diff options
826 files changed, 17061 insertions, 5001 deletions
diff --git a/.clang-format b/.clang-format index 10dc5a9a61b3..01a341ceec6c 100644 --- a/.clang-format +++ b/.clang-format @@ -122,6 +122,7 @@ ForEachMacros: - 'drm_for_each_bridge_in_chain' - 'drm_for_each_connector_iter' - 'drm_for_each_crtc' + - 'drm_for_each_crtc_reverse' - 'drm_for_each_encoder' - 'drm_for_each_encoder_mask' - 'drm_for_each_fb' @@ -203,14 +204,13 @@ ForEachMacros: - 'for_each_matching_node' - 'for_each_matching_node_and_match' - 'for_each_member' - - 'for_each_mem_region' - - 'for_each_memblock_type' - 'for_each_memcg_cache_index' - 'for_each_mem_pfn_range' - '__for_each_mem_range' - 'for_each_mem_range' - '__for_each_mem_range_rev' - 'for_each_mem_range_rev' + - 'for_each_mem_region' - 'for_each_migratetype_order' - 'for_each_msi_entry' - 'for_each_msi_entry_safe' @@ -276,10 +276,8 @@ ForEachMacros: - 'for_each_reserved_mem_range' - 'for_each_reserved_mem_region' - 'for_each_rtd_codec_dais' - - 'for_each_rtd_codec_dais_rollback' - 'for_each_rtd_components' - 'for_each_rtd_cpu_dais' - - 'for_each_rtd_cpu_dais_rollback' - 'for_each_rtd_dais' - 'for_each_set_bit' - 'for_each_set_bit_from' @@ -298,6 +296,7 @@ ForEachMacros: - '__for_each_thread' - 'for_each_thread' - 'for_each_unicast_dest_pgid' + - 'for_each_vsi' - 'for_each_wakeup_source' - 'for_each_zone' - 'for_each_zone_zonelist' @@ -330,6 +329,7 @@ ForEachMacros: - 'hlist_for_each_entry_rcu_bh' - 'hlist_for_each_entry_rcu_notrace' - 'hlist_for_each_entry_safe' + - 'hlist_for_each_entry_srcu' - '__hlist_for_each_rcu' - 'hlist_for_each_safe' - 'hlist_nulls_for_each_entry' @@ -378,6 +378,7 @@ ForEachMacros: - 'list_for_each_entry_safe_continue' - 'list_for_each_entry_safe_from' - 'list_for_each_entry_safe_reverse' + - 'list_for_each_entry_srcu' - 'list_for_each_prev' - 'list_for_each_prev_safe' - 'list_for_each_safe' @@ -411,6 +412,8 @@ ForEachMacros: - 'of_property_for_each_string' - 'of_property_for_each_u32' - 'pci_bus_for_each_resource' + - 'pcl_for_each_chunk' + - 'pcl_for_each_segment' - 'pcm_for_each_format' - 'ping_portaddr_for_each_entry' - 'plist_for_each' @@ -9,9 +9,6 @@ # # Please keep this list dictionary sorted. # -# This comment is parsed by git-shortlog: -# repo-abbrev: /pub/scm/linux/kernel/git/ -# Aaron Durbin <adurbin@google.com> Adam Oldham <oldhamca@gmail.com> Adam Radford <aradford@gmail.com> diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink index b662f747c83e..8a21ce515f61 100644 --- a/Documentation/ABI/testing/sysfs-class-devlink +++ b/Documentation/ABI/testing/sysfs-class-devlink @@ -5,8 +5,8 @@ Description: Provide a place in sysfs for the device link objects in the kernel at any given time. The name of a device link directory, denoted as ... above, is of the form <supplier>--<consumer> - where <supplier> is the supplier device name and <consumer> is - the consumer device name. + where <supplier> is the supplier bus:device name and <consumer> + is the consumer bus:device name. What: /sys/class/devlink/.../auto_remove_on Date: May 2020 diff --git a/Documentation/ABI/testing/sysfs-class-net-dsa b/Documentation/ABI/testing/sysfs-class-net-dsa index 985d84c585c6..e2da26b44dd0 100644 --- a/Documentation/ABI/testing/sysfs-class-net-dsa +++ b/Documentation/ABI/testing/sysfs-class-net-dsa @@ -3,5 +3,12 @@ Date: August 2018 KernelVersion: 4.20 Contact: netdev@vger.kernel.org Description: - String indicating the type of tagging protocol used by the - DSA slave network device. + On read, this file returns a string indicating the type of + tagging protocol used by the DSA network devices that are + attached to this master interface. + On write, this file changes the tagging protocol of the + attached DSA switches, if this operation is supported by the + driver. Changing the tagging protocol must be done with the DSA + interfaces and the master interface all administratively down. + See the "name" field of each registered struct dsa_device_ops + for a list of valid values. diff --git a/Documentation/ABI/testing/sysfs-class-net-qmi b/Documentation/ABI/testing/sysfs-class-net-qmi index c310db4ccbc2..ed79f5893421 100644 --- a/Documentation/ABI/testing/sysfs-class-net-qmi +++ b/Documentation/ABI/testing/sysfs-class-net-qmi @@ -48,3 +48,13 @@ Description: Write a number ranging from 1 to 254 to delete a previously created qmap mux based network device. + +What: /sys/class/net/<qmimux iface>/qmap/mux_id +Date: January 2021 +KernelVersion: 5.12 +Contact: Daniele Palmas <dnlplm@gmail.com> +Description: + Unsigned integer + + Indicates the mux id associated to the qmimux network interface + during its creation. diff --git a/Documentation/ABI/testing/sysfs-devices-consumer b/Documentation/ABI/testing/sysfs-devices-consumer index 1f06d74d1c3c..0809fda092e6 100644 --- a/Documentation/ABI/testing/sysfs-devices-consumer +++ b/Documentation/ABI/testing/sysfs-devices-consumer @@ -4,5 +4,6 @@ Contact: Saravana Kannan <saravanak@google.com> Description: The /sys/devices/.../consumer:<consumer> are symlinks to device links where this device is the supplier. <consumer> denotes the - name of the consumer in that device link. There can be zero or - more of these symlinks for a given device. + name of the consumer in that device link and is of the form + bus:device name. There can be zero or more of these symlinks + for a given device. diff --git a/Documentation/ABI/testing/sysfs-devices-supplier b/Documentation/ABI/testing/sysfs-devices-supplier index a919e0db5e90..207f5972e98d 100644 --- a/Documentation/ABI/testing/sysfs-devices-supplier +++ b/Documentation/ABI/testing/sysfs-devices-supplier @@ -4,5 +4,6 @@ Contact: Saravana Kannan <saravanak@google.com> Description: The /sys/devices/.../supplier:<supplier> are symlinks to device links where this device is the consumer. <supplier> denotes the - name of the supplier in that device link. There can be zero or - more of these symlinks for a given device. + name of the supplier in that device link and is of the form + bus:device name. There can be zero or more of these symlinks + for a given device. diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs index adc0d0e91607..75ccc5c62b3c 100644 --- a/Documentation/ABI/testing/sysfs-driver-ufs +++ b/Documentation/ABI/testing/sysfs-driver-ufs @@ -916,21 +916,25 @@ Date: September 2014 Contact: Subhash Jadavani <subhashj@codeaurora.org> Description: This entry could be used to set or show the UFS device runtime power management level. The current driver - implementation supports 6 levels with next target states: + implementation supports 7 levels with next target states: == ==================================================== - 0 an UFS device will stay active, an UIC link will + 0 UFS device will stay active, UIC link will stay active - 1 an UFS device will stay active, an UIC link will + 1 UFS device will stay active, UIC link will hibernate - 2 an UFS device will moved to sleep, an UIC link will + 2 UFS device will be moved to sleep, UIC link will stay active - 3 an UFS device will moved to sleep, an UIC link will + 3 UFS device will be moved to sleep, UIC link will hibernate - 4 an UFS device will be powered off, an UIC link will + 4 UFS device will be powered off, UIC link will hibernate - 5 an UFS device will be powered off, an UIC link will + 5 UFS device will be powered off, UIC link will be powered off + 6 UFS device will be moved to deep sleep, UIC link + will be powered off. Note, deep sleep might not be + supported in which case this value will not be + accepted == ==================================================== What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_dev_state @@ -954,21 +958,25 @@ Date: September 2014 Contact: Subhash Jadavani <subhashj@codeaurora.org> Description: This entry could be used to set or show the UFS device system power management level. The current driver - implementation supports 6 levels with next target states: + implementation supports 7 levels with next target states: == ==================================================== - 0 an UFS device will stay active, an UIC link will + 0 UFS device will stay active, UIC link will stay active - 1 an UFS device will stay active, an UIC link will + 1 UFS device will stay active, UIC link will hibernate - 2 an UFS device will moved to sleep, an UIC link will + 2 UFS device will be moved to sleep, UIC link will stay active - 3 an UFS device will moved to sleep, an UIC link will + 3 UFS device will be moved to sleep, UIC link will hibernate - 4 an UFS device will be powered off, an UIC link will + 4 UFS device will be powered off, UIC link will hibernate - 5 an UFS device will be powered off, an UIC link will + 5 UFS device will be powered off, UIC link will be powered off + 6 UFS device will be moved to deep sleep, UIC link + will be powered off. Note, deep sleep might not be + supported in which case this value will not be + accepted == ==================================================== What: /sys/bus/platform/drivers/ufshcd/*/spm_target_dev_state diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst index 4e6f504474ac..2cc5488acbd9 100644 --- a/Documentation/admin-guide/device-mapper/dm-integrity.rst +++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst @@ -177,14 +177,20 @@ bitmap_flush_interval:number The bitmap flush interval in milliseconds. The metadata buffers are synchronized when this interval expires. +allow_discards + Allow block discard requests (a.k.a. TRIM) for the integrity device. + Discards are only allowed to devices using internal hash. + fix_padding Use a smaller padding of the tag area that is more space-efficient. If this option is not present, large padding is used - that is for compatibility with older kernels. -allow_discards - Allow block discard requests (a.k.a. TRIM) for the integrity device. - Discards are only allowed to devices using internal hash. +legacy_recalculate + Allow recalculating of volumes with HMAC keys. This is disabled by + default for security reasons - an attacker could modify the volume, + set recalc_sector to zero, and the kernel would not detect the + modification. The journal mode (D/J), buffer_sectors, journal_watermark, commit_time and allow_discards can be changed when reloading the target (load an inactive diff --git a/Documentation/admin-guide/media/rkisp1.rst b/Documentation/admin-guide/media/rkisp1.rst index 2267e4fb475e..ccf418713623 100644 --- a/Documentation/admin-guide/media/rkisp1.rst +++ b/Documentation/admin-guide/media/rkisp1.rst @@ -13,6 +13,22 @@ This file documents the driver for the Rockchip ISP1 that is part of RK3288 and RK3399 SoCs. The driver is located under drivers/staging/media/rkisp1 and uses the Media-Controller API. +Revisions +========= + +There exist multiple smaller revisions to this ISP that got introduced in +later SoCs. Revisions can be found in the enum :c:type:`rkisp1_cif_isp_version` +in the UAPI and the revision of the ISP inside the running SoC can be read +in the field hw_revision of struct media_device_info as returned by +ioctl MEDIA_IOC_DEVICE_INFO. + +Versions in use are: + +- RKISP1_V10: used at least in rk3288 and rk3399 +- RKISP1_V11: declared in the original vendor code, but not used +- RKISP1_V12: used at least in rk3326 and px30 +- RKISP1_V13: used at least in rk1808 + Topology ======== .. _rkisp1_topology_graph: diff --git a/Documentation/asm-annotations.rst b/Documentation/asm-annotations.rst index 32ea57483378..76424e0431f4 100644 --- a/Documentation/asm-annotations.rst +++ b/Documentation/asm-annotations.rst @@ -100,6 +100,11 @@ Instruction Macros ~~~~~~~~~~~~~~~~~~ This section covers ``SYM_FUNC_*`` and ``SYM_CODE_*`` enumerated above. +``objtool`` requires that all code must be contained in an ELF symbol. Symbol +names that have a ``.L`` prefix do not emit symbol table entries. ``.L`` +prefixed symbols can be used within a code region, but should be avoided for +denoting a range of code via ``SYM_*_START/END`` annotations. + * ``SYM_FUNC_START`` and ``SYM_FUNC_START_LOCAL`` are supposed to be **the most frequent markings**. They are used for functions with standard calling conventions -- global and local. Like in C, they both align the functions to diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 0fc3fb1860c4..1651d961f06a 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -160,29 +160,14 @@ intended for use in production as a security mitigation. Therefore it supports boot parameters that allow to disable KASAN competely or otherwise control particular KASAN features. -The things that can be controlled are: +- ``kasan=off`` or ``=on`` controls whether KASAN is enabled (default: ``on``). -1. Whether KASAN is enabled at all. -2. Whether KASAN collects and saves alloc/free stacks. -3. Whether KASAN panics on a detected bug or not. +- ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack + traces collection (default: ``on`` for ``CONFIG_DEBUG_KERNEL=y``, otherwise + ``off``). -The ``kasan.mode`` boot parameter allows to choose one of three main modes: - -- ``kasan.mode=off`` - KASAN is disabled, no tag checks are performed -- ``kasan.mode=prod`` - only essential production features are enabled -- ``kasan.mode=full`` - all KASAN features are enabled - -The chosen mode provides default control values for the features mentioned -above. However it's also possible to override the default values by providing: - -- ``kasan.stacktrace=off`` or ``=on`` - enable alloc/free stack collection - (default: ``on`` for ``mode=full``, - otherwise ``off``) -- ``kasan.fault=report`` or ``=panic`` - only print KASAN report or also panic - (default: ``report``) - -If ``kasan.mode`` parameter is not provided, it defaults to ``full`` when -``CONFIG_DEBUG_KERNEL`` is enabled, and to ``prod`` otherwise. +- ``kasan.fault=report`` or ``=panic`` controls whether to only print a KASAN + report or also panic the kernel (default: ``report``). For developers ~~~~~~~~~~~~~~ diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index d9fdc14f0677..650f99590df5 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -522,6 +522,63 @@ There's more boilerplate involved, but it can: * E.g. if we wanted to also test ``sha256sum``, we could add a ``sha256`` field and reuse ``cases``. +* be converted to a "parameterized test", see below. + +Parameterized Testing +~~~~~~~~~~~~~~~~~~~~~ + +The table-driven testing pattern is common enough that KUnit has special +support for it. + +Reusing the same ``cases`` array from above, we can write the test as a +"parameterized test" with the following. + +.. code-block:: c + + // This is copy-pasted from above. + struct sha1_test_case { + const char *str; + const char *sha1; + }; + struct sha1_test_case cases[] = { + { + .str = "hello world", + .sha1 = "2aae6c35c94fcfb415dbe95f408b9ce91ee846ed", + }, + { + .str = "hello world!", + .sha1 = "430ce34d020724ed75a196dfc2ad67c77772d169", + }, + }; + + // Need a helper function to generate a name for each test case. + static void case_to_desc(const struct sha1_test_case *t, char *desc) + { + strcpy(desc, t->str); + } + // Creates `sha1_gen_params()` to iterate over `cases`. + KUNIT_ARRAY_PARAM(sha1, cases, case_to_desc); + + // Looks no different from a normal test. + static void sha1_test(struct kunit *test) + { + // This function can just contain the body of the for-loop. + // The former `cases[i]` is accessible under test->param_value. + char out[40]; + struct sha1_test_case *test_param = (struct sha1_test_case *)(test->param_value); + + sha1sum(test_param->str, out); + KUNIT_EXPECT_STREQ_MSG(test, (char *)out, test_param->sha1, + "sha1sum(%s)", test_param->str); + } + + // Instead of KUNIT_CASE, we use KUNIT_CASE_PARAM and pass in the + // function declared by KUNIT_ARRAY_PARAM. + static struct kunit_case sha1_test_cases[] = { + KUNIT_CASE_PARAM(sha1_test, sha1_gen_params), + {} + }; + .. _kunit-on-non-uml: KUnit on non-UML architectures diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml index 14cd727d3c4b..f02fd10de604 100644 --- a/Documentation/devicetree/bindings/arm/cpus.yaml +++ b/Documentation/devicetree/bindings/arm/cpus.yaml @@ -232,7 +232,6 @@ properties: by this cpu (see ./idle-states.yaml). capacity-dmips-mhz: - $ref: '/schemas/types.yaml#/definitions/uint32' description: u32 value representing CPU capacity (see ./cpu-capacity.txt) in DMIPS/MHz, relative to highest capacity-dmips-mhz diff --git a/Documentation/devicetree/bindings/display/bridge/sii902x.txt b/Documentation/devicetree/bindings/display/bridge/sii902x.txt index 02c21b584741..3bc760cc31cb 100644 --- a/Documentation/devicetree/bindings/display/bridge/sii902x.txt +++ b/Documentation/devicetree/bindings/display/bridge/sii902x.txt @@ -40,7 +40,7 @@ Optional properties: 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.yaml - Documentation/devicetree/bindings/sound/audio-graph-card.txt + Documentation/devicetree/bindings/sound/audio-graph-card.yaml Note: In case of the audio-graph-card binding the used port index should be 3. diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt index 33977e15bebd..ed76332ec01e 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt @@ -23,7 +23,7 @@ connected to. For a description of the display interface sink function blocks, see Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt and -Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt. +Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.yaml. Required properties (all function blocks): - compatible: "mediatek,<chip>-disp-<function>", one of @@ -61,7 +61,7 @@ Required properties (DMA function blocks): "mediatek,<chip>-disp-wdma" the supported chips are mt2701, mt8167 and mt8173. - larb: Should contain a phandle pointing to the local arbiter device as defined - in Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt + in Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.yaml - iommus: Should point to the respective IOMMU block with master port as argument, see Documentation/devicetree/bindings/iommu/mediatek,iommu.txt for details. diff --git a/Documentation/devicetree/bindings/extcon/wlf,arizona.yaml b/Documentation/devicetree/bindings/extcon/wlf,arizona.yaml index 5fe784f487c5..efdf59abb2e1 100644 --- a/Documentation/devicetree/bindings/extcon/wlf,arizona.yaml +++ b/Documentation/devicetree/bindings/extcon/wlf,arizona.yaml @@ -85,7 +85,6 @@ properties: wlf,micd-timeout-ms: description: Timeout for microphone detection, specified in milliseconds. - $ref: "/schemas/types.yaml#/definitions/uint32" wlf,micd-force-micbias: description: diff --git a/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml b/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml index eef614962b10..bf04151b63d2 100644 --- a/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml +++ b/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml @@ -49,7 +49,6 @@ properties: description: This property controls the Accumulation Dead band which allows to set the level of current below which no accumulation takes place. - $ref: /schemas/types.yaml#/definitions/uint32 maximum: 255 default: 0 diff --git a/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml b/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml index 00a6511354e6..5d3ce641fcde 100644 --- a/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml +++ b/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml @@ -73,11 +73,9 @@ properties: description: | Temperature sensor trimming factor. It can be used to manually adjust the temperature measurements within 7.130 degrees Celsius. - maxItems: 1 - items: - default: 0 - minimum: 0 - maximum: 7130 + default: 0 + minimum: 0 + maximum: 7130 additionalProperties: false diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml index 8020d739a078..1502b22c77cc 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml @@ -52,7 +52,6 @@ properties: ti,bus-range-microvolt: description: | This is the operating range of the bus voltage in microvolt - $ref: /schemas/types.yaml#/definitions/uint32 enum: [16000000, 32000000] default: 32000000 diff --git a/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml b/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml index cc3aa2a5e70b..ff99344788ab 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml @@ -39,11 +39,9 @@ properties: i2c-gpio,delay-us: description: delay between GPIO operations (may depend on each platform) - $ref: /schemas/types.yaml#/definitions/uint32 i2c-gpio,timeout-ms: description: timeout to get data - $ref: /schemas/types.yaml#/definitions/uint32 # Deprecated properties, do not use in new device tree sources: gpios: diff --git a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml index c22b66b6219e..d9293c57f573 100644 --- a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml @@ -66,21 +66,18 @@ properties: default: 400000 i2c-sda-hold-time-ns: - maxItems: 1 description: | The property should contain the SDA hold time in nanoseconds. This option is only supported in hardware blocks version 1.11a or newer or on Microsemi SoCs. i2c-scl-falling-time-ns: - maxItems: 1 description: | The property should contain the SCL falling time in nanoseconds. This value is used to compute the tLOW period. default: 300 i2c-sda-falling-time-ns: - maxItems: 1 description: | The property should contain the SDA falling time in nanoseconds. This value is used to compute the tHIGH period. diff --git a/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml b/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml index 6eef3480ea8f..c2efbb813ca2 100644 --- a/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml +++ b/Documentation/devicetree/bindings/iio/accel/bosch,bma255.yaml @@ -16,8 +16,8 @@ description: properties: compatible: enum: - - bosch,bmc150 - - bosch,bmi055 + - bosch,bmc150_accel + - bosch,bmi055_accel - bosch,bma255 - bosch,bma250e - bosch,bma222 diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml index e0cc3b2e8957..22b7ed3723f6 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml @@ -80,7 +80,7 @@ properties: type: boolean bipolar: - description: see Documentation/devicetree/bindings/iio/adc/adc.txt + description: see Documentation/devicetree/bindings/iio/adc/adc.yaml type: boolean required: diff --git a/Documentation/devicetree/bindings/iio/adc/maxim,max9611.yaml b/Documentation/devicetree/bindings/iio/adc/maxim,max9611.yaml index 9475a9e6e920..95774a55629d 100644 --- a/Documentation/devicetree/bindings/iio/adc/maxim,max9611.yaml +++ b/Documentation/devicetree/bindings/iio/adc/maxim,max9611.yaml @@ -23,7 +23,6 @@ properties: maxItems: 1 shunt-resistor-micro-ohms: - $ref: /schemas/types.yaml#/definitions/uint32 description: | Value in micro Ohms of the shunt resistor connected between the RS+ and RS- inputs, across which the current is measured. Value needed to compute diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml index 28417b31b558..517e32976c30 100644 --- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml @@ -246,7 +246,6 @@ patternProperties: Resolution (bits) to use for conversions: - can be 6, 8, 10 or 12 on stm32f4 - can be 8, 10, 12, 14 or 16 on stm32h7 and stm32mp1 - $ref: /schemas/types.yaml#/definitions/uint32 st,adc-channels: description: | diff --git a/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml b/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml index 692dacd0fee5..7b895784e008 100644 --- a/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/ti,palmas-gpadc.yaml @@ -42,7 +42,6 @@ properties: const: 1 ti,channel0-current-microamp: - $ref: /schemas/types.yaml#/definitions/uint32 description: Channel 0 current in uA. enum: - 0 @@ -51,7 +50,6 @@ properties: - 20 ti,channel3-current-microamp: - $ref: /schemas/types.yaml#/definitions/uint32 description: Channel 3 current in uA. enum: - 0 diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5758.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5758.yaml index 626ccb6fe21e..fd4edca34a28 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5758.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5758.yaml @@ -46,31 +46,42 @@ properties: two properties must be present: adi,range-microvolt: - $ref: /schemas/types.yaml#/definitions/int32-array description: | Voltage output range specified as <minimum, maximum> - enum: - - [[0, 5000000]] - - [[0, 10000000]] - - [[-5000000, 5000000]] - - [[-10000000, 10000000]] + oneOf: + - items: + - const: 0 + - enum: [5000000, 10000000] + - items: + - const: -5000000 + - const: 5000000 + - items: + - const: -10000000 + - const: 10000000 adi,range-microamp: - $ref: /schemas/types.yaml#/definitions/int32-array description: | Current output range specified as <minimum, maximum> - enum: - - [[0, 20000]] - - [[0, 24000]] - - [[4, 24000]] - - [[-20000, 20000]] - - [[-24000, 24000]] - - [[-1000, 22000]] + oneOf: + - items: + - const: 0 + - enum: [20000, 24000] + - items: + - const: 4 + - const: 24000 + - items: + - const: -20000 + - const: 20000 + - items: + - const: -24000 + - const: 24000 + - items: + - const: -1000 + - const: 22000 reset-gpios: true adi,dc-dc-ilim-microamp: - $ref: /schemas/types.yaml#/definitions/uint32 enum: [150000, 200000, 250000, 300000, 350000, 400000] description: | The dc-to-dc converter current limit. diff --git a/Documentation/devicetree/bindings/iio/health/maxim,max30100.yaml b/Documentation/devicetree/bindings/iio/health/maxim,max30100.yaml index 64b862637039..967778fb0ce8 100644 --- a/Documentation/devicetree/bindings/iio/health/maxim,max30100.yaml +++ b/Documentation/devicetree/bindings/iio/health/maxim,max30100.yaml @@ -21,7 +21,6 @@ properties: description: Connected to ADC_RDY pin. maxim,led-current-microamp: - $ref: /schemas/types.yaml#/definitions/uint32-array minItems: 2 maxItems: 2 description: | diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml index a771a15f053f..046ace461cc9 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml +++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml @@ -70,11 +70,9 @@ properties: touchscreen-x-mm: description: horizontal length in mm of the touchscreen - $ref: /schemas/types.yaml#/definitions/uint32 touchscreen-y-mm: description: vertical length in mm of the touchscreen - $ref: /schemas/types.yaml#/definitions/uint32 dependencies: touchscreen-size-x: [ touchscreen-size-y ] diff --git a/Documentation/devicetree/bindings/leds/richtek,rt8515.yaml b/Documentation/devicetree/bindings/leds/richtek,rt8515.yaml new file mode 100644 index 000000000000..68c328eec03b --- /dev/null +++ b/Documentation/devicetree/bindings/leds/richtek,rt8515.yaml @@ -0,0 +1,111 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/richtek,rt8515.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Richtek RT8515 1.5A dual channel LED driver + +maintainers: + - Linus Walleij <linus.walleij@linaro.org> + +description: | + The Richtek RT8515 is a dual channel (two mode) LED driver that + supports driving a white LED in flash or torch mode. The maximum + current for each mode is defined in hardware using two resistors + RFS and RTS. + +properties: + compatible: + const: richtek,rt8515 + + enf-gpios: + maxItems: 1 + description: A connection to the 'ENF' (enable flash) pin. + + ent-gpios: + maxItems: 1 + description: A connection to the 'ENT' (enable torch) pin. + + richtek,rfs-ohms: + minimum: 7680 + maximum: 367000 + description: The resistance value of the RFS resistor. This + resistors limits the maximum flash current. This must be set + for the property flash-max-microamp to work, the RFS resistor + defines the range of the dimmer setting (brightness) of the + flash LED. + + richtek,rts-ohms: + minimum: 7680 + maximum: 367000 + description: The resistance value of the RTS resistor. This + resistors limits the maximum torch current. This must be set + for the property torch-max-microamp to work, the RTS resistor + defines the range of the dimmer setting (brightness) of the + torch LED. + + led: + type: object + $ref: common.yaml# + properties: + function: true + color: true + flash-max-timeout-us: true + + flash-max-microamp: + maximum: 700000 + description: The maximum current for flash mode + is hardwired to the component using the RFS resistor to + ground. The maximum hardware current setting is calculated + according to the formula Imax = 5500 / RFS. The lowest + allowed resistance value is 7.86 kOhm giving an absolute + maximum current of 700mA. By setting this attribute in + the device tree, you can further restrict the maximum + current below the hardware limit. This requires the RFS + to be defined as it defines the maximum range. + + led-max-microamp: + maximum: 700000 + description: The maximum current for torch mode + is hardwired to the component using the RTS resistor to + ground. The maximum hardware current setting is calculated + according to the formula Imax = 5500 / RTS. The lowest + allowed resistance value is 7.86 kOhm giving an absolute + maximum current of 700mA. By setting this attribute in + the device tree, you can further restrict the maximum + current below the hardware limit. This requires the RTS + to be defined as it defines the maximum range. + + additionalProperties: false + +required: + - compatible + - ent-gpios + - enf-gpios + - led + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/leds/common.h> + + led-controller { + compatible = "richtek,rt8515"; + enf-gpios = <&gpio4 12 GPIO_ACTIVE_HIGH>; + ent-gpios = <&gpio4 13 GPIO_ACTIVE_HIGH>; + richtek,rfs-ohms = <16000>; + richtek,rts-ohms = <100000>; + + led { + function = LED_FUNCTION_FLASH; + color = <LED_COLOR_ID_WHITE>; + flash-max-timeout-us = <250000>; + flash-max-microamp = <150000>; + led-max-microamp = <25000>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/media/mediatek-jpeg-decoder.txt b/Documentation/devicetree/bindings/media/mediatek-jpeg-decoder.txt index 044b11913c49..cf60c5acc0e4 100644 --- a/Documentation/devicetree/bindings/media/mediatek-jpeg-decoder.txt +++ b/Documentation/devicetree/bindings/media/mediatek-jpeg-decoder.txt @@ -16,7 +16,7 @@ Required properties: - power-domains: a phandle to the power domain, see Documentation/devicetree/bindings/power/power_domain.txt for details. - mediatek,larb: must contain the local arbiters in the current Socs, see - Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt + Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.yaml for details. - iommus: should point to the respective IOMMU block with master port as argument, see Documentation/devicetree/bindings/iommu/mediatek,iommu.txt diff --git a/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.txt b/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.txt index 736be7cad385..acfb50375b8a 100644 --- a/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.txt +++ b/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.txt @@ -14,7 +14,7 @@ Required properties: - power-domains: a phandle to the power domain, see Documentation/devicetree/bindings/power/power_domain.txt for details. - mediatek,larb: must contain the local arbiters in the current SoCs, see - Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt + Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.yaml for details. - iommus: should point to the respective IOMMU block with master port as argument, see Documentation/devicetree/bindings/iommu/mediatek,iommu.txt diff --git a/Documentation/devicetree/bindings/media/mediatek-mdp.txt b/Documentation/devicetree/bindings/media/mediatek-mdp.txt index 0d03e3ae2be2..f4798d04e925 100644 --- a/Documentation/devicetree/bindings/media/mediatek-mdp.txt +++ b/Documentation/devicetree/bindings/media/mediatek-mdp.txt @@ -28,7 +28,7 @@ Required properties (DMA function blocks, child node): argument, see Documentation/devicetree/bindings/iommu/mediatek,iommu.txt for details. - mediatek,larb: must contain the local arbiters in the current Socs, see - Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt + Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.yaml for details. Example: diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml index 186f04ba9357..e674bba52ee9 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml +++ b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml @@ -259,7 +259,6 @@ properties: waiting for I/O signalling and card power supply to be stable, regardless of whether pwrseq-simple is used. Default to 10ms if no available. - $ref: /schemas/types.yaml#/definitions/uint32 default: 10 supports-cqe: diff --git a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml index 6cd57863c1db..226fb191913d 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml +++ b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml @@ -41,13 +41,11 @@ properties: description: Delay in ms after powering the card and de-asserting the reset-gpios (if any). - $ref: /schemas/types.yaml#/definitions/uint32 power-off-delay-us: description: Delay in us after asserting the reset-gpios (if any) during power off of the card. - $ref: /schemas/types.yaml#/definitions/uint32 required: - compatible diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 0965f6515f9e..dac4aadb6e2e 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -122,7 +122,6 @@ properties: such as flow control thresholds. rx-internal-delay-ps: - $ref: /schemas/types.yaml#/definitions/uint32 description: | RGMII Receive Clock Delay defined in pico seconds. This is used for controllers that have configurable RX internal delays. @@ -140,7 +139,6 @@ properties: is used for components that can have configurable fifo sizes. tx-internal-delay-ps: - $ref: /schemas/types.yaml#/definitions/uint32 description: | RGMII Transmit Clock Delay defined in pico seconds. This is used for controllers that have configurable TX internal delays. diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index dfbf5fe4547a..0642b0f59491 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -212,7 +212,6 @@ properties: Triplet of delays. The 1st cell is reset pre-delay in micro seconds. The 2nd cell is reset pulse in micro seconds. The 3rd cell is reset post-delay in micro seconds. - $ref: /schemas/types.yaml#/definitions/uint32-array minItems: 3 maxItems: 3 diff --git a/Documentation/devicetree/bindings/power/supply/battery.yaml b/Documentation/devicetree/bindings/power/supply/battery.yaml index 0c7e2e44793b..c3b4b7543591 100644 --- a/Documentation/devicetree/bindings/power/supply/battery.yaml +++ b/Documentation/devicetree/bindings/power/supply/battery.yaml @@ -83,21 +83,18 @@ properties: for each of the battery capacity lookup table. operating-range-celsius: - $ref: /schemas/types.yaml#/definitions/uint32-array description: operating temperature range of a battery items: - description: minimum temperature at which battery can operate - description: maximum temperature at which battery can operate ambient-celsius: - $ref: /schemas/types.yaml#/definitions/uint32-array description: safe range of ambient temperature items: - description: alert when ambient temperature is lower than this value - description: alert when ambient temperature is higher than this value alert-celsius: - $ref: /schemas/types.yaml#/definitions/uint32-array description: safe range of battery temperature items: - description: alert when battery temperature is lower than this value diff --git a/Documentation/devicetree/bindings/power/supply/bq2515x.yaml b/Documentation/devicetree/bindings/power/supply/bq2515x.yaml index 75a56773be4a..813d6afde606 100644 --- a/Documentation/devicetree/bindings/power/supply/bq2515x.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq2515x.yaml @@ -50,7 +50,6 @@ properties: maxItems: 1 input-current-limit-microamp: - $ref: /schemas/types.yaml#/definitions/uint32 description: Maximum input current in micro Amps. minimum: 50000 maximum: 500000 diff --git a/Documentation/devicetree/bindings/regulator/dlg,da9121.yaml b/Documentation/devicetree/bindings/regulator/dlg,da9121.yaml index 6f2164f7bc57..228018c87bea 100644 --- a/Documentation/devicetree/bindings/regulator/dlg,da9121.yaml +++ b/Documentation/devicetree/bindings/regulator/dlg,da9121.yaml @@ -62,7 +62,6 @@ properties: description: IRQ line information. dlg,irq-polling-delay-passive-ms: - $ref: "/schemas/types.yaml#/definitions/uint32" minimum: 1000 maximum: 10000 description: | diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml index d3d0dc13dd8b..8850c01bd470 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml @@ -72,11 +72,9 @@ properties: startup-delay-us: description: startup time in microseconds - $ref: /schemas/types.yaml#/definitions/uint32 off-on-delay-us: description: off delay time in microseconds - $ref: /schemas/types.yaml#/definitions/uint32 enable-active-high: description: diff --git a/Documentation/devicetree/bindings/rtc/rtc.yaml b/Documentation/devicetree/bindings/rtc/rtc.yaml index d30dc045aac6..0ec3551f12dd 100644 --- a/Documentation/devicetree/bindings/rtc/rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc.yaml @@ -27,7 +27,6 @@ properties: 1: chargeable quartz-load-femtofarads: - $ref: /schemas/types.yaml#/definitions/uint32 description: The capacitive load of the quartz(x-tal), expressed in femto Farad (fF). The default value shall be listed (if optional), @@ -47,7 +46,6 @@ properties: deprecated: true trickle-resistor-ohms: - $ref: /schemas/types.yaml#/definitions/uint32 description: Selected resistor for trickle charger. Should be given if trickle charger should be enabled. diff --git a/Documentation/devicetree/bindings/serial/pl011.yaml b/Documentation/devicetree/bindings/serial/pl011.yaml index c23c93b400f0..07fa6d26f2b4 100644 --- a/Documentation/devicetree/bindings/serial/pl011.yaml +++ b/Documentation/devicetree/bindings/serial/pl011.yaml @@ -88,14 +88,12 @@ properties: description: Rate at which poll occurs when auto-poll is set. default 100ms. - $ref: /schemas/types.yaml#/definitions/uint32 default: 100 poll-timeout-ms: description: Poll timeout when auto-poll is set, default 3000ms. - $ref: /schemas/types.yaml#/definitions/uint32 default: 3000 required: diff --git a/Documentation/devicetree/bindings/sound/mt8192-mt6359-rt1015-rt5682.yaml b/Documentation/devicetree/bindings/sound/mt8192-mt6359-rt1015-rt5682.yaml index bf8c8ba25009..54650823b29a 100644 --- a/Documentation/devicetree/bindings/sound/mt8192-mt6359-rt1015-rt5682.yaml +++ b/Documentation/devicetree/bindings/sound/mt8192-mt6359-rt1015-rt5682.yaml @@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek MT8192 with MT6359, RT1015 and RT5682 ASoC sound card driver maintainers: - - Jiaxin Yu <jiaxin.yu@mediatek.com> - - Shane Chien <shane.chien@mediatek.com> + - Jiaxin Yu <jiaxin.yu@mediatek.com> + - Shane Chien <shane.chien@mediatek.com> description: This binding describes the MT8192 sound card. diff --git a/Documentation/devicetree/bindings/sound/sgtl5000.yaml b/Documentation/devicetree/bindings/sound/sgtl5000.yaml index d116c174b545..70b4a8831073 100644 --- a/Documentation/devicetree/bindings/sound/sgtl5000.yaml +++ b/Documentation/devicetree/bindings/sound/sgtl5000.yaml @@ -41,14 +41,12 @@ properties: values of 2k, 4k or 8k. If set to 0 it will be off. If this node is not mentioned or if the value is unknown, then micbias resistor is set to 4k. - $ref: "/schemas/types.yaml#/definitions/uint32" enum: [ 0, 2, 4, 8 ] micbias-voltage-m-volts: description: The bias voltage to be used in mVolts. The voltage can take values from 1.25V to 3V by 250mV steps. If this node is not mentioned or the value is unknown, then the value is set to 1.25V. - $ref: "/schemas/types.yaml#/definitions/uint32" enum: [ 1250, 1500, 1750, 2000, 2250, 2500, 2750, 3000 ] lrclk-strength: diff --git a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml index 148b3fb4ceaf..c80a83571919 100644 --- a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml +++ b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml @@ -21,6 +21,8 @@ properties: reg: description: module registers + ranges: true + power-domains: description: PM domain provider node and an args specifier containing @@ -62,6 +64,8 @@ properties: '#size-cells': const: 2 + dma-coherent: true + patternProperties: "^usb@": type: object diff --git a/Documentation/devicetree/bindings/watchdog/watchdog.yaml b/Documentation/devicetree/bindings/watchdog/watchdog.yaml index 4e2c26cd981d..e3dfb02f0ca5 100644 --- a/Documentation/devicetree/bindings/watchdog/watchdog.yaml +++ b/Documentation/devicetree/bindings/watchdog/watchdog.yaml @@ -19,7 +19,6 @@ properties: pattern: "^watchdog(@.*|-[0-9a-f])?$" timeout-sec: - $ref: /schemas/types.yaml#/definitions/uint32 description: Contains the watchdog timeout in seconds. diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst index 2312506b0674..fff96c7ba7a8 100644 --- a/Documentation/driver-api/auxiliary_bus.rst +++ b/Documentation/driver-api/auxiliary_bus.rst @@ -1,5 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0-only +.. _auxiliary_bus: + ============= Auxiliary Bus ============= diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst index e9b65035cd47..a1b32fcd0d76 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst @@ -12,6 +12,8 @@ Contents - `Enabling the driver and kconfig options`_ - `Devlink info`_ - `Devlink parameters`_ +- `mlx5 subfunction`_ +- `mlx5 port function`_ - `Devlink health reporters`_ - `mlx5 tracepoints`_ @@ -97,6 +99,11 @@ Enabling the driver and kconfig options | Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support. +**CONFIG_MLX5_SF=(y/n)** + +| Build support for subfunction. +| Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option +| will enable support for creating subfunction devices. **External options** ( Choose if the corresponding mlx5 feature is required ) @@ -176,6 +183,214 @@ User command examples: values: cmode driverinit value true +mlx5 subfunction +================ +mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface. + +A Subfunction has its own function capabilities and its own resources. This +means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These +queues are neither shared nor stolen from the parent PCI function. + +When a subfunction is RDMA capable, it has its own QP1, GID table and rdma +resources neither shared nor stolen from the parent PCI function. + +A subfunction has a dedicated window in PCI BAR space that is not shared +with ther other subfunctions or the parent PCI function. This ensures that all +devices (netdev, rdma, vdpa etc.) of the subfunction accesses only assigned +PCI BAR space. + +A Subfunction supports eswitch representation through which it supports tc +offloads. The user configures eswitch to send/receive packets from/to +the subfunction port. + +Subfunctions share PCI level resources such as PCI MSI-X IRQs with +other subfunctions and/or with its parent PCI function. + +Example mlx5 software, system and device view:: + + _______ + | admin | + | user |---------- + |_______| | + | | + ____|____ __|______ _________________ + | | | | | | + | devlink | | tc tool | | user | + | tool | |_________| | applications | + |_________| | |_________________| + | | | | + | | | | Userspace + +---------|-------------|-------------------|----------|--------------------+ + | | +----------+ +----------+ Kernel + | | | netdev | | rdma dev | + | | +----------+ +----------+ + (devlink port add/del | ^ ^ + port function set) | | | + | | +---------------| + _____|___ | | _______|_______ + | | | | | mlx5 class | + | devlink | +------------+ | | drivers | + | kernel | | rep netdev | | |(mlx5_core,ib) | + |_________| +------------+ | |_______________| + | | | ^ + (devlink ops) | | (probe/remove) + _________|________ | | ____|________ + | subfunction | | +---------------+ | subfunction | + | management driver|----- | subfunction |---| driver | + | (mlx5_core) | | auxiliary dev | | (mlx5_core) | + |__________________| +---------------+ |_____________| + | ^ + (sf add/del, vhca events) | + | (device add/del) + _____|____ ____|________ + | | | subfunction | + | PCI NIC |---- activate/deactive events---->| host driver | + |__________| | (mlx5_core) | + |_____________| + +Subfunction is created using devlink port interface. + +- Change device to switchdev mode:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +- Add a devlink port of subfunction flaovur:: + + $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 + pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:00:00 state inactive opstate detached + +- Show a devlink port of the subfunction:: + + $ devlink port show pci/0000:06:00.0/32768 + pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88 + function: + hw_addr 00:00:00:00:00:00 state inactive opstate detached + +- Delete a devlink port of subfunction after use:: + + $ devlink port del pci/0000:06:00.0/32768 + +mlx5 function attributes +======================== +The mlx5 driver provides a mechanism to setup PCI VF/SF function attributes in +a unified way for SmartNIC and non-SmartNIC. + +This is supported only when the eswitch mode is set to switchdev. Port function +configuration of the PCI VF/SF is supported through devlink eswitch port. + +Port function attributes should be set before PCI VF/SF is enumerated by the +driver. + +MAC address setup +----------------- +mlx5 driver provides mechanism to setup the MAC address of the PCI VF/SF. + +The configured MAC address of the PCI VF/SF will be used by netdevice and rdma +device created for the PCI VF/SF. + +- Get the MAC address of the VF identified by its unique devlink port index:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 + +- Set the MAC address of the VF identified by its unique devlink port index:: + + $ devlink port function set pci/0000:06:00.0/2 hw_addr 00:11:22:33:44:55 + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:11:22:33:44:55 + +- Get the MAC address of the SF identified by its unique devlink port index:: + + $ devlink port show pci/0000:06:00.0/32768 + pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88 + function: + hw_addr 00:00:00:00:00:00 + +- Set the MAC address of the VF identified by its unique devlink port index:: + + $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88 + + $ devlink port show pci/0000:06:00.0/32768 + pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcivf pfnum 0 sfnum 88 + function: + hw_addr 00:00:00:00:88:88 + +SF state setup +-------------- +To use the SF, the user must active the SF using the SF function state +attribute. + +- Get the state of the SF identified by its unique devlink port index:: + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state inactive opstate detached + +- Activate the function and verify its state is active:: + + $ devlink port function set ens2f0npf0sf88 state active + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state active opstate detached + +Upon function activation, the PF driver instance gets the event from the device +that a particular SF was activated. It's the cue to put the device on bus, probe +it and instantiate the devlink instance and class specific auxiliary devices +for it. + +- Show the auxiliary device and port of the subfunction:: + + $ devlink dev show + devlink dev show auxiliary/mlx5_core.sf.4 + + $ devlink port show auxiliary/mlx5_core.sf.4/1 + auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false + + $ rdma link show mlx5_0/1 + link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 + + $ rdma dev show + 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 + 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 + +- Subfunction auxiliary device and class device hierarchy:: + + mlx5_core.sf.4 + (subfunction auxiliary device) + /\ + / \ + / \ + / \ + / \ + mlx5_core.eth.4 mlx5_core.rdma.4 + (sf eth aux dev) (sf rdma aux dev) + | | + | | + p0sf88 mlx5_0 + (sf netdev) (sf rdma device) + +Additionally, the SF port also gets the event when the driver attaches to the +auxiliary device of the subfunction. This results in changing the operational +state of the function. This provides visiblity to the user to decide when is it +safe to delete the SF port for graceful termination of the subfunction. + +- Show the SF port operational state:: + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state active opstate attached + Devlink health reporters ======================== diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst new file mode 100644 index 000000000000..e99b41599465 --- /dev/null +++ b/Documentation/networking/devlink/devlink-port.rst @@ -0,0 +1,199 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _devlink_port: + +============ +Devlink Port +============ + +``devlink-port`` is a port that exists on the device. It has a logically +separate ingress/egress point of the device. A devlink port can be any one +of many flavours. A devlink port flavour along with port attributes +describe what a port represents. + +A device driver that intends to publish a devlink port sets the +devlink port attributes and registers the devlink port. + +Devlink port flavours are described below. + +.. list-table:: List of devlink port flavours + :widths: 33 90 + + * - Flavour + - Description + * - ``DEVLINK_PORT_FLAVOUR_PHYSICAL`` + - Any kind of physical port. This can be an eswitch physical port or any + other physical port on the device. + * - ``DEVLINK_PORT_FLAVOUR_DSA`` + - This indicates a DSA interconnect port. + * - ``DEVLINK_PORT_FLAVOUR_CPU`` + - This indicates a CPU port applicable only to DSA. + * - ``DEVLINK_PORT_FLAVOUR_PCI_PF`` + - This indicates an eswitch port representing a port of PCI + physical function (PF). + * - ``DEVLINK_PORT_FLAVOUR_PCI_VF`` + - This indicates an eswitch port representing a port of PCI + virtual function (VF). + * - ``DEVLINK_PORT_FLAVOUR_PCI_SF`` + - This indicates an eswitch port representing a port of PCI + subfunction (SF). + * - ``DEVLINK_PORT_FLAVOUR_VIRTUAL`` + - This indicates a virtual port for the PCI virtual function. + +Devlink port can have a different type based on the link layer described below. + +.. list-table:: List of devlink port types + :widths: 23 90 + + * - Type + - Description + * - ``DEVLINK_PORT_TYPE_ETH`` + - Driver should set this port type when a link layer of the port is + Ethernet. + * - ``DEVLINK_PORT_TYPE_IB`` + - Driver should set this port type when a link layer of the port is + InfiniBand. + * - ``DEVLINK_PORT_TYPE_AUTO`` + - This type is indicated by the user when driver should detect the port + type automatically. + +PCI controllers +--------------- +In most cases a PCI device has only one controller. A controller consists of +potentially multiple physical, virtual functions and subfunctions. A function +consists of one or more ports. This port is represented by the devlink eswitch +port. + +A PCI device connected to multiple CPUs or multiple PCI root complexes or a +SmartNIC, however, may have multiple controllers. For a device with multiple +controllers, each controller is distinguished by a unique controller number. +An eswitch is on the PCI device which supports ports of multiple controllers. + +An example view of a system with two controllers:: + + --------------------------------------------------------- + | | + | --------- --------- ------- ------- | + ----------- | | vf(s) | | sf(s) | |vf(s)| |sf(s)| | + | server | | ------- ----/---- ---/----- ------- ---/--- ---/--- | + | pci rc |=== | pf0 |______/________/ | pf1 |___/_______/ | + | connect | | ------- ------- | + ----------- | | controller_num=1 (no eswitch) | + ------|-------------------------------------------------- + (internal wire) + | + --------------------------------------------------------- + | devlink eswitch ports and reps | + | ----------------------------------------------------- | + | |ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 |ctrl-0 | | + | |pf0 | pf0vfN | pf0sfN | pf1 | pf1vfN |pf1sfN | | + | ----------------------------------------------------- | + | |ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 |ctrl-1 | | + | |pf0 | pf0vfN | pf0sfN | pf1 | pf1vfN |pf1sfN | | + | ----------------------------------------------------- | + | | + | | + ----------- | --------- --------- ------- ------- | + | smartNIC| | | vf(s) | | sf(s) | |vf(s)| |sf(s)| | + | pci rc |==| ------- ----/---- ---/----- ------- ---/--- ---/--- | + | connect | | | pf0 |______/________/ | pf1 |___/_______/ | + ----------- | ------- ------- | + | | + | local controller_num=0 (eswitch) | + --------------------------------------------------------- + +In the above example, the external controller (identified by controller number = 1) +doesn't have the eswitch. Local controller (identified by controller number = 0) +has the eswitch. The Devlink instance on the local controller has eswitch +devlink ports for both the controllers. + +Function configuration +====================== + +A user can configure the function attribute before enumerating the PCI +function. Usually it means, user should configure function attribute +before a bus specific device for the function is created. However, when +SRIOV is enabled, virtual function devices are created on the PCI bus. +Hence, function attribute should be configured before binding virtual +function device to the driver. For subfunctions, this means user should +configure port function attribute before activating the port function. + +A user may set the hardware address of the function using +'devlink port function set hw_addr' command. For Ethernet port function +this means a MAC address. + +Subfunction +============ + +Subfunction is a lightweight function that has a parent PCI function on which +it is deployed. Subfunction is created and deployed in unit of 1. Unlike +SRIOV VFs, a subfunction doesn't require its own PCI virtual function. +A subfunction communicates with the hardware through the parent PCI function. + +To use a subfunction, 3 steps setup sequence is followed. +(1) create - create a subfunction; +(2) configure - configure subfunction attributes; +(3) deploy - deploy the subfunction; + +Subfunction management is done using devlink port user interface. +User performs setup on the subfunction management device. + +(1) Create +---------- +A subfunction is created using a devlink port interface. A user adds the +subfunction by adding a devlink port of subfunction flavour. The devlink +kernel code calls down to subfunction management driver (devlink ops) and asks +it to create a subfunction devlink port. Driver then instantiates the +subfunction port and any associated objects such as health reporters and +representor netdevice. + +(2) Configure +------------- +A subfunction devlink port is created but it is not active yet. That means the +entities are created on devlink side, the e-switch port representor is created, +but the subfunction device itself it not created. A user might use e-switch port +representor to do settings, putting it into bridge, adding TC rules, etc. A user +might as well configure the hardware address (such as MAC address) of the +subfunction while subfunction is inactive. + +(3) Deploy +---------- +Once a subfunction is configured, user must activate it to use it. Upon +activation, subfunction management driver asks the subfunction management +device to instantiate the subfunction device on particular PCI function. +A subfunction device is created on the :ref:`Documentation/driver-api/auxiliary_bus.rst <auxiliary_bus>`. +At this point a matching subfunction driver binds to the subfunction's auxiliary device. + +Terms and Definitions +===================== + +.. list-table:: Terms and Definitions + :widths: 22 90 + + * - Term + - Definitions + * - ``PCI device`` + - A physical PCI device having one or more PCI bus consists of one or + more PCI controllers. + * - ``PCI controller`` + - A controller consists of potentially multiple physical functions, + virtual functions and subfunctions. + * - ``Port function`` + - An object to manage the function of a port. + * - ``Subfunction`` + - A lightweight function that has parent PCI function on which it is + deployed. + * - ``Subfunction device`` + - A bus device of the subfunction, usually on a auxiliary bus. + * - ``Subfunction driver`` + - A device driver for the subfunction auxiliary device. + * - ``Subfunction management device`` + - A PCI physical function that supports subfunction management. + * - ``Subfunction management driver`` + - A device driver for PCI physical function that supports + subfunction management using devlink port interface. + * - ``Subfunction host driver`` + - A device driver for PCI physical function that hosts subfunction + devices. In most cases it is same as subfunction management driver. When + subfunction is used on external controller, subfunction management and + host drivers are different. diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index d82874760ae2..aab79667f97b 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -18,6 +18,7 @@ general. devlink-info devlink-flash devlink-params + devlink-port devlink-region devlink-resource devlink-reload diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 0e51ddd9a2f1..61a358301f12 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -178,6 +178,26 @@ min_adv_mss - INTEGER The advertised MSS depends on the first hop route MTU, but will never be lower than this setting. +fib_notify_on_flag_change - INTEGER + Whether to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/ + RTM_F_TRAP flags are changed. + + After installing a route to the kernel, user space receives an + acknowledgment, which means the route was installed in the kernel, + but not necessarily in hardware. + It is also possible for a route already installed in hardware to change + its action and therefore its flags. For example, a host route that is + trapping packets can be "promoted" to perform decapsulation following + the installation of an IPinIP/VXLAN tunnel. + The notifications will indicate to user-space the state of the route. + + Default: 0 (Do not emit notifications.) + + Possible values: + + - 0 - Do not emit notifications. + - 1 - Emit notifications. + IP Fragmentation: ipfrag_high_thresh - LONG INTEGER @@ -1196,7 +1216,7 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN If non-zero, the message will be sent with the primary address of the interface that received the packet that caused the icmp error. - This is the behaviour network many administrators will expect from + This is the behaviour many network administrators will expect from a router. And it can make debugging complicated network layouts much easier. @@ -1775,6 +1795,26 @@ nexthop_compat_mode - BOOLEAN and extraneous notifications. Default: true (backward compat mode) +fib_notify_on_flag_change - INTEGER + Whether to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/ + RTM_F_TRAP flags are changed. + + After installing a route to the kernel, user space receives an + acknowledgment, which means the route was installed in the kernel, + but not necessarily in hardware. + It is also possible for a route already installed in hardware to change + its action and therefore its flags. For example, a host route that is + trapping packets can be "promoted" to perform decapsulation following + the installation of an IPinIP/VXLAN tunnel. + The notifications will indicate to user-space the state of the route. + + Default: 0 (Do not emit notifications.) + + Possible values: + + - 0 - Do not emit notifications. + - 1 - Emit notifications. + IPv6 Fragmentation: ip6frag_high_thresh - INTEGER @@ -1807,12 +1847,24 @@ seg6_flowlabel - INTEGER ``conf/default/*``: Change the interface-specific default settings. + These settings would be used during creating new interfaces. + ``conf/all/*``: Change all the interface-specific settings. [XXX: Other special features than forwarding?] +conf/all/disable_ipv6 - BOOLEAN + Changing this value is same as changing ``conf/default/disable_ipv6`` + setting and also all per-interface ``disable_ipv6`` settings to the same + value. + + Reading this value does not have any particular meaning. It does not say + whether IPv6 support is enabled or disabled. Returned value can be 1 + also in the case when some interface has ``disable_ipv6`` set to 0 and + has configured IPv6 addresses. + conf/all/forwarding - BOOLEAN Enable global IPv6 forwarding between all interfaces. diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index 03f7beade470..f682e88fa87e 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -55,7 +55,8 @@ struct __kernel_sock_timeval format. SO_TIMESTAMP_OLD returns incorrect timestamps after the year 2038 on 32 bit machines. -1.2 SO_TIMESTAMPNS (also SO_TIMESTAMPNS_OLD and SO_TIMESTAMPNS_NEW): +1.2 SO_TIMESTAMPNS (also SO_TIMESTAMPNS_OLD and SO_TIMESTAMPNS_NEW) +------------------------------------------------------------------- This option is identical to SO_TIMESTAMP except for the returned data type. Its struct timespec allows for higher resolution (ns) timestamps than the diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c136e254b496..99ceb978c8b0 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -360,10 +360,9 @@ since the last call to this ioctl. Bit 0 is the first page in the memory slot. Ensure the entire structure is cleared to avoid padding issues. -If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies -the address space for which you want to return the dirty bitmap. -They must be less than the value that KVM_CHECK_EXTENSION returns for -the KVM_CAP_MULTI_ADDRESS_SPACE capability. +If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies +the address space for which you want to return the dirty bitmap. See +KVM_SET_USER_MEMORY_REGION for details on the usage of slot field. The bits in the dirty bitmap are cleared before the ioctl returns, unless KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information, @@ -1281,6 +1280,9 @@ field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including anonymous memory, ordinary files, and hugetlbfs. +On architectures that support a form of address tagging, userspace_addr must +be an untagged address. + It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr be identical. This allows large pages in the guest to be backed by large pages in the host. @@ -1333,7 +1335,7 @@ documentation when it pops into existence). :Capability: KVM_CAP_ENABLE_CAP_VM :Architectures: all -:Type: vcpu ioctl +:Type: vm ioctl :Parameters: struct kvm_enable_cap (in) :Returns: 0 on success; -1 on error @@ -4432,7 +4434,7 @@ to I/O ports. :Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 :Architectures: x86, arm, arm64, mips :Type: vm ioctl -:Parameters: struct kvm_dirty_log (in) +:Parameters: struct kvm_clear_dirty_log (in) :Returns: 0 on success, -1 on error :: @@ -4459,10 +4461,9 @@ in KVM's dirty bitmap, and dirty tracking is re-enabled for that page (for example via write-protection, or by clearing the dirty bit in a page table entry). -If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies -the address space for which you want to return the dirty bitmap. -They must be less than the value that KVM_CHECK_EXTENSION returns for -the KVM_CAP_MULTI_ADDRESS_SPACE capability. +If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies +the address space for which you want to clear the dirty status. See +KVM_SET_USER_MEMORY_REGION for details on the usage of slot field. This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled; for more information, see the description of the capability. diff --git a/MAINTAINERS b/MAINTAINERS index 650deb973913..d1b0057a9797 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3247,6 +3247,7 @@ L: netdev@vger.kernel.org S: Supported W: http://sourceforge.net/projects/bonding/ F: drivers/net/bonding/ +F: include/net/bonding.h F: include/uapi/linux/if_bonding.h BOSCH SENSORTEC BMA400 ACCELEROMETER IIO DRIVER @@ -3420,7 +3421,7 @@ F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml F: drivers/pci/controller/pcie-brcmstb.c F: drivers/staging/vc04_services N: bcm2711 -N: bcm2835 +N: bcm283* BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> @@ -3899,7 +3900,7 @@ F: Documentation/devicetree/bindings/mtd/cadence-nand-controller.txt F: drivers/mtd/nand/raw/cadence-nand-controller.c CADENCE USB3 DRD IP DRIVER -M: Peter Chen <peter.chen@nxp.com> +M: Peter Chen <peter.chen@kernel.org> M: Pawel Laszczak <pawell@cadence.com> R: Roger Quadros <rogerq@kernel.org> R: Aswath Govindraju <a-govindraju@ti.com> @@ -4184,7 +4185,7 @@ S: Maintained F: Documentation/translations/zh_CN/ CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER -M: Peter Chen <Peter.Chen@nxp.com> +M: Peter Chen <peter.chen@kernel.org> L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git @@ -4334,7 +4335,9 @@ W: https://clangbuiltlinux.github.io/ B: https://github.com/ClangBuiltLinux/linux/issues C: irc://chat.freenode.net/clangbuiltlinux F: Documentation/kbuild/llvm.rst +F: include/linux/compiler-clang.h F: scripts/clang-tools/ +F: scripts/clang-version.sh F: scripts/lld-version.sh K: \b(?i:clang|llvm)\b @@ -8454,11 +8457,8 @@ F: drivers/i3c/ F: include/linux/i3c/ IA64 (Itanium) PLATFORM -M: Tony Luck <tony.luck@intel.com> -M: Fenghua Yu <fenghua.yu@intel.com> L: linux-ia64@vger.kernel.org -S: Odd Fixes -T: git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git +S: Orphan F: Documentation/ia64/ F: arch/ia64/ @@ -12436,6 +12436,7 @@ F: tools/testing/selftests/net/ipsec.c NETWORKING [IPv4/IPv6] M: "David S. Miller" <davem@davemloft.net> M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> +M: David Ahern <dsahern@kernel.org> L: netdev@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -12539,6 +12540,14 @@ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: net/nfc/ +NFC VIRTUAL NCI DEVICE DRIVER +M: Bongsu Jeon <bongsu.jeon@samsung.com> +L: netdev@vger.kernel.org +L: linux-nfc@lists.01.org (moderated for non-subscribers) +S: Supported +F: drivers/nfc/virtual_ncidev.c +F: tools/testing/selftests/nci/ + NFS, SUNRPC, AND LOCKD CLIENTS M: Trond Myklebust <trond.myklebust@hammerspace.com> M: Anna Schumaker <anna.schumaker@netapp.com> @@ -12850,6 +12859,7 @@ F: drivers/net/dsa/ocelot/* F: drivers/net/ethernet/mscc/ F: include/soc/mscc/ocelot* F: net/dsa/tag_ocelot.c +F: net/dsa/tag_ocelot_8021q.c F: tools/testing/selftests/drivers/net/ocelot/* OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER @@ -14527,10 +14537,18 @@ S: Supported F: drivers/crypto/qat/ QCOM AUDIO (ASoC) DRIVERS -M: Patrick Lai <plai@codeaurora.org> +M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> M: Banajit Goswami <bgoswami@codeaurora.org> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported +F: sound/soc/codecs/lpass-va-macro.c +F: sound/soc/codecs/lpass-wsa-macro.* +F: sound/soc/codecs/msm8916-wcd-analog.c +F: sound/soc/codecs/msm8916-wcd-digital.c +F: sound/soc/codecs/wcd9335.* +F: sound/soc/codecs/wcd934x.c +F: sound/soc/codecs/wcd-clsh-v2.* +F: sound/soc/codecs/wsa881x.c F: sound/soc/qcom/ QCOM IPA DRIVER @@ -16982,7 +17000,7 @@ M: Olivier Moysan <olivier.moysan@st.com> M: Arnaud Pouliquen <arnaud.pouliquen@st.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained -F: Documentation/devicetree/bindings/sound/st,stm32-*.txt +F: Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml F: sound/soc/stm/ STM32 TIMER/LPTIMER DRIVERS @@ -18435,7 +18453,7 @@ F: Documentation/usb/ohci.rst F: drivers/usb/host/ohci* USB OTG FSM (Finite State Machine) -M: Peter Chen <Peter.Chen@nxp.com> +M: Peter Chen <peter.chen@kernel.org> L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 11 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index 8452753efebe..31927d2fe297 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -15,7 +15,8 @@ static int node_offset(void *fdt, const char *node_path) { int offset = fdt_path_offset(fdt, node_path); if (offset == -FDT_ERR_NOTFOUND) - offset = fdt_add_subnode(fdt, 0, node_path); + /* Add the node to root if not found, dropping the leading '/' */ + offset = fdt_add_subnode(fdt, 0, node_path + 1); return offset; } diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts index 861e05d53157..343364d3e4f7 100644 --- a/arch/arm/boot/dts/imx6q-tbs2910.dts +++ b/arch/arm/boot/dts/imx6q-tbs2910.dts @@ -16,6 +16,13 @@ stdout-path = &uart1; }; + aliases { + mmc0 = &usdhc2; + mmc1 = &usdhc3; + mmc2 = &usdhc4; + /delete-property/ mmc3; + }; + memory@10000000 { device_type = "memory"; reg = <0x10000000 0x80000000>; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 736074f1c3ef..959d8ac2e393 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -418,7 +418,7 @@ /* VDD_AUD_1P8: Audio codec */ reg_aud_1p8v: ldo3 { - regulator-name = "vdd1p8"; + regulator-name = "vdd1p8a"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-boot-on; diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index d6df598bd1c2..b167b33bd108 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -137,7 +137,7 @@ lcd_backlight: lcd-backlight { compatible = "pwm-backlight"; - pwms = <&pwm4 0 5000000>; + pwms = <&pwm4 0 5000000 0>; pwm-names = "LCD_BKLT_PWM"; brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>; @@ -167,7 +167,7 @@ i2c-gpio,delay-us = <2>; /* ~100 kHz */ #address-cells = <1>; #size-cells = <0>; - status = "disabld"; + status = "disabled"; }; i2c_cam: i2c-gpio-cam { @@ -179,7 +179,7 @@ i2c-gpio,delay-us = <2>; /* ~100 kHz */ #address-cells = <1>; #size-cells = <0>; - status = "disabld"; + status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-sr-som.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi index b06577808ff4..7e4e5fd0143a 100644 --- a/arch/arm/boot/dts/imx6qdl-sr-som.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi @@ -53,7 +53,6 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_microsom_enet_ar8035>; - phy-handle = <&phy>; phy-mode = "rgmii-id"; phy-reset-duration = <2>; phy-reset-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; @@ -63,10 +62,19 @@ #address-cells = <1>; #size-cells = <0>; - phy: ethernet-phy@0 { + /* + * The PHY can appear at either address 0 or 4 due to the + * configuration (LED) pin not being pulled sufficiently. + */ + ethernet-phy@0 { reg = <0>; qca,clk-out-frequency = <125000000>; }; + + ethernet-phy@4 { + reg = <4>; + qca,clk-out-frequency = <125000000>; + }; }; }; diff --git a/arch/arm/boot/dts/imx7d-flex-concentrator.dts b/arch/arm/boot/dts/imx7d-flex-concentrator.dts index 84b095279e65..bd6b5285aa8d 100644 --- a/arch/arm/boot/dts/imx7d-flex-concentrator.dts +++ b/arch/arm/boot/dts/imx7d-flex-concentrator.dts @@ -115,6 +115,7 @@ compatible = "nxp,pcf2127"; reg = <0>; spi-max-frequency = <2000000>; + reset-source; }; }; diff --git a/arch/arm/boot/dts/ste-db8500.dtsi b/arch/arm/boot/dts/ste-db8500.dtsi index d309fad32229..344d29853bf7 100644 --- a/arch/arm/boot/dts/ste-db8500.dtsi +++ b/arch/arm/boot/dts/ste-db8500.dtsi @@ -12,4 +12,42 @@ 200000 0>; }; }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + /* Modem trace memory */ + ram@06000000 { + reg = <0x06000000 0x00f00000>; + no-map; + }; + + /* Modem shared memory */ + ram@06f00000 { + reg = <0x06f00000 0x00100000>; + no-map; + }; + + /* Modem private memory */ + ram@07000000 { + reg = <0x07000000 0x01000000>; + no-map; + }; + + /* + * Initial Secure Software ISSW memory + * + * This is probably only used if the kernel tries + * to actually call into trustzone to run secure + * applications, which the mainline kernel probably + * will not do on this old chipset. But you can never + * be too careful, so reserve this memory anyway. + */ + ram@17f00000 { + reg = <0x17f00000 0x00100000>; + no-map; + }; + }; }; diff --git a/arch/arm/boot/dts/ste-db8520.dtsi b/arch/arm/boot/dts/ste-db8520.dtsi index 48bd8728ae27..287804e9e183 100644 --- a/arch/arm/boot/dts/ste-db8520.dtsi +++ b/arch/arm/boot/dts/ste-db8520.dtsi @@ -12,4 +12,42 @@ 200000 0>; }; }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + /* Modem trace memory */ + ram@06000000 { + reg = <0x06000000 0x00f00000>; + no-map; + }; + + /* Modem shared memory */ + ram@06f00000 { + reg = <0x06f00000 0x00100000>; + no-map; + }; + + /* Modem private memory */ + ram@07000000 { + reg = <0x07000000 0x01000000>; + no-map; + }; + + /* + * Initial Secure Software ISSW memory + * + * This is probably only used if the kernel tries + * to actually call into trustzone to run secure + * applications, which the mainline kernel probably + * will not do on this old chipset. But you can never + * be too careful, so reserve this memory anyway. + */ + ram@17f00000 { + reg = <0x17f00000 0x00100000>; + no-map; + }; + }; }; diff --git a/arch/arm/boot/dts/ste-db9500.dtsi b/arch/arm/boot/dts/ste-db9500.dtsi new file mode 100644 index 000000000000..0afff703191c --- /dev/null +++ b/arch/arm/boot/dts/ste-db9500.dtsi @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "ste-dbx5x0.dtsi" + +/ { + cpus { + cpu@300 { + /* cpufreq controls */ + operating-points = <1152000 0 + 800000 0 + 400000 0 + 200000 0>; + }; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + /* + * Initial Secure Software ISSW memory + * + * This is probably only used if the kernel tries + * to actually call into trustzone to run secure + * applications, which the mainline kernel probably + * will not do on this old chipset. But you can never + * be too careful, so reserve this memory anyway. + */ + ram@17f00000 { + reg = <0x17f00000 0x00100000>; + no-map; + }; + }; +}; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index be90e73c923e..27d8a07718a0 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -4,7 +4,7 @@ */ /dts-v1/; -#include "ste-db8500.dtsi" +#include "ste-db9500.dtsi" #include "ste-href-ab8500.dtsi" #include "ste-href-family-pinctrl.dtsi" diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 1eabf2d2834b..e06f946b75b9 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -67,6 +67,7 @@ #define MX6Q_CCM_CCR 0x0 .align 3 + .arm .macro sync_l2_cache diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi index aef8f2b00778..5401a646c840 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi @@ -4,11 +4,16 @@ */ usb { compatible = "simple-bus"; - dma-ranges; #address-cells = <2>; #size-cells = <2>; ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>; + /* + * Internally, USB bus to the interconnect can only address up + * to 40-bit + */ + dma-ranges = <0 0 0 0 0x100 0x0>; + usbphy0: usb-phy@0 { compatible = "brcm,sr-usb-combo-phy"; reg = <0x0 0x00000000 0x0 0x100>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 60ff19fa53b4..6c8a61c2cc74 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -101,7 +101,7 @@ reboot { compatible ="syscon-reboot"; regmap = <&rst>; - offset = <0xb0>; + offset = <0>; mask = <0x02>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index ee1790230490..2a79e89f821e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -253,7 +253,7 @@ #size-cells = <1>; ranges; - spba: bus@30000000 { + spba: spba-bus@30000000 { compatible = "fsl,spba-bus", "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index ecccfbb4f5ad..23f5a5e37167 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -266,7 +266,7 @@ #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; - gpio-ranges = <&iomuxc 0 56 26>, <&iomuxc 0 144 4>; + gpio-ranges = <&iomuxc 0 56 26>, <&iomuxc 26 144 4>; }; gpio4: gpio@30230000 { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 838301650a79..a0bcf0201261 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -991,8 +991,6 @@ CONFIG_ARCH_TEGRA_210_SOC=y CONFIG_ARCH_TEGRA_186_SOC=y CONFIG_ARCH_TEGRA_194_SOC=y CONFIG_ARCH_TEGRA_234_SOC=y -CONFIG_ARCH_K3_AM6_SOC=y -CONFIG_ARCH_K3_J721E_SOC=y CONFIG_TI_SCI_PM_DOMAINS=y CONFIG_EXTCON_PTN5150=m CONFIG_EXTCON_USB_GPIO=y diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 18fce223b67b..99d7e1494aaa 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -247,9 +247,11 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts at the bottom of the virtual address space. + * Check whether an arbitrary address is within the linear map, which + * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the + * kernel's TTBR1 address range. */ -#define __is_lm_address(addr) (((u64)(addr) & ~PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) +#define __is_lm_address(addr) (((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 89c64ada8732..66aac2881ba8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -352,8 +352,8 @@ kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) unsigned long addr = instruction_pointer(regs); struct kprobe *cur = kprobe_running(); - if (cur && (kcb->kprobe_status == KPROBE_HIT_SS) - && ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { kprobes_restore_local_irqflag(kcb, regs); post_kprobe_handler(cur, kcb, regs); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 04c44853b103..fe60d25c000e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1396,8 +1396,9 @@ static void cpu_init_hyp_mode(void) * Calculate the raw per-cpu offset without a translation from the * kernel's mapping to the linear mapping, and store it in tpidr_el2 * so that we can use adr_l to access per-cpu variables in EL2. + * Also drop the KASAN tag which gets in the way... */ - params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) - + params->tpidr_el2 = (unsigned long)kasan_reset_tag(this_cpu_ptr_nvhe_sym(__per_cpu_start)) - (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); params->mair_el2 = read_sysreg(mair_el1); diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index e3947846ffcb..8e7128cb7667 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -77,12 +77,6 @@ static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3)); } -static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt) -{ - psci_forward(host_ctxt); - hyp_panic(); /* unreachable */ -} - static unsigned int find_cpu_id(u64 mpidr) { unsigned int i; @@ -251,10 +245,13 @@ static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ case PSCI_0_2_FN_MIGRATE_INFO_TYPE: case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: return psci_forward(host_ctxt); + /* + * SYSTEM_OFF/RESET should not return according to the spec. + * Allow it so as to stay robust to broken firmware. + */ case PSCI_0_2_FN_SYSTEM_OFF: case PSCI_0_2_FN_SYSTEM_RESET: - psci_forward_noreturn(host_ctxt); - unreachable(); + return psci_forward(host_ctxt); case PSCI_0_2_FN64_CPU_SUSPEND: return psci_cpu_suspend(func_id, host_ctxt); case PSCI_0_2_FN64_CPU_ON: diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 4ad66a532e38..247422ac78a9 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -788,7 +788,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; - int base, i; + int base, i, nr_events; if (!pmceid1) { val = read_sysreg(pmceid0_el0); @@ -801,13 +801,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) if (!bmap) return val; + nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1; + for (i = 0; i < 32; i += 8) { u64 byte; byte = bitmap_get_value8(bmap, base + i); mask |= byte << i; - byte = bitmap_get_value8(bmap, 0x4000 + base + i); - mask |= byte << (32 + i); + if (nr_events >= (0x4000 + base + 32)) { + byte = bitmap_get_value8(bmap, 0x4000 + base + i); + mask |= byte << (32 + i); + } } return val & mask; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 42ccc27fb684..7c4f79532406 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -43,6 +43,10 @@ * 64bit interface. */ +#define reg_to_encoding(x) \ + sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ + (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) + static bool read_from_write_only(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) @@ -273,8 +277,7 @@ static bool trap_loregion(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 sr = reg_to_encoding(r); if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) { kvm_inject_undefined(vcpu); @@ -590,6 +593,15 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1); } +static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + if (kvm_vcpu_has_pmu(vcpu)) + return 0; + + return REG_HIDDEN; +} + static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; @@ -613,9 +625,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) { u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0); - bool enabled = kvm_vcpu_has_pmu(vcpu); + bool enabled = (reg & flags) || vcpu_mode_priv(vcpu); - enabled &= (reg & flags) || vcpu_mode_priv(vcpu); if (!enabled) kvm_inject_undefined(vcpu); @@ -900,11 +911,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (!kvm_vcpu_has_pmu(vcpu)) { - kvm_inject_undefined(vcpu); - return false; - } - if (p->is_write) { if (!vcpu_mode_priv(vcpu)) { kvm_inject_undefined(vcpu); @@ -921,10 +927,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -#define reg_to_encoding(x) \ - sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ - (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) - /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ @@ -936,15 +938,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } +#define PMU_SYS_REG(r) \ + SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility + /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ - { SYS_DESC(SYS_PMEVCNTRn_EL0(n)), \ - access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), } + { PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)), \ + .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ #define PMU_PMEVTYPER_EL0(n) \ - { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ - access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } + { PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)), \ + .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), } static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -1020,8 +1025,7 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r, bool raz) { - u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 id = reg_to_encoding(r); u64 val = raz ? 0 : read_sanitised_ftr_reg(id); if (id == SYS_ID_AA64PFR0_EL1) { @@ -1062,8 +1066,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, static unsigned int id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 id = reg_to_encoding(r); switch (id) { case SYS_ID_AA64ZFR0_EL1: @@ -1486,8 +1489,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, - { SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, - { SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, + { PMU_SYS_REG(SYS_PMINTENSET_EL1), + .access = access_pminten, .reg = PMINTENSET_EL1 }, + { PMU_SYS_REG(SYS_PMINTENCLR_EL1), + .access = access_pminten, .reg = PMINTENSET_EL1 }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, @@ -1526,23 +1531,36 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, - { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, - { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, - { SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 }, - { SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 }, - { SYS_DESC(SYS_PMCEID0_EL0), access_pmceid }, - { SYS_DESC(SYS_PMCEID1_EL0), access_pmceid }, - { SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 }, - { SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper }, - { SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr }, + { PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, + .reset = reset_pmcr, .reg = PMCR_EL0 }, + { PMU_SYS_REG(SYS_PMCNTENSET_EL0), + .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + { PMU_SYS_REG(SYS_PMCNTENCLR_EL0), + .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + { PMU_SYS_REG(SYS_PMOVSCLR_EL0), + .access = access_pmovs, .reg = PMOVSSET_EL0 }, + { PMU_SYS_REG(SYS_PMSWINC_EL0), + .access = access_pmswinc, .reg = PMSWINC_EL0 }, + { PMU_SYS_REG(SYS_PMSELR_EL0), + .access = access_pmselr, .reg = PMSELR_EL0 }, + { PMU_SYS_REG(SYS_PMCEID0_EL0), + .access = access_pmceid, .reset = NULL }, + { PMU_SYS_REG(SYS_PMCEID1_EL0), + .access = access_pmceid, .reset = NULL }, + { PMU_SYS_REG(SYS_PMCCNTR_EL0), + .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 }, + { PMU_SYS_REG(SYS_PMXEVTYPER_EL0), + .access = access_pmu_evtyper, .reset = NULL }, + { PMU_SYS_REG(SYS_PMXEVCNTR_EL0), + .access = access_pmu_evcntr, .reset = NULL }, /* * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ - { SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 }, - { SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, + { PMU_SYS_REG(SYS_PMUSERENR_EL0), .access = access_pmuserenr, + .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 }, + { PMU_SYS_REG(SYS_PMOVSSET_EL0), + .access = access_pmovs, .reg = PMOVSSET_EL0 }, { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, @@ -1694,7 +1712,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ - { SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 }, + { PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper, + .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 }, { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3c40da479899..35d75c60e2b8 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -709,10 +709,11 @@ static int do_tag_check_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { /* - * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN for tag - * check faults. Mask them out now so that userspace doesn't see them. + * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN + * for tag check faults. Set them to corresponding bits in the untagged + * address. */ - far &= (1UL << 60) - 1; + far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index d69c979936d4..5d90307fd6e0 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -54,7 +54,7 @@ extern void ia64_xchg_called_with_bad_pointer(void); }) #define xchg(ptr, x) \ -((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)))) +({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ed9fc3d057a6..43e8050145be 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -171,29 +171,34 @@ void vtime_account_hardirq(struct task_struct *tsk) static irqreturn_t timer_interrupt (int irq, void *dev_id) { - unsigned long cur_itm, new_itm, ticks; + unsigned long new_itm; if (cpu_is_offline(smp_processor_id())) { return IRQ_HANDLED; } new_itm = local_cpu_data->itm_next; - cur_itm = ia64_get_itc(); - if (!time_after(cur_itm, new_itm)) { + if (!time_after(ia64_get_itc(), new_itm)) printk(KERN_ERR "Oops: timer tick before it's due (itc=%lx,itm=%lx)\n", - cur_itm, new_itm); - ticks = 1; - } else { - ticks = DIV_ROUND_UP(cur_itm - new_itm, - local_cpu_data->itm_delta); - new_itm += ticks * local_cpu_data->itm_delta; - } + ia64_get_itc(), new_itm); + + while (1) { + new_itm += local_cpu_data->itm_delta; + + legacy_timer_tick(smp_processor_id() == time_keeper_id); - if (smp_processor_id() != time_keeper_id) - ticks = 0; + local_cpu_data->itm_next = new_itm; - legacy_timer_tick(ticks); + if (time_after(new_itm, ia64_get_itc())) + break; + + /* + * Allow IPIs to interrupt the timer loop. + */ + local_irq_enable(); + local_irq_disable(); + } do { /* diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index 19edf8e69971..292d0425717f 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -51,6 +51,7 @@ extern void kmap_flush_tlb(unsigned long addr); #define flush_cache_kmaps() BUG_ON(cpu_has_dc_aliases) +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) set_pte(ptep, ptev) #define arch_kmap_local_post_map(vaddr, pteval) local_flush_tlb_one(vaddr) #define arch_kmap_local_post_unmap(vaddr) local_flush_tlb_one(vaddr) diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index 7d6b4a77b379..c298061c70a7 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -31,7 +31,7 @@ void __iomem *ioremap(phys_addr_t offset, unsigned long size); #define iounmap iounmap -extern void iounmap(void *addr); +extern void iounmap(void __iomem *addr); #include <asm-generic/io.h> diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 5aed97a18bac..daae13a76743 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -77,7 +77,7 @@ void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size) } EXPORT_SYMBOL(ioremap); -void iounmap(void *addr) +void iounmap(void __iomem *addr) { /* If the page is from the fixmap pool then we just clear out * the fixmap mapping. diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 78b17621ee4a..278462186ac4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -202,9 +202,8 @@ config PREFETCH depends on PA8X00 || PA7200 config MLONGCALLS - bool "Enable the -mlong-calls compiler option for big kernels" - default y if !MODULES || UBSAN || FTRACE - default n + def_bool y if !MODULES || UBSAN || FTRACE + bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE depends on PA8X00 help If you configure the kernel to include many drivers built-in instead diff --git a/arch/parisc/include/asm/irq.h b/arch/parisc/include/asm/irq.h index 959e79cd2c14..378f63c4015b 100644 --- a/arch/parisc/include/asm/irq.h +++ b/arch/parisc/include/asm/irq.h @@ -47,7 +47,4 @@ extern unsigned long txn_affinity_addr(unsigned int irq, int cpu); extern int cpu_claim_irq(unsigned int irq, struct irq_chip *, void *); extern int cpu_check_affinity(struct irq_data *d, const struct cpumask *dest); -/* soft power switch support (power.c) */ -extern struct tasklet_struct power_tasklet; - #endif /* _ASM_PARISC_IRQ_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index beba9816cc6c..4d37cc9cba37 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -997,10 +997,17 @@ intr_do_preempt: bb,<,n %r20, 31 - PSW_SM_I, intr_restore nop + /* ssm PSW_SM_I done later in intr_restore */ +#ifdef CONFIG_MLONGCALLS + ldil L%intr_restore, %r2 + load32 preempt_schedule_irq, %r1 + bv %r0(%r1) + ldo R%intr_restore(%r2), %r2 +#else + ldil L%intr_restore, %r1 BL preempt_schedule_irq, %r2 - nop - - b,n intr_restore /* ssm PSW_SM_I done by intr_restore */ + ldo R%intr_restore(%r1), %r2 +#endif #endif /* CONFIG_PREEMPTION */ /* diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 1d32b174ab6a..c1a8aac01cf9 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -63,6 +63,12 @@ nop; \ nop; +#define SCV_ENTRY_FLUSH_SLOT \ + SCV_ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ @@ -71,6 +77,13 @@ ENTRY_FLUSH_SLOT /* + * r10, ctr must be free to use, r13 must be paca + */ +#define SCV_INTERRUPT_TO_KERNEL \ + STF_ENTRY_BARRIER_SLOT; \ + SCV_ENTRY_FLUSH_SLOT + +/* * Macros for annotating the expected destination of (h)rfid * * The nop instructions allow us to insert one or more instructions to flush the diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index f6d2acb57425..ac605fc369c4 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -240,6 +240,14 @@ label##3: \ FTR_ENTRY_OFFSET 957b-958b; \ .popsection; +#define SCV_ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __scv_entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -273,10 +281,12 @@ label##3: \ extern long stf_barrier_fallback; extern long entry_flush_fallback; +extern long scv_entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; +extern long __start___scv_entry_flush_fixup, __stop___scv_entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 80a5ae771c65..c0fcd1bbdba9 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -58,6 +58,8 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + __set_pte_at(mm, vaddr, ptep, ptev, 1) #define arch_kmap_local_post_map(vaddr, pteval) \ local_flush_tlb_page(NULL, vaddr) #define arch_kmap_local_post_unmap(vaddr) \ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index aa1af139d947..33ddfeef4fe9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -75,7 +75,7 @@ BEGIN_FTR_SECTION bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - INTERRUPT_TO_KERNEL + SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e02ad6fefa46..6e53f7638737 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2993,6 +2993,25 @@ TRAMP_REAL_BEGIN(entry_flush_fallback) ld r11,PACA_EXRFI+EX_R11(r13) blr +/* + * The SCV entry flush happens with interrupts enabled, so it must disable + * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10 + * (containing LR) does not need to be preserved here because scv entry + * puts 0 in the pt_regs, CTR can be clobbered for the same reason. + */ +TRAMP_REAL_BEGIN(scv_entry_flush_fallback) + li r10,0 + mtmsrd r10,1 + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,PACA_IRQ_HARD_DIS + stb r10,PACAIRQHAPPENED(r13) + std r11,PACA_EXRFI+EX_R11(r13) + L1D_DISPLACEMENT_FLUSH + ld r11,PACA_EXRFI+EX_R11(r13) + li r10,MSR_RI + mtmsrd r10,1 + blr + TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 6b1eca53e36c..cc7a6271b6b4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -180,13 +180,18 @@ void notrace restore_interrupts(void) void replay_soft_interrupts(void) { + struct pt_regs regs; + /* - * We use local_paca rather than get_paca() to avoid all - * the debug_smp_processor_id() business in this low level - * function + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. */ - unsigned char happened = local_paca->irq_happened; - struct pt_regs regs; ppc_save_regs(®s); regs.softe = IRQS_ENABLED; @@ -209,7 +214,7 @@ again: * This is a higher priority interrupt than the others, so * replay it first. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { local_paca->irq_happened &= ~PACA_IRQ_HMI; regs.trap = 0xe60; handle_hmi_exception(®s); @@ -217,7 +222,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_DEC) { + if (local_paca->irq_happened & PACA_IRQ_DEC) { local_paca->irq_happened &= ~PACA_IRQ_DEC; regs.trap = 0x900; timer_interrupt(®s); @@ -225,7 +230,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_EE) { + if (local_paca->irq_happened & PACA_IRQ_EE) { local_paca->irq_happened &= ~PACA_IRQ_EE; regs.trap = 0x500; do_IRQ(®s); @@ -233,7 +238,7 @@ again: hard_irq_disable(); } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) { + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (IS_ENABLED(CONFIG_PPC_BOOK3E)) regs.trap = 0x280; @@ -245,7 +250,7 @@ again: } /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { local_paca->irq_happened &= ~PACA_IRQ_PMI; regs.trap = 0xf00; performance_monitor_exception(®s); @@ -253,8 +258,7 @@ again: hard_irq_disable(); } - happened = local_paca->irq_happened; - if (happened & ~PACA_IRQ_HARD_DIS) { + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { /* * We are responding to the next interrupt, so interrupt-off * latencies should be reset here. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 4ab426b8b0e0..72fa3c00229a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -146,6 +146,13 @@ SECTIONS } . = ALIGN(8); + __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) { + __start___scv_entry_flush_fixup = .; + *(__scv_entry_flush_fixup) + __stop___scv_entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 47821055b94c..1fd31b4b0e13 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -290,9 +290,6 @@ void do_entry_flush_fixups(enum l1d_flush_type types) long *start, *end; int i; - start = PTRRELOC(&__start___entry_flush_fixup); - end = PTRRELOC(&__stop___entry_flush_fixup); - instrs[0] = 0x60000000; /* nop */ instrs[1] = 0x60000000; /* nop */ instrs[2] = 0x60000000; /* nop */ @@ -312,6 +309,8 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { dest = (void *)start + *start; @@ -328,6 +327,25 @@ void do_entry_flush_fixups(enum l1d_flush_type types) patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); } + start = PTRRELOC(&__start___scv_entry_flush_fixup); + end = PTRRELOC(&__stop___scv_entry_flush_fixup); + for (; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, (types == L1D_FLUSH_NONE) ? "no" : (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7cd4993f4ff2..f9f9568d689e 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -196,7 +196,7 @@ void __init setup_bootmem(void) max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index a15c033f53ca..87641dd65ccf 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -35,7 +35,7 @@ void uv_query_info(void) uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len; uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE); uv_info.max_num_sec_conf = uvcb.max_num_sec_conf; - uv_info.max_guest_cpus = uvcb.max_guest_cpus; + uv_info.max_guest_cpu_id = uvcb.max_guest_cpu_id; } #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0325fc0469b7..7b98d4caee77 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -96,7 +96,7 @@ struct uv_cb_qui { u32 max_num_sec_conf; u64 max_guest_stor_addr; u8 reserved88[158 - 136]; - u16 max_guest_cpus; + u16 max_guest_cpu_id; u8 reserveda0[200 - 160]; } __packed __aligned(8); @@ -273,7 +273,7 @@ struct uv_info { unsigned long guest_cpu_stor_len; unsigned long max_sec_stor_addr; unsigned int max_num_sec_conf; - unsigned short max_guest_cpus; + unsigned short max_guest_cpu_id; }; extern struct uv_info uv_info; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 883bfed9f5c2..b2d2ad153067 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -368,7 +368,7 @@ static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return scnprintf(page, PAGE_SIZE, "%d\n", - uv_info.max_guest_cpus); + uv_info.max_guest_cpu_id + 1); } static struct kobj_attribute uv_query_max_guest_cpus_attr = diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5fa580219a86..52646f52f130 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -29,7 +29,6 @@ config SUPERH select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DYNAMIC_FTRACE diff --git a/arch/sh/boards/mach-sh03/rtc.c b/arch/sh/boards/mach-sh03/rtc.c index 8b23ed7c201c..7fb474844a2d 100644 --- a/arch/sh/boards/mach-sh03/rtc.c +++ b/arch/sh/boards/mach-sh03/rtc.c @@ -11,7 +11,6 @@ #include <linux/sched.h> #include <linux/time.h> #include <linux/bcd.h> -#include <linux/rtc.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/rtc.h> diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig index ba6ec042606f..e6c5ddf070c0 100644 --- a/arch/sh/configs/landisk_defconfig +++ b/arch/sh/configs/landisk_defconfig @@ -27,13 +27,12 @@ CONFIG_NETFILTER=y CONFIG_ATALK=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_OFFBOARD=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_AEC62XX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_ATP867X=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y CONFIG_MD=y CONFIG_BLK_DEV_MD=m diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig index c65667d00313..e9825196dd66 100644 --- a/arch/sh/configs/microdev_defconfig +++ b/arch/sh/configs/microdev_defconfig @@ -20,8 +20,6 @@ CONFIG_IP_PNP=y # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_SMC91X=y diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig index d10a0414123a..d00376eb044f 100644 --- a/arch/sh/configs/sdk7780_defconfig +++ b/arch/sh/configs/sdk7780_defconfig @@ -44,16 +44,14 @@ CONFIG_NET_SCHED=y CONFIG_PARPORT=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y -CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_SPI_ATTRS=y CONFIG_SCSI_FC_ATTRS=y CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_PLATFORM=y CONFIG_MD=y CONFIG_BLK_DEV_DM=y CONFIG_NETDEVICES=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 61bec46ebd66..4a44cac640bc 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -116,9 +116,6 @@ CONFIG_MTD_UBI_GLUEBI=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig index 3f1c13799d79..4defc7628a49 100644 --- a/arch/sh/configs/se7750_defconfig +++ b/arch/sh/configs/se7750_defconfig @@ -29,7 +29,6 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_ROM=y -CONFIG_IDE=y CONFIG_SCSI=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index f0073ed39947..48b457d59e79 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -39,9 +39,6 @@ CONFIG_IP_PNP_RARP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=m -CONFIG_BLK_DEV_IDETAPE=m CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig index d0de378beefe..7d54f284ce10 100644 --- a/arch/sh/drivers/dma/Kconfig +++ b/arch/sh/drivers/dma/Kconfig @@ -63,8 +63,7 @@ config PVR2_DMA config G2_DMA tristate "G2 Bus DMA support" - depends on SH_DREAMCAST - select SH_DMA_API + depends on SH_DREAMCAST && SH_DMA_API help This enables support for the DMA controller for the Dreamcast's G2 bus. Drivers that want this will generally enable this on diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h index 351918894e86..d643250f0a0f 100644 --- a/arch/sh/include/asm/gpio.h +++ b/arch/sh/include/asm/gpio.h @@ -16,7 +16,6 @@ #include <cpu/gpio.h> #endif -#define ARCH_NR_GPIOS 512 #include <asm-generic/gpio.h> #ifdef CONFIG_GPIOLIB diff --git a/arch/sh/kernel/cpu/sh3/entry.S b/arch/sh/kernel/cpu/sh3/entry.S index 25eb80905416..e48b3dd996f5 100644 --- a/arch/sh/kernel/cpu/sh3/entry.S +++ b/arch/sh/kernel/cpu/sh3/entry.S @@ -14,7 +14,6 @@ #include <cpu/mmu_context.h> #include <asm/page.h> #include <asm/cache.h> -#include <asm/thread_info.h> ! NOTE: ! GNU as (as of 2.9.1) changes bf/s into bt/s and bra, when the address diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 703d3069997c..77aa2f802d8d 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -105,7 +105,7 @@ config VSYSCALL (the default value) say Y. config NUMA - bool "Non Uniform Memory Access (NUMA) Support" + bool "Non-Uniform Memory Access (NUMA) Support" depends on MMU && SYS_SUPPORTS_NUMA select ARCH_WANT_NUMA_VARIABLE_LOCALITY default n diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c index 4c1ca197e9c5..d16d6f5ec774 100644 --- a/arch/sh/mm/asids-debugfs.c +++ b/arch/sh/mm/asids-debugfs.c @@ -26,7 +26,7 @@ #include <asm/processor.h> #include <asm/mmu_context.h> -static int asids_seq_show(struct seq_file *file, void *iter) +static int asids_debugfs_show(struct seq_file *file, void *iter) { struct task_struct *p; @@ -48,18 +48,7 @@ static int asids_seq_show(struct seq_file *file, void *iter) return 0; } -static int asids_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, asids_seq_show, inode->i_private); -} - -static const struct file_operations asids_debugfs_fops = { - .owner = THIS_MODULE, - .open = asids_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(asids_debugfs); static int __init asids_debugfs_init(void) { diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 17d780794497..b0f185169dfa 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -22,7 +22,7 @@ enum cache_type { CACHE_TYPE_UNIFIED, }; -static int cache_seq_show(struct seq_file *file, void *iter) +static int cache_debugfs_show(struct seq_file *file, void *iter) { unsigned int cache_type = (unsigned int)file->private; struct cache_info *cache; @@ -94,18 +94,7 @@ static int cache_seq_show(struct seq_file *file, void *iter) return 0; } -static int cache_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, cache_seq_show, inode->i_private); -} - -static const struct file_operations cache_debugfs_fops = { - .owner = THIS_MODULE, - .open = cache_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(cache_debugfs); static int __init cache_debugfs_init(void) { diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c index b20aba6e1b37..68eb7cc6e564 100644 --- a/arch/sh/mm/pmb.c +++ b/arch/sh/mm/pmb.c @@ -812,7 +812,7 @@ bool __in_29bit_mode(void) return (__raw_readl(PMB_PASCR) & PASCR_SE) == 0; } -static int pmb_seq_show(struct seq_file *file, void *iter) +static int pmb_debugfs_show(struct seq_file *file, void *iter) { int i; @@ -846,18 +846,7 @@ static int pmb_seq_show(struct seq_file *file, void *iter) return 0; } -static int pmb_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmb_seq_show, NULL); -} - -static const struct file_operations pmb_debugfs_fops = { - .owner = THIS_MODULE, - .open = pmb_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmb_debugfs); static int __init pmb_debugfs_init(void) { diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h index 875116209ec1..c7b2e208328b 100644 --- a/arch/sparc/include/asm/highmem.h +++ b/arch/sparc/include/asm/highmem.h @@ -50,10 +50,11 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() -/* FIXME: Use __flush_tlb_one(vaddr) instead of flush_cache_all() -- Anton */ -#define arch_kmap_local_post_map(vaddr, pteval) flush_cache_all() -#define arch_kmap_local_post_unmap(vaddr) flush_cache_all() - +/* FIXME: Use __flush_*_one(vaddr) instead of flush_*_all() -- Anton */ +#define arch_kmap_local_pre_map(vaddr, pteval) flush_cache_all() +#define arch_kmap_local_pre_unmap(vaddr) flush_cache_all() +#define arch_kmap_local_post_map(vaddr, pteval) flush_tlb_all() +#define arch_kmap_local_post_unmap(vaddr) flush_tlb_all() #endif /* __KERNEL__ */ diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 18d8f17f755c..0904f5676e4d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, unsigned int nr) { if (likely(nr < IA32_NR_syscalls)) { - instrumentation_begin(); nr = array_index_nospec(nr, IA32_NR_syscalls); regs->ax = ia32_sys_call_table[nr](regs); - instrumentation_end(); } } @@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) * or may not be necessary, but it matches the old asm behavior. */ nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); } @@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) res = get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp); } - instrumentation_end(); if (res) { /* User code screwed up. */ regs->ax = -EFAULT; + + instrumentation_end(); syscall_exit_to_user_mode(regs); return false; } @@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); return true; } diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index ccd32877a3c4..496b11ec469d 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -10,7 +10,7 @@ #include <asm/export.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro THUNK name, func, put_ret_addr_in_rdi=0 + .macro THUNK name, func SYM_FUNC_START_NOALIGN(\name) pushq %rbp movq %rsp, %rbp @@ -25,13 +25,8 @@ SYM_FUNC_START_NOALIGN(\name) pushq %r10 pushq %r11 - .if \put_ret_addr_in_rdi - /* 8(%rbp) is return addr on stack */ - movq 8(%rbp), %rdi - .endif - call \func - jmp .L_restore + jmp __thunk_restore SYM_FUNC_END(\name) _ASM_NOKPROBE(\name) .endm @@ -44,7 +39,7 @@ SYM_FUNC_END(\name) #endif #ifdef CONFIG_PREEMPTION -SYM_CODE_START_LOCAL_NOALIGN(.L_restore) +SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) popq %r11 popq %r10 popq %r9 @@ -56,6 +51,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.L_restore) popq %rdi popq %rbp ret - _ASM_NOKPROBE(.L_restore) -SYM_CODE_END(.L_restore) + _ASM_NOKPROBE(__thunk_restore) +SYM_CODE_END(__thunk_restore) #endif diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a5aba4ab0224..67a4f1cb2aac 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,14 +16,25 @@ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. - * If you intend to use the FPU in softirq you need to check first with + * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ -extern void kernel_fpu_begin(void); + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. * A context switch will (and softirq might) save CPU's FPU registers to diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 247a60a47331..f656aabd1545 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -613,6 +613,7 @@ DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); #ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); +DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); #endif /* Device interrupts common/spurious */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5e658ba2654a..9abe842dbd84 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -97,6 +97,7 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 +#define INTEL_FAM6_ALDERLAKE_L 0x9A /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 0b4920a7238e..e16cccdd0420 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 488a8e848754..9239399e5491 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +extern unsigned int __max_die_per_package; + #ifdef CONFIG_SMP #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) @@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_logical_packages; #define topology_max_packages() (__max_logical_packages) -extern unsigned int __max_die_per_package; - static inline int topology_max_die_per_package(void) { return __max_die_per_package; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f8ca66f3d861..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 13d3f1cbda17..e133ce1e562b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } @@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 1068002c8532..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..3412c4595efd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -661,17 +661,6 @@ static void __init trim_platform_memory_ranges(void) static void __init trim_bios_range(void) { /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - * - * This typically reserves additional memory (64KiB by default) - * since some BIOSes are known to corrupt low memory. See the - * Kconfig help text for X86_RESERVE_LOW. - */ - e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); - - /* * special case: Some BIOSes report the PC BIOS * area (640Kb -> 1Mb) as RAM even though it is not. * take them out. @@ -728,6 +717,15 @@ early_param("reservelow", parse_reservelow); static void __init trim_low_memory_range(void) { + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0bd1a0fc587e..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8ca66af96a54..117e24fbfd8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -2083,6 +2084,23 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2109,6 +2127,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready) if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index f15bc16de07c..a889563ad02d 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,31 +9,6 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) -static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - -static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -43,7 +18,6 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu, \ unsigned long val) \ { \ vcpu->arch.regs[VCPU_REGS_##uname] = val; \ - kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname); \ } BUILD_KVM_GPR_ACCESSORS(rax, RAX) BUILD_KVM_GPR_ACCESSORS(rbx, RBX) @@ -63,6 +37,31 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) { if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 581925e476d6..261be1d2032b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,8 +44,15 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 -static inline u64 rsvd_bits(int s, int e) +static __always_inline u64 rsvd_bits(int s, int e) { + BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s); + + if (__builtin_constant_p(e)) + BUILD_BUG_ON(e > 63); + else + e &= 63; + if (e < s) return 0; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index cb4c6ee10029..7a605ad8254d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -200,6 +200,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (WARN_ON(!is_guest_mode(vcpu))) + return true; + if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c8ffdbc81709..ac652bc476ae 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1415,16 +1415,13 @@ static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) * to be returned: * GPRs RAX, RBX, RCX, RDX * - * Copy their values to the GHCB if they are dirty. + * Copy their values, even if they may not have been written during the + * VM-Exit. It's the guest's responsibility to not consume random data. */ - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX)) - ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX)) - ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX)) - ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX)) - ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); + ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); + ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); + ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); + ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); } static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7ef171790d02..f923e14e87df 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3739,6 +3739,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + trace_kvm_entry(vcpu); + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0fbb46990dfc..f2b9bfb58206 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3124,13 +3124,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_host_map *map; - struct page *page; - u64 hpa; /* * hv_evmcs may end up being not mapped after migration (when @@ -3153,6 +3149,17 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) } } + return true; +} + +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_host_map *map; + struct page *page; + u64 hpa; + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3221,6 +3228,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + + return true; +} + +static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) +{ + if (!nested_get_evmcs_page(vcpu)) + return false; + + if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) + return false; + return true; } @@ -6077,11 +6096,14 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (vmx->nested.hv_evmcs) - copy_enlightened_to_vmcs12(vmx); - else if (enable_shadow_vmcs) - copy_shadow_to_vmcs12(vmx); + } else { + copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); + if (!vmx->nested.need_vmcs12_to_shadow_sync) { + if (vmx->nested.hv_evmcs) + copy_enlightened_to_vmcs12(vmx); + else if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + } } BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE); @@ -6602,7 +6624,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .hv_timer_pending = nested_vmx_preemption_timer_pending, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, - .get_nested_state_pages = nested_get_vmcs12_pages, + .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index a886a47daebd..cdf5f34518f4 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = { [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, }; /* mapping between fixed pmc index and intel_arch_events array */ @@ -345,7 +345,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, x86_pmu.num_counters_gp); + eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; + eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len); pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -355,6 +357,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, x86_pmu.num_counters_fixed); + edx.split.bit_width_fixed = min_t(int, + edx.split.bit_width_fixed, x86_pmu.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2af05d3b0590..cc60b1fc3ee7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6653,6 +6653,8 @@ reenter_guest: if (vmx->emulation_required) return EXIT_FASTPATH_NONE; + trace_kvm_entry(vcpu); + if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; vmcs_write32(PLE_WINDOW, vmx->ple_window); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9a8969a6dd06..76bce832cade 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -105,6 +105,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); +static void process_smi(struct kvm_vcpu *vcpu); static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); @@ -4230,6 +4231,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { process_nmi(vcpu); + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); + /* * In guest mode, payload delivery should be deferred, * so that the L1 hypervisor can intercept #PF before @@ -8802,9 +8806,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { - if (WARN_ON_ONCE(!is_guest_mode(vcpu))) - ; - else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { + if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; goto out; } @@ -8988,8 +8990,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops.request_immediate_exit(vcpu); } - trace_kvm_entry(vcpu); - fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); @@ -11556,6 +11556,7 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 4321fa02e18d..419365c48b2a 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -26,6 +26,16 @@ #include <asm/fpu/api.h> #include <asm/asm.h> +/* + * Use KFPU_387. MMX instructions are not affected by MXCSR, + * but both AMD and Intel documentation states that even integer MMX + * operations will result in #MF if an exception is pending in FCW. + * + * EMMS is not needed afterwards because, after calling kernel_fpu_end(), + * any subsequent user of the 387 stack will reinitialize it using + * KFPU_387. + */ + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) p = to; i = len >> 6; /* len/64 */ - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" /* This set is 28 bytes */ @@ -127,7 +137,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); /* * maybe the prefetch stuff can go before the expensive fnsave... @@ -247,7 +257,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 4409306364dc..9a5a50cdaab5 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -583,6 +583,13 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_debug) exc_debug(regs); } +DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap) +{ + /* This should never happen and there is no way to handle it. */ + pr_err("Unknown trap in Xen PV mode."); + BUG(); +} + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -631,6 +638,7 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) { unsigned int nr; bool ist_okay = false; + bool found = false; /* * Replace trap handler addresses by Xen specific ones. @@ -645,6 +653,7 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) if (*addr == entry->orig) { *addr = entry->xen; ist_okay = entry->ist_okay; + found = true; break; } } @@ -655,9 +664,13 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) nr = (*addr - (void *)early_idt_handler_array[0]) / EARLY_IDT_HANDLER_SIZE; *addr = (void *)xen_early_idt_handler_array[nr]; + found = true; } - if (WARN_ON(ist != 0 && !ist_okay)) + if (!found) + *addr = (void *)xen_asm_exc_xen_unknown_trap; + + if (WARN_ON(found && ist != 0 && !ist_okay)) return false; return true; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1cb0e84b9161..53cf8aa35032 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -178,6 +178,7 @@ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION xen_pv_trap entry_INT80_compat #endif +xen_pv_trap asm_exc_xen_unknown_trap xen_pv_trap asm_exc_xen_hypervisor_callback __INIT diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 031114d454a6..4221a1539391 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1016,6 +1016,8 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css) */ void blkcg_destroy_blkgs(struct blkcg *blkcg) { + might_sleep(); + spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { @@ -1023,14 +1025,20 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg) struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; - if (spin_trylock(&q->queue_lock)) { - blkg_destroy(blkg); - spin_unlock(&q->queue_lock); - } else { + if (need_resched() || !spin_trylock(&q->queue_lock)) { + /* + * Given that the system can accumulate a huge number + * of blkgs in pathological cases, check to see if we + * need to rescheduling to avoid softlockup. + */ spin_unlock_irq(&blkcg->lock); - cpu_relax(); + cond_resched(); spin_lock_irq(&blkcg->lock); + continue; } + + blkg_destroy(blkg); + spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); diff --git a/block/blk-mq.h b/block/blk-mq.h index c1458d9502f1..3616453ca28c 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -304,7 +304,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags)) + if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return true; users = atomic_read(&set->active_queues_shared_sbitmap); } else { diff --git a/block/genhd.c b/block/genhd.c index 419548e92d82..9e741a4f351b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -45,10 +45,11 @@ static void disk_release_events(struct gendisk *disk); void set_capacity(struct gendisk *disk, sector_t sectors) { struct block_device *bdev = disk->part0; + unsigned long flags; - spin_lock(&bdev->bd_size_lock); + spin_lock_irqsave(&bdev->bd_size_lock, flags); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - spin_unlock(&bdev->bd_size_lock); + spin_unlock_irqrestore(&bdev->bd_size_lock, flags); } EXPORT_SYMBOL(set_capacity); diff --git a/block/partitions/core.c b/block/partitions/core.c index e7d776db803b..4601a845cd79 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -88,9 +88,11 @@ static int (*check_part[])(struct parsed_partitions *) = { static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) { - spin_lock(&bdev->bd_size_lock); + unsigned long flags; + + spin_lock_irqsave(&bdev->bd_size_lock, flags); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - spin_unlock(&bdev->bd_size_lock); + spin_unlock_irqrestore(&bdev->bd_size_lock, flags); } static struct parsed_partitions *allocate_partitions(struct gendisk *hd) @@ -384,7 +386,7 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, err = blk_alloc_devt(bdev, &devt); if (err) - goto out_bdput; + goto out_put; pdev->devt = devt; /* delay uevent until 'holders' subdir is created */ diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index d4eac6d7e9fb..2494138a6905 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1107,6 +1107,11 @@ static int nc_dma_get_range(struct device *dev, u64 *size) ncomp = (struct acpi_iort_named_component *)node->node_data; + if (!ncomp->memory_address_limit) { + pr_warn(FW_BUG "Named component missing memory address limit\n"); + return -EINVAL; + } + *size = ncomp->memory_address_limit >= 64 ? U64_MAX : 1ULL<<ncomp->memory_address_limit; @@ -1126,6 +1131,11 @@ static int rc_dma_get_range(struct device *dev, u64 *size) rc = (struct acpi_iort_root_complex *)node->node_data; + if (!rc->memory_address_limit) { + pr_warn(FW_BUG "Root complex missing memory address limit\n"); + return -EINVAL; + } + *size = rc->memory_address_limit >= 64 ? U64_MAX : 1ULL<<rc->memory_address_limit; @@ -1173,8 +1183,8 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) end = dmaaddr + size - 1; mask = DMA_BIT_MASK(ilog2(end) + 1); dev->bus_dma_limit = end; - dev->coherent_dma_mask = mask; - *dev->dma_mask = mask; + dev->coherent_dma_mask = min(dev->coherent_dma_mask, mask); + *dev->dma_mask = min(*dev->dma_mask, mask); } *dma_addr = dmaaddr; diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index 96869f1538b9..bfca116482b8 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -251,20 +251,12 @@ int __acpi_device_uevent_modalias(struct acpi_device *adev, if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; - len = create_pnp_modalias(adev, &env->buf[env->buflen - 1], - sizeof(env->buf) - env->buflen); - if (len < 0) - return len; - - env->buflen += len; - if (!adev->data.of_compatible) - return 0; - - if (len > 0 && add_uevent_var(env, "MODALIAS=")) - return -ENOMEM; - - len = create_of_modalias(adev, &env->buf[env->buflen - 1], - sizeof(env->buf) - env->buflen); + if (adev->data.of_compatible) + len = create_of_modalias(adev, &env->buf[env->buflen - 1], + sizeof(env->buf) - env->buflen); + else + len = create_pnp_modalias(adev, &env->buf[env->buflen - 1], + sizeof(env->buf) - env->buflen); if (len < 0) return len; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 58ff36340cd7..1db063b02f63 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -586,6 +586,8 @@ static int acpi_get_device_data(acpi_handle handle, struct acpi_device **device, if (!device) return -EINVAL; + *device = NULL; + status = acpi_get_data_full(handle, acpi_scan_drop_device, (void **)device, callback); if (ACPI_FAILURE(status) || !*device) { diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 12c0ece746f0..859b1de31ddc 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -174,6 +174,8 @@ struct acpi_thermal { struct thermal_zone_device *thermal_zone; int kelvin_offset; /* in millidegrees */ struct work_struct thermal_check_work; + struct mutex thermal_check_lock; + refcount_t thermal_check_count; }; /* -------------------------------------------------------------------------- @@ -495,14 +497,6 @@ static int acpi_thermal_get_trip_points(struct acpi_thermal *tz) return 0; } -static void acpi_thermal_check(void *data) -{ - struct acpi_thermal *tz = data; - - thermal_zone_device_update(tz->thermal_zone, - THERMAL_EVENT_UNSPECIFIED); -} - /* sys I/F for generic thermal sysfs support */ static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp) @@ -900,6 +894,12 @@ static void acpi_thermal_unregister_thermal_zone(struct acpi_thermal *tz) Driver Interface -------------------------------------------------------------------------- */ +static void acpi_queue_thermal_check(struct acpi_thermal *tz) +{ + if (!work_pending(&tz->thermal_check_work)) + queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); +} + static void acpi_thermal_notify(struct acpi_device *device, u32 event) { struct acpi_thermal *tz = acpi_driver_data(device); @@ -910,17 +910,17 @@ static void acpi_thermal_notify(struct acpi_device *device, u32 event) switch (event) { case ACPI_THERMAL_NOTIFY_TEMPERATURE: - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); break; case ACPI_THERMAL_NOTIFY_THRESHOLDS: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; case ACPI_THERMAL_NOTIFY_DEVICES: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; @@ -1020,7 +1020,25 @@ static void acpi_thermal_check_fn(struct work_struct *work) { struct acpi_thermal *tz = container_of(work, struct acpi_thermal, thermal_check_work); - acpi_thermal_check(tz); + + /* + * In general, it is not sufficient to check the pending bit, because + * subsequent instances of this function may be queued after one of them + * has started running (e.g. if _TMP sleeps). Avoid bailing out if just + * one of them is running, though, because it may have done the actual + * check some time ago, so allow at least one of them to block on the + * mutex while another one is running the update. + */ + if (!refcount_dec_not_one(&tz->thermal_check_count)) + return; + + mutex_lock(&tz->thermal_check_lock); + + thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED); + + refcount_inc(&tz->thermal_check_count); + + mutex_unlock(&tz->thermal_check_lock); } static int acpi_thermal_add(struct acpi_device *device) @@ -1052,6 +1070,8 @@ static int acpi_thermal_add(struct acpi_device *device) if (result) goto free_memory; + refcount_set(&tz->thermal_check_count, 3); + mutex_init(&tz->thermal_check_lock); INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn); pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device), @@ -1117,7 +1137,7 @@ static int acpi_thermal_resume(struct device *dev) tz->state.active |= tz->trips.active[i].flags.enabled; } - queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); + acpi_queue_thermal_check(tz); return AE_OK; } diff --git a/drivers/base/core.c b/drivers/base/core.c index 14f165816742..6eb4c7a904c5 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -208,6 +208,16 @@ int device_links_read_lock_held(void) #endif #endif /* !CONFIG_SRCU */ +static bool device_is_ancestor(struct device *dev, struct device *target) +{ + while (target->parent) { + target = target->parent; + if (dev == target) + return true; + } + return false; +} + /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. @@ -221,7 +231,12 @@ int device_is_dependent(struct device *dev, void *target) struct device_link *link; int ret; - if (dev == target) + /* + * The "ancestors" check is needed to catch the case when the target + * device has not been completely initialized yet and it is still + * missing from the list of children of its parent device. + */ + if (dev == target || device_is_ancestor(dev, target)) return 1; ret = device_for_each_child(dev, target, device_is_dependent); @@ -456,7 +471,9 @@ static int devlink_add_symlinks(struct device *dev, struct device *con = link->consumer; char *buf; - len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), + strlen(dev_bus_name(con)) + strlen(dev_name(con))); + len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) @@ -470,12 +487,12 @@ static int devlink_add_symlinks(struct device *dev, if (ret) goto err_con; - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); if (ret) goto err_con_dev; - snprintf(buf, len, "supplier:%s", dev_name(sup)); + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); if (ret) goto err_sup_dev; @@ -483,7 +500,7 @@ static int devlink_add_symlinks(struct device *dev, goto out; err_sup_dev: - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); @@ -506,7 +523,9 @@ static void devlink_remove_symlinks(struct device *dev, sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); - len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), + strlen(dev_bus_name(con)) + strlen(dev_name(con))); + len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) { @@ -514,9 +533,9 @@ static void devlink_remove_symlinks(struct device *dev, return; } - snprintf(buf, len, "supplier:%s", dev_name(sup)); + snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); sysfs_remove_link(&con->kobj, buf); - snprintf(buf, len, "consumer:%s", dev_name(con)); + snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); kfree(buf); } @@ -737,8 +756,9 @@ struct device_link *device_link_add(struct device *consumer, link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); - dev_set_name(&link->link_dev, "%s--%s", - dev_name(supplier), dev_name(consumer)); + dev_set_name(&link->link_dev, "%s:%s--%s:%s", + dev_bus_name(supplier), dev_name(supplier), + dev_bus_name(consumer), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(consumer); put_device(supplier); @@ -1808,9 +1828,7 @@ const char *dev_driver_string(const struct device *dev) * never change once they are set, so they don't need special care. */ drv = READ_ONCE(dev->driver); - return drv ? drv->name : - (dev->bus ? dev->bus->name : - (dev->class ? dev->class->name : "")); + return drv ? drv->name : dev_bus_name(dev); } EXPORT_SYMBOL(dev_driver_string); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 2f32f38a11ed..9179825ff646 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -371,13 +371,6 @@ static void driver_bound(struct device *dev) device_pm_check_callbacks(dev); /* - * Reorder successfully probed devices to the end of the device list. - * This ensures that suspend/resume order matches probe order, which - * is usually what drivers rely on. - */ - device_pm_move_to_tail(dev); - - /* * Make sure the device is no longer in one of the deferred lists and * kick off retrying all pending devices */ @@ -619,6 +612,8 @@ dev_groups_failed: else if (drv->remove) drv->remove(dev); probe_failed: + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 95fd1549f87d..8456d8384ac8 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -366,6 +366,8 @@ int devm_platform_get_irqs_affinity(struct platform_device *dev, return -ERANGE; nvec = platform_irq_count(dev); + if (nvec < 0) + return nvec; if (nvec < minvec) return -ENOSPC; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 6727358e147d..e6ea5d344f87 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1022,6 +1022,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, if (!sock) return err; + /* + * We need to make sure we don't get any errant requests while we're + * reallocating the ->socks array. + */ + blk_mq_freeze_queue(nbd->disk->queue); + if (!netlink && !nbd->task_setup && !test_bit(NBD_RT_BOUND, &config->runtime_flags)) nbd->task_setup = current; @@ -1060,10 +1066,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, nsock->cookie = 0; socks[config->num_connections++] = nsock; atomic_inc(&config->live_connections); + blk_mq_unfreeze_queue(nbd->disk->queue); return 0; put_socket: + blk_mq_unfreeze_queue(nbd->disk->queue); sockfd_put(sock); return err; } diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index 148b871f263b..fce0a54df0e5 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -6,7 +6,10 @@ #define CREATE_TRACE_POINTS #include "trace.h" -#define MB_TO_SECTS(mb) (((sector_t)mb * SZ_1M) >> SECTOR_SHIFT) +static inline sector_t mb_to_sects(unsigned long mb) +{ + return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT; +} static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect) { @@ -77,12 +80,11 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) return -EINVAL; } - zone_capacity_sects = MB_TO_SECTS(dev->zone_capacity); - dev_capacity_sects = MB_TO_SECTS(dev->size); - dev->zone_size_sects = MB_TO_SECTS(dev->zone_size); - dev->nr_zones = dev_capacity_sects >> ilog2(dev->zone_size_sects); - if (dev_capacity_sects & (dev->zone_size_sects - 1)) - dev->nr_zones++; + zone_capacity_sects = mb_to_sects(dev->zone_capacity); + dev_capacity_sects = mb_to_sects(dev->size); + dev->zone_size_sects = mb_to_sects(dev->zone_size); + dev->nr_zones = round_up(dev_capacity_sects, dev->zone_size_sects) + >> ilog2(dev->zone_size_sects); dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct nullb_zone), GFP_KERNEL | __GFP_ZERO); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 5265975b3fba..e1c6798889f4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -945,7 +945,8 @@ static void blkif_set_queue_limits(struct blkfront_info *info) if (info->feature_discard) { blk_queue_flag_set(QUEUE_FLAG_DISCARD, rq); blk_queue_max_discard_sectors(rq, get_capacity(gd)); - rq->limits.discard_granularity = info->discard_granularity; + rq->limits.discard_granularity = info->discard_granularity ?: + info->physical_sector_size; rq->limits.discard_alignment = info->discard_alignment; if (info->feature_secdiscard) blk_queue_flag_set(QUEUE_FLAG_SECERASE, rq); @@ -2179,19 +2180,12 @@ static void blkfront_closing(struct blkfront_info *info) static void blkfront_setup_discard(struct blkfront_info *info) { - int err; - unsigned int discard_granularity; - unsigned int discard_alignment; - info->feature_discard = 1; - err = xenbus_gather(XBT_NIL, info->xbdev->otherend, - "discard-granularity", "%u", &discard_granularity, - "discard-alignment", "%u", &discard_alignment, - NULL); - if (!err) { - info->discard_granularity = discard_granularity; - info->discard_alignment = discard_alignment; - } + info->discard_granularity = xenbus_read_unsigned(info->xbdev->otherend, + "discard-granularity", + 0); + info->discard_alignment = xenbus_read_unsigned(info->xbdev->otherend, + "discard-alignment", 0); info->feature_secdiscard = !!xenbus_read_unsigned(info->xbdev->otherend, "discard-secure", 0); diff --git a/drivers/bus/arm-integrator-lm.c b/drivers/bus/arm-integrator-lm.c index 845b6c43fef8..2344d560b144 100644 --- a/drivers/bus/arm-integrator-lm.c +++ b/drivers/bus/arm-integrator-lm.c @@ -54,6 +54,7 @@ static int integrator_lm_populate(int num, struct device *dev) ret = of_platform_default_populate(child, NULL, dev); if (ret) { dev_err(dev, "failed to populate module\n"); + of_node_put(child); return ret; } } diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index d34d7e90e38d..1202433ecf98 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -260,6 +260,18 @@ int mhi_destroy_device(struct device *dev, void *data) return 0; } +int mhi_get_free_desc_count(struct mhi_device *mhi_dev, + enum dma_data_direction dir) +{ + struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; + struct mhi_chan *mhi_chan = (dir == DMA_TO_DEVICE) ? + mhi_dev->ul_chan : mhi_dev->dl_chan; + struct mhi_ring *tre_ring = &mhi_chan->tre_ring; + + return get_nr_avail_ring_elements(mhi_cntrl, tre_ring); +} +EXPORT_SYMBOL_GPL(mhi_get_free_desc_count); + void mhi_notify(struct mhi_device *mhi_dev, enum mhi_callback cb_reason) { struct mhi_driver *mhi_drv; diff --git a/drivers/clk/imx/Kconfig b/drivers/clk/imx/Kconfig index 3061896503f3..47d9ec3abd2f 100644 --- a/drivers/clk/imx/Kconfig +++ b/drivers/clk/imx/Kconfig @@ -6,8 +6,6 @@ config MXC_CLK config MXC_CLK_SCU tristate - depends on ARCH_MXC - depends on IMX_SCU && HAVE_ARM_SMCCC config CLK_IMX1 def_bool SOC_IMX1 diff --git a/drivers/clk/mmp/clk-audio.c b/drivers/clk/mmp/clk-audio.c index eea69d498bd2..7aa7f4a9564f 100644 --- a/drivers/clk/mmp/clk-audio.c +++ b/drivers/clk/mmp/clk-audio.c @@ -392,7 +392,8 @@ static int mmp2_audio_clk_remove(struct platform_device *pdev) return 0; } -static int __maybe_unused mmp2_audio_clk_suspend(struct device *dev) +#ifdef CONFIG_PM +static int mmp2_audio_clk_suspend(struct device *dev) { struct mmp2_audio_clk *priv = dev_get_drvdata(dev); @@ -404,7 +405,7 @@ static int __maybe_unused mmp2_audio_clk_suspend(struct device *dev) return 0; } -static int __maybe_unused mmp2_audio_clk_resume(struct device *dev) +static int mmp2_audio_clk_resume(struct device *dev) { struct mmp2_audio_clk *priv = dev_get_drvdata(dev); @@ -415,6 +416,7 @@ static int __maybe_unused mmp2_audio_clk_resume(struct device *dev) return 0; } +#endif static const struct dev_pm_ops mmp2_audio_clk_pm_ops = { SET_RUNTIME_PM_OPS(mmp2_audio_clk_suspend, mmp2_audio_clk_resume, NULL) diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c index d82d725ac231..b05901b24917 100644 --- a/drivers/clk/qcom/gcc-sc7180.c +++ b/drivers/clk/qcom/gcc-sc7180.c @@ -891,21 +891,6 @@ static struct clk_branch gcc_boot_rom_ahb_clk = { }, }; -static struct clk_branch gcc_camera_ahb_clk = { - .halt_reg = 0xb008, - .halt_check = BRANCH_HALT, - .hwcg_reg = 0xb008, - .hwcg_bit = 1, - .clkr = { - .enable_reg = 0xb008, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_camera_ahb_clk", - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_camera_hf_axi_clk = { .halt_reg = 0xb020, .halt_check = BRANCH_HALT, @@ -2317,7 +2302,6 @@ static struct clk_regmap *gcc_sc7180_clocks[] = { [GCC_AGGRE_UFS_PHY_AXI_CLK] = &gcc_aggre_ufs_phy_axi_clk.clkr, [GCC_AGGRE_USB3_PRIM_AXI_CLK] = &gcc_aggre_usb3_prim_axi_clk.clkr, [GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr, - [GCC_CAMERA_AHB_CLK] = &gcc_camera_ahb_clk.clkr, [GCC_CAMERA_HF_AXI_CLK] = &gcc_camera_hf_axi_clk.clkr, [GCC_CAMERA_THROTTLE_HF_AXI_CLK] = &gcc_camera_throttle_hf_axi_clk.clkr, [GCC_CAMERA_XO_CLK] = &gcc_camera_xo_clk.clkr, @@ -2519,11 +2503,12 @@ static int gcc_sc7180_probe(struct platform_device *pdev) /* * Keep the clocks always-ON - * GCC_CPUSS_GNOC_CLK, GCC_VIDEO_AHB_CLK, GCC_DISP_AHB_CLK - * GCC_GPU_CFG_AHB_CLK + * GCC_CPUSS_GNOC_CLK, GCC_VIDEO_AHB_CLK, GCC_CAMERA_AHB_CLK, + * GCC_DISP_AHB_CLK, GCC_GPU_CFG_AHB_CLK */ regmap_update_bits(regmap, 0x48004, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x0b004, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b008, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x0b00c, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); diff --git a/drivers/clk/qcom/gcc-sm8250.c b/drivers/clk/qcom/gcc-sm8250.c index 6cb6617b8d88..ab594a0f0c40 100644 --- a/drivers/clk/qcom/gcc-sm8250.c +++ b/drivers/clk/qcom/gcc-sm8250.c @@ -722,7 +722,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parent_data_4, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; @@ -745,7 +745,7 @@ static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { .name = "gcc_sdcc4_apps_clk_src", .parent_data = gcc_parent_data_0, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index a60aee1a1a29..65df9ef5b5bc 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -235,36 +235,6 @@ static ssize_t ti_eqep_position_ceiling_write(struct counter_device *counter, return len; } -static ssize_t ti_eqep_position_floor_read(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, char *buf) -{ - struct ti_eqep_cnt *priv = counter->priv; - u32 qposinit; - - regmap_read(priv->regmap32, QPOSINIT, &qposinit); - - return sprintf(buf, "%u\n", qposinit); -} - -static ssize_t ti_eqep_position_floor_write(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, const char *buf, - size_t len) -{ - struct ti_eqep_cnt *priv = counter->priv; - int err; - u32 res; - - err = kstrtouint(buf, 0, &res); - if (err < 0) - return err; - - regmap_write(priv->regmap32, QPOSINIT, res); - - return len; -} - static ssize_t ti_eqep_position_enable_read(struct counter_device *counter, struct counter_count *count, void *ext_priv, char *buf) @@ -302,11 +272,6 @@ static struct counter_count_ext ti_eqep_position_ext[] = { .write = ti_eqep_position_ceiling_write, }, { - .name = "floor", - .read = ti_eqep_position_floor_read, - .write = ti_eqep_position_floor_write, - }, - { .name = "enable", .read = ti_eqep_position_enable_read, .write = ti_eqep_position_enable_write, diff --git a/drivers/crypto/marvell/cesa/cesa.h b/drivers/crypto/marvell/cesa/cesa.h index fabfaaccca87..fa56b45620c7 100644 --- a/drivers/crypto/marvell/cesa/cesa.h +++ b/drivers/crypto/marvell/cesa/cesa.h @@ -300,11 +300,11 @@ struct mv_cesa_tdma_desc { __le32 byte_cnt; union { __le32 src; - dma_addr_t src_dma; + u32 src_dma; }; union { __le32 dst; - dma_addr_t dst_dma; + u32 dst_dma; }; __le32 next_dma; diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c index 34f53d898acb..e1926483ae2f 100644 --- a/drivers/firmware/efi/apple-properties.c +++ b/drivers/firmware/efi/apple-properties.c @@ -3,8 +3,9 @@ * apple-properties.c - EFI device properties on Macs * Copyright (C) 2016 Lukas Wunner <lukas@wunner.de> * - * Note, all properties are considered as u8 arrays. - * To get a value of any of them the caller must use device_property_read_u8_array(). + * Properties are stored either as: + * u8 arrays which can be retrieved with device_property_read_u8_array() or + * booleans which can be queried with device_property_present(). */ #define pr_fmt(fmt) "apple-properties: " fmt @@ -88,8 +89,12 @@ static void __init unmarshal_key_value_pairs(struct dev_header *dev_header, entry_data = ptr + key_len + sizeof(val_len); entry_len = val_len - sizeof(val_len); - entry[i] = PROPERTY_ENTRY_U8_ARRAY_LEN(key, entry_data, - entry_len); + if (entry_len) + entry[i] = PROPERTY_ENTRY_U8_ARRAY_LEN(key, entry_data, + entry_len); + else + entry[i] = PROPERTY_ENTRY_BOOL(key); + if (dump_properties) { dev_info(dev, "property: %s\n", key); print_hex_dump(KERN_INFO, pr_fmt(), DUMP_PREFIX_OFFSET, diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 1d2e5b85d7ca..c027d99f2a59 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -13,6 +13,7 @@ config IMX_DSP config IMX_SCU bool "IMX SCU Protocol driver" depends on IMX_MBOX + select SOC_BUS help The System Controller Firmware (SCFW) is a low-level system function which runs on a dedicated Cortex-M core to provide power, clock, and diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index c70f46e80a3b..dea65d85594f 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -521,7 +521,8 @@ config GPIO_SAMA5D2_PIOBU config GPIO_SIFIVE bool "SiFive GPIO support" - depends on OF_GPIO && IRQ_DOMAIN_HIERARCHY + depends on OF_GPIO + select IRQ_DOMAIN_HIERARCHY select GPIO_GENERIC select GPIOLIB_IRQCHIP select REGMAP_MMIO @@ -597,6 +598,8 @@ config GPIO_TEGRA default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST depends on OF_GPIO + select GPIOLIB_IRQCHIP + select IRQ_DOMAIN_HIERARCHY help Say yes here to support GPIO pins on NVIDIA Tegra SoCs. diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 672681a976f5..a912a8fed197 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -676,20 +676,17 @@ static void mvebu_pwm_get_state(struct pwm_chip *chip, else state->duty_cycle = 1; + val = (unsigned long long) u; /* on duration */ regmap_read(mvpwm->regs, mvebu_pwmreg_blink_off_duration(mvpwm), &u); - val = (unsigned long long) u * NSEC_PER_SEC; + val += (unsigned long long) u; /* period = on + off duration */ + val *= NSEC_PER_SEC; do_div(val, mvpwm->clk_rate); - if (val < state->duty_cycle) { + if (val > UINT_MAX) + state->period = UINT_MAX; + else if (val) + state->period = val; + else state->period = 1; - } else { - val -= state->duty_cycle; - if (val > UINT_MAX) - state->period = UINT_MAX; - else if (val) - state->period = val; - else - state->period = 1; - } regmap_read(mvchip->regs, GPIO_BLINK_EN_OFF + mvchip->offset, &u); if (u) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 12b679ca552c..1a7b51163528 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1979,6 +1979,21 @@ struct gpio_chardev_data { #endif }; +static int chipinfo_get(struct gpio_chardev_data *cdev, void __user *ip) +{ + struct gpio_device *gdev = cdev->gdev; + struct gpiochip_info chipinfo; + + memset(&chipinfo, 0, sizeof(chipinfo)); + + strscpy(chipinfo.name, dev_name(&gdev->dev), sizeof(chipinfo.name)); + strscpy(chipinfo.label, gdev->label, sizeof(chipinfo.label)); + chipinfo.lines = gdev->ngpio; + if (copy_to_user(ip, &chipinfo, sizeof(chipinfo))) + return -EFAULT; + return 0; +} + #ifdef CONFIG_GPIO_CDEV_V1 /* * returns 0 if the versions match, else the previously selected ABI version @@ -1993,6 +2008,41 @@ static int lineinfo_ensure_abi_version(struct gpio_chardev_data *cdata, return abiv; } + +static int lineinfo_get_v1(struct gpio_chardev_data *cdev, void __user *ip, + bool watch) +{ + struct gpio_desc *desc; + struct gpioline_info lineinfo; + struct gpio_v2_line_info lineinfo_v2; + + if (copy_from_user(&lineinfo, ip, sizeof(lineinfo))) + return -EFAULT; + + /* this doubles as a range check on line_offset */ + desc = gpiochip_get_desc(cdev->gdev->chip, lineinfo.line_offset); + if (IS_ERR(desc)) + return PTR_ERR(desc); + + if (watch) { + if (lineinfo_ensure_abi_version(cdev, 1)) + return -EPERM; + + if (test_and_set_bit(lineinfo.line_offset, cdev->watched_lines)) + return -EBUSY; + } + + gpio_desc_to_lineinfo(desc, &lineinfo_v2); + gpio_v2_line_info_to_v1(&lineinfo_v2, &lineinfo); + + if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) { + if (watch) + clear_bit(lineinfo.line_offset, cdev->watched_lines); + return -EFAULT; + } + + return 0; +} #endif static int lineinfo_get(struct gpio_chardev_data *cdev, void __user *ip, @@ -2030,6 +2080,22 @@ static int lineinfo_get(struct gpio_chardev_data *cdev, void __user *ip, return 0; } +static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip) +{ + __u32 offset; + + if (copy_from_user(&offset, ip, sizeof(offset))) + return -EFAULT; + + if (offset >= cdev->gdev->ngpio) + return -EINVAL; + + if (!test_and_clear_bit(offset, cdev->watched_lines)) + return -EBUSY; + + return 0; +} + /* * gpio_ioctl() - ioctl handler for the GPIO chardev */ @@ -2037,80 +2103,24 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; - struct gpio_chip *gc = gdev->chip; void __user *ip = (void __user *)arg; - __u32 offset; /* We fail any subsequent ioctl():s when the chip is gone */ - if (!gc) + if (!gdev->chip) return -ENODEV; /* Fill in the struct and pass to userspace */ if (cmd == GPIO_GET_CHIPINFO_IOCTL) { - struct gpiochip_info chipinfo; - - memset(&chipinfo, 0, sizeof(chipinfo)); - - strscpy(chipinfo.name, dev_name(&gdev->dev), - sizeof(chipinfo.name)); - strscpy(chipinfo.label, gdev->label, - sizeof(chipinfo.label)); - chipinfo.lines = gdev->ngpio; - if (copy_to_user(ip, &chipinfo, sizeof(chipinfo))) - return -EFAULT; - return 0; + return chipinfo_get(cdev, ip); #ifdef CONFIG_GPIO_CDEV_V1 - } else if (cmd == GPIO_GET_LINEINFO_IOCTL) { - struct gpio_desc *desc; - struct gpioline_info lineinfo; - struct gpio_v2_line_info lineinfo_v2; - - if (copy_from_user(&lineinfo, ip, sizeof(lineinfo))) - return -EFAULT; - - /* this doubles as a range check on line_offset */ - desc = gpiochip_get_desc(gc, lineinfo.line_offset); - if (IS_ERR(desc)) - return PTR_ERR(desc); - - gpio_desc_to_lineinfo(desc, &lineinfo_v2); - gpio_v2_line_info_to_v1(&lineinfo_v2, &lineinfo); - - if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) - return -EFAULT; - return 0; } else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) { return linehandle_create(gdev, ip); } else if (cmd == GPIO_GET_LINEEVENT_IOCTL) { return lineevent_create(gdev, ip); - } else if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL) { - struct gpio_desc *desc; - struct gpioline_info lineinfo; - struct gpio_v2_line_info lineinfo_v2; - - if (copy_from_user(&lineinfo, ip, sizeof(lineinfo))) - return -EFAULT; - - /* this doubles as a range check on line_offset */ - desc = gpiochip_get_desc(gc, lineinfo.line_offset); - if (IS_ERR(desc)) - return PTR_ERR(desc); - - if (lineinfo_ensure_abi_version(cdev, 1)) - return -EPERM; - - if (test_and_set_bit(lineinfo.line_offset, cdev->watched_lines)) - return -EBUSY; - - gpio_desc_to_lineinfo(desc, &lineinfo_v2); - gpio_v2_line_info_to_v1(&lineinfo_v2, &lineinfo); - - if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) { - clear_bit(lineinfo.line_offset, cdev->watched_lines); - return -EFAULT; - } - - return 0; + } else if (cmd == GPIO_GET_LINEINFO_IOCTL || + cmd == GPIO_GET_LINEINFO_WATCH_IOCTL) { + return lineinfo_get_v1(cdev, ip, + cmd == GPIO_GET_LINEINFO_WATCH_IOCTL); #endif /* CONFIG_GPIO_CDEV_V1 */ } else if (cmd == GPIO_V2_GET_LINEINFO_IOCTL || cmd == GPIO_V2_GET_LINEINFO_WATCH_IOCTL) { @@ -2119,16 +2129,7 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } else if (cmd == GPIO_V2_GET_LINE_IOCTL) { return linereq_create(gdev, ip); } else if (cmd == GPIO_GET_LINEINFO_UNWATCH_IOCTL) { - if (copy_from_user(&offset, ip, sizeof(offset))) - return -EFAULT; - - if (offset >= cdev->gdev->ngpio) - return -EINVAL; - - if (!test_and_clear_bit(offset, cdev->watched_lines)) - return -EBUSY; - - return 0; + return lineinfo_unwatch(cdev, ip); } return -EINVAL; } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index b02cc2abd3b6..b78a634cca24 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1489,6 +1489,9 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, type = IRQ_TYPE_NONE; } + if (gc->to_irq) + chip_warn(gc, "to_irq is redefined in %s and you shouldn't rely on it\n", __func__); + gc->to_irq = gpiochip_to_irq; gc->irq.default_type = type; gc->irq.lock_key = lock_key; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 087afab67e22..cab1ebaf6d62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -81,7 +81,6 @@ MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/vangogh_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 619d34c041ee..346963e3cf73 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -119,6 +119,8 @@ #define mmVGT_ESGS_RING_SIZE_Vangogh_BASE_IDX 1 #define mmSPI_CONFIG_CNTL_Vangogh 0x2440 #define mmSPI_CONFIG_CNTL_Vangogh_BASE_IDX 1 +#define mmGCR_GENERAL_CNTL_Vangogh 0x1580 +#define mmGCR_GENERAL_CNTL_Vangogh_BASE_IDX 0 #define mmCP_HYP_PFP_UCODE_ADDR 0x5814 #define mmCP_HYP_PFP_UCODE_ADDR_BASE_IDX 1 @@ -3244,7 +3246,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000142), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c index 07104a1de308..1961745e89c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c @@ -491,12 +491,11 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev, { uint32_t def, data, def1, data1; - def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG); + def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL); def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2); if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) { - data |= MM_ATC_L2_MISC_CG__ENABLE_MASK; - + data &= ~MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK; data1 &= ~(DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK | @@ -505,8 +504,7 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev, DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK); } else { - data &= ~MM_ATC_L2_MISC_CG__ENABLE_MASK; - + data |= MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK; data1 |= (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK | @@ -516,7 +514,7 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev, } if (def != data) - WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data); + WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL, data); if (def1 != data1) WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2, data1); } @@ -525,17 +523,44 @@ static void mmhub_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev, bool enable) { - uint32_t def, data; - - def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG); - - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) - data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK; - else - data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK; + uint32_t def, data, def1, data1, def2, data2; + + def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL); + def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL); + def2 = data2 = RREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL); + + if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) { + data &= ~MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK; + data1 &= !(DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + data2 &= !(DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + } else { + data |= MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK; + data1 |= (DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + data2 |= (DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK); + } if (def != data) - WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data); + WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL, data); + if (def1 != data1) + WREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL, data1); + if (def2 != data2) + WREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL, data2); } static int mmhub_v2_3_set_clockgating(struct amdgpu_device *adev, @@ -554,26 +579,39 @@ static int mmhub_v2_3_set_clockgating(struct amdgpu_device *adev, static void mmhub_v2_3_get_clockgating(struct amdgpu_device *adev, u32 *flags) { - int data, data1; + int data, data1, data2, data3; if (amdgpu_sriov_vf(adev)) *flags = 0; - data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG); - data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2); + data = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2); + data1 = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL); + data2 = RREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL); + data3 = RREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL); /* AMD_CG_SUPPORT_MC_MGCG */ - if ((data & MM_ATC_L2_MISC_CG__ENABLE_MASK) && - !(data1 & (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | + if (!(data & (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_RDRET_CG_MASK | DAGB0_CNTL_MISC2__DISABLE_TLBWR_CG_MASK | - DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK))) - *flags |= AMD_CG_SUPPORT_MC_MGCG; + DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK)) + && !(data1 & MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK)) { + *flags |= AMD_CG_SUPPORT_MC_MGCG; + } /* AMD_CG_SUPPORT_MC_LS */ - if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK) + if (!(data1 & MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK) + && !(data2 & (DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK)) + && !(data3 & (DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK | + DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK))) *flags |= AMD_CG_SUPPORT_MC_LS; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index 5b466f440d67..ab98c259ef69 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -251,6 +251,7 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base, struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu; bool force_reset = false; bool update_uclk = false; + bool p_state_change_support; if (dc->work_arounds.skip_clock_update || !clk_mgr->smu_present) return; @@ -291,8 +292,9 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base, clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz; clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support; - if (should_update_pstate_support(safe_to_lower, new_clocks->p_state_change_support, clk_mgr_base->clks.p_state_change_support)) { - clk_mgr_base->clks.p_state_change_support = new_clocks->p_state_change_support; + p_state_change_support = new_clocks->p_state_change_support || (display_count == 0); + if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) { + clk_mgr_base->clks.p_state_change_support = p_state_change_support; /* to disable P-State switching, set UCLK min = max */ if (!clk_mgr_base->clks.p_state_change_support) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 1bd1a0935290..f95bade59624 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2399,6 +2399,9 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting initial_link_setting; uint32_t link_bw; + if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap)) + return false; + /* search for the minimum link setting that: * 1. is supported according to the link training result * 2. could support the b/w requested by the timing @@ -3045,14 +3048,14 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link) + pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) core_link_disable_stream(pipe_ctx); } for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off && - pipe_ctx->stream->link == link) + pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe) core_link_enable_stream(link->dc->current_state, pipe_ctx); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index cfc130e2d6fd..017b67b830e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -647,8 +647,13 @@ static void power_on_plane( if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - hws->funcs.dpp_pg_control(hws, plane_id, true); - hws->funcs.hubp_pg_control(hws, plane_id, true); + + if (hws->funcs.dpp_pg_control) + hws->funcs.dpp_pg_control(hws, plane_id, true); + + if (hws->funcs.hubp_pg_control) + hws->funcs.hubp_pg_control(hws, plane_id, true); + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); DC_LOG_DEBUG( @@ -1082,8 +1087,13 @@ void dcn10_plane_atomic_power_down(struct dc *dc, if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - hws->funcs.dpp_pg_control(hws, dpp->inst, false); - hws->funcs.hubp_pg_control(hws, hubp->inst, false); + + if (hws->funcs.dpp_pg_control) + hws->funcs.dpp_pg_control(hws, dpp->inst, false); + + if (hws->funcs.hubp_pg_control) + hws->funcs.hubp_pg_control(hws, hubp->inst, false); + dpp->funcs->dpp_reset(dpp); REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index cb822df21b7c..480d928cb1ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1062,8 +1062,13 @@ static void dcn20_power_on_plane( if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - dcn20_dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true); - dcn20_hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true); + + if (hws->funcs.dpp_pg_control) + hws->funcs.dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true); + + if (hws->funcs.hubp_pg_control) + hws->funcs.hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true); + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); DC_LOG_DEBUG( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index e04ecf0fc0db..5ed18cac57e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -2517,8 +2517,7 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc, * if this primary pipe has a bottom pipe in prev. state * and if the bottom pipe is still available (which it should be), * pick that pipe as secondary - * Same logic applies for ODM pipes. Since mpo is not allowed with odm - * check in else case. + * Same logic applies for ODM pipes */ if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe) { preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe->pipe_idx; @@ -2526,7 +2525,9 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc, secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx]; secondary_pipe->pipe_idx = preferred_pipe_idx; } - } else if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) { + } + if (secondary_pipe == NULL && + dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) { preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe->pipe_idx; if (res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) { secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 1c88d2edd381..b000b43a820d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_banks = 8, .num_chans = 4, .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 23.84, + .dram_clock_change_latency_us = 11.72, .return_bus_width_bytes = 64, .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile index c20331eb62e0..dfd77b3cc84d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile @@ -32,8 +32,8 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \ ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse -CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -msse +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -msse endif ifdef CONFIG_PPC64 @@ -45,6 +45,8 @@ ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) IS_OLD_GCC = 1 endif +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mhard-float +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mhard-float endif ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile index 3ca7d911d25c..09264716d1dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile @@ -14,7 +14,7 @@ DCN301 = dcn301_init.o dcn301_resource.o dcn301_dccg.o \ dcn301_dio_link_encoder.o dcn301_hwseq.o dcn301_panel_cntl.o dcn301_hubbub.o ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mhard-float -msse +CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -msse endif ifdef CONFIG_PPC64 @@ -25,6 +25,7 @@ ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) IS_OLD_GCC = 1 endif +CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o += -mhard-float endif ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile index 8d4924b7dc22..101620a8867a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile @@ -13,7 +13,7 @@ DCN3_02 = dcn302_init.o dcn302_hwseq.o dcn302_resource.o ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mhard-float -msse +CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -msse endif ifdef CONFIG_PPC64 @@ -24,6 +24,7 @@ ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) IS_OLD_GCC = 1 endif +CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o += -mhard-float endif ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h index 4bdbcce7092d..0d797fa9f5cc 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h @@ -553,6 +553,7 @@ struct pptable_funcs { *clock_req); uint32_t (*get_fan_control_mode)(struct smu_context *smu); int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode); + int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed); int (*set_fan_speed_rpm)(struct smu_context *smu, uint32_t speed); int (*set_xgmi_pstate)(struct smu_context *smu, uint32_t pstate); int (*gfx_off_control)(struct smu_context *smu, bool enable); diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h index 13de692a4213..5d0b29653ffa 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h @@ -203,6 +203,9 @@ int smu_v11_0_set_fan_control_mode(struct smu_context *smu, uint32_t mode); +int +smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed); + int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 8b867a6d52b5..e84c737e3967 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2151,19 +2151,14 @@ int smu_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed) int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed) { int ret = 0; - uint32_t rpm; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) return -EOPNOTSUPP; mutex_lock(&smu->mutex); - if (smu->ppt_funcs->set_fan_speed_rpm) { - if (speed > 100) - speed = 100; - rpm = speed * smu->fan_max_rpm / 100; - ret = smu->ppt_funcs->set_fan_speed_rpm(smu, rpm); - } + if (smu->ppt_funcs->set_fan_speed_percent) + ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed); mutex_unlock(&smu->mutex); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index cd7b411457ff..16db0b506b0d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -2326,6 +2326,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .display_clock_voltage_request = smu_v11_0_display_clock_voltage_request, .get_fan_control_mode = smu_v11_0_get_fan_control_mode, .set_fan_control_mode = smu_v11_0_set_fan_control_mode, + .set_fan_speed_percent = smu_v11_0_set_fan_speed_percent, .set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm, .set_xgmi_pstate = smu_v11_0_set_xgmi_pstate, .gfx_off_control = smu_v11_0_gfx_off_control, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 51e83123f72a..cd7efa923195 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2456,6 +2456,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .display_clock_voltage_request = smu_v11_0_display_clock_voltage_request, .get_fan_control_mode = smu_v11_0_get_fan_control_mode, .set_fan_control_mode = smu_v11_0_set_fan_control_mode, + .set_fan_speed_percent = smu_v11_0_set_fan_speed_percent, .set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm, .set_xgmi_pstate = smu_v11_0_set_xgmi_pstate, .gfx_off_control = smu_v11_0_gfx_off_control, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 12b36eb0ff6a..d68d3dfee51d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2802,6 +2802,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .display_clock_voltage_request = smu_v11_0_display_clock_voltage_request, .get_fan_control_mode = smu_v11_0_get_fan_control_mode, .set_fan_control_mode = smu_v11_0_set_fan_control_mode, + .set_fan_speed_percent = smu_v11_0_set_fan_speed_percent, .set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm, .set_xgmi_pstate = smu_v11_0_set_xgmi_pstate, .gfx_off_control = smu_v11_0_gfx_off_control, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index b279dbbbce6b..5aeb5f5a0447 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1174,6 +1174,35 @@ smu_v11_0_set_fan_static_mode(struct smu_context *smu, uint32_t mode) } int +smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t duty100, duty; + uint64_t tmp64; + + if (speed > 100) + speed = 100; + + if (smu_v11_0_auto_fan_control(smu, 0)) + return -EINVAL; + + duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1), + CG_FDO_CTRL1, FMAX_DUTY100); + if (!duty100) + return -EINVAL; + + tmp64 = (uint64_t)speed * duty100; + do_div(tmp64, 100); + duty = (uint32_t)tmp64; + + WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0, + REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0), + CG_FDO_CTRL0, FDO_STATIC_DUTY, duty)); + + return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC); +} + +int smu_v11_0_set_fan_control_mode(struct smu_context *smu, uint32_t mode) { @@ -1181,7 +1210,7 @@ smu_v11_0_set_fan_control_mode(struct smu_context *smu, switch (mode) { case AMD_FAN_CTRL_NONE: - ret = smu_v11_0_set_fan_speed_rpm(smu, smu->fan_max_rpm); + ret = smu_v11_0_set_fan_speed_percent(smu, 100); break; case AMD_FAN_CTRL_MANUAL: ret = smu_v11_0_auto_fan_control(smu, 0); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index f743685a20e8..9a9697038016 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -1121,7 +1121,7 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu, static int renoir_gfx_state_change_set(struct smu_context *smu, uint32_t state) { - return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GpuChangeState, state, NULL); + return 0; } static const struct pptable_funcs renoir_ppt_funcs = { diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index ba1507036f26..4a8cbec832bc 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -3021,7 +3021,7 @@ int drm_atomic_helper_set_config(struct drm_mode_set *set, ret = handle_conflicting_encoders(state, true); if (ret) - return ret; + goto fail; ret = drm_atomic_commit(state); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 02ca22e90290..0b232a73c1b7 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -387,9 +387,16 @@ static int drm_gem_vram_kmap_locked(struct drm_gem_vram_object *gbo, if (gbo->vmap_use_count > 0) goto out; - ret = ttm_bo_vmap(&gbo->bo, &gbo->map); - if (ret) - return ret; + /* + * VRAM helpers unmap the BO only on demand. So the previous + * page mapping might still be around. Only vmap if the there's + * no mapping present. + */ + if (dma_buf_map_is_null(&gbo->map)) { + ret = ttm_bo_vmap(&gbo->bo, &gbo->map); + if (ret) + return ret; + } out: ++gbo->vmap_use_count; @@ -577,6 +584,7 @@ static void drm_gem_vram_bo_driver_move_notify(struct drm_gem_vram_object *gbo, return; ttm_bo_vunmap(bo, &gbo->map); + dma_buf_map_clear(&gbo->map); /* explicitly clear mapping for next vmap call */ } static int drm_gem_vram_bo_driver_move(struct drm_gem_vram_object *gbo, diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 6e74e6745eca..349146049849 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -388,19 +388,18 @@ int drm_syncobj_find_fence(struct drm_file *file_private, return -ENOENT; *fence = drm_syncobj_fence_get(syncobj); - drm_syncobj_put(syncobj); if (*fence) { ret = dma_fence_chain_find_seqno(fence, point); if (!ret) - return 0; + goto out; dma_fence_put(*fence); } else { ret = -EINVAL; } if (!(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)) - return ret; + goto out; memset(&wait, 0, sizeof(wait)); wait.task = current; @@ -432,6 +431,9 @@ int drm_syncobj_find_fence(struct drm_file *file_private, if (wait.node.next) drm_syncobj_remove_wait(syncobj, &wait); +out: + drm_syncobj_put(syncobj); + return ret; } EXPORT_SYMBOL(drm_syncobj_find_fence); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 92940a0c5ef8..bf17365857ca 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2755,12 +2755,11 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, u32 val; ddi_translations = icl_get_mg_buf_trans(encoder, crtc_state, &n_entries); - /* The table does not have values for level 3 and level 9. */ - if (level >= n_entries || level == 3 || level == 9) { + if (level >= n_entries) { drm_dbg_kms(&dev_priv->drm, "DDI translation not found for level %d. Using %d instead.", - level, n_entries - 2); - level = n_entries - 2; + level, n_entries - 1); + level = n_entries - 1; } /* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */ @@ -3725,7 +3724,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, intel_ddi_init_dp_buf_reg(encoder, crtc_state); if (!is_mst) intel_dp_set_power(intel_dp, DP_SET_POWER_D0); - intel_dp_configure_protocol_converter(intel_dp); + intel_dp_configure_protocol_converter(intel_dp, crtc_state); intel_dp_sink_set_decompression_state(intel_dp, crtc_state, true); intel_dp_sink_set_fec_ready(intel_dp, crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 37f1a10fd021..09123e8625c4 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4014,7 +4014,8 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp, intel_de_posting_read(dev_priv, intel_dp->output_reg); } -void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp) +void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *i915 = dp_to_i915(intel_dp); u8 tmp; @@ -4033,8 +4034,8 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp) drm_dbg_kms(&i915->drm, "Failed to set protocol converter HDMI mode to %s\n", enableddisabled(intel_dp->has_hdmi_sink)); - tmp = intel_dp->dfp.ycbcr_444_to_420 ? - DP_CONVERSION_TO_YCBCR420_ENABLE : 0; + tmp = crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444 && + intel_dp->dfp.ycbcr_444_to_420 ? DP_CONVERSION_TO_YCBCR420_ENABLE : 0; if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_PROTOCOL_CONVERTER_CONTROL_1, tmp) != 1) @@ -4088,7 +4089,7 @@ static void intel_enable_dp(struct intel_atomic_state *state, } intel_dp_set_power(intel_dp, DP_SET_POWER_D0); - intel_dp_configure_protocol_converter(intel_dp); + intel_dp_configure_protocol_converter(intel_dp, pipe_config); intel_dp_start_link_train(intel_dp, pipe_config); intel_dp_stop_link_train(intel_dp, pipe_config); diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index b871a09b6901..05f7ddf7a795 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -51,7 +51,8 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp, int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx); void intel_dp_set_power(struct intel_dp *intel_dp, u8 mode); -void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp); +void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state); void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, bool enable); diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index b2a4bbcfdcd2..b9d8825e2bb1 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -2210,6 +2210,7 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, if (content_protection_type_changed) { mutex_lock(&hdcp->mutex); hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED; + drm_connector_get(&connector->base); schedule_work(&hdcp->prop_work); mutex_unlock(&hdcp->mutex); } @@ -2221,6 +2222,14 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, desired_and_not_enabled = hdcp->value != DRM_MODE_CONTENT_PROTECTION_ENABLED; mutex_unlock(&hdcp->mutex); + /* + * If HDCP already ENABLED and CP property is DESIRED, schedule + * prop_work to update correct CP property to user space. + */ + if (!desired_and_not_enabled && !content_protection_type_changed) { + drm_connector_get(&connector->base); + schedule_work(&hdcp->prop_work); + } } if (desired_and_not_enabled || content_protection_type_changed) diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c index 94465374ca2f..e961ad6a3129 100644 --- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c +++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c @@ -390,6 +390,16 @@ static void emit_batch(struct i915_vma * const vma, &cb_kernel_ivb, desc_count); + /* Reset inherited context registers */ + gen7_emit_pipeline_invalidate(&cmds); + batch_add(&cmds, MI_LOAD_REGISTER_IMM(2)); + batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_0_GEN7)); + batch_add(&cmds, 0xffff0000); + batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_1)); + batch_add(&cmds, 0xffff0000 | PIXEL_SUBSPAN_COLLECT_OPT_DISABLE); + gen7_emit_pipeline_flush(&cmds); + + /* Switch to the media pipeline and our base address */ gen7_emit_pipeline_invalidate(&cmds); batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA); batch_add(&cmds, MI_NOOP); @@ -399,9 +409,11 @@ static void emit_batch(struct i915_vma * const vma, gen7_emit_state_base_address(&cmds, descriptors); gen7_emit_pipeline_invalidate(&cmds); + /* Set the clear-residual kernel state */ gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0); gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count); + /* Execute the kernel on all HW threads */ for (i = 0; i < num_primitives(bv); i++) gen7_emit_media_object(&cmds, i); diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index a24cc1ff08a0..0625cbb3b431 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -134,11 +134,6 @@ static bool remove_signaling_context(struct intel_breadcrumbs *b, return true; } -static inline bool __request_completed(const struct i915_request *rq) -{ - return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno); -} - __maybe_unused static bool check_signal_order(struct intel_context *ce, struct i915_request *rq) { @@ -257,7 +252,7 @@ static void signal_irq_work(struct irq_work *work) list_for_each_entry_rcu(rq, &ce->signals, signal_link) { bool release; - if (!__request_completed(rq)) + if (!__i915_request_is_complete(rq)) break; if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, @@ -379,7 +374,7 @@ static void insert_breadcrumb(struct i915_request *rq) * straight onto a signaled list, and queue the irq worker for * its signal completion. */ - if (__request_completed(rq)) { + if (__i915_request_is_complete(rq)) { if (__signal_request(rq) && llist_add(&rq->signal_node, &b->signaled_requests)) irq_work_queue(&b->irq_work); diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index cf94525be2c1..db8c66dde655 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -526,16 +526,39 @@ static int init_ggtt(struct i915_ggtt *ggtt) mutex_init(&ggtt->error_mutex); if (ggtt->mappable_end) { - /* Reserve a mappable slot for our lockless error capture */ - ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, - &ggtt->error_capture, - PAGE_SIZE, 0, - I915_COLOR_UNEVICTABLE, - 0, ggtt->mappable_end, - DRM_MM_INSERT_LOW); - if (ret) - return ret; + /* + * Reserve a mappable slot for our lockless error capture. + * + * We strongly prefer taking address 0x0 in order to protect + * other critical buffers against accidental overwrites, + * as writing to address 0 is a very common mistake. + * + * Since 0 may already be in use by the system (e.g. the BIOS + * framebuffer), we let the reservation fail quietly and hope + * 0 remains reserved always. + * + * If we fail to reserve 0, and then fail to find any space + * for an error-capture, remain silent. We can afford not + * to reserve an error_capture node as we have fallback + * paths, and we trust that 0 will remain reserved. However, + * the only likely reason for failure to insert is a driver + * bug, which we expect to cause other failures... + */ + ggtt->error_capture.size = I915_GTT_PAGE_SIZE; + ggtt->error_capture.color = I915_COLOR_UNEVICTABLE; + if (drm_mm_reserve_node(&ggtt->vm.mm, &ggtt->error_capture)) + drm_mm_insert_node_in_range(&ggtt->vm.mm, + &ggtt->error_capture, + ggtt->error_capture.size, 0, + ggtt->error_capture.color, + 0, ggtt->mappable_end, + DRM_MM_INSERT_LOW); } + if (drm_mm_node_allocated(&ggtt->error_capture)) + drm_dbg(&ggtt->vm.i915->drm, + "Reserved GGTT:[%llx, %llx] for use by error capture\n", + ggtt->error_capture.start, + ggtt->error_capture.start + ggtt->error_capture.size); /* * The upper portion of the GuC address space has a sizeable hole @@ -548,9 +571,9 @@ static int init_ggtt(struct i915_ggtt *ggtt) /* Clear any non-preallocated blocks */ drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) { - drm_dbg_kms(&ggtt->vm.i915->drm, - "clearing unused GTT space: [%lx, %lx]\n", - hole_start, hole_end); + drm_dbg(&ggtt->vm.i915->drm, + "clearing unused GTT space: [%lx, %lx]\n", + hole_start, hole_end); ggtt->vm.clear_range(&ggtt->vm, hole_start, hole_end - hole_start); } diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 7614a3d24fca..26c7d0a50585 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -3988,6 +3988,9 @@ err: static void lrc_destroy_wa_ctx(struct intel_engine_cs *engine) { i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0); + + /* Called on error unwind, clear all flags to prevent further use */ + memset(&engine->wa_ctx, 0, sizeof(engine->wa_ctx)); } typedef u32 *(*wa_bb_func_t)(struct intel_engine_cs *engine, u32 *batch); diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 7ea94d201fe6..8015964043eb 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -126,6 +126,10 @@ static void __rcu_cacheline_free(struct rcu_head *rcu) struct intel_timeline_cacheline *cl = container_of(rcu, typeof(*cl), rcu); + /* Must wait until after all *rq->hwsp are complete before removing */ + i915_gem_object_unpin_map(cl->hwsp->vma->obj); + __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); + i915_active_fini(&cl->active); kfree(cl); } @@ -133,11 +137,6 @@ static void __rcu_cacheline_free(struct rcu_head *rcu) static void __idle_cacheline_free(struct intel_timeline_cacheline *cl) { GEM_BUG_ON(!i915_active_is_idle(&cl->active)); - - i915_gem_object_unpin_map(cl->hwsp->vma->obj); - i915_vma_put(cl->hwsp->vma); - __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); - call_rcu(&cl->rcu, __rcu_cacheline_free); } @@ -179,7 +178,6 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline) return ERR_CAST(vaddr); } - i915_vma_get(hwsp->vma); cl->hwsp = hwsp; cl->vaddr = page_pack_bits(vaddr, cacheline); diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 10a865f3dc09..9ed19b8bca60 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -631,24 +631,26 @@ static int flush_lazy_signals(struct i915_active *ref) int __i915_active_wait(struct i915_active *ref, int state) { - int err; - might_sleep(); - if (!i915_active_acquire_if_busy(ref)) - return 0; - /* Any fence added after the wait begins will not be auto-signaled */ - err = flush_lazy_signals(ref); - i915_active_release(ref); - if (err) - return err; + if (i915_active_acquire_if_busy(ref)) { + int err; - if (!i915_active_is_idle(ref) && - ___wait_var_event(ref, i915_active_is_idle(ref), - state, 0, 0, schedule())) - return -EINTR; + err = flush_lazy_signals(ref); + i915_active_release(ref); + if (err) + return err; + if (___wait_var_event(ref, i915_active_is_idle(ref), + state, 0, 0, schedule())) + return -EINTR; + } + + /* + * After the wait is complete, the caller may free the active. + * We have to flush any concurrent retirement before returning. + */ flush_work(&ref->work); return 0; } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 632c713227dc..c6964f82a1bb 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1346,7 +1346,7 @@ intel_subplatform(const struct intel_runtime_info *info, enum intel_platform p) { const unsigned int pi = __platform_mask_index(info, p); - return info->platform_mask[pi] & INTEL_SUBPLATFORM_BITS; + return info->platform_mask[pi] & ((1 << INTEL_SUBPLATFORM_BITS) - 1); } static __always_inline bool diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index d76685ce0399..9856479b56d8 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -184,13 +184,24 @@ static u64 get_rc6(struct intel_gt *gt) return val; } -static void park_rc6(struct drm_i915_private *i915) +static void init_rc6(struct i915_pmu *pmu) { - struct i915_pmu *pmu = &i915->pmu; + struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu); + intel_wakeref_t wakeref; - if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY)) + with_intel_runtime_pm(i915->gt.uncore->rpm, wakeref) { pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); + pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = + pmu->sample[__I915_SAMPLE_RC6].cur; + pmu->sleep_last = ktime_get(); + } +} +static void park_rc6(struct drm_i915_private *i915) +{ + struct i915_pmu *pmu = &i915->pmu; + + pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); pmu->sleep_last = ktime_get(); } @@ -201,6 +212,7 @@ static u64 get_rc6(struct intel_gt *gt) return __get_rc6(gt); } +static void init_rc6(struct i915_pmu *pmu) { } static void park_rc6(struct drm_i915_private *i915) {} #endif @@ -612,10 +624,8 @@ static void i915_pmu_enable(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); unsigned int bit = event_enabled_bit(event); struct i915_pmu *pmu = &i915->pmu; - intel_wakeref_t wakeref; unsigned long flags; - wakeref = intel_runtime_pm_get(&i915->runtime_pm); spin_lock_irqsave(&pmu->lock, flags); /* @@ -626,13 +636,6 @@ static void i915_pmu_enable(struct perf_event *event) GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count)); GEM_BUG_ON(pmu->enable_count[bit] == ~0); - if (pmu->enable_count[bit] == 0 && - config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) { - pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = 0; - pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt); - pmu->sleep_last = ktime_get(); - } - pmu->enable |= BIT_ULL(bit); pmu->enable_count[bit]++; @@ -673,8 +676,6 @@ static void i915_pmu_enable(struct perf_event *event) * an existing non-zero value. */ local64_set(&event->hw.prev_count, __i915_pmu_event_read(event)); - - intel_runtime_pm_put(&i915->runtime_pm, wakeref); } static void i915_pmu_disable(struct perf_event *event) @@ -1130,6 +1131,7 @@ void i915_pmu_register(struct drm_i915_private *i915) hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); pmu->timer.function = i915_sample; pmu->cpuhp.cpu = -1; + init_rc6(pmu); if (!is_igp(i915)) { pmu->name = kasprintf(GFP_KERNEL, diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 620b6fab2c5c..92adfee30c7c 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -434,7 +434,7 @@ static inline u32 hwsp_seqno(const struct i915_request *rq) static inline bool __i915_request_has_started(const struct i915_request *rq) { - return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno - 1); + return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno - 1); } /** @@ -465,11 +465,19 @@ static inline bool __i915_request_has_started(const struct i915_request *rq) */ static inline bool i915_request_started(const struct i915_request *rq) { + bool result; + if (i915_request_signaled(rq)) return true; - /* Remember: started but may have since been preempted! */ - return __i915_request_has_started(rq); + result = true; + rcu_read_lock(); /* the HWSP may be freed at runtime */ + if (likely(!i915_request_signaled(rq))) + /* Remember: started but may have since been preempted! */ + result = __i915_request_has_started(rq); + rcu_read_unlock(); + + return result; } /** @@ -482,10 +490,16 @@ static inline bool i915_request_started(const struct i915_request *rq) */ static inline bool i915_request_is_running(const struct i915_request *rq) { + bool result; + if (!i915_request_is_active(rq)) return false; - return __i915_request_has_started(rq); + rcu_read_lock(); + result = __i915_request_has_started(rq) && i915_request_is_active(rq); + rcu_read_unlock(); + + return result; } /** @@ -509,12 +523,25 @@ static inline bool i915_request_is_ready(const struct i915_request *rq) return !list_empty(&rq->sched.link); } +static inline bool __i915_request_is_complete(const struct i915_request *rq) +{ + return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno); +} + static inline bool i915_request_completed(const struct i915_request *rq) { + bool result; + if (i915_request_signaled(rq)) return true; - return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno); + result = true; + rcu_read_lock(); /* the HWSP may be freed at runtime */ + if (likely(!i915_request_signaled(rq))) + result = __i915_request_is_complete(rq); + rcu_read_unlock(); + + return result; } static inline void i915_request_mark_complete(struct i915_request *rq) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index c53a222e3dec..713770fb2b92 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1880,7 +1880,7 @@ static int igt_cs_tlb(void *arg) vma = i915_vma_instance(out, vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); - goto out_put_batch; + goto out_put_out; } err = i915_vma_pin(vma, 0, 0, diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c index 302d4e6fc52f..788db043a342 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c @@ -88,7 +88,11 @@ base507c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) NVVAL(NV507C, SET_CONVERSION, OFS, 0x64)); } else { PUSH_MTHD(push, NV507C, SET_PROCESSING, - NVDEF(NV507C, SET_PROCESSING, USE_GAIN_OFS, DISABLE)); + NVDEF(NV507C, SET_PROCESSING, USE_GAIN_OFS, DISABLE), + + SET_CONVERSION, + NVVAL(NV507C, SET_CONVERSION, GAIN, 0) | + NVVAL(NV507C, SET_CONVERSION, OFS, 0)); } PUSH_MTHD(push, NV507C, SURFACE_SET_OFFSET(0, 0), asyw->image.offset[0] >> 8); diff --git a/drivers/gpu/drm/nouveau/dispnv50/base827c.c b/drivers/gpu/drm/nouveau/dispnv50/base827c.c index 18d34096f125..093d4ba6910e 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base827c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base827c.c @@ -49,7 +49,11 @@ base827c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) NVVAL(NV827C, SET_CONVERSION, OFS, 0x64)); } else { PUSH_MTHD(push, NV827C, SET_PROCESSING, - NVDEF(NV827C, SET_PROCESSING, USE_GAIN_OFS, DISABLE)); + NVDEF(NV827C, SET_PROCESSING, USE_GAIN_OFS, DISABLE), + + SET_CONVERSION, + NVVAL(NV827C, SET_CONVERSION, GAIN, 0) | + NVVAL(NV827C, SET_CONVERSION, OFS, 0)); } PUSH_MTHD(push, NV827C, SURFACE_SET_OFFSET(0, 0), asyw->image.offset[0] >> 8, diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index c6367035970e..5f4f09a601d4 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2663,6 +2663,14 @@ nv50_display_create(struct drm_device *dev) else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; + if (disp->disp->object.oclass >= GK104_DISP) { + dev->mode_config.cursor_width = 256; + dev->mode_config.cursor_height = 256; + } else { + dev->mode_config.cursor_width = 64; + dev->mode_config.cursor_height = 64; + } + /* create crtc objects to represent the hw heads */ if (disp->disp->object.oclass >= GV100_DISP) crtcs = nvif_rd32(&device->object, 0x610060) & 0xff; diff --git a/drivers/gpu/drm/nouveau/dispnv50/head917d.c b/drivers/gpu/drm/nouveau/dispnv50/head917d.c index a5d827403660..ea9f8667305e 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head917d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head917d.c @@ -22,6 +22,7 @@ #include "head.h" #include "core.h" +#include "nvif/push.h" #include <nvif/push507c.h> #include <nvhw/class/cl917d.h> @@ -73,6 +74,31 @@ head917d_base(struct nv50_head *head, struct nv50_head_atom *asyh) return 0; } +static int +head917d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh) +{ + struct nvif_push *push = nv50_disp(head->base.base.dev)->core->chan.push; + const int i = head->base.index; + int ret; + + ret = PUSH_WAIT(push, 5); + if (ret) + return ret; + + PUSH_MTHD(push, NV917D, HEAD_SET_CONTROL_CURSOR(i), + NVDEF(NV917D, HEAD_SET_CONTROL_CURSOR, ENABLE, ENABLE) | + NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, FORMAT, asyh->curs.format) | + NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, SIZE, asyh->curs.layout) | + NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, HOT_SPOT_X, 0) | + NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, HOT_SPOT_Y, 0) | + NVDEF(NV917D, HEAD_SET_CONTROL_CURSOR, COMPOSITION, ALPHA_BLEND), + + HEAD_SET_OFFSET_CURSOR(i), asyh->curs.offset >> 8); + + PUSH_MTHD(push, NV917D, HEAD_SET_CONTEXT_DMA_CURSOR(i), asyh->curs.handle); + return 0; +} + int head917d_curs_layout(struct nv50_head *head, struct nv50_wndw_atom *asyw, struct nv50_head_atom *asyh) @@ -101,7 +127,7 @@ head917d = { .core_clr = head907d_core_clr, .curs_layout = head917d_curs_layout, .curs_format = head507d_curs_format, - .curs_set = head907d_curs_set, + .curs_set = head917d_curs_set, .curs_clr = head907d_curs_clr, .base = head917d_base, .ovly = head907d_ovly, diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index ce451242f79e..271de3a63f21 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -702,6 +702,11 @@ nv50_wndw_init(struct nv50_wndw *wndw) nvif_notify_get(&wndw->notify); } +static const u64 nv50_cursor_format_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID, +}; + int nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev, enum drm_plane_type type, const char *name, int index, @@ -713,6 +718,7 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev, struct nvif_mmu *mmu = &drm->client.mmu; struct nv50_disp *disp = nv50_disp(dev); struct nv50_wndw *wndw; + const u64 *format_modifiers; int nformat; int ret; @@ -728,10 +734,13 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev, for (nformat = 0; format[nformat]; nformat++); - ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw, - format, nformat, - nouveau_display(dev)->format_modifiers, - type, "%s-%d", name, index); + if (type == DRM_PLANE_TYPE_CURSOR) + format_modifiers = nv50_cursor_format_modifiers; + else + format_modifiers = nouveau_display(dev)->format_modifiers; + + ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw, format, nformat, + format_modifiers, type, "%s-%d", name, index); if (ret) { kfree(*pwndw); *pwndw = NULL; diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h index 2a2612d6e1e0..fb223723a38a 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h @@ -66,6 +66,10 @@ #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_ALPHA_BLEND (0x00000000) #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_PREMULT_ALPHA_BLEND (0x00000001) #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_XOR (0x00000002) +#define NV917D_HEAD_SET_OFFSET_CURSOR(a) (0x00000484 + (a)*0x00000300) +#define NV917D_HEAD_SET_OFFSET_CURSOR_ORIGIN 31:0 +#define NV917D_HEAD_SET_CONTEXT_DMA_CURSOR(a) (0x0000048C + (a)*0x00000300) +#define NV917D_HEAD_SET_CONTEXT_DMA_CURSOR_HANDLE 31:0 #define NV917D_HEAD_SET_DITHER_CONTROL(a) (0x000004A0 + (a)*0x00000300) #define NV917D_HEAD_SET_DITHER_CONTROL_ENABLE 0:0 #define NV917D_HEAD_SET_DITHER_CONTROL_ENABLE_DISABLE (0x00000000) diff --git a/drivers/gpu/drm/nouveau/include/nvif/push.h b/drivers/gpu/drm/nouveau/include/nvif/push.h index 168d7694ede5..6d3a8a3d2087 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/push.h +++ b/drivers/gpu/drm/nouveau/include/nvif/push.h @@ -123,131 +123,131 @@ PUSH_KICK(struct nvif_push *push) } while(0) #endif -#define PUSH_1(X,f,ds,n,c,o,p,s,mA,dA) do { \ - PUSH_##o##_HDR((p), s, mA, (c)+(n)); \ - PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, ""); \ +#define PUSH_1(X,f,ds,n,o,p,s,mA,dA) do { \ + PUSH_##o##_HDR((p), s, mA, (ds)+(n)); \ + PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, ""); \ } while(0) -#define PUSH_2(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1"); \ - PUSH_1(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_2(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1"); \ + PUSH_1(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_3(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2"); \ - PUSH_2(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_3(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2"); \ + PUSH_2(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_4(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3"); \ - PUSH_3(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_4(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3"); \ + PUSH_3(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_5(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4"); \ - PUSH_4(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_5(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4"); \ + PUSH_4(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_6(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5"); \ - PUSH_5(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_6(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5"); \ + PUSH_5(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_7(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6"); \ - PUSH_6(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_7(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6"); \ + PUSH_6(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_8(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7"); \ - PUSH_7(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_8(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7"); \ + PUSH_7(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_9(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8"); \ - PUSH_8(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_9(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8"); \ + PUSH_8(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_10(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9"); \ - PUSH_9(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_10(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9"); \ + PUSH_9(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_1D(X,o,p,s,mA,dA) \ - PUSH_1(X, DATA_, 1, 1, 0, o, (p), s, X##mA, (dA)) -#define PUSH_2D(X,o,p,s,mA,dA,mB,dB) \ - PUSH_2(X, DATA_, 1, 1, 0, o, (p), s, X##mB, (dB), \ - X##mA, (dA)) -#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC) \ - PUSH_3(X, DATA_, 1, 1, 0, o, (p), s, X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) -#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD) \ - PUSH_4(X, DATA_, 1, 1, 0, o, (p), s, X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) -#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \ - PUSH_5(X, DATA_, 1, 1, 0, o, (p), s, X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) +#define PUSH_1D(X,o,p,s,mA,dA) \ + PUSH_1(X, DATA_, 1, 0, o, (p), s, X##mA, (dA)) +#define PUSH_2D(X,o,p,s,mA,dA,mB,dB) \ + PUSH_2(X, DATA_, 1, 0, o, (p), s, X##mB, (dB), \ + X##mA, (dA)) +#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC) \ + PUSH_3(X, DATA_, 1, 0, o, (p), s, X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) +#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD) \ + PUSH_4(X, DATA_, 1, 0, o, (p), s, X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) +#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \ + PUSH_5(X, DATA_, 1, 0, o, (p), s, X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_6D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF) \ - PUSH_6(X, DATA_, 1, 1, 0, o, (p), s, X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_6(X, DATA_, 1, 0, o, (p), s, X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_7D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG) \ - PUSH_7(X, DATA_, 1, 1, 0, o, (p), s, X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_7(X, DATA_, 1, 0, o, (p), s, X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_8D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH) \ - PUSH_8(X, DATA_, 1, 1, 0, o, (p), s, X##mH, (dH), \ - X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_8(X, DATA_, 1, 0, o, (p), s, X##mH, (dH), \ + X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_9D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI) \ - PUSH_9(X, DATA_, 1, 1, 0, o, (p), s, X##mI, (dI), \ - X##mH, (dH), \ - X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_9(X, DATA_, 1, 0, o, (p), s, X##mI, (dI), \ + X##mH, (dH), \ + X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_10D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI,mJ,dJ) \ - PUSH_10(X, DATA_, 1, 1, 0, o, (p), s, X##mJ, (dJ), \ - X##mI, (dI), \ - X##mH, (dH), \ - X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_10(X, DATA_, 1, 0, o, (p), s, X##mJ, (dJ), \ + X##mI, (dI), \ + X##mH, (dH), \ + X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) -#define PUSH_1P(X,o,p,s,mA,dp,ds) \ - PUSH_1(X, DATAp, ds, ds, 0, o, (p), s, X##mA, (dp)) -#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds) \ - PUSH_2(X, DATAp, ds, ds, 0, o, (p), s, X##mB, (dp), \ - X##mA, (dA)) -#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds) \ - PUSH_3(X, DATAp, ds, ds, 0, o, (p), s, X##mC, (dp), \ - X##mB, (dB), \ - X##mA, (dA)) +#define PUSH_1P(X,o,p,s,mA,dp,ds) \ + PUSH_1(X, DATAp, ds, 0, o, (p), s, X##mA, (dp)) +#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds) \ + PUSH_2(X, DATAp, ds, 0, o, (p), s, X##mB, (dp), \ + X##mA, (dA)) +#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds) \ + PUSH_3(X, DATAp, ds, 0, o, (p), s, X##mC, (dp), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_(A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,IMPL,...) IMPL #define PUSH(A...) PUSH_(A, PUSH_10P, PUSH_10D, \ diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 4f69e4c3dafd..1c3f890377d2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -315,6 +315,10 @@ nouveau_svmm_init(struct drm_device *dev, void *data, struct drm_nouveau_svm_init *args = data; int ret; + /* We need to fail if svm is disabled */ + if (!cli->drm->svm) + return -ENOSYS; + /* Allocate tracking for SVM-enabled VMM. */ if (!(svmm = kzalloc(sizeof(*svmm), GFP_KERNEL))) return -ENOMEM; diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 8cd776adc592..11e0313db0ea 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -79,12 +79,13 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, struct page *p; void *vaddr; - if (order) { - gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY | + /* Don't set the __GFP_COMP flag for higher order allocations. + * Mapping pages directly into an userspace process and calling + * put_page() on a TTM allocated page is illegal. + */ + if (order) + gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_KSWAPD_RECLAIM; - gfp_flags &= ~__GFP_MOVABLE; - gfp_flags &= ~__GFP_COMP; - } if (!pool->use_dma_alloc) { p = alloc_pages(gfp_flags, order); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 555106220578..98cab0bbe92d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1267,6 +1267,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) card->dai_link = dai_link; card->num_links = 1; card->name = vc4_hdmi->variant->card_name; + card->driver_name = "vc4-hdmi"; card->dev = dev; card->owner = THIS_MODULE; diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index cccd341e5d67..3b722252d1fb 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -620,11 +620,11 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) * for now we just allocate globally. */ if (!hvs->hvs5) - /* 96kB */ - drm_mm_init(&hvs->lbm_mm, 0, 96 * 1024); + /* 48k words of 2x12-bit pixels */ + drm_mm_init(&hvs->lbm_mm, 0, 48 * 1024); else - /* 70k words */ - drm_mm_init(&hvs->lbm_mm, 0, 70 * 2 * 1024); + /* 60k words of 4x12-bit pixels */ + drm_mm_init(&hvs->lbm_mm, 0, 60 * 1024); /* Upload filter kernels. We only have the one for now, so we * keep it around for the lifetime of the driver. diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 6b39cc2ca18d..5612cab55227 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -437,6 +437,7 @@ static void vc4_write_ppf(struct vc4_plane_state *vc4_state, u32 src, u32 dst) static u32 vc4_lbm_size(struct drm_plane_state *state) { struct vc4_plane_state *vc4_state = to_vc4_plane_state(state); + struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev); u32 pix_per_line; u32 lbm; @@ -472,7 +473,11 @@ static u32 vc4_lbm_size(struct drm_plane_state *state) lbm = pix_per_line * 16; } - lbm = roundup(lbm, 32); + /* Align it to 64 or 128 (hvs5) bytes */ + lbm = roundup(lbm, vc4->hvs->hvs5 ? 128 : 64); + + /* Each "word" of the LBM memory contains 2 or 4 (hvs5) pixels */ + lbm /= vc4->hvs->hvs5 ? 4 : 2; return lbm; } @@ -912,9 +917,9 @@ static int vc4_plane_mode_set(struct drm_plane *plane, if (!vc4_state->is_unity) { vc4_dlist_write(vc4_state, VC4_SET_FIELD(vc4_state->crtc_w, - SCALER_POS1_SCL_WIDTH) | + SCALER5_POS1_SCL_WIDTH) | VC4_SET_FIELD(vc4_state->crtc_h, - SCALER_POS1_SCL_HEIGHT)); + SCALER5_POS1_SCL_HEIGHT)); } /* Position Word 2: Source Image Size */ diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 0743ef51d3b2..8429ebe7097e 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -758,7 +758,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, MT_STORE_FIELD(inrange_state); return 1; case HID_DG_CONFIDENCE: - if (cls->name == MT_CLS_WIN_8 && + if ((cls->name == MT_CLS_WIN_8 || + cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT) && (field->application == HID_DG_TOUCHPAD || field->application == HID_DG_TOUCHSCREEN)) app->quirks |= MT_QUIRK_CONFIDENCE; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index e8acd235db2a..aa9e48876ced 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -147,9 +147,9 @@ static int wacom_wac_pen_serial_enforce(struct hid_device *hdev, } if (flush) - wacom_wac_queue_flush(hdev, &wacom_wac->pen_fifo); + wacom_wac_queue_flush(hdev, wacom_wac->pen_fifo); else if (insert) - wacom_wac_queue_insert(hdev, &wacom_wac->pen_fifo, + wacom_wac_queue_insert(hdev, wacom_wac->pen_fifo, raw_data, report_size); return insert && !flush; @@ -1280,7 +1280,7 @@ static void wacom_devm_kfifo_release(struct device *dev, void *res) static int wacom_devm_kfifo_alloc(struct wacom *wacom) { struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct kfifo_rec_ptr_2 *pen_fifo = &wacom_wac->pen_fifo; + struct kfifo_rec_ptr_2 *pen_fifo; int error; pen_fifo = devres_alloc(wacom_devm_kfifo_release, @@ -1297,6 +1297,7 @@ static int wacom_devm_kfifo_alloc(struct wacom *wacom) } devres_add(&wacom->hdev->dev, pen_fifo); + wacom_wac->pen_fifo = pen_fifo; return 0; } diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index da612b6e9c77..195910dd2154 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -342,7 +342,7 @@ struct wacom_wac { struct input_dev *pen_input; struct input_dev *touch_input; struct input_dev *pad_input; - struct kfifo_rec_ptr_2 pen_fifo; + struct kfifo_rec_ptr_2 *pen_fifo; int pid; int num_contacts_left; u8 bt_features; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 52acd77438ed..251e75c9ba9d 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -269,6 +269,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)&intel_th_2x, }, { + /* Alder Lake-P */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x51a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { /* Alder Lake CPU */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f), .driver_data = (kernel_ulong_t)&intel_th_2x, diff --git a/drivers/hwtracing/stm/heartbeat.c b/drivers/hwtracing/stm/heartbeat.c index 3e7df1c0477f..81d7b21d31ec 100644 --- a/drivers/hwtracing/stm/heartbeat.c +++ b/drivers/hwtracing/stm/heartbeat.c @@ -64,7 +64,7 @@ static void stm_heartbeat_unlink(struct stm_source_data *data) static int stm_heartbeat_init(void) { - int i, ret = -ENOMEM; + int i, ret; if (nr_devs < 0 || nr_devs > STM_HEARTBEAT_MAX) return -EINVAL; @@ -72,8 +72,10 @@ static int stm_heartbeat_init(void) for (i = 0; i < nr_devs; i++) { stm_heartbeat[i].data.name = kasprintf(GFP_KERNEL, "heartbeat.%d", i); - if (!stm_heartbeat[i].data.name) + if (!stm_heartbeat[i].data.name) { + ret = -ENOMEM; goto fail_unregister; + } stm_heartbeat[i].data.nr_chans = 1; stm_heartbeat[i].data.link = stm_heartbeat_link; diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index d4d60ad0eda0..ab1f39ac39f4 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -1013,6 +1013,7 @@ config I2C_SIRF config I2C_SPRD tristate "Spreadtrum I2C interface" depends on I2C=y && (ARCH_SPRD || COMPILE_TEST) + depends on COMMON_CLK help If you say yes to this option, support will be included for the Spreadtrum I2C interface. diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index b444fbf1a262..a8e8af57e33f 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -241,6 +241,19 @@ static struct imx_i2c_hwdata vf610_i2c_hwdata = { }; +static const struct platform_device_id imx_i2c_devtype[] = { + { + .name = "imx1-i2c", + .driver_data = (kernel_ulong_t)&imx1_i2c_hwdata, + }, { + .name = "imx21-i2c", + .driver_data = (kernel_ulong_t)&imx21_i2c_hwdata, + }, { + /* sentinel */ + } +}; +MODULE_DEVICE_TABLE(platform, imx_i2c_devtype); + static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx1-i2c", .data = &imx1_i2c_hwdata, }, { .compatible = "fsl,imx21-i2c", .data = &imx21_i2c_hwdata, }, @@ -1330,7 +1343,11 @@ static int i2c_imx_probe(struct platform_device *pdev) return -ENOMEM; match = device_get_match_data(&pdev->dev); - i2c_imx->hwdata = match; + if (match) + i2c_imx->hwdata = match; + else + i2c_imx->hwdata = (struct imx_i2c_hwdata *) + platform_get_device_id(pdev)->driver_data; /* Setup i2c_imx driver structure */ strlcpy(i2c_imx->adapter.name, pdev->name, sizeof(i2c_imx->adapter.name)); @@ -1498,6 +1515,7 @@ static struct platform_driver i2c_imx_driver = { .of_match_table = i2c_imx_dt_ids, .acpi_match_table = i2c_imx_acpi_ids, }, + .id_table = imx_i2c_devtype, }; static int __init i2c_adap_imx_init(void) diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 0818d3e50734..2ffd2f354d0a 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -1275,7 +1275,8 @@ static int mtk_i2c_probe(struct platform_device *pdev) mtk_i2c_clock_disable(i2c); ret = devm_request_irq(&pdev->dev, irq, mtk_i2c_irq, - IRQF_TRIGGER_NONE, I2C_DRV_NAME, i2c); + IRQF_NO_SUSPEND | IRQF_TRIGGER_NONE, + I2C_DRV_NAME, i2c); if (ret < 0) { dev_err(&pdev->dev, "Request I2C IRQ %d fail\n", irq); @@ -1302,7 +1303,16 @@ static int mtk_i2c_remove(struct platform_device *pdev) } #ifdef CONFIG_PM_SLEEP -static int mtk_i2c_resume(struct device *dev) +static int mtk_i2c_suspend_noirq(struct device *dev) +{ + struct mtk_i2c *i2c = dev_get_drvdata(dev); + + i2c_mark_adapter_suspended(&i2c->adap); + + return 0; +} + +static int mtk_i2c_resume_noirq(struct device *dev) { int ret; struct mtk_i2c *i2c = dev_get_drvdata(dev); @@ -1317,12 +1327,15 @@ static int mtk_i2c_resume(struct device *dev) mtk_i2c_clock_disable(i2c); + i2c_mark_adapter_resumed(&i2c->adap); + return 0; } #endif static const struct dev_pm_ops mtk_i2c_pm = { - SET_SYSTEM_SLEEP_PM_OPS(NULL, mtk_i2c_resume) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_i2c_suspend_noirq, + mtk_i2c_resume_noirq) }; static struct platform_driver mtk_i2c_driver = { diff --git a/drivers/i2c/busses/i2c-octeon-core.c b/drivers/i2c/busses/i2c-octeon-core.c index d9607905dc2f..845eda70b8ca 100644 --- a/drivers/i2c/busses/i2c-octeon-core.c +++ b/drivers/i2c/busses/i2c-octeon-core.c @@ -347,7 +347,7 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target, if (result) return result; if (recv_len && i == 0) { - if (data[i] > I2C_SMBUS_BLOCK_MAX + 1) + if (data[i] > I2C_SMBUS_BLOCK_MAX) return -EPROTO; length += data[i]; } diff --git a/drivers/i2c/busses/i2c-tegra-bpmp.c b/drivers/i2c/busses/i2c-tegra-bpmp.c index ec7a7e917edd..c0c7d01473f2 100644 --- a/drivers/i2c/busses/i2c-tegra-bpmp.c +++ b/drivers/i2c/busses/i2c-tegra-bpmp.c @@ -80,7 +80,7 @@ static int tegra_bpmp_xlate_flags(u16 flags, u16 *out) flags &= ~I2C_M_RECV_LEN; } - return (flags != 0) ? -EINVAL : 0; + return 0; } /** diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 6f08c0c3238d..8b113ae32dc7 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -326,6 +326,8 @@ static void i2c_writel(struct tegra_i2c_dev *i2c_dev, u32 val, unsigned int reg) /* read back register to make sure that register writes completed */ if (reg != I2C_TX_FIFO) readl_relaxed(i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, reg)); + else if (i2c_dev->is_vi) + readl_relaxed(i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, I2C_INT_STATUS)); } static u32 i2c_readl(struct tegra_i2c_dev *i2c_dev, unsigned int reg) @@ -339,6 +341,21 @@ static void i2c_writesl(struct tegra_i2c_dev *i2c_dev, void *data, writesl(i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, reg), data, len); } +static void i2c_writesl_vi(struct tegra_i2c_dev *i2c_dev, void *data, + unsigned int reg, unsigned int len) +{ + u32 *data32 = data; + + /* + * VI I2C controller has known hardware bug where writes get stuck + * when immediate multiple writes happen to TX_FIFO register. + * Recommended software work around is to read I2C register after + * each write to TX_FIFO register to flush out the data. + */ + while (len--) + i2c_writel(i2c_dev, *data32++, reg); +} + static void i2c_readsl(struct tegra_i2c_dev *i2c_dev, void *data, unsigned int reg, unsigned int len) { @@ -533,7 +550,7 @@ static int tegra_i2c_poll_register(struct tegra_i2c_dev *i2c_dev, void __iomem *addr = i2c_dev->base + tegra_i2c_reg_addr(i2c_dev, reg); u32 val; - if (!i2c_dev->atomic_mode) + if (!i2c_dev->atomic_mode && !in_irq()) return readl_relaxed_poll_timeout(addr, val, !(val & mask), delay_us, timeout_us); @@ -811,7 +828,10 @@ static int tegra_i2c_fill_tx_fifo(struct tegra_i2c_dev *i2c_dev) i2c_dev->msg_buf_remaining = buf_remaining; i2c_dev->msg_buf = buf + words_to_transfer * BYTES_PER_FIFO_WORD; - i2c_writesl(i2c_dev, buf, I2C_TX_FIFO, words_to_transfer); + if (i2c_dev->is_vi) + i2c_writesl_vi(i2c_dev, buf, I2C_TX_FIFO, words_to_transfer); + else + i2c_writesl(i2c_dev, buf, I2C_TX_FIFO, words_to_transfer); buf += words_to_transfer * BYTES_PER_FIFO_WORD; } diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index b11c8c47ba2a..e946903b0993 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -397,16 +397,12 @@ static int tiadc_iio_buffered_hardware_setup(struct device *dev, ret = devm_request_threaded_irq(dev, irq, pollfunc_th, pollfunc_bh, flags, indio_dev->name, indio_dev); if (ret) - goto error_kfifo_free; + return ret; indio_dev->setup_ops = setup_ops; indio_dev->modes |= INDIO_BUFFER_SOFTWARE; return 0; - -error_kfifo_free: - iio_kfifo_free(indio_dev->buffer); - return ret; } static const char * const chan_name_ain[] = { diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 0507283bd4c1..2dbd2646e44e 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -23,35 +23,31 @@ * @sdata: Sensor data. * * returns: - * 0 - no new samples available - * 1 - new samples available - * negative - error or unknown + * false - no new samples available or read error + * true - new samples available */ -static int st_sensors_new_samples_available(struct iio_dev *indio_dev, - struct st_sensor_data *sdata) +static bool st_sensors_new_samples_available(struct iio_dev *indio_dev, + struct st_sensor_data *sdata) { int ret, status; /* How would I know if I can't check it? */ if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) - return -EINVAL; + return true; /* No scan mask, no interrupt */ if (!indio_dev->active_scan_mask) - return 0; + return false; ret = regmap_read(sdata->regmap, sdata->sensor_settings->drdy_irq.stat_drdy.addr, &status); if (ret < 0) { dev_err(sdata->dev, "error checking samples available\n"); - return ret; + return false; } - if (status & sdata->sensor_settings->drdy_irq.stat_drdy.mask) - return 1; - - return 0; + return !!(status & sdata->sensor_settings->drdy_irq.stat_drdy.mask); } /** @@ -180,9 +176,15 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, /* Tell the interrupt handler that we're dealing with edges */ if (irq_trig == IRQF_TRIGGER_FALLING || - irq_trig == IRQF_TRIGGER_RISING) + irq_trig == IRQF_TRIGGER_RISING) { + if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) { + dev_err(&indio_dev->dev, + "edge IRQ not supported w/o stat register.\n"); + err = -EOPNOTSUPP; + goto iio_trigger_free; + } sdata->edge_irq = true; - else + } else { /* * If we're not using edges (i.e. level interrupts) we * just mask off the IRQ, handle one interrupt, then @@ -190,6 +192,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, * interrupt handler top half again and start over. */ irq_trig |= IRQF_ONESHOT; + } /* * If the interrupt pin is Open Drain, by definition this diff --git a/drivers/iio/dac/ad5504.c b/drivers/iio/dac/ad5504.c index 28921b62e642..e9297c25d4ef 100644 --- a/drivers/iio/dac/ad5504.c +++ b/drivers/iio/dac/ad5504.c @@ -187,9 +187,9 @@ static ssize_t ad5504_write_dac_powerdown(struct iio_dev *indio_dev, return ret; if (pwr_down) - st->pwr_down_mask |= (1 << chan->channel); - else st->pwr_down_mask &= ~(1 << chan->channel); + else + st->pwr_down_mask |= (1 << chan->channel); ret = ad5504_spi_write(st, AD5504_ADDR_CTRL, AD5504_DAC_PWRDWN_MODE(st->pwr_down_mode) | diff --git a/drivers/iio/proximity/sx9310.c b/drivers/iio/proximity/sx9310.c index a2f820997afc..37fd0b65a014 100644 --- a/drivers/iio/proximity/sx9310.c +++ b/drivers/iio/proximity/sx9310.c @@ -601,7 +601,7 @@ static int sx9310_read_thresh(struct sx9310_data *data, return ret; regval = FIELD_GET(SX9310_REG_PROX_CTRL8_9_PTHRESH_MASK, regval); - if (regval > ARRAY_SIZE(sx9310_pthresh_codes)) + if (regval >= ARRAY_SIZE(sx9310_pthresh_codes)) return -EINVAL; *val = sx9310_pthresh_codes[regval]; @@ -1305,7 +1305,8 @@ sx9310_get_default_reg(struct sx9310_data *data, int i, if (ret) break; - pos = min(max(ilog2(pos), 3), 10) - 3; + /* Powers of 2, except for a gap between 16 and 64 */ + pos = clamp(ilog2(pos), 3, 11) - (pos >= 32 ? 4 : 3); reg_def->def &= ~SX9310_REG_PROX_CTRL7_AVGPOSFILT_MASK; reg_def->def |= FIELD_PREP(SX9310_REG_PROX_CTRL7_AVGPOSFILT_MASK, pos); diff --git a/drivers/iio/temperature/mlx90632.c b/drivers/iio/temperature/mlx90632.c index 503fe54a0bb9..608ccb1d8bc8 100644 --- a/drivers/iio/temperature/mlx90632.c +++ b/drivers/iio/temperature/mlx90632.c @@ -248,6 +248,12 @@ static int mlx90632_set_meas_type(struct regmap *regmap, u8 type) if (ret < 0) return ret; + /* + * Give the mlx90632 some time to reset properly before sending a new I2C command + * if this is not done, the following I2C command(s) will not be accepted. + */ + usleep_range(150, 200); + ret = regmap_write_bits(regmap, MLX90632_REG_CONTROL, (MLX90632_CFG_MTYP_MASK | MLX90632_CFG_PWR_MASK), (MLX90632_MTYP_STATUS(type) | MLX90632_PWR_STATUS_HALT)); diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index a7401398cb34..d109bb3822a5 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -2474,7 +2474,7 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, init_attr->cap.max_send_wr = qhp->attr.sq_num_entries; init_attr->cap.max_recv_wr = qhp->attr.rq_num_entries; init_attr->cap.max_send_sge = qhp->attr.sq_max_sges; - init_attr->cap.max_recv_sge = qhp->attr.sq_max_sges; + init_attr->cap.max_recv_sge = qhp->attr.rq_max_sges; init_attr->cap.max_inline_data = T4_MAX_SEND_INLINE; init_attr->sq_sig_type = qhp->sq_sig_all ? IB_SIGNAL_ALL_WR : 0; return 0; diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 55d538625e36..ad8253245a85 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -532,7 +532,7 @@ struct hns_roce_qp_table { struct hns_roce_hem_table sccc_table; struct mutex scc_mutex; struct hns_roce_bank bank[HNS_ROCE_QP_BANK_NUM]; - spinlock_t bank_lock; + struct mutex bank_mutex; }; struct hns_roce_cq_table { diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index d8e2fe5558d2..1116371adf74 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -209,7 +209,7 @@ static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) hr_qp->doorbell_qpn = 1; } else { - spin_lock(&qp_table->bank_lock); + mutex_lock(&qp_table->bank_mutex); bankid = get_least_load_bankid_for_qp(qp_table->bank); ret = alloc_qpn_with_bankid(&qp_table->bank[bankid], bankid, @@ -217,12 +217,12 @@ static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) if (ret) { ibdev_err(&hr_dev->ib_dev, "failed to alloc QPN, ret = %d\n", ret); - spin_unlock(&qp_table->bank_lock); + mutex_unlock(&qp_table->bank_mutex); return ret; } qp_table->bank[bankid].inuse++; - spin_unlock(&qp_table->bank_lock); + mutex_unlock(&qp_table->bank_mutex); hr_qp->doorbell_qpn = (u32)num; } @@ -408,9 +408,9 @@ static void free_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) ida_free(&hr_dev->qp_table.bank[bankid].ida, hr_qp->qpn >> 3); - spin_lock(&hr_dev->qp_table.bank_lock); + mutex_lock(&hr_dev->qp_table.bank_mutex); hr_dev->qp_table.bank[bankid].inuse--; - spin_unlock(&hr_dev->qp_table.bank_lock); + mutex_unlock(&hr_dev->qp_table.bank_mutex); } static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, @@ -1371,6 +1371,7 @@ int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev) unsigned int i; mutex_init(&qp_table->scc_mutex); + mutex_init(&qp_table->bank_mutex); xa_init(&hr_dev->qp_table_xa); reserved_from_bot = hr_dev->caps.reserved_qps; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index d26f3f3e0462..aabdc07e4753 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3311,8 +3311,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num) int err; dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event; - err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev), - &dev->port[port_num].roce.nb); + err = register_netdevice_notifier(&dev->port[port_num].roce.nb); if (err) { dev->port[port_num].roce.nb.notifier_call = NULL; return err; @@ -3324,8 +3323,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num) static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num) { if (dev->port[port_num].roce.nb.notifier_call) { - unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev), - &dev->port[port_num].roce.nb); + unregister_netdevice_notifier(&dev->port[port_num].roce.nb); dev->port[port_num].roce.nb.notifier_call = NULL; } } diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c index e59615a4c9d9..586b0e52ba7f 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c @@ -214,7 +214,7 @@ static ssize_t summary_show(struct usnic_ib_qp_grp *qp_grp, char *buf) struct usnic_vnic_res *vnic_res; int len; - len = sysfs_emit(buf, "QPN: %d State: (%s) PID: %u VF Idx: %hu ", + len = sysfs_emit(buf, "QPN: %d State: (%s) PID: %u VF Idx: %hu", qp_grp->ibqp.qp_num, usnic_ib_qp_grp_state_to_string(qp_grp->state), qp_grp->owner_pid, @@ -224,14 +224,13 @@ static ssize_t summary_show(struct usnic_ib_qp_grp *qp_grp, char *buf) res_chunk = qp_grp->res_chunk_list[i]; for (j = 0; j < res_chunk->cnt; j++) { vnic_res = res_chunk->res[j]; - len += sysfs_emit_at( - buf, len, "%s[%d] ", + len += sysfs_emit_at(buf, len, " %s[%d]", usnic_vnic_res_type_to_str(vnic_res->type), vnic_res->vnic_idx); } } - len = sysfs_emit_at(buf, len, "\n"); + len += sysfs_emit_at(buf, len, "\n"); return len; } diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h index c142f5e7f25f..de57f2fed743 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h @@ -509,6 +509,20 @@ static inline int ib_send_flags_to_pvrdma(int flags) return flags & PVRDMA_MASK(PVRDMA_SEND_FLAGS_MAX); } +static inline int pvrdma_network_type_to_ib(enum pvrdma_network_type type) +{ + switch (type) { + case PVRDMA_NETWORK_ROCE_V1: + return RDMA_NETWORK_ROCE_V1; + case PVRDMA_NETWORK_IPV4: + return RDMA_NETWORK_IPV4; + case PVRDMA_NETWORK_IPV6: + return RDMA_NETWORK_IPV6; + default: + return RDMA_NETWORK_IPV6; + } +} + void pvrdma_qp_cap_to_ib(struct ib_qp_cap *dst, const struct pvrdma_qp_cap *src); void ib_qp_cap_to_pvrdma(struct pvrdma_qp_cap *dst, diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c index a119ac3e103c..6aa40bd2fd52 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c @@ -367,7 +367,7 @@ retry: wc->dlid_path_bits = cqe->dlid_path_bits; wc->port_num = cqe->port_num; wc->vendor_err = cqe->vendor_err; - wc->network_hdr_type = cqe->network_hdr_type; + wc->network_hdr_type = pvrdma_network_type_to_ib(cqe->network_hdr_type); /* Update shared ring state */ pvrdma_idx_ring_inc(&cq->ring_state->rx.cons_head, cq->ibcq.cqe); diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index c4b06ced30a7..943914c2a50c 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -8,6 +8,7 @@ #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/if.h> +#include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/sch_generic.h> #include <linux/netfilter.h> @@ -153,9 +154,14 @@ static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct udphdr *udph; struct net_device *ndev = skb->dev; + struct net_device *rdev = ndev; struct rxe_dev *rxe = rxe_get_dev_from_net(ndev); struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); + if (!rxe && is_vlan_dev(rdev)) { + rdev = vlan_dev_real_dev(ndev); + rxe = rxe_get_dev_from_net(rdev); + } if (!rxe) goto drop; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 5a098083a9d2..c7e3b6a4af38 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -872,6 +872,11 @@ static enum resp_states do_complete(struct rxe_qp *qp, else wc->network_hdr_type = RDMA_NETWORK_IPV6; + if (is_vlan_dev(skb->dev)) { + wc->wc_flags |= IB_WC_WITH_VLAN; + wc->vlan_id = vlan_dev_vlan_id(skb->dev); + } + if (pkt->mask & RXE_IMMDT_MASK) { wc->wc_flags |= IB_WC_WITH_IMM; wc->ex.imm_data = immdt_imm(pkt); diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 6b8cbdf71714..b4adab698563 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -84,12 +84,9 @@ static inline bool is_rd890_iommu(struct pci_dev *pdev) (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); } -static inline bool iommu_feature(struct amd_iommu *iommu, u64 f) +static inline bool iommu_feature(struct amd_iommu *iommu, u64 mask) { - if (!(iommu->cap & (1 << IOMMU_CAP_EFR))) - return false; - - return !!(iommu->features & f); + return !!(iommu->features & mask); } static inline u64 iommu_virt_to_phys(void *vaddr) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 553587827771..1a0495dd5fcb 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -387,6 +387,10 @@ #define IOMMU_CAP_NPCACHE 26 #define IOMMU_CAP_EFR 27 +/* IOMMU IVINFO */ +#define IOMMU_IVINFO_OFFSET 36 +#define IOMMU_IVINFO_EFRSUP BIT(0) + /* IOMMU Feature Reporting Field (for IVHD type 10h */ #define IOMMU_FEAT_GASUP_SHIFT 6 diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 6a1f7048dacc..83d8ab2aed9f 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -257,6 +257,8 @@ static void init_device_table_dma(void); static bool amd_iommu_pre_enabled = true; +static u32 amd_iommu_ivinfo __initdata; + bool translation_pre_enabled(struct amd_iommu *iommu) { return (iommu->flags & AMD_IOMMU_FLAG_TRANS_PRE_ENABLED); @@ -296,6 +298,18 @@ int amd_iommu_get_num_iommus(void) return amd_iommus_present; } +/* + * For IVHD type 0x11/0x40, EFR is also available via IVHD. + * Default to IVHD EFR since it is available sooner + * (i.e. before PCI init). + */ +static void __init early_iommu_features_init(struct amd_iommu *iommu, + struct ivhd_header *h) +{ + if (amd_iommu_ivinfo & IOMMU_IVINFO_EFRSUP) + iommu->features = h->efr_reg; +} + /* Access to l1 and l2 indexed register spaces */ static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address) @@ -1577,6 +1591,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; + + early_iommu_features_init(iommu, h); + break; default: return -EINVAL; @@ -1770,6 +1787,35 @@ static const struct attribute_group *amd_iommu_groups[] = { NULL, }; +/* + * Note: IVHD 0x11 and 0x40 also contains exact copy + * of the IOMMU Extended Feature Register [MMIO Offset 0030h]. + * Default to EFR in IVHD since it is available sooner (i.e. before PCI init). + */ +static void __init late_iommu_features_init(struct amd_iommu *iommu) +{ + u64 features; + + if (!(iommu->cap & (1 << IOMMU_CAP_EFR))) + return; + + /* read extended feature bits */ + features = readq(iommu->mmio_base + MMIO_EXT_FEATURES); + + if (!iommu->features) { + iommu->features = features; + return; + } + + /* + * Sanity check and warn if EFR values from + * IVHD and MMIO conflict. + */ + if (features != iommu->features) + pr_warn(FW_WARN "EFR mismatch. Use IVHD EFR (%#llx : %#llx\n).", + features, iommu->features); +} + static int __init iommu_init_pci(struct amd_iommu *iommu) { int cap_ptr = iommu->cap_ptr; @@ -1789,8 +1835,7 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) amd_iommu_iotlb_sup = false; - /* read extended feature bits */ - iommu->features = readq(iommu->mmio_base + MMIO_EXT_FEATURES); + late_iommu_features_init(iommu); if (iommu_feature(iommu, FEATURE_GT)) { int glxval; @@ -2607,6 +2652,11 @@ static void __init free_dma_resources(void) free_unity_maps(); } +static void __init ivinfo_init(void *ivrs) +{ + amd_iommu_ivinfo = *((u32 *)(ivrs + IOMMU_IVINFO_OFFSET)); +} + /* * This is the hardware init function for AMD IOMMU in the system. * This function is called either from amd_iommu_init or from the interrupt @@ -2661,6 +2711,8 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; + ivinfo_init(ivrs_base); + amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base); DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 004feaed3c72..02e7c10a4224 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1496,7 +1496,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, * Max Invs Pending (MIP) is set to 0 for now until we have DIT in * ECAP. */ - if (addr & GENMASK_ULL(size_order + VTD_PAGE_SHIFT, 0)) + if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order)) pr_warn_ratelimited("Invalidate non-aligned address %llx, order %d\n", addr, size_order); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f665322a0991..06b00b5363d8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5440,6 +5440,36 @@ intel_iommu_domain_set_attr(struct iommu_domain *domain, return ret; } +static bool domain_use_flush_queue(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + bool r = true; + + if (intel_iommu_strict) + return false; + + /* + * The flush queue implementation does not perform page-selective + * invalidations that are required for efficient TLB flushes in virtual + * environments. The benefit of batching is likely to be much lower than + * the overhead of synchronizing the virtual and physical IOMMU + * page-tables. + */ + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!cap_caching_mode(iommu->cap)) + continue; + + pr_warn_once("IOMMU batching is disabled due to virtualization"); + r = false; + break; + } + rcu_read_unlock(); + + return r; +} + static int intel_iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) @@ -5450,7 +5480,7 @@ intel_iommu_domain_get_attr(struct iommu_domain *domain, case IOMMU_DOMAIN_DMA: switch (attr) { case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: - *(int *)data = !intel_iommu_strict; + *(int *)data = domain_use_flush_queue(); return 0; default: return -ENODEV; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 94920a51c628..b147f22a78f4 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -493,8 +493,9 @@ config TI_SCI_INTA_IRQCHIP TI System Controller, say Y here. Otherwise, say N. config TI_PRUSS_INTC - tristate "TI PRU-ICSS Interrupt Controller" - depends on ARCH_DAVINCI || SOC_AM33XX || SOC_AM43XX || SOC_DRA7XX || ARCH_KEYSTONE || ARCH_K3 + tristate + depends on TI_PRUSS + default TI_PRUSS select IRQ_DOMAIN help This enables support for the PRU-ICSS Local Interrupt Controller diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c index 5f5eb8877c41..25c9a9c06e41 100644 --- a/drivers/irqchip/irq-bcm2836.c +++ b/drivers/irqchip/irq-bcm2836.c @@ -167,7 +167,7 @@ static void bcm2836_arm_irqchip_handle_ipi(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static void bcm2836_arm_irqchip_ipi_eoi(struct irq_data *d) +static void bcm2836_arm_irqchip_ipi_ack(struct irq_data *d) { int cpu = smp_processor_id(); @@ -195,7 +195,7 @@ static struct irq_chip bcm2836_arm_irqchip_ipi = { .name = "IPI", .irq_mask = bcm2836_arm_irqchip_dummy_op, .irq_unmask = bcm2836_arm_irqchip_dummy_op, - .irq_eoi = bcm2836_arm_irqchip_ipi_eoi, + .irq_ack = bcm2836_arm_irqchip_ipi_ack, .ipi_send_mask = bcm2836_arm_irqchip_ipi_send_mask, }; diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 9ed1bc473663..09b91b81851c 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -142,8 +142,8 @@ static void liointc_resume(struct irq_chip_generic *gc) static const char * const parent_names[] = {"int0", "int1", "int2", "int3"}; -int __init liointc_of_init(struct device_node *node, - struct device_node *parent) +static int __init liointc_of_init(struct device_node *node, + struct device_node *parent) { struct irq_chip_generic *gc; struct irq_domain *domain; diff --git a/drivers/irqchip/irq-mips-cpu.c b/drivers/irqchip/irq-mips-cpu.c index 95d4fd8f7a96..0bbb0b2d0dd5 100644 --- a/drivers/irqchip/irq-mips-cpu.c +++ b/drivers/irqchip/irq-mips-cpu.c @@ -197,6 +197,13 @@ static int mips_cpu_ipi_alloc(struct irq_domain *domain, unsigned int virq, if (ret) return ret; + ret = irq_domain_set_hwirq_and_chip(domain->parent, virq + i, hwirq, + &mips_mt_cpu_irq_controller, + NULL); + + if (ret) + return ret; + ret = irq_set_irq_type(virq + i, IRQ_TYPE_LEVEL_HIGH); if (ret) return ret; diff --git a/drivers/irqchip/irq-sl28cpld.c b/drivers/irqchip/irq-sl28cpld.c index 0aa50d025ef6..fbb354413ffa 100644 --- a/drivers/irqchip/irq-sl28cpld.c +++ b/drivers/irqchip/irq-sl28cpld.c @@ -66,7 +66,7 @@ static int sl28cpld_intc_probe(struct platform_device *pdev) irqchip->chip.num_regs = 1; irqchip->chip.status_base = base + INTC_IP; irqchip->chip.mask_base = base + INTC_IE; - irqchip->chip.mask_invert = true, + irqchip->chip.mask_invert = true; irqchip->chip.ack_base = base + INTC_IP; return devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(dev), diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 849d3c5f908e..6c1d8b69a465 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -928,6 +928,9 @@ config LEDS_ACER_A500 This option enables support for the Power Button LED of Acer Iconia Tab A500. +comment "Flash and Torch LED drivers" +source "drivers/leds/flash/Kconfig" + comment "LED Triggers" source "drivers/leds/trigger/Kconfig" diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index 73e603e1727e..156c0b4e60d9 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -103,5 +103,8 @@ obj-$(CONFIG_LEDS_SPI_BYTE) += leds-spi-byte.o # LED Userspace Drivers obj-$(CONFIG_LEDS_USER) += uleds.o +# Flash and Torch LED Drivers +obj-$(CONFIG_LEDS_CLASS_FLASH) += flash/ + # LED Triggers obj-$(CONFIG_LEDS_TRIGGERS) += trigger/ diff --git a/drivers/leds/flash/Kconfig b/drivers/leds/flash/Kconfig new file mode 100644 index 000000000000..d21d273ef3da --- /dev/null +++ b/drivers/leds/flash/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 + +if LEDS_CLASS_FLASH + +config LEDS_RT8515 + tristate "LED support for Richtek RT8515 flash/torch LED" + depends on GPIOLIB + help + This option enables support for the Richtek RT8515 flash + and torch LEDs found on some mobile phones. + + To compile this driver as a module, choose M here: the module + will be called leds-rt8515. + +endif # LEDS_CLASS_FLASH diff --git a/drivers/leds/flash/Makefile b/drivers/leds/flash/Makefile new file mode 100644 index 000000000000..e990e257f4d7 --- /dev/null +++ b/drivers/leds/flash/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_LEDS_RT8515) += leds-rt8515.o diff --git a/drivers/leds/flash/leds-rt8515.c b/drivers/leds/flash/leds-rt8515.c new file mode 100644 index 000000000000..590bfa180d10 --- /dev/null +++ b/drivers/leds/flash/leds-rt8515.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * LED driver for Richtek RT8515 flash/torch white LEDs + * found on some Samsung mobile phones. + * + * This is a 1.5A Boost dual channel driver produced around 2011. + * + * The component lacks a datasheet, but in the schematic picture + * from the LG P970 service manual you can see the connections + * from the RT8515 to the LED, with two resistors connected + * from the pins "RFS" and "RTS" to ground. + * + * On the LG P970: + * RFS (resistance flash setting?) is 20 kOhm + * RTS (resistance torch setting?) is 39 kOhm + * + * Some sleuthing finds us the RT9387A which we have a datasheet for: + * https://static5.arrow.com/pdfs/2014/7/27/8/21/12/794/rtt_/manual/94download_ds.jspprt9387a.jspprt9387a.pdf + * This apparently works the same way so in theory this driver + * should cover RT9387A as well. This has not been tested, please + * update the compatibles if you add RT9387A support. + * + * Linus Walleij <linus.walleij@linaro.org> + */ +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/gpio/consumer.h> +#include <linux/led-class-flash.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/property.h> +#include <linux/regulator/consumer.h> + +#include <media/v4l2-flash-led-class.h> + +/* We can provide 15-700 mA out to the LED */ +#define RT8515_MIN_IOUT_MA 15 +#define RT8515_MAX_IOUT_MA 700 +/* The maximum intensity is 1-16 for flash and 1-100 for torch */ +#define RT8515_FLASH_MAX 16 +#define RT8515_TORCH_MAX 100 + +#define RT8515_TIMEOUT_US 250000U +#define RT8515_MAX_TIMEOUT_US 300000U + +struct rt8515 { + struct led_classdev_flash fled; + struct device *dev; + struct v4l2_flash *v4l2_flash; + struct mutex lock; + struct regulator *reg; + struct gpio_desc *enable_torch; + struct gpio_desc *enable_flash; + struct timer_list powerdown_timer; + u32 max_timeout; /* Flash max timeout */ + int flash_max_intensity; + int torch_max_intensity; +}; + +static struct rt8515 *to_rt8515(struct led_classdev_flash *fled) +{ + return container_of(fled, struct rt8515, fled); +} + +static void rt8515_gpio_led_off(struct rt8515 *rt) +{ + gpiod_set_value(rt->enable_flash, 0); + gpiod_set_value(rt->enable_torch, 0); +} + +static void rt8515_gpio_brightness_commit(struct gpio_desc *gpiod, + int brightness) +{ + int i; + + /* + * Toggling a GPIO line with a small delay increases the + * brightness one step at a time. + */ + for (i = 0; i < brightness; i++) { + gpiod_set_value(gpiod, 0); + udelay(1); + gpiod_set_value(gpiod, 1); + udelay(1); + } +} + +/* This is setting the torch light level */ +static int rt8515_led_brightness_set(struct led_classdev *led, + enum led_brightness brightness) +{ + struct led_classdev_flash *fled = lcdev_to_flcdev(led); + struct rt8515 *rt = to_rt8515(fled); + + mutex_lock(&rt->lock); + + if (brightness == LED_OFF) { + /* Off */ + rt8515_gpio_led_off(rt); + } else if (brightness < RT8515_TORCH_MAX) { + /* Step it up to movie mode brightness using the flash pin */ + rt8515_gpio_brightness_commit(rt->enable_torch, brightness); + } else { + /* Max torch brightness requested */ + gpiod_set_value(rt->enable_torch, 1); + } + + mutex_unlock(&rt->lock); + + return 0; +} + +static int rt8515_led_flash_strobe_set(struct led_classdev_flash *fled, + bool state) +{ + struct rt8515 *rt = to_rt8515(fled); + struct led_flash_setting *timeout = &fled->timeout; + int brightness = rt->flash_max_intensity; + + mutex_lock(&rt->lock); + + if (state) { + /* Enable LED flash mode and set brightness */ + rt8515_gpio_brightness_commit(rt->enable_flash, brightness); + /* Set timeout */ + mod_timer(&rt->powerdown_timer, + jiffies + usecs_to_jiffies(timeout->val)); + } else { + del_timer_sync(&rt->powerdown_timer); + /* Turn the LED off */ + rt8515_gpio_led_off(rt); + } + + fled->led_cdev.brightness = LED_OFF; + /* After this the torch LED will be disabled */ + + mutex_unlock(&rt->lock); + + return 0; +} + +static int rt8515_led_flash_strobe_get(struct led_classdev_flash *fled, + bool *state) +{ + struct rt8515 *rt = to_rt8515(fled); + + *state = timer_pending(&rt->powerdown_timer); + + return 0; +} + +static int rt8515_led_flash_timeout_set(struct led_classdev_flash *fled, + u32 timeout) +{ + /* The timeout is stored in the led-class-flash core */ + return 0; +} + +static const struct led_flash_ops rt8515_flash_ops = { + .strobe_set = rt8515_led_flash_strobe_set, + .strobe_get = rt8515_led_flash_strobe_get, + .timeout_set = rt8515_led_flash_timeout_set, +}; + +static void rt8515_powerdown_timer(struct timer_list *t) +{ + struct rt8515 *rt = from_timer(rt, t, powerdown_timer); + + /* Turn the LED off */ + rt8515_gpio_led_off(rt); +} + +static void rt8515_init_flash_timeout(struct rt8515 *rt) +{ + struct led_classdev_flash *fled = &rt->fled; + struct led_flash_setting *s; + + /* Init flash timeout setting */ + s = &fled->timeout; + s->min = 1; + s->max = rt->max_timeout; + s->step = 1; + /* + * Set default timeout to RT8515_TIMEOUT_US except if + * max_timeout from DT is lower. + */ + s->val = min(rt->max_timeout, RT8515_TIMEOUT_US); +} + +#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS) +/* Configure the V2L2 flash subdevice */ +static void rt8515_init_v4l2_flash_config(struct rt8515 *rt, + struct v4l2_flash_config *v4l2_sd_cfg) +{ + struct led_classdev *led = &rt->fled.led_cdev; + struct led_flash_setting *s; + + strscpy(v4l2_sd_cfg->dev_name, led->dev->kobj.name, + sizeof(v4l2_sd_cfg->dev_name)); + + /* + * Init flash intensity setting: this is a linear scale + * capped from the device tree max intensity setting + * 1..flash_max_intensity + */ + s = &v4l2_sd_cfg->intensity; + s->min = 1; + s->max = rt->flash_max_intensity; + s->step = 1; + s->val = s->max; +} + +static void rt8515_v4l2_flash_release(struct rt8515 *rt) +{ + v4l2_flash_release(rt->v4l2_flash); +} + +#else +static void rt8515_init_v4l2_flash_config(struct rt8515 *rt, + struct v4l2_flash_config *v4l2_sd_cfg) +{ +} + +static void rt8515_v4l2_flash_release(struct rt8515 *rt) +{ +} +#endif + +static void rt8515_determine_max_intensity(struct rt8515 *rt, + struct fwnode_handle *led, + const char *resistance, + const char *max_ua_prop, int hw_max, + int *max_intensity_setting) +{ + u32 res = 0; /* Can't be 0 so 0 is undefined */ + u32 ua; + u32 max_ma; + int max_intensity; + int ret; + + fwnode_property_read_u32(rt->dev->fwnode, resistance, &res); + ret = fwnode_property_read_u32(led, max_ua_prop, &ua); + + /* Missing info in DT, OK go with hardware maxima */ + if (ret || res == 0) { + dev_err(rt->dev, + "either %s or %s missing from DT, using HW max\n", + resistance, max_ua_prop); + max_ma = RT8515_MAX_IOUT_MA; + max_intensity = hw_max; + goto out_assign_max; + } + + /* + * Formula from the datasheet, this is the maximum current + * defined by the hardware. + */ + max_ma = (5500 * 1000) / res; + /* + * Calculate max intensity (linear scaling) + * Formula is ((ua / 1000) / max_ma) * 100, then simplified + */ + max_intensity = (ua / 10) / max_ma; + + dev_info(rt->dev, + "current restricted from %u to %u mA, max intensity %d/100\n", + max_ma, (ua / 1000), max_intensity); + +out_assign_max: + dev_info(rt->dev, "max intensity %d/%d = %d mA\n", + max_intensity, hw_max, max_ma); + *max_intensity_setting = max_intensity; +} + +static int rt8515_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct fwnode_handle *child; + struct rt8515 *rt; + struct led_classdev *led; + struct led_classdev_flash *fled; + struct led_init_data init_data = {}; + struct v4l2_flash_config v4l2_sd_cfg = {}; + int ret; + + rt = devm_kzalloc(dev, sizeof(*rt), GFP_KERNEL); + if (!rt) + return -ENOMEM; + + rt->dev = dev; + fled = &rt->fled; + led = &fled->led_cdev; + + /* ENF - Enable Flash line */ + rt->enable_flash = devm_gpiod_get(dev, "enf", GPIOD_OUT_LOW); + if (IS_ERR(rt->enable_flash)) + return dev_err_probe(dev, PTR_ERR(rt->enable_flash), + "cannot get ENF (enable flash) GPIO\n"); + + /* ENT - Enable Torch line */ + rt->enable_torch = devm_gpiod_get(dev, "ent", GPIOD_OUT_LOW); + if (IS_ERR(rt->enable_torch)) + return dev_err_probe(dev, PTR_ERR(rt->enable_torch), + "cannot get ENT (enable torch) GPIO\n"); + + child = fwnode_get_next_available_child_node(dev->fwnode, NULL); + if (!child) { + dev_err(dev, + "No fwnode child node found for connected LED.\n"); + return -EINVAL; + } + init_data.fwnode = child; + + rt8515_determine_max_intensity(rt, child, "richtek,rfs-ohms", + "flash-max-microamp", + RT8515_FLASH_MAX, + &rt->flash_max_intensity); + rt8515_determine_max_intensity(rt, child, "richtek,rts-ohms", + "led-max-microamp", + RT8515_TORCH_MAX, + &rt->torch_max_intensity); + + ret = fwnode_property_read_u32(child, "flash-max-timeout-us", + &rt->max_timeout); + if (ret) { + rt->max_timeout = RT8515_MAX_TIMEOUT_US; + dev_warn(dev, + "flash-max-timeout-us property missing\n"); + } + timer_setup(&rt->powerdown_timer, rt8515_powerdown_timer, 0); + rt8515_init_flash_timeout(rt); + + fled->ops = &rt8515_flash_ops; + + led->max_brightness = rt->torch_max_intensity; + led->brightness_set_blocking = rt8515_led_brightness_set; + led->flags |= LED_CORE_SUSPENDRESUME | LED_DEV_CAP_FLASH; + + mutex_init(&rt->lock); + + platform_set_drvdata(pdev, rt); + + ret = devm_led_classdev_flash_register_ext(dev, fled, &init_data); + if (ret) { + dev_err(dev, "can't register LED %s\n", led->name); + mutex_destroy(&rt->lock); + return ret; + } + + rt8515_init_v4l2_flash_config(rt, &v4l2_sd_cfg); + + /* Create a V4L2 Flash device if V4L2 flash is enabled */ + rt->v4l2_flash = v4l2_flash_init(dev, child, fled, NULL, &v4l2_sd_cfg); + if (IS_ERR(rt->v4l2_flash)) { + ret = PTR_ERR(rt->v4l2_flash); + dev_err(dev, "failed to register V4L2 flash device (%d)\n", + ret); + /* + * Continue without the V4L2 flash + * (we still have the classdev) + */ + } + + return 0; +} + +static int rt8515_remove(struct platform_device *pdev) +{ + struct rt8515 *rt = platform_get_drvdata(pdev); + + rt8515_v4l2_flash_release(rt); + del_timer_sync(&rt->powerdown_timer); + mutex_destroy(&rt->lock); + + return 0; +} + +static const struct of_device_id rt8515_match[] = { + { .compatible = "richtek,rt8515", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, rt8515_match); + +static struct platform_driver rt8515_driver = { + .driver = { + .name = "rt8515", + .of_match_table = rt8515_match, + }, + .probe = rt8515_probe, + .remove = rt8515_remove, +}; +module_platform_driver(rt8515_driver); + +MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>"); +MODULE_DESCRIPTION("Richtek RT8515 LED driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 91da90cfb11d..4e7b78a84149 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -378,14 +378,15 @@ void led_trigger_event(struct led_trigger *trig, enum led_brightness brightness) { struct led_classdev *led_cdev; + unsigned long flags; if (!trig) return; - read_lock(&trig->leddev_list_lock); + read_lock_irqsave(&trig->leddev_list_lock, flags); list_for_each_entry(led_cdev, &trig->led_cdevs, trig_list) led_set_brightness(led_cdev, brightness); - read_unlock(&trig->leddev_list_lock); + read_unlock_irqrestore(&trig->leddev_list_lock, flags); } EXPORT_SYMBOL_GPL(led_trigger_event); @@ -396,11 +397,12 @@ static void led_trigger_blink_setup(struct led_trigger *trig, int invert) { struct led_classdev *led_cdev; + unsigned long flags; if (!trig) return; - read_lock(&trig->leddev_list_lock); + read_lock_irqsave(&trig->leddev_list_lock, flags); list_for_each_entry(led_cdev, &trig->led_cdevs, trig_list) { if (oneshot) led_blink_set_oneshot(led_cdev, delay_on, delay_off, @@ -408,7 +410,7 @@ static void led_trigger_blink_setup(struct led_trigger *trig, else led_blink_set(led_cdev, delay_on, delay_off); } - read_unlock(&trig->leddev_list_lock); + read_unlock_irqrestore(&trig->leddev_list_lock, flags); } void led_trigger_blink(struct led_trigger *trig, diff --git a/drivers/leds/leds-ariel.c b/drivers/leds/leds-ariel.c index bb68ba23a7d4..49e1bddaa15e 100644 --- a/drivers/leds/leds-ariel.c +++ b/drivers/leds/leds-ariel.c @@ -96,14 +96,14 @@ static int ariel_led_probe(struct platform_device *pdev) return -ENOMEM; leds[0].ec_index = EC_BLUE_LED; - leds[0].led_cdev.name = "blue:power", + leds[0].led_cdev.name = "blue:power"; leds[0].led_cdev.default_trigger = "default-on"; leds[1].ec_index = EC_AMBER_LED; - leds[1].led_cdev.name = "amber:status", + leds[1].led_cdev.name = "amber:status"; leds[2].ec_index = EC_GREEN_LED; - leds[2].led_cdev.name = "green:status", + leds[2].led_cdev.name = "green:status"; leds[2].led_cdev.default_trigger = "default-on"; for (i = 0; i < NLEDS; i++) { diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c index b3edee703193..9dd205870525 100644 --- a/drivers/leds/leds-lm3533.c +++ b/drivers/leds/leds-lm3533.c @@ -679,7 +679,7 @@ static int lm3533_led_probe(struct platform_device *pdev) led->cdev.brightness_get = lm3533_led_get; led->cdev.blink_set = lm3533_led_blink_set; led->cdev.brightness = LED_OFF; - led->cdev.groups = lm3533_led_attribute_groups, + led->cdev.groups = lm3533_led_attribute_groups; led->id = pdev->id; mutex_init(&led->mutex); diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index c1bcac71008c..28ddcaa5358b 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -844,11 +844,10 @@ static int nvm_bb_chunk_sense(struct nvm_dev *dev, struct ppa_addr ppa) rqd.ppa_addr = generic_to_dev_addr(dev, ppa); ret = nvm_submit_io_sync_raw(dev, &rqd); + __free_page(page); if (ret) return ret; - __free_page(page); - return rqd.error; } diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index 84fc2c0f0101..d1c8fd3977fc 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -33,6 +33,8 @@ #define BCH_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline int bch_has_feature_##name(struct cache_sb *sb) \ { \ + if (sb->version < BCACHE_SB_VERSION_CDEV_WITH_FEATURES) \ + return 0; \ return (((sb)->feature_compat & \ BCH##_FEATURE_COMPAT_##flagname) != 0); \ } \ @@ -50,6 +52,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \ #define BCH_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline int bch_has_feature_##name(struct cache_sb *sb) \ { \ + if (sb->version < BCACHE_SB_VERSION_CDEV_WITH_FEATURES) \ + return 0; \ return (((sb)->feature_ro_compat & \ BCH##_FEATURE_RO_COMPAT_##flagname) != 0); \ } \ @@ -67,6 +71,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \ #define BCH_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline int bch_has_feature_##name(struct cache_sb *sb) \ { \ + if (sb->version < BCACHE_SB_VERSION_CDEV_WITH_FEATURES) \ + return 0; \ return (((sb)->feature_incompat & \ BCH##_FEATURE_INCOMPAT_##flagname) != 0); \ } \ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 8c874710f0bc..5a55617a08e6 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1481,9 +1481,9 @@ static int crypt_alloc_req_skcipher(struct crypt_config *cc, static int crypt_alloc_req_aead(struct crypt_config *cc, struct convert_context *ctx) { - if (!ctx->r.req) { - ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); - if (!ctx->r.req) + if (!ctx->r.req_aead) { + ctx->r.req_aead = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req_aead) return -ENOMEM; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 81df019ab284..b64fede032dc 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -257,8 +257,9 @@ struct dm_integrity_c { bool journal_uptodate; bool just_formatted; bool recalculate_flag; - bool fix_padding; bool discard; + bool fix_padding; + bool legacy_recalculate; struct alg_spec internal_hash_alg; struct alg_spec journal_crypt_alg; @@ -386,6 +387,14 @@ static int dm_integrity_failed(struct dm_integrity_c *ic) return READ_ONCE(ic->failed); } +static bool dm_integrity_disable_recalculate(struct dm_integrity_c *ic) +{ + if ((ic->internal_hash_alg.key || ic->journal_mac_alg.key) && + !ic->legacy_recalculate) + return true; + return false; +} + static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned i, unsigned j, unsigned char seq) { @@ -3140,6 +3149,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, arg_count += !!ic->journal_crypt_alg.alg_string; arg_count += !!ic->journal_mac_alg.alg_string; arg_count += (ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0; + arg_count += ic->legacy_recalculate; DMEMIT("%s %llu %u %c %u", ic->dev->name, ic->start, ic->tag_size, ic->mode, arg_count); if (ic->meta_dev) @@ -3163,6 +3173,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type, } if ((ic->sb->flags & cpu_to_le32(SB_FLAG_FIXED_PADDING)) != 0) DMEMIT(" fix_padding"); + if (ic->legacy_recalculate) + DMEMIT(" legacy_recalculate"); #define EMIT_ALG(a, n) \ do { \ @@ -3792,7 +3804,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) unsigned extra_args; struct dm_arg_set as; static const struct dm_arg _args[] = { - {0, 15, "Invalid number of feature args"}, + {0, 16, "Invalid number of feature args"}, }; unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec; bool should_write_sb; @@ -3940,6 +3952,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) ic->discard = true; } else if (!strcmp(opt_string, "fix_padding")) { ic->fix_padding = true; + } else if (!strcmp(opt_string, "legacy_recalculate")) { + ic->legacy_recalculate = true; } else { r = -EINVAL; ti->error = "Invalid argument"; @@ -4235,6 +4249,20 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } + } else { + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) { + ti->error = "Recalculate can only be specified with internal_hash"; + r = -EINVAL; + goto bad; + } + } + + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) && + le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors && + dm_integrity_disable_recalculate(ic)) { + ti->error = "Recalculating with HMAC is disabled for security reasons - if you really need it, use the argument \"legacy_recalculate\""; + r = -EOPNOTSUPP; + goto bad; } ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 188f41287f18..4acf2342f7ad 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -363,14 +363,23 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, { int r; dev_t dev; + unsigned int major, minor; + char dummy; struct dm_dev_internal *dd; struct dm_table *t = ti->table; BUG_ON(!t); - dev = dm_get_dev_t(path); - if (!dev) - return -ENODEV; + if (sscanf(path, "%u:%u%c", &major, &minor, &dummy) == 2) { + /* Extract the major/minor numbers */ + dev = MKDEV(major, minor); + if (MAJOR(dev) != major || MINOR(dev) != minor) + return -EOVERFLOW; + } else { + dev = dm_get_dev_t(path); + if (!dev) + return -ENODEV; + } dd = find_device(&t->devices, dev); if (!dd) { diff --git a/drivers/md/md.c b/drivers/md/md.c index ca409428b4fc..04384452a7ab 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -639,8 +639,10 @@ static void md_submit_flush_data(struct work_struct *ws) * could wait for this and below md_handle_request could wait for those * bios because of suspend check */ + spin_lock_irq(&mddev->lock); mddev->prev_flush_start = mddev->start_flush; mddev->flush_bio = NULL; + spin_unlock_irq(&mddev->lock); wake_up(&mddev->sb_wait); if (bio->bi_iter.bi_size == 0) { diff --git a/drivers/media/cec/platform/Makefile b/drivers/media/cec/platform/Makefile index 3a947159b25a..ea6f8ee8161c 100644 --- a/drivers/media/cec/platform/Makefile +++ b/drivers/media/cec/platform/Makefile @@ -10,5 +10,6 @@ obj-$(CONFIG_CEC_MESON_AO) += meson/ obj-$(CONFIG_CEC_SAMSUNG_S5P) += s5p/ obj-$(CONFIG_CEC_SECO) += seco/ obj-$(CONFIG_CEC_STI) += sti/ +obj-$(CONFIG_CEC_STM32) += stm32/ obj-$(CONFIG_CEC_TEGRA) += tegra/ diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 96d3b2b2aa31..3f61f5863bf7 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -118,8 +118,7 @@ static int __verify_length(struct vb2_buffer *vb, const struct v4l2_buffer *b) return -EINVAL; } } else { - length = (b->memory == VB2_MEMORY_USERPTR || - b->memory == VB2_MEMORY_DMABUF) + length = (b->memory == VB2_MEMORY_USERPTR) ? b->length : vb->planes[0].length; if (b->bytesused > length) diff --git a/drivers/media/i2c/ccs-pll.c b/drivers/media/i2c/ccs-pll.c index eb7b6f01f623..58ca47e904a1 100644 --- a/drivers/media/i2c/ccs-pll.c +++ b/drivers/media/i2c/ccs-pll.c @@ -772,14 +772,8 @@ int ccs_pll_calculate(struct device *dev, const struct ccs_pll_limits *lim, switch (pll->bus_type) { case CCS_PLL_BUS_TYPE_CSI2_DPHY: - /* CSI transfers 2 bits per clock per lane; thus times 2 */ - op_sys_clk_freq_hz_sdr = pll->link_freq * 2 - * (pll->flags & CCS_PLL_FLAG_LANE_SPEED_MODEL ? - 1 : pll->csi2.lanes); - break; case CCS_PLL_BUS_TYPE_CSI2_CPHY: - op_sys_clk_freq_hz_sdr = - pll->link_freq + op_sys_clk_freq_hz_sdr = pll->link_freq * 2 * (pll->flags & CCS_PLL_FLAG_LANE_SPEED_MODEL ? 1 : pll->csi2.lanes); break; diff --git a/drivers/media/i2c/ccs/ccs-data.c b/drivers/media/i2c/ccs/ccs-data.c index 9a6097b088bd..6555bd4b325a 100644 --- a/drivers/media/i2c/ccs/ccs-data.c +++ b/drivers/media/i2c/ccs/ccs-data.c @@ -152,7 +152,7 @@ static int ccs_data_parse_version(struct bin_container *bin, vv->version_major = ((u16)v->static_data_version_major[0] << 8) + v->static_data_version_major[1]; vv->version_minor = ((u16)v->static_data_version_minor[0] << 8) + - v->static_data_version_major[1]; + v->static_data_version_minor[1]; vv->date_year = ((u16)v->year[0] << 8) + v->year[1]; vv->date_month = v->month; vv->date_day = v->day; diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2.c b/drivers/media/pci/intel/ipu3/ipu3-cio2.c index 36e354ecf71e..6cada8a6e50c 100644 --- a/drivers/media/pci/intel/ipu3/ipu3-cio2.c +++ b/drivers/media/pci/intel/ipu3/ipu3-cio2.c @@ -302,7 +302,7 @@ static int cio2_csi2_calc_timing(struct cio2_device *cio2, struct cio2_queue *q, if (!q->sensor) return -ENODEV; - freq = v4l2_get_link_rate(q->sensor->ctrl_handler, bpp, lanes); + freq = v4l2_get_link_freq(q->sensor->ctrl_handler, bpp, lanes); if (freq < 0) { dev_err(dev, "error %lld, invalid link_freq\n", freq); return freq; diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index bdd293faaad0..7233a7311757 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -349,8 +349,10 @@ static void venus_core_shutdown(struct platform_device *pdev) { struct venus_core *core = platform_get_drvdata(pdev); + pm_runtime_get_sync(core->dev); venus_shutdown(core); venus_firmware_deinit(core); + pm_runtime_put_sync(core->dev); } static __maybe_unused int venus_runtime_suspend(struct device *dev) diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c index 98bff765b02e..e48d666f2c63 100644 --- a/drivers/media/platform/rcar-vin/rcar-core.c +++ b/drivers/media/platform/rcar-vin/rcar-core.c @@ -654,7 +654,7 @@ static int rvin_parallel_parse_of(struct rvin_dev *vin) out: fwnode_handle_put(fwnode); - return 0; + return ret; } static int rvin_parallel_init(struct rvin_dev *vin) diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c index 68da1eed753d..f7e9fd305548 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c @@ -104,6 +104,7 @@ struct rkisp1_match_data { const char * const *clks; unsigned int size; + enum rkisp1_cif_isp_version isp_ver; }; /* ---------------------------------------------------------------------------- @@ -411,15 +412,16 @@ static const char * const rk3399_isp_clks[] = { "hclk", }; -static const struct rkisp1_match_data rk3399_isp_clk_data = { +static const struct rkisp1_match_data rk3399_isp_match_data = { .clks = rk3399_isp_clks, .size = ARRAY_SIZE(rk3399_isp_clks), + .isp_ver = RKISP1_V10, }; static const struct of_device_id rkisp1_of_match[] = { { .compatible = "rockchip,rk3399-cif-isp", - .data = &rk3399_isp_clk_data, + .data = &rk3399_isp_match_data, }, {}, }; @@ -457,15 +459,15 @@ static void rkisp1_debug_init(struct rkisp1_device *rkisp1) static int rkisp1_probe(struct platform_device *pdev) { - const struct rkisp1_match_data *clk_data; + const struct rkisp1_match_data *match_data; struct device *dev = &pdev->dev; struct rkisp1_device *rkisp1; struct v4l2_device *v4l2_dev; unsigned int i; int ret, irq; - clk_data = of_device_get_match_data(&pdev->dev); - if (!clk_data) + match_data = of_device_get_match_data(&pdev->dev); + if (!match_data) return -ENODEV; rkisp1 = devm_kzalloc(dev, sizeof(*rkisp1), GFP_KERNEL); @@ -494,15 +496,16 @@ static int rkisp1_probe(struct platform_device *pdev) rkisp1->irq = irq; - for (i = 0; i < clk_data->size; i++) - rkisp1->clks[i].id = clk_data->clks[i]; - ret = devm_clk_bulk_get(dev, clk_data->size, rkisp1->clks); + for (i = 0; i < match_data->size; i++) + rkisp1->clks[i].id = match_data->clks[i]; + ret = devm_clk_bulk_get(dev, match_data->size, rkisp1->clks); if (ret) return ret; - rkisp1->clk_size = clk_data->size; + rkisp1->clk_size = match_data->size; pm_runtime_enable(&pdev->dev); + rkisp1->media_dev.hw_revision = match_data->isp_ver; strscpy(rkisp1->media_dev.model, RKISP1_DRIVER_NAME, sizeof(rkisp1->media_dev.model)); rkisp1->media_dev.dev = &pdev->dev; diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c index 6af4d551ffb5..aa5f45749543 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c @@ -391,7 +391,7 @@ static void rkisp1_goc_config(struct rkisp1_params *params, RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA); rkisp1_write(params->rkisp1, arg->mode, RKISP1_CIF_ISP_GAMMA_OUT_MODE); - for (i = 0; i < RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES; i++) + for (i = 0; i < RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10; i++) rkisp1_write(params->rkisp1, arg->gamma_y[i], RKISP1_CIF_ISP_GAMMA_OUT_Y_0 + i * 4); } @@ -589,7 +589,6 @@ static void rkisp1_hst_config(struct rkisp1_params *params, RKISP1_CIF_ISP_HIST_WEIGHT_22TO03, RKISP1_CIF_ISP_HIST_WEIGHT_13TO43, RKISP1_CIF_ISP_HIST_WEIGHT_04TO34, - RKISP1_CIF_ISP_HIST_WEIGHT_44, }; const u8 *weight; unsigned int i; @@ -622,6 +621,8 @@ static void rkisp1_hst_config(struct rkisp1_params *params, weight[2], weight[3]), hist_weight_regs[i]); + + rkisp1_write(params->rkisp1, weight[0] & 0x1F, RKISP1_CIF_ISP_HIST_WEIGHT_44); } static void diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h index 8a8d960a679c..fa33080f51db 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h @@ -365,6 +365,7 @@ #define RKISP1_CIF_ISP_MAX_HIST_PREDIVIDER 0x0000007F #define RKISP1_CIF_ISP_HIST_ROW_NUM 5 #define RKISP1_CIF_ISP_HIST_COLUMN_NUM 5 +#define RKISP1_CIF_ISP_HIST_GET_BIN(x) ((x) & 0x000FFFFF) /* AUTO FOCUS MEASUREMENT: ISP_AFM_CTRL */ #define RKISP1_ISP_AFM_CTRL_ENABLE BIT(0) diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c index 3ddab8fa8f2d..c1d07a2e8839 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-stats.c @@ -203,7 +203,7 @@ static void rkisp1_stats_get_aec_meas(struct rkisp1_stats *stats, unsigned int i; pbuf->meas_type |= RKISP1_CIF_ISP_STAT_AUTOEXP; - for (i = 0; i < RKISP1_CIF_ISP_AE_MEAN_MAX; i++) + for (i = 0; i < RKISP1_CIF_ISP_AE_MEAN_MAX_V10; i++) pbuf->params.ae.exp_mean[i] = (u8)rkisp1_read(rkisp1, RKISP1_CIF_ISP_EXP_MEAN_00 + i * 4); @@ -233,10 +233,11 @@ static void rkisp1_stats_get_hst_meas(struct rkisp1_stats *stats, unsigned int i; pbuf->meas_type |= RKISP1_CIF_ISP_STAT_HIST; - for (i = 0; i < RKISP1_CIF_ISP_HIST_BIN_N_MAX; i++) - pbuf->params.hist.hist_bins[i] = - (u8)rkisp1_read(rkisp1, - RKISP1_CIF_ISP_HIST_BIN_0 + i * 4); + for (i = 0; i < RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10; i++) { + u32 reg_val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_HIST_BIN_0 + i * 4); + + pbuf->params.hist.hist_bins[i] = RKISP1_CIF_ISP_HIST_GET_BIN(reg_val); + } } static void rkisp1_stats_get_bls_meas(struct rkisp1_stats *stats, diff --git a/drivers/media/rc/ir-mce_kbd-decoder.c b/drivers/media/rc/ir-mce_kbd-decoder.c index be8f2756a444..1524dc0fc566 100644 --- a/drivers/media/rc/ir-mce_kbd-decoder.c +++ b/drivers/media/rc/ir-mce_kbd-decoder.c @@ -320,7 +320,7 @@ again: data->body); spin_lock(&data->keylock); if (scancode) { - delay = nsecs_to_jiffies(dev->timeout) + + delay = usecs_to_jiffies(dev->timeout) + msecs_to_jiffies(100); mod_timer(&data->rx_timeout, jiffies + delay); } else { diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c index a905113fef6e..0c6229592e13 100644 --- a/drivers/media/rc/ite-cir.c +++ b/drivers/media/rc/ite-cir.c @@ -1551,7 +1551,7 @@ static int ite_probe(struct pnp_dev *pdev, const struct pnp_device_id rdev->s_rx_carrier_range = ite_set_rx_carrier_range; /* FIFO threshold is 17 bytes, so 17 * 8 samples minimum */ rdev->min_timeout = 17 * 8 * ITE_BAUDRATE_DIVISOR * - itdev->params.sample_period; + itdev->params.sample_period / 1000; rdev->timeout = IR_DEFAULT_TIMEOUT; rdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT; rdev->rx_resolution = ITE_BAUDRATE_DIVISOR * diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 1d811e5ffb55..1fd62c1dac76 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -737,7 +737,7 @@ static unsigned int repeat_period(int protocol) void rc_repeat(struct rc_dev *dev) { unsigned long flags; - unsigned int timeout = nsecs_to_jiffies(dev->timeout) + + unsigned int timeout = usecs_to_jiffies(dev->timeout) + msecs_to_jiffies(repeat_period(dev->last_protocol)); struct lirc_scancode sc = { .scancode = dev->last_scancode, .rc_proto = dev->last_protocol, @@ -855,7 +855,7 @@ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u64 scancode, ir_do_keydown(dev, protocol, scancode, keycode, toggle); if (dev->keypressed) { - dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) + + dev->keyup_jiffies = jiffies + usecs_to_jiffies(dev->timeout) + msecs_to_jiffies(repeat_period(protocol)); mod_timer(&dev->timer_keyup, dev->keyup_jiffies); } @@ -1928,6 +1928,8 @@ int rc_register_device(struct rc_dev *dev) goto out_raw; } + dev->registered = true; + rc = device_add(&dev->dev); if (rc) goto out_rx_free; @@ -1937,8 +1939,6 @@ int rc_register_device(struct rc_dev *dev) dev->device_name ?: "Unspecified device", path ?: "N/A"); kfree(path); - dev->registered = true; - /* * once the the input device is registered in rc_setup_rx_device, * userspace can open the input device and rc_open() will be called diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c index 8cc28c92d05d..96ae0294ac10 100644 --- a/drivers/media/rc/serial_ir.c +++ b/drivers/media/rc/serial_ir.c @@ -385,7 +385,7 @@ static irqreturn_t serial_ir_irq_handler(int i, void *blah) } while (!(sinp(UART_IIR) & UART_IIR_NO_INT)); /* still pending ? */ mod_timer(&serial_ir.timeout_timer, - jiffies + nsecs_to_jiffies(serial_ir.rcdev->timeout)); + jiffies + usecs_to_jiffies(serial_ir.rcdev->timeout)); ir_raw_event_handle(serial_ir.rcdev); diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 78007dba4677..133d20e40f82 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -442,7 +442,7 @@ int v4l2_fill_pixfmt(struct v4l2_pix_format *pixfmt, u32 pixelformat, } EXPORT_SYMBOL_GPL(v4l2_fill_pixfmt); -s64 v4l2_get_link_rate(struct v4l2_ctrl_handler *handler, unsigned int mul, +s64 v4l2_get_link_freq(struct v4l2_ctrl_handler *handler, unsigned int mul, unsigned int div) { struct v4l2_ctrl *ctrl; @@ -473,4 +473,4 @@ s64 v4l2_get_link_rate(struct v4l2_ctrl_handler *handler, unsigned int mul, return freq > 0 ? freq : -EINVAL; } -EXPORT_SYMBOL_GPL(v4l2_get_link_rate); +EXPORT_SYMBOL_GPL(v4l2_get_link_freq); diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 2aa6648fa41f..5a491d2cd1ae 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1512,6 +1512,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, struct pcr_handle *handle; u32 base, len; int ret, i, bar = 0; + u8 val; dev_dbg(&(pcidev->dev), ": Realtek PCI-E Card Reader found at %s [%04x:%04x] (rev %x)\n", @@ -1577,7 +1578,11 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, pcr->host_cmds_addr = pcr->rtsx_resv_buf_addr; pcr->host_sg_tbl_ptr = pcr->rtsx_resv_buf + HOST_CMDS_BUF_LEN; pcr->host_sg_tbl_addr = pcr->rtsx_resv_buf_addr + HOST_CMDS_BUF_LEN; - + rtsx_pci_read_register(pcr, ASPM_FORCE_CTL, &val); + if (val & FORCE_ASPM_CTL0 && val & FORCE_ASPM_CTL1) + pcr->aspm_enabled = false; + else + pcr->aspm_enabled = true; pcr->card_inserted = 0; pcr->card_removed = 0; INIT_DELAYED_WORK(&pcr->carddet_work, rtsx_pci_card_detect); diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 1456eabf9601..69d04eca767f 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -1037,7 +1037,7 @@ kill_processes: if (hard_reset) { /* Release kernel context */ - if (hl_ctx_put(hdev->kernel_ctx) == 1) + if (hdev->kernel_ctx && hl_ctx_put(hdev->kernel_ctx) == 1) hdev->kernel_ctx = NULL; hl_vm_fini(hdev); hl_mmu_fini(hdev); @@ -1487,6 +1487,15 @@ void hl_device_fini(struct hl_device *hdev) } } + /* Disable PCI access from device F/W so it won't send us additional + * interrupts. We disable MSI/MSI-X at the halt_engines function and we + * can't have the F/W sending us interrupts after that. We need to + * disable the access here because if the device is marked disable, the + * message won't be send. Also, in case of heartbeat, the device CPU is + * marked as disable so this message won't be sent + */ + hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS); + /* Mark device as disabled */ hdev->disabled = true; diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c index 20f77f58edef..c9a12980218a 100644 --- a/drivers/misc/habanalabs/common/firmware_if.c +++ b/drivers/misc/habanalabs/common/firmware_if.c @@ -402,6 +402,10 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev, } counters->rx_throughput = result; + memset(&pkt, 0, sizeof(pkt)); + pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_THROUGHPUT_GET << + CPUCP_PKT_CTL_OPCODE_SHIFT); + /* Fetch PCI tx counter */ pkt.index = cpu_to_le32(cpucp_pcie_throughput_tx); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), @@ -414,6 +418,7 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev, counters->tx_throughput = result; /* Fetch PCI replay counter */ + memset(&pkt, 0, sizeof(pkt)); pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_REPLAY_CNT_GET << CPUCP_PKT_CTL_OPCODE_SHIFT); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index e0d7f5fbaa5c..60e16dc4bcac 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -2182,6 +2182,7 @@ void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu); int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr); int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_info *hops); +bool hl_is_dram_va(struct hl_device *hdev, u64 virt_addr); int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name, void __iomem *dst, u32 src_offset, u32 size); diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c index 12efbd9d2e3a..d25892d61ec9 100644 --- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c @@ -133,6 +133,8 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args) hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev, &hw_idle.busy_engines_mask_ext, NULL); + hw_idle.busy_engines_mask = + lower_32_bits(hw_idle.busy_engines_mask_ext); return copy_to_user(out, &hw_idle, min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0; diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index cbe9da4e0211..5d4fbdcaefe3 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -886,8 +886,10 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr, { struct hl_device *hdev = ctx->hdev; u64 next_vaddr, i; + bool is_host_addr; u32 page_size; + is_host_addr = !hl_is_dram_va(hdev, vaddr); page_size = phys_pg_pack->page_size; next_vaddr = vaddr; @@ -900,9 +902,13 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr, /* * unmapping on Palladium can be really long, so avoid a CPU * soft lockup bug by sleeping a little between unmapping pages + * + * In addition, when unmapping host memory we pass through + * the Linux kernel to unpin the pages and that takes a long + * time. Therefore, sleep every 32K pages to avoid soft lockup */ - if (hdev->pldm) - usleep_range(500, 1000); + if (hdev->pldm || (is_host_addr && (i & 0x7FFF) == 0)) + usleep_range(50, 200); } } diff --git a/drivers/misc/habanalabs/common/mmu.c b/drivers/misc/habanalabs/common/mmu.c index 33ae953d3a36..28a4638741d8 100644 --- a/drivers/misc/habanalabs/common/mmu.c +++ b/drivers/misc/habanalabs/common/mmu.c @@ -9,7 +9,7 @@ #include "habanalabs.h" -static bool is_dram_va(struct hl_device *hdev, u64 virt_addr) +bool hl_is_dram_va(struct hl_device *hdev, u64 virt_addr) { struct asic_fixed_properties *prop = &hdev->asic_prop; @@ -156,7 +156,7 @@ int hl_mmu_unmap_page(struct hl_ctx *ctx, u64 virt_addr, u32 page_size, if (!hdev->mmu_enable) return 0; - is_dram_addr = is_dram_va(hdev, virt_addr); + is_dram_addr = hl_is_dram_va(hdev, virt_addr); if (is_dram_addr) mmu_prop = &prop->dmmu; @@ -236,7 +236,7 @@ int hl_mmu_map_page(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, if (!hdev->mmu_enable) return 0; - is_dram_addr = is_dram_va(hdev, virt_addr); + is_dram_addr = hl_is_dram_va(hdev, virt_addr); if (is_dram_addr) mmu_prop = &prop->dmmu; diff --git a/drivers/misc/habanalabs/common/mmu_v1.c b/drivers/misc/habanalabs/common/mmu_v1.c index 2ce6ea89d4fa..06d8a44dd5d4 100644 --- a/drivers/misc/habanalabs/common/mmu_v1.c +++ b/drivers/misc/habanalabs/common/mmu_v1.c @@ -467,8 +467,16 @@ static void hl_mmu_v1_fini(struct hl_device *hdev) { /* MMU H/W fini was already done in device hw_fini() */ - kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0); - gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool); + if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) { + kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0); + gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool); + } + + /* Make sure that if we arrive here again without init was called we + * won't cause kernel panic. This can happen for example if we fail + * during hard reset code at certain points + */ + hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL; } /** diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 8c09e4466af8..b328ddaa64ee 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -4002,7 +4002,8 @@ static int gaudi_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma, vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE; - rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size); + rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, + (dma_addr - HOST_PHYS_BASE), size); if (rc) dev_err(hdev->dev, "dma_mmap_coherent error %d", rc); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index b8b4aa636b7c..63679a747d2c 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2719,7 +2719,8 @@ static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma, vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE; - rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size); + rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, + (dma_addr - HOST_PHYS_BASE), size); if (rc) dev_err(hdev->dev, "dma_mmap_coherent error %d", rc); diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index de7cb0369c30..002426e3cf76 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -384,8 +384,10 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) "merging was advertised but not possible"); blk_queue_max_segments(mq->queue, mmc_get_max_segments(host)); - if (mmc_card_mmc(card)) + if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) { block_size = card->ext_csd.data_sector_size; + WARN_ON(block_size != 512 && block_size != 4096); + } blk_queue_logical_block_size(mq->queue, block_size); /* diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c index bbf3496f4495..f9780c65ebe9 100644 --- a/drivers/mmc/host/sdhci-brcmstb.c +++ b/drivers/mmc/host/sdhci-brcmstb.c @@ -314,11 +314,7 @@ err_clk: static void sdhci_brcmstb_shutdown(struct platform_device *pdev) { - int ret; - - ret = sdhci_pltfm_unregister(pdev); - if (ret) - dev_err(&pdev->dev, "failed to shutdown\n"); + sdhci_pltfm_suspend(&pdev->dev); } MODULE_DEVICE_TABLE(of, sdhci_brcm_of_match); diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 4b673792b5a4..d90020ed3622 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -16,6 +16,8 @@ #include "sdhci-pltfm.h" +#define SDHCI_DWCMSHC_ARG2_STUFF GENMASK(31, 16) + /* DWCMSHC specific Mode Select value */ #define DWCMSHC_CTRL_HS400 0x7 @@ -49,6 +51,29 @@ static void dwcmshc_adma_write_desc(struct sdhci_host *host, void **desc, sdhci_adma_write_desc(host, desc, addr, len, cmd); } +static void dwcmshc_check_auto_cmd23(struct mmc_host *mmc, + struct mmc_request *mrq) +{ + struct sdhci_host *host = mmc_priv(mmc); + + /* + * No matter V4 is enabled or not, ARGUMENT2 register is 32-bit + * block count register which doesn't support stuff bits of + * CMD23 argument on dwcmsch host controller. + */ + if (mrq->sbc && (mrq->sbc->arg & SDHCI_DWCMSHC_ARG2_STUFF)) + host->flags &= ~SDHCI_AUTO_CMD23; + else + host->flags |= SDHCI_AUTO_CMD23; +} + +static void dwcmshc_request(struct mmc_host *mmc, struct mmc_request *mrq) +{ + dwcmshc_check_auto_cmd23(mmc, mrq); + + sdhci_request(mmc, mrq); +} + static void dwcmshc_set_uhs_signaling(struct sdhci_host *host, unsigned int timing) { @@ -133,6 +158,8 @@ static int dwcmshc_probe(struct platform_device *pdev) sdhci_get_of_property(pdev); + host->mmc_host_ops.request = dwcmshc_request; + err = sdhci_add_host(host); if (err) goto err_clk; diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index c67611fdaa8a..d19eef5f725f 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -168,7 +168,12 @@ static void xenon_reset_exit(struct sdhci_host *host, /* Disable tuning request and auto-retuning again */ xenon_retune_setup(host); - xenon_set_acg(host, true); + /* + * The ACG should be turned off at the early init time, in order + * to solve a possible issues with the 1.8V regulator stabilization. + * The feature is enabled in later stage. + */ + xenon_set_acg(host, false); xenon_set_sdclk_off_idle(host, sdhc_id, false); diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 5cdf05bcbf8f..3fa8c22d3f36 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -1615,7 +1615,7 @@ static int gpmi_ecc_read_page_raw(struct nand_chip *chip, uint8_t *buf, /* Extract interleaved payload data and ECC bits */ for (step = 0; step < nfc_geo->ecc_chunk_count; step++) { if (buf) - nand_extract_bits(buf, step * eccsize, tmp_buf, + nand_extract_bits(buf, step * eccsize * 8, tmp_buf, src_bit_off, eccsize * 8); src_bit_off += eccsize * 8; diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c index fdb112e8a90d..a304fda5d1fa 100644 --- a/drivers/mtd/nand/raw/intel-nand-controller.c +++ b/drivers/mtd/nand/raw/intel-nand-controller.c @@ -579,7 +579,7 @@ static int ebu_nand_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct ebu_nand_controller *ebu_host; struct nand_chip *nand; - struct mtd_info *mtd = NULL; + struct mtd_info *mtd; struct resource *res; char *resname; int ret; @@ -647,12 +647,13 @@ static int ebu_nand_probe(struct platform_device *pdev) ebu_host->ebu + EBU_ADDR_SEL(cs)); nand_set_flash_node(&ebu_host->chip, dev->of_node); + + mtd = nand_to_mtd(&ebu_host->chip); if (!mtd->name) { dev_err(ebu_host->dev, "NAND label property is mandatory\n"); return -EINVAL; } - mtd = nand_to_mtd(&ebu_host->chip); mtd->dev.parent = dev; ebu_host->dev = dev; diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index f2b9250c0ea8..0750121ac371 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -2210,6 +2210,9 @@ static int ns_attach_chip(struct nand_chip *chip) { unsigned int eccsteps, eccbytes; + chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; + chip->ecc.algo = bch ? NAND_ECC_ALGO_BCH : NAND_ECC_ALGO_HAMMING; + if (!bch) return 0; @@ -2233,8 +2236,6 @@ static int ns_attach_chip(struct nand_chip *chip) return -EINVAL; } - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_BCH; chip->ecc.size = 512; chip->ecc.strength = bch; chip->ecc.bytes = eccbytes; @@ -2273,8 +2274,6 @@ static int __init ns_init_module(void) nsmtd = nand_to_mtd(chip); nand_set_controller_data(chip, (void *)ns); - chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT; - chip->ecc.algo = NAND_ECC_ALGO_HAMMING; /* The NAND_SKIP_BBTSCAN option is necessary for 'overridesize' */ /* and 'badblocks' parameters to work */ chip->options |= NAND_SKIP_BBTSCAN; diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index fbb9955f2467..2c3e65cb68f3 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -15,6 +15,7 @@ #include <linux/jiffies.h> #include <linux/sched.h> #include <linux/mtd/mtd.h> +#include <linux/mtd/nand-ecc-sw-bch.h> #include <linux/mtd/rawnand.h> #include <linux/mtd/partitions.h> #include <linux/omap-dma.h> @@ -1866,18 +1867,19 @@ static const struct mtd_ooblayout_ops omap_ooblayout_ops = { static int omap_sw_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *oobregion) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct nand_device *nand = mtd_to_nanddev(mtd); + const struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv; int off = BADBLOCK_MARKER_LENGTH; - if (section >= chip->ecc.steps) + if (section >= engine_conf->nsteps) return -ERANGE; /* * When SW correction is employed, one OMAP specific marker byte is * reserved after each ECC step. */ - oobregion->offset = off + (section * (chip->ecc.bytes + 1)); - oobregion->length = chip->ecc.bytes; + oobregion->offset = off + (section * (engine_conf->code_size + 1)); + oobregion->length = engine_conf->code_size; return 0; } @@ -1885,7 +1887,8 @@ static int omap_sw_ooblayout_ecc(struct mtd_info *mtd, int section, static int omap_sw_ooblayout_free(struct mtd_info *mtd, int section, struct mtd_oob_region *oobregion) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct nand_device *nand = mtd_to_nanddev(mtd); + const struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv; int off = BADBLOCK_MARKER_LENGTH; if (section) @@ -1895,7 +1898,7 @@ static int omap_sw_ooblayout_free(struct mtd_info *mtd, int section, * When SW correction is employed, one OMAP specific marker byte is * reserved after each ECC step. */ - off += ((chip->ecc.bytes + 1) * chip->ecc.steps); + off += ((engine_conf->code_size + 1) * engine_conf->nsteps); if (off >= mtd->oobsize) return -ERANGE; diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 8ea545bb924d..61d932c1b718 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -343,6 +343,7 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand, const struct nand_page_io_req *req) { struct nand_device *nand = spinand_to_nand(spinand); + struct mtd_info *mtd = spinand_to_mtd(spinand); struct spi_mem_dirmap_desc *rdesc; unsigned int nbytes = 0; void *buf = NULL; @@ -382,9 +383,16 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand, memcpy(req->databuf.in, spinand->databuf + req->dataoffs, req->datalen); - if (req->ooblen) - memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs, - req->ooblen); + if (req->ooblen) { + if (req->mode == MTD_OPS_AUTO_OOB) + mtd_ooblayout_get_databytes(mtd, req->oobbuf.in, + spinand->oobbuf, + req->ooboffs, + req->ooblen); + else + memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs, + req->ooblen); + } return 0; } diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 98df38fe553c..12d085405bd0 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -332,7 +332,7 @@ static int __init arc_rimi_init(void) dev->irq = 9; if (arcrimi_probe(dev)) { - free_netdev(dev); + free_arcdev(dev); return -EIO; } @@ -349,7 +349,7 @@ static void __exit arc_rimi_exit(void) iounmap(lp->mem_start); release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); free_irq(dev->irq, dev); - free_netdev(dev); + free_arcdev(dev); } #ifndef MODULE diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 22a49c6d7ae6..5d4a4c7efbbf 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -298,6 +298,10 @@ struct arcnet_local { int excnak_pending; /* We just got an excesive nak interrupt */ + /* RESET flag handling */ + int reset_in_progress; + struct work_struct reset_work; + struct { uint16_t sequence; /* sequence number (incs with each packet) */ __be16 aborted_seq; @@ -350,7 +354,9 @@ void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) void arcnet_unregister_proto(struct ArcProto *proto); irqreturn_t arcnet_interrupt(int irq, void *dev_id); + struct net_device *alloc_arcdev(const char *name); +void free_arcdev(struct net_device *dev); int arcnet_open(struct net_device *dev); int arcnet_close(struct net_device *dev); diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index e04efc0a5c97..1bad1866ae46 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -387,15 +387,49 @@ static void arcnet_timer(struct timer_list *t) struct arcnet_local *lp = from_timer(lp, t, timer); struct net_device *dev = lp->dev; - if (!netif_carrier_ok(dev)) { + spin_lock_irq(&lp->lock); + + if (!lp->reset_in_progress && !netif_carrier_ok(dev)) { netif_carrier_on(dev); netdev_info(dev, "link up\n"); } + + spin_unlock_irq(&lp->lock); } -static void arcnet_reply_tasklet(unsigned long data) +static void reset_device_work(struct work_struct *work) { - struct arcnet_local *lp = (struct arcnet_local *)data; + struct arcnet_local *lp; + struct net_device *dev; + + lp = container_of(work, struct arcnet_local, reset_work); + dev = lp->dev; + + /* Do not bring the network interface back up if an ifdown + * was already done. + */ + if (!netif_running(dev) || !lp->reset_in_progress) + return; + + rtnl_lock(); + + /* Do another check, in case of an ifdown that was triggered in + * the small race window between the exit condition above and + * acquiring RTNL. + */ + if (!netif_running(dev) || !lp->reset_in_progress) + goto out; + + dev_close(dev); + dev_open(dev, NULL); + +out: + rtnl_unlock(); +} + +static void arcnet_reply_tasklet(struct tasklet_struct *t) +{ + struct arcnet_local *lp = from_tasklet(lp, t, reply_tasklet); struct sk_buff *ackskb, *skb; struct sock_exterr_skb *serr; @@ -452,12 +486,25 @@ struct net_device *alloc_arcdev(const char *name) lp->dev = dev; spin_lock_init(&lp->lock); timer_setup(&lp->timer, arcnet_timer, 0); + INIT_WORK(&lp->reset_work, reset_device_work); } return dev; } EXPORT_SYMBOL(alloc_arcdev); +void free_arcdev(struct net_device *dev) +{ + struct arcnet_local *lp = netdev_priv(dev); + + /* Do not cancel this at ->ndo_close(), as the workqueue itself + * indirectly calls the ifdown path through dev_close(). + */ + cancel_work_sync(&lp->reset_work); + free_netdev(dev); +} +EXPORT_SYMBOL(free_arcdev); + /* Open/initialize the board. This is called sometime after booting when * the 'ifconfig' program is run. * @@ -483,8 +530,7 @@ int arcnet_open(struct net_device *dev) arc_cont(D_PROTO, "\n"); } - tasklet_init(&lp->reply_tasklet, arcnet_reply_tasklet, - (unsigned long)lp); + tasklet_setup(&lp->reply_tasklet, arcnet_reply_tasklet); arc_printk(D_INIT, dev, "arcnet_open: resetting card.\n"); @@ -587,6 +633,10 @@ int arcnet_close(struct net_device *dev) /* shut down the card */ lp->hw.close(dev); + + /* reset counters */ + lp->reset_in_progress = 0; + module_put(lp->hw.owner); return 0; } @@ -820,6 +870,9 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) spin_lock_irqsave(&lp->lock, flags); + if (lp->reset_in_progress) + goto out; + /* RESET flag was enabled - if device is not running, we must * clear it right away (but nothing else). */ @@ -852,11 +905,14 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) if (status & RESETflag) { arc_printk(D_NORMAL, dev, "spurious reset (status=%Xh)\n", status); - arcnet_close(dev); - arcnet_open(dev); + + lp->reset_in_progress = 1; + netif_stop_queue(dev); + netif_carrier_off(dev); + schedule_work(&lp->reset_work); /* get out of the interrupt handler! */ - break; + goto out; } /* RX is inhibited - we must have received something. * Prepare to receive into the next buffer. @@ -1052,6 +1108,7 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) udelay(1); lp->hw.intmask(dev, lp->intmask); +out: spin_unlock_irqrestore(&lp->lock, flags); return retval; } diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index f983c4ce6b07..be618e4b9ed5 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -169,7 +169,7 @@ static int __init com20020_init(void) dev->irq = 9; if (com20020isa_probe(dev)) { - free_netdev(dev); + free_arcdev(dev); return -EIO; } @@ -182,7 +182,7 @@ static void __exit com20020_exit(void) unregister_netdev(my_dev); free_irq(my_dev->irq, my_dev); release_region(my_dev->base_addr, ARCNET_TOTAL_SIZE); - free_netdev(my_dev); + free_arcdev(my_dev); } #ifndef MODULE diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index eb7f76753c9c..8bdc44b7e09a 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -291,7 +291,7 @@ static void com20020pci_remove(struct pci_dev *pdev) unregister_netdev(dev); free_irq(dev->irq, dev); - free_netdev(dev); + free_arcdev(dev); } } diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 81223f6bebcc..b88a109b3b15 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -177,7 +177,7 @@ static void com20020_detach(struct pcmcia_device *link) dev = info->dev; if (dev) { dev_dbg(&link->dev, "kfree...\n"); - free_netdev(dev); + free_arcdev(dev); } dev_dbg(&link->dev, "kfree2...\n"); kfree(info); diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index cf214b730671..3856b447d38e 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -396,7 +396,7 @@ static int __init com90io_init(void) err = com90io_probe(dev); if (err) { - free_netdev(dev); + free_arcdev(dev); return err; } @@ -419,7 +419,7 @@ static void __exit com90io_exit(void) free_irq(dev->irq, dev); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); - free_netdev(dev); + free_arcdev(dev); } module_init(com90io_init) diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index 3dc3d533cb19..d8dfb9ea0de8 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -554,7 +554,7 @@ err_free_irq: err_release_mem: release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); err_free_dev: - free_netdev(dev); + free_arcdev(dev); return -EIO; } @@ -672,7 +672,7 @@ static void __exit com90xx_exit(void) release_region(dev->base_addr, ARCNET_TOTAL_SIZE); release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); - free_netdev(dev); + free_arcdev(dev); } } diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 47a6d62b7511..106f089eb2a8 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -598,9 +598,9 @@ err: return NETDEV_TX_OK; } -static void cfv_tx_release_tasklet(unsigned long drv) +static void cfv_tx_release_tasklet(struct tasklet_struct *t) { - struct cfv_info *cfv = (struct cfv_info *)drv; + struct cfv_info *cfv = from_tasklet(cfv, t, tx_release_tasklet); cfv_release_used_buf(cfv->vq_tx); } @@ -716,9 +716,7 @@ static int cfv_probe(struct virtio_device *vdev) cfv->ctx.head = USHRT_MAX; netif_napi_add(netdev, &cfv->napi, cfv_rx_poll, CFV_DEFAULT_QUOTA); - tasklet_init(&cfv->tx_release_tasklet, - cfv_tx_release_tasklet, - (unsigned long)cfv); + tasklet_setup(&cfv->tx_release_tasklet, cfv_tx_release_tasklet); /* Carrier is off until netdevice is opened */ netif_carrier_off(netdev); diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 3ae884cdf677..867f6be31230 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -263,7 +263,7 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); struct can_ctrlmode cm = {.flags = priv->ctrlmode}; - struct can_berr_counter bec; + struct can_berr_counter bec = { }; enum can_state state = priv->state; if (priv->do_get_state) diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 3638b474d86b..3c5b92911d46 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -596,11 +596,9 @@ static int mcp251xfd_chip_clock_enable(const struct mcp251xfd_priv *priv) "Timeout waiting for Oscillator Ready (osc=0x%08x, osc_reference=0x%08x)\n", osc, osc_reference); return -ETIMEDOUT; - } else if (err) { - return err; } - return 0; + return err; } static int mcp251xfd_chip_softreset_do(const struct mcp251xfd_priv *priv) @@ -651,7 +649,7 @@ static int mcp251xfd_chip_softreset_check(const struct mcp251xfd_priv *priv) if (osc != osc_reference) { netdev_info(priv->ndev, - "Controller failed to reset. osc=0x%08x, reference value=0x%08x\n", + "Controller failed to reset. osc=0x%08x, reference value=0x%08x.\n", osc, osc_reference); return -ETIMEDOUT; } @@ -666,7 +664,7 @@ static int mcp251xfd_chip_softreset(const struct mcp251xfd_priv *priv) for (i = 0; i < MCP251XFD_SOFTRESET_RETRIES_MAX; i++) { if (i) netdev_info(priv->ndev, - "Retrying to reset Controller.\n"); + "Retrying to reset controller.\n"); err = mcp251xfd_chip_softreset_do(priv); if (err == -ETIMEDOUT) @@ -1239,7 +1237,7 @@ mcp251xfd_handle_tefif_recover(const struct mcp251xfd_priv *priv, const u32 seq) } netdev_info(priv->ndev, - "Transmit Event FIFO buffer %s. (seq=0x%08x, tef_tail=0x%08x, tef_head=0x%08x, tx_head=0x%08x)\n", + "Transmit Event FIFO buffer %s. (seq=0x%08x, tef_tail=0x%08x, tef_head=0x%08x, tx_head=0x%08x).\n", tef_sta & MCP251XFD_REG_TEFSTA_TEFFIF ? "full" : tef_sta & MCP251XFD_REG_TEFSTA_TEFNEIF ? "not empty" : "empty", @@ -1465,7 +1463,7 @@ mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv, hw_rx_obj->id); } - dlc = FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC, hw_rx_obj->flags); + dlc = FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC_MASK, hw_rx_obj->flags); /* CANFD */ if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_FDF) { @@ -1891,7 +1889,7 @@ mcp251xfd_handle_modif(const struct mcp251xfd_priv *priv, bool *set_normal_mode) "Controller changed into %s Mode (%u).\n", mcp251xfd_get_mode_str(mode), mode); - /* After the application requests Normal mode, the Controller + /* After the application requests Normal mode, the controller * will automatically attempt to retransmit the message that * caused the TX MAB underflow. * @@ -2359,7 +2357,7 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv, priv->can.ctrlmode); } - flags |= FIELD_PREP(MCP251XFD_OBJ_FLAGS_DLC, dlc); + flags |= FIELD_PREP(MCP251XFD_OBJ_FLAGS_DLC_MASK, dlc); load_buf = &tx_obj->buf; if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_TX) @@ -2851,32 +2849,28 @@ static int mcp251xfd_probe(struct spi_device *spi) rx_int = devm_gpiod_get_optional(&spi->dev, "microchip,rx-int", GPIOD_IN); - if (PTR_ERR(rx_int) == -EPROBE_DEFER) - return -EPROBE_DEFER; - else if (IS_ERR(rx_int)) - return PTR_ERR(rx_int); + if (IS_ERR(rx_int)) + return dev_err_probe(&spi->dev, PTR_ERR(rx_int), + "Failed to get RX-INT!\n"); reg_vdd = devm_regulator_get_optional(&spi->dev, "vdd"); - if (PTR_ERR(reg_vdd) == -EPROBE_DEFER) - return -EPROBE_DEFER; - else if (PTR_ERR(reg_vdd) == -ENODEV) + if (PTR_ERR(reg_vdd) == -ENODEV) reg_vdd = NULL; else if (IS_ERR(reg_vdd)) - return PTR_ERR(reg_vdd); + return dev_err_probe(&spi->dev, PTR_ERR(reg_vdd), + "Failed to get VDD regulator!\n"); reg_xceiver = devm_regulator_get_optional(&spi->dev, "xceiver"); - if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER) - return -EPROBE_DEFER; - else if (PTR_ERR(reg_xceiver) == -ENODEV) + if (PTR_ERR(reg_xceiver) == -ENODEV) reg_xceiver = NULL; else if (IS_ERR(reg_xceiver)) - return PTR_ERR(reg_xceiver); + return dev_err_probe(&spi->dev, PTR_ERR(reg_xceiver), + "Failed to get Transceiver regulator!\n"); clk = devm_clk_get(&spi->dev, NULL); - if (IS_ERR(clk)) { - dev_err(&spi->dev, "No Oscillator (clock) defined.\n"); - return PTR_ERR(clk); - } + if (IS_ERR(clk)) + dev_err_probe(&spi->dev, PTR_ERR(clk), + "Failed to get Oscillator (clock)!\n"); freq = clk_get_rate(clk); /* Sanity check */ @@ -2932,7 +2926,7 @@ static int mcp251xfd_probe(struct spi_device *spi) spi_get_device_id(spi)->driver_data; /* Errata Reference: - * mcp2517fd: DS80000789B, mcp2518fd: DS80000792C 4. + * mcp2517fd: DS80000792C 5., mcp2518fd: DS80000789C 4. * * The SPI can write corrupted data to the RAM at fast SPI * speeds: @@ -2945,18 +2939,16 @@ static int mcp251xfd_probe(struct spi_device *spi) * Ensure that FSCK is less than or equal to 0.85 * * (FSYSCLK/2). * - * Known good and bad combinations are: + * Known good combinations are: * - * MCP ext-clk SoC SPI SPI-clk max-clk parent-clk Status config + * MCP ext-clk SoC SPI SPI-clk max-clk parent-clk config * - * 2518 20 MHz allwinner,sun8i-h3 allwinner,sun8i-h3-spi 8333333 Hz 83.33% 600000000 Hz good assigned-clocks = <&ccu CLK_SPIx> - * 2518 20 MHz allwinner,sun8i-h3 allwinner,sun8i-h3-spi 9375000 Hz 93.75% 600000000 Hz bad assigned-clocks = <&ccu CLK_SPIx> - * 2518 40 MHz allwinner,sun8i-h3 allwinner,sun8i-h3-spi 16666667 Hz 83.33% 600000000 Hz good assigned-clocks = <&ccu CLK_SPIx> - * 2518 40 MHz allwinner,sun8i-h3 allwinner,sun8i-h3-spi 18750000 Hz 93.75% 600000000 Hz bad assigned-clocks = <&ccu CLK_SPIx> - * 2517 20 MHz fsl,imx8mm fsl,imx51-ecspi 8333333 Hz 83.33% 16666667 Hz good assigned-clocks = <&clk IMX8MM_CLK_ECSPIx_ROOT> - * 2517 20 MHz fsl,imx8mm fsl,imx51-ecspi 9523809 Hz 95.34% 28571429 Hz bad assigned-clocks = <&clk IMX8MM_CLK_ECSPIx_ROOT> - * 2517 40 MHz atmel,sama5d27 atmel,at91rm9200-spi 16400000 Hz 82.00% 82000000 Hz good default - * 2518 40 MHz atmel,sama5d27 atmel,at91rm9200-spi 16400000 Hz 82.00% 82000000 Hz good default + * 2518 20 MHz allwinner,sun8i-h3 allwinner,sun8i-h3-spi 8333333 Hz 83.33% 600000000 Hz assigned-clocks = <&ccu CLK_SPIx> + * 2518 40 MHz allwinner,sun8i-h3 allwinner,sun8i-h3-spi 16666667 Hz 83.33% 600000000 Hz assigned-clocks = <&ccu CLK_SPIx> + * 2517 40 MHz atmel,sama5d27 atmel,at91rm9200-spi 16400000 Hz 82.00% 82000000 Hz default + * 2518 40 MHz atmel,sama5d27 atmel,at91rm9200-spi 16400000 Hz 82.00% 82000000 Hz default + * 2518 40 MHz fsl,imx6dl fsl,imx51-ecspi 15000000 Hz 75.00% 30000000 Hz default + * 2517 20 MHz fsl,imx8mm fsl,imx51-ecspi 8333333 Hz 83.33% 16666667 Hz assigned-clocks = <&clk IMX8MM_CLK_ECSPIx_ROOT> * */ priv->spi_max_speed_hz_orig = spi->max_speed_hz; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index cb6398c2a560..480bd4480bdf 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -305,7 +305,7 @@ #define MCP251XFD_OBJ_FLAGS_BRS BIT(6) #define MCP251XFD_OBJ_FLAGS_RTR BIT(5) #define MCP251XFD_OBJ_FLAGS_IDE BIT(4) -#define MCP251XFD_OBJ_FLAGS_DLC GENMASK(3, 0) +#define MCP251XFD_OBJ_FLAGS_DLC_MASK GENMASK(3, 0) #define MCP251XFD_REG_FRAME_EFF_SID_MASK GENMASK(28, 18) #define MCP251XFD_REG_FRAME_EFF_EID_MASK GENMASK(17, 0) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index d53485c79d77..1857aa9aa84a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -510,15 +510,19 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) /* Find our integrated MDIO bus node */ dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio"); priv->master_mii_bus = of_mdio_find_bus(dn); - if (!priv->master_mii_bus) + if (!priv->master_mii_bus) { + of_node_put(dn); return -EPROBE_DEFER; + } get_device(&priv->master_mii_bus->dev); priv->master_mii_dn = dn; priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev); - if (!priv->slave_mii_bus) + if (!priv->slave_mii_bus) { + of_node_put(dn); return -ENOMEM; + } priv->slave_mii_bus->priv = priv; priv->slave_mii_bus->name = "sf2 slave mii"; diff --git a/drivers/net/dsa/hirschmann/Kconfig b/drivers/net/dsa/hirschmann/Kconfig index e01191107a4b..9ea2c643f8f8 100644 --- a/drivers/net/dsa/hirschmann/Kconfig +++ b/drivers/net/dsa/hirschmann/Kconfig @@ -5,6 +5,7 @@ config NET_DSA_HIRSCHMANN_HELLCREEK depends on NET_DSA depends on PTP_1588_CLOCK depends on LEDS_CLASS + depends on NET_SCH_TAPRIO select NET_DSA_TAG_HELLCREEK help This driver adds support for Hirschmann Hellcreek TSN switches. diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 4cc51fb37e67..f984ca75a71f 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -221,12 +221,11 @@ static void hellcreek_feature_detect(struct hellcreek *hellcreek) features = hellcreek_read(hellcreek, HR_FEABITS0); - /* Currently we only detect the size of the FDB table */ + /* Only detect the size of the FDB table. The size and current + * utilization can be queried via devlink. + */ hellcreek->fdb_entries = ((features & HR_FEABITS0_FDBBINS_MASK) >> HR_FEABITS0_FDBBINS_SHIFT) * 32; - - dev_info(hellcreek->dev, "Feature detect: FDB entries=%zu\n", - hellcreek->fdb_entries); } static enum dsa_tag_protocol hellcreek_get_tag_protocol(struct dsa_switch *ds, @@ -1000,6 +999,84 @@ out: return ret; } +static u64 hellcreek_devlink_vlan_table_get(void *priv) +{ + struct hellcreek *hellcreek = priv; + u64 count = 0; + int i; + + mutex_lock(&hellcreek->reg_lock); + for (i = 0; i < VLAN_N_VID; ++i) + if (hellcreek->vidmbrcfg[i]) + count++; + mutex_unlock(&hellcreek->reg_lock); + + return count; +} + +static u64 hellcreek_devlink_fdb_table_get(void *priv) +{ + struct hellcreek *hellcreek = priv; + u64 count = 0; + + /* Reading this register has side effects. Synchronize against the other + * FDB operations. + */ + mutex_lock(&hellcreek->reg_lock); + count = hellcreek_read(hellcreek, HR_FDBMAX); + mutex_unlock(&hellcreek->reg_lock); + + return count; +} + +static int hellcreek_setup_devlink_resources(struct dsa_switch *ds) +{ + struct devlink_resource_size_params size_vlan_params; + struct devlink_resource_size_params size_fdb_params; + struct hellcreek *hellcreek = ds->priv; + int err; + + devlink_resource_size_params_init(&size_vlan_params, VLAN_N_VID, + VLAN_N_VID, + 1, DEVLINK_RESOURCE_UNIT_ENTRY); + + devlink_resource_size_params_init(&size_fdb_params, + hellcreek->fdb_entries, + hellcreek->fdb_entries, + 1, DEVLINK_RESOURCE_UNIT_ENTRY); + + err = dsa_devlink_resource_register(ds, "VLAN", VLAN_N_VID, + HELLCREEK_DEVLINK_PARAM_ID_VLAN_TABLE, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_vlan_params); + if (err) + goto out; + + err = dsa_devlink_resource_register(ds, "FDB", hellcreek->fdb_entries, + HELLCREEK_DEVLINK_PARAM_ID_FDB_TABLE, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_fdb_params); + if (err) + goto out; + + dsa_devlink_resource_occ_get_register(ds, + HELLCREEK_DEVLINK_PARAM_ID_VLAN_TABLE, + hellcreek_devlink_vlan_table_get, + hellcreek); + + dsa_devlink_resource_occ_get_register(ds, + HELLCREEK_DEVLINK_PARAM_ID_FDB_TABLE, + hellcreek_devlink_fdb_table_get, + hellcreek); + + return 0; + +out: + dsa_devlink_resources_unregister(ds); + + return err; +} + static int hellcreek_setup(struct dsa_switch *ds) { struct hellcreek *hellcreek = ds->priv; @@ -1053,9 +1130,22 @@ static int hellcreek_setup(struct dsa_switch *ds) return ret; } + /* Register devlink resources with DSA */ + ret = hellcreek_setup_devlink_resources(ds); + if (ret) { + dev_err(hellcreek->dev, + "Failed to setup devlink resources!\n"); + return ret; + } + return 0; } +static void hellcreek_teardown(struct dsa_switch *ds) +{ + dsa_devlink_resources_unregister(ds); +} + static void hellcreek_phylink_validate(struct dsa_switch *ds, int port, unsigned long *supported, struct phylink_link_state *state) @@ -1447,6 +1537,7 @@ static const struct dsa_switch_ops hellcreek_ds_ops = { .port_vlan_del = hellcreek_vlan_del, .port_vlan_filtering = hellcreek_vlan_filtering, .setup = hellcreek_setup, + .teardown = hellcreek_teardown, }; static int hellcreek_probe(struct platform_device *pdev) diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h index 854639f87247..305e76dab34d 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.h +++ b/drivers/net/dsa/hirschmann/hellcreek.h @@ -298,4 +298,10 @@ struct hellcreek { #define dw_to_hellcreek_port(dw) \ container_of(dw, struct hellcreek_port, schedule_work) +/* Devlink resources */ +enum hellcreek_devlink_resource_id { + HELLCREEK_DEVLINK_PARAM_ID_VLAN_TABLE, + HELLCREEK_DEVLINK_PARAM_ID_FDB_TABLE, +}; + #endif /* _HELLCREEK_H_ */ diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 37a73421e2cc..c87d445b30fd 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1183,6 +1183,20 @@ static const struct ksz_chip_data ksz8795_switch_chips[] = { .port_cnt = 5, /* total cpu and user ports */ }, { + /* + * WARNING + * ======= + * KSZ8794 is similar to KSZ8795, except the port map + * contains a gap between external and CPU ports, the + * port map is NOT continuous. The per-port register + * map is shifted accordingly too, i.e. registers at + * offset 0x40 are NOT used on KSZ8794 and they ARE + * used on KSZ8795 for external port 3. + * external cpu + * KSZ8794 0,1,2 4 + * KSZ8795 0,1,2,3 4 + * KSZ8765 0,1,2,3 4 + */ .chip_id = 0x8794, .dev_name = "KSZ8794", .num_vlans = 4096, @@ -1216,9 +1230,13 @@ static int ksz8795_switch_init(struct ksz_device *dev) dev->num_vlans = chip->num_vlans; dev->num_alus = chip->num_alus; dev->num_statics = chip->num_statics; - dev->port_cnt = chip->port_cnt; + dev->port_cnt = fls(chip->cpu_ports); + dev->cpu_port = fls(chip->cpu_ports) - 1; + dev->phy_port_cnt = dev->port_cnt - 1; dev->cpu_ports = chip->cpu_ports; - + dev->host_mask = chip->cpu_ports; + dev->port_mask = (BIT(dev->phy_port_cnt) - 1) | + chip->cpu_ports; break; } } @@ -1227,17 +1245,9 @@ static int ksz8795_switch_init(struct ksz_device *dev) if (!dev->cpu_ports) return -ENODEV; - dev->port_mask = BIT(dev->port_cnt) - 1; - dev->port_mask |= dev->host_mask; - dev->reg_mib_cnt = KSZ8795_COUNTER_NUM; dev->mib_cnt = ARRAY_SIZE(mib_names); - dev->phy_port_cnt = dev->port_cnt - 1; - - dev->cpu_port = dev->port_cnt - 1; - dev->host_mask = BIT(dev->cpu_port); - dev->ports = devm_kzalloc(dev->dev, dev->port_cnt * sizeof(struct ksz_port), GFP_KERNEL); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 4e0619c66573..a7e5ac60baef 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -385,7 +385,7 @@ int ksz_switch_register(struct ksz_device *dev, gpiod_set_value_cansleep(dev->reset_gpio, 1); usleep_range(10000, 12000); gpiod_set_value_cansleep(dev->reset_gpio, 0); - usleep_range(100, 1000); + msleep(100); } mutex_init(&dev->dev_mutex); @@ -419,7 +419,7 @@ int ksz_switch_register(struct ksz_device *dev, if (of_property_read_u32(port, "reg", &port_num)) continue; - if (port_num >= dev->port_cnt) + if (!