diff options
913 files changed, 19894 insertions, 6987 deletions
diff --git a/.clang-format b/.clang-format index 6ec5558b516b..e92e6dd1780d 100644 --- a/.clang-format +++ b/.clang-format @@ -142,10 +142,13 @@ ForEachMacros: - 'for_each_card_auxs' - 'for_each_card_auxs_safe' - 'for_each_card_components' + - 'for_each_card_dapms' - 'for_each_card_pre_auxs' - 'for_each_card_prelinks' - 'for_each_card_rtds' - 'for_each_card_rtds_safe' + - 'for_each_card_widgets' + - 'for_each_card_widgets_safe' - 'for_each_cgroup_storage_type' - 'for_each_child_of_node' - 'for_each_clear_bit' @@ -160,6 +163,7 @@ ForEachMacros: - 'for_each_cpu_and' - 'for_each_cpu_not' - 'for_each_cpu_wrap' + - 'for_each_dapm_widgets' - 'for_each_dev_addr' - 'for_each_dev_scope' - 'for_each_displayid_db' @@ -170,7 +174,6 @@ ForEachMacros: - 'for_each_dpcm_fe' - 'for_each_drhd_unit' - 'for_each_dss_dev' - - 'for_each_efi_handle' - 'for_each_efi_memory_desc' - 'for_each_efi_memory_desc_in_map' - 'for_each_element' @@ -191,6 +194,7 @@ ForEachMacros: - 'for_each_ip_tunnel_rcu' - 'for_each_irq_nr' - 'for_each_link_codecs' + - 'for_each_link_cpus' - 'for_each_link_platforms' - 'for_each_lru' - 'for_each_matching_node' @@ -250,6 +254,7 @@ ForEachMacros: - 'for_each_pci_bridge' - 'for_each_pci_dev' - 'for_each_pci_msi_entry' + - 'for_each_pcm_streams' - 'for_each_populated_zone' - 'for_each_possible_cpu' - 'for_each_present_cpu' @@ -260,9 +265,12 @@ ForEachMacros: - 'for_each_property_of_node' - 'for_each_registered_fb' - 'for_each_reserved_mem_region' - - 'for_each_rtd_codec_dai' - - 'for_each_rtd_codec_dai_rollback' + - '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' - 'for_each_set_clump8' @@ -334,6 +342,7 @@ ForEachMacros: - 'klp_for_each_object' - 'klp_for_each_object_safe' - 'klp_for_each_object_static' + - 'kunit_suite_for_each_test_case' - 'kvm_for_each_memslot' - 'kvm_for_each_vcpu' - 'list_for_each' @@ -387,6 +396,7 @@ ForEachMacros: - 'of_property_for_each_string' - 'of_property_for_each_u32' - 'pci_bus_for_each_resource' + - 'pcm_for_each_format' - 'ping_portaddr_for_each_entry' - 'plist_for_each' - 'plist_for_each_continue' @@ -482,7 +492,7 @@ KeepEmptyLinesAtTheStartOfBlocks: false MacroBlockBegin: '' MacroBlockEnd: '' MaxEmptyLinesToKeep: 1 -NamespaceIndentation: Inner +NamespaceIndentation: None #ObjCBinPackProtocolList: Auto # Unknown to clang-format-5.0 ObjCBlockIndentWidth: 8 ObjCSpaceAfterProperty: true diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index 664a8f6a634f..3b404577f380 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -124,6 +124,19 @@ Description: authentication is performed (e.g: 802.1x). 'link_mode' attribute will also reflect the dormant state. +What: /sys/class/net/<iface>/testing +Date: April 2002 +KernelVersion: 5.8 +Contact: netdev@vger.kernel.org +Description: + Indicates whether the interface is under test. Possible + values are: + 0: interface is not being tested + 1: interface is being tested + + When an interface is under test, it cannot be expected + to pass packets as normal. + What: /sys/clas/net/<iface>/duplex Date: October 2009 KernelVersion: 2.6.33 diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 39c95c0e13d3..0d427fd10941 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -390,9 +390,17 @@ When ``kptr_restrict`` is set to 2, kernel pointers printed using modprobe ======== -This gives the full path of the modprobe command which the kernel will -use to load modules. This can be used to debug module loading -requests:: +The full path to the usermode helper for autoloading kernel modules, +by default "/sbin/modprobe". This binary is executed when the kernel +requests a module. For example, if userspace passes an unknown +filesystem type to mount(), then the kernel will automatically request +the corresponding filesystem module by executing this usermode helper. +This usermode helper should insert the needed module into the kernel. + +This sysctl only affects module autoloading. It has no effect on the +ability to explicitly insert modules. + +This sysctl can be used to debug module loading requests:: echo '#! /bin/sh' > /tmp/modprobe echo 'echo "$@" >> /tmp/modprobe.log' >> /tmp/modprobe @@ -400,10 +408,15 @@ requests:: chmod a+x /tmp/modprobe echo /tmp/modprobe > /proc/sys/kernel/modprobe -This only applies when the *kernel* is requesting that the module be -loaded; it won't have any effect if the module is being loaded -explicitly using ``modprobe`` from userspace. +Alternatively, if this sysctl is set to the empty string, then module +autoloading is completely disabled. The kernel will not try to +execute a usermode helper at all, nor will it call the +kernel_module_request LSM hook. +If CONFIG_STATIC_USERMODEHELPER=y is set in the kernel configuration, +then the configured static usermode helper overrides this sysctl, +except that the empty string is still accepted to completely disable +module autoloading as described above. modules_disabled ================ @@ -446,28 +459,6 @@ Notes: successful IPC object allocation. If an IPC object allocation syscall fails, it is undefined if the value remains unmodified or is reset to -1. -modprobe: -========= - -The path to the usermode helper for autoloading kernel modules, by -default "/sbin/modprobe". This binary is executed when the kernel -requests a module. For example, if userspace passes an unknown -filesystem type to mount(), then the kernel will automatically request -the corresponding filesystem module by executing this usermode helper. -This usermode helper should insert the needed module into the kernel. - -This sysctl only affects module autoloading. It has no effect on the -ability to explicitly insert modules. - -If this sysctl is set to the empty string, then module autoloading is -completely disabled. The kernel will not try to execute a usermode -helper at all, nor will it call the kernel_module_request LSM hook. - -If CONFIG_STATIC_USERMODEHELPER=y is set in the kernel configuration, -then the configured static usermode helper overrides this sysctl, -except that the empty string is still accepted to completely disable -module autoloading as described above. - nmi_watchdog ============ diff --git a/Documentation/arm64/amu.rst b/Documentation/arm64/amu.rst index 5057b11100ed..036783ee327f 100644 --- a/Documentation/arm64/amu.rst +++ b/Documentation/arm64/amu.rst @@ -23,13 +23,14 @@ optional external memory-mapped interface. Version 1 of the Activity Monitors architecture implements a counter group of four fixed and architecturally defined 64-bit event counters. - - CPU cycle counter: increments at the frequency of the CPU. - - Constant counter: increments at the fixed frequency of the system - clock. - - Instructions retired: increments with every architecturally executed - instruction. - - Memory stall cycles: counts instruction dispatch stall cycles caused by - misses in the last level cache within the clock domain. + +- CPU cycle counter: increments at the frequency of the CPU. +- Constant counter: increments at the fixed frequency of the system + clock. +- Instructions retired: increments with every architecturally executed + instruction. +- Memory stall cycles: counts instruction dispatch stall cycles caused by + misses in the last level cache within the clock domain. When in WFI or WFE these counters do not increment. @@ -57,11 +58,12 @@ counters, only the presence of the extension. Firmware (code running at higher exception levels, e.g. arm-tf) support is needed to: - - Enable access for lower exception levels (EL2 and EL1) to the AMU - registers. - - Enable the counters. If not enabled these will read as 0. - - Save/restore the counters before/after the CPU is being put/brought up - from the 'off' power state. + +- Enable access for lower exception levels (EL2 and EL1) to the AMU + registers. +- Enable the counters. If not enabled these will read as 0. +- Save/restore the counters before/after the CPU is being put/brought up + from the 'off' power state. When using kernels that have this feature enabled but boot with broken firmware the user may experience panics or lockups when accessing the @@ -78,10 +80,11 @@ are not trapped in EL2/EL3. The fixed counters of AMUv1 are accessible though the following system register definitions: - - SYS_AMEVCNTR0_CORE_EL0 - - SYS_AMEVCNTR0_CONST_EL0 - - SYS_AMEVCNTR0_INST_RET_EL0 - - SYS_AMEVCNTR0_MEM_STALL_EL0 + +- SYS_AMEVCNTR0_CORE_EL0 +- SYS_AMEVCNTR0_CONST_EL0 +- SYS_AMEVCNTR0_INST_RET_EL0 +- SYS_AMEVCNTR0_MEM_STALL_EL0 Auxiliary platform specific counters can be accessed using SYS_AMEVCNTR1_EL0(n), where n is a value between 0 and 15. @@ -93,9 +96,10 @@ Userspace access ---------------- Currently, access from userspace to the AMU registers is disabled due to: - - Security reasons: they might expose information about code executed in - secure mode. - - Purpose: AMU counters are intended for system management use. + +- Security reasons: they might expose information about code executed in + secure mode. +- Purpose: AMU counters are intended for system management use. Also, the presence of the feature is not visible to userspace. @@ -105,8 +109,9 @@ Virtualization Currently, access from userspace (EL0) and kernelspace (EL1) on the KVM guest side is disabled due to: - - Security reasons: they might expose information about code executed - by other guests or the host. + +- Security reasons: they might expose information about code executed + by other guests or the host. Any attempt to access the AMU registers will result in an UNDEFINED exception being injected into the guest. diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst index c0ffa30c7c37..729e24864fe7 100644 --- a/Documentation/core-api/timekeeping.rst +++ b/Documentation/core-api/timekeeping.rst @@ -154,9 +154,9 @@ architectures. These are the recommended replacements: Use ktime_get() or ktime_get_ts64() instead. -.. c:function:: struct timeval do_gettimeofday( void ) - struct timespec getnstimeofday( void ) - struct timespec64 getnstimeofday64( void ) +.. c:function:: void do_gettimeofday( struct timeval * ) + void getnstimeofday( struct timespec * ) + void getnstimeofday64( struct timespec64 * ) void ktime_get_real_ts( struct timespec * ) ktime_get_real_ts64() is a direct replacement, but consider using diff --git a/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml b/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml index aa0738b4d534..e713a6fe4cf7 100644 --- a/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml +++ b/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml @@ -42,6 +42,10 @@ properties: description: See section 2.3.9 of the DeviceTree Specification. + '#address-cells': true + + '#size-cells': true + required: - "#interconnect-cells" - compatible @@ -59,6 +63,8 @@ examples: compatible = "allwinner,sun5i-a13-mbus"; reg = <0x01c01000 0x1000>; clocks = <&ccu CLK_MBUS>; + #address-cells = <1>; + #size-cells = <1>; dma-ranges = <0x00000000 0x40000000 0x20000000>; #interconnect-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml b/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml index de9a465096db..444aeea27db8 100644 --- a/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml +++ b/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml @@ -91,7 +91,7 @@ required: examples: - | - vco1: clock@00 { + vco1: clock { compatible = "arm,impd1-vco1"; #clock-cells = <0>; lock-offset = <0x08>; diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt index a6b2b2b8f3d9..d3c2a4914ea2 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt @@ -1,5 +1,5 @@ -Analog Device ADV7123 Video DAC -------------------------------- +Analog Devices ADV7123 Video DAC +-------------------------------- The ADV7123 is a digital-to-analog converter that outputs VGA signals from a parallel video input. diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt index e8ddec5d9d91..659523f538bf 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt @@ -1,5 +1,5 @@ -Analog Device ADV7511(W)/13/33/35 HDMI Encoders ------------------------------------------ +Analog Devices ADV7511(W)/13/33/35 HDMI Encoders +------------------------------------------------ The ADV7511, ADV7511W, ADV7513, ADV7533 and ADV7535 are HDMI audio and video transmitters compatible with HDMI 1.4 and DVI 1.0. They support color space diff --git a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml index fd931b293816..b900973b5f7b 100644 --- a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml +++ b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml @@ -37,7 +37,6 @@ examples: dsi { #address-cells = <1>; #size-cells = <0>; - reg = <0xff450000 0x1000>; panel@0 { compatible = "leadtek,ltk500hd1829"; diff --git a/Documentation/devicetree/bindings/display/panel/lvds.yaml b/Documentation/devicetree/bindings/display/panel/lvds.yaml index d0083301acbe..946dd354256c 100644 --- a/Documentation/devicetree/bindings/display/panel/lvds.yaml +++ b/Documentation/devicetree/bindings/display/panel/lvds.yaml @@ -96,12 +96,20 @@ properties: If set, reverse the bit order described in the data mappings below on all data lanes, transmitting bits for slots 6 to 0 instead of 0 to 6. + port: true + ports: true + required: - compatible - data-mapping - width-mm - height-mm - panel-timing - - port + +oneOf: + - required: + - port + - required: + - ports ... diff --git a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml index d9fdb58e06b4..6913923df569 100644 --- a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml +++ b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml @@ -37,7 +37,6 @@ examples: dsi { #address-cells = <1>; #size-cells = <0>; - reg = <0xff450000 0x1000>; panel@0 { compatible = "xinpeng,xpp055c272"; diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt index b38ee732efa9..cd17684aaab5 100644 --- a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt +++ b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt @@ -1,4 +1,4 @@ -Analog Device AXI-DMAC DMA controller +Analog Devices AXI-DMAC DMA controller Required properties: - compatible: Must be "adi,axi-dmac-1.00.a". diff --git a/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml b/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml index 57a240d2d026..7db78767c02d 100644 --- a/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml +++ b/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml @@ -2,7 +2,7 @@ # Copyright 2019 Analog Devices Inc. %YAML 1.2 --- -$id: http://devicetree.org/schemas/bindings/hwmon/adi,axi-fan-control.yaml# +$id: http://devicetree.org/schemas/hwmon/adi,axi-fan-control.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Analog Devices AXI FAN Control Device Tree Bindings @@ -47,7 +47,7 @@ required: examples: - | - fpga_axi: fpga-axi@0 { + fpga_axi: fpga-axi { #address-cells = <0x2>; #size-cells = <0x1>; diff --git a/Documentation/devicetree/bindings/hwmon/adt7475.yaml b/Documentation/devicetree/bindings/hwmon/adt7475.yaml index 76985034ea73..46c441574f98 100644 --- a/Documentation/devicetree/bindings/hwmon/adt7475.yaml +++ b/Documentation/devicetree/bindings/hwmon/adt7475.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/adt7475.yaml# +$id: http://devicetree.org/schemas/hwmon/adt7475.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: ADT7475 hwmon sensor diff --git a/Documentation/devicetree/bindings/iio/dac/ad5755.txt b/Documentation/devicetree/bindings/iio/dac/ad5755.txt index f0bbd7e1029b..502e1e55adbd 100644 --- a/Documentation/devicetree/bindings/iio/dac/ad5755.txt +++ b/Documentation/devicetree/bindings/iio/dac/ad5755.txt @@ -1,4 +1,4 @@ -* Analog Device AD5755 IIO Multi-Channel DAC Linux Driver +* Analog Devices AD5755 IIO Multi-Channel DAC Linux Driver Required properties: - compatible: Has to contain one of the following: diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml index d9c25cf4b92f..58d81ca43460 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml @@ -2,7 +2,7 @@ # Copyright 2020 Analog Devices Inc. %YAML 1.2 --- -$id: http://devicetree.org/schemas/bindings/iio/dac/adi,ad5770r.yaml# +$id: http://devicetree.org/schemas/iio/dac/adi,ad5770r.