_work_add(req, &req->task_work); if (unlikely(ret)) { WRITE_ONCE(poll->canceled, true); tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, true); + task_work_add(tsk, &req->task_work, 0); + wake_up_process(tsk); } - wake_up_process(tsk); return 1; } @@ -5353,9 +5385,6 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) { const bool in_async = io_wq_current_is_worker(); - if (req->result == -EAGAIN) - return -EAGAIN; - /* workqueue context doesn't hold uring_lock, grab it now */ if (in_async) mutex_lock(&ctx->uring_lock); @@ -6011,7 +6040,7 @@ static int io_sq_thread(void *data) * If submit got -EBUSY, flag us as needing the application * to enter the kernel to reap and flush events. */ - if (!to_submit || ret == -EBUSY) { + if (!to_submit || ret == -EBUSY || need_resched()) { /* * Drop cur_mm before scheduling, we can't hold it for * long periods (or over schedule()). Do this before @@ -6027,7 +6056,7 @@ static int io_sq_thread(void *data) * more IO, we should wait for the application to * reap events and wake us up. */ - if (!list_empty(&ctx->poll_list) || + if (!list_empty(&ctx->poll_list) || need_resched() || (!time_after(jiffies, timeout) && ret != -EBUSY && !percpu_ref_is_dying(&ctx->refs))) { if (current->task_works) @@ -6053,9 +6082,9 @@ static int io_sq_thread(void *data) } /* Tell userspace we may need a wakeup call */ + spin_lock_irq(&ctx->completion_lock); ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; - /* make sure to read SQ tail after writing flags */ - smp_mb(); + spin_unlock_irq(&ctx->completion_lock); to_submit = io_sqring_entries(ctx); if (!to_submit || ret == -EBUSY) { @@ -6073,13 +6102,17 @@ static int io_sq_thread(void *data) schedule(); finish_wait(&ctx->sqo_wait, &wait); + spin_lock_irq(&ctx->completion_lock); ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + spin_unlock_irq(&ctx->completion_lock); ret = 0; continue; } finish_wait(&ctx->sqo_wait, &wait); + spin_lock_irq(&ctx->completion_lock); ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + spin_unlock_irq(&ctx->completion_lock); } mutex_lock(&ctx->uring_lock); @@ -6178,15 +6211,23 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, do { prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, TASK_INTERRUPTIBLE); + /* make sure we run task_work before checking for signals */ if (current->task_works) task_work_run(); - if (io_should_wake(&iowq, false)) - break; - schedule(); if (signal_pending(current)) { + if (current->jobctl & JOBCTL_TASK_WORK) { + spin_lock_irq(¤t->sighand->siglock); + current->jobctl &= ~JOBCTL_TASK_WORK; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + continue; + } ret = -EINTR; break; } + if (io_should_wake(&iowq, false)) + break; + schedule(); } while (1); finish_wait(&ctx->wait, &iowq.wq); @@ -6658,6 +6699,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, for (i = 0; i < nr_tables; i++) kfree(ctx->file_data->table[i].files); + percpu_ref_exit(&ctx->file_data->refs); kfree(ctx->file_data->table); kfree(ctx->file_data); ctx->file_data = NULL; @@ -6810,8 +6852,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, } table->files[index] = file; err = io_sqe_file_register(ctx, file, i); - if (err) + if (err) { + fput(file); break; + } } nr_args--; done++; @@ -7307,9 +7351,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_mem_free(ctx->sq_sqes); percpu_ref_exit(&ctx->refs); - if (ctx->account_mem) - io_unaccount_mem(ctx->user, - ring_pages(ctx->sq_entries, ctx->cq_entries)); free_uid(ctx->user); put_cred(ctx->creds); kfree(ctx->cancel_hash); @@ -7394,6 +7435,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) if (ctx->rings) io_cqring_overflow_flush(ctx, true); idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); + + /* + * Do this upfront, so we won't have a grace period where the ring + * is closed but resources aren't reaped yet. This can cause + * spurious failure in setting up a new ring. + */ + if (ctx->account_mem) + io_unaccount_mem(ctx->user, + ring_pages(ctx->sq_entries, ctx->cq_entries)); + INIT_WORK(&ctx->exit_work, io_ring_exit_work); queue_work(system_wq, &ctx->exit_work); } @@ -7453,6 +7504,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, if (list_empty(&ctx->cq_overflow_list)) { clear_bit(0, &ctx->sq_check_overflow); clear_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } spin_unlock_irq(&ctx->completion_lock); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1b79dd5cf661..3d113cf8908a 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -267,8 +267,6 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) { struct inode *inode = dreq->inode; - inode_dio_end(inode); - if (dreq->iocb) { long res = (long) dreq->error; if (dreq->count != 0) { @@ -280,7 +278,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) complete(&dreq->completion); + igrab(inode); nfs_direct_req_release(dreq); + inode_dio_end(inode); + iput(inode); } static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) @@ -410,8 +411,10 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - inode_dio_end(inode); + igrab(inode); nfs_direct_req_release(dreq); + inode_dio_end(inode); + iput(inode); return result < 0 ? result : -EIO; } @@ -864,8 +867,10 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - inode_dio_end(inode); + igrab(inode); nfs_direct_req_release(dreq); + inode_dio_end(inode); + iput(inode); return result < 0 ? result : -EIO; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index f96367a2463e..ccd6c1637b27 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -83,6 +83,7 @@ nfs_file_release(struct inode *inode, struct file *filp) dprintk("NFS: release(%pD2)\n", filp); nfs_inc_stats(inode, NFSIOS_VFSRELEASE); + inode_dio_wait(inode); nfs_file_clear_open_context(filp); return 0; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 7d399f72ebbb..de03e440b7ee 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -907,9 +907,8 @@ retry: goto out_mds; /* Use a direct mapping of ds_idx to pgio mirror_idx */ - if (WARN_ON_ONCE(pgio->pg_mirror_count != - FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))) - goto out_mds; + if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)) + goto out_eagain; for (i = 0; i < pgio->pg_mirror_count; i++) { mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); @@ -931,7 +930,10 @@ retry: (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) pgio->pg_maxretrans = io_maxretrans; return; - +out_eagain: + pnfs_generic_pg_cleanup(pgio); + pgio->pg_error = -EAGAIN; + return; out_mds: trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode, 0, NFS4_MAX_UINT64, IOMODE_RW, @@ -941,6 +943,7 @@ out_mds: pgio->pg_lseg = NULL; pgio->pg_maxretrans = 0; nfs_pageio_reset_write_mds(pgio); + pgio->pg_error = -EAGAIN; } static unsigned int diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index a3ab6e219061..873342308dc0 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -308,6 +308,7 @@ static int try_location(struct fs_context *fc, if (IS_ERR(export_path)) return PTR_ERR(export_path); + kfree(ctx->nfs_server.export_path); ctx->nfs_server.export_path = export_path; source = kmalloc(len + 1 + ctx->nfs_server.export_path_len + 1, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index bb3d2c32664a..cce2510b2cca 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7912,9 +7912,14 @@ nfs4_state_start_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; - ret = nfs4_state_create_net(net); + ret = get_nfsdfs(net); if (ret) return ret; + ret = nfs4_state_create_net(net); + if (ret) { + mntput(nn->nfsd_mnt); + return ret; + } locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) @@ -7984,6 +7989,7 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); + mntput(nn->nfsd_mnt); } void diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b68e96681522..cd05732f8eaa 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1335,6 +1335,7 @@ void nfsd_client_rmdir(struct dentry *dentry) WARN_ON_ONCE(ret); fsnotify_rmdir(dir, dentry); d_delete(dentry); + dput(dentry); inode_unlock(dir); } @@ -1424,6 +1425,18 @@ static struct file_system_type nfsd_fs_type = { }; MODULE_ALIAS_FS("nfsd"); +int get_nfsdfs(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct vfsmount *mnt; + + mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + nn->nfsd_mnt = mnt; + return 0; +} + #ifdef CONFIG_PROC_FS static int create_proc_exports_entry(void) { @@ -1451,7 +1464,6 @@ unsigned int nfsd_net_id; static __net_init int nfsd_init_net(struct net *net) { int retval; - struct vfsmount *mnt; struct nfsd_net *nn = net_generic(net, nfsd_net_id); retval = nfsd_export_init(net); @@ -1478,16 +1490,8 @@ static __net_init int nfsd_init_net(struct net *net) init_waitqueue_head(&nn->ntf_wq); seqlock_init(&nn->boot_lock); - mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL); - if (IS_ERR(mnt)) { - retval = PTR_ERR(mnt); - goto out_mount_err; - } - nn->nfsd_mnt = mnt; return 0; -out_mount_err: - nfsd_reply_cache_shutdown(nn); out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: @@ -1500,7 +1504,6 @@ static __net_exit void nfsd_exit_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - mntput(nn->nfsd_mnt); nfsd_reply_cache_shutdown(nn); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 36cdd81b6688..57c832d1b30f 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -90,6 +90,8 @@ void nfsd_destroy(struct net *net); bool i_am_nfsd(void); +int get_nfsdfs(struct net *); + struct nfsdfs_client { struct kref cl_ref; void (*cl_release)(struct kref *kref); @@ -100,6 +102,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, struct nfsdfs_client *ncl, u32 id, const struct tree_descr *); void nfsd_client_rmdir(struct dentry *dentry); + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL extern const struct svc_version nfsd_acl_version2; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c3fbab1753ec..d22a056da477 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1226,6 +1226,9 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode = 0; iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type; + if (!IS_POSIXACL(dirp)) + iap->ia_mode &= ~current_umask(); + err = 0; host_err = 0; switch (type) { @@ -1458,6 +1461,9 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; } + if (!IS_POSIXACL(dirp)) + iap->ia_mode &= ~current_umask(); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (host_err < 0) { fh_drop_write(fhp); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 152a0fc4e905..751bc4dc7466 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -689,6 +689,12 @@ static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res, &ocfs2_nfs_sync_lops, osb); } +static void ocfs2_nfs_sync_lock_init(struct ocfs2_super *osb) +{ + ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + init_rwsem(&osb->nfs_sync_rwlock); +} + void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; @@ -2855,6 +2861,11 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex) if (ocfs2_is_hard_readonly(osb)) return -EROFS; + if (ex) + down_write(&osb->nfs_sync_rwlock); + else + down_read(&osb->nfs_sync_rwlock); + if (ocfs2_mount_local(osb)) return 0; @@ -2873,6 +2884,10 @@ void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex) if (!ocfs2_mount_local(osb)) ocfs2_cluster_unlock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE); + if (ex) + up_write(&osb->nfs_sync_rwlock); + else + up_read(&osb->nfs_sync_rwlock); } int ocfs2_trim_fs_lock(struct ocfs2_super *osb, @@ -3340,7 +3355,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) local: ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb); ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb); - ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb); + ocfs2_nfs_sync_lock_init(osb); ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb); osb->cconn = conn; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index ee5d98516212..2dd71d626196 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -395,6 +395,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; + struct rw_semaphore nfs_sync_rwlock; struct ocfs2_lock_res osb_trim_fs_lockres; struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 0dd8c41bafd4..19137c6d087b 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -290,7 +290,7 @@ #define OCFS2_MAX_SLOTS 255 /* Slot map indicator for an empty slot */ -#define OCFS2_INVALID_SLOT -1 +#define OCFS2_INVALID_SLOT ((u16)-1) #define OCFS2_VOL_UUID_LEN 16 #define OCFS2_MAX_VOL_LABEL_LEN 64 @@ -326,8 +326,8 @@ struct ocfs2_system_inode_info { enum { BAD_BLOCK_SYSTEM_INODE = 0, GLOBAL_INODE_ALLOC_SYSTEM_INODE, +#define OCFS2_FIRST_ONLINE_SYSTEM_INODE GLOBAL_INODE_ALLOC_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE, -#define OCFS2_FIRST_ONLINE_SYSTEM_INODE SLOT_MAP_SYSTEM_INODE HEARTBEAT_SYSTEM_INODE, GLOBAL_BITMAP_SYSTEM_INODE, USER_QUOTA_SYSTEM_INODE, diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 4836becb7578..45745cc3408a 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2825,9 +2825,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) goto bail; } - inode_alloc_inode = - ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE, - suballoc_slot); + if (suballoc_slot == (u16)OCFS2_INVALID_SLOT) + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + GLOBAL_INODE_ALLOC_SYSTEM_INODE, suballoc_slot); + else + inode_alloc_inode = ocfs2_get_system_file_inode(osb, + INODE_ALLOC_SYSTEM_INODE, suballoc_slot); if (!inode_alloc_inode) { /* the error code could be inaccurate, but we are not able to * get the correct one. */ diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 42c5128c7d1c..6c1166ccdaea 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -566,8 +566,9 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf, goto out; /* don't even try if the size is too large */ - if (count > KMALLOC_MAX_SIZE) - return -ENOMEM; + error = -ENOMEM; + if (count >= KMALLOC_MAX_SIZE) + goto out; if (write) { kbuf = memdup_user_nul(ubuf, count); @@ -576,7 +577,6 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf, goto out; } } else { - error = -ENOMEM; kbuf = kzalloc(count, GFP_KERNEL); if (!kbuf) goto out; diff --git a/fs/read_write.c b/fs/read_write.c index bbfa9b12b15e..4fb797822567 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -419,28 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo return ret; } -ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, - loff_t *pos) +ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { + mm_segment_t old_fs = get_fs(); + ssize_t ret; + + if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) + return -EINVAL; + if (!(file->f_mode & FMODE_CAN_READ)) + return -EINVAL; + + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + set_fs(KERNEL_DS); if (file->f_op->read) - return file->f_op->read(file, buf, count, pos); + ret = file->f_op->read(file, (void __user *)buf, count, pos); else if (file->f_op->read_iter) - return new_sync_read(file, buf, count, pos); + ret = new_sync_read(file, (void __user *)buf, count, pos); else - return -EINVAL; + ret = -EINVAL; + set_fs(old_fs); + if (ret > 0) { + fsnotify_access(file); + add_rchar(current, ret); + } + inc_syscr(current); + return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { - mm_segment_t old_fs; - ssize_t result; + ssize_t ret; - old_fs = get_fs(); - set_fs(KERNEL_DS); - /* The cast to a user pointer is valid due to the set_fs() */ - result = vfs_read(file, (void __user *)buf, count, pos); - set_fs(old_fs); - return result; + ret = rw_verify_area(READ, file, pos, count); + if (ret) + return ret; + return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); @@ -456,17 +470,22 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); - if (!ret) { - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - ret = __vfs_read(file, buf, count, pos); - if (ret > 0) { - fsnotify_access(file); - add_rchar(current, ret); - } - inc_syscr(current); - } + if (ret) + return ret; + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + if (file->f_op->read) + ret = file->f_op->read(file, buf, count, pos); + else if (file->f_op->read_iter) + ret = new_sync_read(file, buf, count, pos); + else + ret = -EINVAL; + if (ret > 0) { + fsnotify_access(file); + add_rchar(current, ret); + } + inc_syscr(current); return ret; } @@ -488,23 +507,15 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t return ret; } -static ssize_t __vfs_write(struct file *file, const char __user *p, - size_t count, loff_t *pos) -{ - if (file->f_op->write) - return file->f_op->write(file, p, count, pos); - else if (file->f_op->write_iter) - return new_sync_write(file, p, count, pos); - else - return -EINVAL; -} - +/* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { mm_segment_t old_fs; const char __user *p; ssize_t ret; + if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) + return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; @@ -513,7 +524,12 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; - ret = __vfs_write(file, p, count, pos); + if (file->f_op->write) + ret = file->f_op->write(file, p, count, pos); + else if (file->f_op->write_iter) + ret = new_sync_write(file, p, count, pos); + else + ret = -EINVAL; set_fs(old_fs); if (ret > 0) { fsnotify_modify(file); @@ -522,21 +538,20 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t inc_syscw(current); return ret; } -EXPORT_SYMBOL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { - mm_segment_t old_fs; - ssize_t res; + ssize_t ret; - old_fs = get_fs(); - set_fs(KERNEL_DS); - /* The cast to a user pointer is valid due to the set_fs() */ - res = vfs_write(file, (__force const char __user *)buf, count, pos); - set_fs(old_fs); + ret = rw_verify_area(WRITE, file, pos, count); + if (ret) + return ret; - return res; + file_start_write(file); + ret = __kernel_write(file, buf, count, pos); + file_end_write(file); + return ret; } EXPORT_SYMBOL(kernel_write); @@ -552,19 +567,23 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); - if (!ret) { - if (count > MAX_RW_COUNT) - count = MAX_RW_COUNT; - file_start_write(file); - ret = __vfs_write(file, buf, count, pos); - if (ret > 0) { - fsnotify_modify(file); - add_wchar(current, ret); - } - inc_syscw(current); - file_end_write(file); + if (ret) + return ret; + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; + file_start_write(file); + if (file->f_op->write) + ret = file->f_op->write(file, buf, count, pos); + else if (file->f_op->write_iter) + ret = new_sync_write(file, buf, count, pos); + else + ret = -EINVAL; + if (ret > 0) { + fsnotify_modify(file); + add_wchar(current, ret); } - + inc_syscw(current); + file_end_write(file); return ret; } diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index b43f0e8f43f2..9ed90368ab31 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -671,7 +671,8 @@ xlog_cil_push_work( /* * Wake up any background push waiters now this context is being pushed. */ - wake_up_all(&ctx->push_wait); + if (ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) + wake_up_all(&cil->xc_push_wait); /* * Check if we've anything to push. If there is nothing, then we don't @@ -743,13 +744,12 @@ xlog_cil_push_work( /* * initialise the new context and attach it to the CIL. Then attach - * the current context to the CIL committing lsit so it can be found + * the current context to the CIL committing list so it can be found * during log forces to extract the commit lsn of the sequence that * needs to be forced. */ INIT_LIST_HEAD(&new_ctx->committing); INIT_LIST_HEAD(&new_ctx->busy_extents); - init_waitqueue_head(&new_ctx->push_wait); new_ctx->sequence = ctx->sequence + 1; new_ctx->cil = cil; cil->xc_ctx = new_ctx; @@ -937,7 +937,7 @@ xlog_cil_push_background( if (cil->xc_ctx->space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) { trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket); ASSERT(cil->xc_ctx->space_used < log->l_logsize); - xlog_wait(&cil->xc_ctx->push_wait, &cil->xc_push_lock); + xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock); return; } @@ -1216,12 +1216,12 @@ xlog_cil_init( INIT_LIST_HEAD(&cil->xc_committing); spin_lock_init(&cil->xc_cil_lock); spin_lock_init(&cil->xc_push_lock); + init_waitqueue_head(&cil->xc_push_wait); init_rwsem(&cil->xc_ctx_lock); init_waitqueue_head(&cil->xc_commit_wait); INIT_LIST_HEAD(&ctx->committing); INIT_LIST_HEAD(&ctx->busy_extents); - init_waitqueue_head(&ctx->push_wait); ctx->sequence = 1; ctx->cil = cil; cil->xc_ctx = ctx; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index ec22c7a3867f..75a62870b63a 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -240,7 +240,6 @@ struct xfs_cil_ctx { struct xfs_log_vec *lv_chain; /* logvecs being pushed */ struct list_head iclog_entry; struct list_head committing; /* ctx committing list */ - wait_queue_head_t push_wait; /* background push throttle */ struct work_struct discard_endio_work; }; @@ -274,6 +273,7 @@ struct xfs_cil { wait_queue_head_t xc_commit_wait; xfs_lsn_t xc_current_sequence; struct work_struct xc_push_work; + wait_queue_head_t xc_push_wait; /* background push throttle */ } ____cacheline_aligned_in_smp; /* diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 907fa5d16494..4a674db4e1fa 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -2,6 +2,11 @@ #ifndef _ASM_GENERIC_CACHEFLUSH_H #define _ASM_GENERIC_CACHEFLUSH_H +struct mm_struct; +struct vm_area_struct; +struct page; +struct address_space; + /* * The cache doesn't need to be flushed when TLB entries change when * the cache is mapped to physical memory, not virtual memory diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 56527c85d122..088c1ded2714 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -29,8 +29,8 @@ struct alg_sock { struct sock *parent; - unsigned int refcnt; - unsigned int nokey_refcnt; + atomic_t refcnt; + atomic_t nokey_refcnt; const struct af_alg_type *type; void *private; diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h index 2c4927bf7b8d..fd525c71d676 100644 --- a/include/linux/atomic-fallback.h +++ b/include/linux/atomic-fallback.h @@ -77,6 +77,9 @@ #endif /* cmpxchg64_relaxed */ +#define arch_atomic_read atomic_read +#define arch_atomic_read_acquire atomic_read_acquire + #ifndef atomic_read_acquire static __always_inline int atomic_read_acquire(const atomic_t *v) @@ -86,6 +89,9 @@ atomic_read_acquire(const atomic_t *v) #define atomic_read_acquire atomic_read_acquire #endif +#define arch_atomic_set atomic_set +#define arch_atomic_set_release atomic_set_release + #ifndef atomic_set_release static __always_inline void atomic_set_release(atomic_t *v, int i) @@ -95,6 +101,13 @@ atomic_set_release(atomic_t *v, int i) #define atomic_set_release atomic_set_release #endif +#define arch_atomic_add atomic_add + +#define arch_atomic_add_return atomic_add_return +#define arch_atomic_add_return_acquire atomic_add_return_acquire +#define arch_atomic_add_return_release atomic_add_return_release +#define arch_atomic_add_return_relaxed atomic_add_return_relaxed + #ifndef atomic_add_return_relaxed #define atomic_add_return_acquire atomic_add_return #define atomic_add_return_release atomic_add_return @@ -137,6 +150,11 @@ atomic_add_return(int i, atomic_t *v) #endif /* atomic_add_return_relaxed */ +#define arch_atomic_fetch_add atomic_fetch_add +#define arch_atomic_fetch_add_acquire atomic_fetch_add_acquire +#define arch_atomic_fetch_add_release atomic_fetch_add_release +#define arch_atomic_fetch_add_relaxed atomic_fetch_add_relaxed + #ifndef atomic_fetch_add_relaxed #define atomic_fetch_add_acquire atomic_fetch_add #define atomic_fetch_add_release atomic_fetch_add @@ -179,6 +197,13 @@ atomic_fetch_add(int i, atomic_t *v) #endif /* atomic_fetch_add_relaxed */ +#define arch_atomic_sub atomic_sub + +#define arch_atomic_sub_return atomic_sub_return +#define arch_atomic_sub_return_acquire atomic_sub_return_acquire +#define arch_atomic_sub_return_release atomic_sub_return_release +#define arch_atomic_sub_return_relaxed atomic_sub_return_relaxed + #ifndef atomic_sub_return_relaxed #define atomic_sub_return_acquire atomic_sub_return #define atomic_sub_return_release atomic_sub_return @@ -221,6 +246,11 @@ atomic_sub_return(int i, atomic_t *v) #endif /* atomic_sub_return_relaxed */ +#define arch_atomic_fetch_sub atomic_fetch_sub +#define arch_atomic_fetch_sub_acquire atomic_fetch_sub_acquire +#define arch_atomic_fetch_sub_release atomic_fetch_sub_release +#define arch_atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed + #ifndef atomic_fetch_sub_relaxed #define atomic_fetch_sub_acquire atomic_fetch_sub #define atomic_fetch_sub_release atomic_fetch_sub @@ -263,6 +293,8 @@ atomic_fetch_sub(int i, atomic_t *v) #endif /* atomic_fetch_sub_relaxed */ +#define arch_atomic_inc atomic_inc + #ifndef atomic_inc static __always_inline void atomic_inc(atomic_t *v) @@ -272,6 +304,11 @@ atomic_inc(atomic_t *v) #define atomic_inc atomic_inc #endif +#define arch_atomic_inc_return atomic_inc_return +#define arch_atomic_inc_return_acquire atomic_inc_return_acquire +#define arch_atomic_inc_return_release atomic_inc_return_release +#define arch_atomic_inc_return_relaxed atomic_inc_return_relaxed + #ifndef atomic_inc_return_relaxed #ifdef atomic_inc_return #define atomic_inc_return_acquire atomic_inc_return @@ -353,6 +390,11 @@ atomic_inc_return(atomic_t *v) #endif /* atomic_inc_return_relaxed */ +#define arch_atomic_fetch_inc atomic_fetch_inc +#define arch_atomic_fetch_inc_acquire atomic_fetch_inc_acquire +#define arch_atomic_fetch_inc_release atomic_fetch_inc_release +#define arch_atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed + #ifndef atomic_fetch_inc_relaxed #ifdef atomic_fetch_inc #define atomic_fetch_inc_acquire atomic_fetch_inc @@ -434,6 +476,8 @@ atomic_fetch_inc(atomic_t *v) #endif /* atomic_fetch_inc_relaxed */ +#define arch_atomic_dec atomic_dec + #ifndef atomic_dec static __always_inline void atomic_dec(atomic_t *v) @@ -443,6 +487,11 @@ atomic_dec(atomic_t *v) #define atomic_dec atomic_dec #endif +#define arch_atomic_dec_return atomic_dec_return +#define arch_atomic_dec_return_acquire atomic_dec_return_acquire +#define arch_atomic_dec_return_release atomic_dec_return_release +#define arch_atomic_dec_return_relaxed atomic_dec_return_relaxed + #ifndef atomic_dec_return_relaxed #ifdef atomic_dec_return #define atomic_dec_return_acquire atomic_dec_return @@ -524,6 +573,11 @@ atomic_dec_return(atomic_t *v) #endif /* atomic_dec_return_relaxed */ +#define arch_atomic_fetch_dec atomic_fetch_dec +#define arch_atomic_fetch_dec_acquire atomic_fetch_dec_acquire +#define arch_atomic_fetch_dec_release atomic_fetch_dec_release +#define arch_atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed + #ifndef atomic_fetch_dec_relaxed #ifdef atomic_fetch_dec #define atomic_fetch_dec_acquire atomic_fetch_dec @@ -605,6 +659,13 @@ atomic_fetch_dec(atomic_t *v) #endif /* atomic_fetch_dec_relaxed */ +#define arch_atomic_and atomic_and + +#define arch_atomic_fetch_and atomic_fetch_and +#define arch_atomic_fetch_and_acquire atomic_fetch_and_acquire +#define arch_atomic_fetch_and_release atomic_fetch_and_release +#define arch_atomic_fetch_and_relaxed atomic_fetch_and_relaxed + #ifndef atomic_fetch_and_relaxed #define atomic_fetch_and_acquire atomic_fetch_and #define atomic_fetch_and_release atomic_fetch_and @@ -647,6 +708,8 @@ atomic_fetch_and(int i, atomic_t *v) #endif /* atomic_fetch_and_relaxed */ +#define arch_atomic_andnot atomic_andnot + #ifndef atomic_andnot static __always_inline void atomic_andnot(int i, atomic_t *v) @@ -656,6 +719,11 @@ atomic_andnot(int i, atomic_t *v) #define atomic_andnot atomic_andnot #endif +#define arch_atomic_fetch_andnot atomic_fetch_andnot +#define arch_atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire +#define arch_atomic_fetch_andnot_release atomic_fetch_andnot_release +#define arch_atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed + #ifndef atomic_fetch_andnot_relaxed #ifdef atomic_fetch_andnot #define atomic_fetch_andnot_acquire atomic_fetch_andnot @@ -737,6 +805,13 @@ atomic_fetch_andnot(int i, atomic_t *v) #endif /* atomic_fetch_andnot_relaxed */ +#define arch_atomic_or atomic_or + +#define arch_atomic_fetch_or atomic_fetch_or +#define arch_atomic_fetch_or_acquire atomic_fetch_or_acquire +#define arch_atomic_fetch_or_release atomic_fetch_or_release +#define arch_atomic_fetch_or_relaxed atomic_fetch_or_relaxed + #ifndef atomic_fetch_or_relaxed #define atomic_fetch_or_acquire atomic_fetch_or #define atomic_fetch_or_release atomic_fetch_or @@ -779,6 +854,13 @@ atomic_fetch_or(int i, atomic_t *v) #endif /* atomic_fetch_or_relaxed */ +#define arch_atomic_xor atomic_xor + +#define arch_atomic_fetch_xor atomic_fetch_xor +#define arch_atomic_fetch_xor_acquire atomic_fetch_xor_acquire +#define arch_atomic_fetch_xor_release atomic_fetch_xor_release +#define arch_atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed + #ifndef atomic_fetch_xor_relaxed #define atomic_fetch_xor_acquire atomic_fetch_xor #define atomic_fetch_xor_release atomic_fetch_xor @@ -821,6 +903,11 @@ atomic_fetch_xor(int i, atomic_t *v) #endif /* atomic_fetch_xor_relaxed */ +#define arch_atomic_xchg atomic_xchg +#define arch_atomic_xchg_acquire atomic_xchg_acquire +#define arch_atomic_xchg_release atomic_xchg_release +#define arch_atomic_xchg_relaxed atomic_xchg_relaxed + #ifndef atomic_xchg_relaxed #define atomic_xchg_acquire atomic_xchg #define atomic_xchg_release atomic_xchg @@ -863,6 +950,11 @@ atomic_xchg(atomic_t *v, int i) #endif /* atomic_xchg_relaxed */ +#define arch_atomic_cmpxchg atomic_cmpxchg +#define arch_atomic_cmpxchg_acquire atomic_cmpxchg_acquire +#define arch_atomic_cmpxchg_release atomic_cmpxchg_release +#define arch_atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed + #ifndef atomic_cmpxchg_relaxed #define atomic_cmpxchg_acquire atomic_cmpxchg #define atomic_cmpxchg_release atomic_cmpxchg @@ -905,6 +997,11 @@ atomic_cmpxchg(atomic_t *v, int old, int new) #endif /* atomic_cmpxchg_relaxed */ +#define arch_atomic_try_cmpxchg atomic_try_cmpxchg +#define arch_atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire +#define arch_atomic_try_cmpxchg_release atomic_try_cmpxchg_release +#define arch_atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed + #ifndef atomic_try_cmpxchg_relaxed #ifdef atomic_try_cmpxchg #define atomic_try_cmpxchg_acquire atomic_try_cmpxchg @@ -1002,6 +1099,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) #endif /* atomic_try_cmpxchg_relaxed */ +#define arch_atomic_sub_and_test atomic_sub_and_test + #ifndef atomic_sub_and_test /** * atomic_sub_and_test - subtract value from variable and test result @@ -1020,6 +1119,8 @@ atomic_sub_and_test(int i, atomic_t *v) #define atomic_sub_and_test atomic_sub_and_test #endif +#define arch_atomic_dec_and_test atomic_dec_and_test + #ifndef atomic_dec_and_test /** * atomic_dec_and_test - decrement and test @@ -1037,6 +1138,8 @@ atomic_dec_and_test(atomic_t *v) #define atomic_dec_and_test atomic_dec_and_test #endif +#define arch_atomic_inc_and_test atomic_inc_and_test + #ifndef atomic_inc_and_test /** * atomic_inc_and_test - increment and test @@ -1054,6 +1157,8 @@ atomic_inc_and_test(atomic_t *v) #define atomic_inc_and_test atomic_inc_and_test #endif +#define arch_atomic_add_negative atomic_add_negative + #ifndef atomic_add_negative /** * atomic_add_negative - add and test if negative @@ -1072,6 +1177,8 @@ atomic_add_negative(int i, atomic_t *v) #define atomic_add_negative atomic_add_negative #endif +#define arch_atomic_fetch_add_unless atomic_fetch_add_unless + #ifndef atomic_fetch_add_unless /** * atomic_fetch_add_unless - add unless the number is already a given value @@ -1097,6 +1204,8 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) #define atomic_fetch_add_unless atomic_fetch_add_unless #endif +#define arch_atomic_add_unless atomic_add_unless + #ifndef atomic_add_unless /** * atomic_add_unless - add unless the number is already a given value @@ -1115,6 +1224,8 @@ atomic_add_unless(atomic_t *v, int a, int u) #define atomic_add_unless atomic_add_unless #endif +#define arch_atomic_inc_not_zero atomic_inc_not_zero + #ifndef atomic_inc_not_zero /** * atomic_inc_not_zero - increment unless the number is zero @@ -1131,6 +1242,8 @@ atomic_inc_not_zero(atomic_t *v) #define atomic_inc_not_zero atomic_inc_not_zero #endif +#define arch_atomic_inc_unless_negative atomic_inc_unless_negative + #ifndef atomic_inc_unless_negative static __always_inline bool atomic_inc_unless_negative(atomic_t *v) @@ -1147,6 +1260,8 @@ atomic_inc_unless_negative(atomic_t *v) #define atomic_inc_unless_negative atomic_inc_unless_negative #endif +#define arch_atomic_dec_unless_positive atomic_dec_unless_positive + #ifndef atomic_dec_unless_positive static __always_inline bool atomic_dec_unless_positive(atomic_t *v) @@ -1163,6 +1278,8 @@ atomic_dec_unless_positive(atomic_t *v) #define atomic_dec_unless_positive atomic_dec_unless_positive #endif +#define arch_atomic_dec_if_positive atomic_dec_if_positive + #ifndef atomic_dec_if_positive static __always_inline int atomic_dec_if_positive(atomic_t *v) @@ -1184,6 +1301,9 @@ atomic_dec_if_positive(atomic_t *v) #include <asm-generic/atomic64.h> #endif +#define arch_atomic64_read atomic64_read +#define arch_atomic64_read_acquire atomic64_read_acquire + #ifndef atomic64_read_acquire static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) @@ -1193,6 +1313,9 @@ atomic64_read_acquire(const atomic64_t *v) #define atomic64_read_acquire atomic64_read_acquire #endif +#define arch_atomic64_set atomic64_set +#define arch_atomic64_set_release atomic64_set_release + #ifndef atomic64_set_release static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) @@ -1202,6 +1325,13 @@ atomic64_set_release(atomic64_t *v, s64 i) #define atomic64_set_release atomic64_set_release #endif +#define arch_atomic64_add atomic64_add + +#define arch_atomic64_add_return atomic64_add_return +#define arch_atomic64_add_return_acquire atomic64_add_return_acquire +#define arch_atomic64_add_return_release atomic64_add_return_release +#define arch_atomic64_add_return_relaxed atomic64_add_return_relaxed + #ifndef atomic64_add_return_relaxed #define atomic64_add_return_acquire atomic64_add_return #define atomic64_add_return_release atomic64_add_return @@ -1244,6 +1374,11 @@ atomic64_add_return(s64 i, atomic64_t *v) #endif /* atomic64_add_return_relaxed */ +#define arch_atomic64_fetch_add atomic64_fetch_add +#define arch_atomic64_fetch_add_acquire atomic64_fetch_add_acquire +#define arch_atomic64_fetch_add_release atomic64_fetch_add_release +#define arch_atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed + #ifndef atomic64_fetch_add_relaxed #define atomic64_fetch_add_acquire atomic64_fetch_add #define atomic64_fetch_add_release atomic64_fetch_add @@ -1286,6 +1421,13 @@ atomic64_fetch_add(s64 i, atomic64_t *v) #endif /* atomic64_fetch_add_relaxed */ +#define arch_atomic64_sub atomic64_sub + +#define arch_atomic64_sub_return atomic64_sub_return +#define arch_atomic64_sub_return_acquire atomic64_sub_return_acquire +#define arch_atomic64_sub_return_release atomic64_sub_return_release +#define arch_atomic64_sub_return_relaxed atomic64_sub_return_relaxed + #ifndef atomic64_sub_return_relaxed #define atomic64_sub_return_acquire atomic64_sub_return #define atomic64_sub_return_release atomic64_sub_return @@ -1328,6 +1470,11 @@ atomic64_sub_return(s64 i, atomic64_t *v) #endif /* atomic64_sub_return_relaxed */ +#define arch_atomic64_fetch_sub atomic64_fetch_sub +#define arch_atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire +#define arch_atomic64_fetch_sub_release atomic64_fetch_sub_release +#define arch_atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed + #ifndef atomic64_fetch_sub_relaxed #define atomic64_fetch_sub_acquire atomic64_fetch_sub #define atomic64_fetch_sub_release atomic64_fetch_sub @@ -1370,6 +1517,8 @@ atomic64_fetch_sub(s64 i, atomic64_t *v) #endif /* atomic64_fetch_sub_relaxed */ +#define arch_atomic64_inc atomic64_inc + #ifndef atomic64_inc static __always_inline void atomic64_inc(atomic64_t *v) @@ -1379,6 +1528,11 @@ atomic64_inc(atomic64_t *v) #define atomic64_inc atomic64_inc #endif +#define arch_atomic64_inc_return atomic64_inc_return +#define arch_atomic64_inc_return_acquire atomic64_inc_return_acquire +#define arch_atomic64_inc_return_release atomic64_inc_return_release +#define arch_atomic64_inc_return_relaxed atomic64_inc_return_relaxed + #ifndef atomic64_inc_return_relaxed #ifdef atomic64_inc_return #define atomic64_inc_return_acquire atomic64_inc_return @@ -1460,6 +1614,11 @@ atomic64_inc_return(atomic64_t *v) #endif /* atomic64_inc_return_relaxed */ +#define arch_atomic64_fetch_inc atomic64_fetch_inc +#define arch_atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire +#define arch_atomic64_fetch_inc_release atomic64_fetch_inc_release +#define arch_atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed + #ifndef atomic64_fetch_inc_relaxed #ifdef atomic64_fetch_inc #define atomic64_fetch_inc_acquire atomic64_fetch_inc @@ -1541,6 +1700,8 @@ atomic64_fetch_inc(atomic64_t *v) #endif /* atomic64_fetch_inc_relaxed */ +#define arch_atomic64_dec atomic64_dec + #ifndef atomic64_dec static __always_inline void atomic64_dec(atomic64_t *v) @@ -1550,6 +1711,11 @@ atomic64_dec(atomic64_t *v) #define atomic64_dec atomic64_dec #endif +#define arch_atomic64_dec_return atomic64_dec_return +#define arch_atomic64_dec_return_acquire atomic64_dec_return_acquire +#define arch_atomic64_dec_return_release atomic64_dec_return_release +#define arch_atomic64_dec_return_relaxed atomic64_dec_return_relaxed + #ifndef atomic64_dec_return_relaxed #ifdef atomic64_dec_return #define atomic64_dec_return_acquire atomic64_dec_return @@ -1631,6 +1797,11 @@ atomic64_dec_return(atomic64_t *v) #endif /* atomic64_dec_return_relaxed */ +#define arch_atomic64_fetch_dec atomic64_fetch_dec +#define arch_atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire +#define arch_atomic64_fetch_dec_release atomic64_fetch_dec_release +#define arch_atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed + #ifndef atomic64_fetch_dec_relaxed #ifdef atomic64_fetch_dec #define atomic64_fetch_dec_acquire atomic64_fetch_dec @@ -1712,6 +1883,13 @@ atomic64_fetch_dec(atomic64_t *v) #endif /* atomic64_fetch_dec_relaxed */ +#define arch_atomic64_and atomic64_and + +#define arch_atomic64_fetch_and atomic64_fetch_and +#define arch_atomic64_fetch_and_acquire atomic64_fetch_and_acquire +#define arch_atomic64_fetch_and_release atomic64_fetch_and_release +#define arch_atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed + #ifndef atomic64_fetch_and_relaxed #define atomic64_fetch_and_acquire atomic64_fetch_and #define atomic64_fetch_and_release atomic64_fetch_and @@ -1754,6 +1932,8 @@ atomic64_fetch_and(s64 i, atomic64_t *v) #endif /* atomic64_fetch_and_relaxed */ +#define arch_atomic64_andnot atomic64_andnot + #ifndef atomic64_andnot static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) @@ -1763,6 +1943,11 @@ atomic64_andnot(s64 i, atomic64_t *v) #define atomic64_andnot atomic64_andnot #endif +#define arch_atomic64_fetch_andnot atomic64_fetch_andnot +#define arch_atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire +#define arch_atomic64_fetch_andnot_release atomic64_fetch_andnot_release +#define arch_atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed + #ifndef atomic64_fetch_andnot_relaxed #ifdef atomic64_fetch_andnot #define atomic64_fetch_andnot_acquire atomic64_fetch_andnot @@ -1844,6 +2029,13 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v) #endif /* atomic64_fetch_andnot_relaxed */ +#define arch_atomic64_or atomic64_or + +#define arch_atomic64_fetch_or atomic64_fetch_or +#define arch_atomic64_fetch_or_acquire atomic64_fetch_or_acquire +#define arch_atomic64_fetch_or_release atomic64_fetch_or_release +#define arch_atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed + #ifndef atomic64_fetch_or_relaxed #define atomic64_fetch_or_acquire atomic64_fetch_or #define atomic64_fetch_or_release atomic64_fetch_or @@ -1886,6 +2078,13 @@ atomic64_fetch_or(s64 i, atomic64_t *v) #endif /* atomic64_fetch_or_relaxed */ +#define arch_atomic64_xor atomic64_xor + +#define arch_atomic64_fetch_xor atomic64_fetch_xor +#define arch_atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire +#define arch_atomic64_fetch_xor_release atomic64_fetch_xor_release +#define arch_atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed + #ifndef atomic64_fetch_xor_relaxed #define atomic64_fetch_xor_acquire atomic64_fetch_xor #define atomic64_fetch_xor_release atomic64_fetch_xor @@ -1928,6 +2127,11 @@ atomic64_fetch_xor(s64 i, atomic64_t *v) #endif /* atomic64_fetch_xor_relaxed */ +#define arch_atomic64_xchg atomic64_xchg +#define arch_atomic64_xchg_acquire atomic64_xchg_acquire +#define arch_atomic64_xchg_release atomic64_xchg_release +#define arch_atomic64_xchg_relaxed atomic64_xchg_relaxed + #ifndef atomic64_xchg_relaxed #define atomic64_xchg_acquire atomic64_xchg #define atomic64_xchg_release atomic64_xchg @@ -1970,6 +2174,11 @@ atomic64_xchg(atomic64_t *v, s64 i) #endif /* atomic64_xchg_relaxed */ +#define arch_atomic64_cmpxchg atomic64_cmpxchg +#define arch_atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire +#define arch_atomic64_cmpxchg_release atomic64_cmpxchg_release +#define arch_atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed + #ifndef atomic64_cmpxchg_relaxed #define atomic64_cmpxchg_acquire atomic64_cmpxchg #define atomic64_cmpxchg_release atomic64_cmpxchg @@ -2012,6 +2221,11 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) #endif /* atomic64_cmpxchg_relaxed */ +#define arch_atomic64_try_cmpxchg atomic64_try_cmpxchg +#define arch_atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire +#define arch_atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release +#define arch_atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed + #ifndef atomic64_try_cmpxchg_relaxed #ifdef atomic64_try_cmpxchg #define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg @@ -2109,6 +2323,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) #endif /* atomic64_try_cmpxchg_relaxed */ +#define arch_atomic64_sub_and_test atomic64_sub_and_test + #ifndef atomic64_sub_and_test /** * atomic64_sub_and_test - subtract value from variable and test result @@ -2127,6 +2343,8 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) #define atomic64_sub_and_test atomic64_sub_and_test #endif +#define arch_atomic64_dec_and_test atomic64_dec_and_test + #ifndef atomic64_dec_and_test /** * atomic64_dec_and_test - decrement and test @@ -2144,6 +2362,8 @@ atomic64_dec_and_test(atomic64_t *v) #define atomic64_dec_and_test atomic64_dec_and_test #endif +#define arch_atomic64_inc_and_test atomic64_inc_and_test + #ifndef atomic64_inc_and_test /** * atomic64_inc_and_test - increment and test @@ -2161,6 +2381,8 @@ atomic64_inc_and_test(atomic64_t *v) #define atomic64_inc_and_test atomic64_inc_and_test #endif +#define arch_atomic64_add_negative atomic64_add_negative + #ifndef atomic64_add_negative /** * atomic64_add_negative - add and test if negative @@ -2179,6 +2401,8 @@ atomic64_add_negative(s64 i, atomic64_t *v) #define atomic64_add_negative atomic64_add_negative #endif +#define arch_atomic64_fetch_add_unless atomic64_fetch_add_unless + #ifndef atomic64_fetch_add_unless /** * atomic64_fetch_add_unless - add unless the number is already a given value @@ -2204,6 +2428,8 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) #define atomic64_fetch_add_unless atomic64_fetch_add_unless #endif +#define arch_atomic64_add_unless atomic64_add_unless + #ifndef atomic64_add_unless /** * atomic64_add_unless - add unless the number is already a given value @@ -2222,6 +2448,8 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) #define atomic64_add_unless atomic64_add_unless #endif +#define arch_atomic64_inc_not_zero atomic64_inc_not_zero + #ifndef atomic64_inc_not_zero /** * atomic64_inc_not_zero - increment unless the number is zero @@ -2238,6 +2466,8 @@ atomic64_inc_not_zero(atomic64_t *v) #define atomic64_inc_not_zero atomic64_inc_not_zero #endif +#define arch_atomic64_inc_unless_negative atomic64_inc_unless_negative + #ifndef atomic64_inc_unless_negative static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) @@ -2254,6 +2484,8 @@ atomic64_inc_unless_negative(atomic64_t *v) #define atomic64_inc_unless_negative atomic64_inc_unless_negative #endif +#define arch_atomic64_dec_unless_positive atomic64_dec_unless_positive + #ifndef atomic64_dec_unless_positive static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) @@ -2270,6 +2502,8 @@ atomic64_dec_unless_positive(atomic64_t *v) #define atomic64_dec_unless_positive atomic64_dec_unless_positive #endif +#define arch_atomic64_dec_if_positive atomic64_dec_if_positive + #ifndef atomic64_dec_if_positive static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) @@ -2288,4 +2522,4 @@ atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 1fac0941c79bf0ae100723cc2ac9b94061f0b67a +// 9d95b56f98d82a2a26c7b79ccdd0c47572d50a6f diff --git a/include/linux/bits.h b/include/linux/bits.h index 4671fbf28842..7f475d59a097 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -18,8 +18,7 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#if !defined(__ASSEMBLY__) && \ - (!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000) +#if !defined(__ASSEMBLY__) #include <linux/build_bug.h> #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8fd900998b4e..57241417ff2f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -590,6 +590,7 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; +/* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 4052d649f36d..47d5b0c708c9 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); -int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr, return -EOPNOTSUPP; } -static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +static inline int netns_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) { return -EOPNOTSUPP; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0cd7f6884c5c..c67c88ad35f8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1563,13 +1563,16 @@ static inline void init_btf_sock_ids(struct btf *btf) #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, u32 which) + struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { return -EOPNOTSUPP; } @@ -1579,6 +1582,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/btf.h b/include/linux/btf.h index 5c1ea99b480f..8b81fbb4497c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } +static inline bool btf_type_is_small_int(const struct btf_type *t) +{ + return btf_type_is_int(t) && t->size <= sizeof(u64); +} + static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 52661155f85f..fee0b5547cd0 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -790,7 +790,9 @@ struct sock_cgroup_data { union { #ifdef __LITTLE_ENDIAN struct { - u8 is_data; + u8 is_data : 1; + u8 no_refcnt : 1; + u8 unused : 6; u8 padding; u16 prioidx; u32 classid; @@ -800,7 +802,9 @@ struct sock_cgroup_data { u32 classid; u16 prioidx; u8 padding; - u8 is_data; + u8 unused : 6; + u8 no_refcnt : 1; + u8 is_data : 1; } __packed; #endif u64 val; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4598e4da6b1b..618838c48313 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock; void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); +void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) @@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) */ v = READ_ONCE(skcd->val); - if (v & 1) + if (v & 3) return &cgrp_dfl_root.cgrp; return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; @@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} +static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index ee37256ec8bd..5e55302e3bf6 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -33,6 +33,14 @@ #define __no_sanitize_thread #endif +#if __has_feature(undefined_behavior_sanitizer) +/* GCC does not have __SANITIZE_UNDEFINED__ */ +#define __no_sanitize_undefined \ + __attribute__((no_sanitize("undefined"))) +#else +#define __no_sanitize_undefined +#endif + /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7dd4e0349ef3..0b1dc61f3955 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -11,7 +11,7 @@ + __GNUC_PATCHLEVEL__) /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ -#if GCC_VERSION < 40800 +#if GCC_VERSION < 40900 # error Sorry, your compiler is too old - please upgrade it. #endif @@ -150,6 +150,12 @@ #define __no_sanitize_thread #endif +#if __has_attribute(__no_sanitize_undefined__) +#define __no_sanitize_undefined __attribute__((no_sanitize_undefined)) +#else +#define __no_sanitize_undefined +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 30827f82ad62..204e76856435 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -123,7 +123,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #ifdef CONFIG_DEBUG_ENTRY /* Begin/end of an instrumentation safe region */ #define instrumentation_begin() ({ \ - asm volatile("%c0:\n\t" \ + asm volatile("%c0: nop\n\t" \ ".pushsection .discard.instr_begin\n\t" \ ".long %c0b - .\n\t" \ ".popsection\n\t" : : "i" (__COUNTER__)); \ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index cdf016596659..c8f03d2969df 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___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) # define __GCC4_has_attribute___fallthrough__ 0 #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index e368384445b6..01dd58c74d80 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -118,10 +118,6 @@ struct ftrace_likely_data { #define notrace __attribute__((__no_instrument_function__)) #endif -/* Section for code which can't be instrumented at all */ -#define noinstr \ - noinline notrace __attribute((__section__(".noinstr.text"))) - /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without @@ -193,16 +189,18 @@ struct ftrace_likely_data { #define __no_kcsan __no_sanitize_thread #ifdef __SANITIZE_THREAD__ -# define __no_kcsan_or_inline __no_kcsan notrace __maybe_unused -# define __no_sanitize_or_inline __no_kcsan_or_inline -#else -# define __no_kcsan_or_inline __always_inline +# define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused #endif #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif +/* Section for code which can't be instrumented at all */ +#define noinstr \ + noinline notrace __attribute((__section__(".noinstr.text"))) \ + __no_kcsan __no_sanitize_address + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ @@ -254,32 +252,8 @@ struct ftrace_likely_data { * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving * non-scalar types unchanged. */ -#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900) || defined(__CHECKER__) /* - * We build this out of a couple of helper macros in a vain attempt to - * help you keep your lunch down while reading it. - */ -#define __pick_scalar_type(x, type, otherwise) \ - __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) - -/* - * 'char' is not type-compatible with either 'signed char' or 'unsigned char', - * so we include the naked type here as well as the signed/unsigned variants. - */ -#define __pick_integer_type(x, type, otherwise) \ - __pick_scalar_type(x, type, \ - __pick_scalar_type(x, unsigned type, \ - __pick_scalar_type(x, signed type, otherwise))) - -#define __unqual_scalar_typeof(x) typeof( \ - __pick_integer_type(x, char, \ - __pick_integer_type(x, short, \ - __pick_integer_type(x, int, \ - __pick_integer_type(x, long, \ - __pick_integer_type(x, long long, x)))))) -#else -/* - * If supported, prefer C11 _Generic for better compile-times. As above, 'char' + * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char' * is not type-compatible with 'signed char', and we define a separate case. */ #define __scalar_type_to_expr_cases(type) \ @@ -295,7 +269,6 @@ struct ftrace_likely_data { __scalar_type_to_expr_cases(long), \ __scalar_type_to_expr_cases(long long), \ default: (x))) -#endif /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 63cb3606dea7..851dd1f9a8a5 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -38,6 +38,11 @@ struct debugfs_regset32 { struct device *dev; /* Optional device for Runtime PM */ }; +struct debugfs_u32_array { + u32 *array; + u32 n_elements; +}; + extern struct dentry *arch_debugfs_dir; #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ @@ -136,7 +141,8 @@ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, u32 elements); + struct dentry *parent, + struct debugfs_u32_array *array); struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, struct dentry *parent, @@ -316,8 +322,8 @@ static inline bool debugfs_initialized(void) } static inline void debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, u32 *array, - u32 elements) + struct dentry *parent, + struct debugfs_u32_array *array) { } diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 136f984df0d9..5184735a0fe8 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -77,8 +77,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, - gfp_t gfp, unsigned long attrs); int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); @@ -87,4 +85,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 78f677cf45ab..a33ed3954ed4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, @@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; diff --git a/include/linux/efi.h b/include/linux/efi.h index 2c6495f72f79..bb35f3305e55 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -350,6 +350,7 @@ void efi_native_runtime_setup(void); * associated with ConOut */ #define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID EFI_GUID(0xe03fc20a, 0x85dc, 0x406e, 0xb9, 0x0e, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95) +#define LINUX_EFI_ARM_CPU_STATE_TABLE_GUID EFI_GUID(0xef79e4aa, 0x3c3d, 0x4989, 0xb9, 0x02, 0x07, 0xa9, 0x43, 0xe5, 0x50, 0xd2) #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) #define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) #define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa) @@ -1236,14 +1237,11 @@ struct linux_efi_memreserve { struct { phys_addr_t base; phys_addr_t size; - } entry[0]; + } entry[]; }; -#define EFI_MEMRESERVE_SIZE(count) (sizeof(struct linux_efi_memreserve) + \ - (count) * sizeof(((struct linux_efi_memreserve *)0)->entry[0])) - #define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \ - / sizeof(((struct linux_efi_memreserve *)0)->entry[0])) + / sizeof_field(struct linux_efi_memreserve, entry[0])) void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 48ad3b6a0150..969a80211df6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -502,5 +502,37 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd, u32 *dev_speed, u8 *dev_duplex); +struct netlink_ext_ack; +struct phy_device; +struct phy_tdr_config; + +/** + * struct ethtool_phy_ops - Optional PHY device options + * @get_sset_count: Get number of strings that @get_strings will write. + * @get_strings: Return a set of strings that describe the requested objects + * @get_stats: Return extended statistics about the PHY device. + * @start_cable_test - Start a cable test + * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test + * + * All operations are optional (i.e. the function pointer may be set to %NULL) + * and callers must take this into account. Callers must hold the RTNL lock. + */ +struct ethtool_phy_ops { + int (*get_sset_count)(struct phy_device *dev); + int (*get_strings)(struct phy_device *dev, u8 *data); + int (*get_stats)(struct phy_device *dev, + struct ethtool_stats *stats, u64 *data); + int (*start_cable_test)(struct phy_device *phydev, + struct netlink_ext_ack *extack); + int (*start_cable_test_tdr)(struct phy_device *phydev, + struct netlink_ext_ack *extack, + const struct phy_tdr_config *config); +}; + +/** + * ethtool_set_ethtool_phy_ops - Set the ethtool_phy_ops singleton + * @ops: Ethtool PHY operations to set + */ +void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops); #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 259377723603..0b0144752d78 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -884,12 +884,12 @@ void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_helper_changes_pkt_data(void *func); -static inline bool bpf_dump_raw_ok(void) +static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ - return kallsyms_show_value() == 1; + return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..f5abba86107d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -315,6 +315,7 @@ enum rw_hint { #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) #define IOCB_NOWAIT (1 << 7) +#define IOCB_NOIO (1 << 9) struct kiocb { struct file *ki_filp; @@ -1917,7 +1918,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, struct iovec *fast_pointer, struct iovec **ret_pointer); -extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, @@ -3033,6 +3033,7 @@ extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, lo extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); +ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index c230b4e70d75..a3a568bf9686 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -48,6 +48,9 @@ struct host1x_client_ops { * @channel: host1x channel associated with this client * @syncpts: array of syncpoints requested for this client * @num_syncpts: number of syncpoints requested for this client + * @parent: pointer to parent structure + * @usecount: reference count for this structure + * @lock: mutex for mutually exclusive concurrency */ struct host1x_client { struct list_head list; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index fe15f831841b..9f732499ea88 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3333,13 +3333,17 @@ struct ieee80211_multiple_bssid_configuration { #define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) #define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) #define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) +#define WLAN_AKM_SUITE_AP_PEER_KEY SUITE(0x000FAC, 10) #define WLAN_AKM_SUITE_8021X_SUITE_B SUITE(0x000FAC, 11) #define WLAN_AKM_SUITE_8021X_SUITE_B_192 SUITE(0x000FAC, 12) +#define WLAN_AKM_SUITE_FT_8021X_SHA384 SUITE(0x000FAC, 13) #define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14) #define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) #define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) #define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) #define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18) +#define WLAN_AKM_SUITE_FT_PSK_SHA384 SUITE(0x000FAC, 19) +#define WLAN_AKM_SUITE_PSK_SHA384 SUITE(0x000FAC, 20) #define WLAN_MAX_KEY_LEN 32 diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b05e855f1ddd..41a518336673 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -25,6 +25,8 @@ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ +#define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ + /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID @@ -577,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { - unsigned int vlan_depth = skb->mac_len; + unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at @@ -595,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, vlan_depth = ETH_HLEN; } do { - struct vlan_hdr *vh; + struct vlan_hdr vhdr, *vh; - if (unlikely(!pskb_may_pull(skb, - vlan_depth + VLAN_HLEN))) + vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + if (unlikely(!vh || !--parse_depth)) return 0; - vh = (struct vlan_hdr *)(skb->data + vlan_depth); type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); @@ -620,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 vlan_get_protocol(struct sk_buff *skb) +static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* A getter for the SKB protocol field which will handle VLAN tags consistently + * whether VLAN acceleration is enabled or not. + */ +static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) +{ + if (!skip_vlan) + /* VLAN acceleration strips the VLAN header from the skb and + * moves it to skb->vlan_proto + */ + return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; + + return vlan_get_protocol(skb); +} + static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4100bd224f5c..3e8fa1c7a1e6 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -41,6 +41,7 @@ #define DMA_PTE_SNP BIT_ULL(11) #define DMA_FL_PTE_PRESENT BIT_ULL(0) +#define DMA_FL_PTE_US BIT_ULL(2) #define DMA_FL_PTE_XD BIT_ULL(63) #define ADDR_WIDTH_5LEVEL (57) diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 2735da5f839e..30823780c192 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -2,7 +2,7 @@ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H -#include <linux/llist.h> +#include <linux/smp_types.h> /* * An entry can be in one of four states: @@ -13,24 +13,14 @@ * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ -/* flags share CSD_FLAG_ space */ - -#define IRQ_WORK_PENDING BIT(0) -#define IRQ_WORK_BUSY BIT(1) - -/* Doesn't want IPI, wait for tick: */ -#define IRQ_WORK_LAZY BIT(2) -/* Run hard IRQ context, even on RT */ -#define IRQ_WORK_HARD_IRQ BIT(3) - -#define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) - -/* - * structure shares layout with single_call_data_t. - */ struct irq_work { - struct llist_node llnode; - atomic_t flags; + union { + struct __call_single_node node; + struct { + struct llist_node llnode; + atomic_t flags; + }; + }; void (*func)(struct irq_work *); }; diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 98338dc6b5d2..481273f0c72d 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -18,6 +18,7 @@ #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) +struct cred; struct module; static inline int is_kernel_inittext(unsigned long addr) @@ -98,7 +99,7 @@ int lookup_symbol_name(unsigned long addr, char *symname); int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* How and when do we show kallsyms values? */ -extern int kallsyms_show_value(void); +extern bool kallsyms_show_value(const struct cred *cred); #else /* !CONFIG_KALLSYMS */ @@ -158,7 +159,7 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u return -ERANGE; } -static inline int kallsyms_show_value(void) +static inline bool kallsyms_show_value(const struct cred *cred) { return false; } diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index c62d76478adc..529116b0cabe 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -276,8 +276,7 @@ struct kgdb_arch { * the I/O driver. * @post_exception: Pointer to a function that will do any cleanup work * for the I/O driver. - * @is_console: 1 if the end device is a console 0 if the I/O device is - * not a console + * @cons: valid if the I/O device is a console; else NULL. */ struct kgdb_io { const char *name; @@ -288,7 +287,7 @@ struct kgdb_io { void (*deinit) (void); void (*pre_exception) (void); void (*post_exception) (void); - int is_console; + struct console *cons; }; extern const struct kgdb_arch arch_kgdb_ops; diff --git a/include/linux/libata.h b/include/linux/libata.h index e7e5256817dc..77ccf040a128 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1095,7 +1095,7 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #define ATA_SCSI_COMPAT_IOCTL /* empty */ #endif extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); -#if IS_ENABLED(CONFIG_ATA) +#if IS_REACHABLE(CONFIG_ATA) bool ata_scsi_dma_need_drain(struct request *rq); #else #define ata_scsi_dma_need_drain NULL diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 6791813cd439..af998f93d256 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -150,7 +150,7 @@ LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) -LSM_HOOK(int, 0, inode_copy_up_xattr, const char *name) +LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) @@ -360,7 +360,7 @@ LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, - unsigned perm) + enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer) #endif /* CONFIG_KEYS */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 13c0e4556eda..1e6ca716635a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -147,6 +147,7 @@ enum { MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, MLX5_REG_MIRC = 0x9162, + MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 516fa16f4ed3..791766e15d5c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9960,6 +9960,34 @@ struct mlx5_ifc_pptb_reg_bits { u8 untagged_buff[0x4]; }; +struct mlx5_ifc_sbcam_reg_bits { + u8 reserved_at_0[0x8]; + u8 feature_group[0x8]; + u8 reserved_at_10[0x8]; + u8 access_reg_group[0x8]; + + u8 reserved_at_20[0x20]; + + u8 sb_access_reg_cap_mask[4][0x20]; + + u8 reserved_at_c0[0x80]; + + u8 sb_feature_cap_mask[4][0x20]; + + u8 reserved_at_1c0[0x40]; + + u8 cap_total_buffer_size[0x20]; + + u8 cap_cell_size[0x10]; + u8 cap_max_pg_buffers[0x8]; + u8 cap_num_pool_supported[0x8]; + + u8 reserved_at_240[0x8]; + u8 cap_sbsr_stat_size[0x8]; + u8 cap_max_tclass_data[0x8]; + u8 cap_max_cpu_ingress_tclass_sb[0x8]; +}; + struct mlx5_ifc_pbmc_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index de9a272c9f3d..2d45a6af52a4 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -104,8 +104,11 @@ enum mlx5e_ext_link_mode { MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR = 8, MLX5E_CAUI_4_100GBASE_CR4_KR4 = 9, MLX5E_100GAUI_2_100GBASE_CR2_KR2 = 10, + MLX5E_100GAUI_1_100GBASE_CR_KR = 11, MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12, + MLX5E_200GAUI_2_200GBASE_CR2_KR2 = 13, MLX5E_400GAUI_8 = 15, + MLX5E_400GAUI_4_400GBASE_CR4_KR4 = 16, MLX5E_EXT_LINK_MODES_NUMBER, }; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c4c37fd12104..f6f884970511 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -257,8 +257,8 @@ struct lruvec { */ unsigned long anon_cost; unsigned long file_cost; - /* Evictions & activations on the inactive file list */ - atomic_long_t inactive_age; + /* Non-resident age, driven by LRU movement */ + atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults; /* Various lruvec state flags (enum lruvec_flags) */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 39e28e11863c..ac2cd3f49aba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -65,6 +65,8 @@ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; +struct udp_tunnel_nic_info; +struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; @@ -1836,6 +1838,10 @@ enum netdev_priv_flags { * * @macsec_ops: MACsec offloading ops * + * @udp_tunnel_nic_info: static structure describing the UDP tunnel + * offload capabilities of the device + * @udp_tunnel_nic: UDP tunnel offload state + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2134,6 +2140,8 @@ struct net_device { /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif + const struct udp_tunnel_nic_info *udp_tunnel_nic_info; + struct udp_tunnel_nic *udp_tunnel_nic; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/linux/pci.h b/include/linux/pci.h index c79d83304e52..34c1c4f45288 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2169,12 +2169,11 @@ static inline int pci_pcie_type(const struct pci_dev *dev) */ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) { - struct pci_dev *bridge = pci_upstream_bridge(dev); - - while (bridge) { - if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) - return bridge; - bridge = pci_upstream_bridge(bridge); + while (dev) { + if (pci_is_pcie(dev) && + pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + return dev; + dev = pci_upstream_bridge(dev); } return NULL; diff --git a/include/linux/phy.h b/include/linux/phy.h index 1592c3d0e12f..0403eb799913 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1474,51 +1474,10 @@ int __init mdio_bus_init(void); void mdio_bus_exit(void); #endif -/* Inline function for use within net/core/ethtool.c (built-in) */ -static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) -{ - if (!phydev->drv) - return -EIO; - - mutex_lock(&phydev->lock); - phydev->drv->get_strings(phydev, data); - mutex_unlock(&phydev->lock); - - return 0; -} - -static inline int phy_ethtool_get_sset_count(struct phy_device *phydev) -{ - int ret; - - if (!phydev->drv) - return -EIO; - - if (phydev->drv->get_sset_count && - phydev->drv->get_strings && - phydev->drv->get_stats) { - mutex_lock(&phydev->lock); - ret = phydev->drv->get_sset_count(phydev); - mutex_unlock(&phydev->lock); - - return ret; - } - - return -EOPNOTSUPP; -} - -static inline int phy_ethtool_get_stats(struct phy_device *phydev, - struct ethtool_stats *stats, u64 *data) -{ - if (!phydev->drv) - return -EIO; - - mutex_lock(&phydev->lock); - phydev->drv->get_stats(phydev, stats, data); - mutex_unlock(&phydev->lock); - - return 0; -} +int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); +int phy_ethtool_get_sset_count(struct phy_device *phydev); +int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data); static inline int phy_package_read(struct phy_device *phydev, u32 regnum) { diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 4f922afb607a..45cf7b69d852 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -155,7 +155,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, * Loop over each sg element in the given sg_table object. */ #define for_each_sgtable_sg(sgt, sg, i) \ - for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) + for_each_sg((sgt)->sgl, sg, (sgt)->orig_nents, i) /* * Loop over each sg element in the given *DMA mapped* sg_table object. @@ -163,7 +163,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, * of the each element. */ #define for_each_sgtable_dma_sg(sgt, sg, i) \ - for_each_sg(sgt->sgl, sg, sgt->nents, i) + for_each_sg((sgt)->sgl, sg, (sgt)->nents, i) /** * sg_chain - Chain two sglists together @@ -451,7 +451,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit. */ #define for_each_sgtable_page(sgt, piter, pgoffset) \ - for_each_sg_page(sgt->sgl, piter, sgt->orig_nents, pgoffset) + for_each_sg_page((sgt)->sgl, piter, (sgt)->orig_nents, pgoffset) /** * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object @@ -465,7 +465,7 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter) * unit. */ #define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset) \ - for_each_sg_dma_page(sgt->sgl, dma_iter, sgt->nents, pgoffset) + for_each_sg_dma_page((sgt)->sgl, dma_iter, (sgt)->nents, pgoffset) /* diff --git a/include/linux/sched.h b/include/linux/sched.h index b62e6aaf28f0..692e327d7455 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -654,9 +654,8 @@ struct task_struct { unsigned int ptrace; #ifdef CONFIG_SMP - struct llist_node wake_entry; - unsigned int wake_entry_type; int on_cpu; + struct __call_single_node wake_entry; #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ unsigned int cpu; diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..d2b4204ba4d3 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,7 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_TASK_WORK_BIT 24 /* set by TWA_SIGNAL */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,9 +29,10 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_TASK_WORK (1UL << JOBCTL_TASK_WORK_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) -#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK) extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask); extern void task_clear_jobctl_trapping(struct task_struct *task); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 08674cd14d5a..1e9ed840b9fc 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog, bpf_prog_put(prog); } +static inline int psock_replace_prog(struct bpf_prog **pprog, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + if (cmpxchg(pprog, old, prog) != old) + return -ENOENT; + + if (old) + bpf_prog_put(old); + + return 0; +} + static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); diff --git a/include/linux/smp.h b/include/linux/smp.h index 7ee202ad21a6..80d557ef8a11 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -12,29 +12,22 @@ #include <linux/list.h> #include <linux/cpumask.h> #include <linux/init.h> -#include <linux/llist.h> +#include <linux/smp_types.h> typedef void (*smp_call_func_t)(void *info); typedef bool (*smp_cond_func_t)(int cpu, void *info); -enum { - CSD_FLAG_LOCK = 0x01, - - /* IRQ_WORK_flags */ - - CSD_TYPE_ASYNC = 0x00, - CSD_TYPE_SYNC = 0x10, - CSD_TYPE_IRQ_WORK = 0x20, - CSD_TYPE_TTWU = 0x30, - CSD_FLAG_TYPE_MASK = 0xF0, -}; - /* * structure shares (partial) layout with struct irq_work */ struct __call_single_data { - struct llist_node llist; - unsigned int flags; + union { + struct __call_single_node node; + struct { + struct llist_node llist; + unsigned int flags; + }; + }; smp_call_func_t func; void *info; }; diff --git a/include/linux/smp_types.h b/include/linux/smp_types.h new file mode 100644 index 000000000000..364b3ae3e41d --- /dev/null +++ b/include/linux/smp_types.