(dev->port_mask & BIT(port_num))) return -EINVAL; of_get_phy_mode(port, &dev->ports[port_num].interface); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index b99f27b8c084..ae0b490f00cd 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1686,7 +1686,11 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, if (!entry.portvec) entry.state = 0; } else { - entry.portvec |= BIT(port); + if (state == MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC) + entry.portvec = BIT(port); + else + entry.portvec |= BIT(port); + entry.state = state; } diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index c110e82a7973..932b6b6fe817 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -6,6 +6,7 @@ config NET_DSA_MSCC_FELIX depends on NET_VENDOR_FREESCALE depends on HAS_IOMEM select MSCC_OCELOT_SWITCH_LIB + select NET_DSA_TAG_OCELOT_8021Q select NET_DSA_TAG_OCELOT select FSL_ENETC_MDIO select PCS_LYNX @@ -19,6 +20,7 @@ config NET_DSA_MSCC_SEVILLE depends on NET_VENDOR_MICROSEMI depends on HAS_IOMEM select MSCC_OCELOT_SWITCH_LIB + select NET_DSA_TAG_OCELOT_8021Q select NET_DSA_TAG_OCELOT select PCS_LYNX help diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 767cbdccdb3e..167463010b55 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019-2021 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 @@ -13,6 +13,7 @@ #include <soc/mscc/ocelot_ana.h> #include <soc/mscc/ocelot_ptp.h> #include <soc/mscc/ocelot.h> +#include <linux/dsa/8021q.h> #include <linux/platform_device.h> #include <linux/packing.h> #include <linux/module.h> @@ -24,11 +25,474 @@ #include <net/dsa.h> #include "felix.h" +static int felix_tag_8021q_rxvlan_add(struct felix *felix, int port, u16 vid, + bool pvid, bool untagged) +{ + struct ocelot_vcap_filter *outer_tagging_rule; + struct ocelot *ocelot = &felix->ocelot; + struct dsa_switch *ds = felix->ds; + int key_length, upstream, err; + + /* We don't need to install the rxvlan into the other ports' filtering + * tables, because we're just pushing the rxvlan when sending towards + * the CPU + */ + if (!pvid) + return 0; + + key_length = ocelot->vcap[VCAP_ES0].keys[VCAP_ES0_IGR_PORT].length; + upstream = dsa_upstream_port(ds, port); + + outer_tagging_rule = kzalloc(sizeof(struct ocelot_vcap_filter), + GFP_KERNEL); + if (!outer_tagging_rule) + return -ENOMEM; + + outer_tagging_rule->key_type = OCELOT_VCAP_KEY_ANY; + outer_tagging_rule->prio = 1; + outer_tagging_rule->id.cookie = port; + outer_tagging_rule->id.tc_offload = false; + outer_tagging_rule->block_id = VCAP_ES0; + outer_tagging_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; + outer_tagging_rule->lookup = 0; + outer_tagging_rule->ingress_port.value = port; + outer_tagging_rule->ingress_port.mask = GENMASK(key_length - 1, 0); + outer_tagging_rule->egress_port.value = upstream; + outer_tagging_rule->egress_port.mask = GENMASK(key_length - 1, 0); + outer_tagging_rule->action.push_outer_tag = OCELOT_ES0_TAG; + outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD; + outer_tagging_rule->action.tag_a_vid_sel = 1; + outer_tagging_rule->action.vid_a_val = vid; + + err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL); + if (err) + kfree(outer_tagging_rule); + + return err; +} + +static int felix_tag_8021q_txvlan_add(struct felix *felix, int port, u16 vid, + bool pvid, bool untagged) +{ + struct ocelot_vcap_filter *untagging_rule, *redirect_rule; + struct ocelot *ocelot = &felix->ocelot; + struct dsa_switch *ds = felix->ds; + int upstream, err; + + /* tag_8021q.c assumes we are implementing this via port VLAN + * membership, which we aren't. So we don't need to add any VCAP filter + * for the CPU port. + */ + if (ocelot->ports[port]->is_dsa_8021q_cpu) + return 0; + + untagging_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL); + if (!untagging_rule) + return -ENOMEM; + + redirect_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL); + if (!redirect_rule) { + kfree(untagging_rule); + return -ENOMEM; + } + + upstream = dsa_upstream_port(ds, port); + + untagging_rule->key_type = OCELOT_VCAP_KEY_ANY; + untagging_rule->ingress_port_mask = BIT(upstream); + untagging_rule->vlan.vid.value = vid; + untagging_rule->vlan.vid.mask = VLAN_VID_MASK; + untagging_rule->prio = 1; + untagging_rule->id.cookie = port; + untagging_rule->id.tc_offload = false; + untagging_rule->block_id = VCAP_IS1; + untagging_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; + untagging_rule->lookup = 0; + untagging_rule->action.vlan_pop_cnt_ena = true; + untagging_rule->action.vlan_pop_cnt = 1; + untagging_rule->action.pag_override_mask = 0xff; + untagging_rule->action.pag_val = port; + + err = ocelot_vcap_filter_add(ocelot, untagging_rule, NULL); + if (err) { + kfree(untagging_rule); + kfree(redirect_rule); + return err; + } + + redirect_rule->key_type = OCELOT_VCAP_KEY_ANY; + redirect_rule->ingress_port_mask = BIT(upstream); + redirect_rule->pag = port; + redirect_rule->prio = 1; + redirect_rule->id.cookie = port; + redirect_rule->id.tc_offload = false; + redirect_rule->block_id = VCAP_IS2; + redirect_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; + redirect_rule->lookup = 0; + redirect_rule->action.mask_mode = OCELOT_MASK_MODE_REDIRECT; + redirect_rule->action.port_mask = BIT(port); + + err = ocelot_vcap_filter_add(ocelot, redirect_rule, NULL); + if (err) { + ocelot_vcap_filter_del(ocelot, untagging_rule); + kfree(redirect_rule); + return err; + } + + return 0; +} + +static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, + u16 flags) +{ + bool untagged = flags & BRIDGE_VLAN_INFO_UNTAGGED; + bool pvid = flags & BRIDGE_VLAN_INFO_PVID; + struct ocelot *ocelot = ds->priv; + + if (vid_is_dsa_8021q_rxvlan(vid)) + return felix_tag_8021q_rxvlan_add(ocelot_to_felix(ocelot), + port, vid, pvid, untagged); + + if (vid_is_dsa_8021q_txvlan(vid)) + return felix_tag_8021q_txvlan_add(ocelot_to_felix(ocelot), + port, vid, pvid, untagged); + + return 0; +} + +static int felix_tag_8021q_rxvlan_del(struct felix *felix, int port, u16 vid) +{ + struct ocelot_vcap_filter *outer_tagging_rule; + struct ocelot_vcap_block *block_vcap_es0; + struct ocelot *ocelot = &felix->ocelot; + + block_vcap_es0 = &ocelot->block[VCAP_ES0]; + + outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0, + port, false); + /* In rxvlan_add, we had the "if (!pvid) return 0" logic to avoid + * installing outer tagging ES0 rules where they weren't needed. + * But in rxvlan_del, the API doesn't give us the "flags" anymore, + * so that forces us to be slightly sloppy here, and just assume that + * if we didn't find an outer_tagging_rule it means that there was + * none in the first place, i.e. rxvlan_del is called on a non-pvid + * port. This is most probably true though. + */ + if (!outer_tagging_rule) + return 0; + + return ocelot_vcap_filter_del(ocelot, outer_tagging_rule); +} + +static int felix_tag_8021q_txvlan_del(struct felix *felix, int port, u16 vid) +{ + struct ocelot_vcap_filter *untagging_rule, *redirect_rule; + struct ocelot_vcap_block *block_vcap_is1; + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot *ocelot = &felix->ocelot; + int err; + + if (ocelot->ports[port]->is_dsa_8021q_cpu) + return 0; + + block_vcap_is1 = &ocelot->block[VCAP_IS1]; + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + untagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, + port, false); + if (!untagging_rule) + return 0; + + err = ocelot_vcap_filter_del(ocelot, untagging_rule); + if (err) + return err; + + redirect_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, + port, false); + if (!redirect_rule) + return 0; + + return ocelot_vcap_filter_del(ocelot, redirect_rule); +} + +static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) +{ + struct ocelot *ocelot = ds->priv; + + if (vid_is_dsa_8021q_rxvlan(vid)) + return felix_tag_8021q_rxvlan_del(ocelot_to_felix(ocelot), + port, vid); + + if (vid_is_dsa_8021q_txvlan(vid)) + return felix_tag_8021q_txvlan_del(ocelot_to_felix(ocelot), + port, vid); + + return 0; +} + +static const struct dsa_8021q_ops felix_tag_8021q_ops = { + .vlan_add = felix_tag_8021q_vlan_add, + .vlan_del = felix_tag_8021q_vlan_del, +}; + +/* Alternatively to using the NPI functionality, that same hardware MAC + * connected internally to the enetc or fman DSA master can be configured to + * use the software-defined tag_8021q frame format. As far as the hardware is + * concerned, it thinks it is a "dumb switch" - the queues of the CPU port + * module are now disconnected from it, but can still be accessed through + * register-based MMIO. + */ +static void felix_8021q_cpu_port_init(struct ocelot *ocelot, int port) +{ + ocelot->ports[port]->is_dsa_8021q_cpu = true; + ocelot->npi = -1; + + /* Overwrite PGID_CPU with the non-tagging port */ + ocelot_write_rix(ocelot, BIT(port), ANA_PGID_PGID, PGID_CPU); + + ocelot_apply_bridge_fwd_mask(ocelot); +} + +static void felix_8021q_cpu_port_deinit(struct ocelot *ocelot, int port) +{ + ocelot->ports[port]->is_dsa_8021q_cpu = false; + + /* Restore PGID_CPU */ + ocelot_write_rix(ocelot, BIT(ocelot->num_phys_ports), ANA_PGID_PGID, + PGID_CPU); + + ocelot_apply_bridge_fwd_mask(ocelot); +} + +static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) +{ + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + unsigned long cpu_flood; + int port, err; + + felix_8021q_cpu_port_init(ocelot, cpu); + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_unused_port(ds, port)) + continue; + + /* This overwrites ocelot_init(): + * Do not forward BPDU frames to the CPU port module, + * for 2 reasons: + * - When these packets are injected from the tag_8021q + * CPU port, we want them to go out, not loop back + * into the system. + * - STP traffic ingressing on a user port should go to + * the tag_8021q CPU port, not to the hardware CPU + * port module. + */ + ocelot_write_gix(ocelot, + ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0), + ANA_PORT_CPU_FWD_BPDU_CFG, port); + } + + /* In tag_8021q mode, the CPU port module is unused. So we + * want to disable flooding of any kind to the CPU port module, + * since packets going there will end in a black hole. + */ + cpu_flood = ANA_PGID_PGID_PGID(BIT(ocelot->num_phys_ports)); + ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_UC); + ocelot_rmw_rix(ocelot, 0, cpu_flood, ANA_PGID_PGID, PGID_MC); + + felix->dsa_8021q_ctx = kzalloc(sizeof(*felix->dsa_8021q_ctx), + GFP_KERNEL); + if (!felix->dsa_8021q_ctx) + return -ENOMEM; + + felix->dsa_8021q_ctx->ops = &felix_tag_8021q_ops; + felix->dsa_8021q_ctx->proto = htons(ETH_P_8021AD); + felix->dsa_8021q_ctx->ds = ds; + + err = dsa_8021q_setup(felix->dsa_8021q_ctx, true); + if (err) + goto out_free_dsa_8021_ctx; + + return 0; + +out_free_dsa_8021_ctx: + kfree(felix->dsa_8021q_ctx); + return err; +} + +static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu) +{ + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + int err, port; + + err = dsa_8021q_setup(felix->dsa_8021q_ctx, false); + if (err) + dev_err(ds->dev, "dsa_8021q_setup returned %d", err); + + kfree(felix->dsa_8021q_ctx); + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_unused_port(ds, port)) + continue; + + /* Restore the logic from ocelot_init: + * do not forward BPDU frames to the front ports. + */ + ocelot_write_gix(ocelot, + ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0xffff), + ANA_PORT_CPU_FWD_BPDU_CFG, + port); + } + + felix_8021q_cpu_port_deinit(ocelot, cpu); +} + +/* The CPU port module is connected to the Node Processor Interface (NPI). This + * is the mode through which frames can be injected from and extracted to an + * external CPU, over Ethernet. In NXP SoCs, the "external CPU" is the ARM CPU + * running Linux, and this forms a DSA setup together with the enetc or fman + * DSA master. + */ +static void felix_npi_port_init(struct ocelot *ocelot, int port) +{ + ocelot->npi = port; + + ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M | + QSYS_EXT_CPU_CFG_EXT_CPU_PORT(port), + QSYS_EXT_CPU_CFG); + + /* NPI port Injection/Extraction configuration */ + ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_XTR_HDR, + ocelot->npi_xtr_prefix); + ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_INJ_HDR, + ocelot->npi_inj_prefix); + + /* Disable transmission of pause frames */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0); +} + +static void felix_npi_port_deinit(struct ocelot *ocelot, int port) +{ + /* Restore hardware defaults */ + int unused_port = ocelot->num_phys_ports + 2; + + ocelot->npi = -1; + + ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPU_PORT(unused_port), + QSYS_EXT_CPU_CFG); + + ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_XTR_HDR, + OCELOT_TAG_PREFIX_DISABLED); + ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_INJ_HDR, + OCELOT_TAG_PREFIX_DISABLED); + + /* Enable transmission of pause frames */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 1); +} + +static int felix_setup_tag_npi(struct dsa_switch *ds, int cpu) +{ + struct ocelot *ocelot = ds->priv; + unsigned long cpu_flood; + + felix_npi_port_init(ocelot, cpu); + + /* Include the CPU port module (and indirectly, the NPI port) + * in the forwarding mask for unknown unicast - the hardware + * default value for ANA_FLOODING_FLD_UNICAST excludes + * BIT(ocelot->num_phys_ports), and so does ocelot_init, + * since Ocelot relies on whitelisting MAC addresses towards + * PGID_CPU. + * We do this because DSA does not yet perform RX filtering, + * and the NPI port does not perform source address learning, + * so traffic sent to Linux is effectively unknown from the + * switch's perspective. + */ + cpu_flood = ANA_PGID_PGID_PGID(BIT(ocelot->num_phys_ports)); + ocelot_rmw_rix(ocelot, cpu_flood, cpu_flood, ANA_PGID_PGID, PGID_UC); + + return 0; +} + +static void felix_teardown_tag_npi(struct dsa_switch *ds, int cpu) +{ + struct ocelot *ocelot = ds->priv; + + felix_npi_port_deinit(ocelot, cpu); +} + +static int felix_set_tag_protocol(struct dsa_switch *ds, int cpu, + enum dsa_tag_protocol proto) +{ + int err; + + switch (proto) { + case DSA_TAG_PROTO_OCELOT: + err = felix_setup_tag_npi(ds, cpu); + break; + case DSA_TAG_PROTO_OCELOT_8021Q: + err = felix_setup_tag_8021q(ds, cpu); + break; + default: + err = -EPROTONOSUPPORT; + } + + return err; +} + +static void felix_del_tag_protocol(struct dsa_switch *ds, int cpu, + enum dsa_tag_protocol proto) +{ + switch (proto) { + case DSA_TAG_PROTO_OCELOT: + felix_teardown_tag_npi(ds, cpu); + break; + case DSA_TAG_PROTO_OCELOT_8021Q: + felix_teardown_tag_8021q(ds, cpu); + break; + default: + break; + } +} + +/* This always leaves the switch in a consistent state, because although the + * tag_8021q setup can fail, the NPI setup can't. So either the change is made, + * or the restoration is guaranteed to work. + */ +static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, + enum dsa_tag_protocol proto) +{ + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + enum dsa_tag_protocol old_proto = felix->tag_proto; + int err; + + if (proto != DSA_TAG_PROTO_OCELOT && + proto != DSA_TAG_PROTO_OCELOT_8021Q) + return -EPROTONOSUPPORT; + + felix_del_tag_protocol(ds, cpu, old_proto); + + err = felix_set_tag_protocol(ds, cpu, proto); + if (err) { + felix_set_tag_protocol(ds, cpu, old_proto); + return err; + } + + felix->tag_proto = proto; + + return 0; +} + static enum dsa_tag_protocol felix_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) { - return DSA_TAG_PROTO_OCELOT; + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + + return felix->tag_proto; } static int felix_set_ageing_time(struct dsa_switch *ds, @@ -425,8 +889,8 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) ocelot->num_mact_rows = felix->info->num_mact_rows; ocelot->vcap = felix->info->vcap; ocelot->ops = felix->info->ops; - ocelot->inj_prefix = OCELOT_TAG_PREFIX_SHORT; - ocelot->xtr_prefix = OCELOT_TAG_PREFIX_SHORT; + ocelot->npi_inj_prefix = OCELOT_TAG_PREFIX_SHORT; + ocelot->npi_xtr_prefix = OCELOT_TAG_PREFIX_SHORT; ocelot->devlink = felix->ds->devlink; port_phy_modes = kcalloc(num_phys_ports, sizeof(phy_interface_t), @@ -527,28 +991,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return 0; } -/* The CPU port module is connected to the Node Processor Interface (NPI). This - * is the mode through which frames can be injected from and extracted to an - * external CPU, over Ethernet. - */ -static void felix_npi_port_init(struct ocelot *ocelot, int port) -{ - ocelot->npi = port; - - ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M | - QSYS_EXT_CPU_CFG_EXT_CPU_PORT(port), - QSYS_EXT_CPU_CFG); - - /* NPI port Injection/Extraction configuration */ - ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_XTR_HDR, - ocelot->xtr_prefix); - ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_INJ_HDR, - ocelot->inj_prefix); - - /* Disable transmission of pause frames */ - ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0); -} - /* Hardware initialization done here so that we can allocate structures with * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing * us to allocate structures twice (leak memory) and map PCI memory twice @@ -578,10 +1020,10 @@ static int felix_setup(struct dsa_switch *ds) } for (port = 0; port < ds->num_ports; port++) { - ocelot_init_port(ocelot, port); + if (dsa_is_unused_port(ds, port)) + continue; - if (dsa_is_cpu_port(ds, port)) - felix_npi_port_init(ocelot, port); + ocelot_init_port(ocelot, port); /* Set the default QoS Classification based on PCP and DEI * bits of vlan tag. @@ -593,14 +1035,15 @@ static int felix_setup(struct dsa_switch *ds) if (err) return err; - /* Include the CPU port module in the forwarding mask for unknown - * unicast - the hardware default value for ANA_FLOODING_FLD_UNICAST - * excludes BIT(ocelot->num_phys_ports), and so does ocelot_init, since - * Ocelot relies on whitelisting MAC addresses towards PGID_CPU. - */ - ocelot_write_rix(ocelot, - ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports, 0)), - ANA_PGID_PGID, PGID_UC); + for (port = 0; port < ds->num_ports; port++) { + if (!dsa_is_cpu_port(ds, port)) + continue; + + /* The initial tag protocol is NPI which always returns 0, so + * there's no real point in checking for errors. + */ + felix_set_tag_protocol(ds, port, felix->tag_proto); + } ds->mtu_enforcement_ingress = true; ds->assisted_learning_on_cpu_port = true; @@ -614,6 +1057,13 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); int port; + for (port = 0; port < ds->num_ports; port++) { + if (!dsa_is_cpu_port(ds, port)) + continue; + + felix_del_tag_protocol(ds, port, felix->tag_proto); + } + ocelot_devlink_sb_unregister(ocelot); ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -860,6 +1310,7 @@ static int felix_sb_occ_tc_port_bind_get(struct dsa_switch *ds, int port, const struct dsa_switch_ops felix_switch_ops = { .get_tag_protocol = felix_get_tag_protocol, + .change_tag_protocol = felix_change_tag_protocol, .setup = felix_setup, .teardown = felix_teardown, .set_ageing_time = felix_set_ageing_time, diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 994835cb9307..9d4459f2fffb 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -48,6 +48,8 @@ struct felix { struct lynx_pcs **pcs; resource_size_t switch_base; resource_size_t imdio_base; + struct dsa_8021q_context *dsa_8021q_ctx; + enum dsa_tag_protocol tag_proto; }; struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index f9711e69b8d5..e944868cc120 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1467,6 +1467,7 @@ static int felix_pci_probe(struct pci_dev *pdev, ds->ops = &felix_switch_ops; ds->priv = ocelot; felix->ds = ds; + felix->tag_proto = DSA_TAG_PROTO_OCELOT; err = dsa_register_switch(ds); if (err) { diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 5e9bfdea50be..512f677a6c1c 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1246,6 +1246,7 @@ static int seville_probe(struct platform_device *pdev) ds->ops = &felix_switch_ops; ds->priv = ocelot; felix->ds = ds; + felix->tag_proto = DSA_TAG_PROTO_OCELOT; err = dsa_register_switch(ds); if (err) { diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 5e50bb19bf26..ecffebd513be 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1556,18 +1556,7 @@ static struct platform_driver octeon_mgmt_driver = { .remove = octeon_mgmt_remove, }; -static int __init octeon_mgmt_mod_init(void) -{ - return platform_driver_register(&octeon_mgmt_driver); -} - -static void __exit octeon_mgmt_mod_exit(void) -{ - platform_driver_unregister(&octeon_mgmt_driver); -} - -module_init(octeon_mgmt_mod_init); -module_exit(octeon_mgmt_mod_exit); +module_platform_driver(octeon_mgmt_driver); MODULE_SOFTDEP("pre: mdio-cavium"); MODULE_DESCRIPTION(DRV_DESCRIPTION); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index e5cfbe196ba6..19dc7dc054a2 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1158,11 +1158,9 @@ static struct sock *chtls_recv_sock(struct sock *lsk, #endif } if (!n || !n->dev) - goto free_sk; + goto free_dst; ndev = n->dev; - if (!ndev) - goto free_dst; if (is_vlan_dev(ndev)) ndev = vlan_dev_real_dev(ndev); @@ -1250,7 +1248,8 @@ static struct sock *chtls_recv_sock(struct sock *lsk, free_csk: chtls_sock_release(&csk->kref); free_dst: - neigh_release(n); + if (n) + neigh_release(n); dst_release(dst); free_sk: inet_csk_prepare_forced_close(newsk); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index c527f4ee1d3a..0602d5d5d2ee 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -462,6 +462,11 @@ struct bufdesc_ex { */ #define FEC_QUIRK_CLEAR_SETUP_MII (1 << 17) +/* Some link partners do not tolerate the momentary reset of the REF_CLK + * frequency when the RNCTL register is cleared by hardware reset. + */ +#define FEC_QUIRK_NO_HARD_RESET (1 << 18) + struct bufdesc_prop { int qid; /* Address of Rx and Tx buffers */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 04f24c66cf36..9ebdb0e54291 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -100,7 +100,8 @@ static const struct fec_devinfo fec_imx27_info = { static const struct fec_devinfo fec_imx28_info = { .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME | FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII, + FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII | + FEC_QUIRK_NO_HARD_RESET, }; static const struct fec_devinfo fec_imx6q_info = { @@ -953,7 +954,8 @@ fec_restart(struct net_device *ndev) * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. */ - if (fep->quirks & FEC_QUIRK_HAS_AVB) { + if (fep->quirks & FEC_QUIRK_HAS_AVB || + ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) { writel(0, fep->hwp + FEC_ECNTRL); } else { writel(1, fep->hwp + FEC_ECNTRL); @@ -2165,9 +2167,9 @@ static int fec_enet_mii_init(struct platform_device *pdev) fep->mii_bus->parent = &pdev->dev; err = of_mdiobus_register(fep->mii_bus, node); - of_node_put(node); if (err) goto err_out_free_mdiobus; + of_node_put(node); mii_cnt++; @@ -2180,6 +2182,7 @@ static int fec_enet_mii_init(struct platform_device *pdev) err_out_free_mdiobus: mdiobus_free(fep->mii_bus); err_out: + of_node_put(node); return err; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index a7daf6d4511e..fe09cf6c15f3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -465,6 +465,8 @@ struct hnae3_ae_dev { * Delete clsflower rule * cls_flower_active * Check if any cls flower rule exist + * dbg_read_cmd + * Execute debugfs read command. */ struct hnae3_ae_ops { int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev); @@ -620,6 +622,8 @@ struct hnae3_ae_ops { int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id, u16 flow_id, struct flow_keys *fkeys); int (*dbg_run_cmd)(struct hnae3_handle *handle, const char *cmd_buf); + int (*dbg_read_cmd)(struct hnae3_handle *handle, const char *cmd_buf, + char *buf, int len); pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev); bool (*get_hw_reset_stat)(struct hnae3_handle *handle); bool (*ae_dev_resetting)(struct hnae3_handle *handle); @@ -777,6 +781,10 @@ struct hnae3_handle { #define hnae3_get_bit(origin, shift) \ hnae3_get_field((origin), (0x1 << (shift)), (shift)) +#define HNAE3_DBG_TM_NODES "tm_nodes" +#define HNAE3_DBG_TM_PRI "tm_priority" +#define HNAE3_DBG_TM_QSET "tm_qset" + int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 9d4e9c053a8f..6978304f1ac5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -7,7 +7,7 @@ #include "hnae3.h" #include "hns3_enet.h" -#define HNS3_DBG_READ_LEN 256 +#define HNS3_DBG_READ_LEN 65536 #define HNS3_DBG_WRITE_LEN 1024 static struct dentry *hns3_dbgfs_root; @@ -484,6 +484,42 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer, return count; } +static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + struct hnae3_handle *handle = filp->private_data; + const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + struct hns3_nic_priv *priv = handle->priv; + char *cmd_buf, *read_buf; + ssize_t size = 0; + int ret = 0; + + if (!filp->f_path.dentry->d_iname) + return -EINVAL; + + read_buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL); + if (!read_buf) + return -ENOMEM; + + cmd_buf = filp->f_path.dentry->d_iname; + + if (ops->dbg_read_cmd) + ret = ops->dbg_read_cmd(handle, cmd_buf, read_buf, + HNS3_DBG_READ_LEN); + + if (ret) { + dev_info(priv->dev, "unknown command\n"); + goto out; + } + + size = simple_read_from_buffer(buffer, count, ppos, read_buf, + strlen(read_buf)); + +out: + kfree(read_buf); + return size; +} + static const struct file_operations hns3_dbg_cmd_fops = { .owner = THIS_MODULE, .open = simple_open, @@ -491,14 +527,31 @@ static const struct file_operations hns3_dbg_cmd_fops = { .write = hns3_dbg_cmd_write, }; +static const struct file_operations hns3_dbg_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = hns3_dbg_read, +}; + void hns3_dbg_init(struct hnae3_handle *handle) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev); const char *name = pci_name(handle->pdev); + struct dentry *entry_dir; handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root); debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, &hns3_dbg_cmd_fops); + + entry_dir = debugfs_create_dir("tm", handle->hnae3_dbgfs); + if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2) + debugfs_create_file(HNAE3_DBG_TM_NODES, 0600, entry_dir, handle, + &hns3_dbg_fops); + debugfs_create_file(HNAE3_DBG_TM_PRI, 0600, entry_dir, handle, + &hns3_dbg_fops); + debugfs_create_file(HNAE3_DBG_TM_QSET, 0600, entry_dir, handle, + &hns3_dbg_fops); } void hns3_dbg_uninit(struct hnae3_handle *handle) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index edfadb5cb1c3..f861bdbe46c2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -160,6 +160,7 @@ enum hclge_opcode_type { HCLGE_OPC_TM_PRI_SCH_MODE_CFG = 0x0813, HCLGE_OPC_TM_QS_SCH_MODE_CFG = 0x0814, HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815, + HCLGE_OPC_TM_NODES = 0x0816, HCLGE_OPC_ETS_TC_WEIGHT = 0x0843, HCLGE_OPC_QSET_DFX_STS = 0x0844, HCLGE_OPC_PRI_DFX_STS = 0x0845, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 8f6dea5198cf..8f3fefe50719 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -800,6 +800,140 @@ err_tm_map_cmd_send: cmd, ret); } +static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len) +{ + struct hclge_tm_nodes_cmd *nodes; + struct hclge_desc desc; + int pos = 0; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NODES, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump tm nodes, ret = %d\n", ret); + return ret; + } + + nodes = (struct hclge_tm_nodes_cmd *)desc.data; + + pos += scnprintf(buf + pos, len - pos, " BASE_ID MAX_NUM\n"); + pos += scnprintf(buf + pos, len - pos, "PG %4u %4u\n", + nodes->pg_base_id, nodes->pg_num); + pos += scnprintf(buf + pos, len - pos, "PRI %4u %4u\n", + nodes->pri_base_id, nodes->pri_num); + pos += scnprintf(buf + pos, len - pos, "QSET %4u %4u\n", + le16_to_cpu(nodes->qset_base_id), + le16_to_cpu(nodes->qset_num)); + pos += scnprintf(buf + pos, len - pos, "QUEUE %4u %4u\n", + le16_to_cpu(nodes->queue_base_id), + le16_to_cpu(nodes->queue_num)); + + return 0; +} + +static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len) +{ + struct hclge_pri_shaper_para c_shaper_para; + struct hclge_pri_shaper_para p_shaper_para; + u8 pri_num, sch_mode, weight; + char *sch_mode_str; + int pos = 0; + int ret; + u8 i; + + ret = hclge_tm_get_pri_num(hdev, &pri_num); + if (ret) + return ret; + + pos += scnprintf(buf + pos, len - pos, + "ID MODE DWRR C_IR_B C_IR_U C_IR_S C_BS_B "); + pos += scnprintf(buf + pos, len - pos, + "C_BS_S C_FLAG C_RATE(Mbps) P_IR_B P_IR_U "); + pos += scnprintf(buf + pos, len - pos, + "P_IR_S P_BS_B P_BS_S P_FLAG P_RATE(Mbps)\n"); + + for (i = 0; i < pri_num; i++) { + ret = hclge_tm_get_pri_sch_mode(hdev, i, &sch_mode); + if (ret) + return ret; + + ret = hclge_tm_get_pri_weight(hdev, i, &weight); + if (ret) + return ret; + + ret = hclge_tm_get_pri_shaper(hdev, i, + HCLGE_OPC_TM_PRI_C_SHAPPING, + &c_shaper_para); + if (ret) + return ret; + + ret = hclge_tm_get_pri_shaper(hdev, i, + HCLGE_OPC_TM_PRI_P_SHAPPING, + &p_shaper_para); + if (ret) + return ret; + + sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" : + "sp"; + + pos += scnprintf(buf + pos, len - pos, + "%04u %4s %3u %3u %3u %3u ", + i, sch_mode_str, weight, c_shaper_para.ir_b, + c_shaper_para.ir_u, c_shaper_para.ir_s); + pos += scnprintf(buf + pos, len - pos, + "%3u %3u %1u %6u ", + c_shaper_para.bs_b, c_shaper_para.bs_s, + c_shaper_para.flag, c_shaper_para.rate); + pos += scnprintf(buf + pos, len - pos, + "%3u %3u %3u %3u %3u ", + p_shaper_para.ir_b, p_shaper_para.ir_u, + p_shaper_para.ir_s, p_shaper_para.bs_b, + p_shaper_para.bs_s); + pos += scnprintf(buf + pos, len - pos, "%1u %6u\n", + p_shaper_para.flag, p_shaper_para.rate); + } + + return 0; +} + +static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len) +{ + u8 priority, link_vld, sch_mode, weight; + char *sch_mode_str; + int ret, pos; + u16 qset_num; + u16 i; + + ret = hclge_tm_get_qset_num(hdev, &qset_num); + if (ret) + return ret; + + pos = scnprintf(buf, len, "ID MAP_PRI LINK_VLD MODE DWRR\n"); + + for (i = 0; i < qset_num; i++) { + ret = hclge_tm_get_qset_map_pri(hdev, i, &priority, &link_vld); + if (ret) + return ret; + + ret = hclge_tm_get_qset_sch_mode(hdev, i, &sch_mode); + if (ret) + return ret; + + ret = hclge_tm_get_qset_weight(hdev, i, &weight); + if (ret) + return ret; + + sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" : + "sp"; + pos += scnprintf(buf + pos, len - pos, + "%04u %4u %1u %4s %3u\n", + i, priority, link_vld, sch_mode_str, weight); + } + + return 0; +} + static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev) { struct hclge_cfg_pause_param_cmd *pause_param; @@ -1591,3 +1725,22 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) return 0; } + +int hclge_dbg_read_cmd(struct hnae3_handle *handle, const char *cmd_buf, + char *buf, int len) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (strncmp(cmd_buf, HNAE3_DBG_TM_NODES, + strlen(HNAE3_DBG_TM_NODES)) == 0) + return hclge_dbg_dump_tm_nodes(hdev, buf, len); + else if (strncmp(cmd_buf, HNAE3_DBG_TM_PRI, + strlen(HNAE3_DBG_TM_PRI)) == 0) + return hclge_dbg_dump_tm_pri(hdev, buf, len); + else if (strncmp(cmd_buf, HNAE3_DBG_TM_QSET, + strlen(HNAE3_DBG_TM_QSET)) == 0) + return hclge_dbg_dump_tm_qset(hdev, buf, len); + + return -EINVAL; +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c242883fea5d..16ccb1abe3d9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -11850,6 +11850,7 @@ static const struct hnae3_ae_ops hclge_ops = { .enable_fd = hclge_enable_fd, .add_arfs_entry = hclge_add_fd_entry_by_arfs, .dbg_run_cmd = hclge_dbg_run_cmd, + .dbg_read_cmd = hclge_dbg_read_cmd, .handle_hw_ras_error = hclge_handle_hw_ras_error, .get_hw_reset_stat = hclge_get_hw_reset_stat, .ae_dev_resetting = hclge_ae_dev_resetting, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index ca46bc9110d7..32e5f82ef615 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -1006,6 +1006,8 @@ int hclge_vport_start(struct hclge_vport *vport); void hclge_vport_stop(struct hclge_vport *vport); int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu); int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf); +int hclge_dbg_read_cmd(struct hnae3_handle *handle, const char *cmd_buf, + char *buf, int len); u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id); int hclge_notify_client(struct hclge_dev *hdev, enum hnae3_reset_notify_type type); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 82742a64f3b7..216ab1e92723 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1616,3 +1616,189 @@ int hclge_tm_vport_map_update(struct hclge_dev *hdev) return hclge_tm_bp_setup(hdev); } + +int hclge_tm_get_qset_num(struct hclge_dev *hdev, u16 *qset_num) +{ + struct hclge_tm_nodes_cmd *nodes; + struct hclge_desc desc; + int ret; + + if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) { + /* Each PF has 8 qsets and each VF has 1 qset */ + *qset_num = HCLGE_TM_PF_MAX_QSET_NUM + pci_num_vf(hdev->pdev); + return 0; + } + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NODES, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get qset num, ret = %d\n", ret); + return ret; + } + + nodes = (struct hclge_tm_nodes_cmd *)desc.data; + *qset_num = le16_to_cpu(nodes->qset_num); + return 0; +} + +int hclge_tm_get_pri_num(struct hclge_dev *hdev, u8 *pri_num) +{ + struct hclge_tm_nodes_cmd *nodes; + struct hclge_desc desc; + int ret; + + if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) { + *pri_num = HCLGE_TM_PF_MAX_PRI_NUM; + return 0; + } + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NODES, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get pri num, ret = %d\n", ret); + return ret; + } + + nodes = (struct hclge_tm_nodes_cmd *)desc.data; + *pri_num = nodes->pri_num; + return 0; +} + +int hclge_tm_get_qset_map_pri(struct hclge_dev *hdev, u16 qset_id, u8 *priority, + u8 *link_vld) +{ + struct hclge_qs_to_pri_link_cmd *map; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_TO_PRI_LINK, true); + map = (struct hclge_qs_to_pri_link_cmd *)desc.data; + map->qs_id = cpu_to_le16(qset_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get qset map priority, ret = %d\n", ret); + return ret; + } + + *priority = map->priority; + *link_vld = map->link_vld; + return 0; +} + +int hclge_tm_get_qset_sch_mode(struct hclge_dev *hdev, u16 qset_id, u8 *mode) +{ + struct hclge_qs_sch_mode_cfg_cmd *qs_sch_mode; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_SCH_MODE_CFG, true); + qs_sch_mode = (struct hclge_qs_sch_mode_cfg_cmd *)desc.data; + qs_sch_mode->qs_id = cpu_to_le16(qset_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get qset sch mode, ret = %d\n", ret); + return ret; + } + + *mode = qs_sch_mode->sch_mode; + return 0; +} + +int hclge_tm_get_qset_weight(struct hclge_dev *hdev, u16 qset_id, u8 *weight) +{ + struct hclge_qs_weight_cmd *qs_weight; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_WEIGHT, true); + qs_weight = (struct hclge_qs_weight_cmd *)desc.data; + qs_weight->qs_id = cpu_to_le16(qset_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get qset weight, ret = %d\n", ret); + return ret; + } + + *weight = qs_weight->dwrr; + return 0; +} + +int hclge_tm_get_pri_sch_mode(struct hclge_dev *hdev, u8 pri_id, u8 *mode) +{ + struct hclge_pri_sch_mode_cfg_cmd *pri_sch_mode; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PRI_SCH_MODE_CFG, true); + pri_sch_mode = (struct hclge_pri_sch_mode_cfg_cmd *)desc.data; + pri_sch_mode->pri_id = pri_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get priority sch mode, ret = %d\n", ret); + return ret; + } + + *mode = pri_sch_mode->sch_mode; + return 0; +} + +int hclge_tm_get_pri_weight(struct hclge_dev *hdev, u8 pri_id, u8 *weight) +{ + struct hclge_priority_weight_cmd *priority_weight; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PRI_WEIGHT, true); + priority_weight = (struct hclge_priority_weight_cmd *)desc.data; + priority_weight->pri_id = pri_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get priority weight, ret = %d\n", ret); + return ret; + } + + *weight = priority_weight->dwrr; + return 0; +} + +int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id, + enum hclge_opcode_type cmd, + struct hclge_pri_shaper_para *para) +{ + struct hclge_pri_shapping_cmd *shap_cfg_cmd; + struct hclge_desc desc; + u32 shapping_para; + int ret; + + if (cmd != HCLGE_OPC_TM_PRI_C_SHAPPING && + cmd != HCLGE_OPC_TM_PRI_P_SHAPPING) + return -EINVAL; + + hclge_cmd_setup_basic_desc(&desc, cmd, true); + shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data; + shap_cfg_cmd->pri_id = pri_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get priority shaper(%#x), ret = %d\n", + cmd, ret); + return ret; + } + + shapping_para = le32_to_cpu(shap_cfg_cmd->pri_shapping_para); + para->ir_b = hclge_tm_get_field(shapping_para, IR_B); + para->ir_u = hclge_tm_get_field(shapping_para, IR_U); + para->ir_s = hclge_tm_get_field(shapping_para, IR_S); + para->bs_b = hclge_tm_get_field(shapping_para, BS_B); + para->bs_s = hclge_tm_get_field(shapping_para, BS_S); + para->flag = shap_cfg_cmd->flag; + para->rate = le32_to_cpu(shap_cfg_cmd->pri_rate); + return 0; +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 5498d73ed34b..d33cb04acbef 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -21,6 +21,9 @@ #define HCLGE_ETHER_MAX_RATE 100000 +#define HCLGE_TM_PF_MAX_PRI_NUM 8 +#define HCLGE_TM_PF_MAX_QSET_NUM 8 + struct hclge_pg_to_pri_link_cmd { u8 pg_id; u8 rsvd1[3]; @@ -65,6 +68,18 @@ struct hclge_priority_weight_cmd { u8 dwrr; }; +struct hclge_pri_sch_mode_cfg_cmd { + u8 pri_id; + u8 rsvd[3]; + u8 sch_mode; +}; + +struct hclge_qs_sch_mode_cfg_cmd { + __le16 qs_id; + u8 rsvd[2]; + u8 sch_mode; +}; + struct hclge_qs_weight_cmd { __le16 qs_id; u8 dwrr; @@ -173,6 +188,27 @@ struct hclge_shaper_ir_para { u8 ir_s; /* IR_S parameter of IR shaper */ }; +struct hclge_tm_nodes_cmd { + u8 pg_base_id; + u8 pri_base_id; + __le16 qset_base_id; + __le16 queue_base_id; + u8 pg_num; + u8 pri_num; + __le16 qset_num; + __le16 queue_num; +}; + +struct hclge_pri_shaper_para { + u8 ir_b; + u8 ir_u; + u8 ir_s; + u8 bs_b; + u8 bs_s; + u8 flag; + u32 rate; +}; + #define hclge_tm_set_field(dest, string, val) \ hnae3_set_field((dest), \ (HCLGE_TM_SHAP_##string##_MSK), \ @@ -195,5 +231,15 @@ int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); int hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate); - +int hclge_tm_get_qset_num(struct hclge_dev *hdev, u16 *qset_num); +int hclge_tm_get_pri_num(struct hclge_dev *hdev, u8 *pri_num); +int hclge_tm_get_qset_map_pri(struct hclge_dev *hdev, u16 qset_id, u8 *priority, + u8 *link_vld); +int hclge_tm_get_qset_sch_mode(struct hclge_dev *hdev, u16 qset_id, u8 *mode); +int hclge_tm_get_qset_weight(struct hclge_dev *hdev, u16 qset_id, u8 *weight); +int hclge_tm_get_pri_sch_mode(struct hclge_dev *hdev, u8 pri_id, u8 *mode); +int hclge_tm_get_pri_weight(struct hclge_dev *hdev, u8 pri_id, u8 *weight); +int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id, + enum hclge_opcode_type cmd, + struct hclge_pri_shaper_para *para); #endif diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4c4252e68de5..481bcedb391a 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2444,12 +2444,6 @@ restart_poll: if (!pending_scrq(adapter, rx_scrq)) break; - /* The queue entry at the current index is peeked at above - * to determine that there is a valid descriptor awaiting - * processing. We want to be sure that the current slot - * holds a valid descriptor before reading its contents. - */ - dma_rmb(); next = ibmvnic_next_scrq(adapter, rx_scrq); rx_buff = (struct ibmvnic_rx_buff *)be64_to_cpu(next-> @@ -2516,7 +2510,6 @@ restart_poll: if (napi_complete_done(napi, frames_processed)) { enable_scrq_irq(adapter, rx_scrq); if (pending_scrq(adapter, rx_scrq)) { - rmb(); if (napi_reschedule(napi)) { disable_scrq_irq(adapter, rx_scrq); goto restart_poll; @@ -3189,13 +3182,6 @@ restart_loop: int total_bytes = 0; int num_packets = 0; - /* The queue entry at the current index is peeked at above - * to determine that there is a valid descriptor awaiting - * processing. We want to be sure that the current slot - * holds a valid descriptor before reading its contents. - */ - dma_rmb(); - next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { if (next->tx_comp.rcs[i]) @@ -3569,11 +3555,16 @@ static int pending_scrq(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *scrq) { union sub_crq *entry = &scrq->msgs[scrq->cur]; + int rc; - if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP) - return 1; - else - return 0; + rc = !!(entry->generic.first & IBMVNIC_CRQ_CMD_RSP); + + /* Ensure that the SCRQ valid flag is loaded prior to loading the + * contents of the SCRQ descriptor + */ + dma_rmb(); + + return rc; } static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter, @@ -3592,8 +3583,8 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter, } spin_unlock_irqrestore(&scrq->lock, flags); - /* Ensure that the entire buffer descriptor has been - * loaded before reading its contents + /* Ensure that the SCRQ valid flag is loaded prior to loading the + * contents of the SCRQ descriptor */ dma_rmb(); @@ -5017,6 +5008,12 @@ static void ibmvnic_tasklet(struct tasklet_struct *t) while (!done) { /* Pull all the valid messages off the CRQ */ while ((crq = ibmvnic_next_crq(adapter)) != NULL) { + /* This barrier makes sure ibmvnic_next_crq()'s + * crq->generic.first & IBMVNIC_CRQ_CMD_RSP is loaded + * before ibmvnic_handle_crq()'s + * switch(gen_crq->first) and switch(gen_crq->cmd). + */ + dma_rmb(); ibmvnic_handle_crq(crq, adapter); crq->generic.first = 0; } @@ -5371,11 +5368,6 @@ static int ibmvnic_remove(struct vio_dev *dev) unsigned long flags; spin_lock_irqsave(&adapter->state_lock, flags); - if (test_bit(0, &adapter->resetting)) { - spin_unlock_irqrestore(&adapter->state_lock, flags); - return -EBUSY; - } - adapter->state = VNIC_REMOVING; spin_unlock_irqrestore(&adapter->state_lock, flags); diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 8cc651d37a7f..f8d78af76d7d 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1739,10 +1739,10 @@ static int e100_xmit_prepare(struct nic *nic, struct cb *cb, dma_addr_t dma_addr; cb->command = nic->tx_command; - dma_addr = pci_map_single(nic->pdev, - skb->data, skb->len, PCI_DMA_TODEVICE); + dma_addr = dma_map_single(&nic->pdev->dev, skb->data, skb->len, + DMA_TO_DEVICE); /* If we can't map the skb, have the upper layer try later */ - if (pci_dma_mapping_error(nic->pdev, dma_addr)) { + if (dma_mapping_error(&nic->pdev->dev, dma_addr)) { dev_kfree_skb_any(skb); skb = NULL; return -ENOMEM; @@ -1828,10 +1828,10 @@ static int e100_tx_clean(struct nic *nic) dev->stats.tx_packets++; dev->stats.tx_bytes += cb->skb->len; - pci_unmap_single(nic->pdev, - le32_to_cpu(cb->u.tcb.tbd.buf_addr), - le16_to_cpu(cb->u.tcb.tbd.size), - PCI_DMA_TODEVICE); + dma_unmap_single(&nic->pdev->dev, + le32_to_cpu(cb->u.tcb.tbd.buf_addr), + le16_to_cpu(cb->u.tcb.tbd.size), + DMA_TO_DEVICE); dev_kfree_skb_any(cb->skb); cb->skb = NULL; tx_cleaned = 1; @@ -1855,10 +1855,10 @@ static void e100_clean_cbs(struct nic *nic) while (nic->cbs_avail != nic->params.cbs.count) { struct cb *cb = nic->cb_to_clean; if (cb->skb) { - pci_unmap_single(nic->pdev, - le32_to_cpu(cb->u.tcb.tbd.buf_addr), - le16_to_cpu(cb->u.tcb.tbd.size), - PCI_DMA_TODEVICE); + dma_unmap_single(&nic->pdev->dev, + le32_to_cpu(cb->u.tcb.tbd.buf_addr), + le16_to_cpu(cb->u.tcb.tbd.size), + DMA_TO_DEVICE); dev_kfree_skb(cb->skb); } nic->cb_to_clean = nic->cb_to_clean->next; @@ -1925,10 +1925,10 @@ static int e100_rx_alloc_skb(struct nic *nic, struct rx *rx) /* Init, and map the RFD. */ skb_copy_to_linear_data(rx->skb, &nic->blank_rfd, sizeof(struct rfd)); - rx->dma_addr = pci_map_single(nic->pdev, rx->skb->data, - RFD_BUF_LEN, PCI_DMA_BIDIRECTIONAL); + rx->dma_addr = dma_map_single(&nic->pdev->dev, rx->skb->data, + RFD_BUF_LEN, DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(nic->pdev, rx->dma_addr)) { + if (dma_mapping_error(&nic->pdev->dev, rx->dma_addr)) { dev_kfree_skb_any(rx->skb); rx->skb = NULL; rx->dma_addr = 0; @@ -1941,8 +1941,10 @@ static int e100_rx_alloc_skb(struct nic *nic, struct rx *rx) if (rx->prev->skb) { struct rfd *prev_rfd = (struct rfd *)rx->prev->skb->data; put_unaligned_le32(rx->dma_addr, &prev_rfd->link); - pci_dma_sync_single_for_device(nic->pdev, rx->prev->dma_addr, - sizeof(struct rfd), PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_device(&nic->pdev->dev, + rx->prev->dma_addr, + sizeof(struct rfd), + DMA_BIDIRECTIONAL); } return 0; @@ -1961,8 +1963,8 @@ static int e100_rx_indicate(struct nic *nic, struct rx *rx, return -EAGAIN; /* Need to sync before taking a peek at cb_complete bit */ - pci_dma_sync_single_for_cpu(nic->pdev, rx->dma_addr, - sizeof(struct rfd), PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_cpu(&nic->pdev->dev, rx->dma_addr, + sizeof(struct rfd), DMA_BIDIRECTIONAL); rfd_status = le16_to_cpu(rfd->status); netif_printk(nic, rx_status, KERN_DEBUG, nic->netdev, @@ -1981,9 +1983,9 @@ static int e100_rx_indicate(struct nic *nic, struct rx *rx, if (ioread8(&nic->csr->scb.status) & rus_no_res) nic->ru_running = RU_SUSPENDED; - pci_dma_sync_single_for_device(nic->pdev, rx->dma_addr, - sizeof(struct rfd), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&nic->pdev->dev, rx->dma_addr, + sizeof(struct rfd), + DMA_FROM_DEVICE); return -ENODATA; } @@ -1995,8 +1997,8 @@ static int e100_rx_indicate(struct nic *nic, struct rx *rx, actual_size = RFD_BUF_LEN - sizeof(struct rfd); /* Get data */ - pci_unmap_single(nic->pdev, rx->dma_addr, - RFD_BUF_LEN, PCI_DMA_BIDIRECTIONAL); + dma_unmap_single(&nic->pdev->dev, rx->dma_addr, RFD_BUF_LEN, + DMA_BIDIRECTIONAL); /* If this buffer has the el bit, but we think the receiver * is still running, check to see if it really stopped while @@ -2097,22 +2099,25 @@ static void e100_rx_clean(struct nic *nic, unsigned int *work_done, (struct rfd *)new_before_last_rx->skb->data; new_before_last_rfd->size = 0; new_before_last_rfd->command |= cpu_to_le16(cb_el); - pci_dma_sync_single_for_device(nic->pdev, - new_before_last_rx->dma_addr, sizeof(struct rfd), - PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_device(&nic->pdev->dev, + new_before_last_rx->dma_addr, + sizeof(struct rfd), + DMA_BIDIRECTIONAL); /* Now that we have a new stopping point, we can clear the old * stopping point. We must sync twice to get the proper * ordering on the hardware side of things. */ old_before_last_rfd->command &= ~cpu_to_le16(cb_el); - pci_dma_sync_single_for_device(nic->pdev, - old_before_last_rx->dma_addr, sizeof(struct rfd), - PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_device(&nic->pdev->dev, + old_before_last_rx->dma_addr, + sizeof(struct rfd), + DMA_BIDIRECTIONAL); old_before_last_rfd->size = cpu_to_le16(VLAN_ETH_FRAME_LEN + ETH_FCS_LEN); - pci_dma_sync_single_for_device(nic->pdev, - old_before_last_rx->dma_addr, sizeof(struct rfd), - PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_device(&nic->pdev->dev, + old_before_last_rx->dma_addr, + sizeof(struct rfd), + DMA_BIDIRECTIONAL); } if (restart_required) { @@ -2134,8 +2139,9 @@ static void e100_rx_clean_list(struct nic *nic) if (nic->rxs) { for (rx = nic->rxs, i = 0; i < count; rx++, i++) { if (rx->skb) { - pci_unmap_single(nic->pdev, rx->dma_addr, - RFD_BUF_LEN, PCI_DMA_BIDIRECTIONAL); + dma_unmap_single(&nic->pdev->dev, + rx->dma_addr, RFD_BUF_LEN, + DMA_BIDIRECTIONAL); dev_kfree_skb(rx->skb); } } @@ -2177,8 +2183,8 @@ static int e100_rx_alloc_list(struct nic *nic) before_last = (struct rfd *)rx->skb->data; before_last->command |= cpu_to_le16(cb_el); before_last->size = 0; - pci_dma_sync_single_for_device(nic->pdev, rx->dma_addr, - sizeof(struct rfd), PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_device(&nic->pdev->dev, rx->dma_addr, + sizeof(struct rfd), DMA_BIDIRECTIONAL); nic->rx_to_use = nic->rx_to_clean = nic->rxs; nic->ru_running = RU_SUSPENDED; @@ -2377,8 +2383,8 @@ static int e100_loopback_test(struct nic *nic, enum loopback loopback_mode) msleep(10); - pci_dma_sync_single_for_cpu(nic->pdev, nic->rx_to_clean->dma_addr, - RFD_BUF_LEN, PCI_DMA_BIDIRECTIONAL); + dma_sync_single_for_cpu(&nic->pdev->dev, nic->rx_to_clean->dma_addr, + RFD_BUF_LEN, DMA_BIDIRECTIONAL); if (memcmp(nic->rx_to_clean->skb->data + sizeof(struct rfd), skb->data, ETH_DATA_LEN)) @@ -2751,16 +2757,16 @@ static int e100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) static int e100_alloc(struct nic *nic) { - nic->mem = pci_alloc_consistent(nic->pdev, sizeof(struct mem), - &nic->dma_addr); + nic->mem = dma_alloc_coherent(&nic->pdev->dev, sizeof(struct mem), + &nic->dma_addr, GFP_KERNEL); return nic->mem ? 0 : -ENOMEM; } static void e100_free(struct nic *nic) { if (nic->mem) { - pci_free_consistent(nic->pdev, sizeof(struct mem), - nic->mem, nic->dma_addr); + dma_free_coherent(&nic->pdev->dev, sizeof(struct mem), + nic->mem, nic->dma_addr); nic->mem = NULL; } } @@ -2853,7 +2859,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_disable_pdev; } - if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) { + if ((err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)))) { netif_err(nic, probe, nic->netdev, "No usable DMA configuration, aborting\n"); goto err_out_free_res; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 21ee56420c3a..1b6ec9be155a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -55,12 +55,7 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - - /* Always report link is down if the VF queues aren't enabled */ - if (!vf->queues_enabled) { - pfe.event_data.link_event.link_status = false; - pfe.event_data.link_event.link_speed = 0; - } else if (vf->link_forced) { + if (vf->link_forced) { pfe.event_data.link_event.link_status = vf->link_up; pfe.event_data.link_event.link_speed = (vf->link_up ? i40e_virtchnl_link_speed(ls->link_speed) : 0); @@ -70,7 +65,6 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event_data.link_event.link_speed = i40e_virtchnl_link_speed(ls->link_speed); } - i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, sizeof(pfe), NULL); } @@ -2443,8 +2437,6 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) } } - vf->queues_enabled = true; - error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2466,9 +2458,6 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; - /* Immediately mark queues as disabled */ - vf->queues_enabled = false; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -4046,20 +4035,16 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto error_param; vf = &pf->vf[vf_id]; - vsi = pf->vsi[vf->lan_vsi_idx]; /* When the VF is resetting wait until it is done. * It can take up to 200 milliseconds, * but wait for up to 300 milliseconds to be safe. - * If the VF is indeed in reset, the vsi pointer has - * to show on the newly loaded vsi under pf->vsi[id]. + * Acquire the VSI pointer only after the VF has been + * properly initialized. */ for (i = 0; i < 15; i++) { - if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { - if (i > 0) - vsi = pf->vsi[vf->lan_vsi_idx]; + if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) break; - } msleep(20); } if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { @@ -4068,6 +4053,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) ret = -EAGAIN; goto error_param; } + vsi = pf->vsi[vf->lan_vsi_idx]; if (is_multicast_ether_addr(mac)) { dev_err(&pf->pdev->dev, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 5491215d81de..091e32c1bb46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -98,7 +98,6 @@ struct i40e_vf { unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ bool link_forced; bool link_up; /* only valid if VF link is forced */ - bool queues_enabled; /* true if the VF queues are enabled */ bool spoofchk; u16 num_vlan; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 56725356a17b..fa1e128c24ec 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -68,7 +68,9 @@ #define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16) #define ICE_AQ_LEN 64 #define ICE_MBXSQ_LEN 64 -#define ICE_MIN_MSIX 2 +#define ICE_MIN_LAN_TXRX_MSIX 1 +#define ICE_MIN_LAN_OICR_MSIX 1 +#define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) #define ICE_FDIR_MSIX 1 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 9e8e9531cd87..69c113a4de7e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3258,8 +3258,8 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, */ static int ice_get_max_txq(struct ice_pf *pf) { - return min_t(int, num_online_cpus(), - pf->hw.func_caps.common_cap.num_txq); + return min3(pf->num_lan_msix, (u16)num_online_cpus(), + (u16)pf->hw.func_caps.common_cap.num_txq); } /** @@ -3268,8 +3268,8 @@ static int ice_get_max_txq(struct ice_pf *pf) */ static int ice_get_max_rxq(struct ice_pf *pf) { - return min_t(int, num_online_cpus(), - pf->hw.func_caps.common_cap.num_rxq); + return min3(pf->num_lan_msix, (u16)num_online_cpus(), + (u16)pf->hw.func_caps.common_cap.num_rxq); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 2d27f66ac853..192729546bbf 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1576,7 +1576,13 @@ ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp, sizeof(struct in6_addr)); input->ip.v6.l4_header = fsp->h_u.usr_ip6_spec.l4_4_bytes; input->ip.v6.tc = fsp->h_u.usr_ip6_spec.tclass; - input->ip.v6.proto = fsp->h_u.usr_ip6_spec.l4_proto; + + /* if no protocol requested, use IPPROTO_NONE */ + if (!fsp->m_u.usr_ip6_spec.l4_proto) + input->ip.v6.proto = IPPROTO_NONE; + else + input->ip.v6.proto = fsp->h_u.usr_ip6_spec.l4_proto; + memcpy(input->mask.v6.dst_ip, fsp->m_u.usr_ip6_spec.ip6dst, sizeof(struct in6_addr)); memcpy(input->mask.v6.src_ip, fsp->m_u.usr_ip6_spec.ip6src, diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 3df67486d42d..ad9c22a1b97a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -161,8 +161,9 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) switch (vsi->type) { case ICE_VSI_PF: - vsi->alloc_txq = min_t(int, ice_get_avail_txq_count(pf), - num_online_cpus()); + vsi->alloc_txq = min3(pf->num_lan_msix, + ice_get_avail_txq_count(pf), + (u16)num_online_cpus()); if (vsi->req_txq) { vsi->alloc_txq = vsi->req_txq; vsi->num_txq = vsi->req_txq; @@ -174,8 +175,9 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { vsi->alloc_rxq = 1; } else { - vsi->alloc_rxq = min_t(int, ice_get_avail_rxq_count(pf), - num_online_cpus()); + vsi->alloc_rxq = min3(pf->num_lan_msix, + ice_get_avail_rxq_count(pf), + (u16)num_online_cpus()); if (vsi->req_rxq) { vsi->alloc_rxq = vsi->req_rxq; vsi->num_rxq = vsi->req_rxq; @@ -184,7 +186,9 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) pf->num_lan_rx = vsi->alloc_rxq; - vsi->num_q_vectors = max_t(int, vsi->alloc_rxq, vsi->alloc_txq); + vsi->num_q_vectors = min_t(int, pf->num_lan_msix, + max_t(int, vsi->alloc_rxq, + vsi->alloc_txq)); break; case ICE_VSI_VF: vf = &pf->vf[vsi->vf_id]; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 6e251dfffc91..06aa37549c04 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3430,18 +3430,14 @@ static int ice_ena_msix_range(struct ice_pf *pf) if (v_actual < v_budget) { dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", v_budget, v_actual); -/* 2 vectors each for LAN and RDMA (traffic + OICR), one for flow director */ -#define ICE_MIN_LAN_VECS 2 -#define ICE_MIN_RDMA_VECS 2 -#define ICE_MIN_VECS (ICE_MIN_LAN_VECS + ICE_MIN_RDMA_VECS + 1) - if (v_actual < ICE_MIN_LAN_VECS) { + if (v_actual < ICE_MIN_MSIX) { /* error if we can't get minimum vectors */ pci_disable_msix(pf->pdev); err = -ERANGE; goto msix_err; } else { - pf->num_lan_msix = ICE_MIN_LAN_VECS; + pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; } } @@ -4884,9 +4880,15 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) goto err_update_filters; } - /* Add filter for new MAC. If filter exists, just return success */ + /* Add filter for new MAC. If filter exists, return success */ status = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); if (status == ICE_ERR_ALREADY_EXISTS) { + /* Although this MAC filter is already present in hardware it's + * possible in some cases (e.g. bonding) that dev_addr was + * modified outside of the driver and needs to be restored back + * to this value. + */ + memcpy(netdev->dev_addr, mac, netdev->addr_len); netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 422f53997c02..2c2de56e2824 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1924,12 +1924,15 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) ICE_TX_CTX_EIPT_IPV4_NO_CSUM; l4_proto = ip.v4->protocol; } else if (first->tx_flags & ICE_TX_FLAGS_IPV6) { + int ret; + tunnel |= ICE_TX_CTX_EIPT_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; - if (l4.hdr != exthdr) - ipv6_skip_exthdr(skb, exthdr - skb->data, - &l4_proto, &frag_off); + ret = ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto, &frag_off); + if (ret < 0) + return -1; } /* define outer transport */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 61d331ce38cd..ec8cd69d4992 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1675,12 +1675,18 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, cmd->base.phy_address = hw->phy.addr; /* advertising link modes */ - ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); - ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half); - ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full); + if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); + if (hw->phy.autoneg_advertised & ADVERTISE_10_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full); + if (hw->phy.autoneg_advertised & ADVERTISE_100_HALF) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half); + if (hw->phy.autoneg_advertised & ADVERTISE_100_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full); + if (hw->phy.autoneg_advertised & ADVERTISE_1000_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); + if (hw->phy.autoneg_advertised & ADVERTISE_2500_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full); /* set autoneg settings */ if (hw->mac.autoneg == 1) { @@ -1708,7 +1714,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, Asym_Pause); } - status = rd32(IGC_STATUS); + status = pm_runtime_suspended(&adapter->pdev->dev) ? + 0 : rd32(IGC_STATUS); if (status & IGC_STATUS_LU) { if (status & IGC_STATUS_SPEED_1000) { @@ -1792,6 +1799,12 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, ethtool_convert_link_mode_to_legacy_u32(&advertising, cmd->link_modes.advertising); + /* Converting to legacy u32 drops ETHTOOL_LINK_MODE_2500baseT_Full_BIT. + * We have to check this and convert it to ADVERTISE_2500_FULL + * (aka ETHTOOL_LINK_MODE_2500baseX_Full_BIT) explicitly. + */ + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, 2500baseT_Full)) + advertising |= ADVERTISE_2500_FULL; if (cmd->base.autoneg == AUTONEG_ENABLE) { hw->mac.autoneg = 1; diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 8b67d9b49a83..7ec04e48860c 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -219,9 +219,9 @@ static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words, u16 *data) { struct igc_nvm_info *nvm = &hw->nvm; + s32 ret_val = -IGC_ERR_NVM; u32 attempts = 100000; u32 i, k, eewr = 0; - s32 ret_val = 0; /* A check for invalid values: offset too large, too many words, * too many words for the offset, and not enough words. @@ -229,7 +229,6 @@ static s32 igc_write_nvm_srwr(struct igc_hw *hw, u16 offset, u16 words, if (offset >= nvm->word_size || (words > (nvm->word_size - offset)) || words == 0) { hw_dbg("nvm parameter(s) out of bounds\n"); - ret_val = -IGC_ERR_NVM; goto out; } diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c index 09cd0ec7ee87..67b8ffd21d8a 100644 --- a/drivers/net/ethernet/intel/igc/igc_mac.c +++ b/drivers/net/ethernet/intel/igc/igc_mac.c @@ -638,7 +638,7 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw) } out: - return 0; + return ret_val; } /** diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 6ee53c52627f..0257c987be0c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -29,16 +29,16 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe) /* Clear entry invalidation bit */ pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK; - /* Write tcam index - indirect access */ - mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index); - for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++) - mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]); - /* Write sram index - indirect access */ mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index); for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++) mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]); + /* Write tcam index - indirect access */ + mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index); + for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++) + mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]); + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 0b6bf9f0c6f0..4ef7fc8bbb19 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -646,7 +646,7 @@ setup_vfmsix: } /* HW interprets RVU_AF_MSIXTR_BASE address as an IOVA, hence - * create a IOMMU mapping for the physcial address configured by + * create an IOMMU mapping for the physical address configured by * firmware and reconfig RVU_AF_MSIXTR_BASE with IOVA. */ cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_CONST); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index bdfa2e293531..5ddedc3b754d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -488,10 +488,11 @@ dma_addr_t __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool) dma_addr_t iova; u8 *buf; - buf = napi_alloc_frag(pool->rbsize); + buf = napi_alloc_frag(pool->rbsize + OTX2_ALIGN); if (unlikely(!buf)) return -ENOMEM; + buf = PTR_ALIGN(buf, OTX2_ALIGN); iova = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); if (unlikely(dma_mapping_error(pfvf->dev, iova))) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index d6b5bf247e31..0dbbf38e0597 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Marvell OcteonTx2 RVU Physcial Function ethernet driver +/* Marvell OcteonTx2 RVU Physical Function ethernet driver * * Copyright (C) 2020 Marvell. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 634d60655a74..07ec85aebcca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Marvell OcteonTx2 RVU Physcial Function ethernet driver +/* Marvell OcteonTx2 RVU Physical Function ethernet driver * * Copyright (C) 2020 Marvell International Ltd. * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 6e4d7bb7fea2..ad45d20f9d44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -203,3 +203,22 @@ config MLX5_SW_STEERING default y help Build support for software-managed steering in the NIC. + +config MLX5_SF + bool "Mellanox Technologies subfunction device support using auxiliary device" + depends on MLX5_CORE && MLX5_CORE_EN + default n + help + Build support for subfuction device in the NIC. A Mellanox subfunction + device can support RDMA, netdevice and vdpa device. + It is similar to a SRIOV VF but it doesn't require SRIOV support. + +config MLX5_SF_MANAGER + bool + depends on MLX5_SF && MLX5_ESWITCH + default y + help + Build support for subfuction port in the NIC. A Mellanox subfunction + port is managed through devlink. A subfunction supports RDMA, netdevice + and vdpa device. It is similar to a SRIOV VF but it doesn't require + SRIOV support. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index d44f5f6ee449..8809dd4de57e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -85,6 +85,15 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o steering/dr_matcher.o steering/dr_rule.o \ steering/dr_icm_pool.o steering/dr_buddy.o \ steering/dr_ste.o steering/dr_send.o \ - steering/dr_ste_v0.o \ + steering/dr_ste_v0.o steering/dr_ste_v1.o \ steering/dr_cmd.o steering/dr_fw.o \ steering/dr_action.o steering/fs_dr.o +# +# SF device +# +mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o + +# +# SF manager +# +mlx5_core-$(CONFIG_MLX5_SF_MANAGER) += sf/cmd.o sf/hw_table.o sf/devlink.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 50c7b9ee80c3..e8cecd50558d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -333,6 +333,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_DEALLOC_MEMIC: case MLX5_CMD_OP_PAGE_FAULT_RESUME: case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS: + case MLX5_CMD_OP_DEALLOC_SF: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -464,6 +465,9 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_ALLOC_MEMIC: case MLX5_CMD_OP_MODIFY_XRQ: case MLX5_CMD_OP_RELEASE_XRQ_ERROR: + case MLX5_CMD_OP_QUERY_VHCA_STATE: + case MLX5_CMD_OP_MODIFY_VHCA_STATE: + case MLX5_CMD_OP_ALLOC_SF: *status = MLX5_DRIVER_STATUS_ABORTED; *synd = MLX5_DRIVER_SYND; return -EIO; @@ -657,6 +661,10 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(DESTROY_UMEM); MLX5_COMMAND_STR_CASE(RELEASE_XRQ_ERROR); MLX5_COMMAND_STR_CASE(MODIFY_XRQ); + MLX5_COMMAND_STR_CASE(QUERY_VHCA_STATE); + MLX5_COMMAND_STR_CASE(MODIFY_VHCA_STATE); + MLX5_COMMAND_STR_CASE(ALLOC_SF); + MLX5_COMMAND_STR_CASE(DEALLOC_SF); default: return "unknown command opcode"; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index b23b54814356..aa76a6e0dae8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -7,6 +7,8 @@ #include "fw_reset.h" #include "fs_core.h" #include "eswitch.h" +#include "sf/dev/dev.h" +#include "sf/sf.h" static int mlx5_devlink_flash_update(struct devlink *devlink, struct devlink_flash_update_params *params, @@ -127,6 +129,17 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); + bool sf_dev_allocated; + + sf_dev_allocated = mlx5_sf_dev_allocated(dev); + if (sf_dev_allocated) { + /* Reload results in deleting SF device which further results in + * unregistering devlink instance while holding devlink_mutext. + * Hence, do not support reload. + */ + NL_SET_ERR_MSG_MOD(extack, "reload is unsupported when SFs are allocated\n"); + return -EOPNOTSUPP; + } switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: @@ -264,6 +277,12 @@ static const struct devlink_ops mlx5_devlink_ops = { .port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get, .port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set, #endif +#ifdef CONFIG_MLX5_SF_MANAGER + .port_new = mlx5_devlink_sf_port_new, + .port_del = mlx5_devlink_sf_port_del, + .port_fn_state_get = mlx5_devlink_sf_port_fn_state_get, + .port_fn_state_set = mlx5_devlink_sf_port_fn_state_set, +#endif .flash_update = mlx5_devlink_flash_update, .info_get = mlx5_devlink_info_get, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 39f389cc40fc..a8e31cdd4a4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -137,10 +137,10 @@ struct page_pool; #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES 0x80 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES_MPW 0x2 -#define MLX5E_LOG_INDIR_RQT_SIZE 0x7 +#define MLX5E_LOG_INDIR_RQT_SIZE 0x8 #define MLX5E_INDIR_RQT_SIZE BIT(MLX5E_LOG_INDIR_RQT_SIZE) #define MLX5E_MIN_NUM_CHANNELS 0x1 -#define MLX5E_MAX_NUM_CHANNELS MLX5E_INDIR_RQT_SIZE +#define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE / 2) #define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC) #define MLX5E_TX_CQ_POLL_BUDGET 128 #define MLX5E_TX_XSK_POLL_BUDGET 64 @@ -895,8 +895,7 @@ extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic; struct mlx5e_profile { int (*init)(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, void *ppriv); + struct net_device *netdev); void (*cleanup)(struct mlx5e_priv *priv); int (*init_rx)(struct mlx5e_priv *priv); void (*cleanup_rx)(struct mlx5e_priv *priv); @@ -1155,24 +1154,25 @@ int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv, struct ethtool_pauseparam *pauseparam); /* mlx5e generic netdev management API */ -int mlx5e_netdev_init(struct net_device *netdev, - struct mlx5e_priv *priv, - struct mlx5_core_dev *mdev, - const struct mlx5e_profile *profile, - void *ppriv); -void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv); -struct net_device* -mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, - int nch, void *ppriv); +static inline unsigned int +mlx5e_calc_max_nch(struct mlx5e_priv *priv, const struct mlx5e_profile *profile) +{ + return priv->netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); +} + +int mlx5e_priv_init(struct mlx5e_priv *priv, + struct net_device *netdev, + struct mlx5_core_dev *mdev); +void mlx5e_priv_cleanup(struct mlx5e_priv *priv); +struct net_device * +mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int rxqs); int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); void mlx5e_destroy_netdev(struct mlx5e_priv *priv); +int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, + const struct mlx5e_profile *new_profile, void *new_ppriv); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); -void mlx5e_build_nic_params(struct mlx5e_priv *priv, - struct mlx5e_xsk *xsk, - struct mlx5e_rss_params *rss_params, - struct mlx5e_params *params, - u16 mtu); +void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu); void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 718f8c0a4f6b..84e501e057b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -273,7 +273,7 @@ int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key err = devlink_fmsg_binary_pair_nest_start(fmsg, "data"); if (err) - return err; + goto free_page; cmd = mlx5_rsc_dump_cmd_create(mdev, key); if (IS_ERR(cmd)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 43271a3856ca..36381a2ed5a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -179,7 +179,7 @@ int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params) stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params); if (stop_room >= sq_size) { - netdev_err(priv->netdev, "Stop room %hu is bigger than the SQ size %zu\n", + netdev_err(priv->netdev, "Stop room %u is bigger than the SQ size %zu\n", stop_room, sq_size); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index eeddd1137dda..a76cfefec708 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -428,16 +428,13 @@ static int mlx5e_ptp_open_queues(struct mlx5e_port_ptp *c, if (err) return err; - napi_enable(&c->napi); - err = mlx5e_ptp_open_txqsqs(c, cparams); if (err) - goto disable_napi; + goto close_cqs; return 0; -disable_napi: - napi_disable(&c->napi); +close_cqs: mlx5e_ptp_close_cqs(c); return err; @@ -446,7 +443,6 @@ disable_napi: static void mlx5e_ptp_close_queues(struct mlx5e_port_ptp *c) { mlx5e_ptp_close_txqsqs(c); - napi_disable(&c->napi); mlx5e_ptp_close_cqs(c); } @@ -515,6 +511,8 @@ void mlx5e_ptp_activate_channel(struct mlx5e_port_ptp *c) { int tc; + napi_enable(&c->napi); + for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->ptpsq[tc].txqsq); } @@ -525,4 +523,6 @@ void mlx5e_ptp_deactivate_channel(struct mlx5e_port_ptp *c) for (tc = 0; tc < c->num_tc; tc++) mlx5e_deactivate_txqsq(&c->ptpsq[tc].txqsq); + + napi_disable(&c->napi); } 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 58e27038c947..616ee585a985 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -279,7 +279,7 @@ int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv) err = rhashtable_init(&neigh_update->neigh_ht, &mlx5e_neigh_ht_params); if (err) - return err; + goto out_err; INIT_LIST_HEAD(&neigh_update->neigh_list); mutex_init(&neigh_update->encap_lock); @@ -287,14 +287,19 @@ int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv) mlx5e_rep_neigh_stats_work); mlx5e_rep_neigh_update_init_interval(rpriv); - rpriv->neigh_update.netevent_nb.notifier_call = mlx5e_rep_netevent_event; - err = register_netevent_notifier(&rpriv->neigh_update.netevent_nb); + neigh_update->netevent_nb.notifier_call = mlx5e_rep_netevent_event; + err = register_netevent_notifier(&neigh_update->netevent_nb); if (err) - goto out_err; + goto out_notifier; return 0; -out_err: +out_notifier: + neigh_update->netevent_nb.notifier_call = NULL; rhashtable_destroy(&neigh_update->neigh_ht); +out_err: + netdev_warn(rpriv->netdev, + "Failed to initialize neighbours handling for vport %d\n", + rpriv->rep->vport); return err; } @@ -303,6 +308,9 @@ void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv) struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update; struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); + if (!rpriv->neigh_update.netevent_nb.notifier_call) + return; + unregister_netevent_notifier(&neigh_update->netevent_nb); flush_workqueue(priv->wq); /* flush neigh update works */ 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 e20c1da95a33..40aaa105b2fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -27,6 +27,7 @@ #define MLX5_CT_STATE_ESTABLISHED_BIT BIT(1) #define MLX5_CT_STATE_TRK_BIT BIT(2) #define MLX5_CT_STATE_NAT_BIT BIT(3) +#define MLX5_CT_STATE_REPLY_BIT BIT(4) #define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen * 8) #define MLX5_FTE_ID_MAX GENMASK(MLX5_FTE_ID_BITS - 1, 0) @@ -167,6 +168,12 @@ static const struct rhashtable_params tuples_nat_ht_params = { .min_size = 16 * 1024, }; +static bool +mlx5_tc_ct_entry_has_nat(struct mlx5_ct_entry *entry) +{ + return !!(entry->tuple_nat_node.next); +} + static int mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule) { @@ -635,6 +642,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, } ct_state |= MLX5_CT_STATE_ESTABLISHED_BIT | MLX5_CT_STATE_TRK_BIT; + ct_state |= meta->ct_metadata.orig_dir ? 0 : MLX5_CT_STATE_REPLY_BIT; err = mlx5_tc_ct_entry_set_registers(ct_priv, &mod_acts, ct_state, meta->ct_metadata.mark, @@ -762,7 +770,6 @@ mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_counter *shared_counter; struct mlx5_ct_entry *rev_entry; __be16 tmp_port; - int ret; /* get the reversed tuple */ tmp_port = rev_tuple.port.src; @@ -796,10 +803,8 @@ mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv, mutex_unlock(&ct_priv->shared_counter_lock); shared_counter = mlx5_tc_ct_counter_create(ct_priv); - if (IS_ERR(shared_counter)) { - ret = PTR_ERR(shared_counter); - return ERR_PTR(ret); - } + if (IS_ERR(shared_counter)) + return shared_counter; shared_counter->is_shared = true; refcount_set(&shared_counter->refcount, 1); @@ -909,13 +914,13 @@ 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); + if (mlx5_tc_ct_entry_has_nat(entry)) + 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); + rhashtable_remove_fast(&ct_priv->ct_tuples_ht, + &entry->tuple_node, + tuples_ht_params); err_tuple: err_set: kfree(entry); @@ -930,7 +935,7 @@ mlx5_tc_ct_del_ft_entry(struct mlx5_tc_ct_priv *ct_priv, { mlx5_tc_ct_entry_del_rules(ct_priv, entry); mutex_lock(&ct_priv->shared_counter_lock); - if (entry->tuple_node.next) + if (mlx5_tc_ct_entry_has_nat(entry)) rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht, &entry->tuple_nat_node, tuples_nat_ht_params); @@ -1080,8 +1085,8 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, struct netlink_ext_ack *extack) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); + bool trk, est, untrk, unest, new, rpl, unrpl; struct flow_dissector_key_ct *mask, *key; - bool trk, est, untrk, unest, new; u32 ctstate = 0, ctstate_mask = 0; u16 ct_state_on, ct_state_off; u16 ct_state, ct_state_mask; @@ -1107,9 +1112,10 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, if (ct_state_mask & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED | - TCA_FLOWER_KEY_CT_FLAGS_NEW)) { + TCA_FLOWER_KEY_CT_FLAGS_NEW | + TCA_FLOWER_KEY_CT_FLAGS_REPLY)) { NL_SET_ERR_MSG_MOD(extack, - "only ct_state trk, est and new are supported for offload"); + "only ct_state trk, est, new and rpl are supported for offload"); return -EOPNOTSUPP; } @@ -1118,13 +1124,17 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, trk = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_TRACKED; new = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_NEW; est = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED; + rpl = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_REPLY; untrk = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_TRACKED; unest = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED; + unrpl = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_REPLY; ctstate |= trk ? MLX5_CT_STATE_TRK_BIT : 0; ctstate |= est ? MLX5_CT_STATE_ESTABLISHED_BIT : 0; + ctstate |= rpl ? MLX5_CT_STATE_REPLY_BIT : 0; ctstate_mask |= (untrk || trk) ? MLX5_CT_STATE_TRK_BIT : 0; ctstate_mask |= (unest || est) ? MLX5_CT_STATE_ESTABLISHED_BIT : 0; + ctstate_mask |= (unrpl || rpl) ? MLX5_CT_STATE_REPLY_BIT : 0; if (new) { NL_SET_ERR_MSG_MOD(extack, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index 6488098d2700..959bb6cd7203 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -85,7 +85,7 @@ mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u16 ih } mlx5e_set_eseg_swp(skb, eseg, &swp_spec); - if (skb_vlan_tag_present(skb) && ihs) + if (skb_vlan_tag_present(skb) && ihs) mlx5e_eseg_swp_offsets_add_vlan(eseg); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c index 6c5c54bcd9be..5cb936541b9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c @@ -76,7 +76,7 @@ static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = { static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_sw) { - return NUM_IPSEC_SW_COUNTERS; + return priv->ipsec ? NUM_IPSEC_SW_COUNTERS : 0; } static inline MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_sw) {} @@ -105,7 +105,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw) static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_hw) { - return (mlx5_fpga_ipsec_device_caps(priv->mdev)) ? NUM_IPSEC_HW_COUNTERS : 0; + return (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev)) ? NUM_IPSEC_HW_COUNTERS : 0; } static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_hw) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index 1b392696280d..95293ee0d38d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -2,6 +2,7 @@ // Copyright (c) 2019 Mellanox Technologies. #include "en.h" +#include "en_accel/tls.h" #include "en_accel/ktls.h" #include "en_accel/ktls_utils.h" #include "en_accel/fs_tcp.h" @@ -86,16 +87,33 @@ int mlx5e_ktls_set_feature_rx(struct net_device *netdev, bool enable) int mlx5e_ktls_init_rx(struct mlx5e_priv *priv) { - int err = 0; + int err; - if (priv->netdev->features & NETIF_F_HW_TLS_RX) + if (!mlx5_accel_is_ktls_rx(priv->mdev)) + return 0; + + priv->tls->rx_wq = create_singlethread_workqueue("mlx5e_tls_rx"); + if (!priv->tls->rx_wq) + return -ENOMEM; + + if (priv->netdev->features & NETIF_F_HW_TLS_RX) { err = mlx5e_accel_fs_tcp_create(priv); + if (err) { + destroy_workqueue(priv->tls->rx_wq); + return err; + } + } - return err; + return 0; } void mlx5e_ktls_cleanup_rx(struct mlx5e_priv *priv) { + if (!mlx5_accel_is_ktls_rx(priv->mdev)) + return; + if (priv->netdev->features & NETIF_F_HW_TLS_RX) mlx5e_accel_fs_tcp_destroy(priv); + + destroy_workqueue(priv->tls->rx_wq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c index fee991f5ee7c..d6b21b899dbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c @@ -231,12 +231,6 @@ int mlx5e_tls_init(struct mlx5e_priv *priv) if (!tls) return -ENOMEM; - tls->rx_wq = create_singlethread_workqueue("mlx5e_tls_rx"); - if (!tls->rx_wq) { - kfree(tls); - return -ENOMEM; - } - priv->tls = tls; return 0; } @@ -248,7 +242,6 @@ void mlx5e_tls_cleanup(struct mlx5e_priv *priv) if (!tls) return; - destroy_workqueue(tls->rx_wq); kfree(tls); priv->tls = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index d20243d6a032..f23c67575073 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1151,6 +1151,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) { struct mlx5e_channels new_channels = {}; bool reset_channels = true; + bool opened; int err = 0; mutex_lock(&priv->state_lock); @@ -1159,22 +1160,24 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &new_channels.params, trust_state); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - priv->channels.params = new_channels.params; + opened = test_bit(MLX5E_STATE_OPENED, &priv->state); + if (!opened) reset_channels = false; - } /* Skip if tx_min_inline is the same */ if (new_channels.params.tx_min_inline_mode == priv->channels.params.tx_min_inline_mode) reset_channels = false; - if (reset_channels) + if (reset_channels) { err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_update_trust_state_hw, &trust_state); - else + } else { err = mlx5e_update_trust_state_hw(priv, &trust_state); + if (!err && !opened) + priv->channels.params = new_channels.params; + } mutex_unlock(&priv->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 2e5a0696374a..5e9474dba4e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -458,12 +458,18 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, goto out; } - new_channels.params = priv->channels.params; + new_channels.params = *cur_params; new_channels.params.num_channels = count; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + struct mlx5e_params old_params; + + old_params = *cur_params; *cur_params = new_channels.params; err = mlx5e_num_channels_changed(priv); + if (err) + *cur_params = old_params; + goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f8619d381345..4cfdba997f24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1892,13 +1892,11 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, if (err) goto err_close_rx_cq; - napi_enable(&c->napi); - spin_lock_init(&c->async_icosq_lock); err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq); if (err) - goto err_disable_napi; + goto err_close_xdpsq_cq; err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq); if (err) @@ -1941,9 +1939,7 @@ err_close_icosq: err_close_async_icosq: mlx5e_close_icosq(&c->async_icosq); -err_disable_napi: - napi_disable(&c->napi); - +err_close_xdpsq_cq: if (c->xdp) mlx5e_close_cq(&c->rq_xdpsq.cq); @@ -1974,7 +1970,6 @@ static void mlx5e_close_queues(struct mlx5e_channel *c) mlx5e_close_sqs(c); mlx5e_close_icosq(&c->icosq); mlx5e_close_icosq(&c->async_icosq); - napi_disable(&c->napi); if (c->xdp) mlx5e_close_cq(&c->rq_xdpsq.cq); mlx5e_close_cq(&c->rq.cq); @@ -2059,6 +2054,8 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) { int tc; + napi_enable(&c->napi); + for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_icosq(&c->icosq); @@ -2081,8 +2078,9 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c) mlx5e_deactivate_icosq(&c->icosq); for (tc = 0; tc < c->num_tc; tc++) mlx5e_deactivate_txqsq(&c->sq[tc]); - mlx5e_qos_deactivate_queues(c); + + napi_disable(&c->napi); } static void mlx5e_close_channel(struct mlx5e_channel *c) @@ -3685,18 +3683,23 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, new_channels.params.num_tc = tc ? tc : 1; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + struct mlx5e_params old_params; + + old_params = priv->channels.params; priv->channels.params = new_channels.params; + err = mlx5e_num_channels_changed(priv); + if (err) + priv->channels.params = old_params; + goto out; } err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_num_channels_changed_ctx, NULL); - if (err) - goto out; - priv->max_opened_tc = max_t(u8, priv->max_opened_tc, - new_channels.params.num_tc); out: + priv->max_opened_tc = max_t(u8, priv->max_opened_tc, + priv->channels.params.num_tc); mutex_unlock(&priv->state_lock); return err; } @@ -3876,21 +3879,21 @@ static int set_feature_lro(struct net_device *netdev, bool enable) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_channels new_channels = {}; - struct mlx5e_params *old_params; + struct mlx5e_params *cur_params; int err = 0; bool reset; mutex_lock(&priv->state_lock); if (enable && priv->xsk.refcnt) { - netdev_warn(netdev, "LRO is incompatible with AF_XDP (%hu XSKs are active)\n", + netdev_warn(netdev, "LRO is incompatible with AF_XDP (%u XSKs are active)\n", priv->xsk.refcnt); err = -EINVAL; goto out; } - old_params = &priv->channels.params; - if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) { + cur_params = &priv->channels.params; + if (enable && !MLX5E_GET_PFLAG(cur_params, MLX5E_PFLAG_RX_STRIDING_RQ)) { netdev_warn(netdev, "can't set LRO with legacy RQ\n"); err = -EINVAL; goto out; @@ -3898,18 +3901,23 @@ static int set_feature_lro(struct net_device *netdev, bool enable) reset = test_bit(MLX5E_STATE_OPENED, &priv->state); - new_channels.params = *old_params; + new_channels.params = *cur_params; new_channels.params.lro_en = enable; - if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) { - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params, NULL) == + if (cur_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) { + if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) == mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params, NULL)) reset = false; } if (!reset) { - *old_params = new_channels.params; + struct mlx5e_params old_params; + + old_params = *cur_params; + *cur_params = new_channels.params; err = mlx5e_modify_tirs_lro(priv); + if (err) + *cur_params = old_params; goto out; } @@ -4081,6 +4089,7 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, if (!params->vlan_strip_disable) netdev_warn(netdev, "Dropping C-tag vlan stripping offload due to S-tag vlan\n"); } + if (!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ)) { if (features & NETIF_F_LRO) { netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n"); @@ -4128,7 +4137,7 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev, max_mtu_page = mlx5e_xdp_max_mtu(new_params, &xsk); max_mtu = min(max_mtu_frame, max_mtu_page); - netdev_err(netdev, "MTU %d is too big for an XSK running on channel %hu. Try MTU <= %d\n", + netdev_err(netdev, "MTU %d is too big for an XSK running on channel %u. Try MTU <= %d\n", new_params->sw_mtu, ix, max_mtu); return false; } @@ -4189,9 +4198,16 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, } if (!reset) { + unsigned int old_mtu = params->sw_mtu; + params->sw_mtu = new_mtu; - if (preactivate) - preactivate(priv, NULL); + if (preactivate) { + err = preactivate(priv, NULL); + if (err) { + params->sw_mtu = old_mtu; + goto out; + } + } netdev->mtu = params->sw_mtu; goto out; } @@ -4909,15 +4925,15 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, tirc_default_config[tt].rx_hash_fields; } -void mlx5e_build_nic_params(struct mlx5e_priv *priv, - struct mlx5e_xsk *xsk, - struct mlx5e_rss_params *rss_params, - struct mlx5e_params *params, - u16 mtu) +void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu) { + struct mlx5e_rss_params *rss_params = &priv->rss_params; + struct mlx5e_params *params = &priv->channels.params; struct mlx5_core_dev *mdev = priv->mdev; u8 rx_cq_period_mode; + priv->max_nch = mlx5e_calc_max_nch(priv, priv->profile); + params->sw_mtu = mtu; params->hard_mtu = MLX5E_ETH_HARD_MTU; params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2, @@ -4975,6 +4991,11 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, /* AF_XDP */ params->xsk = xsk; + + /* Do not update netdev->features directly in here + * on mlx5e_attach_netdev() we will call mlx5e_update_features() + * To update netdev->features please modify mlx5e_fix_features() + */ } static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) @@ -5076,8 +5097,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; - mlx5e_vxlan_set_netdev_info(priv); - if (mlx5e_tunnel_any_tx_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; @@ -5127,25 +5146,19 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_RXFCS; netdev->features = netdev->hw_features; - if (!priv->channels.params.lro_en) - netdev->features &= ~NETIF_F_LRO; + /* Defaults */ if (fcs_enabled) netdev->features &= ~NETIF_F_RXALL; - - if (!priv->channels.params.scatter_fcs_en) - netdev->features &= ~NETIF_F_RXFCS; - - /* prefere CQE compression over rxhash */ - if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS)) - netdev->features &= ~NETIF_F_RXHASH; + netdev->features &= ~NETIF_F_LRO; + netdev->features &= ~NETIF_F_RXFCS; #define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f) if (FT_CAP(flow_modify_en) && FT_CAP(modify_root) && FT_CAP(identified_miss_table_mode) && FT_CAP(flow_table_modify)) { -#ifdef CONFIG_MLX5_ESWITCH +#if IS_ENABLED(CONFIG_MLX5_CLS_ACT) netdev->hw_features |= NETIF_F_HW_TC; #endif #ifdef CONFIG_MLX5_EN_ARFS @@ -5204,33 +5217,28 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) } static int mlx5e_nic_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) + struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rss_params *rss = &priv->rss_params; int err; - err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv); - if (err) - return err; - - mlx5e_build_nic_params(priv, &priv->xsk, rss, &priv->channels.params, - netdev->mtu); + mlx5e_build_nic_params(priv, &priv->xsk, netdev->mtu); + mlx5e_vxlan_set_netdev_info(priv); mlx5e_timestamp_init(priv); err = mlx5e_ipsec_init(priv); if (err) mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err); + err = mlx5e_tls_init(priv); 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; @@ -5242,7 +5250,6 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) mlx5e_devlink_port_unregister(priv); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); - mlx5e_netdev_cleanup(priv->netdev, priv); } static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) @@ -5445,21 +5452,16 @@ static const struct mlx5e_profile mlx5e_nic_profile = { }; /* mlx5e generic netdev management API (move to en_common.c) */ - -/* mlx5e_netdev_init/cleanup must be called from profile->init/cleanup callbacks */ -int mlx5e_netdev_init(struct net_device *netdev, - struct mlx5e_priv *priv, - struct mlx5_core_dev *mdev, - const struct mlx5e_profile *profile, - void *ppriv) +int mlx5e_priv_init(struct mlx5e_priv *priv, + struct net_device *netdev, + struct mlx5_core_dev *mdev) { + memset(priv, 0, sizeof(*priv)); + /* priv init */ priv->mdev = mdev; priv->netdev = netdev; - priv->profile = profile; - priv->ppriv = ppriv; priv->msglevel = MLX5E_MSG_LEVEL; - priv->max_nch = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); priv->max_opened_tc = 1; if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL)) @@ -5476,9 +5478,6 @@ int mlx5e_netdev_init(struct net_device *netdev, if (!priv->wq) goto err_free_cpumask; - /* netdev init */ - netif_carrier_off(netdev); - return 0; err_free_cpumask: @@ -5487,7 +5486,7 @@ err_free_cpumask: return -ENOMEM; } -void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv) +void mlx5e_priv_cleanup(struct mlx5e_priv *priv) { int i; @@ -5499,36 +5498,27 @@ void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv) kvfree(priv->htb.qos_sq_stats); } -struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, - const struct mlx5e_profile *profile, - int nch, - void *ppriv) +struct net_device * +mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int rxqs) { struct net_device *netdev; - unsigned int ptp_txqs = 0; - int qos_sqs = 0; int err; - if (MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn)) - ptp_txqs = profile->max_tc; - - if (mlx5_qos_is_supported(mdev)) - qos_sqs = mlx5e_qos_max_leaf_nodes(mdev); - - netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), - nch * profile->max_tc + ptp_txqs + qos_sqs, - nch * profile->rq_groups); + netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), txqs, rxqs); if (!netdev) { mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); return NULL; } - err = profile->init(mdev, netdev, profile, ppriv); + err = mlx5e_priv_init(netdev_priv(netdev), netdev, mdev); if (err) { - mlx5_core_err(mdev, "failed to init mlx5e profile %d\n", err); + mlx5_core_err(mdev, "mlx5e_priv_init failed, err=%d\n", err); goto err_free_netdev; } + netif_carrier_off(netdev); + dev_net_set(netdev, mlx5_core_net(mdev)); + return netdev; err_free_netdev: @@ -5537,14 +5527,23 @@ err_free_netdev: return NULL; } +static void mlx5e_update_features(struct net_device *netdev) +{ + if (netdev->reg_state != NETREG_REGISTERED) + return; /* features will be updated on netdev registration */ + + rtnl_lock(); + netdev_update_features(netdev); + rtnl_unlock(); +} + int mlx5e_attach_netdev(struct mlx5e_priv *priv) { const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED; - const struct mlx5e_profile *profile; + const struct mlx5e_profile *profile = priv->profile; int max_nch; int err; - profile = priv->profile; clear_bit(MLX5E_STATE_DESTROYING, &priv->state); /* max number of channels may have changed */ @@ -5584,6 +5583,8 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) if (profile->enable) profile->enable(priv); + mlx5e_update_features(priv->netdev); + return 0; err_cleanup_tx: @@ -5610,13 +5611,76 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) cancel_work_sync(&priv->update_stats_work); } +static int +mlx5e_netdev_attach_profile(struct mlx5e_priv *priv, + const struct mlx5e_profile *new_profile, void *new_ppriv) +{ + struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = priv->mdev; + int err; + + err = mlx5e_priv_init(priv, netdev, mdev); + if (err) { + mlx5_core_err(mdev, "mlx5e_priv_init failed, err=%d\n", err); + return err; + } + netif_carrier_off(netdev); + priv->profile = new_profile; + priv->ppriv = new_ppriv; + err = new_profile->init(priv->mdev, priv->netdev); + if (err) + return err; + err = mlx5e_attach_netdev(priv); + if (err) + new_profile->cleanup(priv); + return err; +} + +int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, + const struct mlx5e_profile *new_profile, void *new_ppriv) +{ + unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile); + const struct mlx5e_profile *orig_profile = priv->profile; + void *orig_ppriv = priv->ppriv; + int err, rollback_err; + + /* sanity */ + if (new_max_nch != priv->max_nch) { + netdev_warn(priv->netdev, + "%s: Replacing profile with different max channles\n", + __func__); + return -EINVAL; + } + + /* cleanup old profile */ + mlx5e_detach_netdev(priv); + priv->profile->cleanup(priv); + mlx5e_priv_cleanup(priv); + + err = mlx5e_netdev_attach_profile(priv, new_profile, new_ppriv); + if (err) { /* roll back to original profile */ + netdev_warn(priv->netdev, "%s: new profile init failed, %d\n", + __func__, err); + goto rollback; + } + + return 0; + +rollback: + rollback_err = mlx5e_netdev_attach_profile(priv, orig_profile, orig_ppriv); + if (rollback_err) { + netdev_err(priv->netdev, + "%s: failed to rollback to orig profile, %d\n", + __func__, rollback_err); + } + return err; +} + void mlx5e_destroy_netdev(struct mlx5e_priv *priv) { - const struct mlx5e_profile *profile = priv->profile; struct net_device *netdev = priv->netdev; - if (profile->cleanup) - profile->cleanup(priv); + mlx5e_priv_cleanup(priv); free_netdev(netdev); } @@ -5662,28 +5726,48 @@ static int mlx5e_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + const struct mlx5e_profile *profile = &mlx5e_nic_profile; struct mlx5_core_dev *mdev = edev->mdev; struct net_device *netdev; pm_message_t state = {}; - void *priv; + unsigned int txqs, rxqs, ptp_txqs = 0; + struct mlx5e_priv *priv; + int qos_sqs = 0; int err; int nch; + if (MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn)) + ptp_txqs = profile->max_tc; + + if (mlx5_qos_is_supported(mdev)) + qos_sqs = mlx5e_qos_max_leaf_nodes(mdev); + nch = mlx5e_get_max_num_channels(mdev); - netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL); + txqs = nch * profile->max_tc + ptp_txqs + qos_sqs; + rxqs = nch * profile->rq_groups; + netdev = mlx5e_create_netdev(mdev, txqs, rxqs); if (!netdev) { mlx5_core_err(mdev, "mlx5e_create_netdev failed\n"); return -ENOMEM; } - dev_net_set(netdev, mlx5_core_net(mdev)); + mlx5e_build_nic_netdev(netdev); + priv = netdev_priv(netdev); dev_set_drvdata(&adev->dev, priv); + priv->profile = profile; + priv->ppriv = NULL; + err = profile->init(mdev, netdev); + if (err) { + mlx5_core_err(mdev, "mlx5e_nic_profile init failed, %d\n", err); + goto err_destroy_netdev; + } + err = mlx5e_resume(adev); if (err) { mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err); - goto err_destroy_netdev; + goto err_profile_cleanup; } err = register_netdev(netdev); @@ -5699,6 +5783,8 @@ static int mlx5e_probe(struct auxiliary_device *adev, err_resume: mlx5e_suspend(adev, state); +err_profile_cleanup: + profile->cleanup(priv); err_destroy_netdev: mlx5e_destroy_netdev(priv); return err; @@ -5712,6 +5798,7 @@ static void mlx5e_remove(struct auxiliary_device *adev) mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); + priv->profile->cleanup(priv); 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 cfa0e8552975..84eeaa33033f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -684,7 +684,10 @@ static void mlx5e_build_rep_params(struct net_device *netdev) MLX5_CQ_PERIOD_MODE_START_FROM_CQE : MLX5_CQ_PERIOD_MODE_START_FROM_EQE; + priv->max_nch = mlx5e_calc_max_nch(priv, priv->profile); params = &priv->channels.params; + + params->num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS; params->hard_mtu = MLX5E_ETH_HARD_MTU; params->sw_mtu = netdev->mtu; @@ -710,20 +713,16 @@ static void mlx5e_build_rep_params(struct net_device *netdev) mlx5e_build_rss_params(&priv->rss_params, params->num_channels); } -static void mlx5e_build_rep_netdev(struct net_device *netdev) +static void mlx5e_build_rep_netdev(struct net_device *netdev, + struct mlx5_core_dev *mdev, + struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; - struct mlx5_core_dev *mdev = priv->mdev; - SET_NETDEV_DEV(netdev, mdev->device); if (rep->vport == MLX5_VPORT_UPLINK) { netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep; /* we want a persistent mac for the uplink rep */ mlx5_query_mac_address(mdev, netdev->dev_addr); netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops; - mlx5e_vxlan_set_netdev_info(priv); mlx5e_dcbnl_build_rep_netdev(netdev); } else { netdev->netdev_ops = &mlx5e_netdev_ops_rep; @@ -735,7 +734,9 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->features |= NETIF_F_NETNS_LOCAL; +#if IS_ENABLED(CONFIG_MLX5_CLS_ACT) netdev->hw_features |= NETIF_F_HW_TC; +#endif netdev->hw_features |= NETIF_F_SG; netdev->hw_features |= NETIF_F_IP_CSUM; netdev->hw_features |= NETIF_F_IPV6_CSUM; @@ -753,30 +754,27 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) } static int mlx5e_init_rep(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) + struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - int err; - - err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv); - if (err) - return err; - - priv->channels.params.num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS; mlx5e_build_rep_params(netdev); - mlx5e_build_rep_netdev(netdev); - mlx5e_timestamp_init(priv); return 0; } +static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, + struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + mlx5e_vxlan_set_netdev_info(priv); + return mlx5e_init_rep(mdev, netdev); +} + static void mlx5e_cleanup_rep(struct mlx5e_priv *priv) { - mlx5e_netdev_cleanup(priv->netdev, priv); } static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv) @@ -1053,7 +1051,17 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) static void mlx5e_rep_enable(struct mlx5e_priv *priv) { + struct mlx5e_rep_priv *rpriv = priv->ppriv; + mlx5e_set_netdev_mtu_boundaries(priv); + mlx5e_rep_neigh_init(rpriv); +} + +static void mlx5e_rep_disable(struct mlx5e_priv *priv) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + + mlx5e_rep_neigh_cleanup(rpriv); } static int mlx5e_update_rep_rx(struct mlx5e_priv *priv) @@ -1088,6 +1096,7 @@ static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) { + struct mlx5e_rep_priv *rpriv = priv->ppriv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; u16 max_mtu; @@ -1106,12 +1115,15 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5_notifier_register(mdev, &priv->events_nb); mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); + mlx5e_rep_neigh_init(rpriv); } static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { + struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; + mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); mlx5e_rep_tc_disable(priv); @@ -1163,6 +1175,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .init_tx = mlx5e_init_rep_tx, .cleanup_tx = mlx5e_cleanup_rep_tx, .enable = mlx5e_rep_enable, + .disable = mlx5e_rep_disable, .update_rx = mlx5e_update_rep_rx, .update_stats = mlx5e_stats_update_ndo_stats, .rx_handlers = &mlx5e_rx_handlers_rep, @@ -1173,7 +1186,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { }; static const struct mlx5e_profile mlx5e_uplink_rep_profile = { - .init = mlx5e_init_rep, + .init = mlx5e_init_ul_rep, .cleanup = mlx5e_cleanup_rep, .init_rx = mlx5e_init_ul_rep_rx, .cleanup_rx = mlx5e_cleanup_ul_rep_rx, @@ -1199,6 +1212,8 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) struct mlx5e_rep_priv *rpriv; struct devlink_port *dl_port; struct net_device *netdev; + struct mlx5e_priv *priv; + unsigned int txqs, rxqs; int nch, err; rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL); @@ -1208,10 +1223,13 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) /* rpriv->rep to be looked up when profile->init() is called */ rpriv->rep = rep; - nch = mlx5e_get_max_num_channels(dev); profile = (rep->vport == MLX5_VPORT_UPLINK) ? &mlx5e_uplink_rep_profile : &mlx5e_rep_profile; - netdev = mlx5e_create_netdev(dev, profile, nch, rpriv); + + nch = mlx5e_get_max_num_channels(dev); + txqs = nch * profile->max_tc; + rxqs = nch * profile->rq_groups; + netdev = mlx5e_create_netdev(dev, txqs, rxqs); if (!netdev) { mlx5_core_warn(dev, "Failed to create representor netdev for vport %d\n", @@ -1220,7 +1238,8 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return -EINVAL; } - dev_net_set(netdev, mlx5_core_net(dev)); + mlx5e_build_rep_netdev(netdev, dev, rep); + rpriv->netdev = netdev; rep->rep_data[REP_ETH].priv = rpriv; INIT_LIST_HEAD(&rpriv->vport_sqs_list); @@ -1231,20 +1250,21 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) goto err_destroy_netdev; } - err = mlx5e_attach_netdev(netdev_priv(netdev)); + priv = netdev_priv(netdev); + priv->profile = profile; + priv->ppriv = rpriv; + err = profile->init(dev, netdev); if (err) { - netdev_warn(netdev, - "Failed to attach representor netdev for vport %d\n", - rep->vport); + netdev_warn(netdev, "rep profile init failed, %d\n", err); goto err_destroy_mdev_resources; } - err = mlx5e_rep_neigh_init(rpriv); + err = mlx5e_attach_netdev(netdev_priv(netdev)); if (err) { netdev_warn(netdev, - "Failed to initialized neighbours handling for vport %d\n", + "Failed to attach representor netdev for vport %d\n", rep->vport); - goto err_detach_netdev; + goto err_cleanup_profile; } err = register_netdev(netdev); @@ -1252,7 +1272,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) netdev_warn(netdev, "Failed to register representor netdev for vport %d\n", rep->vport); - goto err_neigh_cleanup; + goto err_detach_netdev; } dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); @@ -1260,12 +1280,12 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) devlink_port_type_eth_set(dl_port, netdev); return 0; -err_neigh_cleanup: - mlx5e_rep_neigh_cleanup(rpriv); - err_detach_netdev: mlx5e_detach_netdev(netdev_priv(netdev)); +err_cleanup_profile: + priv->profile->cleanup(priv); + err_destroy_mdev_resources: if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(dev); @@ -1290,8 +1310,8 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) if (dl_port) devlink_port_type_clear(dl_port); unregister_netdev(netdev); - mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); + priv->profile->cleanup(priv); if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(priv->mdev); mlx5e_destroy_netdev(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 98b56f495b32..50723e5fb085 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1259,8 +1259,10 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); if (mlx5e_cqe_regb_chain(cqe)) - if (!mlx5e_tc_update_skb(cqe, skb)) + if (!mlx5e_tc_update_skb(cqe, skb)) { + dev_kfree_skb_any(skb); goto free_wqe; + } napi_gro_receive(rq->cq.napi, skb); @@ -1313,8 +1315,10 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) if (rep->vlan && skb_vlan_tag_present(skb)) skb_vlan_pop(skb); - if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) + if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) { + dev_kfree_skb_any(skb); goto free_wqe; + } napi_gro_receive(rq->cq.napi, skb); @@ -1368,8 +1372,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); - if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) + if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) { + dev_kfree_skb_any(skb); goto mpwrq_cqe_out; + } napi_gro_receive(rq->cq.napi, skb); @@ -1525,8 +1531,10 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); if (mlx5e_cqe_regb_chain(cqe)) - if (!mlx5e_tc_update_skb(cqe, skb)) + if (!mlx5e_tc_update_skb(cqe, skb)) { + dev_kfree_skb_any(skb); goto mpwrq_cqe_out; + } napi_gro_receive(rq->cq.napi, skb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 56aa39ac1a1c..280ea1e1e039 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -67,6 +67,7 @@ #include "lib/geneve.h" #include "lib/fs_chains.h" #include "diag/en_tc_tracepoint.h" +#include <asm/div64.h> #define nic_chains(priv) ((priv)->fs.tc.chains) #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) @@ -189,6 +190,14 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [NIC_ZONE_RESTORE_TO_REG] = nic_zone_restore_to_reg_ct, }; +/* To avoid false lock dependency warning set the tc_ht lock + * class different than the lock class of the ht being used when deleting + * last flow from a group and then deleting a group, we get into del_sw_flow_group() + * which call rhashtable_destroy on fg->ftes_hash which will take ht->mutex but + * it's different than the ht->mutex here. + */ +static struct lock_class_key tc_ht_lock_key; + static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); void @@ -1162,6 +1171,9 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts; struct mlx5_flow_handle *rule; + if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) + return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); + if (flow_flag_test(flow, CT)) { mod_hdr_acts = &attr->parse_attr->mod_hdr_acts; @@ -1192,6 +1204,9 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, { flow_flag_clear(flow, OFFLOADED); + if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) + goto offload_rule_0; + if (flow_flag_test(flow, CT)) { mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); return; @@ -1200,6 +1215,7 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, if (attr->esw_attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); +offload_rule_0: mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); } @@ -2263,8 +2279,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | BIT(FLOW_DISSECTOR_KEY_MPLS))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); - netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", - dissector->used_keys); + netdev_dbg(priv->netdev, "Unsupported key used: 0x%x\n", + dissector->used_keys); return -EOPNOTSUPP; } @@ -5001,13 +5017,13 @@ errout: return err; } -static int apply_police_params(struct mlx5e_priv *priv, u32 rate, +static int apply_police_params(struct mlx5e_priv *priv, u64 rate, struct netlink_ext_ack *extack) { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch *esw; + u32 rate_mbps = 0; u16 vport_num; - u32 rate_mbps; int err; vport_num = rpriv->rep->vport; @@ -5024,7 +5040,11 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate, * Moreover, if rate is non zero we choose to configure to a minimum of * 1 mbit/sec. */ - rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; + if (rate) { + rate = (rate * BITS_PER_BYTE) + 500000; + rate_mbps = max_t(u32, do_div(rate, 1000000), 1); + } + err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); if (err) NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); @@ -5203,6 +5223,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) if (err) return err; + lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); + if (MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) { attr.flags = MLX5_CHAINS_AND_PRIOS_SUPPORTED | MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED; @@ -5321,6 +5343,8 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) if (err) goto err_ht_init; + lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key); + return err; err_ht_init: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index fc0afa03d407..174dfbc996c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -467,7 +467,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++) ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]); - eq_table->irq_table = dev->priv.irq_table; + eq_table->irq_table = mlx5_irq_table_get(dev); return 0; } @@ -595,6 +595,9 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4]) async_event_mask |= (1ull << MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED); + if (MLX5_CAP_GEN_MAX(dev, vhca_state)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_VHCA_STATE_CHANGE); + mask[0] = async_event_mask; if (MLX5_CAP_GEN(dev, event_cap)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c index 4c74e2690d57..26b37a0f8762 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c @@ -150,7 +150,7 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport) static bool esw_acl_egress_needed(const struct mlx5_eswitch *esw, u16 vport_num) { - return mlx5_eswitch_is_vf_vport(esw, vport_num); + return mlx5_eswitch_is_vf_vport(esw, vport_num) || mlx5_esw_is_sf_vport(esw, vport_num); } int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index ffff11baa3d0..cb1e181f4c6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -122,3 +122,44 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1 vport = mlx5_eswitch_get_vport(esw, vport_num); return vport->dl_port; } + +int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port, + u16 vport_num, u32 sfnum) +{ + struct mlx5_core_dev *dev = esw->dev; + struct netdev_phys_item_id ppid = {}; + unsigned int dl_port_index; + struct mlx5_vport *vport; + struct devlink *devlink; + u16 pfnum; + int err; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + pfnum = PCI_FUNC(dev->pdev->devfn); + mlx5_esw_get_port_parent_id(dev, &ppid); + memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len); + dl_port->attrs.switch_id.id_len = ppid.id_len; + devlink_port_attrs_pci_sf_set(dl_port, 0, pfnum, sfnum); + devlink = priv_to_devlink(dev); + dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); + err = devlink_port_register(devlink, dl_port, dl_port_index); + if (err) + return err; + + vport->dl_port = dl_port; + return 0; +} + +void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num) +{ + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return; + devlink_port_unregister(vport->dl_port); + vport->dl_port = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 876e6449edb3..820305b1664e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1272,8 +1272,8 @@ static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport esw_vport_cleanup_acl(esw, vport); } -static int esw_enable_vport(struct mlx5_eswitch *esw, u16 vport_num, - enum mlx5_eswitch_vport_event enabled_events) +int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num, + enum mlx5_eswitch_vport_event enabled_events) { struct mlx5_vport *vport; int ret; @@ -1309,7 +1309,7 @@ done: return ret; } -static void esw_disable_vport(struct mlx5_eswitch *esw, u16 vport_num) +void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_vport *vport; @@ -1365,9 +1365,15 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) { int outlen = MLX5_ST_SZ_BYTES(query_esw_functions_out); u32 in[MLX5_ST_SZ_DW(query_esw_functions_in)] = {}; + u16 max_sf_vports; u32 *out; int err; + max_sf_vports = mlx5_sf_max_functions(dev); + /* Device interface is array of 64-bits */ + if (max_sf_vports) + outlen += DIV_ROUND_UP(max_sf_vports, BITS_PER_TYPE(__be64)) * sizeof(__be64); + out = kvzalloc(outlen, GFP_KERNEL); if (!out) return ERR_PTR(-ENOMEM); @@ -1375,7 +1381,7 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) MLX5_SET(query_esw_functions_in, in, opcode, MLX5_CMD_OP_QUERY_ESW_FUNCTIONS); - err = mlx5_cmd_exec_inout(dev, query_esw_functions, in, out); + err = mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); if (!err) return out; @@ -1425,7 +1431,7 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, { int err; - err = esw_enable_vport(esw, vport_num, enabled_events); + err = mlx5_esw_vport_enable(esw, vport_num, enabled_events); if (err) return err; @@ -1436,14 +1442,14 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, return err; err_rep: - esw_disable_vport(esw, vport_num); + mlx5_esw_vport_disable(esw, vport_num); return err; } void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num) { esw_offloads_unload_rep(esw, vport_num); - esw_disable_vport(esw, vport_num); + mlx5_esw_vport_disable(esw, vport_num); } void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs) @@ -1593,6 +1599,15 @@ mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs) kvfree(out); } +static void mlx5_esw_mode_change_notify(struct mlx5_eswitch *esw, u16 mode) +{ + struct mlx5_esw_event_info info = {}; + + info.new_mode = mode; + + blocking_notifier_call_chain(&esw->n_head, 0, &info); +} + /** * mlx5_eswitch_enable_locked - Enable eswitch * @esw: Pointer to eswitch @@ -1653,6 +1668,8 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs) mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); + mlx5_esw_mode_change_notify(esw, mode); + return 0; abort: @@ -1709,6 +1726,11 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); + /* Notify eswitch users that it is exiting from current mode. + * So that it can do necessary cleanup before the eswitch is disabled. + */ + mlx5_esw_mode_change_notify(esw, MLX5_ESWITCH_NONE); + mlx5_eswitch_event_handlers_unregister(esw); if (esw->mode == MLX5_ESWITCH_LEGACY) @@ -1809,6 +1831,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; dev->priv.eswitch = esw; + BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); return 0; abort: if (esw->work_queue) @@ -1898,7 +1921,8 @@ static bool is_port_function_supported(const struct mlx5_eswitch *esw, u16 vport_num) { return vport_num == MLX5_VPORT_PF || - mlx5_eswitch_is_vf_vport(esw, vport_num); + mlx5_eswitch_is_vf_vport(esw, vport_num) || + mlx5_esw_is_sf_vport(esw, vport_num); } int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, @@ -2499,4 +2523,12 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0, dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS); } +int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&esw->n_head, nb); +} +void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&esw->n_head, nb); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index cf87de94418f..479d2ac2cd85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -43,6 +43,7 @@ #include <linux/mlx5/fs.h> #include "lib/mpfs.h" #include "lib/fs_chains.h" +#include "sf/sf.h" #include "en/tc_ct.h" #ifdef CONFIG_MLX5_ESWITCH @@ -277,6 +278,7 @@ struct mlx5_eswitch { struct { u32 large_group_num; } params; + struct blocking_notifier_head n_head; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -499,6 +501,40 @@ static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev) MLX5_VPORT_PF : MLX5_VPORT_FIRST_VF; } +static inline int mlx5_esw_sf_start_idx(const struct mlx5_eswitch *esw) +{ + /* PF and VF vports indices start from 0 to max_vfs */ + return MLX5_VPORT_PF_PLACEHOLDER + mlx5_core_max_vfs(esw->dev); +} + +static inline int mlx5_esw_sf_end_idx(const struct mlx5_eswitch *esw) +{ + return mlx5_esw_sf_start_idx(esw) + mlx5_sf_max_functions(esw->dev); +} + +static inline int +mlx5_esw_sf_vport_num_to_index(const struct mlx5_eswitch *esw, u16 vport_num) +{ + return vport_num - mlx5_sf_start_function_id(esw->dev) + + MLX5_VPORT_PF_PLACEHOLDER + mlx5_core_max_vfs(esw->dev); +} + +static inline u16 +mlx5_esw_sf_vport_index_to_num(const struct mlx5_eswitch *esw, int idx) +{ + return mlx5_sf_start_function_id(esw->dev) + idx - + (MLX5_VPORT_PF_PLACEHOLDER + mlx5_core_max_vfs(esw->dev)); +} + +static inline bool +mlx5_esw_is_sf_vport(const struct mlx5_eswitch *esw, u16 vport_num) +{ + return mlx5_sf_supported(esw->dev) && + vport_num >= mlx5_sf_start_function_id(esw->dev) && + (vport_num < (mlx5_sf_start_function_id(esw->dev) + + mlx5_sf_max_functions(esw->dev))); +} + static inline bool mlx5_eswitch_is_funcs_handler(const struct mlx5_core_dev *dev) { return mlx5_core_is_ecpf_esw_manager(dev); @@ -527,6 +563,10 @@ static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw, if (vport_num == MLX5_VPORT_UPLINK) return mlx5_eswitch_uplink_idx(esw); + if (mlx5_esw_is_sf_vport(esw, vport_num)) + return mlx5_esw_sf_vport_num_to_index(esw, vport_num); + + /* PF and VF vports start from 0 to max_vfs */ return vport_num; } @@ -540,6 +580,12 @@ static inline u16 mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw, if (index == mlx5_eswitch_uplink_idx(esw)) return MLX5_VPORT_UPLINK; + /* SF vports indices are after VFs and before ECPF */ + if (mlx5_sf_supported(esw->dev) && + index > mlx5_core_max_vfs(esw->dev)) + return mlx5_esw_sf_vport_index_to_num(esw, index); + + /* PF and VF vports start from 0 to max_vfs */ return index; } @@ -625,6 +671,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); for ((vport) = (nvfs); \ (vport) >= (esw)->first_host_vport; (vport)--) +#define mlx5_esw_for_each_sf_rep(esw, i, rep) \ + for ((i) = mlx5_esw_sf_start_idx(esw); \ + (rep) = &(esw)->offloads.vport_reps[(i)], \ + (i) < mlx5_esw_sf_end_idx(esw); (i++)) + struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink); struct mlx5_vport *__must_check mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num); @@ -638,6 +689,10 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, enum mlx5_eswitch_vport_event enabled_events); void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); +int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num, + enum mlx5_eswitch_vport_event enabled_events); +void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num); + int esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, struct mlx5_vport *vport); @@ -656,6 +711,9 @@ esw_get_max_restore_tag(struct mlx5_eswitch *esw); int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num); void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num); +int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num); +void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num); + int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, enum mlx5_eswitch_vport_event enabled_events); void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num); @@ -667,6 +725,26 @@ void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs); int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num); void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num); struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num); + +int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port, + u16 vport_num, u32 sfnum); +void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num); + +int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_port *dl_port, + u16 vport_num, u32 sfnum); +void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num); + +/** + * mlx5_esw_event_info - Indicates eswitch mode changed/changing. + * + * @new_mode: New mode of eswitch. + */ +struct mlx5_esw_event_info { + u16 new_mode; +}; + +int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *n); +void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *n); #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 2f6a0ae20650..7f09f2bbf7c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1800,11 +1800,22 @@ static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, esw->offloads.rep_ops[rep_type]->unload(rep); } +static void __unload_reps_sf_vport(struct mlx5_eswitch *esw, u8 rep_type) +{ + struct mlx5_eswitch_rep *rep; + int i; + + mlx5_esw_for_each_sf_rep(esw, i, rep) + __esw_offloads_unload_rep(esw, rep, rep_type); +} + static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type) { struct mlx5_eswitch_rep *rep; int i; + __unload_reps_sf_vport(esw, rep_type); + mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, esw->esw_funcs.num_vfs) __esw_offloads_unload_rep(esw, rep, rep_type); @@ -1822,7 +1833,7 @@ static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type) __esw_offloads_unload_rep(esw, rep, rep_type); } -static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num) +int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_eswitch_rep *rep; int rep_type; @@ -1846,7 +1857,7 @@ err_reps: return err; } -static void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num) +void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_eswitch_rep *rep; int rep_type; @@ -2824,3 +2835,35 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, return vport->metadata << (32 - ESW_SOURCE_PORT_METADATA_BITS); } EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match); + +int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_port *dl_port, + u16 vport_num, u32 sfnum) +{ + int err; + + err = mlx5_esw_vport_enable(esw, vport_num, MLX5_VPORT_UC_ADDR_CHANGE); + if (err) + return err; + + err = mlx5_esw_devlink_sf_port_register(esw, dl_port, vport_num, sfnum); + if (err) + goto devlink_err; + + err = mlx5_esw_offloads_rep_load(esw, vport_num); + if (err) + goto rep_err; + return 0; + +rep_err: + mlx5_esw_devlink_sf_port_unregister(esw, vport_num); +devlink_err: + mlx5_esw_vport_disable(esw, vport_num); + return err; +} + +void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num) +{ + mlx5_esw_offloads_rep_unload(esw, vport_num); + mlx5_esw_devlink_sf_port_unregister(esw, vport_num); + mlx5_esw_vport_disable(esw, vport_num); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index 670f25f5ffd1..d713ae24d6b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -112,6 +112,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_CMD"; case MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED: return "MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED"; + case MLX5_EVENT_TYPE_VHCA_STATE_CHANGE: + return "MLX5_EVENT_TYPE_VHCA_STATE_CHANGE"; case MLX5_EVENT_TYPE_PAGE_REQUEST: return "MLX5_EVENT_TYPE_PAGE_REQUEST"; case MLX5_EVENT_TYPE_PAGE_FAULT: @@ -434,3 +436,8 @@ int mlx5_blocking_notifier_call_chain(struct mlx5_core_dev *dev, unsigned int ev return blocking_notifier_call_chain(&events->sw_nh, event, data); } + +void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work) +{ + queue_work(dev->priv.events->wq, work); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3dbd63b9845d..11b89a3a2ff5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1141,6 +1141,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa destroy_ft: root->cmds->destroy_flow_table(root, ft); free_ft: + rhltable_destroy(&ft->fgs_hash); kfree(ft); unlock_root: mutex_unlock(&root->chain_lock); @@ -1759,6 +1760,7 @@ search_again_locked: if (!fte_tmp) continue; rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp); + /* No error check needed here, because insert_fte() is not called */ up_write_ref_node(&fte_tmp->node, false); tree_put_node(&fte_tmp->node, false); kmem_cache_free(steering->ftes_cache, fte); @@ -1811,6 +1813,8 @@ skip_search: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); + if (IS_ERR(rule)) + tree_put_node(&fte->node, false); return rule; } rule = ERR_PTR(-ENOENT); @@ -1909,6 +1913,8 @@ search_again_locked: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); + if (IS_ERR(rule)) + tree_put_node(&fte->node, false); tree_put_node(&g->node, false); return rule; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 97b5fcb1f406..1eeca45cfcdf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -72,23 +72,15 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, } /* Called directly after IPoIB netdevice was created to initialize SW structs */ -int mlx5i_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) +int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); - int err; - - err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv); - if (err) - return err; + netif_carrier_off(netdev); mlx5e_set_netdev_mtu_boundaries(priv); netdev->mtu = netdev->max_mtu; - mlx5e_build_nic_params(priv, NULL, &priv->rss_params, &priv->channels.params, - netdev->mtu); + mlx5e_build_nic_params(priv, NULL, netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); mlx5e_timestamp_init(priv); @@ -112,7 +104,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev, /* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */ void mlx5i_cleanup(struct mlx5e_priv *priv) { - mlx5e_netdev_cleanup(priv->netdev, priv); + mlx5e_priv_cleanup(priv); } static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) @@ -753,7 +745,14 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num, goto destroy_ht; } - prof->init(mdev, netdev, prof, ipriv); + err = mlx5e_priv_init(epriv, netdev, mdev); + if (err) + goto destroy_mdev_resources; + + epriv->profile = prof; + epriv->ppriv = ipriv; + + prof->init(mdev, netdev); err = mlx5e_attach_netdev(epriv); if (err) @@ -777,6 +776,7 @@ detach: prof->cleanup(epriv); if (ipriv->sub_interface) return err; +destroy_mdev_resources: mlx5e_destroy_mdev_resources(mdev); destroy_ht: mlx5i_pkey_qpn_ht_cleanup(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index b79dc1e28c41..99d46fda9f82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -87,10 +87,7 @@ void mlx5i_dev_cleanup(struct net_device *dev); int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); /* Parent profile functions */ -int mlx5i_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv); +int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5i_cleanup(struct mlx5e_priv *priv); int mlx5i_update_nic_rx(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 7163d9f6c4a6..3d0a18a0bed4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -276,14 +276,12 @@ static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu) /* Called directly after IPoIB netdevice was created to initialize SW structs */ static int mlx5i_pkey_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) + struct net_device *netdev) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); int err; - err = mlx5i_init(mdev, netdev, profile, ppriv); + err = mlx5i_init(mdev, netdev); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 3a9fa629503f..d046db7bb047 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -90,4 +90,9 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, u32 key_type, u32 *p_key_id); void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id); +static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) +{ + return devlink_net(priv_to_devlink(dev)); +} + #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index bfedf064db1a..e4c9627485aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -73,6 +73,9 @@ #include "ecpf.h" #include "lib/hv_vhca.h" #include "diag/rsc_dump.h" +#include "sf/vhca_event.h" +#include "sf/dev/dev.h" +#include "sf/sf.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -82,7 +85,6 @@ unsigned int mlx5_core_debug_mask; module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644); MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec time, 3 = both. Default=0"); -#define MLX5_DEFAULT_PROF 2 static unsigned int prof_sel = MLX5_DEFAULT_PROF; module_param_named(prof_sel, prof_sel, uint, 0444); MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2"); @@ -567,6 +569,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) if (MLX5_CAP_GEN_MAX(dev, mkey_by_name)) MLX5_SET(cmd_hca_cap, set_hca_cap, mkey_by_name, 1); + mlx5_vhca_state_cap_handle(dev, set_hca_cap); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } @@ -884,6 +888,24 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eswitch_cleanup; } + err = mlx5_vhca_event_init(dev); + if (err) { + mlx5_core_err(dev, "Failed to init vhca event notifier %d\n", err); + goto err_fpga_cleanup; + } + + err = mlx5_sf_hw_table_init(dev); + if (err) { + mlx5_core_err(dev, "Failed to init SF HW table %d\n", err); + goto err_sf_hw_table_cleanup; + } + + err = mlx5_sf_table_init(dev); + if (err) { + mlx5_core_err(dev, "Failed to init SF table %d\n", err); + goto err_sf_table_cleanup; + } + dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) mlx5_core_warn(dev, "Failed to init device memory%d\n", err); @@ -894,6 +916,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) return 0; +err_sf_table_cleanup: + mlx5_sf_hw_table_cleanup(dev); +err_sf_hw_table_cleanup: + mlx5_vhca_event_cleanup(dev); +err_fpga_cleanup: + mlx5_fpga_cleanup(dev); err_eswitch_cleanup: mlx5_eswitch_cleanup(dev->priv.eswitch); err_sriov_cleanup: @@ -925,6 +953,9 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); mlx5_dm_cleanup(dev); + mlx5_sf_table_cleanup(dev); + mlx5_sf_hw_table_cleanup(dev); + mlx5_vhca_event_cleanup(dev); mlx5_fpga_cleanup(dev); mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_sriov_cleanup(dev); @@ -1129,6 +1160,14 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_sriov; } + mlx5_vhca_event_start(dev); + + err = mlx5_sf_hw_table_create(dev); + if (err) { + mlx5_core_err(dev, "sf table create failed %d\n", err); + goto err_vhca; + } + err = mlx5_ec_init(dev); if (err) { mlx5_core_err(dev, "Failed to init embedded CPU\n"); @@ -1141,11 +1180,16 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_sriov; } + mlx5_sf_dev_table_create(dev); + return 0; err_sriov: mlx5_ec_cleanup(dev); err_ec: + mlx5_sf_hw_table_destroy(dev); +err_vhca: + mlx5_vhca_event_stop(dev); mlx5_cleanup_fs(dev); err_fs: mlx5_accel_tls_cleanup(dev); @@ -1171,8 +1215,11 @@ err_irq_table: static void mlx5_unload(struct mlx5_core_dev *dev) { + mlx5_sf_dev_table_destroy(dev); mlx5_sriov_detach(dev); mlx5_ec_cleanup(dev); + mlx5_sf_hw_table_destroy(dev); + mlx5_vhca_event_stop(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); @@ -1283,7 +1330,7 @@ out: mutex_unlock(&dev->intf_state_mutex); } -static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) +int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { struct mlx5_priv *priv = &dev->priv; int err; @@ -1335,7 +1382,7 @@ err_health_init: return err; } -static void mlx5_mdev_uninit(struct mlx5_core_dev *dev) +void mlx5_mdev_uninit(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; @@ -1678,6 +1725,10 @@ static int __init init(void) if (err) goto err_debug; + err = mlx5_sf_driver_register(); + if (err) + goto err_sf; + #ifdef CONFIG_MLX5_CORE_EN err = mlx5e_init(); if (err) { @@ -1688,6 +1739,8 @@ static int __init init(void) return 0; +err_sf: + pci_unregister_driver(&mlx5_core_driver); err_debug: mlx5_unregister_debugfs(); return err; @@ -1698,6 +1751,7 @@ static void __exit cleanup(void) #ifdef CONFIG_MLX5_CORE_EN mlx5e_cleanup(); #endif + mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); mlx5_unregister_debugfs(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 0a0302ce7144..3754ef98554f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -117,6 +117,8 @@ enum mlx5_semaphore_space_address { MLX5_SEMAPHORE_SW_RESET = 0x20, }; +#define MLX5_DEFAULT_PROF 2 + int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init(struct mlx5_core_dev *dev); @@ -176,6 +178,7 @@ struct cpumask * mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx); struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table); int mlx5_irq_get_num_comp(struct mlx5_irq_table *table); +struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); int mlx5_events_init(struct mlx5_core_dev *dev); void mlx5_events_cleanup(struct mlx5_core_dev *dev); @@ -257,6 +260,15 @@ enum { u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); +static inline bool mlx5_core_is_sf(const struct mlx5_core_dev *dev) +{ + return dev->coredev_type == MLX5_COREDEV_SF; +} + +int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx); +void mlx5_mdev_uninit(struct mlx5_core_dev *dev); void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup); int mlx5_load_one(struct mlx5_core_dev *dev, bool boot); + +void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work); #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index eb956ce904bc..c0656d4782e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -58,7 +58,7 @@ struct fw_page { struct rb_node rb_node; u64 addr; struct page *page; - u16 func_id; + u32 function; unsigned long bitmask; struct list_head list; unsigned free_count; @@ -74,12 +74,17 @@ enum { MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, }; -static struct rb_root *page_root_per_func_id(struct mlx5_core_dev *dev, u16 func_id) +static u32 get_function(u16 func_id, bool ec_function) +{ + return (u32)func_id | (ec_function << 16); +} + +static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function) { struct rb_root *root; int err; - root = xa_load(&dev->priv.page_root_xa, func_id); + root = xa_load(&dev->priv.page_root_xa, function); if (root) return root; @@ -87,7 +92,7 @@ static struct rb_root *page_root_per_func_id(struct mlx5_core_dev *dev, u16 func if (!root) return ERR_PTR(-ENOMEM); - err = xa_insert(&dev->priv.page_root_xa, func_id, root, GFP_KERNEL); + err = xa_insert(&dev->priv.page_root_xa, function, root, GFP_KERNEL); if (err) { kfree(root); return ERR_PTR(err); @@ -98,7 +103,7 @@ static struct rb_root *page_root_per_func_id(struct mlx5_core_dev *dev, u16 func return root; } -static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id) +static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u32 function) { struct rb_node *parent = NULL; struct rb_root *root; @@ -107,7 +112,7 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u struct fw_page *tfp; int i; - root = page_root_per_func_id(dev, func_id); + root = page_root_per_function(dev, function); if (IS_ERR(root)) return PTR_ERR(root); @@ -130,7 +135,7 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u nfp->addr = addr; nfp->page = page; - nfp->func_id = func_id; + nfp->function = function; nfp->free_count = MLX5_NUM_4K_IN_PAGE; for (i = 0; i < MLX5_NUM_4K_IN_PAGE; i++) set_bit(i, &nfp->bitmask); @@ -143,14 +148,14 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u } static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr, - u32 func_id) + u32 function) { struct fw_page *result = NULL; struct rb_root *root; struct rb_node *tmp; struct fw_page *tfp; - root = xa_load(&dev->priv.page_root_xa, func_id); + root = xa_load(&dev->priv.page_root_xa, function); if (WARN_ON_ONCE(!root)) return NULL; @@ -194,14 +199,14 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, return err; } -static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u16 func_id) +static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u32 function) { struct fw_page *fp = NULL; struct fw_page *iter; unsigned n; list_for_each_entry(iter, &dev->priv.free_list, list) { - if (iter->func_id != func_id) + if (iter->function != function) continue; fp = iter; } @@ -231,7 +236,7 @@ static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp, { struct rb_root *root; - root = xa_load(&dev->priv.page_root_xa, fwp->func_id); + root = xa_load(&dev->priv.page_root_xa, fwp->function); if (WARN_ON_ONCE(!root)) return; @@ -244,12 +249,12 @@ static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp, kfree(fwp); } -static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 func_id) +static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function) { struct fw_page *fwp; int n; - fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK, func_id); + fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK, function); if (!fwp) { mlx5_core_warn_rl(dev, "page not found\n"); return; @@ -263,7 +268,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 func_id) list_add(&fwp->list, &dev->priv.free_list); } -static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id) +static int alloc_system_page(struct mlx5_core_dev *dev, u32 function) { struct device *device = mlx5_core_dma_dev(dev); int nid = dev_to_node(device); @@ -291,7 +296,7 @@ map: goto map; } - err = insert_page(dev, addr, page, func_id); + err = insert_page(dev, addr, page, function); if (err) { mlx5_core_err(dev, "failed to track allocated page\n"); dma_unmap_page(device, addr, PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -328,6 +333,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id, static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int notify_fail, bool ec_function) { + u32 function = get_function(func_id, ec_function); u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); u64 addr; @@ -345,10 +351,10 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, for (i = 0; i < npages; i++) { retry: - err = alloc_4k(dev, &addr, func_id); + err = alloc_4k(dev, &addr, function); if (err) { if (err == -ENOMEM) - err = alloc_system_page(dev, func_id); + err = alloc_system_page(dev, function); if (err) goto out_4k; @@ -384,7 +390,7 @@ retry: out_4k: for (i--; i >= 0; i--) - free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), func_id); + free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), function); out_free: kvfree(in); if (notify_fail) @@ -392,14 +398,15 @@ out_free: return err; } -static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id, +static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, bool ec_function) { + u32 function = get_function(func_id, ec_function); struct rb_root *root; struct rb_node *p; int npages = 0; - root = xa_load(&dev->priv.page_root_xa, func_id); + root = xa_load(&dev->priv.page_root_xa, function); if (WARN_ON_ONCE(!root)) return; @@ -446,6 +453,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, struct rb_root *root; struct fw_page *fwp; struct rb_node *p; + bool ec_function; u32 func_id; u32 npages; u32 i = 0; @@ -456,8 +464,9 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, /* No hard feelings, we want our pages back! */ npages = MLX5_GET(manage_pages_in, in, input_num_entries); func_id = MLX5_GET(manage_pages_in, in, function_id); + ec_function = MLX5_GET(manage_pages_in, in, embedded_cpu_function); - root = xa_load(&dev->priv.page_root_xa, func_id); + root = xa_load(&dev->priv.page_root_xa, get_function(func_id, ec_function)); if (WARN_ON_ONCE(!root)) return -EEXIST; @@ -473,9 +482,10 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, return 0; } -static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, +static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int *nclaimed, bool ec_function) { + u32 function = get_function(func_id, ec_function); int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {}; int num_claimed; @@ -514,7 +524,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, } for (i = 0; i < num_claimed; i++) - free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]), func_id); + free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]), function); if (nclaimed) *nclaimed = num_claimed; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 6fd974920394..a61e09aff152 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -30,6 +30,9 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev) { struct mlx5_irq_table *irq_table; + if (mlx5_core_is_sf(dev)) + return 0; + irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL); if (!irq_table) return -ENOMEM; @@ -40,6 +43,9 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev) void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev) { + if (mlx5_core_is_sf(dev)) + return; + kvfree(dev->priv.irq_table); } @@ -268,6 +274,9 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev) int nvec; int err; + if (mlx5_core_is_sf(dev)) + return 0; + nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + MLX5_IRQ_VEC_COMP_BASE; nvec = min_t(int, nvec, num_eqs); @@ -319,6 +328,9 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) struct mlx5_irq_table *table = dev->priv.irq_table; int i; + if (mlx5_core_is_sf(dev)) + return; + /* free_irq requires that affinity and rmap will be cleared * before calling it. This is why there is asymmetry with set_rmap * which should be called after alloc_irq but before request_irq. @@ -332,3 +344,11 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) kfree(table->irq); } +struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev) +{ +#ifdef CONFIG_MLX5_SF + if (mlx5_core_is_sf(dev)) + return dev->priv.parent_mdev->priv.irq_table; +#endif + return dev->priv.irq_table; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c new file mode 100644 index 000000000000..a8d75c2f0275 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#include <linux/mlx5/driver.h> +#include "priv.h" + +int mlx5_cmd_alloc_sf(struct mlx5_core_dev *dev, u16 function_id) +{ + u32 out[MLX5_ST_SZ_DW(alloc_sf_out)] = {}; + u32 in[MLX5_ST_SZ_DW(alloc_sf_in)] = {}; + + MLX5_SET(alloc_sf_in, in, opcode, MLX5_CMD_OP_ALLOC_SF); + MLX5_SET(alloc_sf_in, in, function_id, function_id); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id) +{ + u32 out[MLX5_ST_SZ_DW(dealloc_sf_out)] = {}; + u32 in[MLX5_ST_SZ_DW(dealloc_sf_in)] = {}; + + MLX5_SET(dealloc_sf_in, in, opcode, MLX5_CMD_OP_DEALLOC_SF); + MLX5_SET(dealloc_sf_in, in, function_id, function_id); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_cmd_sf_enable_hca(struct mlx5_core_dev *dev, u16 func_id) +{ + u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {}; + + MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); + MLX5_SET(enable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); +} + +int mlx5_cmd_sf_disable_hca(struct mlx5_core_dev *dev, u16 func_id) +{ + u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {}; + + MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); + MLX5_SET(disable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c new file mode 100644 index 000000000000..b265f27b2166 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#include <linux/mlx5/driver.h> +#include <linux/mlx5/device.h> +#include "mlx5_core.h" +#include "dev.h" +#include "sf/vhca_event.h" +#include "sf/sf.h" +#include "sf/mlx5_ifc_vhca_event.h" +#include "ecpf.h" + +struct mlx5_sf_dev_table { + struct xarray devices; + unsigned int max_sfs; + phys_addr_t base_address; + u64 sf_bar_length; + struct notifier_block nb; + struct mlx5_core_dev *dev; +}; + +static bool mlx5_sf_dev_supported(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN(dev, sf) && mlx5_vhca_event_supported(dev); +} + +bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev) +{ + struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; + + if (!mlx5_sf_dev_supported(dev)) + return false; + + return !xa_empty(&table->devices); +} + +static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev); + struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", sf_dev->sfnum); +} +static DEVICE_ATTR_RO(sfnum); + +static struct attribute *sf_device_attrs[] = { + &dev_attr_sfnum.attr, + NULL, +}; + +static const struct attribute_group sf_attr_group = { + .attrs = sf_device_attrs, +}; + +static const struct attribute_group *sf_attr_groups[2] = { + &sf_attr_group, + NULL +}; + +static void mlx5_sf_dev_release(struct device *device) +{ + struct auxiliary_device *adev = container_of(device, struct auxiliary_device, dev); + struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + + mlx5_adev_idx_free(adev->id); + kfree(sf_dev); +} + +static void mlx5_sf_dev_remove(struct mlx5_sf_dev *sf_dev) +{ + auxiliary_device_delete(&sf_dev->adev); + auxiliary_device_uninit(&sf_dev->adev); +} + +static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum) +{ + struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; + struct mlx5_sf_dev *sf_dev; + struct pci_dev *pdev; + int err; + int id; + + id = mlx5_adev_idx_alloc(); + if (id < 0) { + err = id; + goto add_err; + } + + sf_dev = kzalloc(sizeof(*sf_dev), GFP_KERNEL); + if (!sf_dev) { + mlx5_adev_idx_free(id); + err = -ENOMEM; + goto add_err; + } + pdev = dev->pdev; + sf_dev->adev.id = id; + sf_dev->adev.name = MLX5_SF_DEV_ID_NAME; + sf_dev->adev.dev.release = mlx5_sf_dev_release; + sf_dev->adev.dev.parent = &pdev->dev; + sf_dev->adev.dev.groups = sf_attr_groups; + sf_dev->sfnum = sfnum; + sf_dev->parent_mdev = dev; + + if (!table->max_sfs) { + mlx5_adev_idx_free(id); + kfree(sf_dev); + err = -EOPNOTSUPP; + goto add_err; + } + sf_dev->bar_base_addr = table->base_address + (sf_index * table->sf_bar_length); + + err = auxiliary_device_init(&sf_dev->adev); + if (err) { + mlx5_adev_idx_free(id); + kfree(sf_dev); + goto add_err; + } + + err = auxiliary_device_add(&sf_dev->adev); + if (err) { + put_device(&sf_dev->adev.dev); + goto add_err; + } + + err = xa_insert(&table->devices, sf_index, sf_dev, GFP_KERNEL); + if (err) + goto xa_err; + return; + +xa_err: + mlx5_sf_dev_remove(sf_dev); +add_err: + mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n", + sf_index, sfnum, err); +} + +static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev, u16 sf_index) +{ + struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; + + xa_erase(&table->devices, sf_index); + mlx5_sf_dev_remove(sf_dev); +} + +static int +mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_code, void *data) +{ + struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb); + const struct mlx5_vhca_state_event *event = data; + struct mlx5_sf_dev *sf_dev; + u16 sf_index; + + sf_index = event->function_id - MLX5_CAP_GEN(table->dev, sf_base_id); + sf_dev = xa_load(&table->devices, sf_index); + switch (event->new_vhca_state) { + case MLX5_VHCA_STATE_ALLOCATED: + if (sf_dev) + mlx5_sf_dev_del(table->dev, sf_dev, sf_index); + break; + case MLX5_VHCA_STATE_TEARDOWN_REQUEST: + if (sf_dev) + mlx5_sf_dev_del(table->dev, sf_dev, sf_index); + else + mlx5_core_err(table->dev, + "SF DEV: teardown state for invalid dev index=%d fn_id=0x%x\n", + sf_index, event->sw_function_id); + break; + case MLX5_VHCA_STATE_ACTIVE: + if (!sf_dev) + mlx5_sf_dev_add(table->dev, sf_index, event->sw_function_id); + break; + default: + break; + } + return 0; +} + +static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) +{ + struct mlx5_core_dev *dev = table->dev; + u16 max_functions; + u16 function_id; + int err = 0; + bool ecpu; + int i; + + max_functions = mlx5_sf_max_functions(dev); + function_id = MLX5_CAP_GEN(dev, sf_base_id); + ecpu = mlx5_read_embedded_cpu(dev); + /* Arm the vhca context as the vhca event notifier */ + for (i = 0; i < max_functions; i++) { + err = mlx5_vhca_event_arm(dev, function_id, ecpu); + if (err) + return err; + + function_id++; + } + return 0; +} + +void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_dev_table *table; + unsigned int max_sfs; + int err; + + if (!mlx5_sf_dev_supported(dev) || !mlx5_vhca_event_supported(dev)) + return; + + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) { + err = -ENOMEM; + goto table_err; + } + + table->nb.notifier_call = mlx5_sf_dev_state_change_handler; + table->dev = dev; + if (MLX5_CAP_GEN(dev, max_num_sf)) + max_sfs = MLX5_CAP_GEN(dev, max_num_sf); + else + max_sfs = 1 << MLX5_CAP_GEN(dev, log_max_sf); + table->sf_bar_length = 1 << (MLX5_CAP_GEN(dev, log_min_sf_size) + 12); + table->base_address = pci_resource_start(dev->pdev, 2); + table->max_sfs = max_sfs; + xa_init(&table->devices); + dev->priv.sf_dev_table = table; + + err = mlx5_vhca_event_notifier_register(dev, &table->nb); + if (err) + goto vhca_err; + err = mlx5_sf_dev_vhca_arm_all(table); + if (err) + goto arm_err; + mlx5_core_dbg(dev, "SF DEV: max sf devices=%d\n", max_sfs); + return; + +arm_err: + mlx5_vhca_event_notifier_unregister(dev, &table->nb); +vhca_err: + table->max_sfs = 0; + kfree(table); + dev->priv.sf_dev_table = NULL; +table_err: + mlx5_core_err(dev, "SF DEV table create err = %d\n", err); +} + +static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table) +{ + struct mlx5_sf_dev *sf_dev; + unsigned long index; + + xa_for_each(&table->devices, index, sf_dev) { + xa_erase(&table->devices, index); + mlx5_sf_dev_remove(sf_dev); + } +} + +void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; + + if (!table) + return; + + mlx5_vhca_event_notifier_unregister(dev, &table->nb); + + /* Now that event handler is not running, it is safe to destroy + * the sf device without race. + */ + mlx5_sf_dev_destroy_all(table); + + WARN_ON(!xa_empty(&table->devices)); + kfree(table); + dev->priv.sf_dev_table = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h new file mode 100644 index 000000000000..4de02902aef1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#ifndef __MLX5_SF_DEV_H__ +#define __MLX5_SF_DEV_H__ + +#ifdef CONFIG_MLX5_SF + +#include <linux/auxiliary_bus.h> + +#define MLX5_SF_DEV_ID_NAME "sf" + +struct mlx5_sf_dev { + struct auxiliary_device adev; + struct mlx5_core_dev *parent_mdev; + struct mlx5_core_dev *mdev; + phys_addr_t bar_base_addr; + u32 sfnum; +}; + +void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev); +void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev); + +int mlx5_sf_driver_register(void); +void mlx5_sf_driver_unregister(void); + +bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev); + +#else + +static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) +{ +} + +static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) +{ +} + +static inline int mlx5_sf_driver_register(void) +{ + return 0; +} + +static inline void mlx5_sf_driver_unregister(void) +{ +} + +static inline bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev) +{ + return 0; +} + +#endif + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c new file mode 100644 index 000000000000..daf63a8115e0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#include <linux/mlx5/driver.h> +#include <linux/mlx5/device.h> +#include "mlx5_core.h" +#include "dev.h" +#include "devlink.h" + +static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) +{ + struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + struct mlx5_core_dev *mdev; + struct devlink *devlink; + int err; + + devlink = mlx5_devlink_alloc(); + if (!devlink) + return -ENOMEM; + + mdev = devlink_priv(devlink); + mdev->device = &adev->dev; + mdev->pdev = sf_dev->parent_mdev->pdev; + mdev->bar_addr = sf_dev->bar_base_addr; + mdev->iseg_base = sf_dev->bar_base_addr; + mdev->coredev_type = MLX5_COREDEV_SF; + mdev->priv.parent_mdev = sf_dev->parent_mdev; + mdev->priv.adev_idx = adev->id; + sf_dev->mdev = mdev; + + err = mlx5_mdev_init(mdev, MLX5_DEFAULT_PROF); + if (err) { + mlx5_core_warn(mdev, "mlx5_mdev_init on err=%d\n", err); + goto mdev_err; + } + + mdev->iseg = ioremap(mdev->iseg_base, sizeof(*mdev->iseg)); + if (!mdev->iseg) { + mlx5_core_warn(mdev, "remap error\n"); + goto remap_err; + } + + err = mlx5_load_one(mdev, true); + if (err) { + mlx5_core_warn(mdev, "mlx5_load_one err=%d\n", err); + goto load_one_err; + } + return 0; + +load_one_err: + iounmap(mdev->iseg); +remap_err: + mlx5_mdev_uninit(mdev); +mdev_err: + mlx5_devlink_free(devlink); + return err; +} + +static void mlx5_sf_dev_remove(struct auxiliary_device *adev) +{ + struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + struct devlink *devlink; + + devlink = priv_to_devlink(sf_dev->mdev); + mlx5_unload_one(sf_dev->mdev, true); + iounmap(sf_dev->mdev->iseg); + mlx5_mdev_uninit(sf_dev->mdev); + mlx5_devlink_free(devlink); +} + +static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev) +{ + struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + + mlx5_unload_one(sf_dev->mdev, false); +} + +static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = { + { .name = MLX5_ADEV_NAME "." MLX5_SF_DEV_ID_NAME, }, + { }, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5_sf_dev_id_table); + +static struct auxiliary_driver mlx5_sf_driver = { + .name = MLX5_SF_DEV_ID_NAME, + .probe = mlx5_sf_dev_probe, + .remove = mlx5_sf_dev_remove, + .shutdown = mlx5_sf_dev_shutdown, + .id_table = mlx5_sf_dev_id_table, +}; + +int mlx5_sf_driver_register(void) +{ + return auxiliary_driver_register(&mlx5_sf_driver); +} + +void mlx5_sf_driver_unregister(void) +{ + auxiliary_driver_unregister(&mlx5_sf_driver); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c new file mode 100644 index 000000000000..c2ba41bb7a70 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -0,0 +1,556 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#include <linux/mlx5/driver.h> +#include "eswitch.h" +#include "priv.h" +#include "sf/dev/dev.h" +#include "mlx5_ifc_vhca_event.h" +#include "vhca_event.h" +#include "ecpf.h" + +struct mlx5_sf { + struct devlink_port dl_port; + unsigned int port_index; + u16 id; + u16 hw_fn_id; + u16 hw_state; +}; + +struct mlx5_sf_table { + struct mlx5_core_dev *dev; /* To refer from notifier context. */ + struct xarray port_indices; /* port index based lookup. */ + refcount_t refcount; + struct completion disable_complete; + struct mutex sf_state_lock; /* Serializes sf state among user cmds & vhca event handler. */ + struct notifier_block esw_nb; + struct notifier_block vhca_nb; + u8 ecpu: 1; +}; + +static struct mlx5_sf * +mlx5_sf_lookup_by_index(struct mlx5_sf_table *table, unsigned int port_index) +{ + return xa_load(&table->port_indices, port_index); +} + +static struct mlx5_sf * +mlx5_sf_lookup_by_function_id(struct mlx5_sf_table *table, unsigned int fn_id) +{ + unsigned long index; + struct mlx5_sf *sf; + + xa_for_each(&table->port_indices, index, sf) { + if (sf->hw_fn_id == fn_id) + return sf; + } + return NULL; +} + +static int mlx5_sf_id_insert(struct mlx5_sf_table *table, struct mlx5_sf *sf) +{ + return xa_insert(&table->port_indices, sf->port_index, sf, GFP_KERNEL); +} + +static void mlx5_sf_id_erase(struct mlx5_sf_table *table, struct mlx5_sf *sf) +{ + xa_erase(&table->port_indices, sf->port_index); +} + +static struct mlx5_sf * +mlx5_sf_alloc(struct mlx5_sf_table *table, u32 sfnum, struct netlink_ext_ack *extack) +{ + unsigned int dl_port_index; + struct mlx5_sf *sf; + u16 hw_fn_id; + int id_err; + int err; + + id_err = mlx5_sf_hw_table_sf_alloc(table->dev, sfnum); + if (id_err < 0) { + err = id_err; + goto id_err; + } + + sf = kzalloc(sizeof(*sf), GFP_KERNEL); + if (!sf) { + err = -ENOMEM; + goto alloc_err; + } + sf->id = id_err; + hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sf->id); + dl_port_index = mlx5_esw_vport_to_devlink_port_index(table->dev, hw_fn_id); + sf->port_index = dl_port_index; + sf->hw_fn_id = hw_fn_id; + sf->hw_state = MLX5_VHCA_STATE_ALLOCATED; + + err = mlx5_sf_id_insert(table, sf); + if (err) + goto insert_err; + + return sf; + +insert_err: + kfree(sf); +alloc_err: + mlx5_sf_hw_table_sf_free(table->dev, id_err); +id_err: + if (err == -EEXIST) + NL_SET_ERR_MSG_MOD(extack, "SF already exist. Choose different sfnum"); + return ERR_PTR(err); +} + +static void mlx5_sf_free(struct mlx5_sf_table *table, struct mlx5_sf *sf) +{ + mlx5_sf_id_erase(table, sf); + mlx5_sf_hw_table_sf_free(table->dev, sf->id); + kfree(sf); +} + +static struct mlx5_sf_table *mlx5_sf_table_try_get(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_table *table = dev->priv.sf_table; + + if (!table) + return NULL; + + return refcount_inc_not_zero(&table->refcount) ? table : NULL; +} + +static void mlx5_sf_table_put(struct mlx5_sf_table *table) +{ + if (refcount_dec_and_test(&table->refcount)) + complete(&table->disable_complete); +} + +static enum devlink_port_fn_state mlx5_sf_to_devlink_state(u8 hw_state) +{ + switch (hw_state) { + case MLX5_VHCA_STATE_ACTIVE: + case MLX5_VHCA_STATE_IN_USE: + case MLX5_VHCA_STATE_TEARDOWN_REQUEST: + return DEVLINK_PORT_FN_STATE_ACTIVE; + case MLX5_VHCA_STATE_INVALID: + case MLX5_VHCA_STATE_ALLOCATED: + default: + return DEVLINK_PORT_FN_STATE_INACTIVE; + } +} + +static enum devlink_port_fn_opstate mlx5_sf_to_devlink_opstate(u8 hw_state) +{ + switch (hw_state) { + case MLX5_VHCA_STATE_IN_USE: + case MLX5_VHCA_STATE_TEARDOWN_REQUEST: + return DEVLINK_PORT_FN_OPSTATE_ATTACHED; + case MLX5_VHCA_STATE_INVALID: + case MLX5_VHCA_STATE_ALLOCATED: + case MLX5_VHCA_STATE_ACTIVE: + default: + return DEVLINK_PORT_FN_OPSTATE_DETACHED; + } +} + +static bool mlx5_sf_is_active(const struct mlx5_sf *sf) +{ + return sf->hw_state == MLX5_VHCA_STATE_ACTIVE || sf->hw_state == MLX5_VHCA_STATE_IN_USE; +} + +int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_port *dl_port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_sf_table *table; + struct mlx5_sf *sf; + int err = 0; + + table = mlx5_sf_table_try_get(dev); + if (!table) + return -EOPNOTSUPP; + + sf = mlx5_sf_lookup_by_index(table, dl_port->index); + if (!sf) { + err = -EOPNOTSUPP; + goto sf_err; + } + mutex_lock(&table->sf_state_lock); + *state = mlx5_sf_to_devlink_state(sf->hw_state); + *opstate = mlx5_sf_to_devlink_opstate(sf->hw_state); + mutex_unlock(&table->sf_state_lock); +sf_err: + mlx5_sf_table_put(table); + return err; +} + +static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) +{ + int err; + + if (mlx5_sf_is_active(sf)) + return 0; + if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) + return -EINVAL; + + err = mlx5_cmd_sf_enable_hca(dev, sf->hw_fn_id); + if (err) + return err; + + sf->hw_state = MLX5_VHCA_STATE_ACTIVE; + return 0; +} + +static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf) +{ + int err; + + if (!mlx5_sf_is_active(sf)) + return 0; + + err = mlx5_cmd_sf_disable_hca(dev, sf->hw_fn_id); + if (err) + return err; + + sf->hw_state = MLX5_VHCA_STATE_TEARDOWN_REQUEST; + return 0; +} + +static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, + struct mlx5_sf *sf, + enum devlink_port_fn_state state) +{ + int err = 0; + + mutex_lock(&table->sf_state_lock); + if (state == mlx5_sf_to_devlink_state(sf->hw_state)) + goto out; + if (state == DEVLINK_PORT_FN_STATE_ACTIVE) + err = mlx5_sf_activate(dev, sf); + else if (state == DEVLINK_PORT_FN_STATE_INACTIVE) + err = mlx5_sf_deactivate(dev, sf); + else + err = -EINVAL; +out: + mutex_unlock(&table->sf_state_lock); + return err; +} + +int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_port *dl_port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_sf_table *table; + struct mlx5_sf *sf; + int err; + + table = mlx5_sf_table_try_get(dev); + if (!table) { + NL_SET_ERR_MSG_MOD(extack, + "Port state set is only supported in eswitch switchdev mode or SF ports are disabled."); + return -EOPNOTSUPP; + } + sf = mlx5_sf_lookup_by_index(table, dl_port->index); + if (!sf) { + err = -ENODEV; + goto out; + } + + err = mlx5_sf_state_set(dev, table, sf, state); +out: + mlx5_sf_table_put(table); + return err; +} + +static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack, + unsigned int *new_port_index) +{ + struct mlx5_eswitch *esw = dev->priv.eswitch; + struct mlx5_sf *sf; + u16 hw_fn_id; + int err; + + sf = mlx5_sf_alloc(table, new_attr->sfnum, extack); + if (IS_ERR(sf)) + return PTR_ERR(sf); + + hw_fn_id = mlx5_sf_sw_to_hw_id(dev, sf->id); + err = mlx5_esw_offloads_sf_vport_enable(esw, &sf->dl_port, hw_fn_id, new_attr->sfnum); + if (err) + goto esw_err; + *new_port_index = sf->port_index; + return 0; + +esw_err: + mlx5_sf_free(table, sf); + return err; +} + +static int +mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack) +{ + if (new_attr->flavour != DEVLINK_PORT_FLAVOUR_PCI_SF) { + NL_SET_ERR_MSG_MOD(extack, "Driver supports only SF port addition"); + return -EOPNOTSUPP; + } + if (new_attr->port_index_valid) { + NL_SET_ERR_MSG_MOD(extack, + "Driver does not support user defined port index assignment"); + return -EOPNOTSUPP; + } + if (!new_attr->sfnum_valid) { + NL_SET_ERR_MSG_MOD(extack, + "User must provide unique sfnum. Driver does not support auto assignment"); + return -EOPNOTSUPP; + } + if (new_attr->controller_valid && new_attr->controller) { + NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported"); + return -EOPNOTSUPP; + } + if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied"); + return -EOPNOTSUPP; + } + return 0; +} + +int mlx5_devlink_sf_port_new(struct devlink *devlink, + const struct devlink_port_new_attrs *new_attr, + struct netlink_ext_ack *extack, + unsigned int *new_port_index) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_sf_table *table; + int err; + + err = mlx5_sf_new_check_attr(dev, new_attr, extack); + if (err) + return err; + + table = mlx5_sf_table_try_get(dev); + if (!table) { + NL_SET_ERR_MSG_MOD(extack, + "Port add is only supported in eswitch switchdev mode or SF ports are disabled."); + return -EOPNOTSUPP; + } + err = mlx5_sf_add(dev, table, new_attr, extack, new_port_index); + mlx5_sf_table_put(table); + return err; +} + +static void mlx5_sf_dealloc(struct mlx5_sf_table *table, struct mlx5_sf *sf) +{ + if (sf->hw_state == MLX5_VHCA_STATE_ALLOCATED) { + mlx5_sf_free(table, sf); + } else if (mlx5_sf_is_active(sf)) { + /* Even if its active, it is treated as in_use because by the time, + * it is disabled here, it may getting used. So it is safe to + * always look for the event to ensure that it is recycled only after + * firmware gives confirmation that it is detached by the driver. + */ + mlx5_cmd_sf_disable_hca(table->dev, sf->hw_fn_id); + mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->id); + kfree(sf); + } else { + mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->id); + kfree(sf); + } +} + +int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_eswitch *esw = dev->priv.eswitch; + struct mlx5_sf_table *table; + struct mlx5_sf *sf; + int err = 0; + + table = mlx5_sf_table_try_get(dev); + if (!table) { + NL_SET_ERR_MSG_MOD(extack, + "Port del is only supported in eswitch switchdev mode or SF ports are disabled."); + return -EOPNOTSUPP; + } + sf = mlx5_sf_lookup_by_index(table, port_index); + if (!sf) { + err = -ENODEV; + goto sf_err; + } + + mlx5_esw_offloads_sf_vport_disable(esw, sf->hw_fn_id); + mlx5_sf_id_erase(table, sf); + + mutex_lock(&table->sf_state_lock); + mlx5_sf_dealloc(table, sf); + mutex_unlock(&table->sf_state_lock); +sf_err: + mlx5_sf_table_put(table); + return err; +} + +static bool mlx5_sf_state_update_check(const struct mlx5_sf *sf, u8 new_state) +{ + if (sf->hw_state == MLX5_VHCA_STATE_ACTIVE && new_state == MLX5_VHCA_STATE_IN_USE) + return true; + + if (sf->hw_state == MLX5_VHCA_STATE_IN_USE && new_state == MLX5_VHCA_STATE_ACTIVE) + return true; + + if (sf->hw_state == MLX5_VHCA_STATE_TEARDOWN_REQUEST && + new_state == MLX5_VHCA_STATE_ALLOCATED) + return true; + + return false; +} + +static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data) +{ + struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, vhca_nb); + const struct mlx5_vhca_state_event *event = data; + bool update = false; + struct mlx5_sf *sf; + + table = mlx5_sf_table_try_get(table->dev); + if (!table) + return 0; + + mutex_lock(&table->sf_state_lock); + sf = mlx5_sf_lookup_by_function_id(table, event->function_id); + if (!sf) + goto sf_err; + + /* When driver is attached or detached to a function, an event + * notifies such state change. + */ + update = mlx5_sf_state_update_check(sf, event->new_vhca_state); + if (update) + sf->hw_state = event->new_vhca_state; +sf_err: + mutex_unlock(&table->sf_state_lock); + mlx5_sf_table_put(table); + return 0; +} + +static void mlx5_sf_table_enable(struct mlx5_sf_table *table) +{ + if (!mlx5_sf_max_functions(table->dev)) + return; + + init_completion(&table->disable_complete); + refcount_set(&table->refcount, 1); +} + +static void mlx5_sf_deactivate_all(struct mlx5_sf_table *table) +{ + struct mlx5_eswitch *esw = table->dev->priv.eswitch; + unsigned long index; + struct mlx5_sf *sf; + + /* At this point, no new user commands can start and no vhca event can + * arrive. It is safe to destroy all user created SFs. + */ + xa_for_each(&table->port_indices, index, sf) { + mlx5_esw_offloads_sf_vport_disable(esw, sf->hw_fn_id); + mlx5_sf_id_erase(table, sf); + mlx5_sf_dealloc(table, sf); + } +} + +static void mlx5_sf_table_disable(struct mlx5_sf_table *table) +{ + if (!mlx5_sf_max_functions(table->dev)) + return; + + if (!refcount_read(&table->refcount)) + return; + + /* Balances with refcount_set; drop the reference so that new user cmd cannot start + * and new vhca event handler cannnot run. + */ + mlx5_sf_table_put(table); + wait_for_completion(&table->disable_complete); + + mlx5_sf_deactivate_all(table); +} + +static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, void *data) +{ + struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, esw_nb); + const struct mlx5_esw_event_info *mode = data; + + switch (mode->new_mode) { + case MLX5_ESWITCH_OFFLOADS: + mlx5_sf_table_enable(table); + break; + case MLX5_ESWITCH_NONE: + mlx5_sf_table_disable(table); + break; + default: + break; + }; + + return 0; +} + +static bool mlx5_sf_table_supported(const struct mlx5_core_dev *dev) +{ + return dev->priv.eswitch && MLX5_ESWITCH_MANAGER(dev) && mlx5_sf_supported(dev); +} + +int mlx5_sf_table_init(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_table *table; + int err; + + if (!mlx5_sf_table_supported(dev) || !mlx5_vhca_event_supported(dev)) + return 0; + + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + mutex_init(&table->sf_state_lock); + table->dev = dev; + xa_init(&table->port_indices); + dev->priv.sf_table = table; + refcount_set(&table->refcount, 0); + table->esw_nb.notifier_call = mlx5_sf_esw_event; + err = mlx5_esw_event_notifier_register(dev->priv.eswitch, &table->esw_nb); + if (err) + goto reg_err; + + table->vhca_nb.notifier_call = mlx5_sf_vhca_event; + err = mlx5_vhca_event_notifier_register(table->dev, &table->vhca_nb); + if (err) + goto vhca_err; + + return 0; + +vhca_err: + mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb); +reg_err: + mutex_destroy(&table->sf_state_lock); + kfree(table); + dev->priv.sf_table = NULL; + return err; +} + +void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_table *table = dev->priv.sf_table; + + if (!table) + return; + + mlx5_vhca_event_notifier_unregister(table->dev, &table->vhca_nb); + mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb); + WARN_ON(refcount_read(&table->refcount)); + mutex_destroy(&table->sf_state_lock); + WARN_ON(!xa_empty(&table->port_indices)); + kfree(table); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c new file mode 100644 index 000000000000..58b6be0b03d7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd */ +#include <linux/mlx5/driver.h> +#include "vhca_event.h" +#include "priv.h" +#include "sf.h" +#include "mlx5_ifc_vhca_event.h" +#include "vhca_event.h" +#include "ecpf.h" + +struct mlx5_sf_hw { + u32 usr_sfnum; + u8 allocated: 1; + u8 pending_delete: 1; +}; + +struct mlx5_sf_hw_table { + struct mlx5_core_dev *dev; + struct mlx5_sf_hw *sfs; + int max_local_functions; + u8 ecpu: 1; + struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */ + struct notifier_block vhca_nb; +}; + +u16 mlx5_sf_sw_to_hw_id(const struct mlx5_core_dev *dev, u16 sw_id) +{ + return sw_id + mlx5_sf_start_function_id(dev); +} + +static u16 mlx5_sf_hw_to_sw_id(const struct mlx5_core_dev *dev, u16 hw_id) +{ + return hw_id - mlx5_sf_start_function_id(dev); +} + +int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + int sw_id = -ENOSPC; + u16 hw_fn_id; + int err; + int i; + + if (!table->max_local_functions) + return -EOPNOTSUPP; + + mutex_lock(&table->table_lock); + /* Check if sf with same sfnum already exists or not. */ + for (i = 0; i < table->max_local_functions; i++) { + if (table->sfs[i].allocated && table->sfs[i].usr_sfnum == usr_sfnum) { + err = -EEXIST; + goto exist_err; + } + } + + /* Find the free entry and allocate the entry from the array */ + for (i = 0; i < table->max_local_functions; i++) { + if (!table->sfs[i].allocated) { + table->sfs[i].usr_sfnum = usr_sfnum; + table->sfs[i].allocated = true; + sw_id = i; + break; + } + } + if (sw_id == -ENOSPC) { + err = -ENOSPC; + goto err; + } + + hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sw_id); + err = mlx5_cmd_alloc_sf(table->dev, hw_fn_id); + if (err) + goto err; + + err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, table->ecpu, usr_sfnum); + if (err) + goto vhca_err; + + mutex_unlock(&table->table_lock); + return sw_id; + +vhca_err: + mlx5_cmd_dealloc_sf(table->dev, hw_fn_id); +err: + table->sfs[i].allocated = false; +exist_err: + mutex_unlock(&table->table_lock); + return err; +} + +static void _mlx5_sf_hw_id_free(struct mlx5_core_dev *dev, u16 id) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + u16 hw_fn_id; + + hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, id); + mlx5_cmd_dealloc_sf(table->dev, hw_fn_id); + table->sfs[id].allocated = false; + table->sfs[id].pending_delete = false; +} + +void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u16 id) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + + mutex_lock(&table->table_lock); + _mlx5_sf_hw_id_free(dev, id); + mutex_unlock(&table->table_lock); +} + +void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; + u16 hw_fn_id; + u8 state; + int err; + + hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id); + mutex_lock(&table->table_lock); + err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, table->ecpu, out, sizeof(out)); + if (err) + goto err; + state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); + if (state == MLX5_VHCA_STATE_ALLOCATED) { + mlx5_cmd_dealloc_sf(table->dev, hw_fn_id); + table->sfs[id].allocated = false; + } else { + table->sfs[id].pending_delete = true; + } +err: + mutex_unlock(&table->table_lock); +} + +static void mlx5_sf_hw_dealloc_all(struct mlx5_sf_hw_table *table) +{ + int i; + + for (i = 0; i < table->max_local_functions; i++) { + if (table->sfs[i].allocated) + _mlx5_sf_hw_id_free(table->dev, i); + } +} + +int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_hw_table *table; + struct mlx5_sf_hw *sfs; + int max_functions; + + if (!mlx5_sf_supported(dev) || !mlx5_vhca_event_supported(dev)) + return 0; + + max_functions = mlx5_sf_max_functions(dev); + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + sfs = kcalloc(max_functions, sizeof(*sfs), GFP_KERNEL); + if (!sfs) + goto table_err; + + mutex_init(&table->table_lock); + table->dev = dev; + table->sfs = sfs; + table->max_local_functions = max_functions; + table->ecpu = mlx5_read_embedded_cpu(dev); + dev->priv.sf_hw_table = table; + mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions); + return 0; + +table_err: + kfree(table); + return -ENOMEM; +} + +void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + + if (!table) + return; + + mutex_destroy(&table->table_lock); + kfree(table->sfs); + kfree(table); +} + +static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data) +{ + struct mlx5_sf_hw_table *table = container_of(nb, struct mlx5_sf_hw_table, vhca_nb); + const struct mlx5_vhca_state_event *event = data; + struct mlx5_sf_hw *sf_hw; + u16 sw_id; + + if (event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED) + return 0; + + sw_id = mlx5_sf_hw_to_sw_id(table->dev, event->function_id); + sf_hw = &table->sfs[sw_id]; + + mutex_lock(&table->table_lock); + /* SF driver notified through firmware that SF is finally detached. + * Hence recycle the sf hardware id for reuse. + */ + if (sf_hw->allocated && sf_hw->pending_delete) + _mlx5_sf_hw_id_free(table->dev, sw_id); + mutex_unlock(&table->table_lock); + return 0; +} + +int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + + if (!table) + return 0; + + table->vhca_nb.notifier_call = mlx5_sf_hw_vhca_event; + return mlx5_vhca_event_notifier_register(table->dev, &table->vhca_nb); +} + +void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev) +{ + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; + + if (!table) + return; + + mlx5_vhca_event_notifier_unregister(table->dev, &table->vhca_nb); + /* Dealloc SFs whose firmware event has been missed. */ + mlx5_sf_hw_dealloc_all(table); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h new file mode 100644 index 000000000000..1daf5a122ba3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#ifndef __MLX5_IFC_VHCA_EVENT_H__ +#define __MLX5_IFC_VHCA_EVENT_H__ + +enum mlx5_ifc_vhca_state { + MLX5_VHCA_STATE_INVALID = 0x0, + MLX5_VHCA_STATE_ALLOCATED = 0x1, + MLX5_VHCA_STATE_ACTIVE = 0x2, + MLX5_VHCA_STATE_IN_USE = 0x3, + MLX5_VHCA_STATE_TEARDOWN_REQUEST = 0x4, +}; + +struct mlx5_ifc_vhca_state_context_bits { + u8 arm_change_event[0x1]; + u8 reserved_at_1[0xb]; + u8 vhca_state[0x4]; + u8 reserved_at_10[0x10]; + + u8 sw_function_id[0x20]; + + u8 reserved_at_40[0x80]; +}; + +struct mlx5_ifc_query_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_vhca_state_context_bits vhca_state_context; +}; + +struct mlx5_ifc_query_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_vhca_state_field_select_bits { + u8 reserved_at_0[0x1e]; + u8 sw_function_id[0x1]; + u8 arm_change_event[0x1]; +}; + +struct mlx5_ifc_modify_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_modify_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; + u8 function_id[0x10]; + + struct mlx5_ifc_vhca_state_field_select_bits vhca_state_field_select; + + struct mlx5_ifc_vhca_state_context_bits vhca_state_context; +}; + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h new file mode 100644 index 000000000000..cb02a51d0986 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#ifndef __MLX5_SF_PRIV_H__ +#define __MLX5_SF_PRIV_H__ + +#include <linux/mlx5/driver.h> + +int mlx5_cmd_alloc_sf(struct mlx5_core_dev *dev, u16 function_id); +int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id); + +int mlx5_cmd_sf_enable_hca(struct mlx5_core_dev *dev, u16 func_id); +int mlx5_cmd_sf_disable_hca(struct mlx5_core_dev *dev, u16 func_id); + +u16 mlx5_sf_sw_to_hw_id(const struct mlx5_core_dev *dev, u16 sw_id); + +int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum); +void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u16 id); +void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h new file mode 100644 index 000000000000..0b6aea1e6a94 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#ifndef __MLX5_SF_H__ +#define __MLX5_SF_H__ + +#include <linux/mlx5/driver.h> + +static inline u16 mlx5_sf_start_function_id(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN(dev, sf_base_id); +} + +#ifdef CONFIG_MLX5_SF + +static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN(dev, sf); +} + +static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev) +{ + if (!mlx5_sf_supported(dev)) + return 0; + if (MLX5_CAP_GEN(dev, max_num_sf)) + return MLX5_CAP_GEN(dev, max_num_sf); + else + return 1 << MLX5_CAP_GEN(dev, log_max_sf); +} + +#else + +static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev) +{ + return false; +} + +static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev) +{ + return 0; +} + +#endif + +#ifdef CONFIG_MLX5_SF_MANAGER + +int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev); +void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev); + +int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev); +void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev); + +int mlx5_sf_table_init(struct mlx5_core_dev *dev); +void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev); + +int mlx5_devlink_sf_port_new(struct devlink *devlink, + const struct devlink_port_new_attrs *add_attr, + struct netlink_ext_ack *extack, + unsigned int *new_port_index); +int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, + struct netlink_ext_ack *extack); +int mlx5_devlink_sf_port_fn_state_get(struct devlink *devlink, struct devlink_port *dl_port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack); +int mlx5_devlink_sf_port_fn_state_set(struct devlink *devlink, struct devlink_port *dl_port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack); +#else + +static inline int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) +{ + return 0; +} + +static inline void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev) +{ +} + +static inline int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev) +{ + return 0; +} + +static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev) +{ +} + +static inline int mlx5_sf_table_init(struct mlx5_core_dev *dev) +{ + return 0; +} + +static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev) +{ +} + +#endif + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c new file mode 100644 index 000000000000..af2f2dd9db25 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#include <linux/mlx5/driver.h> +#include "mlx5_ifc_vhca_event.h" +#include "mlx5_core.h" +#include "vhca_event.h" +#include "ecpf.h" + +struct mlx5_vhca_state_notifier { + struct mlx5_core_dev *dev; + struct mlx5_nb nb; + struct blocking_notifier_head n_head; +}; + +struct mlx5_vhca_event_work { + struct work_struct work; + struct mlx5_vhca_state_notifier *notifier; + struct mlx5_vhca_state_event event; +}; + +int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, + bool ecpu, u32 *out, u32 outlen) +{ + u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {}; + + MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE); + MLX5_SET(query_vhca_state_in, in, function_id, function_id); + MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, ecpu); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); +} + +static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id, + bool ecpu, u32 *in, u32 inlen) +{ + u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {}; + + MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE); + MLX5_SET(modify_vhca_state_in, in, function_id, function_id); + MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu); + + return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); +} + +int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id) +{ + u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {}; + u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {}; + + MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE); + MLX5_SET(modify_vhca_state_in, in, function_id, function_id); + MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1); + MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id); + + return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out); +} + +int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu) +{ + u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {}; + + MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1); + MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1); + + return mlx5_cmd_modify_vhca_state(dev, function_id, ecpu, in, sizeof(in)); +} + +static void +mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *event) +{ + u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; + int err; + + err = mlx5_cmd_query_vhca_state(dev, event->function_id, event->ecpu, out, sizeof(out)); + if (err) + return; + + event->sw_function_id = MLX5_GET(query_vhca_state_out, out, + vhca_state_context.sw_function_id); + event->new_vhca_state = MLX5_GET(query_vhca_state_out, out, + vhca_state_context.vhca_state); + + mlx5_vhca_event_arm(dev, event->function_id, event->ecpu); + + blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event); +} + +static void mlx5_vhca_state_work_handler(struct work_struct *_work) +{ + struct mlx5_vhca_event_work *work = container_of(_work, struct mlx5_vhca_event_work, work); + struct mlx5_vhca_state_notifier *notifier = work->notifier; + struct mlx5_core_dev *dev = notifier->dev; + + mlx5_vhca_event_notify(dev, &work->event); +} + +static int +mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, void *data) +{ + struct mlx5_vhca_state_notifier *notifier = + mlx5_nb_cof(nb, struct mlx5_vhca_state_notifier, nb); + struct mlx5_vhca_event_work *work; + struct mlx5_eqe *eqe = data; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return NOTIFY_DONE; + INIT_WORK(&work->work, &mlx5_vhca_state_work_handler); + work->notifier = notifier; + work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id); + work->event.ecpu = be16_to_cpu(eqe->data.vhca_state.ec_function); + mlx5_events_work_enqueue(notifier->dev, &work->work); + return NOTIFY_OK; +} + +void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap) +{ + if (!mlx5_vhca_event_supported(dev)) + return; + + MLX5_SET(cmd_hca_cap, set_hca_cap, vhca_state, 1); + MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_allocated, 1); + MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_active, 1); + MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_in_use, 1); + MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_teardown_request, 1); +} + +int mlx5_vhca_event_init(struct mlx5_core_dev *dev) +{ + struct mlx5_vhca_state_notifier *notifier; + + if (!mlx5_vhca_event_supported(dev)) + return 0; + + notifier = kzalloc(sizeof(*notifier), GFP_KERNEL); + if (!notifier) + return -ENOMEM; + + dev->priv.vhca_state_notifier = notifier; + notifier->dev = dev; + BLOCKING_INIT_NOTIFIER_HEAD(¬ifier->n_head); + MLX5_NB_INIT(¬ifier->nb, mlx5_vhca_state_change_notifier, VHCA_STATE_CHANGE); + return 0; +} + +void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev) +{ + if (!mlx5_vhca_event_supported(dev)) + return; + + kfree(dev->priv.vhca_state_notifier); + dev->priv.vhca_state_notifier = NULL; +} + +void mlx5_vhca_event_start(struct mlx5_core_dev *dev) +{ + struct mlx5_vhca_state_notifier *notifier; + + if (!dev->priv.vhca_state_notifier) + return; + + notifier = dev->priv.vhca_state_notifier; + mlx5_eq_notifier_register(dev, ¬ifier->nb); +} + +void mlx5_vhca_event_stop(struct mlx5_core_dev *dev) +{ + struct mlx5_vhca_state_notifier *notifier; + + if (!dev->priv.vhca_state_notifier) + return; + + notifier = dev->priv.vhca_state_notifier; + mlx5_eq_notifier_unregister(dev, ¬ifier->nb); +} + +int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb) +{ + if (!dev->priv.vhca_state_notifier) + return -EOPNOTSUPP; + return blocking_notifier_chain_register(&dev->priv.vhca_state_notifier->n_head, nb); +} + +void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&dev->priv.vhca_state_notifier->n_head, nb); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h new file mode 100644 index 000000000000..1fe1ec6f4d4b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 Mellanox Technologies Ltd */ + +#ifndef __MLX5_VHCA_EVENT_H__ +#define __MLX5_VHCA_EVENT_H__ + +#ifdef CONFIG_MLX5_SF + +struct mlx5_vhca_state_event { + u16 function_id; + u16 sw_function_id; + u8 new_vhca_state; + bool ecpu; +}; + +static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN_MAX(dev, vhca_state); +} + +void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap); +int mlx5_vhca_event_init(struct mlx5_core_dev *dev); +void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev); +void mlx5_vhca_event_start(struct mlx5_core_dev *dev); +void mlx5_vhca_event_stop(struct mlx5_core_dev *dev); +int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); +void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id); +int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu); +int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, + bool ecpu, u32 *out, u32 outlen); +#else + +static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap) +{ +} + +static inline int mlx5_vhca_event_init(struct mlx5_core_dev *dev) +{ + return 0; +} + +static inline void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev) +{ +} + +static inline void mlx5_vhca_event_start(struct mlx5_core_dev *dev) +{ +} + +static inline void mlx5_vhca_event_stop(struct mlx5_core_dev *dev) +{ +} + +#endif + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 27c2b8416d02..28a7971cac6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -447,7 +447,8 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, case DR_ACTION_TYP_MODIFY_HDR: attr.modify_index = action->rewrite.index; attr.modify_actions = action->rewrite.num_of_actions; - recalc_cs_required = action->rewrite.modify_ttl; + recalc_cs_required = action->rewrite.modify_ttl && + !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps); break; case DR_ACTION_TYP_L2_TO_TNL_L2: case DR_ACTION_TYP_L2_TO_TNL_L3: @@ -501,9 +502,9 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, *new_hw_ste_arr_sz = nic_matcher->num_of_builders; last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1); - /* Due to a HW bug, modifying TTL on RX flows will cause an incorrect - * checksum calculation. In this case we will use a FW table to - * recalculate. + /* Due to a HW bug in some devices, modifying TTL on RX flows will + * cause an incorrect checksum calculation. In this case we will + * use a FW table to recalculate. */ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && rx_rule && recalc_cs_required && dest_action) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index ba65ec406cfa..30b0136b5bc7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -78,9 +78,9 @@ int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, caps->uplink_icm_address_tx = MLX5_CAP64_ESW_FLOWTABLE(mdev, sw_steering_uplink_icm_address_tx); - caps->sw_owner = - MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, - sw_owner); + caps->sw_owner_v2 = MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, sw_owner_v2); + if (!caps->sw_owner_v2) + caps->sw_owner = MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, sw_owner); return 0; } @@ -113,10 +113,15 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->nic_tx_allow_address = MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_allow_icm_address); - caps->rx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner); - caps->max_ft_level = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_ft_level); + caps->rx_sw_owner_v2 = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner_v2); + caps->tx_sw_owner_v2 = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner_v2); + + if (!caps->rx_sw_owner_v2) + caps->rx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner); + if (!caps->tx_sw_owner_v2) + caps->tx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner); - caps->tx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner); + caps->max_ft_level = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_ft_level); caps->log_icm_size = MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size); caps->hdr_modify_icm_addr = diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 47ec88964bf3..7091b1be84ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -4,6 +4,11 @@ #include <linux/mlx5/eswitch.h> #include "dr_types.h" +#define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type) \ + ((dmn)->info.caps.dmn_type##_sw_owner || \ + ((dmn)->info.caps.dmn_type##_sw_owner_v2 && \ + (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_6DX)) + static int dr_domain_init_cache(struct mlx5dr_domain *dmn) { /* Per vport cached FW FT for checksum recalculation, this @@ -187,6 +192,7 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, return ret; dmn->info.caps.fdb_sw_owner = dmn->info.caps.esw_caps.sw_owner; + dmn->info.caps.fdb_sw_owner_v2 = dmn->info.caps.esw_caps.sw_owner_v2; dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx; dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx; @@ -229,18 +235,13 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, if (ret) return ret; - if (dmn->info.caps.sw_format_ver != MLX5_STEERING_FORMAT_CONNECTX_5) { - mlx5dr_err(dmn, "SW steering is not supported on this device\n"); - return -EOPNOTSUPP; - } - ret = dr_domain_query_fdb_caps(mdev, dmn); if (ret) return ret; switch (dmn->type) { case MLX5DR_DOMAIN_TYPE_NIC_RX: - if (!dmn->info.caps.rx_sw_owner) + if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, rx)) return -ENOTSUPP; dmn->info.supp_sw_steering = true; @@ -249,7 +250,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address; break; case MLX5DR_DOMAIN_TYPE_NIC_TX: - if (!dmn->info.caps.tx_sw_owner) + if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, tx)) return -ENOTSUPP; dmn->info.supp_sw_steering = true; @@ -261,7 +262,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, if (!dmn->info.caps.eswitch_manager) return -ENOTSUPP; - if (!dmn->info.caps.fdb_sw_owner) + if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, fdb)) return -ENOTSUPP; dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index e3a002983c26..15673cd10039 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -113,7 +113,8 @@ dr_mask_is_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) static bool dr_matcher_supp_vxlan_gpe(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; + return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + (caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED); } static bool @@ -135,7 +136,8 @@ static bool dr_mask_is_tnl_geneve_set(struct mlx5dr_match_misc *misc) static bool dr_matcher_supp_tnl_geneve(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_ENABLED; + return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + (caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_ENABLED); } static bool @@ -148,12 +150,14 @@ dr_mask_is_tnl_geneve(struct mlx5dr_match_param *mask, static int dr_matcher_supp_icmp_v4(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; + return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED); } static int dr_matcher_supp_icmp_v6(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; + return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED); } static bool dr_mask_is_icmpv6_set(struct mlx5dr_match_misc3 *misc3) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index ddcb7017e121..b337d6626bff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -30,7 +30,7 @@ static int dr_rule_append_to_miss_list(struct mlx5dr_ste_ctx *ste_ctx, mlx5dr_ste_get_icm_addr(new_last_ste)); list_add_tail(&new_last_ste->miss_list_node, miss_list); - mlx5dr_send_fill_and_append_ste_send_info(last_ste, DR_STE_SIZE_REDUCED, + mlx5dr_send_fill_and_append_ste_send_info(last_ste, DR_STE_SIZE_CTRL, 0, last_ste->hw_ste, ste_info_last, send_list, true); @@ -106,14 +106,19 @@ dr_rule_handle_one_ste_in_update_list(struct mlx5dr_ste_send_info *ste_info, int ret; list_del(&ste_info->send_list); + + /* Copy data to ste, only reduced size or control, the last 16B (mask) + * is already written to the hw. + */ + if (ste_info->size == DR_STE_SIZE_CTRL) + memcpy(ste_info->ste->hw_ste, ste_info->data, DR_STE_SIZE_CTRL); + else + memcpy(ste_info->ste->hw_ste, ste_info->data, DR_STE_SIZE_REDUCED); + ret = mlx5dr_send_postsend_ste(dmn, ste_info->ste, ste_info->data, ste_info->size, ste_info->offset); if (ret) goto out; - /* Copy data to ste, only reduced size, the last 16B (mask) - * is already written to the hw. - */ - memcpy(ste_info->ste->hw_ste, ste_info->data, DR_STE_SIZE_REDUCED); out: kfree(ste_info); @@ -456,7 +461,7 @@ dr_rule_rehash_htbl(struct mlx5dr_rule *rule, ste_to_update = cur_htbl->pointing_ste; } - mlx5dr_send_fill_and_append_ste_send_info(ste_to_update, DR_STE_SIZE_REDUCED, + mlx5dr_send_fill_and_append_ste_send_info(ste_to_update, DR_STE_SIZE_CTRL, 0, ste_to_update->hw_ste, ste_info, update_list, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 24dede1b0a20..83c4c877d558 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -431,6 +431,8 @@ int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, struct mlx5dr_ste *ste, { struct postsend_info send_info = {}; + mlx5dr_ste_prepare_for_postsend(dmn->ste_ctx, data, size); + send_info.write.addr = (uintptr_t)data; send_info.write.length = size; send_info.write.lkey = 0; @@ -457,6 +459,8 @@ int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn, if (ret) return ret; + mlx5dr_ste_prepare_for_postsend(dmn->ste_ctx, formatted_ste, DR_STE_SIZE); + /* Send the data iteration times */ for (i = 0; i < iterations; i++) { u32 ste_index = i * (byte_size / DR_STE_SIZE); @@ -480,6 +484,10 @@ int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn, /* Copy bit_mask */ memcpy(data + ste_off + DR_STE_SIZE_REDUCED, mask, DR_STE_SIZE_MASK); + /* Only when we have mask we need to re-arrange the STE */ + mlx5dr_ste_prepare_for_postsend(dmn->ste_ctx, + data + (j * DR_STE_SIZE), + DR_STE_SIZE); } } @@ -509,6 +517,7 @@ int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, u32 byte_size = htbl->chunk->byte_size; int iterations; int num_stes; + u8 *copy_dst; u8 *data; int ret; int i; @@ -518,20 +527,22 @@ int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, if (ret) return ret; - for (i = 0; i < num_stes; i++) { - u8 *copy_dst; - - /* Copy the same ste on the data buffer */ - copy_dst = data + i * DR_STE_SIZE; - memcpy(copy_dst, ste_init_data, DR_STE_SIZE); - - if (update_hw_ste) { - /* Copy the reduced ste to hash table ste_arr */ + if (update_hw_ste) { + /* Copy the reduced STE to hash table ste_arr */ + for (i = 0; i < num_stes; i++) { copy_dst = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; memcpy(copy_dst, ste_init_data, DR_STE_SIZE_REDUCED); } } + mlx5dr_ste_prepare_for_postsend(dmn->ste_ctx, ste_init_data, DR_STE_SIZE); + + /* Copy the same STE on the data buffer */ + for (i = 0; i < num_stes; i++) { + copy_dst = data + i * DR_STE_SIZE; + memcpy(copy_dst, ste_init_data, DR_STE_SIZE); + } + /* Send the data iteration times */ for (i = 0; i < iterations; i++) { u8 ste_index = i * (byte_size / DR_STE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 1614481fdf8d..f49abc7a4b9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -18,6 +18,11 @@ static u32 dr_ste_crc32_calc(const void *input_data, size_t length) return (__force u32)htonl(crc); } +bool mlx5dr_ste_supp_ttl_cs_recalc(struct mlx5dr_cmd_caps *caps) +{ + return caps->sw_format_ver > MLX5_STEERING_FORMAT_CONNECTX_5; +} + u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl) { struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; @@ -211,13 +216,17 @@ dr_ste_remove_head_ste(struct mlx5dr_ste_ctx *ste_ctx, * |_ste_| --> |_next_ste_| -->|__| -->|__| -->/0 */ static void -dr_ste_replace_head_ste(struct mlx5dr_ste *ste, struct mlx5dr_ste *next_ste, +dr_ste_replace_head_ste(struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + struct mlx5dr_ste *next_ste, struct mlx5dr_ste_send_info *ste_info_head, struct list_head *send_ste_list, struct mlx5dr_ste_htbl *stats_tbl) { struct mlx5dr_ste_htbl *next_miss_htbl; + u8 hw_ste[DR_STE_SIZE] = {}; + int sb_idx; next_miss_htbl = next_ste->htbl; @@ -230,13 +239,19 @@ dr_ste_replace_head_ste(struct mlx5dr_ste *ste, struct mlx5dr_ste *next_ste, /* Move data from next into ste */ dr_ste_replace(ste, next_ste); + /* Copy all 64 hw_ste bytes */ + memcpy(hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED); + sb_idx = ste->ste_chain_location - 1; + mlx5dr_ste_set_bit_mask(hw_ste, + nic_matcher->ste_builder[sb_idx].bit_mask); + /* Del the htbl that contains the next_ste. * The origin htbl stay with the same number of entries. */ mlx5dr_htbl_put(next_miss_htbl); - mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE_REDUCED, - 0, ste->hw_ste, + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE, + 0, hw_ste, ste_info_head, send_ste_list, true /* Copy data */); @@ -264,7 +279,7 @@ static void dr_ste_remove_middle_ste(struct mlx5dr_ste_ctx *ste_ctx, miss_addr = ste_ctx->get_miss_addr(ste->hw_ste); ste_ctx->set_miss_addr(prev_ste->hw_ste, miss_addr); - mlx5dr_send_fill_and_append_ste_send_info(prev_ste, DR_STE_SIZE_REDUCED, 0, + mlx5dr_send_fill_and_append_ste_send_info(prev_ste, DR_STE_SIZE_CTRL, 0, prev_ste->hw_ste, ste_info, send_ste_list, true /* Copy data*/); @@ -316,7 +331,8 @@ void mlx5dr_ste_free(struct mlx5dr_ste *ste, stats_tbl); } else { /* First but not only entry in the list */ - dr_ste_replace_head_ste(ste, next_ste, &ste_info_head, + dr_ste_replace_head_ste(nic_matcher, ste, + next_ste, &ste_info_head, &send_ste_list, stats_tbl); put_on_origin_table = false; } @@ -356,6 +372,13 @@ void mlx5dr_ste_set_hit_addr_by_next_htbl(struct mlx5dr_ste_ctx *ste_ctx, ste_ctx->set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries); } +void mlx5dr_ste_prepare_for_postsend(struct mlx5dr_ste_ctx *ste_ctx, + u8 *hw_ste_p, u32 ste_size) +{ + if (ste_ctx->prepare_for_postsend) + ste_ctx->prepare_for_postsend(hw_ste_p, ste_size); +} + /* Init one ste as a pattern for ste data array */ void mlx5dr_ste_set_formatted_ste(struct mlx5dr_ste_ctx *ste_ctx, u16 gvmi, @@ -1127,7 +1150,7 @@ void mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_ctx *ste_ctx, static struct mlx5dr_ste_ctx *mlx5dr_ste_ctx_arr[] = { [MLX5_STEERING_FORMAT_CONNECTX_5] = &ste_ctx_v0, - [MLX5_STEERING_FORMAT_CONNECTX_6DX] = NULL, + [MLX5_STEERING_FORMAT_CONNECTX_6DX] = &ste_ctx_v1, }; struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx(u8 version) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h index 4a3d6a849991..06bcb0ee8f96 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h @@ -160,8 +160,12 @@ struct mlx5dr_ste_ctx { u8 *hw_action, u32 hw_action_sz, u16 *used_hw_action_num); + + /* Send */ + void (*prepare_for_postsend)(u8 *hw_ste_p, u32 ste_size); }; extern struct mlx5dr_ste_ctx ste_ctx_v0; +extern struct mlx5dr_ste_ctx ste_ctx_v1; #endif /* _DR_STE_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index b76fdff08890..9ec079247c4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -248,8 +248,8 @@ static void dr_ste_v0_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) static u64 dr_ste_v0_get_miss_addr(u8 *hw_ste_p) { u64 index = - (MLX5_GET(ste_rx_steering_mult, hw_ste_p, miss_address_31_6) | - MLX5_GET(ste_rx_steering_mult, hw_ste_p, miss_address_39_32) << 26); + ((u64)MLX5_GET(ste_rx_steering_mult, hw_ste_p, miss_address_31_6) | + ((u64)MLX5_GET(ste_rx_steering_mult, hw_ste_p, miss_address_39_32)) << 26); return index << 6; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c new file mode 100644 index 000000000000..4088d6e51508 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -0,0 +1,1633 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. */ + +#include <linux/types.h> +#include "mlx5_ifc_dr_ste_v1.h" +#include "dr_ste.h" + +#define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \ + ((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \ + DR_STE_V1_LU_TYPE_##lookup_type##_O) + +enum dr_ste_v1_entry_format { + DR_STE_V1_TYPE_BWC_BYTE = 0x0, + DR_STE_V1_TYPE_BWC_DW = 0x1, + DR_STE_V1_TYPE_MATCH = 0x2, +}; + +/* Lookup type is built from 2B: [ Definer mode 1B ][ Definer index 1B ] */ +enum { + DR_STE_V1_LU_TYPE_NOP = 0x0000, + DR_STE_V1_LU_TYPE_ETHL2_TNL = 0x0002, + DR_STE_V1_LU_TYPE_IBL3_EXT = 0x0102, + DR_STE_V1_LU_TYPE_ETHL2_O = 0x0003, + DR_STE_V1_LU_TYPE_IBL4 = 0x0103, + DR_STE_V1_LU_TYPE_ETHL2_I = 0x0004, + DR_STE_V1_LU_TYPE_SRC_QP_GVMI = 0x0104, + DR_STE_V1_LU_TYPE_ETHL2_SRC_O = 0x0005, + DR_STE_V1_LU_TYPE_ETHL2_HEADERS_O = 0x0105, + DR_STE_V1_LU_TYPE_ETHL2_SRC_I = 0x0006, + DR_STE_V1_LU_TYPE_ETHL2_HEADERS_I = 0x0106, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_O = 0x0007, + DR_STE_V1_LU_TYPE_IPV6_DES_O = 0x0107, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_5_TUPLE_I = 0x0008, + DR_STE_V1_LU_TYPE_IPV6_DES_I = 0x0108, + DR_STE_V1_LU_TYPE_ETHL4_O = 0x0009, + DR_STE_V1_LU_TYPE_IPV6_SRC_O = 0x0109, + DR_STE_V1_LU_TYPE_ETHL4_I = 0x000a, + DR_STE_V1_LU_TYPE_IPV6_SRC_I = 0x010a, + DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_O = 0x000b, + DR_STE_V1_LU_TYPE_MPLS_O = 0x010b, + DR_STE_V1_LU_TYPE_ETHL2_SRC_DST_I = 0x000c, + DR_STE_V1_LU_TYPE_MPLS_I = 0x010c, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_O = 0x000d, + DR_STE_V1_LU_TYPE_GRE = 0x010d, + DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER = 0x000e, + DR_STE_V1_LU_TYPE_GENERAL_PURPOSE = 0x010e, + DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I = 0x000f, + DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0 = 0x010f, + DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1 = 0x0110, + DR_STE_V1_LU_TYPE_FLEX_PARSER_0 = 0x0111, + DR_STE_V1_LU_TYPE_FLEX_PARSER_1 = 0x0112, + DR_STE_V1_LU_TYPE_ETHL4_MISC_O = 0x0113, + DR_STE_V1_LU_TYPE_ETHL4_MISC_I = 0x0114, + DR_STE_V1_LU_TYPE_INVALID = 0x00ff, + DR_STE_V1_LU_TYPE_DONT_CARE = MLX5DR_STE_LU_TYPE_DONT_CARE, +}; + +enum dr_ste_v1_header_anchors { + DR_STE_HEADER_ANCHOR_START_OUTER = 0x00, + DR_STE_HEADER_ANCHOR_1ST_VLAN = 0x02, + DR_STE_HEADER_ANCHOR_IPV6_IPV4 = 0x07, + DR_STE_HEADER_ANCHOR_INNER_MAC = 0x13, + DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4 = 0x19, +}; + +enum dr_ste_v1_action_size { + DR_STE_ACTION_SINGLE_SZ = 4, + DR_STE_ACTION_DOUBLE_SZ = 8, + DR_STE_ACTION_TRIPLE_SZ = 12, +}; + +enum dr_ste_v1_action_insert_ptr_attr { + DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE = 0, /* Regular push header (e.g. push vlan) */ + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP = 1, /* Encapsulation / Tunneling */ + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ESP = 2, /* IPsec */ +}; + +enum dr_ste_v1_action_id { + DR_STE_V1_ACTION_ID_NOP = 0x00, + DR_STE_V1_ACTION_ID_COPY = 0x05, + DR_STE_V1_ACTION_ID_SET = 0x06, + DR_STE_V1_ACTION_ID_ADD = 0x07, + DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE = 0x08, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER = 0x09, + DR_STE_V1_ACTION_ID_INSERT_INLINE = 0x0a, + DR_STE_V1_ACTION_ID_INSERT_POINTER = 0x0b, + DR_STE_V1_ACTION_ID_FLOW_TAG = 0x0c, + DR_STE_V1_ACTION_ID_QUEUE_ID_SEL = 0x0d, + DR_STE_V1_ACTION_ID_ACCELERATED_LIST = 0x0e, + DR_STE_V1_ACTION_ID_MODIFY_LIST = 0x0f, + DR_STE_V1_ACTION_ID_TRAILER = 0x13, + DR_STE_V1_ACTION_ID_COUNTER_ID = 0x14, + DR_STE_V1_ACTION_ID_MAX = 0x21, + /* use for special cases */ + DR_STE_V1_ACTION_ID_SPECIAL_ENCAP_L3 = 0x22, +}; + +enum { + DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0 = 0x00, + DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1 = 0x01, + DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2 = 0x02, + DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0 = 0x08, + DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1 = 0x09, + DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0 = 0x0e, + DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0 = 0x18, + DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1 = 0x19, + DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0 = 0x40, + DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1 = 0x41, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0 = 0x44, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1 = 0x45, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2 = 0x46, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3 = 0x47, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0 = 0x4c, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1 = 0x4d, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2 = 0x4e, + DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, + DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, + DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, + DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, + DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2 = 0x8c, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_3 = 0x8d, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_4 = 0x8e, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_5 = 0x8f, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_6 = 0x90, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_7 = 0x91, +}; + +static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field_arr[] = { + [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_6, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_7, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_4, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_5, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_3, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15, + }, +}; + +static void dr_ste_v1_set_entry_type(u8 *hw_ste_p, u8 entry_type) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, entry_format, entry_type); +} + +static void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) +{ + u64 index = miss_addr >> 6; + + MLX5_SET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32, index >> 26); + MLX5_SET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6, index); +} + +static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p) +{ + u64 index = + (MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) | + MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32) << 26); + + return index << 6; +} + +static void dr_ste_v1_set_byte_mask(u8 *hw_ste_p, u16 byte_mask) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, byte_mask, byte_mask); +} + +static u16 dr_ste_v1_get_byte_mask(u8 *hw_ste_p) +{ + return MLX5_GET(ste_match_bwc_v1, hw_ste_p, byte_mask); +} + +static void dr_ste_v1_set_lu_type(u8 *hw_ste_p, u16 lu_type) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, entry_format, lu_type >> 8); + MLX5_SET(ste_match_bwc_v1, hw_ste_p, match_definer_ctx_idx, lu_type & 0xFF); +} + +static void dr_ste_v1_set_next_lu_type(u8 *hw_ste_p, u16 lu_type) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_entry_format, lu_type >> 8); + MLX5_SET(ste_match_bwc_v1, hw_ste_p, hash_definer_ctx_idx, lu_type & 0xFF); +} + +static u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p) +{ + u8 mode = MLX5_GET(ste_match_bwc_v1, hw_ste_p, next_entry_format); + u8 index = MLX5_GET(ste_match_bwc_v1, hw_ste_p, hash_definer_ctx_idx); + + return (mode << 8 | index); +} + +static void dr_ste_v1_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_table_base_63_48, gvmi); +} + +static void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size) +{ + u64 index = (icm_addr >> 5) | ht_size; + + MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_table_base_39_32_size, index >> 27); + MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_table_base_31_5_size, index); +} + +static void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, + u8 entry_type, u16 gvmi) +{ + dr_ste_v1_set_lu_type(hw_ste_p, lu_type); + dr_ste_v1_set_next_lu_type(hw_ste_p, MLX5DR_STE_LU_TYPE_DONT_CARE); + + MLX5_SET(ste_match_bwc_v1, hw_ste_p, gvmi, gvmi); + MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_table_base_63_48, gvmi); + MLX5_SET(ste_match_bwc_v1, hw_ste_p, miss_address_63_48, gvmi); +} + +static void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, + u32 ste_size) +{ + u8 *tag = hw_ste_p + DR_STE_SIZE_CTRL; + u8 *mask = tag + DR_STE_SIZE_TAG; + u8 tmp_tag[DR_STE_SIZE_TAG] = {}; + + if (ste_size == DR_STE_SIZE_CTRL) + return; + + WARN_ON(ste_size != DR_STE_SIZE); + + /* Backup tag */ + memcpy(tmp_tag, tag, DR_STE_SIZE_TAG); + + /* Swap mask and tag both are the same size */ + memcpy(tag, mask, DR_STE_SIZE_MASK); + memcpy(mask, tmp_tag, DR_STE_SIZE_TAG); +} + +static void dr_ste_v1_set_rx_flow_tag(u8 *s_action, u32 flow_tag) +{ + MLX5_SET(ste_single_action_flow_tag_v1, s_action, action_id, + DR_STE_V1_ACTION_ID_FLOW_TAG); + MLX5_SET(ste_single_action_flow_tag_v1, s_action, flow_tag, flow_tag); +} + +static void dr_ste_v1_set_counter_id(u8 *hw_ste_p, u32 ctr_id) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, counter_id, ctr_id); +} + +static void dr_ste_v1_set_reparse(u8 *hw_ste_p) +{ + MLX5_SET(ste_match_bwc_v1, hw_ste_p, reparse, 1); +} + +static void dr_ste_v1_set_tx_encap(u8 *hw_ste_p, u8 *d_action, + u32 reformat_id, int size) +{ + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_POINTER); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, size, size / 2); + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, pointer, reformat_id); + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, attributes, + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP); + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_tx_push_vlan(u8 *hw_ste_p, u8 *d_action, + u32 vlan_hdr) +{ + MLX5_SET(ste_double_action_insert_with_inline_v1, d_action, + action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); + /* The hardware expects offset to vlan header in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_inline_v1, d_action, + start_offset, HDR_LEN_L2_MACS >> 1); + MLX5_SET(ste_double_action_insert_with_inline_v1, d_action, + inline_data, vlan_hdr); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_rx_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) +{ + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, + action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, + start_anchor, DR_STE_HEADER_ANCHOR_1ST_VLAN); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_single_action_remove_header_size_v1, s_action, + remove_size, (HDR_LEN_L2_VLAN >> 1) * vlans_num); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_tx_encap_l3(u8 *hw_ste_p, + u8 *frst_s_action, + u8 *scnd_d_action, + u32 reformat_id, + int size) +{ + /* Remove L2 headers */ + MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); + MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, end_anchor, + DR_STE_HEADER_ANCHOR_IPV6_IPV4); + + /* Encapsulate with given reformat ID */ + MLX5_SET(ste_double_action_insert_with_ptr_v1, scnd_d_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_POINTER); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_ptr_v1, scnd_d_action, size, size / 2); + MLX5_SET(ste_double_action_insert_with_ptr_v1, scnd_d_action, pointer, reformat_id); + MLX5_SET(ste_double_action_insert_with_ptr_v1, scnd_d_action, attributes, + DR_STE_V1_ACTION_INSERT_PTR_ATTR_ENCAP); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action) +{ + MLX5_SET(ste_single_action_remove_header_v1, s_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); + MLX5_SET(ste_single_action_remove_header_v1, s_action, decap, 1); + MLX5_SET(ste_single_action_remove_header_v1, s_action, vni_to_cqe, 1); + MLX5_SET(ste_single_action_remove_header_v1, s_action, end_anchor, + DR_STE_HEADER_ANCHOR_INNER_MAC); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_rx_decap_l3(u8 *hw_ste_p, + u8 *s_action, + u16 decap_actions, + u32 decap_index) +{ + MLX5_SET(ste_single_action_modify_list_v1, s_action, action_id, + DR_STE_V1_ACTION_ID_MODIFY_LIST); + MLX5_SET(ste_single_action_modify_list_v1, s_action, num_of_modify_actions, + decap_actions); + MLX5_SET(ste_single_action_modify_list_v1, s_action, modify_actions_ptr, + decap_index); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_set_rewrite_actions(u8 *hw_ste_p, + u8 *s_action, + u16 num_of_actions, + u32 re_write_index) +{ + MLX5_SET(ste_single_action_modify_list_v1, s_action, action_id, + DR_STE_V1_ACTION_ID_MODIFY_LIST); + MLX5_SET(ste_single_action_modify_list_v1, s_action, num_of_modify_actions, + num_of_actions); + MLX5_SET(ste_single_action_modify_list_v1, s_action, modify_actions_ptr, + re_write_index); + + dr_ste_v1_set_reparse(hw_ste_p); +} + +static void dr_ste_v1_arr_init_next_match(u8 **last_ste, + u32 *added_stes, + u16 gvmi) +{ + u8 *action; + + (*added_stes)++; + *last_ste += DR_STE_SIZE; + dr_ste_v1_init(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE, 0, gvmi); + dr_ste_v1_set_entry_type(*last_ste, DR_STE_V1_TYPE_MATCH); + + action = MLX5_ADDR_OF(ste_mask_and_match_v1, *last_ste, action); + memset(action, 0, MLX5_FLD_SZ_BYTES(ste_mask_and_match_v1, action)); +} + +static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, + u8 *action_type_set, + u8 *last_ste, + struct mlx5dr_ste_actions_attr *attr, + u32 *added_stes) +{ + u8 *action = MLX5_ADDR_OF(ste_match_bwc_v1, last_ste, action); + u8 action_sz = DR_STE_ACTION_DOUBLE_SZ; + bool allow_encap = true; + + if (action_type_set[DR_ACTION_TYP_CTR]) + dr_ste_v1_set_counter_id(last_ste, attr->ctr_id); + + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (action_sz < DR_STE_ACTION_DOUBLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, + attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, + last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_rewrite_actions(last_ste, action, + attr->modify_actions, + attr->modify_index); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + allow_encap = false; + } + + if (action_type_set[DR_ACTION_TYP_PUSH_VLAN]) { + int i; + + for (i = 0; i < attr->vlans.count; i++) { + if (action_sz < DR_STE_ACTION_DOUBLE_SZ || !allow_encap) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_encap = true; + } + dr_ste_v1_set_tx_push_vlan(last_ste, action, attr->vlans.headers[i]); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + } + } + + if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2]) { + if (!allow_encap || action_sz < DR_STE_ACTION_DOUBLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_encap = true; + } + dr_ste_v1_set_tx_encap(last_ste, action, + attr->reformat_id, + attr->reformat_size); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + } else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) { + u8 *d_action; + + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + d_action = action + DR_STE_ACTION_SINGLE_SZ; + + dr_ste_v1_set_tx_encap_l3(last_ste, + action, d_action, + attr->reformat_id, + attr->reformat_size); + action_sz -= DR_STE_ACTION_TRIPLE_SZ; + action += DR_STE_ACTION_TRIPLE_SZ; + } + + dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); + dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); +} + +static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, + u8 *action_type_set, + u8 *last_ste, + struct mlx5dr_ste_actions_attr *attr, + u32 *added_stes) +{ + u8 *action = MLX5_ADDR_OF(ste_match_bwc_v1, last_ste, action); + u8 action_sz = DR_STE_ACTION_DOUBLE_SZ; + bool allow_modify_hdr = true; + bool allow_ctr = true; + + if (action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) { + dr_ste_v1_set_rx_decap_l3(last_ste, action, + attr->decap_actions, + attr->decap_index); + dr_ste_v1_set_rewrite_actions(last_ste, action, + attr->decap_actions, + attr->decap_index); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + allow_modify_hdr = false; + allow_ctr = false; + } else if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2]) { + dr_ste_v1_set_rx_decap(last_ste, action); + action_sz -= DR_STE_ACTION_SINGLE_SZ; + action += DR_STE_ACTION_SINGLE_SZ; + allow_modify_hdr = false; + allow_ctr = false; + } + + if (action_type_set[DR_ACTION_TYP_TAG]) { + if (action_sz < DR_STE_ACTION_SINGLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_modify_hdr = true; + allow_ctr = true; + } + dr_ste_v1_set_rx_flow_tag(action, attr->flow_tag); + action_sz -= DR_STE_ACTION_SINGLE_SZ; + action += DR_STE_ACTION_SINGLE_SZ; + } + + if (action_type_set[DR_ACTION_TYP_POP_VLAN]) { + if (action_sz < DR_STE_ACTION_SINGLE_SZ || + !allow_modify_hdr) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_modify_hdr = false; + allow_ctr = false; + } + + dr_ste_v1_set_rx_pop_vlan(last_ste, action, attr->vlans.count); + action_sz -= DR_STE_ACTION_SINGLE_SZ; + action += DR_STE_ACTION_SINGLE_SZ; + } + + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + /* Modify header and decapsulation must use different STEs */ + if (!allow_modify_hdr || action_sz < DR_STE_ACTION_DOUBLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_modify_hdr = true; + allow_ctr = true; + } + dr_ste_v1_set_rewrite_actions(last_ste, action, + attr->modify_actions, + attr->modify_index); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + } + + if (action_type_set[DR_ACTION_TYP_CTR]) { + /* Counter action set after decap to exclude decaped header */ + if (!allow_ctr) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + allow_modify_hdr = true; + allow_ctr = false; + } + dr_ste_v1_set_counter_id(last_ste, attr->ctr_id); + } + + dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); + dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); +} + +static void dr_ste_v1_set_action_set(u8 *d_action, + u8 hw_field, + u8 shifter, + u8 length, + u32 data) +{ + shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; + MLX5_SET(ste_double_action_set_v1, d_action, action_id, DR_STE_V1_ACTION_ID_SET); + MLX5_SET(ste_double_action_set_v1, d_action, destination_dw_offset, hw_field); + MLX5_SET(ste_double_action_set_v1, d_action, destination_left_shifter, shifter); + MLX5_SET(ste_double_action_set_v1, d_action, destination_length, length); + MLX5_SET(ste_double_action_set_v1, d_action, inline_data, data); +} + +static void dr_ste_v1_set_action_add(u8 *d_action, + u8 hw_field, + u8 shifter, + u8 length, + u32 data) +{ + shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; + MLX5_SET(ste_double_action_add_v1, d_action, action_id, DR_STE_V1_ACTION_ID_ADD); + MLX5_SET(ste_double_action_add_v1, d_action, destination_dw_offset, hw_field); + MLX5_SET(ste_double_action_add_v1, d_action, destination_left_shifter, shifter); + MLX5_SET(ste_double_action_add_v1, d_action, destination_length, length); + MLX5_SET(ste_double_action_add_v1, d_action, add_value, data); +} + +static void dr_ste_v1_set_action_copy(u8 *d_action, + u8 dst_hw_field, + u8 dst_shifter, + u8 dst_len, + u8 src_hw_field, + u8 src_shifter) +{ + dst_shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; + src_shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; + MLX5_SET(ste_double_action_copy_v1, d_action, action_id, DR_STE_V1_ACTION_ID_COPY); + MLX5_SET(ste_double_action_copy_v1, d_action, destination_dw_offset, dst_hw_field); + MLX5_SET(ste_double_action_copy_v1, d_action, destination_left_shifter, dst_shifter); + MLX5_SET(ste_double_action_copy_v1, d_action, destination_length, dst_len); + MLX5_SET(ste_double_action_copy_v1, d_action, source_dw_offset, src_hw_field); + MLX5_SET(ste_double_action_copy_v1, d_action, source_right_shifter, src_shifter); +} + +#define DR_STE_DECAP_L3_ACTION_NUM 8 +#define DR_STE_L2_HDR_MAX_SZ 20 + +static int dr_ste_v1_set_action_decap_l3_list(void *data, + u32 data_sz, + u8 *hw_action, + u32 hw_action_sz, + u16 *used_hw_action_num) +{ + u8 padded_data[DR_STE_L2_HDR_MAX_SZ] = {}; + void *data_ptr = padded_data; + u16 used_actions = 0; + u32 inline_data_sz; + u32 i; + + if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM) + return -EINVAL; + + memcpy(padded_data, data, data_sz); + + /* Remove L2L3 outer headers */ + MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_HEADER_TO_HEADER); + MLX5_SET(ste_single_action_remove_header_v1, hw_action, decap, 1); + MLX5_SET(ste_single_action_remove_header_v1, hw_action, vni_to_cqe, 1); + MLX5_SET(ste_single_action_remove_header_v1, hw_action, end_anchor, + DR_STE_HEADER_ANCHOR_INNER_IPV6_IPV4); + hw_action += DR_STE_ACTION_DOUBLE_SZ; + used_actions++; /* Remove and NOP are a single double action */ + + inline_data_sz = + MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + + /* Add the new header inline + 2 extra bytes */ + for (i = 0; i < data_sz / inline_data_sz + 1; i++) { + void *addr_inline; + + MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id, + DR_STE_V1_ACTION_ID_INSERT_INLINE); + /* The hardware expects here offset to words (2 bytes) */ + MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, + i * 2); + + /* Copy bytes one by one to avoid endianness problem */ + addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1, + hw_action, inline_data); + memcpy(addr_inline, data_ptr, inline_data_sz); + hw_action += DR_STE_ACTION_DOUBLE_SZ; + data_ptr += inline_data_sz; + used_actions++; + } + + /* Remove 2 extra bytes */ + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id, + DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2); + /* The hardware expects here size in words (2 bytes) */ + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1); + used_actions++; + + *used_hw_action_num = used_actions; + + return 0; +} + +static void dr_ste_v1_build_eth_l2_src_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, dmac_15_0, mask, dmac_15_0); + + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, smac_47_16, mask, smac_47_16); + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, smac_15_0, mask, smac_15_0); + + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_TAG(eth_l2_src_dst_v1, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_ONES(eth_l2_src_dst_v1, bit_mask, l3_type, mask, ip_version); + + if (mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_dst_v1, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + } else if (mask->svlan_tag) { + MLX5_SET(ste_eth_l2_src_dst_v1, bit_mask, first_vlan_qualifier, -1); + mask->svlan_tag = 0; + } +} + +static int dr_ste_v1_build_eth_l2_src_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, dmac_15_0, spec, dmac_15_0); + + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, smac_47_16, spec, smac_47_16); + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, smac_15_0, spec, smac_15_0); + + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_src_dst_v1, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_src_dst_v1, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else if (spec->ip_version) { + return -EINVAL; + } + + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_src_dst_v1, tag, first_priority, spec, first_prio); + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_dst_v1, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_src_dst_v1, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + return 0; +} + +static void dr_ste_v1_build_eth_l2_src_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l2_src_dst_bit_mask(mask, sb->inner, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(ETHL2_SRC_DST, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l2_src_dst_tag; +} + +static int dr_ste_v1_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_127_96, spec, dst_ip_127_96); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_95_64, spec, dst_ip_95_64); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_63_32, spec, dst_ip_63_32); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_31_0, spec, dst_ip_31_0); + + return 0; +} + +static void dr_ste_v1_build_eth_l3_ipv6_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l3_ipv6_dst_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(IPV6_DES, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l3_ipv6_dst_tag; +} + +static int dr_ste_v1_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_127_96, spec, src_ip_127_96); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_95_64, spec, src_ip_95_64); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_63_32, spec, src_ip_63_32); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_31_0, spec, src_ip_31_0); + + return 0; +} + +static void dr_ste_v1_build_eth_l3_ipv6_src_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l3_ipv6_src_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(IPV6_SRC, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l3_ipv6_src_tag; +} + +static int dr_ste_v1_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, destination_address, spec, dst_ip_31_0); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, source_address, spec, src_ip_31_0); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, destination_port, spec, tcp_dport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, destination_port, spec, udp_dport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, source_port, spec, tcp_sport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, source_port, spec, udp_sport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, protocol, spec, ip_protocol); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, fragmented, spec, frag); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, dscp, spec, ip_dscp); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple_v1, tag, ecn, spec, ip_ecn); + + if (spec->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple_v1, tag, spec); + spec->tcp_flags = 0; + } + + return 0; +} + +static void dr_ste_v1_build_eth_l3_ipv4_5_tuple_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l3_ipv4_5_tuple_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(ETHL3_IPV4_5_TUPLE, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l3_ipv4_5_tuple_tag; +} + +static void dr_ste_v1_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, ip_fragmented, mask, frag); // ? + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, l3_ethertype, mask, ethertype); // ? + DR_STE_SET_ONES(eth_l2_src_v1, bit_mask, l3_type, mask, ip_version); + + if (mask->svlan_tag || mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + mask->svlan_tag = 0; + } + + if (inner) { + if (misc_mask->inner_second_cvlan_tag || + misc_mask->inner_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, bit_mask, second_vlan_qualifier, -1); + misc_mask->inner_second_cvlan_tag = 0; + misc_mask->inner_second_svlan_tag = 0; + } + + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, + second_vlan_id, misc_mask, inner_second_vid); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, + second_cfi, misc_mask, inner_second_cfi); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, + second_priority, misc_mask, inner_second_prio); + } else { + if (misc_mask->outer_second_cvlan_tag || + misc_mask->outer_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, bit_mask, second_vlan_qualifier, -1); + misc_mask->outer_second_cvlan_tag = 0; + misc_mask->outer_second_svlan_tag = 0; + } + + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, + second_vlan_id, misc_mask, outer_second_vid); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, + second_cfi, misc_mask, outer_second_cfi); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, + second_priority, misc_mask, outer_second_prio); + } +} + +static int dr_ste_v1_build_eth_l2_src_or_dst_tag(struct mlx5dr_match_param *value, + bool inner, u8 *tag) +{ + struct mlx5dr_match_spec *spec = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc_spec = &value->misc; + + DR_STE_SET_TAG(eth_l2_src_v1, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_src_v1, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_src_v1, tag, first_priority, spec, first_prio); + DR_STE_SET_TAG(eth_l2_src_v1, tag, ip_fragmented, spec, frag); + DR_STE_SET_TAG(eth_l2_src_v1, tag, l3_ethertype, spec, ethertype); + + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_src_v1, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_src_v1, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else if (spec->ip_version) { + return -EINVAL; + } + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + + if (inner) { + if (misc_spec->inner_second_cvlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, tag, second_vlan_qualifier, DR_STE_CVLAN); + misc_spec->inner_second_cvlan_tag = 0; + } else if (misc_spec->inner_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, tag, second_vlan_qualifier, DR_STE_SVLAN); + misc_spec->inner_second_svlan_tag = 0; + } + + DR_STE_SET_TAG(eth_l2_src_v1, tag, second_vlan_id, misc_spec, inner_second_vid); + DR_STE_SET_TAG(eth_l2_src_v1, tag, second_cfi, misc_spec, inner_second_cfi); + DR_STE_SET_TAG(eth_l2_src_v1, tag, second_priority, misc_spec, inner_second_prio); + } else { + if (misc_spec->outer_second_cvlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, tag, second_vlan_qualifier, DR_STE_CVLAN); + misc_spec->outer_second_cvlan_tag = 0; + } else if (misc_spec->outer_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src_v1, tag, second_vlan_qualifier, DR_STE_SVLAN); + misc_spec->outer_second_svlan_tag = 0; + } + DR_STE_SET_TAG(eth_l2_src_v1, tag, second_vlan_id, misc_spec, outer_second_vid); + DR_STE_SET_TAG(eth_l2_src_v1, tag, second_cfi, misc_spec, outer_second_cfi); + DR_STE_SET_TAG(eth_l2_src_v1, tag, second_priority, misc_spec, outer_second_prio); + } + + return 0; +} + +static void dr_ste_v1_build_eth_l2_src_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, smac_47_16, mask, smac_47_16); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, smac_15_0, mask, smac_15_0); + + dr_ste_v1_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask); +} + +static int dr_ste_v1_build_eth_l2_src_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l2_src_v1, tag, smac_47_16, spec, smac_47_16); + DR_STE_SET_TAG(eth_l2_src_v1, tag, smac_15_0, spec, smac_15_0); + + return dr_ste_v1_build_eth_l2_src_or_dst_tag(value, sb->inner, tag); +} + +static void dr_ste_v1_build_eth_l2_src_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l2_src_bit_mask(mask, sb->inner, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(ETHL2_SRC, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l2_src_tag; +} + +static void dr_ste_v1_build_eth_l2_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l2_dst_v1, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_TAG(eth_l2_dst_v1, bit_mask, dmac_15_0, mask, dmac_15_0); + + dr_ste_v1_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask); +} + +static int dr_ste_v1_build_eth_l2_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l2_dst_v1, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_dst_v1, tag, dmac_15_0, spec, dmac_15_0); + + return dr_ste_v1_build_eth_l2_src_or_dst_tag(value, sb->inner, tag); +} + +static void dr_ste_v1_build_eth_l2_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l2_dst_bit_mask(mask, sb->inner, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(ETHL2, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l2_dst_tag; +} + +static void dr_ste_v1_build_eth_l2_tnl_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, dmac_15_0, mask, dmac_15_0); + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, ip_fragmented, mask, frag); + DR_STE_SET_TAG(eth_l2_tnl_v1, bit_mask, l3_ethertype, mask, ethertype); + DR_STE_SET_ONES(eth_l2_tnl_v1, bit_mask, l3_type, mask, ip_version); + + if (misc->vxlan_vni) { + MLX5_SET(ste_eth_l2_tnl_v1, bit_mask, + l2_tunneling_network_id, (misc->vxlan_vni << 8)); + misc->vxlan_vni = 0; + } + + if (mask->svlan_tag || mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_tnl_v1, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + mask->svlan_tag = 0; + } +} + +static int dr_ste_v1_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, dmac_15_0, spec, dmac_15_0); + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, ip_fragmented, spec, frag); + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, first_priority, spec, first_prio); + DR_STE_SET_TAG(eth_l2_tnl_v1, tag, l3_ethertype, spec, ethertype); + + if (misc->vxlan_vni) { + MLX5_SET(ste_eth_l2_tnl_v1, tag, l2_tunneling_network_id, + (misc->vxlan_vni << 8)); + misc->vxlan_vni = 0; + } + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_tnl_v1, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_tnl_v1, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_tnl_v1, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_tnl_v1, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else if (spec->ip_version) { + return -EINVAL; + } + + return 0; +} + +static void dr_ste_v1_build_eth_l2_tnl_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l2_tnl_bit_mask(mask, sb->inner, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_ETHL2_TNL; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l2_tnl_tag; +} + +static int dr_ste_v1_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + + DR_STE_SET_TAG(eth_l3_ipv4_misc_v1, tag, time_to_live, spec, ttl_hoplimit); + + return 0; +} + +static void dr_ste_v1_build_eth_l3_ipv4_misc_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l3_ipv4_misc_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(ETHL3_IPV4_MISC, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l3_ipv4_misc_tag; +} + +static int dr_ste_v1_build_eth_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_TAG(eth_l4_v1, tag, dst_port, spec, tcp_dport); + DR_STE_SET_TAG(eth_l4_v1, tag, src_port, spec, tcp_sport); + DR_STE_SET_TAG(eth_l4_v1, tag, dst_port, spec, udp_dport); + DR_STE_SET_TAG(eth_l4_v1, tag, src_port, spec, udp_sport); + DR_STE_SET_TAG(eth_l4_v1, tag, protocol, spec, ip_protocol); + DR_STE_SET_TAG(eth_l4_v1, tag, fragmented, spec, frag); + DR_STE_SET_TAG(eth_l4_v1, tag, dscp, spec, ip_dscp); + DR_STE_SET_TAG(eth_l4_v1, tag, ecn, spec, ip_ecn); + DR_STE_SET_TAG(eth_l4_v1, tag, ipv6_hop_limit, spec, ttl_hoplimit); + + if (sb->inner) + DR_STE_SET_TAG(eth_l4_v1, tag, flow_label, misc, inner_ipv6_flow_label); + else + DR_STE_SET_TAG(eth_l4_v1, tag, flow_label, misc, outer_ipv6_flow_label); + + if (spec->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l4_v1, tag, spec); + spec->tcp_flags = 0; + } + + return 0; +} + +static void dr_ste_v1_build_eth_ipv6_l3_l4_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_ipv6_l3_l4_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(ETHL4, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_ipv6_l3_l4_tag; +} + +static int dr_ste_v1_build_mpls_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + + if (sb->inner) + DR_STE_SET_MPLS(mpls_v1, misc2, inner, tag); + else + DR_STE_SET_MPLS(mpls_v1, misc2, outer, tag); + + return 0; +} + +static void dr_ste_v1_build_mpls_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_mpls_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_CALC_DFNR_TYPE(MPLS, sb->inner); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_mpls_tag; +} + +static int dr_ste_v1_build_tnl_gre_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_TAG(gre_v1, tag, gre_protocol, misc, gre_protocol); + DR_STE_SET_TAG(gre_v1, tag, gre_k_present, misc, gre_k_present); + DR_STE_SET_TAG(gre_v1, tag, gre_key_h, misc, gre_key_h); + DR_STE_SET_TAG(gre_v1, tag, gre_key_l, misc, gre_key_l); + + DR_STE_SET_TAG(gre_v1, tag, gre_c_present, misc, gre_c_present); + DR_STE_SET_TAG(gre_v1, tag, gre_s_present, misc, gre_s_present); + + return 0; +} + +static void dr_ste_v1_build_tnl_gre_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_tnl_gre_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_GRE; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_tnl_gre_tag; +} + +static int dr_ste_v1_build_tnl_mpls_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + + if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc2)) { + DR_STE_SET_TAG(mpls_v1, tag, mpls0_label, + misc2, outer_first_mpls_over_gre_label); + + DR_STE_SET_TAG(mpls_v1, tag, mpls0_exp, + misc2, outer_first_mpls_over_gre_exp); + + DR_STE_SET_TAG(mpls_v1, tag, mpls0_s_bos, + misc2, outer_first_mpls_over_gre_s_bos); + + DR_STE_SET_TAG(mpls_v1, tag, mpls0_ttl, + misc2, outer_first_mpls_over_gre_ttl); + } else { + DR_STE_SET_TAG(mpls_v1, tag, mpls0_label, + misc2, outer_first_mpls_over_udp_label); + + DR_STE_SET_TAG(mpls_v1, tag, mpls0_exp, + misc2, outer_first_mpls_over_udp_exp); + + DR_STE_SET_TAG(mpls_v1, tag, mpls0_s_bos, + misc2, outer_first_mpls_over_udp_s_bos); + + DR_STE_SET_TAG(mpls_v1, tag, mpls0_ttl, + misc2, outer_first_mpls_over_udp_ttl); + } + + return 0; +} + +static void dr_ste_v1_build_tnl_mpls_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_tnl_mpls_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_MPLS_I; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_tnl_mpls_tag; +} + +static int dr_ste_v1_build_icmp_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + bool is_ipv4 = DR_MASK_IS_ICMPV4_SET(misc3); + u32 *icmp_header_data; + u8 *icmp_type; + u8 *icmp_code; + + if (is_ipv4) { + icmp_header_data = &misc3->icmpv4_header_data; + icmp_type = &misc3->icmpv4_type; + icmp_code = &misc3->icmpv4_code; + } else { + icmp_header_data = &misc3->icmpv6_header_data; + icmp_type = &misc3->icmpv6_type; + icmp_code = &misc3->icmpv6_code; + } + + MLX5_SET(ste_icmp_v1, tag, icmp_header_data, *icmp_header_data); + MLX5_SET(ste_icmp_v1, tag, icmp_type, *icmp_type); + MLX5_SET(ste_icmp_v1, tag, icmp_code, *icmp_code); + + *icmp_header_data = 0; + *icmp_type = 0; + *icmp_code = 0; + + return 0; +} + +static int dr_ste_v1_build_icmp_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_icmp_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_ETHL4_MISC_O; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_icmp_tag; + + return 0; +} + +static int dr_ste_v1_build_general_purpose_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + + DR_STE_SET_TAG(general_purpose, tag, general_purpose_lookup_field, + misc2, metadata_reg_a); + + return 0; +} + +static void dr_ste_v1_build_general_purpose_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_general_purpose_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_GENERAL_PURPOSE; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_general_purpose_tag; +} + +static int dr_ste_v1_build_eth_l4_misc_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + + if (sb->inner) { + DR_STE_SET_TAG(eth_l4_misc_v1, tag, seq_num, misc3, inner_tcp_seq_num); + DR_STE_SET_TAG(eth_l4_misc_v1, tag, ack_num, misc3, inner_tcp_ack_num); + } else { + DR_STE_SET_TAG(eth_l4_misc_v1, tag, seq_num, misc3, outer_tcp_seq_num); + DR_STE_SET_TAG(eth_l4_misc_v1, tag, ack_num, misc3, outer_tcp_ack_num); + } + + return 0; +} + +static void dr_ste_v1_build_eth_l4_misc_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_eth_l4_misc_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_ETHL4_MISC_O; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_eth_l4_misc_tag; +} + +static int +dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + + DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag, + outer_vxlan_gpe_flags, misc3, + outer_vxlan_gpe_flags); + DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag, + outer_vxlan_gpe_next_protocol, misc3, + outer_vxlan_gpe_next_protocol); + DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag, + outer_vxlan_gpe_vni, misc3, + outer_vxlan_gpe_vni); + + return 0; +} + +static void +dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_tag; +} + +static int +dr_ste_v1_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_protocol_type, misc, geneve_protocol_type); + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_oam, misc, geneve_oam); + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_opt_len, misc, geneve_opt_len); + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_vni, misc, geneve_vni); + + return 0; +} + +static void +dr_ste_v1_build_flex_parser_tnl_geneve_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_flex_parser_tnl_geneve_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_flex_parser_tnl_geneve_tag; +} + +static int dr_ste_v1_build_register_0_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + + DR_STE_SET_TAG(register_0, tag, register_0_h, misc2, metadata_reg_c_0); + DR_STE_SET_TAG(register_0, tag, register_0_l, misc2, metadata_reg_c_1); + DR_STE_SET_TAG(register_0, tag, register_1_h, misc2, metadata_reg_c_2); + DR_STE_SET_TAG(register_0, tag, register_1_l, misc2, metadata_reg_c_3); + + return 0; +} + +static void dr_ste_v1_build_register_0_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_register_0_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_register_0_tag; +} + +static int dr_ste_v1_build_register_1_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + + DR_STE_SET_TAG(register_1, tag, register_2_h, misc2, metadata_reg_c_4); + DR_STE_SET_TAG(register_1, tag, register_2_l, misc2, metadata_reg_c_5); + DR_STE_SET_TAG(register_1, tag, register_3_h, misc2, metadata_reg_c_6); + DR_STE_SET_TAG(register_1, tag, register_3_l, misc2, metadata_reg_c_7); + + return 0; +} + +static void dr_ste_v1_build_register_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_register_1_tag(mask, sb, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_register_1_tag; +} + +static void dr_ste_v1_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_ONES(src_gvmi_qp_v1, bit_mask, source_gvmi, misc_mask, source_port); + DR_STE_SET_ONES(src_gvmi_qp_v1, bit_mask, source_qp, misc_mask, source_sqn); +} + +static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *tag) +{ + struct mlx5dr_match_misc *misc = &value->misc; + struct mlx5dr_cmd_vport_cap *vport_cap; + struct mlx5dr_domain *dmn = sb->dmn; + struct mlx5dr_cmd_caps *caps; + u8 *bit_mask = sb->bit_mask; + + DR_STE_SET_TAG(src_gvmi_qp_v1, tag, source_qp, misc, source_sqn); + + if (sb->vhca_id_valid) { + /* Find port GVMI based on the eswitch_owner_vhca_id */ + if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) + caps = &dmn->info.caps; + else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == + dmn->peer_dmn->info.caps.gvmi)) + caps = &dmn->peer_dmn->info.caps; + else + return -EINVAL; + + misc->source_eswitch_owner_vhca_id = 0; + } else { + caps = &dmn->info.caps; + } + + if (!MLX5_GET(ste_src_gvmi_qp_v1, bit_mask, source_gvmi)) + return 0; + + vport_cap = mlx5dr_get_vport_cap(caps, misc->source_port); + if (!vport_cap) { + mlx5dr_err(dmn, "Vport 0x%x is disabled or invalid\n", + misc->source_port); + return -EINVAL; + } + + if (vport_cap->vport_gvmi) + MLX5_SET(ste_src_gvmi_qp_v1, tag, source_gvmi, vport_cap->vport_gvmi); + + misc->source_port = 0; + return 0; +} + +static void dr_ste_v1_build_src_gvmi_qpn_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + dr_ste_v1_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask); + + sb->lu_type = DR_STE_V1_LU_TYPE_SRC_QP_GVMI; + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_src_gvmi_qpn_tag; +} + +struct mlx5dr_ste_ctx ste_ctx_v1 = { + /* Builders */ + .build_eth_l2_src_dst_init = &dr_ste_v1_build_eth_l2_src_dst_init, + .build_eth_l3_ipv6_src_init = &dr_ste_v1_build_eth_l3_ipv6_src_init, + .build_eth_l3_ipv6_dst_init = &dr_ste_v1_build_eth_l3_ipv6_dst_init, + .build_eth_l3_ipv4_5_tuple_init = &dr_ste_v1_build_eth_l3_ipv4_5_tuple_init, + .build_eth_l2_src_init = &dr_ste_v1_build_eth_l2_src_init, + .build_eth_l2_dst_init = &dr_ste_v1_build_eth_l2_dst_init, + .build_eth_l2_tnl_init = &dr_ste_v1_build_eth_l2_tnl_init, + .build_eth_l3_ipv4_misc_init = &dr_ste_v1_build_eth_l3_ipv4_misc_init, + .build_eth_ipv6_l3_l4_init = &dr_ste_v1_build_eth_ipv6_l3_l4_init, + .build_mpls_init = &dr_ste_v1_build_mpls_init, + .build_tnl_gre_init = &dr_ste_v1_build_tnl_gre_init, + .build_tnl_mpls_init = &dr_ste_v1_build_tnl_mpls_init, + .build_icmp_init = &dr_ste_v1_build_icmp_init, + .build_general_purpose_init = &dr_ste_v1_build_general_purpose_init, + .build_eth_l4_misc_init = &dr_ste_v1_build_eth_l4_misc_init, + .build_tnl_vxlan_gpe_init = &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init, + .build_tnl_geneve_init = &dr_ste_v1_build_flex_parser_tnl_geneve_init, + .build_register_0_init = &dr_ste_v1_build_register_0_init, + .build_register_1_init = &dr_ste_v1_build_register_1_init, + .build_src_gvmi_qpn_init = &dr_ste_v1_build_src_gvmi_qpn_init, + /* Getters and Setters */ + .ste_init = &dr_ste_v1_init, + .set_next_lu_type = &dr_ste_v1_set_next_lu_type, + .get_next_lu_type = &dr_ste_v1_get_next_lu_type, + .set_miss_addr = &dr_ste_v1_set_miss_addr, + .get_miss_addr = &dr_ste_v1_get_miss_addr, + .set_hit_addr = &dr_ste_v1_set_hit_addr, + .set_byte_mask = &dr_ste_v1_set_byte_mask, + .get_byte_mask = &dr_ste_v1_get_byte_mask, + /* Actions */ + .set_actions_rx = &dr_ste_v1_set_actions_rx, + .set_actions_tx = &dr_ste_v1_set_actions_tx, + .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v1_action_modify_field_arr), + .modify_field_arr = dr_ste_v1_action_modify_field_arr, + .set_action_set = &dr_ste_v1_set_action_set, + .set_action_add = &dr_ste_v1_set_action_add, + .set_action_copy = &dr_ste_v1_set_action_copy, + .set_action_decap_l3_list = &dr_ste_v1_set_action_decap_l3_list, + /* Send */ + .prepare_for_postsend = &dr_ste_v1_prepare_for_postsend, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 8d2c3b6e2755..4af0e4e6a13c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -666,7 +666,8 @@ struct mlx5dr_esw_caps { u64 drop_icm_address_tx; u64 uplink_icm_address_rx; u64 uplink_icm_address_tx; - bool sw_owner; + u8 sw_owner:1; + u8 sw_owner_v2:1; }; struct mlx5dr_cmd_vport_cap { @@ -699,6 +700,9 @@ struct mlx5dr_cmd_caps { bool rx_sw_owner; bool tx_sw_owner; bool fdb_sw_owner; + u8 rx_sw_owner_v2:1; + u8 tx_sw_owner_v2:1; + u8 fdb_sw_owner_v2:1; u32 num_vports; struct mlx5dr_esw_caps esw_caps; struct mlx5dr_cmd_vport_cap *vports_caps; @@ -1072,6 +1076,9 @@ struct mlx5dr_icm_chunk * mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, enum mlx5dr_icm_chunk_size chunk_size); void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk); + +void mlx5dr_ste_prepare_for_postsend(struct mlx5dr_ste_ctx *ste_ctx, + u8 *hw_ste_p, u32 ste_size); int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, struct mlx5dr_domain_rx_tx *nic_dmn, struct mlx5dr_ste_htbl *htbl, @@ -1204,6 +1211,8 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev, u32 group_id, struct mlx5dr_cmd_fte_info *fte); +bool mlx5dr_ste_supp_ttl_cs_recalc(struct mlx5dr_cmd_caps *caps); + struct mlx5dr_fw_recalc_cs_ft { u64 rx_icm_addr; u32 table_id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h new file mode 100644 index 000000000000..34c2bd17a8b4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h @@ -0,0 +1,434 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. */ + +#ifndef MLX5_IFC_DR_STE_V1_H +#define MLX5_IFC_DR_STE_V1_H + +enum mlx5_ifc_ste_v1_modify_hdr_offset { + MLX5_MODIFY_HEADER_V1_QW_OFFSET = 0x20, +}; + +struct mlx5_ifc_ste_single_action_flow_tag_v1_bits { + u8 action_id[0x8]; + u8 flow_tag[0x18]; +}; + +struct mlx5_ifc_ste_single_action_modify_list_v1_bits { + u8 action_id[0x8]; + u8 num_of_modify_actions[0x8]; + u8 modify_actions_ptr[0x10]; +}; + +struct mlx5_ifc_ste_single_action_remove_header_v1_bits { + u8 action_id[0x8]; + u8 reserved_at_8[0x2]; + u8 start_anchor[0x6]; + u8 reserved_at_10[0x2]; + u8 end_anchor[0x6]; + u8 reserved_at_18[0x4]; + u8 decap[0x1]; + u8 vni_to_cqe[0x1]; + u8 qos_profile[0x2]; +}; + +struct mlx5_ifc_ste_single_action_remove_header_size_v1_bits { + u8 action_id[0x8]; + u8 reserved_at_8[0x2]; + u8 start_anchor[0x6]; + u8 outer_l4_remove[0x1]; + u8 reserved_at_11[0x1]; + u8 start_offset[0x7]; + u8 reserved_at_18[0x1]; + u8 remove_size[0x6]; +}; + +struct mlx5_ifc_ste_double_action_copy_v1_bits { + u8 action_id[0x8]; + u8 destination_dw_offset[0x8]; + u8 reserved_at_10[0x2]; + u8 destination_left_shifter[0x6]; + u8 reserved_at_17[0x2]; + u8 destination_length[0x6]; + + u8 reserved_at_20[0x8]; + u8 source_dw_offset[0x8]; + u8 reserved_at_30[0x2]; + u8 source_right_shifter[0x6]; + u8 reserved_at_38[0x8]; +}; + +struct mlx5_ifc_ste_double_action_set_v1_bits { + u8 action_id[0x8]; + u8 destination_dw_offset[0x8]; + u8 reserved_at_10[0x2]; + u8 destination_left_shifter[0x6]; + u8 reserved_at_18[0x2]; + u8 destination_length[0x6]; + + u8 inline_data[0x20]; +}; + +struct mlx5_ifc_ste_double_action_add_v1_bits { + u8 action_id[0x8]; + u8 destination_dw_offset[0x8]; + u8 reserved_at_10[0x2]; + u8 destination_left_shifter[0x6]; + u8 reserved_at_18[0x2]; + u8 destination_length[0x6]; + + u8 add_value[0x20]; +}; + +struct mlx5_ifc_ste_double_action_insert_with_inline_v1_bits { + u8 action_id[0x8]; + u8 reserved_at_8[0x2]; + u8 start_anchor[0x6]; + u8 start_offset[0x7]; + u8 reserved_at_17[0x9]; + + u8 inline_data[0x20]; +}; + +struct mlx5_ifc_ste_double_action_insert_with_ptr_v1_bits { + u8 action_id[0x8]; + u8 reserved_at_8[0x2]; + u8 start_anchor[0x6]; + u8 start_offset[0x7]; + u8 size[0x6]; + u8 attributes[0x3]; + + u8 pointer[0x20]; +}; + +struct mlx5_ifc_ste_double_action_modify_action_list_v1_bits { + u8 action_id[0x8]; + u8 modify_actions_pattern_pointer[0x18]; + + u8 number_of_modify_actions[0x8]; + u8 modify_actions_argument_pointer[0x18]; +}; + +struct mlx5_ifc_ste_match_bwc_v1_bits { + u8 entry_format[0x8]; + u8 counter_id[0x18]; + + u8 miss_address_63_48[0x10]; + u8 match_definer_ctx_idx[0x8]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 reserved_at_5a[0x1]; + u8 match_polarity[0x1]; + u8 reparse[0x1]; + u8 reserved_at_5d[0x3]; + + u8 next_table_base_63_48[0x10]; + u8 hash_definer_ctx_idx[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 hash_type[0x2]; + u8 hash_after_actions[0x1]; + u8 reserved_at_9e[0x2]; + + u8 byte_mask[0x10]; + u8 next_entry_format[0x1]; + u8 mask_mode[0x1]; + u8 gvmi[0xe]; + + u8 action[0x40]; +}; + +struct mlx5_ifc_ste_mask_and_match_v1_bits { + u8 entry_format[0x8]; + u8 counter_id[0x18]; + + u8 miss_address_63_48[0x10]; + u8 match_definer_ctx_idx[0x8]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 reserved_at_5a[0x1]; + u8 match_polarity[0x1]; + u8 reparse[0x1]; + u8 reserved_at_5d[0x3]; + + u8 next_table_base_63_48[0x10]; + u8 hash_definer_ctx_idx[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 hash_type[0x2]; + u8 hash_after_actions[0x1]; + u8 reserved_at_9e[0x2]; + + u8 action[0x60]; +}; + +struct mlx5_ifc_ste_eth_l2_src_v1_bits { + u8 reserved_at_0[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_loopback[0x1]; + u8 ip_fragmented[0x1]; + u8 qp_type[0x2]; + u8 encapsulation_type[0x2]; + u8 port[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 first_vlan_qualifier[0x2]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_id[0xc]; + + u8 smac_47_16[0x20]; + + u8 smac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 reserved_at_60[0x6]; + u8 tcp_syn[0x1]; + u8 reserved_at_67[0x3]; + u8 force_loopback[0x1]; + u8 l2_ok[0x1]; + u8 l3_ok[0x1]; + u8 l4_ok[0x1]; + u8 second_vlan_qualifier[0x2]; + + u8 second_priority[0x3]; + u8 second_cfi[0x1]; + u8 second_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l2_dst_v1_bits { + u8 reserved_at_0[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 ip_fragmented[0x1]; + u8 qp_type[0x2]; + u8 encapsulation_type[0x2]; + u8 port[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 first_vlan_qualifier[0x2]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_id[0xc]; + + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 reserved_at_60[0x6]; + u8 tcp_syn[0x1]; + u8 reserved_at_67[0x3]; + u8 force_lb[0x1]; + u8 l2_ok[0x1]; + u8 l3_ok[0x1]; + u8 l4_ok[0x1]; + u8 second_vlan_qualifier[0x2]; + u8 second_priority[0x3]; + u8 second_cfi[0x1]; + u8 second_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l2_src_dst_v1_bits { + u8 dmac_47_16[0x20]; + + u8 smac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 reserved_at_50[0x2]; + u8 functional_lb[0x1]; + u8 reserved_at_53[0x5]; + u8 port[0x2]; + u8 l3_type[0x2]; + u8 reserved_at_5c[0x2]; + u8 first_vlan_qualifier[0x2]; + + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_id[0xc]; + u8 smac_15_0[0x10]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv4_5_tuple_v1_bits { + u8 source_address[0x20]; + + u8 destination_address[0x20]; + + u8 source_port[0x10]; + u8 destination_port[0x10]; + + u8 reserved_at_60[0x4]; + u8 l4_ok[0x1]; + u8 l3_ok[0x1]; + u8 fragmented[0x1]; + u8 tcp_ns[0x1]; + u8 tcp_cwr[0x1]; + u8 tcp_ece[0x1]; + u8 tcp_urg[0x1]; + u8 tcp_ack[0x1]; + u8 tcp_psh[0x1]; + u8 tcp_rst[0x1]; + u8 tcp_syn[0x1]; + u8 tcp_fin[0x1]; + u8 dscp[0x6]; + u8 ecn[0x2]; + u8 protocol[0x8]; +}; + +struct mlx5_ifc_ste_eth_l2_tnl_v1_bits { + u8 l2_tunneling_network_id[0x20]; + + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 reserved_at_60[0x3]; + u8 ip_fragmented[0x1]; + u8 reserved_at_64[0x2]; + u8 encp_type[0x2]; + u8 reserved_at_68[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 first_vlan_qualifier[0x2]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv4_misc_v1_bits { + u8 identification[0x10]; + u8 flags[0x3]; + u8 fragment_offset[0xd]; + + u8 total_length[0x10]; + u8 checksum[0x10]; + + u8 version[0x4]; + u8 ihl[0x4]; + u8 time_to_live[0x8]; + u8 reserved_at_50[0x10]; + + u8 reserved_at_60[0x1c]; + u8 voq_internal_prio[0x4]; +}; + +struct mlx5_ifc_ste_eth_l4_v1_bits { + u8 ipv6_version[0x4]; + u8 reserved_at_4[0x4]; + u8 dscp[0x6]; + u8 ecn[0x2]; + u8 ipv6_hop_limit[0x8]; + u8 protocol[0x8]; + + u8 src_port[0x10]; + u8 dst_port[0x10]; + + u8 first_fragment[0x1]; + u8 reserved_at_41[0xb]; + u8 flow_label[0x14]; + + u8 tcp_data_offset[0x4]; + u8 l4_ok[0x1]; + u8 l3_ok[0x1]; + u8 fragmented[0x1]; + u8 tcp_ns[0x1]; + u8 tcp_cwr[0x1]; + u8 tcp_ece[0x1]; + u8 tcp_urg[0x1]; + u8 tcp_ack[0x1]; + u8 tcp_psh[0x1]; + u8 tcp_rst[0x1]; + u8 tcp_syn[0x1]; + u8 tcp_fin[0x1]; + u8 ipv6_paylen[0x10]; +}; + +struct mlx5_ifc_ste_eth_l4_misc_v1_bits { + u8 window_size[0x10]; + u8 urgent_pointer[0x10]; + + u8 ack_num[0x20]; + + u8 seq_num[0x20]; + + u8 length[0x10]; + u8 checksum[0x10]; +}; + +struct mlx5_ifc_ste_mpls_v1_bits { + u8 reserved_at_0[0x15]; + u8 mpls_ok[0x1]; + u8 mpls4_s_bit[0x1]; + u8 mpls4_qualifier[0x1]; + u8 mpls3_s_bit[0x1]; + u8 mpls3_qualifier[0x1]; + u8 mpls2_s_bit[0x1]; + u8 mpls2_qualifier[0x1]; + u8 mpls1_s_bit[0x1]; + u8 mpls1_qualifier[0x1]; + u8 mpls0_s_bit[0x1]; + u8 mpls0_qualifier[0x1]; + + u8 mpls0_label[0x14]; + u8 mpls0_exp[0x3]; + u8 mpls0_s_bos[0x1]; + u8 mpls0_ttl[0x8]; + + u8 mpls1_label[0x20]; + + u8 mpls2_label[0x20]; +}; + +struct mlx5_ifc_ste_gre_v1_bits { + u8 gre_c_present[0x1]; + u8 reserved_at_1[0x1]; + u8 gre_k_present[0x1]; + u8 gre_s_present[0x1]; + u8 strict_src_route[0x1]; + u8 recur[0x3]; + u8 flags[0x5]; + u8 version[0x3]; + u8 gre_protocol[0x10]; + + u8 reserved_at_20[0x20]; + + u8 gre_key_h[0x18]; + u8 gre_key_l[0x8]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_ste_src_gvmi_qp_v1_bits { + u8 loopback_synd[0x8]; + u8 reserved_at_8[0x7]; + u8 functional_lb[0x1]; + u8 source_gvmi[0x10]; + + u8 force_lb[0x1]; + u8 reserved_at_21[0x1]; + u8 source_is_requestor[0x1]; + u8 reserved_at_23[0x5]; + u8 source_qp[0x18]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_ste_icmp_v1_bits { + u8 icmp_payload_data[0x20]; + + u8 icmp_header_data[0x20]; + + u8 icmp_type[0x8]; + u8 icmp_code[0x8]; + u8 reserved_at_50[0x10]; + + u8 reserved_at_60[0x20]; +}; + +#endif /* MLX5_IFC_DR_STE_V1_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 4177786b8eaf..612b0ac31db2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -124,7 +124,10 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action); static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { - return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner); + return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && + (MLX5_CAP_GEN(dev, steering_format_version) <= + MLX5_STEERING_FORMAT_CONNECTX_6DX)); } /* buddy functions & structure */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index bdafc85fd874..ba78e0660523 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -36,6 +36,7 @@ #include <linux/mlx5/vport.h> #include <linux/mlx5/eswitch.h> #include "mlx5_core.h" +#include "sf/sf.h" /* Mutex to hold while enabling or disabling RoCE */ static DEFINE_MUTEX(mlx5_roce_en_lock); @@ -1160,6 +1161,6 @@ EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); */ u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev) { - return MLX5_SPECIAL_VPORTS(dev) + mlx5_core_max_vfs(dev); + return MLX5_SPECIAL_VPORTS(dev) + mlx5_core_max_vfs(dev) + mlx5_sf_max_functions(dev); } EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 41424ee909a0..cf111e73f81e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -4309,11 +4309,18 @@ static int mlxsw_sp_nexthop_obj_validate(struct mlxsw_sp *mlxsw_sp, if (event != NEXTHOP_EVENT_REPLACE) return 0; - if (!info->is_grp) + switch (info->type) { + case NH_NOTIFIER_INFO_TYPE_SINGLE: return mlxsw_sp_nexthop_obj_single_validate(mlxsw_sp, info->nh, info->extack); - return mlxsw_sp_nexthop_obj_group_validate(mlxsw_sp, info->nh_grp, - info->extack); + case NH_NOTIFIER_INFO_TYPE_GRP: + return mlxsw_sp_nexthop_obj_group_validate(mlxsw_sp, + info->nh_grp, + info->extack); + default: + NL_SET_ERR_MSG_MOD(info->extack, "Unsupported nexthop type"); + return -EOPNOTSUPP; + } } static bool mlxsw_sp_nexthop_obj_is_gateway(struct mlxsw_sp *mlxsw_sp, @@ -4321,13 +4328,17 @@ static bool mlxsw_sp_nexthop_obj_is_gateway(struct mlxsw_sp *mlxsw_sp, { const struct net_device *dev; - if (info->is_grp) + switch (info->type) { + case NH_NOTIFIER_INFO_TYPE_SINGLE: + dev = info->nh->dev; + return info->nh->gw_family || info->nh->is_reject || + mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL); + case NH_NOTIFIER_INFO_TYPE_GRP: /* Already validated earlier. */ return true; - - dev = info->nh->dev; - return info->nh->gw_family || info->nh->is_reject || - mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL); + default: + return false; + } } static void mlxsw_sp_nexthop_obj_blackhole_init(struct mlxsw_sp *mlxsw_sp, @@ -4410,11 +4421,22 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct nh_notifier_info *info) { - unsigned int nhs = info->is_grp ? info->nh_grp->num_nh : 1; struct mlxsw_sp_nexthop_group_info *nhgi; struct mlxsw_sp_nexthop *nh; + unsigned int nhs; int err, i; + switch (info->type) { + case NH_NOTIFIER_INFO_TYPE_SINGLE: + nhs = 1; + break; + case NH_NOTIFIER_INFO_TYPE_GRP: + nhs = info->nh_grp->num_nh; + break; + default: + return -EINVAL; + } + nhgi = kzalloc(struct_size(nhgi, nexthops, nhs), GFP_KERNEL); if (!nhgi) return -ENOMEM; @@ -4427,12 +4449,18 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, int weight; nh = &nhgi->nexthops[i]; - if (info->is_grp) { - nh_obj = &info->nh_grp->nh_entries[i].nh; - weight = info->nh_grp->nh_entries[i].weight; - } else { + switch (info->type) { + case NH_NOTIFIER_INFO_TYPE_SINGLE: nh_obj = info->nh; weight = 1; + break; + case NH_NOTIFIER_INFO_TYPE_GRP: + nh_obj = &info->nh_grp->nh_entries[i].nh; + weight = info->nh_grp->nh_entries[i].weight; + break; + default: + err = -EINVAL; + goto err_nexthop_obj_init; } err = mlxsw_sp_nexthop_obj_init(mlxsw_sp, nh_grp, nh, nh_obj, weight); @@ -4960,6 +4988,7 @@ mlxsw_sp_fib4_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, fib_alias_hw_flags_set(mlxsw_sp_net(mlxsw_sp), &fri); } +#if IS_ENABLED(CONFIG_IPV6) static void mlxsw_sp_fib6_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) @@ -4976,10 +5005,18 @@ mlxsw_sp_fib6_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp, fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, common); list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) - fib6_info_hw_flags_set(mlxsw_sp_rt6->rt, should_offload, - !should_offload); + fib6_info_hw_flags_set(mlxsw_sp_net(mlxsw_sp), mlxsw_sp_rt6->rt, + should_offload, !should_offload); +} +#else +static void +mlxsw_sp_fib6_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ } +#endif +#if IS_ENABLED(CONFIG_IPV6) static void mlxsw_sp_fib6_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) @@ -4990,8 +5027,16 @@ mlxsw_sp_fib6_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, common); list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) - fib6_info_hw_flags_set(mlxsw_sp_rt6->rt, false, false); + fib6_info_hw_flags_set(mlxsw_sp_net(mlxsw_sp), mlxsw_sp_rt6->rt, + false, false); } +#else +static void +mlxsw_sp_fib6_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ +} +#endif static void mlxsw_sp_fib_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index c6c5826aba41..1892cea05ee7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -157,6 +157,7 @@ mlxsw_sp1_span_entry_cpu_deconfigure(struct mlxsw_sp_span_entry *span_entry) static const struct mlxsw_sp_span_entry_ops mlxsw_sp1_span_entry_ops_cpu = { + .is_static = true, .can_handle = mlxsw_sp1_span_cpu_can_handle, .parms_set = mlxsw_sp1_span_entry_cpu_parms, .configure = mlxsw_sp1_span_entry_cpu_configure, @@ -214,6 +215,7 @@ mlxsw_sp_span_entry_phys_deconfigure(struct mlxsw_sp_span_entry *span_entry) static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_phys = { + .is_static = true, .can_handle = mlxsw_sp_port_dev_check, .parms_set = mlxsw_sp_span_entry_phys_parms, .configure = mlxsw_sp_span_entry_phys_configure, @@ -721,6 +723,7 @@ mlxsw_sp2_span_entry_cpu_deconfigure(struct mlxsw_sp_span_entry *span_entry) static const struct mlxsw_sp_span_entry_ops mlxsw_sp2_span_entry_ops_cpu = { + .is_static = true, .can_handle = mlxsw_sp2_span_cpu_can_handle, .parms_set = mlxsw_sp2_span_entry_cpu_parms, .configure = mlxsw_sp2_span_entry_cpu_configure, @@ -1036,6 +1039,9 @@ static void mlxsw_sp_span_respin_work(struct work_struct *work) if (!refcount_read(&curr->ref_count)) continue; + if (curr->ops->is_static) + continue; + err = curr->ops->parms_set(mlxsw_sp, curr->to_dev, &sparms); if (err) continue; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index d907718bc8c5..aa1cd409c0e2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -60,6 +60,7 @@ struct mlxsw_sp_span_entry { }; struct mlxsw_sp_span_entry_ops { + bool is_static; bool (*can_handle)(const struct net_device *to_dev); int (*parms_set)(struct mlxsw_sp *mlxsw_sp, const struct net_device *to_dev, diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 3804310c853a..51359ce650bd 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1253,7 +1253,7 @@ static void lan743x_tx_release_desc(struct lan743x_tx *tx, if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_ACTIVE)) goto done; - descriptor_type = (descriptor->data0) & + descriptor_type = le32_to_cpu(descriptor->data0) & TX_DESC_DATA0_DTYPE_MASK_; if (descriptor_type == TX_DESC_DATA0_DTYPE_DATA_) goto clean_up_data_descriptor; @@ -1313,7 +1313,7 @@ static int lan743x_tx_next_index(struct lan743x_tx *tx, int index) static void lan743x_tx_release_completed_descriptors(struct lan743x_tx *tx) { - while ((*tx->head_cpu_ptr) != (tx->last_head)) { + while (le32_to_cpu(*tx->head_cpu_ptr) != (tx->last_head)) { lan743x_tx_release_desc(tx, tx->last_head, false); tx->last_head = lan743x_tx_next_index(tx, tx->last_head); } @@ -1399,10 +1399,10 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx, if (dma_mapping_error(dev, dma_ptr)) return -ENOMEM; - tx_descriptor->data1 = DMA_ADDR_LOW32(dma_ptr); - tx_descriptor->data2 = DMA_ADDR_HIGH32(dma_ptr); - tx_descriptor->data3 = (frame_length << 16) & - TX_DESC_DATA3_FRAME_LENGTH_MSS_MASK_; + tx_descriptor->data1 = cpu_to_le32(DMA_ADDR_LOW32(dma_ptr)); + tx_descriptor->data2 = cpu_to_le32(DMA_ADDR_HIGH32(dma_ptr)); + tx_descriptor->data3 = cpu_to_le32((frame_length << 16) & + TX_DESC_DATA3_FRAME_LENGTH_MSS_MASK_); buffer_info->skb = NULL; buffer_info->dma_ptr = dma_ptr; @@ -1443,7 +1443,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx, tx->frame_data0 |= TX_DESC_DATA0_IOC_; } tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail]; - tx_descriptor->data0 = tx->frame_data0; + tx_descriptor->data0 = cpu_to_le32(tx->frame_data0); /* move to next descriptor */ tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail); @@ -1487,7 +1487,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx, /* wrap up previous descriptor */ tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail]; - tx_descriptor->data0 = tx->frame_data0; + tx_descriptor->data0 = cpu_to_le32(tx->frame_data0); /* move to next descriptor */ tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail); @@ -1513,10 +1513,10 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx, return -ENOMEM; } - tx_descriptor->data1 = DMA_ADDR_LOW32(dma_ptr); - tx_descriptor->data2 = DMA_ADDR_HIGH32(dma_ptr); - tx_descriptor->data3 = (frame_length << 16) & - TX_DESC_DATA3_FRAME_LENGTH_MSS_MASK_; + tx_descriptor->data1 = cpu_to_le32(DMA_ADDR_LOW32(dma_ptr)); + tx_descriptor->data2 = cpu_to_le32(DMA_ADDR_HIGH32(dma_ptr)); + tx_descriptor->data3 = cpu_to_le32((frame_length << 16) & + TX_DESC_DATA3_FRAME_LENGTH_MSS_MASK_); buffer_info->skb = NULL; buffer_info->dma_ptr = dma_ptr; @@ -1560,7 +1560,7 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx, if (ignore_sync) buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC; - tx_descriptor->data0 = tx->frame_data0; + tx_descriptor->data0 = cpu_to_le32(tx->frame_data0); tx->frame_tail = lan743x_tx_next_index(tx, tx->frame_tail); tx->last_tail = tx->frame_tail; @@ -1967,11 +1967,11 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index, } buffer_info->buffer_length = length; - descriptor->data1 = DMA_ADDR_LOW32(buffer_info->dma_ptr); - descriptor->data2 = DMA_ADDR_HIGH32(buffer_info->dma_ptr); + descriptor->data1 = cpu_to_le32(DMA_ADDR_LOW32(buffer_info->dma_ptr)); + descriptor->data2 = cpu_to_le32(DMA_ADDR_HIGH32(buffer_info->dma_ptr)); descriptor->data3 = 0; - descriptor->data0 = (RX_DESC_DATA0_OWN_ | - (length & RX_DESC_DATA0_BUF_LENGTH_MASK_)); + descriptor->data0 = cpu_to_le32((RX_DESC_DATA0_OWN_ | + (length & RX_DESC_DATA0_BUF_LENGTH_MASK_))); skb_reserve(buffer_info->skb, RX_HEAD_PADDING); lan743x_rx_update_tail(rx, index); @@ -1986,12 +1986,12 @@ static void lan743x_rx_reuse_ring_element(struct lan743x_rx *rx, int index) descriptor = &rx->ring_cpu_ptr[index]; buffer_info = &rx->buffer_info[index]; - descriptor->data1 = DMA_ADDR_LOW32(buffer_info->dma_ptr); - descriptor->data2 = DMA_ADDR_HIGH32(buffer_info->dma_ptr); + descriptor->data1 = cpu_to_le32(DMA_ADDR_LOW32(buffer_info->dma_ptr)); + descriptor->data2 = cpu_to_le32(DMA_ADDR_HIGH32(buffer_info->dma_ptr)); descriptor->data3 = 0; - descriptor->data0 = (RX_DESC_DATA0_OWN_ | + descriptor->data0 = cpu_to_le32((RX_DESC_DATA0_OWN_ | ((buffer_info->buffer_length) & - RX_DESC_DATA0_BUF_LENGTH_MASK_)); + RX_DESC_DATA0_BUF_LENGTH_MASK_))); lan743x_rx_update_tail(rx, index); } @@ -2025,7 +2025,7 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx) { struct skb_shared_hwtstamps *hwtstamps = NULL; int result = RX_PROCESS_RESULT_NOTHING_TO_DO; - int current_head_index = *rx->head_cpu_ptr; + int current_head_index = le32_to_cpu(*rx->head_cpu_ptr); struct lan743x_rx_buffer_info *buffer_info; struct lan743x_rx_descriptor *descriptor; int extension_index = -1; @@ -2040,14 +2040,14 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx) if (rx->last_head != current_head_index) { descriptor = &rx->ring_cpu_ptr[rx->last_head]; - if (descriptor->data0 & RX_DESC_DATA0_OWN_) + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_OWN_) goto done; - if (!(descriptor->data0 & RX_DESC_DATA0_FS_)) + if (!(le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_FS_)) goto done; first_index = rx->last_head; - if (descriptor->data0 & RX_DESC_DATA0_LS_) { + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_LS_) { last_index = rx->last_head; } else { int index; @@ -2055,10 +2055,10 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx) index = lan743x_rx_next_index(rx, first_index); while (index != current_head_index) { descriptor = &rx->ring_cpu_ptr[index]; - if (descriptor->data0 & RX_DESC_DATA0_OWN_) + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_OWN_) goto done; - if (descriptor->data0 & RX_DESC_DATA0_LS_) { + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_LS_) { last_index = index; break; } @@ -2067,17 +2067,17 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx) } if (last_index >= 0) { descriptor = &rx->ring_cpu_ptr[last_index]; - if (descriptor->data0 & RX_DESC_DATA0_EXT_) { + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_EXT_) { /* extension is expected to follow */ int index = lan743x_rx_next_index(rx, last_index); if (index != current_head_index) { descriptor = &rx->ring_cpu_ptr[index]; - if (descriptor->data0 & + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_OWN_) { goto done; } - if (descriptor->data0 & + if (le32_to_cpu(descriptor->data0) & RX_DESC_DATA0_EXT_) { extension_index = index; } else { @@ -2129,7 +2129,7 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx) } buffer_info->skb = NULL; packet_length = RX_DESC_DATA0_FRAME_LENGTH_GET_ - (descriptor->data0); + (le32_to_cpu(descriptor->data0)); skb_put(skb, packet_length - 4); skb->protocol = eth_type_trans(skb, rx->adapter->netdev); @@ -2167,8 +2167,8 @@ process_extension: descriptor = &rx->ring_cpu_ptr[extension_index]; buffer_info = &rx->buffer_info[extension_index]; - ts_sec = descriptor->data1; - ts_nsec = (descriptor->data2 & + ts_sec = le32_to_cpu(descriptor->data1); + ts_nsec = (le32_to_cpu(descriptor->data2) & RX_DESC_DATA2_TS_NS_MASK_); lan743x_rx_reuse_ring_element(rx, extension_index); real_last_index = extension_index; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 404af3f4635e..f3f778910fcc 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -661,7 +661,7 @@ struct lan743x_tx { struct lan743x_tx_buffer_info *buffer_info; - u32 *head_cpu_ptr; + __le32 *head_cpu_ptr; dma_addr_t head_dma_ptr; int last_head; int last_tail; @@ -691,7 +691,7 @@ struct lan743x_rx { struct lan743x_rx_buffer_info *buffer_info; - u32 *head_cpu_ptr; + __le32 *head_cpu_ptr; dma_addr_t head_dma_ptr; u32 last_head; u32 last_tail; @@ -775,10 +775,10 @@ struct lan743x_adapter { #define TX_DESC_DATA3_FRAME_LENGTH_MSS_MASK_ (0x3FFF0000) struct lan743x_tx_descriptor { - u32 data0; - u32 data1; - u32 data2; - u32 data3; + __le32 data0; + __le32 data1; + __le32 data2; + __le32 data3; } __aligned(DEFAULT_DMA_DESCRIPTOR_SPACING); #define TX_BUFFER_INFO_FLAG_ACTIVE BIT(0) @@ -813,10 +813,10 @@ struct lan743x_tx_buffer_info { #define RX_HEAD_PADDING NET_IP_ALIGN struct lan743x_rx_descriptor { - u32 data0; - u32 data1; - u32 data2; - u32 data3; + __le32 data0; + __le32 data1; + __le32 data2; + __le32 data3; } __aligned(DEFAULT_DMA_DESCRIPTOR_SPACING); #define RX_BUFFER_INFO_FLAG_ACTIVE BIT(0) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 5b2c0cea49ea..5f21799ad85b 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -889,10 +889,87 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_get_ts_info); +static u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot) +{ + u32 mask = 0; + int port; + + for (port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + if (!ocelot_port) + continue; + + if (ocelot_port->is_dsa_8021q_cpu) + mask |= BIT(port); + } + + return mask; +} + +void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot) +{ + unsigned long cpu_fwd_mask; + int port; + + /* If a DSA tag_8021q CPU exists, it needs to be included in the + * regular forwarding path of the front ports regardless of whether + * those are bridged or standalone. + * If DSA tag_8021q is not used, this returns 0, which is fine because + * the hardware-based CPU port module can be a destination for packets + * even if it isn't part of PGID_SRC. + */ + cpu_fwd_mask = ocelot_get_dsa_8021q_cpu_mask(ocelot); + + /* Apply FWD mask. The loop is needed to add/remove the current port as + * a source for the other ports. + */ + for (port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + unsigned long mask; + + if (!ocelot_port) { + /* Unused ports can't send anywhere */ + mask = 0; + } else if (ocelot_port->is_dsa_8021q_cpu) { + /* The DSA tag_8021q CPU ports need to be able to + * forward packets to all other ports except for + * themselves + */ + mask = GENMASK(ocelot->num_phys_ports - 1, 0); + mask &= ~cpu_fwd_mask; + } else if (ocelot->bridge_fwd_mask & BIT(port)) { + int lag; + + mask = ocelot->bridge_fwd_mask & ~BIT(port); + + for (lag = 0; lag < ocelot->num_phys_ports; lag++) { + unsigned long bond_mask = ocelot->lags[lag]; + + if (!bond_mask) + continue; + + if (bond_mask & BIT(port)) { + mask &= ~bond_mask; + break; + } + } + } else { + /* Standalone ports forward only to DSA tag_8021q CPU + * ports (if those exist), or to the hardware CPU port + * module otherwise. + */ + mask = cpu_fwd_mask; + } + + ocelot_write_rix(ocelot, mask, ANA_PGID_PGID, PGID_SRC + port); + } +} +EXPORT_SYMBOL(ocelot_apply_bridge_fwd_mask); + void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state) { u32 port_cfg; - int p, i; if (!(BIT(port) & ocelot->bridge_mask)) return; @@ -915,32 +992,7 @@ void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state) ocelot_write_gix(ocelot, port_cfg, ANA_PORT_PORT_CFG, port); - /* Apply FWD mask. The loop is needed to add/remove the current port as - * a source for the other ports. - */ - for (p = 0; p < ocelot->num_phys_ports; p++) { - if (ocelot->bridge_fwd_mask & BIT(p)) { - unsigned long mask = ocelot->bridge_fwd_mask & ~BIT(p); - - for (i = 0; i < ocelot->num_phys_ports; i++) { - unsigned long bond_mask = ocelot->lags[i]; - - if (!bond_mask) - continue; - - if (bond_mask & BIT(p)) { - mask &= ~bond_mask; - break; - } - } - - ocelot_write_rix(ocelot, mask, - ANA_PGID_PGID, PGID_SRC + p); - } else { - ocelot_write_rix(ocelot, 0, - ANA_PGID_PGID, PGID_SRC + p); - } - } + ocelot_apply_bridge_fwd_mask(ocelot); } EXPORT_SYMBOL(ocelot_bridge_stp_state_set); @@ -1297,6 +1349,7 @@ int ocelot_port_lag_join(struct ocelot *ocelot, int port, } ocelot_setup_lag(ocelot, lag); + ocelot_apply_bridge_fwd_mask(ocelot); ocelot_set_aggr_pgids(ocelot); return 0; @@ -1330,6 +1383,7 @@ void ocelot_port_lag_leave(struct ocelot *ocelot, int port, ocelot_write_gix(ocelot, port_cfg | ANA_PORT_PORT_CFG_PORTID_VAL(port), ANA_PORT_PORT_CFG, port); + ocelot_apply_bridge_fwd_mask(ocelot); ocelot_set_aggr_pgids(ocelot); } EXPORT_SYMBOL(ocelot_port_lag_leave); @@ -1350,9 +1404,9 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) if (port == ocelot->npi) { maxlen += OCELOT_TAG_LEN; - if (ocelot->inj_prefix == OCELOT_TAG_PREFIX_SHORT) + if (ocelot->npi_inj_prefix == OCELOT_TAG_PREFIX_SHORT) maxlen += OCELOT_SHORT_PREFIX_LEN; - else if (ocelot->inj_prefix == OCELOT_TAG_PREFIX_LONG) + else if (ocelot->npi_inj_prefix == OCELOT_TAG_PREFIX_LONG) maxlen += OCELOT_LONG_PREFIX_LEN; } @@ -1382,9 +1436,9 @@ int ocelot_get_max_mtu(struct ocelot *ocelot, int port) if (port == ocelot->npi) { max_mtu -= OCELOT_TAG_LEN; - if (ocelot->inj_prefix == OCELOT_TAG_PREFIX_SHORT) + if (ocelot->npi_inj_prefix == OCELOT_TAG_PREFIX_SHORT) max_mtu -= OCELOT_SHORT_PREFIX_LEN; - else if (ocelot->inj_prefix == OCELOT_TAG_PREFIX_LONG) + else if (ocelot->npi_inj_prefix == OCELOT_TAG_PREFIX_LONG) max_mtu -= OCELOT_LONG_PREFIX_LEN; } @@ -1469,9 +1523,9 @@ static void ocelot_cpu_port_init(struct ocelot *ocelot) ocelot_fields_write(ocelot, cpu, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); /* CPU port Injection/Extraction configuration */ ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_XTR_HDR, - ocelot->xtr_prefix); + OCELOT_TAG_PREFIX_NONE); ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_INJ_HDR, - ocelot->inj_prefix); + OCELOT_TAG_PREFIX_NONE); /* 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_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 729495a1a77e..c3ac026f6aea 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -622,7 +622,8 @@ static int ocelot_flower_parse(struct ocelot *ocelot, int port, bool ingress, int ret; filter->prio = f->common.prio; - filter->id = f->cookie; + filter->id.cookie = f->cookie; + filter->id.tc_offload = true; ret = ocelot_flower_parse_action(ocelot, port, ingress, f, filter); if (ret) @@ -717,7 +718,7 @@ int ocelot_cls_flower_destroy(struct ocelot *ocelot, int port, block = &ocelot->block[block_id]; - filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie); + filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie, true); if (!filter) return 0; @@ -741,7 +742,7 @@ int ocelot_cls_flower_stats(struct ocelot *ocelot, int port, block = &ocelot->block[block_id]; - filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie); + filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie, true); if (!filter || filter->type == OCELOT_VCAP_FILTER_DUMMY) return 0; diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 9553eb3e441c..05142803a463 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -9,6 +9,7 @@ */ #include <linux/if_bridge.h> +#include <net/pkt_cls.h> #include "ocelot.h" #include "ocelot_vcap.h" diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index d8c778ee6f1b..37a232911395 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -959,6 +959,12 @@ static void ocelot_vcap_filter_add_to_block(struct ocelot *ocelot, list_add(&filter->list, pos->prev); } +static bool ocelot_vcap_filter_equal(const struct ocelot_vcap_filter *a, + const struct ocelot_vcap_filter *b) +{ + return !memcmp(&a->id, &b->id, sizeof(struct ocelot_vcap_id)); +} + static int ocelot_vcap_block_get_filter_index(struct ocelot_vcap_block *block, struct ocelot_vcap_filter *filter) { @@ -966,7 +972,7 @@ static int ocelot_vcap_block_get_filter_index(struct ocelot_vcap_block *block, int index = 0; list_for_each_entry(tmp, &block->rules, list) { - if (filter->id == tmp->id) + if (ocelot_vcap_filter_equal(filter, tmp)) return index; index++; } @@ -991,16 +997,19 @@ ocelot_vcap_block_find_filter_by_index(struct ocelot_vcap_block *block, } struct ocelot_vcap_filter * -ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id) +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int cookie, + bool tc_offload) { struct ocelot_vcap_filter *filter; list_for_each_entry(filter, &block->rules, list) - if (filter->id == id) + if (filter->id.tc_offload == tc_offload && + filter->id.cookie == cookie) return filter; return NULL; } +EXPORT_SYMBOL(ocelot_vcap_block_find_filter_by_id); /* If @on=false, then SNAP, ARP, IP and OAM frames will not match on keys based * on destination and source MAC addresses, but only on higher-level protocol @@ -1150,6 +1159,7 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, vcap_entry_set(ocelot, index, filter); return 0; } +EXPORT_SYMBOL(ocelot_vcap_filter_add); static void ocelot_vcap_block_remove_filter(struct ocelot *ocelot, struct ocelot_vcap_block *block, @@ -1160,7 +1170,7 @@ static void ocelot_vcap_block_remove_filter(struct ocelot *ocelot, list_for_each_safe(pos, q, &block->rules) { tmp = list_entry(pos, struct ocelot_vcap_filter, list); - if (tmp->id == filter->id) { + if (ocelot_vcap_filter_equal(filter, tmp)) { if (tmp->block_id == VCAP_IS2 && tmp->action.police_ena) ocelot_vcap_policer_del(ocelot, block, @@ -1204,6 +1214,7 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, return 0; } +EXPORT_SYMBOL(ocelot_vcap_filter_del); int ocelot_vcap_filter_stats_update(struct ocelot *ocelot, struct ocelot_vcap_filter *filter) diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h index 82fd10581a14..523611ccc48f 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.h +++ b/drivers/net/ethernet/mscc/ocelot_vcap.h @@ -7,304 +7,13 @@ #define _MSCC_OCELOT_VCAP_H_ #include "ocelot.h" -#include "ocelot_police.h" -#include <net/sch_generic.h> -#include <net/pkt_cls.h> +#include <soc/mscc/ocelot_vcap.h> +#include <net/flow_offload.h> #define OCELOT_POLICER_DISCARD 0x17f -struct ocelot_ipv4 { - u8 addr[4]; -}; - -enum ocelot_vcap_bit { - OCELOT_VCAP_BIT_ANY, - OCELOT_VCAP_BIT_0, - OCELOT_VCAP_BIT_1 -}; - -struct ocelot_vcap_u8 { - u8 value[1]; - u8 mask[1]; -}; - -struct ocelot_vcap_u16 { - u8 value[2]; - u8 mask[2]; -}; - -struct ocelot_vcap_u24 { - u8 value[3]; - u8 mask[3]; -}; - -struct ocelot_vcap_u32 { - u8 value[4]; - u8 mask[4]; -}; - -struct ocelot_vcap_u40 { - u8 value[5]; - u8 mask[5]; -}; - -struct ocelot_vcap_u48 { - u8 value[6]; - u8 mask[6]; -}; - -struct ocelot_vcap_u64 { - u8 value[8]; - u8 mask[8]; -}; - -struct ocelot_vcap_u128 { - u8 value[16]; - u8 mask[16]; -}; - -struct ocelot_vcap_vid { - u16 value; - u16 mask; -}; - -struct ocelot_vcap_ipv4 { - struct ocelot_ipv4 value; - struct ocelot_ipv4 mask; -}; - -struct ocelot_vcap_udp_tcp { - u16 value; - u16 mask; -}; - -struct ocelot_vcap_port { - u8 value; - u8 mask; -}; - -enum ocelot_vcap_key_type { - OCELOT_VCAP_KEY_ANY, - OCELOT_VCAP_KEY_ETYPE, - OCELOT_VCAP_KEY_LLC, - OCELOT_VCAP_KEY_SNAP, - OCELOT_VCAP_KEY_ARP, - OCELOT_VCAP_KEY_IPV4, - OCELOT_VCAP_KEY_IPV6 -}; - -struct ocelot_vcap_key_vlan { - struct ocelot_vcap_vid vid; /* VLAN ID (12 bit) */ - struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */ - enum ocelot_vcap_bit dei; /* DEI */ - enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */ -}; - -struct ocelot_vcap_key_etype { - struct ocelot_vcap_u48 dmac; - struct ocelot_vcap_u48 smac; - struct ocelot_vcap_u16 etype; - struct ocelot_vcap_u16 data; /* MAC data */ -}; - -struct ocelot_vcap_key_llc { - struct ocelot_vcap_u48 dmac; - struct ocelot_vcap_u48 smac; - - /* LLC header: DSAP at byte 0, SSAP at byte 1, Control at byte 2 */ - struct ocelot_vcap_u32 llc; -}; - -struct ocelot_vcap_key_snap { - struct ocelot_vcap_u48 dmac; - struct ocelot_vcap_u48 smac; - - /* SNAP header: Organization Code at byte 0, Type at byte 3 */ - struct ocelot_vcap_u40 snap; -}; - -struct ocelot_vcap_key_arp { - struct ocelot_vcap_u48 smac; - enum ocelot_vcap_bit arp; /* Opcode ARP/RARP */ - enum ocelot_vcap_bit req; /* Opcode request/reply */ - enum ocelot_vcap_bit unknown; /* Opcode unknown */ - enum ocelot_vcap_bit smac_match; /* Sender MAC matches SMAC */ - enum ocelot_vcap_bit dmac_match; /* Target MAC matches DMAC */ - - /**< Protocol addr. length 4, hardware length 6 */ - enum ocelot_vcap_bit length; - - enum ocelot_vcap_bit ip; /* Protocol address type IP */ - enum ocelot_vcap_bit ethernet; /* Hardware address type Ethernet */ - struct ocelot_vcap_ipv4 sip; /* Sender IP address */ - struct ocelot_vcap_ipv4 dip; /* Target IP address */ -}; - -struct ocelot_vcap_key_ipv4 { - enum ocelot_vcap_bit ttl; /* TTL zero */ - enum ocelot_vcap_bit fragment; /* Fragment */ - enum ocelot_vcap_bit options; /* Header options */ - struct ocelot_vcap_u8 ds; - struct ocelot_vcap_u8 proto; /* Protocol */ - struct ocelot_vcap_ipv4 sip; /* Source IP address */ - struct ocelot_vcap_ipv4 dip; /* Destination IP address */ - struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */ - struct ocelot_vcap_udp_tcp sport; /* UDP/TCP: Source port */ - struct ocelot_vcap_udp_tcp dport; /* UDP/TCP: Destination port */ - enum ocelot_vcap_bit tcp_fin; - enum ocelot_vcap_bit tcp_syn; - enum ocelot_vcap_bit tcp_rst; - enum ocelot_vcap_bit tcp_psh; - enum ocelot_vcap_bit tcp_ack; - enum ocelot_vcap_bit tcp_urg; - enum ocelot_vcap_bit sip_eq_dip; /* SIP equals DIP */ - enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT */ - enum ocelot_vcap_bit seq_zero; /* TCP sequence number is zero */ -}; - -struct ocelot_vcap_key_ipv6 { - struct ocelot_vcap_u8 proto; /* IPv6 protocol */ - struct ocelot_vcap_u128 sip; /* IPv6 source (byte 0-7 ignored) */ - struct ocelot_vcap_u128 dip; /* IPv6 destination (byte 0-7 ignored) */ - enum ocelot_vcap_bit ttl; /* TTL zero */ - struct ocelot_vcap_u8 ds; - struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */ - struct ocelot_vcap_udp_tcp sport; - struct ocelot_vcap_udp_tcp dport; - enum ocelot_vcap_bit tcp_fin; - enum ocelot_vcap_bit tcp_syn; - enum ocelot_vcap_bit tcp_rst; - enum ocelot_vcap_bit tcp_psh; - enum ocelot_vcap_bit tcp_ack; - enum ocelot_vcap_bit tcp_urg; - enum ocelot_vcap_bit sip_eq_dip; /* SIP equals DIP */ - enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT */ - enum ocelot_vcap_bit seq_zero; /* TCP sequence number is zero */ -}; - -enum ocelot_mask_mode { - OCELOT_MASK_MODE_NONE, - OCELOT_MASK_MODE_PERMIT_DENY, - OCELOT_MASK_MODE_POLICY, - OCELOT_MASK_MODE_REDIRECT, -}; - -enum ocelot_es0_tag { - OCELOT_NO_ES0_TAG, - OCELOT_ES0_TAG, - OCELOT_FORCE_PORT_TAG, - OCELOT_FORCE_UNTAG, -}; - -enum ocelot_tag_tpid_sel { - OCELOT_TAG_TPID_SEL_8021Q, - OCELOT_TAG_TPID_SEL_8021AD, -}; - -struct ocelot_vcap_action { - union { - /* VCAP ES0 */ - struct { - enum ocelot_es0_tag push_outer_tag; - enum ocelot_es0_tag push_inner_tag; - enum ocelot_tag_tpid_sel tag_a_tpid_sel; - int tag_a_vid_sel; - int tag_a_pcp_sel; - u16 vid_a_val; - u8 pcp_a_val; - u8 dei_a_val; - enum ocelot_tag_tpid_sel tag_b_tpid_sel; - int tag_b_vid_sel; - int tag_b_pcp_sel; - u16 vid_b_val; - u8 pcp_b_val; - u8 dei_b_val; - }; - - /* VCAP IS1 */ - struct { - bool vid_replace_ena; - u16 vid; - bool vlan_pop_cnt_ena; - int vlan_pop_cnt; - bool pcp_dei_ena; - u8 pcp; - u8 dei; - bool qos_ena; - u8 qos_val; - u8 pag_override_mask; - u8 pag_val; - }; - - /* VCAP IS2 */ - struct { - bool cpu_copy_ena; - u8 cpu_qu_num; - enum ocelot_mask_mode mask_mode; - unsigned long port_mask; - bool police_ena; - struct ocelot_policer pol; - u32 pol_ix; - }; - }; -}; - -struct ocelot_vcap_stats { - u64 bytes; - u64 pkts; - u64 used; -}; - -enum ocelot_vcap_filter_type { - OCELOT_VCAP_FILTER_DUMMY, - OCELOT_VCAP_FILTER_PAG, - OCELOT_VCAP_FILTER_OFFLOAD, -}; - -struct ocelot_vcap_filter { - struct list_head list; - - enum ocelot_vcap_filter_type type; - int block_id; - int goto_target; - int lookup; - u8 pag; - u16 prio; - u32 id; - - struct ocelot_vcap_action action; - struct ocelot_vcap_stats stats; - /* For VCAP IS1 and IS2 */ - unsigned long ingress_port_mask; - /* For VCAP ES0 */ - struct ocelot_vcap_port ingress_port; - struct ocelot_vcap_port egress_port; - - enum ocelot_vcap_bit dmac_mc; - enum ocelot_vcap_bit dmac_bc; - struct ocelot_vcap_key_vlan vlan; - - enum ocelot_vcap_key_type key_type; - union { - /* OCELOT_VCAP_KEY_ANY: No specific fields */ - struct ocelot_vcap_key_etype etype; - struct ocelot_vcap_key_llc llc; - struct ocelot_vcap_key_snap snap; - struct ocelot_vcap_key_arp arp; - struct ocelot_vcap_key_ipv4 ipv4; - struct ocelot_vcap_key_ipv6 ipv6; - } key; -}; - -int ocelot_vcap_filter_add(struct ocelot *ocelot, - struct ocelot_vcap_filter *rule, - struct netlink_ext_ack *extack); -int ocelot_vcap_filter_del(struct ocelot *ocelot, - struct ocelot_vcap_filter *rule); int ocelot_vcap_filter_stats_update(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); -struct ocelot_vcap_filter * -ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id); void ocelot_detect_vcap_constants(struct ocelot *ocelot); int ocelot_vcap_init(struct ocelot *ocelot); diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 30a38df08a21..407244fe5b17 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -1347,8 +1347,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ocelot->num_flooding_pgids = 1; ocelot->vcap = vsc7514_vcap_props; - ocelot->inj_prefix = OCELOT_TAG_PREFIX_NONE; - ocelot->xtr_prefix = OCELOT_TAG_PREFIX_NONE; ocelot->npi = -1; err = ocelot_init(ocelot); diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index 7be86ef5a584..2728df46ec41 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -63,6 +63,7 @@ enum mac_version { RTL_GIGA_MAC_VER_50, RTL_GIGA_MAC_VER_51, RTL_GIGA_MAC_VER_52, + RTL_GIGA_MAC_VER_53, RTL_GIGA_MAC_VER_60, RTL_GIGA_MAC_VER_61, RTL_GIGA_MAC_VER_63, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 475e6f01ea10..7b053a1f6d59 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -146,6 +146,7 @@ static const struct { [RTL_GIGA_MAC_VER_50] = {"RTL8168ep/8111ep" }, [RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep" }, [RTL_GIGA_MAC_VER_52] = {"RTL8168fp/RTL8117", FIRMWARE_8168FP_3}, + [RTL_GIGA_MAC_VER_53] = {"RTL8168fp/RTL8117", }, [RTL_GIGA_MAC_VER_60] = {"RTL8125A" }, [RTL_GIGA_MAC_VER_61] = {"RTL8125A", FIRMWARE_8125A_3}, /* reserve 62 for CFG_METHOD_4 in the vendor driver */ @@ -696,7 +697,7 @@ static bool rtl_is_8168evl_up(struct rtl8169_private *tp) { return tp->mac_version >= RTL_GIGA_MAC_VER_34 && tp->mac_version != RTL_GIGA_MAC_VER_39 && - tp->mac_version <= RTL_GIGA_MAC_VER_52; + tp->mac_version <= RTL_GIGA_MAC_VER_53; } static bool rtl_supports_eee(struct rtl8169_private *tp) @@ -763,7 +764,9 @@ static bool name ## _check(struct rtl8169_private *tp) static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int type) { /* based on RTL8168FP_OOBMAC_BASE in vendor driver */ - if (tp->mac_version == RTL_GIGA_MAC_VER_52 && type == ERIAR_OOB) + if (type == ERIAR_OOB && + (tp->mac_version == RTL_GIGA_MAC_VER_52 || + tp->mac_version == RTL_GIGA_MAC_VER_53)) *cmd |= 0x7f0 << 18; } @@ -1238,7 +1241,7 @@ static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE; - case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_52: + case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_53: return r8168ep_check_dash(tp) ? RTL_DASH_EP : RTL_DASH_NONE; default: return RTL_DASH_NONE; @@ -1962,6 +1965,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) { 0x7c8, 0x608, RTL_GIGA_MAC_VER_61 }, /* RTL8117 */ + { 0x7cf, 0x54b, RTL_GIGA_MAC_VER_53 }, { 0x7cf, 0x54a, RTL_GIGA_MAC_VER_52 }, /* 8168EP family. */ @@ -2236,7 +2240,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_38: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: @@ -2410,7 +2414,7 @@ DECLARE_RTL_COND(rtl_rxtx_empty_cond_2) static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_52: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42); rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42); break; @@ -3669,6 +3673,7 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_50] = rtl_hw_start_8168ep_2, [RTL_GIGA_MAC_VER_51] = rtl_hw_start_8168ep_3, [RTL_GIGA_MAC_VER_52] = rtl_hw_start_8117, + [RTL_GIGA_MAC_VER_53] = rtl_hw_start_8117, [RTL_GIGA_MAC_VER_60] = rtl_hw_start_8125a_1, [RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2, [RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b, @@ -4007,17 +4012,72 @@ err_out: return -EIO; } -static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp) +static bool rtl_skb_is_udp(struct sk_buff *skb) { + int no = skb_network_offset(skb); + struct ipv6hdr *i6h, _i6h; + struct iphdr *ih, _ih; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + ih = skb_header_pointer(skb, no, sizeof(_ih), &_ih); + return ih && ih->protocol == IPPROTO_UDP; + case htons(ETH_P_IPV6): + i6h = skb_header_pointer(skb, no, sizeof(_i6h), &_i6h); + return i6h && i6h->nexthdr == IPPROTO_UDP; + default: + return false; + } +} + +#define RTL_MIN_PATCH_LEN 47 + +/* see rtl8125_get_patch_pad_len() in r8125 vendor driver */ +static unsigned int rtl8125_quirk_udp_padto(struct rtl8169_private *tp, + struct sk_buff *skb) +{ + unsigned int padto = 0, len = skb->len; + + if (rtl_is_8125(tp) && len < 128 + RTL_MIN_PATCH_LEN && + rtl_skb_is_udp(skb) && skb_transport_header_was_set(skb)) { + unsigned int trans_data_len = skb_tail_pointer(skb) - + skb_transport_header(skb); + + if (trans_data_len >= offsetof(struct udphdr, len) && + trans_data_len < RTL_MIN_PATCH_LEN) { + u16 dest = ntohs(udp_hdr(skb)->dest); + + /* dest is a standard PTP port */ + if (dest == 319 || dest == 320) + padto = len + RTL_MIN_PATCH_LEN - trans_data_len; + } + + if (trans_data_len < sizeof(struct udphdr)) + padto = max_t(unsigned int, padto, + len + sizeof(struct udphdr) - trans_data_len); + } + + return padto; +} + +static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp, + struct sk_buff *skb) +{ + unsigned int padto; + + padto = rtl8125_quirk_udp_padto(tp, skb); + switch (tp->mac_version) { case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_60: case RTL_GIGA_MAC_VER_61: case RTL_GIGA_MAC_VER_63: - return true; + padto = max_t(unsigned int, padto, ETH_ZLEN); default: - return false; + break; } + + return padto; } static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts) @@ -4089,9 +4149,10 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, opts[1] |= transport_offset << TCPHO_SHIFT; } else { - if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp))) - /* eth_skb_pad would free the skb on error */ - return !__skb_put_padto(skb, ETH_ZLEN, false); + unsigned int padto = rtl_quirk_packet_padto(tp, skb); + + /* skb_padto would free the skb on error */ + return !