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Analog Devices AD5770R DAC device driver @@ -49,93 +49,86 @@ properties: asserted during driver probe. maxItems: 1 - channel0: + channel@0: description: Represents an external channel which are connected to the DAC. Channel 0 can act both as a current source and sink. type: object properties: - num: + reg: description: This represents the channel number. - items: - const: 0 + const: 0 adi,range-microamp: description: Output range of the channel. oneOf: - - $ref: /schemas/types.yaml#/definitions/int32-array - items: - - enum: [0 300000] - - enum: [-60000 0] - - enum: [-60000 300000] + - const: 0 + - const: 300000 + - items: + - const: -60000 + - const: 0 + - items: + - const: -60000 + - const: 300000 - channel1: + channel@1: description: Represents an external channel which are connected to the DAC. type: object properties: - num: + reg: description: This represents the channel number. - items: - const: 1 + const: 1 adi,range-microamp: description: Output range of the channel. - oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32-array - - items: - - enum: [0 140000] - - enum: [0 250000] + items: + - const: 0 + - enum: [ 140000, 250000 ] - channel2: + channel@2: description: Represents an external channel which are connected to the DAC. type: object properties: - num: + reg: description: This represents the channel number. - items: - const: 2 + const: 2 adi,range-microamp: description: Output range of the channel. - oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32-array - - items: - - enum: [0 140000] - - enum: [0 250000] + items: + - const: 0 + - enum: [ 55000, 150000 ] patternProperties: "^channel@([3-5])$": type: object description: Represents the external channels which are connected to the DAC. properties: - num: + reg: description: This represents the channel number. - items: - minimum: 3 - maximum: 5 + minimum: 3 + maximum: 5 adi,range-microamp: description: Output range of the channel. - oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32-array - - items: - - enum: [0 45000] - - enum: [0 100000] + items: + - const: 0 + - enum: [ 45000, 100000 ] required: - reg -- diff-channels -- channel0 -- channel1 -- channel2 -- channel3 -- channel4 -- channel5 +- channel@0 +- channel@1 +- channel@2 +- channel@3 +- channel@4 +- channel@5 examples: - | @@ -144,40 +137,42 @@ examples: #size-cells = <0>; ad5770r@0 { - compatible = "ad5770r"; + compatible = "adi,ad5770r"; reg = <0>; spi-max-frequency = <1000000>; vref-supply = <&vref>; adi,external-resistor; reset-gpios = <&gpio 22 0>; + #address-cells = <1>; + #size-cells = <0>; channel@0 { - num = <0>; - adi,range-microamp = <(-60000) 300000>; + reg = <0>; + adi,range-microamp = <0 300000>; }; channel@1 { - num = <1>; + reg = <1>; adi,range-microamp = <0 140000>; }; channel@2 { - num = <2>; + reg = <2>; adi,range-microamp = <0 55000>; }; channel@3 { - num = <3>; + reg = <3>; adi,range-microamp = <0 45000>; }; channel@4 { - num = <4>; + reg = <4>; adi,range-microamp = <0 45000>; }; channel@5 { - num = <5>; + reg = <5>; adi,range-microamp = <0 45000>; }; }; diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml index 8d58709d4b47..383d64a91854 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml +++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml @@ -109,7 +109,7 @@ examples: - | #include <dt-bindings/gpio/gpio.h> #include <dt-bindings/interrupt-controller/arm-gic.h> - i2c@00000000 { + i2c { #address-cells = <1>; #size-cells = <0>; edt-ft5x06@38 { diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml index 9c6b91fee477..26f1fcf0857a 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml @@ -56,9 +56,8 @@ properties: cell with zero. allOf: - $ref: /schemas/types.yaml#/definitions/uint32-array - - items: - minItems: 4 - maxItems: 4 + - minItems: 4 + maxItems: 4 required: diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml index 12516bd89cf9..611bda38d187 100644 --- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml @@ -97,30 +97,35 @@ examples: #include <dt-bindings/clock/tegra186-clock.h> #include <dt-bindings/interrupt-controller/arm-gic.h> - memory-controller@2c00000 { - compatible = "nvidia,tegra186-mc"; - reg = <0x0 0x02c00000 0x0 0xb0000>; - interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>; - + bus { #address-cells = <2>; #size-cells = <2>; - ranges = <0x0 0x02c00000 0x02c00000 0x0 0xb0000>; + memory-controller@2c00000 { + compatible = "nvidia,tegra186-mc"; + reg = <0x0 0x02c00000 0x0 0xb0000>; + interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>; + + #address-cells = <2>; + #size-cells = <2>; + + ranges = <0x0 0x02c00000 0x0 0x02c00000 0x0 0xb0000>; - /* - * Memory clients have access to all 40 bits that the memory - * controller can address. - */ - dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x0>; + /* + * Memory clients have access to all 40 bits that the memory + * controller can address. + */ + dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x0>; - external-memory-controller@2c60000 { - compatible = "nvidia,tegra186-emc"; - reg = <0x0 0x02c60000 0x0 0x50000>; - interrupts = <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&bpmp TEGRA186_CLK_EMC>; - clock-names = "emc"; + external-memory-controller@2c60000 { + compatible = "nvidia,tegra186-emc"; + reg = <0x0 0x02c60000 0x0 0x50000>; + interrupts = <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&bpmp TEGRA186_CLK_EMC>; + clock-names = "emc"; - nvidia,bpmp = <&bpmp>; + nvidia,bpmp = <&bpmp>; + }; }; }; diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml index aa922c560fcc..65018a019e1d 100644 --- a/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml @@ -123,7 +123,9 @@ examples: #include <dt-bindings/leds/common.h> i2c { - pmic: pmic@4b { + #address-cells = <1>; + #size-cells = <0>; + pmic: pmic@4b { compatible = "rohm,bd71837"; reg = <0x4b>; interrupt-parent = <&gpio1>; diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml index 402e40dfe0b8..77bcca2d414f 100644 --- a/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml @@ -128,7 +128,9 @@ examples: #include <dt-bindings/leds/common.h> i2c { - pmic: pmic@4b { + #address-cells = <1>; + #size-cells = <0>; + pmic: pmic@4b { compatible = "rohm,bd71847"; reg = <0x4b>; interrupt-parent = <&gpio1>; diff --git a/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml b/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml index d9ad9260e348..f88d13d70441 100644 --- a/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml +++ b/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml @@ -274,7 +274,7 @@ examples: - | #include <dt-bindings/mfd/st,stpmic1.h> #include <dt-bindings/interrupt-controller/arm-gic.h> - i2c@0 { + i2c { #address-cells = <1>; #size-cells = <0>; pmic@33 { diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml index 8927941c74bb..9b1f1147ca36 100644 --- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml @@ -45,6 +45,9 @@ properties: bits of a vendor specific ID. - items: - pattern: "^ethernet-phy-id[a-f0-9]{4}\\.[a-f0-9]{4}$" + - const: ethernet-phy-ieee802.3-c22 + - items: + - pattern: "^ethernet-phy-id[a-f0-9]{4}\\.[a-f0-9]{4}$" - const: ethernet-phy-ieee802.3-c45 reg: @@ -78,7 +81,8 @@ properties: $ref: /schemas/types.yaml#definitions/flag description: If set, indicates the PHY device does not correctly release - the turn around line low at the end of a MDIO transaction. + the turn around line low at end of the control phase of the + MDIO transaction. enet-phy-lane-swap: $ref: /schemas/types.yaml#definitions/flag diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt index 5b88fae0307d..26c492a2e0e1 100644 --- a/Documentation/devicetree/bindings/net/fsl-fec.txt +++ b/Documentation/devicetree/bindings/net/fsl-fec.txt @@ -22,6 +22,8 @@ Optional properties: - fsl,err006687-workaround-present: If present indicates that the system has the hardware workaround for ERR006687 applied and does not need a software workaround. +- gpr: phandle of SoC general purpose register mode. Required for wake on LAN + on some SoCs -interrupt-names: names of the interrupts listed in interrupts property in the same order. The defaults if not specified are __Number of interrupts__ __Default__ @@ -80,6 +82,7 @@ ethernet@83fec000 { phy-supply = <®_fec_supply>; phy-handle = <ðphy>; mdio { + clock-frequency = <5000000>; ethphy: ethernet-phy@6 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <6>; diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index 50c3397a82bc..d6a3bf8550eb 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -31,13 +31,25 @@ properties: maxItems: 1 description: The phandle and specifier for the GPIO that controls the RESET - lines of all PHYs on that MDIO bus. + lines of all devices on that MDIO bus. reset-delay-us: description: - RESET pulse width in microseconds. It applies to all PHY devices - and must therefore be appropriately determined based on all PHY - requirements (maximum value of all per-PHY RESET pulse widths). + RESET pulse width in microseconds. It applies to all MDIO devices + and must therefore be appropriately determined based on all devices + requirements (maximum value of all per-device RESET pulse widths). + + clock-frequency: + description: + Desired MDIO bus clock frequency in Hz. Values greater than IEEE 802.3 + defined 2.5MHz should only be used when all devices on the bus support + the given clock speed. + + suppress-preamble: + description: + The 32 bit preamble should be suppressed. In order for this to + work, all devices on the bus must support suppressed preamble. + type: boolean patternProperties: "^ethernet-phy@[0-9a-f]+$": @@ -48,7 +60,35 @@ patternProperties: minimum: 0 maximum: 31 description: - The ID number for the PHY. + The ID number for the device. + + broken-turn-around: + $ref: /schemas/types.yaml#definitions/flag + description: + If set, indicates the MDIO device does not correctly release + the turn around line low at end of the control phase of the + MDIO transaction. + + resets: + maxItems: 1 + + reset-names: + const: phy + + reset-gpios: + maxItems: 1 + description: + The GPIO phandle and specifier for the MDIO reset signal. + + reset-assert-us: + description: + Delay after the reset was asserted in microseconds. If this + property is missing the delay will be skipped. + + reset-deassert-us: + description: + Delay after the reset was deasserted in microseconds. If + this property is missing the delay will be skipped. required: - reg diff --git a/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml b/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml new file mode 100644 index 000000000000..42be0255512b --- /dev/null +++ b/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: GPL-2.0+ +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nxp,tja11xx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP TJA11xx PHY + +maintainers: + - Andrew Lunn <andrew@lunn.ch> + - Florian Fainelli <f.fainelli@gmail.com> + - Heiner Kallweit <hkallweit1@gmail.com> + +description: + Bindings for NXP TJA11xx automotive PHYs + +allOf: + - $ref: ethernet-phy.yaml# + +patternProperties: + "^ethernet-phy@[0-9a-f]+$": + type: object + description: | + Some packages have multiple PHYs. Secondary PHY should be defines as + subnode of the first (parent) PHY. + + properties: + reg: + minimum: 0 + maximum: 31 + description: + The ID number for the child PHY. Should be +1 of parent PHY. + + required: + - reg + +examples: + - | + mdio { + #address-cells = <1>; + #size-cells = <0>; + + tja1101_phy0: ethernet-phy@4 { + reg = <0x4>; + }; + }; + - | + mdio { + #address-cells = <1>; + #size-cells = <0>; + + tja1102_phy0: ethernet-phy@4 { + reg = <0x4>; + #address-cells = <1>; + #size-cells = <0>; + + tja1102_phy1: ethernet-phy@5 { + reg = <0x5>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml index b9f90081046f..67df3fe861ee 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml @@ -48,6 +48,7 @@ examples: switch@10 { compatible = "qca,qca8337"; + reg = <0x10>; /* ... */ }; }; diff --git a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt index beca6466d59a..aad2632c6443 100644 --- a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt +++ b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt @@ -13,6 +13,7 @@ Required properties: * "qcom,wcn3990-bt" * "qcom,wcn3991-bt" * "qcom,wcn3998-bt" + * "qcom,qca6390-bt" Optional properties for compatible string qcom,qca6174-bt: @@ -29,7 +30,7 @@ Required properties for compatible string qcom,wcn399x-bt: Optional properties for compatible string qcom,wcn399x-bt: - - max-speed: see Documentation/devicetree/bindings/serial/slave-device.txt + - max-speed: see Documentation/devicetree/bindings/serial/serial.yaml - firmware-name: specify the name of nvm firmware to load - clocks: clock provided to the controller diff --git a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml index fd1982c56104..3f913d6d1c3d 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml @@ -146,7 +146,7 @@ patternProperties: bindings specified in Documentation/devicetree/bindings/phy/phy-cadence-sierra.txt Torrent SERDES should follow the bindings specified in - Documentation/devicetree/bindings/phy/phy-cadence-dp.txt + Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml required: - compatible diff --git a/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml b/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml index 24c217b76580..41ece1d85315 100644 --- a/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml @@ -31,10 +31,17 @@ additionalProperties: false examples: - | - cros-ec@0 { - compatible = "google,cros-ec-spi"; - cros_ec_pwm: ec-pwm { - compatible = "google,cros-ec-pwm"; - #pwm-cells = <1>; + spi { + #address-cells = <1>; + #size-cells = <0>; + + cros-ec@0 { + compatible = "google,cros-ec-spi"; + reg = <0>; + + cros_ec_pwm: ec-pwm { + compatible = "google,cros-ec-pwm"; + #pwm-cells = <1>; + }; }; }; diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml b/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml index 89ab67f20a7f..c147900f9041 100644 --- a/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml +++ b/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml @@ -39,7 +39,7 @@ additionalProperties: false examples: - | - rng { + rng@7e104000 { compatible = "brcm,bcm2835-rng"; reg = <0x7e104000 0x10>; interrupts = <2 29>; diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml b/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml index 7cd0e278ed85..a3ba2186d6a1 100644 --- a/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml +++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml @@ -56,6 +56,9 @@ properties: - const: tx - const: rx + power-domains: + maxItems: 1 + rockchip,capture-channels: allOf: - $ref: /schemas/types.yaml#/definitions/uint32 diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.txt b/Documentation/devicetree/bindings/sound/rockchip-spdif.txt deleted file mode 100644 index ec20c1271e92..000000000000 --- a/Documentation/devicetree/bindings/sound/rockchip-spdif.txt +++ /dev/null @@ -1,45 +0,0 @@ -* Rockchip SPDIF transceiver - -The S/PDIF audio block is a stereo transceiver that allows the -processor to receive and transmit digital audio via an coaxial cable or -a fibre cable. - -Required properties: - -- compatible: should be one of the following: - - "rockchip,rk3066-spdif" - - "rockchip,rk3188-spdif" - - "rockchip,rk3228-spdif" - - "rockchip,rk3288-spdif" - - "rockchip,rk3328-spdif" - - "rockchip,rk3366-spdif" - - "rockchip,rk3368-spdif" - - "rockchip,rk3399-spdif" -- reg: physical base address of the controller and length of memory mapped - region. -- interrupts: should contain the SPDIF interrupt. -- dmas: DMA specifiers for tx dma. See the DMA client binding, - Documentation/devicetree/bindings/dma/dma.txt -- dma-names: should be "tx" -- clocks: a list of phandle + clock-specifier pairs, one for each entry - in clock-names. -- clock-names: should contain following: - - "hclk": clock for SPDIF controller - - "mclk" : clock for SPDIF bus - -Required properties on RK3288: - - rockchip,grf: the phandle of the syscon node for the general register - file (GRF) - -Example for the rk3188 SPDIF controller: - -spdif: spdif@1011e000 { - compatible = "rockchip,rk3188-spdif", "rockchip,rk3066-spdif"; - reg = <0x1011e000 0x2000>; - interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; - dmas = <&dmac1_s 8>; - dma-names = "tx"; - clock-names = "hclk", "mclk"; - clocks = <&cru HCLK_SPDIF>, <&cru SCLK_SPDIF>; - #sound-dai-cells = <0>; -}; diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml new file mode 100644 index 000000000000..c467152656f7 --- /dev/null +++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml @@ -0,0 +1,101 @@ +# SPDX-License-Identifier: GPL-2.0 +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/sound/rockchip-spdif.