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SMP_TYPES_H +#define __LINUX_SMP_TYPES_H + +#include <linux/llist.h> + +enum { + CSD_FLAG_LOCK = 0x01, + + IRQ_WORK_PENDING = 0x01, + IRQ_WORK_BUSY = 0x02, + IRQ_WORK_LAZY = 0x04, /* No IPI, wait for tick */ + IRQ_WORK_HARD_IRQ = 0x08, /* IRQ context on PREEMPT_RT */ + + IRQ_WORK_CLAIMED = (IRQ_WORK_PENDING | IRQ_WORK_BUSY), + + CSD_TYPE_ASYNC = 0x00, + CSD_TYPE_SYNC = 0x10, + CSD_TYPE_IRQ_WORK = 0x20, + CSD_TYPE_TTWU = 0x30, + + CSD_FLAG_TYPE_MASK = 0xF0, +}; + +/* + * struct __call_single_node is the primary type on + * smp.c:call_single_queue. + * + * flush_smp_call_function_queue() only reads the type from + * __call_single_node::u_flags as a regular load, the above + * (anonymous) enum defines all the bits of this word. + * + * Other bits are not modified until the type is known. + * + * CSD_TYPE_SYNC/ASYNC: + * struct { + * struct llist_node node; + * unsigned int flags; + * smp_call_func_t func; + * void *info; + * }; + * + * CSD_TYPE_IRQ_WORK: + * struct { + * struct llist_node node; + * atomic_t flags; + * void (*func)(struct irq_work *); + * }; + * + * CSD_TYPE_TTWU: + * struct { + * struct llist_node node; + * unsigned int flags; + * }; + * + */ + +struct __call_single_node { + struct llist_node llist; + union { + unsigned int u_flags; + atomic_t a_flags; + }; +}; + +#endif /* __LINUX_SMP_TYPES_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 4c5974bb9ba9..5b3216ba39a9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -313,6 +313,7 @@ struct vma_swap_readahead { }; /* linux/mm/workingset.c */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7c354c2955f5..b951a87da987 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1360,7 +1360,7 @@ static inline long ksys_lchown(const char __user *filename, uid_t user, extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small); -static inline long ksys_ftruncate(unsigned int fd, unsigned long length) +static inline long ksys_ftruncate(unsigned int fd, loff_t length) { return do_sys_ftruncate(fd, length, 1); } diff --git a/include/linux/task_work.h b/include/linux/task_work.h index bd9a6a91c097..0fb93aafa478 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -13,7 +13,10 @@ init_task_work(struct callback_head *twork, task_work_func_t func) twork->func = func; } -int task_work_add(struct task_struct *task, struct callback_head *twork, bool); +#define TWA_RESUME 1 +#define TWA_SIGNAL 2 +int task_work_add(struct task_struct *task, struct callback_head *twork, int); + struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index b27e2ffa96c1..d5471d6fa778 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -222,9 +222,9 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* +/** * struct system_time_snapshot - simultaneous raw/real time capture with - * counter value + * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time @@ -239,9 +239,9 @@ struct system_time_snapshot { u8 cs_was_changed_seq; }; -/* +/** * struct system_device_crosststamp - system/device cross-timestamp - * (syncronized capture) + * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time @@ -252,12 +252,12 @@ struct system_device_crosststamp { ktime_t sys_monoraw; }; -/* +/** * struct system_counterval_t - system counter value with the pointer to the - * corresponding clocksource + * corresponding clocksource * @cycles: System counter value * @cs: Clocksource corresponding to system counter value. Used by - * timekeeping code to verify comparibility of two cycle values + * timekeeping code to verify comparibility of two cycle values */ struct system_counterval_t { u64 cycles; diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 4f8c90c93c29..64356b199e94 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -81,6 +81,8 @@ struct tcg_efi_specid_event_algs { u16 digest_size; } __packed; +#define TCG_SPECID_SIG "Spec ID Event03" + struct tcg_efi_specid_event_head { u8 signature[16]; u32 platform_class; @@ -171,6 +173,7 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, int i; int j; u32 count, event_type; + const u8 zero_digest[sizeof(event_header->digest)] = {0}; marker = event; marker_start = marker; @@ -198,10 +201,19 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, count = READ_ONCE(event->count); event_type = READ_ONCE(event->event_type); + /* Verify that it's the log header */ + if (event_header->pcr_idx != 0 || + event_header->event_type != NO_ACTION || + memcmp(event_header->digest, zero_digest, sizeof(zero_digest))) { + size = 0; + goto out; + } + efispecid = (struct tcg_efi_specid_event_head *)event_header->event; /* Check if event is malformed. */ - if (count > efispecid->num_algs) { + if (memcmp(efispecid->signature, TCG_SPECID_SIG, + sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) { size = 0; goto out; } diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 48bb681e6c2a..0221f852a7e1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); diff --git a/include/net/devlink.h b/include/net/devlink.h index 428f55f8197c..913e8679ae35 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -52,7 +52,7 @@ struct devlink_port_phys_attrs { * A physical port which is visible to the user * for a given port flavour. */ - u32 split_subport_number; + u32 split_subport_number; /* If the port is split, this is the number of subport. */ }; struct devlink_port_pci_pf_attrs { @@ -64,10 +64,18 @@ struct devlink_port_pci_vf_attrs { u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ }; +/** + * struct devlink_port_attrs - devlink port object + * @flavour: flavour of the port + * @split: indicates if this is split port + * @splittable: indicates if the port can be split. + * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. + * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL + */ struct devlink_port_attrs { - u8 set:1, - split:1, - switch_port:1; + u8 split:1, + splittable:1; + u32 lanes; enum devlink_port_flavour flavour; struct netdev_phys_item_id switch_id; union { @@ -90,7 +98,11 @@ struct devlink_port { enum devlink_port_type desired_type; void *type_dev; struct devlink_port_attrs attrs; + u8 attrs_set:1, + switch_port:1; struct delayed_work type_warn_dw; + struct list_head reporter_list; + struct mutex reporters_lock; /* Protects reporter_list */ }; struct devlink_sb_pool_info { @@ -1180,17 +1192,9 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev); void devlink_port_type_clear(struct devlink_port *devlink_port); void devlink_port_attrs_set(struct devlink_port *devlink_port, - enum devlink_port_flavour flavour, - u32 port_number, bool split, - u32 split_subport_number, - const unsigned char *switch_id, - unsigned char switch_id_len); -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, - const unsigned char *switch_id, - unsigned char switch_id_len, u16 pf); + struct devlink_port_attrs *devlink_port_attrs); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf); void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - const unsigned char *switch_id, - unsigned char switch_id_len, u16 pf, u16 vf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, @@ -1334,9 +1338,18 @@ struct devlink_health_reporter * devlink_health_reporter_create(struct devlink *devlink, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv); + +struct devlink_health_reporter * +devlink_port_health_reporter_create(struct devlink_port *port, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv); + void devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); +void +devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter); + void * devlink_health_reporter_priv(struct devlink_health_reporter *reporter); int devlink_health_report(struct devlink_health_reporter *reporter, diff --git a/include/net/dsa.h b/include/net/dsa.h index 4046ccd1945d..b28c95c76762 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -44,6 +44,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 +#define DSA_TAG_PROTO_RTL4_A_VALUE 17 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -63,6 +64,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, + DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, }; struct packet_type; diff --git a/include/net/dst.h b/include/net/dst.h index 07adfacd8088..852d8fb36ab7 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -400,7 +400,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { - struct neighbour *n = dst->ops->neigh_lookup(dst, skb, NULL); + struct neighbour *n = NULL; + + /* The packets from tunnel devices (eg bareudp) may have only + * metadata in the dst pointer of skb. Hence a pointer check of + * neigh_lookup is needed. + */ + if (dst->ops->neigh_lookup) + n = dst->ops->neigh_lookup(dst, skb, NULL); + return IS_ERR(n) ? NULL : n; } diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index a7eba43fe4e4..4b6e36288ddd 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -372,7 +372,8 @@ flow_dissector_init_keys(struct flow_dissector_key_control *key_control, } #ifdef CONFIG_BPF_SYSCALL -int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog); +int flow_dissector_bpf_prog_attach_check(struct net *net, + struct bpf_prog *prog); #endif /* CONFIG_BPF_SYSCALL */ #endif diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index de395498440d..9f88a7b730a8 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -444,6 +444,7 @@ struct flow_block_offload { struct list_head cb_list; struct list_head *driver_block_list; struct netlink_ext_ack *extack; + struct Qdisc *sch; }; enum tc_setup_type; @@ -455,6 +456,7 @@ struct flow_block_cb; struct flow_block_indr { struct list_head list; struct net_device *dev; + struct Qdisc *sch; enum flow_block_binder_type binder_type; void *data; void *cb_priv; @@ -479,7 +481,8 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv), struct flow_block_offload *bo, - struct net_device *dev, void *data, + struct net_device *dev, + struct Qdisc *sch, void *data, void *indr_cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)); void flow_block_cb_free(struct flow_block_cb *block_cb); @@ -553,7 +556,7 @@ static inline void flow_block_init(struct flow_block *flow_block) INIT_LIST_HEAD(&flow_block->cb_list); } -typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, +typedef int flow_indr_block_bind_cb_t(struct net_device *dev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); @@ -561,7 +564,7 @@ typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv); void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, void (*release)(void *cb_priv)); -int flow_indr_dev_setup_offload(struct net_device *dev, +int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 74950663bb00..6e5f1e1aa822 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -35,13 +35,6 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks - * @mcast_bind: a socket bound to the given multicast group (which - * is given as the offset into the groups array) - * @mcast_unbind: a socket was unbound from the given multicast group. - * Note that unbind() will not be called symmetrically if the - * generic netlink family is removed while there are still open - * sockets. - * @attrbuf: buffer to store parsed attributes (private) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family @@ -64,9 +57,6 @@ struct genl_family { void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); - int (*mcast_bind)(struct net *net, int group); - void (*mcast_unbind)(struct net *net, int group); - struct nlattr ** attrbuf; /* private */ const struct genl_ops * ops; const struct genl_multicast_group *mcgrps; unsigned int n_ops; diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 0f0d1efe06dd..e1eaf1780288 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -4,6 +4,7 @@ #include <linux/ip.h> #include <linux/skbuff.h> +#include <linux/if_vlan.h> #include <net/inet_sock.h> #include <net/dsfield.h> @@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) static inline int INET_ECN_set_ce(struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) @@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) static inline int INET_ECN_set_ect1(struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) @@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph, { __u8 inner; - if (skb->protocol == htons(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + break; + case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); - else + break; + default: return 0; + } return INET_ECN_decapsulate(skb, oiph->tos, inner); } @@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, { __u8 inner; - if (skb->protocol == htons(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + break; + case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); - else + break; + default: return 0; + } return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 076e5d7db7d3..36025dea7612 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -290,6 +290,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); +extern const struct header_ops ip_tunnel_header_ops; +__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); + struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 83be2d93b407..011f407b76fe 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -874,6 +874,7 @@ struct netns_ipvs { struct ip_vs_stats tot_stats; /* Statistics & est. */ int num_services; /* no of virtual services */ + int num_services6; /* IPv6 virtual services */ /* Trash for destinations */ struct list_head dest_trash; @@ -960,6 +961,7 @@ struct netns_ipvs { * are not supported when synchronization is enabled. */ unsigned int mixed_address_family_dests; + unsigned int hooks_afmask; /* &1=AF_INET, &2=AF_INET6 */ }; #define DEFAULT_SYNC_THRESHOLD 3 @@ -1624,18 +1626,16 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) } #endif /* CONFIG_IP_VS_NFCT */ -/* Really using conntrack? */ -static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp, - struct sk_buff *skb) +/* Using old conntrack that can not be redirected to another real server? */ +static inline bool ip_vs_conn_uses_old_conntrack(struct ip_vs_conn *cp, + struct sk_buff *skb) { #ifdef CONFIG_IP_VS_NFCT enum ip_conntrack_info ctinfo; struct nf_conn *ct; - if (!(cp->flags & IP_VS_CONN_F_NFCT)) - return false; ct = nf_ct_get(skb, &ctinfo); - if (ct) + if (ct && nf_ct_is_confirmed(ct)) return true; #endif return false; @@ -1670,6 +1670,9 @@ static inline void ip_vs_unregister_conntrack(struct ip_vs_service *svc) #endif } +int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af); +void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af); + static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 6f0f6fca9ac3..822c26766330 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -899,6 +899,8 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) return (void *)&rule->data[rule->dlen]; } +void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule); + static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -921,11 +923,6 @@ static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, (expr) != (last); \ (expr) = nft_expr_next(expr)) -enum nft_chain_flags { - NFT_BASE_CHAIN = 0x1, - NFT_CHAIN_HW_OFFLOAD = 0x2, -}; - #define NFT_CHAIN_POLICY_UNSET U8_MAX /** @@ -949,7 +946,8 @@ struct nft_chain { struct nft_table *table; u64 handle; u32 use; - u8 flags:6, + u8 flags:5, + bound:1, genmask:2; char *name; @@ -994,6 +992,14 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); +static inline bool nft_chain_is_bound(struct nft_chain *chain) +{ + return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; +} + +void nft_chain_del(struct nft_chain *chain); +void nf_tables_chain_destroy(struct nft_ctx *ctx); + struct nft_stats { u64 bytes; u64 pkts; @@ -1036,7 +1042,7 @@ static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chai static inline bool nft_is_base_chain(const struct nft_chain *chain) { - return chain->flags & NFT_BASE_CHAIN; + return chain->flags & NFT_CHAIN_BASE; } int __nft_release_basechain(struct nft_ctx *ctx); @@ -1433,6 +1439,7 @@ struct nft_trans_chain { char *name; struct nft_stats __percpu *stats; u8 policy; + u32 chain_id; }; #define nft_trans_chain_update(trans) \ @@ -1443,6 +1450,8 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->stats) #define nft_trans_chain_policy(trans) \ (((struct nft_trans_chain *)trans->data)->policy) +#define nft_trans_chain_id(trans) \ + (((struct nft_trans_chain *)trans->data)->chain_id) struct nft_trans_table { bool update; diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h index a8dce2a380c8..0ca6a1b87185 100644 --- a/include/net/netns/bpf.h +++ b/include/net/netns/bpf.h @@ -9,10 +9,13 @@ #include <linux/bpf-netns.h> struct bpf_prog; +struct bpf_prog_array; struct netns_bpf { - struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE]; - struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE]; + /* Array of programs to run compiled from progs or links */ + struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE]; + struct bpf_prog *progs[MAX_NETNS_BPF_ATTACH_TYPE]; + struct list_head links[MAX_NETNS_BPF_ATTACH_TYPE]; }; #endif /* __NETNS_BPF_H__ */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9092e697059e..ac8c890a2657 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -136,17 +136,6 @@ static inline void qdisc_run(struct Qdisc *q) } } -static inline __be16 tc_skb_protocol(const struct sk_buff *skb) -{ - /* We need to take extra care in case the skb came via - * vlan accelerated path. In that case, use skb->vlan_proto - * as the original vlan header was already stripped. - */ - if (skb_vlan_tag_present(skb)) - return skb->vlan_proto; - return skb->protocol; -} - /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ diff --git a/include/net/sock.h b/include/net/sock.h index 84c813dd0152..4bf884165148 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -533,7 +533,8 @@ enum sk_pacing { * be copied. */ #define SK_USER_DATA_NOCOPY 1UL -#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY) +#define SK_USER_DATA_BPF 2UL /* Managed by BPF */ +#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index e7312ceb2794..dd20ce99740c 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -106,15 +106,16 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { - UDP_TUNNEL_TYPE_VXLAN, /* RFC 7348 */ - UDP_TUNNEL_TYPE_GENEVE, /* draft-ietf-nvo3-geneve */ - UDP_TUNNEL_TYPE_VXLAN_GPE, /* draft-ietf-nvo3-vxlan-gpe */ + UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ + UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ + UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; + u8 hw_priv; }; /* Notify network devices of offloadable types */ @@ -181,4 +182,161 @@ static inline void udp_tunnel_encap_enable(struct socket *sock) udp_encap_enable(); } +#define UDP_TUNNEL_NIC_MAX_TABLES 4 + +enum udp_tunnel_nic_info_flags { + /* Device callbacks may sleep */ + UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), + /* Device only supports offloads when it's open, all ports + * will be removed before close and re-added after open. + */ + UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), + /* Device supports only IPv4 tunnels */ + UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), +}; + +/** + * struct udp_tunnel_nic_info - driver UDP tunnel offload information + * @set_port: callback for adding a new port + * @unset_port: callback for removing a port + * @sync_table: callback for syncing the entire port table at once + * @flags: device flags from enum udp_tunnel_nic_info_flags + * @tables: UDP port tables this device has + * @tables.n_entries: number of entries in this table + * @tables.tunnel_types: types of tunnels this table accepts + * + * Drivers are expected to provide either @set_port and @unset_port callbacks + * or the @sync_table callback. Callbacks are invoked with rtnl lock held. + * + * Known limitations: + * - UDP tunnel port notifications are fundamentally best-effort - + * it is likely the driver will both see skbs which use a UDP tunnel port, + * while not being a tunneled skb, and tunnel skbs from other ports - + * drivers should only use these ports for non-critical RX-side offloads, + * e.g. the checksum offload; + * - none of the devices care about the socket family at present, so we don't + * track it. Please extend this code if you care. + */ +struct udp_tunnel_nic_info { + /* one-by-one */ + int (*set_port)(struct net_device *dev, + unsigned int table, unsigned int entry, + struct udp_tunnel_info *ti); + int (*unset_port)(struct net_device *dev, + unsigned int table, unsigned int entry, + struct udp_tunnel_info *ti); + + /* all at once */ + int (*sync_table)(struct net_device *dev, unsigned int table); + + unsigned int flags; + + struct udp_tunnel_nic_table_info { + unsigned int n_entries; + unsigned int tunnel_types; + } tables[UDP_TUNNEL_NIC_MAX_TABLES]; +}; + +/* UDP tunnel module dependencies + * + * Tunnel drivers are expected to have a hard dependency on the udp_tunnel + * module. NIC drivers are not, they just attach their + * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. + * Loading a tunnel driver will cause the udp_tunnel module to be loaded + * and only then will all the required state structures be allocated. + * Since we want a weak dependency from the drivers and the core to udp_tunnel + * we call things through the following stubs. + */ +struct udp_tunnel_nic_ops { + void (*get_port)(struct net_device *dev, unsigned int table, + unsigned int idx, struct udp_tunnel_info *ti); + void (*set_port_priv)(struct net_device *dev, unsigned int table, + unsigned int idx, u8 priv); + void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); + void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); + void (*reset_ntf)(struct net_device *dev); + + size_t (*dump_size)(struct net_device *dev, unsigned int table); + int (*dump_write)(struct net_device *dev, unsigned int table, + struct sk_buff *skb); +}; + +#ifdef CONFIG_INET +extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; +#else +#define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) +#endif + +static inline void +udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, + unsigned int idx, struct udp_tunnel_info *ti) +{ + /* This helper is used from .sync_table, we indicate empty entries + * by zero'ed @ti. Drivers which need to know the details of a port + * when it gets deleted should use the .set_port / .unset_port + * callbacks. + * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. + */ + memset(ti, 0, sizeof(*ti)); + + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->get_port(dev, table, idx, ti); +} + +static inline void +udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, + unsigned int idx, u8 priv) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); +} + +static inline void +udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->add_port(dev, ti); +} + +static inline void +udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->del_port(dev, ti); +} + +/** + * udp_tunnel_nic_reset_ntf() - device-originating reset notification + * @dev: network interface device structure + * + * Called by the driver to inform the core that the entire UDP tunnel port + * state has been lost, usually due to device reset. Core will assume device + * forgot all the ports and issue .set_port and .sync_table callbacks as + * necessary. + * + * This function must be called with rtnl lock held, and will issue all + * the callbacks before returning. + */ +static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) +{ + if (udp_tunnel_nic_ops) + udp_tunnel_nic_ops->reset_ntf(dev); +} + +static inline size_t +udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) +{ + if (!udp_tunnel_nic_ops) + return 0; + return udp_tunnel_nic_ops->dump_size(dev, table); +} + +static inline int +udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, + struct sk_buff *skb) +{ + if (!udp_tunnel_nic_ops) + return 0; + return udp_tunnel_nic_ops->dump_write(dev, table, skb); +} #endif diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index a4ff226505c9..6842990e2712 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -40,7 +40,7 @@ struct xsk_buff_pool { u32 headroom; u32 chunk_size; u32 frame_len; - bool cheap_dma; + bool dma_need_sync; bool unaligned; void *addrs; struct device *dev; @@ -80,7 +80,7 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) { - if (xskb->pool->cheap_dma) + if (!xskb->pool->dma_need_sync) return; xp_dma_sync_for_cpu_slow(xskb); @@ -91,7 +91,7 @@ void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma, size_t size) { - if (pool->cheap_dma) + if (!pool->dma_need_sync) return; xp_dma_sync_for_device_slow(pool, dma, size); diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index e050f8121ba2..da369b12005f 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -126,6 +126,7 @@ enum ocelot_target { HSIO, PTP, GCB, + DEV_GMII, TARGET_MAX, }; @@ -408,6 +409,48 @@ enum ocelot_reg { PTP_CLK_CFG_ADJ_CFG, PTP_CLK_CFG_ADJ_FREQ, GCB_SOFT_RST = GCB << TARGET_OFFSET, + GCB_MIIM_MII_STATUS, + GCB_MIIM_MII_CMD, + GCB_MIIM_MII_DATA, + DEV_CLOCK_CFG = DEV_GMII << TARGET_OFFSET, + DEV_PORT_MISC, + DEV_EVENTS, + DEV_EEE_CFG, + DEV_RX_PATH_DELAY, + DEV_TX_PATH_DELAY, + DEV_PTP_PREDICT_CFG, + DEV_MAC_ENA_CFG, + DEV_MAC_MODE_CFG, + DEV_MAC_MAXLEN_CFG, + DEV_MAC_TAGS_CFG, + DEV_MAC_ADV_CHK_CFG, + DEV_MAC_IFG_CFG, + DEV_MAC_HDX_CFG, + DEV_MAC_DBG_CFG, + DEV_MAC_FC_MAC_LOW_CFG, + DEV_MAC_FC_MAC_HIGH_CFG, + DEV_MAC_STICKY, + PCS1G_CFG, + PCS1G_MODE_CFG, + PCS1G_SD_CFG, + PCS1G_ANEG_CFG, + PCS1G_ANEG_NP_CFG, + PCS1G_LB_CFG, + PCS1G_DBG_CFG, + PCS1G_CDET_CFG, + PCS1G_ANEG_STATUS, + PCS1G_ANEG_NP_STATUS, + PCS1G_LINK_STATUS, + PCS1G_LINK_DOWN_CNT, + PCS1G_STICKY, + PCS1G_DEBUG_STATUS, + PCS1G_LPI_CFG, + PCS1G_LPI_WAKE_ERROR_CNT, + PCS1G_LPI_STATUS, + PCS1G_TSTPAT_MODE_CFG, + PCS1G_TSTPAT_STATUS, + DEV_PCS_FX100_CFG, + DEV_PCS_FX100_STATUS, }; enum ocelot_regfield { @@ -447,15 +490,30 @@ enum ocelot_regfield { ANA_TABLES_MACACCESS_B_DOM, ANA_TABLES_MACTINDX_BUCKET, ANA_TABLES_MACTINDX_M_INDEX, + QSYS_SWITCH_PORT_MODE_PORT_ENA, + QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG, + QSYS_SWITCH_PORT_MODE_YEL_RSRVD, + QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE, + QSYS_SWITCH_PORT_MODE_TX_PFC_ENA, + QSYS_SWITCH_PORT_MODE_TX_PFC_MODE, QSYS_TIMED_FRAME_ENTRY_TFRM_VLD, QSYS_TIMED_FRAME_ENTRY_TFRM_FP, QSYS_TIMED_FRAME_ENTRY_TFRM_PORTNO, QSYS_TIMED_FRAME_ENTRY_TFRM_TM_SEL, QSYS_TIMED_FRAME_ENTRY_TFRM_TM_T, + SYS_PORT_MODE_DATA_WO_TS, + SYS_PORT_MODE_INCL_INJ_HDR, + SYS_PORT_MODE_INCL_XTR_HDR, + SYS_PORT_MODE_INCL_HDR_ERR, SYS_RESET_CFG_CORE_ENA, SYS_RESET_CFG_MEM_ENA, SYS_RESET_CFG_MEM_INIT, GCB_SOFT_RST_SWC_RST, + GCB_MIIM_MII_STATUS_PENDING, + GCB_MIIM_MII_STATUS_BUSY, + SYS_PAUSE_CFG_PAUSE_START, + SYS_PAUSE_CFG_PAUSE_STOP, + SYS_PAUSE_CFG_PAUSE_ENA, REGFIELD_MAX }; @@ -483,6 +541,7 @@ struct ocelot; struct ocelot_ops { int (*reset)(struct ocelot *ocelot); + u16 (*wm_enc)(u16 value); }; struct ocelot_vcap_block { @@ -494,7 +553,7 @@ struct ocelot_vcap_block { struct ocelot_port { struct ocelot *ocelot; - void __iomem *regs; + struct regmap *target; bool vlan_aware; @@ -509,6 +568,8 @@ struct ocelot_port { u8 ts_id; phy_interface_t phy_mode; + + u8 *xmit_template; }; struct ocelot { @@ -593,6 +654,11 @@ struct ocelot_policer { #define ocelot_rmw_rix(ocelot, val, m, reg, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri)) #define ocelot_rmw(ocelot, val, m, reg) __ocelot_rmw_ix(ocelot, val, m, reg, 0) +#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val)) +#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val)) +#define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val)) +#define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val)) + /* I/O */ u32 ocelot_port_readl(struct ocelot_port *port, u32 reg); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg); diff --git a/include/soc/mscc/ocelot_dev.h b/include/soc/mscc/ocelot_dev.h index 7c08437061fc..0c6021f02fee 100644 --- a/include/soc/mscc/ocelot_dev.h +++ b/include/soc/mscc/ocelot_dev.h @@ -8,8 +8,6 @@ #ifndef _MSCC_OCELOT_DEV_H_ #define _MSCC_OCELOT_DEV_H_ -#define DEV_CLOCK_CFG 0x0 - #define DEV_CLOCK_CFG_MAC_TX_RST BIT(7) #define DEV_CLOCK_CFG_MAC_RX_RST BIT(6) #define DEV_CLOCK_CFG_PCS_TX_RST BIT(5) @@ -19,18 +17,12 @@ #define DEV_CLOCK_CFG_LINK_SPEED(x) ((x) & GENMASK(1, 0)) #define DEV_CLOCK_CFG_LINK_SPEED_M GENMASK(1, 0) -#define DEV_PORT_MISC 0x4 - #define DEV_PORT_MISC_FWD_ERROR_ENA BIT(4) #define DEV_PORT_MISC_FWD_PAUSE_ENA BIT(3) #define DEV_PORT_MISC_FWD_CTRL_ENA BIT(2) #define DEV_PORT_MISC_DEV_LOOP_ENA BIT(1) #define DEV_PORT_MISC_HDX_FAST_DIS BIT(0) -#define DEV_EVENTS 0x8 - -#define DEV_EEE_CFG 0xc - #define DEV_EEE_CFG_EEE_ENA BIT(22) #define DEV_EEE_CFG_EEE_TIMER_AGE(x) (((x) << 15) & GENMASK(21, 15)) #define DEV_EEE_CFG_EEE_TIMER_AGE_M GENMASK(21, 15) @@ -43,33 +35,19 @@ #define DEV_EEE_CFG_EEE_TIMER_HOLDOFF_X(x) (((x) & GENMASK(7, 1)) >> 1) #define DEV_EEE_CFG_PORT_LPI BIT(0) -#define DEV_RX_PATH_DELAY 0x10 - -#define DEV_TX_PATH_DELAY 0x14 - -#define DEV_PTP_PREDICT_CFG 0x18 - #define DEV_PTP_PREDICT_CFG_PTP_PHY_PREDICT_CFG(x) (((x) << 4) & GENMASK(11, 4)) #define DEV_PTP_PREDICT_CFG_PTP_PHY_PREDICT_CFG_M GENMASK(11, 4) #define DEV_PTP_PREDICT_CFG_PTP_PHY_PREDICT_CFG_X(x) (((x) & GENMASK(11, 4)) >> 4) #define DEV_PTP_PREDICT_CFG_PTP_PHASE_PREDICT_CFG(x) ((x) & GENMASK(3, 0)) #define DEV_PTP_PREDICT_CFG_PTP_PHASE_PREDICT_CFG_M GENMASK(3, 0) -#define DEV_MAC_ENA_CFG 0x1c - #define DEV_MAC_ENA_CFG_RX_ENA BIT(4) #define DEV_MAC_ENA_CFG_TX_ENA BIT(0) -#define DEV_MAC_MODE_CFG 0x20 - #define DEV_MAC_MODE_CFG_FC_WORD_SYNC_ENA BIT(8) #define DEV_MAC_MODE_CFG_GIGA_MODE_ENA BIT(4) #define DEV_MAC_MODE_CFG_FDX_ENA BIT(0) -#define DEV_MAC_MAXLEN_CFG 0x24 - -#define DEV_MAC_TAGS_CFG 0x28 - #define DEV_MAC_TAGS_CFG_TAG_ID(x) (((x) << 16) & GENMASK(31, 16)) #define DEV_MAC_TAGS_CFG_TAG_ID_M GENMASK(31, 16) #define DEV_MAC_TAGS_CFG_TAG_ID_X(x) (((x) & GENMASK(31, 16)) >> 16) @@ -77,12 +55,8 @@ #define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA BIT(1) #define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) -#define DEV_MAC_ADV_CHK_CFG 0x2c - #define DEV_MAC_ADV_CHK_CFG_LEN_DROP_ENA BIT(0) -#define DEV_MAC_IFG_CFG 0x30 - #define DEV_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK BIT(17) #define DEV_MAC_IFG_CFG_REDUCED_TX_IFG BIT(16) #define DEV_MAC_IFG_CFG_TX_IFG(x) (((x) << 8) & GENMASK(12, 8)) @@ -94,8 +68,6 @@ #define DEV_MAC_IFG_CFG_RX_IFG1(x) ((x) & GENMASK(3, 0)) #define DEV_MAC_IFG_CFG_RX_IFG1_M GENMASK(3, 0) -#define DEV_MAC_HDX_CFG 0x34 - #define DEV_MAC_HDX_CFG_BYPASS_COL_SYNC BIT(26) #define DEV_MAC_HDX_CFG_OB_ENA BIT(25) #define DEV_MAC_HDX_CFG_WEXC_DIS BIT(24) @@ -107,17 +79,9 @@ #define DEV_MAC_HDX_CFG_LATE_COL_POS(x) ((x) & GENMASK(6, 0)) #define DEV_MAC_HDX_CFG_LATE_COL_POS_M GENMASK(6, 0) -#define DEV_MAC_DBG_CFG 0x38 - #define DEV_MAC_DBG_CFG_TBI_MODE BIT(4) #define DEV_MAC_DBG_CFG_IFG_CRS_EXT_CHK_ENA BIT(0) -#define DEV_MAC_FC_MAC_LOW_CFG 0x3c - -#define DEV_MAC_FC_MAC_HIGH_CFG 0x40 - -#define DEV_MAC_STICKY 0x44 - #define DEV_MAC_STICKY_RX_IPG_SHRINK_STICKY BIT(9) #define DEV_MAC_STICKY_RX_PREAM_SHRINK_STICKY BIT(8) #define DEV_MAC_STICKY_RX_CARRIER_EXT_STICKY BIT(7) @@ -129,25 +93,17 @@ #define DEV_MAC_STICKY_TX_FRM_LEN_OVR_STICKY BIT(1) #define DEV_MAC_STICKY_TX_ABORT_STICKY BIT(0) -#define PCS1G_CFG 0x48 - #define PCS1G_CFG_LINK_STATUS_TYPE BIT(4) #define PCS1G_CFG_AN_LINK_CTRL_ENA BIT(1) #define PCS1G_CFG_PCS_ENA BIT(0) -#define PCS1G_MODE_CFG 0x4c - #define PCS1G_MODE_CFG_UNIDIR_MODE_ENA BIT(4) #define PCS1G_MODE_CFG_SGMII_MODE_ENA BIT(0) -#define PCS1G_SD_CFG 0x50 - #define PCS1G_SD_CFG_SD_SEL BIT(8) #define PCS1G_SD_CFG_SD_POL BIT(4) #define PCS1G_SD_CFG_SD_ENA BIT(0) -#define PCS1G_ANEG_CFG 0x54 - #define PCS1G_ANEG_CFG_ADV_ABILITY(x) (((x) << 16) & GENMASK(31, 16)) #define PCS1G_ANEG_CFG_ADV_ABILITY_M GENMASK(31, 16) #define PCS1G_ANEG_CFG_ADV_ABILITY_X(x) (((x) & GENMASK(31, 16)) >> 16) @@ -155,29 +111,19 @@ #define PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT BIT(1) #define PCS1G_ANEG_CFG_ANEG_ENA BIT(0) -#define PCS1G_ANEG_NP_CFG 0x58 - #define PCS1G_ANEG_NP_CFG_NP_TX(x) (((x) << 16) & GENMASK(31, 16)) #define PCS1G_ANEG_NP_CFG_NP_TX_M GENMASK(31, 16) #define PCS1G_ANEG_NP_CFG_NP_TX_X(x) (((x) & GENMASK(31, 16)) >> 16) #define PCS1G_ANEG_NP_CFG_NP_LOADED_ONE_SHOT BIT(0) -#define PCS1G_LB_CFG 0x5c - #define PCS1G_LB_CFG_RA_ENA BIT(4) #define PCS1G_LB_CFG_GMII_PHY_LB_ENA BIT(1) #define PCS1G_LB_CFG_TBI_HOST_LB_ENA BIT(0) -#define PCS1G_DBG_CFG 0x60 - #define PCS1G_DBG_CFG_UDLT BIT(0) -#define PCS1G_CDET_CFG 0x64 - #define PCS1G_CDET_CFG_CDET_ENA BIT(0) -#define PCS1G_ANEG_STATUS 0x68 - #define PCS1G_ANEG_STATUS_LP_ADV_ABILITY(x) (((x) << 16) & GENMASK(31, 16)) #define PCS1G_ANEG_STATUS_LP_ADV_ABILITY_M GENMASK(31, 16) #define PCS1G_ANEG_STATUS_LP_ADV_ABILITY_X(x) (((x) & GENMASK(31, 16)) >> 16) @@ -185,10 +131,6 @@ #define PCS1G_ANEG_STATUS_PAGE_RX_STICKY BIT(3) #define PCS1G_ANEG_STATUS_ANEG_COMPLETE BIT(0) -#define PCS1G_ANEG_NP_STATUS 0x6c - -#define PCS1G_LINK_STATUS 0x70 - #define PCS1G_LINK_STATUS_DELAY_VAR(x) (((x) << 12) & GENMASK(15, 12)) #define PCS1G_LINK_STATUS_DELAY_VAR_M GENMASK(15, 12) #define PCS1G_LINK_STATUS_DELAY_VAR_X(x) (((x) & GENMASK(15, 12)) >> 12) @@ -196,17 +138,9 @@ #define PCS1G_LINK_STATUS_LINK_STATUS BIT(4) #define PCS1G_LINK_STATUS_SYNC_STATUS BIT(0) -#define PCS1G_LINK_DOWN_CNT 0x74 - -#define PCS1G_STICKY 0x78 - #define PCS1G_STICKY_LINK_DOWN_STICKY BIT(4) #define PCS1G_STICKY_OUT_OF_SYNC_STICKY BIT(0) -#define PCS1G_DEBUG_STATUS 0x7c - -#define PCS1G_LPI_CFG 0x80 - #define PCS1G_LPI_CFG_QSGMII_MS_SEL BIT(20) #define PCS1G_LPI_CFG_RX_LPI_OUT_DIS BIT(17) #define PCS1G_LPI_CFG_LPI_TESTMODE BIT(16) @@ -215,10 +149,6 @@ #define PCS1G_LPI_CFG_LPI_RX_WTIM_X(x) (((x) & GENMASK(5, 4)) >> 4) #define PCS1G_LPI_CFG_TX_ASSERT_LPIDLE BIT(0) -#define PCS1G_LPI_WAKE_ERROR_CNT 0x84 - -#define PCS1G_LPI_STATUS 0x88 - #define PCS1G_LPI_STATUS_RX_LPI_FAIL BIT(16) #define PCS1G_LPI_STATUS_RX_LPI_EVENT_STICKY BIT(12) #define PCS1G_LPI_STATUS_RX_QUIET BIT(9) @@ -227,18 +157,12 @@ #define PCS1G_LPI_STATUS_TX_QUIET BIT(1) #define PCS1G_LPI_STATUS_TX_LPI_MODE BIT(0) -#define PCS1G_TSTPAT_MODE_CFG 0x8c - -#define PCS1G_TSTPAT_STATUS 0x90 - #define PCS1G_TSTPAT_STATUS_JTP_ERR_CNT(x) (((x) << 8) & GENMASK(15, 8)) #define PCS1G_TSTPAT_STATUS_JTP_ERR_CNT_M GENMASK(15, 8) #define PCS1G_TSTPAT_STATUS_JTP_ERR_CNT_X(x) (((x) & GENMASK(15, 8)) >> 8) #define PCS1G_TSTPAT_STATUS_JTP_ERR BIT(4) #define PCS1G_TSTPAT_STATUS_JTP_LOCK BIT(0) -#define DEV_PCS_FX100_CFG 0x94 - #define DEV_PCS_FX100_CFG_SD_SEL BIT(26) #define DEV_PCS_FX100_CFG_SD_POL BIT(25) #define DEV_PCS_FX100_CFG_SD_ENA BIT(24) @@ -259,8 +183,6 @@ #define DEV_PCS_FX100_CFG_FEFGEN_ENA BIT(1) #define DEV_PCS_FX100_CFG_PCS_ENA BIT(0) -#define DEV_PCS_FX100_STATUS 0x98 - #define DEV_PCS_FX100_STATUS_EDGE_POS_PTP(x) (((x) << 8) & GENMASK(11, 8)) #define DEV_PCS_FX100_STATUS_EDGE_POS_PTP_M GENMASK(11, 8) #define DEV_PCS_FX100_STATUS_EDGE_POS_PTP_X(x) (((x) & GENMASK(11, 8)) >> 8) diff --git a/include/soc/mscc/ocelot_qsys.h b/include/soc/mscc/ocelot_qsys.h index d8c63aa761be..a814bc2017d8 100644 --- a/include/soc/mscc/ocelot_qsys.h +++ b/include/soc/mscc/ocelot_qsys.h @@ -13,19 +13,6 @@ #define QSYS_PORT_MODE_DEQUEUE_DIS BIT(1) #define QSYS_PORT_MODE_DEQUEUE_LATE BIT(0) -#define QSYS_SWITCH_PORT_MODE_RSZ 0x4 - -#define QSYS_SWITCH_PORT_MODE_PORT_ENA BIT(14) -#define QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG(x) (((x) << 11) & GENMASK(13, 11)) -#define QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG_M GENMASK(13, 11) -#define QSYS_SWITCH_PORT_MODE_SCH_NEXT_CFG_X(x) (((x) & GENMASK(13, 11)) >> 11) -#define QSYS_SWITCH_PORT_MODE_YEL_RSRVD BIT(10) -#define QSYS_SWITCH_PORT_MODE_INGRESS_DROP_MODE BIT(9) -#define QSYS_SWITCH_PORT_MODE_TX_PFC_ENA(x) (((x) << 1) & GENMASK(8, 1)) -#define QSYS_SWITCH_PORT_MODE_TX_PFC_ENA_M GENMASK(8, 1) -#define QSYS_SWITCH_PORT_MODE_TX_PFC_ENA_X(x) (((x) & GENMASK(8, 1)) >> 1) -#define QSYS_SWITCH_PORT_MODE_TX_PFC_MODE BIT(0) - #define QSYS_STAT_CNT_CFG_TX_GREEN_CNT_MODE BIT(5) #define QSYS_STAT_CNT_CFG_TX_YELLOW_CNT_MODE BIT(4) #define QSYS_STAT_CNT_CFG_DROP_GREEN_CNT_MODE BIT(3) diff --git a/include/soc/mscc/ocelot_sys.h b/include/soc/mscc/ocelot_sys.h index 16f91e172bcb..79cf40ccdbe6 100644 --- a/include/soc/mscc/ocelot_sys.h +++ b/include/soc/mscc/ocelot_sys.h @@ -12,19 +12,6 @@ #define SYS_COUNT_TX_OCTETS_RSZ 0x4 -#define SYS_PORT_MODE_RSZ 0x4 - -#define SYS_PORT_MODE_DATA_WO_TS(x) (((x) << 5) & GENMASK(6, 5)) -#define SYS_PORT_MODE_DATA_WO_TS_M GENMASK(6, 5) -#define SYS_PORT_MODE_DATA_WO_TS_X(x) (((x) & GENMASK(6, 5)) >> 5) -#define SYS_PORT_MODE_INCL_INJ_HDR(x) (((x) << 3) & GENMASK(4, 3)) -#define SYS_PORT_MODE_INCL_INJ_HDR_M GENMASK(4, 3) -#define SYS_PORT_MODE_INCL_INJ_HDR_X(x) (((x) & GENMASK(4, 3)) >> 3) -#define SYS_PORT_MODE_INCL_XTR_HDR(x) (((x) << 1) & GENMASK(2, 1)) -#define SYS_PORT_MODE_INCL_XTR_HDR_M GENMASK(2, 1) -#define SYS_PORT_MODE_INCL_XTR_HDR_X(x) (((x) & GENMASK(2, 1)) >> 1) -#define SYS_PORT_MODE_INJ_HDR_ERR BIT(0) - #define SYS_FRONT_PORT_MODE_RSZ 0x4 #define SYS_FRONT_PORT_MODE_HDX_MODE BIT(0) @@ -56,16 +43,6 @@ #define SYS_TIMESTAMP_OFFSET_TIMESTAMP_OFFSET(x) ((x) & GENMASK(5, 0)) #define SYS_TIMESTAMP_OFFSET_TIMESTAMP_OFFSET_M GENMASK(5, 0) -#define SYS_PAUSE_CFG_RSZ 0x4 - -#define SYS_PAUSE_CFG_PAUSE_START(x) (((x) << 10) & GENMASK(18, 10)) -#define SYS_PAUSE_CFG_PAUSE_START_M GENMASK(18, 10) -#define SYS_PAUSE_CFG_PAUSE_START_X(x) (((x) & GENMASK(18, 10)) >> 10) -#define SYS_PAUSE_CFG_PAUSE_STOP(x) (((x) << 1) & GENMASK(9, 1)) -#define SYS_PAUSE_CFG_PAUSE_STOP_M GENMASK(9, 1) -#define SYS_PAUSE_CFG_PAUSE_STOP_X(x) (((x) & GENMASK(9, 1)) >> 1) -#define SYS_PAUSE_CFG_PAUSE_ENA BIT(0) - #define SYS_PAUSE_TOT_CFG_PAUSE_TOT_START(x) (((x) << 9) & GENMASK(17, 9)) #define SYS_PAUSE_TOT_CFG_PAUSE_TOT_START_M GENMASK(17, 9) #define SYS_PAUSE_TOT_CFG_PAUSE_TOT_START_X(x) (((x) & GENMASK(17, 9)) >> 9) diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index 6ce8effa0b12..70cbc5095e72 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -66,6 +66,7 @@ struct snd_compr_runtime { * @direction: stream direction, playback/recording * @metadata_set: metadata set flag, true when set * @next_track: has userspace signal next track transition, true when set + * @partial_drain: undergoing partial_drain for stream, true when set * @private_data: pointer to DSP private data * @dma_buffer: allocated buffer if any */ @@ -78,6 +79,7 @@ struct snd_compr_stream { enum snd_compr_direction direction; bool metadata_set; bool next_track; + bool partial_drain; void *private_data; struct snd_dma_buffer dma_buffer; }; @@ -182,7 +184,13 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - stream->runtime->state = SNDRV_PCM_STATE_SETUP; + /* for partial_drain case we are back to running state on success */ + if (stream->partial_drain) { + stream->runtime->state = SNDRV_PCM_STATE_RUNNING; + stream->partial_drain = false; /* clear this flag as well */ + } else { + stream->runtime->state = SNDRV_PCM_STATE_SETUP; + } wake_up(&stream->runtime->sleep); } diff --git a/include/uapi/linux/atmioc.h b/include/uapi/linux/atmioc.h index cd7655e40c77..a9030bcc8d56 100644 --- a/include/uapi/linux/atmioc.h +++ b/include/uapi/linux/atmioc.h @@ -5,7 +5,7 @@ /* - * See http://icawww1.epfl.ch/linux-atm/magic.html for the complete list of + * See https://icawww1.epfl.ch/linux-atm/magic.html for the complete list of * "magic" ioctl numbers. */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 548a749aebb3..5e386389913a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3175,13 +3175,12 @@ union bpf_attr { * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return - * 0, on success; - * < 0, on error. + * 0 on success, or a negative error in case of failure. * * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) * Description @@ -3193,20 +3192,20 @@ union bpf_attr { * void bpf_ringbuf_submit(void *data, u64 flags) * Description * Submit reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * * void bpf_ringbuf_discard(void *data, u64 flags) * Description * Discard reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * @@ -3214,16 +3213,18 @@ union bpf_attr { * Description * Query various characteristics of provided ring buffer. What * exactly is queries is determined by *flags*: - * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; - * - BPF_RB_RING_SIZE - the size of ring buffer; - * - BPF_RB_CONS_POS - consumer position (can wrap around); - * - BPF_RB_PROD_POS - producer(s) position (can wrap around); - * Data returned is just a momentary snapshots of actual values + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values * and could be inaccurate, so this facility should be used to * power heuristics and for reporting, not to make 100% correct * calculation. * Return - * Requested value, or 0, if flags are not recognized. + * Requested value, or 0, if *flags* are not recognized. * * long bpf_csum_level(struct sk_buff *skb, u64 level) * Description diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 87c83a82991b..cfef4245ea5a 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -455,6 +455,9 @@ enum devlink_attr { DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, /* string */ + DEVLINK_ATTR_PORT_LANES, /* u32 */ + DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index d1413538ef30..b4f2d134e713 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -669,6 +669,7 @@ enum ethtool_link_ext_substate_cable_issue { * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags * @ETH_SS_TS_TX_TYPES: timestamping Tx types * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters + * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -686,6 +687,7 @@ enum ethtool_stringset { ETH_SS_SOF_TIMESTAMPING, ETH_SS_TS_TX_TYPES, ETH_SS_TS_RX_FILTERS, + ETH_SS_UDP_TUNNEL_TYPES, /* add new constants above here */ ETH_SS_COUNT @@ -1600,6 +1602,21 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT = 72, ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT = 73, ETHTOOL_LINK_MODE_FEC_LLRS_BIT = 74, + ETHTOOL_LINK_MODE_100000baseKR_Full_BIT = 75, + ETHTOOL_LINK_MODE_100000baseSR_Full_BIT = 76, + ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT = 77, + ETHTOOL_LINK_MODE_100000baseCR_Full_BIT = 78, + ETHTOOL_LINK_MODE_100000baseDR_Full_BIT = 79, + ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT = 80, + ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT = 81, + ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT = 82, + ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT = 83, + ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT = 84, + ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT = 85, + ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT = 86, + ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87, + ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT = 88, + ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index c12ce4df4b6b..5dcd24cb33ea 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -41,6 +41,7 @@ enum { ETHTOOL_MSG_TSINFO_GET, ETHTOOL_MSG_CABLE_TEST_ACT, ETHTOOL_MSG_CABLE_TEST_TDR_ACT, + ETHTOOL_MSG_TUNNEL_INFO_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -556,6 +557,60 @@ enum { ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX = __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT - 1 }; +/* TUNNEL INFO */ + +enum { + ETHTOOL_UDP_TUNNEL_TYPE_VXLAN, + ETHTOOL_UDP_TUNNEL_TYPE_GENEVE, + ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE, + + __ETHTOOL_UDP_TUNNEL_TYPE_CNT +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_ENTRY_UNSPEC, + + ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, /* be16 */ + ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, /* u32 */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT, + ETHTOOL_A_TUNNEL_UDP_ENTRY_MAX = (__ETHTOOL_A_TUNNEL_UDP_ENTRY_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_TABLE_UNSPEC, + + ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE, /* u32 */ + ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES, /* bitset */ + ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY, /* nest - _UDP_ENTRY_* */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_UDP_TABLE_CNT, + ETHTOOL_A_TUNNEL_UDP_TABLE_MAX = (__ETHTOOL_A_TUNNEL_UDP_TABLE_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_UDP_UNSPEC, + + ETHTOOL_A_TUNNEL_UDP_TABLE, /* nest - _UDP_TABLE_* */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_UDP_CNT, + ETHTOOL_A_TUNNEL_UDP_MAX = (__ETHTOOL_A_TUNNEL_UDP_CNT - 1) +}; + +enum { + ETHTOOL_A_TUNNEL_INFO_UNSPEC, + ETHTOOL_A_TUNNEL_INFO_HEADER, /* nest - _A_HEADER_* */ + + ETHTOOL_A_TUNNEL_INFO_UDP_PORTS, /* nest - _UDP_TABLE */ + + /* add new constants above here */ + __ETHTOOL_A_TUNNEL_INFO_CNT, + ETHTOOL_A_TUNNEL_INFO_MAX = (__ETHTOOL_A_TUNNEL_INFO_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index b6aac7ee1f67..4c14e8be7267 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -205,6 +205,7 @@ struct fb_bitfield { #define FB_ACTIVATE_ALL 64 /* change all VCs on this fb */ #define FB_ACTIVATE_FORCE 128 /* force apply even when no change*/ #define FB_ACTIVATE_INV_MODE 256 /* invalidate videomode */ +#define FB_ACTIVATE_KD_TEXT 512 /* for KDSET vt ioctl */ #define FB_ACCELF_TEXT 1 /* (OBSOLETE) see fb_info.flags and vc_mode */ diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index e6f183ee8417..5ba122c1949a 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -65,6 +65,7 @@ enum { INET_DIAG_REQ_NONE, INET_DIAG_REQ_BYTECODE, INET_DIAG_REQ_SK_BPF_STORAGES, + INET_DIAG_REQ_PROTOCOL, __INET_DIAG_REQ_MAX, }; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 92c22699a5a7..7843742b8b74 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -197,6 +197,7 @@ struct io_sqring_offsets { * sq_ring->flags */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ +#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ struct io_cqring_offsets { __u32 head; diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 5f2c77082d9e..9762660df741 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -86,4 +86,21 @@ enum { __MPTCP_PM_CMD_AFTER_LAST }; +#define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) +#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) + +struct mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; +}; + #endif /* _UAPI_MPTCP_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 4565456c0ef4..42f351c1f5c5 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -184,6 +184,15 @@ enum nft_table_attributes { }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) +enum nft_chain_flags { + NFT_CHAIN_BASE = (1 << 0), + NFT_CHAIN_HW_OFFLOAD = (1 << 1), + NFT_CHAIN_BINDING = (1 << 2), +}; +#define NFT_CHAIN_FLAGS (NFT_CHAIN_BASE | \ + NFT_CHAIN_HW_OFFLOAD | \ + NFT_CHAIN_BINDING) + /** * enum nft_chain_attributes - nf_tables chain netlink attributes * @@ -196,6 +205,7 @@ enum nft_table_attributes { * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING) * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes) * @NFTA_CHAIN_FLAGS: chain flags + * @NFTA_CHAIN_ID: uniquely identifies a chain in a transaction (NLA_U32) */ enum nft_chain_attributes { NFTA_CHAIN_UNSPEC, @@ -209,6 +219,7 @@ enum nft_chain_attributes { NFTA_CHAIN_COUNTERS, NFTA_CHAIN_PAD, NFTA_CHAIN_FLAGS, + NFTA_CHAIN_ID, __NFTA_CHAIN_MAX }; #define NFTA_CHAIN_MAX (__NFTA_CHAIN_MAX - 1) @@ -238,6 +249,7 @@ enum nft_rule_attributes { NFTA_RULE_PAD, NFTA_RULE_ID, NFTA_RULE_POSITION_ID, + NFTA_RULE_CHAIN_ID, __NFTA_RULE_MAX }; #define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1) @@ -468,11 +480,13 @@ enum nft_data_attributes { * * @NFTA_VERDICT_CODE: nf_tables verdict (NLA_U32: enum nft_verdicts) * @NFTA_VERDICT_CHAIN: jump target chain name (NLA_STRING) + * @NFTA_VERDICT_CHAIN_ID: jump target chain ID (NLA_U32) */ enum nft_verdict_attributes { NFTA_VERDICT_UNSPEC, NFTA_VERDICT_CODE, NFTA_VERDICT_CHAIN, + NFTA_VERDICT_CHAIN_ID, __NFTA_VERDICT_MAX }; #define NFTA_VERDICT_MAX (__NFTA_VERDICT_MAX - 1) diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index eca6692667a3..920470502329 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1030,7 +1030,7 @@ struct vfio_iommu_type1_info_cap_iova_range { * size in bytes that can be used by user applications when getting the dirty * bitmap. */ -#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 1 +#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 2 struct vfio_iommu_type1_info_cap_migration { struct vfio_info_cap_header header; diff --git a/init/Kconfig b/init/Kconfig index a46aa8f3174d..0498af567f70 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -49,13 +49,13 @@ config CLANG_VERSION config CC_CAN_LINK bool - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(m64-flag)) if 64BIT - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(m32-flag)) + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag)) if 64BIT + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m32-flag)) config CC_CAN_LINK_STATIC bool - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) -static $(m64-flag)) if 64BIT - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) -static $(m32-flag)) + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag) -static) if 64BIT + default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m32-flag) -static) config CC_HAS_ASM_GOTO def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC)) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a710e3ee1f18..03d6d43bb1d6 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3774,7 +3774,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; t = btf_type_skip_modifiers(btf, t->type, NULL); - if (!btf_type_is_int(t)) { + if (!btf_type_is_small_int(t)) { bpf_log(log, "ret type %s not allowed for fmod_ret\n", btf_kind_str[BTF_INFO_KIND(t->info)]); @@ -3796,7 +3796,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_type_is_enum(t)) + if (btf_type_is_small_int(t) || btf_type_is_enum(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c index 78cf061f8179..310241ca7991 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -19,18 +19,21 @@ struct bpf_netns_link { * with netns_bpf_mutex held. */ struct net *net; + struct list_head node; /* node in list of links attached to net */ }; /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); /* Must be called with netns_bpf_mutex held. */ -static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link) +static void netns_bpf_run_array_detach(struct net *net, + enum netns_bpf_attach_type type) { - struct bpf_netns_link *net_link = - container_of(link, struct bpf_netns_link, link); + struct bpf_prog_array *run_array; - net_link->net = NULL; + run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL, + lockdep_is_held(&netns_bpf_mutex)); + bpf_prog_array_free(run_array); } static void bpf_netns_link_release(struct bpf_link *link) @@ -40,22 +43,18 @@ static void bpf_netns_link_release(struct bpf_link *link) enum netns_bpf_attach_type type = net_link->netns_type; struct net *net; - /* Link auto-detached by dying netns. */ - if (!net_link->net) - return; - mutex_lock(&netns_bpf_mutex); - /* Recheck after potential sleep. We can race with cleanup_net - * here, but if we see a non-NULL struct net pointer pre_exit - * has not happened yet and will block on netns_bpf_mutex. + /* We can race with cleanup_net, but if we see a non-NULL + * struct net pointer, pre_exit has not run yet and wait for + * netns_bpf_mutex. */ net = net_link->net; if (!net) goto out_unlock; - net->bpf.links[type] = NULL; - RCU_INIT_POINTER(net->bpf.progs[type], NULL); + netns_bpf_run_array_detach(net, type); + list_del(&net_link->node); out_unlock: mutex_unlock(&netns_bpf_mutex); @@ -76,6 +75,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *link, struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; + struct bpf_prog_array *run_array; struct net *net; int ret = 0; @@ -93,8 +93,11 @@ static int bpf_netns_link_update_prog(struct bpf_link *link, goto out_unlock; } + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + WRITE_ONCE(run_array->items[0].prog, new_prog); + old_prog = xchg(&link->prog, new_prog); - rcu_assign_pointer(net->bpf.progs[type], new_prog); bpf_prog_put(old_prog); out_unlock: @@ -142,14 +145,38 @@ static const struct bpf_link_ops bpf_netns_link_ops = { .show_fdinfo = bpf_netns_link_show_fdinfo, }; +/* Must be called with netns_bpf_mutex held. */ +static int __netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr, + struct net *net, + enum netns_bpf_attach_type type) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + struct bpf_prog_array *run_array; + u32 prog_cnt = 0, flags = 0; + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + if (run_array) + prog_cnt = bpf_prog_array_length(run_array); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + return -EFAULT; + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + return 0; + + return bpf_prog_array_copy_to_user(run_array, prog_ids, + attr->query.prog_cnt); +} + int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); - u32 prog_id, prog_cnt = 0, flags = 0; enum netns_bpf_attach_type type; - struct bpf_prog *attached; struct net *net; + int ret; if (attr->query.query_flags) return -EINVAL; @@ -162,36 +189,25 @@ int netns_bpf_prog_query(const union bpf_attr *attr, if (IS_ERR(net)) return PTR_ERR(net); - rcu_read_lock(); - attached = rcu_dereference(net->bpf.progs[type]); - if (attached) { - prog_cnt = 1; - prog_id = attached->aux->id; - } - rcu_read_unlock(); + mutex_lock(&netns_bpf_mutex); + ret = __netns_bpf_prog_query(attr, uattr, net, type); + mutex_unlock(&netns_bpf_mutex); put_net(net); - - if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) - return -EFAULT; - if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) - return -EFAULT; - - if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) - return 0; - - if (copy_to_user(prog_ids, &prog_id, sizeof(u32))) - return -EFAULT; - - return 0; + return ret; } int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + struct bpf_prog_array *run_array; enum netns_bpf_attach_type type; + struct bpf_prog *attached; struct net *net; int ret; + if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; @@ -200,19 +216,47 @@ int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) mutex_lock(&netns_bpf_mutex); /* Attaching prog directly is not compatible with links */ - if (net->bpf.links[type]) { + if (!list_empty(&net->bpf.links[type])) { ret = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: - ret = flow_dissector_bpf_prog_attach(net, prog); + ret = flow_dissector_bpf_prog_attach_check(net, prog); break; default: ret = -EINVAL; break; } + if (ret) + goto out_unlock; + + attached = net->bpf.progs[type]; + if (attached == prog) { + /* The same program cannot be attached twice */ + ret = -EINVAL; + goto out_unlock; + } + + run_array = rcu_dereference_protected(net->bpf.run_array[type], + lockdep_is_held(&netns_bpf_mutex)); + if (run_array) { + WRITE_ONCE(run_array->items[0].prog, prog); + } else { + run_array = bpf_prog_array_alloc(1, GFP_KERNEL); + if (!run_array) { + ret = -ENOMEM; + goto out_unlock; + } + run_array->items[0].prog = prog; + rcu_assign_pointer(net->bpf.run_array[type], run_array); + } + + net->bpf.progs[type] = prog; + if (attached) + bpf_prog_put(attached); + out_unlock: mutex_unlock(&netns_bpf_mutex); @@ -221,63 +265,74 @@ out_unlock: /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_detach(struct net *net, - enum netns_bpf_attach_type type) + enum netns_bpf_attach_type type, + struct bpf_prog *old) { struct bpf_prog *attached; /* Progs attached via links cannot be detached */ - if (net->bpf.links[type]) + if (!list_empty(&net->bpf.links[type])) return -EINVAL; - attached = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (!attached) + attached = net->bpf.progs[type]; + if (!attached || attached != old) return -ENOENT; - RCU_INIT_POINTER(net->bpf.progs[type], NULL); + netns_bpf_run_array_detach(net, type); + net->bpf.progs[type] = NULL; bpf_prog_put(attached); return 0; } -int netns_bpf_prog_detach(const union bpf_attr *attr) +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { enum netns_bpf_attach_type type; + struct bpf_prog *prog; int ret; + if (attr->target_fd) + return -EINVAL; + type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + mutex_lock(&netns_bpf_mutex); - ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type); + ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); mutex_unlock(&netns_bpf_mutex); + bpf_prog_put(prog); + return ret; } static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, enum netns_bpf_attach_type type) { - struct bpf_prog *prog; + struct bpf_netns_link *net_link = + container_of(link, struct bpf_netns_link, link); + struct bpf_prog_array *run_array; int err; mutex_lock(&netns_bpf_mutex); /* Allow attaching only one prog or link for now */ - if (net->bpf.links[type]) { + if (!list_empty(&net->bpf.links[type])) { err = -E2BIG; goto out_unlock; } /* Links are not compatible with attaching prog directly */ - prog = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (prog) { + if (net->bpf.progs[type]) { err = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: - err = flow_dissector_bpf_prog_attach(net, link->prog); + err = flow_dissector_bpf_prog_attach_check(net, link->prog); break; default: err = -EINVAL; @@ -286,7 +341,15 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, if (err) goto out_unlock; - net->bpf.links[type] = link; + run_array = bpf_prog_array_alloc(1, GFP_KERNEL); + if (!run_array) { + err = -ENOMEM; + goto out_unlock; + } + run_array->items[0].prog = link->prog; + rcu_assign_pointer(net->bpf.run_array[type], run_array); + + list_add_tail(&net_link->node, &net->bpf.links[type]); out_unlock: mutex_unlock(&netns_bpf_mutex); @@ -345,23 +408,34 @@ out_put_net: return err; } +static int __net_init netns_bpf_pernet_init(struct net *net) +{ + int type; + + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) + INIT_LIST_HEAD(&net->bpf.links[type]); + + return 0; +} + static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { enum netns_bpf_attach_type type; - struct bpf_link *link; + struct bpf_netns_link *net_link; mutex_lock(&netns_bpf_mutex); for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { - link = net->bpf.links[type]; - if (link) - bpf_netns_link_auto_detach(link); - else - __netns_bpf_prog_detach(net, type); + netns_bpf_run_array_detach(net, type); + list_for_each_entry(net_link, &net->bpf.links[type], node) + net_link->net = NULL; /* auto-detach link */ + if (net->bpf.progs[type]) + bpf_prog_put(net->bpf.progs[type]); } mutex_unlock(&netns_bpf_mutex); } static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { + .init = netns_bpf_pernet_init, .pre_exit = netns_bpf_pernet_pre_exit, }; diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 3625c4fcc65c..90b29c5b1da7 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -20,11 +20,14 @@ static struct reuseport_array *reuseport_array(struct bpf_map *map) /* The caller must hold the reuseport_lock */ void bpf_sk_reuseport_detach(struct sock *sk) { - struct sock __rcu **socks; + uintptr_t sk_user_data; write_lock_bh(&sk->sk_callback_lock); - socks = sk->sk_user_data; - if (socks) { + sk_user_data = (uintptr_t)sk->sk_user_data; + if (sk_user_data & SK_USER_DATA_BPF) { + struct sock __rcu **socks; + + socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK); WRITE_ONCE(sk->sk_user_data, NULL); /* * Do not move this NULL assignment outside of @@ -250,6 +253,7 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, struct sock *free_osk = NULL, *osk, *nsk; struct sock_reuseport *reuse; u32 index = *(u32 *)key; + uintptr_t sk_user_data; struct socket *socket; int err, fd; @@ -303,7 +307,9 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, if (err) goto put_file_unlock; - WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]); + sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY | + SK_USER_DATA_BPF; + WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data); rcu_assign_pointer(array->ptrs[index], nsk); free_osk = osk; err = 0; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 13a8d3967e07..002f8a5c9e51 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -132,15 +132,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) { struct bpf_ringbuf *rb; - if (!data_sz || !PAGE_ALIGNED(data_sz)) - return ERR_PTR(-EINVAL); - -#ifdef CONFIG_64BIT - /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ - if (data_sz > RINGBUF_MAX_DATA_SZ) - return ERR_PTR(-E2BIG); -#endif - rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) return ERR_PTR(-ENOMEM); @@ -166,9 +157,16 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) return ERR_PTR(-EINVAL); if (attr->key_size || attr->value_size || - attr->max_entries == 0 || !PAGE_ALIGNED(attr->max_entries)) + !is_power_of_2(attr->max_entries) || + !PAGE_ALIGNED(attr->max_entries)) return ERR_PTR(-EINVAL); +#ifdef CONFIG_64BIT + /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ + if (attr->max_entries > RINGBUF_MAX_DATA_SZ) + return ERR_PTR(-E2BIG); +#endif + rb_map = kzalloc(sizeof(*rb_map), GFP_USER); if (!rb_map) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 156f51ffada2..7ea9dfbebd8c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2122,7 +2122,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) !bpf_capable()) return -EPERM; - if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN)) + if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) return -EPERM; if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; @@ -2895,13 +2895,11 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, ptype); case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_PROG_TYPE_FLOW_DISSECTOR: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - return netns_bpf_prog_detach(attr); + return netns_bpf_prog_detach(attr, ptype); case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: @@ -3142,7 +3140,8 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, return NULL; } -static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) +static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, + const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; @@ -3168,7 +3167,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) code == (BPF_JMP | BPF_CALL_ARGS)) { if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; - if (!bpf_dump_raw_ok()) + if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } @@ -3224,7 +3223,8 @@ static int set_info_rec_size(struct bpf_prog_info *info) return 0; } -static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, +static int bpf_prog_get_info_by_fd(struct file *file, + struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -3293,11 +3293,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, struct bpf_insn *insns_sanitized; bool fault; - if (prog->blinded && !bpf_dump_raw_ok()) { + if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { info.xlated_prog_insns = 0; goto done; } - insns_sanitized = bpf_insn_prepare_dump(prog); + insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); @@ -3331,7 +3331,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } if (info.jited_prog_len && ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); @@ -3366,7 +3366,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; @@ -3397,7 +3397,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; @@ -3454,7 +3454,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { __u64 __user *user_linfo; u32 i; @@ -3500,7 +3500,8 @@ done: return 0; } -static int bpf_map_get_info_by_fd(struct bpf_map *map, +static int bpf_map_get_info_by_fd(struct file *file, + struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -3543,7 +3544,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, return 0; } -static int bpf_btf_get_info_by_fd(struct btf *btf, +static int bpf_btf_get_info_by_fd(struct file *file, + struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -3558,7 +3560,8 @@ static int bpf_btf_get_info_by_fd(struct btf *btf, return btf_get_info_by_fd(btf, attr, uattr); } -static int bpf_link_get_info_by_fd(struct bpf_link *link, +static int bpf_link_get_info_by_fd(struct file *file, + struct bpf_link *link, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -3611,15 +3614,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return -EBADFD; if (f.file->f_op == &bpf_prog_fops) - err = bpf_prog_get_info_by_fd(f.file->private_data, attr, + err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &bpf_map_fops) - err = bpf_map_get_info_by_fd(f.file->private_data, attr, + err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &btf_fops) - err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr); + err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &bpf_link_fops) - err = bpf_link_get_info_by_fd(f.file->private_data, + err = bpf_link_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else err = -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b608185e1ffd..3c1efc9d08fd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -399,8 +399,7 @@ static bool reg_type_not_null(enum bpf_reg_type type) return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || - type == PTR_TO_SOCK_COMMON || - type == PTR_TO_BTF_ID; + type == PTR_TO_SOCK_COMMON; } static bool reg_type_may_be_null(enum bpf_reg_type type) @@ -9896,7 +9895,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_insn *insn; void *old_bpf_func; - int err; + int err, num_exentries; if (env->subprog_cnt <= 1) return 0; @@ -9971,6 +9970,14 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; + num_exentries = 0; + insn = func[i]->insnsi; + for (j = 0; j < func[i]->len; j++, insn++) { + if (BPF_CLASS(insn->code) == BPF_LDX && + BPF_MODE(insn->code) == BPF_PROBE_MEM) + num_exentries++; + } + func[i]->aux->num_exentries = num_exentries; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1ea181a58465..dd247747ec14 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6439,18 +6439,8 @@ void cgroup_sk_alloc_disable(void) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) - return; - - /* Socket clone path */ - if (skcd->val) { - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); + if (cgroup_sk_alloc_disabled) { + skcd->no_refcnt = 1; return; } @@ -6475,10 +6465,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) rcu_read_unlock(); } +void cgroup_sk_clone(struct sock_cgroup_data *skcd) +{ + if (skcd->val) { + if (skcd->no_refcnt) + return; + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(sock_cgroup_ptr(skcd)); + cgroup_bpf_get(sock_cgroup_ptr(skcd)); + } +} + void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); + if (skcd->no_refcnt) + return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index bc8d25f2ac8a..9e5934780f41 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -587,6 +587,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, arch_kgdb_ops.disable_hw_break(regs); acquirelock: + rcu_read_lock(); /* * Interrupts will be restored by the 'trap return' code, except when * single stepping. @@ -646,6 +647,7 @@ return_normal: atomic_dec(&slaves_in_kgdb); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return 0; } cpu_relax(); @@ -664,6 +666,7 @@ return_normal: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); goto acquirelock; } @@ -787,6 +790,7 @@ kgdb_restore: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return kgdb_info[cpu].ret_state; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 924bc9298a42..683a799618ad 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -542,6 +542,44 @@ static int kdb_search_string(char *searched, char *searchfor) return 0; } +static void kdb_msg_write(const char *msg, int msg_len) +{ + struct console *c; + + if (msg_len == 0) + return; + + if (dbg_io_ops) { + const char *cp = msg; + int len = msg_len; + + while (len--) { + dbg_io_ops->write_char(*cp); + cp++; + } + } + + for_each_console(c) { + if (!