__skb_put_padto(skb, padto, false); } return true; @@ -4268,6 +4329,9 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb, if (skb->len < ETH_ZLEN) features &= ~NETIF_F_CSUM_MASK; + if (rtl_quirk_packet_padto(tp, skb)) + features &= ~NETIF_F_CSUM_MASK; + if (transport_offset > TCPHO_MAX && rtl_chip_supports_csum_v2(tp)) features &= ~NETIF_F_CSUM_MASK; @@ -4605,10 +4669,10 @@ static int rtl8169_close(struct net_device *dev) cancel_work_sync(&tp->wk.work); - phy_disconnect(tp->phydev); - free_irq(pci_irq_vector(pdev, 0), tp); + phy_disconnect(tp->phydev); + dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray, tp->RxPhyAddr); dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray, @@ -5055,7 +5119,7 @@ static void rtl_hw_init_8125(struct rtl8169_private *tp) static void rtl_hw_initialize(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_52: + case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_53: rtl8168ep_stop_cmac(tp); fallthrough; case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48: diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index 913d030d73eb..50f0f621b1aa 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -1358,6 +1358,7 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, [RTL_GIGA_MAC_VER_50] = rtl8168ep_2_hw_phy_config, [RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config, [RTL_GIGA_MAC_VER_52] = rtl8117_hw_phy_config, + [RTL_GIGA_MAC_VER_53] = rtl8117_hw_phy_config, [RTL_GIGA_MAC_VER_60] = rtl8125a_1_hw_phy_config, [RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config, [RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index 82b1c7a5a7a9..ba0e4d2b256a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -129,7 +129,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to set tx_clk\n"); - return ret; + goto err_remove_config_dt; } } } @@ -143,7 +143,7 @@ static int intel_eth_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to set clk_ptp_ref\n"); - return ret; + goto err_remove_config_dt; } } } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 9a6a519426a0..1c9c67b641a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -375,6 +375,7 @@ static int ehl_pse0_common_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->bus_id = 2; + plat->addr64 = 32; return ehl_common_data(pdev, plat); } @@ -406,6 +407,7 @@ static int ehl_pse1_common_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->bus_id = 3; + plat->addr64 = 32; return ehl_common_data(pdev, plat); } @@ -457,6 +459,21 @@ static struct stmmac_pci_info tgl_sgmii1g_info = { .setup = tgl_sgmii_data, }; +static int adls_sgmii_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + plat->bus_id = 1; + plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + + /* SerDes power up and power down are done in BIOS for ADL */ + + return tgl_common_data(pdev, plat); +} + +static struct stmmac_pci_info adls_sgmii1g_info = { + .setup = adls_sgmii_data, +}; + static const struct stmmac_pci_func_data galileo_stmmac_func_data[] = { { .func = 6, @@ -724,6 +741,8 @@ static SIMPLE_DEV_PM_OPS(intel_eth_pm_ops, intel_eth_pci_suspend, #define PCI_DEVICE_ID_INTEL_TGLH_SGMII1G_0_ID 0x43ac #define PCI_DEVICE_ID_INTEL_TGLH_SGMII1G_1_ID 0x43a2 #define PCI_DEVICE_ID_INTEL_TGL_SGMII1G_ID 0xa0ac +#define PCI_DEVICE_ID_INTEL_ADLS_SGMII1G_0_ID 0x7aac +#define PCI_DEVICE_ID_INTEL_ADLS_SGMII1G_1_ID 0x7aad static const struct pci_device_id intel_eth_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, QUARK_ID, &quark_info) }, @@ -739,6 +758,8 @@ static const struct pci_device_id intel_eth_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_info) }, { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_info) }, { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_info) }, + { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0_ID, &adls_sgmii1g_info) }, + { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1_ID, &adls_sgmii1g_info) }, {} }; MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 2a87cfa27ac0..e1a497d3c9ba 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -105,9 +105,43 @@ struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */ u32 processor_masks_entry_size; }; -/* Fwd declaration */ -struct ndis_tcp_ip_checksum_info; -struct ndis_pkt_8021q_info; +struct ndis_tcp_ip_checksum_info { + union { + struct { + u32 is_ipv4:1; + u32 is_ipv6:1; + u32 tcp_checksum:1; + u32 udp_checksum:1; + u32 ip_header_checksum:1; + u32 reserved:11; + u32 tcp_header_offset:10; + } transmit; + struct { + u32 tcp_checksum_failed:1; + u32 udp_checksum_failed:1; + u32 ip_checksum_failed:1; + u32 tcp_checksum_succeeded:1; + u32 udp_checksum_succeeded:1; + u32 ip_checksum_succeeded:1; + u32 loopback:1; + u32 tcp_checksum_value_invalid:1; + u32 ip_checksum_value_invalid:1; + } receive; + u32 value; + }; +}; + +struct ndis_pkt_8021q_info { + union { + struct { + u32 pri:3; /* User Priority */ + u32 cfi:1; /* Canonical Format ID */ + u32 vlanid:12; /* VLAN ID */ + u32 reserved:16; + }; + u32 value; + }; +}; /* * Represent netvsc packet which contains 1 RNDIS and 1 ethernet frame @@ -194,7 +228,8 @@ int netvsc_send(struct net_device *net, struct sk_buff *skb, bool xdp_tx); void netvsc_linkstatus_callback(struct net_device *net, - struct rndis_message *resp); + struct rndis_message *resp, + void *data); int netvsc_recv_callback(struct net_device *net, struct netvsc_device *nvdev, struct netvsc_channel *nvchan); @@ -884,9 +919,10 @@ struct multi_recv_comp { #define NVSP_RSC_MAX 562 /* Max #RSC frags in a vmbus xfer page pkt */ struct nvsc_rsc { - const struct ndis_pkt_8021q_info *vlan; - const struct ndis_tcp_ip_checksum_info *csum_info; - const u32 *hash_info; + struct ndis_pkt_8021q_info vlan; + struct ndis_tcp_ip_checksum_info csum_info; + u32 hash_info; + u8 ppi_flags; /* valid/present bits for the above PPIs */ u8 is_last; /* last RNDIS msg in a vmtransfer_page */ u32 cnt; /* #fragments in an RSC packet */ u32 pktlen; /* Full packet length */ @@ -894,6 +930,10 @@ struct nvsc_rsc { u32 len[NVSP_RSC_MAX]; }; +#define NVSC_RSC_VLAN BIT(0) /* valid/present bit for 'vlan' */ +#define NVSC_RSC_CSUM_INFO BIT(1) /* valid/present bit for 'csum_info' */ +#define NVSC_RSC_HASH_INFO BIT(2) /* valid/present bit for 'hash_info' */ + struct netvsc_stats { u64 packets; u64 bytes; @@ -1002,6 +1042,7 @@ struct net_device_context { struct netvsc_channel { struct vmbus_channel *channel; struct netvsc_device *net_device; + void *recv_buf; /* buffer to copy packets out from the receive buffer */ const struct vmpacket_descriptor *desc; struct napi_struct napi; struct multi_send_data msd; @@ -1234,18 +1275,6 @@ struct rndis_pktinfo_id { u16 pkt_id; }; -struct ndis_pkt_8021q_info { - union { - struct { - u32 pri:3; /* User Priority */ - u32 cfi:1; /* Canonical Format ID */ - u32 vlanid:12; /* VLAN ID */ - u32 reserved:16; - }; - u32 value; - }; -}; - struct ndis_object_header { u8 type; u8 revision; @@ -1436,32 +1465,6 @@ struct ndis_offload_params { }; }; -struct ndis_tcp_ip_checksum_info { - union { - struct { - u32 is_ipv4:1; - u32 is_ipv6:1; - u32 tcp_checksum:1; - u32 udp_checksum:1; - u32 ip_header_checksum:1; - u32 reserved:11; - u32 tcp_header_offset:10; - } transmit; - struct { - u32 tcp_checksum_failed:1; - u32 udp_checksum_failed:1; - u32 ip_checksum_failed:1; - u32 tcp_checksum_succeeded:1; - u32 udp_checksum_succeeded:1; - u32 ip_checksum_succeeded:1; - u32 loopback:1; - u32 tcp_checksum_value_invalid:1; - u32 ip_checksum_value_invalid:1; - } receive; - u32 value; - }; -}; - struct ndis_tcp_lso_info { union { struct { diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 6184e99c7f31..0fba8257fc11 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -131,6 +131,7 @@ static void free_netvsc_device(struct rcu_head *head) for (i = 0; i < VRSS_CHANNEL_MAX; i++) { xdp_rxq_info_unreg(&nvdev->chan_table[i].xdp_rxq); + kfree(nvdev->chan_table[i].recv_buf); vfree(nvdev->chan_table[i].mrc.slots); } @@ -1284,6 +1285,19 @@ static int netvsc_receive(struct net_device *ndev, continue; } + /* We're going to copy (sections of) the packet into nvchan->recv_buf; + * make sure that nvchan->recv_buf is large enough to hold the packet. + */ + if (unlikely(buflen > net_device->recv_section_size)) { + nvchan->rsc.cnt = 0; + status = NVSP_STAT_FAIL; + netif_err(net_device_ctx, rx_err, ndev, + "Packet too big: buflen=%u recv_section_size=%u\n", + buflen, net_device->recv_section_size); + + continue; + } + data = recv_buf + offset; nvchan->rsc.is_last = (i == count - 1); @@ -1535,6 +1549,12 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, for (i = 0; i < VRSS_CHANNEL_MAX; i++) { struct netvsc_channel *nvchan = &net_device->chan_table[i]; + nvchan->recv_buf = kzalloc(device_info->recv_section_size, GFP_KERNEL); + if (nvchan->recv_buf == NULL) { + ret = -ENOMEM; + goto cleanup2; + } + nvchan->channel = device->channel; nvchan->net_device = net_device; u64_stats_init(&nvchan->tx_stats.syncp); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index ac20c432d4d8..8176fa0c8b16 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -743,7 +743,8 @@ static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb, * netvsc_linkstatus_callback - Link up/down notification */ void netvsc_linkstatus_callback(struct net_device *net, - struct rndis_message *resp) + struct rndis_message *resp, + void *data) { struct rndis_indicate_status *indicate = &resp->msg.indicate_status; struct net_device_context *ndev_ctx = netdev_priv(net); @@ -757,6 +758,9 @@ void netvsc_linkstatus_callback(struct net_device *net, return; } + /* Copy the RNDIS indicate status into nvchan->recv_buf */ + memcpy(indicate, data + RNDIS_HEADER_SIZE, sizeof(*indicate)); + /* Update the physical link speed when changing to another vSwitch */ if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) { u32 speed; @@ -771,8 +775,7 @@ void netvsc_linkstatus_callback(struct net_device *net, return; } - speed = *(u32 *)((void *)indicate - + indicate->status_buf_offset) / 10000; + speed = *(u32 *)(data + RNDIS_HEADER_SIZE + indicate->status_buf_offset) / 10000; ndev_ctx->speed = speed; return; } @@ -827,10 +830,11 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, struct xdp_buff *xdp) { struct napi_struct *napi = &nvchan->napi; - const struct ndis_pkt_8021q_info *vlan = nvchan->rsc.vlan; + const struct ndis_pkt_8021q_info *vlan = &nvchan->rsc.vlan; const struct ndis_tcp_ip_checksum_info *csum_info = - nvchan->rsc.csum_info; - const u32 *hash_info = nvchan->rsc.hash_info; + &nvchan->rsc.csum_info; + const u32 *hash_info = &nvchan->rsc.hash_info; + u8 ppi_flags = nvchan->rsc.ppi_flags; struct sk_buff *skb; void *xbuf = xdp->data_hard_start; int i; @@ -874,7 +878,7 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, * We compute it here if the flags are set, because on Linux, the IP * checksum is always checked. */ - if (csum_info && csum_info->receive.ip_checksum_value_invalid && + if ((ppi_flags & NVSC_RSC_CSUM_INFO) && csum_info->receive.ip_checksum_value_invalid && csum_info->receive.ip_checksum_succeeded && skb->protocol == htons(ETH_P_IP)) { /* Check that there is enough space to hold the IP header. */ @@ -886,16 +890,16 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, } /* Do L4 checksum offload if enabled and present. */ - if (csum_info && (net->features & NETIF_F_RXCSUM)) { + if ((ppi_flags & NVSC_RSC_CSUM_INFO) && (net->features & NETIF_F_RXCSUM)) { if (csum_info->receive.tcp_checksum_succeeded || csum_info->receive.udp_checksum_succeeded) skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (hash_info && (net->features & NETIF_F_RXHASH)) + if ((ppi_flags & NVSC_RSC_HASH_INFO) && (net->features & NETIF_F_RXHASH)) skb_set_hash(skb, *hash_info, PKT_HASH_TYPE_L4); - if (vlan) { + if (ppi_flags & NVSC_RSC_VLAN) { u16 vlan_tci = vlan->vlanid | (vlan->pri << VLAN_PRIO_SHIFT) | (vlan->cfi ? VLAN_CFI_MASK : 0); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index c8534b6619b8..6c48a4d62736 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -127,12 +127,13 @@ static void put_rndis_request(struct rndis_device *dev, } static void dump_rndis_message(struct net_device *netdev, - const struct rndis_message *rndis_msg) + const struct rndis_message *rndis_msg, + const void *data) { switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: if (rndis_msg->msg_len - RNDIS_HEADER_SIZE >= sizeof(struct rndis_packet)) { - const struct rndis_packet *pkt = &rndis_msg->msg.pkt; + const struct rndis_packet *pkt = data + RNDIS_HEADER_SIZE; netdev_dbg(netdev, "RNDIS_MSG_PACKET (len %u, " "data offset %u data len %u, # oob %u, " "oob offset %u, oob len %u, pkt offset %u, " @@ -152,7 +153,7 @@ static void dump_rndis_message(struct net_device *netdev, if (rndis_msg->msg_len - RNDIS_HEADER_SIZE >= sizeof(struct rndis_initialize_complete)) { const struct rndis_initialize_complete *init_complete = - &rndis_msg->msg.init_complete; + data + RNDIS_HEADER_SIZE; netdev_dbg(netdev, "RNDIS_MSG_INIT_C " "(len %u, id 0x%x, status 0x%x, major %d, minor %d, " "device flags %d, max xfer size 0x%x, max pkts %u, " @@ -173,7 +174,7 @@ static void dump_rndis_message(struct net_device *netdev, if (rndis_msg->msg_len - RNDIS_HEADER_SIZE >= sizeof(struct rndis_query_complete)) { const struct rndis_query_complete *query_complete = - &rndis_msg->msg.query_complete; + data + RNDIS_HEADER_SIZE; netdev_dbg(netdev, "RNDIS_MSG_QUERY_C " "(len %u, id 0x%x, status 0x%x, buf len %u, " "buf offset %u)\n", @@ -188,7 +189,7 @@ static void dump_rndis_message(struct net_device *netdev, case RNDIS_MSG_SET_C: if (rndis_msg->msg_len - RNDIS_HEADER_SIZE + sizeof(struct rndis_set_complete)) { const struct rndis_set_complete *set_complete = - &rndis_msg->msg.set_complete; + data + RNDIS_HEADER_SIZE; netdev_dbg(netdev, "RNDIS_MSG_SET_C (len %u, id 0x%x, status 0x%x)\n", rndis_msg->msg_len, @@ -201,7 +202,7 @@ static void dump_rndis_message(struct net_device *netdev, if (rndis_msg->msg_len - RNDIS_HEADER_SIZE >= sizeof(struct rndis_indicate_status)) { const struct rndis_indicate_status *indicate_status = - &rndis_msg->msg.indicate_status; + data + RNDIS_HEADER_SIZE; netdev_dbg(netdev, "RNDIS_MSG_INDICATE " "(len %u, status 0x%x, buf len %u, buf offset %u)\n", rndis_msg->msg_len, @@ -286,8 +287,10 @@ static void rndis_set_link_state(struct rndis_device *rdev, static void rndis_filter_receive_response(struct net_device *ndev, struct netvsc_device *nvdev, - const struct rndis_message *resp) + struct rndis_message *resp, + void *data) { + u32 *req_id = &resp->msg.init_complete.req_id; struct rndis_device *dev = nvdev->extension; struct rndis_request *request = NULL; bool found = false; @@ -312,14 +315,16 @@ static void rndis_filter_receive_response(struct net_device *ndev, return; } + /* Copy the request ID into nvchan->recv_buf */ + *req_id = *(u32 *)(data + RNDIS_HEADER_SIZE); + spin_lock_irqsave(&dev->request_lock, flags); list_for_each_entry(request, &dev->req_list, list_ent) { /* * All request/response message contains RequestId as the 1st * field */ - if (request->request_msg.msg.init_req.req_id - == resp->msg.init_complete.req_id) { + if (request->request_msg.msg.init_req.req_id == *req_id) { found = true; break; } @@ -329,8 +334,10 @@ static void rndis_filter_receive_response(struct net_device *ndev, if (found) { if (resp->msg_len <= sizeof(struct rndis_message) + RNDIS_EXT_LEN) { - memcpy(&request->response_msg, resp, - resp->msg_len); + memcpy(&request->response_msg, resp, RNDIS_HEADER_SIZE + sizeof(*req_id)); + memcpy((void *)&request->response_msg + RNDIS_HEADER_SIZE + sizeof(*req_id), + data + RNDIS_HEADER_SIZE + sizeof(*req_id), + resp->msg_len - RNDIS_HEADER_SIZE - sizeof(*req_id)); if (request->request_msg.ndis_msg_type == RNDIS_MSG_QUERY && request->request_msg.msg. query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS) @@ -359,7 +366,7 @@ static void rndis_filter_receive_response(struct net_device *ndev, netdev_err(ndev, "no rndis request found for this response " "(id 0x%x res type 0x%x)\n", - resp->msg.init_complete.req_id, + *req_id, resp->ndis_msg_type); } } @@ -371,7 +378,7 @@ static void rndis_filter_receive_response(struct net_device *ndev, static inline void *rndis_get_ppi(struct net_device *ndev, struct rndis_packet *rpkt, u32 rpkt_len, u32 type, u8 internal, - u32 ppi_size) + u32 ppi_size, void *data) { struct rndis_per_packet_info *ppi; int len; @@ -396,6 +403,8 @@ static inline void *rndis_get_ppi(struct net_device *ndev, ppi = (struct rndis_per_packet_info *)((ulong)rpkt + rpkt->per_pkt_info_offset); + /* Copy the PPIs into nvchan->recv_buf */ + memcpy(ppi, data + RNDIS_HEADER_SIZE + rpkt->per_pkt_info_offset, rpkt->per_pkt_info_len); len = rpkt->per_pkt_info_len; while (len > 0) { @@ -438,10 +447,29 @@ void rsc_add_data(struct netvsc_channel *nvchan, if (cnt) { nvchan->rsc.pktlen += len; } else { - nvchan->rsc.vlan = vlan; - nvchan->rsc.csum_info = csum_info; + /* The data/values pointed by vlan, csum_info and hash_info are shared + * across the different 'fragments' of the RSC packet; store them into + * the packet itself. + */ + if (vlan != NULL) { + memcpy(&nvchan->rsc.vlan, vlan, sizeof(*vlan)); + nvchan->rsc.ppi_flags |= NVSC_RSC_VLAN; + } else { + nvchan->rsc.ppi_flags &= ~NVSC_RSC_VLAN; + } + if (csum_info != NULL) { + memcpy(&nvchan->rsc.csum_info, csum_info, sizeof(*csum_info)); + nvchan->rsc.ppi_flags |= NVSC_RSC_CSUM_INFO; + } else { + nvchan->rsc.ppi_flags &= ~NVSC_RSC_CSUM_INFO; + } nvchan->rsc.pktlen = len; - nvchan->rsc.hash_info = hash_info; + if (hash_info != NULL) { + nvchan->rsc.csum_info = *csum_info; + nvchan->rsc.ppi_flags |= NVSC_RSC_HASH_INFO; + } else { + nvchan->rsc.ppi_flags &= ~NVSC_RSC_HASH_INFO; + } } nvchan->rsc.data[cnt] = data; @@ -453,7 +481,7 @@ static int rndis_filter_receive_data(struct net_device *ndev, struct netvsc_device *nvdev, struct netvsc_channel *nvchan, struct rndis_message *msg, - u32 data_buflen) + void *data, u32 data_buflen) { struct rndis_packet *rndis_pkt = &msg->msg.pkt; const struct ndis_tcp_ip_checksum_info *csum_info; @@ -461,7 +489,6 @@ static int rndis_filter_receive_data(struct net_device *ndev, const struct rndis_pktinfo_id *pktinfo_id; const u32 *hash_info; u32 data_offset, rpkt_len; - void *data; bool rsc_more = false; int ret; @@ -472,6 +499,9 @@ static int rndis_filter_receive_data(struct net_device *ndev, return NVSP_STAT_FAIL; } + /* Copy the RNDIS packet into nvchan->recv_buf */ + memcpy(rndis_pkt, data + RNDIS_HEADER_SIZE, sizeof(*rndis_pkt)); + /* Validate rndis_pkt offset */ if (rndis_pkt->data_offset >= data_buflen - RNDIS_HEADER_SIZE) { netdev_err(ndev, "invalid rndis packet offset: %u\n", @@ -497,18 +527,17 @@ static int rndis_filter_receive_data(struct net_device *ndev, return NVSP_STAT_FAIL; } - vlan = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, IEEE_8021Q_INFO, 0, sizeof(*vlan)); + vlan = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, IEEE_8021Q_INFO, 0, sizeof(*vlan), + data); csum_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, TCPIP_CHKSUM_PKTINFO, 0, - sizeof(*csum_info)); + sizeof(*csum_info), data); hash_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, NBL_HASH_VALUE, 0, - sizeof(*hash_info)); + sizeof(*hash_info), data); pktinfo_id = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, RNDIS_PKTINFO_ID, 1, - sizeof(*pktinfo_id)); - - data = (void *)msg + data_offset; + sizeof(*pktinfo_id), data); /* Identify RSC frags, drop erroneous packets */ if (pktinfo_id && (pktinfo_id->flag & RNDIS_PKTINFO_SUBALLOC)) { @@ -537,7 +566,7 @@ static int rndis_filter_receive_data(struct net_device *ndev, * the data packet to the stack, without the rndis trailer padding */ rsc_add_data(nvchan, vlan, csum_info, hash_info, - data, rndis_pkt->data_len); + data + data_offset, rndis_pkt->data_len); if (rsc_more) return NVSP_STAT_SUCCESS; @@ -559,10 +588,18 @@ int rndis_filter_receive(struct net_device *ndev, void *data, u32 buflen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct rndis_message *rndis_msg = data; + struct rndis_message *rndis_msg = nvchan->recv_buf; + + if (buflen < RNDIS_HEADER_SIZE) { + netdev_err(ndev, "Invalid rndis_msg (buflen: %u)\n", buflen); + return NVSP_STAT_FAIL; + } + + /* Copy the RNDIS msg header into nvchan->recv_buf */ + memcpy(rndis_msg, data, RNDIS_HEADER_SIZE); /* Validate incoming rndis_message packet */ - if (buflen < RNDIS_HEADER_SIZE || rndis_msg->msg_len < RNDIS_HEADER_SIZE || + if (rndis_msg->msg_len < RNDIS_HEADER_SIZE || buflen < rndis_msg->msg_len) { netdev_err(ndev, "Invalid rndis_msg (buflen: %u, msg_len: %u)\n", buflen, rndis_msg->msg_len); @@ -570,22 +607,22 @@ int rndis_filter_receive(struct net_device *ndev, } if (netif_msg_rx_status(net_device_ctx)) - dump_rndis_message(ndev, rndis_msg); + dump_rndis_message(ndev, rndis_msg, data); switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: return rndis_filter_receive_data(ndev, net_dev, nvchan, - rndis_msg, buflen); + rndis_msg, data, buflen); case RNDIS_MSG_INIT_C: case RNDIS_MSG_QUERY_C: case RNDIS_MSG_SET_C: /* completion msgs */ - rndis_filter_receive_response(ndev, net_dev, rndis_msg); + rndis_filter_receive_response(ndev, net_dev, rndis_msg, data); break; case RNDIS_MSG_INDICATE: /* notification msgs */ - netvsc_linkstatus_callback(ndev, rndis_msg); + netvsc_linkstatus_callback(ndev, rndis_msg, data); break; default: netdev_err(ndev, diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index fa63d4dee0ba..ab7022582154 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -59,9 +59,9 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev); static int ifb_open(struct net_device *dev); static int ifb_close(struct net_device *dev); -static void ifb_ri_tasklet(unsigned long _txp) +static void ifb_ri_tasklet(struct tasklet_struct *t) { - struct ifb_q_private *txp = (struct ifb_q_private *)_txp; + struct ifb_q_private *txp = from_tasklet(txp, t, ifb_tasklet); struct netdev_queue *txq; struct sk_buff *skb; @@ -170,8 +170,7 @@ static int ifb_dev_init(struct net_device *dev) __skb_queue_head_init(&txp->tq); u64_stats_init(&txp->rsync); u64_stats_init(&txp->tsync); - tasklet_init(&txp->ifb_tasklet, ifb_ri_tasklet, - (unsigned long)txp); + tasklet_setup(&txp->ifb_tasklet, ifb_ri_tasklet); netif_tx_start_queue(netdev_get_tx_queue(dev, i)); } return 0; diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index f79cf3c327c1..53640447bf12 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -484,7 +484,7 @@ static void gsi_evt_ring_de_alloc_command(struct gsi *gsi, u32 evt_ring_id) static enum gsi_channel_state gsi_channel_state(struct gsi_channel *channel) { u32 channel_id = gsi_channel_id(channel); - void *virt = channel->gsi->virt; + void __iomem *virt = channel->gsi->virt; u32 val; val = ioread32(virt + GSI_CH_C_CNTXT_0_OFFSET(channel_id)); @@ -725,22 +725,38 @@ static void gsi_evt_ring_program(struct gsi *gsi, u32 evt_ring_id) gsi_evt_ring_doorbell(gsi, evt_ring_id, 0); } -/* Return the last (most recent) transaction completed on a channel. */ +/* Find the transaction whose completion indicates a channel is quiesced */ static struct gsi_trans *gsi_channel_trans_last(struct gsi_channel *channel) { struct gsi_trans_info *trans_info = &channel->trans_info; + const struct list_head *list; struct gsi_trans *trans; spin_lock_bh(&trans_info->spinlock); - if (!list_empty(&trans_info->complete)) - trans = list_last_entry(&trans_info->complete, - struct gsi_trans, links); - else if (!list_empty(&trans_info->polled)) - trans = list_last_entry(&trans_info->polled, - struct gsi_trans, links); - else - trans = NULL; + /* There is a small chance a TX transaction got allocated just + * before we disabled transmits, so check for that. + */ + if (channel->toward_ipa) { + list = &trans_info->alloc; + if (!list_empty(list)) + goto done; + list = &trans_info->pending; + if (!list_empty(list)) + goto done; + } + + /* Otherwise (TX or RX) we want to wait for anything that + * has completed, or has been polled but not released yet. + */ + list = &trans_info->complete; + if (!list_empty(list)) + goto done; + list = &trans_info->polled; + if (list_empty(list)) + list = NULL; +done: + trans = list ? list_last_entry(list, struct gsi_trans, links) : NULL; /* Caller will wait for this, so take a reference */ if (trans) @@ -764,24 +780,6 @@ static void gsi_channel_trans_quiesce(struct gsi_channel *channel) } } -/* Stop channel activity. Transactions may not be allocated until thawed. */ -static void gsi_channel_freeze(struct gsi_channel *channel) -{ - gsi_channel_trans_quiesce(channel); - - napi_disable(&channel->napi); - - gsi_irq_ieob_disable_one(channel->gsi, channel->evt_ring_id); -} - -/* Allow transactions to be used on the channel again. */ -static void gsi_channel_thaw(struct gsi_channel *channel) -{ - gsi_irq_ieob_enable_one(channel->gsi, channel->evt_ring_id); - - napi_enable(&channel->napi); -} - /* Program a channel for use */ static void gsi_channel_program(struct gsi_channel *channel, bool doorbell) { @@ -873,31 +871,47 @@ static void gsi_channel_deprogram(struct gsi_channel *channel) /* Nothing to do */ } -/* Start an allocated GSI channel */ -int gsi_channel_start(struct gsi *gsi, u32 channel_id) +static int __gsi_channel_start(struct gsi_channel *channel, bool start) { - struct gsi_channel *channel = &gsi->channel[channel_id]; + struct gsi *gsi = channel->gsi; int ret; + if (!start) + return 0; + mutex_lock(&gsi->mutex); ret = gsi_channel_start_command(channel); mutex_unlock(&gsi->mutex); - gsi_channel_thaw(channel); - return ret; } -/* Stop a started channel */ -int gsi_channel_stop(struct gsi *gsi, u32 channel_id) +/* Start an allocated GSI channel */ +int gsi_channel_start(struct gsi *gsi, u32 channel_id) { struct gsi_channel *channel = &gsi->channel[channel_id]; - u32 retries = GSI_CHANNEL_STOP_RETRIES; int ret; - gsi_channel_freeze(channel); + /* Enable NAPI and the completion interrupt */ + napi_enable(&channel->napi); + gsi_irq_ieob_enable_one(gsi, channel->evt_ring_id); + + ret = __gsi_channel_start(channel, true); + if (ret) { + gsi_irq_ieob_disable_one(gsi, channel->evt_ring_id); + napi_disable(&channel->napi); + } + + return ret; +} + +static int gsi_channel_stop_retry(struct gsi_channel *channel) +{ + u32 retries = GSI_CHANNEL_STOP_RETRIES; + struct gsi *gsi = channel->gsi; + int ret; mutex_lock(&gsi->mutex); @@ -910,13 +924,41 @@ int gsi_channel_stop(struct gsi *gsi, u32 channel_id) mutex_unlock(&gsi->mutex); - /* Thaw the channel if we need to retry (or on error) */ - if (ret) - gsi_channel_thaw(channel); + return ret; +} + +static int __gsi_channel_stop(struct gsi_channel *channel, bool stop) +{ + int ret; + + /* Wait for any underway transactions to complete before stopping. */ + gsi_channel_trans_quiesce(channel); + + ret = stop ? gsi_channel_stop_retry(channel) : 0; + /* Finally, ensure NAPI polling has finished. */ + if (!ret) + napi_synchronize(&channel->napi); return ret; } +/* Stop a started channel */ +int gsi_channel_stop(struct gsi *gsi, u32 channel_id) +{ + struct gsi_channel *channel = &gsi->channel[channel_id]; + int ret; + + /* Only disable the completion interrupt if stop is successful */ + ret = __gsi_channel_stop(channel, true); + if (ret) + return ret; + + gsi_irq_ieob_disable_one(gsi, channel->evt_ring_id); + napi_disable(&channel->napi); + + return 0; +} + /* Reset and reconfigure a channel, (possibly) enabling the doorbell engine */ void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell) { @@ -940,12 +982,7 @@ int gsi_channel_suspend(struct gsi *gsi, u32 channel_id, bool stop) { struct gsi_channel *channel = &gsi->channel[channel_id]; - if (stop) - return gsi_channel_stop(gsi, channel_id); - - gsi_channel_freeze(channel); - - return 0; + return __gsi_channel_stop(channel, stop); } /* Resume a suspended channel (starting will be requested if STOPPED) */ @@ -953,12 +990,7 @@ int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start) { struct gsi_channel *channel = &gsi->channel[channel_id]; - if (start) - return gsi_channel_start(gsi, channel_id); - - gsi_channel_thaw(channel); - - return 0; + return __gsi_channel_start(channel, start); } /** @@ -1400,7 +1432,7 @@ static int gsi_ring_alloc(struct gsi *gsi, struct gsi_ring *ring, u32 count) /* Hardware requires a 2^n ring size, with alignment equal to size */ ring->virt = dma_alloc_coherent(dev, size, &addr, GFP_KERNEL); if (ring->virt && addr % size) { - dma_free_coherent(dev, size, ring->virt, ring->addr); + dma_free_coherent(dev, size, ring->virt, addr); dev_err(dev, "unable to alloc 0x%zx-aligned ring buffer\n", size); return -EINVAL; /* Not a good error value, but distinct */ diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index c6c6a7f6909c..802077631371 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -43,6 +43,7 @@ enum ipa_flag { * @flags: Boolean state flags * @version: IPA hardware version * @pdev: Platform device + * @completion: Used to signal pipeline clear transfer complete * @smp2p: SMP2P information * @clock: IPA clocking information * @table_addr: DMA address of filter/route table content @@ -82,6 +83,7 @@ struct ipa { DECLARE_BITMAP(flags, IPA_FLAG_COUNT); enum ipa_version version; struct platform_device *pdev; + struct completion completion; struct notifier_block nb; void *notifier; struct ipa_smp2p *smp2p; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index 002e51448510..97b50fee6008 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -529,7 +529,7 @@ void ipa_cmd_dma_shared_mem_add(struct gsi_trans *trans, u32 offset, u16 size, direction, opcode); } -static void ipa_cmd_ip_tag_status_add(struct gsi_trans *trans, u64 tag) +static void ipa_cmd_ip_tag_status_add(struct gsi_trans *trans) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); enum ipa_cmd_opcode opcode = IPA_CMD_IP_PACKET_TAG_STATUS; @@ -543,14 +543,14 @@ static void ipa_cmd_ip_tag_status_add(struct gsi_trans *trans, u64 tag) cmd_payload = ipa_cmd_payload_alloc(ipa, &payload_addr); payload = &cmd_payload->ip_packet_tag_status; - payload->tag = u64_encode_bits(tag, IP_PACKET_TAG_STATUS_TAG_FMASK); + payload->tag = le64_encode_bits(0, IP_PACKET_TAG_STATUS_TAG_FMASK); gsi_trans_cmd_add(trans, payload, sizeof(*payload), payload_addr, direction, opcode); } /* Issue a small command TX data transfer */ -static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size) +static void ipa_cmd_transfer_add(struct gsi_trans *trans) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); enum dma_data_direction direction = DMA_TO_DEVICE; @@ -558,8 +558,6 @@ static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size) union ipa_cmd_payload *payload; dma_addr_t payload_addr; - /* assert(size <= sizeof(*payload)); */ - /* Just transfer a zero-filled payload structure */ payload = ipa_cmd_payload_alloc(ipa, &payload_addr); @@ -567,34 +565,53 @@ static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size) direction, opcode); } -void ipa_cmd_tag_process_add(struct gsi_trans *trans) +/* Add immediate commands to a transaction to clear the hardware pipeline */ +void ipa_cmd_pipeline_clear_add(struct gsi_trans *trans) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); struct ipa_endpoint *endpoint; - endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]; + /* This will complete when the transfer is received */ + reinit_completion(&ipa->completion); + /* Issue a no-op register write command (mask 0 means no write) */ ipa_cmd_register_write_add(trans, 0, 0, 0, true); + + /* Send a data packet through the IPA pipeline. The packet_init + * command says to send the next packet directly to the exception + * endpoint without any other IPA processing. The tag_status + * command requests that status be generated on completion of + * that transfer, and that it will be tagged with a value. + * Finally, the transfer command sends a small packet of data + * (instead of a command) using the command endpoint. + */ + endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]; ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); - ipa_cmd_ip_tag_status_add(trans, 0xcba987654321); - ipa_cmd_transfer_add(trans, 4); + ipa_cmd_ip_tag_status_add(trans); + ipa_cmd_transfer_add(trans); } -/* Returns the number of commands required for the tag process */ -u32 ipa_cmd_tag_process_count(void) +/* Returns the number of commands required to clear the pipeline */ +u32 ipa_cmd_pipeline_clear_count(void) { return 4; } -void ipa_cmd_tag_process(struct ipa *ipa) +void ipa_cmd_pipeline_clear_wait(struct ipa *ipa) +{ + wait_for_completion(&ipa->completion); +} + +void ipa_cmd_pipeline_clear(struct ipa *ipa) { - u32 count = ipa_cmd_tag_process_count(); + u32 count = ipa_cmd_pipeline_clear_count(); struct gsi_trans *trans; trans = ipa_cmd_trans_alloc(ipa, count); if (trans) { - ipa_cmd_tag_process_add(trans); + ipa_cmd_pipeline_clear_add(trans); gsi_trans_commit_wait(trans); + ipa_cmd_pipeline_clear_wait(ipa); } else { dev_err(&ipa->pdev->dev, "error allocating %u entry tag transaction\n", count); diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h index 4ed09c486abc..6dd3d35cf315 100644 --- a/drivers/net/ipa/ipa_cmd.h +++ b/drivers/net/ipa/ipa_cmd.h @@ -157,26 +157,30 @@ void ipa_cmd_dma_shared_mem_add(struct gsi_trans *trans, u32 offset, u16 size, dma_addr_t addr, bool toward_ipa); /** - * ipa_cmd_tag_process_add() - Add IPA tag process commands to a transaction + * ipa_cmd_pipeline_clear_add() - Add pipeline clear commands to a transaction * @trans: GSI transaction */ -void ipa_cmd_tag_process_add(struct gsi_trans *trans); +void ipa_cmd_pipeline_clear_add(struct gsi_trans *trans); /** - * ipa_cmd_tag_process_add_count() - Number of commands in a tag process + * ipa_cmd_pipeline_clear_count() - # commands required to clear pipeline * * Return: The number of elements to allocate in a transaction - * to hold tag process commands + * to hold commands to clear the pipeline */ -u32 ipa_cmd_tag_process_count(void); +u32 ipa_cmd_pipeline_clear_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 + * ipa_cmd_pipeline_clear_wait() - Wait pipeline clear to complete + * @ipa: - IPA pointer + */ +void ipa_cmd_pipeline_clear_wait(struct ipa *ipa); + +/** + * ipa_cmd_pipeline_clear() - Clear the hardware pipeline + * @ipa: - IPA pointer */ -void ipa_cmd_tag_process(struct ipa *ipa); +void ipa_cmd_pipeline_clear(struct ipa *ipa); /** * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 688a3dd40510..7a46c790afbe 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -69,8 +69,11 @@ struct ipa_status { }; /* Field masks for struct ipa_status structure fields */ +#define IPA_STATUS_MASK_TAG_VALID_FMASK GENMASK(4, 4) +#define IPA_STATUS_SRC_IDX_FMASK GENMASK(4, 0) #define IPA_STATUS_DST_IDX_FMASK GENMASK(4, 0) #define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK GENMASK(31, 22) +#define IPA_STATUS_FLAGS2_TAG_FMASK GENMASK_ULL(63, 16) #ifdef IPA_VALIDATE @@ -399,7 +402,7 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) * That won't happen, and we could be more precise, but this is fine * for now. We need to end the transaction with a "tag process." */ - count = hweight32(initialized) + ipa_cmd_tag_process_count(); + count = hweight32(initialized) + ipa_cmd_pipeline_clear_count(); trans = ipa_cmd_trans_alloc(ipa, count); if (!trans) { dev_err(&ipa->pdev->dev, @@ -428,11 +431,13 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) ipa_cmd_register_write_add(trans, offset, 0, ~0, false); } - ipa_cmd_tag_process_add(trans); + ipa_cmd_pipeline_clear_add(trans); /* XXX This should have a 1 second timeout */ gsi_trans_commit_wait(trans); + ipa_cmd_pipeline_clear_wait(ipa); + return 0; } @@ -588,7 +593,7 @@ static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) /* Note that HDR_ENDIANNESS indicates big endian header fields */ if (endpoint->data->qmap) - val = cpu_to_be32(IPA_ENDPOINT_QMAP_METADATA_MASK); + val = (__force u32)cpu_to_be32(IPA_ENDPOINT_QMAP_METADATA_MASK); iowrite32(val, endpoint->ipa->reg_virt + offset); } @@ -1164,19 +1169,53 @@ static bool ipa_endpoint_status_skip(struct ipa_endpoint *endpoint, return true; if (!status->pkt_len) return true; - endpoint_id = u32_get_bits(status->endp_dst_idx, - IPA_STATUS_DST_IDX_FMASK); + endpoint_id = u8_get_bits(status->endp_dst_idx, + IPA_STATUS_DST_IDX_FMASK); if (endpoint_id != endpoint->endpoint_id) return true; return false; /* Don't skip this packet, process it */ } +static bool ipa_endpoint_status_tag(struct ipa_endpoint *endpoint, + const struct ipa_status *status) +{ + struct ipa_endpoint *command_endpoint; + struct ipa *ipa = endpoint->ipa; + u32 endpoint_id; + + if (!le16_get_bits(status->mask, IPA_STATUS_MASK_TAG_VALID_FMASK)) + return false; /* No valid tag */ + + /* The status contains a valid tag. We know the packet was sent to + * this endpoint (already verified by ipa_endpoint_status_skip()). + * If the packet came from the AP->command TX endpoint we know + * this packet was sent as part of the pipeline clear process. + */ + endpoint_id = u8_get_bits(status->endp_src_idx, + IPA_STATUS_SRC_IDX_FMASK); + command_endpoint = ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]; + if (endpoint_id == command_endpoint->endpoint_id) { + complete(&ipa->completion); + } else { + dev_err(&ipa->pdev->dev, + "unexpected tagged packet from endpoint %u\n", + endpoint_id); + } + + return true; +} + /* Return whether the status indicates the packet should be dropped */ -static bool ipa_status_drop_packet(const struct ipa_status *status) +static bool ipa_endpoint_status_drop(struct ipa_endpoint *endpoint, + const struct ipa_status *status) { u32 val; + /* If the status indicates a tagged transfer, we'll drop the packet */ + if (ipa_endpoint_status_tag(endpoint, status)) + return true; + /* Deaggregation exceptions we drop; all other types we consume */ if (status->exception) return status->exception == IPA_STATUS_EXCEPTION_DEAGGR; @@ -1213,12 +1252,11 @@ static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, continue; } - /* Compute the amount of buffer space consumed by the - * packet, including the status element. If the hardware - * is configured to pad packet data to an aligned boundary, - * account for that. And if checksum offload is is enabled - * a trailer containing computed checksum information will - * be appended. + /* Compute the amount of buffer space consumed by the packet, + * including the status element. If the hardware is configured + * to pad packet data to an aligned boundary, account for that. + * And if checksum offload is enabled a trailer containing + * computed checksum information will be appended. */ align = endpoint->data->rx.pad_align ? : 1; len = le16_to_cpu(status->pkt_len); @@ -1226,16 +1264,21 @@ static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, if (endpoint->data->checksum) len += sizeof(struct rmnet_map_dl_csum_trailer); - /* Charge the new packet with a proportional fraction of - * the unused space in the original receive buffer. - * XXX Charge a proportion of the *whole* receive buffer? - */ - if (!ipa_status_drop_packet(status)) { - u32 extra = unused * len / total_len; - void *data2 = data + sizeof(*status); - u32 len2 = le16_to_cpu(status->pkt_len); + if (!ipa_endpoint_status_drop(endpoint, status)) { + void *data2; + u32 extra; + u32 len2; /* Client receives only packet data (no status) */ + data2 = data + sizeof(*status); + len2 = le16_to_cpu(status->pkt_len); + + /* Have the true size reflect the extra unused space in + * the original receive buffer. Distribute the "cost" + * proportionately across all aggregated packets in the + * buffer. + */ + extra = DIV_ROUND_CLOSEST(unused * len, total_len); ipa_endpoint_skb_copy(endpoint, data2, len2, extra); } @@ -1564,7 +1607,7 @@ void ipa_endpoint_suspend(struct ipa *ipa) if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); - ipa_cmd_tag_process(ipa); + ipa_cmd_pipeline_clear(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_main.c b/drivers/net/ipa/ipa_main.c index ab0fd5cb4927..c10e7340b031 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -831,6 +831,7 @@ static int ipa_probe(struct platform_device *pdev) dev_set_drvdata(dev, ipa); ipa->clock = clock; ipa->version = data->version; + init_completion(&ipa->completion); ret = ipa_reg_init(ipa); if (ret) diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 0cc3a3374caa..f25029b9ec85 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -336,7 +336,7 @@ static void ipa_imem_exit(struct ipa *ipa) size = iommu_unmap(domain, ipa->imem_iova, ipa->imem_size); if (size != ipa->imem_size) - dev_warn(dev, "unmapped %zu IMEM bytes, expected %lu\n", + dev_warn(dev, "unmapped %zu IMEM bytes, expected %zu\n", size, ipa->imem_size); } else { dev_err(dev, "couldn't get IPA IOMMU domain for IMEM\n"); @@ -440,7 +440,7 @@ static void ipa_smem_exit(struct ipa *ipa) size = iommu_unmap(domain, ipa->smem_iova, ipa->smem_size); if (size != ipa->smem_size) - dev_warn(dev, "unmapped %zu SMEM bytes, expected %lu\n", + dev_warn(dev, "unmapped %zu SMEM bytes, expected %zu\n", size, ipa->smem_size); } else { diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 8801d093135c..6cd50106e611 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -651,8 +651,7 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) } /* Should not reach here */ - WARN_ONCE(true, "ipvlan_queue_xmit() called for mode = [%hx]\n", - port->mode); + WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode); out: kfree_skb(skb); return NET_XMIT_DROP; @@ -749,8 +748,7 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) } /* Should not reach here */ - WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n", - port->mode); + WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode); kfree_skb(skb); return RX_HANDLER_CONSUMED; } diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c index a5a214d29849..4f512531b7d0 100644 --- a/drivers/net/mhi_net.c +++ b/drivers/net/mhi_net.c @@ -25,7 +25,6 @@ struct mhi_net_stats { u64_stats_t tx_bytes; u64_stats_t tx_errors; u64_stats_t tx_dropped; - atomic_t rx_queued; struct u64_stats_sync tx_syncp; struct u64_stats_sync rx_syncp; }; @@ -138,9 +137,9 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev, { struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev); struct sk_buff *skb = mhi_res->buf_addr; - int remaining; + int free_desc_count; - remaining = atomic_dec_return(&mhi_netdev->stats.rx_queued); + free_desc_count = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE); if (unlikely(mhi_res->transaction_status)) { dev_kfree_skb_any(skb); @@ -175,7 +174,7 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev, } /* Refill if RX buffers queue becomes low */ - if (remaining <= mhi_netdev->rx_queue_sz / 2) + if (free_desc_count >= mhi_netdev->rx_queue_sz / 2) schedule_delayed_work(&mhi_netdev->rx_refill, 0); } @@ -222,7 +221,7 @@ static void mhi_net_rx_refill_work(struct work_struct *work) struct sk_buff *skb; int err; - while (atomic_read(&mhi_netdev->stats.rx_queued) < mhi_netdev->rx_queue_sz) { + while (!mhi_queue_is_full(mdev, DMA_FROM_DEVICE)) { skb = netdev_alloc_skb(ndev, size); if (unlikely(!skb)) break; @@ -235,8 +234,6 @@ static void mhi_net_rx_refill_work(struct work_struct *work) break; } - atomic_inc(&mhi_netdev->stats.rx_queued); - /* Do not hog the CPU if rx buffers are consumed faster than * queued (unlikely). */ @@ -244,7 +241,7 @@ static void mhi_net_rx_refill_work(struct work_struct *work) } /* If we're still starved of rx buffers, reschedule later */ - if (unlikely(!atomic_read(&mhi_netdev->stats.rx_queued))) + if (mhi_get_free_desc_count(mdev, DMA_FROM_DEVICE) == mhi_netdev->rx_queue_sz) schedule_delayed_work(&mhi_netdev->rx_refill, HZ / 2); } @@ -273,9 +270,6 @@ static int mhi_net_probe(struct mhi_device *mhi_dev, SET_NETDEV_DEV(ndev, &mhi_dev->dev); SET_NETDEV_DEVTYPE(ndev, &wwan_type); - /* All MHI net channels have 128 ring elements (at least for now) */ - mhi_netdev->rx_queue_sz = 128; - INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work); u64_stats_init(&mhi_netdev->stats.rx_syncp); u64_stats_init(&mhi_netdev->stats.tx_syncp); @@ -285,6 +279,9 @@ static int mhi_net_probe(struct mhi_device *mhi_dev, if (err) goto out_err; + /* Number of transfer descriptors determines size of the queue */ + mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE); + err = register_netdev(ndev); if (err) goto out_err; diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 45d8a7790bd5..1779146926a5 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -31,7 +31,7 @@ struct nsim_fib_entry { u64 max; - u64 num; + atomic64_t num; }; struct nsim_per_fib_data { @@ -46,10 +46,13 @@ struct nsim_fib_data { struct nsim_fib_entry nexthops; struct rhashtable fib_rt_ht; struct list_head fib_rt_list; - spinlock_t fib_lock; /* Protects hashtable, list and accounting */ + struct mutex fib_lock; /* Protects hashtable and list */ struct notifier_block nexthop_nb; struct rhashtable nexthop_ht; struct devlink *devlink; + struct work_struct fib_event_work; + struct list_head fib_event_queue; + spinlock_t fib_event_queue_lock; /* Protects fib event queue list */ }; struct nsim_fib_rt_key { @@ -83,6 +86,22 @@ struct nsim_fib6_rt_nh { struct fib6_info *rt; }; +struct nsim_fib6_event { + struct fib6_info **rt_arr; + unsigned int nrt6; +}; + +struct nsim_fib_event { + struct list_head list; /* node in fib queue */ + union { + struct fib_entry_notifier_info fen_info; + struct nsim_fib6_event fib6_event; + }; + struct nsim_fib_data *data; + unsigned long event; + int family; +}; + static const struct rhashtable_params nsim_fib_rt_ht_params = { .key_offset = offsetof(struct nsim_fib_rt, key), .head_offset = offsetof(struct nsim_fib_rt, ht_node), @@ -128,7 +147,7 @@ u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, return 0; } - return max ? entry->max : entry->num; + return max ? entry->max : atomic64_read(&entry->num); } static void nsim_fib_set_max(struct nsim_fib_data *fib_data, @@ -165,14 +184,12 @@ static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add, int err = 0; if (add) { - if (entry->num < entry->max) { - entry->num++; - } else { + if (!atomic64_add_unless(&entry->num, 1, entry->max)) { err = -ENOSPC; NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib rule entries"); } } else { - entry->num--; + atomic64_dec_if_positive(&entry->num); } return err; @@ -196,20 +213,15 @@ static int nsim_fib_rule_event(struct nsim_fib_data *data, return err; } -static int nsim_fib_account(struct nsim_fib_entry *entry, bool add, - struct netlink_ext_ack *extack) +static int nsim_fib_account(struct nsim_fib_entry *entry, bool add) { int err = 0; if (add) { - if (entry->num < entry->max) { - entry->num++; - } else { + if (!atomic64_add_unless(&entry->num, 1, entry->max)) err = -ENOSPC; - NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); - } } else { - entry->num--; + atomic64_dec_if_positive(&entry->num); } return err; @@ -254,7 +266,7 @@ nsim_fib4_rt_create(struct nsim_fib_data *data, { struct nsim_fib4_rt *fib4_rt; - fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_ATOMIC); + fib4_rt = kzalloc(sizeof(*fib4_rt), GFP_KERNEL); if (!fib4_rt) return NULL; @@ -311,51 +323,52 @@ static void nsim_fib4_rt_hw_flags_set(struct net *net, } static int nsim_fib4_rt_add(struct nsim_fib_data *data, - struct nsim_fib4_rt *fib4_rt, - struct netlink_ext_ack *extack) + struct nsim_fib4_rt *fib4_rt) { struct net *net = devlink_net(data->devlink); int err; - err = nsim_fib_account(&data->ipv4.fib, true, extack); - if (err) - return err; - err = rhashtable_insert_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv4 route"); + if (err) goto err_fib_dismiss; - } + /* Simulate hardware programming latency. */ + msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); return 0; err_fib_dismiss: - nsim_fib_account(&data->ipv4.fib, false, extack); + /* Drop the accounting that was increased from the notification + * context when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + nsim_fib_account(&data->ipv4.fib, false); return err; } static int nsim_fib4_rt_replace(struct nsim_fib_data *data, struct nsim_fib4_rt *fib4_rt, - struct nsim_fib4_rt *fib4_rt_old, - struct netlink_ext_ack *extack) + struct nsim_fib4_rt *fib4_rt_old) { struct net *net = devlink_net(data->devlink); int err; - /* We are replacing a route, so no need to change the accounting. */ + /* We are replacing a route, so need to remove the accounting which + * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + err = nsim_fib_account(&data->ipv4.fib, false); + if (err) + return err; err = rhashtable_replace_fast(&data->fib_rt_ht, &fib4_rt_old->common.ht_node, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv4 route"); + if (err) return err; - } + msleep(1); nsim_fib4_rt_hw_flags_set(net, fib4_rt, true); nsim_fib4_rt_hw_flags_set(net, fib4_rt_old, false); @@ -367,7 +380,6 @@ static int nsim_fib4_rt_replace(struct nsim_fib_data *data, static int nsim_fib4_rt_insert(struct nsim_fib_data *data, struct fib_entry_notifier_info *fen_info) { - struct netlink_ext_ack *extack = fen_info->info.extack; struct nsim_fib4_rt *fib4_rt, *fib4_rt_old; int err; @@ -377,9 +389,9 @@ static int nsim_fib4_rt_insert(struct nsim_fib_data *data, fib4_rt_old = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); if (!fib4_rt_old) - err = nsim_fib4_rt_add(data, fib4_rt, extack); + err = nsim_fib4_rt_add(data, fib4_rt); else - err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old, extack); + err = nsim_fib4_rt_replace(data, fib4_rt, fib4_rt_old); if (err) nsim_fib4_rt_destroy(fib4_rt); @@ -390,7 +402,6 @@ static int nsim_fib4_rt_insert(struct nsim_fib_data *data, static void nsim_fib4_rt_remove(struct nsim_fib_data *data, const struct fib_entry_notifier_info *fen_info) { - struct netlink_ext_ack *extack = fen_info->info.extack; struct nsim_fib4_rt *fib4_rt; fib4_rt = nsim_fib4_rt_lookup(&data->fib_rt_ht, fen_info); @@ -399,19 +410,15 @@ static void nsim_fib4_rt_remove(struct nsim_fib_data *data, rhashtable_remove_fast(&data->fib_rt_ht, &fib4_rt->common.ht_node, nsim_fib_rt_ht_params); - nsim_fib_account(&data->ipv4.fib, false, extack); nsim_fib4_rt_destroy(fib4_rt); } static int nsim_fib4_event(struct nsim_fib_data *data, - struct fib_notifier_info *info, + struct fib_entry_notifier_info *fen_info, unsigned long event) { - struct fib_entry_notifier_info *fen_info; int err = 0; - fen_info = container_of(info, struct fib_entry_notifier_info, info); - switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib4_rt_insert(data, fen_info); @@ -445,7 +452,7 @@ static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, { struct nsim_fib6_rt_nh *fib6_rt_nh; - fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_ATOMIC); + fib6_rt_nh = kzalloc(sizeof(*fib6_rt_nh), GFP_KERNEL); if (!fib6_rt_nh) return -ENOMEM; @@ -457,6 +464,17 @@ static int nsim_fib6_rt_nh_add(struct nsim_fib6_rt *fib6_rt, return 0; } +#if IS_ENABLED(CONFIG_IPV6) +static void nsim_rt6_release(struct fib6_info *rt) +{ + fib6_info_release(rt); +} +#else +static void nsim_rt6_release(struct fib6_info *rt) +{ +} +#endif + static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt, const struct fib6_info *rt) { @@ -468,22 +486,20 @@ static void nsim_fib6_rt_nh_del(struct nsim_fib6_rt *fib6_rt, fib6_rt->nhs--; list_del(&fib6_rt_nh->list); -#if IS_ENABLED(CONFIG_IPV6) - fib6_info_release(fib6_rt_nh->rt); -#endif + nsim_rt6_release(fib6_rt_nh->rt); kfree(fib6_rt_nh); } static struct nsim_fib6_rt * nsim_fib6_rt_create(struct nsim_fib_data *data, - struct fib6_entry_notifier_info *fen6_info) + struct fib6_info **rt_arr, unsigned int nrt6) { - struct fib6_info *iter, *rt = fen6_info->rt; + struct fib6_info *rt = rt_arr[0]; struct nsim_fib6_rt *fib6_rt; int i = 0; int err; - fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_ATOMIC); + fib6_rt = kzalloc(sizeof(*fib6_rt), GFP_KERNEL); if (!fib6_rt) return ERR_PTR(-ENOMEM); @@ -497,32 +513,18 @@ nsim_fib6_rt_create(struct nsim_fib_data *data, */ INIT_LIST_HEAD(&fib6_rt->nh_list); - err = nsim_fib6_rt_nh_add(fib6_rt, rt); - if (err) - goto err_fib_rt_fini; - - if (!fen6_info->nsiblings) - return fib6_rt; - - list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { - if (i == fen6_info->nsiblings) - break; - - err = nsim_fib6_rt_nh_add(fib6_rt, iter); + for (i = 0; i < nrt6; i++) { + err = nsim_fib6_rt_nh_add(fib6_rt, rt_arr[i]); if (err) goto err_fib6_rt_nh_del; - i++; } - WARN_ON_ONCE(i != fen6_info->nsiblings); return fib6_rt; err_fib6_rt_nh_del: - list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings, - fib6_siblings) - nsim_fib6_rt_nh_del(fib6_rt, iter); - nsim_fib6_rt_nh_del(fib6_rt, rt); -err_fib_rt_fini: + for (i--; i >= 0; i--) { + nsim_fib6_rt_nh_del(fib6_rt, rt_arr[i]); + }; nsim_fib_rt_fini(&fib6_rt->common); kfree(fib6_rt); return ERR_PTR(err); @@ -555,127 +557,125 @@ nsim_fib6_rt_lookup(struct rhashtable *fib_rt_ht, const struct fib6_info *rt) } static int nsim_fib6_rt_append(struct nsim_fib_data *data, - struct fib6_entry_notifier_info *fen6_info) + struct nsim_fib6_event *fib6_event) { - struct fib6_info *iter, *rt = fen6_info->rt; + struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; - int i = 0; - int err; + int i, err; fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (WARN_ON_ONCE(!fib6_rt)) return -EINVAL; - err = nsim_fib6_rt_nh_add(fib6_rt, rt); - if (err) - return err; - rt->trap = true; - - if (!fen6_info->nsiblings) - return 0; - - list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { - if (i == fen6_info->nsiblings) - break; - - err = nsim_fib6_rt_nh_add(fib6_rt, iter); + for (i = 0; i < fib6_event->nrt6; i++) { + err = nsim_fib6_rt_nh_add(fib6_rt, fib6_event->rt_arr[i]); if (err) goto err_fib6_rt_nh_del; - iter->trap = true; - i++; + + fib6_event->rt_arr[i]->trap = true; } - WARN_ON_ONCE(i != fen6_info->nsiblings); return 0; err_fib6_rt_nh_del: - list_for_each_entry_continue_reverse(iter, &rt->fib6_siblings, - fib6_siblings) { - iter->trap = false; - nsim_fib6_rt_nh_del(fib6_rt, iter); + for (i--; i >= 0; i--) { + fib6_event->rt_arr[i]->trap = false; + nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); } - rt->trap = false; - nsim_fib6_rt_nh_del(fib6_rt, rt); return err; } -static void nsim_fib6_rt_hw_flags_set(const struct nsim_fib6_rt *fib6_rt, +#if IS_ENABLED(CONFIG_IPV6) +static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, + const struct nsim_fib6_rt *fib6_rt, bool trap) { + struct net *net = devlink_net(data->devlink); struct nsim_fib6_rt_nh *fib6_rt_nh; list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list) - fib6_info_hw_flags_set(fib6_rt_nh->rt, false, trap); + fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap); +} +#else +static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data, + const struct nsim_fib6_rt *fib6_rt, + bool trap) +{ } +#endif static int nsim_fib6_rt_add(struct nsim_fib_data *data, - struct nsim_fib6_rt *fib6_rt, - struct netlink_ext_ack *extack) + struct nsim_fib6_rt *fib6_rt) { int err; - err = nsim_fib_account(&data->ipv6.fib, true, extack); - if (err) - return err; - err = rhashtable_insert_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to insert IPv6 route"); + + if (err) goto err_fib_dismiss; - } - nsim_fib6_rt_hw_flags_set(fib6_rt, true); + msleep(1); + nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); return 0; err_fib_dismiss: - nsim_fib_account(&data->ipv6.fib, false, extack); + /* Drop the accounting that was increased from the notification + * context when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + nsim_fib_account(&data->ipv6.fib, false); return err; } static int nsim_fib6_rt_replace(struct nsim_fib_data *data, struct nsim_fib6_rt *fib6_rt, - struct nsim_fib6_rt *fib6_rt_old, - struct netlink_ext_ack *extack) + struct nsim_fib6_rt *fib6_rt_old) { int err; - /* We are replacing a route, so no need to change the accounting. */ + /* We are replacing a route, so need to remove the accounting which + * was increased when FIB_EVENT_ENTRY_REPLACE was triggered. + */ + err = nsim_fib_account(&data->ipv6.fib, false); + if (err) + return err; + err = rhashtable_replace_fast(&data->fib_rt_ht, &fib6_rt_old->common.ht_node, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to replace IPv6 route"); + + if (err) return err; - } - nsim_fib6_rt_hw_flags_set(fib6_rt, true); + msleep(1); + nsim_fib6_rt_hw_flags_set(data, fib6_rt, true); - nsim_fib6_rt_hw_flags_set(fib6_rt_old, false); + nsim_fib6_rt_hw_flags_set(data, fib6_rt_old, false); nsim_fib6_rt_destroy(fib6_rt_old); return 0; } static int nsim_fib6_rt_insert(struct nsim_fib_data *data, - struct fib6_entry_notifier_info *fen6_info) + struct nsim_fib6_event *fib6_event) { - struct netlink_ext_ack *extack = fen6_info->info.extack; + struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt, *fib6_rt_old; int err; - fib6_rt = nsim_fib6_rt_create(data, fen6_info); + fib6_rt = nsim_fib6_rt_create(data, fib6_event->rt_arr, + fib6_event->nrt6); if (IS_ERR(fib6_rt)) return PTR_ERR(fib6_rt); - fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt); + fib6_rt_old = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt_old) - err = nsim_fib6_rt_add(data, fib6_rt, extack); + err = nsim_fib6_rt_add(data, fib6_rt); else - err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old, extack); + err = nsim_fib6_rt_replace(data, fib6_rt, fib6_rt_old); if (err) nsim_fib6_rt_destroy(fib6_rt); @@ -683,59 +683,100 @@ static int nsim_fib6_rt_insert(struct nsim_fib_data *data, return err; } -static void -nsim_fib6_rt_remove(struct nsim_fib_data *data, - const struct fib6_entry_notifier_info *fen6_info) +static void nsim_fib6_rt_remove(struct nsim_fib_data *data, + struct nsim_fib6_event *fib6_event) { - struct netlink_ext_ack *extack = fen6_info->info.extack; + struct fib6_info *rt = fib6_event->rt_arr[0]; struct nsim_fib6_rt *fib6_rt; + int i; /* Multipath routes are first added to the FIB trie and only then * notified. If we vetoed the addition, we will get a delete * notification for a route we do not have. Therefore, do not warn if * route was not found. */ - fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, fen6_info->rt); + fib6_rt = nsim_fib6_rt_lookup(&data->fib_rt_ht, rt); if (!fib6_rt) return; /* If not all the nexthops are deleted, then only reduce the nexthop * group. */ - if (fen6_info->nsiblings + 1 != fib6_rt->nhs) { - nsim_fib6_rt_nh_del(fib6_rt, fen6_info->rt); + if (fib6_event->nrt6 != fib6_rt->nhs) { + for (i = 0; i < fib6_event->nrt6; i++) + nsim_fib6_rt_nh_del(fib6_rt, fib6_event->rt_arr[i]); return; } rhashtable_remove_fast(&data->fib_rt_ht, &fib6_rt->common.ht_node, nsim_fib_rt_ht_params); - nsim_fib_account(&data->ipv6.fib, false, extack); nsim_fib6_rt_destroy(fib6_rt); } +static int nsim_fib6_event_init(struct nsim_fib6_event *fib6_event, + struct fib6_entry_notifier_info *fen6_info) +{ + struct fib6_info *rt = fen6_info->rt; + struct fib6_info **rt_arr; + struct fib6_info *iter; + unsigned int nrt6; + int i = 0; + + nrt6 = fen6_info->nsiblings + 1; + + rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC); + if (!rt_arr) + return -ENOMEM; + + fib6_event->rt_arr = rt_arr; + fib6_event->nrt6 = nrt6; + + rt_arr[0] = rt; + fib6_info_hold(rt); + + if (!fen6_info->nsiblings) + return 0; + + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { + if (i == fen6_info->nsiblings) + break; + + rt_arr[i + 1] = iter; + fib6_info_hold(iter); + i++; + } + WARN_ON_ONCE(i != fen6_info->nsiblings); + + return 0; +} + +static void nsim_fib6_event_fini(struct nsim_fib6_event *fib6_event) +{ + int i; + + for (i = 0; i < fib6_event->nrt6; i++) + nsim_rt6_release(fib6_event->rt_arr[i]); + kfree(fib6_event->rt_arr); +} + static int nsim_fib6_event(struct nsim_fib_data *data, - struct fib_notifier_info *info, + struct nsim_fib6_event *fib6_event, unsigned long event) { - struct fib6_entry_notifier_info *fen6_info; int err = 0; - fen6_info = container_of(info, struct fib6_entry_notifier_info, info); - - if (fen6_info->rt->fib6_src.plen) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported"); + if (fib6_event->rt_arr[0]->fib6_src.plen) return 0; - } switch (event) { case FIB_EVENT_ENTRY_REPLACE: - err = nsim_fib6_rt_insert(data, fen6_info); + err = nsim_fib6_rt_insert(data, fib6_event); break; case FIB_EVENT_ENTRY_APPEND: - err = nsim_fib6_rt_append(data, fen6_info); + err = nsim_fib6_rt_append(data, fib6_event); break; case FIB_EVENT_ENTRY_DEL: - nsim_fib6_rt_remove(data, fen6_info); + nsim_fib6_rt_remove(data, fib6_event); break; default: break; @@ -744,51 +785,165 @@ static int nsim_fib6_event(struct nsim_fib_data *data, return err; } -static int nsim_fib_event(struct nsim_fib_data *data, - struct fib_notifier_info *info, unsigned long event) +static int nsim_fib_event(struct nsim_fib_event *fib_event) { int err = 0; - switch (info->family) { + switch (fib_event->family) { case AF_INET: - err = nsim_fib4_event(data, info, event); + nsim_fib4_event(fib_event->data, &fib_event->fen_info, + fib_event->event); + fib_info_put(fib_event->fen_info.fi); break; case AF_INET6: - err = nsim_fib6_event(data, info, event); + nsim_fib6_event(fib_event->data, &fib_event->fib6_event, + fib_event->event); + nsim_fib6_event_fini(&fib_event->fib6_event); + break; + } + + return err; +} + +static int nsim_fib4_prepare_event(struct fib_notifier_info *info, + struct nsim_fib_event *fib_event, + unsigned long event) +{ + struct nsim_fib_data *data = fib_event->data; + struct fib_entry_notifier_info *fen_info; + struct netlink_ext_ack *extack; + int err = 0; + + fen_info = container_of(info, struct fib_entry_notifier_info, + info); + fib_event->fen_info = *fen_info; + extack = info->extack; + + switch (event) { + case FIB_EVENT_ENTRY_REPLACE: + err = nsim_fib_account(&data->ipv4.fib, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); + return err; + } + break; + case FIB_EVENT_ENTRY_DEL: + nsim_fib_account(&data->ipv4.fib, false); + break; + } + + /* Take reference on fib_info to prevent it from being + * freed while event is queued. Release it afterwards. + */ + fib_info_hold(fib_event->fen_info.fi); + + return 0; +} + +static int nsim_fib6_prepare_event(struct fib_notifier_info *info, + struct nsim_fib_event *fib_event, + unsigned long event) +{ + struct nsim_fib_data *data = fib_event->data; + struct fib6_entry_notifier_info *fen6_info; + struct netlink_ext_ack *extack; + int err = 0; + + fen6_info = container_of(info, struct fib6_entry_notifier_info, + info); + + err = nsim_fib6_event_init(&fib_event->fib6_event, fen6_info); + if (err) + return err; + + extack = info->extack; + switch (event) { + case FIB_EVENT_ENTRY_REPLACE: + err = nsim_fib_account(&data->ipv6.fib, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported fib entries"); + goto err_fib6_event_fini; + } + break; + case FIB_EVENT_ENTRY_DEL: + nsim_fib_account(&data->ipv6.fib, false); break; } + return 0; + +err_fib6_event_fini: + nsim_fib6_event_fini(&fib_event->fib6_event); return err; } +static int nsim_fib_event_schedule_work(struct nsim_fib_data *data, + struct fib_notifier_info *info, + unsigned long event) +{ + struct nsim_fib_event *fib_event; + int err; + + if (info->family != AF_INET && info->family != AF_INET6) + /* netdevsim does not support 'RTNL_FAMILY_IP6MR' and + * 'RTNL_FAMILY_IPMR' and should ignore them. + */ + return NOTIFY_DONE; + + fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC); + if (!fib_event) + return NOTIFY_BAD; + + fib_event->data = data; + fib_event->event = event; + fib_event->family = info->family; + + switch (info->family) { + case AF_INET: + err = nsim_fib4_prepare_event(info, fib_event, event); + break; + case AF_INET6: + err = nsim_fib6_prepare_event(info, fib_event, event); + break; + } + + if (err) + goto err_fib_prepare_event; + + /* Enqueue the event and trigger the work */ + spin_lock_bh(&data->fib_event_queue_lock); + list_add_tail(&fib_event->list, &data->fib_event_queue); + spin_unlock_bh(&data->fib_event_queue_lock); + schedule_work(&data->fib_event_work); + + return NOTIFY_DONE; + +err_fib_prepare_event: + kfree(fib_event); + return NOTIFY_BAD; +} + static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, void *ptr) { struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, fib_nb); struct fib_notifier_info *info = ptr; - int err = 0; - - /* IPv6 routes can be added via RAs from softIRQ. */ - spin_lock_bh(&data->fib_lock); + int err; switch (event) { case FIB_EVENT_RULE_ADD: case FIB_EVENT_RULE_DEL: err = nsim_fib_rule_event(data, info, event == FIB_EVENT_RULE_ADD); - break; - + return notifier_from_errno(err); case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: - err = nsim_fib_event(data, info, event); - break; + return nsim_fib_event_schedule_work(data, info, event); } - spin_unlock_bh(&data->fib_lock); - - return notifier_from_errno(err); + return NOTIFY_DONE; } static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, @@ -799,7 +954,7 @@ static void nsim_fib4_rt_free(struct nsim_fib_rt *fib_rt, fib4_rt = container_of(fib_rt, struct nsim_fib4_rt, common); nsim_fib4_rt_hw_flags_set(devlink_net(devlink), fib4_rt, false); - nsim_fib_account(&data->ipv4.fib, false, NULL); + nsim_fib_account(&data->ipv4.fib, false); nsim_fib4_rt_destroy(fib4_rt); } @@ -809,8 +964,8 @@ static void nsim_fib6_rt_free(struct nsim_fib_rt *fib_rt, struct nsim_fib6_rt *fib6_rt; fib6_rt = container_of(fib_rt, struct nsim_fib6_rt, common); - nsim_fib6_rt_hw_flags_set(fib6_rt, false); - nsim_fib_account(&data->ipv6.fib, false, NULL); + nsim_fib6_rt_hw_flags_set(data, fib6_rt, false); + nsim_fib_account(&data->ipv6.fib, false); nsim_fib6_rt_destroy(fib6_rt); } @@ -838,6 +993,9 @@ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) fib_nb); struct nsim_fib_rt *fib_rt, *fib_rt_tmp; + /* Flush the work to make sure there is no race with notifications. */ + flush_work(&data->fib_event_work); + /* The notifier block is still not registered, so we do not need to * take any locks here. */ @@ -847,8 +1005,8 @@ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) nsim_fib_rt_free(fib_rt, data); } - data->ipv4.rules.num = 0ULL; - data->ipv6.rules.num = 0ULL; + atomic64_set(&data->ipv4.rules.num, 0ULL); + atomic64_set(&data->ipv6.rules.num, 0ULL); } static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, @@ -860,7 +1018,7 @@ static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL); if (!nexthop) - return NULL; + return ERR_PTR(-ENOMEM); nexthop->id = info->id; @@ -868,15 +1026,20 @@ static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, * occupy. */ - if (!info->is_grp) { + switch (info->type) { + case NH_NOTIFIER_INFO_TYPE_SINGLE: occ = 1; - goto out; + break; + case NH_NOTIFIER_INFO_TYPE_GRP: + for (i = 0; i < info->nh_grp->num_nh; i++) + occ += info->nh_grp->nh_entries[i].weight; + break; + default: + NL_SET_ERR_MSG_MOD(info->extack, "Unsupported nexthop type"); + kfree(nexthop); + return ERR_PTR(-EOPNOTSUPP); } - for (i = 0; i < info->nh_grp->num_nh; i++) - occ += info->nh_grp->nh_entries[i].weight; - -out: nexthop->occ = occ; return nexthop; } @@ -889,22 +1052,28 @@ static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop) static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ, bool add, struct netlink_ext_ack *extack) { - int err = 0; + int i, err = 0; if (add) { - if (data->nexthops.num + occ <= data->nexthops.max) { - data->nexthops.num += occ; - } else { - err = -ENOSPC; - NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops"); - } + for (i = 0; i < occ; i++) + if (!atomic64_add_unless(&data->nexthops.num, 1, + data->nexthops.max)) { + err = -ENOSPC; + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops"); + goto err_num_decrease; + } } else { - if (WARN_ON(occ > data->nexthops.num)) + if (WARN_ON(occ > atomic64_read(&data->nexthops.num))) return -EINVAL; - data->nexthops.num -= occ; + atomic64_sub(occ, &data->nexthops.num); } return err; + +err_num_decrease: + atomic64_sub(i, &data->nexthops.num); + return err; + } static int nsim_nexthop_add(struct nsim_fib_data *data, @@ -972,8 +1141,8 @@ static int nsim_nexthop_insert(struct nsim_fib_data *data, int err; nexthop = nsim_nexthop_create(data, info); - if (!nexthop) - return -ENOMEM; + if (IS_ERR(nexthop)) + return PTR_ERR(nexthop); nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, nsim_nexthop_ht_params); @@ -1097,6 +1266,29 @@ static void nsim_fib_set_max_all(struct nsim_fib_data *data, } } +static void nsim_fib_event_work(struct work_struct *work) +{ + struct nsim_fib_data *data = container_of(work, struct nsim_fib_data, + fib_event_work); + struct nsim_fib_event *fib_event, *next_fib_event; + + LIST_HEAD(fib_event_queue); + + spin_lock_bh(&data->fib_event_queue_lock); + list_splice_init(&data->fib_event_queue, &fib_event_queue); + spin_unlock_bh(&data->fib_event_queue_lock); + + mutex_lock(&data->fib_lock); + list_for_each_entry_safe(fib_event, next_fib_event, &fib_event_queue, + list) { + nsim_fib_event(fib_event); + list_del(&fib_event->list); + kfree(fib_event); + cond_resched(); + } + mutex_unlock(&data->fib_lock); +} + struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, struct netlink_ext_ack *extack) { @@ -1112,12 +1304,16 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, if (err) goto err_data_free; - spin_lock_init(&data->fib_lock); + mutex_init(&data->fib_lock); INIT_LIST_HEAD(&data->fib_rt_list); err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params); if (err) goto err_rhashtable_nexthop_destroy; + INIT_WORK(&data->fib_event_work, nsim_fib_event_work); + INIT_LIST_HEAD(&data->fib_event_queue); + spin_lock_init(&data->fib_event_queue_lock); + nsim_fib_set_max_all(data, devlink); data->nexthop_nb.notifier_call = nsim_nexthop_event_nb; @@ -1161,11 +1357,13 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, err_nexthop_nb_unregister: unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); err_rhashtable_fib_destroy: + flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); err_rhashtable_nexthop_destroy: rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, data); + mutex_destroy(&data->fib_lock); err_data_free: kfree(data); return ERR_PTR(err); @@ -1185,10 +1383,13 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) NSIM_RESOURCE_IPV4_FIB); unregister_fib_notifier(devlink_net(devlink), &data->fib_nb); unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); + flush_work(&data->fib_event_work); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, data); + WARN_ON_ONCE(!list_empty(&data->fib_event_queue)); WARN_ON_ONCE(!list_empty(&data->fib_rt_list)); + mutex_destroy(&data->fib_lock); kfree(data); } diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 3c67ad9951ab..3cfd773ae5f4 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -44,6 +44,17 @@ static void sfp_quirk_2500basex(const struct sfp_eeprom_id *id, phylink_set(modes, 2500baseX_Full); } +static void sfp_quirk_ubnt_uf_instant(const struct sfp_eeprom_id *id, + unsigned long *modes) +{ + /* Ubiquiti U-Fiber Instant module claims that support all transceiver + * types including 10G Ethernet which is not truth. So clear all claimed + * modes and set only one mode which module supports: 1000baseX_Full. + */ + phylink_zero(modes); + phylink_set(modes, 1000baseX_Full); +} + static const struct sfp_quirk sfp_quirks[] = { { // Alcatel Lucent G-010S-P can operate at 2500base-X, but @@ -63,6 +74,10 @@ static const struct sfp_quirk sfp_quirks[] = { .vendor = "HUAWEI", .part = "MA5671A", .modes = sfp_quirk_2500basex, + }, { + .vendor = "UBNT", + .part = "UF-INSTANT", + .modes = sfp_quirk_ubnt_uf_instant, }, }; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index b2a5ed6915fa..7998acc689b7 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -277,8 +277,21 @@ static const struct sff_data sff_data = { static bool sfp_module_supported(const struct sfp_eeprom_id *id) { - return id->base.phys_id == SFF8024_ID_SFP && - id->base.phys_ext_id == SFP_PHYS_EXT_ID_SFP; + if (id->base.phys_id == SFF8024_ID_SFP && + id->base.phys_ext_id == SFP_PHYS_EXT_ID_SFP) + return true; + + /* SFP GPON module Ubiquiti U-Fiber Instant has in its EEPROM stored + * phys id SFF instead of SFP. Therefore mark this module explicitly + * as supported based on vendor name and pn match. + */ + if (id->base.phys_id == SFF8024_ID_SFF_8472 && + id->base.phys_ext_id == SFP_PHYS_EXT_ID_SFP && + !memcmp(id->base.vendor_name, "UBNT ", 16) && + !memcmp(id->base.vendor_pn, "UF-INSTANT ", 16)) + return true; + + return false; } static const struct sff_data sfp_data = { @@ -340,19 +353,11 @@ static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 dev_addr, void *buf, size_t len) { struct i2c_msg msgs[2]; - size_t block_size; + u8 bus_addr = a2 ? 0x51 : 0x50; + size_t block_size = sfp->i2c_block_size; size_t this_len; - u8 bus_addr; int ret; - if (a2) { - block_size = 16; - bus_addr = 0x51; - } else { - block_size = sfp->i2c_block_size; - bus_addr = 0x50; - } - msgs[0].addr = bus_addr; msgs[0].flags = 0; msgs[0].len = 1; @@ -1286,6 +1291,20 @@ static void sfp_hwmon_probe(struct work_struct *work) struct sfp *sfp = container_of(work, struct sfp, hwmon_probe.work); int err, i; + /* hwmon interface needs to access 16bit registers in atomic way to + * guarantee coherency of the diagnostic monitoring data. If it is not + * possible to guarantee coherency because EEPROM is broken in such way + * that does not support atomic 16bit read operation then we have to + * skip registration of hwmon device. + */ + if (sfp->i2c_block_size < 2) { + dev_info(sfp->dev, + "skipping hwmon device registration due to broken EEPROM\n"); + dev_info(sfp->dev, + "diagnostic EEPROM area cannot be read atomically to guarantee data coherency\n"); + return; + } + err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag)); if (err < 0) { if (sfp->hwmon_tries--) { @@ -1702,26 +1721,30 @@ static int sfp_sm_mod_hpower(struct sfp *sfp, bool enable) return 0; } -/* Some modules (Nokia 3FE46541AA) lock up if byte 0x51 is read as a - * single read. Switch back to reading 16 byte blocks unless we have - * a CarlitoxxPro module (rebranded VSOL V2801F). Even more annoyingly, - * some VSOL V2801F have the vendor name changed to OEM. +/* GPON modules based on Realtek RTL8672 and RTL9601C chips (e.g. V-SOL + * V2801F, CarlitoxxPro CPGOS03-0490, Ubiquiti U-Fiber Instant, ...) do + * not support multibyte reads from the EEPROM. Each multi-byte read + * operation returns just one byte of EEPROM followed by zeros. There is + * no way to identify which modules are using Realtek RTL8672 and RTL9601C + * chips. Moreover every OEM of V-SOL V2801F module puts its own vendor + * name and vendor id into EEPROM, so there is even no way to detect if + * module is V-SOL V2801F. Therefore check for those zeros in the read + * data and then based on check switch to reading EEPROM to one byte + * at a time. */ -static int sfp_quirk_i2c_block_size(const struct sfp_eeprom_base *base) +static bool sfp_id_needs_byte_io(struct sfp *sfp, void *buf, size_t len) { - if (!memcmp(base->vendor_name, "VSOL ", 16)) - return 1; - if (!memcmp(base->vendor_name, "OEM ", 16) && - !memcmp(base->vendor_pn, "V2801F ", 16)) - return 1; + size_t i, block_size = sfp->i2c_block_size; - /* Some modules can't cope with long reads */ - return 16; -} + /* Already using byte IO */ + if (block_size == 1) + return false; -static void sfp_quirks_base(struct sfp *sfp, const struct sfp_eeprom_base *base) -{ - sfp->i2c_block_size = sfp_quirk_i2c_block_size(base); + for (i = 1; i < len; i += block_size) { + if (memchr_inv(buf + i, '\0', min(block_size - 1, len - i))) + return false; + } + return true; } static int sfp_cotsworks_fixup_check(struct sfp *sfp, struct sfp_eeprom_id *id) @@ -1765,11 +1788,11 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) u8 check; int ret; - /* Some modules (CarlitoxxPro CPGOS03-0490) do not support multibyte - * reads from the EEPROM, so start by reading the base identifying - * information one byte at a time. + /* Some SFP modules and also some Linux I2C drivers do not like reads + * longer than 16 bytes, so read the EEPROM in chunks of 16 bytes at + * a time. */ - sfp->i2c_block_size = 1; + sfp->i2c_block_size = 16; ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base)); if (ret < 0) { @@ -1783,6 +1806,33 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) return -EAGAIN; } + /* Some SFP modules (e.g. Nokia 3FE46541AA) lock up if read from + * address 0x51 is just one byte at a time. Also SFF-8472 requires + * that EEPROM supports atomic 16bit read operation for diagnostic + * fields, so do not switch to one byte reading at a time unless it + * is really required and we have no other option. + */ + if (sfp_id_needs_byte_io(sfp, &id.base, sizeof(id.base))) { + dev_info(sfp->dev, + "Detected broken RTL8672/RTL9601C emulated EEPROM\n"); + dev_info(sfp->dev, + "Switching to reading EEPROM to one byte at a time\n"); + sfp->i2c_block_size = 1; + + ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base)); + if (ret < 0) { + if (report) + dev_err(sfp->dev, "failed to read EEPROM: %d\n", + ret); + return -EAGAIN; + } + + if (ret != sizeof(id.base)) { + dev_err(sfp->dev, "EEPROM short read: %d\n", ret); + return -EAGAIN; + } + } + /* Cotsworks do not seem to update the checksums when they * do the final programming with the final module part number, * serial number and date code. @@ -1817,9 +1867,6 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) } } - /* Apply any early module-specific quirks */ - sfp_quirks_base(sfp, &id.base); - ret = sfp_read(sfp, false, SFP_CC_BASE + 1, &id.ext, sizeof(id.ext)); if (ret < 0) { if (report) diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 29a0917a81e6..2b66cf301b0e 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -101,7 +101,7 @@ static void ppp_async_input(struct asyncppp *ap, const unsigned char *buf, char *flags, int count); static int ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg); -static void ppp_async_process(unsigned long arg); +static void ppp_async_process(struct tasklet_struct *t); static void async_lcp_peek(struct asyncppp *ap, unsigned char *data, int len, int inbound); @@ -179,7 +179,7 @@ ppp_asynctty_open(struct tty_struct *tty) ap->lcp_fcs = -1; skb_queue_head_init(&ap->rqueue); - tasklet_init(&ap->tsk, ppp_async_process, (unsigned long) ap); + tasklet_setup(&ap->tsk, ppp_async_process); refcount_set(&ap->refcnt, 1); init_completion(&ap->dead); @@ -488,9 +488,9 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) * to the ppp_generic code, and to tell the ppp_generic code * if we can accept more output now. */ -static void ppp_async_process(unsigned long arg) +static void ppp_async_process(struct tasklet_struct *t) { - struct asyncppp *ap = (struct asyncppp *) arg; + struct asyncppp *ap = from_tasklet(ap, t, tsk); struct sk_buff *skb; /* process received packets */ diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 0f338752c38b..86ee5149f4f2 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -90,7 +90,7 @@ static struct sk_buff* ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *); static int ppp_sync_send(struct ppp_channel *chan, struct sk_buff *skb); static int ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg); -static void ppp_sync_process(unsigned long arg); +static void ppp_sync_process(struct tasklet_struct *t); static int ppp_sync_push(struct syncppp *ap); static void ppp_sync_flush_output(struct syncppp *ap); static void ppp_sync_input(struct syncppp *ap, const unsigned char *buf, @@ -177,7 +177,7 @@ ppp_sync_open(struct tty_struct *tty) ap->raccm = ~0U; skb_queue_head_init(&ap->rqueue); - tasklet_init(&ap->tsk, ppp_sync_process, (unsigned long) ap); + tasklet_setup(&ap->tsk, ppp_sync_process); refcount_set(&ap->refcnt, 1); init_completion(&ap->dead_cmp); @@ -480,9 +480,9 @@ ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) * to the ppp_generic code, and to tell the ppp_generic code * if we can accept more output now. */ -static void ppp_sync_process(unsigned long arg) +static void ppp_sync_process(struct tasklet_struct *t) { - struct syncppp *ap = (struct syncppp *) arg; + struct syncppp *ap = from_tasklet(ap, t, tsk); struct sk_buff *skb; /* process received packets */ diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index c19dac21c468..dd7917cab2b1 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -992,7 +992,8 @@ static void __team_compute_features(struct team *team) unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; - list_for_each_entry(port, &team->port_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, TEAM_VLAN_FEATURES); @@ -1006,6 +1007,7 @@ static void __team_compute_features(struct team *team) if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } + rcu_read_unlock(); team->dev->vlan_features = vlan_features; team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | @@ -1020,9 +1022,7 @@ static void __team_compute_features(struct team *team) static void team_compute_features(struct team *team) { - mutex_lock(&team->lock); __team_compute_features(team); - mutex_unlock(&team->lock); netdev_change_features(team->dev); } diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 6aaa0675c28a..a9b551028659 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -969,6 +969,12 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&wwan_info, }, { + /* Cinterion PLS83/PLS63 modem by GEMALTO/THALES */ + USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0069, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index ef6dd012b8c4..31d51346786a 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1213,9 +1213,10 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb) * This needs to be a tasklet otherwise we will * end up recursively calling this function. */ -static void hso_unthrottle_tasklet(unsigned long data) +static void hso_unthrottle_tasklet(struct tasklet_struct *t) { - struct hso_serial *serial = (struct hso_serial *)data; + struct hso_serial *serial = from_tasklet(serial, t, + unthrottle_tasklet); unsigned long flags; spin_lock_irqsave(&serial->serial_lock, flags); @@ -1264,9 +1265,8 @@ static int hso_serial_open(struct tty_struct *tty, struct file *filp) serial->rx_state = RX_IDLE; /* Force default termio settings */ _hso_serial_set_termios(tty, NULL); - tasklet_init(&serial->unthrottle_tasklet, - hso_unthrottle_tasklet, - (unsigned long)serial); + tasklet_setup(&serial->unthrottle_tasklet, + hso_unthrottle_tasklet); result = hso_start_serial_device(serial->parent, GFP_KERNEL); if (result) { hso_stop_serial_device(serial->parent); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index bf243edeb064..e81c5699c952 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3375,9 +3375,9 @@ static void lan78xx_rx_bh(struct lan78xx_net *dev) netif_wake_queue(dev->net); } -static void lan78xx_bh(unsigned long param) +static void lan78xx_bh(struct tasklet_struct *t) { - struct lan78xx_net *dev = (struct lan78xx_net *)param; + struct lan78xx_net *dev = from_tasklet(dev, t, bh); struct sk_buff *skb; struct skb_data *entry; @@ -3655,7 +3655,7 @@ static int lan78xx_probe(struct usb_interface *intf, skb_queue_head_init(&dev->txq_pend); mutex_init(&dev->phy_mutex); - tasklet_init(&dev->bh, lan78xx_bh, (unsigned long)dev); + tasklet_setup(&dev->bh, lan78xx_bh); INIT_DELAYED_WORK(&dev->wq, lan78xx_delayedwork); init_usb_anchor(&dev->deferred); diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 32e1335c94ad..9a907182569c 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -553,12 +553,11 @@ tl_sched: tasklet_schedule(&pegasus->rx_tl); } -static void rx_fixup(unsigned long data) +static void rx_fixup(struct tasklet_struct *t) { - pegasus_t *pegasus; + pegasus_t *pegasus = from_tasklet(pegasus, t, rx_tl); int status; - pegasus = (pegasus_t *) data; if (pegasus->flags & PEGASUS_UNPLUG) return; @@ -1129,7 +1128,7 @@ static int pegasus_probe(struct usb_interface *intf, goto out1; } - tasklet_init(&pegasus->rx_tl, rx_fixup, (unsigned long) pegasus); + tasklet_setup(&pegasus->rx_tl, rx_fixup); INIT_DELAYED_WORK(&pegasus->carrier_check, check_carrier); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 7ea113f51074..c8b2b60d2183 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -57,6 +57,7 @@ struct qmi_wwan_state { enum qmi_wwan_flags { QMI_WWAN_FLAG_RAWIP = 1 << 0, QMI_WWAN_FLAG_MUX = 1 << 1, + QMI_WWAN_FLAG_PASS_THROUGH = 1 << 2, }; enum qmi_wwan_quirks { @@ -218,6 +219,28 @@ skip: return 1; } +static ssize_t mux_id_show(struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_device *dev = to_net_dev(d); + struct qmimux_priv *priv; + + priv = netdev_priv(dev); + + return sysfs_emit(buf, "0x%02x\n", priv->mux_id); +} + +static DEVICE_ATTR_RO(mux_id); + +static struct attribute *qmi_wwan_sysfs_qmimux_attrs[] = { + &dev_attr_mux_id.attr, + NULL, +}; + +static struct attribute_group qmi_wwan_sysfs_qmimux_attr_group = { + .name = "qmap", + .attrs = qmi_wwan_sysfs_qmimux_attrs, +}; + static int qmimux_register_device(struct net_device *real_dev, u8 mux_id) { struct net_device *new_dev; @@ -240,6 +263,8 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id) goto out_free_newdev; } + new_dev->sysfs_groups[0] = &qmi_wwan_sysfs_qmimux_attr_group; + err = register_netdevice(new_dev); if (err < 0) goto out_free_newdev; @@ -326,6 +351,13 @@ static ssize_t raw_ip_store(struct device *d, struct device_attribute *attr, co if (enable == (info->flags & QMI_WWAN_FLAG_RAWIP)) return len; + /* ip mode cannot be cleared when pass through mode is set */ + if (!enable && (info->flags & QMI_WWAN_FLAG_PASS_THROUGH)) { + netdev_err(dev->net, + "Cannot clear ip mode on pass through device\n"); + return -EINVAL; + } + if (!rtnl_trylock()) return restart_syscall(); @@ -456,14 +488,59 @@ err: return ret; } +static ssize_t pass_through_show(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct usbnet *dev = netdev_priv(to_net_dev(d)); + struct qmi_wwan_state *info; + + info = (void *)&dev->data; + return sprintf(buf, "%c\n", + info->flags & QMI_WWAN_FLAG_PASS_THROUGH ? 'Y' : 'N'); +} + +static ssize_t pass_through_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct usbnet *dev = netdev_priv(to_net_dev(d)); + struct qmi_wwan_state *info; + bool enable; + + if (strtobool(buf, &enable)) + return -EINVAL; + + info = (void *)&dev->data; + + /* no change? */ + if (enable == (info->flags & QMI_WWAN_FLAG_PASS_THROUGH)) + return len; + + /* pass through mode can be set for raw ip devices only */ + if (!(info->flags & QMI_WWAN_FLAG_RAWIP)) { + netdev_err(dev->net, + "Cannot set pass through mode on non ip device\n"); + return -EINVAL; + } + + if (enable) + info->flags |= QMI_WWAN_FLAG_PASS_THROUGH; + else + info->flags &= ~QMI_WWAN_FLAG_PASS_THROUGH; + + return len; +} + static DEVICE_ATTR_RW(raw_ip); static DEVICE_ATTR_RW(add_mux); static DEVICE_ATTR_RW(del_mux); +static DEVICE_ATTR_RW(pass_through); static struct attribute *qmi_wwan_sysfs_attrs[] = { &dev_attr_raw_ip.attr, &dev_attr_add_mux.attr, &dev_attr_del_mux.attr, + &dev_attr_pass_through.attr, NULL, }; @@ -510,6 +587,11 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (info->flags & QMI_WWAN_FLAG_MUX) return qmimux_rx_fixup(dev, skb); + if (info->flags & QMI_WWAN_FLAG_PASS_THROUGH) { + skb->protocol = htons(ETH_P_MAP); + return (netif_rx(skb) == NET_RX_SUCCESS); + } + switch (skb->data[0] & 0xf0) { case 0x40: proto = htons(ETH_P_IP); @@ -1303,6 +1385,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)}, /* Olivetti Olicard 160 */ {QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)}, /* Olivetti Olicard 500 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ + {QMI_QUIRK_SET_DTR(0x1e2d, 0x006f, 8)}, /* Cinterion PLS83/PLS63 */ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ {QMI_FIXED_INTF(0x1e2d, 0x0063, 10)}, /* Cinterion ALASxx (1 RmNet) */ {QMI_FIXED_INTF(0x1e2d, 0x0082, 4)}, /* Cinterion PHxx,PXxx (2 RmNet) */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 67cd6986634f..0d7d2938e21d 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2393,11 +2393,9 @@ static void tx_bottom(struct r8152 *tp) } while (res == 0); } -static void bottom_half(unsigned long data) +static void bottom_half(struct tasklet_struct *t) { - struct r8152 *tp; - - tp = (struct r8152 *)data; + struct r8152 *tp = from_tasklet(tp, t, tx_tl); if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; @@ -6714,7 +6712,7 @@ static int rtl8152_probe(struct usb_interface *intf, mutex_init(&tp->control); INIT_DELAYED_WORK(&tp->schedule, rtl_work_func_t); INIT_DELAYED_WORK(&tp->hw_phy_work, rtl_hw_phy_work_func_t); - tasklet_init(&tp->tx_tl, bottom_half, (unsigned long)tp); + tasklet_setup(&tp->tx_tl, bottom_half); tasklet_disable(&tp->tx_tl); netdev->netdev_ops = &rtl8152_netdev_ops; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index bf8a60533f3e..7656f2a3afd9 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -577,9 +577,9 @@ static void free_skb_pool(rtl8150_t *dev) dev_kfree_skb(dev->rx_skb_pool[i]); } -static void rx_fixup(unsigned long data) +static void rx_fixup(struct tasklet_struct *t) { - struct rtl8150 *dev = (struct rtl8150 *)data; + struct rtl8150 *dev = from_tasklet(dev, t, tl); struct sk_buff *skb; int status; @@ -878,7 +878,7 @@ static int rtl8150_probe(struct usb_interface *intf, return -ENOMEM; } - tasklet_init(&dev->tl, rx_fixup, (unsigned long)dev); + tasklet_setup(&dev->tl, rx_fixup); spin_lock_init(&dev->rx_pool_lock); dev->udev = udev; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 336504b7531d..6e87f1fc4874 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -451,12 +451,8 @@ vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq, tq->comp_ring.base, tq->comp_ring.basePA); tq->comp_ring.base = NULL; } - if (tq->buf_info) { - dma_free_coherent(&adapter->pdev->dev, - tq->tx_ring.size * sizeof(tq->buf_info[0]), - tq->buf_info, tq->buf_info_pa); - tq->buf_info = NULL; - } + kfree(tq->buf_info); + tq->buf_info = NULL; } @@ -505,8 +501,6 @@ static int vmxnet3_tq_create(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) { - size_t sz; - BUG_ON(tq->tx_ring.base || tq->data_ring.base || tq->comp_ring.base || tq->buf_info); @@ -534,9 +528,9 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq, goto err; } - sz = tq->tx_ring.size * sizeof(tq->buf_info[0]); - tq->buf_info = dma_alloc_coherent(&adapter->pdev->dev, sz, - &tq->buf_info_pa, GFP_KERNEL); + tq->buf_info = kcalloc_node(tq->tx_ring.size, sizeof(tq->buf_info[0]), + GFP_KERNEL, + dev_to_node(&adapter->pdev->dev)); if (!tq->buf_info) goto err; @@ -1737,13 +1731,9 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, rq->comp_ring.base = NULL; } - if (rq->buf_info[0]) { - size_t sz = sizeof(struct vmxnet3_rx_buf_info) * - (rq->rx_ring[0].size + rq->rx_ring[1].size); - dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0], - rq->buf_info_pa); - rq->buf_info[0] = rq->buf_info[1] = NULL; - } + kfree(rq->buf_info[0]); + rq->buf_info[0] = NULL; + rq->buf_info[1] = NULL; } static void @@ -1883,10 +1873,9 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter) goto err; } - sz = sizeof(struct vmxnet3_rx_buf_info) * (rq->rx_ring[0].size + - rq->rx_ring[1].size); - bi = dma_alloc_coherent(&adapter->pdev->dev, sz, &rq->buf_info_pa, - GFP_KERNEL); + bi = kcalloc_node(rq->rx_ring[0].size + rq->rx_ring[1].size, + sizeof(rq->buf_info[0][0]), GFP_KERNEL, + dev_to_node(&adapter->pdev->dev)); if (!bi) goto err; @@ -2522,14 +2511,12 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) tqc->txRingBasePA = cpu_to_le64(tq->tx_ring.basePA); tqc->dataRingBasePA = cpu_to_le64(tq->data_ring.basePA); tqc->compRingBasePA = cpu_to_le64(tq->comp_ring.basePA); - tqc->ddPA = cpu_to_le64(tq->buf_info_pa); + tqc->ddPA = cpu_to_le64(~0ULL); tqc->txRingSize = cpu_to_le32(tq->tx_ring.size); tqc->dataRingSize = cpu_to_le32(tq->data_ring.size); tqc->txDataRingDescSize = cpu_to_le32(tq->txdata_desc_size); tqc->compRingSize = cpu_to_le32(tq->comp_ring.size); - tqc->ddLen = cpu_to_le32( - sizeof(struct vmxnet3_tx_buf_info) * - tqc->txRingSize); + tqc->ddLen = cpu_to_le32(0); tqc->intrIdx = tq->comp_ring.intr_idx; } @@ -2541,14 +2528,11 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) rqc->rxRingBasePA[0] = cpu_to_le64(rq->rx_ring[0].basePA); rqc->rxRingBasePA[1] = cpu_to_le64(rq->rx_ring[1].basePA); rqc->compRingBasePA = cpu_to_le64(rq->comp_ring.basePA); - rqc->ddPA = cpu_to_le64(rq->buf_info_pa); + rqc->ddPA = cpu_to_le64(~0ULL); rqc->rxRingSize[0] = cpu_to_le32(rq->rx_ring[0].size); rqc->rxRingSize[1] = cpu_to_le32(rq->rx_ring[1].size); rqc->compRingSize = cpu_to_le32(rq->comp_ring.size); - rqc->ddLen = cpu_to_le32( - sizeof(struct vmxnet3_rx_buf_info) * - (rqc->rxRingSize[0] + - rqc->rxRingSize[1])); + rqc->ddLen = cpu_to_le32(0); rqc->intrIdx = rq->comp_ring.intr_idx; if (VMXNET3_VERSION_GE_3(adapter)) { rqc->rxDataRingBasePA = diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index d958b92c9429..e910596b79cf 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -240,7 +240,6 @@ struct vmxnet3_tx_queue { spinlock_t tx_lock; struct vmxnet3_cmd_ring tx_ring; struct vmxnet3_tx_buf_info *buf_info; - dma_addr_t buf_info_pa; struct vmxnet3_tx_data_ring data_ring; struct vmxnet3_comp_ring comp_ring; struct Vmxnet3_TxQueueCtrl *shared; @@ -298,7 +297,6 @@ struct vmxnet3_rx_queue { u32 qid2; /* rqID in RCD for buffer from 2nd ring */ u32 dataRingQid; /* rqID in RCD for buffer from data ring */ struct vmxnet3_rx_buf_info *buf_info[2]; - dma_addr_t buf_info_pa; struct Vmxnet3_RxQueueCtrl *shared; struct vmxnet3_rq_driver_stats stats; } __attribute__((__aligned__(SMP_CACHE_BYTES))); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index 7220fc8fd9b0..8280092066e7 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -314,6 +314,7 @@ const struct iwl_cfg_trans_params iwl_ma_trans_cfg = { const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101"; const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz"; const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz"; +const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203"; const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6 AX211 160MHz"; const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6 AX411 160MHz"; const char iwl_ma_name[] = "Intel(R) Wi-Fi 6"; @@ -340,6 +341,18 @@ const struct iwl_cfg iwl_qu_b0_hr1_b0 = { .num_rbds = IWL_NUM_RBDS_22000_HE, }; +const struct iwl_cfg iwl_qu_b0_hr_b0 = { + .fw_name_pre = IWL_QU_B_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, + .num_rbds = IWL_NUM_RBDS_22000_HE, +}; + const struct iwl_cfg iwl_ax201_cfg_qu_hr = { .name = "Intel(R) Wi-Fi 6 AX201 160MHz", .fw_name_pre = IWL_QU_B_HR_B_FW_PRE, @@ -366,6 +379,18 @@ const struct iwl_cfg iwl_qu_c0_hr1_b0 = { .num_rbds = IWL_NUM_RBDS_22000_HE, }; +const struct iwl_cfg iwl_qu_c0_hr_b0 = { + .fw_name_pre = IWL_QU_C_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, + .num_rbds = IWL_NUM_RBDS_22000_HE, +}; + const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0 = { .name = "Intel(R) Wi-Fi 6 AX201 160MHz", .fw_name_pre = IWL_QU_C_HR_B_FW_PRE, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 15248b064380..d8b7776a8dde 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -80,19 +80,45 @@ static void *iwl_acpi_get_dsm_object(struct device *dev, int rev, int func, } /* - * Evaluate a DSM with no arguments and a single u8 return value (inside a - * buffer object), verify and return that value. + * Generic function to evaluate a DSM with no arguments + * and an integer return value, + * (as an integer object or inside a buffer object), + * verify and assign the value in the "value" parameter. + * return 0 in success and the appropriate errno otherwise. */ -int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func) +static int iwl_acpi_get_dsm_integer(struct device *dev, int rev, int func, + u64 *value, size_t expected_size) { union acpi_object *obj; - int ret; + int ret = 0; obj = iwl_acpi_get_dsm_object(dev, rev, func, NULL); - if (IS_ERR(obj)) + if (IS_ERR(obj)) { + IWL_DEBUG_DEV_RADIO(dev, + "Failed to get DSM object. func= %d\n", + func); return -ENOENT; + } + + if (obj->type == ACPI_TYPE_INTEGER) { + *value = obj->integer.value; + } else if (obj->type == ACPI_TYPE_BUFFER) { + __le64 le_value = 0; - if (obj->type != ACPI_TYPE_BUFFER) { + if (WARN_ON_ONCE(expected_size > sizeof(le_value))) + return -EINVAL; + + /* if the buffer size doesn't match the expected size */ + if (obj->buffer.length != expected_size) + IWL_DEBUG_DEV_RADIO(dev, + "ACPI: DSM invalid buffer size, padding or truncating (%d)\n", + obj->buffer.length); + + /* assuming LE from Intel BIOS spec */ + memcpy(&le_value, obj->buffer.pointer, + min_t(size_t, expected_size, (size_t)obj->buffer.length)); + *value = le64_to_cpu(le_value); + } else { IWL_DEBUG_DEV_RADIO(dev, "ACPI: DSM method did not return a valid object, type=%d\n", obj->type); @@ -100,15 +126,6 @@ int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func) goto out; } - if (obj->buffer.length != sizeof(u8)) { - IWL_DEBUG_DEV_RADIO(dev, - "ACPI: DSM method returned invalid buffer, length=%d\n", - obj->buffer.length); - ret = -EINVAL; - goto out; - } - - ret = obj->buffer.pointer[0]; IWL_DEBUG_DEV_RADIO(dev, "ACPI: DSM method evaluated: func=%d, ret=%d\n", func, ret); @@ -116,6 +133,24 @@ out: ACPI_FREE(obj); return ret; } + +/* + * Evaluate a DSM with no arguments and a u8 return value, + */ +int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func, u8 *value) +{ + int ret; + u64 val; + + ret = iwl_acpi_get_dsm_integer(dev, rev, func, &val, sizeof(u8)); + + if (ret < 0) + return ret; + + /* cast val (u64) to be u8 */ + *value = (u8)val; + return 0; +} IWL_EXPORT_SYMBOL(iwl_acpi_get_dsm_u8); union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h index 042dd247d387..1cce30d1ef55 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #ifndef __iwl_fw_acpi__ #define __iwl_fw_acpi__ @@ -99,7 +99,7 @@ struct iwl_fw_runtime; void *iwl_acpi_get_object(struct device *dev, acpi_string method); -int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func); +int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func, u8 *value); union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, union acpi_object *data, @@ -159,7 +159,8 @@ static inline void *iwl_acpi_get_dsm_object(struct device *dev, int rev, return ERR_PTR(-ENOENT); } -static inline int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func) +static inline +int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func, u8 *value) { return -ENOENT; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c index 6d8f7bff1243..895a907acdf0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c @@ -224,40 +224,46 @@ static int iwl_pnvm_parse(struct iwl_trans *trans, const u8 *data, int iwl_pnvm_load(struct iwl_trans *trans, struct iwl_notif_wait_data *notif_wait) { - const struct firmware *pnvm; struct iwl_notification_wait pnvm_wait; static const u16 ntf_cmds[] = { WIDE_ID(REGULATORY_AND_NVM_GROUP, PNVM_INIT_COMPLETE_NTFY) }; - char pnvm_name[64]; - int ret; /* if the SKU_ID is empty, there's nothing to do */ if (!trans->sku_id[0] && !trans->sku_id[1] && !trans->sku_id[2]) return 0; - /* if we already have it, nothing to do either */ - if (trans->pnvm_loaded) - return 0; + /* load from disk only if we haven't done it (or tried) before */ + if (!trans->pnvm_loaded) { + const struct firmware *pnvm; + char pnvm_name[64]; + int ret; + + /* + * The prefix unfortunately includes a hyphen at the end, so + * don't add the dot here... + */ + snprintf(pnvm_name, sizeof(pnvm_name), "%spnvm", + trans->cfg->fw_name_pre); + + /* ...but replace the hyphen with the dot here. */ + if (strlen(trans->cfg->fw_name_pre) < sizeof(pnvm_name)) + pnvm_name[strlen(trans->cfg->fw_name_pre) - 1] = '.'; + + ret = firmware_request_nowarn(&pnvm, pnvm_name, trans->dev); + if (ret) { + IWL_DEBUG_FW(trans, "PNVM file %s not found %d\n", + pnvm_name, ret); + /* + * Pretend we've loaded it - at least we've tried and + * couldn't load it at all, so there's no point in + * trying again over and over. + */ + trans->pnvm_loaded = true; + } else { + iwl_pnvm_parse(trans, pnvm->data, pnvm->size); - /* - * The prefix unfortunately includes a hyphen at the end, so - * don't add the dot here... - */ - snprintf(pnvm_name, sizeof(pnvm_name), "%spnvm", - trans->cfg->fw_name_pre); - - /* ...but replace the hyphen with the dot here. */ - if (strlen(trans->cfg->fw_name_pre) < sizeof(pnvm_name)) - pnvm_name[strlen(trans->cfg->fw_name_pre) - 1] = '.'; - - ret = firmware_request_nowarn(&pnvm, pnvm_name, trans->dev); - if (ret) { - IWL_DEBUG_FW(trans, "PNVM file %s not found %d\n", - pnvm_name, ret); - } else { - iwl_pnvm_parse(trans, pnvm->data, pnvm->size); - - release_firmware(pnvm); + release_firmware(pnvm); + } } iwl_init_notification_wait(notif_wait, &pnvm_wait, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 27cb0406ba9a..86e1d57df65e 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2020 Intel Corporation + * Copyright (C) 2005-2014, 2018-2021 Intel Corporation * Copyright (C) 2016-2017 Intel Deutschland GmbH */ #ifndef __IWL_CONFIG_H__ @@ -445,7 +445,7 @@ struct iwl_cfg { #define IWL_CFG_CORES_BT_GNSS 0x5 #define IWL_SUBDEVICE_RF_ID(subdevice) ((u16)((subdevice) & 0x00F0) >> 4) -#define IWL_SUBDEVICE_NO_160(subdevice) ((u16)((subdevice) & 0x0100) >> 9) +#define IWL_SUBDEVICE_NO_160(subdevice) ((u16)((subdevice) & 0x0200) >> 9) #define IWL_SUBDEVICE_CORES(subdevice) ((u16)((subdevice) & 0x1C00) >> 10) struct iwl_dev_info { @@ -491,6 +491,7 @@ extern const char iwl9260_killer_1550_name[]; extern const char iwl9560_killer_1550i_name[]; extern const char iwl9560_killer_1550s_name[]; extern const char iwl_ax200_name[]; +extern const char iwl_ax203_name[]; extern const char iwl_ax201_name[]; extern const char iwl_ax101_name[]; extern const char iwl_ax200_killer_1650w_name[]; @@ -574,6 +575,8 @@ extern const struct iwl_cfg iwl9560_2ac_cfg_soc; extern const struct iwl_cfg iwl_qu_b0_hr1_b0; extern const struct iwl_cfg iwl_qu_c0_hr1_b0; extern const struct iwl_cfg iwl_quz_a0_hr1_b0; +extern const struct iwl_cfg iwl_qu_b0_hr_b0; +extern const struct iwl_cfg iwl_qu_c0_hr_b0; extern const struct iwl_cfg iwl_ax200_cfg_cc; extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index a654147d3cd6..a80a35a7740f 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -180,13 +180,6 @@ static int iwl_dbg_tlv_alloc_region(struct iwl_trans *trans, if (le32_to_cpu(tlv->length) < sizeof(*reg)) return -EINVAL; - /* For safe using a string from FW make sure we have a - * null terminator - */ - reg->name[IWL_FW_INI_MAX_NAME - 1] = 0; - - IWL_DEBUG_FW(trans, "WRT: parsing region: %s\n", reg->name); - if (id >= IWL_FW_INI_MAX_REGION_ID) { IWL_ERR(trans, "WRT: Invalid region id %u\n", id); return -EINVAL; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.c b/drivers/net/wireless/intel/iwlwifi/iwl-io.c index 2ac20d0a30eb..2b7ef1583e7f 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-io.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.c @@ -150,16 +150,17 @@ u32 iwl_read_prph(struct iwl_trans *trans, u32 ofs) } IWL_EXPORT_SYMBOL(iwl_read_prph); -void iwl_write_prph(struct iwl_trans *trans, u32 ofs, u32 val) +void iwl_write_prph_delay(struct iwl_trans *trans, u32 ofs, u32 val, u32 delay_ms) { unsigned long flags; if (iwl_trans_grab_nic_access(trans, &flags)) { + mdelay(delay_ms); iwl_write_prph_no_grab(trans, ofs, val); iwl_trans_release_nic_access(trans, &flags); } } -IWL_EXPORT_SYMBOL(iwl_write_prph); +IWL_EXPORT_SYMBOL(iwl_write_prph_delay); int iwl_poll_prph_bit(struct iwl_trans *trans, u32 addr, u32 bits, u32 mask, int timeout) @@ -219,8 +220,8 @@ IWL_EXPORT_SYMBOL(iwl_clear_bits_prph); void iwl_force_nmi(struct iwl_trans *trans) { if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000) - iwl_write_prph(trans, DEVICE_SET_NMI_REG, - DEVICE_SET_NMI_VAL_DRV); + iwl_write_prph_delay(trans, DEVICE_SET_NMI_REG, + DEVICE_SET_NMI_VAL_DRV, 1); else if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) iwl_write_umac_prph(trans, UREG_NIC_SET_NMI_DRIVER, UREG_NIC_SET_NMI_DRIVER_NMI_FROM_DRIVER); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.h b/drivers/net/wireless/intel/iwlwifi/iwl-io.h index 39bceee4e9e7..3c21c0e081f8 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-io.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #ifndef __iwl_io_h__ #define __iwl_io_h__ @@ -37,7 +37,13 @@ u32 iwl_read_prph_no_grab(struct iwl_trans *trans, u32 ofs); u32 iwl_read_prph(struct iwl_trans *trans, u32 ofs); void iwl_write_prph_no_grab(struct iwl_trans *trans, u32 ofs, u32 val); void iwl_write_prph64_no_grab(struct iwl_trans *trans, u64 ofs, u64 val); -void iwl_write_prph(struct iwl_trans *trans, u32 ofs, u32 val); +void iwl_write_prph_delay(struct iwl_trans *trans, u32 ofs, + u32 val, u32 delay_ms); +static inline void iwl_write_prph(struct iwl_trans *trans, u32 ofs, u32 val) +{ + iwl_write_prph_delay(trans, ofs, val, 0); +} + int iwl_poll_prph_bit(struct iwl_trans *trans, u32 addr, u32 bits, u32 mask, int timeout); void iwl_set_bits_prph(struct iwl_trans *trans, u32 ofs, u32 mask); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index 0b03fdedc1f7..1158e256f601 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -301,6 +301,12 @@ #define RADIO_RSP_ADDR_POS (6) #define RADIO_RSP_RD_CMD (3) +/* LTR control (Qu only) */ +#define HPM_MAC_LTR_CSR 0xa0348c +#define HPM_MAC_LRT_ENABLE_ALL 0xf +/* also uses CSR_LTR_* for values */ +#define HPM_UMAC_LTR 0xa03480 + /* FW monitor */ #define MON_BUFF_SAMPLE_CTL (0xa03c00) #define MON_BUFF_BASE_ADDR (0xa03c1c) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index a0b7331cab31..64c10ca0d31e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -2032,8 +2032,6 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) mutex_lock(&mvm->mutex); - clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); - /* get the BSS vif pointer again */ vif = iwl_mvm_get_bss_vif(mvm); if (IS_ERR_OR_NULL(vif)) @@ -2148,6 +2146,8 @@ out_iterate: iwl_mvm_d3_disconnect_iter, keep ? vif : NULL); out: + clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); + /* no need to reset the device in unified images, if successful */ if (unified_image && !ret) { /* nothing else to do if we already sent D0I3_END_CMD */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index 573e46956c14..38d0bfb649cc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -459,7 +459,10 @@ static ssize_t iwl_dbgfs_os_device_timediff_read(struct file *file, const size_t bufsz = sizeof(buf); int pos = 0; + mutex_lock(&mvm->mutex); iwl_mvm_get_sync_time(mvm, &curr_gp2, &curr_os); + mutex_unlock(&mvm->mutex); + do_div(curr_os, NSEC_PER_USEC); diff = curr_os - curr_gp2; pos += scnprintf(buf + pos, bufsz - pos, "diff=%lld\n", diff); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 0637eb1cff4e..313e9f106f46 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1090,20 +1090,22 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm) static u8 iwl_mvm_eval_dsm_indonesia_5g2(struct iwl_mvm *mvm) { + u8 value; + int ret = iwl_acpi_get_dsm_u8((&mvm->fwrt)->dev, 0, - DSM_FUNC_ENABLE_INDONESIA_5G2); + DSM_FUNC_ENABLE_INDONESIA_5G2, &value); if (ret < 0) IWL_DEBUG_RADIO(mvm, "Failed to evaluate DSM function ENABLE_INDONESIA_5G2, ret=%d\n", ret); - else if (ret >= DSM_VALUE_INDONESIA_MAX) + else if (value >= DSM_VALUE_INDONESIA_MAX) IWL_DEBUG_RADIO(mvm, - "DSM function ENABLE_INDONESIA_5G2 return invalid value, ret=%d\n", - ret); + "DSM function ENABLE_INDONESIA_5G2 return invalid value, value=%d\n", + value); - else if (ret == DSM_VALUE_INDONESIA_ENABLE) { + else if (value == DSM_VALUE_INDONESIA_ENABLE) { IWL_DEBUG_RADIO(mvm, "Evaluated DSM function ENABLE_INDONESIA_5G2: Enabling 5g2\n"); return DSM_VALUE_INDONESIA_ENABLE; @@ -1114,25 +1116,26 @@ static u8 iwl_mvm_eval_dsm_indonesia_5g2(struct iwl_mvm *mvm) static u8 iwl_mvm_eval_dsm_disable_srd(struct iwl_mvm *mvm) { + u8 value; int ret = iwl_acpi_get_dsm_u8((&mvm->fwrt)->dev, 0, - DSM_FUNC_DISABLE_SRD); + DSM_FUNC_DISABLE_SRD, &value); if (ret < 0) IWL_DEBUG_RADIO(mvm, "Failed to evaluate DSM function DISABLE_SRD, ret=%d\n", ret); - else if (ret >= DSM_VALUE_SRD_MAX) + else if (value >= DSM_VALUE_SRD_MAX) IWL_DEBUG_RADIO(mvm, - "DSM function DISABLE_SRD return invalid value, ret=%d\n", - ret); + "DSM function DISABLE_SRD return invalid value, value=%d\n", + value); - else if (ret == DSM_VALUE_SRD_PASSIVE) { + else if (value == DSM_VALUE_SRD_PASSIVE) { IWL_DEBUG_RADIO(mvm, "Evaluated DSM function DISABLE_SRD: setting SRD to passive\n"); return DSM_VALUE_SRD_PASSIVE; - } else if (ret == DSM_VALUE_SRD_DISABLE) { + } else if (value == DSM_VALUE_SRD_DISABLE) { IWL_DEBUG_RADIO(mvm, "Evaluated DSM function DISABLE_SRD: disabling SRD\n"); return DSM_VALUE_SRD_DISABLE; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 6cce72b0685b..bcbd77ef68df 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -4194,6 +4194,9 @@ static void __iwl_mvm_unassign_vif_chanctx(struct iwl_mvm *mvm, iwl_mvm_binding_remove_vif(mvm, vif); out: + if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_CHANNEL_SWITCH_CMD) && + switching_chanctx) + return; mvmvif->phy_ctxt = NULL; iwl_mvm_power_update_mac(mvm); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 98f62d78cf9c..61618f607927 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -791,6 +791,10 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, if (!mvm->scan_cmd) goto out_free; + /* invalidate ids to prevent accidental removal of sta_id 0 */ + mvm->aux_sta.sta_id = IWL_MVM_INVALID_STA; + mvm->snif_sta.sta_id = IWL_MVM_INVALID_STA; + /* Set EBS as successful as long as not stated otherwise by the FW. */ mvm->last_ebs_successful = true; @@ -1205,6 +1209,7 @@ static void iwl_mvm_reprobe_wk(struct work_struct *wk) reprobe = container_of(wk, struct iwl_mvm_reprobe, work); if (device_reprobe(reprobe->dev)) dev_err(reprobe->dev, "reprobe failed!\n"); + put_device(reprobe->dev); kfree(reprobe); module_put(THIS_MODULE); } @@ -1255,7 +1260,7 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error) module_put(THIS_MODULE); return; } - reprobe->dev = mvm->trans->dev; + reprobe->dev = get_device(mvm->trans->dev); INIT_WORK(&reprobe->work, iwl_mvm_reprobe_wk); schedule_work(&reprobe->work); } else if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index dc174410bf9c..578c353ae02c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2057,6 +2057,9 @@ int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) lockdep_assert_held(&mvm->mutex); + if (WARN_ON_ONCE(mvm->snif_sta.sta_id == IWL_MVM_INVALID_STA)) + return -EINVAL; + iwl_mvm_disable_txq(mvm, NULL, mvm->snif_queue, IWL_MAX_TID_COUNT, 0); ret = iwl_mvm_rm_sta_common(mvm, mvm->snif_sta.sta_id); if (ret) @@ -2071,6 +2074,9 @@ int iwl_mvm_rm_aux_sta(struct iwl_mvm *mvm) lockdep_assert_held(&mvm->mutex); + if (WARN_ON_ONCE(mvm->aux_sta.sta_id == IWL_MVM_INVALID_STA)) + return -EINVAL; + iwl_mvm_disable_txq(mvm, NULL, mvm->aux_queue, IWL_MAX_TID_COUNT, 0); ret = iwl_mvm_rm_sta_common(mvm, mvm->aux_sta.sta_id); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index a983c215df31..3712adc3ccc2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -773,6 +773,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, next = skb_gso_segment(skb, netdev_flags); skb_shinfo(skb)->gso_size = mss; + skb_shinfo(skb)->gso_type = ipv4 ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6; if (WARN_ON_ONCE(IS_ERR(next))) return -EINVAL; else if (next) @@ -795,6 +796,8 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, if (tcp_payload_len > mss) { skb_shinfo(tmp)->gso_size = mss; + skb_shinfo(tmp)->gso_type = ipv4 ? SKB_GSO_TCPV4 : + SKB_GSO_TCPV6; } else { if (qos) { u8 *qc; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index 36bf414a388a..5b5134dd49af 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -75,6 +75,15 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, const struct fw_img *fw) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | + u32_encode_bits(250, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | + CSR_LTR_LONG_VAL_AD_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | + u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); struct iwl_context_info_gen3 *ctxt_info_gen3; struct iwl_prph_scratch *prph_scratch; struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl; @@ -189,8 +198,10 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, /* Allocate IML */ iml_img = dma_alloc_coherent(trans->dev, trans->iml_len, &trans_pcie->iml_dma_addr, GFP_KERNEL); - if (!iml_img) - return -ENOMEM; + if (!iml_img) { + ret = -ENOMEM; + goto err_free_ctxt_info; + } memcpy(iml_img, trans->iml, trans->iml_len); @@ -206,23 +217,19 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA); - if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210) { - /* - * The firmware initializes this again later (to a smaller - * value), but for the boot process initialize the LTR to - * ~250 usec. - */ - u32 val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | - u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, - CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | - u32_encode_bits(250, - CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | - CSR_LTR_LONG_VAL_AD_SNOOP_REQ | - u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, - CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | - u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); - - iwl_write32(trans, CSR_LTR_LONG_VAL_AD, val); + /* + * To workaround hardware latency issues during the boot process, + * initialize the LTR to ~250 usec (see ltr_val above). + * The firmware initializes this again later (to a smaller value). + */ + if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 || + trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) && + !trans->trans_cfg->integrated) { + iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val); + } else if (trans->trans_cfg->integrated && + trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) { + iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL); + iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val); } if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) @@ -232,6 +239,11 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, return 0; +err_free_ctxt_info: + dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3), + trans_pcie->ctxt_info_gen3, + trans_pcie->ctxt_info_dma_addr); + trans_pcie->ctxt_info_gen3 = NULL; err_free_prph_info: dma_free_coherent(trans->dev, sizeof(*prph_info), @@ -294,6 +306,9 @@ int iwl_trans_pcie_ctx_info_gen3_set_pnvm(struct iwl_trans *trans, return ret; } + if (WARN_ON(prph_sc_ctrl->pnvm_cfg.pnvm_size)) + return -EBUSY; + prph_sc_ctrl->pnvm_cfg.pnvm_base_addr = cpu_to_le64(trans_pcie->pnvm_dram.physical); prph_sc_ctrl->pnvm_cfg.pnvm_size = diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 965982612e74..ed3f5b7aa71e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -910,6 +910,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_qu_b0_hr1_b0, iwl_ax101_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, + iwl_qu_b0_hr_b0, iwl_ax203_name), /* Qu C step */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, @@ -917,6 +922,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_qu_c0_hr1_b0, iwl_ax101_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, + iwl_qu_c0_hr_b0, iwl_ax203_name), /* QuZ */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 285e0d586021..ab93a848a466 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2107,7 +2107,8 @@ static int iwl_trans_pcie_read_mem(struct iwl_trans *trans, u32 addr, while (offs < dwords) { /* limit the time we spin here under lock to 1/2s */ - ktime_t timeout = ktime_add_us(ktime_get(), 500 * USEC_PER_MSEC); + unsigned long end = jiffies + HZ / 2; + bool resched = false; if (iwl_trans_grab_nic_access(trans, &flags)) { iwl_write32(trans, HBUS_TARG_MEM_RADDR, @@ -2118,14 +2119,15 @@ static int iwl_trans_pcie_read_mem(struct iwl_trans *trans, u32 addr, HBUS_TARG_MEM_RDAT); offs++; - /* calling ktime_get is expensive so - * do it once in 128 reads - */ - if (offs % 128 == 0 && ktime_after(ktime_get(), - timeout)) + if (time_after(jiffies, end)) { + resched = true; break; + } } iwl_trans_release_nic_access(trans, &flags); + + if (resched) + cond_resched(); } else { return -EBUSY; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 5dda0015522d..83f4964f3cb2 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -201,6 +201,11 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id) struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct iwl_txq *txq = trans->txqs.txq[txq_id]; + if (!txq) { + IWL_ERR(trans, "Trying to free a queue that wasn't allocated?\n"); + return; + } + spin_lock_bh(&txq->lock); while (txq->write_ptr != txq->read_ptr) { IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n", diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c index 27eea909e32d..7ff1bb0ccc9c 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c @@ -142,26 +142,25 @@ void iwl_txq_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq) * idx is bounded by n_window */ int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr); + struct sk_buff *skb; lockdep_assert_held(&txq->lock); + if (!txq->entries) + return; + iwl_txq_gen2_tfd_unmap(trans, &txq->entries[idx].meta, iwl_txq_get_tfd(trans, txq, idx)); - /* free SKB */ - if (txq->entries) { - struct sk_buff *skb; - - skb = txq->entries[idx].skb; + skb = txq->entries[idx].skb; - /* Can be called from irqs-disabled context - * If skb is not NULL, it means that the whole queue is being - * freed and that the queue is not empty - free the skb - */ - if (skb) { - iwl_op_mode_free_skb(trans->op_mode, skb); - txq->entries[idx].skb = NULL; - } + /* Can be called from irqs-disabled context + * If skb is not NULL, it means that the whole queue is being + * freed and that the queue is not empty - free the skb + */ + if (skb) { + iwl_op_mode_free_skb(trans->op_mode, skb); + txq->entries[idx].skb = NULL; } } @@ -841,10 +840,8 @@ void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id) int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr); struct sk_buff *skb = txq->entries[idx].skb; - if (WARN_ON_ONCE(!skb)) - continue; - - iwl_txq_free_tso_page(trans, skb); + if (!WARN_ON_ONCE(!skb)) + iwl_txq_free_tso_page(trans, skb); } iwl_txq_gen2_free_tfd(trans, txq); txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr); @@ -1494,28 +1491,28 @@ void iwl_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq) */ int rd_ptr = txq->read_ptr; int idx = iwl_txq_get_cmd_index(txq, rd_ptr); + struct sk_buff *skb; lockdep_assert_held(&txq->lock); + if (!txq->entries) + return; + /* We have only q->n_window txq->entries, but we use * TFD_QUEUE_SIZE_MAX tfds */ iwl_txq_gen1_tfd_unmap(trans, &txq->entries[idx].meta, txq, rd_ptr); /* free SKB */ - if (txq->entries) { - struct sk_buff *skb; - - skb = txq->entries[idx].skb; + skb = txq->entries[idx].skb; - /* Can be called from irqs-disabled context - * If skb is not NULL, it means that the whole queue is being - * freed and that the queue is not empty - free the skb - */ - if (skb) { - iwl_op_mode_free_skb(trans->op_mode, skb); - txq->entries[idx].skb = NULL; - } + /* Can be called from irqs-disabled context + * If skb is not NULL, it means that the whole queue is being + * freed and that the queue is not empty - free the skb + */ + if (skb) { + iwl_op_mode_free_skb(trans->op_mode, skb); + txq->entries[idx].skb = NULL; } } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index a44b7766dec6..c13547841a4e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -231,7 +231,7 @@ mt7615_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, int cmd, int *seq) { struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); - enum mt76_txq_id qid; + enum mt76_mcuq_id qid; mt7615_mcu_fill_msg(dev, skb, cmd, seq); if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state)) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c index 13d77f8fca86..9fb506f2ace6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c @@ -83,7 +83,7 @@ static int mt7663s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid, { struct mt76_queue *q = &dev->q_rx[qid]; struct mt76_sdio *sdio = &dev->sdio; - int len = 0, err, i, order; + int len = 0, err, i; struct page *page; u8 *buf; @@ -96,8 +96,7 @@ static int mt7663s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid, if (len > sdio->func->cur_blksize) len = roundup(len, sdio->func->cur_blksize); - order = get_order(len); - page = __dev_alloc_pages(GFP_KERNEL, order); + page = __dev_alloc_pages(GFP_KERNEL, get_order(len)); if (!page) return -ENOMEM; @@ -106,7 +105,7 @@ static int mt7663s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid, err = sdio_readsb(sdio->func, buf, MCR_WRDR(qid), len); if (err < 0) { dev_err(dev->dev, "sdio read data failed:%d\n", err); - __free_pages(page, order); + put_page(page); return err; } @@ -123,7 +122,7 @@ static int mt7663s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid, if (q->queued + i + 1 == q->ndesc) break; } - __free_pages(page, order); + put_page(page); spin_lock_bh(&q->lock); q->head = (q->head + i) % q->ndesc; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 5fdd1a6d32ee..e211a2bd4d3c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -256,7 +256,7 @@ mt7915_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); struct mt7915_mcu_txd *mcu_txd; u8 seq, pkt_fmt, qidx; - enum mt76_txq_id txq; + enum mt76_mcuq_id qid; __le32 *txd; u32 val; @@ -268,18 +268,18 @@ mt7915_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, seq = ++dev->mt76.mcu.msg_seq & 0xf; if (cmd == -MCU_CMD_FW_SCATTER) { - txq = MT_MCUQ_FWDL; + qid = MT_MCUQ_FWDL; goto exit; } mcu_txd = (struct mt7915_mcu_txd *)skb_push(skb, sizeof(*mcu_txd)); if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state)) { - txq = MT_MCUQ_WA; + qid = MT_MCUQ_WA; qidx = MT_TX_MCU_PORT_RX_Q0; pkt_fmt = MT_TX_TYPE_CMD; } else { - txq = MT_MCUQ_WM; + qid = MT_MCUQ_WM; qidx = MT_TX_MCU_PORT_RX_Q0; pkt_fmt = MT_TX_TYPE_CMD; } @@ -326,7 +326,7 @@ exit: if (wait_seq) *wait_seq = seq; - return mt76_tx_queue_skb_raw(dev, mdev->q_mcu[txq], skb, 0); + return mt76_tx_queue_skb_raw(dev, mdev->q_mcu[qid], skb, 0); } static void diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.c b/drivers/net/wireless/mediatek/mt7601u/dma.c index 5f99054f535b..af7d1ecb777c 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -152,8 +152,7 @@ mt7601u_rx_process_entry(struct mt7601u_dev *dev, struct mt7601u_dma_buf_rx *e) if (new_p) { /* we have one extra ref from the allocator */ - __free_pages(e->p, MT_RX_ORDER); - + put_page(e->p); e->p = new_p; } } @@ -310,7 +309,6 @@ static int mt7601u_dma_submit_tx(struct mt7601u_dev *dev, } e = &q->e[q->end]; - e->skb = skb; usb_fill_bulk_urb(e->urb, usb_dev, snd_pipe, skb->data, skb->len, mt7601u_complete_tx, q); ret = usb_submit_urb(e->urb, GFP_ATOMIC); @@ -328,6 +326,7 @@ static int mt7601u_dma_submit_tx(struct mt7601u_dev *dev, q->end = (q->end + 1) % q->entries; q->used++; + e->skb = skb; if (q->used >= q->entries) ieee80211_stop_queue(dev->hw, skb_get_queue_mapping(skb)); diff --git a/drivers/nfc/Kconfig b/drivers/nfc/Kconfig index 75c65d339018..288c6f1c6979 100644 --- a/drivers/nfc/Kconfig +++ b/drivers/nfc/Kconfig @@ -49,6 +49,17 @@ config NFC_PORT100 If unsure, say N. +config NFC_VIRTUAL_NCI + tristate "NCI device simulator driver" + depends on NFC_NCI + help + NCI virtual device simulates a NCI device to the user. + It can be used to validate the NCI module and applications. + This driver supports communication between the virtual NCI device and + module. + + If unsure, say N. + source "drivers/nfc/fdp/Kconfig" source "drivers/nfc/pn544/Kconfig" source "drivers/nfc/pn533/Kconfig" diff --git a/drivers/nfc/Makefile b/drivers/nfc/Makefile index 5393ba59b17d..7b1bfde1d971 100644 --- a/drivers/nfc/Makefile +++ b/drivers/nfc/Makefile @@ -17,3 +17,4 @@ obj-$(CONFIG_NFC_ST_NCI) += st-nci/ obj-$(CONFIG_NFC_NXP_NCI) += nxp-nci/ obj-$(CONFIG_NFC_S3FWRN5) += s3fwrn5/ obj-$(CONFIG_NFC_ST95HF) += st95hf/ +obj-$(CONFIG_NFC_VIRTUAL_NCI) += virtual_ncidev.o diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c new file mode 100644 index 000000000000..f73ee0bf3593 --- /dev/null +++ b/drivers/nfc/virtual_ncidev.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Virtual NCI device simulation driver + * + * Copyright (C) 2020 Samsung Electrnoics + * Bongsu Jeon <bongsu.jeon@samsung.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/miscdevice.h> +#include <linux/mutex.h> +#include <net/nfc/nci_core.h> + +enum virtual_ncidev_mode { + virtual_ncidev_enabled, + virtual_ncidev_disabled, + virtual_ncidev_disabling, +}; + +#define IOCTL_GET_NCIDEV_IDX 0 +#define VIRTUAL_NFC_PROTOCOLS (NFC_PROTO_JEWEL_MASK | \ + NFC_PROTO_MIFARE_MASK | \ + NFC_PROTO_FELICA_MASK | \ + NFC_PROTO_ISO14443_MASK | \ + NFC_PROTO_ISO14443_B_MASK | \ + NFC_PROTO_ISO15693_MASK) + +static enum virtual_ncidev_mode state; +static struct miscdevice miscdev; +static struct sk_buff *send_buff; +static struct nci_dev *ndev; +static DEFINE_MUTEX(nci_mutex); + +static int virtual_nci_open(struct nci_dev *ndev) +{ + return 0; +} + +static int virtual_nci_close(struct nci_dev *ndev) +{ + mutex_lock(&nci_mutex); + kfree_skb(send_buff); + send_buff = NULL; + mutex_unlock(&nci_mutex); + + return 0; +} + +static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb) +{ + mutex_lock(&nci_mutex); + if (state != virtual_ncidev_enabled) { + mutex_unlock(&nci_mutex); + return 0; + } + + if (send_buff) { + mutex_unlock(&nci_mutex); + return -1; + } + send_buff = skb_copy(skb, GFP_KERNEL); + mutex_unlock(&nci_mutex); + + return 0; +} + +static struct nci_ops virtual_nci_ops = { + .open = virtual_nci_open, + .close = virtual_nci_close, + .send = virtual_nci_send +}; + +static ssize_t virtual_ncidev_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + size_t actual_len; + + mutex_lock(&nci_mutex); + if (!send_buff) { + mutex_unlock(&nci_mutex); + return 0; + } + + actual_len = min_t(size_t, count, send_buff->len); + + if (copy_to_user(buf, send_buff->data, actual_len)) { + mutex_unlock(&nci_mutex); + return -EFAULT; + } + + skb_pull(send_buff, actual_len); + if (send_buff->len == 0) { + consume_skb(send_buff); + send_buff = NULL; + } + mutex_unlock(&nci_mutex); + + return actual_len; +} + +static ssize_t virtual_ncidev_write(struct file *file, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct sk_buff *skb; + + skb = alloc_skb(count, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + if (copy_from_user(skb_put(skb, count), buf, count)) { + kfree_skb(skb); + return -EFAULT; + } + + nci_recv_frame(ndev, skb); + return count; +} + +static int virtual_ncidev_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + mutex_lock(&nci_mutex); + if (state != virtual_ncidev_disabled) { + mutex_unlock(&nci_mutex); + return -EBUSY; + } + + ndev = nci_allocate_device(&virtual_nci_ops, VIRTUAL_NFC_PROTOCOLS, + 0, 0); + if (!ndev) { + mutex_unlock(&nci_mutex); + return -ENOMEM; + } + + ret = nci_register_device(ndev); + if (ret < 0) { + nci_free_device(ndev); + mutex_unlock(&nci_mutex); + return ret; + } + state = virtual_ncidev_enabled; + mutex_unlock(&nci_mutex); + + return 0; +} + +static int virtual_ncidev_close(struct inode *inode, struct file *file) +{ + mutex_lock(&nci_mutex); + + if (state == virtual_ncidev_enabled) { + state = virtual_ncidev_disabling; + mutex_unlock(&nci_mutex); + + nci_unregister_device(ndev); + nci_free_device(ndev); + + mutex_lock(&nci_mutex); + } + + state = virtual_ncidev_disabled; + mutex_unlock(&nci_mutex); + + return 0; +} + +static long virtual_ncidev_ioctl(struct file *flip, unsigned int cmd, + unsigned long arg) +{ + struct nfc_dev *nfc_dev = ndev->nfc_dev; + void __user *p = (void __user *)arg; + + if (cmd != IOCTL_GET_NCIDEV_IDX) + return -ENOTTY; + + if (copy_to_user(p, &nfc_dev->idx, sizeof(nfc_dev->idx))) + return -EFAULT; + + return 0; +} + +static const struct file_operations virtual_ncidev_fops = { + .owner = THIS_MODULE, + .read = virtual_ncidev_read, + .write = virtual_ncidev_write, + .open = virtual_ncidev_open, + .release = virtual_ncidev_close, + .unlocked_ioctl = virtual_ncidev_ioctl +}; + +static int __init virtual_ncidev_init(void) +{ + state = virtual_ncidev_disabled; + miscdev.minor = MISC_DYNAMIC_MINOR; + miscdev.name = "virtual_nci"; + miscdev.fops = &virtual_ncidev_fops; + miscdev.mode = S_IALLUGO; + + return misc_register(&miscdev); +} + +static void __exit virtual_ncidev_exit(void) +{ + misc_deregister(&miscdev); +} + +module_init(virtual_ncidev_init); +module_exit(virtual_ncidev_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Virtual NCI device simulation driver"); +MODULE_AUTHOR("Bongsu Jeon <bongsu.jeon@samsung.com>"); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 200bdd672c28..f13eb4ded95f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1543,8 +1543,21 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) } length = (io.nblocks + 1) << ns->lba_shift; - meta_len = (io.nblocks + 1) * ns->ms; - metadata = nvme_to_user_ptr(io.metadata); + + if ((io.control & NVME_RW_PRINFO_PRACT) && + ns->ms == sizeof(struct t10_pi_tuple)) { + /* + * Protection information is stripped/inserted by the + * controller. + */ + if (nvme_to_user_ptr(io.metadata)) + return -EINVAL; + meta_len = 0; + metadata = NULL; + } else { + meta_len = (io.nblocks + 1) * ns->ms; + metadata = nvme_to_user_ptr(io.metadata); + } if (ns->features & NVME_NS_EXT_LBAS) { length += meta_len; @@ -3816,7 +3829,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, } } - list_add_tail(&ns->siblings, &head->list); + list_add_tail_rcu(&ns->siblings, &head->list); ns->head = head; mutex_unlock(&ctrl->subsys->lock); return 0; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 9ac762b28811..282b7a4ea9a9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -221,7 +221,7 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, } for (ns = nvme_next_ns(head, old); - ns != old; + ns && ns != old; ns = nvme_next_ns(head, ns)) { if (nvme_path_is_disabled(ns)) continue; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 50d9a20568a2..81e6389b2042 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -23,6 +23,7 @@ #include <linux/t10-pi.h> #include <linux/types.h> #include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/io-64-nonatomic-hi-lo.h> #include <linux/sed-opal.h> #include <linux/pci-p2pdma.h> @@ -542,50 +543,71 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) return true; } -static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +static void nvme_free_prps(struct nvme_dev *dev, struct request *req) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1; - dma_addr_t dma_addr = iod->first_dma, next_dma_addr; + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + dma_addr_t dma_addr = iod->first_dma; int i; - if (iod->dma_len) { - dma_unmap_page(dev->dev, dma_addr, iod->dma_len, - rq_dma_dir(req)); - return; + for (i = 0; i < iod->npages; i++) { + __le64 *prp_list = nvme_pci_iod_list(req)[i]; + dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]); + + dma_pool_free(dev->prp_page_pool, prp_list, dma_addr); + dma_addr = next_dma_addr; } - WARN_ON_ONCE(!iod->nents); +} - if (is_pci_p2pdma_page(sg_page(iod->sg))) - pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents, - rq_dma_dir(req)); - else - dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req)); +static void nvme_free_sgls(struct nvme_dev *dev, struct request *req) +{ + const int last_sg = SGES_PER_PAGE - 1; + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + dma_addr_t dma_addr = iod->first_dma; + int i; + for (i = 0; i < iod->npages; i++) { + struct nvme_sgl_desc *sg_list = nvme_pci_iod_list(req)[i]; + dma_addr_t next_dma_addr = le64_to_cpu((sg_list[last_sg]).addr); - if (iod->npages == 0) - dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], - dma_addr); + dma_pool_free(dev->prp_page_pool, sg_list, dma_addr); + dma_addr = next_dma_addr; + } - for (i = 0; i < iod->npages; i++) { - void *addr = nvme_pci_iod_list(req)[i]; +} - if (iod->use_sgl) { - struct nvme_sgl_desc *sg_list = addr; +static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - next_dma_addr = - le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr); - } else { - __le64 *prp_list = addr; + if (is_pci_p2pdma_page(sg_page(iod->sg))) + pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents, + rq_dma_dir(req)); + else + dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req)); +} - next_dma_addr = le64_to_cpu(prp_list[last_prp]); - } +static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - dma_pool_free(dev->prp_page_pool, addr, dma_addr); - dma_addr = next_dma_addr; + if (iod->dma_len) { + dma_unmap_page(dev->dev, iod->first_dma, iod->dma_len, + rq_dma_dir(req)); + return; } + WARN_ON_ONCE(!iod->nents); + + nvme_unmap_sg(dev, req); + if (iod->npages == 0) + dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], + iod->first_dma); + else if (iod->use_sgl) + nvme_free_sgls(dev, req); + else + nvme_free_prps(dev, req); mempool_free(iod->sg, dev->iod_mempool); } @@ -661,7 +683,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, __le64 *old_prp_list = prp_list; prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) - return BLK_STS_RESOURCE; + goto free_prps; list[iod->npages++] = prp_list; prp_list[0] = old_prp_list[i - 1]; old_prp_list[i - 1] = cpu_to_le64(prp_dma); @@ -681,14 +703,14 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, dma_addr = sg_dma_address(sg); dma_len = sg_dma_len(sg); } - done: cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg)); cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma); - return BLK_STS_OK; - - bad_sgl: +free_prps: + nvme_free_prps(dev, req); + return BLK_STS_RESOURCE; +bad_sgl: WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents), "Invalid SGL for payload:%d nents:%d\n", blk_rq_payload_bytes(req), iod->nents); @@ -760,7 +782,7 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); if (!sg_list) - return BLK_STS_RESOURCE; + goto free_sgls; i = 0; nvme_pci_iod_list(req)[iod->npages++] = sg_list; @@ -773,6 +795,9 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, } while (--entries > 0); return BLK_STS_OK; +free_sgls: + nvme_free_sgls(dev, req); + return BLK_STS_RESOURCE; } static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, @@ -841,7 +866,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); iod->nents = blk_rq_map_sg(req->q, req, iod->sg); if (!iod->nents) - goto out; + goto out_free_sg; if (is_pci_p2pdma_page(sg_page(iod->sg))) nr_mapped = pci_p2pdma_map_sg_attrs(dev->dev, iod->sg, @@ -850,16 +875,21 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, rq_dma_dir(req), DMA_ATTR_NO_WARN); if (!nr_mapped) - goto out; + goto out_free_sg; iod->use_sgl = nvme_pci_use_sgls(dev, req); if (iod->use_sgl) ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped); else ret = nvme_pci_setup_prps(dev, req, &cmnd->rw); -out: if (ret != BLK_STS_OK) - nvme_unmap_data(dev, req); + goto out_unmap_sg; + return BLK_STS_OK; + +out_unmap_sg: + nvme_unmap_sg(dev, req); +out_free_sg: + mempool_free(iod->sg, dev->iod_mempool); return ret; } @@ -1795,6 +1825,9 @@ static void nvme_map_cmb(struct nvme_dev *dev) if (dev->cmb_size) return; + if (NVME_CAP_CMBS(dev->ctrl.cap)) + writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC); + dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!dev->cmbsz) return; @@ -1809,6 +1842,16 @@ static void nvme_map_cmb(struct nvme_dev *dev) return; /* + * Tell the controller about the host side address mapping the CMB, + * and enable CMB decoding for the NVMe 1.4+ scheme: + */ + if (NVME_CAP_CMBS(dev->ctrl.cap)) { + hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE | + (pci_bus_address(pdev, bar) + offset), + dev->bar + NVME_REG_CMBMSC); + } + + /* * Controllers may support a CMB size larger than their BAR, * for example, due to being behind a bridge. Reduce the CMB to * the reported size of the BAR @@ -3214,6 +3257,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x15b7, 0x2001), /* Sandisk Skyhawk */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x1d97, 0x2263), /* SPCC */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), .driver_data = NVME_QUIRK_SINGLE_VECTOR }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index cf6c49d09c82..b7ce4f221d99 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -97,6 +97,7 @@ struct nvme_rdma_queue { struct completion cm_done; bool pi_support; int cq_size; + struct mutex queue_lock; }; struct nvme_rdma_ctrl { @@ -579,6 +580,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, int ret; queue = &ctrl->queues[idx]; + mutex_init(&queue->queue_lock); queue->ctrl = ctrl; if (idx && ctrl->ctrl.max_integrity_segments) queue->pi_support = true; @@ -598,7 +600,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, if (IS_ERR(queue->cm_id)) { dev_info(ctrl->ctrl.device, "failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id)); - return PTR_ERR(queue->cm_id); + ret = PTR_ERR(queue->cm_id); + goto out_destroy_mutex; } if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR) @@ -628,6 +631,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, out_destroy_cm_id: rdma_destroy_id(queue->cm_id); nvme_rdma_destroy_queue_ib(queue); +out_destroy_mutex: + mutex_destroy(&queue->queue_lock); return ret; } @@ -639,9 +644,10 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { - if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) - return; - __nvme_rdma_stop_queue(queue); + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) + __nvme_rdma_stop_queue(queue); + mutex_unlock(&queue->queue_lock); } static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) @@ -651,6 +657,7 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + mutex_destroy(&queue->queue_lock); } static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 216619926563..881d28eb15e9 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -76,6 +76,7 @@ struct nvme_tcp_queue { struct work_struct io_work; int io_cpu; + struct mutex queue_lock; struct mutex send_mutex; struct llist_head req_list; struct list_head send_list; @@ -1219,6 +1220,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) sock_release(queue->sock); kfree(queue->pdu); + mutex_destroy(&queue->queue_lock); } static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) @@ -1380,6 +1382,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, struct nvme_tcp_queue *queue = &ctrl->queues[qid]; int ret, rcv_pdu_size; + mutex_init(&queue->queue_lock); queue->ctrl = ctrl; init_llist_head(&queue->req_list); INIT_LIST_HEAD(&queue->send_list); @@ -1398,7 +1401,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (ret) { dev_err(nctrl->device, "failed to create socket: %d\n", ret); - return ret; + goto err_destroy_mutex; } /* Single syn retry */ @@ -1507,6 +1510,8 @@ err_crypto: err_sock: sock_release(queue->sock); queue->sock = NULL; +err_destroy_mutex: + mutex_destroy(&queue->queue_lock); return ret; } @@ -1534,9 +1539,10 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; - if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) - return; - __nvme_tcp_stop_queue(queue); + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) + __nvme_tcp_stop_queue(queue); + mutex_unlock(&queue->queue_lock); } static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 8d90235e4fcc..dc1ea468b182 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -487,8 +487,10 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) /* return an all zeroed buffer if we can't find an active namespace */ ns = nvmet_find_namespace(ctrl, req->cmd->identify.nsid); - if (!ns) + if (!ns) { + status = NVME_SC_INVALID_NS; goto done; + } nvmet_ns_revalidate(ns); @@ -541,7 +543,9 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) id->nsattr |= (1 << 0); nvmet_put_namespace(ns); done: - status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + if (!status) + status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + kfree(id); out: nvmet_req_complete(req, status); diff --git a/drivers/of/device.c b/drivers/of/device.c index aedfaaafd3e7..1122daa8e273 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -162,9 +162,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np, mask = DMA_BIT_MASK(ilog2(end) + 1); dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; - /* ...but only set bus limit if we found valid dma-ranges earlier */ - if (!ret) + /* ...but only set bus limit and range map if we found valid dma-ranges earlier */ + if (!ret) { dev->bus_dma_limit = end; + dev->dma_range_map = map; + } coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", @@ -172,6 +174,9 @@ int of_dma_configure_id(struct device *dev, struct device_node *np, iommu = of_iommu_configure(dev, np, id); if (PTR_ERR(iommu) == -EPROBE_DEFER) { + /* Don't touch range map if it wasn't set from a valid dma-ranges */ + if (!ret) + dev->dma_range_map = NULL; kfree(map); return -EPROBE_DEFER; } @@ -181,7 +186,6 @@ int of_dma_configure_id(struct device *dev, struct device_node *np, arch_setup_dma_ops(dev, dma_start, size, iommu, coherent); - dev->dma_range_map = map; return 0; } EXPORT_SYMBOL_GPL(of_dma_configure_id); diff --git a/drivers/phy/ingenic/Makefile b/drivers/phy/ingenic/Makefile index 65d5ea00fc9d..1cb158d7233f 100644 --- a/drivers/phy/ingenic/Makefile +++ b/drivers/phy/ingenic/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += phy-ingenic-usb.o +obj-$(CONFIG_PHY_INGENIC_USB) += phy-ingenic-usb.o diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig index d38def43b1bf..55f8e6c048ab 100644 --- a/drivers/phy/mediatek/Kconfig +++ b/drivers/phy/mediatek/Kconfig @@ -49,7 +49,9 @@ config PHY_MTK_HDMI config PHY_MTK_MIPI_DSI tristate "MediaTek MIPI-DSI Driver" - depends on ARCH_MEDIATEK && OF + depends on ARCH_MEDIATEK || COMPILE_TEST + depends on COMMON_CLK + depends on OF select GENERIC_PHY help Support MIPI DSI for Mediatek SoCs. diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index 442522ba487f..4728e2bff662 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -662,35 +662,42 @@ static int cpcap_usb_phy_probe(struct platform_device *pdev) generic_phy = devm_phy_create(ddata->dev, NULL, &ops); if (IS_ERR(generic_phy)) { error = PTR_ERR(generic_phy); - return PTR_ERR(generic_phy); + goto out_reg_disable; } phy_set_drvdata(generic_phy, ddata); phy_provider = devm_of_phy_provider_register(ddata->dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); + if (IS_ERR(phy_provider)) { + error = PTR_ERR(phy_provider); + goto out_reg_disable; + } error = cpcap_usb_init_optional_pins(ddata); if (error) - return error; + goto out_reg_disable; cpcap_usb_init_optional_gpios(ddata); error = cpcap_usb_init_iio(ddata); if (error) - return error; + goto out_reg_disable; error = cpcap_usb_init_interrupts(pdev, ddata); if (error) - return error; + goto out_reg_disable; usb_add_phy_dev(&ddata->phy); atomic_set(&ddata->active, 1); schedule_delayed_work(&ddata->detect_work, msecs_to_jiffies(1)); return 0; + +out_reg_disable: + regulator_disable(ddata->vusb); + + return error; } static int cpcap_usb_phy_remove(struct platform_device *pdev) diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index 34803a6c7664..5c1a109842a7 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -347,7 +347,7 @@ FUNC_GROUP_DECL(RMII4, F24, E23, E24, E25, C25, C24, B26, B25, B24); #define D22 40 SIG_EXPR_LIST_DECL_SESG(D22, SD1CLK, SD1, SIG_DESC_SET(SCU414, 8)); -SIG_EXPR_LIST_DECL_SEMG(D22, PWM8, PWM8G0, PWM8, SIG_DESC_SET(SCU414, 8)); +SIG_EXPR_LIST_DECL_SEMG(D22, PWM8, PWM8G0, PWM8, SIG_DESC_SET(SCU4B4, 8)); PIN_DECL_2(D22, GPIOF0, SD1CLK, PWM8); GROUP_DECL(PWM8G0, D22); diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 7aeb552d16ce..72f17f26acd8 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -920,6 +920,10 @@ int mtk_pinconf_adv_pull_set(struct mtk_pinctrl *hw, err = hw->soc->bias_set(hw, desc, pullup); if (err) return err; + } else if (hw->soc->bias_set_combo) { + err = hw->soc->bias_set_combo(hw, desc, pullup, arg); + if (err) + return err; } else { return -ENOTSUPP; } diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index d4ea10803fd9..abfe11c7b49f 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -949,7 +949,6 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s, } else { int irq = chip->to_irq(chip, offset); const int pullidx = pull ? 1 : 0; - bool wake; int val; static const char * const pulls[] = { "none ", diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 53a6a24bd052..3ea163498647 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -37,11 +37,11 @@ #define JZ4740_GPIO_TRIG 0x70 #define JZ4740_GPIO_FLAG 0x80 -#define JZ4760_GPIO_INT 0x10 -#define JZ4760_GPIO_PAT1 0x30 -#define JZ4760_GPIO_PAT0 0x40 -#define JZ4760_GPIO_FLAG 0x50 -#define JZ4760_GPIO_PEN 0x70 +#define JZ4770_GPIO_INT 0x10 +#define JZ4770_GPIO_PAT1 0x30 +#define JZ4770_GPIO_PAT0 0x40 +#define JZ4770_GPIO_FLAG 0x50 +#define JZ4770_GPIO_PEN 0x70 #define X1830_GPIO_PEL 0x110 #define X1830_GPIO_PEH 0x120 @@ -1688,8 +1688,8 @@ static inline bool ingenic_gpio_get_value(struct ingenic_gpio_chip *jzgc, static void ingenic_gpio_set_value(struct ingenic_gpio_chip *jzgc, u8 offset, int value) { - if (jzgc->jzpc->info->version >= ID_JZ4760) - ingenic_gpio_set_bit(jzgc, JZ4760_GPIO_PAT0, offset, !!value); + if (jzgc->jzpc->info->version >= ID_JZ4770) + ingenic_gpio_set_bit(jzgc, JZ4770_GPIO_PAT0, offset, !!value); else ingenic_gpio_set_bit(jzgc, JZ4740_GPIO_DATA, offset, !!value); } @@ -1718,9 +1718,9 @@ static void irq_set_type(struct ingenic_gpio_chip *jzgc, break; } - if (jzgc->jzpc->info->version >= ID_JZ4760) { - reg1 = JZ4760_GPIO_PAT1; - reg2 = JZ4760_GPIO_PAT0; + if (jzgc->jzpc->info->version >= ID_JZ4770) { + reg1 = JZ4770_GPIO_PAT1; + reg2 = JZ4770_GPIO_PAT0; } else { reg1 = JZ4740_GPIO_TRIG; reg2 = JZ4740_GPIO_DIR; @@ -1758,8 +1758,8 @@ static void ingenic_gpio_irq_enable(struct irq_data *irqd) struct ingenic_gpio_chip *jzgc = gpiochip_get_data(gc); int irq = irqd->hwirq; - if (jzgc->jzpc->info->version >= ID_JZ4760) - ingenic_gpio_set_bit(jzgc, JZ4760_GPIO_INT, irq, true); + if (jzgc->jzpc->info->version >= ID_JZ4770) + ingenic_gpio_set_bit(jzgc, JZ4770_GPIO_INT, irq, true); else ingenic_gpio_set_bit(jzgc, JZ4740_GPIO_SELECT, irq, true); @@ -1774,8 +1774,8 @@ static void ingenic_gpio_irq_disable(struct irq_data *irqd) ingenic_gpio_irq_mask(irqd); - if (jzgc->jzpc->info->version >= ID_JZ4760) - ingenic_gpio_set_bit(jzgc, JZ4760_GPIO_INT, irq, false); + if (jzgc->jzpc->info->version >= ID_JZ4770) + ingenic_gpio_set_bit(jzgc, JZ4770_GPIO_INT, irq, false); else ingenic_gpio_set_bit(jzgc, JZ4740_GPIO_SELECT, irq, false); } @@ -1799,8 +1799,8 @@ static void ingenic_gpio_irq_ack(struct irq_data *irqd) irq_set_type(jzgc, irq, IRQ_TYPE_LEVEL_HIGH); } - if (jzgc->jzpc->info->version >= ID_JZ4760) - ingenic_gpio_set_bit(jzgc, JZ4760_GPIO_FLAG, irq, false); + if (jzgc->jzpc->info->version >= ID_JZ4770) + ingenic_gpio_set_bit(jzgc, JZ4770_GPIO_FLAG, irq, false); else ingenic_gpio_set_bit(jzgc, JZ4740_GPIO_DATA, irq, true); } @@ -1856,8 +1856,8 @@ static void ingenic_gpio_irq_handler(struct irq_desc *desc) chained_irq_enter(irq_chip, desc); - if (jzgc->jzpc->info->version >= ID_JZ4760) - flag = ingenic_gpio_read_reg(jzgc, JZ4760_GPIO_FLAG); + if (jzgc->jzpc->info->version >= ID_JZ4770) + flag = ingenic_gpio_read_reg(jzgc, JZ4770_GPIO_FLAG); else flag = ingenic_gpio_read_reg(jzgc, JZ4740_GPIO_FLAG); @@ -1938,9 +1938,9 @@ static int ingenic_gpio_get_direction(struct gpio_chip *gc, unsigned int offset) struct ingenic_pinctrl *jzpc = jzgc->jzpc; unsigned int pin = gc->base + offset; - if (jzpc->info->version >= ID_JZ4760) { - if (ingenic_get_pin_config(jzpc, pin, JZ4760_GPIO_INT) || - ingenic_get_pin_config(jzpc, pin, JZ4760_GPIO_PAT1)) + if (jzpc->info->version >= ID_JZ4770) { + if (ingenic_get_pin_config(jzpc, pin, JZ4770_GPIO_INT) || + ingenic_get_pin_config(jzpc, pin, JZ4770_GPIO_PAT1)) return GPIO_LINE_DIRECTION_IN; return GPIO_LINE_DIRECTION_OUT; } @@ -1991,20 +1991,20 @@ static int ingenic_pinmux_set_pin_fn(struct ingenic_pinctrl *jzpc, 'A' + offt, idx, func); if (jzpc->info->version >= ID_X1000) { - ingenic_shadow_config_pin(jzpc, pin, JZ4760_GPIO_INT, false); + ingenic_shadow_config_pin(jzpc, pin, JZ4770_GPIO_INT, false); ingenic_shadow_config_pin(jzpc, pin, GPIO_MSK, false); - ingenic_shadow_config_pin(jzpc, pin, JZ4760_GPIO_PAT1, func & 0x2); - ingenic_shadow_config_pin(jzpc, pin, JZ4760_GPIO_PAT0, func & 0x1); + ingenic_shadow_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, func & 0x2); + ingenic_shadow_config_pin(jzpc, pin, JZ4770_GPIO_PAT0, func & 0x1); ingenic_shadow_config_pin_load(jzpc, pin); - } else if (jzpc->info->version >= ID_JZ4760) { - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_INT, false); + } else if (jzpc->info->version >= ID_JZ4770) { + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_INT, false); ingenic_config_pin(jzpc, pin, GPIO_MSK, false); - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_PAT1, func & 0x2); - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_PAT0, func & 0x1); + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, func & 0x2); + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT0, func & 0x1); } else { ingenic_config_pin(jzpc, pin, JZ4740_GPIO_FUNC, true); ingenic_config_pin(jzpc, pin, JZ4740_GPIO_TRIG, func & 0x2); - ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, func > 0); + ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, func & 0x1); } return 0; @@ -2057,14 +2057,14 @@ static int ingenic_pinmux_gpio_set_direction(struct pinctrl_dev *pctldev, 'A' + offt, idx, input ? "in" : "out"); if (jzpc->info->version >= ID_X1000) { - ingenic_shadow_config_pin(jzpc, pin, JZ4760_GPIO_INT, false); + ingenic_shadow_config_pin(jzpc, pin, JZ4770_GPIO_INT, false); ingenic_shadow_config_pin(jzpc, pin, GPIO_MSK, true); - ingenic_shadow_config_pin(jzpc, pin, JZ4760_GPIO_PAT1, input); + ingenic_shadow_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input); ingenic_shadow_config_pin_load(jzpc, pin); - } else if (jzpc->info->version >= ID_JZ4760) { - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_INT, false); + } else if (jzpc->info->version >= ID_JZ4770) { + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_INT, false); ingenic_config_pin(jzpc, pin, GPIO_MSK, true); - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_PAT1, input); + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input); } else { ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, false); ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, !input); @@ -2091,8 +2091,8 @@ static int ingenic_pinconf_get(struct pinctrl_dev *pctldev, unsigned int offt = pin / PINS_PER_GPIO_CHIP; bool pull; - if (jzpc->info->version >= ID_JZ4760) - pull = !ingenic_get_pin_config(jzpc, pin, JZ4760_GPIO_PEN); + if (jzpc->info->version >= ID_JZ4770) + pull = !ingenic_get_pin_config(jzpc, pin, JZ4770_GPIO_PEN); else pull = !ingenic_get_pin_config(jzpc, pin, JZ4740_GPIO_PULL_DIS); @@ -2141,8 +2141,8 @@ static void ingenic_set_bias(struct ingenic_pinctrl *jzpc, REG_SET(X1830_GPIO_PEH), bias << idxh); } - } else if (jzpc->info->version >= ID_JZ4760) { - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_PEN, !bias); + } else if (jzpc->info->version >= ID_JZ4770) { + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PEN, !bias); } else { ingenic_config_pin(jzpc, pin, JZ4740_GPIO_PULL_DIS, !bias); } @@ -2151,8 +2151,8 @@ static void ingenic_set_bias(struct ingenic_pinctrl *jzpc, static void ingenic_set_output_level(struct ingenic_pinctrl *jzpc, unsigned int pin, bool high) { - if (jzpc->info->version >= ID_JZ4760) - ingenic_config_pin(jzpc, pin, JZ4760_GPIO_PAT0, high); + if (jzpc->info->version >= ID_JZ4770) + ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT0, high); else ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DATA, high); } diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index e051aecf95c4..d70caecd21d2 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -51,6 +51,7 @@ * @dual_edge_irqs: Bitmap of irqs that need sw emulated dual edge * detection. * @skip_wake_irqs: Skip IRQs that are handled by wakeup interrupt controller + * @disabled_for_mux: These IRQs were disabled because we muxed away. * @soc: Reference to soc_data of platform specific data. * @regs: Base addresses for the TLMM tiles. * @phys_base: Physical base address @@ -72,6 +73,7 @@ struct msm_pinctrl { DECLARE_BITMAP(dual_edge_irqs, MAX_NR_GPIO); DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO); DECLARE_BITMAP(skip_wake_irqs, MAX_NR_GPIO); + DECLARE_BITMAP(disabled_for_mux, MAX_NR_GPIO); const struct msm_pinctrl_soc_data *soc; void __iomem *regs[MAX_NR_TILES]; @@ -96,6 +98,14 @@ MSM_ACCESSOR(intr_cfg) MSM_ACCESSOR(intr_status) MSM_ACCESSOR(intr_target) +static void msm_ack_intr_status(struct msm_pinctrl *pctrl, + const struct msm_pingroup *g) +{ + u32 val = g->intr_ack_high ? BIT(g->intr_status_bit) : 0; + + msm_writel_intr_status(val, pctrl, g); +} + static int msm_get_groups_count(struct pinctrl_dev *pctldev) { struct msm_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); @@ -171,6 +181,10 @@ static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned group) { struct msm_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); + struct gpio_chip *gc = &pctrl->chip; + unsigned int irq = irq_find_mapping(gc->irq.domain, group); + struct irq_data *d = irq_get_irq_data(irq); + unsigned int gpio_func = pctrl->soc->gpio_func; const struct msm_pingroup *g; unsigned long flags; u32 val, mask; @@ -187,6 +201,20 @@ static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev, if (WARN_ON(i == g->nfuncs)) return -EINVAL; + /* + * If an GPIO interrupt is setup on this pin then we need special + * handling. Specifically interrupt detection logic will still see + * the pin twiddle even when we're muxed away. + * + * When we see a pin with an interrupt setup on it then we'll disable + * (mask) interrupts on it when we mux away until we mux back. Note + * that disable_irq() refcounts and interrupts are disabled as long as + * at least one disable_irq() has been called. + */ + if (d && i != gpio_func && + !test_and_set_bit(d->hwirq, pctrl->disabled_for_mux)) + disable_irq(irq); + raw_spin_lock_irqsave(&pctrl->lock, flags); val = msm_readl_ctl(pctrl, g); @@ -196,6 +224,20 @@ static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev, raw_spin_unlock_irqrestore(&pctrl->lock, flags); + if (d && i == gpio_func && + test_and_clear_bit(d->hwirq, pctrl->disabled_for_mux)) { + /* + * Clear interrupts detected while not GPIO since we only + * masked things. + */ + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, false); + else + msm_ack_intr_status(pctrl, g); + + enable_irq(irq); + } + return 0; } @@ -210,8 +252,7 @@ static int msm_pinmux_request_gpio(struct pinctrl_dev *pctldev, if (!g->nfuncs) return 0; - /* For now assume function 0 is GPIO because it always is */ - return msm_pinmux_set_mux(pctldev, g->funcs[0], offset); + return msm_pinmux_set_mux(pctldev, g->funcs[pctrl->soc->gpio_func], offset); } static const struct pinmux_ops msm_pinmux_ops = { @@ -774,7 +815,7 @@ static void msm_gpio_irq_mask(struct irq_data *d) raw_spin_unlock_irqrestore(&pctrl->lock, flags); } -static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) +static void msm_gpio_irq_unmask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct msm_pinctrl *pctrl = gpiochip_get_data(gc); @@ -792,17 +833,6 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) raw_spin_lock_irqsave(&pctrl->lock, flags); - if (status_clear) { - /* - * clear the interrupt status bit before unmask to avoid - * any erroneous interrupts that would have got latched - * when the interrupt is not in use. - */ - val = msm_readl_intr_status(pctrl, g); - val &= ~BIT(g->intr_status_bit); - msm_writel_intr_status(val, pctrl, g); - } - val = msm_readl_intr_cfg(pctrl, g); val |= BIT(g->intr_raw_status_bit); val |= BIT(g->intr_enable_bit); @@ -822,7 +852,7 @@ static void msm_gpio_irq_enable(struct irq_data *d) irq_chip_enable_parent(d); if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) - msm_gpio_irq_clear_unmask(d, true); + msm_gpio_irq_unmask(d); } static void msm_gpio_irq_disable(struct irq_data *d) @@ -837,11 +867,6 @@ static void msm_gpio_irq_disable(struct irq_data *d) msm_gpio_irq_mask(d); } -static void msm_gpio_irq_unmask(struct irq_data *d) -{ - msm_gpio_irq_clear_unmask(d, false); -} - /** * msm_gpio_update_dual_edge_parent() - Prime next edge for IRQs handled by parent. * @d: The irq dta. @@ -894,7 +919,6 @@ static void msm_gpio_irq_ack(struct irq_data *d) struct msm_pinctrl *pctrl = gpiochip_get_data(gc); const struct msm_pingroup *g; unsigned long flags; - u32 val; if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) @@ -906,12 +930,7 @@ static void msm_gpio_irq_ack(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); - val = msm_readl_intr_status(pctrl, g); - if (g->intr_ack_high) - val |= BIT(g->intr_status_bit); - else - val &= ~BIT(g->intr_status_bit); - msm_writel_intr_status(val, pctrl, g); + msm_ack_intr_status(pctrl, g); if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) msm_gpio_update_dual_edge_pos(pctrl, g, d); @@ -936,6 +955,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) struct msm_pinctrl *pctrl = gpiochip_get_data(gc); const struct msm_pingroup *g; unsigned long flags; + bool was_enabled; u32 val; if (msm_gpio_needs_dual_edge_parent_workaround(d, type)) { @@ -997,6 +1017,7 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) * could cause the INTR_STATUS to be set for EDGE interrupts. */ val = msm_readl_intr_cfg(pctrl, g); + was_enabled = val & BIT(g->intr_raw_status_bit); val |= BIT(g->intr_raw_status_bit); if (g->intr_detection_width == 2) { val &= ~(3 << g->intr_detection_bit); @@ -1046,6 +1067,14 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) } msm_writel_intr_cfg(val, pctrl, g); + /* + * The first time we set RAW_STATUS_EN it could trigger an interrupt. + * Clear the interrupt. This is safe because we have + * IRQCHIP_SET_TYPE_MASKED. + */ + if (!was_enabled) + msm_ack_intr_status(pctrl, g); + if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) msm_gpio_update_dual_edge_pos(pctrl, g, d); @@ -1099,16 +1128,11 @@ static int msm_gpio_irq_reqres(struct irq_data *d) } /* - * Clear the interrupt that may be pending before we enable - * the line. - * This is especially a problem with the GPIOs routed to the - * PDC. These GPIOs are direct-connect interrupts to the GIC. - * Disabling the interrupt line at the PDC does not prevent - * the interrupt from being latched at the GIC. The state at - * GIC needs to be cleared before enabling. + * The disable / clear-enable workaround we do in msm_pinmux_set_mux() + * only works if disable is not lazy since we only clear any bogus + * interrupt in hardware. Explicitly mark the interrupt as UNLAZY. */ - if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) - irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + irq_set_status_flags(d->irq, IRQ_DISABLE_UNLAZY); return 0; out: diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 333f99243c43..e31a5167c91e 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -118,6 +118,7 @@ struct msm_gpio_wakeirq_map { * @wakeirq_dual_edge_errata: If true then GPIOs using the wakeirq_map need * to be aware that their parent can't handle dual * edge interrupts. + * @gpio_func: Which function number is GPIO (usually 0). */ struct msm_pinctrl_soc_data { const struct pinctrl_pin_desc *pins; @@ -134,6 +135,7 @@ struct msm_pinctrl_soc_data { const struct msm_gpio_wakeirq_map *wakeirq_map; unsigned int nwakeirq_map; bool wakeirq_dual_edge_errata; + unsigned int gpio_func; }; extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops; diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 33040b0b3b79..2c941cdac9ee 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -5,6 +5,7 @@ menuconfig SURFACE_PLATFORMS bool "Microsoft Surface Platform-Specific Device Drivers" + depends on ACPI default y help Say Y here to get to see options for platform-specific device drivers @@ -29,20 +30,19 @@ config SURFACE3_WMI config SURFACE_3_BUTTON tristate "Power/home/volume buttons driver for Microsoft Surface 3 tablet" - depends on ACPI && KEYBOARD_GPIO && I2C + depends on KEYBOARD_GPIO && I2C help This driver handles the power/home/volume buttons on the Microsoft Surface 3 tablet. config SURFACE_3_POWER_OPREGION tristate "Surface 3 battery platform operation region support" - depends on ACPI && I2C + depends on I2C help This driver provides support for ACPI operation region of the Surface 3 battery platform driver. config SURFACE_GPE tristate "Surface GPE/Lid Support Driver" - depends on ACPI depends on DMI help This driver marks the GPEs related to the ACPI lid device found on @@ -52,7 +52,7 @@ config SURFACE_GPE config SURFACE_PRO3_BUTTON tristate "Power/home/volume buttons driver for Microsoft Surface Pro 3/4 tablet" - depends on ACPI && INPUT + depends on INPUT help This driver handles the power/home/volume buttons on the Microsoft Surface Pro 3/4 tablet. diff --git a/drivers/platform/surface/surface_gpe.c b/drivers/platform/surface/surface_gpe.c index e49e5d6d5d4e..86f6991b1215 100644 --- a/drivers/platform/surface/surface_gpe.c +++ b/drivers/platform/surface/surface_gpe.c @@ -181,12 +181,12 @@ static int surface_lid_enable_wakeup(struct device *dev, bool enable) return 0; } -static int surface_gpe_suspend(struct device *dev) +static int __maybe_unused surface_gpe_suspend(struct device *dev) { return surface_lid_enable_wakeup(dev, true); } -static int surface_gpe_resume(struct device *dev) +static int __maybe_unused surface_gpe_resume(struct device *dev) { return surface_lid_enable_wakeup(dev, false); } diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 0102bf1c7916..ef8342572463 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -85,7 +85,7 @@ static inline void amd_pmc_reg_write(struct amd_pmc_dev *dev, int reg_offset, u3 iowrite32(val, dev->regbase + reg_offset); } -#if CONFIG_DEBUG_FS +#ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) { struct amd_pmc_dev *dev = s->private; diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index ecd477964d11..18bf8aeb5f87 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -247,7 +247,8 @@ static int hp_wmi_perform_query(int query, enum hp_wmi_command command, ret = bios_return->return_code; if (ret) { - if (ret != HPWMI_RET_UNKNOWN_CMDTYPE) + if (ret != HPWMI_RET_UNKNOWN_COMMAND && + ret != HPWMI_RET_UNKNOWN_CMDTYPE) pr_warn("query 0x%x returned error 0x%x\n", query, ret); goto out_free; } diff --git a/drivers/platform/x86/i2c-multi-instantiate.c b/drivers/platform/x86/i2c-multi-instantiate.c index b457b0babde3..2cce82579d09 100644 --- a/drivers/platform/x86/i2c-multi-instantiate.c +++ b/drivers/platform/x86/i2c-multi-instantiate.c @@ -164,13 +164,29 @@ static const struct i2c_inst_data bsg2150_data[] = { {} }; -static const struct i2c_inst_data int3515_data[] = { - { "tps6598x", IRQ_RESOURCE_APIC, 0 }, - { "tps6598x", IRQ_RESOURCE_APIC, 1 }, - { "tps6598x", IRQ_RESOURCE_APIC, 2 }, - { "tps6598x", IRQ_RESOURCE_APIC, 3 }, - {} -}; +/* + * Device with _HID INT3515 (TI PD controllers) has some unresolved interrupt + * issues. The most common problem seen is interrupt flood. + * + * There are at least two known causes. Firstly, on some boards, the + * I2CSerialBus resource index does not match the Interrupt resource, i.e. they + * are not one-to-one mapped like in the array below. Secondly, on some boards + * the IRQ line from the PD controller is not actually connected at all. But the + * interrupt flood is also seen on some boards where those are not a problem, so + * there are some other problems as well. + * + * Because of the issues with the interrupt, the device is disabled for now. If + * you wish to debug the issues, uncomment the below, and add an entry for the + * INT3515 device to the i2c_multi_instance_ids table. + * + * static const struct i2c_inst_data int3515_data[] = { + * { "tps6598x", IRQ_RESOURCE_APIC, 0 }, + * { "tps6598x", IRQ_RESOURCE_APIC, 1 }, + * { "tps6598x", IRQ_RESOURCE_APIC, 2 }, + * { "tps6598x", IRQ_RESOURCE_APIC, 3 }, + * { } + * }; + */ /* * Note new device-ids must also be added to i2c_multi_instantiate_ids in @@ -179,7 +195,6 @@ static const struct i2c_inst_data int3515_data[] = { static const struct acpi_device_id i2c_multi_inst_acpi_ids[] = { { "BSG1160", (unsigned long)bsg1160_data }, { "BSG2150", (unsigned long)bsg2150_data }, - { "INT3515", (unsigned long)int3515_data }, { } }; MODULE_DEVICE_TABLE(acpi, i2c_multi_inst_acpi_ids); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 7598cd46cf60..5b81bafa5c16 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -92,6 +92,7 @@ struct ideapad_private { struct dentry *debug; unsigned long cfg; bool has_hw_rfkill_switch; + bool has_touchpad_switch; const char *fnesc_guid; }; @@ -535,7 +536,9 @@ static umode_t ideapad_is_visible(struct kobject *kobj, } else if (attr == &dev_attr_fn_lock.attr) { supported = acpi_has_method(priv->adev->handle, "HALS") && acpi_has_method(priv->adev->handle, "SALS"); - } else + } else if (attr == &dev_attr_touchpad.attr) + supported = priv->has_touchpad_switch; + else supported = true; return supported ? attr->mode : 0; @@ -867,6 +870,9 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv) { unsigned long value; + if (!priv->has_touchpad_switch) + return; + /* Without reading from EC touchpad LED doesn't switch state */ if (!read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value)) { /* Some IdeaPads don't really turn off touchpad - they only @@ -989,6 +995,9 @@ static int ideapad_acpi_add(struct platform_device *pdev) priv->platform_device = pdev; priv->has_hw_rfkill_switch = dmi_check_system(hw_rfkill_list); + /* Most ideapads with ELAN0634 touchpad don't use EC touchpad switch */ + priv->has_touchpad_switch = !acpi_dev_present("ELAN0634", NULL, -1); + ret = ideapad_sysfs_init(priv); if (ret) return ret; @@ -1006,6 +1015,10 @@ static int ideapad_acpi_add(struct platform_device *pdev) if (!priv->has_hw_rfkill_switch) write_ec_cmd(priv->adev->handle, VPCCMD_W_RF, 1); + /* The same for Touchpad */ + if (!priv->has_touchpad_switch) + write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, 1); + for (i = 0; i < IDEAPAD_RFKILL_DEV_NUM; i++) if (test_bit(ideapad_rfk_data[i].cfgbit, &priv->cfg)) ideapad_register_rfkill(priv, i); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 3b49a1f4061b..30a9062d2b4b 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -207,19 +207,19 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion 13 x360 PC"), }, }, { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion 13 x360 PC"), + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271"), }, }, { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7352"), }, }, {} /* Array terminator */ diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index e03df2881dc6..f3e8eca8d86d 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8783,6 +8783,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '1', 'T', TPACPI_FAN_2CTL), /* P71 */ TPACPI_Q_LNV3('N', '1', 'U', TPACPI_FAN_2CTL), /* P51 */ TPACPI_Q_LNV3('N', '2', 'C', TPACPI_FAN_2CTL), /* P52 / P72 */ + TPACPI_Q_LNV3('N', '2', 'N', TPACPI_FAN_2CTL), /* P53 / P73 */ TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */ TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ @@ -9951,9 +9952,9 @@ static int tpacpi_proxsensor_init(struct ibm_init_struct *iibm) if ((palm_err == -ENODEV) && (lap_err == -ENODEV)) return 0; /* Otherwise, if there was an error return it */ - if (palm_err && (palm_err != ENODEV)) + if (palm_err && (palm_err != -ENODEV)) return palm_err; - if (lap_err && (lap_err != ENODEV)) + if (lap_err && (lap_err != -ENODEV)) return lap_err; if (has_palmsensor) { diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 5783139d0a11..c4de932302d6 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -263,6 +263,16 @@ static const struct ts_dmi_data digma_citi_e200_data = { .properties = digma_citi_e200_props, }; +static const struct property_entry estar_beauty_hd_props[] = { + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + { } +}; + +static const struct ts_dmi_data estar_beauty_hd_data = { + .acpi_name = "GDIX1001:00", + .properties = estar_beauty_hd_props, +}; + static const struct property_entry gp_electronic_t701_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 960), PROPERTY_ENTRY_U32("touchscreen-size-y", 640), @@ -943,6 +953,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Estar Beauty HD (MID 7316R) */ + .driver_data = (void *)&estar_beauty_hd_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Estar"), + DMI_MATCH(DMI_PRODUCT_NAME, "eSTAR BEAUTY HD Intel Quad core"), + }, + }, + { /* GP-electronic T701 */ .driver_data = (void *)&gp_electronic_t701_data, .matches = { diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index ca03d8e70bd1..67a768fe5b2a 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1813,13 +1813,13 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) { struct regulator_dev *r; struct device *dev = rdev->dev.parent; - int ret; + int ret = 0; /* No supply to resolve? */ if (!rdev->supply_name) return 0; - /* Supply already resolved? */ + /* Supply already resolved? (fast-path without locking contention) */ if (rdev->supply) return 0; @@ -1829,7 +1829,7 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) /* Did the lookup explicitly defer for us? */ if (ret == -EPROBE_DEFER) - return ret; + goto out; if (have_full_constraints()) { r = dummy_regulator_rdev; @@ -1837,15 +1837,18 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) } else { dev_err(dev, "Failed to resolve %s-supply for %s\n", rdev->supply_name, rdev->desc->name); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out; } } if (r == rdev) { dev_err(dev, "Supply for %s (%s) resolved to itself\n", rdev->desc->name, rdev->supply_name); - if (!have_full_constraints()) - return -EINVAL; + if (!have_full_constraints()) { + ret = -EINVAL; + goto out; + } r = dummy_regulator_rdev; get_device(&r->dev); } @@ -1859,7 +1862,8 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (r->dev.parent && r->dev.parent != rdev->dev.parent) { if (!device_is_bound(r->dev.parent)) { put_device(&r->dev); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out; } } @@ -1867,15 +1871,32 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) ret = regulator_resolve_supply(r); if (ret < 0) { put_device(&r->dev); - return ret; + goto out; + } + + /* + * Recheck rdev->supply with rdev->mutex lock held to avoid a race + * between rdev->supply null check and setting rdev->supply in + * set_supply() from concurrent tasks. + */ + regulator_lock(rdev); + + /* Supply just resolved by a concurrent task? */ + if (rdev->supply) { + regulator_unlock(rdev); + put_device(&r->dev); + goto out; } ret = set_supply(rdev, r); if (ret < 0) { + regulator_unlock(rdev); put_device(&r->dev); - return ret; + goto out; } + regulator_unlock(rdev); + /* * In set_machine_constraints() we may have turned this regulator on * but we couldn't propagate to the supply if it hadn't been resolved @@ -1886,11 +1907,12 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (ret < 0) { _regulator_put(rdev->supply); rdev->supply = NULL; - return ret; + goto out; } } - return 0; +out: + return ret; } /* Internal regulator request function */ diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 51e80bc70d42..68a9ac6f2fe1 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -805,6 +805,14 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) spin_lock_irq(&rtc_lock); + /* Ensure that the RTC is accessible. Bit 0-6 must be 0! */ + if ((CMOS_READ(RTC_VALID) & 0x7f) != 0) { + spin_unlock_irq(&rtc_lock); + dev_warn(dev, "not accessible\n"); + retval = -ENXIO; + goto cleanup1; + } + if (!