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Rockchip SPDIF transceiver + +description: + The S/PDIF audio block is a stereo transceiver that allows the + processor to receive and transmit digital audio via a coaxial or + fibre cable. + +maintainers: + - Heiko Stuebner <heiko@sntech.de> + +properties: + compatible: + oneOf: + - const: rockchip,rk3066-spdif + - const: rockchip,rk3228-spdif + - const: rockchip,rk3328-spdif + - const: rockchip,rk3366-spdif + - const: rockchip,rk3368-spdif + - const: rockchip,rk3399-spdif + - items: + - enum: + - rockchip,rk3188-spdif + - rockchip,rk3288-spdif + - const: rockchip,rk3066-spdif + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + items: + - description: clock for SPDIF bus + - description: clock for SPDIF controller + + clock-names: + items: + - const: mclk + - const: hclk + + dmas: + maxItems: 1 + + dma-names: + const: tx + + power-domains: + maxItems: 1 + + rockchip,grf: + $ref: /schemas/types.yaml#/definitions/phandle + description: + The phandle of the syscon node for the GRF register. + Required property on RK3288. + + "#sound-dai-cells": + const: 0 + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - dmas + - dma-names + - "#sound-dai-cells" + +if: + properties: + compatible: + contains: + const: rockchip,rk3288-spdif + +then: + required: + - rockchip,grf + +additionalProperties: false + +examples: + - | + #include <dt-bindings/clock/rk3188-cru.h> + #include <dt-bindings/interrupt-controller/arm-gic.h> + spdif: spdif@1011e000 { + compatible = "rockchip,rk3188-spdif", "rockchip,rk3066-spdif"; + reg = <0x1011e000 0x2000>; + interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&cru SCLK_SPDIF>, <&cru HCLK_SPDIF>; + clock-names = "mclk", "hclk"; + dmas = <&dmac1_s 8>; + dma-names = "tx"; + #sound-dai-cells = <0>; + }; diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml index 0cf470eaf2a0..5c16cf59ca00 100644 --- a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml +++ b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml @@ -61,7 +61,7 @@ examples: #include <dt-bindings/clock/qcom,gcc-sdm845.h> #include <dt-bindings/interrupt-controller/arm-gic.h> - soc: soc@0 { + soc: soc { #address-cells = <2>; #size-cells = <2>; diff --git a/Documentation/devicetree/bindings/usb/ingenic,musb.yaml b/Documentation/devicetree/bindings/usb/ingenic,musb.yaml index 1d6877875077..c2d2ee43ba67 100644 --- a/Documentation/devicetree/bindings/usb/ingenic,musb.yaml +++ b/Documentation/devicetree/bindings/usb/ingenic,musb.yaml @@ -56,7 +56,7 @@ additionalProperties: false examples: - | #include <dt-bindings/clock/jz4740-cgu.h> - usb_phy: usb-phy@0 { + usb_phy: usb-phy { compatible = "usb-nop-xceiv"; #phy-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.txt b/Documentation/devicetree/bindings/usb/qcom,dwc3.txt index cb695aa3fba4..fbdd01756752 100644 --- a/Documentation/devicetree/bindings/usb/qcom,dwc3.txt +++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.txt @@ -52,8 +52,8 @@ A child node must exist to represent the core DWC3 IP block. The name of the node is not important. The content of the node is defined in dwc3.txt. Phy documentation is provided in the following places: -Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt - USB3 QMP PHY -Documentation/devicetree/bindings/phy/qcom-qusb2-phy.txt - USB2 QUSB2 PHY +Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt - USB3 QMP PHY +Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml - USB2 QUSB2 PHY Example device nodes: diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt index c8c4b00ecb94..94520493233b 100644 --- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt +++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt @@ -16,7 +16,7 @@ A child node must exist to represent the core DWC3 IP block. The name of the node is not important. The content of the node is defined in dwc3.txt. Phy documentation is provided in the following places: -Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY +Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.yaml - USB2.0 PHY Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt - Type-C PHY Example device nodes: diff --git a/Documentation/hwmon/bcm54140.rst b/Documentation/hwmon/bcm54140.rst new file mode 100644 index 000000000000..bc6ea4b45966 --- /dev/null +++ b/Documentation/hwmon/bcm54140.rst @@ -0,0 +1,45 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +Broadcom BCM54140 Quad SGMII/QSGMII PHY +======================================= + +Supported chips: + + * Broadcom BCM54140 + + Datasheet: not public + +Author: Michael Walle <michael@walle.cc> + +Description +----------- + +The Broadcom BCM54140 is a Quad SGMII/QSGMII PHY which supports monitoring +its die temperature as well as two analog voltages. + +The AVDDL is a 1.0V analogue voltage, the AVDDH is a 3.3V analogue voltage. +Both voltages and the temperature are measured in a round-robin fashion. + +Sysfs entries +------------- + +The following attributes are supported. + +======================= ======================================================== +in0_label "AVDDL" +in0_input Measured AVDDL voltage. +in0_min Minimum AVDDL voltage. +in0_max Maximum AVDDL voltage. +in0_alarm AVDDL voltage alarm. + +in1_label "AVDDH" +in1_input Measured AVDDH voltage. +in1_min Minimum AVDDH voltage. +in1_max Maximum AVDDH voltage. +in1_alarm AVDDH voltage alarm. + +temp1_input Die temperature. +temp1_min Minimum die temperature. +temp1_max Maximum die temperature. +temp1_alarm Die temperature alarm. +======================= ======================================================== diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst index 8ef62fd39787..1f0affb3b6e0 100644 --- a/Documentation/hwmon/index.rst +++ b/Documentation/hwmon/index.rst @@ -42,6 +42,7 @@ Hardware Monitoring Kernel Drivers asb100 asc7621 aspeed-pwm-tacho + bcm54140 bel-pfe coretemp da9052 diff --git a/Documentation/hwmon/isl68137.rst b/Documentation/hwmon/isl68137.rst index cc4b61447b63..0e71b22047f8 100644 --- a/Documentation/hwmon/isl68137.rst +++ b/Documentation/hwmon/isl68137.rst @@ -16,7 +16,7 @@ Supported chips: * Renesas ISL68220 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl68220' Addresses scanned: - @@ -26,7 +26,7 @@ Supported chips: * Renesas ISL68221 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl68221' Addresses scanned: - @@ -36,7 +36,7 @@ Supported chips: * Renesas ISL68222 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl68222' Addresses scanned: - @@ -46,7 +46,7 @@ Supported chips: * Renesas ISL68223 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl68223' Addresses scanned: - @@ -56,7 +56,7 @@ Supported chips: * Renesas ISL68224 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl68224' Addresses scanned: - @@ -66,7 +66,7 @@ Supported chips: * Renesas ISL68225 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl68225' Addresses scanned: - @@ -76,7 +76,7 @@ Supported chips: * Renesas ISL68226 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl68226' Addresses scanned: - @@ -86,7 +86,7 @@ Supported chips: * Renesas ISL68227 - Prefix: 'raa_dmpvr2_1rail' + Prefix: 'isl68227' Addresses scanned: - @@ -96,7 +96,7 @@ Supported chips: * Renesas ISL68229 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl68229' Addresses scanned: - @@ -106,7 +106,7 @@ Supported chips: * Renesas ISL68233 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl68233' Addresses scanned: - @@ -116,7 +116,7 @@ Supported chips: * Renesas ISL68239 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl68239' Addresses scanned: - @@ -126,7 +126,7 @@ Supported chips: * Renesas ISL69222 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69222' Addresses scanned: - @@ -136,7 +136,7 @@ Supported chips: * Renesas ISL69223 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl69223' Addresses scanned: - @@ -146,7 +146,7 @@ Supported chips: * Renesas ISL69224 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69224' Addresses scanned: - @@ -156,7 +156,7 @@ Supported chips: * Renesas ISL69225 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69225' Addresses scanned: - @@ -166,7 +166,7 @@ Supported chips: * Renesas ISL69227 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl69227' Addresses scanned: - @@ -176,7 +176,7 @@ Supported chips: * Renesas ISL69228 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl69228' Addresses scanned: - @@ -186,7 +186,7 @@ Supported chips: * Renesas ISL69234 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69234' Addresses scanned: - @@ -196,7 +196,7 @@ Supported chips: * Renesas ISL69236 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69236' Addresses scanned: - @@ -206,7 +206,7 @@ Supported chips: * Renesas ISL69239 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl69239' Addresses scanned: - @@ -216,7 +216,7 @@ Supported chips: * Renesas ISL69242 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69242' Addresses scanned: - @@ -226,7 +226,7 @@ Supported chips: * Renesas ISL69243 - Prefix: 'raa_dmpvr2_1rail' + Prefix: 'isl69243' Addresses scanned: - @@ -236,7 +236,7 @@ Supported chips: * Renesas ISL69247 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69247' Addresses scanned: - @@ -246,7 +246,7 @@ Supported chips: * Renesas ISL69248 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69248' Addresses scanned: - @@ -256,7 +256,7 @@ Supported chips: * Renesas ISL69254 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69254' Addresses scanned: - @@ -266,7 +266,7 @@ Supported chips: * Renesas ISL69255 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69255' Addresses scanned: - @@ -276,7 +276,7 @@ Supported chips: * Renesas ISL69256 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69256' Addresses scanned: - @@ -286,7 +286,7 @@ Supported chips: * Renesas ISL69259 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69259' Addresses scanned: - @@ -296,7 +296,7 @@ Supported chips: * Renesas ISL69260 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69260' Addresses scanned: - @@ -306,7 +306,7 @@ Supported chips: * Renesas ISL69268 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69268' Addresses scanned: - @@ -316,7 +316,7 @@ Supported chips: * Renesas ISL69269 - Prefix: 'raa_dmpvr2_3rail' + Prefix: 'isl69269' Addresses scanned: - @@ -326,7 +326,7 @@ Supported chips: * Renesas ISL69298 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'isl69298' Addresses scanned: - @@ -336,7 +336,7 @@ Supported chips: * Renesas RAA228000 - Prefix: 'raa_dmpvr2_hv' + Prefix: 'raa228000' Addresses scanned: - @@ -346,7 +346,7 @@ Supported chips: * Renesas RAA228004 - Prefix: 'raa_dmpvr2_hv' + Prefix: 'raa228004' Addresses scanned: - @@ -356,7 +356,7 @@ Supported chips: * Renesas RAA228006 - Prefix: 'raa_dmpvr2_hv' + Prefix: 'raa228006' Addresses scanned: - @@ -366,7 +366,7 @@ Supported chips: * Renesas RAA228228 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'raa228228' Addresses scanned: - @@ -376,7 +376,7 @@ Supported chips: * Renesas RAA229001 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'raa229001' Addresses scanned: - @@ -386,7 +386,7 @@ Supported chips: * Renesas RAA229004 - Prefix: 'raa_dmpvr2_2rail' + Prefix: 'raa229004' Addresses scanned: - diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 04d5c01a2e99..b80257a03830 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -1241,7 +1241,8 @@ When kbuild executes, the following steps are followed (roughly): will be displayed with "make KBUILD_VERBOSE=0". ---- 6.9 Preprocessing linker scripts +6.9 Preprocessing linker scripts +-------------------------------- When the vmlinux image is built, the linker script arch/$(ARCH)/kernel/vmlinux.lds is used. diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index a09971c2115c..fe089acb7783 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -257,6 +257,8 @@ drivers: * :doc:`netdevsim` * :doc:`mlxsw` +.. _Generic-Packet-Trap-Groups: + Generic Packet Trap Groups ========================== diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 50133d9761c9..6538ede29661 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -22,6 +22,7 @@ Contents: z8530book msg_zerocopy failover + net_dim net_failover phy sfp-phylink diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ee961d322d93..9375324aa8e1 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -812,7 +812,7 @@ tcp_limit_output_bytes - INTEGER tcp_challenge_ack_limit - INTEGER Limits number of Challenge ACK sent per second, as recommended in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks) - Default: 100 + Default: 1000 tcp_rx_skb_cache - BOOLEAN Controls a per TCP socket cache of one skb, that might help @@ -983,6 +983,13 @@ ip_early_demux - BOOLEAN reduces overall throughput, in such case you should disable it. Default: 1 +ping_group_range - 2 INTEGERS + Restrict ICMP_PROTO datagram sockets to users in the group range. + The default is "1 0", meaning, that nobody (not even root) may + create ping sockets. Setting it to "100 100" would grant permissions + to the single group. "0 4294967295" would enable it for the world, "100 + 4294967295" would enable it for the users, but not daemons. + tcp_early_demux - BOOLEAN Enable early demux for established TCP sockets. Default: 1 diff --git a/Documentation/networking/net_dim.txt b/Documentation/networking/net_dim.rst index 9bdb7d5a3ba3..3bed9fd95336 100644 --- a/Documentation/networking/net_dim.txt +++ b/Documentation/networking/net_dim.rst @@ -1,28 +1,20 @@ +====================================================== Net DIM - Generic Network Dynamic Interrupt Moderation ====================================================== -Author: - Tal Gilboa <talgi@mellanox.com> - - -Contents -========= +:Author: Tal Gilboa <talgi@mellanox.com> -- Assumptions -- Introduction -- The Net DIM Algorithm -- Registering a Network Device to DIM -- Example +.. contents:: :depth: 2 -Part 0: Assumptions -====================== +Assumptions +=========== This document assumes the reader has basic knowledge in network drivers and in general interrupt moderation. -Part I: Introduction -====================== +Introduction +============ Dynamic Interrupt Moderation (DIM) (in networking) refers to changing the interrupt moderation configuration of a channel in order to optimize packet @@ -41,14 +33,15 @@ number of wanted packets per event. The Net DIM algorithm ascribes importance to increase bandwidth over reducing interrupt rate. -Part II: The Net DIM Algorithm -=============================== +Net DIM Algorithm +================= Each iteration of the Net DIM algorithm follows these steps: -1. Calculates new data sample. -2. Compares it to previous sample. -3. Makes a decision - suggests interrupt moderation configuration fields. -4. Applies a schedule work function, which applies suggested configuration. + +#. Calculates new data sample. +#. Compares it to previous sample. +#. Makes a decision - suggests interrupt moderation configuration fields. +#. Applies a schedule work function, which