(c->flags & CON_ENABLED)) + continue; + if (c == dbg_io_ops->cons) + continue; + /* + * Set oops_in_progress to encourage the console drivers to + * disregard their internal spin locks: in the current calling + * context the risk of deadlock is a bigger problem than risks + * due to re-entering the console driver. We operate directly on + * oops_in_progress rather than using bust_spinlocks() because + * the calls bust_spinlocks() makes on exit are not appropriate + * for this calling context. + */ + ++oops_in_progress; + c->write(c, msg, msg_len); + --oops_in_progress; + touch_nmi_watchdog(); + } +} + int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) { int diag; @@ -553,7 +591,6 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) int this_cpu, old_cpu; char *cp, *cp2, *cphold = NULL, replaced_byte = ' '; char *moreprompt = "more> "; - struct console *c; unsigned long uninitialized_var(flags); /* Serialize kdb_printf if multiple cpus try to write at once. @@ -687,22 +724,11 @@ kdb_printit: */ retlen = strlen(kdb_buffer); cp = (char *) printk_skip_headers(kdb_buffer); - if (!dbg_kdb_mode && kgdb_connected) { + if (!dbg_kdb_mode && kgdb_connected) gdbstub_msg_write(cp, retlen - (cp - kdb_buffer)); - } else { - if (dbg_io_ops && !dbg_io_ops->is_console) { - len = retlen - (cp - kdb_buffer); - cp2 = cp; - while (len--) { - dbg_io_ops->write_char(*cp2); - cp2++; - } - } - for_each_console(c) { - c->write(c, cp, retlen - (cp - kdb_buffer)); - touch_nmi_watchdog(); - } - } + else + kdb_msg_write(cp, retlen - (cp - kdb_buffer)); + if (logging) { saved_loglevel = console_loglevel; console_loglevel = CONSOLE_LOGLEVEL_SILENT; @@ -751,19 +777,7 @@ kdb_printit: moreprompt = "more> "; kdb_input_flush(); - - if (dbg_io_ops && !dbg_io_ops->is_console) { - len = strlen(moreprompt); - cp = moreprompt; - while (len--) { - dbg_io_ops->write_char(*cp); - cp++; - } - } - for_each_console(c) { - c->write(c, moreprompt, strlen(moreprompt)); - touch_nmi_watchdog(); - } + kdb_msg_write(moreprompt, strlen(moreprompt)); if (logging) printk("%s", moreprompt); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index a0ce3c1494fd..1da3f44f2565 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -71,15 +71,16 @@ config SWIOTLB # in the pagetables # config DMA_NONCOHERENT_MMAP + default y if !MMU bool config DMA_COHERENT_POOL + select GENERIC_ALLOCATOR bool config DMA_REMAP bool depends on MMU - select GENERIC_ALLOCATOR select DMA_NONCOHERENT_MMAP config DMA_DIRECT_REMAP diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 0a4881e59aa7..95866b647581 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -109,14 +109,15 @@ static inline bool dma_should_free_from_pool(struct device *dev, return false; } -struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, +static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp_t gfp, unsigned long attrs) { - size_t alloc_size = PAGE_ALIGN(size); int node = dev_to_node(dev); struct page *page = NULL; u64 phys_limit; + WARN_ON_ONCE(!PAGE_ALIGNED(size)); + if (attrs & DMA_ATTR_NO_WARN) gfp |= __GFP_NOWARN; @@ -124,14 +125,14 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp &= ~__GFP_ZERO; gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, &phys_limit); - page = dma_alloc_contiguous(dev, alloc_size, gfp); + page = dma_alloc_contiguous(dev, size, gfp); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { - dma_free_contiguous(dev, page, alloc_size); + dma_free_contiguous(dev, page, size); page = NULL; } again: if (!page) - page = alloc_pages_node(node, gfp, get_order(alloc_size)); + page = alloc_pages_node(node, gfp, get_order(size)); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { dma_free_contiguous(dev, page, size); page = NULL; @@ -157,9 +158,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, { struct page *page; void *ret; + int err; + + size = PAGE_ALIGN(size); if (dma_should_alloc_from_pool(dev, gfp, attrs)) { - ret = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page, gfp); + ret = dma_alloc_from_pool(dev, size, &page, gfp); if (!ret) return NULL; goto done; @@ -183,14 +187,20 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, dma_alloc_need_uncached(dev, attrs)) || (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) { /* remove any dirty cache lines on the kernel alias */ - arch_dma_prep_coherent(page, PAGE_ALIGN(size)); + arch_dma_prep_coherent(page, size); /* create a coherent mapping */ - ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size), + ret = dma_common_contiguous_remap(page, size, dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) goto out_free_pages; + if (force_dma_unencrypted(dev)) { + err = set_memory_decrypted((unsigned long)ret, + 1 << get_order(size)); + if (err) + goto out_free_pages; + } memset(ret, 0, size); goto done; } @@ -207,8 +217,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, } ret = page_address(page); - if (force_dma_unencrypted(dev)) - set_memory_decrypted((unsigned long)ret, 1 << get_order(size)); + if (force_dma_unencrypted(dev)) { + err = set_memory_decrypted((unsigned long)ret, + 1 << get_order(size)); + if (err) + goto out_free_pages; + } memset(ret, 0, size); @@ -217,7 +231,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, arch_dma_prep_coherent(page, size); ret = arch_dma_set_uncached(ret, size); if (IS_ERR(ret)) - goto out_free_pages; + goto out_encrypt_pages; } done: if (force_dma_unencrypted(dev)) @@ -225,6 +239,15 @@ done: else *dma_handle = phys_to_dma(dev, page_to_phys(page)); return ret; + +out_encrypt_pages: + if (force_dma_unencrypted(dev)) { + err = set_memory_encrypted((unsigned long)page_address(page), + 1 << get_order(size)); + /* If memory cannot be re-encrypted, it must be leaked */ + if (err) + return NULL; + } out_free_pages: dma_free_contiguous(dev, page, size); return NULL; @@ -459,7 +482,6 @@ int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, return ret; } -#ifdef CONFIG_MMU bool dma_direct_can_mmap(struct device *dev) { return dev_is_dma_coherent(dev) || @@ -485,19 +507,6 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, user_count << PAGE_SHIFT, vma->vm_page_prot); } -#else /* CONFIG_MMU */ -bool dma_direct_can_mmap(struct device *dev) -{ - return false; -} - -int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -ENXIO; -} -#endif /* CONFIG_MMU */ int dma_direct_supported(struct device *dev, u64 mask) { @@ -530,3 +539,9 @@ size_t dma_direct_max_mapping_size(struct device *dev) return swiotlb_max_mapping_size(dev); return SIZE_MAX; } + +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return !dev_is_dma_coherent(dev) || + is_swiotlb_buffer(dma_to_phys(dev, dma_addr)); +} diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 98e3d873792e..a8c18c9a796f 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -397,6 +397,16 @@ size_t dma_max_mapping_size(struct device *dev) } EXPORT_SYMBOL_GPL(dma_max_mapping_size); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_is_direct(ops)) + return dma_direct_need_sync(dev, dma_addr); + return ops->sync_single_for_cpu || ops->sync_single_for_device; +} +EXPORT_SYMBOL_GPL(dma_need_sync); + unsigned long dma_get_merge_boundary(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 8cfa01243ed2..39ca26fa41b5 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -239,12 +239,16 @@ void *dma_alloc_from_pool(struct device *dev, size_t size, } val = gen_pool_alloc(pool, size); - if (val) { + if (likely(val)) { phys_addr_t phys = gen_pool_virt_to_phys(pool, val); *ret_page = pfn_to_page(__phys_to_pfn(phys)); ptr = (void *)val; memset(ptr, 0, size); + } else { + WARN_ONCE(1, "DMA coherent pool depleted, increase size " + "(recommended min coherent_pool=%zuK)\n", + gen_pool_size(pool) >> 9); } if (gen_pool_avail(pool) < atomic_pool_size) schedule_work(&atomic_pool_work); diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index e739a6eea6e7..78b23f089cf1 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -24,7 +24,8 @@ void *dma_common_pages_remap(struct page **pages, size_t size, { void *vaddr; - vaddr = vmap(pages, size >> PAGE_SHIFT, VM_DMA_COHERENT, prot); + vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT, + VM_DMA_COHERENT, prot); if (vaddr) find_vm_area(vaddr)->pages = pages; return vaddr; @@ -37,7 +38,7 @@ void *dma_common_pages_remap(struct page **pages, size_t size, void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot, const void *caller) { - int count = size >> PAGE_SHIFT; + int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page **pages; void *vaddr; int i; diff --git a/kernel/fork.c b/kernel/fork.c index 142b23645d82..efc5493203ae 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1977,7 +1977,7 @@ static __latent_entropy struct task_struct *copy_process( * to stop root fork bombs. */ retval = -EAGAIN; - if (nr_threads >= max_threads) + if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 16c8c605f4b0..bb14e64f62a4 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -644,19 +644,20 @@ static inline int kallsyms_for_perf(void) * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to * block even that). */ -int kallsyms_show_value(void) +bool kallsyms_show_value(const struct cred *cred) { switch (kptr_restrict) { case 0: if (kallsyms_for_perf()) - return 1; + return true; /* fallthrough */ case 1: - if (has_capability_noaudit(current, CAP_SYSLOG)) - return 1; + if (security_capable(cred, &init_user_ns, CAP_SYSLOG, + CAP_OPT_NOAUDIT) == 0) + return true; /* fallthrough */ default: - return 0; + return false; } } @@ -673,7 +674,11 @@ static int kallsyms_open(struct inode *inode, struct file *file) return -ENOMEM; reset_iter(iter, 0); - iter->show_value = kallsyms_show_value(); + /* + * Instead of checking this on every s_show() call, cache + * the result here at open time. + */ + iter->show_value = kallsyms_show_value(file->f_cred); return 0; } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index bb05fd52de85..09cc78df53c6 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -181,34 +181,19 @@ void kimage_file_post_load_cleanup(struct kimage *image) static int kimage_validate_signature(struct kimage *image) { - const char *reason; int ret; ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf, image->kernel_buf_len); - switch (ret) { - case 0: - break; + if (ret) { - /* Certain verification errors are non-fatal if we're not - * checking errors, provided we aren't mandating that there - * must be a valid signature. - */ - case -ENODATA: - reason = "kexec of unsigned image"; - goto decide; - case -ENOPKG: - reason = "kexec of image with unsupported crypto"; - goto decide; - case -ENOKEY: - reason = "kexec of image with unavailable key"; - decide: if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) { - pr_notice("%s rejected\n", reason); + pr_notice("Enforced kernel signature verification failed (%d).\n", ret); return ret; } - /* If IMA is guaranteed to appraise a signature on the kexec + /* + * If IMA is guaranteed to appraise a signature on the kexec * image, permit it even if the kernel is otherwise locked * down. */ @@ -216,17 +201,10 @@ kimage_validate_signature(struct kimage *image) security_locked_down(LOCKDOWN_KEXEC)) return -EPERM; - return 0; - - /* All other errors are fatal, including nomem, unparseable - * signatures and signature check failures - even if signatures - * aren't required. - */ - default: - pr_notice("kernel signature verification failed (%d).\n", ret); + pr_debug("kernel signature verification failed (%d).\n", ret); } - return ret; + return 0; } #endif diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 4a904cc56d68..2e97febeef77 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2448,7 +2448,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, else kprobe_type = "k"; - if (!kallsyms_show_value()) + if (!kallsyms_show_value(pi->file->f_cred)) addr = NULL; if (sym) @@ -2540,7 +2540,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) * If /proc/kallsyms is not showing kernel address, we won't * show them here either. */ - if (!kallsyms_show_value()) + if (!kallsyms_show_value(m->file->f_cred)) seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, (void *)ent->start_addr); else diff --git a/kernel/module.c b/kernel/module.c index e8a198588f26..aa183c9ac0a2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1510,8 +1510,7 @@ static inline bool sect_empty(const Elf_Shdr *sect) } struct module_sect_attr { - struct module_attribute mattr; - char *name; + struct bin_attribute battr; unsigned long address; }; @@ -1521,13 +1520,18 @@ struct module_sect_attrs { struct module_sect_attr attrs[]; }; -static ssize_t module_sect_show(struct module_attribute *mattr, - struct module_kobject *mk, char *buf) +static ssize_t module_sect_read(struct file *file, struct kobject *kobj, + struct bin_attribute *battr, + char *buf, loff_t pos, size_t count) { struct module_sect_attr *sattr = - container_of(mattr, struct module_sect_attr, mattr); - return sprintf(buf, "0x%px\n", kptr_restrict < 2 ? - (void *)sattr->address : NULL); + container_of(battr, struct module_sect_attr, battr); + + if (pos != 0) + return -EINVAL; + + return sprintf(buf, "0x%px\n", + kallsyms_show_value(file->f_cred) ? (void *)sattr->address : NULL); } static void free_sect_attrs(struct module_sect_attrs *sect_attrs) @@ -1535,7 +1539,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs) unsigned int section; for (section = 0; section < sect_attrs->nsections; section++) - kfree(sect_attrs->attrs[section].name); + kfree(sect_attrs->attrs[section].battr.attr.name); kfree(sect_attrs); } @@ -1544,42 +1548,41 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; struct module_sect_attr *sattr; - struct attribute **gattr; + struct bin_attribute **gattr; /* Count loaded sections and allocate structures */ for (i = 0; i < info->hdr->e_shnum; i++) if (!sect_empty(&info->sechdrs[i])) nloaded++; size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded), - sizeof(sect_attrs->grp.attrs[0])); - size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]); + sizeof(sect_attrs->grp.bin_attrs[0])); + size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); if (sect_attrs == NULL) return; /* Setup section attributes. */ sect_attrs->grp.name = "sections"; - sect_attrs->grp.attrs = (void *)sect_attrs + size[0]; + sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0]; sect_attrs->nsections = 0; sattr = §_attrs->attrs[0]; - gattr = §_attrs->grp.attrs[0]; + gattr = §_attrs->grp.bin_attrs[0]; for (i = 0; i < info->hdr->e_shnum; i++) { Elf_Shdr *sec = &info->sechdrs[i]; if (sect_empty(sec)) continue; + sysfs_bin_attr_init(&sattr->battr); sattr->address = sec->sh_addr; - sattr->name = kstrdup(info->secstrings + sec->sh_name, - GFP_KERNEL); - if (sattr->name == NULL) + sattr->battr.attr.name = + kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); + if (sattr->battr.attr.name == NULL) goto out; sect_attrs->nsections++; - sysfs_attr_init(&sattr->mattr.attr); - sattr->mattr.show = module_sect_show; - sattr->mattr.store = NULL; - sattr->mattr.attr.name = sattr->name; - sattr->mattr.attr.mode = S_IRUSR; - *(gattr++) = &(sattr++)->mattr.attr; + sattr->battr.read = module_sect_read; + sattr->battr.size = 3 /* "0x", "\n" */ + (BITS_PER_LONG / 4); + sattr->battr.attr.mode = 0400; + *(gattr++) = &(sattr++)->battr; } *gattr = NULL; @@ -1669,7 +1672,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) continue; if (info->sechdrs[i].sh_type == SHT_NOTE) { sysfs_bin_attr_init(nattr); - nattr->attr.name = mod->sect_attrs->attrs[loaded].name; + nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name; nattr->attr.mode = S_IRUGO; nattr->size = info->sechdrs[i].sh_size; nattr->private = (void *) info->sechdrs[i].sh_addr; @@ -2783,7 +2786,9 @@ static void dynamic_debug_remove(struct module *mod, struct _ddebug *debug) void * __weak module_alloc(unsigned long size) { - return vmalloc_exec(size); + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } bool __weak module_init_section(const char *name) @@ -4377,7 +4382,7 @@ static int modules_open(struct inode *inode, struct file *file) if (!err) { struct seq_file *m = file->private_data; - m->private = kallsyms_show_value() ? NULL : (void *)8ul; + m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul; } return err; diff --git a/kernel/padata.c b/kernel/padata.c index 29fc5d87a4cd..4373f7adaa40 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -335,7 +335,7 @@ static void padata_reorder(struct parallel_data *pd) * * Ensure reorder queue is read after pd->lock is dropped so we see * new objects from another task in padata_do_serial. Pairs with - * smp_mb__after_atomic in padata_do_serial. + * smp_mb in padata_do_serial. */ smp_mb(); @@ -418,7 +418,7 @@ void padata_do_serial(struct padata_priv *padata) * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb * in padata_reorder. */ - smp_mb__after_atomic(); + smp_mb(); padata_reorder(pd); } diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 16dd1e6b7c09..9eb39c20082c 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -723,7 +723,7 @@ kfree_perf_init(void) schedule_timeout_uninterruptible(1); } - pr_alert("kfree object size=%lu\n", kfree_mult * sizeof(struct kfree_obj)); + pr_alert("kfree object size=%zu\n", kfree_mult * sizeof(struct kfree_obj)); kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]), GFP_KERNEL); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c716eadc7617..6c6569e0586c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -250,7 +250,7 @@ static noinstr void rcu_dynticks_eqs_enter(void) * next idle sojourn. */ rcu_dynticks_task_trace_enter(); // Before ->dynticks update! - seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); + seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); // RCU is no longer watching. Better be in extended quiescent state! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICK_CTRL_CTR)); @@ -274,13 +274,13 @@ static noinstr void rcu_dynticks_eqs_exit(void) * and we also must force ordering with the next RCU read-side * critical section. */ - seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); + seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); // RCU is now watching. Better not be in an extended quiescent state! rcu_dynticks_task_trace_exit(); // After ->dynticks update! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICK_CTRL_CTR)); if (seq & RCU_DYNTICK_CTRL_MASK) { - atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks); + arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks); smp_mb__after_atomic(); /* _exit after clearing mask. */ } } @@ -313,7 +313,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR); + return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR); } /* @@ -633,6 +633,10 @@ static noinstr void rcu_eqs_enter(bool user) do_nocb_deferred_wakeup(rdp); rcu_prepare_for_idle(); rcu_preempt_deferred_qs(current); + + // instrumentation for the noinstr rcu_dynticks_eqs_enter() + instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); + instrumentation_end(); WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */ // RCU is watching here ... @@ -692,6 +696,7 @@ noinstr void rcu_nmi_exit(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + instrumentation_begin(); /* * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. * (We are exiting an NMI handler, so RCU better be paying attention @@ -705,7 +710,6 @@ noinstr void rcu_nmi_exit(void) * leave it in non-RCU-idle state. */ if (rdp->dynticks_nmi_nesting != 1) { - instrumentation_begin(); trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */ @@ -714,13 +718,15 @@ noinstr void rcu_nmi_exit(void) return; } - instrumentation_begin(); /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ if (!in_nmi()) rcu_prepare_for_idle(); + + // instrumentation for the noinstr rcu_dynticks_eqs_enter() + instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); instrumentation_end(); // RCU is watching here ... @@ -838,6 +844,10 @@ static void noinstr rcu_eqs_exit(bool user) rcu_dynticks_eqs_exit(); // ... but is watching here. instrumentation_begin(); + + // instrumentation for the noinstr rcu_dynticks_eqs_exit() + instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); + rcu_cleanup_after_idle(); trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks)); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); @@ -983,13 +993,21 @@ noinstr void rcu_nmi_enter(void) if (!in_nmi()) rcu_cleanup_after_idle(); + instrumentation_begin(); + // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs() + instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks)); + // instrumentation for the noinstr rcu_dynticks_eqs_exit() + instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks)); + incby = 1; } else if (!in_nmi()) { instrumentation_begin(); rcu_irq_enter_check_tick(); instrumentation_end(); + } else { + instrumentation_begin(); } - instrumentation_begin(); + trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks)); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8f360326861e..ca5db40392d4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1637,7 +1637,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - if (cpumask_equal(p->cpus_ptr, new_mask)) + if (cpumask_equal(&p->cpus_mask, new_mask)) goto out; /* @@ -2293,8 +2293,15 @@ void sched_ttwu_pending(void *arg) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - llist_for_each_entry_safe(p, t, llist, wake_entry) + llist_for_each_entry_safe(p, t, llist, wake_entry.llist) { + if (WARN_ON_ONCE(p->on_cpu)) + smp_cond_load_acquire(&p->on_cpu, !VAL); + + if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq))) + set_task_cpu(p, cpu_of(rq)); + ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf); + } rq_unlock_irqrestore(rq, &rf); } @@ -2322,7 +2329,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED); WRITE_ONCE(rq->ttwu_pending, 1); - __smp_call_single_queue(cpu, &p->wake_entry); + __smp_call_single_queue(cpu, &p->wake_entry.llist); } void wake_up_if_idle(int cpu) @@ -2369,7 +2376,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags) * the soon-to-be-idle CPU as the current CPU is likely busy. * nr_running is checked to avoid unnecessary task stacking. */ - if ((wake_flags & WF_ON_RQ) && cpu_rq(cpu)->nr_running <= 1) + if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1) return true; return false; @@ -2378,6 +2385,9 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags) static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags) { if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) { + if (WARN_ON_ONCE(cpu == smp_processor_id())) + return false; + sched_clock_cpu(cpu); /* Sync clocks across CPUs */ __ttwu_queue_wakelist(p, cpu, wake_flags); return true; @@ -2528,7 +2538,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) goto out; success = 1; - cpu = task_cpu(p); trace_sched_waking(p); p->state = TASK_RUNNING; trace_sched_wakeup(p); @@ -2550,7 +2559,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) /* We're going to change ->state: */ success = 1; - cpu = task_cpu(p); /* * Ensure we load p->on_rq _after_ p->state, otherwise it would @@ -2614,8 +2622,21 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * which potentially sends an IPI instead of spinning on p->on_cpu to * let the waker make forward progress. This is safe because IRQs are * disabled and the IPI will deliver after on_cpu is cleared. + * + * Ensure we load task_cpu(p) after p->on_cpu: + * + * set_task_cpu(p, cpu); + * STORE p->cpu = @cpu + * __schedule() (switch to task 'p') + * LOCK rq->lock + * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu) + * STORE p->on_cpu = 1 LOAD p->cpu + * + * to ensure we observe the correct CPU on which the task is currently + * scheduling. */ - if (READ_ONCE(p->on_cpu) && ttwu_queue_wakelist(p, cpu, wake_flags | WF_ON_RQ)) + if (smp_load_acquire(&p->on_cpu) && + ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU)) goto unlock; /* @@ -2635,6 +2656,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } +#else + cpu = task_cpu(p); #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags); @@ -2642,7 +2665,7 @@ unlock: raw_spin_unlock_irqrestore(&p->pi_lock, flags); out: if (success) - ttwu_stat(p, cpu, wake_flags); + ttwu_stat(p, task_cpu(p), wake_flags); preempt_enable(); return success; @@ -2763,7 +2786,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #endif init_numa_balancing(clone_flags, p); #ifdef CONFIG_SMP - p->wake_entry_type = CSD_TYPE_TTWU; + p->wake_entry.u_flags = CSD_TYPE_TTWU; #endif } @@ -4533,7 +4556,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) */ if (dl_prio(prio)) { if (!dl_prio(p->normal_prio) || - (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { + (pi_task && dl_prio(pi_task->prio) && + dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; queue_flag |= ENQUEUE_REPLENISH; } else diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 504d2f51b0d6..f63f337c7147 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2692,6 +2692,7 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_density = 0; + dl_se->dl_boosted = 0; dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cbcb2f71599b..658aa7a2ae6f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -806,7 +806,7 @@ void post_init_entity_util_avg(struct task_struct *p) } } - sa->runnable_avg = cpu_scale; + sa->runnable_avg = sa->util_avg; if (p->sched_class != &fair_sched_class) { /* diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 05deb81bb3e3..1ae95b9150d3 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -96,6 +96,15 @@ void __cpuidle default_idle_call(void) } } +static int call_cpuidle_s2idle(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + if (current_clr_polling_and_test()) + return -EBUSY; + + return cpuidle_enter_s2idle(drv, dev); +} + static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, int next_state) { @@ -171,11 +180,9 @@ static void cpuidle_idle_call(void) if (idle_should_enter_s2idle()) { rcu_idle_enter(); - entered_state = cpuidle_enter_s2idle(drv, dev); - if (entered_state > 0) { - local_irq_enable(); + entered_state = call_cpuidle_s2idle(drv, dev); + if (entered_state > 0) goto exit_idle; - } rcu_idle_exit(); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1d4e94c1e5fe..877fb08eb1b0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1682,7 +1682,7 @@ static inline int task_on_rq_migrating(struct task_struct *p) #define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */ #define WF_FORK 0x02 /* Child wakeup after fork */ #define WF_MIGRATED 0x04 /* Internal use, task got migrated */ -#define WF_ON_RQ 0x08 /* Wakee is on_rq */ +#define WF_ON_CPU 0x08 /* Wakee is on_cpu */ /* * To aid in avoiding the subversion of "niceness" due to uneven distribution diff --git a/kernel/signal.c b/kernel/signal.c index 5ca48cc5da76..ee22ec78fd6d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2529,9 +2529,6 @@ bool get_signal(struct ksignal *ksig) struct signal_struct *signal = current->signal; int signr; - if (unlikely(current->task_works)) - task_work_run(); - if (unlikely(uprobe_deny_signal())) return false; @@ -2544,6 +2541,13 @@ bool get_signal(struct ksignal *ksig) relock: spin_lock_irq(&sighand->siglock); + current->jobctl &= ~JOBCTL_TASK_WORK; + if (unlikely(current->task_works)) { + spin_unlock_irq(&sighand->siglock); + task_work_run(); + goto relock; + } + /* * Every stopped thread goes here after wakeup. Check to see if * we should notify the parent, prepare_signal(SIGCONT) encodes diff --git a/kernel/smp.c b/kernel/smp.c index 472c2b274c65..aa17eedff5be 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -669,24 +669,6 @@ void __init smp_init(void) { int num_nodes, num_cpus; - /* - * Ensure struct irq_work layout matches so that - * flush_smp_call_function_queue() can do horrible things. - */ - BUILD_BUG_ON(offsetof(struct irq_work, llnode) != - offsetof(struct __call_single_data, llist)); - BUILD_BUG_ON(offsetof(struct irq_work, func) != - offsetof(struct __call_single_data, func)); - BUILD_BUG_ON(offsetof(struct irq_work, flags) != - offsetof(struct __call_single_data, flags)); - - /* - * Assert the CSD_TYPE_TTWU layout is similar enough - * for task_struct to be on the @call_single_queue. - */ - BUILD_BUG_ON(offsetof(struct task_struct, wake_entry_type) - offsetof(struct task_struct, wake_entry) != - offsetof(struct __call_single_data, flags) - offsetof(struct __call_single_data, llist)); - idle_threads_init(); cpuhp_threads_init(); diff --git a/kernel/task_work.c b/kernel/task_work.c index 825f28259a19..5c0848ca1287 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -25,9 +25,10 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ * 0 if succeeds or -ESRCH. */ int -task_work_add(struct task_struct *task, struct callback_head *work, bool notify) +task_work_add(struct task_struct *task, struct callback_head *work, int notify) { struct callback_head *head; + unsigned long flags; do { head = READ_ONCE(task->task_works); @@ -36,8 +37,19 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify) work->next = head; } while (cmpxchg(&task->task_works, head, work) != head); - if (notify) + switch (notify) { + case TWA_RESUME: set_notify_resume(task); + break; + case TWA_SIGNAL: + if (lock_task_sighand(task, &flags)) { + task->jobctl |= JOBCTL_TASK_WORK; + signal_wake_up(task, 0); + unlock_task_sighand(task, &flags); + } + break; + } + return 0; } diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 81f5464ea9e1..34b84bcbd3d9 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -15,11 +15,15 @@ config CC_HAS_KASAN_GENERIC config CC_HAS_KASAN_SW_TAGS def_bool $(cc-option, -fsanitize=kernel-hwaddress) +config CC_HAS_WORKING_NOSANITIZE_ADDRESS + def_bool !CC_IS_GCC || GCC_VERSION >= 80300 + config KASAN bool "KASAN: runtime memory debugger" depends on (HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \ (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS) depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) + depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS help Enables KASAN (KernelAddressSANitizer) - runtime memory debugger, designed to find out-of-bounds accesses and use-after-free bugs. diff --git a/lib/packing.c b/lib/packing.c index 50d1e9f2f5a7..6ed72dccfdb5 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -73,6 +73,7 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit, * @endbit: The index (in logical notation, compensated for quirks) where * the packed value ends within pbuf. Must be smaller than, or equal * to, startbit. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. * @op: If PACK, then uval will be treated as const pointer and copied (packed) * into pbuf, between startbit and endbit. * If UNPACK, then pbuf will be treated as const pointer and the logical diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 28528285942c..a2a82262b97b 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -520,8 +520,7 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, err_free: kfree(devmem); err_release: - release_mem_region(devmem->pagemap.res.start, - resource_size(&devmem->pagemap.res)); + release_mem_region(res->start, resource_size(res)); err: mutex_unlock(&mdevice->devmem_lock); return false; @@ -339,13 +339,13 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, */ if (base < highmem_start && limit > highmem_start) { addr = memblock_alloc_range_nid(size, alignment, - highmem_start, limit, nid, false); + highmem_start, limit, nid, true); limit = highmem_start; } if (!addr) { addr = memblock_alloc_range_nid(size, alignment, base, - limit, nid, false); + limit, nid, true); if (!addr) { ret = -ENOMEM; goto err; @@ -2,6 +2,8 @@ #ifndef __MM_CMA_H__ #define __MM_CMA_H__ +#include <linux/debugfs.h> + struct cma { unsigned long base_pfn; unsigned long count; @@ -11,6 +13,7 @@ struct cma { #ifdef CONFIG_CMA_DEBUGFS struct hlist_head mem_head; spinlock_t mem_head_lock; + struct debugfs_u32_array dfs_bitmap; #endif const char *name; }; diff --git a/mm/cma_debug.c b/mm/cma_debug.c index 4e6cbe2f586e..d5bf8aa34fdc 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -164,7 +164,6 @@ static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry) { struct dentry *tmp; char name[16]; - int u32s; scnprintf(name, sizeof(name), "cma-%s", cma->name); @@ -180,8 +179,10 @@ static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry) debugfs_create_file("used", 0444, tmp, cma, &cma_used_fops); debugfs_create_file("maxchunk", 0444, tmp, cma, &cma_maxchunk_fops); - u32s = DIV_ROUND_UP(cma_bitmap_maxno(cma), BITS_PER_BYTE * sizeof(u32)); - debugfs_create_u32_array("bitmap", 0444, tmp, (u32 *)cma->bitmap, u32s); + cma->dfs_bitmap.array = (u32 *)cma->bitmap; + cma->dfs_bitmap.n_elements = DIV_ROUND_UP(cma_bitmap_maxno(cma), + BITS_PER_BYTE * sizeof(u32)); + debugfs_create_u32_array("bitmap", 0444, tmp, &cma->dfs_bitmap); } static int __init cma_debugfs_init(void) diff --git a/mm/compaction.c b/mm/compaction.c index fd988b7e5f2b..86375605faa9 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2316,15 +2316,26 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .page = NULL, }; - current->capture_control = &capc; + /* + * Make sure the structs are really initialized before we expose the + * capture control, in case we are interrupted and the interrupt handler + * frees a page. + */ + barrier(); + WRITE_ONCE(current->capture_control, &capc); ret = compact_zone(&cc, &capc); VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); - *capture = capc.page; - current->capture_control = NULL; + /* + * Make sure we hide capture control first before we read the captured + * page pointer, otherwise an interrupt could free and capture a page + * and we would leak it. + */ + WRITE_ONCE(current->capture_control, NULL); + *capture = READ_ONCE(capc.page); return ret; } diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index e45623016aea..61ab16fb2e36 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -246,13 +246,13 @@ static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp, static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep, unsigned long vaddr) { - pte_t pte = READ_ONCE(*ptep); + pte_t pte = ptep_get(ptep); pte = __pte(pte_val(pte) | RANDOM_ORVALUE); set_pte_at(mm, vaddr, ptep, pte); barrier(); pte_clear(mm, vaddr, ptep); - pte = READ_ONCE(*ptep); + pte = ptep_get(ptep); WARN_ON(!pte_none(pte)); } diff --git a/mm/filemap.c b/mm/filemap.c index f0ae9a6308cb..385759c4ce4b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2028,7 +2028,7 @@ find_page: page = find_get_page(mapping, index); if (!page) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto would_block; page_cache_sync_readahead(mapping, ra, filp, @@ -2038,6 +2038,10 @@ find_page: goto no_cached_page; } if (PageReadahead(page)) { + if (iocb->ki_flags & IOCB_NOIO) { + put_page(page); + goto out; + } page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); @@ -2160,6 +2164,11 @@ page_not_up_to_date_locked: } readpage: + if (iocb->ki_flags & IOCB_NOIO) { + unlock_page(page); + put_page(page); + goto would_block; + } /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. @@ -2249,9 +2258,19 @@ EXPORT_SYMBOL_GPL(generic_file_buffered_read); * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. + * + * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall + * be returned when no data can be read without waiting for I/O requests + * to complete; it doesn't prevent readahead. + * + * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O + * requests shall be made for the read or for readahead. When no data + * can be read, -EAGAIN shall be returned. When readahead would be + * triggered, a partial, possibly empty read shall be returned. + * * Return: * * number of bytes copied, even for partial reads - * * negative error code if nothing was read + * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 57ece74e3aae..fab4485b9e52 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1593,7 +1593,7 @@ static struct address_space *_get_hugetlb_page_mapping(struct page *hpage) /* Use first found vma */ pgoff_start = page_to_pgoff(hpage); - pgoff_end = pgoff_start + hpage_nr_pages(hpage) - 1; + pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0b38b6ad547d..19622328e4b5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2772,8 +2772,10 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, return; cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN); - if (!cw) + if (!cw) { + css_put(&memcg->css); return; + } cw->memcg = memcg; cw->cachep = cachep; @@ -6360,11 +6362,16 @@ static unsigned long effective_protection(unsigned long usage, * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. + * + * Check both usage and parent_usage against the respective + * protected values. One should imply the other, but they + * aren't read atomically - make sure the division is sane. */ if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)) return ep; - - if (parent_effective > siblings_protected && usage > protected) { + if (parent_effective > siblings_protected && + parent_usage > siblings_protected && + usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; @@ -6416,7 +6423,7 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, if (parent == root) { memcg->memory.emin = READ_ONCE(memcg->memory.min); - memcg->memory.elow = memcg->memory.low; + memcg->memory.elow = READ_ONCE(memcg->memory.low); goto out; } @@ -6428,7 +6435,8 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_min_usage))); WRITE_ONCE(memcg->memory.elow, effective_protection(usage, parent_usage, - memcg->memory.low, READ_ONCE(parent->memory.elow), + READ_ONCE(memcg->memory.low), + READ_ONCE(parent->memory.elow), atomic_long_read(&parent->memory.children_low_usage))); out: diff --git a/mm/memory.c b/mm/memory.c index dc7f3543b1fd..87ec87cdc1ff 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1498,7 +1498,7 @@ out: } #ifdef pte_index -static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd, +static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; @@ -1506,8 +1506,9 @@ static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd, if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); - return err ? err : insert_page_into_pte_locked( - mm, pte_offset_map(pmd, addr), addr, page, prot); + if (err) + return err; + return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations @@ -1517,7 +1518,8 @@ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; - spinlock_t *pte_lock = NULL; + pte_t *start_pte, *pte; + spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; @@ -1536,18 +1538,17 @@ more: ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; - pte_lock = pte_lockptr(mm, pmd); while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); - spin_lock(pte_lock); - for (; pte_idx < batch_size; ++pte_idx) { - int err = insert_page_in_batch_locked(mm, pmd, + start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); + for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { + int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { - spin_unlock(pte_lock); + pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; @@ -1555,7 +1556,7 @@ more: addr += PAGE_SIZE; ++curr_page_idx; } - spin_unlock(pte_lock); + pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } @@ -3140,8 +3141,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); - if (err) + if (err) { + ret = VM_FAULT_OOM; goto out_page; + } + + /* + * XXX: Move to lru_cache_add() when it + * supports new vs putback + */ + spin_lock_irq(&page_pgdat(page)->lru_lock); + lru_note_cost_page(page); + spin_unlock_irq(&page_pgdat(page)->lru_lock); lru_cache_add(page); swap_readpage(page, true); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9b34e03e730a..da374cd3d45b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -471,11 +471,20 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { + const unsigned long end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; - unsigned long flags; + unsigned long pfn, cur_nr_pages, flags; /* Poison struct pages because they are now uninitialized again. */ - page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); + for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { + cond_resched(); + + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = + min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); + page_init_poison(pfn_to_page(pfn), + sizeof(struct page) * cur_nr_pages); + } #ifdef CONFIG_ZONE_DEVICE /* diff --git a/mm/migrate.c b/mm/migrate.c index f37729673558..40cd7016ae6f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1161,21 +1161,10 @@ out: } /* - * gcc 4.7 and 4.8 on arm get an ICEs when inlining unmap_and_move(). Work - * around it. - */ -#if defined(CONFIG_ARM) && \ - defined(GCC_VERSION) && GCC_VERSION < 40900 && GCC_VERSION >= 40700 -#define ICE_noinline noinline -#else -#define ICE_noinline -#endif - -/* * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static ICE_noinline int unmap_and_move(new_page_t get_new_page, +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, unsigned long private, struct page *page, int force, enum migrate_mode mode, diff --git a/mm/nommu.c b/mm/nommu.c index cdcad5d61dd1..f32a69095d50 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -291,23 +291,6 @@ void *vzalloc_node(unsigned long size, int node) EXPORT_SYMBOL(vzalloc_node); /** - * vmalloc_exec - allocate virtually contiguous, executable memory - * @size: allocation size - * - * Kernel-internal function to allocate enough pages to cover @size - * the page level allocator and map them into contiguous and - * executable kernel virtual space. - * - * For tight control over page level allocator and protection flags - * use __vmalloc() instead. - */ - -void *vmalloc_exec(unsigned long size) -{ - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); -} - -/** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 48eb0f1410d4..e028b87ce294 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7832,7 +7832,7 @@ void setup_per_zone_wmarks(void) * Initialise min_free_kbytes. * * For small machines we want it small (128k min). For large machines - * we want it large (64MB max). But it is not linear, because network + * we want it large (256MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: diff --git a/mm/slab.h b/mm/slab.h index 207c83ef6e06..74f7e09a7cfd 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -348,7 +348,7 @@ static __always_inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, struct kmem_cache *s) { - unsigned int nr_pages = 1 << order; + int nr_pages = 1 << order; struct mem_cgroup *memcg; struct lruvec *lruvec; int ret; @@ -388,7 +388,7 @@ out: static __always_inline void memcg_uncharge_slab(struct page *page, int order, struct kmem_cache *s) { - unsigned int nr_pages = 1 << order; + int nr_pages = 1 << order; struct mem_cgroup *memcg; struct lruvec *lruvec; diff --git a/mm/slab_common.c b/mm/slab_common.c index 9e72ba224175..37d48a56431d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1726,7 +1726,7 @@ void kzfree(const void *p) if (unlikely(ZERO_OR_NULL_PTR(mem))) return; ks = ksize(mem); - memset(mem, 0, ks); + memzero_explicit(mem, ks); kfree(mem); } EXPORT_SYMBOL(kzfree); diff --git a/mm/slub.c b/mm/slub.c index fe81773fd97e..ef303070d175 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3766,15 +3766,13 @@ error: } static void list_slab_objects(struct kmem_cache *s, struct page *page, - const char *text, unsigned long *map) + const char *text) { #ifdef CONFIG_SLUB_DEBUG void *addr = page_address(page); + unsigned long *map; void *p; - if (!map) - return; - slab_err(s, page, text, s->name); slab_lock(page); @@ -3786,6 +3784,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, print_tracking(s, p); } } + put_map(map); slab_unlock(page); #endif } @@ -3799,11 +3798,6 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { LIST_HEAD(discard); struct page *page, *h; - unsigned long *map = NULL; - -#ifdef CONFIG_SLUB_DEBUG - map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL); -#endif BUG_ON(irqs_disabled()); spin_lock_irq(&n->list_lock); @@ -3813,16 +3807,11 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_add(&page->slab_list, &discard); } else { list_slab_objects(s, page, - "Objects remaining in %s on __kmem_cache_shutdown()", - map); + "Objects remaining in %s on __kmem_cache_shutdown()"); } } spin_unlock_irq(&n->list_lock); -#ifdef CONFIG_SLUB_DEBUG - bitmap_free(map); -#endif - list_for_each_entry_safe(page, h, &discard, slab_list) discard_slab(s, page); } diff --git a/mm/swap.c b/mm/swap.c index dbcab84c6fce..a82efc33411f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -443,8 +443,7 @@ void mark_page_accessed(struct page *page) else __lru_cache_activate_page(page); ClearPageReferenced(page); - if (page_is_file_lru(page)) - workingset_activation(page); + workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); diff --git a/mm/swap_state.c b/mm/swap_state.c index e98ff460e9e9..05889e8e3c97 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -21,7 +21,7 @@ #include <linux/vmalloc.h> #include <linux/swap_slots.h> #include <linux/huge_mm.h> - +#include "internal.h" /* * swapper_space is a fiction, retained to simplify the path through @@ -429,7 +429,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, __SetPageSwapBacked(page); /* May fail (-ENOMEM) if XArray node allocation failed. */ - if (add_to_swap_cache(page, entry, gfp_mask & GFP_KERNEL)) { + if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK)) { put_swap_page(page, entry); goto fail_unlock; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3091c2ca60df..5a2b55c8dd9a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1862,7 +1862,6 @@ EXPORT_SYMBOL(vm_unmap_ram); * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node - * @prot: memory protection to use. PAGE_KERNEL for regular RAM * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life @@ -2696,26 +2695,6 @@ void *vzalloc_node(unsigned long size, int node) } EXPORT_SYMBOL(vzalloc_node); -/** - * vmalloc_exec - allocate virtually contiguous, executable memory - * @size: allocation size - * - * Kernel-internal function to allocate enough pages to cover @size - * the page level allocator and map them into contiguous and - * executable kernel virtual space. - * - * For tight control over page level allocator and protection flags - * use __vmalloc() instead. - * - * Return: pointer to the allocated memory or %NULL on error - */ -void *vmalloc_exec(unsigned long size) -{ - return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, - NUMA_NO_NODE, __builtin_return_address(0)); -} - #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) diff --git a/mm/vmscan.c b/mm/vmscan.c index b6d84326bdf2..749d239c62b2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -904,6 +904,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, __delete_from_swap_cache(page, swap); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); + workingset_eviction(page, target_memcg); } else { void (*freepage)(struct page *); void *shadow = NULL; @@ -1884,6 +1885,8 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, list_add(&page->lru, &pages_to_free); } else { nr_moved += nr_pages; + if (PageActive(page)) + workingset_age_nonresident(lruvec, nr_pages); } } diff --git a/mm/workingset.c b/mm/workingset.c index d481ea452eeb..50b7937bab32 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -156,8 +156,8 @@ * * Implementation * - * For each node's file LRU lists, a counter for inactive evictions - * and activations is maintained (node->inactive_age). + * For each node's LRU lists, a counter for inactive evictions and + * activations is maintained (node->nonresident_age). * * On eviction, a snapshot of this counter (along with some bits to * identify the node) is stored in the now empty page cache @@ -213,7 +213,17 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *workingsetp = workingset; } -static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) +/** + * workingset_age_nonresident - age non-resident entries as LRU ages + * @memcg: the lruvec that was aged + * @nr_pages: the number of pages to count + * + * As in-memory pages are aged, non-resident pages need to be aged as + * well, in order for the refault distances later on to be comparable + * to the in-memory dimensions. This function allows reclaim and LRU + * operations to drive the non-resident aging along in parallel. + */ +void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) { /* * Reclaiming a cgroup means reclaiming all its children in a @@ -227,11 +237,8 @@ static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) * the root cgroup's, age as well. */ do { - struct lruvec *lruvec; - - lruvec = mem_cgroup_lruvec(memcg, pgdat); - atomic_long_inc(&lruvec->inactive_age); - } while (memcg && (memcg = parent_mem_cgroup(memcg))); + atomic_long_add(nr_pages, &lruvec->nonresident_age); + } while ((lruvec = parent_lruvec(lruvec))); } /** @@ -254,12 +261,11 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - advance_inactive_age(page_memcg(page), pgdat); - lruvec = mem_cgroup_lruvec(target_memcg, pgdat); + workingset_age_nonresident(lruvec, hpage_nr_pages(page)); /* XXX: target_memcg can be NULL, go through lruvec */ memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); - eviction = atomic_long_read(&lruvec->inactive_age); + eviction = atomic_long_read(&lruvec->nonresident_age); return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } @@ -309,20 +315,20 @@ void workingset_refault(struct page *page, void *shadow) if (!mem_cgroup_disabled() && !eviction_memcg) goto out; eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); - refault = atomic_long_read(&eviction_lruvec->inactive_age); + refault = atomic_long_read(&eviction_lruvec->nonresident_age); /* * Calculate the refault distance * * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. There is a + * across nonresident_age overflows in most cases. There is a * special case: usually, shadow entries have a short lifetime * and are either refaulted or reclaimed along with the inode * before they get too old. But it is not impossible for the - * inactive_age to lap a shadow entry in the field, which can - * then result in a false small refault distance, leading to a - * false activation should this old entry actually refault - * again. However, earlier kernels used to deactivate + * nonresident_age to lap a shadow entry in the field, which + * can then result in a false small refault distance, leading + * to a false activation should this old entry actually + * refault again. However, earlier kernels used to deactivate * unconditionally with *every* reclaim invocation for the * longest time, so the occasional inappropriate activation * leading to pressure on the active list is not a problem. @@ -359,7 +365,7 @@ void workingset_refault(struct page *page, void *shadow) goto out; SetPageActive(page); - advance_inactive_age(memcg, pgdat); + workingset_age_nonresident(lruvec, hpage_nr_pages(page)); inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); /* Page was active prior to eviction */ @@ -382,6 +388,7 @@ out: void workingset_activation(struct page *page) { struct mem_cgroup *memcg; + struct lruvec *lruvec; rcu_read_lock(); /* @@ -394,7 +401,8 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - advance_inactive_age(memcg, page_pgdat(page)); + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + workingset_age_nonresident(lruvec, hpage_nr_pages(page)); out: rcu_read_unlock(); } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index c8d6a07e23c5..3dd7c972677b 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -503,11 +503,10 @@ static void vlan_dev_set_lockdep_one(struct net_device *dev, lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key); } -static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) +static void vlan_dev_set_lockdep_class(struct net_device *dev) { - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &vlan_netdev_addr_lock_key, - subclass); + lockdep_set_class(&dev->addr_list_lock, + &vlan_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL); } @@ -601,7 +600,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev, dev->lower_level); + vlan_dev_set_lockdep_class(dev); vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) diff --git a/net/9p/client.c b/net/9p/client.c index fc1f3635e5dd..09f1ec589b80 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -811,7 +811,7 @@ reterr: * @uodata: source for zero copy write * @inlen: read buffer size * @olen: write buffer size - * @hdrlen: reader header size, This is the size of response protocol data + * @in_hdrlen: reader header size, This is the size of response protocol data * @fmt: protocol format string (see protocol.c) * * Returns request structure (which client must free using p9_tag_remove) diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index b21c3c209815..2885ff9c76f0 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -94,14 +94,15 @@ struct p9_trans_rdma { struct completion cm_done; }; +struct p9_rdma_req; + /** - * p9_rdma_context - Keeps track of in-process WR + * struct p9_rdma_context - Keeps track of in-process WR * * @busa: Bus address to unmap when the WR completes * @req: Keeps track of requests (send) * @rc: Keepts track of replies (receive) */ -struct p9_rdma_req; struct p9_rdma_context { struct ib_cqe cqe; dma_addr_t busa; @@ -112,7 +113,7 @@ struct p9_rdma_context { }; /** - * p9_rdma_opts - Collection of mount options + * struct p9_rdma_opts - Collection of mount options * @port: port of connection * @sq_depth: The requested depth of the SQ. This really doesn't need * to be any deeper than the number of threads used in the client diff --git a/net/Kconfig b/net/Kconfig index d1672280d6a4..3831206977a1 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -455,7 +455,6 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" default y - depends on PHYLIB=y || PHYLIB=n help An alternative userspace interface for ethtool based on generic netlink. It provides better extensibility and some new features, diff --git a/net/ax25/Kconfig b/net/ax25/Kconfig index 97d686d115c0..d3a9843a043d 100644 --- a/net/ax25/Kconfig +++ b/net/ax25/Kconfig @@ -8,7 +8,7 @@ menuconfig HAMRADIO bool "Amateur Radio support" help If you want to connect your Linux box to an amateur radio, answer Y - here. You want to read <http://www.tapr.org/> + here. You want to read <https://www.tapr.org/> and more specifically about AX.25 on Linux <http://www.linux-ax25.org/>. @@ -39,11 +39,11 @@ config AX25 Information about where to get supporting software for Linux amateur radio as well as information about how to configure an AX.25 port is contained in the AX25-HOWTO, available from - <http://www.tldp.org/docs.html#howto>. You might also want to + <https://www.tldp.org/docs.html#howto>. You might also want to check out the file <file:Documentation/networking/ax25.rst> in the kernel source. More information about digital amateur radio in general is on the WWW at - <http://www.tapr.org/>. + <https://www.tapr.org/>. To compile this driver as a module, choose M here: the module will be called ax25. @@ -90,7 +90,7 @@ config NETROM <http://www.linux-ax25.org>. You also might want to check out the file <file:Documentation/networking/ax25.rst>. More information about digital amateur radio in general is on the WWW at - <http://www.tapr.org/>. + <https://www.tapr.org/>. To compile this driver as a module, choose M here: the module will be called netrom. @@ -109,7 +109,7 @@ config ROSE <http://www.linux-ax25.org>. You also might want to check out the file <file:Documentation/networking/ax25.rst>. More information about digital amateur radio in general is on the WWW at - <http://www.tapr.org/>. + <https://www.tapr.org/>. To compile this driver as a module, choose M here: the module will be called rose. diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index bfd4ccd80847..b03c469cd01f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -147,6 +147,20 @@ int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f) return a + (long)b + c + d + (long)e + f; } +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg) +{ + return (long)arg; +} + +int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) +{ + return (long)arg->a; +} + int noinline bpf_modify_return_test(int a, int *b) { *b += 1; @@ -185,6 +199,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { + struct bpf_fentry_test_t arg = {}; u16 side_effect = 0, ret = 0; int b = 2, err = -EFAULT; u32 retval = 0; @@ -197,7 +212,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, bpf_fentry_test3(4, 5, 6) != 15 || bpf_fentry_test4((void *)7, 8, 9, 10) != 34 || bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || - bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) + bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 || + bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 || + bpf_fentry_test8(&arg) != 0) goto out; break; case BPF_MODIFY_RETURN: diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index c0f0990f30b6..1905e01c3aa9 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -50,7 +50,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, req.len = optlen; if (!bpfilter_ops.info.pid) goto out; - n = __kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req), + n = kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req), &pos); if (n != sizeof(req)) { pr_err("write fail %zd\n", n); diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 779e1eb75443..90592af9db61 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -86,7 +86,7 @@ static struct sk_buff *br_mrp_skb_alloc(struct net_bridge_port *p, { struct ethhdr *eth_hdr; struct sk_buff *skb; - u16 *version; + __be16 *version; skb = dev_alloc_skb(MRP_MAX_FRAME_LENGTH); if (!skb) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 83490bf73a13..4c4a93abde68 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1007,7 +1007,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); if (skb_transport_offset(skb) + ipv6_transport_len(skb) < - nsrcs_offset + sizeof(_nsrcs)) + nsrcs_offset + sizeof(__nsrcs)) return -EINVAL; _nsrcs = skb_header_pointer(skb, nsrcs_offset, diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 162998e2f039..8914290c75d4 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -250,6 +250,36 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr, return 0; } +/* send a notification if v_curr can't enter the range and start a new one */ +static void __vlan_tunnel_handle_range(const struct net_bridge_port *p, + struct net_bridge_vlan **v_start, + struct net_bridge_vlan **v_end, + int v_curr, bool curr_change) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + + vg = nbp_vlan_group(p); + if (!vg) + return; + + v = br_vlan_find(vg, v_curr); + + if (!*v_start) + goto out_init; + + if (v && curr_change && br_vlan_can_enter_range(v, *v_end)) { + *v_end = v; + return; + } + + br_vlan_notify(p->br, p, (*v_start)->vid, (*v_end)->vid, RTM_NEWVLAN); +out_init: + /* we start a range only if there are any changes to notify about */ + *v_start = curr_change ? v : NULL; + *v_end = *v_start; +} + int br_process_vlan_tunnel_info(const struct net_bridge *br, const struct net_bridge_port *p, int cmd, struct vtunnel_info *tinfo_curr, @@ -263,6 +293,7 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, return -EINVAL; memcpy(tinfo_last, tinfo_curr, sizeof(struct vtunnel_info)); } else if (tinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END) { + struct net_bridge_vlan *v_start = NULL, *v_end = NULL; int t, v; if (!