(flags & CMOS_RTC_FLAGS_NOFREQ)) { /* force periodic irq to CMOS reset default of 1024Hz; * diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index 972a5b9a629d..f83c13818af3 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -21,6 +21,13 @@ unsigned int mc146818_get_time(struct rtc_time *time) again: spin_lock_irqsave(&rtc_lock, flags); + /* Ensure that the RTC is accessible. Bit 0-6 must be 0! */ + if (WARN_ON_ONCE((CMOS_READ(RTC_VALID) & 0x7f) != 0)) { + spin_unlock_irqrestore(&rtc_lock, flags); + memset(time, 0xff, sizeof(*time)); + return 0; + } + /* * Check whether there is an update in progress during which the * readout is unspecified. The maximum update time is ~2ms. Poll diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 16bb135c20aa..03d27ee9cac6 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -1874,18 +1874,26 @@ void dasd_path_create_kobjects(struct dasd_device *device) } EXPORT_SYMBOL(dasd_path_create_kobjects); -/* - * As we keep kobjects for the lifetime of a device, this function must not be - * called anywhere but in the context of offlining a device. - */ -void dasd_path_remove_kobj(struct dasd_device *device, int chp) +static void dasd_path_remove_kobj(struct dasd_device *device, int chp) { if (device->path[chp].in_sysfs) { kobject_put(&device->path[chp].kobj); device->path[chp].in_sysfs = false; } } -EXPORT_SYMBOL(dasd_path_remove_kobj); + +/* + * As we keep kobjects for the lifetime of a device, this function must not be + * called anywhere but in the context of offlining a device. + */ +void dasd_path_remove_kobjects(struct dasd_device *device) +{ + int i; + + for (i = 0; i < 8; i++) + dasd_path_remove_kobj(device, i); +} +EXPORT_SYMBOL(dasd_path_remove_kobjects); int dasd_add_sysfs_files(struct ccw_device *cdev) { diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 3caa1ee5f4b0..65eb87cbbb9b 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1036,7 +1036,6 @@ static void dasd_eckd_clear_conf_data(struct dasd_device *device) device->path[i].ssid = 0; device->path[i].chpid = 0; dasd_path_notoper(device, i); - dasd_path_remove_kobj(device, i); } } @@ -2173,6 +2172,7 @@ out_err2: device->block = NULL; out_err1: dasd_eckd_clear_conf_data(device); + dasd_path_remove_kobjects(device); kfree(device->private); device->private = NULL; return rc; @@ -2191,6 +2191,7 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device) private->vdsneq = NULL; private->gneq = NULL; dasd_eckd_clear_conf_data(device); + dasd_path_remove_kobjects(device); } static struct dasd_ccw_req * diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 3bc008f9136c..b8a04c42d1d2 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -858,7 +858,7 @@ int dasd_add_sysfs_files(struct ccw_device *); void dasd_remove_sysfs_files(struct ccw_device *); void dasd_path_create_kobj(struct dasd_device *, int); void dasd_path_create_kobjects(struct dasd_device *); -void dasd_path_remove_kobj(struct dasd_device *, int); +void dasd_path_remove_kobjects(struct dasd_device *); struct dasd_device *dasd_device_from_cdev(struct ccw_device *); struct dasd_device *dasd_device_from_cdev_locked(struct ccw_device *); diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index be2520cc010b..7dc72cb718b0 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -71,15 +71,11 @@ static int vfio_ap_queue_dev_probe(struct ap_device *apdev) static void vfio_ap_queue_dev_remove(struct ap_device *apdev) { struct vfio_ap_queue *q; - int apid, apqi; mutex_lock(&matrix_dev->lock); q = dev_get_drvdata(&apdev->device); + vfio_ap_mdev_reset_queue(q, 1); dev_set_drvdata(&apdev->device, NULL); - apid = AP_QID_CARD(q->apqn); - apqi = AP_QID_QUEUE(q->apqn); - vfio_ap_mdev_reset_queue(apid, apqi, 1); - vfio_ap_irq_disable(q); kfree(q); mutex_unlock(&matrix_dev->lock); } diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index e0bde8518745..41fc2e4135fe 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -25,6 +25,7 @@ #define VFIO_AP_MDEV_NAME_HWVIRT "VFIO AP Passthrough Device" static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev); +static struct vfio_ap_queue *vfio_ap_find_queue(int apqn); static int match_apqn(struct device *dev, const void *data) { @@ -49,20 +50,15 @@ static struct vfio_ap_queue *vfio_ap_get_queue( int apqn) { struct vfio_ap_queue *q; - struct device *dev; if (!test_bit_inv(AP_QID_CARD(apqn), matrix_mdev->matrix.apm)) return NULL; if (!test_bit_inv(AP_QID_QUEUE(apqn), matrix_mdev->matrix.aqm)) return NULL; - dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL, - &apqn, match_apqn); - if (!dev) - return NULL; - q = dev_get_drvdata(dev); - q->matrix_mdev = matrix_mdev; - put_device(dev); + q = vfio_ap_find_queue(apqn); + if (q) + q->matrix_mdev = matrix_mdev; return q; } @@ -119,13 +115,18 @@ static void vfio_ap_wait_for_irqclear(int apqn) */ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) { - if (q->saved_isc != VFIO_AP_ISC_INVALID && q->matrix_mdev) + if (!q) + return; + if (q->saved_isc != VFIO_AP_ISC_INVALID && + !WARN_ON(!(q->matrix_mdev && q->matrix_mdev->kvm))) { kvm_s390_gisc_unregister(q->matrix_mdev->kvm, q->saved_isc); - if (q->saved_pfn && q->matrix_mdev) + q->saved_isc = VFIO_AP_ISC_INVALID; + } + if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) { vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &q->saved_pfn, 1); - q->saved_pfn = 0; - q->saved_isc = VFIO_AP_ISC_INVALID; + q->saved_pfn = 0; + } } /** @@ -144,7 +145,7 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q) * Returns if ap_aqic function failed with invalid, deconfigured or * checkstopped AP. */ -struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q) +static struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q) { struct ap_qirq_ctrl aqic_gisa = {}; struct ap_queue_status status; @@ -1037,19 +1038,14 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, { struct ap_matrix_mdev *m; - mutex_lock(&matrix_dev->lock); - list_for_each_entry(m, &matrix_dev->mdev_list, node) { - if ((m != matrix_mdev) && (m->kvm == kvm)) { - mutex_unlock(&matrix_dev->lock); + if ((m != matrix_mdev) && (m->kvm == kvm)) return -EPERM; - } } matrix_mdev->kvm = kvm; kvm_get_kvm(kvm); kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook; - mutex_unlock(&matrix_dev->lock); return 0; } @@ -1083,79 +1079,118 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb, return NOTIFY_DONE; } +static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) +{ + kvm_arch_crypto_clear_masks(matrix_mdev->kvm); + matrix_mdev->kvm->arch.crypto.pqap_hook = NULL; + vfio_ap_mdev_reset_queues(matrix_mdev->mdev); + kvm_put_kvm(matrix_mdev->kvm); + matrix_mdev->kvm = NULL; +} + static int vfio_ap_mdev_group_notifier(struct notifier_block *nb, unsigned long action, void *data) { - int ret; + int ret, notify_rc = NOTIFY_OK; struct ap_matrix_mdev *matrix_mdev; if (action != VFIO_GROUP_NOTIFY_SET_KVM) return NOTIFY_OK; matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier); + mutex_lock(&matrix_dev->lock); if (!data) { - matrix_mdev->kvm = NULL; - return NOTIFY_OK; + if (matrix_mdev->kvm) + vfio_ap_mdev_unset_kvm(matrix_mdev); + goto notify_done; } ret = vfio_ap_mdev_set_kvm(matrix_mdev, data); - if (ret) - return NOTIFY_DONE; + if (ret) { + notify_rc = NOTIFY_DONE; + goto notify_done; + } /* If there is no CRYCB pointer, then we can't copy the masks */ - if (!matrix_mdev->kvm->arch.crypto.crycbd) - return NOTIFY_DONE; + if (!matrix_mdev->kvm->arch.crypto.crycbd) { + notify_rc = NOTIFY_DONE; + goto notify_done; + } kvm_arch_crypto_set_masks(matrix_mdev->kvm, matrix_mdev->matrix.apm, matrix_mdev->matrix.aqm, matrix_mdev->matrix.adm); - return NOTIFY_OK; +notify_done: + mutex_unlock(&matrix_dev->lock); + return notify_rc; } -static void vfio_ap_irq_disable_apqn(int apqn) +static struct vfio_ap_queue *vfio_ap_find_queue(int apqn) { struct device *dev; - struct vfio_ap_queue *q; + struct vfio_ap_queue *q = NULL; dev = driver_find_device(&matrix_dev->vfio_ap_drv->driver, NULL, &apqn, match_apqn); if (dev) { q = dev_get_drvdata(dev); - vfio_ap_irq_disable(q); put_device(dev); } + + return q; } -int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, +int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q, unsigned int retry) { struct ap_queue_status status; + int ret; int retry2 = 2; - int apqn = AP_MKQID(apid, apqi); - do { - status = ap_zapq(apqn); - switch (status.response_code) { - case AP_RESPONSE_NORMAL: - while (!status.queue_empty && retry2--) { - msleep(20); - status = ap_tapq(apqn, NULL); - } - WARN_ON_ONCE(retry2 <= 0); - return 0; - case AP_RESPONSE_RESET_IN_PROGRESS: - case AP_RESPONSE_BUSY: + if (!q) + return 0; + +retry_zapq: + status = ap_zapq(q->apqn); + switch (status.response_code) { + case AP_RESPONSE_NORMAL: + ret = 0; + break; + case AP_RESPONSE_RESET_IN_PROGRESS: + if (retry--) { msleep(20); - break; - default: - /* things are really broken, give up */ - return -EIO; + goto retry_zapq; } - } while (retry--); + ret = -EBUSY; + break; + case AP_RESPONSE_Q_NOT_AVAIL: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + WARN_ON_ONCE(status.irq_enabled); + ret = -EBUSY; + goto free_resources; + default: + /* things are really broken, give up */ + WARN(true, "PQAP/ZAPQ completed with invalid rc (%x)\n", + status.response_code); + return -EIO; + } + + /* wait for the reset to take effect */ + while (retry2--) { + if (status.queue_empty && !status.irq_enabled) + break; + msleep(20); + status = ap_tapq(q->apqn, NULL); + } + WARN_ON_ONCE(retry2 <= 0); - return -EBUSY; +free_resources: + vfio_ap_free_aqic_resources(q); + + return ret; } static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev) @@ -1163,13 +1198,15 @@ static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev) int ret; int rc = 0; unsigned long apid, apqi; + struct vfio_ap_queue *q; struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev); for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, matrix_mdev->matrix.apm_max + 1) { for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, matrix_mdev->matrix.aqm_max + 1) { - ret = vfio_ap_mdev_reset_queue(apid, apqi, 1); + q = vfio_ap_find_queue(AP_MKQID(apid, apqi)); + ret = vfio_ap_mdev_reset_queue(q, 1); /* * Regardless whether a queue turns out to be busy, or * is not operational, we need to continue resetting @@ -1177,7 +1214,6 @@ static int vfio_ap_mdev_reset_queues(struct mdev_device *mdev) */ if (ret) rc = ret; - vfio_ap_irq_disable_apqn(AP_MKQID(apid, apqi)); } } @@ -1222,13 +1258,8 @@ static void vfio_ap_mdev_release(struct mdev_device *mdev) struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev); mutex_lock(&matrix_dev->lock); - if (matrix_mdev->kvm) { - kvm_arch_crypto_clear_masks(matrix_mdev->kvm); - matrix_mdev->kvm->arch.crypto.pqap_hook = NULL; - vfio_ap_mdev_reset_queues(mdev); - kvm_put_kvm(matrix_mdev->kvm); - matrix_mdev->kvm = NULL; - } + if (matrix_mdev->kvm) + vfio_ap_mdev_unset_kvm(matrix_mdev); mutex_unlock(&matrix_dev->lock); vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY, diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index f46dde56b464..28e9d9989768 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -88,11 +88,6 @@ struct ap_matrix_mdev { struct mdev_device *mdev; }; -extern int vfio_ap_mdev_register(void); -extern void vfio_ap_mdev_unregister(void); -int vfio_ap_mdev_reset_queue(unsigned int apid, unsigned int apqi, - unsigned int retry); - struct vfio_ap_queue { struct ap_matrix_mdev *matrix_mdev; unsigned long saved_pfn; @@ -100,5 +95,10 @@ struct vfio_ap_queue { #define VFIO_AP_ISC_INVALID 0xff unsigned char saved_isc; }; -struct ap_queue_status vfio_ap_irq_disable(struct vfio_ap_queue *q); + +int vfio_ap_mdev_register(void); +void vfio_ap_mdev_unregister(void); +int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q, + unsigned int retry); + #endif /* _VFIO_AP_PRIVATE_H_ */ diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 28f637042d44..a1da83b0b0ef 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -956,24 +956,6 @@ static inline int qeth_get_elements_for_range(addr_t start, addr_t end) return PFN_UP(end) - PFN_DOWN(start); } -static inline int qeth_get_ip_version(struct sk_buff *skb) -{ - struct vlan_ethhdr *veth = vlan_eth_hdr(skb); - __be16 prot = veth->h_vlan_proto; - - if (prot == htons(ETH_P_8021Q)) - prot = veth->h_vlan_encapsulated_proto; - - switch (prot) { - case htons(ETH_P_IPV6): - return 6; - case htons(ETH_P_IP): - return 4; - default: - return 0; - } -} - static inline int qeth_get_ether_cast_type(struct sk_buff *skb) { u8 *addr = eth_hdr(skb)->h_dest; @@ -984,14 +966,20 @@ static inline int qeth_get_ether_cast_type(struct sk_buff *skb) return RTN_UNICAST; } -static inline struct dst_entry *qeth_dst_check_rcu(struct sk_buff *skb, int ipv) +static inline struct dst_entry *qeth_dst_check_rcu(struct sk_buff *skb, + __be16 proto) { struct dst_entry *dst = skb_dst(skb); struct rt6_info *rt; rt = (struct rt6_info *) dst; - if (dst) - dst = dst_check(dst, (ipv == 6) ? rt6_get_cookie(rt) : 0); + if (dst) { + if (proto == htons(ETH_P_IPV6)) + dst = dst_check(dst, rt6_get_cookie(rt)); + else + dst = dst_check(dst, 0); + } + return dst; } @@ -1014,11 +1002,11 @@ static inline struct in6_addr *qeth_next_hop_v6_rcu(struct sk_buff *skb, return &ipv6_hdr(skb)->daddr; } -static inline void qeth_tx_csum(struct sk_buff *skb, u8 *flags, int ipv) +static inline void qeth_tx_csum(struct sk_buff *skb, u8 *flags, __be16 proto) { *flags |= QETH_HDR_EXT_CSUM_TRANSP_REQ; - if ((ipv == 4 && ip_hdr(skb)->protocol == IPPROTO_UDP) || - (ipv == 6 && ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)) + if ((proto == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_UDP) || + (proto == htons(ETH_P_IPV6) && ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)) *flags |= QETH_HDR_EXT_UDP; } @@ -1067,8 +1055,8 @@ extern const struct device_type qeth_generic_devtype; const char *qeth_get_cardname_short(struct qeth_card *); int qeth_resize_buffer_pool(struct qeth_card *card, unsigned int count); -int qeth_core_load_discipline(struct qeth_card *, enum qeth_discipline_id); -void qeth_core_free_discipline(struct qeth_card *); +int qeth_setup_discipline(struct qeth_card *card, enum qeth_discipline_id disc); +void qeth_remove_discipline(struct qeth_card *card); /* exports for qeth discipline device drivers */ extern struct kmem_cache *qeth_core_header_cache; @@ -1145,10 +1133,10 @@ int qeth_stop(struct net_device *dev); int qeth_vm_request_mac(struct qeth_card *card); int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, + struct qeth_qdio_out_q *queue, __be16 proto, void (*fill_header)(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, unsigned int data_len)); + __be16 proto, unsigned int data_len)); /* exports for OSN */ int qeth_osn_assist(struct net_device *, void *, int); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index cf18d87da41e..89b223885b0c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -825,7 +825,8 @@ static bool qeth_next_hop_is_local_v4(struct qeth_card *card, return false; rcu_read_lock(); - next_hop = qeth_next_hop_v4_rcu(skb, qeth_dst_check_rcu(skb, 4)); + next_hop = qeth_next_hop_v4_rcu(skb, + qeth_dst_check_rcu(skb, htons(ETH_P_IP))); key = ipv4_addr_hash(next_hop); hash_for_each_possible_rcu(card->local_addrs4, tmp, hnode, key) { @@ -851,7 +852,8 @@ static bool qeth_next_hop_is_local_v6(struct qeth_card *card, return false; rcu_read_lock(); - next_hop = qeth_next_hop_v6_rcu(skb, qeth_dst_check_rcu(skb, 6)); + next_hop = qeth_next_hop_v6_rcu(skb, + qeth_dst_check_rcu(skb, htons(ETH_P_IPV6))); key = ipv6_addr_hash(next_hop); hash_for_each_possible_rcu(card->local_addrs6, tmp, hnode, key) { @@ -1407,10 +1409,12 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q, struct sk_buff *skb; skb_queue_walk(&buf->skb_list, skb) { + struct sock *sk = skb->sk; + QETH_CARD_TEXT_(q->card, 5, "skbn%d", notification); QETH_CARD_TEXT_(q->card, 5, "%lx", (long) skb); - if (skb->sk && skb->sk->sk_family == PF_IUCV) - iucv_sk(skb->sk)->sk_txnotify(skb, notification); + if (sk && sk->sk_family == PF_IUCV) + iucv_sk(sk)->sk_txnotify(sk, notification); } } @@ -3690,24 +3694,27 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags, queue->queue_no, index, count); - /* Fake the TX completion interrupt: */ - if (IS_IQD(card)) { - unsigned int frames = READ_ONCE(queue->max_coalesced_frames); - unsigned int usecs = READ_ONCE(queue->coalesce_usecs); + switch (rc) { + case 0: + case -ENOBUFS: + /* ignore temporary SIGA errors without busy condition */ - if (frames && queue->coalesced_frames >= frames) { - napi_schedule(&queue->napi); - queue->coalesced_frames = 0; - QETH_TXQ_STAT_INC(queue, coal_frames); - } else if (usecs) { - qeth_tx_arm_timer(queue, usecs); + /* Fake the TX completion interrupt: */ + if (IS_IQD(card)) { + unsigned int frames = READ_ONCE(queue->max_coalesced_frames); + unsigned int usecs = READ_ONCE(queue->coalesce_usecs); + + if (frames && queue->coalesced_frames >= frames) { + napi_schedule(&queue->napi); + queue->coalesced_frames = 0; + QETH_TXQ_STAT_INC(queue, coal_frames); + } else if (usecs) { + qeth_tx_arm_timer(queue, usecs); + } } - } - if (rc) { - /* ignore temporary SIGA errors without busy condition */ - if (rc == -ENOBUFS) - return; + break; + default: QETH_CARD_TEXT(queue->card, 2, "flushbuf"); QETH_CARD_TEXT_(queue->card, 2, " q%d", queue->queue_no); QETH_CARD_TEXT_(queue->card, 2, " idx%d", index); @@ -3717,7 +3724,6 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, /* this must not happen under normal circumstances. if it * happens something is really wrong -> recover */ qeth_schedule_recovery(queue->card); - return; } } @@ -3896,11 +3902,11 @@ int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb) switch (card->qdio.do_prio_queueing) { case QETH_PRIO_Q_ING_TOS: case QETH_PRIO_Q_ING_PREC: - switch (qeth_get_ip_version(skb)) { - case 4: + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): tos = ipv4_get_dsfield(ip_hdr(skb)); break; - case 6: + case htons(ETH_P_IPV6): tos = ipv6_get_dsfield(ipv6_hdr(skb)); break; default: @@ -4365,10 +4371,10 @@ static void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr, } int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, + struct qeth_qdio_out_q *queue, __be16 proto, void (*fill_header)(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, unsigned int data_len)) + __be16 proto, unsigned int data_len)) { unsigned int proto_len, hw_hdr_len; unsigned int frame_len = skb->len; @@ -4401,7 +4407,7 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, data_offset = push_len + proto_len; } memset(hdr, 0, hw_hdr_len); - fill_header(queue, hdr, skb, ipv, frame_len); + fill_header(queue, hdr, skb, proto, frame_len); if (is_tso) qeth_fill_tso_ext((struct qeth_hdr_tso *) hdr, frame_len - proto_len, skb, proto_len); @@ -6349,9 +6355,11 @@ static int qeth_register_dbf_views(void) static DEFINE_MUTEX(qeth_mod_mutex); /* for synchronized module loading */ -int qeth_core_load_discipline(struct qeth_card *card, - enum qeth_discipline_id discipline) +int qeth_setup_discipline(struct qeth_card *card, + enum qeth_discipline_id discipline) { + int rc; + mutex_lock(&qeth_mod_mutex); switch (discipline) { case QETH_DISCIPLINE_LAYER3: @@ -6373,12 +6381,25 @@ int qeth_core_load_discipline(struct qeth_card *card, return -EINVAL; } + rc = card->discipline->setup(card->gdev); + if (rc) { + if (discipline == QETH_DISCIPLINE_LAYER2) + symbol_put(qeth_l2_discipline); + else + symbol_put(qeth_l3_discipline); + card->discipline = NULL; + + return rc; + } + card->options.layer = discipline; return 0; } -void qeth_core_free_discipline(struct qeth_card *card) +void qeth_remove_discipline(struct qeth_card *card) { + card->discipline->remove(card->gdev); + if (IS_LAYER2(card)) symbol_put(qeth_l2_discipline); else @@ -6586,23 +6607,18 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) default: card->info.layer_enforced = true; /* It's so early that we don't need the discipline_mutex yet. */ - rc = qeth_core_load_discipline(card, enforced_disc); + rc = qeth_setup_discipline(card, enforced_disc); if (rc) - goto err_load; + goto err_setup_disc; gdev->dev.type = IS_OSN(card) ? &qeth_osn_devtype : card->discipline->devtype; - rc = card->discipline->setup(card->gdev); - if (rc) - goto err_disc; break; } return 0; -err_disc: - qeth_core_free_discipline(card); -err_load: +err_setup_disc: err_chp_desc: free_netdev(card->dev); err_card: @@ -6619,10 +6635,8 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev) QETH_CARD_TEXT(card, 2, "removedv"); mutex_lock(&card->discipline_mutex); - if (card->discipline) { - card->discipline->remove(gdev); - qeth_core_free_discipline(card); - } + if (card->discipline) + qeth_remove_discipline(card); mutex_unlock(&card->discipline_mutex); qeth_free_qdio_queues(card); @@ -6642,14 +6656,9 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev) if (!card->discipline) { def_discipline = IS_IQD(card) ? QETH_DISCIPLINE_LAYER3 : QETH_DISCIPLINE_LAYER2; - rc = qeth_core_load_discipline(card, def_discipline); + rc = qeth_setup_discipline(card, def_discipline); if (rc) goto err; - rc = card->discipline->setup(card->gdev); - if (rc) { - qeth_core_free_discipline(card); - goto err; - } } rc = qeth_set_online(card, card->discipline); diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index a0f777f76f66..5815114da468 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -384,19 +384,13 @@ static ssize_t qeth_dev_layer2_store(struct device *dev, goto out; } - card->discipline->remove(card->gdev); - qeth_core_free_discipline(card); + qeth_remove_discipline(card); free_netdev(card->dev); card->dev = ndev; } - rc = qeth_core_load_discipline(card, newdis); - if (rc) - goto out; + rc = qeth_setup_discipline(card, newdis); - rc = card->discipline->setup(card->gdev); - if (rc) - qeth_core_free_discipline(card); out: mutex_unlock(&card->discipline_mutex); return rc ? rc : count; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 4254caf1d9b6..ca44421a6d6e 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -157,7 +157,7 @@ static void qeth_l2_drain_rx_mode_cache(struct qeth_card *card) static void qeth_l2_fill_header(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, unsigned int data_len) + __be16 proto, unsigned int data_len) { int cast_type = qeth_get_ether_cast_type(skb); struct vlan_ethhdr *veth = vlan_eth_hdr(skb); @@ -169,7 +169,7 @@ static void qeth_l2_fill_header(struct qeth_qdio_out_q *queue, } else { hdr->hdr.l2.id = QETH_HEADER_TYPE_LAYER2; if (skb->ip_summed == CHECKSUM_PARTIAL) - qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); + qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], proto); } /* set byte byte 3 to casting flags */ @@ -551,7 +551,7 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, if (IS_OSN(card)) rc = qeth_l2_xmit_osn(card, skb, queue); else - rc = qeth_xmit(card, skb, queue, qeth_get_ip_version(skb), + rc = qeth_xmit(card, skb, queue, vlan_get_protocol(skb), qeth_l2_fill_header); if (!rc) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 4c2cae7ae9a7..dd441eaec66e 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1576,7 +1576,7 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } static int qeth_l3_get_cast_type_rcu(struct sk_buff *skb, struct dst_entry *dst, - int ipv) + __be16 proto) { struct neighbour *n = NULL; @@ -1595,30 +1595,31 @@ static int qeth_l3_get_cast_type_rcu(struct sk_buff *skb, struct dst_entry *dst, } /* no neighbour (eg AF_PACKET), fall back to target's IP address ... */ - switch (ipv) { - case 4: + switch (proto) { + case htons(ETH_P_IP): if (ipv4_is_lbcast(ip_hdr(skb)->daddr)) return RTN_BROADCAST; return ipv4_is_multicast(ip_hdr(skb)->daddr) ? RTN_MULTICAST : RTN_UNICAST; - case 6: + case htons(ETH_P_IPV6): return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ? RTN_MULTICAST : RTN_UNICAST; + case htons(ETH_P_AF_IUCV): + return RTN_UNICAST; default: - /* ... and MAC address */ + /* OSA only: ... and MAC address */ return qeth_get_ether_cast_type(skb); } } -static int qeth_l3_get_cast_type(struct sk_buff *skb) +static int qeth_l3_get_cast_type(struct sk_buff *skb, __be16 proto) { - int ipv = qeth_get_ip_version(skb); struct dst_entry *dst; int cast_type; rcu_read_lock(); - dst = qeth_dst_check_rcu(skb, ipv); - cast_type = qeth_l3_get_cast_type_rcu(skb, dst, ipv); + dst = qeth_dst_check_rcu(skb, proto); + cast_type = qeth_l3_get_cast_type_rcu(skb, dst, proto); rcu_read_unlock(); return cast_type; @@ -1637,7 +1638,7 @@ static u8 qeth_l3_cast_type_to_flag(int cast_type) static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, struct qeth_hdr *hdr, struct sk_buff *skb, - int ipv, unsigned int data_len) + __be16 proto, unsigned int data_len) { struct qeth_hdr_layer3 *l3_hdr = &hdr->hdr.l3; struct vlan_ethhdr *veth = vlan_eth_hdr(skb); @@ -1652,23 +1653,15 @@ static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, } else { hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; - if (skb->protocol == htons(ETH_P_AF_IUCV)) { - l3_hdr->flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST; - l3_hdr->next_hop.addr.s6_addr16[0] = htons(0xfe80); - memcpy(&l3_hdr->next_hop.addr.s6_addr32[2], - iucv_trans_hdr(skb)->destUserID, 8); - return; - } - if (skb->ip_summed == CHECKSUM_PARTIAL) { - qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv); + qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, proto); /* some HW requires combined L3+L4 csum offload: */ - if (ipv == 4) + if (proto == htons(ETH_P_IP)) hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_CSUM_HDR_REQ; } } - if (ipv == 4 || IS_IQD(card)) { + if (proto == htons(ETH_P_IP) || IS_IQD(card)) { /* NETIF_F_HW_VLAN_CTAG_TX */ if (skb_vlan_tag_present(skb)) { hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_VLAN_FRAME; @@ -1680,24 +1673,33 @@ static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, } rcu_read_lock(); - dst = qeth_dst_check_rcu(skb, ipv); + dst = qeth_dst_check_rcu(skb, proto); if (IS_IQD(card) && skb_get_queue_mapping(skb) != QETH_IQD_MCAST_TXQ) cast_type = RTN_UNICAST; else - cast_type = qeth_l3_get_cast_type_rcu(skb, dst, ipv); + cast_type = qeth_l3_get_cast_type_rcu(skb, dst, proto); l3_hdr->flags |= qeth_l3_cast_type_to_flag(cast_type); - if (ipv == 4) { + switch (proto) { + case htons(ETH_P_IP): l3_hdr->next_hop.addr.s6_addr32[3] = qeth_next_hop_v4_rcu(skb, dst); - } else if (ipv == 6) { + break; + case htons(ETH_P_IPV6): l3_hdr->next_hop.addr = *qeth_next_hop_v6_rcu(skb, dst); hdr->hdr.l3.flags |= QETH_HDR_IPV6; if (!IS_IQD(card)) hdr->hdr.l3.flags |= QETH_HDR_PASSTHRU; - } else { + break; + case htons(ETH_P_AF_IUCV): + l3_hdr->next_hop.addr.s6_addr16[0] = htons(0xfe80); + memcpy(&l3_hdr->next_hop.addr.s6_addr32[2], + iucv_trans_hdr(skb)->destUserID, 8); + l3_hdr->flags |= QETH_HDR_IPV6; + break; + default: /* OSA only: */ l3_hdr->flags |= QETH_HDR_PASSTHRU; } @@ -1719,7 +1721,7 @@ static void qeth_l3_fixup_headers(struct sk_buff *skb) } static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv) + struct qeth_qdio_out_q *queue, __be16 proto) { unsigned int hw_hdr_len; int rc; @@ -1733,15 +1735,15 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, skb_pull(skb, ETH_HLEN); qeth_l3_fixup_headers(skb); - return qeth_xmit(card, skb, queue, ipv, qeth_l3_fill_header); + return qeth_xmit(card, skb, queue, proto, qeth_l3_fill_header); } static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct qeth_card *card = dev->ml_priv; + __be16 proto = vlan_get_protocol(skb); u16 txq = skb_get_queue_mapping(skb); - int ipv = qeth_get_ip_version(skb); struct qeth_qdio_out_q *queue; int rc; @@ -1752,22 +1754,32 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, if (card->options.sniffer) goto tx_drop; - if ((card->options.cq != QETH_CQ_ENABLED && !ipv) || - (card->options.cq == QETH_CQ_ENABLED && - skb->protocol != htons(ETH_P_AF_IUCV))) + + switch (proto) { + case htons(ETH_P_AF_IUCV): + if (card->options.cq != QETH_CQ_ENABLED) + goto tx_drop; + break; + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + if (card->options.cq == QETH_CQ_ENABLED) + goto tx_drop; + break; + default: goto tx_drop; + } } else { queue = card->qdio.out_qs[txq]; } if (!(dev->flags & IFF_BROADCAST) && - qeth_l3_get_cast_type(skb) == RTN_BROADCAST) + qeth_l3_get_cast_type(skb, proto) == RTN_BROADCAST) goto tx_drop; - if (ipv == 4 || IS_IQD(card)) - rc = qeth_l3_xmit(card, skb, queue, ipv); + if (proto == htons(ETH_P_IP) || IS_IQD(card)) + rc = qeth_l3_xmit(card, skb, queue, proto); else - rc = qeth_xmit(card, skb, queue, ipv, qeth_l3_fill_header); + rc = qeth_xmit(card, skb, queue, proto, qeth_l3_fill_header); if (!rc) return NETDEV_TX_OK; @@ -1821,8 +1833,10 @@ static netdev_features_t qeth_l3_osa_features_check(struct sk_buff *skb, static u16 qeth_l3_iqd_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { - return qeth_iqd_select_queue(dev, skb, qeth_l3_get_cast_type(skb), - sb_dev); + __be16 proto = vlan_get_protocol(skb); + + return qeth_iqd_select_queue(dev, skb, + qeth_l3_get_cast_type(skb, proto), sb_dev); } static u16 qeth_l3_osa_select_queue(struct net_device *dev, struct sk_buff *skb, diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c index a2beee6e09f0..5988c300cc82 100644 --- a/drivers/scsi/fnic/vnic_dev.c +++ b/drivers/scsi/fnic/vnic_dev.c @@ -444,7 +444,8 @@ static int vnic_dev_init_devcmd2(struct vnic_dev *vdev) fetch_index = ioread32(&vdev->devcmd2->wq.ctrl->fetch_index); if (fetch_index == 0xFFFFFFFF) { /* check for hardware gone */ pr_err("error in devcmd2 init"); - return -ENODEV; + err = -ENODEV; + goto err_free_wq; } /* @@ -460,7 +461,7 @@ static int vnic_dev_init_devcmd2(struct vnic_dev *vdev) err = vnic_dev_alloc_desc_ring(vdev, &vdev->devcmd2->results_ring, DEVCMD2_RING_SIZE, DEVCMD2_DESC_SIZE); if (err) - goto err_free_wq; + goto err_disable_wq; vdev->devcmd2->result = (struct devcmd2_result *) vdev->devcmd2->results_ring.descs; @@ -481,8 +482,9 @@ static int vnic_dev_init_devcmd2(struct vnic_dev *vdev) err_free_desc_ring: vnic_dev_free_desc_ring(vdev, &vdev->devcmd2->results_ring); -err_free_wq: +err_disable_wq: vnic_wq_disable(&vdev->devcmd2->wq); +err_free_wq: vnic_wq_free(&vdev->devcmd2->wq); err_free_devcmd2: kfree(vdev->devcmd2); diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 42e4d35e0d35..65f168c41d23 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -1744,7 +1744,7 @@ static int ibmvfc_queuecommand_lck(struct scsi_cmnd *cmnd, iu->pri_task_attr = IBMVFC_SIMPLE_TASK; } - vfc_cmd->correlation = cpu_to_be64(evt); + vfc_cmd->correlation = cpu_to_be64((u64)evt); if (likely(!(rc = ibmvfc_map_sg_data(cmnd, evt, vfc_cmd, vhost->dev)))) return ibmvfc_send_event(evt, vhost, 0); @@ -2418,7 +2418,7 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev) tmf->flags = cpu_to_be16((IBMVFC_NO_MEM_DESC | IBMVFC_TMF)); evt->sync_iu = &rsp_iu; - tmf->correlation = cpu_to_be64(evt); + tmf->correlation = cpu_to_be64((u64)evt); init_completion(&evt->comp); rsp_rc = ibmvfc_send_event(evt, vhost, default_timeout); @@ -3007,8 +3007,10 @@ static int ibmvfc_slave_configure(struct scsi_device *sdev) unsigned long flags = 0; spin_lock_irqsave(shost->host_lock, flags); - if (sdev->type == TYPE_DISK) + if (sdev->type == TYPE_DISK) { sdev->allow_restart = 1; + blk_queue_rq_timeout(sdev->request_queue, 120 * HZ); + } spin_unlock_irqrestore(shost->host_lock, flags); return 0; } diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index d71afae6191c..841000445b9a 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -1623,8 +1623,13 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) rc = fc_exch_done_locked(ep); WARN_ON(fc_seq_exch(sp) != ep); spin_unlock_bh(&ep->ex_lock); - if (!rc) + if (!rc) { fc_exch_delete(ep); + } else { + FC_EXCH_DBG(ep, "ep is completed already," + "hence skip calling the resp\n"); + goto skip_resp; + } } /* @@ -1643,6 +1648,7 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) if (!fc_invoke_resp(ep, sp, fp)) fc_frame_free(fp); +skip_resp: fc_exch_release(ep); return; rel: @@ -1899,10 +1905,16 @@ static void fc_exch_reset(struct fc_exch *ep) fc_exch_hold(ep); - if (!rc) + if (!rc) { fc_exch_delete(ep); + } else { + FC_EXCH_DBG(ep, "ep is completed already," + "hence skip calling the resp\n"); + goto skip_resp; + } fc_invoke_resp(ep, sp, ERR_PTR(-FC_EX_CLOSED)); +skip_resp: fc_seq_set_resp(sp, NULL, ep->arg); fc_exch_release(ep); } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index af192096a82b..63a4f48bdc75 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -8244,11 +8244,9 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance, goto out; } + /* always store 64 bits regardless of addressing */ sense_ptr = (void *)cmd->frame + ioc->sense_off; - if (instance->consistent_mask_64bit) - put_unaligned_le64(sense_handle, sense_ptr); - else - put_unaligned_le32(sense_handle, sense_ptr); + put_unaligned_le64(sense_handle, sense_ptr); } /* diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index f80abe28f35a..0e0fe5b09496 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -42,7 +42,7 @@ MODULE_PARM_DESC(ql2xfulldump_on_mpifail, int ql2xenforce_iocb_limit = 1; module_param(ql2xenforce_iocb_limit, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ql2xenforce_iocb_limit, - "Enforce IOCB throttling, to avoid FW congestion. (default: 0)"); + "Enforce IOCB throttling, to avoid FW congestion. (default: 1)"); /* * CT6 CTX allocation cache diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index cba1cf6a1c12..1e939a2a387f 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -541,7 +541,14 @@ int srp_reconnect_rport(struct srp_rport *rport) res = mutex_lock_interruptible(&rport->mutex); if (res) goto out; - scsi_target_block(&shost->shost_gendev); + if (rport->state != SRP_RPORT_FAIL_FAST) + /* + * sdev state must be SDEV_TRANSPORT_OFFLINE, transition + * to SDEV_BLOCK is illegal. Calling scsi_target_unblock() + * later is ok though, scsi_internal_device_unblock_nowait() + * treats SDEV_TRANSPORT_OFFLINE like SDEV_BLOCK. + */ + scsi_target_block(&shost->shost_gendev); res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV; pr_debug("%s (state %d): transport.reconnect() returned %d\n", dev_name(&shost->shost_gendev), rport->state, res); diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig index 3f6dfed4fe84..b915b38c2b27 100644 --- a/drivers/scsi/ufs/Kconfig +++ b/drivers/scsi/ufs/Kconfig @@ -72,6 +72,7 @@ config SCSI_UFS_DWC_TC_PCI config SCSI_UFSHCD_PLATFORM tristate "Platform bus based UFS Controller support" depends on SCSI_UFSHCD + depends on HAS_IOMEM help This selects the UFS host controller support. Select this if you have an UFS controller on Platform bus. diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index e31d2c5c7b23..fb32d122f2e3 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -3996,6 +3996,8 @@ int ufshcd_link_recovery(struct ufs_hba *hba) if (ret) dev_err(hba->dev, "%s: link recovery failed, err %d", __func__, ret); + else + ufshcd_clear_ua_wluns(hba); return ret; } @@ -4992,7 +4994,8 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) break; } /* end of switch */ - if ((host_byte(result) != DID_OK) && !hba->silence_err_logs) + if ((host_byte(result) != DID_OK) && + (host_byte(result) != DID_REQUEUE) && !hba->silence_err_logs) ufshcd_print_trs(hba, 1 << lrbp->task_tag, true); return result; } @@ -6001,6 +6004,9 @@ skip_err_handling: ufshcd_scsi_unblock_requests(hba); ufshcd_err_handling_unprepare(hba); up(&hba->eh_sem); + + if (!err && needs_reset) + ufshcd_clear_ua_wluns(hba); } /** @@ -6295,9 +6301,13 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); } - if (enabled_intr_status && retval == IRQ_NONE) { - dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n", - __func__, intr_status); + if (enabled_intr_status && retval == IRQ_NONE && + !ufshcd_eh_in_progress(hba)) { + dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x (0x%08x, 0x%08x)\n", + __func__, + intr_status, + hba->ufs_stats.last_intr_status, + enabled_intr_status); ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: "); } @@ -6341,7 +6351,10 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, * Even though we use wait_event() which sleeps indefinitely, * the maximum wait time is bounded by %TM_CMD_TIMEOUT. */ - req = blk_get_request(q, REQ_OP_DRV_OUT, BLK_MQ_REQ_RESERVED); + req = blk_get_request(q, REQ_OP_DRV_OUT, 0); + if (IS_ERR(req)) + return PTR_ERR(req); + req->end_io_data = &wait; free_slot = req->tag; WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs); @@ -6938,14 +6951,11 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) ufshcd_set_clk_freq(hba, true); err = ufshcd_hba_enable(hba); - if (err) - goto out; /* Establish the link again and restore the device */ - err = ufshcd_probe_hba(hba, false); if (!err) - ufshcd_clear_ua_wluns(hba); -out: + err = ufshcd_probe_hba(hba, false); + if (err) dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err); ufshcd_update_evt_hist(hba, UFS_EVT_HOST_RESET, (u32)err); @@ -7716,6 +7726,8 @@ static int ufshcd_add_lus(struct ufs_hba *hba) if (ret) goto out; + ufshcd_clear_ua_wluns(hba); + /* Initialize devfreq after UFS device is detected */ if (ufshcd_is_clkscaling_supported(hba)) { memcpy(&hba->clk_scaling.saved_pwr_info.info, @@ -7917,8 +7929,6 @@ out: pm_runtime_put_sync(hba->dev); ufshcd_exit_clk_scaling(hba); ufshcd_hba_exit(hba); - } else { - ufshcd_clear_ua_wluns(hba); } } @@ -8775,6 +8785,7 @@ enable_gating: ufshcd_resume_clkscaling(hba); hba->clk_gating.is_suspended = false; hba->dev_info.b_rpm_dev_flush_capable = false; + ufshcd_clear_ua_wluns(hba); ufshcd_release(hba); out: if (hba->dev_info.b_rpm_dev_flush_capable) { @@ -8885,6 +8896,8 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) cancel_delayed_work(&hba->rpm_dev_flush_recheck_work); } + ufshcd_clear_ua_wluns(hba); + /* Schedule clock gating in case of no access to UFS device yet */ ufshcd_release(hba); diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c index f8e070d67fa3..a14684ffe4c1 100644 --- a/drivers/sh/intc/core.c +++ b/drivers/sh/intc/core.c @@ -214,7 +214,7 @@ int __init register_intc_controller(struct intc_desc *desc) d->window[k].phys = res->start; d->window[k].size = resource_size(res); d->window[k].virt = ioremap(res->start, - resource_size(res)); + resource_size(res)); if (!d->window[k].virt) goto err2; } diff --git a/drivers/sh/intc/virq-debugfs.c b/drivers/sh/intc/virq-debugfs.c index 9e62ba9311f0..939915a07d99 100644 --- a/drivers/sh/intc/virq-debugfs.c +++ b/drivers/sh/intc/virq-debugfs.c @@ -16,7 +16,7 @@ #include <linux/debugfs.h> #include "internals.h" -static int intc_irq_xlate_debug(struct seq_file *m, void *priv) +static int intc_irq_xlate_show(struct seq_file *m, void *priv) { int i; @@ -37,17 +37,7 @@ static int intc_irq_xlate_debug(struct seq_file *m, void *priv) return 0; } -static int intc_irq_xlate_open(struct inode *inode, struct file *file) -{ - return single_open(file, intc_irq_xlate_debug, inode->i_private); -} - -static const struct file_operations intc_irq_xlate_fops = { - .open = intc_irq_xlate_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(intc_irq_xlate); static int __init intc_irq_xlate_init(void) { diff --git a/drivers/soc/atmel/soc.c b/drivers/soc/atmel/soc.c index c4472b68b7c2..698d21f50516 100644 --- a/drivers/soc/atmel/soc.c +++ b/drivers/soc/atmel/soc.c @@ -271,8 +271,21 @@ struct soc_device * __init at91_soc_init(const struct at91_soc *socs) return soc_dev; } +static const struct of_device_id at91_soc_allowed_list[] __initconst = { + { .compatible = "atmel,at91rm9200", }, + { .compatible = "atmel,at91sam9", }, + { .compatible = "atmel,sama5", }, + { .compatible = "atmel,samv7", }, + { } +}; + static int __init atmel_soc_device_init(void) { + struct device_node *np = of_find_node_by_path("/"); + + if (!of_match_node(at91_soc_allowed_list, np)) + return 0; + at91_soc_init(socs); return 0; diff --git a/drivers/soc/imx/Kconfig b/drivers/soc/imx/Kconfig index a9370f4aacca..05812f8ae734 100644 --- a/drivers/soc/imx/Kconfig +++ b/drivers/soc/imx/Kconfig @@ -13,7 +13,7 @@ config SOC_IMX8M depends on ARCH_MXC || COMPILE_TEST default ARCH_MXC && ARM64 select SOC_BUS - select ARM_GIC_V3 if ARCH_MXC + select ARM_GIC_V3 if ARCH_MXC && ARCH_MULTI_V7 help If you say yes here you get support for the NXP i.MX8M family support, it will provide the SoC info like SoC family, diff --git a/drivers/soc/litex/Kconfig b/drivers/soc/litex/Kconfig index 7c6b009b6f6c..7a7c38282e11 100644 --- a/drivers/soc/litex/Kconfig +++ b/drivers/soc/litex/Kconfig @@ -8,6 +8,7 @@ config LITEX config LITEX_SOC_CONTROLLER tristate "Enable LiteX SoC Controller driver" depends on OF || COMPILE_TEST + depends on HAS_IOMEM select LITEX help This option enables the SoC Controller Driver which verifies diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c index 1217cafdfd4d..9b0766384570 100644 --- a/drivers/soc/litex/litex_soc_ctrl.c +++ b/drivers/soc/litex/litex_soc_ctrl.c @@ -140,12 +140,13 @@ struct litex_soc_ctrl_device { void __iomem *base; }; +#ifdef CONFIG_OF static const struct of_device_id litex_soc_ctrl_of_match[] = { {.compatible = "litex,soc-controller"}, {}, }; - MODULE_DEVICE_TABLE(of, litex_soc_ctrl_of_match); +#endif /* CONFIG_OF */ static int litex_soc_ctrl_probe(struct platform_device *pdev) { diff --git a/drivers/spi/spi-altera.c b/drivers/spi/spi-altera.c index cbc4c28c1541..62ea0c9e321b 100644 --- a/drivers/spi/spi-altera.c +++ b/drivers/spi/spi-altera.c @@ -254,7 +254,8 @@ static int altera_spi_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Invalid number of chipselect: %hu\n", pdata->num_chipselect); - return -EINVAL; + err = -EINVAL; + goto exit; } master->num_chipselect = pdata->num_chipselect; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 859910ec8d9f..8cb4d923aeaa 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -682,6 +682,7 @@ static const struct of_device_id spidev_dt_ids[] = { { .compatible = "lwn,bk4" }, { .compatible = "dh,dhcom-board" }, { .compatible = "menlo,m53cpld" }, + { .compatible = "cisco,spi-petra" }, {}, }; MODULE_DEVICE_TABLE(of, spidev_dt_ids); diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c index b668a82d40ad..f5fbdbc4ffdb 100644 --- a/drivers/staging/media/hantro/hantro_v4l2.c +++ b/drivers/staging/media/hantro/hantro_v4l2.c @@ -367,7 +367,7 @@ hantro_reset_raw_fmt(struct hantro_ctx *ctx) hantro_reset_fmt(raw_fmt, raw_vpu_fmt); raw_fmt->width = encoded_fmt->width; - raw_fmt->width = encoded_fmt->width; + raw_fmt->height = encoded_fmt->height; if (ctx->is_encoder) hantro_set_fmt_out(ctx, raw_fmt); else diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c index 781c84a9b1b7..de7442d4834d 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c @@ -203,7 +203,7 @@ static void _cedrus_write_ref_list(struct cedrus_ctx *ctx, position = cedrus_buf->codec.h264.position; sram_array[i] |= position << 1; - if (ref_list[i].fields & V4L2_H264_BOTTOM_FIELD_REF) + if (ref_list[i].fields == V4L2_H264_BOTTOM_FIELD_REF) sram_array[i] |= BIT(0); } diff --git a/drivers/staging/rtl8723bs/include/rtw_wifi_regd.h b/drivers/staging/rtl8723bs/include/rtw_wifi_regd.h index ab5a8627d371..f798b0c744a4 100644 --- a/drivers/staging/rtl8723bs/include/rtw_wifi_regd.h +++ b/drivers/staging/rtl8723bs/include/rtw_wifi_regd.h @@ -20,9 +20,9 @@ enum country_code_type_t { COUNTRY_CODE_MAX }; -int rtw_regd_init(struct adapter *padapter, - void (*reg_notifier)(struct wiphy *wiphy, - struct regulatory_request *request)); +void rtw_regd_init(struct wiphy *wiphy, + void (*reg_notifier)(struct wiphy *wiphy, + struct regulatory_request *request)); void rtw_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request); diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index bf1417236161..11032316c53d 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -3211,9 +3211,6 @@ void rtw_cfg80211_init_wiphy(struct adapter *padapter) rtw_cfg80211_init_ht_capab(&bands->ht_cap, NL80211_BAND_2GHZ, rf_type); } - /* init regulary domain */ - rtw_regd_init(padapter, rtw_reg_notifier); - /* copy mac_addr to wiphy */ memcpy(wiphy->perm_addr, padapter->eeprompriv.mac_addr, ETH_ALEN); @@ -3328,6 +3325,9 @@ int rtw_wdev_alloc(struct adapter *padapter, struct device *dev) *((struct adapter **)wiphy_priv(wiphy)) = padapter; rtw_cfg80211_preinit_wiphy(padapter, wiphy); + /* init regulary domain */ + rtw_regd_init(wiphy, rtw_reg_notifier); + ret = wiphy_register(wiphy); if (ret < 0) { DBG_8192C("Couldn't register wiphy device\n"); diff --git a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c index b2208e5f190a..301ffff12e82 100644 --- a/drivers/staging/rtl8723bs/os_dep/sdio_intf.c +++ b/drivers/staging/rtl8723bs/os_dep/sdio_intf.c @@ -339,8 +339,6 @@ static struct adapter *rtw_sdio_if1_init(struct dvobj_priv *dvobj, const struct padapter = rtw_netdev_priv(pnetdev); - rtw_wdev_alloc(padapter, dvobj_to_dev(dvobj)); - /* 3 3. init driver special setting, interface, OS and hardware relative */ /* 4 3.1 set hardware operation functions */ @@ -378,6 +376,8 @@ static struct adapter *rtw_sdio_if1_init(struct dvobj_priv *dvobj, const struct goto free_hal_data; } + rtw_wdev_alloc(padapter, dvobj_to_dev(dvobj)); + /* 3 8. get WLan MAC address */ /* set mac addr */ rtw_macaddr_cfg(&psdio->func->dev, padapter->eeprompriv.mac_addr); diff --git a/drivers/staging/rtl8723bs/os_dep/wifi_regd.c b/drivers/staging/rtl8723bs/os_dep/wifi_regd.c index 578b9f734231..2833fc6901e6 100644 --- a/drivers/staging/rtl8723bs/os_dep/wifi_regd.c +++ b/drivers/staging/rtl8723bs/os_dep/wifi_regd.c @@ -139,15 +139,11 @@ static void _rtw_regd_init_wiphy(struct rtw_regulatory *reg, _rtw_reg_apply_flags(wiphy); } -int rtw_regd_init(struct adapter *padapter, - void (*reg_notifier)(struct wiphy *wiphy, - struct regulatory_request *request)) +void rtw_regd_init(struct wiphy *wiphy, + void (*reg_notifier)(struct wiphy *wiphy, + struct regulatory_request *request)) { - struct wiphy *wiphy = padapter->rtw_wdev->wiphy; - _rtw_regd_init_wiphy(NULL, wiphy, reg_notifier); - - return 0; } void rtw_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request) diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 893d1b406c29..1a9c50401bdb 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -896,7 +896,7 @@ int iscsit_setup_np( else len = sizeof(struct sockaddr_in); /* - * Set SO_REUSEADDR, and disable Nagel Algorithm with TCP_NODELAY. + * Set SO_REUSEADDR, and disable Nagle Algorithm with TCP_NODELAY. */ if (np->np_network_transport == ISCSI_TCP) tcp_sock_set_nodelay(sock->sk); diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 6b171fff007b..a5991df23581 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -562,8 +562,6 @@ tcmu_get_block_page(struct tcmu_dev *udev, uint32_t dbi) static inline void tcmu_free_cmd(struct tcmu_cmd *tcmu_cmd) { - if (tcmu_cmd->se_cmd) - tcmu_cmd->se_cmd->priv = NULL; kfree(tcmu_cmd->dbi); kmem_cache_free(tcmu_cmd_cache, tcmu_cmd); } @@ -1174,11 +1172,12 @@ tcmu_queue_cmd(struct se_cmd *se_cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; mutex_lock(&udev->cmdr_lock); - se_cmd->priv = tcmu_cmd; if (!(se_cmd->transport_state & CMD_T_ABORTED)) ret = queue_cmd_ring(tcmu_cmd, &scsi_ret); if (ret < 0) tcmu_free_cmd(tcmu_cmd); + else + se_cmd->priv = tcmu_cmd; mutex_unlock(&udev->cmdr_lock); return scsi_ret; } @@ -1241,6 +1240,7 @@ tcmu_tmr_notify(struct se_device *se_dev, enum tcm_tmreq_table tmf, list_del_init(&cmd->queue_entry); tcmu_free_cmd(cmd); + se_cmd->priv = NULL; target_complete_cmd(se_cmd, SAM_STAT_TASK_ABORTED); unqueued = true; } @@ -1332,6 +1332,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * } done: + se_cmd->priv = NULL; if (read_len_valid) { pr_debug("read_len = %d\n", read_len); target_complete_cmd_with_length(cmd->se_cmd, @@ -1478,6 +1479,7 @@ static void tcmu_check_expired_queue_cmd(struct tcmu_cmd *cmd) se_cmd = cmd->se_cmd; tcmu_free_cmd(cmd); + se_cmd->priv = NULL; target_complete_cmd(se_cmd, SAM_STAT_TASK_SET_FULL); } @@ -1592,6 +1594,7 @@ static void run_qfull_queue(struct tcmu_dev *udev, bool fail) * removed then LIO core will do the right thing and * fail the retry. */ + tcmu_cmd->se_cmd->priv = NULL; target_complete_cmd(tcmu_cmd->se_cmd, SAM_STAT_BUSY); tcmu_free_cmd(tcmu_cmd); continue; @@ -1605,6 +1608,7 @@ static void run_qfull_queue(struct tcmu_dev *udev, bool fail) * Ignore scsi_ret for now. target_complete_cmd * drops it. */ + tcmu_cmd->se_cmd->priv = NULL; target_complete_cmd(tcmu_cmd->se_cmd, SAM_STAT_CHECK_CONDITION); tcmu_free_cmd(tcmu_cmd); @@ -2212,6 +2216,7 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level) if (!test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) { WARN_ON(!cmd->se_cmd); list_del_init(&cmd->queue_entry); + cmd->se_cmd->priv = NULL; if (err_level == 1) { /* * Userspace was not able to start the diff --git a/drivers/tee/optee/call.c b/drivers/tee/optee/call.c index c981757ba0d4..780d7c4fd756 100644 --- a/drivers/tee/optee/call.c +++ b/drivers/tee/optee/call.c @@ -7,6 +7,7 @@ #include <linux/err.h> #include <linux/errno.h> #include <linux/mm.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/tee_drv.h> #include <linux/types.h> @@ -148,7 +149,8 @@ u32 optee_do_call_with_arg(struct tee_context *ctx, phys_addr_t parg) */ optee_cq_wait_for_completion(&optee->call_queue, &w); } else if (OPTEE_SMC_RETURN_IS_RPC(res.a0)) { - might_sleep(); + if (need_resched()) + cond_resched(); param.a0 = res.a0; param.a1 = res.a1; param.a2 = res.a2; diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 8b7f941a9bb7..b8c4159bc32d 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2316,7 +2316,7 @@ static int icm_usb4_switch_nvm_authenticate_status(struct tb_switch *sw, if (auth && auth->reply.route_hi == sw->config.route_hi && auth->reply.route_lo == sw->config.route_lo) { - tb_dbg(tb, "NVM_AUTH found for %llx flags 0x%#x status %#x\n", + tb_dbg(tb, "NVM_AUTH found for %llx flags %#x status %#x\n", tb_route(sw), auth->reply.hdr.flags, auth->reply.status); if (auth->reply.hdr.flags & ICM_FLAGS_ERROR) ret = -EIO; diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 319d68c8a5df..219e85756171 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2081,9 +2081,6 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, return 0; } -extern ssize_t redirected_tty_write(struct file *, const char __user *, - size_t, loff_t *); - /** * job_control - check job control * @tty: tty @@ -2105,7 +2102,7 @@ static int job_control(struct tty_struct *tty, struct file *file) /* NOTE: not yet done after every sleep pending a thorough check of the logic of this change. -- jlc */ /* don't stop on /dev/console */ - if (file->f_op->write == redirected_tty_write) + if (file->f_op->write_iter == redirected_tty_write) return 0; return __tty_check_change(tty, SIGTTIN); @@ -2309,7 +2306,7 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file, ssize_t retval = 0; /* Job control check -- must be done at start (POSIX.1 7.1.1.4). */ - if (L_TOSTOP(tty) && file->f_op->write != redirected_tty_write) { + if (L_TOSTOP(tty) && file->f_op->write_iter != redirected_tty_write) { retval = tty_check_change(tty); if (retval) return retval; diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 118b29912289..e0c00a1b0763 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -648,6 +648,14 @@ static void wait_for_xmitr(struct uart_port *port) (val & STAT_TX_RDY(port)), 1, 10000); } +static void wait_for_xmite(struct uart_port *port) +{ + u32 val; + + readl_poll_timeout_atomic(port->membase + UART_STAT, val, + (val & STAT_TX_EMP), 1, 10000); +} + static void mvebu_uart_console_putchar(struct uart_port *port, int ch) { wait_for_xmitr(port); @@ -675,7 +683,7 @@ static void mvebu_uart_console_write(struct console *co, const char *s, uart_console_write(port, s, count, mvebu_uart_console_putchar); - wait_for_xmitr(port); + wait_for_xmite(port); if (ier) writel(ier, port->membase + UART_CTRL(port)); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 8034489337d7..816e709afa56 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -143,12 +143,9 @@ LIST_HEAD(tty_drivers); /* linked list of tty drivers */ DEFINE_MUTEX(tty_mutex); static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *); -static ssize_t tty_write(struct file *, const char __user *, size_t, loff_t *); -ssize_t redirected_tty_write(struct file *, const char __user *, - size_t, loff_t *); +static ssize_t tty_write(struct kiocb *, struct iov_iter *); static __poll_t tty_poll(struct file *, poll_table *); static int tty_open(struct inode *, struct file *); -long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long tty_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -438,8 +435,7 @@ static ssize_t hung_up_tty_read(struct file *file, char __user *buf, return 0; } -static ssize_t hung_up_tty_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t hung_up_tty_write(struct kiocb *iocb, struct iov_iter *from) { return -EIO; } @@ -478,7 +474,8 @@ static void tty_show_fdinfo(struct seq_file *m, struct file *file) static const struct file_operations tty_fops = { .llseek = no_llseek, .read = tty_read, - .write = tty_write, + .write_iter = tty_write, + .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, .compat_ioctl = tty_compat_ioctl, @@ -491,7 +488,8 @@ static const struct file_operations tty_fops = { static const struct file_operations console_fops = { .llseek = no_llseek, .read = tty_read, - .write = redirected_tty_write, + .write_iter = redirected_tty_write, + .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, .compat_ioctl = tty_compat_ioctl, @@ -503,7 +501,7 @@ static const struct file_operations console_fops = { static const struct file_operations hung_up_tty_fops = { .llseek = no_llseek, .read = hung_up_tty_read, - .write = hung_up_tty_write, + .write_iter = hung_up_tty_write, .poll = hung_up_tty_poll, .unlocked_ioctl = hung_up_tty_ioctl, .compat_ioctl = hung_up_tty_compat_ioctl, @@ -606,9 +604,9 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session) /* This breaks for file handles being sent over AF_UNIX sockets ? */ list_for_each_entry(priv, &tty->tty_files, list) { filp = priv->file; - if (filp->f_op->write == redirected_tty_write) + if (filp->f_op->write_iter == redirected_tty_write) cons_filp = filp; - if (filp->f_op->write != tty_write) + if (filp->f_op->write_iter != tty_write) continue; closecount++; __tty_fasync(-1, filp, 0); /* can't block */ @@ -901,9 +899,9 @@ static inline ssize_t do_tty_write( ssize_t (*write)(struct tty_struct *, struct file *, const unsigned char *, size_t), struct tty_struct *tty, struct file *file, - const char __user *buf, - size_t count) + struct iov_iter *from) { + size_t count = iov_iter_count(from); ssize_t ret, written = 0; unsigned int chunk; @@ -955,14 +953,20 @@ static inline ssize_t do_tty_write( size_t size = count; if (size > chunk) size = chunk; + ret = -EFAULT; - if (copy_from_user(tty->write_buf, buf, size)) + if (copy_from_iter(tty->write_buf, size, from) != size) break; + ret = write(tty, file, tty->write_buf, size); if (ret <= 0) break; + + /* FIXME! Have Al check this! */ + if (ret != size) + iov_iter_revert(from, size-ret); + written += ret; - buf += ret; count -= ret; if (!count) break; @@ -1022,8 +1026,7 @@ void tty_write_message(struct tty_struct *tty, char *msg) * write method will not be invoked in parallel for each device. */ -static ssize_t tty_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t file_tty_write(struct file *file, struct kiocb *iocb, struct iov_iter *from) { struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; @@ -1038,17 +1041,21 @@ static ssize_t tty_write(struct file *file, const char __user *buf, tty_err(tty, "missing write_room method\n"); ld = tty_ldisc_ref_wait(tty); if (!ld) - return hung_up_tty_write(file, buf, count, ppos); + return hung_up_tty_write(iocb, from); if (!ld->ops->write) ret = -EIO; else - ret = do_tty_write(ld->ops->write, tty, file, buf, count); + ret = do_tty_write(ld->ops->write, tty, file, from); tty_ldisc_deref(ld); return ret; } -ssize_t redirected_tty_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t tty_write(struct kiocb *iocb, struct iov_iter *from) +{ + return file_tty_write(iocb->ki_filp, iocb, from); +} + +ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter) { struct file *p = NULL; @@ -1057,13 +1064,17 @@ ssize_t redirected_tty_write(struct file *file, const char __user *buf, p = get_file(redirect); spin_unlock(&redirect_lock); + /* + * We know the redirected tty is just another tty, we can can + * call file_tty_write() directly with that file pointer. + */ if (p) { ssize_t res; - res = vfs_write(p, buf, count, &p->f_pos); + res = file_tty_write(p, iocb, iter); fput(p); return res; } - return tty_write(file, buf, count, ppos); + return tty_write(iocb, iter); } /* @@ -2295,7 +2306,7 @@ static int tioccons(struct file *file) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (file->f_op->write == redirected_tty_write) { + if (file->f_op->write_iter == redirected_tty_write) { struct file *f; spin_lock(&redirect_lock); f = redirect; @@ -2305,6 +2316,12 @@ static int tioccons(struct file *file) fput(f); return 0; } + if (file->f_op->write_iter != tty_write) + return -ENOTTY; + if (!(file->f_mode & FMODE_WRITE)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_WRITE)) + return -EINVAL; spin_lock(&redirect_lock); if (redirect) { spin_unlock(&redirect_lock); diff --git a/drivers/usb/cdns3/cdns3-imx.c b/drivers/usb/cdns3/cdns3-imx.c index 22a56c4dce67..7990fee03fe4 100644 --- a/drivers/usb/cdns3/cdns3-imx.c +++ b/drivers/usb/cdns3/cdns3-imx.c @@ -185,7 +185,11 @@ static int cdns_imx_probe(struct platform_device *pdev) } data->num_clks = ARRAY_SIZE(imx_cdns3_core_clks); - data->clks = (struct clk_bulk_data *)imx_cdns3_core_clks; + data->clks = devm_kmemdup(dev, imx_cdns3_core_clks, + sizeof(imx_cdns3_core_clks), GFP_KERNEL); + if (!data->clks) + return -ENOMEM; + ret = devm_clk_bulk_get(dev, data->num_clks, data->clks); if (ret) return ret; @@ -214,20 +218,16 @@ err: return ret; } -static int cdns_imx_remove_core(struct device *dev, void *data) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int cdns_imx_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct cdns_imx *data = dev_get_drvdata(dev); - device_for_each_child(dev, NULL, cdns_imx_remove_core); + pm_runtime_get_sync(dev); + of_platform_depopulate(dev); + clk_bulk_disable_unprepare(data->num_clks, data->clks); + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); platform_set_drvdata(pdev, NULL); return 0; diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 0bd6b20435b8..02d8bfae58fb 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -420,7 +420,10 @@ static void ast_vhub_stop_active_req(struct ast_vhub_ep *ep, u32 state, reg, loops; /* Stop DMA activity */ - writel(0, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT); + if (ep->epn.desc_mode) + writel(VHUB_EP_DMA_CTRL_RESET, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT); + else + writel(0, ep->epn.regs + AST_VHUB_EP_DMA_CTLSTAT); /* Wait for it to complete */ for (loops = 0; loops < 1000; loops++) { diff --git a/drivers/usb/gadget/udc/bdc/Kconfig b/drivers/usb/gadget/udc/bdc/Kconfig index 3e88c7670b2e..fb01ff47b64c 100644 --- a/drivers/usb/gadget/udc/bdc/Kconfig +++ b/drivers/usb/gadget/udc/bdc/Kconfig @@ -17,7 +17,7 @@ if USB_BDC_UDC comment "Platform Support" config USB_BDC_PCI tristate "BDC support for PCIe based platforms" - depends on USB_PCI + depends on USB_PCI && BROKEN default USB_BDC_UDC help Enable support for platforms which have BDC connected through PCIe, such as Lego3 FPGA platform. diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 6a62bbd01324..ea114f922ccf 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1529,10 +1529,13 @@ static ssize_t soft_connect_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + ssize_t ret; + mutex_lock(&udc_lock); if (!udc->driver) { dev_err(dev, "soft-connect without a gadget driver\n"); - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + goto out; } if (sysfs_streq(buf, "connect")) { @@ -1543,10 +1546,14 @@ static ssize_t soft_connect_store(struct device *dev, usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); - return -EINVAL; + ret = -EINVAL; + goto out; } - return n; + ret = n; +out: + mutex_unlock(&udc_lock); + return ret; } static DEVICE_ATTR_WO(soft_connect); diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index 1a953f44183a..57067763b100 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -2270,17 +2270,20 @@ static int dummy_hub_control( } fallthrough; case USB_PORT_FEAT_RESET: + if (!(dum_hcd->port_status & USB_PORT_STAT_CONNECTION)) + break; /* if it's already enabled, disable */ if (hcd->speed == HCD_USB3) { - dum_hcd->port_status = 0; dum_hcd->port_status = (USB_SS_PORT_STAT_POWER | USB_PORT_STAT_CONNECTION | USB_PORT_STAT_RESET); - } else + } else { dum_hcd->port_status &= ~(USB_PORT_STAT_ENABLE | USB_PORT_STAT_LOW_SPEED | USB_PORT_STAT_HIGH_SPEED); + dum_hcd->port_status |= USB_PORT_STAT_RESET; + } /* * We want to reset device status. All but the * Self powered feature @@ -2292,7 +2295,8 @@ static int dummy_hub_control( * interval? Is it still 50msec as for HS? */ dum_hcd->re_timeout = jiffies + msecs_to_jiffies(50); - fallthrough; + set_link_state(dum_hcd); + break; case USB_PORT_FEAT_C_CONNECTION: case USB_PORT_FEAT_C_RESET: case USB_PORT_FEAT_C_ENABLE: diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index e358ae17d51e..1926b328b6aa 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -574,6 +574,7 @@ static int ehci_run (struct usb_hcd *hcd) struct ehci_hcd *ehci = hcd_to_ehci (hcd); u32 temp; u32 hcc_params; + int rc; hcd->uses_new_polling = 1; @@ -629,9 +630,20 @@ static int ehci_run (struct usb_hcd *hcd) down_write(&ehci_cf_port_reset_rwsem); ehci->rh_state = EHCI_RH_RUNNING; ehci_writel(ehci, FLAG_CF, &ehci->regs->configured_flag); + + /* Wait until HC become operational */ ehci_readl(ehci, &ehci->regs->command); /* unblock posted writes */ msleep(5); + rc = ehci_handshake(ehci, &ehci->regs->status, STS_HALT, 0, 100 * 1000); + up_write(&ehci_cf_port_reset_rwsem); + + if (rc) { + ehci_err(ehci, "USB %x.%x, controller refused to start: %d\n", + ((ehci->sbrn & 0xf0)>>4), (ehci->sbrn & 0x0f), rc); + return rc; + } + ehci->last_periodic_enable = ktime_get_real(); temp = HC_VERSION(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase)); diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index 087402aec5cb..9f9ab5ccea88 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -345,6 +345,9 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) unlink_empty_async_suspended(ehci); + /* Some Synopsys controllers mistakenly leave IAA turned on */ + ehci_writel(ehci, STS_IAA, &ehci->regs->status); + /* Any IAA cycle that started before the suspend is now invalid */ end_iaa_cycle(ehci); ehci_handle_start_intr_unlinks(ehci); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5677b81c0915..cf0c93a90200 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2931,6 +2931,8 @@ static void queue_trb(struct xhci_hcd *xhci, struct xhci_ring *ring, trb->field[0] = cpu_to_le32(field1); trb->field[1] = cpu_to_le32(field2); trb->field[2] = cpu_to_le32(field3); + /* make sure TRB is fully written before giving it to the controller */ + wmb(); trb->field[3] = cpu_to_le32(field4); trace_xhci_queue_trb(ring, trb); diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 934be1686352..50bb91b6a4b8 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -623,6 +623,13 @@ static void tegra_xusb_mbox_handle(struct tegra_xusb *tegra, enable); if (err < 0) break; + + /* + * wait 500us for LFPS detector to be disabled before + * sending ACK + */ + if (!enable) + usleep_range(500, 1000); } if (err < 0) { diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 5c92a576edae..08f742fd2409 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -15,6 +15,7 @@ struct mlx5_vdpa_direct_mr { struct sg_table sg_head; int log_size; int nsg; + int nent; struct list_head list; u64 offset; }; diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 4b6195666c58..d300f799efcd 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -25,17 +25,6 @@ static int get_octo_len(u64 len, int page_shift) return (npages + 1) / 2; } -static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) -{ - struct scatterlist *sg; - __be64 *pas; - int i; - - pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) - (*pas) = cpu_to_be64(sg_dma_address(sg)); -} - static void mlx5_set_access_mode(void *mkc, int mode) { MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); @@ -45,10 +34,18 @@ static void mlx5_set_access_mode(void *mkc, int mode) static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) { struct scatterlist *sg; + int nsg = mr->nsg; + u64 dma_addr; + u64 dma_len; + int j = 0; int i; - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) - mtt[i] = cpu_to_be64(sg_dma_address(sg)); + for_each_sg(mr->sg_head.sgl, sg, mr->nent, i) { + for (dma_addr = sg_dma_address(sg), dma_len = sg_dma_len(sg); + nsg && dma_len; + nsg--, dma_addr += BIT(mr->log_size), dma_len -= BIT(mr->log_size)) + mtt[j++] = cpu_to_be64(dma_addr); + } } static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) @@ -64,7 +61,6 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct return -ENOMEM; MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); - fill_sg(mr, in); mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); @@ -276,8 +272,8 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr done: mr->log_size = log_entity_size; mr->nsg = nsg; - err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); - if (!err) + mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); + if (!mr->nent) goto err_map; err = create_direct_mr(mvdev, mr); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index c8f0282bb649..18ffd0551b54 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -714,6 +714,23 @@ static bool xs_hvm_defer_init_for_callback(void) #endif } +static int xenbus_probe_thread(void *unused) +{ + DEFINE_WAIT(w); + + /* + * We actually just want to wait for *any* trigger of xb_waitq, + * and run xenbus_probe() the moment it occurs. + */ + prepare_to_wait(&xb_waitq, &w, TASK_INTERRUPTIBLE); + schedule(); + finish_wait(&xb_waitq, &w); + + DPRINTK("probing"); + xenbus_probe(); + return 0; +} + static int __init xenbus_probe_initcall(void) { /* @@ -725,6 +742,20 @@ static int __init xenbus_probe_initcall(void) !xs_hvm_defer_init_for_callback())) xenbus_probe(); + /* + * For XS_LOCAL, spawn a thread which will wait for xenstored + * or a xenstore-stubdom to be started, then probe. It will be + * triggered when communication starts happening, by waiting + * on xb_waitq. + */ + if (xen_store_domain_type == XS_LOCAL) { + struct task_struct *probe_task; + + probe_task = kthread_run(xenbus_probe_thread, NULL, + "xenbus_probe"); + if (IS_ERR(probe_task)) + return PTR_ERR(probe_task); + } return 0; } device_initcall(xenbus_probe_initcall); diff --git a/fs/afs/main.c b/fs/afs/main.c index accdd8970e7c..b2975256dadb 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -193,7 +193,7 @@ static int __init afs_init(void) goto error_cache; #endif - ret = register_pernet_subsys(&afs_net_ops); + ret = register_pernet_device(&afs_net_ops); if (ret < 0) goto error_net; @@ -213,7 +213,7 @@ static int __init afs_init(void) error_proc: afs_fs_exit(); error_fs: - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); error_net: #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); @@ -244,7 +244,7 @@ static void __exit afs_exit(void) proc_remove(afs_proc_symlink); afs_fs_exit(); - unregister_pernet_subsys(&afs_net_ops); + unregister_pernet_device(&afs_net_ops); #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); #endif diff --git a/fs/block_dev.c b/fs/block_dev.c index 3b8963e228a1..235b5042672e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -130,7 +130,15 @@ EXPORT_SYMBOL(truncate_bdev_range); static void set_init_blocksize(struct block_device *bdev) { - bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev)); + unsigned int bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_inode->i_blkbits = blksize_bits(bsize); } int set_blocksize(struct block_device *bdev, int size) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 02d7d7b2563b..9cadacf3ec27 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3117,7 +3117,7 @@ void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache, list_del_init(&lower->list); if (lower == node) node = NULL; - btrfs_backref_free_node(cache, lower); + btrfs_backref_drop_node(cache, lower); } btrfs_backref_cleanup_node(cache, node); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 52f2198d44c9..48ebc106a606 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -673,7 +673,15 @@ static noinline void caching_thread(struct btrfs_work *work) wake_up(&caching_ctl->wait); } - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + /* + * If we are in the transaction that populated the free space tree we + * can't actually cache from the free space tree as our commit root and + * real root are the same, so we could change the contents of the blocks + * while caching. Instead do the slow caching in this case, and after + * the transaction has committed we will be safe. + */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); @@ -2669,7 +2677,8 @@ again: * Go through delayed refs for all the stuff we've just kicked off * and then loop back (just once) */ - ret = btrfs_run_delayed_refs(trans, 0); + if (!ret) + ret = btrfs_run_delayed_refs(trans, 0); if (!ret && loops == 0) { loops++; spin_lock(&cur_trans->dirty_bgs_lock); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e6e37591f1de..4debdbdde2ab 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -563,6 +563,9 @@ enum { /* Indicate that we need to cleanup space cache v1 */ BTRFS_FS_CLEANUP_SPACE_CACHE_V1, + + /* Indicate that we can't trust the free space tree for caching yet */ + BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, }; /* diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d79b8369e6aa..0c335dae5af7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2602,8 +2602,6 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; int ret; - btrfs_add_excluded_extent(trans->fs_info, bytenr, num_bytes); - cache = btrfs_lookup_block_group(trans->fs_info, bytenr); if (!cache) return -EINVAL; @@ -2615,11 +2613,19 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, * the pinned extents. */ btrfs_cache_block_group(cache, 1); + /* + * Make sure we wait until the cache is completely built in case it is + * missing or is invalid and therefore needs to be rebuilt. + */ + ret = btrfs_wait_block_group_cache_done(cache); + if (ret) + goto out; pin_down_extent(trans, cache, bytenr, num_bytes, 0); /* remove us from the free space cache (if we're there at all) */ ret = btrfs_remove_free_space(cache, bytenr, num_bytes); +out: btrfs_put_block_group(cache); return ret; } @@ -2629,50 +2635,22 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, { int ret; struct btrfs_block_group *block_group; - struct btrfs_caching_control *caching_ctl; block_group = btrfs_lookup_block_group(fs_info, start); if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 0); - caching_ctl = btrfs_get_caching_control(block_group); - - if (!caching_ctl) { - /* Logic error */ - BUG_ON(!btrfs_block_group_done(block_group)); - ret = btrfs_remove_free_space(block_group, start, num_bytes); - } else { - /* - * We must wait for v1 caching to finish, otherwise we may not - * remove our space. - */ - btrfs_wait_space_cache_v1_finished(block_group, caching_ctl); - mutex_lock(&caching_ctl->mutex); - - if (start >= caching_ctl->progress) { - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } else if (start + num_bytes <= caching_ctl->progress) { - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - } else { - num_bytes = caching_ctl->progress - start; - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - if (ret) - goto out_lock; + btrfs_cache_block_group(block_group, 1); + /* + * Make sure we wait until the cache is completely built in case it is + * missing or is invalid and therefore needs to be rebuilt. + */ + ret = btrfs_wait_block_group_cache_done(block_group); + if (ret) + goto out; - num_bytes = (start + num_bytes) - - caching_ctl->progress; - start = caching_ctl->progress; - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } -out_lock: - mutex_unlock(&caching_ctl->mutex); - btrfs_put_caching_control(caching_ctl); - } + ret = btrfs_remove_free_space(block_group, start, num_bytes); +out: btrfs_put_block_group(block_group); return ret; } @@ -2863,9 +2841,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; } - if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) - clear_extent_bits(&fs_info->excluded_extents, start, - end, EXTENT_UPTODATE); if (btrfs_test_opt(fs_info, DISCARD_SYNC)) ret = btrfs_discard_extent(fs_info, start, @@ -5549,7 +5524,15 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) goto out_free; } - trans = btrfs_start_transaction(tree_root, 0); + /* + * Use join to avoid potential EINTR from transaction + * start. See wait_reserve_ticket and the whole + * reservation callchain. + */ + if (for_reloc) + trans = btrfs_join_transaction(tree_root); + else + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto out_free; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index e33a65bd9a0c..a33bca94d133 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { @@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + ret = btrfs_commit_transaction(trans); - return btrfs_commit_transaction(trans); + /* + * Now that we've committed the transaction any reading of our commit + * root will be safe, so we can cache from the free space tree now. + */ + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index ae97f4dbaff3..78a35374d492 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5512,6 +5512,21 @@ static int clone_range(struct send_ctx *sctx, break; offset += clone_len; clone_root->offset += clone_len; + + /* + * If we are cloning from the file we are currently processing, + * and using the send root as the clone root, we must stop once + * the current clone offset reaches the current eof of the file + * at the receiver, otherwise we would issue an invalid clone + * operation (source range going beyond eof) and cause the + * receiver to fail. So if we reach the current eof, bail out + * and fallback to a regular write. + */ + if (clone_root->root == sctx->send_root && + clone_root->ino == sctx->cur_ino && + clone_root->offset >= sctx->cur_inode_next_write_offset) + break; + data_offset += clone_len; next: path->slots[0]++; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8e0f7a1029c6..6af7f2bf92de 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2265,14 +2265,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_free_log_root_tree(trans, fs_info); /* - * commit_fs_roots() can call btrfs_save_ino_cache(), which generates - * new delayed refs. Must handle them or qgroup can be wrong. - */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - goto unlock_tree_log; - - /* * Since fs roots are all committed, we can get a quite accurate * new_roots. So let's do quota accounting. */ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b62be84833e9..d6c24c8ad749 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -433,7 +433,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info) atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); - btrfs_device_data_ordered_init(dev, fs_info); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); extent_io_tree_init(fs_info, &dev->alloc_state, @@ -4317,6 +4317,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info) btrfs_warn(fs_info, "balance: cannot set exclusive op status, resume manually"); + btrfs_release_path(path); + mutex_lock(&fs_info->balance_mutex); BUG_ON(fs_info->balance_ctl); spin_lock(&fs_info->balance_lock); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 1997a4649a66..c43663d9c22e 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -39,10 +39,10 @@ struct btrfs_io_geometry { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __BTRFS_NEED_DEVICE_DATA_ORDERED -#define btrfs_device_data_ordered_init(device, info) \ - seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex) +#define btrfs_device_data_ordered_init(device) \ + seqcount_init(&device->data_seqcount) #else -#define btrfs_device_data_ordered_init(device, info) do { } while (0) +#define btrfs_device_data_ordered_init(device) do { } while (0) #endif #define BTRFS_DEV_STATE_WRITEABLE (0) @@ -76,8 +76,7 @@ struct btrfs_device { blk_status_t last_flush_error; #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED - /* A seqcount_t with associated chunk_mutex (for lockdep) */ - seqcount_mutex_t data_seqcount; + seqcount_t data_seqcount; #endif /* the internal btrfs device id */ @@ -168,9 +167,11 @@ btrfs_device_get_##name(const struct btrfs_device *dev) \ static inline void \ btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \ { \ + preempt_disable(); \ write_seqcount_begin(&dev->data_seqcount); \ dev->name = size; \ write_seqcount_end(&dev->data_seqcount); \ + preempt_enable(); \ } #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) #define BTRFS_DEVICE_GETSET_FUNCS(name) \ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 840587037b59..d87bd852ed96 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5038,7 +5038,7 @@ bad: return; } -static struct ceph_connection *con_get(struct ceph_connection *con) +static struct ceph_connection *mds_get_con(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; @@ -5047,7 +5047,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con) return NULL; } -static void con_put(struct ceph_connection *con) +static void mds_put_con(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; @@ -5058,7 +5058,7 @@ static void con_put(struct ceph_connection *con) * if the client is unresponsive for long enough, the mds will kill * the session entirely. */ -static void peer_reset(struct ceph_connection *con) +static void mds_peer_reset(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5067,7 +5067,7 @@ static void peer_reset(struct ceph_connection *con) send_mds_reconnect(mdsc, s); } -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5125,8 +5125,8 @@ out: * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ -static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, - int *proto, int force_new) +static struct ceph_auth_handshake * +mds_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5142,7 +5142,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, return auth; } -static int add_authorizer_challenge(struct ceph_connection *con, +static int mds_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_mds_session *s = con->private; @@ -5153,7 +5153,7 @@ static int add_authorizer_challenge(struct ceph_connection *con, challenge_buf, challenge_buf_len); } -static int verify_authorizer_reply(struct ceph_connection *con) +static int mds_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5165,7 +5165,7 @@ static int verify_authorizer_reply(struct ceph_connection *con) NULL, NULL, NULL, NULL); } -static int invalidate_authorizer(struct ceph_connection *con) +static int mds_invalidate_authorizer(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; @@ -5288,15 +5288,15 @@ static int mds_check_message_signature(struct ceph_msg *msg) } static const struct ceph_connection_operations mds_con_ops = { - .get = con_get, - .put = con_put, - .dispatch = dispatch, - .get_authorizer = get_authorizer, - .add_authorizer_challenge = add_authorizer_challenge, - .verify_authorizer_reply = verify_authorizer_reply, - .invalidate_authorizer = invalidate_authorizer, - .peer_reset = peer_reset, + .get = mds_get_con, + .put = mds_put_con, .alloc_msg = mds_alloc_msg, + .dispatch = mds_dispatch, + .peer_reset = mds_peer_reset, + .get_authorizer = mds_get_authorizer, + .add_authorizer_challenge = mds_add_authorizer_challenge, + .verify_authorizer_reply = mds_verify_authorizer_reply, + .invalidate_authorizer = mds_invalidate_authorizer, .sign_message = mds_sign_message, .check_message_signature = mds_check_message_signature, .get_auth_request = mds_get_auth_request, diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index e4c6ae47a796..6b1ce4efb591 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -133,8 +133,9 @@ cifs_build_devname(char *nodename, const char *prepath) * Caller is responsible for freeing returned value if it is not error. */ char *cifs_compose_mount_options(const char *sb_mountdata, - const char *fullpath, - const struct dfs_info3_param *ref) + const char *fullpath, + const struct dfs_info3_param *ref, + char **devname) { int rc; char *name; @@ -231,7 +232,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata, strcat(mountdata, "ip="); strcat(mountdata, srvIP); - kfree(name); + if (devname) + *devname = name; + else + kfree(name); /*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/ /*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/ @@ -278,7 +282,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt, /* strip first '\' from fullpath */ mountdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - fullpath + 1, NULL); + fullpath + 1, NULL, NULL); if (IS_ERR(mountdata)) { kfree(devname); return (struct vfsmount *)mountdata; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ce0d0037fd0a..e46da536ed33 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -822,7 +822,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, goto out; } - rc = cifs_setup_volume_info(cifs_sb->ctx); + rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC); if (rc) { root = ERR_PTR(rc); goto out; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 340ff81ee87b..32f7a013402e 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -78,7 +78,8 @@ extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx, int add_treename); extern char *build_wildcard_path_from_dentry(struct dentry *direntry); extern char *cifs_compose_mount_options(const char *sb_mountdata, - const char *fullpath, const struct dfs_info3_param *ref); + const char *fullpath, const struct dfs_info3_param *ref, + char **devname); /* extern void renew_parental_timestamps(struct dentry *direntry);*/ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server); @@ -89,6 +90,7 @@ extern void cifs_wake_up_task(struct mid_q_entry *mid); extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx); +extern int smb3_parse_opt(const char *options, const char *key, char **val); extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); extern int cifs_discard_remaining_data(struct TCP_Server_Info *server); extern int cifs_call_async(struct TCP_Server_Info *server, @@ -549,7 +551,7 @@ extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); extern int -cifs_setup_volume_info(struct smb3_fs_context *ctx); +cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname); extern struct TCP_Server_Info * cifs_find_tcp_session(struct smb3_fs_context *ctx); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 5d39129406ea..10fe6d6d2dee 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2195,7 +2195,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) tcon->nohandlecache = ctx->nohandlecache; else - tcon->nohandlecache = 1; + tcon->nohandlecache = true; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); @@ -2628,7 +2628,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, } else if (ctx) tcon->unix_ext = 1; /* Unix Extensions supported */ - if (tcon->unix_ext == 0) { + if (!tcon->unix_ext) { cifs_dbg(FYI, "Unix extensions disabled so not set on reconnect\n"); return; } @@ -2972,17 +2972,20 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), ref_path, &referral, NULL); if (!rc) { + char *fake_devname = NULL; + mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &referral); + full_path + 1, &referral, + &fake_devname); free_dfs_info_param(&referral); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else { - smb3_cleanup_fs_context_contents(ctx); - rc = cifs_setup_volume_info(ctx); + rc = cifs_setup_volume_info(ctx, mdata, fake_devname); } + kfree(fake_devname); kfree(cifs_sb->ctx->mount_options); cifs_sb->ctx->mount_options = mdata; } @@ -3036,6 +3039,7 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path, struct dfs_info3_param ref = {0}; char *mdata = NULL; struct smb3_fs_context fake_ctx = {NULL}; + char *fake_devname = NULL; cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path); @@ -3044,16 +3048,18 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path, return rc; mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &ref); + full_path + 1, &ref, + &fake_devname); free_dfs_info_param(&ref); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else - rc = cifs_setup_volume_info(&fake_ctx); + rc = cifs_setup_volume_info(&fake_ctx, mdata, fake_devname); kfree(mdata); + kfree(fake_devname); if (!rc) { /* @@ -3122,10 +3128,24 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ * we should pass a clone of the original context? */ int -cifs_setup_volume_info(struct smb3_fs_context *ctx) +cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname) { int rc = 0; + smb3_parse_devname(devname, ctx); + + if (mntopts) { + char *ip; + + cifs_dbg(FYI, "%s: mntopts=%s\n", __func__, mntopts); + rc = smb3_parse_opt(mntopts, "ip", &ip); + if (!rc && !cifs_convert_address((struct sockaddr *)&ctx->dstaddr, ip, + strlen(ip))) { + cifs_dbg(VFS, "%s: failed to convert ip address\n", __func__); + return -EINVAL; + } + } + if (ctx->nullauth) { cifs_dbg(FYI, "Anonymous login\n"); kfree(ctx->username); diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 0fdb0de7ff86..4950ab0486ae 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1417,7 +1417,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, int rc; struct cache_entry *ce; struct dfs_info3_param ref = {0}; - char *mdata = NULL; + char *mdata = NULL, *devname = NULL; struct TCP_Server_Info *server; struct cifs_ses *ses; struct smb3_fs_context ctx = {NULL}; @@ -1444,7 +1444,8 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, up_read(&htable_rw_lock); - mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref); + mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref, + &devname); free_dfs_info_param(&ref); if (IS_ERR(mdata)) { @@ -1453,7 +1454,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi, goto out; } - rc = cifs_setup_volume_info(&ctx); + rc = cifs_setup_volume_info(&ctx, NULL, devname); if (rc) { ses = ERR_PTR(rc); @@ -1472,6 +1473,7 @@ out: smb3_cleanup_fs_context_contents(&ctx); kfree(mdata); kfree(rpath); + kfree(devname); return ses; } diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 076bcadc756a..5111aadfdb6b 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -175,8 +175,10 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_flag_no("exec", Opt_ignore), fsparam_flag_no("dev", Opt_ignore), fsparam_flag_no("mand", Opt_ignore), + fsparam_flag_no("auto", Opt_ignore), fsparam_string("cred", Opt_ignore), fsparam_string("credentials", Opt_ignore), + fsparam_string("prefixpath", Opt_ignore), {} }; @@ -399,6 +401,37 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3) return 0; } +int smb3_parse_opt(const char *options, const char *key, char **val) +{ + int rc = -ENOENT; + char *opts, *orig, *p; + + orig = opts = kstrdup(options, GFP_KERNEL); + if (!opts) + return -ENOMEM; + + while ((p = strsep(&opts, ","))) { + char *nval; + + if (!*p) + continue; + if (strncasecmp(p, key, strlen(key))) + continue; + nval = strchr(p, '='); + if (nval) { + if (nval == p) + continue; + *nval++ = 0; + *val = kstrndup(nval, strlen(nval), GFP_KERNEL); + rc = !*val ? -ENOMEM : 0; + goto out; + } + } +out: + kfree(orig); + return rc; +} + /* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise @@ -531,7 +564,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) { cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n"); - return -1; + return -EOPNOTSUPP; } #ifndef CONFIG_KEYS @@ -554,7 +587,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* make sure UNC has a share name */ if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) { cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n"); - return -1; + return -ENOENT; } if (!ctx->got_ip) { @@ -568,7 +601,7 @@ static int smb3_fs_context_validate(struct fs_context *fc) if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr, &ctx->UNC[2], len)) { pr_err("Unable to determine destination address\n"); - return -1; + return -EHOSTUNREACH; } } @@ -1263,7 +1296,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, return 0; cifs_parse_mount_err: - return 1; + return -EINVAL; } int smb3_init_fs_context(struct fs_context *fc) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e9abb41aa89b..95ef26b555b9 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -338,7 +338,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (ssocket == NULL) return -EAGAIN; - if (signal_pending(current)) { + if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); return -ERESTARTSYS; } @@ -429,7 +429,7 @@ unmask: if (signal_pending(current) && (total_len != send_length)) { cifs_dbg(FYI, "signal is pending after attempt to send\n"); - rc = -EINTR; + rc = -ERESTARTSYS; } /* uncork it */ diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a79f..58d0f7187997 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1016,15 +1016,19 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, { int rc; struct dentry *lower_dentry; + struct inode *lower_inode; lower_dentry = ecryptfs_dentry_to_lower(dentry); - if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) { + lower_inode = d_inode(lower_dentry); + if (!(lower_inode->i_opflags & IOP_XATTR)) { rc = -EOPNOTSUPP; goto out; } - rc = vfs_setxattr(lower_dentry, name, value, size, flags); + inode_lock(lower_inode); + rc = __vfs_setxattr_locked(lower_dentry, name, value, size, flags, NULL); + inode_unlock(lower_inode); if (!rc && inode) - fsstack_copy_attr_all(inode, d_inode(lower_dentry)); + fsstack_copy_attr_all(inode, lower_inode); out: return rc; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index acfb55834af2..c41cb887eb7d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1474,21 +1474,25 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Some filesystems may redirty the inode during the writeback - * due to delalloc, clear dirty metadata flags right before - * write_inode() + * If the inode has dirty timestamps and we need to write them, call + * mark_inode_dirty_sync() to notify the filesystem about it and to + * change I_DIRTY_TIME into I_DIRTY_SYNC. */ - spin_lock(&inode->i_lock); - - dirty = inode->i_state & I_DIRTY; if ((inode->i_state & I_DIRTY_TIME) && - ((dirty & I_DIRTY_INODE) || - wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { - dirty |= I_DIRTY_TIME; trace_writeback_lazytime(inode); + mark_inode_dirty_sync(inode); } + + /* + * Some filesystems may redirty the inode during the writeback + * due to delalloc, clear dirty metadata flags right before + * write_inode() + */ + spin_lock(&inode->i_lock); + dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* @@ -1509,8 +1513,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_unlock(&inode->i_lock); - if (dirty & I_DIRTY_TIME) - mark_inode_dirty_sync(inode); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); diff --git a/fs/io_uring.c b/fs/io_uring.c index 985a9e3f976d..38c6cbe1ab38 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1025,6 +1025,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force); +static void io_req_drop_files(struct io_kiocb *req); +static void io_req_task_queue(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -1048,8 +1050,7 @@ EXPORT_SYMBOL(io_uring_get_socket); static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | - REQ_F_INFLIGHT)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) __io_clean_op(req); } @@ -1069,14 +1070,21 @@ static bool io_match_task(struct io_kiocb *head, { struct io_kiocb *req; - if (task && head->task != task) + if (task && head->task != task) { + /* in terms of cancelation, always match if req task is dead */ + if (head->task->flags & PF_EXITING) + return true; return false; + } if (!files) return true; io_for_each_link(req, head) { - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES) && + if (!(req->flags & REQ_F_WORK_INITIALIZED)) + continue; + if (req->file && req->file->f_op == &io_uring_fops) + return true; + if ((req->work.flags & IO_WQ_WORK_FILES) && req->work.identity->files == files) return true; } @@ -1394,6 +1402,8 @@ static void io_req_clean_work(struct io_kiocb *req) free_fs_struct(fs); req->work.flags &= ~IO_WQ_WORK_FS; } + if (req->flags & REQ_F_INFLIGHT) + io_req_drop_files(req); io_put_identity(req->task->io_uring, req); } @@ -1503,11 +1513,14 @@ static bool io_grab_identity(struct io_kiocb *req) return false; atomic_inc(&id->files->count); get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } req->work.flags |= IO_WQ_WORK_FILES; } if (!(req->work.flags & IO_WQ_WORK_MM) && @@ -1622,18 +1635,11 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) do { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); - struct io_kiocb *link; if (req_need_defer(de->req, de->seq)) break; list_del_init(&de->list); - /* punt-init is done before queueing for defer */ - link = __io_queue_async_work(de->req); - if (link) { - __io_queue_linked_timeout(link); - /* drop submission reference */ - io_put_req_deferred(link, 1); - } + io_req_task_queue(de->req); kfree(de); } while (!list_empty(&ctx->defer_list)); } @@ -1767,12 +1773,13 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, struct io_kiocb *req, *tmp; struct io_uring_cqe *cqe; unsigned long flags; - bool all_flushed; + bool all_flushed, posted; LIST_HEAD(list); if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries) return false; + posted = false; spin_lock_irqsave(&ctx->completion_lock, flags); list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { if (!io_match_task(req, tsk, files)) @@ -1792,6 +1799,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow); } + posted = true; } all_flushed = list_empty(&ctx->cq_overflow_list); @@ -1801,9 +1809,11 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } - io_commit_cqring(ctx); + if (posted) + io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); + if (posted) + io_cqring_ev_posted(ctx); while (!list_empty(&list)) { req = list_first_entry(&list, struct io_kiocb, compl.list); @@ -2270,6 +2280,8 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx, struct io_uring_task *tctx = rb->task->io_uring; percpu_counter_sub(&tctx->inflight, rb->task_refs); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); put_task_struct_many(rb->task, rb->task_refs); rb->task = NULL; } @@ -2288,6 +2300,8 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) struct io_uring_task *tctx = rb->task->io_uring; percpu_counter_sub(&tctx->inflight, rb->task_refs); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); put_task_struct_many(rb->task, rb->task_refs); } rb->task = req->task; @@ -3548,7 +3562,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, /* read it all, or we did blocking attempt. no retry. */ if (!iov_iter_count(iter) || !force_nonblock || - (req->file->f_flags & O_NONBLOCK)) + (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG)) goto done; io_size -= ret; @@ -4468,7 +4482,6 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) * io_wq_work.flags, so initialize io_wq_work firstly. */ io_req_init_async(req); - req->work.flags |= IO_WQ_WORK_NO_CANCEL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; @@ -4501,6 +4514,8 @@ static int io_close(struct io_kiocb *req, bool force_nonblock, /* if the file has a flush method, be safe and punt to async */ if (close->put_file->f_op->flush && force_nonblock) { + /* not safe to cancel at this point */ + req->work.flags |= IO_WQ_WORK_NO_CANCEL; /* was never set, but play safe */ req->flags &= ~REQ_F_NOWAIT; /* avoid grabbing files - we don't need the files */ @@ -6157,8 +6172,10 @@ static void io_req_drop_files(struct io_kiocb *req) struct io_uring_task *tctx = req->task->io_uring; unsigned long flags; - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); + if (req->work.flags & IO_WQ_WORK_FILES) { + put_files_struct(req->work.identity->files); + put_nsproxy(req->work.identity->nsproxy); + } spin_lock_irqsave(&ctx->inflight_lock, flags); list_del(&req->inflight_entry); spin_unlock_irqrestore(&ctx->inflight_lock, flags); @@ -6225,9 +6242,6 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } - - if (req->flags & REQ_F_INFLIGHT) - io_req_drop_files(req); } static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, @@ -6446,6 +6460,16 @@ static struct file *io_file_get(struct io_submit_state *state, file = __io_file_get(state, fd); } + if (file && file->f_op == &io_uring_fops && + !(req->flags & REQ_F_INFLIGHT)) { + io_req_init_async(req); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + } + return file; } @@ -7245,14 +7269,18 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, TASK_INTERRUPTIBLE); /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); - if (ret > 0) + if (ret > 0) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } else if (ret < 0) break; if (io_should_wake(&iowq)) break; - if (test_bit(0, &ctx->cq_check_overflow)) + if (test_bit(0, &ctx->cq_check_overflow)) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } if (uts) { timeout = schedule_timeout(timeout); if (timeout == 0) { @@ -8844,39 +8872,44 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } +static int io_uring_count_inflight(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + struct io_kiocb *req; + int cnt = 0; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) + cnt += io_match_task(req, task, files); + spin_unlock_irq(&ctx->inflight_lock); + return cnt; +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct task_struct *task, struct files_struct *files) { while (!list_empty_careful(&ctx->inflight_list)) { struct io_task_cancel cancel = { .task = task, .files = files }; - struct io_kiocb *req; DEFINE_WAIT(wait); - bool found = false; + int inflight; - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (req->task != task || - req->work.identity->files != files) - continue; - found = true; - break; - } - if (found) - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&ctx->inflight_lock); - - /* We need to keep going until we don't find a matching req */ - if (!found) + inflight = io_uring_count_inflight(ctx, task, files); + if (!inflight) break; io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); io_poll_remove_all(ctx, task, files); io_kill_timeouts(ctx, task, files); + io_cqring_overflow_flush(ctx, true, task, files); /* cancellations _may_ trigger task work */ io_run_task_work(); - schedule(); + + prepare_to_wait(&task->io_uring->wait, &wait, + TASK_UNINTERRUPTIBLE); + if (inflight == io_uring_count_inflight(ctx, task, files)) + schedule(); finish_wait(&task->io_uring->wait, &wait); } } @@ -8914,8 +8947,6 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, static void io_disable_sqo_submit(struct io_ring_ctx *ctx) { - WARN_ON_ONCE(ctx->sqo_task != current); - mutex_lock(&ctx->uring_lock); ctx->sqo_dead = 1; mutex_unlock(&ctx->uring_lock); @@ -8936,7 +8967,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, struct task_struct *task = current; if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - /* for SQPOLL only sqo_task has task notes */ io_disable_sqo_submit(ctx); task = ctx->sq_data->thread; atomic_inc(&task->io_uring->in_idle); @@ -8946,10 +8976,9 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, io_cancel_defer_files(ctx, task, files); io_cqring_overflow_flush(ctx, true, task, files); + io_uring_cancel_files(ctx, task, files); if (!files) __io_uring_cancel_task_requests(ctx, task); - else - io_uring_cancel_files(ctx, task, files); if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { atomic_dec(&task->io_uring->in_idle); @@ -9082,6 +9111,10 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + /* trigger io_disable_sqo_submit() */ + if (tctx->sqpoll) + __io_uring_files_cancel(NULL); + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); @@ -9092,16 +9125,15 @@ void __io_uring_task_cancel(void) prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); /* - * If we've seen completions, retry. This avoids a race where - * a completion comes in before we did prepare_to_wait(). + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). */ - if (inflight != tctx_inflight(tctx)) - continue; - schedule(); + if (inflight == tctx_inflight(tctx)) + schedule(); finish_wait(&tctx->wait, &wait); } while (1); - finish_wait(&tctx->wait, &wait); atomic_dec(&tctx->in_idle); io_uring_remove_task_files(tctx); @@ -9112,6 +9144,9 @@ static int io_uring_flush(struct file *file, void *data) struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx = file->private_data; + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_uring_cancel_task_requests(ctx, NULL); + if (!tctx) return 0; @@ -9128,7 +9163,10 @@ static int io_uring_flush(struct file *file, void *data) if (ctx->flags & IORING_SETUP_SQPOLL) { /* there is only one file note, which is owned by sqo_task */ - WARN_ON_ONCE((ctx->sqo_task == current) == + WARN_ON_ONCE(ctx->sqo_task != current && + xa_load(&tctx->xa, (unsigned long)file)); + /* sqo_dead check is for when this happens after cancellation */ + WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead && !xa_load(&tctx->xa, (unsigned long)file)); io_disable_sqo_submit(ctx); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f277d023ebcd..c75719312147 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> +#include <linux/uio.h> #include "kernfs-internal.h" @@ -180,11 +181,10 @@ static const struct seq_operations kernfs_seq_ops = { * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ -static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, - char __user *user_buf, size_t count, - loff_t *ppos) +static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - ssize_t len = min_t(size_t, count, PAGE_SIZE); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; @@ -210,7 +210,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) - len = ops->read(of, buf, len, *ppos); + len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -220,12 +220,12 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, if (len < 0) goto out_free; - if (copy_to_user(user_buf, buf, len)) { + if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -235,31 +235,14 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, return len; } -/** - * kernfs_fop_read - kernfs vfs read callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - */ -static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); - - if (of->kn->flags & KERNFS_HAS_SEQ_SHOW) - return seq_read(file, user_buf, count, ppos); - else - return kernfs_file_direct_read(of, user_buf, count, ppos); + if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) + return seq_read_iter(iocb, iter); + return kernfs_file_read_iter(iocb, iter); } -/** - * kernfs_fop_write - kernfs vfs write callback - * @file: file pointer - * @user_buf: data to write - * @count: number of bytes - * @ppos: starting offset - * +/* * Copy data in from userland and pass it to the matching kernfs write * operation. * @@ -269,20 +252,18 @@ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, * modify only the the value you're changing, then write entire buffer * back. */ -static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct kernfs_open_file *of = kernfs_of(file); + struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); + ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; - ssize_t len; char *buf; if (of->atomic_write_len) { - len = count; if (len > of->atomic_write_len) return -E2BIG; } else { - len = min_t(size_t, count, PAGE_SIZE); + len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; @@ -293,7 +274,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, if (!buf) return -ENOMEM; - if (copy_from_user(buf, user_buf, len)) { + if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } @@ -312,7 +293,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, ops = kernfs_ops(of->kn); if (ops->write) - len = ops->write(of, buf, len, *ppos); + len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; @@ -320,7 +301,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, mutex_unlock(&of->mutex); if (len > 0) - *ppos += len; + iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) @@ -673,7 +654,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* * Write path needs to atomic_write_len outside active reference. - * Cache it in open_file. See kernfs_fop_write() for details. + * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; @@ -960,14 +941,16 @@ void kernfs_notify(struct kernfs_node *kn) EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { - .read = kernfs_fop_read, - .write = kernfs_fop_write, + .read_iter = kernfs_fop_read_iter, + .write_iter = kernfs_fop_write_iter, .llseek = generic_file_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, }; /** diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 4f274f21c4ab..af64b4e6fd1f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -324,6 +324,21 @@ pnfs_grab_inode_layout_hdr(struct pnfs_layout_hdr *lo) return NULL; } +/* + * Compare 2 layout stateid sequence ids, to see which is newer, + * taking into account wraparound issues. + */ +static bool pnfs_seqid_is_newer(u32 s1, u32 s2) +{ + return (s32)(s1 - s2) > 0; +} + +static void pnfs_barrier_update(struct pnfs_layout_hdr *lo, u32 newseq) +{ + if (pnfs_seqid_is_newer(newseq, lo->plh_barrier)) + lo->plh_barrier = newseq; +} + static void pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode, u32 seq) @@ -335,6 +350,7 @@ pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode, if (seq != 0) { WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq); lo->plh_return_seq = seq; + pnfs_barrier_update(lo, seq); } } @@ -639,15 +655,6 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg, return rv; } -/* - * Compare 2 layout stateid sequence ids, to see which is newer, - * taking into account wraparound issues. - */ -static bool pnfs_seqid_is_newer(u32 s1, u32 s2) -{ - return (s32)(s1 - s2) > 0; -} - static bool pnfs_should_free_range(const struct pnfs_layout_range *lseg_range, const struct pnfs_layout_range *recall_range) @@ -984,8 +991,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new, new_barrier = be32_to_cpu(new->seqid); else if (new_barrier == 0) return; - if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier)) - lo->plh_barrier = new_barrier; + pnfs_barrier_update(lo, new_barrier); } static bool @@ -994,7 +1000,7 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo, { u32 seqid = be32_to_cpu(stateid->seqid); - return !pnfs_seqid_is_newer(seqid, lo->plh_barrier); + return !pnfs_seqid_is_newer(seqid, lo->plh_barrier) && lo->plh_barrier; } /* lget is set to 1 if called from inside send_layoutget call chain */ @@ -1183,20 +1189,17 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, return false; set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); pnfs_get_layout_hdr(lo); + nfs4_stateid_copy(stateid, &lo->plh_stateid); + *cred = get_cred(lo->plh_lc_cred); if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) { - nfs4_stateid_copy(stateid, &lo->plh_stateid); - *cred = get_cred(lo->plh_lc_cred); if (lo->plh_return_seq != 0) stateid->seqid = cpu_to_be32(lo->plh_return_seq); if (iomode != NULL) *iomode = lo->plh_return_iomode; pnfs_clear_layoutreturn_info(lo); - return true; - } - nfs4_stateid_copy(stateid, &lo->plh_stateid); - *cred = get_cred(lo->plh_lc_cred); - if (iomode != NULL) + } else if (iomode != NULL) *iomode = IOMODE_ANY; + pnfs_barrier_update(lo, be32_to_cpu(stateid->seqid)); return true; } @@ -1909,6 +1912,11 @@ static void nfs_layoutget_end(struct pnfs_layout_hdr *lo) wake_up_var(&lo->plh_outstanding); } +static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags); +} + static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo) { unsigned long *bitlock = &lo->plh_flags; @@ -2383,23 +2391,34 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) goto out_forget; } - if (!pnfs_layout_is_valid(lo)) { - /* We have a completely new layout */ - pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true); - } else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { + if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) { /* existing state ID, make sure the sequence number matches. */ if (pnfs_layout_stateid_blocked(lo, &res->stateid)) { + if (!pnfs_layout_is_valid(lo) && + pnfs_is_first_layoutget(lo)) + lo->plh_barrier = 0; dprintk("%s forget reply due to sequence\n", __func__); goto out_forget; } pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false); - } else { + } else if (pnfs_layout_is_valid(lo)) { /* * We got an entirely new state ID. Mark all segments for the * inode invalid, and retry the layoutget */ - pnfs_mark_layout_stateid_invalid(lo, &free_me); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .length = NFS4_MAX_UINT64, + }; + pnfs_set_plh_return_info(lo, IOMODE_ANY, 0); + pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &range, 0); goto out_forget; + } else { + /* We have a completely new layout */ + if (!pnfs_is_first_layoutget(lo)) + goto out_forget; + pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true); } pnfs_get_lseg(lseg); diff --git a/fs/pipe.c b/fs/pipe.c index c5989cfd564d..39c96845a72f 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1206,6 +1206,7 @@ const struct file_operations pipefifo_fops = { .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, + .splice_write = iter_file_splice_write, }; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 317899222d7f..d2018f70d1fa 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1770,6 +1770,12 @@ static int process_sysctl_arg(char *param, char *val, return 0; } + if (!val) + return -EINVAL; + len = strlen(val); + if (len == 0) + return -EINVAL; + /* * To set sysctl options, we use a temporary mount of proc, look up the * respective sys/ file and write to it. To avoid mounting it when no @@ -1811,7 +1817,6 @@ static int process_sysctl_arg(char *param, char *val, file, param, val); goto out; } - len = strlen(val); wret = kernel_write(file, val, len, &pos); if (wret < 0) { err = wret; diff --git a/fs/udf/super.c b/fs/udf/super.c index 5bef3a68395d..d0df217f4712 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -705,6 +705,7 @@ static int udf_check_vsd(struct super_block *sb) struct buffer_head *bh = NULL; int nsr = 0; struct udf_sb_info *sbi; + loff_t session_offset; sbi = UDF_SB(sb); if (sb->s_blocksize < sizeof(struct volStructDesc)) @@ -712,7 +713,8 @@ static int udf_check_vsd(struct super_block *sb) else sectorsize = sb->s_blocksize; - sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits); + session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits; + sector += session_offset; udf_debug("Starting at sector %u (%lu byte sectors)\n", (unsigned int)(sector >> sb->s_blocksize_bits), @@ -757,8 +759,7 @@ static int udf_check_vsd(struct super_block *sb) if (nsr > 0) return 1; - else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) == - VSD_FIRST_SECTOR_OFFSET) + else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET) return -1; else return 0; diff --git a/include/dt-bindings/sound/apq8016-lpass.h b/include/dt-bindings/sound/apq8016-lpass.h index 3c3e16c0aadb..dc605c4bc224 100644 --- a/include/dt-bindings/sound/apq8016-lpass.h +++ b/include/dt-bindings/sound/apq8016-lpass.h @@ -2,9 +2,8 @@ #ifndef __DT_APQ8016_LPASS_H #define __DT_APQ8016_LPASS_H -#define MI2S_PRIMARY 0 -#define MI2S_SECONDARY 1 -#define MI2S_TERTIARY 2 -#define MI2S_QUATERNARY 3 +#include <dt-bindings/sound/qcom,lpass.h> + +/* NOTE: Use qcom,lpass.h to define any AIF ID's for LPASS */ #endif /* __DT_APQ8016_LPASS_H */ diff --git a/include/dt-bindings/sound/qcom,lpass.h b/include/dt-bindings/sound/qcom,lpass.h new file mode 100644 index 000000000000..7b0b80b38699 --- /dev/null +++ b/include/dt-bindings/sound/qcom,lpass.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DT_QCOM_LPASS_H +#define __DT_QCOM_LPASS_H + +#define MI2S_PRIMARY 0 +#define MI2S_SECONDARY 1 +#define MI2S_TERTIARY 2 +#define MI2S_QUATERNARY 3 +#define MI2S_QUINARY 4 + +#define LPASS_DP_RX 5 + +#define LPASS_MCLK0 0 + +#endif /* __DT_QCOM_LPASS_H */ diff --git a/include/dt-bindings/sound/sc7180-lpass.h b/include/dt-bindings/sound/sc7180-lpass.h index 56ecaafd2dc6..5c1ee8b36b19 100644 --- a/include/dt-bindings/sound/sc7180-lpass.h +++ b/include/dt-bindings/sound/sc7180-lpass.h @@ -2,10 +2,8 @@ #ifndef __DT_SC7180_LPASS_H #define __DT_SC7180_LPASS_H -#define MI2S_PRIMARY 0 -#define MI2S_SECONDARY 1 -#define LPASS_DP_RX 2 +#include <dt-bindings/sound/qcom,lpass.h> -#define LPASS_MCLK0 0 +/* NOTE: Use qcom,lpass.h to define any AIF ID's for LPASS */ #endif /* __DT_APQ8016_LPASS_H */ diff --git a/include/linux/device.h b/include/linux/device.h index 89bb8b84173e..1779f90eeb4c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -609,6 +609,18 @@ static inline const char *dev_name(const struct device *dev) return kobject_name(&dev->kobj); } +/** + * dev_bus_name - Return a device's bus/class name, if at all possible + * @dev: struct device to get the bus/class name of + * + * Will return the name of the bus/class the device is attached to. If it is + * not attached to a bus/class, an empty string will be returned. + */ +static inline const char *dev_bus_name(const struct device *dev) +{ + return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); +} + __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 88cd72dfa4e0..b12b05f1c8b4 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -64,6 +64,10 @@ int dsa_8021q_rx_source_port(u16 vid); u16 dsa_8021q_rx_subvlan(u16 vid); +bool vid_is_dsa_8021q_rxvlan(u16 vid); + +bool vid_is_dsa_8021q_txvlan(u16 vid); + bool vid_is_dsa_8021q(u16 vid); #else @@ -123,6 +127,16 @@ u16 dsa_8021q_rx_subvlan(u16 vid) return 0; } +bool vid_is_dsa_8021q_rxvlan(u16 vid) +{ + return false; +} + +bool vid_is_dsa_8021q_txvlan(u16 vid) +{ + return false; +} + bool vid_is_dsa_8021q(u16 vid) { return false; diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 65b81e0c494d..2484ed97e72f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,6 +33,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void kthread_set_per_cpu(struct task_struct *k, int cpu); +bool kthread_is_per_cpu(struct task_struct *k); + /** * kthread_run - create and wake a thread. * @threadfn: the function to run until signal_pending(current). diff --git a/include/linux/ktime.h b/include/linux/ktime.h index a12b5523cc18..73f20deb497d 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -230,6 +230,5 @@ static inline ktime_t ms_to_ktime(u64 ms) } # include <linux/timekeeping.h> -# include <linux/timekeeping32.h> #endif diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 5bcfbd972e97..dbf8506decca 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -178,6 +178,11 @@ * Objtool generates debug info for both FUNC & CODE, but needs special * annotations for each CODE's start (to describe the actual stack frame). * + * Objtool requires that all code must be contained in an ELF symbol. Symbol + * names that have a .L prefix do not emit symbol table entries. .L + * prefixed symbols can be used within a code region, but should be avoided for + * denoting a range of code via ``SYM_*_START/END`` annotations. + * * ALIAS -- does not generate debug info -- the aliased function will */ diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..ece53a252217 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -599,6 +599,15 @@ void mhi_set_mhi_state(struct mhi_controller *mhi_cntrl, void mhi_notify(struct mhi_device *mhi_dev, enum mhi_callback cb_reason); /** + * mhi_get_free_desc_count - Get transfer ring length + * Get # of TD available to queue buffers + * @mhi_dev: Device associated with the channels + * @dir: Direction of the channel + */ +int mhi_get_free_desc_count(struct mhi_device *mhi_dev, + enum dma_data_direction dir); + +/** * mhi_prepare_for_power_up - Do pre-initialization before power up. * This is optional, call this before power up if * the controller does not want bus framework to diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 45df5b465ba8..88197b87bd81 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -193,7 +193,8 @@ enum port_state_policy { enum mlx5_coredev_type { MLX5_COREDEV_PF, - MLX5_COREDEV_VF + MLX5_COREDEV_VF, + MLX5_COREDEV_SF, }; struct mlx5_field_desc { @@ -507,6 +508,10 @@ struct mlx5_devcom; struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; +struct mlx5_vhca_state_notifier; +struct mlx5_sf_dev_table; +struct mlx5_sf_hw_table; +struct mlx5_sf_table; struct mlx5_rate_limit { u32 rate; @@ -604,6 +609,15 @@ struct mlx5_priv { struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; +#ifdef CONFIG_MLX5_SF + struct mlx5_vhca_state_notifier *vhca_state_notifier; + struct mlx5_sf_dev_table *sf_dev_table; + struct mlx5_core_dev *parent_mdev; +#endif +#ifdef CONFIG_MLX5_SF_MANAGER + struct mlx5_sf_hw_table *sf_hw_table; + struct mlx5_sf_table *sf_table; +#endif }; enum mlx5_device_state { @@ -1225,22 +1239,4 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) return val.vbool; } -/** - * mlx5_core_net - Provide net namespace of the mlx5_core_dev - * @dev: mlx5 core device - * - * mlx5_core_net() returns the net namespace of mlx5 core device. - * This can be called only in below described limited context. - * (a) When a devlink instance for mlx5_core is registered and - * when devlink reload operation is disabled. - * or - * (b) during devlink reload reload_down() and reload_up callbacks - * where it is ensured that devlink instance's net namespace is - * stable. - */ -static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) -{ - return devlink_net(priv_to_devlink(dev)); -} - #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e8572533d8e..e9e7ada07ea1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1858,7 +1858,6 @@ struct net_device { unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; - int irq; /* * Some hardware also needs these fields (state,dev_list, @@ -1880,6 +1879,23 @@ struct net_device { struct list_head lower; } adj_list; + /* Read-mostly cache-line for fast-path access */ + unsigned int flags; + unsigned int priv_flags; + const struct net_device_ops *netdev_ops; + int ifindex; + unsigned short gflags; + unsigned short hard_header_len; + + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ + unsigned int mtu; + unsigned short needed_headroom; + unsigned short needed_tailroom; + netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; @@ -1888,10 +1904,15 @@ struct net_device { netdev_features_t mpls_features; netdev_features_t gso_partial_features; - int ifindex; + unsigned int min_mtu; + unsigned int max_mtu; + unsigned short type; + unsigned char min_header_len; + unsigned char name_assign_type; + int group; - struct net_device_stats stats; + struct net_device_stats stats; /* not used by modern drivers */ atomic_long_t rx_dropped; atomic_long_t tx_dropped; @@ -1905,7 +1926,6 @@ struct net_device { const struct iw_handler_def *wireless_handlers; struct iw_public_data *wireless_data; #endif - const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; @@ -1924,34 +1944,12 @@ struct net_device { const struct header_ops *header_ops; - unsigned int flags; - unsigned int priv_flags; - - unsigned short gflags; - unsigned short padded; - unsigned char operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; - /* Note : dev->mtu is often read without holding a lock. - * Writers usually hold RTNL. - * It is recommended to use READ_ONCE() to annotate the reads, - * and to use WRITE_ONCE() to annotate the writes. - */ - unsigned int mtu; - unsigned int min_mtu; - unsigned int max_mtu; - unsigned short type; - unsigned short hard_header_len; - unsigned char min_header_len; - unsigned char name_assign_type; - - unsigned short needed_headroom; - unsigned short needed_tailroom; - /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; @@ -1962,7 +1960,10 @@ struct net_device { unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; + unsigned short padded; + spinlock_t addr_list_lock; + int irq; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d92535997687..bfed36e342cc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -116,6 +116,9 @@ enum { NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer * Location */ + NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory + * Space Control + */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -135,6 +138,7 @@ enum { #define NVME_CAP_CSS(cap) (((cap) >> 37) & 0xff) #define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) #define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) +#define NVME_CAP_CMBS(cap) (((cap) >> 57) & 0x1) #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) @@ -192,6 +196,8 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, + NVME_CMBMSC_CRE = 1 << 0, + NVME_CMBMSC_CMSE = 1 << 1, }; struct nvme_id_power_state { diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 4d58dc8943f0..e339b48de32d 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -470,7 +470,7 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) /** * @brief qed_chain_reset - Resets the chain to its start state * - * @param p_chain pointer to a previously allocted chain + * @param p_chain pointer to a previously allocated chain */ static inline void qed_chain_reset(struct qed_chain *p_chain) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 2024944fd2f7..20e84a84fb77 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -332,6 +332,12 @@ regulator_get_exclusive(struct device *dev, const char *id) } static inline struct regulator *__must_check +devm_regulator_get_exclusive(struct device *dev, const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id) { return ERR_PTR(-ENODEV); @@ -486,6 +492,11 @@ static inline int regulator_get_voltage(struct regulator *regulator) return -EINVAL; } +static inline int regulator_sync_voltage(struct regulator *regulator) +{ + return -EINVAL; +} + static inline int regulator_is_supported_voltage(struct regulator *regulator, int min_uV, int max_uV) { @@ -578,6 +589,25 @@ static inline int devm_regulator_unregister_notifier(struct regulator *regulator return 0; } +static inline int regulator_suspend_enable(struct regulator_dev *rdev, + suspend_state_t state) +{ + return -EINVAL; +} + +static inline int regulator_suspend_disable(struct regulator_dev *rdev, + suspend_state_t state) +{ + return -EINVAL; +} + +static inline int regulator_set_suspend_voltage(struct regulator *regulator, + int min_uV, int max_uV, + suspend_state_t state) +{ + return -EINVAL; +} + static inline void *regulator_get_drvdata(struct regulator *regulator) { return NULL; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 19b6dea27367..b26213ae8c1a 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -25,8 +25,7 @@ struct rpc_rqst; #define XDR_QUADLEN(l) (((l) + 3) >> 2) /* - * Generic opaque `network object.' At the kernel level, this type - * is used only by lockd. + * Generic opaque `network object.' */ #define XDR_MAX_NETOBJ 1024 struct xdr_netobj { diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h deleted file mode 100644 index 266017fc9ee9..000000000000 --- a/include/linux/timekeeping32.