applies suggested configuration. The first two steps are straightforward, both the new and the previous data are supplied by the driver registered to Net DIM. The previous data is the new data @@ -89,19 +82,21 @@ manoeuvre as it may provide partial data or ignore the algorithm suggestion under some conditions. -Part III: Registering a Network Device to DIM -============================================== +Registering a Network Device to DIM +=================================== -Net DIM API exposes the main function net_dim(struct dim *dim, -struct dim_sample end_sample). This function is the entry point to the Net +Net DIM API exposes the main function net_dim(). +This function is the entry point to the Net DIM algorithm and has to be called every time the driver would like to check if it should change interrupt moderation parameters. The driver should provide two -data structures: struct dim and struct dim_sample. Struct dim +data structures: :c:type:`struct dim <dim>` and +:c:type:`struct dim_sample <dim_sample>`. :c:type:`struct dim <dim>` describes the state of DIM for a specific object (RX queue, TX queue, other queues, etc.). This includes the current selected profile, previous data samples, the callback function provided by the driver and more. -Struct dim_sample describes a data sample, which will be compared to the -data sample stored in struct dim in order to decide on the algorithm's next +:c:type:`struct dim_sample <dim_sample>` describes a data sample, +which will be compared to the data sample stored in :c:type:`struct dim <dim>` +in order to decide on the algorithm's next step. The sample should include bytes, packets and interrupts, measured by the driver. @@ -110,9 +105,10 @@ main net_dim() function. The recommended method is to call net_dim() on each interrupt. Since Net DIM has a built-in moderation and it might decide to skip iterations under certain conditions, there is no need to moderate the net_dim() calls as well. As mentioned above, the driver needs to provide an object of type -struct dim to the net_dim() function call. It is advised for each entity -using Net DIM to hold a struct dim as part of its data structure and use it -as the main Net DIM API object. The struct dim_sample should hold the latest +:c:type:`struct dim <dim>` to the net_dim() function call. It is advised for +each entity using Net DIM to hold a :c:type:`struct dim <dim>` as part of its +data structure and use it as the main Net DIM API object. +The :c:type:`struct dim_sample <dim_sample>` should hold the latest bytes, packets and interrupts count. No need to perform any calculations, just include the raw data. @@ -124,19 +120,19 @@ the data flow. After the work is done, Net DIM algorithm needs to be set to the proper state in order to move to the next iteration. -Part IV: Example -================= +Example +======= The following code demonstrates how to register a driver to Net DIM. The actual usage is not complete but it should make the outline of the usage clear. -my_driver.c: +.. code-block:: c -#include <linux/dim.h> + #include <linux/dim.h> -/* Callback for net DIM to schedule on a decision to change moderation */ -void my_driver_do_dim_work(struct work_struct *work) -{ + /* Callback for net DIM to schedule on a decision to change moderation */ + void my_driver_do_dim_work(struct work_struct *work) + { /* Get struct dim from struct work_struct */ struct dim *dim = container_of(work, struct dim, work); @@ -145,11 +141,11 @@ void my_driver_do_dim_work(struct work_struct *work) /* Signal net DIM work is done and it should move to next iteration */ dim->state = DIM_START_MEASURE; -} + } -/* My driver's interrupt handler */ -int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...) -{ + /* My driver's interrupt handler */ + int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...) + { ... /* A struct to hold current measured data */ struct dim_sample dim_sample; @@ -162,13 +158,19 @@ int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...) /* Call net DIM */ net_dim(&my_entity->dim, dim_sample); ... -} + } -/* My entity's initialization function (my_entity was already allocated) */ -int my_driver_init_my_entity(struct my_driver_entity *my_entity, ...) -{ + /* My entity's initialization function (my_entity was already allocated) */ + int my_driver_init_my_entity(struct my_driver_entity *my_entity, ...) + { ... /* Initiate struct work_struct with my driver's callback function */ INIT_WORK(&my_entity->dim.work, my_driver_do_dim_work); ... -} + } + +Dynamic Interrupt Moderation (DIM) library API +============================================== + +.. kernel-doc:: include/linux/dim.h + :internal: diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst index fa7ddc0428c8..5325c71ca877 100644 --- a/Documentation/x86/boot.rst +++ b/Documentation/x86/boot.rst @@ -1399,8 +1399,8 @@ must have read/write permission; CS must be __BOOT_CS and DS, ES, SS must be __BOOT_DS; interrupt must be disabled; %rsi must hold the base address of the struct boot_params. -EFI Handover Protocol -===================== +EFI Handover Protocol (deprecated) +================================== This protocol allows boot loaders to defer initialisation to the EFI boot stub. The boot loader is required to load the kernel/initrd(s) @@ -1408,6 +1408,12 @@ from the boot media and jump to the EFI handover protocol entry point which is hdr->handover_offset bytes from the beginning of startup_{32,64}. +The boot loader MUST respect the kernel's PE/COFF metadata when it comes +to section alignment, the memory footprint of the executable image beyond +the size of the file itself, and any other aspect of the PE/COFF header +that may affect correct operation of the image as a PE/COFF binary in the +execution context provided by the EFI firmware. + The function prototype for the handover entry point looks like this:: efi_main(void *handle, efi_system_table_t *table, struct boot_params *bp) @@ -1419,9 +1425,18 @@ UEFI specification. 'bp' is the boot loader-allocated boot params. The boot loader *must* fill out the following fields in bp:: - - hdr.code32_start - hdr.cmd_line_ptr - hdr.ramdisk_image (if applicable) - hdr.ramdisk_size (if applicable) All other fields should be zero. + +NOTE: The EFI Handover Protocol is deprecated in favour of the ordinary PE/COFF + entry point, combined with the LINUX_EFI_INITRD_MEDIA_GUID based initrd + loading protocol (refer to [0] for an example of the bootloader side of + this), which removes the need for any knowledge on the part of the EFI + bootloader regarding the internal representation of boot_params or any + requirements/limitations regarding the placement of the command line + and ramdisk in memory, or the placement of the kernel image itself. + +[0] https://github.com/u-boot/u-boot/commit/ec80b4735a593961fe701cc3a5d717d4739b0fd0 diff --git a/MAINTAINERS b/MAINTAINERS index e64e5db31497..453fe0713e68 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -189,7 +189,7 @@ F: drivers/net/hamradio/6pack.c M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git F: Documentation/driver-api/80211/cfg80211.rst @@ -505,7 +505,7 @@ F: drivers/hwmon/adm1029.c ADM8211 WIRELESS DRIVER L: linux-wireless@vger.kernel.org S: Orphan -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ F: drivers/net/wireless/admtek/adm8211.* ADP1653 FLASH CONTROLLER DRIVER @@ -1323,7 +1323,10 @@ ARM INTEGRATOR, VERSATILE AND REALVIEW SUPPORT M: Linus Walleij <linus.walleij@linaro.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -F: Documentation/devicetree/bindings/arm/arm-boards +F: Documentation/devicetree/bindings/arm/arm,integrator.yaml +F: Documentation/devicetree/bindings/arm/arm,realview.yaml +F: Documentation/devicetree/bindings/arm/arm,versatile.yaml +F: Documentation/devicetree/bindings/arm/arm,vexpress-juno.yaml F: Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt F: Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml F: Documentation/devicetree/bindings/i2c/i2c-versatile.txt @@ -2847,14 +2850,14 @@ M: Nick Kossifidis <mickflemm@gmail.com> M: Luis Chamberlain <mcgrof@kernel.org> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/en/users/Drivers/ath5k +W: https://wireless.wiki.kernel.org/en/users/Drivers/ath5k F: drivers/net/wireless/ath/ath5k/ ATHEROS ATH6KL WIRELESS DRIVER M: Kalle Valo <kvalo@codeaurora.org> L: linux-wireless@vger.kernel.org S: Supported -W: http://wireless.kernel.org/en/users/Drivers/ath6kl +W: https://wireless.wiki.kernel.org/en/users/Drivers/ath6kl T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git F: drivers/net/wireless/ath/ath6kl/ @@ -3017,7 +3020,7 @@ B43 WIRELESS DRIVER L: linux-wireless@vger.kernel.org L: b43-dev@lists.infradead.org S: Odd Fixes -W: http://wireless.kernel.org/en/users/Drivers/b43 +W: https://wireless.wiki.kernel.org/en/users/Drivers/b43 F: drivers/net/wireless/broadcom/b43/ B43LEGACY WIRELESS DRIVER @@ -3025,7 +3028,7 @@ M: Larry Finger <Larry.Finger@lwfinger.net> L: linux-wireless@vger.kernel.org L: b43-dev@lists.infradead.org S: Maintained -W: http://wireless.kernel.org/en/users/Drivers/b43 +W: https://wireless.wiki.kernel.org/en/users/Drivers/b43 F: drivers/net/wireless/broadcom/b43legacy/ BACKLIGHT CLASS/SUBSYSTEM @@ -3840,7 +3843,7 @@ CARL9170 LINUX COMMUNITY WIRELESS DRIVER M: Christian Lamparter <chunkeey@googlemail.com> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/en/users/Drivers/carl9170 +W: https://wireless.wiki.kernel.org/en/users/Drivers/carl9170 F: drivers/net/wireless/ath/carl9170/ CAVIUM I2C DRIVER @@ -5173,6 +5176,7 @@ S: Maintained F: drivers/soc/fsl/dpio DPAA2 ETHERNET DRIVER +M: Ioana Ciornei <ioana.ciornei@nxp.com> M: Ioana Radulescu <ruxandra.radulescu@nxp.com> L: netdev@vger.kernel.org S: Maintained @@ -5552,7 +5556,7 @@ M: Chen-Yu Tsai <wens@csie.org> L: dri-devel@lists.freedesktop.org S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc -F: Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt +F: Documentation/devicetree/bindings/display/allwinner* F: drivers/gpu/drm/sun4i/ DRM DRIVERS FOR AMLOGIC SOCS @@ -5934,6 +5938,7 @@ M: Tal Gilboa <talgi@mellanox.com> S: Maintained F: include/linux/dim.h F: lib/dim/ +F: Documentation/networking/net_dim.rst DZ DECSTATION DZ11 SERIAL DRIVER M: "Maciej W. Rozycki" <macro@linux-mips.org> @@ -9325,6 +9330,7 @@ M: Christian Borntraeger <borntraeger@de.ibm.com> M: Janosch Frank <frankja@linux.ibm.com> R: David Hildenbrand <david@redhat.com> R: Cornelia Huck <cohuck@redhat.com> +R: Claudio Imbrenda <imbrenda@linux.ibm.com> L: kvm@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -9412,6 +9418,13 @@ F: include/linux/keyctl.h F: include/uapi/linux/keyctl.h F: security/keys/ +KFIFO +M: Stefani Seibold <stefani@seibold.net> +S: Maintained +F: include/linux/kfifo.h +F: lib/kfifo.c +F: samples/kfifo/ + KGDB / KDB /debug_core M: Jason Wessel <jason.wessel@windriver.com> M: Daniel Thompson <daniel.thompson@linaro.org> @@ -10063,7 +10076,7 @@ MAC80211 M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git F: Documentation/networking/mac80211-injection.txt @@ -10693,7 +10706,6 @@ MEDIATEK MT76 WIRELESS LAN DRIVER M: Felix Fietkau <nbd@nbd.name> M: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com> R: Ryder Lee <ryder.lee@mediatek.com> -R: Roy Luo <royluo@google.com> L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/mediatek/mt76/ @@ -12644,7 +12656,7 @@ F: fs/orangefs/ ORINOCO DRIVER L: linux-wireless@vger.kernel.org S: Orphan -W: http://wireless.kernel.org/en/users/Drivers/orinoco +W: https://wireless.wiki.kernel.org/en/users/Drivers/orinoco W: http://www.nongnu.org/orinoco/ F: drivers/net/wireless/intersil/orinoco/ @@ -12670,7 +12682,7 @@ P54 WIRELESS DRIVER M: Christian Lamparter <chunkeey@googlemail.com> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/en/users/Drivers/p54 +W: https://wireless.wiki.kernel.org/en/users/Drivers/p54 F: drivers/net/wireless/intersil/p54/ PACKING @@ -13038,7 +13050,7 @@ F: drivers/pci/controller/pci-xgene-msi.c PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> -R: Andrew Murray <amurray@thegoodpenguin.co.uk> +R: Rob Herring <robh@kernel.org> L: linux-pci@vger.kernel.org S: Supported Q: http://patchwork.ozlabs.org/project/linux-pci/list/ @@ -13591,7 +13603,7 @@ PRISM54 WIRELESS DRIVER M: Luis Chamberlain <mcgrof@kernel.org> L: linux-wireless@vger.kernel.org S: Obsolete -W: http://wireless.kernel.org/en/users/Drivers/p54 +W: https://wireless.wiki.kernel.org/en/users/Drivers/p54 F: drivers/net/wireless/intersil/prism54/ PROC FILESYSTEM @@ -13853,7 +13865,8 @@ S: Maintained F: drivers/scsi/qla1280.[ch] QLOGIC QLA2XXX FC-SCSI DRIVER -M: hmadhani@marvell.com +M: Nilesh Javali <njavali@marvell.com> +M: GR-QLogic-Storage-Upstream@marvell.com L: linux-scsi@vger.kernel.org S: Supported F: Documentation/scsi/LICENSE.qla2xxx @@ -13931,7 +13944,7 @@ QUALCOMM ATHEROS ATH10K WIRELESS DRIVER M: Kalle Valo <kvalo@codeaurora.org> L: ath10k@lists.infradead.org S: Supported -W: http://wireless.kernel.org/en/users/Drivers/ath10k +W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git F: drivers/net/wireless/ath/ath10k/ @@ -13946,7 +13959,7 @@ QUALCOMM ATHEROS ATH9K WIRELESS DRIVER M: QCA ath9k Development <ath9k-devel@qca.qualcomm.com> L: linux-wireless@vger.kernel.org S: Supported -W: http://wireless.kernel.org/en/users/Drivers/ath9k +W: https://wireless.wiki.kernel.org/en/users/Drivers/ath9k F: drivers/net/wireless/ath/ath9k/ QUALCOMM CAMERA SUBSYSTEM DRIVER @@ -14043,13 +14056,12 @@ QUALCOMM WCN36XX WIRELESS DRIVER M: Kalle Valo <kvalo@codeaurora.org> L: wcn36xx@lists.infradead.org S: Supported -W: http://wireless.kernel.org/en/users/Drivers/wcn36xx +W: https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx T: git git://github.com/KrasnikovEugene/wcn36xx.git F: drivers/net/wireless/ath/wcn36xx/ QUANTENNA QTNFMAC WIRELESS DRIVER M: Igor Mitsyanko <imitsyanko@quantenna.com> -M: Avinash Patil <avinashp@quantenna.com> M: Sergey Matyukevich <smatyukevich@quantenna.com> L: linux-wireless@vger.kernel.org S: Maintained @@ -14271,7 +14283,7 @@ REALTEK WIRELESS DRIVER (rtlwifi family) M: Ping-Ke Shih <pkshih@realtek.com> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtlwifi/ @@ -14406,7 +14418,7 @@ RFKILL M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git F: Documentation/ABI/stable/sysfs-class-rfkill @@ -14555,7 +14567,7 @@ F: drivers/media/dvb-frontends/rtl2832_sdr* RTL8180 WIRELESS DRIVER L: linux-wireless@vger.kernel.org S: Orphan -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtl818x/rtl8180/ @@ -14565,7 +14577,7 @@ M: Hin-Tak Leung <htl10@users.sourceforge.net> M: Larry Finger <Larry.Finger@lwfinger.net> L: linux-wireless@vger.kernel.org S: Maintained -W: http://wireless.kernel.org/ +W: https://wireless.wiki.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtl818x/rtl8187/ @@ -16920,8 +16932,8 @@ F: drivers/media/platform/ti-vpe/ TI WILINK WIRELESS DRIVERS L: linux-wireless@vger.kernel.org S: Orphan -W: http://wireless.kernel.org/en/users/Drivers/wl12xx -W: http://wireless.kernel.org/en/users/Drivers/wl1251 +W: https://wireless.wiki.kernel.org/en/users/Drivers/wl12xx +W: https://wireless.wiki.kernel.org/en/users/Drivers/wl1251 T: git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git F: drivers/net/wireless/ti/ F: include/linux/wl12xx.h @@ -18203,7 +18215,7 @@ M: Maya Erez <merez@codeaurora.org> L: linux-wireless@vger.kernel.org L: wil6210@qti.qualcomm.com S: Supported -W: http://wireless.kernel.org/en/users/Drivers/wil6210 +W: https://wireless.wiki.kernel.org/en/users/Drivers/wil6210 F: drivers/net/wireless/ath/wil6210/ WIMAX STACK @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h index 48f13a4ace4b..f534a1fef070 100644 --- a/arch/arc/include/asm/module.h +++ b/arch/arc/include/asm/module.h @@ -3,7 +3,6 @@ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * * Amit Bhor, Sameer Dhavale: Codito Technologies 2004 - */ #ifndef _ASM_ARC_MODULE_H @@ -19,8 +18,4 @@ struct mod_arch_specific { const char *secstr; }; -#define MODULE_PROC_FAMILY "ARC700" - -#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY - #endif /* _ASM_ARC_MODULE_H */ diff --git a/arch/arc/include/asm/vermagic.h b/arch/arc/include/asm/vermagic.h new file mode 100644 index 000000000000..a10257d2c62c --- /dev/null +++ b/arch/arc/include/asm/vermagic.