(tinfo_last->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN)) @@ -272,11 +303,24 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, return -EINVAL; t = tinfo_last->tunid; for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) { - err = br_vlan_tunnel_info(p, cmd, v, t, changed); + bool curr_change = false; + + err = br_vlan_tunnel_info(p, cmd, v, t, &curr_change); if (err) - return err; + break; t++; + + if (curr_change) + *changed = curr_change; + __vlan_tunnel_handle_range(p, &v_start, &v_end, v, + curr_change); } + if (v_start && v_end) + br_vlan_notify(br, p, v_start->vid, v_end->vid, + RTM_NEWVLAN); + if (err) + return err; + memset(tinfo_last, 0, sizeof(struct vtunnel_info)); memset(tinfo_curr, 0, sizeof(struct vtunnel_info)); } else { @@ -286,6 +330,7 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, tinfo_curr->tunid, changed); if (err) return err; + br_vlan_notify(br, p, tinfo_curr->vid, 0, RTM_NEWVLAN); memset(tinfo_last, 0, sizeof(struct vtunnel_info)); memset(tinfo_curr, 0, sizeof(struct vtunnel_info)); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 65d2c163a24a..baa1500f384f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -434,7 +434,7 @@ struct net_bridge { struct hlist_head fdb_list; #if IS_ENABLED(CONFIG_BRIDGE_MRP) - struct list_head __rcu mrp_list; + struct list_head mrp_list; #endif }; @@ -1200,6 +1200,12 @@ static inline void br_vlan_notify(const struct net_bridge *br, int cmd) { } + +static inline bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *range_end) +{ + return true; +} #endif /* br_vlan_options.c */ diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 33b255e38ffe..315eb37d89f0 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -8,7 +8,7 @@ struct br_mrp { /* list of mrp instances */ - struct list_head __rcu list; + struct list_head list; struct net_bridge_port __rcu *p_port; struct net_bridge_port __rcu *s_port; diff --git a/net/can/af_can.c b/net/can/af_can.c index 128d37a4c2e0..5c06404bdf3e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -410,6 +410,7 @@ static struct hlist_head *can_rcv_list_find(canid_t *can_id, canid_t *mask, /** * can_rx_register - subscribe CAN frames from a specific interface + * @net: the applicable net namespace * @dev: pointer to netdevice (NULL => subcribe from 'all' CAN devices list) * @can_id: CAN identifier (see description) * @mask: CAN mask (see description) @@ -498,6 +499,7 @@ static void can_rx_delete_receiver(struct rcu_head *rp) /** * can_rx_unregister - unsubscribe CAN frames from a specific interface + * @net: the applicable net namespace * @dev: pointer to netdevice (NULL => unsubscribe from 'all' CAN devices list) * @can_id: CAN identifier * @mask: CAN mask diff --git a/net/core/dev.c b/net/core/dev.c index c02bae927812..b61075828358 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5591,7 +5591,7 @@ void netif_receive_skb_list(struct list_head *head) } EXPORT_SYMBOL(netif_receive_skb_list); -DEFINE_PER_CPU(struct work_struct, flush_works); +static DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) @@ -7908,6 +7908,7 @@ EXPORT_SYMBOL(netdev_bonding_info_change); /** * netdev_get_xmit_slave - Get the xmit slave of master device + * @dev: device * @skb: The packet * @all_slaves: assume all the slaves are active * diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6393ba930097..54cd568e7c2f 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -690,6 +690,15 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return; + /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two + * reasons: + * 1) This is always called without any addr_list_lock, so as the + * outermost one here, it must be 0. + * 2) This is called by some callers after unlinking the upper device, + * so the dev->lower_level becomes 1 again. + * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or + * larger. + */ netif_addr_lock_bh(from); netif_addr_lock_nested(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); @@ -911,6 +920,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return; + /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock_nested(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); diff --git a/net/core/devlink.c b/net/core/devlink.c index 6ae36808c152..6335e1851088 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -386,19 +386,21 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) -#define DEVLINK_NL_FLAG_NEED_PORT BIT(1) -#define DEVLINK_NL_FLAG_NEED_SB BIT(2) +#define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) +#define DEVLINK_NL_FLAG_NEED_PORT BIT(1) +#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(2) +#define DEVLINK_NL_FLAG_NEED_SB BIT(3) /* The per devlink instance lock is taken by default in the pre-doit * operation, yet several commands do not require this. The global * devlink lock is taken and protects from disruption by user-calls. */ -#define DEVLINK_NL_FLAG_NO_LOCK BIT(3) +#define DEVLINK_NL_FLAG_NO_LOCK BIT(4) static int devlink_nl_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { + struct devlink_port *devlink_port; struct devlink *devlink; int err; @@ -413,14 +415,17 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { info->user_ptr[0] = devlink; } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { - struct devlink_port *devlink_port; - devlink_port = devlink_port_get_from_info(devlink, info); if (IS_ERR(devlink_port)) { err = PTR_ERR(devlink_port); goto unlock; } info->user_ptr[0] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) { + info->user_ptr[0] = devlink; + devlink_port = devlink_port_get_from_info(devlink, info); + if (!IS_ERR(devlink_port)) + info->user_ptr[1] = devlink_port; } if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_SB) { struct devlink_sb *devlink_sb; @@ -528,8 +533,14 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, { struct devlink_port_attrs *attrs = &devlink_port->attrs; - if (!attrs->set) + if (!devlink_port->attrs_set) return 0; + if (attrs->lanes) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes)) + return -EMSGSIZE; + } + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable)) + return -EMSGSIZE; if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) return -EMSGSIZE; switch (devlink_port->attrs.flavour) { @@ -934,6 +945,7 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port; u32 port_index; u32 count; @@ -941,8 +953,27 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]) return -EINVAL; + devlink_port = devlink_port_get_from_info(devlink, info); port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); + + if (IS_ERR(devlink_port)) + return -EINVAL; + + if (!devlink_port->attrs.splittable) { + /* Split ports cannot be split. */ + if (devlink_port->attrs.split) + NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split further"); + else + NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split"); + return -EINVAL; + } + + if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid split count"); + return -EINVAL; + } + return devlink_port_split(devlink, port_index, count, info->extack); } @@ -5261,6 +5292,7 @@ struct devlink_health_reporter { void *priv; const struct devlink_health_reporter_ops *ops; struct devlink *devlink; + struct devlink_port *devlink_port; struct devlink_fmsg *dump_fmsg; struct mutex dump_lock; /* lock parallel read/write from dump buffers */ u64 graceful_period; @@ -5283,18 +5315,98 @@ devlink_health_reporter_priv(struct devlink_health_reporter *reporter) EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); static struct devlink_health_reporter * -devlink_health_reporter_find_by_name(struct devlink *devlink, - const char *reporter_name) +__devlink_health_reporter_find_by_name(struct list_head *reporter_list, + struct mutex *list_lock, + const char *reporter_name) { struct devlink_health_reporter *reporter; - lockdep_assert_held(&devlink->reporters_lock); - list_for_each_entry(reporter, &devlink->reporter_list, list) + lockdep_assert_held(list_lock); + list_for_each_entry(reporter, reporter_list, list) if (!strcmp(reporter->ops->name, reporter_name)) return reporter; return NULL; } +static struct devlink_health_reporter * +devlink_health_reporter_find_by_name(struct devlink *devlink, + const char *reporter_name) +{ + return __devlink_health_reporter_find_by_name(&devlink->reporter_list, + &devlink->reporters_lock, + reporter_name); +} + +static struct devlink_health_reporter * +devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port, + const char *reporter_name) +{ + return __devlink_health_reporter_find_by_name(&devlink_port->reporter_list, + &devlink_port->reporters_lock, + reporter_name); +} + +static struct devlink_health_reporter * +__devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + + if (WARN_ON(graceful_period && !ops->recover)) + return ERR_PTR(-EINVAL); + + reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); + if (!reporter) + return ERR_PTR(-ENOMEM); + + reporter->priv = priv; + reporter->ops = ops; + reporter->devlink = devlink; + reporter->graceful_period = graceful_period; + reporter->auto_recover = !!ops->recover; + reporter->auto_dump = !!ops->dump; + mutex_init(&reporter->dump_lock); + refcount_set(&reporter->refcount, 1); + return reporter; +} + +/** + * devlink_port_health_reporter_create - create devlink health reporter for + * specified port instance + * + * @port: devlink_port which should contain the new reporter + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_port_health_reporter_create(struct devlink_port *port, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&port->reporters_lock); + if (__devlink_health_reporter_find_by_name(&port->reporter_list, + &port->reporters_lock, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + reporter = __devlink_health_reporter_create(port->devlink, ops, + graceful_period, priv); + if (IS_ERR(reporter)) + goto unlock; + + reporter->devlink_port = port; + list_add_tail(&reporter->list, &port->reporter_list); +unlock: + mutex_unlock(&port->reporters_lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create); + /** * devlink_health_reporter_create - create devlink health reporter * @@ -5316,25 +5428,11 @@ devlink_health_reporter_create(struct devlink *devlink, goto unlock; } - if (WARN_ON(graceful_period && !ops->recover)) { - reporter = ERR_PTR(-EINVAL); + reporter = __devlink_health_reporter_create(devlink, ops, + graceful_period, priv); + if (IS_ERR(reporter)) goto unlock; - } - - reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); - if (!reporter) { - reporter = ERR_PTR(-ENOMEM); - goto unlock; - } - reporter->priv = priv; - reporter->ops = ops; - reporter->devlink = devlink; - reporter->graceful_period = graceful_period; - reporter->auto_recover = !!ops->recover; - reporter->auto_dump = !!ops->dump; - mutex_init(&reporter->dump_lock); - refcount_set(&reporter->refcount, 1); list_add_tail(&reporter->list, &devlink->reporter_list); unlock: mutex_unlock(&devlink->reporters_lock); @@ -5342,6 +5440,29 @@ unlock: } EXPORT_SYMBOL_GPL(devlink_health_reporter_create); +static void +devlink_health_reporter_free(struct devlink_health_reporter *reporter) +{ + mutex_destroy(&reporter->dump_lock); + if (reporter->dump_fmsg) + devlink_fmsg_free(reporter->dump_fmsg); + kfree(reporter); +} + +static void +devlink_health_reporter_put(struct devlink_health_reporter *reporter) +{ + if (refcount_dec_and_test(&reporter->refcount)) + devlink_health_reporter_free(reporter); +} + +static void +__devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + list_del(&reporter->list); + devlink_health_reporter_put(reporter); +} + /** * devlink_health_reporter_destroy - destroy devlink health reporter * @@ -5350,18 +5471,30 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_create); void devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) { - mutex_lock(&reporter->devlink->reporters_lock); - list_del(&reporter->list); - mutex_unlock(&reporter->devlink->reporters_lock); - while (refcount_read(&reporter->refcount) > 1) - msleep(100); - mutex_destroy(&reporter->dump_lock); - if (reporter->dump_fmsg) - devlink_fmsg_free(reporter->dump_fmsg); - kfree(reporter); + struct mutex *lock = &reporter->devlink->reporters_lock; + + mutex_lock(lock); + __devlink_health_reporter_destroy(reporter); + mutex_unlock(lock); } EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); +/** + * devlink_port_health_reporter_destroy - destroy devlink port health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_port_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + struct mutex *lock = &reporter->devlink_port->reporters_lock; + + mutex_lock(lock); + __devlink_health_reporter_destroy(reporter); + mutex_unlock(lock); +} +EXPORT_SYMBOL_GPL(devlink_port_health_reporter_destroy); + static int devlink_nl_health_reporter_fill(struct sk_buff *msg, struct devlink *devlink, @@ -5379,6 +5512,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg, if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; + if (reporter->devlink_port) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, reporter->devlink_port->index)) + goto genlmsg_cancel; + } reporter_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_HEALTH_REPORTER); if (!reporter_attr) @@ -5586,17 +5723,28 @@ devlink_health_reporter_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { struct devlink_health_reporter *reporter; + struct devlink_port *devlink_port; char *reporter_name; if (!attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) return NULL; reporter_name = nla_data(attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); - mutex_lock(&devlink->reporters_lock); - reporter = devlink_health_reporter_find_by_name(devlink, reporter_name); - if (reporter) - refcount_inc(&reporter->refcount); - mutex_unlock(&devlink->reporters_lock); + devlink_port = devlink_port_get_from_attrs(devlink, attrs); + if (IS_ERR(devlink_port)) { + mutex_lock(&devlink->reporters_lock); + reporter = devlink_health_reporter_find_by_name(devlink, reporter_name); + if (reporter) + refcount_inc(&reporter->refcount); + mutex_unlock(&devlink->reporters_lock); + } else { + mutex_lock(&devlink_port->reporters_lock); + reporter = devlink_port_health_reporter_find_by_name(devlink_port, reporter_name); + if (reporter) + refcount_inc(&reporter->refcount); + mutex_unlock(&devlink_port->reporters_lock); + } + return reporter; } @@ -5628,12 +5776,6 @@ unlock: return NULL; } -static void -devlink_health_reporter_put(struct devlink_health_reporter *reporter) -{ - refcount_dec(&reporter->refcount); -} - void devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, enum devlink_health_reporter_state state) @@ -5690,6 +5832,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink_health_reporter *reporter; + struct devlink_port *port; struct devlink *devlink; int start = cb->args[0]; int idx = 0; @@ -5720,6 +5863,31 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, } mutex_unlock(&devlink->reporters_lock); } + + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + list_for_each_entry(port, &devlink->port_list, list) { + mutex_lock(&port->reporters_lock); + list_for_each_entry(reporter, &port->reporter_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill(msg, devlink, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&port->reporters_lock); + goto out; + } + idx++; + } + mutex_unlock(&port->reporters_lock); + } + } out: mutex_unlock(&devlink_mutex); @@ -7099,7 +7267,7 @@ static const struct genl_ops devlink_nl_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_get_doit, .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | DEVLINK_NL_FLAG_NO_LOCK, /* can be retrieved by unprivileged users */ }, @@ -7108,7 +7276,7 @@ static const struct genl_ops devlink_nl_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_set_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | DEVLINK_NL_FLAG_NO_LOCK, }, { @@ -7116,7 +7284,7 @@ static const struct genl_ops devlink_nl_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_recover_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | DEVLINK_NL_FLAG_NO_LOCK, }, { @@ -7124,7 +7292,7 @@ static const struct genl_ops devlink_nl_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_diagnose_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | DEVLINK_NL_FLAG_NO_LOCK, }, { @@ -7133,7 +7301,7 @@ static const struct genl_ops devlink_nl_ops[] = { GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | DEVLINK_NL_FLAG_NO_LOCK, }, { @@ -7141,7 +7309,7 @@ static const struct genl_ops devlink_nl_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | DEVLINK_NL_FLAG_NO_LOCK, }, { @@ -7401,6 +7569,8 @@ int devlink_port_register(struct devlink *devlink, list_add_tail(&devlink_port->list, &devlink->port_list); INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); + INIT_LIST_HEAD(&devlink_port->reporter_list); + mutex_init(&devlink_port->reporters_lock); INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); @@ -7417,6 +7587,8 @@ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; + WARN_ON(!list_empty(&devlink_port->reporter_list)); + mutex_destroy(&devlink_port->reporters_lock); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink->lock); @@ -7510,24 +7682,20 @@ void devlink_port_type_clear(struct devlink_port *devlink_port) EXPORT_SYMBOL_GPL(devlink_port_type_clear); static int __devlink_port_attrs_set(struct devlink_port *devlink_port, - enum devlink_port_flavour flavour, - const unsigned char *switch_id, - unsigned char switch_id_len) + enum devlink_port_flavour flavour) { struct devlink_port_attrs *attrs = &devlink_port->attrs; if (WARN_ON(devlink_port->registered)) return -EEXIST; - attrs->set = true; + devlink_port->attrs_set = true; attrs->flavour = flavour; - if (switch_id) { - attrs->switch_port = true; - if (WARN_ON(switch_id_len > MAX_PHYS_ITEM_ID_LEN)) - switch_id_len = MAX_PHYS_ITEM_ID_LEN; - memcpy(attrs->switch_id.id, switch_id, switch_id_len); - attrs->switch_id.id_len = switch_id_len; + if (attrs->switch_id.id_len) { + devlink_port->switch_port = true; + if (WARN_ON(attrs->switch_id.id_len > MAX_PHYS_ITEM_ID_LEN)) + attrs->switch_id.id_len = MAX_PHYS_ITEM_ID_LEN; } else { - attrs->switch_port = false; + devlink_port->switch_port = false; } return 0; } @@ -7536,33 +7704,18 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port, * devlink_port_attrs_set - Set port attributes * * @devlink_port: devlink port - * @flavour: flavour of the port - * @port_number: number of the port that is facing user, for example - * the front panel port number - * @split: indicates if this is split port - * @split_subport_number: if the port is split, this is the number - * of subport. - * @switch_id: if the port is part of switch, this is buffer with ID, - * otwerwise this is NULL - * @switch_id_len: length of the switch_id buffer + * @attrs: devlink port attrs */ void devlink_port_attrs_set(struct devlink_port *devlink_port, - enum devlink_port_flavour flavour, - u32 port_number, bool split, - u32 split_subport_number, - const unsigned char *switch_id, - unsigned char switch_id_len) + struct devlink_port_attrs *attrs) { - struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; - ret = __devlink_port_attrs_set(devlink_port, flavour, - switch_id, switch_id_len); + devlink_port->attrs = *attrs; + ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) return; - attrs->split = split; - attrs->phys.port_number = port_number; - attrs->phys.split_subport_number = split_subport_number; + WARN_ON(attrs->splittable && attrs->split); } EXPORT_SYMBOL_GPL(devlink_port_attrs_set); @@ -7571,20 +7724,14 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set); * * @devlink_port: devlink port * @pf: associated PF for the devlink port instance - * @switch_id: if the port is part of switch, this is buffer with ID, - * otherwise this is NULL - * @switch_id_len: length of the switch_id buffer */ -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, - const unsigned char *switch_id, - unsigned char switch_id_len, u16 pf) +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ret = __devlink_port_attrs_set(devlink_port, - DEVLINK_PORT_FLAVOUR_PCI_PF, - switch_id, switch_id_len); + DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) return; @@ -7598,21 +7745,15 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); * @devlink_port: devlink port * @pf: associated PF for the devlink port instance * @vf: associated VF of a PF for the devlink port instance - * @switch_id: if the port is part of switch, this is buffer with ID, - * otherwise this is NULL - * @switch_id_len: length of the switch_id buffer */ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - const unsigned char *switch_id, - unsigned char switch_id_len, u16 pf, u16 vf) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; ret = __devlink_port_attrs_set(devlink_port, - DEVLINK_PORT_FLAVOUR_PCI_VF, - switch_id, switch_id_len); + DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) return; attrs->pci_vf.pf = pf; @@ -7626,7 +7767,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; - if (!attrs->set) + if (!devlink_port->attrs_set) return -EOPNOTSUPP; switch (attrs->flavour) { @@ -9461,7 +9602,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, * any devlink lock as only permanent values are accessed. */ devlink_port = netdev_to_devlink_port(dev); - if (!devlink_port || !devlink_port->attrs.switch_port) + if (!devlink_port || !devlink_port->switch_port) return -EOPNOTSUPP; memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid)); diff --git a/net/core/filter.c b/net/core/filter.c index 4e572441e64a..bdd2382e655d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5894,12 +5894,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; - if (skb->protocol == cpu_to_be16(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); - else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) + break; + case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); - else + break; + default: return 0; + } if (skb_headlen(skb) < iphdr_len) return 0; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d02df0b6d0d9..142a8824f0a8 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -70,10 +70,10 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL -int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) +int flow_dissector_bpf_prog_attach_check(struct net *net, + struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; - struct bpf_prog *attached; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides @@ -86,26 +86,17 @@ int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) for_each_net(ns) { if (ns == &init_net) continue; - if (rcu_access_pointer(ns->bpf.progs[type])) + if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ - if (rcu_access_pointer(init_net.bpf.progs[type])) + if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } - attached = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (attached == prog) - /* The same program cannot be attached twice */ - return -EINVAL; - - rcu_assign_pointer(net->bpf.progs[type], prog); - if (attached) - bpf_prog_put(attached); return 0; } #endif /* CONFIG_BPF_SYSCALL */ @@ -903,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; - struct bpf_prog *attached = NULL; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; @@ -960,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net, WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; + struct bpf_prog_array *run_array; rcu_read_lock(); - attached = rcu_dereference(init_net.bpf.progs[type]); - - if (!attached) - attached = rcu_dereference(net->bpf.progs[type]); + run_array = rcu_dereference(init_net.bpf.run_array[type]); + if (!run_array) + run_array = rcu_dereference(net->bpf.run_array[type]); - if (attached) { + if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, @@ -975,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net, .data_end = data + hlen, }; __be16 n_proto = proto; + struct bpf_prog *prog; if (skb) { ctx.skb = skb; @@ -985,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net, n_proto = skb->protocol; } - ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, + prog = READ_ONCE(run_array->items[0].prog); + ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index b739cfab796e..b8cf6ff5f961 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -429,7 +429,7 @@ EXPORT_SYMBOL(flow_indr_dev_unregister); static void flow_block_indr_init(struct flow_block_cb *flow_block, struct flow_block_offload *bo, - struct net_device *dev, void *data, + struct net_device *dev, struct Qdisc *sch, void *data, void *cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)) { @@ -437,6 +437,7 @@ static void flow_block_indr_init(struct flow_block_cb *flow_block, flow_block->indr.data = data; flow_block->indr.cb_priv = cb_priv; flow_block->indr.dev = dev; + flow_block->indr.sch = sch; flow_block->indr.cleanup = cleanup; } @@ -444,7 +445,8 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv), struct flow_block_offload *bo, - struct net_device *dev, void *data, + struct net_device *dev, + struct Qdisc *sch, void *data, void *indr_cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)) { @@ -454,7 +456,7 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, if (IS_ERR(block_cb)) goto out; - flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup); + flow_block_indr_init(block_cb, bo, dev, sch, data, indr_cb_priv, cleanup); list_add(&block_cb->indr.list, &flow_block_indr_list); out: @@ -462,7 +464,7 @@ out: } EXPORT_SYMBOL(flow_indr_block_cb_alloc); -int flow_indr_dev_setup_offload(struct net_device *dev, +int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)) @@ -471,7 +473,7 @@ int flow_indr_dev_setup_offload(struct net_device *dev, mutex_lock(&flow_indr_block_lock); list_for_each_entry(this, &flow_block_indr_dev_list, list) - this->cb(dev, this->cb_priv, type, bo, data, cleanup); + this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup); mutex_unlock(&flow_indr_block_lock); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 351afbf6bfba..6a32a1fd34f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -683,7 +683,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp) return container_of(parser, struct sk_psock, parser); } -static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb) +static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; @@ -715,12 +715,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb) } } -static void sk_psock_tls_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) { switch (verdict) { case __SK_REDIRECT: - sk_psock_skb_redirect(psock, skb); + sk_psock_skb_redirect(skb); break; case __SK_PASS: case __SK_DROP: @@ -741,8 +740,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } + sk_psock_tls_verdict_apply(skb, ret); rcu_read_unlock(); - sk_psock_tls_verdict_apply(psock, skb, ret); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); @@ -770,7 +769,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, } goto out_free; case __SK_REDIRECT: - sk_psock_skb_redirect(psock, skb); + sk_psock_skb_redirect(skb); break; case __SK_DROP: /* fall-through */ @@ -782,11 +781,18 @@ out_free: static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; + struct sock *sk; rcu_read_lock(); + sk = strp->sk; + psock = sk_psock(sk); + if (unlikely(!psock)) { + kfree_skb(skb); + goto out; + } prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_orphan(skb); @@ -794,8 +800,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } - rcu_read_unlock(); sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); } static int sk_psock_strp_read_done(struct strparser *strp, int err) diff --git a/net/core/sock.c b/net/core/sock.c index f5b5fdd61c88..11d6f77dd562 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1917,7 +1917,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; - cgroup_sk_alloc(&newsk->sk_cgrp_data); + cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -3566,6 +3566,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && + protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 4c1123c749bb..119f52a99dc1 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -70,11 +70,49 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) struct fd f; int ret; + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -1209,27 +1247,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) } int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index f93f8ace6c56..6ada114bbcca 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -274,7 +274,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (jit_enable < 2 || - (jit_enable == 2 && bpf_dump_raw_ok())) { + (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) { *(int *)table->data = jit_enable; if (jit_enable == 2) pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n"); diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index 51ac2631fb48..0c7d2f66ba27 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -5,7 +5,7 @@ menuconfig IP_DCCP help Datagram Congestion Control Protocol (RFC 4340) - From http://www.ietf.org/rfc/rfc4340.txt: + From https://www.ietf.org/rfc/rfc4340.txt: The Datagram Congestion Control Protocol (DCCP) is a transport protocol that implements bidirectional, unicast connections of diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index 4d7771f36eff..a3eeb84d16f9 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -26,13 +26,13 @@ config IP_DCCP_CCID3 relatively smooth sending rate is of importance. CCID-3 is further described in RFC 4342, - http://www.ietf.org/rfc/rfc4342.txt + https://www.ietf.org/rfc/rfc4342.txt The TFRC congestion control algorithms were initially described in RFC 5348. This text was extracted from RFC 4340 (sec. 10.2), - http://www.ietf.org/rfc/rfc4340.txt + https://www.ietf.org/rfc/rfc4340.txt If in doubt, say N. diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 9ef9bee9610f..aef72f6a2829 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -7,7 +7,7 @@ * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * * This code also uses code from Lulea University, rereleased as GPL by its * authors: diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 081c195e7f7d..02e0fc9f6334 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -6,7 +6,7 @@ * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz * * This code also uses code from Lulea University, rereleased as GPL by its diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index 2d41bb036271..af08e2df7108 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -6,7 +6,7 @@ * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz * * This code also uses code from Lulea University, rereleased as GPL by its @@ -365,6 +365,7 @@ void tfrc_rx_hist_purge(struct tfrc_rx_hist *h) /** * tfrc_rx_hist_rtt_last_s - reference entry to compute RTT samples against + * @h: The non-empty RX history object */ static inline struct tfrc_rx_hist_entry * tfrc_rx_hist_rtt_last_s(const struct tfrc_rx_hist *h) @@ -374,6 +375,7 @@ static inline struct tfrc_rx_hist_entry * /** * tfrc_rx_hist_rtt_prev_s - previously suitable (wrt rtt_last_s) RTT-sampling entry + * @h: The non-empty RX history object */ static inline struct tfrc_rx_hist_entry * tfrc_rx_hist_rtt_prev_s(const struct tfrc_rx_hist *h) diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h index a157d874840b..159cc9326eab 100644 --- a/net/dccp/ccids/lib/packet_history.h +++ b/net/dccp/ccids/lib/packet_history.h @@ -6,7 +6,7 @@ * Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand. * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz * * This code also uses code from Lulea University, rereleased as GPL by its diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 9c3b5e056234..afc071ea1271 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -165,6 +165,8 @@ static const struct { /** * dccp_feat_index - Hash function to map feature number into array position + * @feat_num: feature to hash, one of %dccp_feature_numbers + * * Returns consecutive array index or -1 if the feature is not understood. */ static int dccp_feat_index(u8 feat_num) @@ -567,6 +569,8 @@ cloning_failed: /** * dccp_feat_valid_nn_length - Enforce length constraints on NN options + * @feat_num: feature to return length of, one of %dccp_feature_numbers + * * Length is between 0 and %DCCP_OPTVAL_MAXLEN. Used for outgoing packets only, * incoming options are accepted as long as their values are valid. */ @@ -1429,6 +1433,8 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, /** * dccp_feat_init - Seed feature negotiation with host-specific defaults + * @sk: Socket to initialize. + * * This initialises global defaults, depending on the value of the sysctls. * These can later be overridden by registering changes via setsockopt calls. * The last link in the chain is finalise_settings, to make sure that between diff --git a/net/dccp/input.c b/net/dccp/input.c index 6dce68a55964..bd9cfdb67436 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -715,6 +715,7 @@ EXPORT_SYMBOL_GPL(dccp_rcv_state_process); /** * dccp_sample_rtt - Validate and finalise computation of RTT sample + * @sk: socket structure * @delta: number of microseconds between packet and acknowledgment * * The routine is kept generic to work in different contexts. It should be diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d19557c6d04b..a7e989919c53 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -694,6 +694,8 @@ EXPORT_SYMBOL_GPL(dccp_v4_do_rcv); /** * dccp_invalid_packet - check for malformed packets + * @skb: Packet to validate + * * Implements RFC 4340, 8.5: Step 1: Check header basics * Packets that fail these checks are ignored and do not receive Resets. */ diff --git a/net/dccp/options.c b/net/dccp/options.c index 3b42f5c6a63d..daa9eed92646 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -43,6 +43,7 @@ u64 dccp_decode_value_var(const u8 *bf, const u8 len) * dccp_parse_options - Parse DCCP options present in @skb * @sk: client|server|listening dccp socket (when @dreq != NULL) * @dreq: request socket to use during connection setup, or NULL + * @skb: frame to parse */ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct sk_buff *skb) @@ -471,6 +472,8 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) + * @skb: frame into which to insert option + * * Note that since we are using skb_push, this function needs to be called * _after_ inserting the option it is supposed to influence (stack order). */ @@ -486,6 +489,7 @@ int dccp_insert_option_mandatory(struct sk_buff *skb) /** * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb + * @skb: frame to insert feature negotiation option into * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R * @feat: one out of %dccp_feature_numbers * @val: NN value or SP array (preferred element first) to copy diff --git a/net/dccp/timer.c b/net/dccp/timer.c index c0b3672637c4..0e06dfc32273 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -216,6 +216,8 @@ out: /** * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface + * @data: Socket to act on + * * See the comments above %ccid_dequeueing_decision for supported modes. */ static void dccp_write_xmitlet(unsigned long data) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 9eb7e4b62d9b..4cac31d22a50 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -494,6 +494,8 @@ static int dn_return_long(struct sk_buff *skb) /** * dn_route_rx_packet - Try and find a route for an incoming packet + * @net: The applicable net namespace + * @sk: Socket packet transmitted on * @skb: The packet to find a route for * * Returns: result of input function if route is found, error code otherwise diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index d5bc6ac599ef..1f9b9b11008c 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -86,6 +86,13 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 8795/9477/9893 families of switches. +config NET_DSA_TAG_RTL4_A + tristate "Tag driver for Realtek 4 byte protocol A tags" + help + Say Y or M if you want to enable support for tagging frames for the + Realtek switches with 4 byte protocol A tags, sich as found in + the Realtek RTL8366RB. + config NET_DSA_TAG_OCELOT tristate "Tag driver for Ocelot family of switches" select PACKING diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 108486cfdeef..4f47b2025ff5 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o +obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 076908fdd29b..e055efff390b 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -261,10 +261,15 @@ static int dsa_port_setup(struct dsa_port *dp) struct devlink_port *dlp = &dp->devlink_port; bool dsa_port_link_registered = false; bool devlink_port_registered = false; + struct devlink_port_attrs attrs = {}; struct devlink *dl = ds->devlink; bool dsa_port_enabled = false; int err = 0; + attrs.phys.port_number = dp->index; + memcpy(attrs.switch_id.id, id, len); + attrs.switch_id.id_len = len; + if (dp->setup) return 0; @@ -274,8 +279,8 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_CPU: memset(dlp, 0, sizeof(*dlp)); - devlink_port_attrs_set(dlp, DEVLINK_PORT_FLAVOUR_CPU, - dp->index, false, 0, id, len); + attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; + devlink_port_attrs_set(dlp, &attrs); err = devlink_port_register(dl, dlp, dp->index); if (err) break; @@ -294,8 +299,8 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_DSA: memset(dlp, 0, sizeof(*dlp)); - devlink_port_attrs_set(dlp, DEVLINK_PORT_FLAVOUR_DSA, - dp->index, false, 0, id, len); + attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; + devlink_port_attrs_set(dlp, &attrs); err = devlink_port_register(dl, dlp, dp->index); if (err) break; @@ -314,8 +319,8 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_USER: memset(dlp, 0, sizeof(*dlp)); - devlink_port_attrs_set(dlp, DEVLINK_PORT_FLAVOUR_PHYSICAL, - dp->index, false, 0, id, len); + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + devlink_port_attrs_set(dlp, &attrs); err = devlink_port_register(dl, dlp, dp->index); if (err) break; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index b0c98ee4e13b..42f327c06dca 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -137,11 +137,10 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - u64 bypass, dest, src, qos_class, rew_op; struct dsa_switch *ds = dp->ds; - int port = dp->index; struct ocelot *ocelot = ds->priv; - struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct ocelot_port *ocelot_port; + u64 qos_class, rew_op; u8 *injection; if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) { @@ -149,19 +148,15 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, return NULL; } - injection = skb_push(skb, OCELOT_TAG_LEN); + ocelot_port = ocelot->ports[dp->index]; - memset(injection, 0, OCELOT_TAG_LEN); + injection = skb_push(skb, OCELOT_TAG_LEN); - /* Set the source port as the CPU port module and not the NPI port */ - src = ocelot->num_phys_ports; - dest = BIT(port); - bypass = true; + memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN); + /* Fix up the fields which are not statically determined + * in the template + */ qos_class = skb->priority; - - packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0); - packing(injection, &dest, 68, 56, OCELOT_TAG_LEN, PACK, 0); - packing(injection, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0); packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c new file mode 100644 index 000000000000..7b63010fa87b --- /dev/null +++ b/net/dsa/tag_rtl4_a.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handler for Realtek 4 byte DSA switch tags + * Currently only supports protocol "A" found in RTL8366RB + * Copyright (c) 2020 Linus Walleij <linus.walleij@linaro.org> + * + * This "proprietary tag" header looks like so: + * + * ------------------------------------------------- + * | MAC DA | MAC SA | 0x8899 | 2 bytes tag | Type | + * ------------------------------------------------- + * + * The 2 bytes tag form a 16 bit big endian word. The exact + * meaning has been guessed from packet dumps from ingress + * frames, as no working egress traffic has been available + * we do not know the format of the egress tags or if they + * are even supported. + */ + +#include <linux/etherdevice.h> +#include <linux/bits.h> + +#include "dsa_priv.h" + +#define RTL4_A_HDR_LEN 4 +#define RTL4_A_ETHERTYPE 0x8899 +#define RTL4_A_PROTOCOL_SHIFT 12 +/* + * 0x1 = Realtek Remote Control protocol (RRCP) + * 0x2/0x3 seems to be used for loopback testing + * 0x9 = RTL8306 DSA protocol + * 0xa = RTL8366RB DSA protocol + */ +#define RTL4_A_PROTOCOL_RTL8366RB 0xa + +static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* + * Just let it pass thru, we don't know if it is possible + * to tag a frame with the 0x8899 ethertype and direct it + * to a specific port, all attempts at reverse-engineering have + * ended up with the frames getting dropped. + * + * The VLAN set-up needs to restrict the frames to the right port. + * + * If you have documentation on the tagging format for RTL8366RB + * (tag type A) then please contribute. + */ + return skb; +} + +static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + u16 protport; + __be16 *p; + u16 etype; + u8 *tag; + u8 prot; + u8 port; + + if (unlikely(!pskb_may_pull(skb, RTL4_A_HDR_LEN))) + return NULL; + + /* The RTL4 header has its own custom Ethertype 0x8899 and that + * starts right at the beginning of the packet, after the src + * ethernet addr. Apparantly skb->data always points 2 bytes in, + * behind the Ethertype. + */ + tag = skb->data - 2; + p = (__be16 *)tag; + etype = ntohs(*p); + if (etype != RTL4_A_ETHERTYPE) { + /* Not custom, just pass through */ + netdev_dbg(dev, "non-realtek ethertype 0x%04x\n", etype); + return skb; + } + p = (__be16 *)(tag + 2); + protport = ntohs(*p); + /* The 4 upper bits are the protocol */ + prot = (protport >> RTL4_A_PROTOCOL_SHIFT) & 0x0f; + if (prot != RTL4_A_PROTOCOL_RTL8366RB) { + netdev_err(dev, "unknown realtek protocol 0x%01x\n", prot); + return NULL; + } + port = protport & 0xff; + + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) { + netdev_dbg(dev, "could not find slave for port %d\n", port); + return NULL; + } + + /* Remove RTL4 tag and recalculate checksum */ + skb_pull_rcsum(skb, RTL4_A_HDR_LEN); + + /* Move ethernet DA and SA in front of the data */ + memmove(skb->data - ETH_HLEN, + skb->data - ETH_HLEN - RTL4_A_HDR_LEN, + 2 * ETH_ALEN); + + skb->offload_fwd_mark = 1; + + return skb; +} + +static int rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + *offset = RTL4_A_HDR_LEN; + /* Skip past the tag and fetch the encapsulated Ethertype */ + *proto = ((__be16 *)skb->data)[1]; + + return 0; +} + +static const struct dsa_device_ops rtl4a_netdev_ops = { + .name = "rtl4a", + .proto = DSA_TAG_PROTO_RTL4_A, + .xmit = rtl4a_tag_xmit, + .rcv = rtl4a_tag_rcv, + .flow_dissect = rtl4a_tag_flow_dissect, + .overhead = RTL4_A_HDR_LEN, +}; +module_dsa_tag_driver(rtl4a_netdev_ops); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL4_A); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 0c2b94f20499..7a849ff22dad 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -6,4 +6,5 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ - channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o + channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ + tunnels.o diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 7194956aa09e..888f6e101f34 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -58,6 +58,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ETHTOOL_A_CABLE_TEST_MAX + 1]; struct ethnl_req_info req_info = {}; + const struct ethtool_phy_ops *ops; struct net_device *dev; int ret; @@ -81,11 +82,17 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) } rtnl_lock(); + ops = ethtool_phy_ops; + if (!ops || !ops->start_cable_test) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; - ret = phy_start_cable_test(dev->phydev, info->extack); + ret = ops->start_cable_test(dev->phydev, info->extack); ethnl_ops_complete(dev); @@ -308,6 +315,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1]; struct ethnl_req_info req_info = {}; + const struct ethtool_phy_ops *ops; struct phy_tdr_config cfg; struct net_device *dev; int ret; @@ -337,11 +345,17 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) goto out_dev_put; rtnl_lock(); + ops = ethtool_phy_ops; + if (!ops || !ops->start_cable_test_tdr) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; - ret = phy_start_cable_test_tdr(dev->phydev, info->extack, &cfg); + ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg); ethnl_ops_complete(dev); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index aaecfc916a4d..ed19573fccd7 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/ethtool_netlink.h> #include <linux/net_tstamp.h> #include <linux/phy.h> +#include <linux/rtnetlink.h> #include "common.h" @@ -175,6 +177,21 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(400000, DR8, Full), __DEFINE_LINK_MODE_NAME(400000, CR8, Full), __DEFINE_SPECIAL_MODE_NAME(FEC_LLRS, "LLRS"), + __DEFINE_LINK_MODE_NAME(100000, KR, Full), + __DEFINE_LINK_MODE_NAME(100000, SR, Full), + __DEFINE_LINK_MODE_NAME(100000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_NAME(100000, DR, Full), + __DEFINE_LINK_MODE_NAME(100000, CR, Full), + __DEFINE_LINK_MODE_NAME(200000, KR2, Full), + __DEFINE_LINK_MODE_NAME(200000, SR2, Full), + __DEFINE_LINK_MODE_NAME(200000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_NAME(200000, DR2, Full), + __DEFINE_LINK_MODE_NAME(200000, CR2, Full), + __DEFINE_LINK_MODE_NAME(400000, KR4, Full), + __DEFINE_LINK_MODE_NAME(400000, SR4, Full), + __DEFINE_LINK_MODE_NAME(400000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_NAME(400000, DR4, Full), + __DEFINE_LINK_MODE_NAME(400000, CR4, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -256,6 +273,14 @@ const char ts_rx_filter_names[][ETH_GSTRING_LEN] = { }; static_assert(ARRAY_SIZE(ts_rx_filter_names) == __HWTSTAMP_FILTER_CNT); +const char udp_tunnel_type_names[][ETH_GSTRING_LEN] = { + [ETHTOOL_UDP_TUNNEL_TYPE_VXLAN] = "vxlan", + [ETHTOOL_UDP_TUNNEL_TYPE_GENEVE] = "geneve", + [ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE] = "vxlan-gpe", +}; +static_assert(ARRAY_SIZE(udp_tunnel_type_names) == + __ETHTOOL_UDP_TUNNEL_TYPE_CNT); + /* return false if legacy contained non-0 deprecated fields * maxtxpkt/maxrxpkt. rest of ksettings always updated */ @@ -373,3 +398,13 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } + +const struct ethtool_phy_ops *ethtool_phy_ops; + +void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) +{ + rtnl_lock(); + ethtool_phy_ops = ops; + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(ethtool_set_ethtool_phy_ops); diff --git a/net/ethtool/common.h b/net/ethtool/common.h index a62f68ccc43a..3d9251c95a8b 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -28,6 +28,7 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN]; extern const char sof_timestamping_names[][ETH_GSTRING_LEN]; extern const char ts_tx_type_names[][ETH_GSTRING_LEN]; extern const char ts_rx_filter_names[][ETH_GSTRING_LEN]; +extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN]; int __ethtool_get_link(struct net_device *dev); @@ -37,4 +38,6 @@ bool convert_legacy_settings_to_link_ksettings( int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max); int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); +extern const struct ethtool_phy_ops *ethtool_phy_ops; + #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 83f22196d64c..441794e0034f 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -135,6 +135,7 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) static int __ethtool_get_sset_count(struct net_device *dev, int sset) { + const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; if (sset == ETH_SS_FEATURES) @@ -150,8 +151,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) return ARRAY_SIZE(phy_tunable_strings); if (sset == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) - return phy_ethtool_get_sset_count(dev->phydev); + !ops->get_ethtool_phy_stats && + phy_ops && phy_ops->get_sset_count) + return phy_ops->get_sset_count(dev->phydev); if (sset == ETH_SS_LINK_MODES) return __ETHTOOL_LINK_MODE_MASK_NBITS; @@ -165,6 +167,7 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) static void __ethtool_get_strings(struct net_device *dev, u32 stringset, u8 *data) { + const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; if (stringset == ETH_SS_FEATURES) @@ -178,8 +181,9 @@ static void __ethtool_get_strings(struct net_device *dev, else if (stringset == ETH_SS_PHY_TUNABLES) memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings)); else if (stringset == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) - phy_ethtool_get_strings(dev->phydev, data); + !ops->get_ethtool_phy_stats && phy_ops && + phy_ops->get_strings) + phy_ops->get_strings(dev->phydev, data); else if (stringset == ETH_SS_LINK_MODES) memcpy(data, link_mode_names, __ETHTOOL_LINK_MODE_MASK_NBITS * ETH_GSTRING_LEN); @@ -1929,6 +1933,7 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) { + const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; struct ethtool_stats stats; @@ -1938,8 +1943,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count)) return -EOPNOTSUPP; - if (dev->phydev && !ops->get_ethtool_phy_stats) - n_stats = phy_ethtool_get_sset_count(dev->phydev); + if (dev->phydev && !ops->get_ethtool_phy_stats && + phy_ops && phy_ops->get_sset_count) + n_stats = phy_ops->get_sset_count(dev->phydev); else n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); if (n_stats < 0) @@ -1958,8 +1964,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) if (!data) return -ENOMEM; - if (dev->phydev && !ops->get_ethtool_phy_stats) { - ret = phy_ethtool_get_stats(dev->phydev, &stats, data); + if (dev->phydev && !ops->get_ethtool_phy_stats && + phy_ops && phy_ops->get_stats) { + ret = phy_ops->get_stats(dev->phydev, &stats, data); if (ret < 0) goto out; } else { diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index fd4f3e58c6f6..317a93129551 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -257,6 +257,21 @@ static const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), __DEFINE_SPECIAL_MODE_PARAMS(FEC_LLRS), + __DEFINE_LINK_MODE_PARAMS(100000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, DR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(200000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, SR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, DR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, CR2, Full), + __DEFINE_LINK_MODE_PARAMS(400000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, DR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, CR4, Full), }; static const struct nla_policy diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 88fd07f47040..5c2072765be7 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -181,6 +181,12 @@ err: return NULL; } +void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd) +{ + return genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + ðtool_genl_family, 0, cmd); +} + void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd) { return genlmsg_put(skb, 0, ++ethnl_bcast_seq, ðtool_genl_family, 0, @@ -376,10 +382,17 @@ err_dev: } static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, - const struct ethnl_dump_ctx *ctx) + const struct ethnl_dump_ctx *ctx, + struct netlink_callback *cb) { + void *ehdr; int ret; + ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + ðtool_genl_family, 0, ctx->ops->reply_cmd); + if (!ehdr) + return -EMSGSIZE; + ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); rtnl_lock(); ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL); @@ -395,6 +408,10 @@ out: if (ctx->ops->cleanup_data) ctx->ops->cleanup_data(ctx->reply_data); ctx->reply_data->dev = NULL; + if (ret < 0) + genlmsg_cancel(skb, ehdr); + else + genlmsg_end(skb, ehdr); return ret; } @@ -411,7 +428,6 @@ static int ethnl_default_dumpit(struct sk_buff *skb, int s_idx = ctx->pos_idx; int h, idx = 0; int ret = 0; - void *ehdr; rtnl_lock(); for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { @@ -431,26 +447,15 @@ restart_chain: dev_hold(dev); rtnl_unlock(); - ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - ðtool_genl_family, 0, - ctx->ops->reply_cmd); - if (!ehdr) { - dev_put(dev); - ret = -EMSGSIZE; - goto out; - } - ret = ethnl_default_dump_one(skb, dev, ctx); + ret = ethnl_default_dump_one(skb, dev, ctx, cb); dev_put(dev); if (ret < 0) { - genlmsg_cancel(skb, ehdr); if (ret == -EOPNOTSUPP) goto lock_and_cont; if (likely(skb->len)) ret = skb->len; goto out; } - genlmsg_end(skb, ehdr); lock_and_cont: rtnl_lock(); if (net->dev_base_seq != seq) { @@ -849,6 +854,12 @@ static const struct genl_ops ethtool_genl_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test_tdr, }, + { + .cmd = ETHTOOL_MSG_TUNNEL_INFO_GET, + .doit = ethnl_tunnel_info_doit, + .start = ethnl_tunnel_info_start, + .dumpit = ethnl_tunnel_info_dumpit, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 9a96b6e90dc2..e2085005caac 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -19,6 +19,7 @@ int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, u16 hdr_attrtype, struct genl_info *info, void **ehdrp); +void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd); void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd); int ethnl_multicast(struct sk_buff *skb, struct net_device *dev); @@ -361,5 +362,8 @@ int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info); int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info); +int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); +int ethnl_tunnel_info_start(struct netlink_callback *cb); +int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); #endif /* _NET_ETHTOOL_NETLINK_H */ diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 0eed4e4909ab..82707b662fe4 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -75,6 +75,11 @@ static const struct strset_info info_template[] = { .count = __HWTSTAMP_FILTER_CNT, .strings = ts_rx_filter_names, }, + [ETH_SS_UDP_TUNNEL_TYPES] = { + .per_dev = false, + .count = __ETHTOOL_UDP_TUNNEL_TYPE_CNT, + .strings = udp_tunnel_type_names, + }, }; struct strset_req_info { @@ -209,13 +214,15 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base) static int strset_prepare_set(struct strset_info *info, struct net_device *dev, unsigned int id, bool counts_only) { + const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; void *strings; int count, ret; if (id == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) - ret = phy_ethtool_get_sset_count(dev->phydev); + !ops->get_ethtool_phy_stats && phy_ops && + phy_ops->get_sset_count) + ret = phy_ops->get_sset_count(dev->phydev); else if (ops->get_sset_count && ops->get_strings) ret = ops->get_sset_count(dev, id); else @@ -231,8 +238,9 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev, if (!strings) return -ENOMEM; if (id == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) - phy_ethtool_get_strings(dev->phydev, strings); + !ops->get_ethtool_phy_stats && phy_ops && + phy_ops->get_strings) + phy_ops->get_strings(dev->phydev, strings); else ops->get_strings(dev, id, strings); info->strings = strings; diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c new file mode 100644 index 000000000000..6b89255f1231 --- /dev/null +++ b/net/ethtool/tunnels.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/ethtool_netlink.h> +#include <net/udp_tunnel.h> + +#include "bitset.h" +#include "common.h" +#include "netlink.h" + +static const struct nla_policy +ethtool_tunnel_info_policy[ETHTOOL_A_TUNNEL_INFO_MAX + 1] = { + [ETHTOOL_A_TUNNEL_INFO_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_TUNNEL_INFO_HEADER] = { .type = NLA_NESTED }, +}; + +static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN == ilog2(UDP_TUNNEL_TYPE_VXLAN)); +static_assert(ETHTOOL_UDP_TUNNEL_TYPE_GENEVE == ilog2(UDP_TUNNEL_TYPE_GENEVE)); +static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE == + ilog2(UDP_TUNNEL_TYPE_VXLAN_GPE)); + +static ssize_t +ethnl_tunnel_info_reply_size(const struct ethnl_req_info *req_base, + struct netlink_ext_ack *extack) +{ + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct udp_tunnel_nic_info *info; + unsigned int i; + size_t size; + int ret; + + info = req_base->dev->udp_tunnel_nic_info; + if (!info) { + NL_SET_ERR_MSG(extack, + "device does not report tunnel offload info"); + return -EOPNOTSUPP; + } + + size = nla_total_size(0); /* _INFO_UDP_PORTS */ + + for (i = 0; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { + if (!info->tables[i].n_entries) + return size; + + size += nla_total_size(0); /* _UDP_TABLE */ + size += nla_total_size(sizeof(u32)); /* _UDP_TABLE_SIZE */ + ret = ethnl_bitset32_size(&info->tables[i].tunnel_types, NULL, + __ETHTOOL_UDP_TUNNEL_TYPE_CNT, + udp_tunnel_type_names, compact); + if (ret < 0) + return ret; + size += ret; + + size += udp_tunnel_nic_dump_size(req_base->dev, i); + } + + return size; +} + +static int +ethnl_tunnel_info_fill_reply(const struct ethnl_req_info *req_base, + struct sk_buff *skb) +{ + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct udp_tunnel_nic_info *info; + struct nlattr *ports, *table; + unsigned int i; + + info = req_base->dev->udp_tunnel_nic_info; + if (!info) + return -EOPNOTSUPP; + + ports = nla_nest_start(skb, ETHTOOL_A_TUNNEL_INFO_UDP_PORTS); + if (!ports) + return -EMSGSIZE; + + for (i = 0; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { + if (!info->tables[i].n_entries) + break; + + table = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE); + if (!table) + goto err_cancel_ports; + + if (nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE, + info->tables[i].n_entries)) + goto err_cancel_table; + + if (ethnl_put_bitset32(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES, + &info->tables[i].tunnel_types, NULL, + __ETHTOOL_UDP_TUNNEL_TYPE_CNT, + udp_tunnel_type_names, compact)) + goto err_cancel_table; + + if (udp_tunnel_nic_dump_write(req_base->dev, i, skb)) + goto err_cancel_table; + + nla_nest_end(skb, table); + } + + nla_nest_end(skb, ports); + + return 0; + +err_cancel_table: + nla_nest_cancel(skb, table); +err_cancel_ports: + nla_nest_cancel(skb, ports); + return -EMSGSIZE; +} + +static int +ethnl_tunnel_info_req_parse(struct ethnl_req_info *req_info, + const struct nlmsghdr *nlhdr, struct net *net, + struct netlink_ext_ack *extack, bool require_dev) +{ + struct nlattr *tb[ETHTOOL_A_TUNNEL_INFO_MAX + 1]; + int ret; + + ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_TUNNEL_INFO_MAX, + ethtool_tunnel_info_policy, extack); + if (ret < 0) + return ret; + + return ethnl_parse_header_dev_get(req_info, + tb[ETHTOOL_A_TUNNEL_INFO_HEADER], + net, extack, require_dev); +} + +int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct sk_buff *rskb; + void *reply_payload; + int reply_len; + int ret; + + ret = ethnl_tunnel_info_req_parse(&req_info, info->nlhdr, + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + rtnl_lock(); + ret = ethnl_tunnel_info_reply_size(&req_info, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + reply_len = ret + ethnl_reply_header_size(); + + rskb = ethnl_reply_init(reply_len, req_info.dev, + ETHTOOL_MSG_TUNNEL_INFO_GET, + ETHTOOL_A_TUNNEL_INFO_HEADER, + info, &reply_payload); + if (!rskb) { + ret = -ENOMEM; + goto err_unlock_rtnl; + } + + ret = ethnl_tunnel_info_fill_reply(&req_info, rskb); + if (ret) + goto err_free_msg; + rtnl_unlock(); + dev_put(req_info.dev); + genlmsg_end(rskb, reply_payload); + + return genlmsg_reply(rskb, info); + +err_free_msg: + nlmsg_free(rskb); +err_unlock_rtnl: + rtnl_unlock(); + dev_put(req_info.dev); + return ret; +} + +struct ethnl_tunnel_info_dump_ctx { + struct ethnl_req_info req_info; + int pos_hash; + int pos_idx; +}; + +int ethnl_tunnel_info_start(struct netlink_callback *cb) +{ + struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + memset(ctx, 0, sizeof(*ctx)); + + ret = ethnl_tunnel_info_req_parse(&ctx->req_info, cb->nlh, + sock_net(cb->skb->sk), cb->extack, + false); + if (ctx->req_info.dev) { + dev_put(ctx->req_info.dev); + ctx->req_info.dev = NULL; + } + + return ret; +} + +int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + int s_idx = ctx->pos_idx; + int h, idx = 0; + int ret = 0; + void *ehdr; + + rtnl_lock(); + cb->seq = net->dev_base_seq; + for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + struct hlist_head *head; + struct net_device *dev; + + head = &net->dev_index_head[h]; + idx = 0; + hlist_for_each_entry(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + + ehdr = ethnl_dump_put(skb, cb, + ETHTOOL_MSG_TUNNEL_INFO_GET); + if (!ehdr) { + ret = -EMSGSIZE; + goto out; + } + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TUNNEL_INFO_HEADER); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + goto out; + } + + ctx->req_info.dev = dev; + ret = ethnl_tunnel_info_fill_reply(&ctx->req_info, skb); + ctx->req_info.dev = NULL; + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + if (ret == -EOPNOTSUPP) + goto cont; + goto out; + } + genlmsg_end(skb, ehdr); +cont: + idx++; + } + } +out: + rtnl_unlock(); + + ctx->pos_hash = h; + ctx->pos_idx = idx; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + + if (ret == -EMSGSIZE && skb->len) + return skb->len; + return ret; +} diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 1032b83d7047..8a927b647829 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -415,6 +415,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { + bool unregister = false; struct hsr_priv *hsr; int res; @@ -466,25 +467,27 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], if (res) goto err_unregister; + unregister = true; + res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) - goto err_add_slaves; + goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) - goto err_add_slaves; + goto err_unregister; hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; -err_add_slaves: - unregister_netdevice(hsr_dev); err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); + if (unregister) + unregister_netdevice(hsr_dev); return res; } diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 9e1a186a3671..5b77a46885b9 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -14,7 +14,7 @@ obj-y := route.o inetpeer.o protocol.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ - metrics.o netlink.o nexthop.o + metrics.o netlink.o nexthop.o udp_tunnel_stub.o obj-$(CONFIG_BPFILTER) += bpfilter/ @@ -29,6 +29,7 @@ gre-y := gre_demux.o obj-$(CONFIG_NET_FOU) += fou.o obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o +udp_tunnel-y := udp_tunnel_core.o udp_tunnel_nic.o obj-$(CONFIG_NET_UDP_TUNNEL) += udp_tunnel.o obj-$(CONFIG_NET_IPVTI) += ip_vti.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 0f1b9065c0a6..2eb71579f4d2 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -283,7 +283,7 @@ static int cipso_v4_cache_check(const unsigned char *key, /** * cipso_v4_cache_add - Add an entry to the CIPSO cache - * @skb: the packet + * @cipso_ptr: pointer to CIPSO IP option * @secattr: the packet's security attributes * * Description: @@ -1535,6 +1535,7 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) /** * cipso_v4_validate - Validate a CIPSO option + * @skb: the packet * @option: the start of the option, on error it is set to point to the error * * Description: @@ -2066,7 +2067,7 @@ void cipso_v4_sock_delattr(struct sock *sk) /** * cipso_v4_req_delattr - Delete the CIPSO option from a request socket - * @reg: the request socket + * @req: the request socket * * Description: * Removes the CIPSO option from a request socket, if present. @@ -2158,6 +2159,7 @@ int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) /** * cipso_v4_skbuff_setattr - Set the CIPSO option on a packet * @skb: the packet + * @doi_def: the DOI structure * @secattr: the security attributes * * Description: diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 956a806649f7..e30515f89802 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; - sk->sk_mark = mark; + ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -710,10 +710,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; - sk->sk_mark = mark; ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; + ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index afaf582a5aa9..22b0e7336360 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -648,20 +648,19 @@ no_route: EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); /* Decide when to expire the request and when to resend SYN-ACK */ -static inline void syn_ack_recalc(struct request_sock *req, const int thresh, - const int max_retries, - const u8 rskq_defer_accept, - int *expire, int *resend) +static void syn_ack_recalc(struct request_sock *req, + const int max_syn_ack_retries, + const u8 rskq_defer_accept, + int *expire, int *resend) { if (!rskq_defer_accept) { - *expire = req->num_timeout >= thresh; + *expire = req->num_timeout >= max_syn_ack_retries; *resend = 1; return; } - *expire = req->num_timeout >= thresh && - (!inet_rsk(req)->acked || req->num_timeout >= max_retries); - /* - * Do not resend while waiting for data after ACK, + *expire = req->num_timeout >= max_syn_ack_retries && + (!inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept); + /* Do not resend while waiting for data after ACK, * start to resend on end of deferring period to give * last chance for data or ACK to create established socket. */ @@ -720,15 +719,12 @@ static void reqsk_timer_handler(struct timer_list *t) struct net *net = sock_net(sk_listener); struct inet_connection_sock *icsk = inet_csk(sk_listener); struct request_sock_queue *queue = &icsk->icsk_accept_queue; - int qlen, expire = 0, resend = 0; - int max_retries, thresh; - u8 defer_accept; + int max_syn_ack_retries, qlen, expire = 0, resend = 0; if (inet_sk_state_load(sk_listener) != TCP_LISTEN) goto drop; - max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; - thresh = max_retries; + max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means @@ -750,17 +746,14 @@ static void reqsk_timer_handler(struct timer_list *t) if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; - while (thresh > 2) { + while (max_syn_ack_retries > 2) { if (qlen < young) break; - thresh--; + max_syn_ack_retries--; young <<= 1; } } - defer_accept = READ_ONCE(queue->rskq_defer_accept); - if (defer_accept) - max_retries = defer_accept; - syn_ack_recalc(req, thresh, max_retries, defer_accept, + syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept), &expire, &resend); req->rsk_ops->syn_ack_timeout(req); if (!expire && diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 125f4f8a36b4..4a98dd736270 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -52,6 +52,11 @@ static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { + if (proto < 0 || proto >= IPPROTO_MAX) { + mutex_lock(&inet_diag_table_mutex); + return ERR_PTR(-ENOENT); + } + if (!inet_diag_table[proto]) sock_load_diag_module(AF_INET, proto); @@ -181,6 +186,28 @@ errout: } EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill); +static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr **req_nlas) +{ + struct nlattr *nla; + int remaining; + + nlmsg_for_each_attr(nla, nlh, hdrlen, remaining) { + int type = nla_type(nla); + + if (type < __INET_DIAG_REQ_MAX) + req_nlas[type] = nla; + } +} + +static int inet_diag_get_protocol(const struct inet_diag_req_v2 *req, + const struct inet_diag_dump_data *data) +{ + if (data->req_nlas[INET_DIAG_REQ_PROTOCOL]) + return nla_get_u32(data->req_nlas[INET_DIAG_REQ_PROTOCOL]); + return req->sdiag_protocol; +} + #define MAX_DUMP_ALLOC_SIZE (KMALLOC_MAX_SIZE - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, @@ -198,7 +225,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, void *info = NULL; cb_data = cb->data; - handler = inet_diag_table[req->sdiag_protocol]; + handler = inet_diag_table[inet_diag_get_protocol(req, cb_data)]; BUG_ON(!handler); nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -539,20 +566,25 @@ EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, + int hdrlen, const struct inet_diag_req_v2 *req) { const struct inet_diag_handler *handler; - int err; + struct inet_diag_dump_data dump_data; + int err, protocol; - handler = inet_diag_lock_handler(req->sdiag_protocol); + memset(&dump_data, 0, sizeof(dump_data)); + inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas); + protocol = inet_diag_get_protocol(req, &dump_data); + + handler = inet_diag_lock_handler(protocol); if (IS_ERR(handler)) { err = PTR_ERR(handler); } else if (cmd == SOCK_DIAG_BY_FAMILY) { - struct inet_diag_dump_data empty_dump_data = {}; struct netlink_callback cb = { .nlh = nlh, .skb = in_skb, - .data = &empty_dump_data, + .data = &dump_data, }; err = handler->dump_one(&cb, req); } else if (cmd == SOCK_DESTROY && handler->destroy) { @@ -1103,13 +1135,16 @@ EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { + struct inet_diag_dump_data *cb_data = cb->data; const struct inet_diag_handler *handler; u32 prev_min_dump_alloc; - int err = 0; + int protocol, err = 0; + + protocol = inet_diag_get_protocol(r, cb_data); again: prev_min_dump_alloc = cb->min_dump_alloc; - handler = inet_diag_lock_handler(r->sdiag_protocol); + handler = inet_diag_lock_handler(protocol); if (!IS_ERR(handler)) handler->dump(skb, cb, r); else @@ -1139,19 +1174,13 @@ static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen) struct inet_diag_dump_data *cb_data; struct sk_buff *skb = cb->skb; struct nlattr *nla; - int rem, err; + int err; cb_data = kzalloc(sizeof(*cb_data), GFP_KERNEL); if (!cb_data) return -ENOMEM; - nla_for_each_attr(nla, nlmsg_attrdata(nlh, hdrlen), - nlmsg_attrlen(nlh, hdrlen), rem) { - int type = nla_type(nla); - - if (type < __INET_DIAG_REQ_MAX) - cb_data->req_nlas[type] = nla; - } + inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas); nla = cb_data->inet_diag_nla_bc; if (nla) { @@ -1237,7 +1266,8 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, req.idiag_states = rc->idiag_states; req.id = rc->id; - return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, &req); + return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, + sizeof(struct inet_diag_req), &req); } static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -1279,7 +1309,8 @@ static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) return netlink_dump_start(net->diag_nlsk, skb, h, &c); } - return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h)); + return inet_diag_cmd_exact(h->nlmsg_type, skb, h, hdrlen, + nlmsg_data(h)); } static diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d946356187ed..61f802d5350c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1708,7 +1708,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_mark = fl4.flowi4_mark; + ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 181b7a2a0247..f8b419e2475c 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -844,3 +844,21 @@ void ip_tunnel_unneed_metadata(void) static_branch_dec(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); + +/* Returns either the correct skb->protocol value, or 0 if invalid. */ +__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb) +{ + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) && + ip_hdr(skb)->version == 4) + return htons(ETH_P_IP); + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) && + ipv6_hdr(skb)->version == 6) + return htons(ETH_P_IPV6); + return 0; +} +EXPORT_SYMBOL(ip_tunnel_parse_protocol); + +const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol }; +EXPORT_SYMBOL(ip_tunnel_header_ops); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1d9c8cff5ac3..460ca1099e8a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -441,6 +441,7 @@ static const struct net_device_ops vti_netdev_ops = { static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 40fea52c8277..75d35e76bec2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -361,6 +361,7 @@ static const struct net_device_ops ipip_netdev_ops = { static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index f5c7a58844a4..678639c01e48 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -636,7 +636,10 @@ static int call_ipmr_mfc_entry_notifiers(struct net *net, /** * vif_delete - Delete a VIF entry + * @mrt: Table to delete from + * @vifi: VIF identifier to delete * @notify: Set to 1, if the caller is a notifier_call + * @head: if unregistering the VIF, place it on this queue */ static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 2361fdac2c43..9dcfa4e461b6 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -96,6 +96,21 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, } EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); +static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) +{ + struct dst_entry *dst = NULL; + struct flowi fl; + + memset(&fl, 0, sizeof(struct flowi)); + fl.u.ip4.daddr = ip_hdr(skb_in)->saddr; + nf_ip_route(dev_net(skb_in->dev), &dst, &fl, false); + if (!dst) + return -1; + + skb_dst_set(skb_in, dst); + return 0; +} + /* Send RST reply */ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) { @@ -109,6 +124,9 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) if (!oth) return; + if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(oldskb)) + return; + if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return; @@ -175,6 +193,9 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) if (iph->frag_off & htons(IP_OFFSET)) return; + if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(skb_in)) + return; + if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) { icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); return; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 535427292194..df6fbefe44d4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = user_icmph.type; + fl4.fl4_icmp_code = user_icmph.code; + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1d7076b78e63..a01efa062f6b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2027,7 +2027,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct sk_buff *hint) { struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt = (struct rtable *)hint; + struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); int err = -EINVAL; u32 tag = 0; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index de36c91d32ea..254b6a4cc95b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2691,6 +2691,9 @@ int tcp_disconnect(struct sock *sk, int flags) tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; + if (icsk->icsk_ca_ops->release) + icsk->icsk_ca_ops->release(sk); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -3246,10 +3249,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); - else - err = -EINVAL; + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -4033,11 +4033,14 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { + u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; - sg_init_one(&sg, key->key, key->keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen); - return crypto_ahash_update(hp->md5_req); + sg_init_one(&sg, key->key, keylen); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + + /* We use data_race() because tcp_md5_do_add() might change key->key under us */ + return data_race(crypto_ahash_update(hp->md5_req)); } EXPORT_SYMBOL(tcp_md5_hash_key); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 3172e31987be..62878cf26d9c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - if (sk->sk_state != TCP_CLOSE) + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index dc77309ea15b..b03ca68d4111 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4448,7 +4448,6 @@ static void tcp_sack_remove(struct tcp_sock *tp) /** * tcp_try_coalesce - try to merge skb to prior one * @sk: socket - * @dest: destination queue * @to: prior buffer * @from: buffer to add in queue * @fragstolen: pointer to boolean @@ -4604,6 +4603,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + sk->sk_data_ready(sk); tcp_drop(sk, skb); return; } @@ -4850,6 +4850,7 @@ queue_and_out: sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + sk->sk_data_ready(sk); goto drop; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ea0df9fd7618..116c11a0aaed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1111,9 +1111,21 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (key) { - /* Pre-existing entry - just update that one. */ - memcpy(key->key, newkey, newkeylen); - key->keylen = newkeylen; + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + * data_race() is telling kcsan that we do not care of + * key mismatches, since changing MD5 key on live flows + * can lead to packet drops. + */ + data_race(memcpy(key->key, newkey, newkeylen)); + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + return 0; } @@ -1129,7 +1141,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, rcu_assign_pointer(tp->md5sig_info, md5sig); } - key = sock_kmalloc(sk, sizeof(*key), gfp); + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 04b70fe31fa2..dc0117013ba5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -700,7 +700,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -715,7 +716,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - ireq->tstamp_ok &= !ireq->sack_ok; + if (synack_type != TCP_SYNACK_COOKIE) + ireq->tstamp_ok &= !ireq->sack_ok; } #endif @@ -3335,6 +3337,8 @@ int tcp_send_synack(struct sock *sk) * sk: listener socket * dst: dst entry attached to the SYNACK * req: request_sock pointer + * foc: cookie for tcp fast open + * synack_type: Type of synback to prepare * * Allocate one skb and build a SYNACK packet. * @dst is consumed : Caller should not use it again. @@ -3402,7 +3406,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index ada046f425d2..0c08c420fbc2 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -314,7 +314,7 @@ out: /** * tcp_delack_timer() - The TCP delayed ACK timeout handler - * @data: Pointer to the current socket. (gets casted to struct sock *) + * @t: Pointer to the timer. (gets casted to struct sock *) * * This function gets (indirectly) called when the kernel timer for a TCP packet * of this socket expires. Calls tcp_delack_timer_handler() to do the actual work. diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 31530129f137..073d346f515c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2743,9 +2743,9 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname, #endif /** * udp_poll - wait for a UDP event. - * @file - file struct - * @sock - socket - * @wait - poll table + * @file: - file struct + * @sock: - socket + * @wait: - poll table * * This is same as datagram poll, except for the special case of * blocking sockets. If application is using a blocking fd diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel_core.c index 3eecba0874aa..3eecba0874aa 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel_core.c diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c new file mode 100644 index 000000000000..f0dbd9905a53 --- /dev/null +++ b/net/ipv4/udp_tunnel_nic.c @@ -0,0 +1,890 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2020 Facebook Inc. + +#include <linux/ethtool_netlink.h> +#include <linux/netdevice.