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef _LINUX_TIMEKEEPING32_H -#define _LINUX_TIMEKEEPING32_H -/* - * These interfaces are all based on the old timespec type - * and should get replaced with the timespec64 based versions - * over time so we can remove the file here. - */ - -static inline unsigned long get_seconds(void) -{ - return ktime_get_real_seconds(); -} - -#endif diff --git a/include/linux/tty.h b/include/linux/tty.h index c873f475f0a7..37803f3e6d49 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -421,6 +421,7 @@ extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); extern int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); extern void tty_ldisc_unlock(struct tty_struct *tty); +extern ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); #else static inline void tty_kref_put(struct tty_struct *tty) { } diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index be36cbdcc1bd..3eb202259e8c 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -520,7 +520,7 @@ int v4l2_fill_pixfmt_mp(struct v4l2_pix_format_mplane *pixfmt, u32 pixelformat, u32 width, u32 height); /** - * v4l2_get_link_rate - Get link rate from transmitter + * v4l2_get_link_freq - Get link rate from transmitter * * @handler: The transmitter's control handler * @mul: The multiplier between pixel rate and link frequency. Bits per pixel on @@ -537,7 +537,7 @@ int v4l2_fill_pixfmt_mp(struct v4l2_pix_format_mplane *pixfmt, u32 pixelformat, * -ENOENT: Link frequency or pixel rate control not found * -EINVAL: Invalid link frequency value */ -s64 v4l2_get_link_rate(struct v4l2_ctrl_handler *handler, unsigned int mul, +s64 v4l2_get_link_freq(struct v4l2_ctrl_handler *handler, unsigned int mul, unsigned int div); static inline u64 v4l2_buffer_get_timestamp(const struct v4l2_buffer *buf) diff --git a/include/net/devlink.h b/include/net/devlink.h index 426b98e74b6e..47b4b063401b 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -94,6 +94,18 @@ struct devlink_port_pci_vf_attrs { }; /** + * struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes + * @controller: Associated controller number + * @sf: Associated PCI SF for of the PCI PF for this port. + * @pf: Associated PCI PF number for this port. + */ +struct devlink_port_pci_sf_attrs { + u32 controller; + u32 sf; + u16 pf; +}; + +/** * struct devlink_port_attrs - devlink port object * @flavour: flavour of the port * @split: indicates if this is split port @@ -103,6 +115,7 @@ struct devlink_port_pci_vf_attrs { * @phys: physical port attributes * @pci_pf: PCI PF port attributes * @pci_vf: PCI VF port attributes + * @pci_sf: PCI SF port attributes */ struct devlink_port_attrs { u8 split:1, @@ -114,6 +127,7 @@ struct devlink_port_attrs { struct devlink_port_phys_attrs phys; struct devlink_port_pci_pf_attrs pci_pf; struct devlink_port_pci_vf_attrs pci_vf; + struct devlink_port_pci_sf_attrs pci_sf; }; }; @@ -138,6 +152,17 @@ struct devlink_port { struct mutex reporters_lock; /* Protects reporter_list */ }; +struct devlink_port_new_attrs { + enum devlink_port_flavour flavour; + unsigned int port_index; + u32 controller; + u32 sfnum; + u16 pfnum; + u8 port_index_valid:1, + controller_valid:1, + sfnum_valid:1; +}; + struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; @@ -1353,6 +1378,79 @@ struct devlink_ops { int (*port_function_hw_addr_set)(struct devlink *devlink, struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); + /** + * port_new() - Add a new port function of a specified flavor + * @devlink: Devlink instance + * @attrs: attributes of the new port + * @extack: extack for reporting error messages + * @new_port_index: index of the new port + * + * Devlink core will call this device driver function upon user request + * to create a new port function of a specified flavor and optional + * attributes + * + * Notes: + * - Called without devlink instance lock being held. Drivers must + * implement own means of synchronization + * - On success, drivers must register a port with devlink core + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_new)(struct devlink *devlink, + const struct devlink_port_new_attrs *attrs, + struct netlink_ext_ack *extack, + unsigned int *new_port_index); + /** + * port_del() - Delete a port function + * @devlink: Devlink instance + * @port_index: port function index to delete + * @extack: extack for reporting error messages + * + * Devlink core will call this device driver function upon user request + * to delete a previously created port function + * + * Notes: + * - Called without devlink instance lock being held. Drivers must + * implement own means of synchronization + * - On success, drivers must unregister the corresponding devlink + * port + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_del)(struct devlink *devlink, unsigned int port_index, + struct netlink_ext_ack *extack); + /** + * port_fn_state_get() - Get the state of a port function + * @devlink: Devlink instance + * @port: The devlink port + * @state: Admin configured state + * @opstate: Current operational state + * @extack: extack for reporting error messages + * + * Reports the admin and operational state of a devlink port function + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_fn_state_get)(struct devlink *devlink, + struct devlink_port *port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack); + /** + * port_fn_state_set() - Set the admin state of a port function + * @devlink: Devlink instance + * @port: The devlink port + * @state: Admin state + * @extack: extack for reporting error messages + * + * Set the admin state of a devlink port function + * + * Return: 0 on success, negative value otherwise. + */ + int (*port_fn_state_set)(struct devlink *devlink, + struct devlink_port *port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) @@ -1409,6 +1507,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro u16 pf, bool external); void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u16 vf, bool external); +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, + u32 controller, u16 pf, u32 sf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/net/dsa.h b/include/net/dsa.h index 2f5435d3d1db..60acb9fca124 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -47,6 +47,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 +#define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -69,6 +70,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, + DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, }; struct packet_type; @@ -140,6 +142,9 @@ struct dsa_switch_tree { /* Has this tree been applied to the hardware? */ bool setup; + /* Tagging protocol operations */ + const struct dsa_device_ops *tag_ops; + /* * Configuration data for the platform device that owns * this dsa switch tree instance. @@ -225,7 +230,9 @@ struct dsa_port { struct net_device *slave; }; - /* CPU port tagging operations used by master or slave devices */ + /* Copy of the tagging protocol operations, for quicker access + * in the data path. Valid only for the CPU ports. + */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in master receive hot path */ @@ -480,9 +487,18 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { + /* + * Tagging protocol helpers called for the CPU ports and DSA links. + * @get_tag_protocol retrieves the initial tagging protocol and is + * mandatory. Switches which can operate using multiple tagging + * protocols should implement @change_tag_protocol and report in + * @get_tag_protocol the tagger in current use. + */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); + int (*change_tag_protocol)(struct dsa_switch *ds, int port, + enum dsa_tag_protocol proto); int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 123b1e9ea304..e6bd8ebf9ac3 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -245,6 +245,7 @@ struct flow_action_entry { unsigned long cookie; u32 mark; u32 labels[4]; + bool orig_dir; } ct_metadata; struct { /* FLOW_ACTION_MPLS_PUSH */ u32 label; diff --git a/include/net/gre.h b/include/net/gre.h index b60f212c16c6..4e209708b754 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -106,17 +106,6 @@ static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) return flags; } -static inline __sum16 gre_checksum(struct sk_buff *skb) -{ - __wsum csum; - - if (skb->ip_summed == CHECKSUM_PARTIAL) - csum = lco_csum(skb); - else - csum = skb_checksum(skb, 0, skb->len, 0); - return csum_fold(csum); -} - static inline void gre_build_header(struct sk_buff *skb, int hdr_len, __be16 flags, __be16 proto, __be32 key, __be32 seq) @@ -146,7 +135,13 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; - *(__sum16 *)ptr = gre_checksum(skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + *(__sum16 *)ptr = csum_fold(lco_csum(skb)); + } else { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = sizeof(*greh); + } } } } diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c11f80f328f1..10a625760de9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -120,14 +120,14 @@ struct inet_connection_sock { __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { - int enabled; - /* Range of MTUs to search */ int search_high; int search_low; /* Information on the current probe. */ - int probe_size; + u32 probe_size:31, + /* Is the MTUP feature enabled for this connection? */ + enabled:1; u32 probe_timestamp; } icsk_mtup; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index ac5ff3c3afb1..1e262b23c68b 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -336,13 +336,6 @@ static inline void fib6_info_release(struct fib6_info *f6i) call_rcu(&f6i->rcu, fib6_info_destroy_rcu); } -static inline void fib6_info_hw_flags_set(struct fib6_info *f6i, bool offload, - bool trap) -{ - f6i->offload = offload; - f6i->trap = trap; -} - enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, @@ -545,6 +538,8 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) { return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } +void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, + bool offload, bool trap); #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index 9259ce2b22f3..ff06246dbbb9 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -128,11 +128,12 @@ struct iucv_sock { u8 flags; u16 msglimit; u16 msglimit_peer; + atomic_t skbs_in_xmit; atomic_t msg_sent; atomic_t msg_recv; atomic_t pendings; int transport; - void (*sk_txnotify)(struct sk_buff *skb, + void (*sk_txnotify)(struct sock *sk, enum iucv_tx_notify n); }; diff --git a/include/net/lapb.h b/include/net/lapb.h index ccc3d1f020b0..eee73442a1ba 100644 --- a/include/net/lapb.h +++ b/include/net/lapb.h @@ -92,6 +92,7 @@ struct lapb_cb { unsigned short n2, n2count; unsigned short t1, t2; struct timer_list t1timer, t2timer; + bool t1timer_stop, t2timer_stop; /* Internal control information */ struct sk_buff_head write_queue; @@ -103,6 +104,7 @@ struct lapb_cb { struct lapb_frame frmr_data; unsigned char frmr_type; + spinlock_t lock; refcount_t refcnt; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f4af8362d234..4b6ecf532623 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -721,6 +721,8 @@ void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *key_end, const u32 *data, u64 timeout, u64 expiration, gfp_t gfp); +int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 8e4fcac4df72..70a2a085dd1a 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -188,6 +188,8 @@ struct netns_ipv4 { int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; + int sysctl_fib_notify_on_flag_change; + #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_udp_l3mdev_accept; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 5ec054473d81..21c0debbd39e 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -51,6 +51,7 @@ struct netns_sysctl_ipv6 { int max_hbh_opts_len; int seg6_flowlabel; bool skip_notify_on_dev_down; + int fib_notify_on_flag_change; }; struct netns_ipv6 { diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 226930d66b63..7bc057aee40b 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -66,7 +66,12 @@ struct nh_info { struct nh_grp_entry { struct nexthop *nh; u8 weight; - atomic_t upper_bound; + + union { + struct { + atomic_t upper_bound; + } mpath; + }; struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ @@ -109,6 +114,11 @@ enum nexthop_event_type { NEXTHOP_EVENT_REPLACE, }; +enum nh_notifier_info_type { + NH_NOTIFIER_INFO_TYPE_SINGLE, + NH_NOTIFIER_INFO_TYPE_GRP, +}; + struct nh_notifier_single_info { struct net_device *dev; u8 gw_family; @@ -137,7 +147,7 @@ struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; u32 id; - bool is_grp; + enum nh_notifier_info_type type; union { struct nh_notifier_single_info *nh; struct nh_notifier_grp_info *nh_grp; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 070f01bf17eb..2d6eb60c58c8 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1151,7 +1151,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, old = *pold; *pold = new; if (old != NULL) - qdisc_tree_flush_backlog(old); + qdisc_purge_queue(old); sch_tree_unlock(sch); return old; diff --git a/include/net/tcp.h b/include/net/tcp.h index 78d13c88720f..25bbada379c4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -630,6 +630,7 @@ static inline void tcp_clear_xmit_timers(struct sock *sk) unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); +u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) @@ -2060,7 +2061,7 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); -extern void tcp_rack_mark_lost(struct sock *sk); +extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); diff --git a/include/net/udp.h b/include/net/udp.h index 877832bed471..01351ba25b87 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -178,7 +178,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, - netdev_features_t features); + netdev_features_t features, bool is_ipv6); static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) { diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index cdc33fa05660..6a61c499a30d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -610,6 +610,7 @@ struct ocelot_port { phy_interface_t phy_mode; u8 *xmit_template; + bool is_dsa_8021q_cpu; }; struct ocelot { @@ -651,8 +652,8 @@ struct ocelot { int npi; - enum ocelot_tag_prefix inj_prefix; - enum ocelot_tag_prefix xtr_prefix; + enum ocelot_tag_prefix npi_inj_prefix; + enum ocelot_tag_prefix npi_xtr_prefix; u32 *lags; @@ -760,6 +761,7 @@ void ocelot_adjust_link(struct ocelot *ocelot, int port, struct phy_device *phydev); int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); +void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot); int ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge); int ocelot_port_bridge_leave(struct ocelot *ocelot, int port, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 96300adf3648..25fd525aaf92 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -400,4 +400,301 @@ enum vcap_es0_action_field { VCAP_ES0_ACT_HIT_STICKY, }; +struct ocelot_ipv4 { + u8 addr[4]; +}; + +enum ocelot_vcap_bit { + OCELOT_VCAP_BIT_ANY, + OCELOT_VCAP_BIT_0, + OCELOT_VCAP_BIT_1 +}; + +struct ocelot_vcap_u8 { + u8 value[1]; + u8 mask[1]; +}; + +struct ocelot_vcap_u16 { + u8 value[2]; + u8 mask[2]; +}; + +struct ocelot_vcap_u24 { + u8 value[3]; + u8 mask[3]; +}; + +struct ocelot_vcap_u32 { + u8 value[4]; + u8 mask[4]; +}; + +struct ocelot_vcap_u40 { + u8 value[5]; + u8 mask[5]; +}; + +struct ocelot_vcap_u48 { + u8 value[6]; + u8 mask[6]; +}; + +struct ocelot_vcap_u64 { + u8 value[8]; + u8 mask[8]; +}; + +struct ocelot_vcap_u128 { + u8 value[16]; + u8 mask[16]; +}; + +struct ocelot_vcap_vid { + u16 value; + u16 mask; +}; + +struct ocelot_vcap_ipv4 { + struct ocelot_ipv4 value; + struct ocelot_ipv4 mask; +}; + +struct ocelot_vcap_udp_tcp { + u16 value; + u16 mask; +}; + +struct ocelot_vcap_port { + u8 value; + u8 mask; +}; + +enum ocelot_vcap_key_type { + OCELOT_VCAP_KEY_ANY, + OCELOT_VCAP_KEY_ETYPE, + OCELOT_VCAP_KEY_LLC, + OCELOT_VCAP_KEY_SNAP, + OCELOT_VCAP_KEY_ARP, + OCELOT_VCAP_KEY_IPV4, + OCELOT_VCAP_KEY_IPV6 +}; + +struct ocelot_vcap_key_vlan { + struct ocelot_vcap_vid vid; /* VLAN ID (12 bit) */ + struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */ + enum ocelot_vcap_bit dei; /* DEI */ + enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */ +}; + +struct ocelot_vcap_key_etype { + struct ocelot_vcap_u48 dmac; + struct ocelot_vcap_u48 smac; + struct ocelot_vcap_u16 etype; + struct ocelot_vcap_u16 data; /* MAC data */ +}; + +struct ocelot_vcap_key_llc { + struct ocelot_vcap_u48 dmac; + struct ocelot_vcap_u48 smac; + + /* LLC header: DSAP at byte 0, SSAP at byte 1, Control at byte 2 */ + struct ocelot_vcap_u32 llc; +}; + +struct ocelot_vcap_key_snap { + struct ocelot_vcap_u48 dmac; + struct ocelot_vcap_u48 smac; + + /* SNAP header: Organization Code at byte 0, Type at byte 3 */ + struct ocelot_vcap_u40 snap; +}; + +struct ocelot_vcap_key_arp { + struct ocelot_vcap_u48 smac; + enum ocelot_vcap_bit arp; /* Opcode ARP/RARP */ + enum ocelot_vcap_bit req; /* Opcode request/reply */ + enum ocelot_vcap_bit unknown; /* Opcode unknown */ + enum ocelot_vcap_bit smac_match; /* Sender MAC matches SMAC */ + enum ocelot_vcap_bit dmac_match; /* Target MAC matches DMAC */ + + /**< Protocol addr. length 4, hardware length 6 */ + enum ocelot_vcap_bit length; + + enum ocelot_vcap_bit ip; /* Protocol address type IP */ + enum ocelot_vcap_bit ethernet; /* Hardware address type Ethernet */ + struct ocelot_vcap_ipv4 sip; /* Sender IP address */ + struct ocelot_vcap_ipv4 dip; /* Target IP address */ +}; + +struct ocelot_vcap_key_ipv4 { + enum ocelot_vcap_bit ttl; /* TTL zero */ + enum ocelot_vcap_bit fragment; /* Fragment */ + enum ocelot_vcap_bit options; /* Header options */ + struct ocelot_vcap_u8 ds; + struct ocelot_vcap_u8 proto; /* Protocol */ + struct ocelot_vcap_ipv4 sip; /* Source IP address */ + struct ocelot_vcap_ipv4 dip; /* Destination IP address */ + struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */ + struct ocelot_vcap_udp_tcp sport; /* UDP/TCP: Source port */ + struct ocelot_vcap_udp_tcp dport; /* UDP/TCP: Destination port */ + enum ocelot_vcap_bit tcp_fin; + enum ocelot_vcap_bit tcp_syn; + enum ocelot_vcap_bit tcp_rst; + enum ocelot_vcap_bit tcp_psh; + enum ocelot_vcap_bit tcp_ack; + enum ocelot_vcap_bit tcp_urg; + enum ocelot_vcap_bit sip_eq_dip; /* SIP equals DIP */ + enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT */ + enum ocelot_vcap_bit seq_zero; /* TCP sequence number is zero */ +}; + +struct ocelot_vcap_key_ipv6 { + struct ocelot_vcap_u8 proto; /* IPv6 protocol */ + struct ocelot_vcap_u128 sip; /* IPv6 source (byte 0-7 ignored) */ + struct ocelot_vcap_u128 dip; /* IPv6 destination (byte 0-7 ignored) */ + enum ocelot_vcap_bit ttl; /* TTL zero */ + struct ocelot_vcap_u8 ds; + struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */ + struct ocelot_vcap_udp_tcp sport; + struct ocelot_vcap_udp_tcp dport; + enum ocelot_vcap_bit tcp_fin; + enum ocelot_vcap_bit tcp_syn; + enum ocelot_vcap_bit tcp_rst; + enum ocelot_vcap_bit tcp_psh; + enum ocelot_vcap_bit tcp_ack; + enum ocelot_vcap_bit tcp_urg; + enum ocelot_vcap_bit sip_eq_dip; /* SIP equals DIP */ + enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT */ + enum ocelot_vcap_bit seq_zero; /* TCP sequence number is zero */ +}; + +enum ocelot_mask_mode { + OCELOT_MASK_MODE_NONE, + OCELOT_MASK_MODE_PERMIT_DENY, + OCELOT_MASK_MODE_POLICY, + OCELOT_MASK_MODE_REDIRECT, +}; + +enum ocelot_es0_tag { + OCELOT_NO_ES0_TAG, + OCELOT_ES0_TAG, + OCELOT_FORCE_PORT_TAG, + OCELOT_FORCE_UNTAG, +}; + +enum ocelot_tag_tpid_sel { + OCELOT_TAG_TPID_SEL_8021Q, + OCELOT_TAG_TPID_SEL_8021AD, +}; + +struct ocelot_vcap_action { + union { + /* VCAP ES0 */ + struct { + enum ocelot_es0_tag push_outer_tag; + enum ocelot_es0_tag push_inner_tag; + enum ocelot_tag_tpid_sel tag_a_tpid_sel; + int tag_a_vid_sel; + int tag_a_pcp_sel; + u16 vid_a_val; + u8 pcp_a_val; + u8 dei_a_val; + enum ocelot_tag_tpid_sel tag_b_tpid_sel; + int tag_b_vid_sel; + int tag_b_pcp_sel; + u16 vid_b_val; + u8 pcp_b_val; + u8 dei_b_val; + }; + + /* VCAP IS1 */ + struct { + bool vid_replace_ena; + u16 vid; + bool vlan_pop_cnt_ena; + int vlan_pop_cnt; + bool pcp_dei_ena; + u8 pcp; + u8 dei; + bool qos_ena; + u8 qos_val; + u8 pag_override_mask; + u8 pag_val; + }; + + /* VCAP IS2 */ + struct { + bool cpu_copy_ena; + u8 cpu_qu_num; + enum ocelot_mask_mode mask_mode; + unsigned long port_mask; + bool police_ena; + struct ocelot_policer pol; + u32 pol_ix; + }; + }; +}; + +struct ocelot_vcap_stats { + u64 bytes; + u64 pkts; + u64 used; +}; + +enum ocelot_vcap_filter_type { + OCELOT_VCAP_FILTER_DUMMY, + OCELOT_VCAP_FILTER_PAG, + OCELOT_VCAP_FILTER_OFFLOAD, +}; + +struct ocelot_vcap_id { + unsigned long cookie; + bool tc_offload; +}; + +struct ocelot_vcap_filter { + struct list_head list; + + enum ocelot_vcap_filter_type type; + int block_id; + int goto_target; + int lookup; + u8 pag; + u16 prio; + struct ocelot_vcap_id id; + + struct ocelot_vcap_action action; + struct ocelot_vcap_stats stats; + /* For VCAP IS1 and IS2 */ + unsigned long ingress_port_mask; + /* For VCAP ES0 */ + struct ocelot_vcap_port ingress_port; + struct ocelot_vcap_port egress_port; + + enum ocelot_vcap_bit dmac_mc; + enum ocelot_vcap_bit dmac_bc; + struct ocelot_vcap_key_vlan vlan; + + enum ocelot_vcap_key_type key_type; + union { + /* OCELOT_VCAP_KEY_ANY: No specific fields */ + struct ocelot_vcap_key_etype etype; + struct ocelot_vcap_key_llc llc; + struct ocelot_vcap_key_snap snap; + struct ocelot_vcap_key_arp arp; + struct ocelot_vcap_key_ipv4 ipv4; + struct ocelot_vcap_key_ipv6 ipv6; + } key; +}; + +int ocelot_vcap_filter_add(struct ocelot *ocelot, + struct ocelot_vcap_filter *rule, + struct netlink_ext_ack *extack); +int ocelot_vcap_filter_del(struct ocelot *ocelot, + struct ocelot_vcap_filter *rule); +struct ocelot_vcap_filter * +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id, + bool tc_offload); + #endif /* _OCELOT_VCAP_H_ */ diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 2336bf9243e1..2e1200d17d0c 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -229,7 +229,7 @@ typedef int (*snd_pcm_hw_rule_func_t)(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule { unsigned int cond; int var; - int deps[4]; + int deps[5]; snd_pcm_hw_rule_func_t func; void *private; diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 5039af667645..cbe3e152d24c 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -366,7 +366,7 @@ TRACE_EVENT(sched_process_wait, ); /* - * Tracepoint for do_fork: + * Tracepoint for kernel_clone: */ TRACE_EVENT(sched_process_fork, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cf89c318f2ac..f6008b2fa60f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -200,6 +200,10 @@ enum devlink_port_flavour { DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but * is not used in any way. */ + DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port + * for the PCI SF. It is an internal + * port that faces the PCI SF. + */ }; enum devlink_param_cmode { @@ -529,6 +533,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ + DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, @@ -578,9 +583,29 @@ enum devlink_resource_unit { enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ + DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ + DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 }; +enum devlink_port_fn_state { + DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE, +}; + +/** + * enum devlink_port_fn_opstate - indicates operational state of the function + * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function. + * For graceful tear down of the function, after inactivation of the + * function, user should wait for operational state to turn DETACHED. + * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function. + * It is safe to delete the port. + */ +enum devlink_port_fn_opstate { + DEVLINK_PORT_FN_OPSTATE_DETACHED, + DEVLINK_PORT_FN_OPSTATE_ATTACHED, +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h index 9744773de5ff..bd4424de56ff 100644 --- a/include/uapi/linux/mrp_bridge.h +++ b/include/uapi/linux/mrp_bridge.h @@ -71,90 +71,4 @@ enum br_mrp_sub_tlv_header_type { BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR = 0x3, }; -struct br_mrp_tlv_hdr { - __u8 type; - __u8 length; -}; - -struct br_mrp_sub_tlv_hdr { - __u8 type; - __u8 length; -}; - -struct br_mrp_end_hdr { - struct br_mrp_tlv_hdr hdr; -}; - -struct br_mrp_common_hdr { - __be16 seq_id; - __u8 domain[MRP_DOMAIN_UUID_LENGTH]; -}; - -struct br_mrp_ring_test_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 state; - __be16 transitions; - __be32 timestamp; -}; - -struct br_mrp_ring_topo_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 interval; -}; - -struct br_mrp_ring_link_hdr { - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 interval; - __be16 blocked; -}; - -struct br_mrp_sub_opt_hdr { - __u8 type; - __u8 manufacture_data[MRP_MANUFACTURE_DATA_LENGTH]; -}; - -struct br_mrp_test_mgr_nack_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 other_prio; - __u8 other_sa[ETH_ALEN]; -}; - -struct br_mrp_test_prop_hdr { - __be16 prio; - __u8 sa[ETH_ALEN]; - __be16 other_prio; - __u8 other_sa[ETH_ALEN]; -}; - -struct br_mrp_oui_hdr { - __u8 oui[MRP_OUI_LENGTH]; -}; - -struct br_mrp_in_test_hdr { - __be16 id; - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 state; - __be16 transitions; - __be32 timestamp; -}; - -struct br_mrp_in_topo_hdr { - __u8 sa[ETH_ALEN]; - __be16 id; - __be16 interval; -}; - -struct br_mrp_in_link_hdr { - __u8 sa[ETH_ALEN]; - __be16 port_role; - __be16 id; - __be16 interval; -}; - #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 709668e264b0..afe6836e44b1 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -592,6 +592,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ + TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */ }; enum { diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 6e449e784260..36e3efb81b01 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -49,8 +49,14 @@ #define RKISP1_CIF_ISP_CTK_COEFF_MAX 0x100 #define RKISP1_CIF_ISP_CTK_OFFSET_MAX 0x800 -#define RKISP1_CIF_ISP_AE_MEAN_MAX 25 -#define RKISP1_CIF_ISP_HIST_BIN_N_MAX 16 +#define RKISP1_CIF_ISP_AE_MEAN_MAX_V10 25 +#define RKISP1_CIF_ISP_AE_MEAN_MAX_V12 81 +#define RKISP1_CIF_ISP_AE_MEAN_MAX RKISP1_CIF_ISP_AE_MEAN_MAX_V12 + +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 16 +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 32 +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 + #define RKISP1_CIF_ISP_AFM_MAX_WINDOWS 3 #define RKISP1_CIF_ISP_DEGAMMA_CURVE_SIZE 17 @@ -86,7 +92,9 @@ * Gamma out */ /* Maximum number of color samples supported */ -#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES 17 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 17 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 34 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 /* * Lens shade correction @@ -102,8 +110,9 @@ /* * Histogram calculation */ -/* Last 3 values unused. */ -#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 28 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 25 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 81 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 /* * Defect Pixel Cluster Correction @@ -124,6 +133,21 @@ #define RKISP1_CIF_ISP_STAT_AFM (1U << 2) #define RKISP1_CIF_ISP_STAT_HIST (1U << 3) +/** + * enum rkisp1_cif_isp_version - ISP variants + * + * @RKISP1_V10: used at least in rk3288 and rk3399 + * @RKISP1_V11: declared in the original vendor code, but not used + * @RKISP1_V12: used at least in rk3326 and px30 + * @RKISP1_V13: used at least in rk1808 + */ +enum rkisp1_cif_isp_version { + RKISP1_V10 = 10, + RKISP1_V11, + RKISP1_V12, + RKISP1_V13, +}; + enum rkisp1_cif_isp_histogram_mode { RKISP1_CIF_ISP_HISTOGRAM_MODE_DISABLE, RKISP1_CIF_ISP_HISTOGRAM_MODE_RGB_COMBINED, @@ -510,6 +534,15 @@ enum rkisp1_cif_isp_goc_mode { * * @mode: goc mode (from enum rkisp1_cif_isp_goc_mode) * @gamma_y: gamma out curve y-axis for all color components + * + * The number of entries of @gamma_y depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 + * entries, versions >= V12 have RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 + * entries. RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES is equal to the maximum + * of the two. */ struct rkisp1_cif_isp_goc_config { __u32 mode; @@ -524,6 +557,15 @@ struct rkisp1_cif_isp_goc_config { * skipped * @meas_window: coordinates of the measure window * @hist_weight: weighting factor for sub-windows + * + * The number of entries of @hist_weight depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 + * entries, versions >= V12 have RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 + * entries. RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE is equal to the maximum + * of the two. */ struct rkisp1_cif_isp_hst_config { __u32 mode; @@ -811,7 +853,15 @@ struct rkisp1_cif_isp_bls_meas_val { * @exp_mean: Mean luminance value of block xx * @bls_val: BLS measured values * - * Image is divided into 5x5 blocks. + * The number of entries of @exp_mean depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_AE_MEAN_MAX_V10 entries, + * versions >= V12 have RKISP1_CIF_ISP_AE_MEAN_MAX_V12 entries. + * RKISP1_CIF_ISP_AE_MEAN_MAX is equal to the maximum of the two. + * + * Image is divided into 5x5 blocks on V10 and 9x9 blocks on V12. */ struct rkisp1_cif_isp_ae_stat { __u8 exp_mean[RKISP1_CIF_ISP_AE_MEAN_MAX]; @@ -844,13 +894,29 @@ struct rkisp1_cif_isp_af_stat { /** * struct rkisp1_cif_isp_hist_stat - statistics histogram data * - * @hist_bins: measured bin counters + * @hist_bins: measured bin counters. Each bin is a 20 bits unsigned fixed point + * type. Bits 0-4 are the fractional part and bits 5-19 are the + * integer part. + * + * The window of the measurements area is divided to 5x5 sub-windows for + * V10/V11 and to 9x9 sub-windows for V12. The histogram is then computed for + * each sub-window independently and the final result is a weighted average of + * the histogram measurements on all sub-windows. The window of the + * measurements area and the weight of each sub-window are configurable using + * struct @rkisp1_cif_isp_hst_config. + * + * The histogram contains 16 bins in V10/V11 and 32 bins in V12/V13. + * + * The number of entries of @hist_bins depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. * - * Measurement window divided into 25 sub-windows, set - * with ISP_HIST_XXX + * Versions <= V11 have RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 entries, + * versions >= V12 have RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 entries. + * RKISP1_CIF_ISP_HIST_BIN_N_MAX is equal to the maximum of the two. */ struct rkisp1_cif_isp_hist_stat { - __u16 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; + __u32 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; }; /** diff --git a/include/uapi/linux/rpl.h b/include/uapi/linux/rpl.h index 1dccb55cf8c6..708adddf9f13 100644 --- a/include/uapi/linux/rpl.h +++ b/include/uapi/linux/rpl.h @@ -28,10 +28,10 @@ struct ipv6_rpl_sr_hdr { pad:4, reserved1:16; #elif defined(__BIG_ENDIAN_BITFIELD) - __u32 reserved:20, + __u32 cmpri:4, + cmpre:4, pad:4, - cmpri:4, - cmpre:4; + reserved:20; #else #error "Please fix <asm/byteorder.h>" #endif diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 00850b98078a..a38454d9e0f5 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -176,7 +176,7 @@ struct v4l2_subdev_capability { }; /* The v4l2 sub-device video device node is registered in read-only mode. */ -#define V4L2_SUBDEV_CAP_RO_SUBDEV BIT(0) +#define V4L2_SUBDEV_CAP_RO_SUBDEV 0x00000001 /* Backwards compatibility define --- to be removed */ #define v4l2_subdev_edid v4l2_edid diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h index f8b638c73371..901a4fd72c09 100644 --- a/include/uapi/rdma/vmw_pvrdma-abi.h +++ b/include/uapi/rdma/vmw_pvrdma-abi.h @@ -133,6 +133,13 @@ enum pvrdma_wc_flags { PVRDMA_WC_FLAGS_MAX = PVRDMA_WC_WITH_NETWORK_HDR_TYPE, }; +enum pvrdma_network_type { + PVRDMA_NETWORK_IB, + PVRDMA_NETWORK_ROCE_V1 = PVRDMA_NETWORK_IB, + PVRDMA_NETWORK_IPV4, + PVRDMA_NETWORK_IPV6 +}; + struct pvrdma_alloc_ucontext_resp { __u32 qp_tab_size; __u32 reserved; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 2f0597320b6d..6639640523c0 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -125,8 +125,12 @@ static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, fd = *(int *)key; f = fget_raw(fd); - if (!f || !inode_storage_ptr(f->f_inode)) + if (!f) + return -EBADF; + if (!inode_storage_ptr(f->f_inode)) { + fput(f); return -EBADF; + } sdata = bpf_local_storage_update(f->f_inode, (struct bpf_local_storage_map *)map, diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 70e5e0b6d69d..1622a44d1617 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -149,7 +149,11 @@ BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) + +#ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_inet_conn_established) +#endif /* CONFIG_SECURITY_NETWORK */ + BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) @@ -166,7 +170,11 @@ BTF_ID(func, bpf_lsm_inode_symlink) BTF_ID(func, bpf_lsm_inode_unlink) BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernfs_init_security) + +#ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) +#endif /* CONFIG_KEYS */ + BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) @@ -181,6 +189,8 @@ BTF_ID(func, bpf_lsm_sb_show_options) BTF_ID(func, bpf_lsm_sb_statfs) BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) + +#ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) @@ -195,6 +205,8 @@ BTF_ID(func, bpf_lsm_socket_recvmsg) BTF_ID(func, bpf_lsm_socket_sendmsg) BTF_ID(func, bpf_lsm_socket_shutdown) BTF_ID(func, bpf_lsm_socket_socketpair) +#endif /* CONFIG_SECURITY_NETWORK */ + BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_task_getsecid) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 96555a8a2c54..6aa9e10c6335 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1442,6 +1442,11 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } + if (ctx.optlen < 0) { + ret = -EFAULT; + goto out; + } + if (copy_from_user(ctx.optval, optval, min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; @@ -1459,7 +1464,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen) { + if (ctx.optlen > max_optlen || ctx.optlen < 0) { ret = -EFAULT; goto out; } diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile index 23ee310b6eb4..1951332dd15f 100644 --- a/kernel/bpf/preload/Makefile +++ b/kernel/bpf/preload/Makefile @@ -4,8 +4,11 @@ LIBBPF_SRCS = $(srctree)/tools/lib/bpf/ LIBBPF_A = $(obj)/libbpf.a LIBBPF_OUT = $(abspath $(obj)) +# Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test +# in tools/scripts/Makefile.include always succeeds when building the kernel +# with $(O) pointing to a relative path, as in "make O=build bindeb-pkg". $(LIBBPF_A): - $(Q)$(MAKE) -C $(LIBBPF_SRCS) OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a + $(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \ -I $(srctree)/tools/lib/ -Wno-unused-result diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index b1496e744c68..1b1b8ff875cb 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -147,8 +147,10 @@ static int do_map_benchmark(struct map_benchmark_data *map) atomic64_set(&map->sum_sq_unmap, 0); atomic64_set(&map->loops, 0); - for (i = 0; i < threads; i++) + for (i = 0; i < threads; i++) { + get_task_struct(tsk[i]); wake_up_process(tsk[i]); + } msleep_interruptible(map->bparam.seconds * 1000); @@ -183,6 +185,8 @@ static int do_map_benchmark(struct map_benchmark_data *map) } out: + for (i = 0; i < threads; i++) + put_task_struct(tsk[i]); put_device(map->dev); kfree(tsk); return ret; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 378341642f94..6dd82be60df8 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -222,7 +222,7 @@ static inline bool report_single_step(unsigned long work) */ static inline bool report_single_step(unsigned long work) { - if (!(work & SYSCALL_WORK_SYSCALL_EMU)) + if (work & SYSCALL_WORK_SYSCALL_EMU) return false; return !!(current_thread_info()->flags & _TIF_SINGLESTEP); diff --git a/kernel/fork.c b/kernel/fork.c index 37720a6d04ea..d66cd1014211 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -819,9 +819,8 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - for (i = 0; i < UCOUNT_COUNTS; i++) { + for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - } #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", @@ -1654,9 +1653,8 @@ static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; - for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { + for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); - } } static inline void diff --git a/kernel/futex.c b/kernel/futex.c index c47d1015d759..45a13eb8894e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -763,6 +763,29 @@ static struct futex_pi_state *alloc_pi_state(void) return pi_state; } +static void pi_state_update_owner(struct futex_pi_state *pi_state, + struct task_struct *new_owner) +{ + struct task_struct *old_owner = pi_state->owner; + + lockdep_assert_held(&pi_state->pi_mutex.wait_lock); + + if (old_owner) { + raw_spin_lock(&old_owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock(&old_owner->pi_lock); + } + + if (new_owner) { + raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + } +} + static void get_pi_state(struct futex_pi_state *pi_state) { WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount)); @@ -785,17 +808,11 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - struct task_struct *owner; unsigned long flags; raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); - owner = pi_state->owner; - if (owner) { - raw_spin_lock(&owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock(&owner->pi_lock); - } - rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + pi_state_update_owner(pi_state, NULL); + rt_mutex_proxy_unlock(&pi_state->pi_mutex); raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } @@ -941,7 +958,8 @@ static inline void exit_pi_state_list(struct task_struct *curr) { } * FUTEX_OWNER_DIED bit. See [4] * * [10] There is no transient state which leaves owner and user space - * TID out of sync. + * TID out of sync. Except one error case where the kernel is denied + * write access to the user address, see fixup_pi_state_owner(). * * * Serialization and lifetime rules: @@ -1521,26 +1539,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ ret = -EINVAL; } - if (ret) - goto out_unlock; - - /* - * This is a point of no return; once we modify the uval there is no - * going back and subsequent operations must not fail. - */ - - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - - raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; - raw_spin_unlock(&new_owner->pi_lock); - - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + if (!ret) { + /* + * This is a point of no return; once we modified the uval + * there is no going back and subsequent operations must + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + } out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); @@ -2323,18 +2330,13 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *argowner) +static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) { struct futex_pi_state *pi_state = q->pi_state; - u32 uval, curval, newval; struct task_struct *oldowner, *newowner; - u32 newtid; - int ret, err = 0; - - lockdep_assert_held(q->lock_ptr); - - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + u32 uval, curval, newval, newtid; + int err = 0; oldowner = pi_state->owner; @@ -2368,14 +2370,12 @@ retry: * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 0; } if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { - /* We got the lock after all, nothing to fix. */ - ret = 0; - goto out_unlock; + /* We got the lock. pi_state is correct. Tell caller. */ + return 1; } /* @@ -2402,8 +2402,7 @@ retry: * We raced against a concurrent self; things are * already fixed up. Nothing to do. */ - ret = 0; - goto out_unlock; + return 1; } newowner = argowner; } @@ -2433,22 +2432,9 @@ retry: * We fixed up user space. Now we need to fix the pi_state * itself. */ - if (pi_state->owner != NULL) { - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - } + pi_state_update_owner(pi_state, newowner); - pi_state->owner = newowner; - - raw_spin_lock(&newowner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &newowner->pi_state_list); - raw_spin_unlock(&newowner->pi_lock); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - - return 0; + return argowner == current; /* * In order to reschedule or handle a page fault, we need to drop the @@ -2469,17 +2455,16 @@ handle_err: switch (err) { case -EFAULT: - ret = fault_in_user_writeable(uaddr); + err = fault_in_user_writeable(uaddr); break; case -EAGAIN: cond_resched(); - ret = 0; + err = 0; break; default: WARN_ON_ONCE(1); - ret = err; break; } @@ -2489,17 +2474,44 @@ handle_err: /* * Check if someone else fixed it for us: */ - if (pi_state->owner != oldowner) { - ret = 0; - goto out_unlock; - } + if (pi_state->owner != oldowner) + return argowner == current; - if (ret) - goto out_unlock; + /* Retry if err was -EAGAIN or the fault in succeeded */ + if (!err) + goto retry; - goto retry; + /* + * fault_in_user_writeable() failed so user state is immutable. At + * best we can make the kernel state consistent but user state will + * be most likely hosed and any subsequent unlock operation will be + * rejected due to PI futex rule [10]. + * + * Ensure that the rtmutex owner is also the pi_state owner despite + * the user space value claiming something different. There is no + * point in unlocking the rtmutex if current is the owner as it + * would need to wait until the next waiter has taken the rtmutex + * to guarantee consistent state. Keep it simple. Userspace asked + * for this wreckaged state. + * + * The rtmutex has an owner - either current or some other + * task. See the EAGAIN loop above. + */ + pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex)); -out_unlock: + return err; +} + +static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, + struct task_struct *argowner) +{ + struct futex_pi_state *pi_state = q->pi_state; + int ret; + + lockdep_assert_held(q->lock_ptr); + + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + ret = __fixup_pi_state_owner(uaddr, q, argowner); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; } @@ -2523,8 +2535,6 @@ static long futex_wait_restart(struct restart_block *restart); */ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) { - int ret = 0; - if (locked) { /* * Got the lock. We might not be the anticipated owner if we @@ -2535,8 +2545,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) - ret = fixup_pi_state_owner(uaddr, q, current); - return ret ? ret : locked; + return fixup_pi_state_owner(uaddr, q, current); + return 1; } /* @@ -2547,23 +2557,17 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Another speculative read; pi_state->owner == current is unstable * but needs our attention. */ - if (q->pi_state->owner == current) { - ret = fixup_pi_state_owner(uaddr, q, NULL); - return ret; - } + if (q->pi_state->owner == current) + return fixup_pi_state_owner(uaddr, q, NULL); /* * Paranoia check. If we did not take the lock, then we should not be - * the owner of the rt_mutex. + * the owner of the rt_mutex. Warn and establish consistent state. */ - if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) { - printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p " - "pi-state %p\n", ret, - q->pi_state->pi_mutex.owner, - q->pi_state->owner); - } + if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current)) + return fixup_pi_state_owner(uaddr, q, current); - return ret; + return 0; } /** @@ -2771,7 +2775,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to; - struct futex_pi_state *pi_state = NULL; struct task_struct *exiting = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; @@ -2907,23 +2910,8 @@ no_block: if (res) ret = (res < 0) ? res : 0; - /* - * If fixup_owner() faulted and was unable to handle the fault, unlock - * it and return the fault to userspace. - */ - if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock */ unqueue_me_pi(&q); - - if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - goto out; out_unlock_put_key: @@ -3183,7 +3171,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 __user *uaddr2) { struct hrtimer_sleeper timeout, *to; - struct futex_pi_state *pi_state = NULL; struct rt_mutex_waiter rt_waiter; struct futex_hash_bucket *hb; union futex_key key2 = FUTEX_KEY_INIT; @@ -3261,16 +3248,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } /* * Drop the reference to the pi state which * the requeue_pi() code acquired for us. */ put_pi_state(q.pi_state); spin_unlock(q.lock_ptr); + /* + * Adjust the return value. It's either -EFAULT or + * success (1) but the caller expects 0 for success. + */ + ret = ret < 0 ? ret : 0; } } else { struct rt_mutex *pi_mutex; @@ -3301,25 +3289,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (res) ret = (res < 0) ? res : 0; - /* - * If fixup_pi_state_owner() faulted and was unable to handle - * the fault, unlock the rt_mutex and return the fault to - * userspace. - */ - if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { - pi_state = q.pi_state; - get_pi_state(pi_state); - } - /* Unqueue and drop the lock. */ unqueue_me_pi(&q); } - if (pi_state) { - rt_mutex_futex_unlock(&pi_state->pi_mutex); - put_pi_state(pi_state); - } - if (ret == -EINTR) { /* * We've already been requeued, but cannot restart by calling diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ab8567f32501..dec3f73e8db9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -2859,3 +2859,4 @@ bool irq_check_status_bit(unsigned int irq, unsigned int bitmask) rcu_read_unlock(); return res; } +EXPORT_SYMBOL_GPL(irq_check_status_bit); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 2c0c4d6d0f83..dc0e2d7fbdfd 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -402,7 +402,7 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct msi_domain_ops *ops = info->ops; struct irq_data *irq_data; struct msi_desc *desc; - msi_alloc_info_t arg; + msi_alloc_info_t arg = { }; int i, ret, virq; bool can_reserve; diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 4f8efc278aa7..aa919585c24b 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1134,7 +1134,6 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { - lock_system_sleep(); pm_prepare_console(); error = freeze_processes(); if (error) { @@ -1197,7 +1196,6 @@ int kernel_kexec(void) thaw_processes(); Restore_console: pm_restore_console(); - unlock_system_sleep(); } #endif diff --git a/kernel/kthread.c b/kernel/kthread.c index a5eceecd4513..1578973c5740 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -294,7 +294,7 @@ static int kthread(void *_create) do_exit(ret); } -/* called from do_fork() to get node information for about to be created task */ +/* called from kernel_clone() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA @@ -493,11 +493,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c1418b47f625..bdaf4829098c 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644); DEFINE_PER_CPU(unsigned int, lockdep_recursion); EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion); -static inline bool lockdep_enabled(void) +static __always_inline bool lockdep_enabled(void) { if (!debug_locks) return false; @@ -5271,12 +5271,15 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie /* * Check whether we follow the irq-flags state precisely: */ -static void check_flags(unsigned long flags) +static noinstr void check_flags(unsigned long flags) { #if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) if (!debug_locks) return; + /* Get the warning out.. */ + instrumentation_begin(); + if (irqs_disabled_flags(flags)) { if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) { printk("possible reason: unannotated irqs-off.\n"); @@ -5304,6 +5307,8 @@ static void check_flags(unsigned long flags) if (!debug_locks) print_irqtrace_events(current); + + instrumentation_end(); #endif } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index cfdd5b93264d..2f8cd616d3b2 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1716,8 +1716,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, * possible because it belongs to the pi_state which is about to be freed * and it is not longer visible to other tasks. */ -void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner) +void rt_mutex_proxy_unlock(struct rt_mutex *lock) { debug_rt_mutex_proxy_unlock(lock); rt_mutex_set_owner(lock, NULL); diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index d1d62f942be2..ca6fb489007b 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -133,8 +133,7 @@ enum rtmutex_chainwalk { extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); -extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, - struct task_struct *proxy_owner); +extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, diff --git a/kernel/power/swap.c b/kernel/power/swap.c index c73f2e295167..72e33054a2e1 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -497,10 +497,10 @@ static int swap_writer_finish(struct swap_map_handle *handle, unsigned int flags, int error) { if (!error) { - flush_swap_writer(handle); pr_info("S"); error = mark_swapfiles(handle, flags); pr_cont("|\n"); + flush_swap_writer(handle); } if (error) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ffdd0dc7ec6d..5a95c688621f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1291,11 +1291,16 @@ static size_t info_print_prefix(const struct printk_info *info, bool syslog, * done: * * - Add prefix for each line. + * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). - * - Drop truncated lines that do not longer fit into the buffer. + * - Add a string terminator. + * + * Since the produced string is always terminated, the maximum possible + * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added - * prefixes and the newline. The dropped line(s) are not counted. + * prefixes and the newline. The terminator is not counted. The dropped + * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) @@ -1338,26 +1343,31 @@ static size_t record_print_text(struct printk_record *r, bool syslog, /* * Truncate the text if there is not enough space to add the - * prefix and a trailing newline. + * prefix and a trailing newline and a terminator. */ - if (len + prefix_len + text_len + 1 > buf_size) { + if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ - if (len + prefix_len + line_len + 1 > buf_size) + if (len + prefix_len + line_len + 1 + 1 > buf_size) break; - text_len = buf_size - len - prefix_len - 1; + text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); + /* + * Increment the prepared length to include the text and + * prefix that were just moved+copied. Also increment for the + * newline at the end of this line. If this is the last line, + * there is no newline, but it will be added immediately below. + */ len += prefix_len + line_len + 1; - if (text_len == line_len) { /* - * Add the trailing newline removed in - * vprintk_store(). + * This is the last line. Add the trailing newline + * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; @@ -1382,6 +1392,14 @@ static size_t record_print_text(struct printk_record *r, bool syslog, text_len -= line_len + 1; } + /* + * If a buffer was provided, it will be terminated. Space for the + * string terminator is guaranteed to be available. The terminator is + * not counted in the return value. + */ + if (buf_size > 0) + r->text_buf[len] = 0; + return len; } @@ -3427,7 +3445,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, while (prb_read_valid_info(prb, seq, &info, &line_count)) { if (r.info->seq >= dumper->next_seq) break; - l += get_record_print_text_size(&info, line_count, true, time); + l += get_record_print_text_size(&info, line_count, syslog, time); seq = r.info->seq + 1; } @@ -3437,7 +3455,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, &info, &line_count)) { if (r.info->seq >= dumper->next_seq) break; - l -= get_record_print_text_size(&info, line_count, true, time); + l -= get_record_print_text_size(&info, line_count, syslog, time); seq = r.info->seq + 1; } diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index 6704f06e0417..8a7b7362c0dd 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -1718,7 +1718,7 @@ static bool copy_data(struct prb_data_ring *data_ring, /* Caller interested in the line count? */ if (line_count) - *line_count = count_lines(data, data_size); + *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 15d2562118d1..ff74fca39ed2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1796,13 +1796,28 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { + /* When not in the task's cpumask, no point in looking further. */ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; - if (is_per_cpu_kthread(p) || is_migration_disabled(p)) + /* migrate_disabled() must be allowed to finish. */ + if (is_migration_disabled(p)) return cpu_online(cpu); - return cpu_active(cpu); + /* Non kernel threads are not allowed during either online or offline. */ + if (!(p->flags & PF_KTHREAD)) + return cpu_active(cpu); + + /* KTHREAD_IS_PER_CPU is always allowed. */ + if (kthread_is_per_cpu(p)) + return cpu_online(cpu); + + /* Regular kernel threads don't get to stay during offline. */ + if (cpu_rq(cpu)->balance_push) + return false; + + /* But are allowed during online. */ + return cpu_online(cpu); } /* @@ -2327,7 +2342,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (p->flags & PF_KTHREAD || is_migration_disabled(p)) { /* - * Kernel threads are allowed on online && !active CPUs. + * Kernel threads are allowed on online && !active CPUs, + * however, during cpu-hot-unplug, even these might get pushed + * away if not KTHREAD_IS_PER_CPU. * * Specifically, migration_disabled() tasks must not fail the * cpumask_any_and_distribute() pick below, esp. so on @@ -2371,16 +2388,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, __do_set_cpus_allowed(p, new_mask, flags); - if (p->flags & PF_KTHREAD) { - /* - * For kernel threads that do indeed end up on online && - * !active we want to ensure they are strict per-CPU threads. - */ - WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && - !cpumask_intersects(new_mask, cpu_active_mask) && - p->nr_cpus_allowed != 1); - } - return affine_move_task(rq, p, &rf, dest_cpu, flags); out: @@ -3122,6 +3129,13 @@ bool cpus_share_cache(int this_cpu, int that_cpu) static inline bool ttwu_queue_cond(int cpu, int wake_flags) { /* + * Do not complicate things with the async wake_list while the CPU is + * in hotplug state. + */ + if (!cpu_active(cpu)) + return false; + + /* * If the CPU does not share cache, then queue the task on the * remote rqs wakelist to avoid accessing remote data. */ @@ -7276,8 +7290,14 @@ static void balance_push(struct rq *rq) /* * Both the cpu-hotplug and stop task are in this case and are * required to complete the hotplug process. + * + * XXX: the idle task does not match kthread_is_per_cpu() due to + * histerical raisins. */ - if (is_per_cpu_kthread(push_task) || is_migration_disabled(push_task)) { + if (rq->idle == push_task || + ((push_task->flags & PF_KTHREAD) && kthread_is_per_cpu(push_task)) || + is_migration_disabled(push_task)) { + /* * If this is the idle task on the outgoing CPU try to wake * up the hotplug control thread which might wait for the @@ -7309,7 +7329,7 @@ static void balance_push(struct rq *rq) /* * At this point need_resched() is true and we'll take the loop in * schedule(). The next pick is obviously going to be the stop task - * which is_per_cpu_kthread() and will push this task away. + * which kthread_is_per_cpu() and will push this task away. */ raw_spin_lock(&rq->lock); } @@ -7320,10 +7340,13 @@ static void balance_push_set(int cpu, bool on) struct rq_flags rf; rq_lock_irqsave(rq, &rf); - if (on) + rq->balance_push = on; + if (on) { + WARN_ON_ONCE(rq->balance_callback); rq->balance_callback = &balance_push_callback; - else + } else if (rq->balance_callback == &balance_push_callback) { rq->balance_callback = NULL; + } rq_unlock_irqrestore(rq, &rf); } @@ -7441,6 +7464,10 @@ int sched_cpu_activate(unsigned int cpu) struct rq *rq = cpu_rq(cpu); struct rq_flags rf; + /* + * Make sure that when the hotplug state machine does a roll-back + * we clear balance_push. Ideally that would happen earlier... + */ balance_push_set(cpu, false); #ifdef CONFIG_SCHED_SMT @@ -7483,17 +7510,27 @@ int sched_cpu_deactivate(unsigned int cpu) int ret; set_cpu_active(cpu, false); + + /* + * From this point forward, this CPU will refuse to run any task that + * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively + * push those tasks away until this gets cleared, see + * sched_cpu_dying(). + */ + balance_push_set(cpu, true); + /* - * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU - * users of this state to go away such that all new such users will - * observe it. + * We've cleared cpu_active_mask / set balance_push, wait for all + * preempt-disabled and RCU users of this state to go away such that + * all new such users will observe it. + * + * Specifically, we rely on ttwu to no longer target this CPU, see + * ttwu_queue_cond() and is_cpu_allowed(). * * Do sync before park smpboot threads to take care the rcu boost case. */ synchronize_rcu(); - balance_push_set(cpu, true); - rq_lock_irqsave(rq, &rf); if (rq->rd) { update_rq_clock(rq); @@ -7574,6 +7611,25 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } +static void dump_rq_tasks(struct rq *rq, const char *loglvl) +{ + struct task_struct *g, *p; + int cpu = cpu_of(rq); + + lockdep_assert_held(&rq->lock); + + printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running); + for_each_process_thread(g, p) { + if (task_cpu(p) != cpu) + continue; + + if (!task_on_rq_queued(p)) + continue; + + printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm); + } +} + int sched_cpu_dying(unsigned int cpu) { struct rq *rq = cpu_rq(cpu); @@ -7583,9 +7639,18 @@ int sched_cpu_dying(unsigned int cpu) sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); - BUG_ON(rq->nr_running != 1 || rq_has_pinned_tasks(rq)); + if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) { + WARN(true, "Dying CPU not properly vacated!"); + dump_rq_tasks(rq, KERN_WARNING); + } rq_unlock_irqrestore(rq, &rf); + /* + * Now that the CPU is offline, make sure we're welcome + * to new tasks once we come back up. + */ + balance_push_set(cpu, false); + calc_load_migrate(rq); update_max_interval(); nohz_balance_exit_idle(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 12ada79d40f3..bb09988451a0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -975,6 +975,7 @@ struct rq { unsigned long cpu_capacity_orig; struct callback_head *balance_callback; + unsigned char balance_push; unsigned char nohz_idle_balance; unsigned char idle_balance; diff --git a/kernel/signal.c b/kernel/signal.c index 6b9c431da08f..5ad8566534e7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3704,7 +3704,8 @@ static bool access_pidfd_pidns(struct pid *pid) return true; } -static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info) +static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, + siginfo_t __user *info) { #ifdef CONFIG_COMPAT /* diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2efe1e206167..f25208e8df83 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available. diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 7404d3831527..87389b9e21ab 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -498,7 +498,7 @@ out: static void sync_hw_clock(struct work_struct *work); static DECLARE_WORK(sync_work, sync_hw_clock); static struct hrtimer sync_hrtimer; -#define SYNC_PERIOD_NS (11UL * 60 * NSEC_PER_SEC) +#define SYNC_PERIOD_NS (11ULL * 60 * NSEC_PER_SEC) static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer) { @@ -512,7 +512,7 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) ktime_t exp = ktime_set(ktime_get_real_seconds(), 0); if (retry) - exp = ktime_add_ns(exp, 2 * NSEC_PER_SEC - offset_nsec); + exp = ktime_add_ns(exp, 2ULL * NSEC_PER_SEC - offset_nsec); else exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a45cedda93a7..6aee5768c86f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -991,8 +991,7 @@ EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * - * Returns the wall clock seconds since 1970. This replaces the - * get_seconds() interface which is not y2038 safe on 32bit systems. + * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9880b6c0e272..894bb885b40b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1849,18 +1849,17 @@ static void worker_attach_to_pool(struct worker *worker, mutex_lock(&wq_pool_attach_mutex); /* - * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any - * online CPUs. It'll be re-applied when any of the CPUs come up. - */ - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); - - /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag * definition for details. */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; + else + kthread_set_per_cpu(worker->task, pool->cpu); + + if (worker->rescue_wq) + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; @@ -1883,6 +1882,7 @@ static void worker_detach_from_pool(struct worker *worker) mutex_lock(&wq_pool_attach_mutex); + kthread_set_per_cpu(worker->task, -1); list_del(&worker->node); worker->pool = NULL; @@ -4919,8 +4919,10 @@ static void unbind_workers(int cpu) raw_spin_unlock_irq(&pool->lock); - for_each_pool_worker(worker, pool) - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0); + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, -1); + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); + } mutex_unlock(&wq_pool_attach_mutex); @@ -4972,9 +4974,11 @@ static void rebind_workers(struct worker_pool *pool) * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ - for_each_pool_worker(worker, pool) + for_each_pool_worker(worker, pool) { + kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); + } raw_spin_lock_irq(&pool->lock); diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 8b635fd75fe4..3a0b1c930733 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -123,6 +123,7 @@ config UBSAN_SIGNED_OVERFLOW config UBSAN_UNSIGNED_OVERFLOW bool "Perform checking for unsigned arithmetic overflow" depends on $(cc-option,-fsanitize=unsigned-integer-overflow) + depends on !X86_32 # avoid excessive stack usage on x86-32/clang help This option enables -fsanitize=unsigned-integer-overflow which checks for overflow of any arithmetic operations with unsigned integers. This diff --git a/mm/highmem.c b/mm/highmem.c index c3a9ea7875ef..874b732b120c 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -473,6 +473,11 @@ static inline void *arch_kmap_local_high_get(struct page *page) } #endif +#ifndef arch_kmap_local_set_pte +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + set_pte_at(mm, vaddr, ptep, ptev) +#endif + /* Unmap a local mapping which was obtained by kmap_high_get() */ static inline bool kmap_high_unmap_local(unsigned long vaddr) { @@ -515,7 +520,7 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot) vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte - idx))); pteval = pfn_pte(pfn, prot); - set_pte_at(&init_mm, vaddr, kmap_pte - idx, pteval); + arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval); arch_kmap_local_post_map(vaddr, pteval); current->kmap_ctrl.pteval[kmap_local_idx()] = pteval; preempt_enable(); diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 55bd6f09c70f..e529428e7a11 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -19,11 +19,10 @@ #include "kasan.h" -enum kasan_arg_mode { - KASAN_ARG_MODE_DEFAULT, - KASAN_ARG_MODE_OFF, - KASAN_ARG_MODE_PROD, - KASAN_ARG_MODE_FULL, +enum kasan_arg { + KASAN_ARG_DEFAULT, + KASAN_ARG_OFF, + KASAN_ARG_ON, }; enum kasan_arg_stacktrace { @@ -38,7 +37,7 @@ enum kasan_arg_fault { KASAN_ARG_FAULT_PANIC, }; -static enum kasan_arg_mode kasan_arg_mode __ro_after_init; +static enum kasan_arg kasan_arg __ro_after_init; static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init; static enum kasan_arg_fault kasan_arg_fault __ro_after_init; @@ -52,26 +51,24 @@ DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace); /* Whether panic or disable tag checking on fault. */ bool kasan_flag_panic __ro_after_init; -/* kasan.mode=off/prod/full */ -static int __init early_kasan_mode(char *arg) +/* kasan=off/on */ +static int __init early_kasan_flag(char *arg) { if (!arg) return -EINVAL; if (!strcmp(arg, "off")) - kasan_arg_mode = KASAN_ARG_MODE_OFF; - else if (!strcmp(arg, "prod")) - kasan_arg_mode = KASAN_ARG_MODE_PROD; - else if (!strcmp(arg, "full")) - kasan_arg_mode = KASAN_ARG_MODE_FULL; + kasan_arg = KASAN_ARG_OFF; + else if (!strcmp(arg, "on")) + kasan_arg = KASAN_ARG_ON; else return -EINVAL; return 0; } -early_param("kasan.mode", early_kasan_mode); +early_param("kasan", early_kasan_flag); -/* kasan.stack=off/on */ +/* kasan.stacktrace=off/on */ static int __init early_kasan_flag_stacktrace(char *arg) { if (!arg) @@ -113,8 +110,8 @@ void kasan_init_hw_tags_cpu(void) * as this function is only called for MTE-capable hardware. */ - /* If KASAN is disabled, do nothing. */ - if (kasan_arg_mode == KASAN_ARG_MODE_OFF) + /* If KASAN is disabled via command line, don't initialize it. */ + if (kasan_arg == KASAN_ARG_OFF) return; hw_init_tags(KASAN_TAG_MAX); @@ -124,43 +121,28 @@ void kasan_init_hw_tags_cpu(void) /* kasan_init_hw_tags() is called once on boot CPU. */ void __init kasan_init_hw_tags(void) { - /* If hardware doesn't support MTE, do nothing. */ + /* If hardware doesn't support MTE, don't initialize KASAN. */ if (!system_supports_mte()) return; - /* Choose KASAN mode if kasan boot parameter is not provided. */ - if (kasan_arg_mode == KASAN_ARG_MODE_DEFAULT) { - if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) - kasan_arg_mode = KASAN_ARG_MODE_FULL; - else - kasan_arg_mode = KASAN_ARG_MODE_PROD; - } - - /* Preset parameter values based on the mode. */ - switch (kasan_arg_mode) { - case KASAN_ARG_MODE_DEFAULT: - /* Shouldn't happen as per the check above. */ - WARN_ON(1); - return; - case KASAN_ARG_MODE_OFF: - /* If KASAN is disabled, do nothing. */ + /* If KASAN is disabled via command line, don't initialize it. */ + if (kasan_arg == KASAN_ARG_OFF) return; - case KASAN_ARG_MODE_PROD: - static_branch_enable(&kasan_flag_enabled); - break; - case KASAN_ARG_MODE_FULL: - static_branch_enable(&kasan_flag_enabled); - static_branch_enable(&kasan_flag_stacktrace); - break; - } - /* Now, optionally override the presets. */ + /* Enable KASAN. */ + static_branch_enable(&kasan_flag_enabled); switch (kasan_arg_stacktrace) { case KASAN_ARG_STACKTRACE_DEFAULT: + /* + * Default to enabling stack trace collection for + * debug kernels. + */ + if (IS_ENABLED(CONFIG_DEBUG_KERNEL)) + static_branch_enable(&kasan_flag_stacktrace); break; case KASAN_ARG_STACKTRACE_OFF: - static_branch_disable(&kasan_flag_stacktrace); + /* Do nothing, kasan_flag_stacktrace keeps its default value. */ break; case KASAN_ARG_STACKTRACE_ON: static_branch_enable(&kasan_flag_stacktrace); @@ -169,11 +151,16 @@ void __init kasan_init_hw_tags(void) switch (kasan_arg_fault) { case KASAN_ARG_FAULT_DEFAULT: + /* + * Default to no panic on report. + * Do nothing, kasan_flag_panic keeps its default value. + */ break; case KASAN_ARG_FAULT_REPORT: - kasan_flag_panic = false; + /* Do nothing, kasan_flag_panic keeps its default value. */ break; case KASAN_ARG_FAULT_PANIC: + /* Enable panic on report. */ kasan_flag_panic = true; break; } diff --git a/mm/kasan/init.c b/mm/kasan/init.c index 7ca0b92d5886..c4605ac9837b 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -373,9 +373,10 @@ static void kasan_remove_pmd_table(pmd_t *pmd, unsigned long addr, if (kasan_pte_table(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && - IS_ALIGNED(next, PMD_SIZE)) + IS_ALIGNED(next, PMD_SIZE)) { pmd_clear(pmd); - continue; + continue; + } } pte = pte_offset_kernel(pmd, addr); kasan_remove_pte_table(pte, addr, next); @@ -398,9 +399,10 @@ static void kasan_remove_pud_table(pud_t *pud, unsigned long addr, if (kasan_pmd_table(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && - IS_ALIGNED(next, PUD_SIZE)) + IS_ALIGNED(next, PUD_SIZE)) { pud_clear(pud); - continue; + continue; + } } pmd = pmd_offset(pud, addr); pmd_base = pmd_offset(pud, 0); @@ -424,9 +426,10 @@ static void kasan_remove_p4d_table(p4d_t *p4d, unsigned long addr, if (kasan_pud_table(*p4d)) { if (IS_ALIGNED(addr, P4D_SIZE) && - IS_ALIGNED(next, P4D_SIZE)) + IS_ALIGNED(next, P4D_SIZE)) { p4d_clear(p4d); - continue; + continue; + } } pud = pud_offset(p4d, addr); kasan_remove_pud_table(pud, addr, next); @@ -457,9 +460,10 @@ void kasan_remove_zero_shadow(void *start, unsigned long size) if (kasan_p4d_table(*pgd)) { if (IS_ALIGNED(addr, PGDIR_SIZE) && - IS_ALIGNED(next, PGDIR_SIZE)) + IS_ALIGNED(next, PGDIR_SIZE)) { pgd_clear(pgd); - continue; + continue; + } } p4d = p4d_offset(pgd, addr); @@ -482,7 +486,6 @@ int kasan_add_zero_shadow(void *start, unsigned long size) ret = kasan_populate_early_shadow(shadow_start, shadow_end); if (ret) - kasan_remove_zero_shadow(shadow_start, - size >> KASAN_SHADOW_SCALE_SHIFT); + kasan_remove_zero_shadow(start, size); return ret; } diff --git a/mm/memblock.c b/mm/memblock.c index d24bcfa88d2f..1eaaec1e7687 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1427,7 +1427,7 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, } /** - * memblock_phys_alloc_try_nid - allocate a memory block from specified MUMA node + * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 605f671203ef..e2de77b5bcc2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3115,9 +3115,7 @@ void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) page_counter_uncharge(&memcg->kmem, nr_pages); - page_counter_uncharge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_uncharge(&memcg->memsw, nr_pages); + refill_stock(memcg, nr_pages); } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 04d9f154a130..e9481632fcd1 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1885,6 +1885,12 @@ static int soft_offline_free_page(struct page *page) return rc; } +static void put_ref_page(struct page *page) +{ + if (page) + put_page(page); +} + /** * soft_offline_page - Soft offline a page. * @pfn: pfn to soft-offline @@ -1910,20 +1916,26 @@ static int soft_offline_free_page(struct page *page) int soft_offline_page(unsigned long pfn, int flags) { int ret; - struct page *page; bool try_again = true; + struct page *page, *ref_page = NULL; + + WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED)); if (!pfn_valid(pfn)) return -ENXIO; + if (flags & MF_COUNT_INCREASED) + ref_page = pfn_to_page(pfn); + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ page = pfn_to_online_page(pfn); - if (!page) + if (!page) { + put_ref_page(ref_page); return -EIO; + } if (PageHWPoison(page)) { pr_info("%s: %#lx page already poisoned\n", __func__, pfn); - if (flags & MF_COUNT_INCREASED) - put_page(page); + put_ref_page(ref_page); return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index ee5e612b4cd8..c0efe921bca5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -402,6 +402,7 @@ int migrate_page_move_mapping(struct address_space *mapping, struct zone *oldzone, *newzone; int dirty; int expected_count = expected_page_refs(mapping, page) + extra_count; + int nr = thp_nr_pages(page); if (!mapping) { /* Anonymous page without mapping */ @@ -437,7 +438,7 @@ int migrate_page_move_mapping(struct address_space *mapping, */ newpage->index = page->index; newpage->mapping = page->mapping; - page_ref_add(newpage, thp_nr_pages(page)); /* add cache reference */ + page_ref_add(newpage, nr); /* add cache reference */ if (PageSwapBacked(page)) { __SetPageSwapBacked(newpage); if (PageSwapCache(page)) { @@ -459,7 +460,7 @@ int migrate_page_move_mapping(struct address_space *mapping, if (PageTransHuge(page)) { int i; - for (i = 1; i < HPAGE_PMD_NR; i++) { + for (i = 1; i < nr; i++) { xas_next(&xas); xas_store(&xas, newpage); } @@ -470,7 +471,7 @@ int migrate_page_move_mapping(struct address_space *mapping, * to one less reference. * We know this isn't the last reference. */ - page_ref_unfreeze(page, expected_count - thp_nr_pages(page)); + page_ref_unfreeze(page, expected_count - nr); xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ @@ -493,17 +494,17 @@ int migrate_page_move_mapping(struct address_space *mapping, old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); - __dec_lruvec_state(old_lruvec, NR_FILE_PAGES); - __inc_lruvec_state(new_lruvec, NR_FILE_PAGES); + __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); + __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); if (PageSwapBacked(page) && !PageSwapCache(page)) { - __dec_lruvec_state(old_lruvec, NR_SHMEM); - __inc_lruvec_state(new_lruvec, NR_SHMEM); + __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); + __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); } if (dirty && mapping_can_writeback(mapping)) { - __dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY); - __dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING); - __inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY); - __inc_zone_state(newzone, NR_ZONE_WRITE_PENDING); + __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); + __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr); + __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr); + __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr); } } local_irq_enable(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 027f6481ba59..519a60d5b6f7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1207,8 +1207,10 @@ static void kernel_init_free_pages(struct page *page, int numpages) /* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); for (i = 0; i < numpages; i++) { + u8 tag = page_kasan_tag(page + i); page_kasan_tag_reset(page + i); clear_highpage(page + i); + page_kasan_tag_set(page + i, tag); } kasan_enable_current(); } diff --git a/mm/slub.c b/mm/slub.c index d9e4e10683cc..7ecbbbe5bc0c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2791,7 +2791,8 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, void *obj) { if (unlikely(slab_want_init_on_free(s)) && obj) - memset((void *)((char *)obj + s->offset), 0, sizeof(void *)); + memset((void *)((char *)kasan_reset_tag(obj) + s->offset), + 0, sizeof(void *)); } /* @@ -2883,7 +2884,7 @@ redo: stat(s, ALLOC_FASTPATH); } - maybe_wipe_obj_freeptr(s, kasan_reset_tag(object)); + maybe_wipe_obj_freeptr(s, object); if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(kasan_reset_tag(object), 0, s->object_size); @@ -3329,7 +3330,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, int j; for (j = 0; j < i; j++) - memset(p[j], 0, s->object_size); + memset(kasan_reset_tag(p[j]), 0, s->object_size); } /* memcg and kmem_cache debug support */ @@ -5624,10 +5625,8 @@ static int sysfs_slab_add(struct kmem_cache *s) s->kobj.kset = kset; err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); - if (err) { - kobject_put(&s->kobj); + if (err) goto out; - } err = sysfs_create_group(&s->kobj, &slab_attr_group); if (err) diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 579b66da1d95..3e4f17d335fe 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -101,9 +101,11 @@ static inline struct pppoatm_vcc *chan_to_pvcc(const struct ppp_channel *chan) * doesn't want to be called in interrupt context, so we do it from * a tasklet */ -static void pppoatm_wakeup_sender(unsigned long arg) +static void pppoatm_wakeup_sender(struct tasklet_struct *t) { - ppp_output_wakeup((struct ppp_channel *) arg); + struct pppoatm_vcc *pvcc = from_tasklet(pvcc, t, wakeup_tasklet); + + ppp_output_wakeup(&pvcc->chan); } static void pppoatm_release_cb(struct atm_vcc *atmvcc) @@ -389,11 +391,7 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) struct atm_backend_ppp be; struct pppoatm_vcc *pvcc; int err; - /* - * Each PPPoATM instance has its own tasklet - this is just a - * prototypical one used to initialize them - */ - static const DECLARE_TASKLET_OLD(tasklet_proto, pppoatm_wakeup_sender); + if (copy_from_user(&be, arg, sizeof be)) return -EFAULT; if (be.encaps != PPPOATM_ENCAPS_AUTODETECT && @@ -415,8 +413,7 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) pvcc->chan.ops = &pppoatm_ops; pvcc->chan.mtu = atmvcc->qos.txtp.max_sdu - PPP_HDRLEN - (be.encaps == e_vc ? 0 : LLC_LEN); - pvcc->wakeup_tasklet = tasklet_proto; - pvcc->wakeup_tasklet.data = (unsigned long) &pvcc->chan; + tasklet_setup(&pvcc->wakeup_tasklet, pppoatm_wakeup_sender); err = ppp_register_channel(&pvcc->chan); if (err != 0) { kfree(pvcc); diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 1883118aae55..32a48e5418da 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -88,4 +88,33 @@ int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, int br_mrp_ring_port_open(struct net_device *dev, u8 loc); int br_mrp_in_port_open(struct net_device *dev, u8 loc); +/* MRP protocol data units */ +struct br_mrp_tlv_hdr { + __u8 type; + __u8 length; +}; + +struct br_mrp_common_hdr { + __be16 seq_id; + __u8 domain[MRP_DOMAIN_UUID_LENGTH]; +}; + +struct br_mrp_ring_test_hdr { + __be16 prio; + __u8 sa[ETH_ALEN]; + __be16 port_role; + __be16 state; + __be16 transitions; + __be32 timestamp; +} __attribute__((__packed__)); + +struct br_mrp_in_test_hdr { + __be16 id; + __u8 sa[ETH_ALEN]; + __be16 port_role; + __be16 state; + __be16 transitions; + __be32 timestamp; +} __attribute__((__packed__)); + #endif /* _BR_PRIVATE_MRP_H */ diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 7db06e3f642a..71f0f671c4ef 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -19,6 +19,10 @@ #include "br_private.h" +/* IMPORTANT: new bridge options must be added with netlink support only + * please do not add new sysfs entries + */ + #define to_bridge(cd) ((struct net_bridge *)netdev_priv(to_net_dev(cd))) /* diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index b66305fae26b..96ff63cde1be 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -16,7 +16,10 @@ #include <linux/sched/signal.h> #include "br_private.h" -#include "br_private_mcast_eht.h" + +/* IMPORTANT: new bridge port options must be added with netlink support only + * please do not add new sysfs entries + */ struct brport_attribute { struct attribute attr; @@ -246,29 +249,6 @@ static int store_multicast_router(struct net_bridge_port *p, static BRPORT_ATTR(multicast_router, 0644, show_multicast_router, store_multicast_router); -static ssize_t show_multicast_eht_hosts_limit(struct net_bridge_port *p, - char *buf) -{ - return sprintf(buf, "%u\n", p->multicast_eht_hosts_limit); -} - -static int store_multicast_eht_hosts_limit(struct net_bridge_port *p, - unsigned long v) -{ - return br_multicast_eht_set_hosts_limit(p, v); -} -static BRPORT_ATTR(multicast_eht_hosts_limit, 0644, - show_multicast_eht_hosts_limit, - store_multicast_eht_hosts_limit); - -static ssize_t show_multicast_eht_hosts_cnt(struct net_bridge_port *p, - char *buf) -{ - return sprintf(buf, "%u\n", p->multicast_eht_hosts_cnt); -} -static BRPORT_ATTR(multicast_eht_hosts_cnt, 0444, show_multicast_eht_hosts_cnt, - NULL); - BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE); BRPORT_ATTR_FLAG(multicast_to_unicast, BR_MULTICAST_TO_UNICAST); #endif @@ -298,8 +278,6 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_router, &brport_attr_multicast_fast_leave, &brport_attr_multicast_to_unicast, - &brport_attr_multicast_eht_hosts_limit, - &brport_attr_multicast_eht_hosts_cnt, #endif &brport_attr_proxyarp, &brport_attr_proxyarp_wifi, diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 9815cfe42af0..ca44c327bace 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -569,6 +569,34 @@ e_range: return -ERANGE; } +static int decode_con_secret(void **p, void *end, u8 *con_secret, + int *con_secret_len) +{ + int len; + + ceph_decode_32_safe(p, end, len, bad); + ceph_decode_need(p, end, len, bad); + + dout("%s len %d\n", __func__, len); + if (con_secret) { + if (len > CEPH_MAX_CON_SECRET_LEN) { + pr_err("connection secret too big %d\n", len); + goto bad_memzero; + } + memcpy(con_secret, *p, len); + *con_secret_len = len; + } + memzero_explicit(*p, len); + *p += len; + return 0; + +bad_memzero: + memzero_explicit(*p, len); +bad: + pr_err("failed to decode connection secret\n"); + return -EINVAL; +} + static int handle_auth_session_key(struct ceph_auth_client *ac, void **p, void *end, u8 *session_key, int *session_key_len, @@ -612,17 +640,9 @@ static int handle_auth_session_key(struct ceph_auth_client *ac, dout("%s decrypted %d bytes\n", __func__, ret); dend = dp + ret; - ceph_decode_32_safe(&dp, dend, len, e_inval); - if (len > CEPH_MAX_CON_SECRET_LEN) { - pr_err("connection secret too big %d\n", len); - return -EINVAL; - } - - dout("%s connection secret len %d\n", __func__, len); - if (con_secret) { - memcpy(con_secret, dp, len); - *con_secret_len = len; - } + ret = decode_con_secret(&dp, dend, con_secret, con_secret_len); + if (ret) + return ret; } /* service tickets */ @@ -828,7 +848,6 @@ static int decrypt_authorizer_reply(struct ceph_crypto_key *secret, { void *dp, *dend; u8 struct_v; - int len; int ret; dp = *p + ceph_x_encrypt_offset(); @@ -843,17 +862,9 @@ static int decrypt_authorizer_reply(struct ceph_crypto_key *secret, ceph_decode_64_safe(&dp, dend, *nonce_plus_one, e_inval); dout("%s nonce_plus_one %llu\n", __func__, *nonce_plus_one); if (struct_v >= 2) { - ceph_decode_32_safe(&dp, dend, len, e_inval); - if (len > CEPH_MAX_CON_SECRET_LEN) { - pr_err("connection secret too big %d\n", len); - return -EINVAL; - } - - dout("%s connection secret len %d\n", __func__, len); - if (con_secret) { - memcpy(con_secret, dp, len); - *con_secret_len = len; - } + ret = decode_con_secret(&dp, dend, con_secret, con_secret_len); + if (ret) + return ret; } return 0; diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 4f75df40fb12..92d89b331645 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -96,6 +96,7 @@ int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end) key->len = ceph_decode_16(p); ceph_decode_need(p, end, key->len, bad); ret = set_secret(key, *p); + memzero_explicit(*p, key->len); *p += key->len; return ret; @@ -134,7 +135,7 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey) void ceph_crypto_key_destroy(struct ceph_crypto_key *key) { if (key) { - kfree(key->key); + kfree_sensitive(key->key); key->key = NULL; if (key->tfm) { crypto_free_sync_skcipher(key->tfm); diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index 04f653b3c897..2cb5ffdf071a 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -1100,7 +1100,7 @@ static int read_partial_message(struct ceph_connection *con) if (ret < 0) return ret; - BUG_ON(!con->in_msg ^ skip); + BUG_ON((!con->in_msg) ^ skip); if (skip) { /* skip this message */ dout("alloc_msg said skip message\n"); diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index c38d8de93836..cc40ce4e02fb 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -689,11 +689,10 @@ static int verify_epilogue_crcs(struct ceph_connection *con, u32 front_crc, } static int setup_crypto(struct ceph_connection *con, - u8 *session_key, int session_key_len, - u8 *con_secret, int con_secret_len) + const u8 *session_key, int session_key_len, + const u8 *con_secret, int con_secret_len) { unsigned int noio_flag; - void *p; int ret; dout("%s con %p con_mode %d session_key_len %d con_secret_len %d\n", @@ -751,15 +750,14 @@ static int setup_crypto(struct ceph_connection *con, return ret; } - p = con_secret; - WARN_ON((unsigned long)p & crypto_aead_alignmask(con->v2.gcm_tfm)); - ret = crypto_aead_setkey(con->v2.gcm_tfm, p, CEPH_GCM_KEY_LEN); + WARN_ON((unsigned long)con_secret & + crypto_aead_alignmask(con->v2.gcm_tfm)); + ret = crypto_aead_setkey(con->v2.gcm_tfm, con_secret, CEPH_GCM_KEY_LEN); if (ret) { pr_err("failed to set gcm key: %d\n", ret); return ret; } - p += CEPH_GCM_KEY_LEN; WARN_ON(crypto_aead_ivsize(con->v2.gcm_tfm) != CEPH_GCM_IV_LEN); ret = crypto_aead_setauthsize(con->v2.gcm_tfm, CEPH_GCM_TAG_LEN); if (ret) { @@ -777,8 +775,11 @@ static int setup_crypto(struct ceph_connection *con, aead_request_set_callback(con->v2.gcm_req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &con->v2.gcm_wait); - memcpy(&con->v2.in_gcm_nonce, p, CEPH_GCM_IV_LEN); - memcpy(&con->v2.out_gcm_nonce, p + CEPH_GCM_IV_LEN, CEPH_GCM_IV_LEN); + memcpy(&con->v2.in_gcm_nonce, con_secret + CEPH_GCM_KEY_LEN, + CEPH_GCM_IV_LEN); + memcpy(&con->v2.out_gcm_nonce, + con_secret + CEPH_GCM_KEY_LEN + CEPH_GCM_IV_LEN, + CEPH_GCM_IV_LEN); return 0; /* auth_x, secure mode */ } @@ -800,7 +801,7 @@ static int hmac_sha256(struct ceph_connection *con, const struct kvec *kvecs, desc->tfm = con->v2.hmac_tfm; ret = crypto_shash_init(desc); if (ret) - return ret; + goto out; for (i = 0; i < kvec_cnt; i++) { WARN_ON((unsigned long)kvecs[i].iov_base & @@ -808,15 +809,14 @@ static int hmac_sha256(struct ceph_connection *con, const struct kvec *kvecs, ret = crypto_shash_update(desc, kvecs[i].iov_base, kvecs[i].iov_len); if (ret) - return ret; + goto out; } ret = crypto_shash_final(desc, hmac); - if (ret) - return ret; +out: shash_desc_zero(desc); - return 0; /* auth_x, both plain and secure modes */ + return ret; /* auth_x, both plain and secure modes */ } static void gcm_inc_nonce(struct ceph_gcm_nonce *nonce) @@ -2072,27 +2072,32 @@ static int process_auth_done(struct ceph_connection *con, void *p, void *end) if (con->state != CEPH_CON_S_V2_AUTH) { dout("%s con %p state changed to %d\n", __func__, con, con->state); - return -EAGAIN; + ret = -EAGAIN; + goto out; } dout("%s con %p handle_auth_done ret %d\n", __func__, con, ret); if (ret) - return ret; + goto out; ret = setup_crypto(con, session_key, session_key_len, con_secret, con_secret_len); if (ret) - return ret; + goto out; reset_out_kvecs(con); ret = prepare_auth_signature(con); if (ret) { pr_err("prepare_auth_signature failed: %d\n", ret); - return ret; + goto out; } con->state = CEPH_CON_S_V2_AUTH_SIGNATURE; - return 0; + +out: + memzero_explicit(session_key_buf, sizeof(session_key_buf)); + memzero_explicit(con_secret_buf, sizeof(con_secret_buf)); + return ret; bad: pr_err("failed to decode auth_done\n"); @@ -3436,6 +3441,8 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con) } con->v2.con_mode = CEPH_CON_MODE_UNKNOWN; + memzero_explicit(&con->v2.in_gcm_nonce, CEPH_GCM_IV_LEN); + memzero_explicit(&con->v2.out_gcm_nonce, CEPH_GCM_IV_LEN); if (con->v2.hmac_tfm) { crypto_free_shash(con->v2.hmac_tfm); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index b9d54ed9f338..195ceb8afb06 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1433,7 +1433,7 @@ static int mon_handle_auth_bad_method(struct ceph_connection *con, /* * handle incoming message */ -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +static void mon_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_mon_client *monc = con->private; int type = le16_to_cpu(msg->hdr.type); @@ -1565,21 +1565,21 @@ static void mon_fault(struct ceph_connection *con) * will come from the messenger workqueue, which is drained prior to * mon_client destruction. */ -static struct ceph_connection *con_get(struct ceph_connection *con) +static struct ceph_connection *mon_get_con(struct ceph_connection *con) { return con; } -static void con_put(struct ceph_connection *con) +static void mon_put_con(struct ceph_connection *con) { } static const struct ceph_connection_operations mon_con_ops = { - .get = con_get, - .put = con_put, - .dispatch = dispatch, - .fault = mon_fault, + .get = mon_get_con, + .put = mon_put_con, .alloc_msg = mon_alloc_msg, + .dispatch = mon_dispatch, + .fault = mon_fault, .get_auth_request = mon_get_auth_request, .handle_auth_reply_more = mon_handle_auth_reply_more, .handle_auth_done = mon_handle_auth_done, diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 61229c5e22cb..ff8624a7c964 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5412,7 +5412,7 @@ void ceph_osdc_cleanup(void) /* * handle incoming message */ -static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) +static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; @@ -5534,9 +5534,9 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) return m; } -static struct ceph_msg *alloc_msg(struct ceph_connection *con, - struct ceph_msg_header *hdr, - int *skip) +static struct ceph_msg *osd_alloc_msg(struct ceph_connection *con, + struct ceph_msg_header *hdr, + int *skip) { struct ceph_osd *osd = con->private; int type = le16_to_cpu(hdr->type); @@ -5560,7 +5560,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con, /* * Wrappers to refcount containing ceph_osd struct */ -static struct ceph_connection *get_osd_con(struct ceph_connection *con) +static struct ceph_connection *osd_get_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; if (get_osd(osd)) @@ -5568,7 +5568,7 @@ static struct ceph_connection *get_osd_con(struct ceph_connection *con) return NULL; } -static void put_osd_con(struct ceph_connection *con) +static void osd_put_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; put_osd(osd); @@ -5582,8 +5582,8 @@ static void put_osd_con(struct ceph_connection *con) * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ -static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, - int *proto, int force_new) +static struct ceph_auth_handshake * +osd_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; @@ -5599,7 +5599,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, return auth; } -static int add_authorizer_challenge(struct ceph_connection *con, +static int osd_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_osd *o = con->private; @@ -5610,7 +5610,7 @@ static int add_authorizer_challenge(struct ceph_connection *con, challenge_buf, challenge_buf_len); } -static int verify_authorizer_reply(struct ceph_connection *con) +static int osd_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; @@ -5622,7 +5622,7 @@ static int verify_authorizer_reply(struct ceph_connection *con) NULL, NULL, NULL, NULL); } -static int invalidate_authorizer(struct ceph_connection *con) +static int osd_invalidate_authorizer(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; @@ -5731,18 +5731,18 @@ static int osd_check_message_signature(struct ceph_msg *msg) } static const struct ceph_connection_operations osd_con_ops = { - .get = get_osd_con, - .put = put_osd_con, - .dispatch = dispatch, - .get_authorizer = get_authorizer, - .add_authorizer_challenge = add_authorizer_challenge, - .verify_authorizer_reply = verify_authorizer_reply, - .invalidate_authorizer = invalidate_authorizer, - .alloc_msg = alloc_msg, + .get = osd_get_con, + .put = osd_put_con, + .alloc_msg = osd_alloc_msg, + .dispatch = osd_dispatch, + .fault = osd_fault, .reencode_message = osd_reencode_message, + .get_authorizer = osd_get_authorizer, + .add_authorizer_challenge = osd_add_authorizer_challenge, + .verify_authorizer_reply = osd_verify_authorizer_reply, + .invalidate_authorizer = osd_invalidate_authorizer, .sign_message = osd_sign_message, .check_message_signature = osd_check_message_signature, - .fault = osd_fault, .get_auth_request = osd_get_auth_request, .handle_auth_reply_more = osd_handle_auth_reply_more, .handle_auth_done = osd_handle_auth_done, diff --git a/net/core/dev.c b/net/core/dev.c index 6df3f1bcdc68..aae116d059da 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3621,7 +3621,18 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); - return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb); + if (features & NETIF_F_HW_CSUM) + return 0; + + if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + case offsetof(struct udphdr, check): + return 0; + } + } + + return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); diff --git a/net/core/devlink.c b/net/core/devlink.c index f6e6445b9801..737b61c2976e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -87,6 +87,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, + [DEVLINK_PORT_FN_ATTR_STATE] = + NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE), }; static LIST_HEAD(devlink_list); @@ -690,6 +693,15 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_sf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, + attrs->pci_sf.pf) || + nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + attrs->pci_sf.sf)) + return -EMSGSIZE; + break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -713,42 +725,105 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, } static int +devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, bool *msg_updated) +{ + u8 hw_addr[MAX_ADDR_LEN]; + int hw_addr_len; + int err; + + if (!ops->port_function_hw_addr_get) + return 0; + + err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); + if (err) + return err; + *msg_updated = true; + return 0; +} + +static bool +devlink_port_fn_state_valid(enum devlink_port_fn_state state) +{ + return state == DEVLINK_PORT_FN_STATE_INACTIVE || + state == DEVLINK_PORT_FN_STATE_ACTIVE; +} + +static bool +devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) +{ + return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || + opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; +} + +static int +devlink_port_fn_state_fill(struct devlink *devlink, + const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + enum devlink_port_fn_opstate opstate; + enum devlink_port_fn_state state; + int err; + + if (!ops->port_fn_state_get) + return 0; + + err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + if (!devlink_port_fn_state_valid(state)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); + return -EINVAL; + } + if (!devlink_port_fn_opstate_valid(opstate)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, + "Invalid operational state read from driver"); + return -EINVAL; + } + if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || + nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) + return -EMSGSIZE; + *msg_updated = true; + return 0; +} + +static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { struct devlink *devlink = port->devlink; const struct devlink_ops *ops; struct nlattr *function_attr; - bool empty_nest = true; - int err = 0; + bool msg_updated = false; + int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; ops = devlink->ops; - if (ops->port_function_hw_addr_get) { - int hw_addr_len; - u8 hw_addr[MAX_ADDR_LEN]; - - err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); - if (err == -EOPNOTSUPP) { - /* Port function attributes are optional for a port. If port doesn't - * support function attribute, returning -EOPNOTSUPP is not an error. - */ - err = 0; - goto out; - } else if (err) { - goto out; - } - err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); - if (err) - goto out; - empty_nest = false; - } - + err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, + extack, &msg_updated); + if (err) + goto out; + err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack, + &msg_updated); out: - if (err || empty_nest) + if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); @@ -986,7 +1061,6 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * const struct devlink_ops *ops; const u8 *hw_addr; int hw_addr_len; - int err; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); @@ -1011,12 +1085,25 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * return -EOPNOTSUPP; } - err = ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); - if (err) - return err; + return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); +} - devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); - return 0; +static int devlink_port_fn_state_set(struct devlink *devlink, + struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + enum devlink_port_fn_state state; + const struct devlink_ops *ops; + + state = nla_get_u8(attr); + ops = devlink->ops; + if (!ops->port_fn_state_set) { + NL_SET_ERR_MSG_MOD(extack, + "Function does not support state setting"); + return -EOPNOTSUPP; + } + return ops->port_fn_state_set(devlink, port, state, extack); } static int @@ -1034,9 +1121,21 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, } attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; - if (attr) + if (attr) { err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when + * multiple port function attributes are set along with state, + * Those can be applied first before activating the state. + */ + attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; + if (attr) + err = devlink_port_fn_state_set(devlink, port, attr, extack); + if (!err) + devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } @@ -1136,6 +1235,111 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return devlink_port_unsplit(devlink, port_index, info->extack); } +static int devlink_port_new_notifiy(struct devlink *devlink, + unsigned int port_index, + struct genl_info *info) +{ + struct devlink_port *devlink_port; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&devlink->lock); + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) { + err = -ENODEV; + goto out; + } + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, info->snd_portid, + info->snd_seq, 0, NULL); + if (err) + goto out; + + err = genlmsg_reply(msg, info); + mutex_unlock(&devlink->lock); + return err; + +out: + mutex_unlock(&devlink->lock); + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink_port_new_attrs new_attrs = {}; + struct devlink *devlink = info->user_ptr[0]; + unsigned int new_port_index; + int err; + + if (!devlink->ops->port_new || !devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || + !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { + NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified"); + return -EINVAL; + } + new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); + new_attrs.pfnum = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + /* Port index of the new port being created by driver. */ + new_attrs.port_index = + nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + new_attrs.port_index_valid = true; + } + if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { + new_attrs.controller = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); + new_attrs.controller_valid = true; + } + if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && + info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { + new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); + new_attrs.sfnum_valid = true; + } + + err = devlink->ops->port_new(devlink, &new_attrs, extack, + &new_port_index); + if (err) + return err; + + err = devlink_port_new_notifiy(devlink, new_port_index, info); + if (err && err != -ENODEV) { + /* Fail to send the response; destroy newly created port. */ + devlink->ops->port_del(devlink, new_port_index, extack); + } + return err; +} + +static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + unsigned int port_index; + + if (!devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + NL_SET_ERR_MSG_MOD(extack, "Port index is not specified"); + return -EINVAL; + } + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + return devlink->ops->port_del(devlink, port_index, extack); +} + static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, @@ -7594,6 +7798,10 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_ACTION_MAX), [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), + [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -7634,6 +7842,18 @@ static const struct genl_small_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, }, { + .cmd = DEVLINK_CMD_PORT_NEW, + .doit = devlink_nl_cmd_port_new_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .doit = devlink_nl_cmd_port_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_get_doit, @@ -8372,6 +8592,32 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); +/** + * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @sf: associated SF of a PF for the devlink port instance + */ +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u32 sf) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + if (WARN_ON(devlink_port->registered)) + return; + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_SF); + if (ret) + return; + attrs->pci_sf.controller = controller; + attrs->pci_sf.pf = pf; + attrs->pci_sf.sf = sf; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8420,6 +8666,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, + attrs->pci_sf.sf); + break; } if (n >= len) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ff073581b5b1..e2982b3970b8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1244,13 +1244,14 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, old = neigh->nud_state; err = -EPERM; - if (!(flags & NEIGH_UPDATE_F_ADMIN) && - (old & (NUD_NOARP | NUD_PERMANENT))) - goto out; if (neigh->dead) { NL_SET_ERR_MSG(extack, "Neighbor entry is now dead"); + new = old; goto out; } + if (!(flags & NEIGH_UPDATE_F_ADMIN) && + (old & (NUD_NOARP | NUD_PERMANENT))) + goto out; ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2af12f7e170c..3787093239f5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3289,7 +3289,19 @@ EXPORT_SYMBOL(skb_split); */ static int skb_prepare_for_shift(struct sk_buff *skb) { - return skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + int ret = 0; + + if (skb_cloned(skb)) { + /* Save and restore truesize: pskb_expand_head() may reallocate + * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we + * cannot change truesize at this point. + */ + unsigned int save_truesize = skb->truesize; + + ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + skb->truesize = save_truesize; + } + return ret; } /** diff --git a/net/core/sock.c b/net/core/sock.c index bbcd4b97eddd..648a5cb46209 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1657,6 +1657,16 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif + + /* If we move sk_tx_queue_mapping out of the private section, + * we must check if sk_tx_queue_clear() is called after + * sock_copy() in sk_clone_lock(). + */ + BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < + offsetof(struct sock, sk_dontcopy_begin) || + offsetof(struct sock, sk_tx_queue_mapping) >= + offsetof(struct sock, sk_dontcopy_end)); + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, @@ -1690,7 +1700,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; - sk_tx_queue_clear(sk); } return sk; @@ -1876,123 +1885,120 @@ static void sk_init_common(struct sock *sk) struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); - struct sock *newsk; + struct sk_filter *filter; bool is_charged = true; + struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); - if (newsk != NULL) { - struct sk_filter *filter; + if (!newsk) + goto out; - sock_copy(newsk, sk); + sock_copy(newsk, sk); - newsk->sk_prot_creator = prot; + newsk->sk_prot_creator = prot; - /* SANITY */ - if (likely(newsk->sk_net_refcnt)) - get_net(sock_net(newsk)); - sk_node_init(&newsk->sk_node); - sock_lock_init(newsk); - bh_lock_sock(newsk); - newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; - newsk->sk_backlog.len = 0; + /* SANITY */ + if (likely(newsk->sk_net_refcnt)) + get_net(sock_net(newsk)); + sk_node_init(&newsk->sk_node); + sock_lock_init(newsk); + bh_lock_sock(newsk); + newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; + newsk->sk_backlog.len = 0; - atomic_set(&newsk->sk_rmem_alloc, 0); - /* - * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) - */ - refcount_set(&newsk->sk_wmem_alloc, 1); - atomic_set(&newsk->sk_omem_alloc, 0); - sk_init_common(newsk); + atomic_set(&newsk->sk_rmem_alloc, 0); - newsk->sk_dst_cache = NULL; - newsk->sk_dst_pending_confirm = 0; - newsk->sk_wmem_queued = 0; - newsk->sk_forward_alloc = 0; - atomic_set(&newsk->sk_drops, 0); - newsk->sk_send_head = NULL; - newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; - atomic_set(&newsk->sk_zckey, 0); + /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ + refcount_set(&newsk->sk_wmem_alloc, 1); - sock_reset_flag(newsk, SOCK_DONE); + atomic_set(&newsk->sk_omem_alloc, 0); + sk_init_common(newsk); - /* sk->sk_memcg will be populated at accept() time */ - newsk->sk_memcg = NULL; + newsk->sk_dst_cache = NULL; + newsk->sk_dst_pending_confirm = 0; + newsk->sk_wmem_queued = 0; + newsk->sk_forward_alloc = 0; + atomic_set(&newsk->sk_drops, 0); + newsk->sk_send_head = NULL; + newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; + atomic_set(&newsk->sk_zckey, 0); - cgroup_sk_clone(&newsk->sk_cgrp_data); + sock_reset_flag(newsk, SOCK_DONE); - rcu_read_lock(); - filter = rcu_dereference(sk->sk_filter); - if (filter != NULL) - /* though it's an empty new sock, the charging may fail - * if sysctl_optmem_max was changed between creation of - * original socket and cloning - */ - is_charged = sk_filter_charge(newsk, filter); - RCU_INIT_POINTER(newsk->sk_filter, filter); - rcu_read_unlock(); + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; - if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { - /* We need to make sure that we don't uncharge the new - * socket if we couldn't charge it in the first place - * as otherwise we uncharge the parent's filter. - */ - if (!is_charged) - RCU_INIT_POINTER(newsk->sk_filter, NULL); - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } - RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); + cgroup_sk_clone(&newsk->sk_cgrp_data); - if (bpf_sk_storage_clone(sk, newsk)) { - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (filter != NULL) + /* though it's an empty new sock, the charging may fail + * if sysctl_optmem_max was changed between creation of + * original socket and cloning + */ + is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); - /* Clear sk_user_data if parent had the pointer tagged - * as not suitable for copying when cloning. + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { + /* We need to make sure that we don't uncharge the new + * socket if we couldn't charge it in the first place + * as otherwise we uncharge the parent's filter. */ - if (sk_user_data_is_nocopy(newsk)) - newsk->sk_user_data = NULL; + if (!is_charged) + RCU_INIT_POINTER(newsk->sk_filter, NULL); + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } + RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); - newsk->sk_err = 0; - newsk->sk_err_soft = 0; - newsk->sk_priority = 0; - newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); + if (bpf_sk_storage_clone(sk, newsk)) { + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } - /* - * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.rst for details) - */ - smp_wmb(); - refcount_set(&newsk->sk_refcnt, 2); + /* Clear sk_user_data if parent had the pointer tagged + * as not suitable for copying when cloning. + */ + if (sk_user_data_is_nocopy(newsk)) + newsk->sk_user_data = NULL; - /* - * Increment the counter in the same struct proto as the master - * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that - * is the same as sk->sk_prot->socks, as this field was copied - * with memcpy). - * - * This _changes_ the previous behaviour, where - * tcp_create_openreq_child always was incrementing the - * equivalent to tcp_prot->socks (inet_sock_nr), so this have - * to be taken into account in all callers. -acme - */ - sk_refcnt_debug_inc(newsk); - sk_set_socket(newsk, NULL); - sk_tx_queue_clear(newsk); - RCU_INIT_POINTER(newsk->sk_wq, NULL); + newsk->sk_err = 0; + newsk->sk_err_soft = 0; + newsk->sk_priority = 0; + newsk->sk_incoming_cpu = raw_smp_processor_id(); + if (likely(newsk->sk_net_refcnt)) + sock_inuse_add(sock_net(newsk), 1); - if (newsk->sk_prot->sockets_allocated) - sk_sockets_allocated_inc(newsk); + /* Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.rst for details) + */ + smp_wmb(); + refcount_set(&newsk->sk_refcnt, 2); - if (sock_needs_netstamp(sk) && - newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); - } + /* Increment the counter in the same struct proto as the master + * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that + * is the same as sk->sk_prot->socks, as this field was copied + * with memcpy). + * + * This _changes_ the previous behaviour, where + * tcp_create_openreq_child always was incrementing the + * equivalent to tcp_prot->socks (inet_sock_nr), so this have + * to be taken into account in all callers. -acme + */ + sk_refcnt_debug_inc(newsk); + sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); + RCU_INIT_POINTER(newsk->sk_wq, NULL); + + if (newsk->sk_prot->sockets_allocated) + sk_sockets_allocated_inc(newsk); + + if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); out: return newsk; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 4cac31d22a50..2193ae529e75 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1035,7 +1035,7 @@ source_ok: fld.saddr = dnet_select_source(dev_out, 0, RT_SCOPE_HOST); if (!fld.daddr) - goto out; + goto done; } fld.flowidn_oif = LOOPBACK_IFINDEX; res.type = RTN_LOCAL; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 2d226a5c085f..a45572cfb71a 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -105,11 +105,26 @@ config NET_DSA_TAG_RTL4_A the Realtek RTL8366RB. config NET_DSA_TAG_OCELOT - tristate "Tag driver for Ocelot family of switches" + tristate "Tag driver for Ocelot family of switches, using NPI port" select PACKING help - Say Y or M if you want to enable support for tagging frames for the - Ocelot switches (VSC7511, VSC7512, VSC7513, VSC7514, VSC9959). + Say Y or M if you want to enable NPI tagging for the Ocelot switches + (VSC7511, VSC7512, VSC7513, VSC7514, VSC9953, VSC9959). In this mode, + the frames over the Ethernet CPU port are prepended with a + hardware-defined injection/extraction frame header. Flow control + (PAUSE frames) over the CPU port is not supported when operating in + this mode. + +config NET_DSA_TAG_OCELOT_8021Q + tristate "Tag driver for Ocelot family of switches, using VLAN" + select NET_DSA_TAG_8021Q + help + Say Y or M if you want to enable support for tagging frames with a + custom VLAN-based header. Frames that require timestamping, such as + PTP, are not delivered over Ethernet but over register-based MMIO. + Flow control over the CPU port is functional in this mode. When using + this mode, less TCAM resources (VCAP IS1, IS2, ES0) are available for + use with tc-flower. config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 92cea2132241..44bc79952b8b 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -15,6 +15,7 @@ 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-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o +obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index f4ce3c5826a0..84cad1be9ce4 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -84,6 +84,32 @@ const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) return ops->name; }; +/* Function takes a reference on the module owning the tagger, + * so dsa_tag_driver_put must be called afterwards. + */ +const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf) +{ + const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); + struct dsa_tag_driver *dsa_tag_driver; + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + const struct dsa_device_ops *tmp = dsa_tag_driver->ops; + + if (!sysfs_streq(buf, tmp->name)) + continue; + + if (!try_module_get(dsa_tag_driver->owner)) + break; + + ops = tmp; + break; + } + mutex_unlock(&dsa_tag_drivers_lock); + + return ops; +} + const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol) { struct dsa_tag_driver *dsa_tag_driver; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index cc13549120e5..96249c4ad5f2 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -22,6 +22,49 @@ static DEFINE_MUTEX(dsa2_mutex); LIST_HEAD(dsa_tree_list); /** + * dsa_tree_notify - Execute code for all switches in a DSA switch tree. + * @dst: collection of struct dsa_switch devices to notify. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Given a struct dsa_switch_tree, this can be used to run a function once for + * each member DSA switch. The other alternative of traversing the tree is only + * through its ports list, which does not uniquely list the switches. + */ +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v) +{ + struct raw_notifier_head *nh = &dst->nh; + int err; + + err = raw_notifier_call_chain(nh, e, v); + + return notifier_to_errno(err); +} + +/** + * dsa_broadcast - Notify all DSA trees in the system. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Can be used to notify the switching fabric of events such as cross-chip + * bridging between disjoint trees (such as islands of tagger-compatible + * switches bridged by an incompatible middle switch). + */ +int dsa_broadcast(unsigned long e, void *v) +{ + struct dsa_switch_tree *dst; + int err = 0; + + list_for_each_entry(dst, &dsa_tree_list, list) { + err = dsa_tree_notify(dst, e, v); + if (err) + break; + } + + return err; +} + +/** * dsa_lag_map() - Map LAG netdev to a linear LAG ID * @dst: Tree in which to record the mapping. * @lag: Netdev that is to be mapped to an ID. @@ -136,6 +179,8 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index) static void dsa_tree_free(struct dsa_switch_tree *dst) { + if (dst->tag_ops) + dsa_tag_driver_put(dst->tag_ops); list_del(&dst->list); kfree(dst); } @@ -424,7 +469,6 @@ static void dsa_port_teardown(struct dsa_port *dp) break; case DSA_PORT_TYPE_CPU: dsa_port_disable(dp); - dsa_tag_driver_put(dp->tag_ops); dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_DSA: @@ -898,6 +942,57 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dst->setup = false; } +/* Since the dsa/tagging sysfs device attribute is per master, the assumption + * is that all DSA switches within a tree share the same tagger, otherwise + * they would have formed disjoint trees (different "dsa,member" values). + */ +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + struct net_device *master, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops) +{ + struct dsa_notifier_tag_proto_info info; + struct dsa_port *dp; + int err = -EBUSY; + + if (!rtnl_trylock()) + return restart_syscall(); + + /* At the moment we don't allow changing the tag protocol under + * traffic. The rtnl_mutex also happens to serialize concurrent + * attempts to change the tagging protocol. If we ever lift the IFF_UP + * restriction, there needs to be another mutex which serializes this. + */ + if (master->flags & IFF_UP) + goto out_unlock; + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_is_user_port(dp->ds, dp->index)) + continue; + + if (dp->slave->flags & IFF_UP) + goto out_unlock; + } + + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); + if (err) + goto out_unwind_tagger; + + dst->tag_ops = tag_ops; + + rtnl_unlock(); + + return 0; + +out_unwind_tagger: + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); +out_unlock: + rtnl_unlock(); + return err; +} + static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) { struct dsa_switch_tree *dst = ds->dst; @@ -968,24 +1063,33 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; - const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; tag_protocol = dsa_get_tag_protocol(dp, master); - tag_ops = dsa_tag_driver_get(tag_protocol); - if (IS_ERR(tag_ops)) { - if (PTR_ERR(tag_ops) == -ENOPROTOOPT) - return -EPROBE_DEFER; - dev_warn(ds->dev, "No tagger for this switch\n"); - dp->master = NULL; - return PTR_ERR(tag_ops); + if (dst->tag_ops) { + if (dst->tag_ops->proto != tag_protocol) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + return -EINVAL; + } + /* In the case of multiple CPU ports per switch, the tagging + * protocol is still reference-counted only per switch tree, so + * nothing to do here. + */ + } else { + dst->tag_ops = dsa_tag_driver_get(tag_protocol); + if (IS_ERR(dst->tag_ops)) { + if (PTR_ERR(dst->tag_ops) == -ENOPROTOOPT) + return -EPROBE_DEFER; + dev_warn(ds->dev, "No tagger for this switch\n"); + dp->master = NULL; + return PTR_ERR(dst->tag_ops); + } } dp->master = master; dp->type = DSA_PORT_TYPE_CPU; - dp->filter = tag_ops->filter; - dp->rcv = tag_ops->rcv; - dp->tag_ops = tag_ops; + dsa_port_set_tag_protocol(dp, dst->tag_ops); dp->dst = dst; return 0; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2ce46bb87703..edca57b558ad 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -28,6 +28,7 @@ enum { DSA_NOTIFIER_VLAN_ADD, DSA_NOTIFIER_VLAN_DEL, DSA_NOTIFIER_MTU, + DSA_NOTIFIER_TAG_PROTO, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -82,6 +83,11 @@ struct dsa_notifier_mtu_info { int mtu; }; +/* DSA_NOTIFIER_TAG_PROTO_* */ +struct dsa_notifier_tag_proto_info { + const struct dsa_device_ops *tag_ops; +}; + struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; @@ -115,6 +121,7 @@ struct dsa_slave_priv { /* dsa.c */ const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol); void dsa_tag_driver_put(const struct dsa_device_ops *ops); +const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); @@ -139,6 +146,8 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, } /* port.c */ +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops); int dsa_port_set_state(struct dsa_port *dp, u8 state); int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); @@ -201,6 +210,8 @@ int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +void dsa_slave_setup_tagger(struct net_device *slave); +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) { @@ -283,6 +294,12 @@ void dsa_switch_unregister_notifier(struct dsa_switch *ds); /* dsa2.c */ void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag); void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag); +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); +int dsa_broadcast(unsigned long e, void *v); +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + struct net_device *master, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops); extern struct list_head dsa_tree_list; diff --git a/net/dsa/master.c b/net/dsa/master.c index cb3a5cf99b25..052a977914a6 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -280,7 +280,44 @@ static ssize_t tagging_show(struct device *d, struct device_attribute *attr, return sprintf(buf, "%s\n", dsa_tag_protocol_to_str(cpu_dp->tag_ops)); } -static DEVICE_ATTR_RO(tagging); + +static ssize_t tagging_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t count) +{ + const struct dsa_device_ops *new_tag_ops, *old_tag_ops; + struct net_device *dev = to_net_dev(d); + struct dsa_port *cpu_dp = dev->dsa_ptr; + int err; + + old_tag_ops = cpu_dp->tag_ops; + new_tag_ops = dsa_find_tagger_by_name(buf); + /* Bad tagger name, or module is not loaded? */ + if (IS_ERR(new_tag_ops)) + return PTR_ERR(new_tag_ops); + + if (new_tag_ops == old_tag_ops) + /* Drop the temporarily held duplicate reference, since + * the DSA switch tree uses this tagger. + */ + goto out; + + err = dsa_tree_change_tag_proto(cpu_dp->ds->dst, dev, new_tag_ops, + old_tag_ops); + if (err) { + /* On failure the old tagger is restored, so we don't need the + * driver for the new one. + */ + dsa_tag_driver_put(new_tag_ops); + return err; + } + + /* On success we no longer need the module for the old tagging protocol + */ +out: + dsa_tag_driver_put(old_tag_ops); + return count; +} +static DEVICE_ATTR_RW(tagging); static struct attribute *dsa_slave_attrs[] = { &dev_attr_tagging.attr, diff --git a/net/dsa/port.c b/net/dsa/port.c index f5b0f72ee7cd..5e079a61528e 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -13,31 +13,21 @@ #include "dsa_priv.h" -static int dsa_broadcast(unsigned long e, void *v) -{ - struct dsa_switch_tree *dst; - int err = 0; - - list_for_each_entry(dst, &dsa_tree_list, list) { - struct raw_notifier_head *nh = &dst->nh; - - err = raw_notifier_call_chain(nh, e, v); - err = notifier_to_errno(err); - if (err) - break; - } - - return err; -} - +/** + * dsa_port_notify - Notify the switching fabric of changes to a port + * @dp: port on which change occurred + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Notify all switches in the DSA tree that this port's switch belongs to, + * including this switch itself, of an event. Allows the other switches to + * reconfigure themselves for cross-chip operations. Can also be used to + * reconfigure ports without net_devices (CPU ports, DSA links) whenever + * a user port's state changes. + */ static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v) { - struct raw_notifier_head *nh = &dp->ds->dst->nh; - int err; - - err = raw_notifier_call_chain(nh, e, v); - - return notifier_to_errno(err); + return dsa_tree_notify(dp->ds->dst, e, v); } int dsa_port_set_state(struct dsa_port *dp, u8 state) @@ -536,6 +526,14 @@ int dsa_port_vlan_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); } +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops) +{ + cpu_dp->filter = tag_ops->filter; + cpu_dp->rcv = tag_ops->rcv; + cpu_dp->tag_ops = tag_ops; +} + static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { struct device_node *phy_dn; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index f2fb433f3828..b0571ab4e5a7 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1430,7 +1430,7 @@ out: dsa_hw_port_list_free(&hw_port_list); } -static int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1708,6 +1708,27 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } +void dsa_slave_setup_tagger(struct net_device *slave) +{ + struct dsa_port *dp = dsa_slave_to_port(slave); + struct dsa_slave_priv *p = netdev_priv(slave); + const struct dsa_port *cpu_dp = dp->cpu_dp; + struct net_device *master = cpu_dp->master; + + if (cpu_dp->tag_ops->tail_tag) + slave->needed_tailroom = cpu_dp->tag_ops->overhead; + else + slave->needed_headroom = cpu_dp->tag_ops->overhead; + /* Try to save one extra realloc later in the TX path (in the master) + * by also inheriting the master's needed headroom and tailroom. + * The 8021q driver also does this. + */ + slave->needed_headroom += master->needed_headroom; + slave->needed_tailroom += master->needed_tailroom; + + p->xmit = cpu_dp->tag_ops->xmit; +} + static struct lock_class_key dsa_slave_netdev_xmit_lock_key; static void dsa_slave_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, @@ -1782,16 +1803,6 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->netdev_ops = &dsa_slave_netdev_ops; if (ds->ops->port_max_mtu) slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); - if (cpu_dp->tag_ops->tail_tag) - slave_dev->needed_tailroom = cpu_dp->tag_ops->overhead; - else - slave_dev->needed_headroom = cpu_dp->tag_ops->overhead; - /* Try to save one extra realloc later in the TX path (in the master) - * by also inheriting the master's needed headroom and tailroom. - * The 8021q driver also does this. - */ - slave_dev->needed_headroom += master->needed_headroom; - slave_dev->needed_tailroom += master->needed_tailroom; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, @@ -1814,8 +1825,8 @@ int dsa_slave_create(struct dsa_port *port) p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - p->xmit = cpu_dp->tag_ops->xmit; port->slave = slave_dev; + dsa_slave_setup_tagger(slave_dev); rtnl_lock(); ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index cc0b25f3adea..5026e4143663 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -297,6 +297,58 @@ static int dsa_switch_vlan_del(struct dsa_switch *ds, return 0; } +static bool dsa_switch_tag_proto_match(struct dsa_switch *ds, int port, + struct dsa_notifier_tag_proto_info *info) +{ + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + return true; + + return false; +} + +static int dsa_switch_change_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + int port, err; + + if (!ds->ops->change_tag_protocol) + return -EOPNOTSUPP; + + ASSERT_RTNL(); + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_proto_match(ds, port, info)) { + err = ds->ops->change_tag_protocol(ds, port, + tag_ops->proto); + if (err) + return err; + + if (dsa_is_cpu_port(ds, port)) + dsa_port_set_tag_protocol(dsa_to_port(ds, port), + tag_ops); + } + } + + /* Now that changing the tag protocol can no longer fail, let's update + * the remaining bits which are "duplicated for faster access", and the + * bits that depend on the tagger, such as the MTU. + */ + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_user_port(ds, port)) { + struct net_device *slave; + + slave = dsa_to_port(ds, port)->slave; + dsa_slave_setup_tagger(slave); + + /* rtnl_mutex is held in dsa_tree_change_tag_proto */ + dsa_slave_change_mtu(slave, slave->mtu); + } + } + + return 0; +} + static int dsa_switch_event(struct notifier_block *nb, unsigned long event, void *info) { @@ -343,6 +395,9 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MTU: err = dsa_switch_mtu(ds, info); break; + case DSA_NOTIFIER_TAG_PROTO: + err = dsa_switch_change_tag_proto(ds, info); + break; default: err = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 8e3e8a5b8559..008c1ec6e20c 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -133,10 +133,21 @@ u16 dsa_8021q_rx_subvlan(u16 vid) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_subvlan); +bool vid_is_dsa_8021q_rxvlan(u16 vid) +{ + return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX; +} +EXPORT_SYMBOL_GPL(vid_is_dsa_8021q_rxvlan); + +bool vid_is_dsa_8021q_txvlan(u16 vid) +{ + return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_TX; +} +EXPORT_SYMBOL_GPL(vid_is_dsa_8021q_txvlan); + bool vid_is_dsa_8021q(u16 vid) { - return ((vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX || - (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_TX); + return vid_is_dsa_8021q_rxvlan(vid) || vid_is_dsa_8021q_txvlan(vid); } EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c new file mode 100644 index 000000000000..8991ebf098a3 --- /dev/null +++ b/net/dsa/tag_ocelot_8021q.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2020-2021 NXP Semiconductors + * + * An implementation of the software-defined tag_8021q.c tagger format, which + * also preserves full functionality under a vlan_filtering bridge. It does + * this by using the TCAM engines for: + * - pushing the RX VLAN as a second, outer tag, on egress towards the CPU port + * - redirecting towards the correct front port based on TX VLAN and popping + * that on egress + */ +#include <linux/dsa/8021q.h> +#include "dsa_priv.h" + +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + + return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff *ocelot_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int src_port, switch_id, qos_class; + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + src_port = dsa_8021q_rx_source_port(vid); + switch_id = dsa_8021q_rx_switch_id(vid); + qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + + skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); + if (!skb->dev) + return NULL; + + skb->offload_fwd_mark = 1; + skb->priority = qos_class; + + return skb; +} + +static const struct dsa_device_ops ocelot_8021q_netdev_ops = { + .name = "ocelot-8021q", + .proto = DSA_TAG_PROTO_OCELOT_8021Q, + .xmit = ocelot_xmit, + .rcv = ocelot_rcv, + .overhead = VLAN_HLEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q); + +module_dsa_tag_driver(ocelot_8021q_netdev_ops); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 7dc92ce5a134..a9c30a608e35 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -217,7 +217,10 @@ struct hsr_priv { u8 net_id; /* for PRP, it occupies most significant 3 bits * of lan_id */ - unsigned char sup_multicast_addr[ETH_ALEN]; + unsigned char sup_multicast_addr[ETH_ALEN] __aligned(sizeof(u16)); + /* Align to u16 boundary to avoid unaligned access + * in ether_addr_equal + */ #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; #endif diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b94fa8eb831b..ab42f6404fc6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1871,6 +1871,8 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_igmp_llm_reports = 1; net->ipv4.sysctl_igmp_qrv = 2; + net->ipv4.sysctl_fib_notify_on_flag_change = 0; + return 0; } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 818916b2a04d..aff454ef0fa3 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -39,9 +39,10 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - struct fib_rt_info *fri, unsigned int flags); + const struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); +size_t fib_nlmsg_size(struct fib_info *fi); static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b5400cec4f69..4c38facf91c0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -452,7 +452,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) return -1; } -static inline size_t fib_nlmsg_size(struct fib_info *fi) +size_t fib_nlmsg_size(struct fib_info *fi) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ @@ -1733,7 +1733,7 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) #endif int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - struct fib_rt_info *fri, unsigned int flags) + const struct fib_rt_info *fri, unsigned int flags) { unsigned int nhs = fib_info_num_path(fri->fi); struct fib_info *fi = fri->fi; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 28117c05dc35..60559b708158 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1038,6 +1038,8 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { struct fib_alias *fa_match; + struct sk_buff *skb; + int err; rcu_read_lock(); @@ -1045,9 +1047,34 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) if (!fa_match) goto out; + if (fa_match->offload == fri->offload && fa_match->trap == fri->trap) + goto out; + fa_match->offload = fri->offload; fa_match->trap = fri->trap; + if (!net->ipv4.sysctl_fib_notify_on_flag_change) + goto out; + + skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC); + goto out; + +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err); out: rcu_read_unlock(); } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 10bc49bde9a1..1121a9d5fed9 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -15,10 +15,10 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + bool need_csum, offload_csum, gso_partial, need_ipsec; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; - bool need_csum, gso_partial; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; @@ -47,6 +47,11 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, if (need_csum) features &= ~NETIF_F_SCTP_CRC; + need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + /* Try to offload checksum if possible */ + offload_csum = !!(need_csum && !need_ipsec && + (skb->dev->features & NETIF_F_HW_CSUM)); + /* segment inner packet. */ segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { @@ -100,7 +105,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } *(pcsum + 1) = 0; - *pcsum = gso_make_checksum(skb, 0); + if (skb->encapsulation || !offload_csum) { + *pcsum = gso_make_checksum(skb, 0); + } else { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = sizeof(*greh); + } } while ((skb = skb->next)); out: return segs; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 64594aa755f0..76a420c76f16 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) } dev->needed_headroom = t_hlen + hlen; - mtu -= (dev->hard_header_len + t_hlen); + mtu -= t_hlen; if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; @@ -347,7 +347,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; + dev->max_mtu = IP_MAX_MTU - t_hlen; ip_tunnel_add(itn, nt); return nt; @@ -488,11 +488,10 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, int mtu; tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; - pkt_size = skb->len - tunnel_hlen - dev->hard_header_len; + pkt_size = skb->len - tunnel_hlen; if (df) - mtu = dst_mtu(&rt->dst) - dev->hard_header_len - - sizeof(struct iphdr) - tunnel_hlen; + mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); else mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; @@ -972,7 +971,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); - int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; + int max_mtu = IP_MAX_MTU - t_hlen; if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1149,10 +1148,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { - unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen; + unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); - mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, - (unsigned int)(max - sizeof(struct iphdr))); + mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } err = dev_set_mtu(dev, mtu); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index e6dfca426242..f1c6cbdb9e43 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -71,6 +71,7 @@ __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, static int nh_notifier_single_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { + info->type = NH_NOTIFIER_INFO_TYPE_SINGLE; info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); if (!info->nh) return -ENOMEM; @@ -85,13 +86,13 @@ static void nh_notifier_single_info_fini(struct nh_notifier_info *info) kfree(info->nh); } -static int nh_notifier_grp_info_init(struct nh_notifier_info *info, - const struct nexthop *nh) +static int nh_notifier_mp_info_init(struct nh_notifier_info *info, + struct nh_group *nhg) { - struct nh_group *nhg = rtnl_dereference(nh->nh_grp); u16 num_nh = nhg->num_nh; int i; + info->type = NH_NOTIFIER_INFO_TYPE_GRP; info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh), GFP_KERNEL); if (!info->nh_grp) @@ -112,27 +113,41 @@ static int nh_notifier_grp_info_init(struct nh_notifier_info *info, return 0; } -static void nh_notifier_grp_info_fini(struct nh_notifier_info *info) +static int nh_notifier_grp_info_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + + if (nhg->mpath) + return nh_notifier_mp_info_init(info, nhg); + return -EINVAL; +} + +static void nh_notifier_grp_info_fini(struct nh_notifier_info *info, + const struct nexthop *nh) { - kfree(info->nh_grp); + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + + if (nhg->mpath) + kfree(info->nh_grp); } static int nh_notifier_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { info->id = nh->id; - info->is_grp = nh->is_group; - if (info->is_grp) + if (nh->is_group) return nh_notifier_grp_info_init(info, nh); else return nh_notifier_single_info_init(info, nh); } -static void nh_notifier_info_fini(struct nh_notifier_info *info) +static void nh_notifier_info_fini(struct nh_notifier_info *info, + const struct nexthop *nh) { - if (info->is_grp) - nh_notifier_grp_info_fini(info); + if (nh->is_group) + nh_notifier_grp_info_fini(info, nh); else nh_notifier_single_info_fini(info); } @@ -161,7 +176,7 @@ static int call_nexthop_notifiers(struct net *net, err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, event_type, &info); - nh_notifier_info_fini(&info); + nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } @@ -182,7 +197,7 @@ static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, return err; err = nb->notifier_call(nb, event_type, &info); - nh_notifier_info_fini(&info); + nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } @@ -209,7 +224,7 @@ static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) hlist_add_head(&nhi->dev_hash, head); } -static void nexthop_free_mpath(struct nexthop *nh) +static void nexthop_free_group(struct nexthop *nh) { struct nh_group *nhg; int i; @@ -249,7 +264,7 @@ void nexthop_free_rcu(struct rcu_head *head) struct nexthop *nh = container_of(head, struct nexthop, rcu); if (nh->is_group) - nexthop_free_mpath(nh); + nexthop_free_group(nh); else nexthop_free_single(nh); @@ -680,21 +695,16 @@ static bool ipv4_good_nh(const struct fib_nh *nh) return !!(state & NUD_VALID); } -struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) +static struct nexthop *nexthop_select_path_mp(struct nh_group *nhg, int hash) { struct nexthop *rc = NULL; - struct nh_group *nhg; int i; - if (!nh->is_group) - return nh; - - nhg = rcu_dereference(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; - if (hash > atomic_read(&nhge->upper_bound)) + if (hash > atomic_read(&nhge->mpath.upper_bound)) continue; nhi = rcu_dereference(nhge->nh->nh_info); @@ -721,6 +731,21 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) return rc; } + +struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) +{ + struct nh_group *nhg; + + if (!nh->is_group) + return nh; + + nhg = rcu_dereference(nh->nh_grp); + if (nhg->mpath) + return nexthop_select_path_mp(nhg, hash); + + /* Unreachable. */ + return NULL; +} EXPORT_SYMBOL_GPL(nexthop_select_path); int nexthop_for_each_fib6_nh(struct nexthop *nh, @@ -914,7 +939,7 @@ static void nh_group_rebalance(struct nh_group *nhg) w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; - atomic_set(&nhge->upper_bound, upper_bound); + atomic_set(&nhge->mpath.upper_bound, upper_bound); } } @@ -1456,10 +1481,13 @@ static struct nexthop *nexthop_create_group(struct net *net, nhg->nh_entries[i].nh_parent = nh; } - if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { + if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) nhg->mpath = 1; + + WARN_ON_ONCE(nhg->mpath != 1); + + if (nhg->mpath) nh_group_rebalance(nhg); - } if (cfg->nh_fdb) nhg->fdb_nh = 1; @@ -1844,37 +1872,44 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static int nh_valid_get_del_req(struct nlmsghdr *nlh, u32 *id, - struct netlink_ext_ack *extack) +static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, + struct nlattr **tb, u32 *id, + struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; - int err; - err = nlmsg_parse(nlh, sizeof(*nhm), tb, - ARRAY_SIZE(rtm_nh_policy_get) - 1, - rtm_nh_policy_get, extack); - if (err < 0) - return err; - - err = -EINVAL; if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header"); - goto out; + return -EINVAL; } if (!tb[NHA_ID]) { NL_SET_ERR_MSG(extack, "Nexthop id is missing"); - goto out; + return -EINVAL; } *id = nla_get_u32(tb[NHA_ID]); - if (!(*id)) + if (!(*id)) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); - else - err = 0; -out: - return err; + return -EINVAL; + } + + return 0; +} + +static int nh_valid_get_del_req(const struct nlmsghdr *nlh, u32 *id, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; + int err; + + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_get) - 1, + rtm_nh_policy_get, extack); + if (err < 0) + return err; + + return __nh_valid_get_del_req(nlh, tb, id, extack); } /* rtnl */ @@ -1943,16 +1978,23 @@ errout_free: goto out; } -static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, - bool group_filter, u8 family) +struct nh_dump_filter { + int dev_idx; + int master_idx; + bool group_filter; + bool fdb_filter; +}; + +static bool nh_dump_filtered(struct nexthop *nh, + struct nh_dump_filter *filter, u8 family) { const struct net_device *dev; const struct nh_info *nhi; - if (group_filter && !nh->is_group) + if (filter->group_filter && !nh->is_group) return true; - if (!dev_idx && !master_idx && !family) + if (!filter->dev_idx && !filter->master_idx && !family) return false; if (nh->is_group) @@ -1963,46 +2005,37 @@ static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, return true; dev = nhi->fib_nhc.nhc_dev; - if (dev_idx && (!dev || dev->ifindex != dev_idx)) + if (filter->dev_idx && (!dev || dev->ifindex != filter->dev_idx)) return true; - if (master_idx) { + if (filter->master_idx) { struct net_device *master; if (!dev) return true; master = netdev_master_upper_dev_get((struct net_device *)dev); - if (!master || master->ifindex != master_idx) + if (!master || master->ifindex != filter->master_idx) return true; } return false; } -static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, - int *master_idx, bool *group_filter, - bool *fdb_filter, struct netlink_callback *cb) +static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, + struct nh_dump_filter *filter, + struct netlink_ext_ack *extack) { - struct netlink_ext_ack *extack = cb->extack; - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; struct nhmsg *nhm; - int err; u32 idx; - err = nlmsg_parse(nlh, sizeof(*nhm), tb, - ARRAY_SIZE(rtm_nh_policy_dump) - 1, - rtm_nh_policy_dump, NULL); - if (err < 0) - return err; - if (tb[NHA_OIF]) { idx = nla_get_u32(tb[NHA_OIF]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid device index"); return -EINVAL; } - *dev_idx = idx; + filter->dev_idx = idx; } if (tb[NHA_MASTER]) { idx = nla_get_u32(tb[NHA_MASTER]); @@ -2010,10 +2043,10 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, NL_SET_ERR_MSG(extack, "Invalid master device index"); return -EINVAL; } - *master_idx = idx; + filter->master_idx = idx; } - *group_filter = nla_get_flag(tb[NHA_GROUPS]); - *fdb_filter = nla_get_flag(tb[NHA_FDB]); + filter->group_filter = nla_get_flag(tb[NHA_GROUPS]); + filter->fdb_filter = nla_get_flag(tb[NHA_FDB]); nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { @@ -2024,24 +2057,49 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, return 0; } -/* rtnl */ -static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) +static int nh_valid_dump_req(const struct nlmsghdr *nlh, + struct nh_dump_filter *filter, + struct netlink_callback *cb) { - bool group_filter = false, fdb_filter = false; - struct nhmsg *nhm = nlmsg_data(cb->nlh); - int dev_filter_idx = 0, master_idx = 0; - struct net *net = sock_net(skb->sk); - struct rb_root *root = &net->nexthop.rb_root; - struct rb_node *node; - int idx = 0, s_idx; + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; int err; - err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx, - &group_filter, &fdb_filter, cb); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_dump) - 1, + rtm_nh_policy_dump, cb->extack); if (err < 0) return err; - s_idx = cb->args[0]; + return __nh_valid_dump_req(nlh, tb, filter, cb->extack); +} + +struct rtm_dump_nh_ctx { + u32 idx; +}; + +static struct rtm_dump_nh_ctx * +rtm_dump_nh_ctx(struct netlink_callback *cb) +{ + struct rtm_dump_nh_ctx *ctx = (void *)cb->ctx; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + return ctx; +} + +static int rtm_dump_walk_nexthops(struct sk_buff *skb, + struct netlink_callback *cb, + struct rb_root *root, + struct rtm_dump_nh_ctx *ctx, + int (*nh_cb)(struct sk_buff *skb, + struct netlink_callback *cb, + struct nexthop *nh, void *data), + void *data) +{ + struct rb_node *node; + int idx = 0, s_idx; + int err; + + s_idx = ctx->idx; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; @@ -2049,30 +2107,58 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) goto cont; nh = rb_entry(node, struct nexthop, rb_node); - if (nh_dump_filtered(nh, dev_filter_idx, master_idx, - group_filter, nhm->nh_family)) - goto cont; - - err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err < 0) { - if (likely(skb->len)) - goto out; - - goto out_err; - } + ctx->idx = idx; + err = nh_cb(skb, cb, nh, data); + if (err) + return err; cont: idx++; } + ctx->idx = idx; + return 0; +} + +static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, + struct nexthop *nh, void *data) +{ + struct nhmsg *nhm = nlmsg_data(cb->nlh); + struct nh_dump_filter *filter = data; + + if (nh_dump_filtered(nh, filter, nhm->nh_family)) + return 0; + + return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); +} + +/* rtnl */ +static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rtm_dump_nh_ctx *ctx = rtm_dump_nh_ctx(cb); + struct net *net = sock_net(skb->sk); + struct rb_root *root = &net->nexthop.rb_root; + struct nh_dump_filter filter = {}; + int err; + + err = nh_valid_dump_req(cb->nlh, &filter, cb); + if (err < 0) + return err; + + err = rtm_dump_walk_nexthops(skb, cb, root, ctx, + &rtm_dump_nexthop_cb, &filter); + if (err < 0) { + if (likely(skb->len)) + goto out; + goto out_err; + } + out: err = skb->len; out_err: - cb->args[0] = idx; cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); - return err; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 63cd370ea29d..6d46297a99f8 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -464,30 +464,52 @@ static int snmp_seq_show(struct seq_file *seq, void *v) */ static int netstat_seq_show(struct seq_file *seq, void *v) { - int i; + const int ip_cnt = ARRAY_SIZE(snmp4_ipextstats_list) - 1; + const int tcp_cnt = ARRAY_SIZE(snmp4_net_list) - 1; struct net *net = seq->private; + unsigned long *buff; + int i; seq_puts(seq, "TcpExt:"); - for (i = 0; snmp4_net_list[i].name; i++) + for (i = 0; i < tcp_cnt; i++) seq_printf(seq, " %s", snmp4_net_list[i].name); seq_puts(seq, "\nTcpExt:"); - for (i = 0; snmp4_net_list[i].name; i++) - seq_printf(seq, " %lu", - snmp_fold_field(net->mib.net_statistics, - snmp4_net_list[i].entry)); - + buff = kzalloc(max(tcp_cnt * sizeof(long), ip_cnt * sizeof(u64)), + GFP_KERNEL); + if (buff) { + snmp_get_cpu_field_batch(buff, snmp4_net_list, + net->mib.net_statistics); + for (i = 0; i < tcp_cnt; i++) + seq_printf(seq, " %lu", buff[i]); + } else { + for (i = 0; i < tcp_cnt; i++) + seq_printf(seq, " %lu", + snmp_fold_field(net->mib.net_statistics, + snmp4_net_list[i].entry)); + } seq_puts(seq, "\nIpExt:"); - for (i = 0; snmp4_ipextstats_list[i].name; i++) + for (i = 0; i < ip_cnt; i++) seq_printf(seq, " %s", snmp4_ipextstats_list[i].name); seq_puts(seq, "\nIpExt:"); - for (i = 0; snmp4_ipextstats_list[i].name; i++) - seq_printf(seq, " %llu", - snmp_fold_field64(net->mib.ip_statistics, - snmp4_ipextstats_list[i].entry, - offsetof(struct ipstats_mib, syncp))); - + if (buff) { + u64 *buff64 = (u64 *)buff; + + memset(buff64, 0, ip_cnt * sizeof(u64)); + snmp_get_cpu_field64_batch(buff64, snmp4_ipextstats_list, + net->mib.ip_statistics, + offsetof(struct ipstats_mib, syncp)); + for (i = 0; i < ip_cnt; i++) + seq_printf(seq, " %llu", buff64[i]); + } else { + for (i = 0; i < ip_cnt; i++) + seq_printf(seq, " %llu", + snmp_fold_field64(net->mib.ip_statistics, + snmp4_ipextstats_list[i].entry, + offsetof(struct ipstats_mib, syncp))); + } + kfree(buff); seq_putc(seq, '\n'); mptcp_seq_show(seq); return 0; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3e5f4f2e705e..e5798b3b59d2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1354,6 +1354,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, + { + .procname = "fib_notify_on_flag_change", + .data = &init_net.ipv4.sysctl_fib_notify_on_flag_change, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, { } }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d4f66aba9fd8..a8f8f9815953 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2859,7 +2859,8 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) } else if (tcp_is_rack(sk)) { u32 prior_retrans = tp->retrans_out; - tcp_rack_mark_lost(sk); + if (tcp_rack_mark_lost(sk)) + *ack_flag &= ~FLAG_SET_XMIT_TIMER; if (prior_retrans > tp->retrans_out) *ack_flag |= FLAG_LOST_RETRANS; } @@ -3392,8 +3393,8 @@ static void tcp_ack_probe(struct sock *sk) } else { unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX); - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - when, TCP_RTO_MAX); + when = tcp_clamp_probe0_to_user_timeout(sk, when); + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX); } } @@ -3816,9 +3817,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); - /* If needed, reset TLP/RTO timer; RACK may later override this. */ - if (flag & FLAG_SET_XMIT_TIMER) - tcp_set_xmit_timer(sk); if (tcp_ack_is_dubious(sk, flag)) { if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) { @@ -3831,6 +3829,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &rexmit); } + /* If needed, reset TLP/RTO timer when RACK doesn't set. */ + if (flag & FLAG_SET_XMIT_TIMER) + tcp_set_xmit_timer(sk); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b0a6b0b30a6b..fbf140a770d8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -4099,6 +4099,8 @@ void tcp_send_probe0(struct sock *sk) */ timeout = TCP_RESOURCE_PROBE_INTERVAL; } + + timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); } diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 177307a3081f..6f1b4ac7fe99 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -96,13 +96,13 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) } } -void tcp_rack_mark_lost(struct sock *sk) +bool tcp_rack_mark_lost(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 timeout; if (!tp->rack.advanced) - return; + return false; /* Reset the advanced flag to avoid unnecessary queue scanning */ tp->rack.advanced = 0; @@ -112,6 +112,7 @@ void tcp_rack_mark_lost(struct sock *sk) inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } + return !!timeout; } /* Record the most recently (re)sent time among the (s)acked packets diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index faa92948441b..4ef08079ccfa 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -40,6 +40,24 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } +u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + u32 remaining; + s32 elapsed; + + if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp) + return when; + + elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; + if (unlikely(elapsed < 0)) + elapsed = 0; + remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed; + remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); + + return min_t(u32, remaining, when); +} + /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 41249705d9e9..b76c48efd37e 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -187,8 +187,67 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); +static void __udpv4_gso_segment_csum(struct sk_buff *seg, + __be32 *oldip, __be32 *newip, + __be16 *oldport, __be16 *newport) +{ + struct udphdr *uh; + struct iphdr *iph; + + if (*oldip == *newip && *oldport == *newport) + return; + + uh = udp_hdr(seg); + iph = ip_hdr(seg); + + if (uh->check) { + inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, + true); + inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, + false); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + *oldport = *newport; + + csum_replace4(&iph->check, *oldip, *newip); + *oldip = *newip; +} + +static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) +{ + struct sk_buff *seg; + struct udphdr *uh, *uh2; + struct iphdr *iph, *iph2; + + seg = segs; + uh = udp_hdr(seg); + iph = ip_hdr(seg); + + if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && + (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && + (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && + (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) + return segs; + + while ((seg = seg->next)) { + uh2 = udp_hdr(seg); + iph2 = ip_hdr(seg); + + __udpv4_gso_segment_csum(seg, + &iph2->saddr, &iph->saddr, + &uh2->source, &uh->source); + __udpv4_gso_segment_csum(seg, + &iph2->daddr, &iph->daddr, + &uh2->dest, &uh->dest); + } + + return segs; +} + static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, - netdev_features_t features) + netdev_features_t features, + bool is_ipv6) { unsigned int mss = skb_shinfo(skb)->gso_size; @@ -198,11 +257,11 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); - return skb; + return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, - netdev_features_t features) + netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; @@ -214,7 +273,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __be16 newlen; if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features); + return __udp_gso_segment_list(gso_skb, features, is_ipv6); mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) @@ -328,7 +387,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) - return __udp_gso_segment(skb, features); + return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8e9c3e9ea36e..0e9994e0ecd7 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -954,6 +954,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; + net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 41d8f801b75f..92b400eb8476 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6064,6 +6064,50 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } +void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, + bool offload, bool trap) +{ + struct sk_buff *skb; + int err; + + if (f6i->offload == offload && f6i->trap == trap) + return; + + f6i->offload = offload; + f6i->trap = trap; + + if (!rcu_access_pointer(f6i->fib6_node)) + /* The route was removed from the tree, do not send + * notfication. + */ + return; + + if (!net->ipv6.sysctl.fib_notify_on_flag_change) + return; + + skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, + 0, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); + return; + +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); +} +EXPORT_SYMBOL(fib6_info_hw_flags_set); + static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 5b60a4bdd36a..392ef01e3366 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -160,6 +160,15 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "fib_notify_on_flag_change", + .