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#define MODULE_ARCH_VERMAGIC "ARC700" + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index cabdd8f4a248..e8e1c866e413 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1450,7 +1450,8 @@ ENTRY(efi_enter_kernel) @ running beyond the PoU, and so calling cache_off below from @ inside the PE/COFF loader allocated region is unsafe unless @ we explicitly clean it to the PoC. - adr r0, call_cache_fn @ region of code we will + ARM( adrl r0, call_cache_fn ) + THUMB( adr r0, call_cache_fn ) @ region of code we will adr r1, 0f @ run with MMU off bl cache_clean_flush bl cache_off diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi index fd2c766e0f71..f7ae5a4530b8 100644 --- a/arch/arm/boot/dts/bcm2835-rpi.dtsi +++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi @@ -14,6 +14,9 @@ soc { firmware: firmware { compatible = "raspberrypi,bcm2835-firmware", "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + mboxes = <&mailbox>; dma-ranges; }; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index e1abe8c730ce..b83a864e2e8b 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -372,6 +372,7 @@ "dsi0_ddr2", "dsi0_ddr"; + status = "disabled"; }; aux: aux@7e215000 { diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 47982889d774..98da446aa0f2 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -1039,13 +1039,13 @@ compatible = "fsl,imx6q-fec"; reg = <0x02188000 0x4000>; interrupt-names = "int0", "pps"; - interrupts-extended = - <&intc 0 118 IRQ_TYPE_LEVEL_HIGH>, - <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>, + <0 119 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6QDL_CLK_ENET>, <&clks IMX6QDL_CLK_ENET>, <&clks IMX6QDL_CLK_ENET_REF>; clock-names = "ipg", "ahb", "ptp"; + gpr = <&gpr>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx6qp.dtsi b/arch/arm/boot/dts/imx6qp.dtsi index 93b89dc1f53b..b310f13a53f2 100644 --- a/arch/arm/boot/dts/imx6qp.dtsi +++ b/arch/arm/boot/dts/imx6qp.dtsi @@ -77,7 +77,6 @@ }; &fec { - /delete-property/interrupts-extended; interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>, <0 119 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index a075b63f3087..11d41e86f814 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -341,6 +341,11 @@ status = "disabled"; }; +/* RNG not directly accessible on N950/N9. */ +&rng_target { + status = "disabled"; +}; + &usb_otg_hs { interface-type = <0>; usb-phy = <&usb2_phy>; diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index 182163b55546..4b0df09cbe67 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -37,30 +37,6 @@ struct mod_arch_specific { struct module; u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val); -/* - * Add the ARM architecture version to the version magic string - */ -#define MODULE_ARCH_VERMAGIC_ARMVSN "ARMv" __stringify(__LINUX_ARM_ARCH__) " " - -/* Add __virt_to_phys patching state as well */ -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT -#define MODULE_ARCH_VERMAGIC_P2V "p2v8 " -#else -#define MODULE_ARCH_VERMAGIC_P2V "" -#endif - -/* Add instruction set architecture tag to distinguish ARM/Thumb kernels */ -#ifdef CONFIG_THUMB2_KERNEL -#define MODULE_ARCH_VERMAGIC_ARMTHUMB "thumb2 " -#else -#define MODULE_ARCH_VERMAGIC_ARMTHUMB "" -#endif - -#define MODULE_ARCH_VERMAGIC \ - MODULE_ARCH_VERMAGIC_ARMVSN \ - MODULE_ARCH_VERMAGIC_ARMTHUMB \ - MODULE_ARCH_VERMAGIC_P2V - #ifdef CONFIG_THUMB2_KERNEL #define HAVE_ARCH_KALLSYMS_SYMBOL_VALUE static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) diff --git a/arch/arm/include/asm/vermagic.h b/arch/arm/include/asm/vermagic.h new file mode 100644 index 000000000000..62ce94e26a63 --- /dev/null +++ b/arch/arm/include/asm/vermagic.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#include <linux/stringify.h> + +/* + * Add the ARM architecture version to the version magic string + */ +#define MODULE_ARCH_VERMAGIC_ARMVSN "ARMv" __stringify(__LINUX_ARM_ARCH__) " " + +/* Add __virt_to_phys patching state as well */ +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT +#define MODULE_ARCH_VERMAGIC_P2V "p2v8 " +#else +#define MODULE_ARCH_VERMAGIC_P2V "" +#endif + +/* Add instruction set architecture tag to distinguish ARM/Thumb kernels */ +#ifdef CONFIG_THUMB2_KERNEL +#define MODULE_ARCH_VERMAGIC_ARMTHUMB "thumb2 " +#else +#define MODULE_ARCH_VERMAGIC_ARMTHUMB "" +#endif + +#define MODULE_ARCH_VERMAGIC \ + MODULE_ARCH_VERMAGIC_ARMVSN \ + MODULE_ARCH_VERMAGIC_ARMTHUMB \ + MODULE_ARCH_VERMAGIC_P2V + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 03506ce46149..e7364e6c8c6b 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -91,8 +91,10 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o endif +ifeq ($(CONFIG_ARM_CPU_SUSPEND),y) AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a obj-$(CONFIG_SOC_IMX6) += resume-imx6.o +endif obj-$(CONFIG_SOC_IMX6) += pm-imx6.o obj-$(CONFIG_SOC_IMX1) += mach-imx1.o diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index cc29869d12a3..bf85d6db4931 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -929,7 +929,11 @@ static inline void emit_a32_rsh_i64(const s8 dst[], rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do LSR operation */ - if (val < 32) { + if (val == 0) { + /* An immediate value of 0 encodes a shift amount of 32 + * for LSR. To shift by 0, don't do anything. + */ + } else if (val < 32) { emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx); emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx); emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx); @@ -955,7 +959,11 @@ static inline void emit_a32_arsh_i64(const s8 dst[], rd = arm_bpf_get_reg64(dst, tmp, ctx); /* Do ARSH operation */ - if (val < 32) { + if (val == 0) { + /* An immediate value of 0 encodes a shift amount of 32 + * for ASR. To shift by 0, don't do anything. + */ + } else if (val < 32) { emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx); emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx); emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx); @@ -992,21 +1000,35 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], arm_bpf_put_reg32(dst_hi, rd[0], ctx); } +static bool is_ldst_imm(s16 off, const u8 size) +{ + s16 off_max = 0; + + switch (size) { + case BPF_B: + case BPF_W: + off_max = 0xfff; + break; + case BPF_H: + off_max = 0xff; + break; + case BPF_DW: + /* Need to make sure off+4 does not overflow. */ + off_max = 0xfff - 4; + break; + } + return -off_max <= off && off <= off_max; +} + /* *(size *)(dst + off) = src */ static inline void emit_str_r(const s8 dst, const s8 src[], - s32 off, struct jit_ctx *ctx, const u8 sz){ + s16 off, struct jit_ctx *ctx, const u8 sz){ const s8 *tmp = bpf2a32[TMP_REG_1]; - s32 off_max; s8 rd; rd = arm_bpf_get_reg32(dst, tmp[1], ctx); - if (sz == BPF_H) - off_max = 0xff; - else - off_max = 0xfff; - - if (off < 0 || off > off_max) { + if (!is_ldst_imm(off, sz)) { emit_a32_mov_i(tmp[0], off, ctx); emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx); rd = tmp[0]; @@ -1035,18 +1057,12 @@ static inline void emit_str_r(const s8 dst, const s8 src[], /* dst = *(size*)(src + off) */ static inline void emit_ldx_r(const s8 dst[], const s8 src, - s32 off, struct jit_ctx *ctx, const u8 sz){ + s16 off, struct jit_ctx *ctx, const u8 sz){ const s8 *tmp = bpf2a32[TMP_REG_1]; const s8 *rd = is_stacked(dst_lo) ? tmp : dst; s8 rm = src; - s32 off_max; - - if (sz == BPF_H) - off_max = 0xff; - else - off_max = 0xfff; - if (off < 0 || off > off_max) { + if (!is_ldst_imm(off, sz)) { emit_a32_mov_i(tmp[0], off, ctx); emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx); rm = tmp[0]; diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index dd6804a64f1a..fd4e1ce1daf9 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -36,7 +36,7 @@ #include <linux/mm.h> -struct start_info _xen_start_info; +static struct start_info _xen_start_info; struct start_info *xen_start_info = &_xen_start_info; EXPORT_SYMBOL(xen_start_info); diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index 1e93de68c044..4e7fa2623896 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -7,8 +7,6 @@ #include <asm-generic/module.h> -#define MODULE_ARCH_VERMAGIC "aarch64" - #ifdef CONFIG_ARM64_MODULE_PLTS struct mod_plt_sec { int plt_shndx; diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index 70c47156e54b..c6b4f0603024 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -47,7 +47,7 @@ static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys) get_random_bytes(&keys->apga, sizeof(keys->apga)); } -#define __ptrauth_key_install(k, v) \ +#define __ptrauth_key_install_nosync(k, v) \ do { \ struct ptrauth_key __pki_v = (v); \ write_sysreg_s(__pki_v.lo, SYS_ ## k ## KEYLO_EL1); \ @@ -62,8 +62,11 @@ static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys) { - if (system_supports_address_auth()) - __ptrauth_key_install(APIA, keys->apia); + if (!system_supports_address_auth()) + return; + + __ptrauth_key_install_nosync(APIA, keys->apia); + isb(); } extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index ebc622432831..c4ac0ac25a00 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -49,7 +49,9 @@ #ifndef CONFIG_BROKEN_GAS_INST #ifdef __ASSEMBLY__ -#define __emit_inst(x) .inst (x) +// The space separator is omitted so that __emit_inst(x) can be parsed as +// either an assembler directive or an assembler macro argument. +#define __emit_inst(x) .inst(x) #else #define __emit_inst(x) ".inst " __stringify((x)) "\n\t" #endif diff --git a/arch/arm64/include/asm/vermagic.h b/arch/arm64/include/asm/vermagic.h new file mode 100644 index 000000000000..a1eec6a000f1 --- /dev/null +++ b/arch/arm64/include/asm/vermagic.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 ARM Ltd. + */ +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#define MODULE_ARCH_VERMAGIC "aarch64" + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 354b11e27c07..033a48f30dbb 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -260,18 +260,7 @@ static int __aarch32_alloc_vdso_pages(void) if (ret) return ret; - ret = aarch32_alloc_kuser_vdso_page(); - if (ret) { - unsigned long c_vvar = - (unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]); - unsigned long c_vdso = - (unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]); - - free_page(c_vvar); - free_page(c_vdso); - } - - return ret; + return aarch32_alloc_kuser_vdso_page(); } #else static int __aarch32_alloc_vdso_pages(void) diff --git a/arch/h8300/kernel/.gitignore b/arch/h8300/kernel/.gitignore new file mode 100644 index 000000000000..bbb90f92d051 --- /dev/null +++ b/arch/h8300/kernel/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +vmlinux.lds diff --git a/arch/hexagon/include/asm/module.h b/arch/hexagon/include/asm/vermagic.h index e8de4fe03543..0e8dedc8c486 100644 --- a/arch/hexagon/include/asm/module.h +++ b/arch/hexagon/include/asm/vermagic.h @@ -3,11 +3,11 @@ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. */ -#ifndef _ASM_MODULE_H -#define _ASM_MODULE_H +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H -#include <asm-generic/module.h> +#include <linux/stringify.h> #define MODULE_ARCH_VERMAGIC __stringify(PROCESSOR_MODEL_NAME) " " -#endif +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h index f319144260ce..5a29652e6def 100644 --- a/arch/ia64/include/asm/module.h +++ b/arch/ia64/include/asm/module.h @@ -26,10 +26,6 @@ struct mod_arch_specific { unsigned int next_got_entry; /* index of next available got entry */ }; -#define MODULE_PROC_FAMILY "ia64" -#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY \ - "gcc-" __stringify(__GNUC__) "." __stringify(__GNUC_MINOR__) - #define ARCH_SHF_SMALL SHF_IA_64_SHORT #endif /* _ASM_IA64_MODULE_H */ diff --git a/arch/ia64/include/asm/vermagic.h b/arch/ia64/include/asm/vermagic.h new file mode 100644 index 000000000000..29c7424f4c25 --- /dev/null +++ b/arch/ia64/include/asm/vermagic.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2003 Hewlett-Packard Co + * David Mosberger-Tang <davidm@hpl.hp.com> + */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#include <linux/stringify.h> + +#define MODULE_ARCH_VERMAGIC "ia64" \ + "gcc-" __stringify(__GNUC__) "." __stringify(__GNUC_MINOR__) + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index a0765aa60ea9..1bff55aa2d54 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h generic-y += extable.h -generic-y += hardirq.h generic-y += kvm_para.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index 9846047b3d3d..724a0882576b 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -83,65 +83,4 @@ search_module_dbetables(unsigned long addr) } #endif -#ifdef CONFIG_CPU_BMIPS -#define MODULE_PROC_FAMILY "BMIPS " -#elif defined CONFIG_CPU_MIPS32_R1 -#define MODULE_PROC_FAMILY "MIPS32_R1 " -#elif defined CONFIG_CPU_MIPS32_R2 -#define MODULE_PROC_FAMILY "MIPS32_R2 " -#elif defined CONFIG_CPU_MIPS32_R6 -#define MODULE_PROC_FAMILY "MIPS32_R6 " -#elif defined CONFIG_CPU_MIPS64_R1 -#define MODULE_PROC_FAMILY "MIPS64_R1 " -#elif defined CONFIG_CPU_MIPS64_R2 -#define MODULE_PROC_FAMILY "MIPS64_R2 " -#elif defined CONFIG_CPU_MIPS64_R6 -#define MODULE_PROC_FAMILY "MIPS64_R6 " -#elif defined CONFIG_CPU_R3000 -#define MODULE_PROC_FAMILY "R3000 " -#elif defined CONFIG_CPU_TX39XX -#define MODULE_PROC_FAMILY "TX39XX " -#elif defined CONFIG_CPU_VR41XX -#define MODULE_PROC_FAMILY "VR41XX " -#elif defined CONFIG_CPU_R4X00 -#define MODULE_PROC_FAMILY "R4X00 " -#elif defined CONFIG_CPU_TX49XX -#define MODULE_PROC_FAMILY "TX49XX " -#elif defined CONFIG_CPU_R5000 -#define MODULE_PROC_FAMILY "R5000 " -#elif defined CONFIG_CPU_R5500 -#define MODULE_PROC_FAMILY "R5500 " -#elif defined CONFIG_CPU_NEVADA -#define MODULE_PROC_FAMILY "NEVADA " -#elif defined CONFIG_CPU_R10000 -#define MODULE_PROC_FAMILY "R10000 " -#elif defined CONFIG_CPU_RM7000 -#define MODULE_PROC_FAMILY "RM7000 " -#elif defined CONFIG_CPU_SB1 -#define MODULE_PROC_FAMILY "SB1 " -#elif defined CONFIG_CPU_LOONGSON32 -#define MODULE_PROC_FAMILY "LOONGSON32 " -#elif defined CONFIG_CPU_LOONGSON2EF -#define MODULE_PROC_FAMILY "LOONGSON2EF " -#elif defined CONFIG_CPU_LOONGSON64 -#define MODULE_PROC_FAMILY "LOONGSON64 " -#elif defined CONFIG_CPU_CAVIUM_OCTEON -#define MODULE_PROC_FAMILY "OCTEON " -#elif defined CONFIG_CPU_XLR -#define MODULE_PROC_FAMILY "XLR " -#elif defined CONFIG_CPU_XLP -#define MODULE_PROC_FAMILY "XLP " -#else -#error MODULE_PROC_FAMILY undefined for your processor configuration -#endif - -#ifdef CONFIG_32BIT -#define MODULE_KERNEL_TYPE "32BIT " -#elif defined CONFIG_64BIT -#define MODULE_KERNEL_TYPE "64BIT " -#endif - -#define MODULE_ARCH_VERMAGIC \ - MODULE_PROC_FAMILY MODULE_KERNEL_TYPE - #endif /* _ASM_MODULE_H */ diff --git a/arch/mips/include/asm/vermagic.h b/arch/mips/include/asm/vermagic.h new file mode 100644 index 000000000000..24dc3d35161c --- /dev/null +++ b/arch/mips/include/asm/vermagic.