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <net/udp_tunnel.h> + +enum udp_tunnel_nic_table_entry_flags { + UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), + UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), + UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), + UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), +}; + +struct udp_tunnel_nic_table_entry { + __be16 port; + u8 type; + u8 use_cnt; + u8 flags; + u8 hw_priv; +}; + +/** + * struct udp_tunnel_nic - UDP tunnel port offload state + * @work: async work for talking to hardware from process context + * @dev: netdev pointer + * @need_sync: at least one port start changed + * @need_replay: space was freed, we need a replay of all ports + * @work_pending: @work is currently scheduled + * @n_tables: number of tables under @entries + * @missed: bitmap of tables which overflown + * @entries: table of tables of ports currently offloaded + */ +struct udp_tunnel_nic { + struct work_struct work; + + struct net_device *dev; + + u8 need_sync:1; + u8 need_replay:1; + u8 work_pending:1; + + unsigned int n_tables; + unsigned long missed; + struct udp_tunnel_nic_table_entry **entries; +}; + +/* We ensure all work structs are done using driver state, but not the code. + * We need a workqueue we can flush before module gets removed. + */ +static struct workqueue_struct *udp_tunnel_nic_workqueue; + +static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) +{ + switch (type) { + case UDP_TUNNEL_TYPE_VXLAN: + return "vxlan"; + case UDP_TUNNEL_TYPE_GENEVE: + return "geneve"; + case UDP_TUNNEL_TYPE_VXLAN_GPE: + return "vxlan-gpe"; + default: + return "unknown"; + } +} + +static bool +udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) +{ + return entry->use_cnt == 0 && !entry->flags; +} + +static bool +udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) +{ + return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); +} + +static bool +udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) +{ + return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; +} + +static void +udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) +{ + if (!udp_tunnel_nic_entry_is_free(entry)) + entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; +} + +static void +udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) +{ + entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; +} + +static bool +udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) +{ + return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | + UDP_TUNNEL_NIC_ENTRY_DEL); +} + +static void +udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, + struct udp_tunnel_nic_table_entry *entry, + unsigned int flag) +{ + entry->flags |= flag; + utn->need_sync = 1; +} + +static void +udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, + struct udp_tunnel_info *ti) +{ + memset(ti, 0, sizeof(*ti)); + ti->port = entry->port; + ti->type = entry->type; + ti->hw_priv = entry->hw_priv; +} + +static bool +udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + unsigned int i, j; + + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) + if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) + return false; + return true; +} + +static bool +udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_table_info *table; + unsigned int i, j; + + if (!utn->missed) + return false; + + for (i = 0; i < utn->n_tables; i++) { + table = &dev->udp_tunnel_nic_info->tables[i]; + if (!test_bit(i, &utn->missed)) + continue; + + for (j = 0; j < table->n_entries; j++) + if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) + return true; + } + + return false; +} + +static void +__udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, + unsigned int idx, struct udp_tunnel_info *ti) +{ + struct udp_tunnel_nic_table_entry *entry; + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + entry = &utn->entries[table][idx]; + + if (entry->use_cnt) + udp_tunnel_nic_ti_from_entry(entry, ti); +} + +static void +__udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, + unsigned int idx, u8 priv) +{ + dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; +} + +static void +udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, + int err) +{ + bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; + + WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && + entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); + + if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && + (!err || (err == -EEXIST && dodgy))) + entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; + + if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && + (!err || (err == -ENOENT && dodgy))) + entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; + + if (!err) + entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; + else + entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; +} + +static void +udp_tunnel_nic_device_sync_one(struct net_device *dev, + struct udp_tunnel_nic *utn, + unsigned int table, unsigned int idx) +{ + struct udp_tunnel_nic_table_entry *entry; + struct udp_tunnel_info ti; + int err; + + entry = &utn->entries[table][idx]; + if (!udp_tunnel_nic_entry_is_queued(entry)) + return; + + udp_tunnel_nic_ti_from_entry(entry, &ti); + if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) + err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); + else + err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, + &ti); + udp_tunnel_nic_entry_update_done(entry, err); + + if (err) + netdev_warn(dev, + "UDP tunnel port sync failed port %d type %s: %d\n", + be16_to_cpu(entry->port), + udp_tunnel_nic_tunnel_type_name(entry->type), + err); +} + +static void +udp_tunnel_nic_device_sync_by_port(struct net_device *dev, + struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + unsigned int i, j; + + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) + udp_tunnel_nic_device_sync_one(dev, utn, i, j); +} + +static void +udp_tunnel_nic_device_sync_by_table(struct net_device *dev, + struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + unsigned int i, j; + int err; + + for (i = 0; i < utn->n_tables; i++) { + /* Find something that needs sync in this table */ + for (j = 0; j < info->tables[i].n_entries; j++) + if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) + break; + if (j == info->tables[i].n_entries) + continue; + + err = info->sync_table(dev, i); + if (err) + netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", + i, err); + + for (j = 0; j < info->tables[i].n_entries; j++) { + struct udp_tunnel_nic_table_entry *entry; + + entry = &utn->entries[i][j]; + if (udp_tunnel_nic_entry_is_queued(entry)) + udp_tunnel_nic_entry_update_done(entry, err); + } + } +} + +static void +__udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + if (!utn->need_sync) + return; + + if (dev->udp_tunnel_nic_info->sync_table) + udp_tunnel_nic_device_sync_by_table(dev, utn); + else + udp_tunnel_nic_device_sync_by_port(dev, utn); + + utn->need_sync = 0; + /* Can't replay directly here, in case we come from the tunnel driver's + * notification - trying to replay may deadlock inside tunnel driver. + */ + utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); +} + +static void +udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + bool may_sleep; + + if (!utn->need_sync) + return; + + /* Drivers which sleep in the callback need to update from + * the workqueue, if we come from the tunnel driver's notification. + */ + may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; + if (!may_sleep) + __udp_tunnel_nic_device_sync(dev, utn); + if (may_sleep || utn->need_replay) { + queue_work(udp_tunnel_nic_workqueue, &utn->work); + utn->work_pending = 1; + } +} + +static bool +udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, + struct udp_tunnel_info *ti) +{ + return table->tunnel_types & ti->type; +} + +static bool +udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, + struct udp_tunnel_info *ti) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + unsigned int i; + + /* Special case IPv4-only NICs */ + if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && + ti->sa_family != AF_INET) + return false; + + for (i = 0; i < utn->n_tables; i++) + if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) + return true; + return false; +} + +static int +udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, + struct udp_tunnel_info *ti) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic_table_entry *entry; + unsigned int i, j; + + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) { + entry = &utn->entries[i][j]; + + if (!udp_tunnel_nic_entry_is_free(entry) && + entry->port == ti->port && + entry->type != ti->type) { + __set_bit(i, &utn->missed); + return true; + } + } + return false; +} + +static void +udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, + unsigned int table, unsigned int idx, int use_cnt_adj) +{ + struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; + bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; + unsigned int from, to; + + /* If not going from used to unused or vice versa - all done. + * For dodgy entries make sure we try to sync again (queue the entry). + */ + entry->use_cnt += use_cnt_adj; + if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) + return; + + /* Cancel the op before it was sent to the device, if possible, + * otherwise we'd need to take special care to issue commands + * in the same order the ports arrived. + */ + if (use_cnt_adj < 0) { + from = UDP_TUNNEL_NIC_ENTRY_ADD; + to = UDP_TUNNEL_NIC_ENTRY_DEL; + } else { + from = UDP_TUNNEL_NIC_ENTRY_DEL; + to = UDP_TUNNEL_NIC_ENTRY_ADD; + } + + if (entry->flags & from) { + entry->flags &= ~from; + if (!dodgy) + return; + } + + udp_tunnel_nic_entry_queue(utn, entry, to); +} + +static bool +udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, + unsigned int table, unsigned int idx, + struct udp_tunnel_info *ti, int use_cnt_adj) +{ + struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; + + if (udp_tunnel_nic_entry_is_free(entry) || + entry->port != ti->port || + entry->type != ti->type) + return false; + + if (udp_tunnel_nic_entry_is_frozen(entry)) + return true; + + udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); + return true; +} + +/* Try to find existing matching entry and adjust its use count, instead of + * adding a new one. Returns true if entry was found. In case of delete the + * entry may have gotten removed in the process, in which case it will be + * queued for removal. + */ +static bool +udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, + struct udp_tunnel_info *ti, int use_cnt_adj) +{ + const struct udp_tunnel_nic_table_info *table; + unsigned int i, j; + + for (i = 0; i < utn->n_tables; i++) { + table = &dev->udp_tunnel_nic_info->tables[i]; + if (!udp_tunnel_nic_table_is_capable(table, ti)) + continue; + + for (j = 0; j < table->n_entries; j++) + if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, + use_cnt_adj)) + return true; + } + + return false; +} + +static bool +udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, + struct udp_tunnel_info *ti) +{ + return udp_tunnel_nic_try_existing(dev, utn, ti, +1); +} + +static bool +udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, + struct udp_tunnel_info *ti) +{ + return udp_tunnel_nic_try_existing(dev, utn, ti, -1); +} + +static bool +udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, + struct udp_tunnel_info *ti) +{ + const struct udp_tunnel_nic_table_info *table; + unsigned int i, j; + + for (i = 0; i < utn->n_tables; i++) { + table = &dev->udp_tunnel_nic_info->tables[i]; + if (!udp_tunnel_nic_table_is_capable(table, ti)) + continue; + + for (j = 0; j < table->n_entries; j++) { + struct udp_tunnel_nic_table_entry *entry; + + entry = &utn->entries[i][j]; + if (!udp_tunnel_nic_entry_is_free(entry)) + continue; + + entry->port = ti->port; + entry->type = ti->type; + entry->use_cnt = 1; + udp_tunnel_nic_entry_queue(utn, entry, + UDP_TUNNEL_NIC_ENTRY_ADD); + return true; + } + + /* The different table may still fit this port in, but there + * are no devices currently which have multiple tables accepting + * the same tunnel type, and false positives are okay. + */ + __set_bit(i, &utn->missed); + } + + return false; +} + +static void +__udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (!utn) + return; + if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) + return; + + if (!udp_tunnel_nic_is_capable(dev, utn, ti)) + return; + + /* It may happen that a tunnel of one type is removed and different + * tunnel type tries to reuse its port before the device was informed. + * Rely on utn->missed to re-add this port later. + */ + if (udp_tunnel_nic_has_collision(dev, utn, ti)) + return; + + if (!udp_tunnel_nic_add_existing(dev, utn, ti)) + udp_tunnel_nic_add_new(dev, utn, ti); + + udp_tunnel_nic_device_sync(dev, utn); +} + +static void +__udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) +{ + struct udp_tunnel_nic *utn; + + utn = dev->udp_tunnel_nic; + if (!utn) + return; + + if (!udp_tunnel_nic_is_capable(dev, utn, ti)) + return; + + udp_tunnel_nic_del_existing(dev, utn, ti); + + udp_tunnel_nic_device_sync(dev, utn); +} + +static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic *utn; + unsigned int i, j; + + ASSERT_RTNL(); + + utn = dev->udp_tunnel_nic; + if (!utn) + return; + + utn->need_sync = false; + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) { + struct udp_tunnel_nic_table_entry *entry; + + entry = &utn->entries[i][j]; + + entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | + UDP_TUNNEL_NIC_ENTRY_OP_FAIL); + /* We don't release rtnl across ops */ + WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); + if (!entry->use_cnt) + continue; + + udp_tunnel_nic_entry_queue(utn, entry, + UDP_TUNNEL_NIC_ENTRY_ADD); + } + + __udp_tunnel_nic_device_sync(dev, utn); +} + +static size_t +__udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic *utn; + unsigned int j; + size_t size; + + utn = dev->udp_tunnel_nic; + if (!utn) + return 0; + + size = 0; + for (j = 0; j < info->tables[table].n_entries; j++) { + if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) + continue; + + size += nla_total_size(0) + /* _TABLE_ENTRY */ + nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ + nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ + } + + return size; +} + +static int +__udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, + struct sk_buff *skb) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic *utn; + struct nlattr *nest; + unsigned int j; + + utn = dev->udp_tunnel_nic; + if (!utn) + return 0; + + for (j = 0; j < info->tables[table].n_entries; j++) { + if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) + continue; + + nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); + + if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, + utn->entries[table][j].port) || + nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, + ilog2(utn->entries[table][j].type))) + goto err_cancel; + + nla_nest_end(skb, nest); + } + + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { + .get_port = __udp_tunnel_nic_get_port, + .set_port_priv = __udp_tunnel_nic_set_port_priv, + .add_port = __udp_tunnel_nic_add_port, + .del_port = __udp_tunnel_nic_del_port, + .reset_ntf = __udp_tunnel_nic_reset_ntf, + .dump_size = __udp_tunnel_nic_dump_size, + .dump_write = __udp_tunnel_nic_dump_write, +}; + +static void +udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + unsigned int i, j; + + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) { + int adj_cnt = -utn->entries[i][j].use_cnt; + + if (adj_cnt) + udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); + } + + __udp_tunnel_nic_device_sync(dev, utn); + + for (i = 0; i < utn->n_tables; i++) + memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, + sizeof(**utn->entries))); + WARN_ON(utn->need_sync); + utn->need_replay = 0; +} + +static void +udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + unsigned int i, j; + + /* Freeze all the ports we are already tracking so that the replay + * does not double up the refcount. + */ + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) + udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); + utn->missed = 0; + utn->need_replay = 0; + + udp_tunnel_get_rx_info(dev); + + for (i = 0; i < utn->n_tables; i++) + for (j = 0; j < info->tables[i].n_entries; j++) + udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); +} + +static void udp_tunnel_nic_device_sync_work(struct work_struct *work) +{ + struct udp_tunnel_nic *utn = + container_of(work, struct udp_tunnel_nic, work); + + rtnl_lock(); + utn->work_pending = 0; + __udp_tunnel_nic_device_sync(utn->dev, utn); + + if (utn->need_replay) + udp_tunnel_nic_replay(utn->dev, utn); + rtnl_unlock(); +} + +static struct udp_tunnel_nic * +udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, + unsigned int n_tables) +{ + struct udp_tunnel_nic *utn; + unsigned int i; + + utn = kzalloc(sizeof(*utn), GFP_KERNEL); + if (!utn) + return NULL; + utn->n_tables = n_tables; + INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); + + utn->entries = kmalloc_array(n_tables, sizeof(void *), GFP_KERNEL); + if (!utn->entries) + goto err_free_utn; + + for (i = 0; i < n_tables; i++) { + utn->entries[i] = kcalloc(info->tables[i].n_entries, + sizeof(*utn->entries[i]), GFP_KERNEL); + if (!utn->entries[i]) + goto err_free_prev_entries; + } + + return utn; + +err_free_prev_entries: + while (i--) + kfree(utn->entries[i]); + kfree(utn->entries); +err_free_utn: + kfree(utn); + return NULL; +} + +static int udp_tunnel_nic_register(struct net_device *dev) +{ + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic *utn; + unsigned int n_tables, i; + + BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < + UDP_TUNNEL_NIC_MAX_TABLES); + + if (WARN_ON(!info->set_port != !info->unset_port) || + WARN_ON(!info->set_port == !info->sync_table) || + WARN_ON(!info->tables[0].n_entries)) + return -EINVAL; + + n_tables = 1; + for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { + if (!info->tables[i].n_entries) + continue; + + n_tables++; + if (WARN_ON(!info->tables[i - 1].n_entries)) + return -EINVAL; + } + + utn = udp_tunnel_nic_alloc(info, n_tables); + if (!utn) + return -ENOMEM; + + utn->dev = dev; + dev_hold(dev); + dev->udp_tunnel_nic = utn; + + if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) + udp_tunnel_get_rx_info(dev); + + return 0; +} + +static void +udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) +{ + unsigned int i; + + /* Flush before we check work, so we don't waste time adding entries + * from the work which we will boot immediately. + */ + udp_tunnel_nic_flush(dev, utn); + + /* Wait for the work to be done using the state, netdev core will + * retry unregister until we give up our reference on this device. + */ + if (utn->work_pending) + return; + + for (i = 0; i < utn->n_tables; i++) + kfree(utn->entries[i]); + kfree(utn->entries); + kfree(utn); + dev->udp_tunnel_nic = NULL; + dev_put(dev); +} + +static int +udp_tunnel_nic_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + const struct udp_tunnel_nic_info *info; + struct udp_tunnel_nic *utn; + + info = dev->udp_tunnel_nic_info; + if (!info) + return NOTIFY_DONE; + + if (event == NETDEV_REGISTER) { + int err; + + err = udp_tunnel_nic_register(dev); + if (err) + netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); + return notifier_from_errno(err); + } + /* All other events will need the udp_tunnel_nic state */ + utn = dev->udp_tunnel_nic; + if (!utn) + return NOTIFY_DONE; + + if (event == NETDEV_UNREGISTER) { + udp_tunnel_nic_unregister(dev, utn); + return NOTIFY_OK; + } + + /* All other events only matter if NIC has to be programmed open */ + if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) + return NOTIFY_DONE; + + if (event == NETDEV_UP) { + WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); + udp_tunnel_get_rx_info(dev); + return NOTIFY_OK; + } + if (event == NETDEV_GOING_DOWN) { + udp_tunnel_nic_flush(dev, utn); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { + .notifier_call = udp_tunnel_nic_netdevice_event, +}; + +static int __init udp_tunnel_nic_init_module(void) +{ + int err; + + udp_tunnel_nic_workqueue = alloc_workqueue("udp_tunnel_nic", 0, 0); + if (!udp_tunnel_nic_workqueue) + return -ENOMEM; + + rtnl_lock(); + udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; + rtnl_unlock(); + + err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); + if (err) + goto err_unset_ops; + + return 0; + +err_unset_ops: + rtnl_lock(); + udp_tunnel_nic_ops = NULL; + rtnl_unlock(); + destroy_workqueue(udp_tunnel_nic_workqueue); + return err; +} +late_initcall(udp_tunnel_nic_init_module); + +static void __exit udp_tunnel_nic_cleanup_module(void) +{ + unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); + + rtnl_lock(); + udp_tunnel_nic_ops = NULL; + rtnl_unlock(); + + destroy_workqueue(udp_tunnel_nic_workqueue); +} +module_exit(udp_tunnel_nic_cleanup_module); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/udp_tunnel_stub.c b/net/ipv4/udp_tunnel_stub.c new file mode 100644 index 000000000000..c4b2888f5fef --- /dev/null +++ b/net/ipv4/udp_tunnel_stub.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2020 Facebook Inc. + +#include <net/udp_tunnel.h> + +const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; +EXPORT_SYMBOL_GPL(udp_tunnel_nic_ops); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index e9b366994475..374105e4394f 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1232,7 +1232,6 @@ static void ipv6_renew_option(int renewtype, * @opt: original options * @newtype: option type to replace in @opt * @newopt: new option of type @newtype to replace (user-mem) - * @newoptlen: length of @newopt * * Returns a new set of options which is a copy of @opt with the * option type @newtype replaced with @newopt. diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 91e0f2fd2523..a4e4912ad607 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -566,7 +566,6 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); - sk->sk_mark = mark; np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6)) @@ -583,6 +582,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.flowi6_oif = np->ucast_oif; ipcm6_init_sk(&ipc6, np); + ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); @@ -752,7 +752,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) @@ -780,6 +779,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + ipc6.sockc.mark = mark; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8a8c2d0cfcc8..c78e67d7747f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1118,6 +1118,7 @@ out_err_release: /** * ip6_dst_lookup - perform route lookup on flow + * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @dst: pointer to dst_entry * for result * @fl6: flow to lookup @@ -1136,6 +1137,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** * ip6_dst_lookup_flow - perform route lookup on flow with ipsec + * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup @@ -1202,11 +1204,11 @@ EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); * @skb: Packet for which lookup is done * @dev: Tunnel device * @net: Network namespace of tunnel device - * @sk: Socket which provides route info + * @sock: Socket which provides route info * @saddr: Memory to store the src ip address * @info: Tunnel information * @protocol: IP protocol - * @use_cahce: Flag to enable cache usage + * @use_cache: Flag to enable cache usage * This function performs a route lookup on a tunnel * * It returns a valid dst pointer and stores src address to be used in diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 821d96c720b9..f635914f42ec 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -124,8 +124,12 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) return &dev->stats; } +#define for_each_ip6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses + * @net: network namespace * @link: ifindex of underlying interface * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point @@ -136,9 +140,6 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * else %NULL **/ -#define for_each_ip6_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - static struct ip6_tnl * ip6_tnl_lookup(struct net *net, int link, const struct in6_addr *remote, const struct in6_addr *local) @@ -302,8 +303,8 @@ out: /** * ip6_tnl_create - create a new tunnel + * @net: network namespace * @p: tunnel parameters - * @pt: pointer to new tunnel * * Description: * Create tunnel matching given parameters. @@ -351,6 +352,7 @@ failed: /** * ip6_tnl_locate - find or create tunnel matching given parameters + * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * @@ -1846,6 +1848,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6_dev_free; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 1147f647b9a0..0d964160a9dd 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -905,6 +905,7 @@ static const struct net_device_ops vti6_netdev_ops = { static void vti6_dev_setup(struct net_device *dev) { dev->netdev_ops = &vti6_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = vti6_dev_free; diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 5fae66f66671..4aef6baaa55e 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -126,6 +126,21 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, } EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put); +static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) +{ + struct dst_entry *dst = NULL; + struct flowi fl; + + memset(&fl, 0, sizeof(struct flowi)); + fl.u.ip6.daddr = ipv6_hdr(skb_in)->saddr; + nf_ip6_route(dev_net(skb_in->dev), &dst, &fl, false); + if (!dst) + return -1; + + skb_dst_set(skb_in, dst); + return 0; +} + void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) { struct net_device *br_indev __maybe_unused; @@ -154,6 +169,14 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; + + if (hook == NF_INET_PRE_ROUTING) { + nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); + if (!dst) + return; + skb_dst_set(oldskb, dst); + } + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); @@ -245,6 +268,9 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; + if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in)) + return; + icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); } EXPORT_SYMBOL_GPL(nf_send_unreach6); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5852039ca9cf..427b81cbc164 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -431,9 +431,12 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; - if ((!match->fib6_nsiblings && !match->nh) || have_oif_match) + if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; + if (match->nh && have_oif_match && res->nh) + return; + /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ @@ -3402,7 +3405,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && - !(flags & RTF_LOCAL))) + !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1fbb4dfbb191..5e2c34c0ac97 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1421,6 +1421,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7d4151747340..38c0d9350c6b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1059,6 +1059,9 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, * @sk: socket we are sending on * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) + * @saddr: source address + * @daddr: destination address + * @len: length of packet */ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, const struct in6_addr *saddr, diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 6d7ef78c88af..6434d17e6e8e 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1028,6 +1028,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; + skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); @@ -1099,10 +1100,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } - /* Get routing info from the tunnel socket */ - skb_dst_drop(skb); - skb_dst_set(skb, sk_dst_check(sk, 0)); - inet = inet_sk(sk); fl = &inet->cork.fl; switch (tunnel->encap) { diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 54fb8d452a7b..6140a3e46c26 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -273,6 +273,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) if (!sock_flag(sk, SOCK_ZAPPED)) goto out; + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (addr->sllc_arphrd != ARPHRD_ETHER) + goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); @@ -328,7 +332,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; - if (unlikely(addr->sllc_family != AF_LLC)) + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; @@ -336,8 +342,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { - if (!addr->sllc_arphrd) - addr->sllc_arphrd = llc->dev->type; if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); @@ -980,7 +984,6 @@ out: * llc_ui_getname - return the address info of a socket * @sock: Socket to get address of. * @uaddr: Address structure to return information. - * @uaddrlen: Length of address structure. * @peer: Does user want local or remote address information. * * Return the address information of a socket. diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 7b620acaca9e..1144cda2a0fc 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -284,8 +284,8 @@ out:; /** * llc_conn_remove_acked_pdus - Removes acknowledged pdus from tx queue * @sk: active connection - * nr: NR - * how_many_unacked: size of pdu_unack_q after removing acked pdus + * @nr: NR + * @how_many_unacked: size of pdu_unack_q after removing acked pdus * * Removes acknowledged pdus from transmit queue (pdu_unack_q). Returns * the number of pdus that removed from queue. @@ -906,6 +906,7 @@ static void llc_sk_init(struct sock *sk) /** * llc_sk_alloc - Allocates LLC sock + * @net: network namespace * @family: upper layer protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @@ -951,7 +952,7 @@ void llc_sk_stop_all_timers(struct sock *sk, bool sync) /** * llc_sk_free - Frees a LLC socket - * @sk - socket to free + * @sk: - socket to free * * Frees a LLC socket */ diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 82cb93f66b9b..c309b72a5877 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -144,6 +144,7 @@ static inline int llc_fixup_skb(struct sk_buff *skb) * @skb: received pdu * @dev: device that receive pdu * @pt: packet type + * @orig_dev: the original receive net device * * When the system receives a 802.2 frame this function is called. It * checks SAP and connection of received pdu and passes frame to diff --git a/net/llc/llc_pdu.c b/net/llc/llc_pdu.c index 2e6cb79196bb..792d195c8bae 100644 --- a/net/llc/llc_pdu.c +++ b/net/llc/llc_pdu.c @@ -25,7 +25,7 @@ void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 pdu_type) /** * pdu_set_pf_bit - sets poll/final bit in LLC header - * @pdu_frame: input frame that p/f bit must be set into it. + * @skb: Frame to set bit in * @bit_value: poll/final bit (0 or 1). * * This function sets poll/final bit in LLC header (based on type of PDU). diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index be419062e19a..6805ce43a055 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -37,6 +37,7 @@ static int llc_mac_header_len(unsigned short devtype) /** * llc_alloc_frame - allocates sk_buff for frame + * @sk: socket to allocate frame to * @dev: network device this skb will be sent over * @type: pdu type to allocate * @data_size: data size to allocate @@ -273,6 +274,7 @@ void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb, * llc_sap_rcv - sends received pdus to the sap state machine * @sap: current sap component structure. * @skb: received frame. + * @sk: socket to associate to frame * * Sends received pdus to the sap state machine. */ @@ -379,6 +381,7 @@ static void llc_do_mcast(struct llc_sap *sap, struct sk_buff *skb, * llc_sap_mcast - Deliver multicast PDU's to all matching datagram sockets. * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @skb: PDU to deliver * * Search socket list of the SAP and finds connections with same sap. * Deliver clone to each. diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index aa5150929996..02cde0fd08fe 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1105,11 +1105,8 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) ttl, lifetime, 0, ifmsh->preq_id++, sdata); spin_lock_bh(&mpath->state_lock); - if (mpath->flags & MESH_PATH_DELETED) { - spin_unlock_bh(&mpath->state_lock); - goto enddiscovery; - } - mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); + if (!(mpath->flags & MESH_PATH_DELETED)) + mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); spin_unlock_bh(&mpath->state_lock); enddiscovery: diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 117519bf33d6..fe4e853c61f4 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -72,7 +72,6 @@ static void mesh_table_free(struct mesh_table *tbl) } /** - * * mesh_path_assign_nexthop - update mesh path next hop * * @mpath: mesh path to update @@ -140,7 +139,6 @@ static void prepare_for_gate(struct sk_buff *skb, char *dst_addr, } /** - * * mesh_path_move_to_queue - Move or copy frames from one mpath queue to another * * This function is used to transfer or copy frames from an unresolved mpath to @@ -152,7 +150,7 @@ static void prepare_for_gate(struct sk_buff *skb, char *dst_addr, * * The gate mpath must be an active mpath with a valid mpath->next_hop. * - * @mpath: An active mpath the frames will be sent to (i.e. the gate) + * @gate_mpath: An active mpath the frames will be sent to (i.e. the gate) * @from_mpath: The failed mpath * @copy: When true, copy all the frames to the new mpath queue. When false, * move them. diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a88ab6fb16f2..5c5af4b5fc08 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2396,6 +2396,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) { + struct ieee80211_hdr *hdr = (void *)rx->skb->data; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -2406,6 +2407,31 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) if (status->flag & RX_FLAG_DECRYPTED) return 0; + /* check mesh EAPOL frames first */ + if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) && + ieee80211_is_data(fc))) { + struct ieee80211s_hdr *mesh_hdr; + u16 hdr_len = ieee80211_hdrlen(fc); + u16 ethertype_offset; + __be16 ethertype; + + if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr)) + goto drop_check; + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdr_len + 6)) + goto drop_check; + + mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len); + ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) + + sizeof(rfc1042_header); + + if (skb_copy_bits(rx->skb, ethertype_offset, ðertype, 2) == 0 && + ethertype == rx->sdata->control_port_protocol) + return 0; + } + +drop_check: /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && !ieee80211_is_any_nullfunc(fc) && diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 7b1bacac39c6..cbc40b358ba2 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -639,11 +639,23 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr = (void *)skb->data; + __be16 ethertype = 0; + + if (skb->len >= ETH_HLEN && skb->protocol == cpu_to_be16(ETH_P_802_3)) + skb_copy_bits(skb, 2 * ETH_ALEN, ðertype, ETH_TLEN); rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { - if (ieee80211_is_any_nullfunc(hdr->frame_control)) + if (ethertype == sdata->control_port_protocol || + ethertype == cpu_to_be16(ETH_P_PREAUTH)) + cfg80211_control_port_tx_status(&sdata->wdev, + cookie, + skb->data, + skb->len, + acked, + GFP_ATOMIC); + else if (ieee80211_is_any_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, @@ -654,12 +666,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, skb->data, skb->len, acked, GFP_ATOMIC); else - cfg80211_control_port_tx_status(&sdata->wdev, - cookie, - skb->data, - skb->len, - acked, - GFP_ATOMIC); + pr_warn("Unknown status report in ack skb\n"); + } rcu_read_unlock(); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e9ce658141f5..1a2941e5244f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3996,6 +3996,9 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); + if (skb->protocol == sdata->control_port_protocol) + ctrl_flags |= IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta, ctrl_flags, cookie); if (IS_ERR(skb)) { @@ -4206,7 +4209,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER))) ra = sdata->u.mgd.bssid; - if (!is_valid_ether_addr(ra)) + if (is_zero_ether_addr(ra)) goto out_free; multicast = is_multicast_ether_addr(ra); @@ -5371,7 +5374,8 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; if (proto == sdata->control_port_protocol) - ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO | + IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; if (unencrypted) flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index af84fce70bb0..698bc3525160 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -13,6 +13,10 @@ config MPTCP if MPTCP +config INET_MPTCP_DIAG + depends on INET_DIAG + def_tristate INET_DIAG + config MPTCP_IPV6 bool "MPTCP: IPv6 support for Multipath TCP" select IPV6 diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index c53f9b845523..2360cbd27d59 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -4,6 +4,8 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ mib.o pm_netlink.o +obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o + mptcp_crypto_test-objs := crypto_test.o mptcp_token_test-objs := token_test.o obj-$(CONFIG_MPTCP_KUNIT_TESTS) += mptcp_crypto_test.o mptcp_token_test.o diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c new file mode 100644 index 000000000000..5f390a97f556 --- /dev/null +++ b/net/mptcp/mptcp_diag.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* MPTCP socket monitoring support + * + * Copyright (c) 2020 Red Hat + * + * Author: Paolo Abeni <pabeni@redhat.com> + */ + +#include <linux/kernel.h> +#include <linux/net.h> +#include <linux/inet_diag.h> +#include <net/netlink.h> +#include <uapi/linux/mptcp.h> +#include "protocol.h" + +static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, + const struct inet_diag_req_v2 *req, + struct nlattr *bc, bool net_admin) +{ + if (!inet_diag_bc_sk(bc, sk)) + return 0; + + return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, req, NLM_F_MULTI, + net_admin); +} + +static int mptcp_diag_dump_one(struct netlink_callback *cb, + const struct inet_diag_req_v2 *req) +{ + struct sk_buff *in_skb = cb->skb; + struct mptcp_sock *msk = NULL; + struct sk_buff *rep; + int err = -ENOENT; + struct net *net; + struct sock *sk; + + net = sock_net(in_skb->sk); + msk = mptcp_token_get_sock(req->id.idiag_cookie[0]); + if (!msk) + goto out_nosk; + + err = -ENOMEM; + sk = (struct sock *)msk; + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct mptcp_info)) + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, + GFP_KERNEL); + if (!rep) + goto out; + + err = inet_sk_diag_fill(sk, inet_csk(sk), rep, cb, req, 0, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + kfree_skb(rep); + goto out; + } + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, + MSG_DONTWAIT); + if (err > 0) + err = 0; +out: + sock_put(sk); + +out_nosk: + return err; +} + +static void mptcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + const struct inet_diag_req_v2 *r) +{ + bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); + struct net *net = sock_net(skb->sk); + struct inet_diag_dump_data *cb_data; + struct mptcp_sock *msk; + struct nlattr *bc; + + cb_data = cb->data; + bc = cb_data->inet_diag_nla_bc; + + while ((msk = mptcp_token_iter_next(net, &cb->args[0], &cb->args[1])) != + NULL) { + struct inet_sock *inet = (struct inet_sock *)msk; + struct sock *sk = (struct sock *)msk; + int ret = 0; + + if (!(r->idiag_states & (1 << sk->sk_state))) + goto next; + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next; + if (r->id.idiag_sport != inet->inet_sport && + r->id.idiag_sport) + goto next; + if (r->id.idiag_dport != inet->inet_dport && + r->id.idiag_dport) + goto next; + + ret = sk_diag_dump(sk, skb, cb, r, bc, net_admin); +next: + sock_put(sk); + if (ret < 0) { + /* will retry on the same position */ + cb->args[1]--; + break; + } + cond_resched(); + } +} + +static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, + void *_info) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct mptcp_info *info = _info; + u32 flags = 0; + bool slow; + u8 val; + + r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_wqueue = sk_wmem_alloc_get(sk); + if (!info) + return; + + slow = lock_sock_fast(sk); + info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); + info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); + info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); + info->mptcpi_subflows_max = READ_ONCE(msk->pm.subflows_max); + val = READ_ONCE(msk->pm.add_addr_signal_max); + info->mptcpi_add_addr_signal_max = val; + val = READ_ONCE(msk->pm.add_addr_accept_max); + info->mptcpi_add_addr_accepted_max = val; + if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) + flags |= MPTCP_INFO_FLAG_FALLBACK; + if (READ_ONCE(msk->can_ack)) + flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; + info->mptcpi_flags = flags; + info->mptcpi_token = READ_ONCE(msk->token); + info->mptcpi_write_seq = READ_ONCE(msk->write_seq); + info->mptcpi_snd_una = atomic64_read(&msk->snd_una); + info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); + unlock_sock_fast(sk, slow); +} + +static const struct inet_diag_handler mptcp_diag_handler = { + .dump = mptcp_diag_dump, + .dump_one = mptcp_diag_dump_one, + .idiag_get_info = mptcp_diag_get_info, + .idiag_type = IPPROTO_MPTCP, + .idiag_info_size = sizeof(struct mptcp_info), +}; + +static int __init mptcp_diag_init(void) +{ + return inet_diag_register(&mptcp_diag_handler); +} + +static void __exit mptcp_diag_exit(void) +{ + inet_diag_unregister(&mptcp_diag_handler); +} + +module_init(mptcp_diag_init); +module_exit(mptcp_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b96d3660562f..19707c07efc1 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -449,9 +449,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, } static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, - struct mptcp_ext *ext) + struct sk_buff *skb, struct mptcp_ext *ext) { - if (!ext->use_map) { + if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values * if DATA_FIN is set but no data payload is mapped */ @@ -503,7 +503,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, opts->ext_copy = *mpext; if (skb && tcp_fin && subflow->data_fin_tx_enable) - mptcp_write_data_fin(subflow, &opts->ext_copy); + mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 39bfec3f1586..e5baaef5ec89 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -391,6 +391,8 @@ int mptcp_token_new_connect(struct sock *sk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); struct mptcp_sock *mptcp_token_get_sock(u32 token); +struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, + long *s_num); void mptcp_token_destroy(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 66a4990bd897..7d8106026081 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -238,6 +238,66 @@ found: rcu_read_unlock(); return msk; } +EXPORT_SYMBOL_GPL(mptcp_token_get_sock); + +/** + * mptcp_token_iter_next - iterate over the token container from given pos + * @net: namespace to be iterated + * @s_slot: start slot number + * @s_num: start number inside the given lock + * + * This function returns the first mptcp connection structure found inside the + * token container starting from the specified position, or NULL. + * + * On successful iteration, the iterator is move to the next position and the + * the acquires a reference to the returned socket. + */ +struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, + long *s_num) +{ + struct mptcp_sock *ret = NULL; + struct hlist_nulls_node *pos; + int slot, num; + + for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) { + struct token_bucket *bucket = &token_hash[slot]; + struct sock *sk; + + num = 0; + + if (hlist_nulls_empty(&bucket->msk_chain)) + continue; + + rcu_read_lock(); + sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { + ++num; + if (!net_eq(sock_net(sk), net)) + continue; + + if (num <= *s_num) + continue; + + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + continue; + + if (!net_eq(sock_net(sk), net)) { + sock_put(sk); + continue; + } + + ret = mptcp_sk(sk); + rcu_read_unlock(); + goto out; + } + rcu_read_unlock(); + } + +out: + *s_slot = slot; + *s_num = num; + return ret; +} +EXPORT_SYMBOL_GPL(mptcp_token_iter_next); /** * mptcp_token_destroy_request - remove mptcp connection/token @@ -312,7 +372,6 @@ void __init mptcp_token_init(void) EXPORT_SYMBOL_GPL(mptcp_token_new_request); EXPORT_SYMBOL_GPL(mptcp_token_new_connect); EXPORT_SYMBOL_GPL(mptcp_token_accept); -EXPORT_SYMBOL_GPL(mptcp_token_get_sock); EXPORT_SYMBOL_GPL(mptcp_token_destroy_request); EXPORT_SYMBOL_GPL(mptcp_token_destroy); #endif diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 486959f70cf3..a8ce04a4bb72 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -326,7 +326,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 2310a316e0af..2c625e0f49ec 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -363,7 +363,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index e56ced66f202..7138e080def4 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -274,7 +274,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 1ee43752d6d3..521e970be402 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -682,7 +682,7 @@ retry: } t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); if (!t->hregion) { - kfree(t); + ip_set_free(t); ret = -ENOMEM; goto out; } @@ -1533,7 +1533,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, } t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); if (!t->hregion) { - kfree(t); + ip_set_free(t); kfree(h); return -ENOMEM; } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 02f2f636798d..b3921ae92740 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -807,6 +807,31 @@ static void ip_vs_conn_rcu_free(struct rcu_head *head) kmem_cache_free(ip_vs_conn_cachep, cp); } +/* Try to delete connection while not holding reference */ +static void ip_vs_conn_del(struct ip_vs_conn *cp) +{ + if (del_timer(&cp->timer)) { + /* Drop cp->control chain too */ + if (cp->control) + cp->timeout = 0; + ip_vs_conn_expire(&cp->timer); + } +} + +/* Try to delete connection while holding reference */ +static void ip_vs_conn_del_put(struct ip_vs_conn *cp) +{ + if (del_timer(&cp->timer)) { + /* Drop cp->control chain too */ + if (cp->control) + cp->timeout = 0; + __ip_vs_conn_put(cp); + ip_vs_conn_expire(&cp->timer); + } else { + __ip_vs_conn_put(cp); + } +} + static void ip_vs_conn_expire(struct timer_list *t) { struct ip_vs_conn *cp = from_timer(cp, t, timer); @@ -827,14 +852,17 @@ static void ip_vs_conn_expire(struct timer_list *t) /* does anybody control me? */ if (ct) { + bool has_ref = !cp->timeout && __ip_vs_conn_get(ct); + ip_vs_control_del(cp); /* Drop CTL or non-assured TPL if not used anymore */ - if (!cp->timeout && !atomic_read(&ct->n_control) && + if (has_ref && !atomic_read(&ct->n_control) && (!(ct->flags & IP_VS_CONN_F_TEMPLATE) || !(ct->state & IP_VS_CTPL_S_ASSURED))) { IP_VS_DBG(4, "drop controlling connection\n"); - ct->timeout = 0; - ip_vs_conn_expire_now(ct); + ip_vs_conn_del_put(ct); + } else if (has_ref) { + __ip_vs_conn_put(ct); } } @@ -1317,8 +1345,7 @@ try_drop: drop: IP_VS_DBG(4, "drop connection\n"); - cp->timeout = 0; - ip_vs_conn_expire_now(cp); + ip_vs_conn_del(cp); } cond_resched_rcu(); } @@ -1341,19 +1368,15 @@ flush_again: hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { if (cp->ipvs != ipvs) continue; - /* As timers are expired in LIFO order, restart - * the timer of controlling connection first, so - * that it is expired after us. - */ + if (atomic_read(&cp->n_control)) + continue; cp_c = cp->control; - /* cp->control is valid only with reference to cp */ - if (cp_c && __ip_vs_conn_get(cp)) { + IP_VS_DBG(4, "del connection\n"); + ip_vs_conn_del(cp); + if (cp_c && !atomic_read(&cp_c->n_control)) { IP_VS_DBG(4, "del controlling connection\n"); - ip_vs_conn_expire_now(cp_c); - __ip_vs_conn_put(cp); + ip_vs_conn_del(cp_c); } - IP_VS_DBG(4, "del connection\n"); - ip_vs_conn_expire_now(cp); } cond_resched_rcu(); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index aa6a603a2425..b4a6b7662f3f 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2066,14 +2066,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { - bool uses_ct = false, resched = false; + bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (is_new_conn_expected(cp, conn_reuse_mode)) { - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { @@ -2081,15 +2081,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int * that uses conntrack while it is still * referenced by controlled connection(s). */ - resched = !uses_ct; + resched = !old_ct; } } if (resched) { + if (!old_ct) + cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); - if (uses_ct) + if (old_ct) return NF_DROP; cp = NULL; } @@ -2256,7 +2258,7 @@ ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, #endif -static const struct nf_hook_ops ip_vs_ops[] = { +static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, @@ -2302,7 +2304,10 @@ static const struct nf_hook_ops ip_vs_ops[] = { .hooknum = NF_INET_FORWARD, .priority = 100, }, +}; + #ifdef CONFIG_IP_VS_IPV6 +static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, @@ -2348,8 +2353,64 @@ static const struct nf_hook_ops ip_vs_ops[] = { .hooknum = NF_INET_FORWARD, .priority = 100, }, -#endif }; +#endif + +int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af) +{ + const struct nf_hook_ops *ops; + unsigned int count; + unsigned int afmask; + int ret = 0; + + if (af == AF_INET6) { +#ifdef CONFIG_IP_VS_IPV6 + ops = ip_vs_ops6; + count = ARRAY_SIZE(ip_vs_ops6); + afmask = 2; +#else + return -EINVAL; +#endif + } else { + ops = ip_vs_ops4; + count = ARRAY_SIZE(ip_vs_ops4); + afmask = 1; + } + + if (!(ipvs->hooks_afmask & afmask)) { + ret = nf_register_net_hooks(ipvs->net, ops, count); + if (ret >= 0) + ipvs->hooks_afmask |= afmask; + } + return ret; +} + +void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af) +{ + const struct nf_hook_ops *ops; + unsigned int count; + unsigned int afmask; + + if (af == AF_INET6) { +#ifdef CONFIG_IP_VS_IPV6 + ops = ip_vs_ops6; + count = ARRAY_SIZE(ip_vs_ops6); + afmask = 2; +#else + return; +#endif + } else { + ops = ip_vs_ops4; + count = ARRAY_SIZE(ip_vs_ops4); + afmask = 1; + } + + if (ipvs->hooks_afmask & afmask) { + nf_unregister_net_hooks(ipvs->net, ops, count); + ipvs->hooks_afmask &= ~afmask; + } +} + /* * Initialize IP Virtual Server netns mem. */ @@ -2425,19 +2486,6 @@ static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list) } } -static int __net_init __ip_vs_dev_init(struct net *net) -{ - int ret; - - ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); - if (ret < 0) - goto hook_fail; - return 0; - -hook_fail: - return ret; -} - static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; @@ -2446,7 +2494,8 @@ static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) EnterFunction(2); list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); - nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + ip_vs_unregister_hooks(ipvs, AF_INET); + ip_vs_unregister_hooks(ipvs, AF_INET6); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs); @@ -2462,7 +2511,6 @@ static struct pernet_operations ipvs_core_ops = { }; static struct pernet_operations ipvs_core_dev_ops = { - .init = __ip_vs_dev_init, .exit_batch = __ip_vs_dev_cleanup_batch, }; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 412656c34f20..4af83f466dfc 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -224,7 +224,8 @@ static void defense_work_handler(struct work_struct *work) update_defense_level(ipvs); if (atomic_read(&ipvs->dropentry)) ip_vs_random_dropentry(ipvs); - schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); + queue_delayed_work(system_long_wq, &ipvs->defense_work, + DEFENSE_TIMER_PERIOD); } #endif @@ -1272,6 +1273,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_scheduler *sched = NULL; struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; + int ret_hooks = -1; /* increase the module use count */ if (!ip_vs_use_count_inc()) @@ -1313,6 +1315,14 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, } #endif + if ((u->af == AF_INET && !ipvs->num_services) || + (u->af == AF_INET6 && !ipvs->num_services6)) { + ret = ip_vs_register_hooks(ipvs, u->af); + if (ret < 0) + goto out_err; + ret_hooks = ret; + } + svc = kzalloc(sizeof(struct ip_vs_service), GFP_KERNEL); if (svc == NULL) { IP_VS_DBG(1, "%s(): no memory\n", __func__); @@ -1374,6 +1384,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) ipvs->num_services++; + else if (svc->af == AF_INET6) + ipvs->num_services6++; /* Hash the service into the service table */ ip_vs_svc_hash(svc); @@ -1385,6 +1397,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, out_err: + if (ret_hooks >= 0) + ip_vs_unregister_hooks(ipvs, u->af); if (svc != NULL) { ip_vs_unbind_scheduler(svc, sched); ip_vs_service_free(svc); @@ -1500,9 +1514,15 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) struct ip_vs_pe *old_pe; struct netns_ipvs *ipvs = svc->ipvs; - /* Count only IPv4 services for old get/setsockopt interface */ - if (svc->af == AF_INET) + if (svc->af == AF_INET) { ipvs->num_services--; + if (!ipvs->num_services) + ip_vs_unregister_hooks(ipvs, svc->af); + } else if (svc->af == AF_INET6) { + ipvs->num_services6--; + if (!ipvs->num_services6) + ip_vs_unregister_hooks(ipvs, svc->af); + } ip_vs_stop_estimator(svc->ipvs, &svc->stats); @@ -4063,7 +4083,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) ipvs->sysctl_tbl = tbl; /* Schedule defense work */ INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); - schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); + queue_delayed_work(system_long_wq, &ipvs->defense_work, + DEFENSE_TIMER_PERIOD); return 0; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 79cd9dde457b..358108ff0833 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1006,7 +1006,7 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) * * @skb: skb that causes the clash * @h: tuplehash of the clashing entry already in table - * @hash_reply: hash slot for reply direction + * @reply_hash: hash slot for reply direction * * A conntrack entry can be inserted to the connection tracking table * if there is no existing entry with an identical tuple. @@ -2158,6 +2158,8 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) err = __nf_conntrack_update(net, skb, ct, ctinfo); if (err < 0) return err; + + ct = nf_ct_get(skb, &ctinfo); } return nf_confirm_cthelper(skb, ct, ctinfo); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 5fff1e040168..2a6993fa40d7 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -964,7 +964,7 @@ static int nf_flow_table_indr_offload_cmd(struct flow_block_offload *bo, nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable, extack); - return flow_indr_dev_setup_offload(dev, TC_SETUP_FT, flowtable, bo, + return flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_FT, flowtable, bo, nf_flow_table_indr_cleanup); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7647ecfa0d40..6708a4f2eec8 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -280,9 +280,15 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) if (trans == NULL) return ERR_PTR(-ENOMEM); - if (msg_type == NFT_MSG_NEWCHAIN) + if (msg_type == NFT_MSG_NEWCHAIN) { nft_activate_next(ctx->net, ctx->chain); + if (ctx->nla[NFTA_CHAIN_ID]) { + nft_trans_chain_id(trans) = + ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); + } + } + list_add_tail(&trans->list, &ctx->net->nft.commit_list); return trans; } @@ -1050,6 +1056,9 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; + ctx->chain = chain; err = nft_delrule_by_chain(ctx); @@ -1092,6 +1101,9 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; + ctx->chain = chain; err = nft_delchain(ctx); @@ -1274,6 +1286,7 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, [NFTA_CHAIN_FLAGS] = { .type = NLA_U32 }, + [NFTA_CHAIN_ID] = { .type = NLA_U32 }, }; static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = { @@ -1406,13 +1419,12 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, lockdep_commit_lock_is_held(net)); if (nft_dump_stats(skb, stats)) goto nla_put_failure; - - if ((chain->flags & NFT_CHAIN_HW_OFFLOAD) && - nla_put_be32(skb, NFTA_CHAIN_FLAGS, - htonl(NFT_CHAIN_HW_OFFLOAD))) - goto nla_put_failure; } + if (chain->flags && + nla_put_be32(skb, NFTA_CHAIN_FLAGS, htonl(chain->flags))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; @@ -1614,7 +1626,7 @@ static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) kvfree(chain->rules_next); } -static void nf_tables_chain_destroy(struct nft_ctx *ctx) +void nf_tables_chain_destroy(struct nft_ctx *ctx) { struct nft_chain *chain = ctx->chain; struct nft_hook *hook, *next; @@ -1896,7 +1908,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, nft_basechain_hook_init(&basechain->ops, family, hook, chain); } - chain->flags |= NFT_BASE_CHAIN | flags; + chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && nft_chain_offload_priority(basechain) < 0) @@ -1907,6 +1919,22 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, return 0; } +static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) +{ + int err; + + err = rhltable_insert_key(&table->chains_ht, chain->name, + &chain->rhlhead, nft_chain_ht_params); + if (err) + return err; + + list_add_tail_rcu(&chain->list, &table->chains); + + return 0; +} + +static u64 chain_id; + static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, u8 policy, u32 flags) { @@ -1915,6 +1943,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_base_chain *basechain; struct nft_stats __percpu *stats; struct net *net = ctx->net; + char name[NFT_NAME_MAXLEN]; struct nft_trans *trans; struct nft_chain *chain; struct nft_rule **rules; @@ -1926,6 +1955,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_HOOK]) { struct nft_chain_hook hook; + if (flags & NFT_CHAIN_BINDING) + return -EOPNOTSUPP; + err = nft_chain_parse_hook(net, nla, &hook, family, true); if (err < 0) return err; @@ -1955,16 +1987,33 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, return err; } } else { + if (flags & NFT_CHAIN_BASE) + return -EINVAL; + if (flags & NFT_CHAIN_HW_OFFLOAD) + return -EOPNOTSUPP; + chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (chain == NULL) return -ENOMEM; + + chain->flags = flags; } ctx->chain = chain; INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); chain->table = table; - chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + + if (nla[NFTA_CHAIN_NAME]) { + chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + } else { + if (!