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, { } }; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index c7bd7b1a04c1..faa823c24292 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -42,7 +42,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) - return __udp_gso_segment(skb, features); + return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 882f028992c3..6092d5cb7168 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -89,7 +89,7 @@ static struct sock *iucv_accept_dequeue(struct sock *parent, static void iucv_sock_kill(struct sock *sk); static void iucv_sock_close(struct sock *sk); -static void afiucv_hs_callback_txnotify(struct sk_buff *, enum iucv_tx_notify); +static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify); /* Call Back functions */ static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); @@ -182,7 +182,7 @@ static inline int iucv_below_msglim(struct sock *sk) if (sk->sk_state != IUCV_CONNECTED) return 1; if (iucv->transport == AF_IUCV_TRANS_IUCV) - return (skb_queue_len(&iucv->send_skb_q) < iucv->path->msglim); + return (atomic_read(&iucv->skbs_in_xmit) < iucv->path->msglim); else return ((atomic_read(&iucv->msg_sent) < iucv->msglimit_peer) && (atomic_read(&iucv->pendings) <= 0)); @@ -211,7 +211,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, { struct iucv_sock *iucv = iucv_sk(sock); struct af_iucv_trans_hdr *phs_hdr; - struct sk_buff *nskb; int err, confirm_recv = 0; phs_hdr = skb_push(skb, sizeof(*phs_hdr)); @@ -257,22 +256,16 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, err = -EMSGSIZE; goto err_free; } - skb_trim(skb, skb->dev->mtu); + err = pskb_trim(skb, skb->dev->mtu); + if (err) + goto err_free; } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); - __skb_header_release(skb); - nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) { - err = -ENOMEM; - goto err_free; - } - - skb_queue_tail(&iucv->send_skb_q, nskb); + atomic_inc(&iucv->skbs_in_xmit); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { - skb_unlink(nskb, &iucv->send_skb_q); - kfree_skb(nskb); + atomic_dec(&iucv->skbs_in_xmit); } else { atomic_sub(confirm_recv, &iucv->msg_recv); WARN_ON(atomic_read(&iucv->msg_recv) < 0); @@ -424,7 +417,7 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); - if (!err && !skb_queue_empty(&iucv->send_skb_q)) { + if (!err && atomic_read(&iucv->skbs_in_xmit) > 0) { if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) timeo = sk->sk_lingertime; else @@ -491,6 +484,7 @@ static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio, atomic_set(&iucv->pendings, 0); iucv->flags = 0; iucv->msglimit = 0; + atomic_set(&iucv->skbs_in_xmit, 0); atomic_set(&iucv->msg_sent, 0); atomic_set(&iucv->msg_recv, 0); iucv->path = NULL; @@ -1004,7 +998,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (iucv->transport == AF_IUCV_TRANS_HIPER) { headroom = sizeof(struct af_iucv_trans_hdr) + LL_RESERVED_SPACE(iucv->hs_dev); - linear = len; + linear = min(len, PAGE_SIZE - headroom); } else { if (len < PAGE_SIZE) { linear = len; @@ -1055,6 +1049,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, } } else { /* Classic VM IUCV transport */ skb_queue_tail(&iucv->send_skb_q, skb); + atomic_inc(&iucv->skbs_in_xmit); if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags) && skb->len <= 7) { @@ -1063,6 +1058,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, /* on success: there is no message_complete callback */ /* for an IPRMDATA msg; remove skb from send queue */ if (err == 0) { + atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); kfree_skb(skb); } @@ -1071,6 +1067,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, /* IUCV_IPRMDATA path flag is set... sever path */ if (err == 0x15) { pr_iucv->path_sever(iucv->path, NULL); + atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); err = -EPIPE; goto fail; @@ -1109,6 +1106,8 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, } else { err = -EPIPE; } + + atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); goto fail; } @@ -1748,10 +1747,14 @@ static void iucv_callback_txdone(struct iucv_path *path, { struct sock *sk = path->private; struct sk_buff *this = NULL; - struct sk_buff_head *list = &iucv_sk(sk)->send_skb_q; + struct sk_buff_head *list; struct sk_buff *list_skb; + struct iucv_sock *iucv; unsigned long flags; + iucv = iucv_sk(sk); + list = &iucv->send_skb_q; + bh_lock_sock(sk); spin_lock_irqsave(&list->lock, flags); @@ -1761,8 +1764,11 @@ static void iucv_callback_txdone(struct iucv_path *path, break; } } - if (this) + if (this) { + atomic_dec(&iucv->skbs_in_xmit); __skb_unlink(this, list); + } + spin_unlock_irqrestore(&list->lock, flags); if (this) { @@ -1772,7 +1778,7 @@ static void iucv_callback_txdone(struct iucv_path *path, } if (sk->sk_state == IUCV_CLOSING) { - if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) { + if (atomic_read(&iucv->skbs_in_xmit) == 0) { sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); } @@ -2036,7 +2042,6 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, char nullstring[8]; if (!pskb_may_pull(skb, sizeof(*trans_hdr))) { - WARN_ONCE(1, "AF_IUCV failed to receive skb, len=%u", skb->len); kfree_skb(skb); return NET_RX_SUCCESS; } @@ -2132,73 +2137,40 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, * afiucv_hs_callback_txnotify() - handle send notifcations from HiperSockets * transport **/ -static void afiucv_hs_callback_txnotify(struct sk_buff *skb, - enum iucv_tx_notify n) +static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify n) { - struct sock *isk = skb->sk; - struct sock *sk = NULL; - struct iucv_sock *iucv = NULL; - struct sk_buff_head *list; - struct sk_buff *list_skb; - struct sk_buff *nskb; - unsigned long flags; - - read_lock_irqsave(&iucv_sk_list.lock, flags); - sk_for_each(sk, &iucv_sk_list.head) - if (sk == isk) { - iucv = iucv_sk(sk); - break; - } - read_unlock_irqrestore(&iucv_sk_list.lock, flags); + struct iucv_sock *iucv = iucv_sk(sk); - if (!iucv || sock_flag(sk, SOCK_ZAPPED)) + if (sock_flag(sk, SOCK_ZAPPED)) return; - list = &iucv->send_skb_q; - spin_lock_irqsave(&list->lock, flags); - skb_queue_walk_safe(list, list_skb, nskb) { - if (skb_shinfo(list_skb) == skb_shinfo(skb)) { - switch (n) { - case TX_NOTIFY_OK: - __skb_unlink(list_skb, list); - kfree_skb(list_skb); - iucv_sock_wake_msglim(sk); - break; - case TX_NOTIFY_PENDING: - atomic_inc(&iucv->pendings); - break; - case TX_NOTIFY_DELAYED_OK: - __skb_unlink(list_skb, list); - atomic_dec(&iucv->pendings); - if (atomic_read(&iucv->pendings) <= 0) - iucv_sock_wake_msglim(sk); - kfree_skb(list_skb); - break; - case TX_NOTIFY_UNREACHABLE: - case TX_NOTIFY_DELAYED_UNREACHABLE: - case TX_NOTIFY_TPQFULL: /* not yet used */ - case TX_NOTIFY_GENERALERROR: - case TX_NOTIFY_DELAYED_GENERALERROR: - __skb_unlink(list_skb, list); - kfree_skb(list_skb); - if (sk->sk_state == IUCV_CONNECTED) { - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); - } - break; - } - break; + switch (n) { + case TX_NOTIFY_OK: + atomic_dec(&iucv->skbs_in_xmit); + iucv_sock_wake_msglim(sk); + break; + case TX_NOTIFY_PENDING: + atomic_inc(&iucv->pendings); + break; + case TX_NOTIFY_DELAYED_OK: + atomic_dec(&iucv->skbs_in_xmit); + if (atomic_dec_return(&iucv->pendings) <= 0) + iucv_sock_wake_msglim(sk); + break; + default: + atomic_dec(&iucv->skbs_in_xmit); + if (sk->sk_state == IUCV_CONNECTED) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); } } - spin_unlock_irqrestore(&list->lock, flags); if (sk->sk_state == IUCV_CLOSING) { - if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) { + if (atomic_read(&iucv->skbs_in_xmit) == 0) { sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); } } - } /* diff --git a/net/key/af_key.c b/net/key/af_key.c index c12dbc51ef5f..ef9b4ac03e7b 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2902,7 +2902,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2920,7 +2920,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2931,7 +2931,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 40961889e9c0..0511bbe4af7b 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -122,6 +122,8 @@ static struct lapb_cb *lapb_create_cb(void) timer_setup(&lapb->t1timer, NULL, 0); timer_setup(&lapb->t2timer, NULL, 0); + lapb->t1timer_stop = true; + lapb->t2timer_stop = true; lapb->t1 = LAPB_DEFAULT_T1; lapb->t2 = LAPB_DEFAULT_T2; @@ -129,6 +131,8 @@ static struct lapb_cb *lapb_create_cb(void) lapb->mode = LAPB_DEFAULT_MODE; lapb->window = LAPB_DEFAULT_WINDOW; lapb->state = LAPB_STATE_0; + + spin_lock_init(&lapb->lock); refcount_set(&lapb->refcnt, 1); out: return lapb; @@ -178,11 +182,23 @@ int lapb_unregister(struct net_device *dev) goto out; lapb_put(lapb); + /* Wait for other refs to "lapb" to drop */ + while (refcount_read(&lapb->refcnt) > 2) + usleep_range(1, 10); + + spin_lock_bh(&lapb->lock); + lapb_stop_t1timer(lapb); lapb_stop_t2timer(lapb); lapb_clear_queues(lapb); + spin_unlock_bh(&lapb->lock); + + /* Wait for running timers to stop */ + del_timer_sync(&lapb->t1timer); + del_timer_sync(&lapb->t2timer); + __lapb_remove_cb(lapb); lapb_put(lapb); @@ -201,6 +217,8 @@ int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms) if (!lapb) goto out; + spin_lock_bh(&lapb->lock); + parms->t1 = lapb->t1 / HZ; parms->t2 = lapb->t2 / HZ; parms->n2 = lapb->n2; @@ -219,6 +237,7 @@ int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms) else parms->t2timer = (lapb->t2timer.expires - jiffies) / HZ; + spin_unlock_bh(&lapb->lock); lapb_put(lapb); rc = LAPB_OK; out: @@ -234,6 +253,8 @@ int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms) if (!lapb) goto out; + spin_lock_bh(&lapb->lock); + rc = LAPB_INVALUE; if (parms->t1 < 1 || parms->t2 < 1 || parms->n2 < 1) goto out_put; @@ -256,6 +277,7 @@ int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms) rc = LAPB_OK; out_put: + spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; @@ -270,6 +292,8 @@ int lapb_connect_request(struct net_device *dev) if (!lapb) goto out; + spin_lock_bh(&lapb->lock); + rc = LAPB_OK; if (lapb->state == LAPB_STATE_1) goto out_put; @@ -285,24 +309,18 @@ int lapb_connect_request(struct net_device *dev) rc = LAPB_OK; out_put: + spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; } EXPORT_SYMBOL(lapb_connect_request); -int lapb_disconnect_request(struct net_device *dev) +static int __lapb_disconnect_request(struct lapb_cb *lapb) { - struct lapb_cb *lapb = lapb_devtostruct(dev); - int rc = LAPB_BADTOKEN; - - if (!lapb) - goto out; - switch (lapb->state) { case LAPB_STATE_0: - rc = LAPB_NOTCONNECTED; - goto out_put; + return LAPB_NOTCONNECTED; case LAPB_STATE_1: lapb_dbg(1, "(%p) S1 TX DISC(1)\n", lapb->dev); @@ -310,12 +328,10 @@ int lapb_disconnect_request(struct net_device *dev) lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); lapb->state = LAPB_STATE_0; lapb_start_t1timer(lapb); - rc = LAPB_NOTCONNECTED; - goto out_put; + return LAPB_NOTCONNECTED; case LAPB_STATE_2: - rc = LAPB_OK; - goto out_put; + return LAPB_OK; } lapb_clear_queues(lapb); @@ -328,8 +344,22 @@ int lapb_disconnect_request(struct net_device *dev) lapb_dbg(1, "(%p) S3 DISC(1)\n", lapb->dev); lapb_dbg(0, "(%p) S3 -> S2\n", lapb->dev); - rc = LAPB_OK; -out_put: + return LAPB_OK; +} + +int lapb_disconnect_request(struct net_device *dev) +{ + struct lapb_cb *lapb = lapb_devtostruct(dev); + int rc = LAPB_BADTOKEN; + + if (!lapb) + goto out; + + spin_lock_bh(&lapb->lock); + + rc = __lapb_disconnect_request(lapb); + + spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; @@ -344,6 +374,8 @@ int lapb_data_request(struct net_device *dev, struct sk_buff *skb) if (!lapb) goto out; + spin_lock_bh(&lapb->lock); + rc = LAPB_NOTCONNECTED; if (lapb->state != LAPB_STATE_3 && lapb->state != LAPB_STATE_4) goto out_put; @@ -352,6 +384,7 @@ int lapb_data_request(struct net_device *dev, struct sk_buff *skb) lapb_kick(lapb); rc = LAPB_OK; out_put: + spin_unlock_bh(&lapb->lock); lapb_put(lapb); out: return rc; @@ -364,7 +397,9 @@ int lapb_data_received(struct net_device *dev, struct sk_buff *skb) int rc = LAPB_BADTOKEN; if (lapb) { + spin_lock_bh(&lapb->lock); lapb_data_input(lapb, skb); + spin_unlock_bh(&lapb->lock); lapb_put(lapb); rc = LAPB_OK; } @@ -435,6 +470,8 @@ static int lapb_device_event(struct notifier_block *this, unsigned long event, if (!lapb) return NOTIFY_DONE; + spin_lock_bh(&lapb->lock); + switch (event) { case NETDEV_UP: lapb_dbg(0, "(%p) Interface up: %s\n", dev, dev->name); @@ -454,7 +491,7 @@ static int lapb_device_event(struct notifier_block *this, unsigned long event, break; case NETDEV_GOING_DOWN: if (netif_carrier_ok(dev)) - lapb_disconnect_request(dev); + __lapb_disconnect_request(lapb); break; case NETDEV_DOWN: lapb_dbg(0, "(%p) Interface down: %s\n", dev, dev->name); @@ -489,6 +526,7 @@ static int lapb_device_event(struct notifier_block *this, unsigned long event, break; } + spin_unlock_bh(&lapb->lock); lapb_put(lapb); return NOTIFY_DONE; } diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c index 7a4d0715d1c3..a966d29c772d 100644 --- a/net/lapb/lapb_out.c +++ b/net/lapb/lapb_out.c @@ -82,7 +82,8 @@ void lapb_kick(struct lapb_cb *lapb) skb = skb_dequeue(&lapb->write_queue); do { - if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) { + skbn = skb_copy(skb, GFP_ATOMIC); + if (!skbn) { skb_queue_head(&lapb->write_queue, skb); break; } diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index baa247fe4ed0..0230b272b7d1 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -40,6 +40,7 @@ void lapb_start_t1timer(struct lapb_cb *lapb) lapb->t1timer.function = lapb_t1timer_expiry; lapb->t1timer.expires = jiffies + lapb->t1; + lapb->t1timer_stop = false; add_timer(&lapb->t1timer); } @@ -50,16 +51,19 @@ void lapb_start_t2timer(struct lapb_cb *lapb) lapb->t2timer.function = lapb_t2timer_expiry; lapb->t2timer.expires = jiffies + lapb->t2; + lapb->t2timer_stop = false; add_timer(&lapb->t2timer); } void lapb_stop_t1timer(struct lapb_cb *lapb) { + lapb->t1timer_stop = true; del_timer(&lapb->t1timer); } void lapb_stop_t2timer(struct lapb_cb *lapb) { + lapb->t2timer_stop = true; del_timer(&lapb->t2timer); } @@ -72,16 +76,31 @@ static void lapb_t2timer_expiry(struct timer_list *t) { struct lapb_cb *lapb = from_timer(lapb, t, t2timer); + spin_lock_bh(&lapb->lock); + if (timer_pending(&lapb->t2timer)) /* A new timer has been set up */ + goto out; + if (lapb->t2timer_stop) /* The timer has been stopped */ + goto out; + if (lapb->condition & LAPB_ACK_PENDING_CONDITION) { lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; lapb_timeout_response(lapb); } + +out: + spin_unlock_bh(&lapb->lock); } static void lapb_t1timer_expiry(struct timer_list *t) { struct lapb_cb *lapb = from_timer(lapb, t, t1timer); + spin_lock_bh(&lapb->lock); + if (timer_pending(&lapb->t1timer)) /* A new timer has been set up */ + goto out; + if (lapb->t1timer_stop) /* The timer has been stopped */ + goto out; + switch (lapb->state) { /* @@ -108,7 +127,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb->state = LAPB_STATE_0; lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev); - return; + goto out; } else { lapb->n2count++; if (lapb->mode & LAPB_EXTENDED) { @@ -132,7 +151,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb->state = LAPB_STATE_0; lapb_disconnect_confirmation(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S2 -> S0\n", lapb->dev); - return; + goto out; } else { lapb->n2count++; lapb_dbg(1, "(%p) S2 TX DISC(1)\n", lapb->dev); @@ -150,7 +169,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb_stop_t2timer(lapb); lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S3 -> S0\n", lapb->dev); - return; + goto out; } else { lapb->n2count++; lapb_requeue_frames(lapb); @@ -167,7 +186,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb->state = LAPB_STATE_0; lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S4 -> S0\n", lapb->dev); - return; + goto out; } else { lapb->n2count++; lapb_transmit_frmr(lapb); @@ -176,4 +195,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) } lapb_start_t1timer(lapb); + +out: + spin_unlock_bh(&lapb->lock); } diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index c9a8a2433e8a..48322e45e7dd 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -125,8 +125,11 @@ int drv_sta_state(struct ieee80211_local *local, } else if (old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) { ret = drv_sta_add(local, sdata, &sta->sta); - if (ret == 0) + if (ret == 0) { sta->uploaded = true; + if (rcu_access_pointer(sta->sta.rates)) + drv_sta_rate_tbl_update(local, sdata, &sta->sta); + } } else if (old_state == IEEE80211_STA_ASSOC && new_state == IEEE80211_STA_AUTH) { drv_sta_remove(local, sdata, &sta->sta); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 982fdc12abd9..ecda126a7026 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1077,6 +1077,7 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_FLUSH, IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN, IEEE80211_QUEUE_STOP_REASON_RESERVE_TID, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE, IEEE80211_QUEUE_STOP_REASONS, }; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 4bc350cf4eee..b80c9b016b2b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1633,6 +1633,10 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, if (ret) return ret; + ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); + synchronize_net(); + ieee80211_do_stop(sdata, false); ieee80211_teardown_sdata(sdata); @@ -1655,6 +1659,8 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, err = ieee80211_do_open(&sdata->wdev, false); WARN(err, "type change: do_open returned %d", err); + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); return ret; } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 45927202c71c..63652c39c8e0 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -960,7 +960,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw, if (old) kfree_rcu(old, rcu_head); - drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); + if (sta->uploaded) + drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta)); diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index ae1cb2c68722..76747bfdaddd 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -133,16 +133,20 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, } if (wide_bw_chansw_ie) { + u8 new_seg1 = wide_bw_chansw_ie->new_center_freq_seg1; struct ieee80211_vht_operation vht_oper = { .chan_width = wide_bw_chansw_ie->new_channel_width, .center_freq_seg0_idx = wide_bw_chansw_ie->new_center_freq_seg0, - .center_freq_seg1_idx = - wide_bw_chansw_ie->new_center_freq_seg1, + .center_freq_seg1_idx = new_seg1, /* .basic_mcs_set doesn't matter */ }; - struct ieee80211_ht_operation ht_oper = {}; + struct ieee80211_ht_operation ht_oper = { + .operation_mode = + cpu_to_le16(new_seg1 << + IEEE80211_HT_OP_MODE_CCFS2_SHIFT), + }; /* default, for the case of IEEE80211_VHT_CHANWIDTH_USE_HT, * to the previously parsed chandef diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 8ca196489893..3780c29c321d 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -29,6 +29,12 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), + SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), + SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), + SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX), + SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX), + SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX), + SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 63914a5ef6a5..72afbc135f8e 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -22,6 +22,12 @@ enum linux_mptcp_mib_field { MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */ MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */ + MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */ + MPTCP_MIB_JOINPORTSYNACKRX, /* Received a SYNACK MP_JOIN with a different port-number */ + MPTCP_MIB_JOINPORTACKRX, /* Received an ACK MP_JOIN with a different port-number */ + MPTCP_MIB_MISMATCHPORTSYNRX, /* Received a SYN MP_JOIN with a mismatched port-number */ + MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */ MPTCP_MIB_RMADDR, /* Received RM_ADDR */ MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index b70ae4ba3000..00ed742f48a4 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -128,10 +128,10 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, 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_subflows_max = mptcp_pm_get_subflows_max(msk); + val = mptcp_pm_get_add_addr_signal_max(msk); info->mptcpi_add_addr_signal_max = val; - val = READ_ONCE(msk->pm.add_addr_accept_max); + val = mptcp_pm_get_add_addr_accept_max(msk); info->mptcpi_add_addr_accepted_max = val; if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) flags |= MPTCP_INFO_FLAG_FALLBACK; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c9643344a8d7..3b71d68b3863 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -699,10 +699,11 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, if (!subflow->send_mp_prio) return false; - if (remaining < TCPOLEN_MPTCP_PRIO) + /* account for the trailing 'nop' option */ + if (remaining < TCPOLEN_MPTCP_PRIO_ALIGN) return false; - *size = TCPOLEN_MPTCP_PRIO; + *size = TCPOLEN_MPTCP_PRIO_ALIGN; opts->suboptions |= OPTION_MPTCP_PRIO; opts->backup = subflow->request_bkup; @@ -1024,6 +1025,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mptcp_pm_del_add_timer(msk, &addr); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); } + + if (mp_opt.port) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD); + mp_opt.add_addr = 0; } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 0a6ebd0642ec..3a22e73220b9 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -78,10 +78,13 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side) bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; + unsigned int subflows_max; int ret = 0; + subflows_max = mptcp_pm_get_subflows_max(msk); + pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows, - pm->subflows_max, READ_ONCE(pm->accept_subflow)); + subflows_max, READ_ONCE(pm->accept_subflow)); /* try to avoid acquiring the lock below */ if (!READ_ONCE(pm->accept_subflow)) @@ -89,8 +92,8 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) spin_lock_bh(&pm->lock); if (READ_ONCE(pm->accept_subflow)) { - ret = pm->subflows < pm->subflows_max; - if (ret && ++pm->subflows == pm->subflows_max) + ret = pm->subflows < subflows_max; + if (ret && ++pm->subflows == subflows_max) WRITE_ONCE(pm->accept_subflow, false); } spin_unlock_bh(&pm->lock); @@ -188,8 +191,7 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk) { - if (!mptcp_pm_should_add_signal_ipv6(msk) && - !mptcp_pm_should_add_signal_port(msk)) + if (!mptcp_pm_should_add_signal(msk)) return; mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 83976b9ee99b..e7b1abb4f0c2 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -26,6 +26,7 @@ struct mptcp_pm_addr_entry { struct list_head list; struct mptcp_addr_info addr; struct rcu_head rcu; + struct socket *lsk; }; struct mptcp_pm_add_entry { @@ -90,14 +91,14 @@ static bool address_zero(const struct mptcp_addr_info *addr) memset(&zero, 0, sizeof(zero)); zero.family = addr->family; - return addresses_equal(addr, &zero, false); + return addresses_equal(addr, &zero, true); } static void local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { - addr->port = 0; addr->family = skc->skc_family; + addr->port = htons(skc->skc_num); if (addr->family == AF_INET) addr->addr.s_addr = skc->skc_rcv_saddr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -130,7 +131,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); local_address(skc, &cur); - if (addresses_equal(&cur, saddr, false)) + if (addresses_equal(&cur, saddr, saddr->port)) return true; } @@ -196,11 +197,46 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos) return ret; } +unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->add_addr_signal_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max); + +unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->add_addr_accept_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max); + +unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->subflows_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max); + +static unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->local_addr_max); +} + static void check_work_pending(struct mptcp_sock *msk) { - if (msk->pm.add_addr_signaled == msk->pm.add_addr_signal_max && - (msk->pm.local_addr_used == msk->pm.local_addr_max || - msk->pm.subflows == msk->pm.subflows_max)) + if (msk->pm.add_addr_signaled == mptcp_pm_get_add_addr_signal_max(msk) && + (msk->pm.local_addr_used == mptcp_pm_get_local_addr_max(msk) || + msk->pm.subflows == mptcp_pm_get_subflows_max(msk))) WRITE_ONCE(msk->pm.work_pending, false); } @@ -211,13 +247,34 @@ lookup_anno_list_by_saddr(struct mptcp_sock *msk, struct mptcp_pm_add_entry *entry; list_for_each_entry(entry, &msk->pm.anno_list, list) { - if (addresses_equal(&entry->addr, addr, false)) + if (addresses_equal(&entry->addr, addr, true)) return entry; } return NULL; } +bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk) +{ + struct mptcp_pm_add_entry *entry; + struct mptcp_addr_info saddr; + bool ret = false; + + local_address((struct sock_common *)sk, &saddr); + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.anno_list, list) { + if (addresses_equal(&entry->addr, &saddr, true)) { + ret = true; + goto out; + } + } + +out: + spin_unlock_bh(&msk->pm.lock); + return ret; +} + static void mptcp_pm_add_timer(struct timer_list *timer) { struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer); @@ -327,17 +384,24 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *local; + unsigned int add_addr_signal_max; + unsigned int local_addr_max; struct pm_nl_pernet *pernet; + unsigned int subflows_max; pernet = net_generic(sock_net(sk), pm_nl_pernet_id); + add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk); + local_addr_max = mptcp_pm_get_local_addr_max(msk); + subflows_max = mptcp_pm_get_subflows_max(msk); + pr_debug("local %d:%d signal %d:%d subflows %d:%d\n", - msk->pm.local_addr_used, msk->pm.local_addr_max, - msk->pm.add_addr_signaled, msk->pm.add_addr_signal_max, - msk->pm.subflows, msk->pm.subflows_max); + msk->pm.local_addr_used, local_addr_max, + msk->pm.add_addr_signaled, add_addr_signal_max, + msk->pm.subflows, subflows_max); /* check first for announce */ - if (msk->pm.add_addr_signaled < msk->pm.add_addr_signal_max) { + if (msk->pm.add_addr_signaled < add_addr_signal_max) { local = select_signal_address(pernet, msk->pm.add_addr_signaled); @@ -349,15 +413,15 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) } } else { /* pick failed, avoid fourther attempts later */ - msk->pm.local_addr_used = msk->pm.add_addr_signal_max; + msk->pm.local_addr_used = add_addr_signal_max; } check_work_pending(msk); } /* check if should create a new subflow */ - if (msk->pm.local_addr_used < msk->pm.local_addr_max && - msk->pm.subflows < msk->pm.subflows_max) { + if (msk->pm.local_addr_used < local_addr_max && + msk->pm.subflows < subflows_max) { local = select_local_address(pernet, msk); if (local) { struct mptcp_addr_info remote = { 0 }; @@ -373,7 +437,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) } /* lookup failed, avoid fourther attempts later */ - msk->pm.local_addr_used = msk->pm.local_addr_max; + msk->pm.local_addr_used = local_addr_max; check_work_pending(msk); } } @@ -391,17 +455,22 @@ void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; + unsigned int add_addr_accept_max; struct mptcp_addr_info remote; struct mptcp_addr_info local; + unsigned int subflows_max; bool use_port = false; + add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); + subflows_max = mptcp_pm_get_subflows_max(msk); + pr_debug("accepted %d:%d remote family %d", - msk->pm.add_addr_accepted, msk->pm.add_addr_accept_max, + msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); msk->pm.add_addr_accepted++; msk->pm.subflows++; - if (msk->pm.add_addr_accepted >= msk->pm.add_addr_accept_max || - msk->pm.subflows >= msk->pm.subflows_max) + if (msk->pm.add_addr_accepted >= add_addr_accept_max || + msk->pm.subflows >= subflows_max) WRITE_ONCE(msk->pm.accept_addr, false); /* connect to the specified remote address, using whatever @@ -427,8 +496,7 @@ void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - if (!mptcp_pm_should_add_signal_ipv6(msk) && - !mptcp_pm_should_add_signal_port(msk)) + if (!mptcp_pm_should_add_signal(msk)) return; __mptcp_flush_join_list(msk); @@ -438,10 +506,9 @@ void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) u8 add_addr; spin_unlock_bh(&msk->pm.lock); - if (mptcp_pm_should_add_signal_ipv6(msk)) - pr_debug("send ack for add_addr6"); - if (mptcp_pm_should_add_signal_port(msk)) - pr_debug("send ack for add_addr_port"); + pr_debug("send ack for add_addr%s%s", + mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "", + mptcp_pm_should_add_signal_port(msk) ? " [port]" : ""); lock_sock(ssk); tcp_send_ack(ssk); @@ -572,6 +639,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry) { struct mptcp_pm_addr_entry *cur; + unsigned int addr_max; int ret = -EINVAL; spin_lock_bh(&pernet->lock); @@ -614,10 +682,14 @@ find_next: if (entry->addr.id > pernet->next_id) pernet->next_id = entry->addr.id; - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) - pernet->add_addr_signal_max++; - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - pernet->local_addr_max++; + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + addr_max = pernet->add_addr_signal_max; + WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1); + } + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + addr_max = pernet->local_addr_max; + WRITE_ONCE(pernet->local_addr_max, addr_max + 1); + } pernet->addrs++; list_add_tail_rcu(&entry->list, &pernet->local_addr_list); @@ -628,6 +700,53 @@ out: return ret; } +static int mptcp_pm_nl_create_listen_socket(struct sock *sk, + struct mptcp_pm_addr_entry *entry) +{ + struct sockaddr_storage addr; + struct mptcp_sock *msk; + struct socket *ssock; + int backlog = 1024; + int err; + + err = sock_create_kern(sock_net(sk), entry->addr.family, + SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk); + if (err) + return err; + + msk = mptcp_sk(entry->lsk->sk); + if (!msk) { + err = -EINVAL; + goto out; + } + + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + err = -EINVAL; + goto out; + } + + mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); + err = kernel_bind(ssock, (struct sockaddr *)&addr, + sizeof(struct sockaddr_in)); + if (err) { + pr_warn("kernel_bind error, err=%d", err); + goto out; + } + + err = kernel_listen(ssock, backlog); + if (err) { + pr_warn("kernel_listen error, err=%d", err); + goto out; + } + + return 0; + +out: + sock_release(entry->lsk); + return err; +} + int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) { struct mptcp_pm_addr_entry *entry; @@ -654,7 +773,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { - if (addresses_equal(&entry->addr, &skc_local, false)) { + if (addresses_equal(&entry->addr, &skc_local, entry->addr.port)) { ret = entry->addr.id; break; } @@ -672,6 +791,8 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->addr.ifindex = 0; entry->addr.flags = 0; entry->addr.id = 0; + entry->addr.port = 0; + entry->lsk = NULL; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) kfree(entry); @@ -682,19 +803,12 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) void mptcp_pm_nl_data_init(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; - struct pm_nl_pernet *pernet; bool subflows; - pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); - - pm->add_addr_signal_max = READ_ONCE(pernet->add_addr_signal_max); - pm->add_addr_accept_max = READ_ONCE(pernet->add_addr_accept_max); - pm->local_addr_max = READ_ONCE(pernet->local_addr_max); - pm->subflows_max = READ_ONCE(pernet->subflows_max); - subflows = !!pm->subflows_max; - WRITE_ONCE(pm->work_pending, (!!pm->local_addr_max && subflows) || - !!pm->add_addr_signal_max); - WRITE_ONCE(pm->accept_addr, !!pm->add_addr_accept_max && subflows); + subflows = !!mptcp_pm_get_subflows_max(msk); + WRITE_ONCE(pm->work_pending, (!!mptcp_pm_get_local_addr_max(msk) && subflows) || + !!mptcp_pm_get_add_addr_signal_max(msk)); + WRITE_ONCE(pm->accept_addr, !!mptcp_pm_get_add_addr_accept_max(msk) && subflows); WRITE_ONCE(pm->accept_subflow, subflows); } @@ -797,6 +911,9 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->addr.flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) + entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); + return 0; } @@ -805,6 +922,31 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) return net_generic(genl_info_net(info), pm_nl_pernet_id); } +static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) +{ + struct mptcp_sock *msk; + long s_slot = 0, s_num = 0; + + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { + struct sock *sk = (struct sock *)msk; + + if (!READ_ONCE(msk->fully_established)) + goto next; + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + mptcp_pm_create_subflow_or_signal_addr(msk); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + +next: + sock_put(sk); + cond_resched(); + } + + return 0; +} + static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -823,13 +965,25 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) } *entry = addr; + if (entry->addr.port) { + ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); + if (ret) { + GENL_SET_ERR_MSG(info, "create listen socket error"); + kfree(entry); + return ret; + } + } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) { GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); + if (entry->lsk) + sock_release(entry->lsk); kfree(entry); return ret; } + mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk)); + return 0; } @@ -907,11 +1061,44 @@ next: return 0; } +struct addr_entry_release_work { + struct rcu_work rwork; + struct mptcp_pm_addr_entry *entry; +}; + +static void mptcp_pm_release_addr_entry(struct work_struct *work) +{ + struct addr_entry_release_work *w; + struct mptcp_pm_addr_entry *entry; + + w = container_of(to_rcu_work(work), struct addr_entry_release_work, rwork); + entry = w->entry; + if (entry) { + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); + } + kfree(w); +} + +static void mptcp_pm_free_addr_entry(struct mptcp_pm_addr_entry *entry) +{ + struct addr_entry_release_work *w; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + INIT_RCU_WORK(&w->rwork, mptcp_pm_release_addr_entry); + w->entry = entry; + queue_rcu_work(system_wq, &w->rwork); + } +} + static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; + unsigned int addr_max; int ret; ret = mptcp_pm_parse_addr(attr, info, false, &addr); @@ -925,10 +1112,14 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); return -EINVAL; } - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) - pernet->add_addr_signal_max--; - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - pernet->local_addr_max--; + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + addr_max = pernet->add_addr_signal_max; + WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1); + } + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + addr_max = pernet->local_addr_max; + WRITE_ONCE(pernet->local_addr_max, addr_max - 1); + } pernet->addrs--; list_del_rcu(&entry->list); @@ -936,7 +1127,7 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); - kfree_rcu(entry, rcu); + mptcp_pm_free_addr_entry(entry); return ret; } @@ -950,15 +1141,15 @@ static void __flush_addrs(struct net *net, struct list_head *list) struct mptcp_pm_addr_entry, list); mptcp_nl_remove_subflow_and_signal_addr(net, &cur->addr); list_del_rcu(&cur->list); - kfree_rcu(cur, rcu); + mptcp_pm_free_addr_entry(cur); } } static void __reset_counters(struct pm_nl_pernet *pernet) { - pernet->add_addr_signal_max = 0; - pernet->add_addr_accept_max = 0; - pernet->local_addr_max = 0; + WRITE_ONCE(pernet->add_addr_signal_max, 0); + WRITE_ONCE(pernet->add_addr_accept_max, 0); + WRITE_ONCE(pernet->local_addr_max, 0); pernet->addrs = 0; } @@ -989,6 +1180,8 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb, if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family)) goto nla_put_failure; + if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_PORT, ntohs(addr->port))) + goto nla_put_failure; if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->addr.flags)) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a033bf9c26ee..1405e146dd7c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -52,7 +52,7 @@ static struct net_device mptcp_napi_dev; * completed yet or has failed, return the subflow socket. * Otherwise return NULL. */ -static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk) +struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk) { if (!msk->subflow || READ_ONCE(msk->can_ack)) return NULL; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 1460705aaad0..1cc7948a1826 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -60,7 +60,8 @@ #define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 24 #define TCPOLEN_MPTCP_PORT_LEN 4 #define TCPOLEN_MPTCP_RM_ADDR_BASE 4 -#define TCPOLEN_MPTCP_PRIO 4 +#define TCPOLEN_MPTCP_PRIO 3 +#define TCPOLEN_MPTCP_PRIO_ALIGN 4 #define TCPOLEN_MPTCP_FASTCLOSE 12 /* MPTCP MP_JOIN flags */ @@ -202,10 +203,6 @@ struct mptcp_pm_data { u8 add_addr_accepted; u8 local_addr_used; u8 subflows; - u8 add_addr_signal_max; - u8 add_addr_accept_max; - u8 local_addr_max; - u8 subflows_max; u8 status; u8 rm_id; }; @@ -541,11 +538,15 @@ void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); void mptcp_subflow_reset(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); +struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, const struct mptcp_addr_info *remote); int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); +void mptcp_info2sockaddr(const struct mptcp_addr_info *info, + struct sockaddr_storage *addr, + unsigned short family); static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) @@ -649,6 +650,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct mptcp_addr_info *addr, u8 bkup); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); +bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, struct mptcp_addr_info *addr); @@ -713,6 +715,9 @@ void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); +unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 586156281e5a..280da418d60b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -64,11 +64,23 @@ static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk) } /* validate received token and create truncated hmac and nonce for SYN-ACK */ -static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, - const struct sk_buff *skb) +static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req) { - struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_sock *msk = subflow_req->msk; u8 hmac[SHA256_DIGEST_SIZE]; + + get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); + + subflow_generate_hmac(msk->local_key, msk->remote_key, + subflow_req->local_nonce, + subflow_req->remote_nonce, hmac); + + subflow_req->thmac = get_unaligned_be64(hmac); +} + +static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_sock *msk; int local_id; @@ -85,13 +97,6 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, } subflow_req->local_id = local_id; - get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); - - subflow_generate_hmac(msk->local_key, msk->remote_key, - subflow_req->local_nonce, - subflow_req->remote_nonce, hmac); - - subflow_req->thmac = get_unaligned_be64(hmac); return msk; } @@ -115,6 +120,11 @@ static int __subflow_init_req(struct request_sock *req, const struct sock *sk_li return 0; } +static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk) +{ + return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport; +} + /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset @@ -181,12 +191,30 @@ again: subflow_req->remote_id = mp_opt.join_id; subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; - subflow_req->msk = subflow_token_join_request(req, skb); + subflow_req->msk = subflow_token_join_request(req); /* Can't fall back to TCP in this case. */ if (!subflow_req->msk) return -EPERM; + if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { + pr_debug("syn inet_sport=%d %d", + ntohs(inet_sk(sk_listener)->inet_sport), + ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); + if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { + sock_put((struct sock *)subflow_req->msk); + mptcp_token_destroy_request(req); + tcp_request_sock_ops.destructor(req); + subflow_req->msk = NULL; + subflow_req->mp_join = 0; + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); + return -EPERM; + } + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX); + } + + subflow_req_create_thmac(subflow_req); + if (unlikely(req->syncookie)) { if (mptcp_can_accept_new_subflow(subflow_req->msk)) subflow_init_req_cookie_join_save(subflow_req, skb); @@ -329,6 +357,11 @@ void mptcp_subflow_reset(struct sock *ssk) sock_put(sk); } +static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk) +{ + return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -395,6 +428,13 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + + if (subflow_use_different_dport(mptcp_sk(parent), sk)) { + pr_debug("synack inet_dport=%d %d", + ntohs(inet_sk(sk)->inet_dport), + ntohs(inet_sk(parent)->inet_dport)); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); + } } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); @@ -660,6 +700,17 @@ create_child: SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); tcp_rsk(req)->drop_req = true; + + if (subflow_use_different_sport(owner, sk)) { + pr_debug("ack inet_sport=%d %d", + ntohs(inet_sk(sk)->inet_sport), + ntohs(inet_sk((struct sock *)owner)->inet_sport)); + if (!mptcp_pm_sport_in_anno_list(owner, sk)) { + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); + goto out; + } + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); + } } } @@ -1084,9 +1135,9 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) } #endif -static void mptcp_info2sockaddr(const struct mptcp_addr_info *info, - struct sockaddr_storage *addr, - unsigned short family) +void mptcp_info2sockaddr(const struct mptcp_addr_info *info, + struct sockaddr_storage *addr, + unsigned short family) { memset(addr, 0, sizeof(*addr)); addr->ss_family = family; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 15c467f1a9dd..8d3aa97b52e7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5235,9 +5235,8 @@ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, kfree(elem); } -static int nft_set_elem_expr_clone(const struct nft_ctx *ctx, - struct nft_set *set, - struct nft_expr *expr_array[]) +int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_expr *expr_array[]) { struct nft_expr *expr; int err, i, k; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 0b053f75cd60..d164ef9e6843 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -295,6 +295,12 @@ static int nft_dynset_init(const struct nft_ctx *ctx, err = -EOPNOTSUPP; goto err_expr_free; } + } else if (set->num_exprs > 0) { + err = nft_set_elem_expr_clone(ctx, set, priv->expr_array); + if (err < 0) + return err; + + priv->num_exprs = set->num_exprs; } nft_set_ext_prepare(&priv->tmpl); @@ -306,8 +312,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, nft_dynset_ext_add_expr(priv); if (set->flags & NFT_SET_TIMEOUT) { - if (timeout || set->timeout) + if (timeout || set->timeout) { + nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT); nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION); + } } priv->timeout = timeout; @@ -376,22 +384,25 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) nf_jiffies64_to_msecs(priv->timeout), NFTA_DYNSET_PAD)) goto nla_put_failure; - if (priv->num_exprs == 1) { - if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr_array[0])) - goto nla_put_failure; - } else if (priv->num_exprs > 1) { - struct nlattr *nest; - - nest = nla_nest_start_noflag(skb, NFTA_DYNSET_EXPRESSIONS); - if (!nest) - goto nla_put_failure; - - for (i = 0; i < priv->num_exprs; i++) { - if (nft_expr_dump(skb, NFTA_LIST_ELEM, - priv->expr_array[i])) + if (priv->set->num_exprs == 0) { + if (priv->num_exprs == 1) { + if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, + priv->expr_array[0])) goto nla_put_failure; + } else if (priv->num_exprs > 1) { + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, NFTA_DYNSET_EXPRESSIONS); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < priv->num_exprs; i++) { + if (nft_expr_dump(skb, NFTA_LIST_ELEM, + priv->expr_array[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); } - nla_nest_end(skb, nest); } if (nla_put_be32(skb, NFTA_DYNSET_FLAGS, htonl(flags))) goto nla_put_failure; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 640906359c22..722f7ef891e1 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -852,6 +852,7 @@ static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) if (!dev->polling) { device_unlock(&dev->dev); + nfc_put_device(dev); return -EINVAL; } diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 955c195ae14b..9c7eb8455ba8 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -105,7 +105,7 @@ static int rawsock_connect(struct socket *sock, struct sockaddr *_addr, if (addr->target_idx > dev->target_next_idx - 1 || addr->target_idx < dev->target_next_idx - dev->n_targets) { rc = -EINVAL; - goto error; + goto put_dev; } rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol); diff --git a/net/packet/internal.h b/net/packet/internal.h index baafc3f3fa25..5f61e59ebbff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -139,7 +139,7 @@ struct packet_sock { atomic_t tp_drops ____cacheline_aligned_in_smp; }; -static struct packet_sock *pkt_sk(struct sock *sk) +static inline struct packet_sock *pkt_sk(struct sock *sk) { return (struct packet_sock *)sk; } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 1d0afb1dd77b..6f1a50d50d06 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -565,6 +565,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args, if (args->nr_local == 0) return -EINVAL; + if (args->nr_local > UIO_MAXIOV) + return -EMSGSIZE; + iov->iov = kcalloc(args->nr_local, sizeof(struct rds_iovec), GFP_KERNEL); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0a2f4817ec6c..41671af6b33f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -990,7 +990,7 @@ static int __init af_rxrpc_init(void) goto error_security; } - ret = register_pernet_subsys(&rxrpc_net_ops); + ret = register_pernet_device(&rxrpc_net_ops); if (ret) goto error_pernet; @@ -1035,7 +1035,7 @@ error_key_type: error_sock: proto_unregister(&rxrpc_proto); error_proto: - unregister_pernet_subsys(&rxrpc_net_ops); + unregister_pernet_device(&rxrpc_net_ops); error_pernet: rxrpc_exit_security(); error_security: @@ -1057,7 +1057,7 @@ static void __exit af_rxrpc_exit(void) unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); - unregister_pernet_subsys(&rxrpc_net_ops); + unregister_pernet_device(&rxrpc_net_ops); ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 382add72c66f..1ae90fb97936 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -197,6 +197,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->peer_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_peer *peer = b->peer_backlog[tail]; + rxrpc_put_local(peer->local); kfree(peer); tail = (tail + 1) & (size - 1); } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b3442078aabc..f0a0aa125b00 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -183,6 +183,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, IP_CT_ESTABLISHED_REPLY; /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; + entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; act_ct_labels = entry->ct_metadata.labels; ct_labels = nf_ct_labels_find(ct); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 4a9297a89c77..caf7643e9c83 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -291,9 +291,11 @@ static u16 fl_ct_info_to_flower_map[] = { [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_RELATED, [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED, + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_RELATED, + TCA_FLOWER_KEY_CT_FLAGS_RELATED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_NEW, }; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 4ecc2a959567..5f42aa5fc612 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -29,6 +29,7 @@ #include <linux/uaccess.h> #include <linux/hashtable.h> +#include "auth_gss_internal.h" #include "../netns.h" #include <trace/events/rpcgss.h> @@ -125,35 +126,6 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx) clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags); } -static const void * -simple_get_bytes(const void *p, const void *end, void *res, size_t len) -{ - const void *q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - memcpy(res, p, len); - return q; -} - -static inline const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) -{ - const void *q; - unsigned int len; - - p = simple_get_bytes(p, end, &len, sizeof(len)); - if (IS_ERR(p)) - return p; - q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - dest->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(dest->data == NULL)) - return ERR_PTR(-ENOMEM); - dest->len = len; - return q; -} - static struct gss_cl_ctx * gss_cred_get_ctx(struct rpc_cred *cred) { diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h new file mode 100644 index 000000000000..f6d9631bd9d0 --- /dev/null +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * linux/net/sunrpc/auth_gss/auth_gss_internal.h + * + * Internal definitions for RPCSEC_GSS client authentication + * + * Copyright (c) 2000 The Regents of the University of Michigan. + * All rights reserved. + * + */ +#include <linux/err.h> +#include <linux/string.h> +#include <linux/sunrpc/xdr.h> + +static inline const void * +simple_get_bytes(const void *p, const void *end, void *res, size_t len) +{ + const void *q = (const void *)((const char *)p + len); + if (unlikely(q > end || q < p)) + return ERR_PTR(-EFAULT); + memcpy(res, p, len); + return q; +} + +static inline const void * +simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) +{ + const void *q; + unsigned int len; + + p = simple_get_bytes(p, end, &len, sizeof(len)); + if (IS_ERR(p)) + return p; + q = (const void *)((const char *)p + len); + if (unlikely(q > end || q < p)) + return ERR_PTR(-EFAULT); + if (len) { + dest->data = kmemdup(p, len, GFP_NOFS); + if (unlikely(dest->data == NULL)) + return ERR_PTR(-ENOMEM); + } else + dest->data = NULL; + dest->len = len; + return q; +} diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index ae9acf3a7389..1c092b05c2bb 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -21,6 +21,8 @@ #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/gss_krb5_enctypes.h> +#include "auth_gss_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -143,35 +145,6 @@ get_gss_krb5_enctype(int etype) return NULL; } -static const void * -simple_get_bytes(const void *p, const void *end, void *res, int len) -{ - const void *q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - memcpy(res, p, len); - return q; -} - -static const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res) -{ - const void *q; - unsigned int len; - - p = simple_get_bytes(p, end, &len, sizeof(len)); - if (IS_ERR(p)) - return p; - q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - res->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(res->data == NULL)) - return ERR_PTR(-ENOMEM); - res->len = len; - return q; -} - static inline const void * get_key(const void *p, const void *end, struct krb5_ctx *ctx, struct crypto_sync_skcipher **res) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 855a10feef3d..94113ca29dcf 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -388,9 +388,10 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, extack = switchdev_notifier_info_to_extack(&port_obj_info->info); if (check_cb(dev)) { - /* This flag is only checked if the return value is success. */ - port_obj_info->handled = true; - return add_cb(dev, port_obj_info->obj, extack); + err = add_cb(dev, port_obj_info->obj, extack); + if (err != -EOPNOTSUPP) + port_obj_info->handled = true; + return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the @@ -441,9 +442,10 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, int err = -EOPNOTSUPP; if (check_cb(dev)) { - /* This flag is only checked if the return value is success. */ - port_obj_info->handled = true; - return del_cb(dev, port_obj_info->obj); + err = del_cb(dev, port_obj_info->obj); + if (err != -EOPNOTSUPP) + port_obj_info->handled = true; + return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the @@ -493,8 +495,10 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, int err = -EOPNOTSUPP; if (check_cb(dev)) { - port_attr_info->handled = true; - return set_cb(dev, port_attr_info->attr); + err = set_cb(dev, port_attr_info->attr); + if (err != -EOPNOTSUPP) + port_attr_info->handled = true; + return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b12d3a322242..6894f21dc147 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1014,9 +1014,12 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } else if (sock->type == SOCK_STREAM) { - const struct vsock_transport *transport = vsk->transport; + const struct vsock_transport *transport; + lock_sock(sk); + transport = vsk->transport; + /* Listening sockets that have connections in their accept * queue can be read. */ @@ -1099,10 +1102,11 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, err = 0; sk = sock->sk; vsk = vsock_sk(sk); - transport = vsk->transport; lock_sock(sk); + transport = vsk->transport; + err = vsock_auto_bind(vsk); if (err) goto out; @@ -1561,10 +1565,11 @@ static int vsock_stream_setsockopt(struct socket *sock, err = 0; sk = sock->sk; vsk = vsock_sk(sk); - transport = vsk->transport; lock_sock(sk); + transport = vsk->transport; + switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: COPY_IN(val); @@ -1697,7 +1702,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, sk = sock->sk; vsk = vsock_sk(sk); - transport = vsk->transport; total_written = 0; err = 0; @@ -1706,6 +1710,8 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); + transport = vsk->transport; + /* Callers should not provide a destination with stream sockets. */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; @@ -1840,11 +1846,12 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, sk = sock->sk; vsk = vsock_sk(sk); - transport = vsk->transport; err = 0; lock_sock(sk); + transport = vsk->transport; + if (!transport || sk->sk_state != TCP_ESTABLISHED) { /* Recvmsg is supposed to return 0 if a peer performs an * orderly shutdown. Differentiate between that case and when a diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 69102fda9ebd..76a80a41615b 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -896,8 +896,9 @@ out: int call_commit_handler(struct net_device *dev) { #ifdef CONFIG_WIRELESS_EXT - if ((netif_running(dev)) && - (dev->wireless_handlers->standard[0] != NULL)) + if (netif_running(dev) && + dev->wireless_handlers && + dev->wireless_handlers->standard[0]) /* Call the commit handler on the driver */ return dev->wireless_handlers->standard[0](dev, NULL, NULL, NULL); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index be6351e3f3cd..1158cd0311d7 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -660,7 +660,7 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0; - if (async && x->repl->recheck(x, skb, seq)) { + if (x->repl->recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d622c2548d22..b74f28cabe24 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -793,15 +793,22 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a, const xfrm_address_t *b, u8 prefixlen, u16 family) { + u32 ma, mb, mask; unsigned int pdw, pbi; int delta = 0; switch (family) { case AF_INET: - if (sizeof(long) == 4 && prefixlen == 0) - return ntohl(a->a4) - ntohl(b->a4); - return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) - - (ntohl(b->a4) & ((~0UL << (32 - prefixlen)))); + if (prefixlen == 0) + return 0; + mask = ~0U << (32 - prefixlen); + ma = ntohl(a->a4) & mask; + mb = ntohl(b->a4) & mask; + if (ma < mb) + delta = -1; + else if (ma > mb) + delta = 1; + break; case AF_INET6: pdw = prefixlen >> 5; pbi = prefixlen & 0x1f; @@ -812,10 +819,13 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a, return delta; } if (pbi) { - u32 mask = ~0u << (32 - pbi); - - delta = (ntohl(a->a6[pdw]) & mask) - - (ntohl(b->a6[pdw]) & mask); + mask = ~0U << (32 - pbi); + ma = ntohl(a->a6[pdw]) & mask; + mb = ntohl(b->a6[pdw]) & mask; + if (ma < mb) + delta = -1; + else if (ma > mb) + delta = 1; } break; default: @@ -3078,8 +3088,8 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, xflo.flags = flags; /* To accelerate a bit... */ - if ((dst_orig->flags & DST_NOXFRM) || - !net->xfrm.policy_count[XFRM_POLICY_OUT]) + if (!if_id && ((dst_orig->flags & DST_NOXFRM) || + !net->xfrm.policy_count[XFRM_POLICY_OUT])) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 9f3f8e953ff0..c4aac703dc22 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -382,8 +382,8 @@ retry: continue; /* - * The 'deps' array includes maximum three dependencies - * to SNDRV_PCM_HW_PARAM_XXXs for this rule. The fourth + * The 'deps' array includes maximum four dependencies + * to SNDRV_PCM_HW_PARAM_XXXs for this rule. The fifth * member of this array is a sentinel and should be * negative value. * diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index 11554d0412f0..1b8409ec2c97 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -611,7 +611,8 @@ snd_seq_oss_synth_make_info(struct seq_oss_devinfo *dp, int dev, struct synth_in if (info->is_midi) { struct midi_info minf; - snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf); + if (snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf)) + return -ENXIO; inf->synth_type = SYNTH_TYPE_MIDI; inf->synth_subtype = 0; inf->nr_voices = 16; diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 6a0d070c60c9..c45686172517 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -307,6 +307,10 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0xa0c8, }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x43c8, + }, #endif /* Elkhart Lake */ diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 687216e74526..eec1775dfffe 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2934,7 +2934,7 @@ static void hda_call_codec_resume(struct hda_codec *codec) snd_hdac_leave_pm(&codec->core); } -static int hda_codec_suspend(struct device *dev) +static int hda_codec_runtime_suspend(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); unsigned int state; @@ -2953,7 +2953,7 @@ static int hda_codec_suspend(struct device *dev) return 0; } -static int hda_codec_resume(struct device *dev) +static int hda_codec_runtime_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); @@ -2968,16 +2968,6 @@ static int hda_codec_resume(struct device *dev) return 0; } -static int hda_codec_runtime_suspend(struct device *dev) -{ - return hda_codec_suspend(dev); -} - -static int hda_codec_runtime_resume(struct device *dev) -{ - return hda_codec_resume(dev); -} - #endif /* CONFIG_PM */ #ifdef CONFIG_PM_SLEEP @@ -2998,31 +2988,31 @@ static void hda_codec_pm_complete(struct device *dev) static int hda_codec_pm_suspend(struct device *dev) { dev->power.power_state = PMSG_SUSPEND; - return hda_codec_suspend(dev); + return pm_runtime_force_suspend(dev); } static int hda_codec_pm_resume(struct device *dev) { dev->power.power_state = PMSG_RESUME; - return hda_codec_resume(dev); + return pm_runtime_force_resume(dev); } static int hda_codec_pm_freeze(struct device *dev) { dev->power.power_state = PMSG_FREEZE; - return hda_codec_suspend(dev); + return pm_runtime_force_suspend(dev); } static int hda_codec_pm_thaw(struct device *dev) { dev->power.power_state = PMSG_THAW; - return hda_codec_resume(dev); + return pm_runtime_force_resume(dev); } static int hda_codec_pm_restore(struct device *dev) { dev->power.power_state = PMSG_RESTORE; - return hda_codec_resume(dev); + return pm_runtime_force_resume(dev); } #endif /* CONFIG_PM_SLEEP */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e4dd2ff5e473..5a50d3a46445 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2484,6 +2484,9 @@ static const struct pci_device_id azx_ids[] = { /* CometLake-S */ { PCI_DEVICE(0x8086, 0xa3f0), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* CometLake-R */ + { PCI_DEVICE(0x8086, 0xf0c8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Icelake */ { PCI_DEVICE(0x8086, 0x34c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, @@ -2507,6 +2510,9 @@ static const struct pci_device_id azx_ids[] = { /* Alderlake-S */ { PCI_DEVICE(0x8086, 0x7ad0), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Alderlake-P */ + { PCI_DEVICE(0x8086, 0x51c8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Elkhart Lake */ { PCI_DEVICE(0x8086, 0x4b55), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 74d246a0dc6d..97adff0cbcab 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4346,6 +4346,7 @@ HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi), +HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index dd82ff2bd5d6..290645516313 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6371,6 +6371,7 @@ enum { ALC256_FIXUP_HP_HEADSET_MIC, ALC236_FIXUP_DELL_AIO_HEADSET_MIC, ALC282_FIXUP_ACER_DISABLE_LINEOUT, + ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST, }; static const struct hda_fixup alc269_fixups[] = { @@ -7808,6 +7809,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE }, + [ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC255_FIXUP_ACER_MIC_NO_PRESENCE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7826,6 +7833,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { 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, 0x1094, "Acer Aspire E5-575T", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST), 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, 0x1166, "Acer Veriton N4640G", ALC269_FIXUP_LIFEBOOK), @@ -7998,6 +8006,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x1982, "ASUS B1400CEPE", ALC256_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index 0ab40a8a68fb..a5c1a2c4eae4 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -113,6 +113,7 @@ static struct via_spec *via_new_spec(struct hda_codec *codec) spec->codec_type = VT1708S; spec->gen.indep_hp = 1; spec->gen.keep_eapd_on = 1; + spec->gen.dac_min_mute = 1; spec->gen.pcm_playback_hook = via_playback_pcm_hook; spec->gen.add_stereo_mix_input = HDA_HINT_STEREO_MIX_AUTO; codec->power_save_node = 1; @@ -1042,7 +1043,7 @@ static const struct hda_fixup via_fixups[] = { static const struct snd_pci_quirk vt2002p_fixups[] = { SND_PCI_QUIRK(0x1043, 0x1487, "Asus G75", VIA_FIXUP_ASUS_G75), SND_PCI_QUIRK(0x1043, 0x8532, "Asus X202E", VIA_FIXUP_INTMIC_BOOST), - SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", VIA_FIXUP_POWER_SAVE), + SND_PCI_QUIRK_VENDOR(0x1558, "Clevo", VIA_FIXUP_POWER_SAVE), {} }; diff --git a/sound/soc/amd/renoir/rn-pci-acp3x.c b/sound/soc/amd/renoir/rn-pci-acp3x.c index deca8c7a0e87..050a61fe9693 100644 --- a/sound/soc/amd/renoir/rn-pci-acp3x.c +++ b/sound/soc/amd/renoir/rn-pci-acp3x.c @@ -165,10 +165,24 @@ static int rn_acp_deinit(void __iomem *acp_base) static const struct dmi_system_id rn_acp_quirk_table[] = { { - /* Lenovo IdeaPad Flex 5 14ARE05, IdeaPad 5 15ARE05 */ + /* Lenovo IdeaPad S340-14API */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_BOARD_NAME, "LNVNB161216"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "81NB"), + } + }, + { + /* Lenovo IdeaPad Flex 5 14ARE05 */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "81X2"), + } + }, + { + /* Lenovo IdeaPad 5 15ARE05 */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "81YQ"), } }, { diff --git a/sound/soc/codecs/ak4458.c b/sound/soc/codecs/ak4458.c index 1010c9ee2e83..472caad17012 100644 --- a/sound/soc/codecs/ak4458.c +++ b/sound/soc/codecs/ak4458.c @@ -595,18 +595,10 @@ static struct snd_soc_dai_driver ak4497_dai = { .ops = &ak4458_dai_ops, }; -static void ak4458_power_off(struct ak4458_priv *ak4458) +static void ak4458_reset(struct ak4458_priv *ak4458, bool active) { if (ak4458->reset_gpiod) { - gpiod_set_value_cansleep(ak4458->reset_gpiod, 0); - usleep_range(1000, 2000); - } -} - -static void ak4458_power_on(struct ak4458_priv *ak4458) -{ - if (ak4458->reset_gpiod) { - gpiod_set_value_cansleep(ak4458->reset_gpiod, 1); + gpiod_set_value_cansleep(ak4458->reset_gpiod, active); usleep_range(1000, 2000); } } @@ -620,7 +612,7 @@ static int ak4458_init(struct snd_soc_component *component) if (ak4458->mute_gpiod) gpiod_set_value_cansleep(ak4458->mute_gpiod, 1); - ak4458_power_on(ak4458); + ak4458_reset(ak4458, false); ret = snd_soc_component_update_bits(component, AK4458_00_CONTROL1, 0x80, 0x80); /* ACKS bit = 1; 10000000 */ @@ -650,7 +642,7 @@ static void ak4458_remove(struct snd_soc_component *component) { struct ak4458_priv *ak4458 = snd_soc_component_get_drvdata(component); - ak4458_power_off(ak4458); + ak4458_reset(ak4458, true); } #ifdef CONFIG_PM @@ -660,7 +652,7 @@ static int __maybe_unused ak4458_runtime_suspend(struct device *dev) regcache_cache_only(ak4458->regmap, true); - ak4458_power_off(ak4458); + ak4458_reset(ak4458, true); if (ak4458->mute_gpiod) gpiod_set_value_cansleep(ak4458->mute_gpiod, 0); @@ -685,8 +677,8 @@ static int __maybe_unused ak4458_runtime_resume(struct device *dev) if (ak4458->mute_gpiod) gpiod_set_value_cansleep(ak4458->mute_gpiod, 1); - ak4458_power_off(ak4458); - ak4458_power_on(ak4458); + ak4458_reset(ak4458, true); + ak4458_reset(ak4458, false); regcache_cache_only(ak4458->regmap, false); regcache_mark_dirty(ak4458->regmap); diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index d5fcc4db8284..0f3ac22f2cf8 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -717,7 +717,7 @@ static int hdmi_codec_set_jack(struct snd_soc_component *component, void *data) { struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component); - int ret = -EOPNOTSUPP; + int ret = -ENOTSUPP; if (hcp->hcd.ops->hook_plugged_cb) { hcp->jack = jack; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index dec8716aa8ef..985b2dcecf13 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -2031,11 +2031,14 @@ static struct wm_coeff_ctl *wm_adsp_get_ctl(struct wm_adsp *dsp, unsigned int alg) { struct wm_coeff_ctl *pos, *rslt = NULL; + const char *fw_txt = wm_adsp_fw_text[dsp->fw]; list_for_each_entry(pos, &dsp->ctl_list, list) { if (!pos->subname) continue; if (strncmp(pos->subname, name, pos->subname_len) == 0 && + strncmp(pos->fw_name, fw_txt, + SNDRV_CTL_ELEM_ID_NAME_MAXLEN) == 0 && pos->alg_region.alg == alg && pos->alg_region.type == type) { rslt = pos; diff --git a/sound/soc/fsl/imx-hdmi.c b/sound/soc/fsl/imx-hdmi.c index ede4a9ad1054..dbbb7618351c 100644 --- a/sound/soc/fsl/imx-hdmi.c +++ b/sound/soc/fsl/imx-hdmi.c @@ -90,7 +90,7 @@ static int imx_hdmi_init(struct snd_soc_pcm_runtime *rtd) } ret = snd_soc_component_set_jack(component, &data->hdmi_jack, NULL); - if (ret && ret != -EOPNOTSUPP) { + if (ret && ret != -ENOTSUPP) { dev_err(card->dev, "Can't set HDMI Jack %d\n", ret); return ret; } diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index ca968901ac96..6d0d6ef711e0 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -71,6 +71,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0A5E") + }, + .driver_data = (void *)(SOF_RT711_JD_SRC_JD2 | + SOF_RT715_DAI_ID_FIX | + SOF_SDW_FOUR_SPK), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "09C6") }, .driver_data = (void *)(SOF_RT711_JD_SRC_JD2 | diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index ae466cd59292..b824086203b9 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -3619,19 +3619,20 @@ static void skl_tplg_complete(struct snd_soc_component *component) list_for_each_entry(dobj, &component->dobj_list, list) { struct snd_kcontrol *kcontrol = dobj->control.kcontrol; - struct soc_enum *se = - (struct soc_enum *)kcontrol->private_value; - char **texts = dobj->control.dtexts; + struct soc_enum *se; + char **texts; char chan_text[4]; - if (dobj->type != SND_SOC_DOBJ_ENUM || - dobj->control.kcontrol->put != - skl_tplg_multi_config_set_dmic) + if (dobj->type != SND_SOC_DOBJ_ENUM || !kcontrol || + kcontrol->put != skl_tplg_multi_config_set_dmic) continue; + + se = (struct soc_enum *)kcontrol->private_value; + texts = dobj->control.dtexts; sprintf(chan_text, "c%d", mach->mach_params.dmic_num); for (i = 0; i < se->items; i++) { - struct snd_ctl_elem_value val; + struct snd_ctl_elem_value val = {}; if (strstr(texts[i], chan_text)) { val.value.enumerated.item[0] = i; diff --git a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c index 078e58f1ad0b..cfbd0c65c7a3 100644 --- a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c +++ b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c @@ -532,6 +532,7 @@ static struct snd_soc_dai_link mt8183_da7219_dai_links[] = { .dpcm_playback = 1, .ignore_suspend = 1, .be_hw_params_fixup = mt8183_i2s_hw_params_fixup, + .ignore = 1, .init = mt8183_da7219_max98357_hdmi_init, SND_SOC_DAILINK_REG(tdm), }, @@ -754,8 +755,10 @@ static int mt8183_da7219_max98357_dev_probe(struct platform_device *pdev) } } - if (hdmi_codec && strcmp(dai_link->name, "TDM") == 0) + if (hdmi_codec && strcmp(dai_link->name, "TDM") == 0) { dai_link->codecs->of_node = hdmi_codec; + dai_link->ignore = 0; + } if (!dai_link->platforms->name) dai_link->platforms->of_node = platform_node; diff --git a/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c b/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c index 8c8340854859..1ce3eddbee13 100644 --- a/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c +++ b/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c @@ -515,6 +515,7 @@ static struct snd_soc_dai_link mt8183_mt6358_ts3a227_dai_links[] = { .ignore_suspend = 1, .be_hw_params_fixup = mt8183_i2s_hw_params_fixup, .ops = &mt8183_mt6358_tdm_ops, + .ignore = 1, .init = mt8183_mt6358_ts3a227_max98357_hdmi_init, SND_SOC_DAILINK_REG(tdm), }, @@ -661,8 +662,10 @@ mt8183_mt6358_ts3a227_max98357_dev_probe(struct platform_device *pdev) SND_SOC_DAIFMT_CBM_CFM; } - if (hdmi_codec && strcmp(dai_link->name, "TDM") == 0) + if (hdmi_codec && strcmp(dai_link->name, "TDM") == 0) { dai_link->codecs->of_node = hdmi_codec; + dai_link->ignore = 0; + } if (!dai_link->platforms->name) dai_link->platforms->of_node = platform_node; diff --git a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c index 716fbb4126b5..ae2c748eb19c 100644 --- a/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c +++ b/sound/soc/mediatek/mt8192/mt8192-mt6359-rt1015-rt5682.c @@ -401,6 +401,53 @@ static const struct snd_soc_ops mt8192_mt6359_rt1015_rt5682_capture1_ops = { .startup = mt8192_mt6359_rt1015_rt5682_cap1_startup, }; +static int +mt8192_mt6359_rt5682_startup(struct snd_pcm_substream *substream) +{ + static const unsigned int channels[] = { + 1, 2 + }; + static const struct snd_pcm_hw_constraint_list constraints_channels = { + .count = ARRAY_SIZE(channels), + .list = channels, + .mask = 0, + }; + static const unsigned int rates[] = { + 48000 + }; + static const struct snd_pcm_hw_constraint_list constraints_rates = { + .count = ARRAY_SIZE(rates), + .list = rates, + .mask = 0, + }; + + struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); + struct snd_pcm_runtime *runtime = substream->runtime; + int ret; + + ret = snd_pcm_hw_constraint_list(runtime, 0, + SNDRV_PCM_HW_PARAM_CHANNELS, + &constraints_channels); + if (ret < 0) { + dev_err(rtd->dev, "hw_constraint_list channels failed\n"); + return ret; + } + + ret = snd_pcm_hw_constraint_list(runtime, 0, + SNDRV_PCM_HW_PARAM_RATE, + &constraints_rates); + if (ret < 0) { + dev_err(rtd->dev, "hw_constraint_list rate failed\n"); + return ret; + } + + return 0; +} + +static const struct snd_soc_ops mt8192_mt6359_rt5682_ops = { + .startup = mt8192_mt6359_rt5682_startup, +}; + /* FE */ SND_SOC_DAILINK_DEFS(playback1, DAILINK_COMP_ARRAY(COMP_CPU("DL1")), @@ -648,6 +695,7 @@ static struct snd_soc_dai_link mt8192_mt6359_dai_links[] = { SND_SOC_DPCM_TRIGGER_PRE}, .dynamic = 1, .dpcm_playback = 1, + .ops = &mt8192_mt6359_rt5682_ops, SND_SOC_DAILINK_REG(playback3), }, { @@ -721,6 +769,7 @@ static struct snd_soc_dai_link mt8192_mt6359_dai_links[] = { SND_SOC_DPCM_TRIGGER_PRE}, .dynamic = 1, .dpcm_capture = 1, + .ops = &mt8192_mt6359_rt5682_ops, SND_SOC_DAILINK_REG(capture2), }, { diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index c5e99c2d89c7..66b834312f33 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -344,8 +344,30 @@ int asoc_qcom_lpass_cpu_dai_probe(struct snd_soc_dai *dai) } EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_probe); +static int asoc_qcom_of_xlate_dai_name(struct snd_soc_component *component, + struct of_phandle_args *args, + const char **dai_name) +{ + struct lpass_data *drvdata = snd_soc_component_get_drvdata(component); + struct lpass_variant *variant = drvdata->variant; + int id = args->args[0]; + int ret = -EINVAL; + int i; + + for (i = 0; i < variant->num_dai; i++) { + if (variant->dai_driver[i].id == id) { + *dai_name = variant->dai_driver[i].name; + ret = 0; + break; + } + } + + return ret; +} + static const struct snd_soc_component_driver lpass_cpu_comp_driver = { .name = "lpass-cpu", + .of_xlate_dai_name = asoc_qcom_of_xlate_dai_name, }; static bool lpass_cpu_regmap_writeable(struct device *dev, unsigned int reg) diff --git a/sound/soc/qcom/lpass-ipq806x.c b/sound/soc/qcom/lpass-ipq806x.c index 92f98b4df47f..ef8a7984f232 100644 --- a/sound/soc/qcom/lpass-ipq806x.c +++ b/sound/soc/qcom/lpass-ipq806x.c @@ -131,7 +131,7 @@ static struct lpass_variant ipq806x_data = { .micmode = REG_FIELD_ID(0x0010, 4, 7, 5, 0x4), .micmono = REG_FIELD_ID(0x0010, 3, 3, 5, 0x4), .wssrc = REG_FIELD_ID(0x0010, 2, 2, 5, 0x4), - .bitwidth = REG_FIELD_ID(0x0010, 0, 0, 5, 0x4), + .bitwidth = REG_FIELD_ID(0x0010, 0, 1, 5, 0x4), .rdma_dyncclk = REG_FIELD_ID(0x6000, 12, 12, 4, 0x1000), .rdma_bursten = REG_FIELD_ID(0x6000, 11, 11, 4, 0x1000), diff --git a/sound/soc/qcom/lpass-lpaif-reg.h b/sound/soc/qcom/lpass-lpaif-reg.h index 405542832e99..baf72f124ea9 100644 --- a/sound/soc/qcom/lpass-lpaif-reg.h +++ b/sound/soc/qcom/lpass-lpaif-reg.h @@ -133,7 +133,7 @@ #define LPAIF_WRDMAPERCNT_REG(v, chan) LPAIF_WRDMA_REG_ADDR(v, 0x14, (chan)) #define LPAIF_INTFDMA_REG(v, chan, reg, dai_id) \ - ((v->dai_driver[dai_id].id == LPASS_DP_RX) ? \ + ((dai_id == LPASS_DP_RX) ? \ LPAIF_HDMI_RDMA##reg##_REG(v, chan) : \ LPAIF_RDMA##reg##_REG(v, chan)) diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index d1c248590f3a..0074b7f2dbc1 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -257,6 +257,9 @@ static int lpass_platform_pcmops_hw_params(struct snd_soc_component *component, break; case MI2S_PRIMARY: case MI2S_SECONDARY: + case MI2S_TERTIARY: + case MI2S_QUATERNARY: + case MI2S_QUINARY: ret = regmap_fields_write(dmactl->intf, id, LPAIF_DMACTL_AUDINTF(dma_port)); if (ret) { @@ -507,6 +510,9 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component, break; case MI2S_PRIMARY: case MI2S_SECONDARY: + case MI2S_TERTIARY: + case MI2S_QUATERNARY: + case MI2S_QUINARY: reg_irqclr = LPAIF_IRQCLEAR_REG(v, LPAIF_IRQ_PORT_HOST); val_irqclr = LPAIF_IRQ_ALL(ch); @@ -559,6 +565,9 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component, break; case MI2S_PRIMARY: case MI2S_SECONDARY: + case MI2S_TERTIARY: + case MI2S_QUATERNARY: + case MI2S_QUINARY: reg_irqen = LPAIF_IRQEN_REG(v, LPAIF_IRQ_PORT_HOST); val_mask = LPAIF_IRQ_ALL(ch); val_irqen = 0; @@ -655,6 +664,9 @@ static irqreturn_t lpass_dma_interrupt_handler( break; case MI2S_PRIMARY: case MI2S_SECONDARY: + case MI2S_TERTIARY: + case MI2S_QUATERNARY: + case MI2S_QUINARY: map = drvdata->lpaif_map; reg = LPAIF_IRQCLEAR_REG(v, LPAIF_IRQ_PORT_HOST); val = 0; diff --git a/sound/soc/qcom/lpass-sc7180.c b/sound/soc/qcom/lpass-sc7180.c index 85db650c2169..735c9dac28f2 100644 --- a/sound/soc/qcom/lpass-sc7180.c +++ b/sound/soc/qcom/lpass-sc7180.c @@ -20,7 +20,7 @@ #include "lpass.h" static struct snd_soc_dai_driver sc7180_lpass_cpu_dai_driver[] = { - [MI2S_PRIMARY] = { + { .id = MI2S_PRIMARY, .name = "Primary MI2S", .playback = { @@ -44,9 +44,7 @@ static struct snd_soc_dai_driver sc7180_lpass_cpu_dai_driver[] = { }, .probe = &asoc_qcom_lpass_cpu_dai_probe, .ops = &asoc_qcom_lpass_cpu_dai_ops, - }, - - [MI2S_SECONDARY] = { + }, { .id = MI2S_SECONDARY, .name = "Secondary MI2S", .playback = { @@ -60,8 +58,7 @@ static struct snd_soc_dai_driver sc7180_lpass_cpu_dai_driver[] = { }, .probe = &asoc_qcom_lpass_cpu_dai_probe, .ops = &asoc_qcom_lpass_cpu_dai_ops, - }, - [LPASS_DP_RX] = { + }, { .id = LPASS_DP_RX, .name = "Hdmi", .playback = { @@ -174,7 +171,7 @@ static struct lpass_variant sc7180_data = { .rdma_channels = 5, .hdmi_rdma_reg_base = 0x64000, .hdmi_rdma_reg_stride = 0x1000, - .hdmi_rdma_channels = 4, + .hdmi_rdma_channels = 3, .dmactl_audif_start = 1, .wrdma_reg_base = 0x18000, .wrdma_reg_stride = 0x1000, diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h index 0195372905ed..2d68af0da34d 100644 --- a/sound/soc/qcom/lpass.h +++ b/sound/soc/qcom/lpass.h @@ -12,7 +12,7 @@ #include <linux/compiler.h> #include <linux/platform_device.h> #include <linux/regmap.h> -#include <dt-bindings/sound/sc7180-lpass.h> +#include <dt-bindings/sound/qcom,lpass.h> #include "lpass-hdmi.h" #define LPASS_AHBIX_CLOCK_FREQUENCY 131072000 diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 950c45008e24..22e7b4c9115b 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -447,7 +447,7 @@ static void remove_dai(struct snd_soc_component *comp, { struct snd_soc_dai_driver *dai_drv = container_of(dobj, struct snd_soc_dai_driver, dobj); - struct snd_soc_dai *dai; + struct snd_soc_dai *dai, *_dai; if (pass != SOC_TPLG_PASS_PCM_DAI) return; @@ -455,9 +455,9 @@ static void remove_dai(struct snd_soc_component *comp, if (dobj->ops && dobj->ops->dai_unload) dobj->ops->dai_unload(comp, dobj); - for_each_component_dais(comp, dai) + for_each_component_dais_safe(comp, dai, _dai) if (dai->driver == dai_drv) - dai->driver = NULL; + snd_soc_unregister_dai(dai); list_del(&dobj->list); } @@ -902,7 +902,7 @@ static int soc_tplg_denum_create_values(struct soc_tplg *tplg, struct soc_enum * return -EINVAL; se->dobj.control.dvalues = devm_kcalloc(tplg->dev, le32_to_cpu(ec->items), - sizeof(u32), + sizeof(*se->dobj.control.dvalues), GFP_KERNEL); if (!se->dobj.control.dvalues) return -ENOMEM; @@ -1742,7 +1742,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, list_add(&dai_drv->dobj.list, &tplg->comp->dobj_list); /* register the DAI to the component */ - dai = devm_snd_soc_register_dai(tplg->dev, tplg->comp, dai_drv, false); + dai = snd_soc_register_dai(tplg->comp, dai_drv, false); if (!dai) return -ENOMEM; @@ -1750,6 +1750,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, ret = snd_soc_dapm_new_dai_widgets(dapm, dai); if (ret != 0) { dev_err(dai->dev, "Failed to create DAI widgets %d\n", ret); + snd_soc_unregister_dai(dai); return ret; } diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig index d306c370e5d1..4797a1cf8c80 100644 --- a/sound/soc/sof/intel/Kconfig +++ b/sound/soc/sof/intel/Kconfig @@ -355,7 +355,7 @@ config SND_SOC_SOF_HDA config SND_SOC_SOF_INTEL_SOUNDWIRE_LINK bool "SOF support for SoundWire" - depends on SOUNDWIRE && ACPI + depends on ACPI help This adds support for SoundWire with Sound Open Firmware for Intel(R) platforms. @@ -371,6 +371,7 @@ config SND_SOC_SOF_INTEL_SOUNDWIRE_LINK_BASELINE config SND_SOC_SOF_INTEL_SOUNDWIRE tristate + select SOUNDWIRE select SOUNDWIRE_INTEL help This option is not user-selectable but automagically handled by diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 6875fa570c2c..6744318de612 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -63,16 +63,18 @@ static int hda_codec_load_module(struct hda_codec *codec) } /* enable controller wake up event for all codecs with jack connectors */ -void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev) +void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev, bool enable) { struct hda_bus *hbus = sof_to_hbus(sdev); struct hdac_bus *bus = sof_to_bus(sdev); struct hda_codec *codec; unsigned int mask = 0; - list_for_each_codec(codec, hbus) - if (codec->jacktbl.used) - mask |= BIT(codec->core.addr); + if (enable) { + list_for_each_codec(codec, hbus) + if (codec->jacktbl.used) + mask |= BIT(codec->core.addr); + } snd_hdac_chip_updatew(bus, WAKEEN, STATESTS_INT_MASK, mask); } @@ -81,23 +83,18 @@ void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev) void hda_codec_jack_check(struct snd_sof_dev *sdev) { struct hda_bus *hbus = sof_to_hbus(sdev); - struct hdac_bus *bus = sof_to_bus(sdev); struct hda_codec *codec; - /* disable controller Wake Up event*/ - snd_hdac_chip_updatew(bus, WAKEEN, STATESTS_INT_MASK, 0); - list_for_each_codec(codec, hbus) /* * Wake up all jack-detecting codecs regardless whether an event * has been recorded in STATESTS */ if (codec->jacktbl.used) - schedule_delayed_work(&codec->jackpoll_work, - codec->jackpoll_interval); + pm_request_resume(&codec->core.dev); } #else -void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev) {} +void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev, bool enable) {} void hda_codec_jack_check(struct snd_sof_dev *sdev) {} #endif /* CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC */ EXPORT_SYMBOL_NS(hda_codec_jack_wake_enable, SND_SOC_SOF_HDA_AUDIO_CODEC); @@ -156,7 +153,8 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address, if (!hdev->bus->audio_component) { dev_dbg(sdev->dev, "iDisp hw present but no driver\n"); - goto error; + ret = -ENOENT; + goto out; } hda_priv->need_display_power = true; } @@ -173,24 +171,23 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address, * other return codes without modification */ if (ret == 0) - goto error; + ret = -ENOENT; } - return ret; - -error: - snd_hdac_ext_bus_device_exit(hdev); - return -ENOENT; - +out: + if (ret < 0) { + snd_hdac_device_unregister(hdev); + put_device(&hdev->dev); + } #else hdev = devm_kzalloc(sdev->dev, sizeof(*hdev), GFP_KERNEL); if (!hdev) return -ENOMEM; ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev, HDA_DEV_ASOC); +#endif return ret; -#endif } /* Codec initialization */ diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index 2b001151fe37..1c5e05b88a90 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -617,7 +617,7 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend) #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) if (runtime_suspend) - hda_codec_jack_wake_enable(sdev); + hda_codec_jack_wake_enable(sdev, true); /* power down all hda link */ snd_hdac_ext_bus_link_power_down_all(bus); @@ -683,8 +683,11 @@ static int hda_resume(struct snd_sof_dev *sdev, bool runtime_resume) #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) /* check jack status */ - if (runtime_resume) - hda_codec_jack_check(sdev); + if (runtime_resume) { + hda_codec_jack_wake_enable(sdev, false); + if (sdev->system_suspend_target == SOF_SUSPEND_NONE) + hda_codec_jack_check(sdev); + } /* turn off the links that were off before suspend */ list_for_each_entry(hlink, &bus->hlink_list, list) { diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index 9ec8ae0fd649..a3b6f3e9121c 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -650,7 +650,7 @@ void sof_hda_bus_init(struct hdac_bus *bus, struct device *dev); */ void hda_codec_probe_bus(struct snd_sof_dev *sdev, bool hda_codec_use_common_hdmi); -void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev); +void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev, bool enable); void hda_codec_jack_check(struct snd_sof_dev *sdev); #endif /* CONFIG_SND_SOC_SOF_HDA */ diff --git a/sound/soc/sof/sof-acpi-dev.c b/sound/soc/sof/sof-acpi-dev.c index 2a369c2c6551..cc2e257087e4 100644 --- a/sound/soc/sof/sof-acpi-dev.c +++ b/sound/soc/sof/sof-acpi-dev.c @@ -131,12 +131,13 @@ static int sof_acpi_probe(struct platform_device *pdev) if (!id) return -ENODEV; - ret = snd_intel_acpi_dsp_driver_probe(dev, id->id); - if (ret != SND_INTEL_DSP_DRIVER_ANY && ret != SND_INTEL_DSP_DRIVER_SOF) { - dev_dbg(dev, "SOF ACPI driver not selected, aborting probe\n"); - return -ENODEV; + if (IS_REACHABLE(CONFIG_SND_INTEL_DSP_CONFIG)) { + ret = snd_intel_acpi_dsp_driver_probe(dev, id->id); + if (ret != SND_INTEL_DSP_DRIVER_ANY && ret != SND_INTEL_DSP_DRIVER_SOF) { + dev_dbg(dev, "SOF ACPI driver not selected, aborting probe\n"); + return -ENODEV; + } } - dev_dbg(dev, "ACPI DSP detected"); sof_pdata = devm_kzalloc(dev, sizeof(*sof_pdata), GFP_KERNEL); diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index 63b989e3ec40..215711ac7450 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -344,10 +344,12 @@ static int sof_pci_probe(struct pci_dev *pci, const struct snd_sof_dsp_ops *ops; int ret; - ret = snd_intel_dsp_driver_probe(pci); - if (ret != SND_INTEL_DSP_DRIVER_ANY && ret != SND_INTEL_DSP_DRIVER_SOF) { - dev_dbg(&pci->dev, "SOF PCI driver not selected, aborting probe\n"); - return -ENODEV; + if (IS_REACHABLE(CONFIG_SND_INTEL_DSP_CONFIG)) { + ret = snd_intel_dsp_driver_probe(pci); + if (ret != SND_INTEL_DSP_DRIVER_ANY && ret != SND_INTEL_DSP_DRIVER_SOF) { + dev_dbg(&pci->dev, "SOF PCI driver not selected, aborting probe\n"); + return -ENODEV; + } } dev_dbg(&pci->dev, "PCI DSP detected"); diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 31051f2be46d..dc68ed65e478 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -485,18 +485,9 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, const struct audioformat *fmt, int rate) { struct usb_device *dev = chip->dev; - struct usb_host_interface *alts; - unsigned int ep; unsigned char data[3]; int err, crate; - alts = snd_usb_get_host_interface(chip, fmt->iface, fmt->altsetting); - if (!alts) - return -EINVAL; - if (get_iface_desc(alts)->bNumEndpoints < 1) - return -EINVAL; - ep = get_endpoint(alts, 0)->bEndpointAddress; - /* if endpoint doesn't have sampling rate control, bail out */ if (!(fmt->attributes & UAC_EP_CS_ATTR_SAMPLE_RATE)) return 0; @@ -506,11 +497,11 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, data[2] = rate >> 16; err = snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR, USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_OUT, - UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep, - data, sizeof(data)); + UAC_EP_CS_ATTR_SAMPLE_RATE << 8, + fmt->endpoint, data, sizeof(data)); if (err < 0) { dev_err(&dev->dev, "%d:%d: cannot set freq %d to ep %#x\n", - fmt->iface, fmt->altsetting, rate, ep); + fmt->iface, fmt->altsetting, rate, fmt->endpoint); return err; } @@ -524,11 +515,11 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip, err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC_GET_CUR, USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_IN, - UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep, - data, sizeof(data)); + UAC_EP_CS_ATTR_SAMPLE_RATE << 8, + fmt->endpoint, data, sizeof(data)); if (err < 0) { dev_err(&dev->dev, "%d:%d: cannot get freq at ep %#x\n", - fmt->iface, fmt->altsetting, ep); + fmt->iface, fmt->altsetting, fmt->endpoint); chip->sample_rate_read_error++; return 0; /* some devices don't support reading */ } diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index fe73fe3ff2bc..8e568823c992 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1252,6 +1252,15 @@ int snd_usb_endpoint_configure(struct snd_usb_audio *chip, /* If the interface has been already set up, just set EP parameters */ if (!ep->iface_ref->need_setup) { + /* sample rate setup of UAC1 is per endpoint, and we need + * to update at each EP configuration + */ + if (ep->cur_audiofmt->protocol == UAC_VERSION_1) { + err = snd_usb_init_sample_rate(chip, ep->cur_audiofmt, + ep->cur_rate); + if (err < 0) + goto unlock; + } err = snd_usb_endpoint_set_params(chip, ep); if (err < 0) goto unlock; diff --git a/sound/usb/format.c b/sound/usb/format.c index 9ebc5d202c87..e6ff317a6785 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -466,6 +466,17 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip, unsigned int nr_rates; int i, err; + /* performing the rate verification may lead to unexpected USB bus + * behavior afterwards by some unknown reason. Do this only for the + * known devices. + */ + switch (USB_ID_VENDOR(chip->usb_id)) { + case 0x07fd: /* MOTU */ + break; + default: + return 0; /* don't perform the validation as default */ + } + table = kcalloc(fp->nr_rates, sizeof(*table), GFP_KERNEL); if (!table) return -ENOMEM; diff --git a/sound/usb/implicit.c b/sound/usb/implicit.c index 1ac2cc6c33fb..521cc846d9d9 100644 --- a/sound/usb/implicit.c +++ b/sound/usb/implicit.c @@ -175,11 +175,13 @@ static int add_roland_implicit_fb(struct snd_usb_audio *chip, ifnum, alts); } -/* Pioneer devices: playback and capture streams sharing the same iface/altset +/* Playback and capture EPs on Pioneer devices share the same iface/altset, + * but they don't seem working with the implicit fb mode well, hence we + * just return as if the sync were already set up. */ -static int add_pioneer_implicit_fb(struct snd_usb_audio *chip, - struct audioformat *fmt, - struct usb_host_interface *alts) +static int skip_pioneer_sync_ep(struct snd_usb_audio *chip, + struct audioformat *fmt, + struct usb_host_interface *alts) { struct usb_endpoint_descriptor *epd; @@ -194,8 +196,7 @@ static int add_pioneer_implicit_fb(struct snd_usb_audio *chip, (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) != USB_ENDPOINT_USAGE_IMPLICIT_FB)) return 0; - return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 1, - alts->desc.bInterfaceNumber, alts); + return 1; /* don't handle with the implicit fb, just skip sync EP */ } static int __add_generic_implicit_fb(struct snd_usb_audio *chip, @@ -298,11 +299,11 @@ static int audioformat_implicit_fb_quirk(struct snd_usb_audio *chip, return 1; } - /* Pioneer devices implicit feedback with vendor spec class */ + /* Pioneer devices with vendor spec class */ if (attr == USB_ENDPOINT_SYNC_ASYNC && alts->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC && USB_ID_VENDOR(chip->usb_id) == 0x2b73 /* Pioneer */) { - if (add_pioneer_implicit_fb(chip, fmt, alts)) + if (skip_pioneer_sync_ep(chip, fmt, alts)) return 1; } diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 56079901769f..078bb4c94033 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -663,7 +663,7 @@ static int hw_check_valid_format(struct snd_usb_substream *subs, check_fmts.bits[1] = (u32)(fp->formats >> 32); snd_mask_intersect(&check_fmts, fmts); if (snd_mask_empty(&check_fmts)) { - hwc_debug(" > check: no supported format %d\n", fp->format); + hwc_debug(" > check: no supported format 0x%llx\n", fp->formats); return 0; } /* check the channels */ @@ -775,24 +775,11 @@ static int hw_rule_channels(struct snd_pcm_hw_params *params, return apply_hw_params_minmax(it, rmin, rmax); } -static int hw_rule_format(struct snd_pcm_hw_params *params, - struct snd_pcm_hw_rule *rule) +static int apply_hw_params_format_bits(struct snd_mask *fmt, u64 fbits) { - struct snd_usb_substream *subs = rule->private; - const struct audioformat *fp; - struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); - u64 fbits; u32 oldbits[2]; int changed; - hwc_debug("hw_rule_format: %x:%x\n", fmt->bits[0], fmt->bits[1]); - fbits = 0; - list_for_each_entry(fp, &subs->fmt_list, list) { - if (!hw_check_valid_format(subs, params, fp)) - continue; - fbits |= fp->formats; - } - oldbits[0] = fmt->bits[0]; oldbits[1] = fmt->bits[1]; fmt->bits[0] &= (u32)fbits; @@ -806,6 +793,24 @@ static int hw_rule_format(struct snd_pcm_hw_params *params, return changed; } +static int hw_rule_format(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct snd_usb_substream *subs = rule->private; + const struct audioformat *fp; + struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); + u64 fbits; + + hwc_debug("hw_rule_format: %x:%x\n", fmt->bits[0], fmt->bits[1]); + fbits = 0; + list_for_each_entry(fp, &subs->fmt_list, list) { + if (!hw_check_valid_format(subs, params, fp)) + continue; + fbits |= fp->formats; + } + return apply_hw_params_format_bits(fmt, fbits); +} + static int hw_rule_period_time(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { @@ -833,64 +838,92 @@ static int hw_rule_period_time(struct snd_pcm_hw_params *params, return apply_hw_params_minmax(it, pmin, UINT_MAX); } -/* apply PCM hw constraints from the concurrent sync EP */ -static int apply_hw_constraint_from_sync(struct snd_pcm_runtime *runtime, - struct snd_usb_substream *subs) +/* get the EP or the sync EP for implicit fb when it's already set up */ +static const struct snd_usb_endpoint * +get_sync_ep_from_substream(struct snd_usb_substream *subs) { struct snd_usb_audio *chip = subs->stream->chip; - struct snd_usb_endpoint *ep; const struct audioformat *fp; - int err; + const struct snd_usb_endpoint *ep; list_for_each_entry(fp, &subs->fmt_list, list) { ep = snd_usb_get_endpoint(chip, fp->endpoint); if (ep && ep->cur_rate) - goto found; + return ep; if (!fp->implicit_fb) continue; /* for the implicit fb, check the sync ep as well */ ep = snd_usb_get_endpoint(chip, fp->sync_ep); if (ep && ep->cur_rate) - goto found; + return ep; } - return 0; + return NULL; +} - found: - if (!find_format(&subs->fmt_list, ep->cur_format, ep->cur_rate, - ep->cur_channels, false, NULL)) { - usb_audio_dbg(chip, "EP 0x%x being used, but not applicable\n", - ep->ep_num); +/* additional hw constraints for implicit feedback mode */ +static int hw_rule_format_implicit_fb(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct snd_usb_substream *subs = rule->private; + const struct snd_usb_endpoint *ep; + struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); + + ep = get_sync_ep_from_substream(subs); + if (!ep) return 0; - } - usb_audio_dbg(chip, "EP 0x%x being used, using fixed params:\n", - ep->ep_num); - usb_audio_dbg(chip, "rate=%d, period_size=%d, periods=%d\n", - ep->cur_rate, ep->cur_period_frames, - ep->cur_buffer_periods); + hwc_debug("applying %s\n", __func__); + return apply_hw_params_format_bits(fmt, pcm_format_to_bits(ep->cur_format)); +} - runtime->hw.formats = subs->formats; - runtime->hw.rate_min = runtime->hw.rate_max = ep->cur_rate; - runtime->hw.rates = SNDRV_PCM_RATE_KNOT; - runtime->hw.periods_min = runtime->hw.periods_max = - ep->cur_buffer_periods; +static int hw_rule_rate_implicit_fb(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct snd_usb_substream *subs = rule->private; + const struct snd_usb_endpoint *ep; + struct snd_interval *it; - err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, - hw_rule_channels, subs, - SNDRV_PCM_HW_PARAM_FORMAT, - SNDRV_PCM_HW_PARAM_RATE, - -1); - if (err < 0) - return err; + ep = get_sync_ep_from_substream(subs); + if (!ep) + return 0; - err = snd_pcm_hw_constraint_minmax(runtime, - SNDRV_PCM_HW_PARAM_PERIOD_SIZE, - ep->cur_period_frames, - ep->cur_period_frames); - if (err < 0) - return err; + hwc_debug("applying %s\n", __func__); + it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE); + return apply_hw_params_minmax(it, ep->cur_rate, ep->cur_rate); +} - return 1; /* notify the finding */ +static int hw_rule_period_size_implicit_fb(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct snd_usb_substream *subs = rule->private; + const struct snd_usb_endpoint *ep; + struct snd_interval *it; + + ep = get_sync_ep_from_substream(subs); + if (!ep) + return 0; + + hwc_debug("applying %s\n", __func__); + it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE); + return apply_hw_params_minmax(it, ep->cur_period_frames, + ep->cur_period_frames); +} + +static int hw_rule_periods_implicit_fb(struct snd_pcm_hw_params *params, + struct snd_pcm_hw_rule *rule) +{ + struct snd_usb_substream *subs = rule->private; + const struct snd_usb_endpoint *ep; + struct snd_interval *it; + + ep = get_sync_ep_from_substream(subs); + if (!ep) + return 0; + + hwc_debug("applying %s\n", __func__); + it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIODS); + return apply_hw_params_minmax(it, ep->cur_buffer_periods, + ep->cur_buffer_periods); } /* @@ -899,20 +932,11 @@ static int apply_hw_constraint_from_sync(struct snd_pcm_runtime *runtime, static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substream *subs) { - struct snd_usb_audio *chip = subs->stream->chip; const struct audioformat *fp; unsigned int pt, ptmin; int param_period_time_if_needed = -1; int err; - mutex_lock(&chip->mutex); - err = apply_hw_constraint_from_sync(runtime, subs); - mutex_unlock(&chip->mutex); - if (err < 0) - return err; - if (err > 0) /* found the matching? */ - goto add_extra_rules; - runtime->hw.formats = subs->formats; runtime->hw.rate_min = 0x7fffffff; @@ -957,6 +981,7 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, hw_rule_rate, subs, + SNDRV_PCM_HW_PARAM_RATE, SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_CHANNELS, param_period_time_if_needed, @@ -964,9 +989,9 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre if (err < 0) return err; -add_extra_rules: err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, hw_rule_channels, subs, + SNDRV_PCM_HW_PARAM_CHANNELS, SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_RATE, param_period_time_if_needed, @@ -975,6 +1000,7 @@ add_extra_rules: return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, hw_rule_format, subs, + SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_RATE, SNDRV_PCM_HW_PARAM_CHANNELS, param_period_time_if_needed, @@ -993,6 +1019,28 @@ add_extra_rules: return err; } + /* additional hw constraints for implicit fb */ + err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, + hw_rule_format_implicit_fb, subs, + SNDRV_PCM_HW_PARAM_FORMAT, -1); + if (err < 0) + return err; + err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, + hw_rule_rate_implicit_fb, subs, + SNDRV_PCM_HW_PARAM_RATE, -1); + if (err < 0) + return err; + err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, + hw_rule_period_size_implicit_fb, subs, + SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1); + if (err < 0) + return err; + err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIODS, + hw_rule_periods_implicit_fb, subs, + SNDRV_PCM_HW_PARAM_PERIODS, -1); + if (err < 0) + return err; + return 0; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 89e172642d98..e196e364cef1 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1470,30 +1470,6 @@ static void set_format_emu_quirk(struct snd_usb_substream *subs, subs->pkt_offset_adj = (emu_samplerate_id >= EMU_QUIRK_SR_176400HZ) ? 4 : 0; } - -/* - * Pioneer DJ DJM-900NXS2 - * Device needs to know the sample rate each time substream is started - */ -static int pioneer_djm_set_format_quirk(struct snd_usb_substream *subs) -{ - unsigned int cur_rate = subs->data_endpoint->cur_rate; - /* Convert sample rate value to little endian */ - u8 sr[3]; - - sr[0] = cur_rate & 0xff; - sr[1] = (cur_rate >> 8) & 0xff; - sr[2] = (cur_rate >> 16) & 0xff; - - /* Configure device */ - usb_set_interface(subs->dev, 0, 1); - snd_usb_ctl_msg(subs->stream->chip->dev, - usb_rcvctrlpipe(subs->stream->chip->dev, 0), - 0x01, 0x22, 0x0100, 0x0082, &sr, 0x0003); - - return 0; -} - void snd_usb_set_format_quirk(struct snd_usb_substream *subs, const struct audioformat *fmt) { @@ -1504,10 +1480,6 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs, case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */ set_format_emu_quirk(subs, fmt); break; - case USB_ID(0x2b73, 0x000a): /* Pioneer DJ DJM-900NXS2 */ - case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */ - pioneer_djm_set_format_quirk(subs); - break; case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */ subs->stream_offset_adj = 2; break; diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index cacd66ad7926..a2b233fdb572 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -107,8 +107,8 @@ int monitor_device(const char *device_name, ret = -EIO; break; } - fprintf(stdout, "GPIO EVENT at %llu on line %d (%d|%d) ", - event.timestamp_ns, event.offset, event.line_seqno, + fprintf(stdout, "GPIO EVENT at %" PRIu64 " on line %d (%d|%d) ", + (uint64_t)event.timestamp_ns, event.offset, event.line_seqno, event.seqno); switch (event.id) { case GPIO_V2_LINE_EVENT_RISING_EDGE: diff --git a/tools/gpio/gpio-watch.c b/tools/gpio/gpio-watch.c index f229ec62301b..41e76d244192 100644 --- a/tools/gpio/gpio-watch.c +++ b/tools/gpio/gpio-watch.c @@ -10,6 +10,7 @@ #include <ctype.h> #include <errno.h> #include <fcntl.h> +#include <inttypes.h> #include <linux/gpio.h> #include <poll.h> #include <stdbool.h> @@ -86,8 +87,8 @@ int main(int argc, char **argv) return EXIT_FAILURE; } - printf("line %u: %s at %llu\n", - chg.info.offset, event, chg.timestamp_ns); + printf("line %u: %s at %" PRIu64 "\n", + chg.info.offset, event, (uint64_t)chg.timestamp_ns); } } diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index cfcdbd7be066..17465d454a0e 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -367,21 +367,13 @@ static struct perf_mmap* perf_evlist__alloc_mmap(struct perf_evlist *evlist, boo return map; } -static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx, int cpu, - int thread) +static void perf_evsel__set_sid_idx(struct perf_evsel *evsel, int idx, int cpu, int thread) { struct perf_sample_id *sid = SID(evsel, cpu, thread); sid->idx = idx; - if (evlist->cpus && cpu >= 0) - sid->cpu = evlist->cpus->map[cpu]; - else - sid->cpu = -1; - if (!evsel->system_wide && evlist->threads && thread >= 0) - sid->tid = perf_thread_map__pid(evlist->threads, thread); - else - sid->tid = -1; + sid->cpu = perf_cpu_map__cpu(evsel->cpus, cpu); + sid->tid = perf_thread_map__pid(evsel->threads, thread); } static struct perf_mmap* @@ -500,8 +492,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) return -1; - perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, - thread); + perf_evsel__set_sid_idx(evsel, idx, cpu, thread); } } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5f8d3eed78a1..4bd30315eb62 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2928,14 +2928,10 @@ int check(struct objtool_file *file) warnings += ret; out: - if (ret < 0) { - /* - * Fatal error. The binary is corrupt or otherwise broken in - * some way, or objtool itself is broken. Fail the kernel - * build. - */ - return ret; - } - + /* + * For now, don't fail the kernel build on fatal warnings. These + * errors are still fairly common due to the growing matrix of + * supported toolchains and their recent pace of change. + */ return 0; } diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index be89c741ba9a..d8421e1d06be 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -380,8 +380,11 @@ static int read_symbols(struct elf *elf) symtab = find_section_by_name(elf, ".symtab"); if (!symtab) { - WARN("missing symbol table"); - return -1; + /* + * A missing symbol table is actually possible if it's an empty + * .o file. This can happen for thunk_64.o. + */ + return 0; } symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); @@ -448,6 +451,13 @@ static int read_symbols(struct elf *elf) list_add(&sym->list, entry); elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx); elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name)); + + /* + * Don't store empty STT_NOTYPE symbols in the rbtree. They + * can exist within a function, confusing the sorting. + */ + if (!sym->len) + rb_erase(&sym->node, &sym->sec->symbol_tree); } if (stats) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index edacfa98d073..42dad4a0f8cf 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -186,6 +186,7 @@ struct output_option { enum { OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_OTHER, OUTPUT_TYPE_MAX }; @@ -283,6 +284,18 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_OTHER] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, }; struct evsel_script { @@ -343,8 +356,11 @@ static inline int output_type(unsigned int type) case PERF_TYPE_SYNTH: return OUTPUT_TYPE_SYNTH; default: - return type; + if (type < PERF_TYPE_MAX) + return type; } + + return OUTPUT_TYPE_OTHER; } static inline unsigned int attr_type(unsigned int type) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index ee94d3e8dd65..e6d3452031e5 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -162,6 +162,14 @@ static bool contains_event(struct evsel **metric_events, int num_events, return false; } +static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) +{ + if (!ev1->pmu_name || !ev2->pmu_name) + return false; + + return !strcmp(ev1->pmu_name, ev2->pmu_name); +} + /** * Find a group of events in perf_evlist that correspond to those from a parsed * metric expression. Note, as find_evsel_group is called in the same order as @@ -280,8 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, */ if (!has_constraint && ev->leader != metric_events[i]->leader && - !strcmp(ev->leader->pmu_name, - metric_events[i]->leader->pmu_name)) + evsel_same_pmu(ev->leader, metric_events[i]->leader)) break; if (!strcmp(metric_events[i]->name, ev->name)) { set_bit(ev->idx, evlist_used); @@ -766,7 +773,6 @@ int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused) struct metricgroup_add_iter_data { struct list_head *metric_list; const char *metric; - struct metric **m; struct expr_ids *ids; int *ret; bool *has_match; @@ -1058,12 +1064,13 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, void *data) { struct metricgroup_add_iter_data *d = data; + struct metric *m = NULL; int ret; if (!match_pe_metric(pe, d->metric)) return 0; - ret = add_metric(d->metric_list, pe, d->metric_no_group, d->m, NULL, d->ids); + ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); if (ret) return ret; @@ -1114,7 +1121,6 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group, .metric_list = &list, .metric = metric, .metric_no_group = metric_no_group, - .m = &m, .ids = &ids, .has_match = &has_match, .ret = &ret, diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 5390158cdb40..09cb3a6672f3 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -1249,6 +1249,8 @@ static void dump_isst_config(int arg) isst_ctdp_display_information_end(outf); } +static void adjust_scaling_max_from_base_freq(int cpu); + static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, void *arg4) { @@ -1267,6 +1269,9 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, int pkg_id = get_physical_package_id(cpu); int die_id = get_physical_die_id(cpu); + /* Wait for updated base frequencies */ + usleep(2000); + fprintf(stderr, "Option is set to online/offline\n"); ctdp_level.core_cpumask_size = alloc_cpu_set(&ctdp_level.core_cpumask); @@ -1283,6 +1288,7 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, if (CPU_ISSET_S(i, ctdp_level.core_cpumask_size, ctdp_level.core_cpumask)) { fprintf(stderr, "online cpu %d\n", i); set_cpu_online_offline(i, 1); + adjust_scaling_max_from_base_freq(i); } else { fprintf(stderr, "offline cpu %d\n", i); set_cpu_online_offline(i, 0); @@ -1440,6 +1446,31 @@ static int set_cpufreq_scaling_min_max(int cpu, int max, int freq) return 0; } +static int no_turbo(void) +{ + return parse_int_file(0, "/sys/devices/system/cpu/intel_pstate/no_turbo"); +} + +static void adjust_scaling_max_from_base_freq(int cpu) +{ + int base_freq, scaling_max_freq; + + scaling_max_freq = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_max_freq", cpu); + base_freq = get_cpufreq_base_freq(cpu); + if (scaling_max_freq < base_freq || no_turbo()) + set_cpufreq_scaling_min_max(cpu, 1, base_freq); +} + +static void adjust_scaling_min_from_base_freq(int cpu) +{ + int base_freq, scaling_min_freq; + + scaling_min_freq = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_min_freq", cpu); + base_freq = get_cpufreq_base_freq(cpu); + if (scaling_min_freq < base_freq) + set_cpufreq_scaling_min_max(cpu, 0, base_freq); +} + static int set_clx_pbf_cpufreq_scaling_min_max(int cpu) { struct isst_pkg_ctdp_level_info *ctdp_level; @@ -1537,6 +1568,7 @@ static void set_scaling_min_to_cpuinfo_max(int cpu) continue; set_cpufreq_scaling_min_max_from_cpuinfo(i, 1, 0); + adjust_scaling_min_from_base_freq(i); } } diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 21516e293d17..e808a47c839b 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -43,9 +43,9 @@ class KunitStatus(Enum): BUILD_FAILURE = auto() TEST_FAILURE = auto() -def get_kernel_root_path(): - parts = sys.argv[0] if not __file__ else __file__ - parts = os.path.realpath(parts).split('tools/testing/kunit') +def get_kernel_root_path() -> str: + path = sys.argv[0] if not __file__ else __file__ + parts = os.path.realpath(path).split('tools/testing/kunit') if len(parts) != 2: sys.exit(1) return parts[0] @@ -171,7 +171,7 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, exec_result.elapsed_time)) return parse_result -def add_common_opts(parser): +def add_common_opts(parser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' 'directory.', @@ -183,13 +183,13 @@ def add_common_opts(parser): help='Run all KUnit tests through allyesconfig', action='store_true') -def add_build_opts(parser): +def add_build_opts(parser) -> None: parser.add_argument('--jobs', help='As in the make command, "Specifies the number of ' 'jobs (commands) to run simultaneously."', type=int, default=8, metavar='jobs') -def add_exec_opts(parser): +def add_exec_opts(parser) -> None: parser.add_argument('--timeout', help='maximum number of seconds to allow for all tests ' 'to run. This does not include time taken to build the ' @@ -198,7 +198,7 @@ def add_exec_opts(parser): default=300, metavar='timeout') -def add_parse_opts(parser): +def add_parse_opts(parser) -> None: parser.add_argument('--raw_output', help='don\'t format output from kernel', action='store_true') parser.add_argument('--json', @@ -256,10 +256,7 @@ def main(argv, linux=None): os.mkdir(cli_args.build_dir) if not linux: - linux = kunit_kernel.LinuxSourceTree() - - linux.create_kunitconfig(cli_args.build_dir) - linux.read_kunitconfig(cli_args.build_dir) + linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir) request = KunitRequest(cli_args.raw_output, cli_args.timeout, @@ -277,10 +274,7 @@ def main(argv, linux=None): os.mkdir(cli_args.build_dir) if not linux: - linux = kunit_kernel.LinuxSourceTree() - - linux.create_kunitconfig(cli_args.build_dir) - linux.read_kunitconfig(cli_args.build_dir) + linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir) request = KunitConfigRequest(cli_args.build_dir, cli_args.make_options) @@ -292,10 +286,7 @@ def main(argv, linux=None): sys.exit(1) elif cli_args.subcommand == 'build': if not linux: - linux = kunit_kernel.LinuxSourceTree() - - linux.create_kunitconfig(cli_args.build_dir) - linux.read_kunitconfig(cli_args.build_dir) + linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir) request = KunitBuildRequest(cli_args.jobs, cli_args.build_dir, @@ -309,10 +300,7 @@ def main(argv, linux=None): sys.exit(1) elif cli_args.subcommand == 'exec': if not linux: - linux = kunit_kernel.LinuxSourceTree() - - linux.create_kunitconfig(cli_args.build_dir) - linux.read_kunitconfig(cli_args.build_dir) + linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir) exec_request = KunitExecRequest(cli_args.timeout, cli_args.build_dir, diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py index 02ffc3a3e5dc..bdd60230764b 100644 --- a/tools/testing/kunit/kunit_config.py +++ b/tools/testing/kunit/kunit_config.py @@ -8,6 +8,7 @@ import collections import re +from typing import List, Set CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$' CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$' @@ -30,10 +31,10 @@ class KconfigParseError(Exception): class Kconfig(object): """Represents defconfig or .config specified using the Kconfig language.""" - def __init__(self): - self._entries = [] + def __init__(self) -> None: + self._entries = [] # type: List[KconfigEntry] - def entries(self): + def entries(self) -> Set[KconfigEntry]: return set(self._entries) def add_entry(self, entry: KconfigEntry) -> None: diff --git a/tools/testing/kunit/kunit_json.py b/tools/testing/kunit/kunit_json.py index 624b31b2dbd6..f5cca5c38cac 100644 --- a/tools/testing/kunit/kunit_json.py +++ b/tools/testing/kunit/kunit_json.py @@ -13,7 +13,7 @@ import kunit_parser from kunit_parser import TestStatus -def get_json_result(test_result, def_config, build_dir, json_path): +def get_json_result(test_result, def_config, build_dir, json_path) -> str: sub_groups = [] # Each test suite is mapped to a KernelCI sub_group diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 698358c9c0d6..2076a5a2d060 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -11,6 +11,7 @@ import subprocess import os import shutil import signal +from typing import Iterator from contextlib import ExitStack @@ -39,7 +40,7 @@ class BuildError(Exception): class LinuxSourceTreeOperations(object): """An abstraction over command line operations performed on a source tree.""" - def make_mrproper(self): + def make_mrproper(self) -> None: try: subprocess.check_output(['make', 'mrproper'], stderr=subprocess.STDOUT) except OSError as e: @@ -47,7 +48,7 @@ class LinuxSourceTreeOperations(object): except subprocess.CalledProcessError as e: raise ConfigError(e.output.decode()) - def make_olddefconfig(self, build_dir, make_options): + def make_olddefconfig(self, build_dir, make_options) -> None: command = ['make', 'ARCH=um', 'olddefconfig'] if make_options: command.extend(make_options) @@ -60,7 +61,7 @@ class LinuxSourceTreeOperations(object): except subprocess.CalledProcessError as e: raise ConfigError(e.output.decode()) - def make_allyesconfig(self, build_dir, make_options): + def make_allyesconfig(self, build_dir, make_options) -> None: kunit_parser.print_with_timestamp( 'Enabling all CONFIGs for UML...') command = ['make', 'ARCH=um', 'allyesconfig'] @@ -82,7 +83,7 @@ class LinuxSourceTreeOperations(object): kunit_parser.print_with_timestamp( 'Starting Kernel with all configs takes a few minutes...') - def make(self, jobs, build_dir, make_options): + def make(self, jobs, build_dir, make_options) -> None: command = ['make', 'ARCH=um', '--jobs=' + str(jobs)] if make_options: command.extend(make_options) @@ -100,7 +101,7 @@ class LinuxSourceTreeOperations(object): if stderr: # likely only due to build warnings print(stderr.decode()) - def linux_bin(self, params, timeout, build_dir): + def linux_bin(self, params, timeout, build_dir) -> None: """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = get_file_path(build_dir, 'linux') outfile = get_outfile_path(build_dir) @@ -110,41 +111,42 @@ class LinuxSourceTreeOperations(object): stderr=subprocess.STDOUT) process.wait(timeout) -def get_kconfig_path(build_dir): +def get_kconfig_path(build_dir) -> str: return get_file_path(build_dir, KCONFIG_PATH) -def get_kunitconfig_path(build_dir): +def get_kunitconfig_path(build_dir) -> str: return get_file_path(build_dir, KUNITCONFIG_PATH) -def get_outfile_path(build_dir): +def get_outfile_path(build_dir) -> str: return get_file_path(build_dir, OUTFILE_PATH) class LinuxSourceTree(object): """Represents a Linux kernel source tree with KUnit tests.""" - def __init__(self): - self._ops = LinuxSourceTreeOperations() + def __init__(self, build_dir: str, load_config=True, defconfig=DEFAULT_KUNITCONFIG_PATH) -> None: signal.signal(signal.SIGINT, self.signal_handler) - def clean(self): - try: - self._ops.make_mrproper() - except ConfigError as e: - logging.error(e) - return False - return True + self._ops = LinuxSourceTreeOperations() + + if not load_config: + return - def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH): kunitconfig_path = get_kunitconfig_path(build_dir) if not os.path.exists(kunitconfig_path): shutil.copyfile(defconfig, kunitconfig_path) - def read_kunitconfig(self, build_dir): - kunitconfig_path = get_kunitconfig_path(build_dir) self._kconfig = kunit_config.Kconfig() self._kconfig.read_from_file(kunitconfig_path) - def validate_config(self, build_dir): + def clean(self) -> bool: + try: + self._ops.make_mrproper() + except ConfigError as e: + logging.error(e) + return False + return True + + def validate_config(self, build_dir) -> bool: kconfig_path = get_kconfig_path(build_dir) validated_kconfig = kunit_config.Kconfig() validated_kconfig.read_from_file(kconfig_path) @@ -158,7 +160,7 @@ class LinuxSourceTree(object): return False return True - def build_config(self, build_dir, make_options): + def build_config(self, build_dir, make_options) -> bool: kconfig_path = get_kconfig_path(build_dir) if build_dir and not os.path.exists(build_dir): os.mkdir(build_dir) @@ -170,7 +172,7 @@ class LinuxSourceTree(object): return False return self.validate_config(build_dir) - def build_reconfig(self, build_dir, make_options): + def build_reconfig(self, build_dir, make_options) -> bool: """Creates a new .config if it is not a subset of the .kunitconfig.""" kconfig_path = get_kconfig_path(build_dir) if os.path.exists(kconfig_path): @@ -186,7 +188,7 @@ class LinuxSourceTree(object): print('Generating .config ...') return self.build_config(build_dir, make_options) - def build_um_kernel(self, alltests, jobs, build_dir, make_options): + def build_um_kernel(self, alltests, jobs, build_dir, make_options) -> bool: try: if alltests: self._ops.make_allyesconfig(build_dir, make_options) @@ -197,7 +199,7 @@ class LinuxSourceTree(object): return False return self.validate_config(build_dir) - def run_kernel(self, args=[], build_dir='', timeout=None): + def run_kernel(self, args=[], build_dir='', timeout=None) -> Iterator[str]: args.extend(['mem=1G', 'console=tty']) self._ops.linux_bin(args, timeout, build_dir) outfile = get_outfile_path(build_dir) @@ -206,6 +208,6 @@ class LinuxSourceTree(object): for line in file: yield line - def signal_handler(self, sig, frame): + def signal_handler(self, sig, frame) -> None: logging.error('Build interruption occurred. Cleaning console.') subprocess.call(['stty', 'sane']) diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 6614ec4d0898..e8bcc139702e 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -12,32 +12,32 @@ from collections import namedtuple from datetime import datetime from enum import Enum, auto from functools import reduce -from typing import List, Optional, Tuple +from typing import Iterable, Iterator, List, Optional, Tuple TestResult = namedtuple('TestResult', ['status','suites','log']) class TestSuite(object): - def __init__(self): - self.status = None - self.name = None - self.cases = [] + def __init__(self) -> None: + self.status = TestStatus.SUCCESS + self.name = '' + self.cases = [] # type: List[TestCase] - def __str__(self): - return 'TestSuite(' + self.status + ',' + self.name + ',' + str(self.cases) + ')' + def __str__(self) -> str: + return 'TestSuite(' + str(self.status) + ',' + self.name + ',' + str(self.cases) + ')' - def __repr__(self): + def __repr__(self) -> str: return str(self) class TestCase(object): - def __init__(self): - self.status = None + def __init__(self) -> None: + self.status = TestStatus.SUCCESS self.name = '' - self.log = [] + self.log = [] # type: List[str] - def __str__(self): - return 'TestCase(' + self.status + ',' + self.name + ',' + str(self.log) + ')' + def __str__(self) -> str: + return 'TestCase(' + str(self.status) + ',' + self.name + ',' + str(self.log) + ')' - def __repr__(self): + def __repr__(self) -> str: return str(self) class TestStatus(Enum): @@ -51,7 +51,7 @@ kunit_start_re = re.compile(r'TAP version [0-9]+$') kunit_end_re = re.compile('(List of all partitions:|' 'Kernel panic - not syncing: VFS:)') -def isolate_kunit_output(kernel_output): +def isolate_kunit_output(kernel_output) -> Iterator[str]: started = False for line in kernel_output: line = line.rstrip() # line always has a trailing \n @@ -64,7 +64,7 @@ def isolate_kunit_output(kernel_output): elif started: yield line[prefix_len:] if prefix_len > 0 else line -def raw_output(kernel_output): +def raw_output(kernel_output) -> None: for line in kernel_output: print(line.rstrip()) @@ -72,36 +72,36 @@ DIVIDER = '=' * 60 RESET = '\033[0;0m' -def red(text): +def red(text) -> str: return '\033[1;31m' + text + RESET -def yellow(text): +def yellow(text) -> str: return '\033[1;33m' + text + RESET -def green(text): +def green(text) -> str: return '\033[1;32m' + text + RESET -def print_with_timestamp(message): +def print_with_timestamp(message) -> None: print('[%s] %s' % (datetime.now().strftime('%H:%M:%S'), message)) -def format_suite_divider(message): +def format_suite_divider(message) -> str: return '======== ' + message + ' ========' -def print_suite_divider(message): +def print_suite_divider(message) -> None: print_with_timestamp(DIVIDER) print_with_timestamp(format_suite_divider(message)) -def print_log(log): +def print_log(log) -> None: for m in log: print_with_timestamp(m) TAP_ENTRIES = re.compile(r'^(TAP|[\s]*ok|[\s]*not ok|[\s]*[0-9]+\.\.[0-9]+|[\s]*#).*$') -def consume_non_diagnositic(lines: List[str]) -> None: +def consume_non_diagnostic(lines: List[str]) -> None: while lines and not TAP_ENTRIES.match(lines[0]): lines.pop(0) -def save_non_diagnositic(lines: List[str], test_case: TestCase) -> None: +def save_non_diagnostic(lines: List[str], test_case: TestCase) -> None: while lines and not TAP_ENTRIES.match(lines[0]): test_case.log.append(lines[0]) lines.pop(0) @@ -113,7 +113,7 @@ OK_NOT_OK_SUBTEST = re.compile(r'^[\s]+(ok|not ok) [0-9]+ - (.*)$') OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) ([0-9]+) - (.*)$') def parse_ok_not_ok_test_case(lines: List[str], test_case: TestCase) -> bool: - save_non_diagnositic(lines, test_case) + save_non_diagnostic(lines, test_case) if not lines: test_case.status = TestStatus.TEST_CRASHED return True @@ -139,7 +139,7 @@ SUBTEST_DIAGNOSTIC = re.compile(r'^[\s]+# (.*)$') DIAGNOSTIC_CRASH_MESSAGE = re.compile(r'^[\s]+# .*?: kunit test case crashed!$') def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: - save_non_diagnositic(lines, test_case) + save_non_diagnostic(lines, test_case) if not lines: return False line = lines[0] @@ -155,7 +155,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool: def parse_test_case(lines: List[str]) -> Optional[TestCase]: test_case = TestCase() - save_non_diagnositic(lines, test_case) + save_non_diagnostic(lines, test_case) while parse_diagnostic(lines, test_case): pass if parse_ok_not_ok_test_case(lines, test_case): @@ -166,7 +166,7 @@ def parse_test_case(lines: List[str]) -> Optional[TestCase]: SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$') def parse_subtest_header(lines: List[str]) -> Optional[str]: - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) if not lines: return None match = SUBTEST_HEADER.match(lines[0]) @@ -179,7 +179,7 @@ def parse_subtest_header(lines: List[str]) -> Optional[str]: SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)') def parse_subtest_plan(lines: List[str]) -> Optional[int]: - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) match = SUBTEST_PLAN.match(lines[0]) if match: lines.pop(0) @@ -202,7 +202,7 @@ def max_status(left: TestStatus, right: TestStatus) -> TestStatus: def parse_ok_not_ok_test_suite(lines: List[str], test_suite: TestSuite, expected_suite_index: int) -> bool: - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) if not lines: test_suite.status = TestStatus.TEST_CRASHED return False @@ -224,18 +224,17 @@ def parse_ok_not_ok_test_suite(lines: List[str], else: return False -def bubble_up_errors(to_status, status_container_list) -> TestStatus: - status_list = map(to_status, status_container_list) - return reduce(max_status, status_list, TestStatus.SUCCESS) +def bubble_up_errors(statuses: Iterable[TestStatus]) -> TestStatus: + return reduce(max_status, statuses, TestStatus.SUCCESS) def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus: - max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases) + max_test_case_status = bubble_up_errors(x.status for x in test_suite.cases) return max_status(max_test_case_status, test_suite.status) def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]: if not lines: return None - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) test_suite = TestSuite() test_suite.status = TestStatus.SUCCESS name = parse_subtest_header(lines) @@ -264,7 +263,7 @@ def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[Te TAP_HEADER = re.compile(r'^TAP version 14$') def parse_tap_header(lines: List[str]) -> bool: - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) if TAP_HEADER.match(lines[0]): lines.pop(0) return True @@ -274,7 +273,7 @@ def parse_tap_header(lines: List[str]) -> bool: TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)') def parse_test_plan(lines: List[str]) -> Optional[int]: - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) match = TEST_PLAN.match(lines[0]) if match: lines.pop(0) @@ -282,11 +281,11 @@ def parse_test_plan(lines: List[str]) -> Optional[int]: else: return None -def bubble_up_suite_errors(test_suite_list: List[TestSuite]) -> TestStatus: - return bubble_up_errors(lambda x: x.status, test_suite_list) +def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus: + return bubble_up_errors(x.status for x in test_suites) def parse_test_result(lines: List[str]) -> TestResult: - consume_non_diagnositic(lines) + consume_non_diagnostic(lines) if not lines or not parse_tap_header(lines): return TestResult(TestStatus.NO_TESTS, [], lines) expected_test_suite_num = parse_test_plan(lines) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 8a917cb4426a..c42aacec5038 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -34,6 +34,7 @@ TARGETS += memory-hotplug TARGETS += mincore TARGETS += mount TARGETS += mqueue +TARGETS += nci TARGETS += net TARGETS += net/forwarding TARGETS += net/mptcp diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh index eab79b9e58cd..dcbf32b99bb6 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/fib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh @@ -225,6 +225,16 @@ ipv6_local_replace() ip -n $ns link del dev dummy1 } +fib_notify_on_flag_change_set() +{ + local notify=$1; shift + + ip netns exec testns1 sysctl -qw net.ipv4.fib_notify_on_flag_change=$notify + ip netns exec testns1 sysctl -qw net.ipv6.fib_notify_on_flag_change=$notify + + log_info "Set fib_notify_on_flag_change to $notify" +} + setup_prepare() { ip netns add testns1 @@ -251,6 +261,10 @@ trap cleanup EXIT setup_prepare +fib_notify_on_flag_change_set 1 +tests_run + +fib_notify_on_flag_change_set 0 tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh index 2f87c3be76a9..251f228ce63e 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/fib.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh @@ -302,6 +302,16 @@ ipv6_error_path() ipv6_error_path_replay } +fib_notify_on_flag_change_set() +{ + local notify=$1; shift + + ip netns exec testns1 sysctl -qw net.ipv4.fib_notify_on_flag_change=$notify + ip netns exec testns1 sysctl -qw net.ipv6.fib_notify_on_flag_change=$notify + + log_info "Set fib_notify_on_flag_change to $notify" +} + setup_prepare() { local netdev @@ -336,6 +346,10 @@ trap cleanup EXIT setup_prepare +fib_notify_on_flag_change_set 1 +tests_run + +fib_notify_on_flag_change_set 0 tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh new file mode 100755 index 000000000000..16a9dd43aefc --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh @@ -0,0 +1,300 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_route_addition_test + ipv4_route_deletion_test + ipv4_route_replacement_test + ipv6_route_addition_test + ipv6_route_deletion_test + ipv6_route_replacement_test +" + +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ +NUM_NETIFS=0 +source $lib_dir/lib.sh + +check_rt_trap() +{ + local outfile=$1; shift + local line + + # Make sure that the first notification was emitted without RTM_F_TRAP + # flag and the second with RTM_F_TRAP flag + head -n 1 $outfile | grep -q "rt_trap" + if [[ $? -eq 0 ]]; then + return 1 + fi + + head -n 2 $outfile | tail -n 1 | grep -q "rt_trap" +} + +route_notify_check() +{ + local outfile=$1; shift + local expected_num_lines=$1; shift + + # check the monitor results + lines=`wc -l $outfile | cut "-d " -f1` + test $lines -eq $expected_num_lines + check_err $? "$expected_num_lines notifications were expected but $lines were received" + + if [[ $expected_num_lines -eq 2 ]]; then + check_rt_trap $outfile + check_err $? "Wrong RTM_F_TRAP flags in notifications" + fi +} + +route_addition_check() +{ + local ip=$1; shift + local notify=$1; shift + local route=$1; shift + local expected_num_notifications=$1; shift + + ip netns exec testns1 sysctl -qw net.$ip.fib_notify_on_flag_change=$notify + + local outfile=$(mktemp) + + $IP monitor route &> $outfile & + sleep 1 + $IP route add $route dev dummy1 + sleep 1 + kill %% && wait %% &> /dev/null + + route_notify_check $outfile $expected_num_notifications + rm -f $outfile + + $IP route del $route dev dummy1 +} + +ipv4_route_addition_test() +{ + RET=0 + + local ip="ipv4" + local route=192.0.2.0/24 + + # Make sure a single notification will be emitted for the programmed + # route. + local notify=0 + local expected_num_notifications=1 + # route_addition_check will assign value to RET. + route_addition_check $ip $notify $route $expected_num_notifications + + # Make sure two notifications will be emitted for the programmed route. + notify=1 + expected_num_notifications=2 + route_addition_check $ip $notify $route $expected_num_notifications + + log_test "IPv4 route addition" +} + +route_deletion_check() +{ + local ip=$1; shift + local notify=$1; shift + local route=$1; shift + local expected_num_notifications=$1; shift + + ip netns exec testns1 sysctl -qw net.$ip.fib_notify_on_flag_change=$notify + $IP route add $route dev dummy1 + sleep 1 + + local outfile=$(mktemp) + + $IP monitor route &> $outfile & + sleep 1 + $IP route del $route dev dummy1 + sleep 1 + kill %% && wait %% &> /dev/null + + route_notify_check $outfile $expected_num_notifications + rm -f $outfile +} + +ipv4_route_deletion_test() +{ + RET=0 + + local ip="ipv4" + local route=192.0.2.0/24 + local expected_num_notifications=1 + + # Make sure a single notification will be emitted for the deleted route, + # regardless of fib_notify_on_flag_change value. + local notify=0 + # route_deletion_check will assign value to RET. + route_deletion_check $ip $notify $route $expected_num_notifications + + notify=1 + route_deletion_check $ip $notify $route $expected_num_notifications + + log_test "IPv4 route deletion" +} + +route_replacement_check() +{ + local ip=$1; shift + local notify=$1; shift + local route=$1; shift + local expected_num_notifications=$1; shift + + ip netns exec testns1 sysctl -qw net.$ip.fib_notify_on_flag_change=$notify + $IP route add $route dev dummy1 + sleep 1 + + local outfile=$(mktemp) + + $IP monitor route &> $outfile & + sleep 1 + $IP route replace $route dev dummy2 + sleep 1 + kill %% && wait %% &> /dev/null + + route_notify_check $outfile $expected_num_notifications + rm -f $outfile + + $IP route del $route dev dummy2 +} + +ipv4_route_replacement_test() +{ + RET=0 + + local ip="ipv4" + local route=192.0.2.0/24 + + $IP link add name dummy2 type dummy + $IP link set dev dummy2 up + + # Make sure a single notification will be emitted for the new route. + local notify=0 + local expected_num_notifications=1 + # route_replacement_check will assign value to RET. + route_replacement_check $ip $notify $route $expected_num_notifications + + # Make sure two notifications will be emitted for the new route. + notify=1 + expected_num_notifications=2 + route_replacement_check $ip $notify $route $expected_num_notifications + + $IP link del name dummy2 + + log_test "IPv4 route replacement" +} + +ipv6_route_addition_test() +{ + RET=0 + + local ip="ipv6" + local route=2001:db8:1::/64 + + # Make sure a single notification will be emitted for the programmed + # route. + local notify=0 + local expected_num_notifications=1 + route_addition_check $ip $notify $route $expected_num_notifications + + # Make sure two notifications will be emitted for the programmed route. + notify=1 + expected_num_notifications=2 + route_addition_check $ip $notify $route $expected_num_notifications + + log_test "IPv6 route addition" +} + +ipv6_route_deletion_test() +{ + RET=0 + + local ip="ipv6" + local route=2001:db8:1::/64 + local expected_num_notifications=1 + + # Make sure a single notification will be emitted for the deleted route, + # regardless of fib_notify_on_flag_change value. + local notify=0 + route_deletion_check $ip $notify $route $expected_num_notifications + + notify=1 + route_deletion_check $ip $notify $route $expected_num_notifications + + log_test "IPv6 route deletion" +} + +ipv6_route_replacement_test() +{ + RET=0 + + local ip="ipv6" + local route=2001:db8:1::/64 + + $IP link add name dummy2 type dummy + $IP link set dev dummy2 up + + # Make sure a single notification will be emitted for the new route. + local notify=0 + local expected_num_notifications=1 + route_replacement_check $ip $notify $route $expected_num_notifications + + # Make sure two notifications will be emitted for the new route. + notify=1 + expected_num_notifications=2 + route_replacement_check $ip $notify $route $expected_num_notifications + + $IP link del name dummy2 + + log_test "IPv6 route replacement" +} + +setup_prepare() +{ + modprobe netdevsim &> /dev/null + echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $SYSFS_NET_DIR ] ; do :; done + + ip netns add testns1 + + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi + + IP="ip -n testns1" + + $IP link add name dummy1 type dummy + $IP link set dev dummy1 up +} + +cleanup() +{ + pre_cleanup + + $IP link del name dummy1 + ip netns del testns1 + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device + modprobe -r netdevsim &> /dev/null +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/nci/Makefile b/tools/testing/selftests/nci/Makefile new file mode 100644 index 000000000000..47669a1d6a59 --- /dev/null +++ b/tools/testing/selftests/nci/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wl,-no-as-needed -Wall +LDFLAGS += -lpthread + +TEST_GEN_PROGS := nci_dev +include ../lib.mk diff --git a/tools/testing/selftests/nci/config b/tools/testing/selftests/nci/config new file mode 100644 index 000000000000..b084e78276be --- /dev/null +++ b/tools/testing/selftests/nci/config @@ -0,0 +1,3 @@ +CONFIG_NFC=y +CONFIG_NFC_NCI=y +CONFIG_NFC_VIRTUAL_NCI=y diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c new file mode 100644 index 000000000000..57b505cb1561 --- /dev/null +++ b/tools/testing/selftests/nci/nci_dev.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Samsung Electrnoics + * Bongsu Jeon <bongsu.jeon@samsung.com> + * + * Test code for nci + */ + +#include <stdlib.h> +#include <errno.h> +#include <string.h> +#include <sys/ioctl.h> +#include <fcntl.h> +#include <pthread.h> +#include <linux/genetlink.h> +#include <sys/socket.h> +#include <linux/nfc.h> + +#include "../kselftest_harness.h" + +#define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) +#define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) +#define NLA_DATA(na) ((void *)((char *)(na) + NLA_HDRLEN)) +#define NLA_PAYLOAD(len) ((len) - NLA_HDRLEN) + +#define MAX_MSG_SIZE 1024 + +#define IOCTL_GET_NCIDEV_IDX 0 +#define VIRTUAL_NFC_PROTOCOLS (NFC_PROTO_JEWEL_MASK | \ + NFC_PROTO_MIFARE_MASK | \ + NFC_PROTO_FELICA_MASK | \ + NFC_PROTO_ISO14443_MASK | \ + NFC_PROTO_ISO14443_B_MASK | \ + NFC_PROTO_ISO15693_MASK) + +const __u8 nci_reset_cmd[] = {0x20, 0x00, 0x01, 0x01}; +const __u8 nci_init_cmd[] = {0x20, 0x01, 0x00}; +const __u8 nci_rf_discovery_cmd[] = {0x21, 0x03, 0x09, 0x04, 0x00, 0x01, + 0x01, 0x01, 0x02, 0x01, 0x06, 0x01}; +const __u8 nci_init_cmd_v2[] = {0x20, 0x01, 0x02, 0x00, 0x00}; +const __u8 nci_rf_disc_map_cmd[] = {0x21, 0x00, 0x07, 0x02, 0x04, 0x03, + 0x02, 0x05, 0x03, 0x03}; +const __u8 nci_rf_deact_cmd[] = {0x21, 0x06, 0x01, 0x00}; +const __u8 nci_reset_rsp[] = {0x40, 0x00, 0x03, 0x00, 0x10, 0x01}; +const __u8 nci_reset_rsp_v2[] = {0x40, 0x00, 0x01, 0x00}; +const __u8 nci_reset_ntf[] = {0x60, 0x00, 0x09, 0x02, 0x01, 0x20, 0x0e, + 0x04, 0x61, 0x00, 0x04, 0x02}; +const __u8 nci_init_rsp[] = {0x40, 0x01, 0x14, 0x00, 0x02, 0x0e, 0x02, + 0x00, 0x03, 0x01, 0x02, 0x03, 0x02, 0xc8, + 0x00, 0xff, 0x10, 0x00, 0x0e, 0x12, 0x00, + 0x00, 0x04}; +const __u8 nci_init_rsp_v2[] = {0x40, 0x01, 0x1c, 0x00, 0x1a, 0x7e, 0x06, + 0x00, 0x02, 0x92, 0x04, 0xff, 0xff, 0x01, + 0x00, 0x40, 0x06, 0x00, 0x00, 0x01, 0x01, + 0x00, 0x02, 0x00, 0x03, 0x01, 0x01, 0x06, + 0x00, 0x80, 0x00}; +const __u8 nci_rf_disc_map_rsp[] = {0x41, 0x00, 0x01, 0x00}; +const __u8 nci_rf_disc_rsp[] = {0x41, 0x03, 0x01, 0x00}; +const __u8 nci_rf_deact_rsp[] = {0x41, 0x06, 0x01, 0x00}; + +struct msgtemplate { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[MAX_MSG_SIZE]; +}; + +static int create_nl_socket(void) +{ + int fd; + struct sockaddr_nl local; + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + if (fd < 0) + return -1; + + memset(&local, 0, sizeof(local)); + local.nl_family = AF_NETLINK; + + if (bind(fd, (struct sockaddr *)&local, sizeof(local)) < 0) + goto error; + + return fd; +error: + close(fd); + return -1; +} + +static int send_cmd_mt_nla(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u8 genl_cmd, int nla_num, __u16 nla_type[], + void *nla_data[], int nla_len[]) +{ + struct sockaddr_nl nladdr; + struct msgtemplate msg; + struct nlattr *na; + int cnt, prv_len; + int r, buflen; + char *buf; + + msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + msg.n.nlmsg_type = nlmsg_type; + msg.n.nlmsg_flags = NLM_F_REQUEST; + msg.n.nlmsg_seq = 0; + msg.n.nlmsg_pid = nlmsg_pid; + msg.g.cmd = genl_cmd; + msg.g.version = 0x1; + + prv_len = 0; + for (cnt = 0; cnt < nla_num; cnt++) { + na = (struct nlattr *)(GENLMSG_DATA(&msg) + prv_len); + na->nla_type = nla_type[cnt]; + na->nla_len = nla_len[cnt] + NLA_HDRLEN; + + if (nla_len > 0) + memcpy(NLA_DATA(na), nla_data[cnt], nla_len[cnt]); + + msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len); + prv_len = na->nla_len; + } + + buf = (char *)&msg; + buflen = msg.n.nlmsg_len; + memset(&nladdr, 0, sizeof(nladdr)); + nladdr.nl_family = AF_NETLINK; + + while ((r = sendto(sd, buf, buflen, 0, (struct sockaddr *)&nladdr, + sizeof(nladdr))) < buflen) { + if (r > 0) { + buf += r; + buflen -= r; + } else if (errno != EAGAIN) { + return -1; + } + } + return 0; +} + +static int send_get_nfc_family(int sd, __u32 pid) +{ + __u16 nla_get_family_type = CTRL_ATTR_FAMILY_NAME; + void *nla_get_family_data; + int nla_get_family_len; + char family_name[100]; + + nla_get_family_len = strlen(NFC_GENL_NAME) + 1; + strcpy(family_name, NFC_GENL_NAME); + nla_get_family_data = family_name; + + return send_cmd_mt_nla(sd, GENL_ID_CTRL, pid, CTRL_CMD_GETFAMILY, + 1, &nla_get_family_type, + &nla_get_family_data, &nla_get_family_len); +} + +static int get_family_id(int sd, __u32 pid) +{ + struct { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[512]; + } ans; + struct nlattr *na; + int rep_len; + __u16 id; + int rc; + + rc = send_get_nfc_family(sd, pid); + + if (rc < 0) + return 0; + + rep_len = recv(sd, &ans, sizeof(ans), 0); + + if (ans.n.nlmsg_type == NLMSG_ERROR || rep_len < 0 || + !NLMSG_OK(&ans.n, rep_len)) + return 0; + + na = (struct nlattr *)GENLMSG_DATA(&ans); + na = (struct nlattr *)((char *)na + NLA_ALIGN(na->nla_len)); + if (na->nla_type == CTRL_ATTR_FAMILY_ID) + id = *(__u16 *)NLA_DATA(na); + + return id; +} + +static int send_cmd_with_idx(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u8 genl_cmd, int dev_id) +{ + __u16 nla_type = NFC_ATTR_DEVICE_INDEX; + void *nla_data = &dev_id; + int nla_len = 4; + + return send_cmd_mt_nla(sd, nlmsg_type, nlmsg_pid, genl_cmd, 1, + &nla_type, &nla_data, &nla_len); +} + +static int get_nci_devid(int sd, __u16 fid, __u32 pid, int dev_id, struct msgtemplate *msg) +{ + int rc, rep_len; + + rc = send_cmd_with_idx(sd, fid, pid, NFC_CMD_GET_DEVICE, dev_id); + if (rc < 0) { + rc = -1; + goto error; + } + + rep_len = recv(sd, msg, sizeof(*msg), 0); + if (rep_len < 0) { + rc = -2; + goto error; + } + + if (msg->n.nlmsg_type == NLMSG_ERROR || + !NLMSG_OK(&msg->n, rep_len)) { + rc = -3; + goto error; + } + + return 0; +error: + return rc; +} + +static __u8 get_dev_enable_state(struct msgtemplate *msg) +{ + struct nlattr *na; + int rep_len; + int len; + + rep_len = GENLMSG_PAYLOAD(&msg->n); + na = (struct nlattr *)GENLMSG_DATA(msg); + len = 0; + + while (len < rep_len) { + len += NLA_ALIGN(na->nla_len); + if (na->nla_type == NFC_ATTR_DEVICE_POWERED) + return *(char *)NLA_DATA(na); + na = (struct nlattr *)(GENLMSG_DATA(msg) + len); + } + + return rep_len; +} + +FIXTURE(NCI) { + int virtual_nci_fd; + bool open_state; + int dev_idex; + bool isNCI2; + int proto; + __u32 pid; + __u16 fid; + int sd; +}; + +FIXTURE_VARIANT(NCI) { + bool isNCI2; +}; + +FIXTURE_VARIANT_ADD(NCI, NCI1_0) { + .isNCI2 = false, +}; + +FIXTURE_VARIANT_ADD(NCI, NCI2_0) { + .isNCI2 = true, +}; + +static void *virtual_dev_open(void *data) +{ + char buf[258]; + int dev_fd; + int len; + + dev_fd = *(int *)data; + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_reset_cmd)) + goto error; + if (memcmp(nci_reset_cmd, buf, len)) + goto error; + write(dev_fd, nci_reset_rsp, sizeof(nci_reset_rsp)); + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_init_cmd)) + goto error; + if (memcmp(nci_init_cmd, buf, len)) + goto error; + write(dev_fd, nci_init_rsp, sizeof(nci_init_rsp)); + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_rf_disc_map_cmd)) + goto error; + if (memcmp(nci_rf_disc_map_cmd, buf, len)) + goto error; + write(dev_fd, nci_rf_disc_map_rsp, sizeof(nci_rf_disc_map_rsp)); + + return (void *)0; +error: + return (void *)-1; +} + +static void *virtual_dev_open_v2(void *data) +{ + char buf[258]; + int dev_fd; + int len; + + dev_fd = *(int *)data; + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_reset_cmd)) + goto error; + if (memcmp(nci_reset_cmd, buf, len)) + goto error; + write(dev_fd, nci_reset_rsp_v2, sizeof(nci_reset_rsp_v2)); + write(dev_fd, nci_reset_ntf, sizeof(nci_reset_ntf)); + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_init_cmd_v2)) + goto error; + if (memcmp(nci_init_cmd_v2, buf, len)) + goto error; + write(dev_fd, nci_init_rsp_v2, sizeof(nci_init_rsp_v2)); + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_rf_disc_map_cmd)) + goto error; + if (memcmp(nci_rf_disc_map_cmd, buf, len)) + goto error; + write(dev_fd, nci_rf_disc_map_rsp, sizeof(nci_rf_disc_map_rsp)); + + return (void *)0; +error: + return (void *)-1; +} + +FIXTURE_SETUP(NCI) +{ + struct msgtemplate msg; + pthread_t thread_t; + int status; + int rc; + + self->open_state = false; + self->proto = VIRTUAL_NFC_PROTOCOLS; + self->isNCI2 = variant->isNCI2; + + self->sd = create_nl_socket(); + ASSERT_NE(self->sd, -1); + + self->pid = getpid(); + self->fid = get_family_id(self->sd, self->pid); + ASSERT_NE(self->fid, -1); + + self->virtual_nci_fd = open("/dev/virtual_nci", O_RDWR); + ASSERT_GT(self->virtual_nci_fd, -1); + + rc = ioctl(self->virtual_nci_fd, IOCTL_GET_NCIDEV_IDX, &self->dev_idex); + ASSERT_EQ(rc, 0); + + rc = get_nci_devid(self->sd, self->fid, self->pid, self->dev_idex, &msg); + ASSERT_EQ(rc, 0); + EXPECT_EQ(get_dev_enable_state(&msg), 0); + + if (self->isNCI2) + rc = pthread_create(&thread_t, NULL, virtual_dev_open_v2, + (void *)&self->virtual_nci_fd); + else + rc = pthread_create(&thread_t, NULL, virtual_dev_open, + (void *)&self->virtual_nci_fd); + ASSERT_GT(rc, -1); + + rc = send_cmd_with_idx(self->sd, self->fid, self->pid, + NFC_CMD_DEV_UP, self->dev_idex); + EXPECT_EQ(rc, 0); + + pthread_join(thread_t, (void **)&status); + ASSERT_EQ(status, 0); + self->open_state = true; +} + +static void *virtual_deinit(void *data) +{ + char buf[258]; + int dev_fd; + int len; + + dev_fd = *(int *)data; + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_reset_cmd)) + goto error; + if (memcmp(nci_reset_cmd, buf, len)) + goto error; + write(dev_fd, nci_reset_rsp, sizeof(nci_reset_rsp)); + + return (void *)0; +error: + return (void *)-1; +} + +static void *virtual_deinit_v2(void *data) +{ + char buf[258]; + int dev_fd; + int len; + + dev_fd = *(int *)data; + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_reset_cmd)) + goto error; + if (memcmp(nci_reset_cmd, buf, len)) + goto error; + write(dev_fd, nci_reset_rsp_v2, sizeof(nci_reset_rsp_v2)); + write(dev_fd, nci_reset_ntf, sizeof(nci_reset_ntf)); + + return (void *)0; +error: + return (void *)-1; +} + +FIXTURE_TEARDOWN(NCI) +{ + pthread_t thread_t; + int status; + int rc; + + if (self->open_state) { + if (self->isNCI2) + rc = pthread_create(&thread_t, NULL, + virtual_deinit_v2, + (void *)&self->virtual_nci_fd); + else + rc = pthread_create(&thread_t, NULL, virtual_deinit, + (void *)&self->virtual_nci_fd); + + ASSERT_GT(rc, -1); + rc = send_cmd_with_idx(self->sd, self->fid, self->pid, + NFC_CMD_DEV_DOWN, self->dev_idex); + EXPECT_EQ(rc, 0); + + pthread_join(thread_t, (void **)&status); + ASSERT_EQ(status, 0); + } + + close(self->sd); + close(self->virtual_nci_fd); + self->open_state = false; +} + +TEST_F(NCI, init) +{ + struct msgtemplate msg; + int rc; + + rc = get_nci_devid(self->sd, self->fid, self->pid, self->dev_idex, + &msg); + ASSERT_EQ(rc, 0); + EXPECT_EQ(get_dev_enable_state(&msg), 1); +} + +static void *virtual_poll_start(void *data) +{ + char buf[258]; + int dev_fd; + int len; + + dev_fd = *(int *)data; + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_rf_discovery_cmd)) + goto error; + if (memcmp(nci_rf_discovery_cmd, buf, len)) + goto error; + write(dev_fd, nci_rf_disc_rsp, sizeof(nci_rf_disc_rsp)) + ; + + return (void *)0; +error: + return (void *)-1; +} + +static void *virtual_poll_stop(void *data) +{ + char buf[258]; + int dev_fd; + int len; + + dev_fd = *(int *)data; + + while ((len = read(dev_fd, buf, 258)) == 0) + ; + if (len <= 0) + goto error; + if (len != sizeof(nci_rf_deact_cmd)) + goto error; + if (memcmp(nci_rf_deact_cmd, buf, len)) + goto error; + write(dev_fd, nci_rf_deact_rsp, sizeof(nci_rf_deact_rsp)); + + return (void *)0; +error: + return (void *)-1; +} + +TEST_F(NCI, start_poll) +{ + __u16 nla_start_poll_type[2] = {NFC_ATTR_DEVICE_INDEX, + NFC_ATTR_PROTOCOLS}; + void *nla_start_poll_data[2] = {&self->dev_idex, &self->proto}; + int nla_start_poll_len[2] = {4, 4}; + pthread_t thread_t; + int status; + int rc; + + rc = pthread_create(&thread_t, NULL, virtual_poll_start, + (void *)&self->virtual_nci_fd); + ASSERT_GT(rc, -1); + + rc = send_cmd_mt_nla(self->sd, self->fid, self->pid, + NFC_CMD_START_POLL, 2, nla_start_poll_type, + nla_start_poll_data, nla_start_poll_len); + EXPECT_EQ(rc, 0); + + pthread_join(thread_t, (void **)&status); + ASSERT_EQ(status, 0); + + rc = pthread_create(&thread_t, NULL, virtual_poll_stop, + (void *)&self->virtual_nci_fd); + ASSERT_GT(rc, -1); + + rc = send_cmd_with_idx(self->sd, self->fid, self->pid, + NFC_CMD_STOP_POLL, self->dev_idex); + EXPECT_EQ(rc, 0); + + pthread_join(thread_t, (void **)&status); + ASSERT_EQ(status, 0); +} + +TEST_F(NCI, deinit) +{ + struct msgtemplate msg; + pthread_t thread_t; + int status; + int rc; + + rc = get_nci_devid(self->sd, self->fid, self->pid, self->dev_idex, + &msg); + ASSERT_EQ(rc, 0); + EXPECT_EQ(get_dev_enable_state(&msg), 1); + + if (self->isNCI2) + rc = pthread_create(&thread_t, NULL, virtual_deinit_v2, + (void *)&self->virtual_nci_fd); + else + rc = pthread_create(&thread_t, NULL, virtual_deinit, + (void *)&self->virtual_nci_fd); + ASSERT_GT(rc, -1); + + rc = send_cmd_with_idx(self->sd, self->fid, self->pid, + NFC_CMD_DEV_DOWN, self->dev_idex); + EXPECT_EQ(rc, 0); + + pthread_join(thread_t, (void **)&status); + self->open_state = 0; + ASSERT_EQ(status, 0); + + rc = get_nci_devid(self->sd, self->fid, self->pid, self->dev_idex, + &msg); + ASSERT_EQ(rc, 0); + EXPECT_EQ(get_dev_enable_state(&msg), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index 388e4492b81b..76efb1f8375e 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -203,7 +203,7 @@ multipath4_test() t0_rp12=$(link_stats_tx_packets_get $rp12) t0_rp13=$(link_stats_tx_packets_get $rp13) - ip vrf exec vrf-h1 $MZ -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ + ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ -d 1msec -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 79a209927962..464821c587a5 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -178,7 +178,7 @@ multipath4_test() t0_rp12=$(link_stats_tx_packets_get $rp12) t0_rp13=$(link_stats_tx_packets_get $rp13) - ip vrf exec vrf-h1 $MZ -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ + ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ -d 1msec -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index be34b9ccbd20..b8fd924033b1 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -209,8 +209,8 @@ do_transfer() srv_proto="$4" connect_addr="$5" test_link_fail="$6" - rm_nr_ns1="$7" - rm_nr_ns2="$8" + addr_nr_ns1="$7" + addr_nr_ns2="$8" speed="$9" bkup="${10}" @@ -264,7 +264,24 @@ do_transfer() fi cpid=$! - if [ $rm_nr_ns1 -gt 0 ]; then + if [ $addr_nr_ns1 -gt 0 ]; then + let add_nr_ns1=addr_nr_ns1 + counter=2 + sleep 1 + while [ $add_nr_ns1 -gt 0 ]; do + local addr + if is_v6 "${connect_addr}"; then + addr="dead:beef:$counter::1" + else + addr="10.0.$counter.1" + fi + ip netns exec $ns1 ./pm_nl_ctl add $addr flags signal + let counter+=1 + let add_nr_ns1-=1 + done + sleep 1 + elif [ $addr_nr_ns1 -lt 0 ]; then + let rm_nr_ns1=-addr_nr_ns1 if [ $rm_nr_ns1 -lt 8 ]; then counter=1 sleep 1 @@ -281,7 +298,24 @@ do_transfer() fi fi - if [ $rm_nr_ns2 -gt 0 ]; then + if [ $addr_nr_ns2 -gt 0 ]; then + let add_nr_ns2=addr_nr_ns2 + counter=3 + sleep 1 + while [ $add_nr_ns2 -gt 0 ]; do + local addr + if is_v6 "${connect_addr}"; then + addr="dead:beef:$counter::2" + else + addr="10.0.$counter.2" + fi + ip netns exec $ns2 ./pm_nl_ctl add $addr flags subflow + let counter+=1 + let add_nr_ns2-=1 + done + sleep 1 + elif [ $addr_nr_ns2 -lt 0 ]; then + let rm_nr_ns2=-addr_nr_ns2 if [ $rm_nr_ns2 -lt 8 ]; then counter=1 sleep 1 @@ -368,8 +402,8 @@ run_tests() connector_ns="$2" connect_addr="$3" test_linkfail="${4:-0}" - rm_nr_ns1="${5:-0}" - rm_nr_ns2="${6:-0}" + addr_nr_ns1="${5:-0}" + addr_nr_ns2="${6:-0}" speed="${7:-fast}" bkup="${8:-""}" lret=0 @@ -386,7 +420,7 @@ run_tests() fi do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${rm_nr_ns1} ${rm_nr_ns2} ${speed} ${bkup} + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} lret=$? if [ "$test_linkfail" -eq 1 ];then @@ -453,6 +487,12 @@ chk_add_nr() { local add_nr=$1 local echo_nr=$2 + local port_nr=${3:-0} + local syn_nr=${4:-$port_nr} + local syn_ack_nr=${5:-$port_nr} + local ack_nr=${6:-$port_nr} + local mis_syn_nr=${7:-0} + local mis_ack_nr=${8:-0} local count local dump_stats @@ -475,7 +515,87 @@ chk_add_nr() ret=1 dump_stats=1 else - echo "[ ok ]" + echo -n "[ ok ]" + fi + + if [ $port_nr -gt 0 ]; then + echo -n " - pt " + count=`ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$port_nr" ]; then + echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + + printf "%-39s %s" " " "syn" + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | + awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$syn_nr" ]; then + echo "[fail] got $count JOIN[s] syn with a different \ + port-number expected $syn_nr" + ret=1 + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - synack" + count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | + awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$syn_ack_nr" ]; then + echo "[fail] got $count JOIN[s] synack with a different \ + port-number expected $syn_ack_nr" + ret=1 + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - ack" + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | + awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$ack_nr" ]; then + echo "[fail] got $count JOIN[s] ack with a different \ + port-number expected $ack_nr" + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + + printf "%-39s %s" " " "syn" + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | + awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$mis_syn_nr" ]; then + echo "[fail] got $count JOIN[s] syn with a mismatched \ + port-number expected $mis_syn_nr" + ret=1 + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - ack " + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | + awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$mis_ack_nr" ]; then + echo "[fail] got $count JOIN[s] ack with a mismatched \ + port-number expected $mis_ack_nr" + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + else + echo "" fi if [ "${dump_stats}" = 1 ]; then @@ -677,7 +797,7 @@ reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow -run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow +run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow chk_join_nr "remove single subflow" 1 1 1 chk_rm_nr 1 1 @@ -687,7 +807,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2 ip netns exec $ns2 ./pm_nl_ctl limits 0 2 ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow -run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow +run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow chk_join_nr "remove multiple subflows" 2 2 2 chk_rm_nr 2 2 @@ -696,7 +816,7 @@ reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 1 -run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow +run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow chk_join_nr "remove single address" 1 1 1 chk_add_nr 1 1 chk_rm_nr 0 0 @@ -707,7 +827,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 2 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow -run_tests $ns1 $ns2 10.0.1.1 0 1 1 slow +run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow chk_join_nr "remove subflow and signal" 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -719,7 +839,7 @@ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 3 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow -run_tests $ns1 $ns2 10.0.1.1 0 1 2 slow +run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow chk_join_nr "remove subflows and signal" 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -731,11 +851,48 @@ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 3 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow -run_tests $ns1 $ns2 10.0.1.1 0 8 8 slow +run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush subflows and signal" 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 +# add single subflow +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 0 1 +run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow +chk_join_nr "add single subflow" 1 1 1 + +# add signal address +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow +chk_join_nr "add signal address" 1 1 1 +chk_add_nr 1 1 + +# add multiple subflows +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow +chk_join_nr "add multiple subflows" 2 2 2 + +# add multiple subflows IPv6 +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 0 2 +run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow +chk_join_nr "add multiple subflows IPv6" 2 2 2 + +# add multiple addresses IPv6 +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 2 2 +run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow +chk_join_nr "add multiple addresses IPv6" 2 2 2 +chk_add_nr 2 2 + # subflow IPv6 reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 @@ -774,7 +931,7 @@ reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 1 -run_tests $ns1 $ns2 dead:beef:1::1 0 1 0 slow +run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow chk_join_nr "remove single address IPv6" 1 1 1 chk_add_nr 1 1 chk_rm_nr 0 0 @@ -785,7 +942,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2 ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 2 ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow -run_tests $ns1 $ns2 dead:beef:1::1 0 1 1 slow +run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow chk_join_nr "remove subflow and signal IPv6" 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -884,6 +1041,78 @@ chk_join_nr "single address, backup" 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 0 +# signal address with port +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "signal address with port" 1 1 1 +chk_add_nr 1 1 1 + +# subflow and signal with port +reset +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns2 ./pm_nl_ctl limits 1 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "subflow and signal with port" 2 2 2 +chk_add_nr 1 1 1 + +# single address with port, remove +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow +chk_join_nr "remove single address with port" 1 1 1 +chk_add_nr 1 1 1 +chk_rm_nr 0 0 + +# subflow and signal with port, remove +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 2 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +ip netns exec $ns2 ./pm_nl_ctl limits 1 2 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow +chk_join_nr "remove subflow and signal with port" 2 2 2 +chk_add_nr 1 1 1 +chk_rm_nr 1 1 + +# subflows and signal with port, flush +reset +ip netns exec $ns1 ./pm_nl_ctl limits 0 3 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +ip netns exec $ns2 ./pm_nl_ctl limits 1 3 +ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow +ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow +run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow +chk_join_nr "flush subflows and signal with port" 3 3 3 +chk_add_nr 1 1 +chk_rm_nr 2 2 + +# multiple addresses with port +reset +ip netns exec $ns1 ./pm_nl_ctl limits 2 2 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10100 +ip netns exec $ns2 ./pm_nl_ctl limits 2 2 +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "multiple addresses with port" 2 2 2 +chk_add_nr 2 2 2 + +# multiple addresses with ports +reset +ip netns exec $ns1 ./pm_nl_ctl limits 2 2 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10101 +ip netns exec $ns2 ./pm_nl_ctl limits 2 2 +run_tests $ns1 $ns2 10.0.1.1 +chk_join_nr "multiple addresses with ports" 2 2 2 +chk_add_nr 2 2 2 + # single subflow, syncookies reset_with_cookies ip netns exec $ns1 ./pm_nl_ctl limits 0 1 diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index abc269e96a07..7b4167f3f9a2 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -177,8 +177,8 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) 1024]; struct rtattr *rta, *nest; struct nlmsghdr *nh; + u_int32_t flags = 0; u_int16_t family; - u_int32_t flags; int nest_start; u_int8_t id; int off = 0; @@ -224,7 +224,6 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) char *tok, *str; /* flags */ - flags = 0; if (++arg >= argc) error(1, 0, " missing flags value"); @@ -272,6 +271,20 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) rta->rta_len = RTA_LENGTH(4); memcpy(RTA_DATA(rta), &ifindex, 4); off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (++arg >= argc) + error(1, 0, " missing port value"); + if (!(flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) + error(1, 0, " flags must be signal when using port"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); } else error(1, 0, "unknown keyword %s", argv[arg]); } @@ -324,6 +337,7 @@ int del_addr(int fd, int pm_family, int argc, char *argv[]) static void print_addr(struct rtattr *attrs, int len) { uint16_t family = 0; + uint16_t port = 0; char str[1024]; uint32_t flags; uint8_t id; @@ -331,12 +345,16 @@ static void print_addr(struct rtattr *attrs, int len) while (RTA_OK(attrs, len)) { if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_FAMILY) memcpy(&family, RTA_DATA(attrs), 2); + if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_PORT) + memcpy(&port, RTA_DATA(attrs), 2); if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR4) { if (family != AF_INET) error(1, errno, "wrong IP (v4) for family %d", family); inet_ntop(AF_INET, RTA_DATA(attrs), str, sizeof(str)); printf("%s", str); + if (port) + printf(" %d", port); } if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ADDR6) { if (family != AF_INET6) @@ -344,6 +362,8 @@ static void print_addr(struct rtattr *attrs, int len) family); inet_ntop(AF_INET6, RTA_DATA(attrs), str, sizeof(str)); printf("%s", str); + if (port) + printf(" %d", port); } if (attrs->rta_type == MPTCP_PM_ADDR_ATTR_ID) { memcpy(&id, RTA_DATA(attrs), 1); diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 7a1bf94c5bd3..bdf450eaf60c 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -202,7 +202,7 @@ check_xfrm() { # 1: iptables -m policy rule count != 0 rval=$1 ip=$2 - lret=0 + local lret=0 ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null @@ -287,6 +287,47 @@ check_hthresh_repeat() return 0 } +# insert non-overlapping policies in a random order and check that +# all of them can be fetched using the traffic selectors. +check_random_order() +{ + local ns=$1 + local log=$2 + + for i in $(seq 100); do + ip -net $ns xfrm policy flush + for j in $(seq 0 16 255 | sort -R); do + ip -net $ns xfrm policy add dst $j.0.0.0/24 dir out priority 10 action allow + done + for j in $(seq 0 16 255); do + if ! ip -net $ns xfrm policy get dst $j.0.0.0/24 dir out > /dev/null; then + echo "FAIL: $log" 1>&2 + return 1 + fi + done + done + + for i in $(seq 100); do + ip -net $ns xfrm policy flush + for j in $(seq 0 16 255 | sort -R); do + local addr=$(printf "e000:0000:%02x00::/56" $j) + ip -net $ns xfrm policy add dst $addr dir out priority 10 action allow + done + for j in $(seq 0 16 255); do + local addr=$(printf "e000:0000:%02x00::/56" $j) + if ! ip -net $ns xfrm policy get dst $addr dir out > /dev/null; then + echo "FAIL: $log" 1>&2 + return 1 + fi + done + done + + ip -net $ns xfrm policy flush + + echo "PASS: $log" + return 0 +} + #check for needed privileges if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" @@ -438,6 +479,8 @@ check_exceptions "exceptions and block policies after htresh change to normal" check_hthresh_repeat "policies with repeated htresh change" +check_random_order ns3 "policies inserted in random order" + for i in 1 2 3 4;do ip netns del ns$i;done exit $ret diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index cb53a8b777e6..c25cf7cd45e9 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -443,7 +443,6 @@ int test_alignment_handler_integer(void) LOAD_DFORM_TEST(ldu); LOAD_XFORM_TEST(ldx); LOAD_XFORM_TEST(ldux); - LOAD_DFORM_TEST(lmw); STORE_DFORM_TEST(stb); STORE_XFORM_TEST(stbx); STORE_DFORM_TEST(stbu); @@ -462,7 +461,11 @@ int test_alignment_handler_integer(void) STORE_XFORM_TEST(stdx); STORE_DFORM_TEST(stdu); STORE_XFORM_TEST(stdux); + +#ifdef __BIG_ENDIAN__ + LOAD_DFORM_TEST(lmw); STORE_DFORM_TEST(stmw); +#endif return rc; } diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c index 9e5c7f3f498a..0af4f02669a1 100644 --- a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c +++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c @@ -290,5 +290,5 @@ static int test(void) int main(void) { - test_harness(test, "pkey_exec_prot"); + return test_harness(test, "pkey_exec_prot"); } diff --git a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c index 4f815d7c1214..2db76e56d4cb 100644 --- a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c +++ b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c @@ -329,5 +329,5 @@ static int test(void) int main(void) { - test_harness(test, "pkey_siginfo"); + return test_harness(test, "pkey_siginfo"); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fa9e3614d30e..8367d88ce39b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1292,6 +1292,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; |