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_CPU_BMIPS +#define MODULE_PROC_FAMILY "BMIPS " +#elif defined CONFIG_CPU_MIPS32_R1 +#define MODULE_PROC_FAMILY "MIPS32_R1 " +#elif defined CONFIG_CPU_MIPS32_R2 +#define MODULE_PROC_FAMILY "MIPS32_R2 " +#elif defined CONFIG_CPU_MIPS32_R6 +#define MODULE_PROC_FAMILY "MIPS32_R6 " +#elif defined CONFIG_CPU_MIPS64_R1 +#define MODULE_PROC_FAMILY "MIPS64_R1 " +#elif defined CONFIG_CPU_MIPS64_R2 +#define MODULE_PROC_FAMILY "MIPS64_R2 " +#elif defined CONFIG_CPU_MIPS64_R6 +#define MODULE_PROC_FAMILY "MIPS64_R6 " +#elif defined CONFIG_CPU_R3000 +#define MODULE_PROC_FAMILY "R3000 " +#elif defined CONFIG_CPU_TX39XX +#define MODULE_PROC_FAMILY "TX39XX " +#elif defined CONFIG_CPU_VR41XX +#define MODULE_PROC_FAMILY "VR41XX " +#elif defined CONFIG_CPU_R4X00 +#define MODULE_PROC_FAMILY "R4X00 " +#elif defined CONFIG_CPU_TX49XX +#define MODULE_PROC_FAMILY "TX49XX " +#elif defined CONFIG_CPU_R5000 +#define MODULE_PROC_FAMILY "R5000 " +#elif defined CONFIG_CPU_R5500 +#define MODULE_PROC_FAMILY "R5500 " +#elif defined CONFIG_CPU_NEVADA +#define MODULE_PROC_FAMILY "NEVADA " +#elif defined CONFIG_CPU_R10000 +#define MODULE_PROC_FAMILY "R10000 " +#elif defined CONFIG_CPU_RM7000 +#define MODULE_PROC_FAMILY "RM7000 " +#elif defined CONFIG_CPU_SB1 +#define MODULE_PROC_FAMILY "SB1 " +#elif defined CONFIG_CPU_LOONGSON32 +#define MODULE_PROC_FAMILY "LOONGSON32 " +#elif defined CONFIG_CPU_LOONGSON2EF +#define MODULE_PROC_FAMILY "LOONGSON2EF " +#elif defined CONFIG_CPU_LOONGSON64 +#define MODULE_PROC_FAMILY "LOONGSON64 " +#elif defined CONFIG_CPU_CAVIUM_OCTEON +#define MODULE_PROC_FAMILY "OCTEON " +#elif defined CONFIG_CPU_XLR +#define MODULE_PROC_FAMILY "XLR " +#elif defined CONFIG_CPU_XLP +#define MODULE_PROC_FAMILY "XLP " +#else +#error MODULE_PROC_FAMILY undefined for your processor configuration +#endif + +#ifdef CONFIG_32BIT +#define MODULE_KERNEL_TYPE "32BIT " +#elif defined CONFIG_64BIT +#define MODULE_KERNEL_TYPE "64BIT " +#endif + +#define MODULE_ARCH_VERMAGIC \ + MODULE_PROC_FAMILY MODULE_KERNEL_TYPE + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/nds32/include/asm/module.h b/arch/nds32/include/asm/vermagic.h index a3a08e993c65..f772e7ba33f1 100644 --- a/arch/nds32/include/asm/module.h +++ b/arch/nds32/include/asm/vermagic.h @@ -1,11 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ // Copyright (C) 2005-2017 Andes Technology Corporation -#ifndef _ASM_NDS32_MODULE_H -#define _ASM_NDS32_MODULE_H - -#include <asm-generic/module.h> +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H #define MODULE_ARCH_VERMAGIC "NDS32v3" -#endif /* _ASM_NDS32_MODULE_H */ +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 356658711a86..5398bfc465b4 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -3,28 +3,10 @@ #define _ASM_POWERPC_MODULE_H #ifdef __KERNEL__ -/* - */ - #include <linux/list.h> #include <asm/bug.h> #include <asm-generic/module.h> - -#ifdef CONFIG_MPROFILE_KERNEL -#define MODULE_ARCH_VERMAGIC_FTRACE "mprofile-kernel " -#else -#define MODULE_ARCH_VERMAGIC_FTRACE "" -#endif - -#ifdef CONFIG_RELOCATABLE -#define MODULE_ARCH_VERMAGIC_RELOCATABLE "relocatable " -#else -#define MODULE_ARCH_VERMAGIC_RELOCATABLE "" -#endif - -#define MODULE_ARCH_VERMAGIC MODULE_ARCH_VERMAGIC_FTRACE MODULE_ARCH_VERMAGIC_RELOCATABLE - #ifndef __powerpc64__ /* * Thanks to Paul M for explaining this. diff --git a/arch/powerpc/include/asm/vermagic.h b/arch/powerpc/include/asm/vermagic.h new file mode 100644 index 000000000000..b054a8576e5d --- /dev/null +++ b/arch/powerpc/include/asm/vermagic.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_MPROFILE_KERNEL +#define MODULE_ARCH_VERMAGIC_FTRACE "mprofile-kernel " +#else +#define MODULE_ARCH_VERMAGIC_FTRACE "" +#endif + +#ifdef CONFIG_RELOCATABLE +#define MODULE_ARCH_VERMAGIC_RELOCATABLE "relocatable " +#else +#define MODULE_ARCH_VERMAGIC_RELOCATABLE "" +#endif + +#define MODULE_ARCH_VERMAGIC \ + MODULE_ARCH_VERMAGIC_FTRACE MODULE_ARCH_VERMAGIC_RELOCATABLE + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 6404df613ea3..2b35f9bcf892 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -604,18 +604,19 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ local_irq_disable(); ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + pte = __pte(0); + if (ptep) + pte = *ptep; + local_irq_enable(); /* * If the PTE disappeared temporarily due to a THP * collapse, just return and let the guest try again. */ - if (!ptep) { - local_irq_enable(); + if (!pte_present(pte)) { if (page) put_page(page); return RESUME_GUEST; } - pte = *ptep; - local_irq_enable(); hpa = pte_pfn(pte) << PAGE_SHIFT; pte_size = PAGE_SIZE; if (shift) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 9f050064d2a2..aa12cd4078b3 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -815,18 +815,19 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, */ local_irq_disable(); ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + pte = __pte(0); + if (ptep) + pte = *ptep; + local_irq_enable(); /* * If the PTE disappeared temporarily due to a THP * collapse, just return and let the guest try again. */ - if (!ptep) { - local_irq_enable(); + if (!pte_present(pte)) { if (page) put_page(page); return RESUME_GUEST; } - pte = *ptep; - local_irq_enable(); /* If we're logging dirty pages, always map single pages */ large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a197258595ef..62f7bfeb709e 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -55,7 +55,7 @@ config RISCV select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MMIOWB select ARCH_HAS_DEBUG_VIRTUAL - select HAVE_EBPF_JIT + select HAVE_EBPF_JIT if MMU select EDAC_SUPPORT select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_SET_DIRECT_MAP diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h index 46202dad365d..76aa96a9fc08 100644 --- a/arch/riscv/include/asm/module.h +++ b/arch/riscv/include/asm/module.h @@ -6,8 +6,6 @@ #include <asm-generic/module.h> -#define MODULE_ARCH_VERMAGIC "riscv" - struct module; unsigned long module_emit_got_entry(struct module *mod, unsigned long val); unsigned long module_emit_plt_entry(struct module *mod, unsigned long val); diff --git a/arch/riscv/include/asm/vermagic.h b/arch/riscv/include/asm/vermagic.h new file mode 100644 index 000000000000..7b9441a57466 --- /dev/null +++ b/arch/riscv/include/asm/vermagic.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#define MODULE_ARCH_VERMAGIC "riscv" + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 302934177760..11083d4d5f2d 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -770,12 +770,13 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); /* - * if ((temp_tcc = tcc - 1) < 0) + * temp_tcc = tcc - 1; + * if (tcc < 0) * goto out; */ emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx); off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; - emit_bcc(BPF_JSLT, RV_REG_T1, RV_REG_ZERO, off, ctx); + emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); /* * prog = array->ptrs[index]; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index cc1985d8750a..d208a9fd6c52 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -110,6 +110,16 @@ static bool is_32b_int(s64 val) return -(1L << 31) <= val && val < (1L << 31); } +static bool in_auipc_jalr_range(s64 val) +{ + /* + * auipc+jalr can reach any signed PC-relative offset in the range + * [-2^31 - 2^11, 2^31 - 2^11). + */ + return (-(1L << 31) - (1L << 11)) <= val && + val < ((1L << 31) - (1L << 11)); +} + static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) { /* Note that the immediate from the add is sign-extended, @@ -380,20 +390,24 @@ static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx) *rd = RV_REG_T2; } -static void emit_jump_and_link(u8 rd, s64 rvoff, bool force_jalr, - struct rv_jit_context *ctx) +static int emit_jump_and_link(u8 rd, s64 rvoff, bool force_jalr, + struct rv_jit_context *ctx) { s64 upper, lower; if (rvoff && is_21b_int(rvoff) && !force_jalr) { emit(rv_jal(rd, rvoff >> 1), ctx); - return; + return 0; + } else if (in_auipc_jalr_range(rvoff)) { + upper = (rvoff + (1 << 11)) >> 12; + lower = rvoff & 0xfff; + emit(rv_auipc(RV_REG_T1, upper), ctx); + emit(rv_jalr(rd, RV_REG_T1, lower), ctx); + return 0; } - upper = (rvoff + (1 << 11)) >> 12; - lower = rvoff & 0xfff; - emit(rv_auipc(RV_REG_T1, upper), ctx); - emit(rv_jalr(rd, RV_REG_T1, lower), ctx); + pr_err("bpf-jit: target offset 0x%llx is out of range\n", rvoff); + return -ERANGE; } static bool is_signed_bpf_cond(u8 cond) @@ -407,18 +421,16 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) s64 off = 0; u64 ip; u8 rd; + int ret; if (addr && ctx->insns) { ip = (u64)(long)(ctx->insns + ctx->ninsns); off = addr - ip; - if (!is_32b_int(off)) { - pr_err("bpf-jit: target call addr %pK is out of range\n", - (void *)addr); - return -ERANGE; - } } - emit_jump_and_link(RV_REG_RA, off, !fixed, ctx); + ret = emit_jump_and_link(RV_REG_RA, off, !fixed, ctx); + if (ret) + return ret; rd = bpf_to_rv_reg(BPF_REG_0, ctx); emit(rv_addi(rd, RV_REG_A0, 0), ctx); return 0; @@ -429,7 +441,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || BPF_CLASS(insn->code) == BPF_JMP; - int s, e, rvoff, i = insn - ctx->prog->insnsi; + int s, e, rvoff, ret, i = insn - ctx->prog->insnsi; struct bpf_prog_aux *aux = ctx->prog->aux; u8 rd = -1, rs = -1, code = insn->code; s16 off = insn->off; @@ -699,7 +711,9 @@ out_be: /* JUMP off */ case BPF_JMP | BPF_JA: rvoff = rv_offset(i, off, ctx); - emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + ret = emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + if (ret) + return ret; break; /* IF (dst COND src) JUMP off */ @@ -801,7 +815,6 @@ out_be: case BPF_JMP | BPF_CALL: { bool fixed; - int ret; u64 addr; mark_call(ctx); @@ -826,7 +839,9 @@ out_be: break; rvoff = epilogue_offset(ctx); - emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + ret = emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + if (ret) + return ret; break; /* dst = imm64 */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 8191106bf7b9..bfb481134994 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -393,7 +393,7 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; /* PV guest cpus can have a single interruption injected at a time. */ - if (kvm_s390_pv_cpu_is_protected(vcpu) && + if (kvm_s390_pv_cpu_get_handle(vcpu) && vcpu->arch.sie_block->iictl != IICTL_CODE_NONE) active_mask &= ~(IRQ_PEND_EXT_II_MASK | IRQ_PEND_IO_MASK | diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 19a81024fe16..5dcf9ff12828 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1939,6 +1939,9 @@ static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) start = slot + 1; } + if (start >= slots->used_slots) + return slots->used_slots - 1; + if (gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { atomic_set(&slots->lru_slot, start); diff --git a/arch/sh/include/asm/module.h b/arch/sh/include/asm/module.h index 9f38fb35fe96..337663a028db 100644 --- a/arch/sh/include/asm/module.h +++ b/arch/sh/include/asm/module.h @@ -11,32 +11,4 @@ struct mod_arch_specific { }; #endif -#ifdef CONFIG_CPU_LITTLE_ENDIAN -# ifdef CONFIG_CPU_SH2 -# define MODULE_PROC_FAMILY "SH2LE " -# elif defined CONFIG_CPU_SH3 -# define MODULE_PROC_FAMILY "SH3LE " -# elif defined CONFIG_CPU_SH4 -# define MODULE_PROC_FAMILY "SH4LE " -# elif defined CONFIG_CPU_SH5 -# define MODULE_PROC_FAMILY "SH5LE " -# else -# error unknown processor family -# endif -#else -# ifdef CONFIG_CPU_SH2 -# define MODULE_PROC_FAMILY "SH2BE " -# elif defined CONFIG_CPU_SH3 -# define MODULE_PROC_FAMILY "SH3BE " -# elif defined CONFIG_CPU_SH4 -# define MODULE_PROC_FAMILY "SH4BE " -# elif defined CONFIG_CPU_SH5 -# define MODULE_PROC_FAMILY "SH5BE " -# else -# error unknown processor family -# endif -#endif - -#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY - #endif /* _ASM_SH_MODULE_H */ diff --git a/arch/sh/include/asm/vermagic.h b/arch/sh/include/asm/vermagic.h new file mode 100644 index 000000000000..13d8eaa9188e --- /dev/null +++ b/arch/sh/include/asm/vermagic.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_CPU_LITTLE_ENDIAN +# ifdef CONFIG_CPU_SH2 +# define MODULE_PROC_FAMILY "SH2LE " +# elif defined CONFIG_CPU_SH3 +# define MODULE_PROC_FAMILY "SH3LE " +# elif defined CONFIG_CPU_SH4 +# define MODULE_PROC_FAMILY "SH4LE " +# elif defined CONFIG_CPU_SH5 +# define MODULE_PROC_FAMILY "SH5LE " +# else +# error unknown processor family +# endif +#else +# ifdef CONFIG_CPU_SH2 +# define MODULE_PROC_FAMILY "SH2BE " +# elif defined CONFIG_CPU_SH3 +# define MODULE_PROC_FAMILY "SH3BE " +# elif defined CONFIG_CPU_SH4 +# define MODULE_PROC_FAMILY "SH4BE " +# elif defined CONFIG_CPU_SH5 +# define MODULE_PROC_FAMILY "SH5BE " +# else +# error unknown processor family +# endif +#endif + +#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index b9de2d4fa57e..8d2a68aea1fc 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -412,7 +412,7 @@ int arch_add_memory(int nid, u64 start, u64 size, unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot) + if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)) return -EINVAL; /* We only have ZONE_NORMAL, so this is easy.. */ diff --git a/arch/um/Makefile b/arch/um/Makefile index d2daa206872d..275f5ffdf6f0 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -140,6 +140,7 @@ export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) # When cleaning we don't include .config, so we don't include # TT or skas makefiles and don't clean skas_ptregs.h. CLEAN_FILES += linux x.i gmon.out +MRPROPER_DIRS += arch/$(SUBARCH)/include/generated archclean: @find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d6104ea8af0..1197b5596d5a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -149,7 +149,7 @@ config X86 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 - select HAVE_ARCH_USERFAULTFD_WP if USERFAULTFD + select HAVE_ARCH_USERFAULTFD_WP if X86_64 && USERFAULTFD select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_ASM_MODVERSIONS diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index e4aa20c0426f..442e1ed4acd4 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -643,6 +643,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index b0da5320bcff..624f5d9b0f79 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/hyperv.h> #include <linux/slab.h> +#include <linux/kernel.h> #include <linux/cpuhotplug.h> #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> @@ -419,11 +420,14 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -void hyperv_report_panic(struct pt_regs *regs, long err) +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) { static bool panic_reported; u64 guest_id; + if (in_die && !panic_on_oops) + return; + /* * We prefer to report panic on 'die' chain as we have proper * registers to report, but if we miss it (e.g. on BUG()) we need diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index cdcf48d52a12..8391c115c0ec 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -178,8 +178,10 @@ extern void efi_free_boot_services(void); extern pgd_t * __init efi_uv1_memmap_phys_prolog(void); extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd); +/* kexec external ABI */ struct efi_setup_data { u64 fw_vendor; + u64 __unused; u64 tables; u64 smbios; u64 reserved[8]; diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 6685e1218959..7063b5a43220 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -41,7 +41,7 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define PATCH_MAX_SIZE PAGE_SIZE +#define PATCH_MAX_SIZE (3 * PAGE_SIZE) #ifdef CONFIG_MICROCODE_AMD extern void __init load_ucode_amd_bsp(unsigned int family); diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index c215d2762488..e988bac0a4a1 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -13,64 +13,4 @@ struct mod_arch_specific { #endif }; -#ifdef CONFIG_X86_64 -/* X86_64 does not define MODULE_PROC_FAMILY */ -#elif defined CONFIG_M486SX -#define MODULE_PROC_FAMILY "486SX " -#elif defined CONFIG_M486 -#define MODULE_PROC_FAMILY "486 " -#elif defined CONFIG_M586 -#define MODULE_PROC_FAMILY "586 " -#elif defined CONFIG_M586TSC -#define MODULE_PROC_FAMILY "586TSC " -#elif defined CONFIG_M586MMX -#define MODULE_PROC_FAMILY "586MMX " -#elif defined CONFIG_MCORE2 -#define MODULE_PROC_FAMILY "CORE2 " -#elif defined CONFIG_MATOM -#define MODULE_PROC_FAMILY "ATOM " -#elif defined CONFIG_M686 -#define MODULE_PROC_FAMILY "686 " -#elif defined CONFIG_MPENTIUMII -#define MODULE_PROC_FAMILY "PENTIUMII " -#elif defined CONFIG_MPENTIUMIII -#define MODULE_PROC_FAMILY "PENTIUMIII " -#elif defined CONFIG_MPENTIUMM -#define MODULE_PROC_FAMILY "PENTIUMM " -#elif defined CONFIG_MPENTIUM4 -#define MODULE_PROC_FAMILY "PENTIUM4 " -#elif defined CONFIG_MK6 -#define MODULE_PROC_FAMILY "K6 " -#elif defined CONFIG_MK7 -#define MODULE_PROC_FAMILY "K7 " -#elif defined CONFIG_MK8 -#define MODULE_PROC_FAMILY "K8 " -#elif defined CONFIG_MELAN -#define MODULE_PROC_FAMILY "ELAN " -#elif defined CONFIG_MCRUSOE -#define MODULE_PROC_FAMILY "CRUSOE " -#elif defined CONFIG_MEFFICEON -#define MODULE_PROC_FAMILY "EFFICEON " -#elif defined CONFIG_MWINCHIPC6 -#define MODULE_PROC_FAMILY "WINCHIPC6 " -#elif defined CONFIG_MWINCHIP3D -#define MODULE_PROC_FAMILY "WINCHIP3D " -#elif defined CONFIG_MCYRIXIII -#define MODULE_PROC_FAMILY "CYRIXIII " -#elif defined CONFIG_MVIAC3_2 -#define MODULE_PROC_FAMILY "VIAC3-2 " -#elif defined CONFIG_MVIAC7 -#define MODULE_PROC_FAMILY "VIAC7 " -#elif defined CONFIG_MGEODEGX1 -#define MODULE_PROC_FAMILY "GEODEGX1 " -#elif defined CONFIG_MGEODE_LX -#define MODULE_PROC_FAMILY "GEODE " -#else -#error unknown processor family -#endif - -#ifdef CONFIG_X86_32 -# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY -#endif - #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 07e95dcb40ad..7e9a281e2660 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -237,27 +237,6 @@ enum ssb_mitigation { extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; -/* - * On VMEXIT we must ensure that no RSB predictions learned in the guest - * can be followed in the host, by overwriting the RSB completely. Both - * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ALL *might* it be avoided. - */ -static inline void vmexit_fill_RSB(void) -{ -#ifdef CONFIG_RETPOLINE - unsigned long loops; - - asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE("jmp 910f", - __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), - X86_FEATURE_RETPOLINE) - "910:" - : "=r" (loops), ASM_CALL_CONSTRAINT - : : "memory" ); -#endif -} - static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h new file mode 100644 index 000000000000..75884d2cdec3 --- /dev/null +++ b/arch/x86/include/asm/vermagic.