(flags & NFT_CHAIN_BINDING)) + return -EINVAL; + + snprintf(name, sizeof(name), "__chain%llu", ++chain_id); + chain->name = kstrdup(name, GFP_KERNEL); + } + if (!chain->name) { err = -ENOMEM; goto err1; @@ -1984,16 +2033,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err1; - err = rhltable_insert_key(&table->chains_ht, chain->name, - &chain->rhlhead, nft_chain_ht_params); - if (err) - goto err2; - trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - rhltable_remove(&table->chains_ht, &chain->rhlhead, - nft_chain_ht_params); goto err2; } @@ -2001,8 +2043,13 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nft_is_base_chain(chain)) nft_trans_chain_policy(trans) = policy; + err = nft_chain_add(table, chain); + if (err < 0) { + nft_trans_destroy(trans); + goto err2; + } + table->use++; - list_add_tail_rcu(&chain->list, &table->chains); return 0; err2: @@ -2146,6 +2193,22 @@ err: return err; } +static struct nft_chain *nft_chain_lookup_byid(const struct net *net, + const struct nlattr *nla) +{ + u32 id = ntohl(nla_get_be32(nla)); + struct nft_trans *trans; + + list_for_each_entry(trans, &net->nft.commit_list, list) { + struct nft_chain *chain = trans->ctx.chain; + + if (trans->msg_type == NFT_MSG_NEWCHAIN && + id == nft_trans_chain_id(trans)) + return chain; + } + return ERR_PTR(-ENOENT); +} + static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -2154,9 +2217,9 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + struct nft_chain *chain = NULL; const struct nlattr *attr; struct nft_table *table; - struct nft_chain *chain; u8 policy = NF_ACCEPT; struct nft_ctx ctx; u64 handle = 0; @@ -2181,7 +2244,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } attr = nla[NFTA_CHAIN_HANDLE]; - } else { + } else if (nla[NFTA_CHAIN_NAME]) { chain = nft_chain_lookup(net, table, attr, genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) != -ENOENT) { @@ -2190,6 +2253,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, } chain = NULL; } + } else if (!nla[NFTA_CHAIN_ID]) { + return -EINVAL; } if (nla[NFTA_CHAIN_POLICY]) { @@ -2220,6 +2285,9 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, else if (chain) flags = chain->flags; + if (flags & ~NFT_CHAIN_FLAGS) + return -EOPNOTSUPP; + nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); if (chain != NULL) { @@ -2230,7 +2298,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - flags |= chain->flags & NFT_BASE_CHAIN; + flags |= chain->flags & NFT_CHAIN_BASE; return nf_tables_updchain(&ctx, genmask, policy, flags); } @@ -2307,7 +2375,7 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, /** * nft_register_expr - register nf_tables expr type - * @ops: expr type + * @type: expr type * * Registers the expr type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. @@ -2326,7 +2394,7 @@ EXPORT_SYMBOL_GPL(nft_register_expr); /** * nft_unregister_expr - unregister nf_tables expr type - * @ops: expr type + * @type: expr type * * Unregisters the expr typefor use with nf_tables. */ @@ -2624,6 +2692,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { .len = NFT_USERDATA_MAXLEN }, [NFTA_RULE_ID] = { .type = NLA_U32 }, [NFTA_RULE_POSITION_ID] = { .type = NLA_U32 }, + [NFTA_RULE_CHAIN_ID] = { .type = NLA_U32 }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, @@ -2938,8 +3007,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } -static void nf_tables_rule_release(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); @@ -3030,10 +3098,24 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); - if (IS_ERR(chain)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); - return PTR_ERR(chain); + if (nla[NFTA_RULE_CHAIN]) { + chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], + genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); + return PTR_ERR(chain); + } + if (nft_chain_is_bound(chain)) + return -EOPNOTSUPP; + + } else if (nla[NFTA_RULE_CHAIN_ID]) { + chain = nft_chain_lookup_byid(net, nla[NFTA_RULE_CHAIN_ID]); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); + return PTR_ERR(chain); + } + } else { + return -EINVAL; } if (nla[NFTA_RULE_HANDLE]) { @@ -3245,6 +3327,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } + if (nft_chain_is_bound(chain)) + return -EOPNOTSUPP; } nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); @@ -5281,11 +5365,24 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, */ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { + struct nft_chain *chain; + struct nft_rule *rule; + if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->verdict.chain->use++; + chain = data->verdict.chain; + chain->use++; + + if (!nft_chain_is_bound(chain)) + break; + + chain->table->use++; + list_for_each_entry(rule, &chain->rules, list) + chain->use++; + + nft_chain_add(chain->table, chain); break; } } @@ -5498,7 +5595,7 @@ struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, /** * nft_register_obj- register nf_tables stateful object type - * @obj: object type + * @obj_type: object type * * Registers the object type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. @@ -5517,7 +5614,7 @@ EXPORT_SYMBOL_GPL(nft_register_obj); /** * nft_unregister_obj - unregister nf_tables object type - * @obj: object type + * @obj_type: object type * * Unregisters the object type for use with nf_tables. */ @@ -7425,7 +7522,7 @@ static void nft_obj_del(struct nft_object *obj) list_del_rcu(&obj->list); } -static void nft_chain_del(struct nft_chain *chain) +void nft_chain_del(struct nft_chain *chain) { struct nft_table *table = chain->table; @@ -7776,6 +7873,10 @@ static int __nf_tables_abort(struct net *net, bool autoload) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { + if (nft_chain_is_bound(trans->ctx.chain)) { + nft_trans_destroy(trans); + break; + } trans->ctx.table->use--; nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, @@ -8205,6 +8306,7 @@ static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, [NFTA_VERDICT_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, + [NFTA_VERDICT_CHAIN_ID] = { .type = NLA_U32 }, }; static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, @@ -8241,10 +8343,19 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, break; case NFT_JUMP: case NFT_GOTO: - if (!tb[NFTA_VERDICT_CHAIN]) + if (tb[NFTA_VERDICT_CHAIN]) { + chain = nft_chain_lookup(ctx->net, ctx->table, + tb[NFTA_VERDICT_CHAIN], + genmask); + } else if (tb[NFTA_VERDICT_CHAIN_ID]) { + chain = nft_chain_lookup_byid(ctx->net, + tb[NFTA_VERDICT_CHAIN_ID]); + if (IS_ERR(chain)) + return PTR_ERR(chain); + } else { return -EINVAL; - chain = nft_chain_lookup(ctx->net, ctx->table, - tb[NFTA_VERDICT_CHAIN], genmask); + } + if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) @@ -8262,10 +8373,23 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, static void nft_verdict_uninit(const struct nft_data *data) { + struct nft_chain *chain; + struct nft_rule *rule; + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->verdict.chain->use--; + chain = data->verdict.chain; + chain->use--; + + if (!nft_chain_is_bound(chain)) + break; + + chain->table->use--; + list_for_each_entry(rule, &chain->rules, list) + chain->use--; + + nft_chain_del(chain); break; } } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index c7cf1cde46de..9ef37c1b7b3b 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -312,7 +312,7 @@ static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); - err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, basechain, &bo, + err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index c7f0ef73d939..9e556638bb32 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -54,6 +54,23 @@ static int nft_immediate_init(const struct nft_ctx *ctx, if (err < 0) goto err1; + if (priv->dreg == NFT_REG_VERDICT) { + struct nft_chain *chain = priv->data.verdict.chain; + + switch (priv->data.verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + if (nft_chain_is_bound(chain)) { + err = -EBUSY; + goto err1; + } + chain->bound = true; + break; + default: + break; + } + } + return 0; err1: @@ -81,6 +98,39 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } +static void nft_immediate_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg != NFT_REG_VERDICT) + return; + + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + + if (!nft_chain_is_bound(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nf_tables_rule_release(&chain_ctx, rule); + + nf_tables_chain_destroy(&chain_ctx); + break; + default: + break; + } +} + static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); @@ -170,6 +220,7 @@ static const struct nft_expr_ops nft_imm_ops = { .init = nft_immediate_init, .activate = nft_immediate_activate, .deactivate = nft_immediate_deactivate, + .destroy = nft_immediate_destroy, .dump = nft_immediate_dump, .validate = nft_immediate_validate, .offload = nft_immediate_offload, diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 86eafbb0fdd0..61fb7e8afbf0 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -30,7 +30,8 @@ int nft_reject_validate(const struct nft_ctx *ctx, return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | - (1 << NF_INET_LOCAL_OUT)); + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_PRE_ROUTING)); } EXPORT_SYMBOL_GPL(nft_reject_validate); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 8c04388296b0..cc6082a5f7ad 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -401,7 +401,7 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, * nft_pipapo_lookup() - Lookup function * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @key: nftables API element representation containing key data * @ext: nftables API extension pointer, filled with matching reference * * For more details, see DOC: Theory of Operation. @@ -1075,7 +1075,7 @@ out: * @m: Matching data, including mapping table * @map: Table of rule maps: array of first rule and amount of rules * in next field a given rule maps to, for each field - * @ext: For last field, nft_set_ext pointer matching rules map to + * @e: For last field, nft_set_ext pointer matching rules map to */ static void pipapo_map(struct nft_pipapo_match *m, union nft_pipapo_map_bucket map[NFT_PIPAPO_MAX_FIELDS], @@ -1099,7 +1099,7 @@ static void pipapo_map(struct nft_pipapo_match *m, /** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions - * @bsize_max Maximum bucket size, scratch maps cover two buckets + * @bsize_max: Maximum bucket size, scratch maps cover two buckets * * Return: 0 on success, -ENOMEM on failure. */ @@ -1249,8 +1249,6 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (err) return err; - this_cpu_write(nft_pipapo_scratch_index, false); - m->bsize_max = bsize_max; } else { put_cpu_ptr(m->scratch); @@ -1449,7 +1447,7 @@ static void pipapo_unmap(union nft_pipapo_map_bucket *mt, int rules, /** * pipapo_drop() - Delete entry from lookup and mapping tables, given rule map * @m: Matching data - * @rulemap Table of rule maps, arrays of first rule and amount of rules + * @rulemap: Table of rule maps, arrays of first rule and amount of rules * in next field a given entry maps to, for each field * * For each rule in lookup table buckets mapping to this set of rules, drop diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index a1f2320ecc16..d07de2c0fbc7 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -92,7 +92,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) /** * netlbl_domhsh_hash - Hashing function for the domain hash table - * @domain: the domain name to hash + * @key: the domain name to hash * * Description: * This is the hashing function for the domain hash table, it returns the diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 55ee680e9db1..9395ee8a868d 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -351,22 +351,11 @@ int genl_register_family(struct genl_family *family) start = end = GENL_ID_VFS_DQUOT; } - if (family->maxattr && !family->parallel_ops) { - family->attrbuf = kmalloc_array(family->maxattr + 1, - sizeof(struct nlattr *), - GFP_KERNEL); - if (family->attrbuf == NULL) { - err = -ENOMEM; - goto errout_locked; - } - } else - family->attrbuf = NULL; - family->id = idr_alloc_cyclic(&genl_fam_idr, family, start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; - goto errout_free; + goto errout_locked; } err = genl_validate_assign_mc_groups(family); @@ -385,8 +374,6 @@ int genl_register_family(struct genl_family *family) errout_remove: idr_remove(&genl_fam_idr, family->id); -errout_free: - kfree(family->attrbuf); errout_locked: genl_unlock_all(); return err; @@ -419,8 +406,6 @@ int genl_unregister_family(const struct genl_family *family) atomic_read(&genl_sk_destructing_cnt) == 0); genl_unlock(); - kfree(family->attrbuf); - genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); return 0; @@ -485,30 +470,23 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, if (!family->maxattr) return NULL; - if (family->parallel_ops) { - attrbuf = kmalloc_array(family->maxattr + 1, - sizeof(struct nlattr *), GFP_KERNEL); - if (!attrbuf) - return ERR_PTR(-ENOMEM); - } else { - attrbuf = family->attrbuf; - } + attrbuf = kmalloc_array(family->maxattr + 1, + sizeof(struct nlattr *), GFP_KERNEL); + if (!attrbuf) + return ERR_PTR(-ENOMEM); err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); if (err) { - if (family->parallel_ops) - kfree(attrbuf); + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; } -static void genl_family_rcv_msg_attrs_free(const struct genl_family *family, - struct nlattr **attrbuf) +static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf) { - if (family->parallel_ops) - kfree(attrbuf); + kfree(attrbuf); } struct genl_start_context { @@ -542,7 +520,7 @@ static int genl_start(struct netlink_callback *cb) no_attrs: info = genl_dumpit_info_alloc(); if (!info) { - genl_family_rcv_msg_attrs_free(ctx->family, attrs); + genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } info->family = ctx->family; @@ -559,7 +537,7 @@ no_attrs: } if (rc) { - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } @@ -588,7 +566,7 @@ static int genl_lock_done(struct netlink_callback *cb) rc = ops->done(cb); genl_unlock(); } - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } @@ -601,7 +579,7 @@ static int genl_parallel_done(struct netlink_callback *cb) if (ops->done) rc = ops->done(cb); - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } @@ -694,7 +672,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, family->post_doit(ops, skb, &info); out: - genl_family_rcv_msg_attrs_free(family, attrbuf); + genl_family_rcv_msg_attrs_free(attrbuf); return err; } @@ -1166,60 +1144,11 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; -static int genl_bind(struct net *net, int group) -{ - struct genl_family *f; - int err = -ENOENT; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } - } - up_read(&cb_lock); - - return err; -} - -static void genl_unbind(struct net *net, int group) -{ - struct genl_family *f; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } - } - up_read(&cb_lock); -} - static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, - .bind = genl_bind, - .unbind = genl_unbind, }; /* we'll bump the group number right afterwards */ diff --git a/net/nfc/core.c b/net/nfc/core.c index c5f9c3ee82f8..eb377f87bcae 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -704,7 +704,6 @@ EXPORT_SYMBOL(nfc_tm_deactivated); * nfc_alloc_send_skb - allocate a skb for data exchange responses * * @size: size to allocate - * @gfp: gfp flags */ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, @@ -749,7 +748,7 @@ EXPORT_SYMBOL(nfc_alloc_recv_skb); * * @dev: The nfc device that found the targets * @targets: array of nfc targets found - * @ntargets: targets array size + * @n_targets: targets array size * * The device driver must call this function when one or many nfc targets * are found. After calling this function, the device driver must stop diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 7cd524884304..f7b7dc5fe84a 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1182,7 +1182,7 @@ EXPORT_SYMBOL(nci_free_device); /** * nci_register_device - register a nci device in the nfc subsystem * - * @dev: The nci device to register + * @ndev: The nci device to register */ int nci_register_device(struct nci_dev *ndev) { @@ -1246,7 +1246,7 @@ EXPORT_SYMBOL(nci_register_device); /** * nci_unregister_device - unregister a nci device in the nfc subsystem * - * @dev: The nci device to unregister + * @ndev: The nci device to unregister */ void nci_unregister_device(struct nci_dev *ndev) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 79252d4887ff..9d3e50c4d29f 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1763,11 +1763,11 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val) * does not include any don't care bit. * @net: Used to determine per-namespace field support. * @match: receives the extracted flow match information. - * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute + * @nla_key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute * sequence. The fields should of the packet that triggered the creation * of this flow. - * @mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink - * attribute specifies the mask field of the wildcarded flow. + * @nla_mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* + * Netlink attribute specifies the mask field of the wildcarded flow. * @log: Boolean to allow kernel error logging. Normally true, but when * probing for feature compatibility this should be passed in as false to * suppress unnecessary error logging. diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 47febb4504f0..0d44c5c013fa 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -87,6 +87,7 @@ EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister); /** * ovs_vport_locate - find a port that has already been created * + * @net: network namespace * @name: name of port to find * * Must be called with ovs or RCU read lock. @@ -418,7 +419,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) * * @vport: vport that received the packet * @skb: skb that was received - * @tun_key: tunnel (if any) that carried packet + * @tun_info: tunnel (if any) that carried packet * * Must be called with rcu_read_lock. The packet cannot be shared and * skb->data should point to the Ethernet header. diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2d8d6131bc5f..24a8c3c6da0d 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -166,6 +166,7 @@ static void __qrtr_node_release(struct kref *kref) { struct qrtr_node *node = container_of(kref, struct qrtr_node, ref); struct radix_tree_iter iter; + struct qrtr_tx_flow *flow; unsigned long flags; void __rcu **slot; @@ -181,8 +182,9 @@ static void __qrtr_node_release(struct kref *kref) /* Free tx flow counters */ radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + flow = *slot; radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot); - kfree(*slot); + kfree(flow); } kfree(node); } @@ -427,7 +429,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) unsigned int ver; size_t hdrlen; - if (len & 3) + if (len == 0 || len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); @@ -441,6 +443,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) switch (ver) { case QRTR_PROTO_VER_1: + if (len < sizeof(*v1)) + goto err; v1 = data; hdrlen = sizeof(*v1); @@ -454,6 +458,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) size = le32_to_cpu(v1->size); break; case QRTR_PROTO_VER_2: + if (len < sizeof(*v2)) + goto err; v2 = data; hdrlen = sizeof(*v2) + v2->optlen; diff --git a/net/rds/connection.c b/net/rds/connection.c index ed7f2133acc2..f2fcab182095 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -905,6 +905,17 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp) } EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down); +/* Check connectivity of all paths + */ +void rds_check_all_paths(struct rds_connection *conn) +{ + int i = 0; + + do { + rds_conn_path_connect_if_down(&conn->c_path[i]); + } while (++i < conn->c_npaths); +} + void rds_conn_connect_if_down(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); diff --git a/net/rds/rds.h b/net/rds/rds.h index 6019b0c004a9..106e862996b9 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -778,6 +778,7 @@ void rds_conn_drop(struct rds_connection *conn); void rds_conn_path_drop(struct rds_conn_path *cpath, bool destroy); void rds_conn_connect_if_down(struct rds_connection *conn); void rds_conn_path_connect_if_down(struct rds_conn_path *cp); +void rds_check_all_paths(struct rds_connection *conn); void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, @@ -823,6 +824,12 @@ rds_conn_path_up(struct rds_conn_path *cp) } static inline int +rds_conn_path_down(struct rds_conn_path *cp) +{ + return atomic_read(&cp->cp_state) == RDS_CONN_DOWN; +} + +static inline int rds_conn_up(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); diff --git a/net/rds/send.c b/net/rds/send.c index 68e2bdb08fd0..9a529a01cdc6 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1340,7 +1340,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - rds_conn_path_connect_if_down(cpath); + if (rds_conn_path_down(cpath)) + rds_check_all_paths(conn); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); if (ret) { diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 394189b81849..cd7d0d204c74 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -267,7 +267,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue * @upgrade: Request service upgrade for call - * @intr: The call is interruptible + * @interruptibility: The call is interruptible, or can be canceled. * @debug_id: The debug ID for tracing to be assigned to the call * * Allow a kernel service to begin a call on the nominated socket. This just diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 43a243081e7d..f901421b0634 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); - if (skb->protocol == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index cb8608f0a77a..f5826e457679 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - protocol = tc_skb_protocol(skb); + protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): @@ -598,7 +598,8 @@ again: if (!tcf_csum_ipv6(skb, update_flags)) goto drop; break; - case cpu_to_be16(ETH_P_8021AD): /* fall through */ + case cpu_to_be16(ETH_P_8021AD): + fallthrough; case cpu_to_be16(ETH_P_8021Q): if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) { protocol = skb->protocol; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 1b9c6d4a1b6b..3893e03454db 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -624,7 +624,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): family = NFPROTO_IPV4; break; @@ -748,6 +748,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { + __be16 proto = skb_protocol(skb, true); int hooknum, err = NF_ACCEPT; /* See HOOK2MANIP(). */ @@ -759,14 +760,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (proto == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && - skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -783,7 +783,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } } /* Non-ICMP, fall thru to initialize if needed. */ - /* fall through */ + fallthrough; case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. @@ -925,6 +925,8 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, force = p->ct_action & TCA_CT_ACT_FORCE; tmpl = p->tmpl; + tcf_lastuse_update(&c->tcf_tm); + if (clear) { ct = nf_ct_get(skb, &ctinfo); if (ct) { @@ -1550,4 +1552,3 @@ MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>"); MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>"); MODULE_DESCRIPTION("Connection tracking action"); MODULE_LICENSE("GPL v2"); - diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 19649623493b..b5042f3ea079 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); - if (tc_skb_protocol(skb) == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV4; - } else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index be3f215cd027..8118e2640979 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_PUSH: - new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); + new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 361b863e0634..d0652386c6e2 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e9e119ea6813..322b279154de 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -622,7 +622,7 @@ static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); static void tcf_block_offload_init(struct flow_block_offload *bo, - struct net_device *dev, + struct net_device *dev, struct Qdisc *sch, enum flow_block_command command, enum flow_block_binder_type binder_type, struct flow_block *flow_block, @@ -634,6 +634,7 @@ static void tcf_block_offload_init(struct flow_block_offload *bo, bo->block = flow_block; bo->block_shared = shared; bo->extack = extack; + bo->sch = sch; INIT_LIST_HEAD(&bo->cb_list); } @@ -644,10 +645,11 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) { struct tcf_block *block = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; + struct Qdisc *sch = block_cb->indr.sch; struct netlink_ext_ack extack = {}; struct flow_block_offload bo; - tcf_block_offload_init(&bo, dev, FLOW_BLOCK_UNBIND, + tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND, block_cb->indr.binder_type, &block->flow_block, tcf_block_shared(block), &extack); @@ -666,14 +668,14 @@ static bool tcf_block_offload_in_use(struct tcf_block *block) } static int tcf_block_offload_cmd(struct tcf_block *block, - struct net_device *dev, + struct net_device *dev, struct Qdisc *sch, struct tcf_block_ext_info *ei, enum flow_block_command command, struct netlink_ext_ack *extack) { struct flow_block_offload bo = {}; - tcf_block_offload_init(&bo, dev, command, ei->binder_type, + tcf_block_offload_init(&bo, dev, sch, command, ei->binder_type, &block->flow_block, tcf_block_shared(block), extack); @@ -690,7 +692,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block, return tcf_block_setup(block, &bo); } - flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo, + flow_indr_dev_setup_offload(dev, sch, TC_SETUP_BLOCK, block, &bo, tc_block_indr_cleanup); tcf_block_setup(block, &bo); @@ -717,7 +719,7 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, goto err_unlock; } - err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack); + err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_BIND, extack); if (err == -EOPNOTSUPP) goto no_offload_dev_inc; if (err) @@ -744,7 +746,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, int err; down_write(&block->cb_lock); - err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL); + err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_UNBIND, NULL); if (err == -EOPNOTSUPP) goto no_offload_dev_dec; up_write(&block->cb_lock); @@ -1538,7 +1540,7 @@ static inline int __tcf_classify(struct sk_buff *skb, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); + __be16 protocol = skb_protocol(skb, false); int err; if (tp->protocol != protocol && diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 80ae7b9fa90a..ab53a93b2f2b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -164,7 +164,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 391971672d54..acd8e05c2ba5 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -313,7 +313,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c index b9a94fdf9397..5ea84decec19 100644 --- a/net/sched/em_canid.c +++ b/net/sched/em_canid.c @@ -40,6 +40,7 @@ struct canid_match { /** * em_canid_get_id() - Extracts Can ID out of the sk_buff structure. + * @skb: buffer to extract Can ID from */ static canid_t em_canid_get_id(struct sk_buff *skb) { diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df00566d327d..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c index 18755d29fd15..3650117da47f 100644 --- a/net/sched/em_ipt.c +++ b/net/sched/em_ipt.c @@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, struct nf_hook_state state; int ret; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index d99966a55c84..46254968d390 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -195,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) diff --git a/net/sched/ematch.c b/net/sched/ematch.c index dd3b8c11a2e0..f885bea5b452 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -389,7 +389,6 @@ EXPORT_SYMBOL(tcf_em_tree_validate); /** * tcf_em_tree_destroy - destroy an ematch tree * - * @tp: classifier kind handle * @tree: ematch tree to be deleted * * This functions destroys an ematch tree previously created by @@ -425,7 +424,7 @@ EXPORT_SYMBOL(tcf_em_tree_destroy); * tcf_em_tree_dump - dump ematch tree into a rtnl message * * @skb: skb holding the rtnl message - * @t: ematch tree to be dumped + * @tree: ematch tree to be dumped * @tlv: TLV type to be used to encapsulate the tree * * This function dumps a ematch tree into a rtnl message. It is valid to diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index fb6b16c4e46d..1d5e422d9be2 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); + p->link.vcc = NULL; + p->link.sock = NULL; + p->link.common.classid = sch->handle; + p->link.ref = 1; err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, extack); if (err) return err; - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index e9c502dd29a2..b3cdcd86cbfd 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -592,7 +592,7 @@ static bool cake_update_flowkeys(struct flow_keys *keys, bool rev = !skb->_nfct, upd = false; __be32 ip; - if (tc_skb_protocol(skb) != htons(ETH_P_IP)) + if (skb_protocol(skb, true) != htons(ETH_P_IP)) return false; if (!nf_ct_get_tuple_skb(&tuple, skb)) @@ -1557,7 +1557,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) u16 *buf, buf_; u8 dscp; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 052d4a1af69a..9e16fdf47fe7 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -250,7 +250,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; case TC_ACT_RECLASSIFY: diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 0d5c9a8ec61d..ad14df2ecf3a 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -324,7 +324,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index fbe49fffcdbb..76a9c4f277f2 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *ro if (p->set_tc_index) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || @@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, p->mv[index].value); @@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); + __func__, ntohs(skb_protocol(skb, true))); break; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 373dc5855d4e..1af86f30b18e 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -397,7 +397,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6bf979f95509..bca016ffc069 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -99,7 +99,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return 0; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index a27a250ab8f9..741840b9994f 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -102,7 +102,7 @@ static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return 0; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 7f6670044f0a..13ba8648bb63 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1136,7 +1136,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 52fc513688b1..b07f29059f47 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -239,7 +239,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 648611f5c105..56bdc4bcdc63 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -43,7 +43,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index a3e187f2603c..46b7ce81c6e3 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -46,7 +46,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index ede854516825..3cfe6262eb00 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -699,7 +699,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return NULL; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index d2a6e78262bb..356f6d1d30db 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -265,7 +265,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return false; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 46cdefd69e44..a1314510dc69 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -186,7 +186,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - /* fall through */ + fallthrough; case TC_ACT_SHOT: return 0; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 511964653476..b586eec2eaeb 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index d5627df24215..779f4142a11d 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -27,6 +27,7 @@ #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 +#define SMC_CLC_RECV_BUF_LEN 100 /* eye catcher "SMCR" EBCDIC for CLC messages */ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; @@ -36,7 +37,7 @@ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; /* check if received message has a correct header length and contains valid * heading and trailing eyecatchers */ -static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) +static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) { struct smc_clc_msg_proposal_prefix *pclc_prfx; struct smc_clc_msg_accept_confirm *clc; @@ -49,12 +50,9 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) return false; switch (clcm->type) { case SMC_CLC_PROPOSAL: - if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D && - clcm->path != SMC_TYPE_B) - return false; pclc = (struct smc_clc_msg_proposal *)clcm; pclc_prfx = smc_clc_proposal_get_prefix(pclc); - if (ntohs(pclc->hdr.length) != + if (ntohs(pclc->hdr.length) < sizeof(*pclc) + ntohs(pclc->iparea_offset) + sizeof(*pclc_prfx) + pclc_prfx->ipv6_prefixes_cnt * @@ -86,7 +84,8 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) default: return false; } - if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && + if (check_trl && + memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER))) return false; return true; @@ -276,7 +275,8 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, struct msghdr msg = {NULL, 0}; int reason_code = 0; struct kvec vec = {buf, buflen}; - int len, datlen; + int len, datlen, recvlen; + bool check_trl = true; int krflags; /* peek the first few bytes to determine length of data to receive @@ -320,10 +320,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || - (datlen > buflen) || - (clcm->version != SMC_CLC_V1) || - (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D && - clcm->path != SMC_TYPE_B) || + (clcm->version < SMC_CLC_V1) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; @@ -331,16 +328,38 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, goto out; } + if (clcm->type == SMC_CLC_PROPOSAL && clcm->path == SMC_TYPE_N) + reason_code = SMC_CLC_DECL_VERSMISMAT; /* just V2 offered */ + /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen); + if (datlen > buflen) { + check_trl = false; + recvlen = buflen; + } else { + recvlen = datlen; + } + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, recvlen); krflags = MSG_WAITALL; len = sock_recvmsg(smc->clcsock, &msg, krflags); - if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { + if (len < recvlen || !smc_clc_msg_hdr_valid(clcm, check_trl)) { smc->sk.sk_err = EPROTO; reason_code = -EPROTO; goto out; } + datlen -= len; + while (datlen) { + u8 tmp[SMC_CLC_RECV_BUF_LEN]; + + vec.iov_base = &tmp; + vec.iov_len = SMC_CLC_RECV_BUF_LEN; + /* receive remaining proposal message */ + recvlen = datlen > SMC_CLC_RECV_BUF_LEN ? + SMC_CLC_RECV_BUF_LEN : datlen; + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, recvlen); + len = sock_recvmsg(smc->clcsock, &msg, krflags); + datlen -= len; + } if (clcm->type == SMC_CLC_DECLINE) { struct smc_clc_msg_decline *dclc; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 465876701b75..76c2b150d040 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -25,6 +25,7 @@ #define SMC_CLC_V1 0x1 /* SMC version */ #define SMC_TYPE_R 0 /* SMC-R only */ #define SMC_TYPE_D 1 /* SMC-D only */ +#define SMC_TYPE_N 2 /* neither SMC-R nor SMC-D */ #define SMC_TYPE_B 3 /* SMC-R and SMC-D */ #define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */ #define CLC_WAIT_TIME_SHORT HZ /* short wait time on clcsock */ @@ -46,6 +47,7 @@ #define SMC_CLC_DECL_ISMVLANERR 0x03090000 /* err to reg vlan id on ism dev */ #define SMC_CLC_DECL_NOACTLINK 0x030a0000 /* no active smc-r link in lgr */ #define SMC_CLC_DECL_NOSRVLINK 0x030b0000 /* SMC-R link from srv not found */ +#define SMC_CLC_DECL_VERSMISMAT 0x030c0000 /* SMC version mismatch */ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ #define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 7964a21e5e6f..f69d205b3e11 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -15,6 +15,7 @@ #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/reboot.h> +#include <linux/mutex.h> #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> @@ -247,7 +248,8 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) if (smc_link_usable(lnk)) lnk->state = SMC_LNK_INACTIVE; } - wake_up_interruptible_all(&lgr->llc_waiter); + wake_up_all(&lgr->llc_msg_waiter); + wake_up_all(&lgr->llc_flow_waiter); } static void smc_lgr_free(struct smc_link_group *lgr); @@ -1130,18 +1132,19 @@ static void smcr_link_up(struct smc_link_group *lgr, return; if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* some other llc task is ongoing */ - wait_event_interruptible_timeout(lgr->llc_waiter, - (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), + wait_event_timeout(lgr->llc_flow_waiter, + (list_empty(&lgr->list) || + lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); } - if (list_empty(&lgr->list) || - !smc_ib_port_active(smcibdev, ibport)) - return; /* lgr or device no longer active */ - link = smc_llc_usable_link(lgr); - if (!link) - return; - smc_llc_send_add_link(link, smcibdev->mac[ibport - 1], gid, - NULL, SMC_LLC_REQ); + /* lgr or device no longer active? */ + if (!list_empty(&lgr->list) && + smc_ib_port_active(smcibdev, ibport)) + link = smc_llc_usable_link(lgr); + if (link) + smc_llc_send_add_link(link, smcibdev->mac[ibport - 1], + gid, NULL, SMC_LLC_REQ); + wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } @@ -1195,13 +1198,17 @@ static void smcr_link_down(struct smc_link *lnk) if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ mutex_unlock(&lgr->llc_conf_mutex); - wait_event_interruptible_timeout(lgr->llc_waiter, - (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), + wait_event_timeout(lgr->llc_flow_waiter, + (list_empty(&lgr->list) || + lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); mutex_lock(&lgr->llc_conf_mutex); } - smc_llc_send_delete_link(to_lnk, del_link_id, SMC_LLC_REQ, true, - SMC_LLC_DEL_LOST_PATH); + if (!list_empty(&lgr->list)) + smc_llc_send_delete_link(to_lnk, del_link_id, + SMC_LLC_REQ, true, + SMC_LLC_DEL_LOST_PATH); + wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } @@ -1262,7 +1269,7 @@ static void smc_link_down_work(struct work_struct *work) if (list_empty(&lgr->list)) return; - wake_up_interruptible_all(&lgr->llc_waiter); + wake_up_all(&lgr->llc_msg_waiter); mutex_lock(&lgr->llc_conf_mutex); smcr_link_down(link); mutex_unlock(&lgr->llc_conf_mutex); @@ -1955,20 +1962,20 @@ static void smc_core_going_away(void) struct smc_ib_device *smcibdev; struct smcd_dev *smcd; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { int i; for (i = 0; i < SMC_MAX_PORTS; i++) set_bit(i, smcibdev->ports_going_away); } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { smcd->going_away = 1; } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); } /* Clean up all SMC link groups */ @@ -1980,10 +1987,10 @@ static void smc_lgrs_shutdown(void) smc_smcr_terminate_all(NULL); - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) smc_smcd_terminate_all(smcd); - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); } static int smc_core_reboot_event(struct notifier_block *this, diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 86d160f0d187..c3ff512fd891 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -262,8 +262,10 @@ struct smc_link_group { struct work_struct llc_del_link_work; struct work_struct llc_event_work; /* llc event worker */ - wait_queue_head_t llc_waiter; + wait_queue_head_t llc_flow_waiter; /* w4 next llc event */ + wait_queue_head_t llc_msg_waiter; + /* w4 next llc msg */ struct smc_llc_flow llc_flow_lcl; /* llc local control field */ struct smc_llc_flow llc_flow_rmt; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 562a52d01ad1..7637fdebbb78 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -16,6 +16,7 @@ #include <linux/workqueue.h> #include <linux/scatterlist.h> #include <linux/wait.h> +#include <linux/mutex.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> @@ -33,7 +34,7 @@ #define SMC_QP_RNR_RETRY 7 /* 7: infinite */ struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */ - .lock = __SPIN_LOCK_UNLOCKED(smc_ib_devices.lock), + .mutex = __MUTEX_INITIALIZER(smc_ib_devices.mutex), .list = LIST_HEAD_INIT(smc_ib_devices.list), }; @@ -565,9 +566,9 @@ static int smc_ib_add_dev(struct ib_device *ibdev) INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work); atomic_set(&smcibdev->lnk_cnt, 0); init_waitqueue_head(&smcibdev->lnks_deleted); - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_add_tail(&smcibdev->list, &smc_ib_devices.list); - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); ib_set_client_data(ibdev, &smc_ib_client, smcibdev); INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev, smc_ib_global_event_handler); @@ -602,9 +603,9 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) { struct smc_ib_device *smcibdev = client_data; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); pr_warn_ratelimited("smc: removing ib device %s\n", smcibdev->ibdev->name); smc_smcr_terminate_all(smcibdev); diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index e6a696ae15f3..ae6776e1e726 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -14,6 +14,7 @@ #include <linux/interrupt.h> #include <linux/if_ether.h> +#include <linux/mutex.h> #include <linux/wait.h> #include <rdma/ib_verbs.h> #include <net/smc.h> @@ -25,7 +26,7 @@ struct smc_ib_devices { /* list of smc ib devices definition */ struct list_head list; - spinlock_t lock; /* protects list of smc ib devices */ + struct mutex mutex; /* protects list of smc ib devices */ }; extern struct smc_ib_devices smc_ib_devices; /* list of smc ib devices */ diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 91f85fc09fb8..998c525de785 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -7,6 +7,7 @@ */ #include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/slab.h> #include <asm/page.h> @@ -17,7 +18,7 @@ struct smcd_dev_list smcd_dev_list = { .list = LIST_HEAD_INIT(smcd_dev_list.list), - .lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock) + .mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex) }; /* Test if an ISM communication is possible. */ @@ -317,9 +318,9 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev); int smcd_register_dev(struct smcd_dev *smcd) { - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_add_tail(&smcd->list, &smcd_dev_list.list); - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n", dev_name(&smcd->dev), smcd->pnetid, @@ -333,9 +334,9 @@ void smcd_unregister_dev(struct smcd_dev *smcd) { pr_warn_ratelimited("smc: removing smcd device %s\n", dev_name(&smcd->dev)); - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_del_init(&smcd->list); - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); smcd->going_away = 1; smc_smcd_terminate_all(smcd); flush_workqueue(smcd->event_wq); diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 4da946cbfa29..81cc4537efd3 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -10,12 +10,13 @@ #define SMCD_ISM_H #include <linux/uio.h> +#include <linux/mutex.h> #include "smc.h" struct smcd_dev_list { /* List of SMCD devices */ struct list_head list; - spinlock_t lock; /* Protects list of devices */ + struct mutex mutex; /* Protects list of devices */ }; extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 391237b601fe..c1a038689c63 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -186,6 +186,26 @@ static inline void smc_llc_flow_qentry_set(struct smc_llc_flow *flow, flow->qentry = qentry; } +static void smc_llc_flow_parallel(struct smc_link_group *lgr, u8 flow_type, + struct smc_llc_qentry *qentry) +{ + u8 msg_type = qentry->msg.raw.hdr.common.type; + + if ((msg_type == SMC_LLC_ADD_LINK || msg_type == SMC_LLC_DELETE_LINK) && + flow_type != msg_type && !lgr->delayed_event) { + lgr->delayed_event = qentry; + return; + } + /* drop parallel or already-in-progress llc requests */ + if (flow_type != msg_type) + pr_warn_once("smc: SMC-R lg %*phN dropped parallel " + "LLC msg: msg %d flow %d role %d\n", + SMC_LGR_ID_SIZE, &lgr->id, + qentry->msg.raw.hdr.common.type, + flow_type, lgr->role); + kfree(qentry); +} + /* try to start a new llc flow, initiated by an incoming llc msg */ static bool smc_llc_flow_start(struct smc_llc_flow *flow, struct smc_llc_qentry *qentry) @@ -195,14 +215,7 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, spin_lock_bh(&lgr->llc_flow_lock); if (flow->type) { /* a flow is already active */ - if ((qentry->msg.raw.hdr.common.type == SMC_LLC_ADD_LINK || - qentry->msg.raw.hdr.common.type == SMC_LLC_DELETE_LINK) && - !lgr->delayed_event) { - lgr->delayed_event = qentry; - } else { - /* forget this llc request */ - kfree(qentry); - } + smc_llc_flow_parallel(lgr, flow->type, qentry); spin_unlock_bh(&lgr->llc_flow_lock); return false; } @@ -222,8 +235,8 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, } if (qentry == lgr->delayed_event) lgr->delayed_event = NULL; - spin_unlock_bh(&lgr->llc_flow_lock); smc_llc_flow_qentry_set(flow, qentry); + spin_unlock_bh(&lgr->llc_flow_lock); return true; } @@ -251,11 +264,11 @@ again: return 0; } spin_unlock_bh(&lgr->llc_flow_lock); - rc = wait_event_interruptible_timeout(lgr->llc_waiter, - (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE && - (lgr->llc_flow_rmt.type == SMC_LLC_FLOW_NONE || - lgr->llc_flow_rmt.type == allowed_remote)), - SMC_LLC_WAIT_TIME); + rc = wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || + (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE && + (lgr->llc_flow_rmt.type == SMC_LLC_FLOW_NONE || + lgr->llc_flow_rmt.type == allowed_remote))), + SMC_LLC_WAIT_TIME * 10); if (!rc) return -ETIMEDOUT; goto again; @@ -272,7 +285,7 @@ void smc_llc_flow_stop(struct smc_link_group *lgr, struct smc_llc_flow *flow) flow == &lgr->llc_flow_lcl) schedule_work(&lgr->llc_event_work); else - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_flow_waiter); } /* lnk is optional and used for early wakeup when link goes down, useful in @@ -283,26 +296,32 @@ struct smc_llc_qentry *smc_llc_wait(struct smc_link_group *lgr, int time_out, u8 exp_msg) { struct smc_llc_flow *flow = &lgr->llc_flow_lcl; + u8 rcv_msg; - wait_event_interruptible_timeout(lgr->llc_waiter, - (flow->qentry || - (lnk && !smc_link_usable(lnk)) || - list_empty(&lgr->list)), - time_out); + wait_event_timeout(lgr->llc_msg_waiter, + (flow->qentry || + (lnk && !smc_link_usable(lnk)) || + list_empty(&lgr->list)), + time_out); if (!flow->qentry || (lnk && !smc_link_usable(lnk)) || list_empty(&lgr->list)) { smc_llc_flow_qentry_del(flow); goto out; } - if (exp_msg && flow->qentry->msg.raw.hdr.common.type != exp_msg) { + rcv_msg = flow->qentry->msg.raw.hdr.common.type; + if (exp_msg && rcv_msg != exp_msg) { if (exp_msg == SMC_LLC_ADD_LINK && - flow->qentry->msg.raw.hdr.common.type == - SMC_LLC_DELETE_LINK) { + rcv_msg == SMC_LLC_DELETE_LINK) { /* flow_start will delay the unexpected msg */ smc_llc_flow_start(&lgr->llc_flow_lcl, smc_llc_flow_qentry_clr(flow)); return NULL; } + pr_warn_once("smc: SMC-R lg %*phN dropped unexpected LLC msg: " + "msg %d exp %d flow %d role %d flags %x\n", + SMC_LGR_ID_SIZE, &lgr->id, rcv_msg, exp_msg, + flow->type, lgr->role, + flow->qentry->msg.raw.hdr.flags); smc_llc_flow_qentry_del(flow); } out: @@ -1222,8 +1241,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_llc_send_message(lnk, &qentry->msg); /* response */ if (smc_link_downing(&lnk_del->state)) { - smc_switch_conns(lgr, lnk_del, false); - smc_wr_tx_wait_no_pending_sends(lnk_del); + if (smc_switch_conns(lgr, lnk_del, false)) + smc_wr_tx_wait_no_pending_sends(lnk_del); } smcr_link_clear(lnk_del, true); @@ -1297,8 +1316,8 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) goto out; /* asymmetric link already deleted */ if (smc_link_downing(&lnk_del->state)) { - smc_switch_conns(lgr, lnk_del, false); - smc_wr_tx_wait_no_pending_sends(lnk_del); + if (smc_switch_conns(lgr, lnk_del, false)) + smc_wr_tx_wait_no_pending_sends(lnk_del); } if (!list_empty(&lgr->list)) { /* qentry is either a request from peer (send it back to @@ -1459,7 +1478,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_msg_waiter); } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { schedule_work(&lgr->llc_add_link_work); @@ -1474,7 +1493,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_msg_waiter); return; } break; @@ -1485,7 +1504,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) /* DEL LINK REQ during ADD LINK SEQ */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_msg_waiter); } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { schedule_work(&lgr->llc_del_link_work); @@ -1496,7 +1515,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) /* DEL LINK REQ during ADD LINK SEQ */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_msg_waiter); } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { schedule_work(&lgr->llc_del_link_work); @@ -1581,7 +1600,7 @@ static void smc_llc_rx_response(struct smc_link *link, case SMC_LLC_DELETE_RKEY: /* assign responses to the local flow, we requested them */ smc_llc_flow_qentry_set(&link->lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&link->lgr->llc_waiter); + wake_up(&link->lgr->llc_msg_waiter); return; case SMC_LLC_CONFIRM_RKEY_CONT: /* not used because max links is 3 */ @@ -1616,7 +1635,7 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) spin_lock_irqsave(&lgr->llc_event_q_lock, flags); list_add_tail(&qentry->list, &lgr->llc_event_q); spin_unlock_irqrestore(&lgr->llc_event_q_lock, flags); - schedule_work(&link->lgr->llc_event_work); + schedule_work(&lgr->llc_event_work); } /* copy received msg and add it to the event queue */ @@ -1677,7 +1696,8 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) INIT_LIST_HEAD(&lgr->llc_event_q); spin_lock_init(&lgr->llc_event_q_lock); spin_lock_init(&lgr->llc_flow_lock); - init_waitqueue_head(&lgr->llc_waiter); + init_waitqueue_head(&lgr->llc_flow_waiter); + init_waitqueue_head(&lgr->llc_msg_waiter); mutex_init(&lgr->llc_conf_mutex); lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time; } @@ -1686,7 +1706,8 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) void smc_llc_lgr_clear(struct smc_link_group *lgr) { smc_llc_event_flush(lgr); - wake_up_interruptible_all(&lgr->llc_waiter); + wake_up_all(&lgr->llc_flow_waiter); + wake_up_all(&lgr->llc_msg_waiter); cancel_work_sync(&lgr->llc_event_work); cancel_work_sync(&lgr->llc_add_link_work); cancel_work_sync(&lgr->llc_del_link_work); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 014d91b9778e..30e5fac7034e 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> +#include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -129,7 +130,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) return rc; /* remove ib devices */ - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && @@ -149,9 +150,9 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) } } } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (smcd_dev->pnetid_by_user && (!pnet_name || @@ -165,7 +166,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) rc = 0; } } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); return rc; } @@ -240,14 +241,14 @@ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, u8 pnet_null[SMC_MAX_PNETID_LEN] = {0}; bool applied = false; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); return applied; } @@ -258,13 +259,13 @@ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) u8 pnet_null[SMC_MAX_PNETID_LEN] = {0}; bool applied = false; - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); return applied; } @@ -300,7 +301,7 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || @@ -311,7 +312,7 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) } ibdev = NULL; out: - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); return ibdev; } @@ -320,7 +321,7 @@ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(&smcd_dev->dev), smcd_name, IB_DEVICE_NAME_MAX - 1)) @@ -328,7 +329,7 @@ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) } smcd_dev = NULL; out: - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } @@ -825,7 +826,7 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, int i; ini->ib_dev = NULL; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev) continue; @@ -844,7 +845,7 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, } } out: - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id and vlan_id */ @@ -863,7 +864,7 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, { struct smc_ib_device *ibdev; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; @@ -888,7 +889,7 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, } } } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. @@ -924,7 +925,7 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away) { @@ -932,7 +933,7 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, break; } } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 7239ba9b99dc..1e23cdd41eb1 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -169,6 +169,8 @@ void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context) static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) { *idx = link->wr_tx_cnt; + if (!smc_link_usable(link)) + return -ENOLINK; for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) { if (!test_and_set_bit(*idx, link->wr_tx_mask)) return 0; @@ -560,15 +562,15 @@ void smc_wr_free_link(struct smc_link *lnk) { struct ib_device *ibdev; + if (!lnk->smcibdev) + return; + ibdev = lnk->smcibdev->ibdev; + if (smc_wr_tx_wait_no_pending_sends(lnk)) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); - if (!lnk->smcibdev) - return; - ibdev = lnk->smcibdev->ibdev; - if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, diff --git a/net/socket.c b/net/socket.c index d87812a9ed4b..770503c4ca76 100644 --- a/net/socket.c +++ b/net/socket.c @@ -586,15 +586,6 @@ struct socket *sock_alloc(void) } EXPORT_SYMBOL(sock_alloc); -/** - * sock_release - close a socket - * @sock: socket to close - * - * The socket is released from the protocol stack if it has a release - * callback, and the inode is then released if the socket is bound to - * an inode not a file. - */ - static void __sock_release(struct socket *sock, struct inode *inode) { if (sock->ops) { @@ -620,6 +611,14 @@ static void __sock_release(struct socket *sock, struct inode *inode) sock->file = NULL; } +/** + * sock_release - close a socket + * @sock: socket to close + * + * The socket is released from the protocol stack if it has a release + * callback, and the inode is then released if the socket is bound to + * an inode not a file. + */ void sock_release(struct socket *sock) { __sock_release(sock, NULL); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 39e14d5edaf1..e9d0953522f0 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1317,6 +1317,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) q.len = strlen(gssd_dummy_clnt_dir[0].name); clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); if (!clnt_dentry) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); goto out; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5c4ec9386f81..c537272f9c7e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -44,6 +44,7 @@ #include <net/tcp.h> #include <net/tcp_states.h> #include <linux/uaccess.h> +#include <linux/highmem.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 6f7d82fb1eb0..be11d672b5b9 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1118,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->head[0].iov_len; + subbuf->head[0].iov_base = buf->head[0].iov_base; subbuf->head[0].iov_len = 0; } @@ -1130,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->page_len; + subbuf->pages = buf->pages; + subbuf->page_base = 0; subbuf->page_len = 0; } @@ -1141,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->tail[0].iov_len; + subbuf->tail[0].iov_base = buf->tail[0].iov_base; subbuf->tail[0].iov_len = 0; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ef997880e17a..b647562a26dd 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -367,7 +367,7 @@ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_fastreg(wc, frwr); /* The MR will get recycled when the associated req is retransmitted */ - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -452,7 +452,7 @@ static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_li(wc, frwr); __frwr_release_mr(wc, mr); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -474,7 +474,7 @@ static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) __frwr_release_mr(wc, mr); complete(&frwr->fr_linv_done); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -582,7 +582,7 @@ static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc) smp_rmb(); rpcrdma_complete_rqst(rep); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 2081c8fbfa48..935bbef2f7be 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1349,8 +1349,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } - r_xprt->rx_stats.bad_reply_count++; - return -EREMOTEIO; + return -EIO; } /* Perform XID lookup, reconstruction of the RPC reply, and @@ -1387,13 +1386,11 @@ out: spin_unlock(&xprt->queue_lock); return; -/* If the incoming reply terminated a pending RPC, the next - * RPC call will post a replacement receive buffer as it is - * being marshaled. - */ out_badheader: trace_xprtrdma_reply_hdr(rep); r_xprt->rx_stats.bad_reply_count++; + rqst->rq_task->tk_status = status; + status = 0; goto out; } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 0c4af7f5e241..14165b673b20 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -242,7 +242,7 @@ xprt_rdma_connect_worker(struct work_struct *work) rc = rpcrdma_xprt_connect(r_xprt); xprt_clear_connecting(xprt); - if (r_xprt->rx_ep && r_xprt->rx_ep->re_connect_status > 0) { + if (!rc) { xprt->connect_cookie++; xprt->stat.connect_count++; xprt->stat.connect_time += (long)jiffies - diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 2ae348377806..2198c8ec8dff 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -84,7 +84,8 @@ static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep); static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt); -static int rpcrdma_ep_destroy(struct rpcrdma_ep *ep); +static void rpcrdma_ep_get(struct rpcrdma_ep *ep); +static int rpcrdma_ep_put(struct rpcrdma_ep *ep); static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); @@ -97,7 +98,8 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); */ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) { - struct rdma_cm_id *id = r_xprt->rx_ep->re_id; + struct rpcrdma_ep *ep = r_xprt->rx_ep; + struct rdma_cm_id *id = ep->re_id; /* Flush Receives, then wait for deferred Reply work * to complete. @@ -108,6 +110,8 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) * local invalidations. */ ib_drain_sq(id->qp); + + rpcrdma_ep_put(ep); } /** @@ -126,23 +130,27 @@ static void rpcrdma_qp_event_handler(struct ib_event *event, void *context) trace_xprtrdma_qp_event(ep, event); } +/* Ensure xprt_force_disconnect() is invoked exactly once when a + * connection is closed or lost. (The important thing is it needs + * to be invoked "at least" once). + */ +static void rpcrdma_force_disconnect(struct rpcrdma_ep *ep) +{ + if (atomic_add_unless(&ep->re_force_disconnect, 1, 1)) + xprt_force_disconnect(ep->re_xprt); +} + /** * rpcrdma_flush_disconnect - Disconnect on flushed completion - * @cq: completion queue + * @r_xprt: transport to disconnect * @wc: work completion entry * * Must be called in process context. */ -void rpcrdma_flush_disconnect(struct ib_cq *cq, struct ib_wc *wc) +void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc) { - struct rpcrdma_xprt *r_xprt = cq->cq_context; - struct rpc_xprt *xprt = &r_xprt->rx_xprt; - - if (wc->status != IB_WC_SUCCESS && - r_xprt->rx_ep->re_connect_status == 1) { - r_xprt->rx_ep->re_connect_status = -ECONNABORTED; - xprt_force_disconnect(xprt); - } + if (wc->status != IB_WC_SUCCESS) + rpcrdma_force_disconnect(r_xprt->rx_ep); } /** @@ -156,11 +164,12 @@ static void rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct rpcrdma_sendctx *sc = container_of(cqe, struct rpcrdma_sendctx, sc_cqe); + struct rpcrdma_xprt *r_xprt = cq->cq_context; /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_send(sc, wc); - rpcrdma_sendctx_put_locked((struct rpcrdma_xprt *)cq->cq_context, sc); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_sendctx_put_locked(r_xprt, sc); + rpcrdma_flush_disconnect(r_xprt, wc); } /** @@ -195,7 +204,7 @@ static void rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) return; out_flushed: - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(r_xprt, wc); rpcrdma_rep_destroy(rep); } @@ -239,7 +248,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct sockaddr *sap = (struct sockaddr *)&id->route.addr.dst_addr; struct rpcrdma_ep *ep = id->context; - struct rpc_xprt *xprt = ep->re_xprt; might_sleep(); @@ -263,10 +271,9 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) /* fall through */ case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; - xprt_force_disconnect(xprt); goto disconnected; case RDMA_CM_EVENT_ESTABLISHED: - kref_get(&ep->re_kref); + rpcrdma_ep_get(ep); ep->re_connect_status = 1; rpcrdma_update_cm_private(ep, &event->param.conn); trace_xprtrdma_inline_thresh(ep); @@ -288,8 +295,8 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: ep->re_connect_status = -ECONNABORTED; disconnected: - xprt_force_disconnect(xprt); - return rpcrdma_ep_destroy(ep); + rpcrdma_force_disconnect(ep); + return rpcrdma_ep_put(ep); default: break; } @@ -345,7 +352,7 @@ out: return ERR_PTR(rc); } -static void rpcrdma_ep_put(struct kref *kref) +static void rpcrdma_ep_destroy(struct kref *kref) { struct rpcrdma_ep *ep = container_of(kref, struct rpcrdma_ep, re_kref); @@ -369,13 +376,18 @@ static void rpcrdma_ep_put(struct kref *kref) module_put(THIS_MODULE); } +static noinline void rpcrdma_ep_get(struct rpcrdma_ep *ep) +{ + kref_get(&ep->re_kref); +} + /* Returns: * %0 if @ep still has a positive kref count, or * %1 if @ep was destroyed successfully. */ -static int rpcrdma_ep_destroy(struct rpcrdma_ep *ep) +static noinline int rpcrdma_ep_put(struct rpcrdma_ep *ep) { - return kref_put(&ep->re_kref, rpcrdma_ep_put); + return kref_put(&ep->re_kref, rpcrdma_ep_destroy); } static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) @@ -492,7 +504,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) return 0; out_destroy: - rpcrdma_ep_destroy(ep); + rpcrdma_ep_put(ep); rdma_destroy_id(id); out_free: kfree(ep); @@ -519,10 +531,13 @@ retry: return rc; ep = r_xprt->rx_ep; - ep->re_connect_status = 0; xprt_clear_connected(xprt); - rpcrdma_reset_cwnd(r_xprt); + + /* Bump the ep's reference count while there are + * outstanding Receives. + */ + rpcrdma_ep_get(ep); rpcrdma_post_recvs(r_xprt, true); rc = rpcrdma_sendctxs_create(r_xprt); @@ -552,8 +567,6 @@ retry: rpcrdma_mrs_create(r_xprt); out: - if (rc) - ep->re_connect_status = rc; trace_xprtrdma_connect(r_xprt, rc); return rc; } @@ -587,7 +600,7 @@ void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt) rpcrdma_mrs_destroy(r_xprt); rpcrdma_sendctxs_destroy(r_xprt); - if (rpcrdma_ep_destroy(ep)) + if (rpcrdma_ep_put(ep)) rdma_destroy_id(id); r_xprt->rx_ep = NULL; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0a16fdb09b2c..43974ef39a50 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -82,6 +82,7 @@ struct rpcrdma_ep { unsigned int re_max_inline_recv; int re_async_rc; int re_connect_status; + atomic_t re_force_disconnect; struct ib_qp_init_attr re_attr; wait_queue_head_t re_connect_wait; struct rpc_xprt *re_xprt; @@ -446,7 +447,7 @@ extern unsigned int xprt_rdma_memreg_strategy; /* * Endpoint calls - xprtrdma/verbs.c */ -void rpcrdma_flush_disconnect(struct ib_cq *cq, struct ib_wc *wc); +void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc); int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt); void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index f25604d68337..865f3e037425 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -304,8 +304,8 @@ static int switchdev_port_obj_add_defer(struct net_device *dev, * switchdev_port_obj_add - Add port object * * @dev: port device - * @id: object ID * @obj: object to add + * @extack: netlink extended ack * * Use a 2-phase prepare-commit transaction model to ensure * system is not left in a partially updated state due to @@ -357,7 +357,6 @@ static int switchdev_port_obj_del_defer(struct net_device *dev, * switchdev_port_obj_del - Delete port object * * @dev: port device - * @id: object ID * @obj: object to delete * * rtnl_lock must be held and must not be in atomic section, diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index e366ec9a7e4d..808b147df7d5 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -595,7 +595,7 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, /** * tipc_l2_rcv_msg - handle incoming TIPC message from an interface - * @buf: the received packet + * @skb: the received message * @dev: the net device that the packet was received on * @pt: the packet_type structure which was used to register this handler * @orig_dev: the original receive net device in case the device is a bond diff --git a/net/tipc/discover.c b/net/tipc/discover.c index bfe43da127c0..d4ecacddb40c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -74,7 +74,7 @@ struct tipc_discoverer { /** * tipc_disc_init_msg - initialize a link setup message * @net: the applicable net namespace - * @type: message type (request or response) + * @mtyp: message type (request or response) * @b: ptr to bearer issuing message */ static void tipc_disc_init_msg(struct net *net, struct sk_buff *skb, @@ -339,7 +339,7 @@ exit: * @net: the applicable net namespace * @b: ptr to bearer issuing requests * @dest: destination address for request messages - * @dest_domain: network domain to which links can be established + * @skb: pointer to created frame * * Returns 0 if successful, otherwise -errno. */ @@ -393,7 +393,6 @@ void tipc_disc_delete(struct tipc_discoverer *d) * tipc_disc_reset - reset object to send periodic link setup requests * @net: the applicable net namespace * @b: ptr to bearer issuing requests - * @dest_domain: network domain to which links can be established */ void tipc_disc_reset(struct net *net, struct tipc_bearer *b) { diff --git a/net/tipc/link.c b/net/tipc/link.c index 1c579357ccdf..d46d4ee5c4fd 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -445,7 +445,7 @@ u32 tipc_link_state(struct tipc_link *l) /** * tipc_link_create - create a new link - * @n: pointer to associated node + * @net: pointer to associated network namespace * @if_name: associated interface name * @bearer_id: id (index) of associated bearer * @tolerance: link tolerance to be used by link @@ -530,7 +530,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, /** * tipc_link_bc_create - create new link to be used for broadcast - * @n: pointer to associated node + * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers * @window: send window to be used * @inputq: queue to put messages ready for delivery @@ -921,6 +921,21 @@ static void link_prepare_wakeup(struct tipc_link *l) } +/** + * tipc_link_set_skb_retransmit_time - set the time at which retransmission of + * the given skb should be next attempted + * @skb: skb to set a future retransmission time for + * @l: link the skb will be transmitted on + */ +static void tipc_link_set_skb_retransmit_time(struct sk_buff *skb, + struct tipc_link *l) +{ + if (link_is_bc_sndlink(l)) + TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + else + TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; +} + void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; @@ -974,7 +989,7 @@ void tipc_link_reset(struct tipc_link *l) /** * tipc_link_xmit(): enqueue buffer list according to queue situation - * @link: link to use + * @l: link to use * @list: chain of buffers containing message * @xmitq: returned list of packets to be sent by caller * @@ -1036,9 +1051,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return -ENOBUFS; } __skb_queue_tail(transmq, skb); - /* next retransmit attempt */ - if (link_is_bc_sndlink(l)) - TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; @@ -1139,9 +1152,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l, 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)) - TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; @@ -1584,8 +1595,7 @@ release: /* retransmit skb if unrestricted*/ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue; - TIPC_SKB_CB(skb)->nxt_retr = (is_uc) ? - TIPC_UC_RETR_TIME : TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) continue; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 01b64869a173..848fae674532 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -202,7 +202,7 @@ err: /** * tipc_msg_append(): Append data to tail of an existing buffer queue - * @hdr: header to be used + * @_hdr: header to be used * @m: the data to be appended * @mss: max allowable size of buffer * @dlen: size of data to be appended diff --git a/net/tipc/node.c b/net/tipc/node.c index 030a51c4d1fa..4edcee3088da 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1515,7 +1515,7 @@ static void node_lost_contact(struct tipc_node *n, * tipc_node_get_linkname - get the name of a link * * @bearer_id: id of the bearer - * @node: peer node address + * @addr: peer node address * @linkname: link name output buffer * * Returns 0 on success @@ -2022,7 +2022,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, * tipc_rcv - process TIPC packets/messages arriving from off-node * @net: the applicable net namespace * @skb: TIPC packet - * @bearer: pointer to bearer message arrived on + * @b: pointer to bearer message arrived on * * Invoked with no locks held. Bearer pointer must point to a valid bearer * structure (i.e. cannot be NULL), but bearer can be inactive. diff --git a/net/tipc/socket.c b/net/tipc/socket.c index a94f38333698..fc388cef6471 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -711,7 +711,6 @@ exit: * tipc_getname - get port ID of socket or peer socket * @sock: socket structure * @uaddr: area for returned socket address - * @uaddr_len: area for returned length of socket address * @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID * * Returns 0 on success, errno otherwise @@ -1053,7 +1052,7 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, /** * tipc_send_group_bcast - send message to all members in communication group - * @sk: socket structure + * @sock: socket structure * @m: message to send * @dlen: total length of message data * @timeout: timeout to wait for wakeup @@ -1673,7 +1672,7 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, /** * tipc_sk_set_orig_addr - capture sender's address for received message * @m: descriptor for message info - * @hdr: received message header + * @skb: received message * * Note: Address is not captured if not requested by receiver. */ @@ -2095,7 +2094,6 @@ static void tipc_write_space(struct sock *sk) /** * tipc_data_ready - wake up threads to indicate messages have been received * @sk: socket - * @len: the length of messages */ static void tipc_data_ready(struct sock *sk) { @@ -2677,7 +2675,7 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) /** * tipc_accept - wait for connection request * @sock: listening socket - * @newsock: new socket that is to be connected + * @new_sock: new socket that is to be connected * @flags: file-related flags associated with socket * * Returns 0 on success, errno otherwise diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 28a283f26a8d..d91b7c543e39 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -565,7 +565,7 @@ msg_full: /** * tipc_parse_udp_addr - build udp media address from netlink data - * @nlattr: netlink attribute containing sockaddr storage aligned address + * @nla: netlink attribute containing sockaddr storage aligned address * @addr: tipc media address to fill with address, port and protocol type * @scope_id: IPv6 scope id pointer, not NULL indicates it's required */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 263ae395ad44..0e07fb8585fb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5016,7 +5016,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - goto out; + if (err) + goto out; } if (info->attrs[NL80211_ATTR_HE_BSS_COLOR]) { @@ -5024,7 +5025,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_HE_BSS_COLOR], ¶ms.he_bss_color); if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0d74a31ef0ab..35b8847a2f6d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2384,7 +2384,7 @@ static void reg_set_request_processed(void) /** * reg_process_hint_core - process core regulatory requests - * @pending_request: a pending core regulatory request + * @core_request: a pending core regulatory request * * The wireless subsystem can use this function to process * a regulatory request issued by the regulatory core. @@ -2493,6 +2493,7 @@ __reg_process_hint_driver(struct regulatory_request *driver_request) /** * reg_process_hint_driver - process driver regulatory requests + * @wiphy: the wireless device for the regulatory request * @driver_request: a pending driver regulatory request * * The wireless subsystem can use this function to process @@ -2593,6 +2594,7 @@ __reg_process_hint_country_ie(struct wiphy *wiphy, /** * reg_process_hint_country_ie - process regulatory requests from country IEs + * @wiphy: the wireless device for the regulatory request * @country_ie_request: a regulatory request from a country IE * * The wireless subsystem can use this function to process diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index cac9e28d852b..aa918d7ff6bd 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -220,7 +220,6 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwrange); /** * cfg80211_wext_freq - get wext frequency for non-"auto" - * @dev: the net device * @freq: the wext freq encoding * * Returns a frequency, or a negative error code, or 0 for auto. diff --git a/net/x25/Kconfig b/net/x25/Kconfig index e3ed23245a82..68729aa3a5d5 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -17,7 +17,7 @@ config X25 if you want that) and the lower level data link layer protocol LAPB (say Y to "LAPB Data Link Driver" below if you want that). - You can read more about X.25 at <http://www.sangoma.com/tutorials/x25/> and + You can read more about X.25 at <https://www.sangoma.com/tutorials/x25/> and <http://docwiki.cisco.com/wiki/X.25>. Information about X.25 for Linux is contained in the files <file:Documentation/networking/x25.rst> and diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 7d02532aad0d..fdae054b7dc1 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -270,7 +270,7 @@ void x25_link_device_up(struct net_device *dev) /** * __x25_remove_neigh - remove neighbour from x25_neigh_list - * @nb - neigh to remove + * @nb: - neigh to remove * * Remove neighbour from x25_neigh_list. If it was there. * Caller must hold x25_neigh_list_lock. diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index b8e94d58d0f1..00e46c9a5280 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -142,7 +142,7 @@ struct net_device *x25_dev_get(char *devname) /** * x25_get_route - Find a route given an X.25 address. - * @addr - address to find a route for + * @addr: - address to find a route for * * Find a route given an X.25 address. */ diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 89cf3551d3e9..a2044c245215 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -2,9 +2,6 @@ #include <net/xsk_buff_pool.h> #include <net/xdp_sock.h> -#include <linux/dma-direct.h> -#include <linux/dma-noncoherent.h> -#include <linux/swiotlb.h> #include "xsk_queue.h" @@ -55,7 +52,6 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, pool->free_heads_cnt = chunks; pool->headroom = headroom; pool->chunk_size = chunk_size; - pool->cheap_dma = true; pool->unaligned = unaligned; pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; INIT_LIST_HEAD(&pool->free_list); @@ -125,48 +121,6 @@ static void xp_check_dma_contiguity(struct xsk_buff_pool *pool) } } -static bool __maybe_unused xp_check_swiotlb_dma(struct xsk_buff_pool *pool) -{ -#if defined(CONFIG_SWIOTLB) - phys_addr_t paddr; - u32 i; - - for (i = 0; i < pool->dma_pages_cnt; i++) { - paddr = dma_to_phys(pool->dev, pool->dma_pages[i]); - if (is_swiotlb_buffer(paddr)) - return false; - } -#endif - return true; -} - -static bool xp_check_cheap_dma(struct xsk_buff_pool *pool) -{ -#if defined(CONFIG_HAS_DMA) - const struct dma_map_ops *ops = get_dma_ops(pool->dev); - - if (ops) { - return !ops->sync_single_for_cpu && - !ops->sync_single_for_device; - } - - if (!dma_is_direct(ops)) - return false; - - if (!xp_check_swiotlb_dma(pool)) - return false; - - if (!dev_is_dma_coherent(pool->dev)) { -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) - return false; -#endif - } -#endif - return true; -} - int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { @@ -180,6 +134,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, pool->dev = dev; pool->dma_pages_cnt = nr_pages; + pool->dma_need_sync = false; for (i = 0; i < pool->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, @@ -188,14 +143,13 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, xp_dma_unmap(pool, attrs); return -ENOMEM; } + if (dma_need_sync(dev, dma)) + pool->dma_need_sync = true; pool->dma_pages[i] = dma; } if (pool->unaligned) xp_check_dma_contiguity(pool); - - pool->dev = dev; - pool->cheap_dma = xp_check_cheap_dma(pool); return 0; } EXPORT_SYMBOL(xp_dma_map); @@ -281,7 +235,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; xskb->xdp.data_meta = xskb->xdp.data; - if (!pool->cheap_dma) { + if (pool->dma_need_sync) { dma_sync_single_range_for_device(pool->dev, xskb->dma, 0, pool->frame_len, DMA_BIDIRECTIONAL); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index c407ecbc5d46..b615729812e5 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -37,6 +37,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/ip_tunnels.