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_X86_64 +/* X86_64 does not define MODULE_PROC_FAMILY */ +#elif defined CONFIG_M486SX +#define MODULE_PROC_FAMILY "486SX " +#elif defined CONFIG_M486 +#define MODULE_PROC_FAMILY "486 " +#elif defined CONFIG_M586 +#define MODULE_PROC_FAMILY "586 " +#elif defined CONFIG_M586TSC +#define MODULE_PROC_FAMILY "586TSC " +#elif defined CONFIG_M586MMX +#define MODULE_PROC_FAMILY "586MMX " +#elif defined CONFIG_MCORE2 +#define MODULE_PROC_FAMILY "CORE2 " +#elif defined CONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM " +#elif defined CONFIG_M686 +#define MODULE_PROC_FAMILY "686 " +#elif defined CONFIG_MPENTIUMII +#define MODULE_PROC_FAMILY "PENTIUMII " +#elif defined CONFIG_MPENTIUMIII +#define MODULE_PROC_FAMILY "PENTIUMIII " +#elif defined CONFIG_MPENTIUMM +#define MODULE_PROC_FAMILY "PENTIUMM " +#elif defined CONFIG_MPENTIUM4 +#define MODULE_PROC_FAMILY "PENTIUM4 " +#elif defined CONFIG_MK6 +#define MODULE_PROC_FAMILY "K6 " +#elif defined CONFIG_MK7 +#define MODULE_PROC_FAMILY "K7 " +#elif defined CONFIG_MK8 +#define MODULE_PROC_FAMILY "K8 " +#elif defined CONFIG_MELAN +#define MODULE_PROC_FAMILY "ELAN " +#elif defined CONFIG_MCRUSOE +#define MODULE_PROC_FAMILY "CRUSOE " +#elif defined CONFIG_MEFFICEON +#define MODULE_PROC_FAMILY "EFFICEON " +#elif defined CONFIG_MWINCHIPC6 +#define MODULE_PROC_FAMILY "WINCHIPC6 " +#elif defined CONFIG_MWINCHIP3D +#define MODULE_PROC_FAMILY "WINCHIP3D " +#elif defined CONFIG_MCYRIXIII +#define MODULE_PROC_FAMILY "CYRIXIII " +#elif defined CONFIG_MVIAC3_2 +#define MODULE_PROC_FAMILY "VIAC3-2 " +#elif defined CONFIG_MVIAC7 +#define MODULE_PROC_FAMILY "VIAC7 " +#elif defined CONFIG_MGEODEGX1 +#define MODULE_PROC_FAMILY "GEODEGX1 " +#elif defined CONFIG_MGEODE_LX +#define MODULE_PROC_FAMILY "GEODE " +#else +#error unknown processor family +#endif + +#ifdef CONFIG_X86_32 +# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY +#else +# define MODULE_ARCH_VERMAGIC "" +#endif + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index bf08d4508ecb..a19a680542ce 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1119,35 +1119,53 @@ void switch_to_sld(unsigned long tifn) sld_update_msr(!(tifn & _TIF_SLD)); } -#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY} - /* - * The following processors have the split lock detection feature. But - * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot - * be enumerated. Enable it by family and model matching on these - * processors. + * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should + * only be trusted if it is confirmed that a CPU model implements a + * specific feature at a particular bit position. + * + * The possible driver data field values: + * + * - 0: CPU models that are known to have the per-core split-lock detection + * feature even though they do not enumerate IA32_CORE_CAPABILITIES. + * + * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use + * bit 5 to enumerate the per-core split-lock detection feature. */ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { - SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X), - SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, 1), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, 1), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, 1), {} }; void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) { - u64 ia32_core_caps = 0; + const struct x86_cpu_id *m; + u64 ia32_core_caps; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; - if (c->x86_vendor != X86_VENDOR_INTEL) + m = x86_match_cpu(split_lock_cpu_ids); + if (!m) return; - if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) { - /* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */ + + switch (m->driver_data) { + case 0: + break; + case 1: + if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) + return; rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps); - } else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - /* Enumerate split lock detection by family and model. */ - if (x86_match_cpu(split_lock_cpu_ids)) - ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT; + if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)) + return; + break; + default: + return; } - if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT) - split_lock_setup(); + split_lock_setup(); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index caa032ce3fe3..ebf34c7bc8bc 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -227,8 +227,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void) cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); } + /* + * Hyper-V expects to get crash register data or kmsg when + * crash enlightment is available and system crashes. Set + * crash_kexec_post_notifiers to be true to make sure that + * calling crash enlightment interface before running kdump + * kernel. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + crash_kexec_post_notifiers = true; + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 89049b343c7a..d8cc5223b7ce 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); + rdt_domain_reconfigure_cdp(r); + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { kfree(d); return; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 181c992f448c..3dd13f3a8b23 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -601,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r); bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r); +void rdt_domain_reconfigure_cdp(struct rdt_resource *r); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 064e9ef44cd6..5a359d9fcc05 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) +{ + if (!r->alloc_capable) + return; + + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + l2_qos_cfg_update(&r->alloc_enabled); + + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + l3_qos_cfg_update(&r->alloc_enabled); +} + /* * Enable or disable the MBA software controller * which helps user specify bandwidth in MBps. @@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn && + rdtgrp != &rdtgroup_default) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { ret = rdtgroup_ctrl_remove(kn, rdtgrp); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fe3ab9632f3b..8c89e4d9ad28 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -147,7 +147,7 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } -static void init_freq_invariance(void); +static void init_freq_invariance(bool secondary); /* * Report back to the Boot Processor during boot time or to the caller processor @@ -185,7 +185,7 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); - init_freq_invariance(); + init_freq_invariance(true); /* * Get our bogomips. @@ -1341,7 +1341,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); - init_freq_invariance(); + init_freq_invariance(false); smp_sanity_check(); switch (apic_intr_mode) { @@ -1877,9 +1877,6 @@ static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int err, i; u64 msr; - if (!x86_match_cpu(has_knl_turbo_ratio_limits)) - return false; - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; @@ -1945,18 +1942,23 @@ static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { + u64 msr; int err; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq); + err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */ + *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ + *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ + + /* The CPU may have less than 4 cores */ + if (!*turbo_freq) + *turbo_freq = msr & 0xFF; /* 1C turbo */ return true; } @@ -1972,7 +1974,8 @@ static bool intel_set_max_freq_ratio(void) skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; - if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) + if (x86_match_cpu(has_knl_turbo_ratio_limits) && + knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_skx_turbo_ratio_limits) && @@ -1985,13 +1988,22 @@ static bool intel_set_max_freq_ratio(void) return false; out: + /* + * Some hypervisors advertise X86_FEATURE_APERFMPERF + * but then fill all MSR's with zeroes. + */ + if (!base_freq) { + pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n"); + return false; + } + arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); arch_set_max_freq_ratio(turbo_disabled()); return true; } -static void init_counter_refs(void *arg) +static void init_counter_refs(void) { u64 aperf, mperf; @@ -2002,18 +2014,25 @@ static void init_counter_refs(void *arg) this_cpu_write(arch_prev_mperf, mperf); } -static void init_freq_invariance(void) +static void init_freq_invariance(bool secondary) { bool ret = false; - if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF)) + if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) return; + if (secondary) { + if (static_branch_likely(&arch_scale_freq_key)) { + init_counter_refs(); + } + return; + } + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) ret = intel_set_max_freq_ratio(); if (ret) { - on_each_cpu(init_counter_refs, NULL, 1); + init_counter_refs(); static_branch_enable(&arch_scale_freq_key); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 4d732a444711..8d5cbe1bbb3b 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -81,7 +81,7 @@ #define UMIP_INST_SLDT 3 /* 0F 00 /0 */ #define UMIP_INST_STR 4 /* 0F 00 /1 */ -const char * const umip_insns[5] = { +static const char * const umip_insns[5] = { [UMIP_INST_SGDT] = "SGDT", [UMIP_INST_SIDT] = "SIDT", [UMIP_INST_SMSW] = "SMSW", diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a789759b7261..4a3081e9f4b5 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,6 +3,10 @@ ccflags-y += -Iarch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror +ifeq ($(CONFIG_FRAME_POINTER),y) +OBJECT_FILES_NON_STANDARD_vmenter.o := y +endif + KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0e3fc311d7da..cf912b4aaba8 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/highmem.h> #include <linux/psp-sev.h> +#include <linux/pagemap.h> #include <linux/swap.h> #include "x86.h" @@ -1117,7 +1118,7 @@ int __init sev_hardware_setup(void) /* Maximum number of encrypted guests supported simultaneously */ max_sev_asid = cpuid_ecx(0x8000001F); - if (!max_sev_asid) + if (!svm_sev_enabled()) return 1; /* Minimum ASID value that should be used for SEV guest */ @@ -1156,6 +1157,9 @@ err: void sev_hardware_teardown(void) { + if (!svm_sev_enabled()) + return; + bitmap_free(sev_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2be5bbae3a40..2f379bacbb26 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3276,7 +3276,7 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); } -bool __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); +void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); static void svm_vcpu_run(struct kvm_vcpu *vcpu) { @@ -3330,13 +3330,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) */ x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); - local_irq_enable(); - __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else @@ -3366,8 +3361,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) reload_tss(vcpu); - local_irq_disable(); - x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); vcpu->arch.cr2 = svm->vmcb->save.cr2; @@ -3411,7 +3404,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) mark_all_clean(svm->vmcb); } -STACK_FRAME_NON_STANDARD(svm_vcpu_run); static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root) { diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index fa1af90067e9..bf944334003a 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> +#include <asm/nospec-branch.h> #define WORD_SIZE (BITS_PER_LONG / 8) @@ -35,7 +36,6 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP - mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -78,6 +78,7 @@ SYM_FUNC_START(__svm_vcpu_run) pop %_ASM_AX /* Enter guest mode */ + sti 1: vmload %_ASM_AX jmp 3f 2: cmpb $0, kvm_rebooting @@ -99,6 +100,13 @@ SYM_FUNC_START(__svm_vcpu_run) ud2 _ASM_EXTABLE(5b, 6b) 7: + cli + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + /* "POP" @regs to RAX. */ pop %_ASM_AX diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index cbc9ea2de28f..fd78ffbde644 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5533,8 +5533,25 @@ static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu, return 1 & (b >> (field & 7)); } +static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12) +{ + u32 entry_intr_info = vmcs12->vm_entry_intr_info_field; + + if (nested_cpu_has_mtf(vmcs12)) + return true; + + /* + * An MTF VM-exit may be injected into the guest by setting the + * interruption-type to 7 (other event) and the vector field to 0. Such + * is the case regardless of the 'monitor trap flag' VM-execution + * control. + */ + return entry_intr_info == (INTR_INFO_VALID_MASK + | INTR_TYPE_OTHER_EVENT); +} + /* - * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we + * Return true if we should exit from L2 to L1 to handle an exit, or false if we * should handle it ourselves in L0 (and then continue L2). Only call this * when in is_guest_mode (L2). */ @@ -5633,7 +5650,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_TRAP_FLAG: - return nested_cpu_has_mtf(vmcs12); + return nested_vmx_exit_handled_mtf(vmcs12); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 83050977490c..c2c6335a998c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4572,7 +4572,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, */ static void kvm_machine_check(void) { -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) +#if defined(CONFIG_X86_MCE) struct pt_regs regs = { .cs = 3, /* Fake ring 3 no matter what the guest ran on */ .flags = X86_EFLAGS_IF, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3bf2ecafd027..c5835f9cb9ad 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3060,6 +3060,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: case MSR_F15H_EX_CFG: + /* + * Intel Sandy Bridge CPUs must support the RAPL (running average power + * limit) MSRs. Just return 0, as we do not want to expose the host + * data here. Do not conditionalize this on CPUID, as KVM does not do + * so for existing CPU-specific MSRs. + */ + case MSR_RAPL_POWER_UNIT: + case MSR_PP0_ENERGY_STATUS: /* Power plane 0 (core) */ + case