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/net_namespace.h> @@ -581,6 +582,7 @@ static const struct net_device_ops xfrmi_netdev_ops = { static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_NONE; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; diff --git a/samples/vfs/test-statx.c b/samples/vfs/test-statx.c index 76c577ea4fd8..49c7a46cee07 100644 --- a/samples/vfs/test-statx.c +++ b/samples/vfs/test-statx.c @@ -23,6 +23,8 @@ #include <linux/fcntl.h> #define statx foo #define statx_timestamp foo_timestamp +struct statx; +struct statx_timestamp; #include <sys/stat.h> #undef statx #undef statx_timestamp diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 4aea7cf71d11..62c275685b75 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -35,6 +35,7 @@ KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation) # The following turn off the warnings enabled by -Wextra KBUILD_CFLAGS += -Wno-missing-field-initializers KBUILD_CFLAGS += -Wno-sign-compare +KBUILD_CFLAGS += -Wno-type-limits KBUILD_CPPFLAGS += -DKBUILD_EXTRA_WARN1 @@ -66,6 +67,7 @@ KBUILD_CFLAGS += -Wshadow KBUILD_CFLAGS += $(call cc-option, -Wlogical-op) KBUILD_CFLAGS += -Wmissing-field-initializers KBUILD_CFLAGS += -Wsign-compare +KBUILD_CFLAGS += -Wtype-limits KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 99ac59c59826..916b2f7f7098 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -212,6 +212,9 @@ $(foreach m, $(notdir $1), \ $(addprefix $(obj)/, $(foreach s, $3, $($(m:%$(strip $2)=%$(s))))))) endef +quiet_cmd_copy = COPY $@ + cmd_copy = cp $< $@ + # Shipped files # =========================================================================== @@ -259,6 +262,7 @@ quiet_cmd_gzip = GZIP $@ # DTC # --------------------------------------------------------------------------- DTC ?= $(objtree)/scripts/dtc/dtc +DTC_FLAGS += -Wno-interrupt_provider # Disable noisy checks by default ifeq ($(findstring 1,$(KBUILD_EXTRA_WARN)),) @@ -274,7 +278,8 @@ endif ifneq ($(findstring 2,$(KBUILD_EXTRA_WARN)),) DTC_FLAGS += -Wnode_name_chars_strict \ - -Wproperty_name_chars_strict + -Wproperty_name_chars_strict \ + -Winterrupt_provider endif DTC_FLAGS += $(DTC_FLAGS_$(basetarget)) diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh index 0fd1cf0c2b94..693dfa1de430 100755 --- a/scripts/atomic/gen-atomic-fallback.sh +++ b/scripts/atomic/gen-atomic-fallback.sh @@ -58,6 +58,21 @@ cat << EOF EOF } +gen_proto_order_variant() +{ + local meta="$1"; shift + local pfx="$1"; shift + local name="$1"; shift + local sfx="$1"; shift + local order="$1"; shift + local arch="$1" + local atomic="$2" + + local basename="${arch}${atomic}_${pfx}${name}${sfx}" + + printf "#define arch_${basename}${order} ${basename}${order}\n" +} + #gen_proto_order_variants(meta, pfx, name, sfx, arch, atomic, int, args...) gen_proto_order_variants() { @@ -72,6 +87,22 @@ gen_proto_order_variants() local template="$(find_fallback_template "${pfx}" "${name}" "${sfx}" "${order}")" + if [ -z "$arch" ]; then + gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "" "$@" + + if meta_has_acquire "${meta}"; then + gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_acquire" "$@" + fi + if meta_has_release "${meta}"; then + gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_release" "$@" + fi + if meta_has_relaxed "${meta}"; then + gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_relaxed" "$@" + fi + + echo "" + fi + # If we don't have relaxed atomics, then we don't bother with ordering fallbacks # read_acquire and set_release need to be templated, though if ! meta_has_relaxed "${meta}"; then diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c index 4b3c486f1399..b7955dbd71ca 100644 --- a/scripts/dtc/checks.c +++ b/scripts/dtc/checks.c @@ -1022,6 +1022,9 @@ static void check_i2c_bus_bridge(struct check *c, struct dt_info *dti, struct no } WARNING(i2c_bus_bridge, check_i2c_bus_bridge, NULL, &addr_size_cells); +#define I2C_OWN_SLAVE_ADDRESS (1U << 30) +#define I2C_TEN_BIT_ADDRESS (1U << 31) + static void check_i2c_bus_reg(struct check *c, struct dt_info *dti, struct node *node) { struct property *prop; @@ -1044,6 +1047,8 @@ static void check_i2c_bus_reg(struct check *c, struct dt_info *dti, struct node } reg = fdt32_to_cpu(*cells); + /* Ignore I2C_OWN_SLAVE_ADDRESS */ + reg &= ~I2C_OWN_SLAVE_ADDRESS; snprintf(unit_addr, sizeof(unit_addr), "%x", reg); if (!streq(unitname, unit_addr)) FAIL(c, dti, node, "I2C bus unit address format error, expected \"%s\"", @@ -1051,10 +1056,15 @@ static void check_i2c_bus_reg(struct check *c, struct dt_info *dti, struct node for (len = prop->val.len; len > 0; len -= 4) { reg = fdt32_to_cpu(*(cells++)); - if (reg > 0x3ff) + /* Ignore I2C_OWN_SLAVE_ADDRESS */ + reg &= ~I2C_OWN_SLAVE_ADDRESS; + + if ((reg & I2C_TEN_BIT_ADDRESS) && ((reg & ~I2C_TEN_BIT_ADDRESS) > 0x3ff)) FAIL_PROP(c, dti, node, prop, "I2C address must be less than 10-bits, got \"0x%x\"", reg); - + else if (reg > 0x7f) + FAIL_PROP(c, dti, node, prop, "I2C address must be less than 7-bits, got \"0x%x\". Set I2C_TEN_BIT_ADDRESS for 10 bit addresses or fix the property", + reg); } } WARNING(i2c_bus_reg, check_i2c_bus_reg, NULL, ®_format, &i2c_bus_bridge); @@ -1547,6 +1557,28 @@ static bool node_is_interrupt_provider(struct node *node) return false; } + +static void check_interrupt_provider(struct check *c, + struct dt_info *dti, + struct node *node) +{ + struct property *prop; + + if (!node_is_interrupt_provider(node)) + return; + + prop = get_property(node, "#interrupt-cells"); + if (!prop) + FAIL(c, dti, node, + "Missing #interrupt-cells in interrupt provider"); + + prop = get_property(node, "#address-cells"); + if (!prop) + FAIL(c, dti, node, + "Missing #address-cells in interrupt provider"); +} +WARNING(interrupt_provider, check_interrupt_provider, NULL); + static void check_interrupts_property(struct check *c, struct dt_info *dti, struct node *node) @@ -1604,7 +1636,7 @@ static void check_interrupts_property(struct check *c, prop = get_property(irq_node, "#interrupt-cells"); if (!prop) { - FAIL(c, dti, irq_node, "Missing #interrupt-cells in interrupt-parent"); + /* We warn about that already in another test. */ return; } @@ -1828,6 +1860,7 @@ static struct check *check_table[] = { &deprecated_gpio_property, &gpios_property, &interrupts_property, + &interrupt_provider, &alias_paths, diff --git a/scripts/dtc/dtc.h b/scripts/dtc/dtc.h index 6e74ecea55a3..a08f4159cd03 100644 --- a/scripts/dtc/dtc.h +++ b/scripts/dtc/dtc.h @@ -51,6 +51,37 @@ extern int annotate; /* annotate .dts with input source location */ typedef uint32_t cell_t; +static inline uint16_t dtb_ld16(const void *p) +{ + const uint8_t *bp = (const uint8_t *)p; + + return ((uint16_t)bp[0] << 8) + | bp[1]; +} + +static inline uint32_t dtb_ld32(const void *p) +{ + const uint8_t *bp = (const uint8_t *)p; + + return ((uint32_t)bp[0] << 24) + | ((uint32_t)bp[1] << 16) + | ((uint32_t)bp[2] << 8) + | bp[3]; +} + +static inline uint64_t dtb_ld64(const void *p) +{ + const uint8_t *bp = (const uint8_t *)p; + + return ((uint64_t)bp[0] << 56) + | ((uint64_t)bp[1] << 48) + | ((uint64_t)bp[2] << 40) + | ((uint64_t)bp[3] << 32) + | ((uint64_t)bp[4] << 24) + | ((uint64_t)bp[5] << 16) + | ((uint64_t)bp[6] << 8) + | bp[7]; +} #define streq(a, b) (strcmp((a), (b)) == 0) #define strstarts(s, prefix) (strncmp((s), (prefix), strlen(prefix)) == 0) diff --git a/scripts/dtc/flattree.c b/scripts/dtc/flattree.c index bd6977eedcb8..07f10d2b5d79 100644 --- a/scripts/dtc/flattree.c +++ b/scripts/dtc/flattree.c @@ -156,7 +156,7 @@ static void asm_emit_data(void *e, struct data d) emit_offset_label(f, m->ref, m->offset); while ((d.len - off) >= sizeof(uint32_t)) { - asm_emit_cell(e, fdt32_to_cpu(*((fdt32_t *)(d.val+off)))); + asm_emit_cell(e, dtb_ld32(d.val + off)); off += sizeof(uint32_t); } diff --git a/scripts/dtc/libfdt/fdt_rw.c b/scripts/dtc/libfdt/fdt_rw.c index 524b520c8486..93e4a2b56348 100644 --- a/scripts/dtc/libfdt/fdt_rw.c +++ b/scripts/dtc/libfdt/fdt_rw.c @@ -436,7 +436,7 @@ int fdt_open_into(const void *fdt, void *buf, int bufsize) return struct_size; } - if (can_assume(LIBFDT_ORDER) | + if (can_assume(LIBFDT_ORDER) || !fdt_blocks_misordered_(fdt, mem_rsv_size, struct_size)) { /* no further work necessary */ err = fdt_move(fdt, buf, bufsize); diff --git a/scripts/dtc/libfdt/fdt_sw.c b/scripts/dtc/libfdt/fdt_sw.c index 26759d5dfb8c..94ce4bb91a00 100644 --- a/scripts/dtc/libfdt/fdt_sw.c +++ b/scripts/dtc/libfdt/fdt_sw.c @@ -32,7 +32,7 @@ static int fdt_sw_probe_(void *fdt) /* 'memrsv' state: Initial state after fdt_create() * * Allowed functions: - * fdt_add_reservmap_entry() + * fdt_add_reservemap_entry() * fdt_finish_reservemap() [moves to 'struct' state] */ static int fdt_sw_probe_memrsv_(void *fdt) diff --git a/scripts/dtc/libfdt/libfdt.h b/scripts/dtc/libfdt/libfdt.h index 36fadcdea516..fe49b5d78938 100644 --- a/scripts/dtc/libfdt/libfdt.h +++ b/scripts/dtc/libfdt/libfdt.h @@ -9,6 +9,10 @@ #include "libfdt_env.h" #include "fdt.h" +#ifdef __cplusplus +extern "C" { +#endif + #define FDT_FIRST_SUPPORTED_VERSION 0x02 #define FDT_LAST_SUPPORTED_VERSION 0x11 @@ -2069,4 +2073,8 @@ int fdt_overlay_apply(void *fdt, void *fdto); const char *fdt_strerror(int errval); +#ifdef __cplusplus +} +#endif + #endif /* LIBFDT_H */ diff --git a/scripts/dtc/treesource.c b/scripts/dtc/treesource.c index c9d980c8abfc..061ba8c9c5e8 100644 --- a/scripts/dtc/treesource.c +++ b/scripts/dtc/treesource.c @@ -110,13 +110,13 @@ static void write_propval_int(FILE *f, const char *p, size_t len, size_t width) fprintf(f, "%02"PRIx8, *(const uint8_t*)p); break; case 2: - fprintf(f, "0x%02"PRIx16, fdt16_to_cpu(*(const fdt16_t*)p)); + fprintf(f, "0x%02"PRIx16, dtb_ld16(p)); break; case 4: - fprintf(f, "0x%02"PRIx32, fdt32_to_cpu(*(const fdt32_t*)p)); + fprintf(f, "0x%02"PRIx32, dtb_ld32(p)); break; case 8: - fprintf(f, "0x%02"PRIx64, fdt64_to_cpu(*(const fdt64_t*)p)); + fprintf(f, "0x%02"PRIx64, dtb_ld64(p)); break; } if (p + width < end) @@ -183,7 +183,7 @@ static enum markertype guess_value_type(struct property *prop) nnotcelllbl++; } - if ((p[len-1] == '\0') && (nnotstring == 0) && (nnul < (len-nnul)) + if ((p[len-1] == '\0') && (nnotstring == 0) && (nnul <= (len-nnul)) && (nnotstringlbl == 0)) { return TYPE_STRING; } else if (((len % sizeof(cell_t)) == 0) && (nnotcelllbl == 0)) { diff --git a/scripts/dtc/version_gen.h b/scripts/dtc/version_gen.h index 61dd7112d6e4..0714799446f8 100644 --- a/scripts/dtc/version_gen.h +++ b/scripts/dtc/version_gen.h @@ -1 +1 @@ -#define DTC_VERSION "DTC 1.6.0-g87a656ae" +#define DTC_VERSION "DTC 1.6.0-g9d7888cb" diff --git a/scripts/dtc/yamltree.c b/scripts/dtc/yamltree.c index 5b6ea8ea862f..4e93c12dc658 100644 --- a/scripts/dtc/yamltree.c +++ b/scripts/dtc/yamltree.c @@ -59,10 +59,10 @@ static void yaml_propval_int(yaml_emitter_t *emitter, struct marker *markers, ch sprintf(buf, "0x%"PRIx8, *(uint8_t*)(data + off)); break; case 2: - sprintf(buf, "0x%"PRIx16, fdt16_to_cpu(*(fdt16_t*)(data + off))); + sprintf(buf, "0x%"PRIx16, dtb_ld16(data + off)); break; case 4: - sprintf(buf, "0x%"PRIx32, fdt32_to_cpu(*(fdt32_t*)(data + off))); + sprintf(buf, "0x%"PRIx32, dtb_ld32(data + off)); m = markers; is_phandle = false; for_each_marker_of_type(m, REF_PHANDLE) { @@ -73,7 +73,7 @@ static void yaml_propval_int(yaml_emitter_t *emitter, struct marker *markers, ch } break; case 8: - sprintf(buf, "0x%"PRIx64, fdt64_to_cpu(*(fdt64_t*)(data + off))); + sprintf(buf, "0x%"PRIx64, dtb_ld64(data + off)); break; } diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index ce0b99fb5847..ae19fb0243b9 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -78,7 +78,7 @@ config GCC_PLUGIN_RANDSTRUCT source tree isn't cleaned after kernel installation). The seed used for compilation is located at - scripts/gcc-plgins/randomize_layout_seed.h. It remains after + scripts/gcc-plugins/randomize_layout_seed.h. It remains after a make clean to allow for external modules to be compiled with the existing seed and will be removed by a make mrproper or make distclean. diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index c0ac8f7b5f1a..4a616128a154 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -4,27 +4,19 @@ * Copyright (C) 2015 Boris Barbulovski <bbarbulovski@gmail.com> */ -#include <qglobal.h> - -#include <QMainWindow> -#include <QList> -#include <qtextbrowser.h> #include <QAction> +#include <QApplication> +#include <QCloseEvent> +#include <QDebug> +#include <QDesktopWidget> #include <QFileDialog> +#include <QLabel> +#include <QLayout> +#include <QList> #include <QMenu> - -#include <qapplication.h> -#include <qdesktopwidget.h> -#include <qtoolbar.h> -#include <qlayout.h> -#include <qsplitter.h> -#include <qlineedit.h> -#include <qlabel.h> -#include <qpushbutton.h> -#include <qmenubar.h> -#include <qmessagebox.h> -#include <qregexp.h> -#include <qevent.h> +#include <QMenuBar> +#include <QMessageBox> +#include <QToolBar> #include <stdlib.h> @@ -445,9 +437,10 @@ void ConfigList::updateList(ConfigItem* item) if (rootEntry != &rootmenu && (mode == singleMode || (mode == symbolMode && rootEntry->parent != &rootmenu))) { item = (ConfigItem *)topLevelItem(0); - if (!item) + if (!item && mode != symbolMode) { item = new ConfigItem(this, 0, true); - last = item; + last = item; + } } if ((mode == singleMode || (mode == symbolMode && !(rootEntry->flags & MENU_ROOT))) && rootEntry->sym && rootEntry->prompt) { @@ -545,7 +538,7 @@ void ConfigList::setRootMenu(struct menu *menu) rootEntry = menu; updateListAll(); if (currentItem()) { - currentItem()->setSelected(hasFocus()); + setSelected(currentItem(), hasFocus()); scrollToItem(currentItem()); } } @@ -873,7 +866,7 @@ void ConfigList::focusInEvent(QFocusEvent *e) ConfigItem* item = (ConfigItem *)currentItem(); if (item) { - item->setSelected(true); + setSelected(item, true); menu = item->menu; } emit gotFocus(menu); @@ -1021,7 +1014,7 @@ ConfigInfoView::ConfigInfoView(QWidget* parent, const char *name) : Parent(parent), sym(0), _menu(0) { setObjectName(name); - + setOpenLinks(false); if (!objectName().isEmpty()) { configSettings->beginGroup(objectName()); @@ -1094,7 +1087,7 @@ void ConfigInfoView::menuInfo(void) if (sym->name) { head += " ("; if (showDebug()) - head += QString().sprintf("<a href=\"s%p\">", sym); + head += QString().sprintf("<a href=\"s%s\">", sym->name); head += print_filter(sym->name); if (showDebug()) head += "</a>"; @@ -1103,7 +1096,7 @@ void ConfigInfoView::menuInfo(void) } else if (sym->name) { head += "<big><b>"; if (showDebug()) - head += QString().sprintf("<a href=\"s%p\">", sym); + head += QString().sprintf("<a href=\"s%s\">", sym->name); head += print_filter(sym->name); if (showDebug()) head += "</a>"; @@ -1154,13 +1147,16 @@ QString ConfigInfoView::debug_info(struct symbol *sym) switch (prop->type) { case P_PROMPT: case P_MENU: - debug += QString().sprintf("prompt: <a href=\"m%p\">", prop->menu); + debug += QString().sprintf("prompt: <a href=\"m%s\">", sym->name); debug += print_filter(prop->text); debug += "</a><br>"; break; case P_DEFAULT: case P_SELECT: case P_RANGE: + case P_COMMENT: + case P_IMPLY: + case P_SYMBOL: debug += prop_get_type_name(prop->type); debug += ": "; expr_print(prop->expr, expr_print_help, &debug, E_NONE); @@ -1226,13 +1222,62 @@ void ConfigInfoView::expr_print_help(void *data, struct symbol *sym, const char QString str2 = print_filter(str); if (sym && sym->name && !(sym->flags & SYMBOL_CONST)) { - *text += QString().sprintf("<a href=\"s%p\">", sym); + *text += QString().sprintf("<a href=\"s%s\">", sym->name); *text += str2; *text += "</a>"; } else *text += str2; } +void ConfigInfoView::clicked(const QUrl &url) +{ + QByteArray str = url.toEncoded(); + const std::size_t count = str.size(); + char *data = new char[count + 1]; + struct symbol **result; + struct menu *m = NULL; + + if (count < 1) { + qInfo() << "Clicked link is empty"; + delete data; + return; + } + + memcpy(data, str.constData(), count); + data[count] = '\0'; + + /* Seek for exact match */ + data[0] = '^'; + strcat(data, "$"); + result = sym_re_search(data); + if (!result) { + qInfo() << "Clicked symbol is invalid:" << data; + delete data; + return; + } + + sym = *result; + + /* Seek for the menu which holds the symbol */ + for (struct property *prop = sym->prop; prop; prop = prop->next) { + if (prop->type != P_PROMPT && prop->type != P_MENU) + continue; + m = prop->menu; + break; + } + + if (!m) { + /* Symbol is not visible as a menu */ + symbolInfo(); + emit showDebugChanged(true); + } else { + emit menuSelected(m); + } + + free(result); + delete data; +} + QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos) { QMenu* popup = Parent::createStandardContextMenu(pos); @@ -1402,18 +1447,22 @@ ConfigMainWindow::ConfigMainWindow(void) addToolBar(toolBar); backAction = new QAction(QPixmap(xpm_back), "Back", this); - connect(backAction, SIGNAL(triggered(bool)), SLOT(goBack())); - backAction->setEnabled(false); + connect(backAction, SIGNAL(triggered(bool)), SLOT(goBack())); + QAction *quitAction = new QAction("&Quit", this); quitAction->setShortcut(Qt::CTRL + Qt::Key_Q); - connect(quitAction, SIGNAL(triggered(bool)), SLOT(close())); + connect(quitAction, SIGNAL(triggered(bool)), SLOT(close())); + QAction *loadAction = new QAction(QPixmap(xpm_load), "&Load", this); loadAction->setShortcut(Qt::CTRL + Qt::Key_L); - connect(loadAction, SIGNAL(triggered(bool)), SLOT(loadConfig())); + connect(loadAction, SIGNAL(triggered(bool)), SLOT(loadConfig())); + saveAction = new QAction(QPixmap(xpm_save), "&Save", this); saveAction->setShortcut(Qt::CTRL + Qt::Key_S); - connect(saveAction, SIGNAL(triggered(bool)), SLOT(saveConfig())); + connect(saveAction, SIGNAL(triggered(bool)), SLOT(saveConfig())); + conf_set_changed_callback(conf_changed); + // Set saveAction's initial state conf_changed(); configname = xstrdup(conf_get_configname()); @@ -1506,6 +1555,9 @@ ConfigMainWindow::ConfigMainWindow(void) helpMenu->addAction(showIntroAction); helpMenu->addAction(showAboutAction); + connect (helpText, SIGNAL (anchorClicked (const QUrl &)), + helpText, SLOT (clicked (const QUrl &)) ); + connect(configList, SIGNAL(menuChanged(struct menu *)), helpText, SLOT(setInfo(struct menu *))); connect(configList, SIGNAL(menuSelected(struct menu *)), @@ -1611,21 +1663,11 @@ void ConfigMainWindow::searchConfig(void) void ConfigMainWindow::changeItens(struct menu *menu) { configList->setRootMenu(menu); - - if (configList->rootEntry->parent == &rootmenu) - backAction->setEnabled(false); - else - backAction->setEnabled(true); } void ConfigMainWindow::changeMenu(struct menu *menu) { menuList->setRootMenu(menu); - - if (menuList->rootEntry->parent == &rootmenu) - backAction->setEnabled(false); - else - backAction->setEnabled(true); } void ConfigMainWindow::setMenuLink(struct menu *menu) @@ -1645,22 +1687,26 @@ void ConfigMainWindow::setMenuLink(struct menu *menu) return; list->setRootMenu(parent); break; - case symbolMode: + case menuMode: if (menu->flags & MENU_ROOT) { - configList->setRootMenu(menu); + menuList->setRootMenu(menu); configList->clearSelection(); - list = menuList; - } else { list = configList; + } else { parent = menu_get_parent_menu(menu->parent); if (!parent) return; - item = menuList->findConfigItem(parent); + + /* Select the config view */ + item = configList->findConfigItem(parent); if (item) { - item->setSelected(true); - menuList->scrollToItem(item); + configList->setSelected(item, true); + configList->scrollToItem(item); } - list->setRootMenu(parent); + + menuList->setRootMenu(parent); + menuList->clearSelection(); + list = menuList; } break; case fullMode: @@ -1673,9 +1719,10 @@ void ConfigMainWindow::setMenuLink(struct menu *menu) if (list) { item = list->findConfigItem(menu); if (item) { - item->setSelected(true); + list->setSelected(item, true); list->scrollToItem(item); list->setFocus(); + helpText->setInfo(menu); } } } @@ -1688,25 +1735,11 @@ void ConfigMainWindow::listFocusChanged(void) void ConfigMainWindow::goBack(void) { - ConfigItem* item, *oldSelection; - - configList->setParentMenu(); +qInfo() << __FUNCTION__; if (configList->rootEntry == &rootmenu) - backAction->setEnabled(false); - - if (menuList->selectedItems().count() == 0) return; - item = (ConfigItem*)menuList->selectedItems().first(); - oldSelection = item; - while (item) { - if (item->menu == configList->rootEntry) { - oldSelection->setSelected(false); - item->setSelected(true); - break; - } - item = (ConfigItem*)item->parent(); - } + configList->setParentMenu(); } void ConfigMainWindow::showSingleView(void) @@ -1718,6 +1751,8 @@ void ConfigMainWindow::showSingleView(void) fullViewAction->setEnabled(true); fullViewAction->setChecked(false); + backAction->setEnabled(true); + menuView->hide(); menuList->setRootMenu(0); configList->mode = singleMode; @@ -1737,6 +1772,8 @@ void ConfigMainWindow::showSplitView(void) fullViewAction->setEnabled(true); fullViewAction->setChecked(false); + backAction->setEnabled(false); + configList->mode = menuMode; if (configList->rootEntry == &rootmenu) configList->updateListAll(); @@ -1760,6 +1797,8 @@ void ConfigMainWindow::showFullView(void) fullViewAction->setEnabled(false); fullViewAction->setChecked(true); + backAction->setEnabled(false); + menuView->hide(); menuList->setRootMenu(0); configList->mode = fullMode; diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index c879d79ce817..fb9e9729266f 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -3,17 +3,17 @@ * Copyright (C) 2002 Roman Zippel <zippel@linux-m68k.org> */ -#include <QTextBrowser> -#include <QTreeWidget> -#include <QMainWindow> +#include <QCheckBox> +#include <QDialog> #include <QHeaderView> -#include <qsettings.h> +#include <QLineEdit> +#include <QMainWindow> #include <QPushButton> #include <QSettings> -#include <QLineEdit> #include <QSplitter> -#include <QCheckBox> -#include <QDialog> +#include <QTextBrowser> +#include <QTreeWidget> + #include "expr.h" class ConfigView; @@ -45,11 +45,17 @@ class ConfigList : public QTreeWidget { public: ConfigList(ConfigView* p, const char *name = 0); void reinit(void); + ConfigItem* findConfigItem(struct menu *); ConfigView* parent(void) const { return (ConfigView*)Parent::parent(); } - ConfigItem* findConfigItem(struct menu *); + void setSelected(QTreeWidgetItem *item, bool enable) { + for (int i = 0; i < selectedItems().size(); i++) + selectedItems().at(i)->setSelected(false); + + item->setSelected(enable); + } protected: void keyPressEvent(QKeyEvent *e); @@ -250,6 +256,7 @@ public slots: void setInfo(struct menu *menu); void saveSettings(void); void setShowDebug(bool); + void clicked (const QUrl &url); signals: void showDebugChanged(bool); diff --git a/security/integrity/iint.c b/security/integrity/iint.c index e12c4900510f..1d20003243c3 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -188,19 +188,7 @@ DEFINE_LSM(integrity) = { int integrity_kernel_read(struct file *file, loff_t offset, void *addr, unsigned long count) { - mm_segment_t old_fs; - char __user *buf = (char __user *)addr; - ssize_t ret; - - if (!(file->f_mode & FMODE_READ)) - return -EBADF; - - old_fs = get_fs(); - set_fs(KERNEL_DS); - ret = __vfs_read(file, buf, count, &offset); - set_fs(old_fs); - - return ret; + return __kernel_read(file, addr, count, &offset); } /* diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index df93ac258e01..9d94080bdad8 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -30,7 +30,7 @@ enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN, IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII }; -enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 }; +enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8, TPM_PCR10 = 10 }; /* digest size for IMA, fits SHA1 or MD5 */ #define IMA_DIGEST_SIZE SHA1_DIGEST_SIZE diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index 220b14920c37..011c3c76af86 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -823,13 +823,26 @@ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, if (rc != 0) return rc; - /* cumulative sha1 over tpm registers 0-7 */ + /* cumulative digest over TPM registers 0-7 */ for (i = TPM_PCR0; i < TPM_PCR8; i++) { ima_pcrread(i, &d); /* now accumulate with current aggregate */ rc = crypto_shash_update(shash, d.digest, crypto_shash_digestsize(tfm)); } + /* + * Extend cumulative digest over TPM registers 8-9, which contain + * measurement for the kernel command line (reg. 8) and image (reg. 9) + * in a typical PCR allocation. Registers 8-9 are only included in + * non-SHA1 boot_aggregate digests to avoid ambiguity. + */ + if (alg_id != TPM_ALG_SHA1) { + for (i = TPM_PCR8; i < TPM_PCR10; i++) { + ima_pcrread(i, &d); + rc = crypto_shash_update(shash, d.digest, + crypto_shash_digestsize(tfm)); + } + } if (!rc) crypto_shash_final(shash, digest); return rc; diff --git a/security/security.c b/security/security.c index 0ce3e73edd42..70a7ad357bc6 100644 --- a/security/security.c +++ b/security/security.c @@ -1414,7 +1414,22 @@ EXPORT_SYMBOL(security_inode_copy_up); int security_inode_copy_up_xattr(const char *name) { - return call_int_hook(inode_copy_up_xattr, -EOPNOTSUPP, name); + struct security_hook_list *hp; + int rc; + + /* + * The implementation can return 0 (accept the xattr), 1 (discard the + * xattr), -EOPNOTSUPP if it does not know anything about the xattr or + * any other error code incase of an error. + */ + hlist_for_each_entry(hp, + &security_hook_heads.inode_copy_up_xattr, list) { + rc = hp->hook.inode_copy_up_xattr(name); + if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) + return rc; + } + + return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 509290f2efa8..0e53f6f31916 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -764,6 +764,9 @@ static int snd_compr_stop(struct snd_compr_stream *stream) retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP); if (!retval) { + /* clear flags and stop any drain wait */ + stream->partial_drain = false; + stream->metadata_set = false; snd_compr_drain_notify(stream); stream->runtime->total_bytes_available = 0; stream->runtime->total_bytes_transferred = 0; @@ -921,6 +924,7 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream) if (stream->next_track == false) return -EPERM; + stream->partial_drain = true; retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN); if (retval) { pr_debug("Partial drain returned failure\n"); diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c index e69a4ef0d6bd..08c10ac9d6c8 100644 --- a/sound/drivers/opl3/opl3_synth.c +++ b/sound/drivers/opl3/opl3_synth.c @@ -91,6 +91,8 @@ int snd_opl3_ioctl(struct snd_hwdep * hw, struct file *file, { struct snd_dm_fm_info info; + memset(&info, 0, sizeof(info)); + info.fm_mode = opl3->fm_mode; info.rhythm = opl3->rhythm; if (copy_to_user(argp, &info, sizeof(struct snd_dm_fm_info))) diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c index 2c6d2becfe1a..824f4ac1a8ce 100644 --- a/sound/pci/hda/hda_auto_parser.c +++ b/sound/pci/hda/hda_auto_parser.c @@ -72,6 +72,12 @@ static int compare_input_type(const void *ap, const void *bp) if (a->type != b->type) return (int)(a->type - b->type); + /* If has both hs_mic and hp_mic, pick the hs_mic ahead of hp_mic. */ + if (a->is_headset_mic && b->is_headphone_mic) + return -1; /* don't swap */ + else if (a->is_headphone_mic && b->is_headset_mic) + return 1; /* swap */ + /* In case one has boost and the other one has not, pick the one with boost first. */ return (int)(b->has_boost_on_pin - a->has_boost_on_pin); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index e2b21ef5d7d1..41eaa89660c3 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -259,7 +259,7 @@ static int hinfo_to_pcm_index(struct hda_codec *codec, if (get_pcm_rec(spec, pcm_idx)->stream == hinfo) return pcm_idx; - codec_warn(codec, "HDMI: hinfo %p not registered\n", hinfo); + codec_warn(codec, "HDMI: hinfo %p not tied to a PCM\n", hinfo); return -EINVAL; } @@ -277,7 +277,8 @@ static int hinfo_to_pin_index(struct hda_codec *codec, return pin_idx; } - codec_dbg(codec, "HDMI: hinfo %p not registered\n", hinfo); + codec_dbg(codec, "HDMI: hinfo %p (pcm %d) not registered\n", hinfo, + hinfo_to_pcm_index(codec, hinfo)); return -EINVAL; } @@ -1804,33 +1805,43 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) static int hdmi_parse_codec(struct hda_codec *codec) { - hda_nid_t nid; + hda_nid_t start_nid; + unsigned int caps; int i, nodes; - nodes = snd_hda_get_sub_nodes(codec, codec->core.afg, &nid); - if (!nid || nodes < 0) { + nodes = snd_hda_get_sub_nodes(codec, codec->core.afg, &start_nid); + if (!start_nid || nodes < 0) { codec_warn(codec, "HDMI: failed to get afg sub nodes\n"); return -EINVAL; } - for (i = 0; i < nodes; i++, nid++) { - unsigned int caps; - unsigned int type; + /* + * hdmi_add_pin() assumes total amount of converters to + * be known, so first discover all converters + */ + for (i = 0; i < nodes; i++) { + hda_nid_t nid = start_nid + i; caps = get_wcaps(codec, nid); - type = get_wcaps_type(caps); if (!(caps & AC_WCAP_DIGITAL)) continue; - switch (type) { - case AC_WID_AUD_OUT: + if (get_wcaps_type(caps) == AC_WID_AUD_OUT) hdmi_add_cvt(codec, nid); - break; - case AC_WID_PIN: + } + + /* discover audio pins */ + for (i = 0; i < nodes; i++) { + hda_nid_t nid = start_nid + i; + + caps = get_wcaps(codec, nid); + + if (!(caps & AC_WCAP_DIGITAL)) + continue; + + if (get_wcaps_type(caps) == AC_WID_PIN) hdmi_add_pin(codec, nid); - break; - } } return 0; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 737ef82a75fd..194ffa8c66ce 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6149,6 +6149,9 @@ enum { ALC236_FIXUP_HP_MUTE_LED, ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS, + ALC269VC_FIXUP_ACER_HEADSET_MIC, + ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -7327,6 +7330,35 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE }, + [ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x14, 0x90100120 }, /* use as internal speaker */ + { 0x18, 0x02a111f0 }, /* use as headset mic, without its own jack detect */ + { 0x1a, 0x01011020 }, /* use as line out */ + { }, + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC + }, + [ALC269VC_FIXUP_ACER_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x18, 0x02a11030 }, /* use as headset mic */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC + }, + [ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x18, 0x01a11130 }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7342,10 +7374,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK), + SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), + SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), @@ -7571,8 +7606,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), - SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), + SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), diff --git a/sound/soc/amd/renoir/Makefile b/sound/soc/amd/renoir/Makefile index e4371932a55a..4a82690aec16 100644 --- a/sound/soc/amd/renoir/Makefile +++ b/sound/soc/amd/renoir/Makefile @@ -2,6 +2,7 @@ # Renoir platform Support snd-rn-pci-acp3x-objs := rn-pci-acp3x.o snd-acp3x-pdm-dma-objs := acp3x-pdm-dma.o -obj-$(CONFIG_SND_SOC_AMD_RENOIR) += snd-rn-pci-acp3x.o -obj-$(CONFIG_SND_SOC_AMD_RENOIR) += snd-acp3x-pdm-dma.o -obj-$(CONFIG_SND_SOC_AMD_RENOIR_MACH) += acp3x-rn.o +snd-acp3x-rn-objs := acp3x-rn.o +obj-$(CONFIG_SND_SOC_AMD_RENOIR) += snd-rn-pci-acp3x.o +obj-$(CONFIG_SND_SOC_AMD_RENOIR) += snd-acp3x-pdm-dma.o +obj-$(CONFIG_SND_SOC_AMD_RENOIR_MACH) += snd-acp3x-rn.o diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 3e9d2c6c51f9..7d6670abdb08 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -932,7 +932,9 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) RT5682_PWR_ANLG_1, RT5682_PWR_FV2, RT5682_PWR_FV2); snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3, RT5682_PWR_CBJ, RT5682_PWR_CBJ); - + snd_soc_component_update_bits(component, + RT5682_HP_CHARGE_PUMP_1, + RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH); @@ -956,6 +958,11 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) rt5682->jack_type = SND_JACK_HEADPHONE; break; } + + snd_soc_component_update_bits(component, + RT5682_HP_CHARGE_PUMP_1, + RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, + RT5682_OSW_L_EN | RT5682_OSW_R_EN); } else { rt5682_enable_push_button_irq(component, false); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c index 0c813a45bba7..69aeb0e71844 100644 --- a/sound/soc/fsl/fsl_mqs.c +++ b/sound/soc/fsl/fsl_mqs.c @@ -265,12 +265,20 @@ static int fsl_mqs_remove(struct platform_device *pdev) static int fsl_mqs_runtime_resume(struct device *dev) { struct fsl_mqs *mqs_priv = dev_get_drvdata(dev); + int ret; - if (mqs_priv->ipg) - clk_prepare_enable(mqs_priv->ipg); + ret = clk_prepare_enable(mqs_priv->ipg); + if (ret) { + dev_err(dev, "failed to enable ipg clock\n"); + return ret; + } - if (mqs_priv->mclk) - clk_prepare_enable(mqs_priv->mclk); + ret = clk_prepare_enable(mqs_priv->mclk); + if (ret) { + dev_err(dev, "failed to enable mclk clock\n"); + clk_disable_unprepare(mqs_priv->ipg); + return ret; + } if (mqs_priv->use_gpr) regmap_write(mqs_priv->regmap, IOMUXC_GPR2, @@ -292,11 +300,8 @@ static int fsl_mqs_runtime_suspend(struct device *dev) regmap_read(mqs_priv->regmap, REG_MQS_CTRL, &mqs_priv->reg_mqs_ctrl); - if (mqs_priv->mclk) - clk_disable_unprepare(mqs_priv->mclk); - - if (mqs_priv->ipg) - clk_disable_unprepare(mqs_priv->ipg); + clk_disable_unprepare(mqs_priv->mclk); + clk_disable_unprepare(mqs_priv->ipg); return 0; } diff --git a/sound/usb/card.h b/sound/usb/card.h index d6219fba9699..de43267b9c8a 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -84,10 +84,10 @@ struct snd_usb_endpoint { dma_addr_t sync_dma; /* DMA address of syncbuf */ unsigned int pipe; /* the data i/o pipe */ - unsigned int framesize[2]; /* small/large frame sizes in samples */ - unsigned int sample_rem; /* remainder from division fs/fps */ + unsigned int packsize[2]; /* small/large packet sizes in samples */ + unsigned int sample_rem; /* remainder from division fs/pps */ unsigned int sample_accum; /* sample accumulator */ - unsigned int fps; /* frames per second */ + unsigned int pps; /* packets per second */ unsigned int freqn; /* nominal sampling rate in fs/fps in Q16.16 format */ unsigned int freqm; /* momentary sampling rate in fs/fps in Q16.16 format */ int freqshift; /* how much to shift the feedback value to get Q16.16 */ diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 9bea7d3f99f8..88760268fb55 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -159,11 +159,11 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep) return ep->maxframesize; ep->sample_accum += ep->sample_rem; - if (ep->sample_accum >= ep->fps) { - ep->sample_accum -= ep->fps; - ret = ep->framesize[1]; + if (ep->sample_accum >= ep->pps) { + ep->sample_accum -= ep->pps; + ret = ep->packsize[1]; } else { - ret = ep->framesize[0]; + ret = ep->packsize[0]; } return ret; @@ -1088,15 +1088,15 @@ int snd_usb_endpoint_set_params(struct snd_usb_endpoint *ep, if (snd_usb_get_speed(ep->chip->dev) == USB_SPEED_FULL) { ep->freqn = get_usb_full_speed_rate(rate); - ep->fps = 1000; + ep->pps = 1000 >> ep->datainterval; } else { ep->freqn = get_usb_high_speed_rate(rate); - ep->fps = 8000; + ep->pps = 8000 >> ep->datainterval; } - ep->sample_rem = rate % ep->fps; - ep->framesize[0] = rate / ep->fps; - ep->framesize[1] = (rate + (ep->fps - 1)) / ep->fps; + ep->sample_rem = rate % ep->pps; + ep->packsize[0] = rate / ep->pps; + ep->packsize[1] = (rate + (ep->pps - 1)) / ep->pps; /* calculate the frequency in 16.16 format */ ep->freqm = ep->freqn; diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index a777d36c4f5a..40b7cd13fed9 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -368,6 +368,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, goto add_sync_ep_from_ifnum; case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ + case USB_ID(0x0d9a, 0x00df): /* RTX6001 */ ep = 0x81; ifnum = 2; goto add_sync_ep_from_ifnum; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 4ec491011b19..9092cc0aa807 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3633,4 +3633,56 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ } }, +/* + * MacroSilicon MS2109 based HDMI capture cards + * + * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch. + * They also need QUIRK_AUDIO_ALIGN_TRANSFER, which makes one wonder if + * they pretend to be 96kHz mono as a workaround for stereo being broken + * by that... + * + * They also have swapped L-R channels, but that's for userspace to deal + * with. + */ +{ + USB_DEVICE(0x534d, 0x2109), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .vendor_name = "MacroSilicon", + .product_name = "MS2109", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = &(const struct snd_usb_audio_quirk[]) { + { + .ifnum = 2, + .type = QUIRK_AUDIO_ALIGN_TRANSFER, + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 3, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels = 2, + .iface = 3, + .altsetting = 1, + .altset_idx = 1, + .attributes = 0, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC | + USB_ENDPOINT_SYNC_ASYNC, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 48000, + .rate_max = 48000, + } + }, + { + .ifnum = -1 + } + } + } +}, + #undef USB_DEVICE_VENDOR_SPEC diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index df767afc690f..45f8e1b02241 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include <asm/alternative-asm.h> #include <asm/export.h> +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 4671fbf28842..7f475d59a097 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -18,8 +18,7 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#if !defined(__ASSEMBLY__) && \ - (!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000) +#if !defined(__ASSEMBLY__) #include <linux/build_bug.h> #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 548a749aebb3..5e386389913a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3175,13 +3175,12 @@ union bpf_attr { * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) * Description * Copy *size* bytes from *data* into a ring buffer *ringbuf*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return - * 0, on success; - * < 0, on error. + * 0 on success, or a negative error in case of failure. * * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) * Description @@ -3193,20 +3192,20 @@ union bpf_attr { * void bpf_ringbuf_submit(void *data, u64 flags) * Description * Submit reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * * void bpf_ringbuf_discard(void *data, u64 flags) * Description * Discard reserved ring buffer sample, pointed to by *data*. - * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of - * new data availability is sent. - * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of - * new data availability is sent unconditionally. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. * Return * Nothing. Always succeeds. * @@ -3214,16 +3213,18 @@ union bpf_attr { * Description * Query various characteristics of provided ring buffer. What * exactly is queries is determined by *flags*: - * - BPF_RB_AVAIL_DATA - amount of data not yet consumed; - * - BPF_RB_RING_SIZE - the size of ring buffer; - * - BPF_RB_CONS_POS - consumer position (can wrap around); - * - BPF_RB_PROD_POS - producer(s) position (can wrap around); - * Data returned is just a momentary snapshots of actual values + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values * and could be inaccurate, so this facility should be used to * power heuristics and for reporting, not to make 100% correct * calculation. * Return - * Requested value, or 0, if flags are not recognized. + * Requested value, or 0, if *flags* are not recognized. * * long bpf_csum_level(struct sk_buff *skb, u64 level) * Description diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 1b6015b21ba8..dbef24ebcfcb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -233,6 +233,8 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); + +enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */ LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); #ifdef __cplusplus diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index df59fd4fc95b..e0af36b0e5d8 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -11,14 +11,18 @@ #include <stdbool.h> #include <stddef.h> #include <limits.h> -#ifndef __WORDSIZE -#define __WORDSIZE (__SIZEOF_LONG__ * 8) -#endif static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ - return (h * 11400714819323198485llu) >> (__WORDSIZE - bits); +#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) + /* LP64 case */ + return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); +#elif (__SIZEOF_SIZE_T__ <= __SIZEOF_LONG__) + return (h * 2654435769lu) >> (__SIZEOF_LONG__ * 8 - bits); +#else +# error "Unsupported size_t size" +#endif } typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 25e4f77be8d7..4489f95f1d1a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4978,7 +4978,13 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) err = -EINVAL; goto out; } - prog = bpf_object__find_program_by_title(obj, sec_name); + prog = NULL; + for (i = 0; i < obj->nr_programs; i++) { + if (!strcmp(obj->programs[i].section_name, sec_name)) { + prog = &obj->programs[i]; + break; + } + } if (!prog) { pr_warn("failed to find program '%s' for CO-RE offset relocation\n", sec_name); @@ -6904,7 +6910,7 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, .attach_fn = attach_iter), - BPF_EAPROG_SEC("xdp_devmap", BPF_PROG_TYPE_XDP, + BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index 27f3b07fdae8..f1640d651c8a 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -361,6 +361,7 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, break; case KBUFFER_TYPE_TIME_EXTEND: + case KBUFFER_TYPE_TIME_STAMP: extend = read_4(kbuf, data); data += 4; extend <<= TS_SHIFT; @@ -369,10 +370,6 @@ translate_data(struct kbuffer *kbuf, void *data, void **rptr, *length = 0; break; - case KBUFFER_TYPE_TIME_STAMP: - data += 12; - *length = 0; - break; case 0: *length = read_4(kbuf, data) - 4; *length = (*length + 3) & ~3; @@ -397,7 +394,11 @@ static unsigned int update_pointers(struct kbuffer *kbuf) type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); - kbuf->timestamp += delta; + if (type_len == KBUFFER_TYPE_TIME_STAMP) + kbuf->timestamp = delta; + else + kbuf->timestamp += delta; + kbuf->index = calc_index(kbuf, ptr); kbuf->next = kbuf->index + length; @@ -454,7 +455,9 @@ static int __next_event(struct kbuffer *kbuf) if (kbuf->next >= kbuf->size) return -1; type = update_pointers(kbuf); - } while (type == KBUFFER_TYPE_TIME_EXTEND || type == KBUFFER_TYPE_PADDING); + } while (type == KBUFFER_TYPE_TIME_EXTEND || + type == KBUFFER_TYPE_TIME_STAMP || + type == KBUFFER_TYPE_PADDING); return 0; } @@ -547,6 +550,34 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer) } /** + * kbuffer_subbuf_timestamp - read the timestamp from a sub buffer + * @kbuf: The kbuffer to load + * @subbuf: The subbuffer to read from. + * + * Return the timestamp from a subbuffer. + */ +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf) +{ + return kbuf->read_8(subbuf); +} + +/** + * kbuffer_ptr_delta - read the delta field from a record + * @kbuf: The kbuffer to load + * @ptr: The record in the buffe. + * + * Return the timestamp delta from a record + */ +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr) +{ + unsigned int type_len_ts; + + type_len_ts = read_4(kbuf, ptr); + return ts4host(kbuf, type_len_ts); +} + + +/** * kbuffer_read_event - read the next event in the kbuffer subbuffer * @kbuf: The kbuffer to read from * @ts: The address to store the timestamp of the event (may be NULL to ignore) diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h index ed4d697fc137..5fa8292e341b 100644 --- a/tools/lib/traceevent/kbuffer.h +++ b/tools/lib/traceevent/kbuffer.h @@ -49,6 +49,8 @@ int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer); void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts); void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts); unsigned long long kbuffer_timestamp(struct kbuffer *kbuf); +unsigned long long kbuffer_subbuf_timestamp(struct kbuffer *kbuf, void *subbuf); +unsigned int kbuffer_ptr_delta(struct kbuffer *kbuf, void *ptr); void *kbuffer_translate_data(int swap, void *data, unsigned int *size); diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index eda15a5a285e..3c5967748abb 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -84,4 +84,6 @@ unsigned long arch_jump_destination(struct instruction *insn); unsigned long arch_dest_rela_offset(int addend); +const char *arch_nop_insn(int len); + #endif /* _ARCH_H */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 4b504fc90bbb..9872195f998b 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -565,3 +565,21 @@ void arch_initial_func_cfi_state(struct cfi_init_state *state) state->regs[16].base = CFI_CFA; state->regs[16].offset = -8; } + +const char *arch_nop_insn(int len) +{ + static const char nops[5][5] = { + /* 1 */ { 0x90 }, + /* 2 */ { 0x66, 0x90 }, + /* 3 */ { 0x0f, 0x1f, 0x00 }, + /* 4 */ { 0x0f, 0x1f, 0x40, 0x00 }, + /* 5 */ { 0x0f, 0x1f, 0x44, 0x00, 0x00 }, + }; + + if (len < 1 || len > 5) { + WARN("invalid NOP size: %d\n", len); + return NULL; + } + + return nops[len-1]; +} diff --git a/tools/objtool/arch/x86/include/arch_elf.h b/tools/objtool/arch/x86/include/arch_elf.h new file mode 100644 index 000000000000..69cc4264b28a --- /dev/null +++ b/tools/objtool/arch/x86/include/arch_elf.h @@ -0,0 +1,6 @@ +#ifndef _OBJTOOL_ARCH_ELF +#define _OBJTOOL_ARCH_ELF + +#define R_NONE R_X86_64_NONE + +#endif /* _OBJTOOL_ARCH_ELF */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5fbb90a80d23..5e0d70a89fb8 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -12,6 +12,7 @@ #include "check.h" #include "special.h" #include "warn.h" +#include "arch_elf.h" #include <linux/hashtable.h> #include <linux/kernel.h> @@ -766,6 +767,24 @@ static int add_call_destinations(struct objtool_file *file) insn->call_dest = rela->sym; /* + * Many compilers cannot disable KCOV with a function attribute + * so they need a little help, NOP out any KCOV calls from noinstr + * text. + */ + if (insn->sec->noinstr && + !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { + if (rela) { + rela->type = R_NONE; + elf_write_rela(file->elf, rela); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + arch_nop_insn(insn->len)); + insn->type = INSN_NOP; + } + + /* * Whatever stack impact regular CALLs have, should be undone * by the RETURN of the called function. * @@ -2190,10 +2209,36 @@ static inline const char *call_dest_name(struct instruction *insn) return "{dynamic}"; } +static inline bool noinstr_call_dest(struct symbol *func) +{ + /* + * We can't deal with indirect function calls at present; + * assume they're instrumented. + */ + if (!func) + return false; + + /* + * If the symbol is from a noinstr section; we good. + */ + if (func->sec->noinstr) + return true; + + /* + * The __ubsan_handle_*() calls are like WARN(), they only happen when + * something 'BAD' happened. At the risk of taking the machine down, + * let them proceed to get the message out. + */ + if (!strncmp(func->name, "__ubsan_handle_", 15)) + return true; + + return false; +} + static int validate_call(struct instruction *insn, struct insn_state *state) { if (state->noinstr && state->instr <= 0 && - (!insn->call_dest || !insn->call_dest->sec->noinstr)) { + !noinstr_call_dest(insn->call_dest)) { WARN_FUNC("call to %s() leaves .noinstr.text section", insn->sec, insn->offset, call_dest_name(insn)); return 1; @@ -2740,13 +2785,13 @@ int check(const char *_objname, bool orc) objname = _objname; - file.elf = elf_open_read(objname, orc ? O_RDWR : O_RDONLY); + file.elf = elf_open_read(objname, O_RDWR); if (!file.elf) return 1; INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); - file.c_file = find_section_by_name(file.elf, ".comment"); + file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment"); file.ignore_unreachables = no_unreachable; file.hints = false; @@ -2801,7 +2846,9 @@ int check(const char *_objname, bool orc) ret = create_orc_sections(&file); if (ret < 0) goto out; + } + if (file.elf->changed) { ret = elf_write(file.elf); if (ret < 0) goto out; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 84225679f96d..26d11d821941 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -529,8 +529,9 @@ static int read_relas(struct elf *elf) rela->addend = rela->rela.r_addend; rela->offset = rela->rela.r_offset; symndx = GELF_R_SYM(rela->rela.r_info); - rela->sym = find_symbol_by_index(elf, symndx); rela->sec = sec; + rela->idx = i; + rela->sym = find_symbol_by_index(elf, symndx); if (!rela->sym) { WARN("can't find rela entry symbol %d for %s", symndx, sec->name); @@ -713,6 +714,8 @@ struct section *elf_create_section(struct elf *elf, const char *name, elf_hash_add(elf->section_hash, &sec->hash, sec->idx); elf_hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name)); + elf->changed = true; + return sec; } @@ -746,7 +749,7 @@ struct section *elf_create_rela_section(struct elf *elf, struct section *base) return sec; } -int elf_rebuild_rela_section(struct section *sec) +int elf_rebuild_rela_section(struct elf *elf, struct section *sec) { struct rela *rela; int nr, idx = 0, size; @@ -763,6 +766,9 @@ int elf_rebuild_rela_section(struct section *sec) return -1; } + sec->changed = true; + elf->changed = true; + sec->data->d_buf = relas; sec->data->d_size = size; @@ -779,7 +785,44 @@ int elf_rebuild_rela_section(struct section *sec) return 0; } -int elf_write(const struct elf *elf) +int elf_write_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int len, + const char *insn) +{ + Elf_Data *data = sec->data; + + if (data->d_type != ELF_T_BYTE || data->d_off) { + WARN("write to unexpected data for section: %s", sec->name); + return -1; + } + + memcpy(data->d_buf + offset, insn, len); + elf_flagdata(data, ELF_C_SET, ELF_F_DIRTY); + + elf->changed = true; + + return 0; +} + +int elf_write_rela(struct elf *elf, struct rela *rela) +{ + struct section *sec = rela->sec; + + rela->rela.r_info = GELF_R_INFO(rela->sym->idx, rela->type); + rela->rela.r_addend = rela->addend; + rela->rela.r_offset = rela->offset; + + if (!gelf_update_rela(sec->data, rela->idx, &rela->rela)) { + WARN_ELF("gelf_update_rela"); + return -1; + } + + elf->changed = true; + + return 0; +} + +int elf_write(struct elf *elf) { struct section *sec; Elf_Scn *s; @@ -796,6 +839,8 @@ int elf_write(const struct elf *elf) WARN_ELF("gelf_update_shdr"); return -1; } + + sec->changed = false; } } @@ -808,6 +853,8 @@ int elf_write(const struct elf *elf) return -1; } + elf->changed = false; + return 0; } diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index f4fe1d6ea392..7324e772583e 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -64,9 +64,10 @@ struct rela { GElf_Rela rela; struct section *sec; struct symbol *sym; - unsigned int type; unsigned long offset; + unsigned int type; int addend; + int idx; bool jump_table_start; }; @@ -76,6 +77,7 @@ struct elf { Elf *elf; GElf_Ehdr ehdr; int fd; + bool changed; char *name; struct list_head sections; DECLARE_HASHTABLE(symbol_hash, ELF_HASH_BITS); @@ -118,7 +120,11 @@ struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, size_t entsize, int nr); struct section *elf_create_rela_section(struct elf *elf, struct section *base); void elf_add_rela(struct elf *elf, struct rela *rela); -int elf_write(const struct elf *elf); +int elf_write_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int len, + const char *insn); +int elf_write_rela(struct elf *elf, struct rela *rela); +int elf_write(struct elf *elf); void elf_close(struct elf *elf); struct section *find_section_by_name(const struct elf *elf, const char *name); @@ -130,7 +136,7 @@ struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsig struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_func_containing(struct section *sec, unsigned long offset); -int elf_rebuild_rela_section(struct section *sec); +int elf_rebuild_rela_section(struct elf *elf, struct section *sec); #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index c9549988121a..4c37f80eb987 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -222,7 +222,7 @@ int create_orc_sections(struct objtool_file *file) } } - if (elf_rebuild_rela_section(ip_relasec)) + if (elf_rebuild_rela_section(file->elf, ip_relasec)) return -1; return 0; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 839ef52c1ac2..6ce451293634 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -641,6 +641,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, } evsel->core.attr.freq = 0; evsel->core.attr.sample_period = 1; + evsel->no_aux_samples = true; intel_pt_evsel = evsel; opts->full_auxtrace = true; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e108d90ae2ed..a37e7910e9e9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -852,20 +852,20 @@ static int record__open(struct record *rec) * event synthesis. */ if (opts->initial_delay || target__has_cpu(&opts->target)) { - if (perf_evlist__add_dummy(evlist)) - return -ENOMEM; + pos = perf_evlist__get_tracking_event(evlist); + if (!evsel__is_dummy_event(pos)) { + /* Set up dummy event. */ + if (perf_evlist__add_dummy(evlist)) + return -ENOMEM; + pos = evlist__last(evlist); + perf_evlist__set_tracking_event(evlist, pos); + } - /* Disable tracking of mmaps on lead event. */ - pos = evlist__first(evlist); - pos->tracking = 0; - /* Set up dummy event. */ - pos = evlist__last(evlist); - pos->tracking = 1; /* * Enable the dummy event when the process is forked for * initial_delay, immediately for system wide. */ - if (opts->initial_delay) + if (opts->initial_delay && !pos->immediate) pos->core.attr.enable_on_exec = 1; else pos->immediate = 1; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 181d65e5a450..447457786362 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -462,7 +462,7 @@ static int perf_evsel__check_attr(struct evsel *evsel, struct perf_session *sess return -EINVAL; if (PRINT_FIELD(IREGS) && - evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS)) + evsel__do_check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS, allow_user_set)) return -EINVAL; if (PRINT_FIELD(UREGS) && diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 7bd73a904b4e..d187e46c2683 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -1055,7 +1055,7 @@ def cbr(id, raw_buf): cbr = data[0] MHz = (data[4] + 500) / 1000 percent = ((cbr * 1000 / data[2]) + 5) / 10 - value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent) + value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, int(MHz), 4, int(percent)) cbr_file.write(value) def mwait(id, raw_buf): diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 26d7be785288..7daa8bb70a5a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -768,7 +768,8 @@ class CallGraphModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " GROUP BY comm_id, thread_id, call_path_id" " ORDER BY comm_id, thread_id, call_path_id") @@ -963,7 +964,8 @@ class CallTreeModel(CallGraphModelBase): " FROM calls" " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" - " WHERE symbols.name" + match + + " WHERE calls.id <> 0" + " AND symbols.name" + match + " ORDER BY comm_id, thread_id, call_time, calls.id") def FindPath(self, query): @@ -1050,6 +1052,7 @@ class TreeWindowBase(QMdiSubWindow): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break @@ -1127,6 +1130,7 @@ class CallTreeWindow(TreeWindowBase): child = self.model.index(row, 0, parent) if child.internalPointer().dbid == dbid: found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) parent = child break @@ -1139,6 +1143,7 @@ class CallTreeWindow(TreeWindowBase): return last_child = None for row in xrange(n): + self.view.setExpanded(parent, True) child = self.model.index(row, 0, parent) child_call_time = child.internalPointer().call_time if child_call_time < time: @@ -1151,9 +1156,11 @@ class CallTreeWindow(TreeWindowBase): if not last_child: if not found: child = self.model.index(0, 0, parent) + self.view.setExpanded(parent, True) self.view.setCurrentIndex(child) return found = True + self.view.setExpanded(parent, True) self.view.setCurrentIndex(last_child) parent = last_child diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py index 61f3be9add6b..65780013f745 100755 --- a/tools/perf/scripts/python/flamegraph.py +++ b/tools/perf/scripts/python/flamegraph.py @@ -17,6 +17,7 @@ from __future__ import print_function import sys import os +import io import argparse import json @@ -81,7 +82,7 @@ class FlameGraphCLI: if self.args.format == "html": try: - with open(self.args.template) as f: + with io.open(self.args.template, encoding="utf-8") as f: output_str = f.read().replace("/** @flamegraph_json **/", json_str) except IOError as e: @@ -93,11 +94,12 @@ class FlameGraphCLI: output_fn = self.args.output or "stacks.json" if output_fn == "-": - sys.stdout.write(output_str) + with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out: + out.write(output_str) else: print("dumping data to {}".format(output_fn)) try: - with open(output_fn, "w") as out: + with io.open(output_fn, "w", encoding="utf-8") as out: out.write(output_str) except IOError as e: print("Error writing output file: {}".format(e), file=sys.stderr) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index f98a118dfc49..be9c4c0549bc 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2288,6 +2288,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser return browser->he_selection->thread; } +static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser) +{ + return browser->he_selection ? browser->he_selection->res_samples : NULL; +} + /* Check whether the browser is for 'top' or 'report' */ static inline bool is_report_browser(void *timer) { @@ -3357,16 +3362,16 @@ skip_annotation: &options[nr_options], NULL, NULL, evsel); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_NORMAL); + hist_browser__selected_res_sample(browser), + evsel, A_NORMAL); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_ASM); + hist_browser__selected_res_sample(browser), + evsel, A_ASM); nr_options += add_res_sample_opt(browser, &actions[nr_options], &options[nr_options], - hist_browser__selected_entry(browser)->res_samples, - evsel, A_SOURCE); + hist_browser__selected_res_sample(browser), + evsel, A_SOURCE); nr_options += add_switch_opt(browser, &actions[nr_options], &options[nr_options]); skip_scripting: @@ -3598,6 +3603,23 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist, hbt, warn_lost_event); } +static bool perf_evlist__single_entry(struct evlist *evlist) +{ + int nr_entries = evlist->core.nr_entries; + + if (nr_entries == 1) + return true; + + if (nr_entries == 2) { + struct evsel *last = evlist__last(evlist); + + if (evsel__is_dummy_event(last)) + return true; + } + + return false; +} + int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, @@ -3608,7 +3630,7 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, int nr_entries = evlist->core.nr_entries; single_entry: - if (nr_entries == 1) { + if (perf_evlist__single_entry(evlist)) { struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 173b4f0e0e6e..ab48be4cf258 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1566,6 +1566,18 @@ void perf_evlist__to_front(struct evlist *evlist, list_splice(&move, &evlist->core.entries); } +struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->tracking) + return evsel; + } + + return evlist__first(evlist); +} + void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b6f325dfb4d2..a8081dfc19cf 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -335,6 +335,7 @@ void perf_evlist__to_front(struct evlist *evlist, evlist__cpu_iter_start(evlist); \ perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) +struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist); void perf_evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 96e5171dce41..ef802f6d40c1 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -898,12 +898,6 @@ static void evsel__apply_config_terms(struct evsel *evsel, } } -static bool is_dummy_event(struct evsel *evsel) -{ - return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && - (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); -} - struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type) { struct evsel_config_term *term, *found_term = NULL; @@ -1020,12 +1014,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (callchain && callchain->enabled && !evsel->no_aux_samples) evsel__config_callchain(evsel, opts, callchain); - if (opts->sample_intr_regs) { + if (opts->sample_intr_regs && !evsel->no_aux_samples) { attr->sample_regs_intr = opts->sample_intr_regs; evsel__set_sample_bit(evsel, REGS_INTR); } - if (opts->sample_user_regs) { + if (opts->sample_user_regs && !evsel->no_aux_samples) { attr->sample_regs_user |= opts->sample_user_regs; evsel__set_sample_bit(evsel, REGS_USER); } @@ -1161,7 +1155,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, * The software event will trigger -EOPNOTSUPP error out, * if BRANCH_STACK bit is set. */ - if (is_dummy_event(evsel)) + if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0f963c2a88a5..35e3f6d66085 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -399,6 +399,12 @@ static inline bool evsel__has_br_stack(const struct evsel *evsel) evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK; } +static inline bool evsel__is_dummy_event(struct evsel *evsel) +{ + return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) && + (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); +} + struct perf_env *evsel__env(struct evsel *evsel); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index e4dd8bf610ce..cb3c1e569a2d 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1735,6 +1735,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) u64 sample_type = evsel->core.attr.sample_type; u64 id = evsel->core.id[0]; u8 cpumode; + u64 regs[8 * sizeof(sample.intr_regs.mask)]; if (intel_pt_skip_event(pt)) return 0; @@ -1784,8 +1785,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) } if (sample_type & PERF_SAMPLE_REGS_INTR && - items->mask[INTEL_PT_GP_REGS_POS]) { - u64 regs[sizeof(sample.intr_regs.mask)]; + (items->mask[INTEL_PT_GP_REGS_POS] || + items->mask[INTEL_PT_XMM_POS])) { u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 787b6d4ad716..f9b769f3437d 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -82,7 +82,9 @@ def build_tests(linux: kunit_kernel.LinuxSourceTree, request.make_options) build_end = time.time() if not success: - return KunitResult(KunitStatus.BUILD_FAILURE, 'could not build kernel') + return KunitResult(KunitStatus.BUILD_FAILURE, + 'could not build kernel', + build_end - build_start) if not success: return KunitResult(KunitStatus.BUILD_FAILURE, 'could not build kernel', diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py index e75063d603b5..02ffc3a3e5dc 100644 --- a/tools/testing/kunit/kunit_config.py +++ b/tools/testing/kunit/kunit_config.py @@ -10,7 +10,7 @@ import collections import re CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$' -CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+)$' +CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$' KconfigEntryBase = collections.namedtuple('KconfigEntry', ['name', 'value']) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 64aac9dcd431..f13e0c0d6663 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -265,11 +265,9 @@ def bubble_up_suite_errors(test_suite_list: List[TestSuite]) -> TestStatus: return bubble_up_errors(lambda x: x.status, test_suite_list) def parse_test_result(lines: List[str]) -> TestResult: - if not lines: - return TestResult(TestStatus.NO_TESTS, [], lines) consume_non_diagnositic(lines) - if not parse_tap_header(lines): - return None + if not lines or not parse_tap_header(lines): + return TestResult(TestStatus.NO_TESTS, [], lines) test_suites = [] test_suite = parse_test_suite(lines) while test_suite: @@ -282,6 +280,8 @@ def parse_run_tests(kernel_output) -> TestResult: failed_tests = 0 crashed_tests = 0 test_result = parse_test_result(list(isolate_kunit_output(kernel_output))) + if test_result.status == TestStatus.NO_TESTS: + print_with_timestamp(red('[ERROR] ') + 'no kunit output detected') for test_suite in test_result.suites: if test_suite.status == TestStatus.SUCCESS: print_suite_divider(green('[PASSED] ') + test_suite.name) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 5bb7b118ebd9..f9eeaea94cad 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -170,6 +170,17 @@ class KUnitParserTest(unittest.TestCase): result.status) file.close() + def test_no_kunit_output(self): + crash_log = get_absolute_path( + 'test_data/test_insufficient_memory.log') + file = open(crash_log) + print_mock = mock.patch('builtins.print').start() + result = kunit_parser.parse_run_tests( + kunit_parser.isolate_kunit_output(file.readlines())) + print_mock.assert_any_call(StrContains("no kunit output detected")) + print_mock.stop() + file.close() + def test_crashed_test(self): crashed_log = get_absolute_path( 'test_data/test_is_test_passed-crash.log') diff --git a/tools/testing/kunit/test_data/test_insufficient_memory.log b/tools/testing/kunit/test_data/test_insufficient_memory.log new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/kunit/test_data/test_insufficient_memory.log diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile index b497cfea4643..ac4ad0005715 100644 --- a/tools/testing/selftests/arm64/signal/Makefile +++ b/tools/testing/selftests/arm64/signal/Makefile @@ -21,10 +21,6 @@ include ../../lib.mk $(TEST_GEN_PROGS): $(PROGS) cp $(PROGS) $(OUTPUT)/ -clean: - $(CLEAN) - rm -f $(PROGS) - # Common test-unit targets to build common-layout test-cases executables # Needs secondary expansion to properly include the testcase c-file in pre-reqs .SECONDEXPANSION: diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 83493bd5745c..109d0345a2be 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -36,7 +36,7 @@ void test_fentry_fexit(void) fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss; printf("%lld\n", fentry_skel->bss->test1_result); - for (i = 0; i < 6; i++) { + for (i = 0; i < 8; i++) { CHECK(fentry_res[i] != 1, "result", "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); CHECK(fexit_res[i] != 1, "result", diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ea14e3ece812..f11f187990e9 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -527,8 +527,8 @@ static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd) run_tests_skb_less(tap_fd, skel->maps.last_dissection); - err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); - CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno); + err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno); } static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 15cb554a66d8..172c586b6996 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -1,9 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Test that the flow_dissector program can be updated with a single - * syscall by attaching a new program that replaces the existing one. - * - * Corner case - the same program cannot be attached twice. + * Tests for attaching, detaching, and replacing flow_dissector BPF program. */ #define _GNU_SOURCE @@ -116,7 +113,7 @@ static void test_prog_attach_prog_attach(int netns, int prog1, int prog2) CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2)); out_detach: - err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog2, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); CHECK_FAIL(prog_is_attached(netns)); @@ -152,7 +149,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); int err, link; - err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(err)) { perror("bpf_prog_attach(prog1)"); return; @@ -168,7 +165,7 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) close(link); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); - err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) perror("bpf_prog_detach"); CHECK_FAIL(prog_is_attached(netns)); @@ -188,7 +185,7 @@ static void test_link_create_prog_attach(int netns, int prog1, int prog2) /* Expect failure attaching prog when link exists */ errno = 0; - err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0); + err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0); if (CHECK_FAIL(!err || errno != EEXIST)) perror("bpf_prog_attach(prog2) expected EEXIST"); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -211,7 +208,7 @@ static void test_link_create_prog_detach(int netns, int prog1, int prog2) /* Expect failure detaching prog when link exists */ errno = 0; - err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(!err || errno != EINVAL)) perror("bpf_prog_detach expected EINVAL"); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -231,7 +228,7 @@ static void test_prog_attach_detach_query(int netns, int prog1, int prog2) } CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); - err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR); + err = bpf_prog_detach2(prog1, 0, BPF_FLOW_DISSECTOR); if (CHECK_FAIL(err)) { perror("bpf_prog_detach"); return; @@ -308,6 +305,31 @@ static void test_link_update_replace_old_prog(int netns, int prog1, int prog2) CHECK_FAIL(prog_is_attached(netns)); } +static void test_link_update_same_prog(int netns, int prog1, int prog2) +{ + DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int err, link; + + link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts); + if (CHECK_FAIL(link < 0)) { + perror("bpf_link_create(prog1)"); + return; + } + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + /* Expect success updating the prog with the same one */ + update_opts.flags = 0; + update_opts.old_prog_fd = 0; + err = bpf_link_update(link, prog1, &update_opts); + if (CHECK_FAIL(err)) + perror("bpf_link_update"); + CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); + + close(link); + CHECK_FAIL(prog_is_attached(netns)); +} + static void test_link_update_invalid_opts(int netns, int prog1, int prog2) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts); @@ -571,6 +593,8 @@ static void run_tests(int netns) test_link_update_no_old_prog }, { "link update with replace old prog", test_link_update_replace_old_prog }, + { "link update with same prog", + test_link_update_same_prog }, { "link update invalid opts", test_link_update_invalid_opts }, { "link update invalid prog", diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index cec82a419800..b9c2756c5c97 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -7,7 +7,21 @@ char _license[] SEC("license") = "GPL"; -static inline struct inode *SOCK_INODE(struct socket *socket) +#define sk_rmem_alloc sk_backlog.rmem_alloc +#define sk_refcnt __sk_common.skc_refcnt + +struct bpf_iter_meta { + struct seq_file *seq; + __u64 session_id; + __u64 seq_num; +} __attribute__((preserve_access_index)); + +struct bpf_iter__netlink { + struct bpf_iter_meta *meta; + struct netlink_sock *sk; +} __attribute__((preserve_access_index)); + +static __attribute__((noinline)) struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 9365b686f84b..5f645fdaba6f 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -55,3 +55,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f) e == (void *)20 && f == 21; return 0; } + +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +__u64 test7_result = 0; +SEC("fentry/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (arg == 0) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fentry/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index bd1e17d8024c..0952affb22a6 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -56,3 +56,25 @@ int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret) e == (void *)20 && f == 21 && ret == 111; return 0; } + +struct bpf_fentry_test_t { + struct bpf_fentry_test *a; +}; + +__u64 test7_result = 0; +SEC("fexit/bpf_fentry_test7") +int BPF_PROG(test7, struct bpf_fentry_test_t *arg) +{ + if (arg == 0) + test7_result = 1; + return 0; +} + +__u64 test8_result = 0; +SEC("fexit/bpf_fentry_test8") +int BPF_PROG(test8, struct bpf_fentry_test_t *arg) +{ + if (arg->a == 0) + test8_result = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 057036ca1111..3dca4c2e2418 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -79,7 +79,7 @@ struct { struct { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 2); + __uint(max_entries, 3); __type(key, int); __type(value, int); } sock_skb_opts SEC(".maps"); @@ -94,6 +94,12 @@ struct { SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { + int *f, two = 2; + + f = bpf_map_lookup_elem(&sock_skb_opts, &two); + if (f && *f) { + return *f; + } return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 330811260123..0ac086497722 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -27,7 +27,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) /* valid program on DEVMAP entry via SEC name; * has access to egress and ingress ifindex */ -SEC("xdp_devmap") +SEC("xdp_devmap/map_prog") int xdp_dummy_dm(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 6a12a0e01e07..754cf611723e 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -789,19 +789,19 @@ static void test_sockmap(unsigned int tasks, void *data) } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER); - if (err) { + if (!err) { printf("Failed empty parser prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT); - if (err) { + if (!err) { printf("Failed empty verdict prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_MSG_VERDICT); - if (err) { + if (!err) { printf("Failed empty msg verdict prog detach\n"); goto out_sockmap; } @@ -1090,19 +1090,19 @@ static void test_sockmap(unsigned int tasks, void *data) assert(status == 0); } - err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE); + err = bpf_prog_detach2(parse_prog, map_fd_rx, __MAX_BPF_ATTACH_TYPE); if (!err) { printf("Detached an invalid prog type.\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER); + err = bpf_prog_detach2(parse_prog, map_fd_rx, BPF_SK_SKB_STREAM_PARSER); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); + err = bpf_prog_detach2(verdict_prog, map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 37695fc8096a..78789b27e573 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -85,6 +85,7 @@ int txmsg_ktls_skb_drop; int txmsg_ktls_skb_redir; int ktls; int peek_flag; +int skb_use_parser; static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, @@ -174,6 +175,7 @@ static void test_reset(void) txmsg_apply = txmsg_cork = 0; txmsg_ingress = txmsg_redir_skb = 0; txmsg_ktls_skb = txmsg_ktls_skb_drop = txmsg_ktls_skb_redir = 0; + skb_use_parser = 0; } static int test_start_subtest(const struct _test *t, struct sockmap_options *o) @@ -1211,6 +1213,11 @@ run: } } + if (skb_use_parser) { + i = 2; + err = bpf_map_update_elem(map_fd[7], &i, &skb_use_parser, BPF_ANY); + } + if (txmsg_drop) options->drop_expected = true; @@ -1650,6 +1657,16 @@ static void test_txmsg_cork(int cgrp, struct sockmap_options *opt) test_send(opt, cgrp); } +static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt) +{ + txmsg_pass = 1; + skb_use_parser = 512; + opt->iov_length = 256; + opt->iov_count = 1; + opt->rate = 2; + test_exec(cgrp, opt); +} + char *map_names[] = { "sock_map", "sock_map_txmsg", @@ -1748,6 +1765,7 @@ struct _test test[] = { {"txmsg test pull-data", test_txmsg_pull}, {"txmsg test pop-data", test_txmsg_pop}, {"txmsg test push/pop data", test_txmsg_push_pop}, + {"txmsg text ingress parser", test_txmsg_ingress_parser}, }; static int check_whitelist(struct _test *t, struct sockmap_options *opt) diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 0d347d48c112..45042105ead7 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -121,6 +121,7 @@ h1_destroy() h2_create() { host_create $h2 2 + tc qdisc add dev $h2 clsact # Some of the tests in this suite use multicast traffic. As this traffic # enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus @@ -141,6 +142,7 @@ h2_create() h2_destroy() { ethtool -s $h2 autoneg on + tc qdisc del dev $h2 clsact host_destroy $h2 } @@ -336,6 +338,17 @@ get_qdisc_npackets() qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets } +send_packets() +{ + local vlan=$1; shift + local proto=$1; shift + local pkts=$1; shift + + $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ + -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ + -t $proto -q -c $pkts "$@" +} + # This sends traffic in an attempt to build a backlog of $size. Returns 0 on # success. After 10 failed attempts it bails out and returns 1. It dumps the # backlog size to stdout. @@ -364,9 +377,7 @@ build_backlog() return 1 fi - $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ - -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ - -t $proto -q -c $pkts "$@" + send_packets $vlan $proto $pkts "$@" done } @@ -531,3 +542,92 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } + +do_drop_test() +{ + local vlan=$1; shift + local limit=$1; shift + local trigger=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local backlog + local base + local now + local pct + + RET=0 + + start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac + + # Create a bit of a backlog and observe no mirroring due to drops. + qevent_rule_install_$subtest + base=$($fetch_counter) + + build_backlog $vlan $((2 * limit / 3)) udp >/dev/null + + busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed without buffer pressure" + + qevent_rule_uninstall_$subtest + + # Push to the queue until it's at the limit. The configured limit is + # rounded by the qdisc and then by the driver, so this is the best we + # can do to get to the real limit of the system. Do this with the rules + # uninstalled so that the inevitable drops don't get counted. + build_backlog $vlan $((3 * limit / 2)) udp >/dev/null + + qevent_rule_install_$subtest + base=$($fetch_counter) + + send_packets $vlan udp 11 + + now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter) + check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen" + + # When no extra traffic is injected, there should be no mirroring. + busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + send_packets $vlan udp 11 + busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null + check_fail $? "Spurious packets observed after uninstall" + + log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd" + + stop_traffic + sleep 1 +} + +qevent_rule_install_mirror() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action mirred egress mirror dev $swp2 hw_stats disabled +} + +qevent_rule_uninstall_mirror() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} + +qevent_counter_fetch_mirror() +{ + tc_rule_handle_stats_get "dev $h2 ingress" 101 +} + +do_drop_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + local qevent_name=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto udp \ + action drop + + do_drop_test "$vlan" "$limit" "$qevent_name" mirror \ + qevent_counter_fetch_mirror + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index 1c36c576613b..c8968b041bea 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -7,6 +7,7 @@ ALL_TESTS=" ecn_nodrop_test red_test mc_backlog_test + red_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -83,6 +84,16 @@ mc_backlog_test() uninstall_qdisc } +red_mirror_test() +{ + install_qdisc qevent early_drop block 10 + + do_drop_mirror_test 10 $BACKLOG1 early_drop + do_drop_mirror_test 11 $BACKLOG2 early_drop + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index 558667ea11ec..ede9c38d3eff 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -7,6 +7,7 @@ ALL_TESTS=" ecn_nodrop_test red_test mc_backlog_test + red_mirror_test " source sch_red_core.sh @@ -57,6 +58,13 @@ mc_backlog_test() uninstall_qdisc } +red_mirror_test() +{ + install_qdisc qevent early_drop block 10 + do_drop_mirror_test 10 $BACKLOG + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh new file mode 100644 index 000000000000..ba1d53b9f815 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -0,0 +1,786 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +VNI_GEN=$RANDOM +NSIM_ID=$((RANDOM % 1024)) +NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID +NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID +NSIM_NETDEV= +HAS_ETHTOOL= +EXIT_STATUS=0 +num_cases=0 +num_errors=0 + +clean_up_devs=( ) + +function err_cnt { + echo "ERROR:" $@ + EXIT_STATUS=1 + ((num_errors++)) + ((num_cases++)) +} + +function pass_cnt { + ((num_cases++)) +} + +function cleanup_tuns { + for dev in "${clean_up_devs[@]}"; do + [ -e /sys/class/net/$dev ] && ip link del dev $dev + done + clean_up_devs=( ) +} + +function cleanup_nsim { + if [ -e $NSIM_DEV_SYS ]; then + echo $NSIM_ID > /sys/bus/netdevsim/del_device + fi +} + +function cleanup { + cleanup_tuns + cleanup_nsim +} + +trap cleanup EXIT + +function new_vxlan { + local dev=$1 + local dstport=$2 + local lower=$3 + local ipver=$4 + local flags=$5 + + local group ipfl + + [ "$ipver" != '6' ] && group=239.1.1.1 || group=fff1::1 + [ "$ipver" != '6' ] || ipfl="-6" + + [[ ! "$flags" =~ "external" ]] && flags="$flags id $((VNI_GEN++))" + + ip $ipfl link add $dev type vxlan \ + group $group \ + dev $lower \ + dstport $dstport \ + $flags + + ip link set dev $dev up + + clean_up_devs=("${clean_up_devs[@]}" $dev) + + check_tables +} + +function new_geneve { + local dev=$1 + local dstport=$2 + local ipver=$3 + local flags=$4 + + local group ipfl + + [ "$ipver" != '6' ] && remote=1.1.1.2 || group=::2 + [ "$ipver" != '6' ] || ipfl="-6" + + [[ ! "$flags" =~ "external" ]] && flags="$flags vni $((VNI_GEN++))" + + ip $ipfl link add $dev type geneve \ + remote $remote \ + dstport $dstport \ + $flags + + ip link set dev $dev up + + clean_up_devs=("${clean_up_devs[@]}" $dev) + + check_tables +} + +function del_dev { + local dev=$1 + + ip link del dev $dev + check_tables +} + +# Helpers for netdevsim port/type encoding +function mke { + local port=$1 + local type=$2 + + echo $((port << 16 | type)) +} + +function pre { + local val=$1 + + echo -e "port: $((val >> 16))\ttype: $((val & 0xffff))" +} + +function pre_ethtool { + local val=$1 + local port=$((val >> 16)) + local type=$((val & 0xffff)) + + case $type in + 1) + type_name="vxlan" + ;; + 2) + type_name="geneve" + ;; + 4) + type_name="vxlan-gpe" + ;; + *) + type_name="bit X" + ;; + esac + + echo "port $port, $type_name" +} + +function check_table { + local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local -n expected=$2 + local last=$3 + + read -a have < $path + + if [ ${#expected[@]} -ne ${#have[@]} ]; then + echo "check_table: BAD NUMBER OF ITEMS" + return 0 + fi + + for i in "${!expected[@]}"; do + if [ -n "$HAS_ETHTOOL" -a ${expected[i]} -ne 0 ]; then + pp_expected=`pre_ethtool ${expected[i]}` + ethtool --show-tunnels $NSIM_NETDEV | grep "$pp_expected" >/dev/null + if [ $? -ne 0 -a $last -ne 0 ]; then + err_cnt "ethtool table $1 on port $port: $pfx - $msg" + echo " check_table: ethtool does not contain '$pp_expected'" + ethtool --show-tunnels $NSIM_NETDEV + return 0 + + fi + fi + + if [ ${expected[i]} != ${have[i]} ]; then + if [ $last -ne 0 ]; then + err_cnt "table $1 on port $port: $pfx - $msg" + echo " check_table: wrong entry $i" + echo " expected: `pre ${expected[i]}`" + echo " have: `pre ${have[i]}`" + return 0 + fi + return 1 + fi + done + + pass_cnt + return 0 +} + +function check_tables { + # Need retries in case we have workqueue making the changes + local retries=10 + + while ! check_table 0 exp0 $((retries == 0)); do + sleep 0.02 + ((retries--)) + done + while ! check_table 1 exp1 $((retries == 0)); do + sleep 0.02 + ((retries--)) + done +} + +function print_table { + local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + read -a have < $path + + tree $NSIM_DEV_DFS/ + + echo "Port $port table $1:" + + for i in "${!have[@]}"; do + echo " `pre ${have[i]}`" + done + +} + +function print_tables { + print_table 0 + print_table 1 +} + +function get_netdev_name { + local -n old=$1 + + new=$(ls /sys/class/net) + + for netdev in $new; do + for check in $old; do + [ $netdev == $check ] && break + done + + if [ $netdev != $check ]; then + echo $netdev + break + fi + done +} + +### +### Code start +### + +# Probe ethtool support +ethtool -h | grep show-tunnels 2>&1 >/dev/null && HAS_ETHTOOL=y + +modprobe netdevsim + +# Basic test +pfx="basic" + +for port in 0 1; do + old_netdevs=$(ls /sys/class/net) + if [ $port -eq 0 ]; then + echo $NSIM_ID > /sys/bus/netdevsim/new_device + else + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + echo 1 > $NSIM_DEV_SYS/new_port + fi + NSIM_NETDEV=`get_netdev_name old_netdevs` + + msg="new NIC device created" + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + check_tables + + msg="VxLAN v4 devices" + exp0=( `mke 4789 1` 0 0 0 ) + new_vxlan vxlan0 4789 $NSIM_NETDEV + new_vxlan vxlan1 4789 $NSIM_NETDEV + + msg="VxLAN v4 devices go down" + exp0=( 0 0 0 0 ) + ifconfig vxlan1 down + ifconfig vxlan0 down + check_tables + + msg="VxLAN v6 devices" + exp0=( `mke 4789 1` 0 0 0 ) + new_vxlan vxlanA 4789 $NSIM_NETDEV 6 + + for ifc in vxlan0 vxlan1; do + ifconfig $ifc up + done + + new_vxlan vxlanB 4789 $NSIM_NETDEV 6 + + msg="another VxLAN v6 devices" + exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) + new_vxlan vxlanC 4790 $NSIM_NETDEV 6 + + msg="Geneve device" + exp1=( `mke 6081 2` 0 0 0 ) + new_geneve gnv0 6081 + + msg="NIC device goes down" + ifconfig $NSIM_NETDEV down + if [ $port -eq 1 ]; then + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + fi + check_tables + msg="NIC device goes up again" + ifconfig $NSIM_NETDEV up + exp0=( `mke 4789 1` `mke 4790 1` 0 0 ) + exp1=( `mke 6081 2` 0 0 0 ) + check_tables + + cleanup_tuns + + msg="tunnels destroyed" + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + check_tables + + modprobe -r geneve + modprobe -r vxlan + modprobe -r udp_tunnel + + check_tables +done + +modprobe -r netdevsim + +# Module tests +pfx="module tests" + +if modinfo netdevsim | grep udp_tunnel >/dev/null; then + err_cnt "netdevsim depends on udp_tunnel" +else + pass_cnt +fi + +modprobe netdevsim + +old_netdevs=$(ls /sys/class/net) +port=0 +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep +echo 0 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` + +msg="create VxLANs" +exp0=( 0 0 0 0 ) # sleep is longer than out wait +new_vxlan vxlan0 10000 $NSIM_NETDEV + +modprobe -r vxlan +modprobe -r udp_tunnel + +msg="remove tunnels" +exp0=( 0 0 0 0 ) +check_tables + +msg="create VxLANs" +exp0=( 0 0 0 0 ) # sleep is longer than out wait +new_vxlan vxlan0 10000 $NSIM_NETDEV + +exp0=( 0 0 0 0 ) + +modprobe -r netdevsim +modprobe netdevsim + +# Overflow the table + +function overflow_table0 { + local pfx=$1 + + msg="create VxLANs 1/5" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="create VxLANs 2/5" + exp0=( `mke 10000 1` `mke 10001 1` 0 0 ) + new_vxlan vxlan1 10001 $NSIM_NETDEV + + msg="create VxLANs 3/5" + exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` 0 ) + new_vxlan vxlan2 10002 $NSIM_NETDEV + + msg="create VxLANs 4/5" + exp0=( `mke 10000 1` `mke 10001 1` `mke 10002 1` `mke 10003 1` ) + new_vxlan vxlan3 10003 $NSIM_NETDEV + + msg="create VxLANs 5/5" + new_vxlan vxlan4 10004 $NSIM_NETDEV +} + +function overflow_table1 { + local pfx=$1 + + msg="create GENEVE 1/5" + exp1=( `mke 20000 2` 0 0 0 ) + new_geneve gnv0 20000 + + msg="create GENEVE 2/5" + exp1=( `mke 20000 2` `mke 20001 2` 0 0 ) + new_geneve gnv1 20001 + + msg="create GENEVE 3/5" + exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` 0 ) + new_geneve gnv2 20002 + + msg="create GENEVE 4/5" + exp1=( `mke 20000 2` `mke 20001 2` `mke 20002 2` `mke 20003 2` ) + new_geneve gnv3 20003 + + msg="create GENEVE 5/5" + new_geneve gnv4 20004 +} + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "overflow NIC table" + overflow_table1 "overflow NIC table" + + msg="replace VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` ) + del_dev vxlan1 + + msg="vacate VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) + del_dev vxlan2 + + msg="replace GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` ) + del_dev gnv1 + + msg="vacate GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` ) + del_dev gnv2 + + msg="table sharing - share" + exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` ) + new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external" + + msg="table sharing - overflow" + new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external" + msg="table sharing - overflow v6" + new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external" + + exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` ) + del_dev gnv4 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Sync all +pfx="sync all" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "overflow NIC table" + overflow_table1 "overflow NIC table" + + msg="replace VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` ) + del_dev vxlan1 + + msg="vacate VxLAN in overflow table" + exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) + del_dev vxlan2 + + msg="replace GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` `mke 20002 2` `mke 20003 2` ) + del_dev gnv1 + + msg="vacate GENEVE in overflow table" + exp1=( `mke 20000 2` `mke 20004 2` 0 `mke 20003 2` ) + del_dev gnv2 + + msg="table sharing - share" + exp1=( `mke 20000 2` `mke 20004 2` `mke 30001 4` `mke 20003 2` ) + new_vxlan vxlanG0 30001 $NSIM_NETDEV 4 "gpe external" + + msg="table sharing - overflow" + new_vxlan vxlanG1 30002 $NSIM_NETDEV 4 "gpe external" + msg="table sharing - overflow v6" + new_vxlan vxlanG2 30002 $NSIM_NETDEV 6 "gpe external" + + exp1=( `mke 20000 2` `mke 30002 4` `mke 30001 4` `mke 20003 2` ) + del_dev gnv4 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Destroy full NIC +pfx="destroy full" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + overflow_table0 "destroy NIC" + overflow_table1 "destroy NIC" + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# IPv4 only +pfx="IPv4 only" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port +echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v6" + new_vxlan vxlanA1 10000 $NSIM_NETDEV 6 + + ip link set dev vxlanA0 down + ip link set dev vxlanA0 up + check_tables + + msg="create VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="down VxLANs v4" + exp0=( 0 0 0 0 ) + ip link set dev vxlan0 down + check_tables + + msg="up VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + ip link set dev vxlan0 up + check_tables + + msg="destroy VxLANs v4" + exp0=( 0 0 0 0 ) + del_dev vxlan0 + + msg="recreate VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + del_dev vxlanA0 + del_dev vxlanA1 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# Failures +pfx="error injection" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + + msg="1 - create VxLANs v6" + exp0=( 0 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="1 - create VxLANs v4" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="1 - remove VxLANs v4" + del_dev vxlan0 + + msg="1 - remove VxLANs v6" + exp0=( 0 0 0 0 ) + del_dev vxlanA0 + + msg="2 - create GENEVE" + exp1=( `mke 20000 2` 0 0 0 ) + new_geneve gnv0 20000 + + msg="2 - destroy GENEVE" + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + exp1=( `mke 20000 2` 0 0 0 ) + del_dev gnv0 + + msg="2 - create second GENEVE" + exp1=( 0 `mke 20001 2` 0 0 ) + new_geneve gnv0 20001 + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# netdev flags +pfx="netdev flags" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v4" + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="turn off" + exp0=( 0 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off + check_tables + + msg="turn on" + exp0=( `mke 10000 1` 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on + check_tables + + msg="remove both" + del_dev vxlanA0 + exp0=( 0 0 0 0 ) + del_dev vxlan0 + check_tables + + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off + + msg="create VxLANs v4 - off" + exp0=( 0 0 0 0 ) + new_vxlan vxlan0 10000 $NSIM_NETDEV + + msg="created off - turn on" + exp0=( `mke 10000 1` 0 0 0 ) + ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on + check_tables + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +cleanup_nsim + +# device initiated reset +pfx="reset notification" + +echo $NSIM_ID > /sys/bus/netdevsim/new_device +echo 0 > $NSIM_DEV_SYS/del_port + +for port in 0 1; do + if [ $port -ne 0 ]; then + echo 1 > $NSIM_DEV_DFS/udp_ports_open_only + echo 1 > $NSIM_DEV_DFS/udp_ports_sleep + fi + + echo $port > $NSIM_DEV_SYS/new_port + ifconfig $NSIM_NETDEV up + + msg="create VxLANs v6" + exp0=( `mke 10000 1` 0 0 0 ) + new_vxlan vxlanA0 10000 $NSIM_NETDEV 6 + + msg="create VxLANs v4" + new_vxlan vxlan0 10000 $NSIM_NETDEV + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="NIC device goes down" + ifconfig $NSIM_NETDEV down + if [ $port -eq 1 ]; then + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) + fi + check_tables + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="NIC device goes up again" + ifconfig $NSIM_NETDEV up + exp0=( `mke 10000 1` 0 0 0 ) + check_tables + + msg="remove both" + del_dev vxlanA0 + exp0=( 0 0 0 0 ) + del_dev vxlan0 + check_tables + + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + check_tables + + msg="destroy NIC" + echo $port > $NSIM_DEV_SYS/del_port + + cleanup_tuns + exp0=( 0 0 0 0 ) + exp1=( 0 0 0 0 ) +done + +modprobe -r netdevsim + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $num_cases checks" +else + echo "FAILED $num_errors/$num_cases checks" +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index 3702dbcc90a7..c82aa77958e5 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -63,6 +63,8 @@ ALL_TESTS="$ALL_TESTS 0008:150:1" ALL_TESTS="$ALL_TESTS 0009:150:1" ALL_TESTS="$ALL_TESTS 0010:1:1" ALL_TESTS="$ALL_TESTS 0011:1:1" +ALL_TESTS="$ALL_TESTS 0012:1:1" +ALL_TESTS="$ALL_TESTS 0013:1:1" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -470,6 +472,38 @@ kmod_test_0011() echo "$MODPROBE" > /proc/sys/kernel/modprobe } +kmod_check_visibility() +{ + local name="$1" + local cmd="$2" + + modprobe $DEFAULT_KMOD_DRIVER + + local priv=$(eval $cmd) + local unpriv=$(capsh --drop=CAP_SYSLOG -- -c "$cmd") + + if [ "$priv" = "$unpriv" ] || \ + [ "${priv:0:3}" = "0x0" ] || \ + [ "${unpriv:0:3}" != "0x0" ] ; then + echo "${FUNCNAME[0]}: FAIL, $name visible to unpriv: '$priv' vs '$unpriv'" >&2 + exit 1 + else + echo "${FUNCNAME[0]}: OK!" + fi +} + +kmod_test_0012() +{ + kmod_check_visibility /proc/modules \ + "grep '^${DEFAULT_KMOD_DRIVER}\b' /proc/modules | awk '{print \$NF}'" +} + +kmod_test_0013() +{ + kmod_check_visibility '/sys/module/*/sections/*' \ + "cat /sys/module/${DEFAULT_KMOD_DRIVER}/sections/.*text | head -n1" +} + list_tests() { echo "Test ID list:" @@ -489,6 +523,8 @@ list_tests() echo "0009 x $(get_test_count 0009) - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()" echo "0010 x $(get_test_count 0010) - test nonexistent modprobe path" echo "0011 x $(get_test_count 0011) - test completely disabling module autoloading" + echo "0012 x $(get_test_count 0012) - test /proc/modules address visibility under CAP_SYSLOG" + echo "0013 x $(get_test_count 0013) - test /sys/module/*/sections/* visibility under CAP_SYSLOG" } usage() diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 0ac49d91a260..862eee734553 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -36,7 +36,7 @@ struct ksft_count { static struct ksft_count ksft_cnt; static unsigned int ksft_plan; -static inline int ksft_test_num(void) +static inline unsigned int ksft_test_num(void) { return ksft_cnt.ksft_pass + ksft_cnt.ksft_fail + ksft_cnt.ksft_xfail + ksft_cnt.ksft_xpass + diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index bfacb960450f..9491bbaa0831 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -18,6 +18,7 @@ TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh TEST_PROGS += vrf-xfrm-tests.sh TEST_PROGS += rxtimestamp.sh +TEST_PROGS += devlink_port_split.py TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py new file mode 100755 index 000000000000..58bb7e9b88ce --- /dev/null +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -0,0 +1,277 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0 + +from subprocess import PIPE, Popen +import json +import time +import argparse +import collections +import sys + +# +# Test port split configuration using devlink-port lanes attribute. +# The test is skipped in case the attribute is not available. +# +# First, check that all the ports with 1 lane fail to split. +# Second, check that all the ports with more than 1 lane can be split +# to all valid configurations (e.g., split to 2, split to 4 etc.) +# + + +Port = collections.namedtuple('Port', 'bus_info name') + + +def run_command(cmd, should_fail=False): + """ + Run a command in subprocess. + Return: Tuple of (stdout, stderr). + """ + + p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True) + stdout, stderr = p.communicate() + stdout, stderr = stdout.decode(), stderr.decode() + + if stderr != "" and not should_fail: + print("Error sending command: %s" % cmd) + print(stdout) + print(stderr) + return stdout, stderr + + +class devlink_ports(object): + """ + Class that holds information on the devlink ports, required to the tests; + if_names: A list of interfaces in the devlink ports. + """ + + def get_if_names(dev): + """ + Get a list of physical devlink ports. + Return: Array of tuples (bus_info/port, if_name). + """ + + arr = [] + + cmd = "devlink -j port show" + stdout, stderr = run_command(cmd) + assert stderr == "" + ports = json.loads(stdout)['port'] + + for port in ports: + if dev in port: + if ports[port]['flavour'] == 'physical': + arr.append(Port(bus_info=port, name=ports[port]['netdev'])) + + return arr + + def __init__(self, dev): + self.if_names = devlink_ports.get_if_names(dev) + + +def get_max_lanes(port): + """ + Get the $port's maximum number of lanes. + Return: number of lanes, e.g. 1, 2, 4 and 8. + """ + + cmd = "devlink -j port show %s" % port + stdout, stderr = run_command(cmd) + assert stderr == "" + values = list(json.loads(stdout)['port'].values())[0] + + if 'lanes' in values: + lanes = values['lanes'] + else: + lanes = 0 + return lanes + + +def get_split_ability(port): + """ + Get the $port split ability. + Return: split ability, true or false. + """ + + cmd = "devlink -j port show %s" % port.name + stdout, stderr = run_command(cmd) + assert stderr == "" + values = list(json.loads(stdout)['port'].values())[0] + + return values['splittable'] + + +def split(k, port, should_fail=False): + """ + Split $port into $k ports. + If should_fail == True, the split should fail. Otherwise, should pass. + Return: Array of sub ports after splitting. + If the $port wasn't split, the array will be empty. + """ + + cmd = "devlink port split %s count %s" % (port.bus_info, k) + stdout, stderr = run_command(cmd, should_fail=should_fail) + + if should_fail: + if not test(stderr != "", "%s is unsplittable" % port.name): + print("split an unsplittable port %s" % port.name) + return create_split_group(port, k) + else: + if stderr == "": + return create_split_group(port, k) + print("didn't split a splittable port %s" % port.name) + + return [] + + +def unsplit(port): + """ + Unsplit $port. + """ + + cmd = "devlink port unsplit %s" % port + stdout, stderr = run_command(cmd) + test(stderr == "", "Unsplit port %s" % port) + + +def exists(port, dev): + """ + Check if $port exists in the devlink ports. + Return: True is so, False otherwise. + """ + + return any(dev_port.name == port + for dev_port in devlink_ports.get_if_names(dev)) + + +def exists_and_lanes(ports, lanes, dev): + """ + Check if every port in the list $ports exists in the devlink ports and has + $lanes number of lanes after splitting. + Return: True if both are True, False otherwise. + """ + + for port in ports: + max_lanes = get_max_lanes(port) + if not exists(port, dev): + print("port %s doesn't exist in devlink ports" % port) + return False + if max_lanes != lanes: + print("port %s has %d lanes, but %s were expected" + % (port, lanes, max_lanes)) + return False + return True + + +def test(cond, msg): + """ + Check $cond and print a message accordingly. + Return: True is pass, False otherwise. + """ + + if cond: + print("TEST: %-60s [ OK ]" % msg) + else: + print("TEST: %-60s [FAIL]" % msg) + + return cond + + +def create_split_group(port, k): + """ + Create the split group for $port. + Return: Array with $k elements, which are the split port group. + """ + + return list(port.name + "s" + str(i) for i in range(k)) + + +def split_unsplittable_port(port, k): + """ + Test that splitting of unsplittable port fails. + """ + + # split to max + new_split_group = split(k, port, should_fail=True) + + if new_split_group != []: + unsplit(port.bus_info) + + +def split_splittable_port(port, k, lanes, dev): + """ + Test that splitting of splittable port passes correctly. + """ + + new_split_group = split(k, port) + + # Once the split command ends, it takes some time to the sub ifaces' + # to get their names. Use udevadm to continue only when all current udev + # events are handled. + cmd = "udevadm settle" + stdout, stderr = run_command(cmd) + assert stderr == "" + + if new_split_group != []: + test(exists_and_lanes(new_split_group, lanes/k, dev), + "split port %s into %s" % (port.name, k)) + + unsplit(port.bus_info) + + +def make_parser(): + parser = argparse.ArgumentParser(description='A test for port splitting.') + parser.add_argument('--dev', + help='The devlink handle of the device under test. ' + + 'The default is the first registered devlink ' + + 'handle.') + + return parser + + +def main(cmdline=None): + parser = make_parser() + args = parser.parse_args(cmdline) + + dev = args.dev + if not dev: + cmd = "devlink -j dev show" + stdout, stderr = run_command(cmd) + assert stderr == "" + + devs = json.loads(stdout)['dev'] + dev = list(devs.keys())[0] + + cmd = "devlink dev show %s" % dev + stdout, stderr = run_command(cmd) + if stderr != "": + print("devlink device %s can not be found" % dev) + sys.exit(1) + + ports = devlink_ports(dev) + + for port in ports.if_names: + max_lanes = get_max_lanes(port.name) + + # If max lanes is 0, do not test port splitting at all + if max_lanes == 0: + continue + + # If 1 lane, shouldn't be able to split + elif max_lanes == 1: + test(not get_split_ability(port), + "%s should not be able to split" % port.name) + split_unsplittable_port(port, max_lanes) + + # Else, splitting should pass and all the split ports should exist. + else: + lane = max_lanes + test(get_split_ability(port), + "%s should be able to split" % port.name) + while lane > 1: + split_splittable_port(port, lane, max_lanes, dev) + + lane //= 2 + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index dee567f7576a..22dc2f3d428b 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -747,6 +747,19 @@ ipv6_fcnal_runtime() run_cmd "$IP nexthop add id 86 via 2001:db8:91::2 dev veth1" run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81" + # rpfilter and default route + $IP nexthop flush >/dev/null 2>&1 + run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP" + run_cmd "$IP nexthop add id 91 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 92 via 2001:db8:92::2 dev veth3" + run_cmd "$IP nexthop add id 93 group 91/92" + run_cmd "$IP -6 ro add default nhid 91" + run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1" + log_test $? 0 "Nexthop with default route and rpfilter" + run_cmd "$IP -6 ro replace default nhid 93" + run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1" + log_test $? 0 "Nexthop with multipath default route and rpfilter" + # TO-DO: # existing route with old nexthop; append route with new nexthop # existing route with old nexthop; replace route with new diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f50976ee7d44..aa254aefc2c3 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -5,7 +5,7 @@ KSFT_KHDR_INSTALL := 1 CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh +TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh new file mode 100755 index 000000000000..39edce4f541c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns="ns1-$rndh" +ksft_skip=4 +test_cnt=1 +ret=0 +pids=() + +flush_pids() +{ + # mptcp_connect in join mode will sleep a bit before completing, + # give it some time + sleep 1.1 + + for pid in ${pids[@]}; do + [ -d /proc/$pid ] && kill -SIGUSR1 $pid >/dev/null 2>&1 + done + pids=() +} + +cleanup() +{ + ip netns del $ns + for pid in ${pids[@]}; do + [ -d /proc/$pid ] && kill -9 $pid >/dev/null 2>&1 + done +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi +ss -h | grep -q MPTCP +if [ $? -ne 0 ];then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip +fi + +__chk_nr() +{ + local condition="$1" + local expected=$2 + local msg nr + + shift 2 + msg=$* + nr=$(ss -inmHMN $ns | $condition) + + printf "%-50s" "$msg" + if [ $nr != $expected ]; then + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + else + echo "[ ok ]" + fi + test_cnt=$((test_cnt+1)) +} + +chk_msk_nr() +{ + __chk_nr "grep -c token:" $* +} + +chk_msk_fallback_nr() +{ + __chk_nr "grep -c fallback" $* +} + +chk_msk_remote_key_nr() +{ + __chk_nr "grep -c remote_key" $* +} + + +trap cleanup EXIT +ip netns add $ns +ip -n $ns link set dev lo up + +echo "a" | ip netns exec $ns ./mptcp_connect -p 10000 -l 0.0.0.0 -t 100 >/dev/null & +sleep 0.1 +pids[0]=$! +chk_msk_nr 0 "no msk on netns creation" + +echo "b" | ip netns exec $ns ./mptcp_connect -p 10000 127.0.0.1 -j -t 100 >/dev/null & +sleep 0.1 +pids[1]=$! +chk_msk_nr 2 "after MPC handshake " +chk_msk_remote_key_nr 2 "....chk remote_key" +chk_msk_fallback_nr 0 "....chk no fallback" +flush_pids + + +echo "a" | ip netns exec $ns ./mptcp_connect -p 10001 -s TCP -l 0.0.0.0 -t 100 >/dev/null & +pids[0]=$! +sleep 0.1 +echo "b" | ip netns exec $ns ./mptcp_connect -p 10001 127.0.0.1 -j -t 100 >/dev/null & +pids[1]=$! +sleep 0.1 +chk_msk_fallback_nr 1 "check fallback" +flush_pids + +NR_CLIENTS=100 +for I in `seq 1 $NR_CLIENTS`; do + echo "a" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) -l 0.0.0.0 -t 100 -w 10 >/dev/null & + pids[$((I*2))]=$! +done +sleep 0.1 + +for I in `seq 1 $NR_CLIENTS`; do + echo "b" | ip netns exec $ns ./mptcp_connect -p $((I+10001)) 127.0.0.1 -t 100 -w 10 >/dev/null & + pids[$((I*2 + 1))]=$! +done +sleep 1.5 + +chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +flush_pids + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index cedee5b952ba..cad6f73a5fd0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -11,6 +11,7 @@ #include <stdio.h> #include <stdlib.h> #include <strings.h> +#include <signal.h> #include <unistd.h> #include <sys/poll.h> @@ -36,6 +37,7 @@ extern int optind; static int poll_timeout = 10 * 1000; static bool listen_mode; +static bool quit; enum cfg_mode { CFG_MODE_POLL, @@ -52,11 +54,12 @@ static int pf = AF_INET; static int cfg_sndbuf; static int cfg_rcvbuf; static bool cfg_join; +static int cfg_wait; static void die_usage(void) { fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]" - "[-l] connect_address\n"); + "[-l] [-w sec] connect_address\n"); fprintf(stderr, "\t-6 use ipv6\n"); fprintf(stderr, "\t-t num -- set poll timeout to num\n"); fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n"); @@ -65,9 +68,15 @@ static void die_usage(void) fprintf(stderr, "\t-m [MPTCP|TCP] -- use tcp or mptcp sockets\n"); fprintf(stderr, "\t-s [mmap|poll] -- use poll (default) or mmap\n"); fprintf(stderr, "\t-u -- check mptcp ulp\n"); + fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); exit(1); } +static void handle_signal(int nr) +{ + quit = true; +} + static const char *getxinfo_strerr(int err) { if (err == EAI_SYSTEM) @@ -418,8 +427,8 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd) } /* leave some time for late join/announce */ - if (cfg_join) - usleep(400000); + if (cfg_wait) + usleep(cfg_wait); close(peerfd); return 0; @@ -812,11 +821,12 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:")) != -1) { + while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:w:")) != -1) { switch (c) { case 'j': cfg_join = true; cfg_mode = CFG_MODE_POLL; + cfg_wait = 400000; break; case 'l': listen_mode = true; @@ -850,6 +860,9 @@ static void parse_opts(int argc, char **argv) case 'R': cfg_rcvbuf = parse_int(optarg); break; + case 'w': + cfg_wait = atoi(optarg)*1000000; + break; } } @@ -865,6 +878,7 @@ int main(int argc, char *argv[]) { init_rng(); + signal(SIGUSR1, handle_signal); parse_opts(argc, argv); if (tcpulp_audit) diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index ca35dd8848b0..af3df79d8163 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -7,7 +7,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 -TMPOUT = $(OUTPUT)/ +TMPOUT = $(OUTPUT)/TMPDIR/ # Toolchains may build PIE by default which breaks the assembly 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) diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 663062701d5a..3e5ff29ee1dd 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -1,15 +1,10 @@ -#!/bin/bash +#!/bin/sh # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -[ -f /dev/tpm0 ] || exit $ksft_skip +[ -e /dev/tpm0 ] || exit $ksft_skip -python -m unittest -v tpm2_tests.SmokeTest -python -m unittest -v tpm2_tests.AsyncTest - -CLEAR_CMD=$(which tpm2_clear) -if [ -n $CLEAR_CMD ]; then - tpm2_clear -T device -fi +python3 -m unittest -v tpm2_tests.SmokeTest +python3 -m unittest -v tpm2_tests.AsyncTest diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index 36c9d030a1c6..04c47b13fe8a 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -1,9 +1,9 @@ -#!/bin/bash +#!/bin/sh # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -[ -f /dev/tpmrm0 ] || exit $ksft_skip +[ -e /dev/tpmrm0 ] || exit $ksft_skip -python -m unittest -v tpm2_tests.SpaceTest +python3 -m unittest -v tpm2_tests.SpaceTest diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index d0fcb66a88a6..f34486cd7342 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -247,14 +247,14 @@ class ProtocolError(Exception): class AuthCommand(object): """TPMS_AUTH_COMMAND""" - def __init__(self, session_handle=TPM2_RS_PW, nonce='', session_attributes=0, - hmac=''): + def __init__(self, session_handle=TPM2_RS_PW, nonce=bytes(), + session_attributes=0, hmac=bytes()): self.session_handle = session_handle self.nonce = nonce self.session_attributes = session_attributes self.hmac = hmac - def __str__(self): + def __bytes__(self): fmt = '>I H%us B H%us' % (len(self.nonce), len(self.hmac)) return struct.pack(fmt, self.session_handle, len(self.nonce), self.nonce, self.session_attributes, len(self.hmac), @@ -268,11 +268,11 @@ class AuthCommand(object): class SensitiveCreate(object): """TPMS_SENSITIVE_CREATE""" - def __init__(self, user_auth='', data=''): + def __init__(self, user_auth=bytes(), data=bytes()): self.user_auth = user_auth self.data = data - def __str__(self): + def __bytes__(self): fmt = '>H%us H%us' % (len(self.user_auth), len(self.data)) return struct.pack(fmt, len(self.user_auth), self.user_auth, len(self.data), self.data) @@ -296,8 +296,9 @@ class Public(object): return '>HHIH%us%usH%us' % \ (len(self.auth_policy), len(self.parameters), len(self.unique)) - def __init__(self, object_type, name_alg, object_attributes, auth_policy='', - parameters='', unique=''): + def __init__(self, object_type, name_alg, object_attributes, + auth_policy=bytes(), parameters=bytes(), + unique=bytes()): self.object_type = object_type self.name_alg = name_alg self.object_attributes = object_attributes @@ -305,7 +306,7 @@ class Public(object): self.parameters = parameters self.unique = unique - def __str__(self): + def __bytes__(self): return struct.pack(self.__fmt(), self.object_type, self.name_alg, @@ -343,7 +344,7 @@ def get_algorithm(name): def hex_dump(d): d = [format(ord(x), '02x') for x in d] - d = [d[i: i + 16] for i in xrange(0, len(d), 16)] + d = [d[i: i + 16] for i in range(0, len(d), 16)] d = [' '.join(x) for x in d] d = os.linesep.join(d) @@ -401,7 +402,7 @@ class Client: pcrsel_len = max((i >> 3) + 1, 3) pcrsel = [0] * pcrsel_len pcrsel[i >> 3] = 1 << (i & 7) - pcrsel = ''.join(map(chr, pcrsel)) + pcrsel = ''.join(map(chr, pcrsel)).encode() fmt = '>HII IHB%us' % (pcrsel_len) cmd = struct.pack(fmt, @@ -443,7 +444,7 @@ class Client: TPM2_CC_PCR_EXTEND, i, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), 1, bank_alg, dig) self.send_cmd(cmd) @@ -457,7 +458,7 @@ class Client: TPM2_RH_NULL, TPM2_RH_NULL, 16, - '\0' * 16, + ('\0' * 16).encode(), 0, session_type, TPM2_ALG_NULL, @@ -472,7 +473,7 @@ class Client: for i in pcrs: pcr = self.read_pcr(i, bank_alg) - if pcr == None: + if pcr is None: return None x += pcr @@ -489,7 +490,7 @@ class Client: pcrsel = [0] * pcrsel_len for i in pcrs: pcrsel[i >> 3] |= 1 << (i & 7) - pcrsel = ''.join(map(chr, pcrsel)) + pcrsel = ''.join(map(chr, pcrsel)).encode() fmt = '>HII IH%usIHB3s' % ds cmd = struct.pack(fmt, @@ -497,7 +498,8 @@ class Client: struct.calcsize(fmt), TPM2_CC_POLICY_PCR, handle, - len(dig), str(dig), + len(dig), + bytes(dig), 1, bank_alg, pcrsel_len, pcrsel) @@ -534,7 +536,7 @@ class Client: self.send_cmd(cmd) - def create_root_key(self, auth_value = ''): + def create_root_key(self, auth_value = bytes()): attributes = \ Public.FIXED_TPM | \ Public.FIXED_PARENT | \ @@ -570,11 +572,11 @@ class Client: TPM2_CC_CREATE_PRIMARY, TPM2_RH_OWNER, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), len(sensitive), - str(sensitive), + bytes(sensitive), len(public), - str(public), + bytes(public), 0, 0) return struct.unpack('>I', self.send_cmd(cmd)[10:14])[0] @@ -587,7 +589,7 @@ class Client: attributes = 0 if not policy_dig: attributes |= Public.USER_WITH_AUTH - policy_dig = '' + policy_dig = bytes() auth_cmd = AuthCommand() sensitive = SensitiveCreate(user_auth=auth_value, data=data) @@ -608,11 +610,11 @@ class Client: TPM2_CC_CREATE, parent_key, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), len(sensitive), - str(sensitive), + bytes(sensitive), len(public), - str(public), + bytes(public), 0, 0) rsp = self.send_cmd(cmd) @@ -635,7 +637,7 @@ class Client: TPM2_CC_LOAD, parent_key, len(auth_cmd), - str(auth_cmd), + bytes(auth_cmd), blob) data_handle = struct.unpack('>I', self.send_cmd(cmd)[10:14])[0] @@ -653,7 +655,7 @@ class Client: TPM2_CC_UNSEAL, data_handle, len(auth_cmd), - str(auth_cmd)) + bytes(auth_cmd)) try: rsp = self.send_cmd(cmd) @@ -675,7 +677,7 @@ class Client: TPM2_CC_DICTIONARY_ATTACK_LOCK_RESET, TPM2_RH_LOCKOUT, len(auth_cmd), - str(auth_cmd)) + bytes(auth_cmd)) self.send_cmd(cmd) @@ -693,7 +695,7 @@ class Client: more_data, cap, cnt = struct.unpack('>BII', rsp[:9]) rsp = rsp[9:] - for i in xrange(0, cnt): + for i in range(0, cnt): handle = struct.unpack('>I', rsp[:4])[0] handles.append(handle) rsp = rsp[4:] diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 728be7c69b76..9d764306887b 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -20,8 +20,8 @@ class SmokeTest(unittest.TestCase): self.client.close() def test_seal_with_auth(self): - data = 'X' * 64 - auth = 'A' * 15 + data = ('X' * 64).encode() + auth = ('A' * 15).encode() blob = self.client.seal(self.root_key, data, auth, None) result = self.client.unseal(self.root_key, blob, auth, None) @@ -30,8 +30,8 @@ class SmokeTest(unittest.TestCase): def test_seal_with_policy(self): handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) - data = 'X' * 64 - auth = 'A' * 15 + data = ('X' * 64).encode() + auth = ('A' * 15).encode() pcrs = [16] try: @@ -58,14 +58,15 @@ class SmokeTest(unittest.TestCase): self.assertEqual(data, result) def test_unseal_with_wrong_auth(self): - data = 'X' * 64 - auth = 'A' * 20 + data = ('X' * 64).encode() + auth = ('A' * 20).encode() rc = 0 blob = self.client.seal(self.root_key, data, auth, None) try: - result = self.client.unseal(self.root_key, blob, auth[:-1] + 'B', None) - except ProtocolError, e: + result = self.client.unseal(self.root_key, blob, + auth[:-1] + 'B'.encode(), None) + except ProtocolError as e: rc = e.rc self.assertEqual(rc, tpm2.TPM2_RC_AUTH_FAIL) @@ -73,8 +74,8 @@ class SmokeTest(unittest.TestCase): def test_unseal_with_wrong_policy(self): handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL) - data = 'X' * 64 - auth = 'A' * 17 + data = ('X' * 64).encode() + auth = ('A' * 17).encode() pcrs = [16] try: @@ -91,7 +92,7 @@ class SmokeTest(unittest.TestCase): # This should succeed. ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1) - self.client.extend_pcr(1, 'X' * ds) + self.client.extend_pcr(1, ('X' * ds).encode()) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) @@ -108,7 +109,7 @@ class SmokeTest(unittest.TestCase): # Then, extend a PCR that is part of the policy and try to unseal. # This should fail. - self.client.extend_pcr(16, 'X' * ds) + self.client.extend_pcr(16, ('X' * ds).encode()) handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY) @@ -119,7 +120,7 @@ class SmokeTest(unittest.TestCase): self.client.policy_password(handle) result = self.client.unseal(self.root_key, blob, auth, handle) - except ProtocolError, e: + except ProtocolError as e: rc = e.rc self.client.flush_context(handle) except: @@ -130,13 +131,13 @@ class SmokeTest(unittest.TestCase): def test_seal_with_too_long_auth(self): ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1) - data = 'X' * 64 - auth = 'A' * (ds + 1) + data = ('X' * 64).encode() + auth = ('A' * (ds + 1)).encode() rc = 0 try: blob = self.client.seal(self.root_key, data, auth, None) - except ProtocolError, e: + except ProtocolError as e: rc = e.rc self.assertEqual(rc, tpm2.TPM2_RC_SIZE) @@ -152,7 +153,7 @@ class SmokeTest(unittest.TestCase): 0xDEADBEEF) self.client.send_cmd(cmd) - except IOError, e: + except IOError as e: rejected = True except: pass @@ -212,7 +213,7 @@ class SmokeTest(unittest.TestCase): self.client.tpm.write(cmd) rsp = self.client.tpm.read() - except IOError, e: + except IOError as e: # read the response rsp = self.client.tpm.read() rejected = True @@ -283,7 +284,7 @@ class SpaceTest(unittest.TestCase): rc = 0 try: space1.send_cmd(cmd) - except ProtocolError, e: + except ProtocolError as e: rc = e.rc self.assertEqual(rc, tpm2.TPM2_RC_COMMAND_CODE | diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 5f16821c7f63..d2796ea98c5a 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -70,10 +70,10 @@ all_64: $(BINARIES_64) EXTRA_CLEAN := $(BINARIES_32) $(BINARIES_64) -$(BINARIES_32): $(OUTPUT)/%_32: %.c +$(BINARIES_32): $(OUTPUT)/%_32: %.c helpers.h $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm -$(BINARIES_64): $(OUTPUT)/%_64: %.c +$(BINARIES_64): $(OUTPUT)/%_64: %.c helpers.h $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl # x86_64 users should be encouraged to install 32-bit libraries diff --git a/tools/testing/selftests/x86/helpers.h b/tools/testing/selftests/x86/helpers.h new file mode 100644 index 000000000000..f5ff2a2615df --- /dev/null +++ b/tools/testing/selftests/x86/helpers.h @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __SELFTESTS_X86_HELPERS_H +#define __SELFTESTS_X86_HELPERS_H + +#include <asm/processor-flags.h> + +static inline unsigned long get_eflags(void) +{ + unsigned long eflags; + + asm volatile ( +#ifdef __x86_64__ + "subq $128, %%rsp\n\t" + "pushfq\n\t" + "popq %0\n\t" + "addq $128, %%rsp" +#else + "pushfl\n\t" + "popl %0" +#endif + : "=r" (eflags) :: "memory"); + + return eflags; +} + +static inline void set_eflags(unsigned long eflags) +{ + asm volatile ( +#ifdef __x86_64__ + "subq $128, %%rsp\n\t" + "pushq %0\n\t" + "popfq\n\t" + "addq $128, %%rsp" +#else + "pushl %0\n\t" + "popfl" +#endif + :: "r" (eflags) : "flags", "memory"); +} + +#endif /* __SELFTESTS_X86_HELPERS_H */ diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c index 1063328e275c..120ac741fe44 100644 --- a/tools/testing/selftests/x86/single_step_syscall.c +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -31,6 +31,8 @@ #include <sys/ptrace.h> #include <sys/user.h> +#include "helpers.h" + static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { @@ -67,21 +69,6 @@ static unsigned char altstack_data[SIGSTKSZ]; # define INT80_CLOBBERS #endif -static unsigned long get_eflags(void) -{ - unsigned long eflags; - asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags)); - return eflags; -} - -static void set_eflags(unsigned long eflags) -{ - asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH - : : "rm" (eflags) : "flags"); -} - -#define X86_EFLAGS_TF (1UL << 8) - static void sigtrap(int sig, siginfo_t *info, void *ctx_void) { ucontext_t *ctx = (ucontext_t*)ctx_void; diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c index bc0ecc2e862e..5b7abebbcbb9 100644 --- a/tools/testing/selftests/x86/syscall_arg_fault.c +++ b/tools/testing/selftests/x86/syscall_arg_fault.c @@ -15,30 +15,11 @@ #include <setjmp.h> #include <errno.h> -#ifdef __x86_64__ -# define WIDTH "q" -#else -# define WIDTH "l" -#endif +#include "helpers.h" /* Our sigaltstack scratch space. */ static unsigned char altstack_data[SIGSTKSZ]; -static unsigned long get_eflags(void) -{ - unsigned long eflags; - asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags)); - return eflags; -} - -static void set_eflags(unsigned long eflags) -{ - asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH - : : "rm" (eflags) : "flags"); -} - -#define X86_EFLAGS_TF (1UL << 8) - static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c index 02309a195041..a108b80dd082 100644 --- a/tools/testing/selftests/x86/syscall_nt.c +++ b/tools/testing/selftests/x86/syscall_nt.c @@ -13,29 +13,11 @@ #include <signal.h> #include <err.h> #include <sys/syscall.h> -#include <asm/processor-flags.h> -#ifdef __x86_64__ -# define WIDTH "q" -#else -# define WIDTH "l" -#endif +#include "helpers.h" static unsigned int nerrs; -static unsigned long get_eflags(void) -{ - unsigned long eflags; - asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags)); - return eflags; -} - -static void set_eflags(unsigned long eflags) -{ - asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH - : : "rm" (eflags) : "flags"); -} - static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { @@ -59,6 +41,7 @@ static void do_it(unsigned long extraflags) set_eflags(get_eflags() | extraflags); syscall(SYS_getpid); flags = get_eflags(); + set_eflags(X86_EFLAGS_IF | X86_EFLAGS_FIXED); if ((flags & extraflags) == extraflags) { printf("[OK]\tThe syscall worked and flags are still set\n"); } else { @@ -73,6 +56,12 @@ int main(void) printf("[RUN]\tSet NT and issue a syscall\n"); do_it(X86_EFLAGS_NT); + printf("[RUN]\tSet AC and issue a syscall\n"); + do_it(X86_EFLAGS_AC); + + printf("[RUN]\tSet NT|AC and issue a syscall\n"); + do_it(X86_EFLAGS_NT | X86_EFLAGS_AC); + /* * Now try it again with TF set -- TF forces returns via IRET in all * cases except non-ptregs-using 64-bit full fast path syscalls. @@ -80,8 +69,28 @@ int main(void) sethandler(SIGTRAP, sigtrap, 0); + printf("[RUN]\tSet TF and issue a syscall\n"); + do_it(X86_EFLAGS_TF); + printf("[RUN]\tSet NT|TF and issue a syscall\n"); do_it(X86_EFLAGS_NT | X86_EFLAGS_TF); + printf("[RUN]\tSet AC|TF and issue a syscall\n"); + do_it(X86_EFLAGS_AC | X86_EFLAGS_TF); + + printf("[RUN]\tSet NT|AC|TF and issue a syscall\n"); + do_it(X86_EFLAGS_NT | X86_EFLAGS_AC | X86_EFLAGS_TF); + + /* + * Now try DF. This is evil and it's plausible that we will crash + * glibc, but glibc would have to do something rather surprising + * for this to happen. + */ + printf("[RUN]\tSet DF and issue a syscall\n"); + do_it(X86_EFLAGS_DF); + + printf("[RUN]\tSet TF|DF and issue a syscall\n"); + do_it(X86_EFLAGS_TF | X86_EFLAGS_DF); + return nerrs == 0 ? 0 : 1; } diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index a4f4d4cf22c3..c41f24b517f4 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -20,6 +20,8 @@ #include <setjmp.h> #include <sys/uio.h> +#include "helpers.h" + #ifdef __x86_64__ # define VSYS(x) (x) #else @@ -493,21 +495,8 @@ static int test_process_vm_readv(void) } #ifdef __x86_64__ -#define X86_EFLAGS_TF (1UL << 8) static volatile sig_atomic_t num_vsyscall_traps; -static unsigned long get_eflags(void) -{ - unsigned long eflags; - asm volatile ("pushfq\n\tpopq %0" : "=rm" (eflags)); - return eflags; -} - -static void set_eflags(unsigned long eflags) -{ - asm volatile ("pushq %0\n\tpopfq" : : "rm" (eflags) : "flags"); -} - static void sigtrap(int sig, siginfo_t *info, void *ctx_void) { ucontext_t *ctx = (ucontext_t *)ctx_void; diff --git a/tools/testing/selftests/x86/unwind_vdso.c b/tools/testing/selftests/x86/unwind_vdso.c index 0075ccd65407..4c311e1af4c7 100644 --- a/tools/testing/selftests/x86/unwind_vdso.c +++ b/tools/testing/selftests/x86/unwind_vdso.c @@ -11,6 +11,8 @@ #include <features.h> #include <stdio.h> +#include "helpers.h" + #if defined(__GLIBC__) && __GLIBC__ == 2 && __GLIBC_MINOR__ < 16 int main() @@ -53,27 +55,6 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), err(1, "sigaction"); } -#ifdef __x86_64__ -# define WIDTH "q" -#else -# define WIDTH "l" -#endif - -static unsigned long get_eflags(void) -{ - unsigned long eflags; - asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags)); - return eflags; -} - -static void set_eflags(unsigned long eflags) -{ - asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH - : : "rm" (eflags) : "flags"); -} - -#define X86_EFLAGS_TF (1UL << 8) - static volatile sig_atomic_t nerrs; static unsigned long sysinfo; static bool got_sysinfo = false; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a852af5c3214..0a68c9d3d3ab 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3350,7 +3350,8 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, if (kvm_sigmask.len != sizeof(compat_sigset_t)) goto out; r = -EFAULT; - if (get_compat_sigset(&sigset, (void *)sigmask_arg->sigset)) + if (get_compat_sigset(&sigset, + (compat_sigset_t __user *)sigmask_arg->sigset)) goto out; r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); } else |