MSR_PP1_ENERGY_STATUS: /* Power plane 1 (graphics uncore) */ + case MSR_PKG_ENERGY_STATUS: /* Total package */ + case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: @@ -5049,10 +5060,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -5072,10 +5086,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 5ea7c2cf7ab4..42b6709e6dc7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -158,6 +158,19 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_AX)); } +/* + * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 + * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte + * of encoding. al,cl,dl,bl have simpler encoding. + */ +static bool is_ereg_8l(u32 reg) +{ + return is_ereg(reg) || + (1 << reg) & (BIT(BPF_REG_1) | + BIT(BPF_REG_2) | + BIT(BPF_REG_FP)); +} + static bool is_axreg(u32 reg) { return reg == BPF_REG_0; @@ -598,9 +611,8 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) switch (size) { case BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ - if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* We have to add extra byte for x86 SIL, DIL regs */ - src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) + /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 4d2a7a764602..66cd150b7e54 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1847,14 +1847,16 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_B: case BPF_H: case BPF_W: - if (!bpf_prog->aux->verifier_zext) + if (bpf_prog->aux->verifier_zext) break; if (dstk) { EMIT3(0xC7, add_1reg(0x40, IA32_EBP), STACK_VAR(dst_hi)); EMIT(0x0, 4); } else { - EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0); + /* xor dst_hi,dst_hi */ + EMIT2(0x33, + add_2reg(0xC0, dst_hi, dst_hi)); } break; case BPF_DW: @@ -2013,8 +2015,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = sstk ? IA32_ECX : src_lo; u8 sreg_hi = sstk ? IA32_EBX : src_hi; @@ -2026,6 +2028,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } if (sstk) { @@ -2050,8 +2059,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: { bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP; - u8 dreg_lo = dstk ? IA32_EAX : dst_lo; - u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 dreg_lo = IA32_EAX; + u8 dreg_hi = IA32_EDX; u8 sreg_lo = IA32_ECX; u8 sreg_hi = IA32_EBX; u32 hi; @@ -2064,6 +2073,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst_hi)); + } else { + /* mov dreg_lo,dst_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo)); + if (is_jmp64) + /* mov dreg_hi,dst_hi */ + EMIT2(0x89, + add_2reg(0xC0, dreg_hi, dst_hi)); } /* mov ecx,imm32 */ diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 211bb9358b73..c5e393f8bb3f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -202,7 +202,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size) int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - unsigned long pfn, text, pf; + unsigned long pfn, text, pf, rodata; struct page *page; unsigned npages; pgd_t *pgd = efi_mm.pgd; @@ -256,7 +256,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ - npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT; + npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); pfn = text >> PAGE_SHIFT; @@ -266,6 +266,14 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } + npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; + rodata = __pa(__start_rodata); + pfn = rodata >> PAGE_SHIFT; + if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { + pr_err("Failed to map kernel rodata 1:1\n"); + return 1; + } + return 0; } @@ -638,7 +646,7 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, @@ -669,7 +677,7 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, diff --git a/arch/xtensa/include/asm/module.h b/arch/xtensa/include/asm/vermagic.h index 488b40c6f9b9..6d9c670e4ba9 100644 --- a/arch/xtensa/include/asm/module.h +++ b/arch/xtensa/include/asm/vermagic.h @@ -1,8 +1,4 @@ /* - * include/asm-xtensa/module.h - * - * This file contains the module code specific to the Xtensa architecture. - * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. @@ -10,11 +6,12 @@ * Copyright (C) 2001 - 2005 Tensilica Inc. */ -#ifndef _XTENSA_MODULE_H -#define _XTENSA_MODULE_H +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H -#define MODULE_ARCH_VERMAGIC "xtensa-" __stringify(XCHAL_CORE_ID) " " +#include <linux/stringify.h> +#include <variant/core.h> -#include <asm-generic/module.h> +#define MODULE_ARCH_VERMAGIC "xtensa-" __stringify(XCHAL_CORE_ID) " " -#endif /* _XTENSA_MODULE_H */ +#endif /* _ASM_VERMAGIC_H */ diff --git a/block/blk-iocost.c b/block/blk-iocost.c index db35ee682294..3ab0c1c704b6 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1591,7 +1591,7 @@ skip_surplus_transfers: vrate_min, vrate_max); } - trace_iocost_ioc_vrate_adj(ioc, vrate, &missed_ppm, rq_wait_pct, + trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages, nr_surpluses); @@ -1600,7 +1600,7 @@ skip_surplus_transfers: ioc->period_us * vrate * INUSE_MARGIN_PCT, 100); } else if (ioc->busy_level != prev_busy_level || nr_lagging) { trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate), - &missed_ppm, rq_wait_pct, nr_lagging, + missed_ppm, rq_wait_pct, nr_lagging, nr_shortages, nr_surpluses); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 8e56884fd2e9..a7785df2c944 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1222,8 +1222,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, rq = list_first_entry(list, struct request, queuelist); hctx = rq->mq_hctx; - if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) + if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) { + blk_mq_put_driver_tag(rq); break; + } if (!blk_mq_get_driver_tag(rq)) { /* diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 8641ba9793c5..9cb082f38b93 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -313,7 +313,7 @@ static void scale_up(struct rq_wb *rwb) calc_wb_limits(rwb); rwb->unknown_cnt = 0; rwb_wake_all(rwb); - rwb_trace_step(rwb, "scale up"); + rwb_trace_step(rwb, tracepoint_string("scale up")); } static void scale_down(struct rq_wb *rwb, bool hard_throttle) @@ -322,7 +322,7 @@ static void scale_down(struct rq_wb *rwb, bool hard_throttle) return; calc_wb_limits(rwb); rwb->unknown_cnt = 0; - rwb_trace_step(rwb, "scale down"); + rwb_trace_step(rwb, tracepoint_string("scale down")); } static void rwb_arm_timer(struct rq_wb *rwb) diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 00112cf15322..78cfc70cb320 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -88,18 +88,6 @@ static const struct dmi_system_id dmi_lid_quirks[] = { .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED, }, { - /* - * Asus T200TA, _LID keeps reporting closed after every second - * openening of the lid. Causing immediate re-suspend after - * opening every other open. Using LID_INIT_OPEN fixes this. - */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"), - }, - .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, - }, - { /* GP-electronic T701, _LID method points to a floating GPIO */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 00a6da2121be..ed3d2182cf2c 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -322,10 +322,10 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) resource->res.data.extended_irq.polarity = link->irq.polarity; if (link->irq.triggering == ACPI_EDGE_SENSITIVE) - resource->res.data.irq.shareable = + resource->res.data.extended_irq.shareable = ACPI_EXCLUSIVE; else - resource->res.data.irq.shareable = ACPI_SHARED; + resource->res.data.extended_irq.shareable = ACPI_SHARED; resource->res.data.extended_irq.interrupt_count = 1; resource->res.data.extended_irq.interrupts[0] = irq; /* ignore resource_source, it's optional */ diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 0101b65250cb..0c0a736eb861 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -410,6 +410,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */ { PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */ { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */ + { PCI_VDEVICE(INTEL, 0x02d3), board_ahci_mobile }, /* Comet Lake PCH-U AHCI */ { PCI_VDEVICE(INTEL, 0x02d7), board_ahci_mobile }, /* Comet Lake PCH RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index a6b76cc12a66..e517bd8822a5 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -145,7 +145,7 @@ enum { /* PORT_IDMA_CTL bits */ IDMA_CTL_RST_ATA = (1 << 2), /* hardreset ATA bus */ - IDMA_CTL_RST_IDMA = (1 << 5), /* reset IDMA machinary */ + IDMA_CTL_RST_IDMA = (1 << 5), /* reset IDMA machinery */ IDMA_CTL_GO = (1 << 7), /* IDMA mode go */ IDMA_CTL_ATA_NIEN = (1 << 8), /* ATA IRQ disable */ diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index fdd508a78ffd..0e07e17c2def 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -730,7 +730,7 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) if (is_async(dev)) { get_device(dev); - async_schedule(func, dev); + async_schedule_dev(func, dev); return true; } diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index 62b660821dbc..81b311c9d781 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -85,26 +85,35 @@ struct nullb { char disk_name[DISK_NAME_LEN]; }; +blk_status_t null_process_cmd(struct nullb_cmd *cmd, + enum req_opf op, sector_t sector, + unsigned int nr_sectors); + #ifdef CONFIG_BLK_DEV_ZONED -int null_zone_init(struct nullb_device *dev); -void null_zone_exit(struct nullb_device *dev); +int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q); +int null_register_zoned_dev(struct nullb *nullb); +void null_free_zoned_dev(struct nullb_device *dev); int null_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); -blk_status_t null_handle_zoned(struct nullb_cmd *cmd, - enum req_opf op, sector_t sector, - sector_t nr_sectors); +blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, + enum req_opf op, sector_t sector, + sector_t nr_sectors); size_t null_zone_valid_read_len(struct nullb *nullb, sector_t sector, unsigned int len); #else -static inline int null_zone_init(struct nullb_device *dev) +static inline int null_init_zoned_dev(struct nullb_device *dev, + struct request_queue *q) { pr_err("CONFIG_BLK_DEV_ZONED not enabled\n"); return -EINVAL; } -static inline void null_zone_exit(struct nullb_device *dev) {} -static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd, - enum req_opf op, sector_t sector, - sector_t nr_sectors) +static inline int null_register_zoned_dev(struct nullb *nullb) +{ + return -ENODEV; +} +static inline void null_free_zoned_dev(struct nullb_device *dev) {} +static inline blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, + enum req_opf op, sector_t sector, sector_t nr_sectors) { return BLK_STS_NOTSUPP; } diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 4e1c0712278e..8efd8778e209 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -580,7 +580,7 @@ static void null_free_dev(struct nullb_device *dev) if (!dev) return; - null_zone_exit(dev); + null_free_zoned_dev(dev); badblocks_exit(&dev->badblocks); kfree(dev); } @@ -1276,6 +1276,25 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd) } } +blk_status_t null_process_cmd(struct nullb_cmd *cmd, + enum req_opf op, sector_t sector, + unsigned int nr_sectors) +{ + struct nullb_device *dev = cmd->nq->dev; + blk_status_t ret; + + if (dev->badblocks.shift != -1) { + ret = null_handle_badblocks(cmd, sector, nr_sectors); + if (ret != BLK_STS_OK) + return ret; + } + + if (dev->memory_backed) + return null_handle_memory_backed(cmd, op); + + return BLK_STS_OK; +} + static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector, sector_t nr_sectors, enum req_opf op) { @@ -1294,17 +1313,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector, goto out; } - if (nullb->dev->badblocks.shift != -1) { - cmd->error = null_handle_badblocks(cmd, sector, nr_sectors); - if (cmd->error != BLK_STS_OK) - goto out; - } - - if (dev->memory_backed) - cmd->error = null_handle_memory_backed(cmd, op); - - if (!cmd->error && dev->zoned) - cmd->error = null_handle_zoned(cmd, op, sector, nr_sectors); + if (dev->zoned) + cmd->error = null_process_zoned_cmd(cmd, op, + sector, nr_sectors); + else + cmd->error = null_process_cmd(cmd, op, sector, nr_sectors); out: nullb_complete_cmd(cmd); @@ -1605,19 +1618,12 @@ static int null_gendisk_register(struct nullb *nullb) disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); -#ifdef CONFIG_BLK_DEV_ZONED if (nullb->dev->zoned) { - if (queue_is_mq(nullb->q)) { - int ret = blk_revalidate_disk_zones(disk); - if (ret) - return ret; - } else { - blk_queue_chunk_sectors(nullb->q, - nullb->dev->zone_size_sects); - nullb->q->nr_zones = blkdev_nr_zones(disk); - } + int ret = null_register_zoned_dev(nullb); + + if (ret) + return ret; } -#endif add_disk(disk); return 0; @@ -1773,14 +1779,9 @@ static int null_add_dev(struct nullb_device *dev) } if (dev->zoned) { - rv = null_zone_init(dev); + rv = null_init_zoned_dev(dev, nullb->q); if (rv) goto out_cleanup_blk_queue; - - nullb->q->limits.zoned = BLK_ZONED_HM; - blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, nullb->q); - blk_queue_required_elevator_features(nullb->q, - ELEVATOR_F_ZBD_SEQ_WRITE); } nullb->q->queuedata = nullb; @@ -1809,8 +1810,7 @@ static int null_add_dev(struct nullb_device *dev) return 0; out_cleanup_zone: - if (dev->zoned) - null_zone_exit(dev); + null_free_zoned_dev(dev); out_cleanup_blk_queue: blk_cleanup_queue(nullb->q); out_cleanup_tags: diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 673618d8222a..9e4bcdad1a80 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -13,7 +13,7 @@ static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect) return sect >> ilog2(dev->zone_size_sects); } -int null_zone_init(struct nullb_device *dev) +int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) { sector_t dev_size = (sector_t)dev->size * 1024 * 1024; sector_t sector = 0; @@ -61,10 +61,27 @@ int null_zone_init(struct nullb_device *dev) sector += dev->zone_size_sects; } + q->limits.zoned = BLK_ZONED_HM; + blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); + blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE); + + return 0; +} + +int null_register_zoned_dev(struct nullb *nullb) +{ + struct request_queue *q = nullb->q; + + if (queue_is_mq(q)) + return blk_revalidate_disk_zones(nullb->disk); + + blk_queue_chunk_sectors(q, nullb->dev->zone_size_sects); + q->nr_zones = blkdev_nr_zones(nullb->disk); + return 0; } -void null_zone_exit(struct nullb_device *dev) +void null_free_zoned_dev(struct nullb_device *dev) { kvfree(dev->zones); } @@ -126,11 +143,16 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, struct nullb_device *dev = cmd->nq->dev; unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; + blk_status_t ret; + + trace_nullb_zone_op(cmd, zno, zone->cond); + + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors); switch (zone->cond) { case BLK_ZONE_COND_FULL: /* Cannot write to a full zone */ - cmd->error = BLK_STS_IOERR; return BLK_STS_IOERR; case BLK_ZONE_COND_EMPTY: case BLK_ZONE_COND_IMP_OPEN: @@ -143,19 +165,18 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector, if (zone->cond != BLK_ZONE_COND_EXP_OPEN) zone->cond = BLK_ZONE_COND_IMP_OPEN; + ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors); + if (ret != BLK_STS_OK) + return ret; + zone->wp += nr_sectors; if (zone->wp == zone->start + zone->len) zone->cond = BLK_ZONE_COND_FULL; - break; - case BLK_ZONE_COND_NOT_WP: - break; + return BLK_STS_OK; default: /* Invalid zone condition */ return BLK_STS_IOERR; } - - trace_nullb_zone_op(cmd, zno, zone->cond); - return BLK_STS_OK; } static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, @@ -216,8 +237,8 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, return BLK_STS_OK; } -blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, - sector_t sector, sector_t nr_sectors) +blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op, + sector_t sector, sector_t nr_sectors) { switch (op) { case REQ_OP_WRITE: @@ -229,6 +250,6 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, case REQ_OP_ZONE_FINISH: return null_zone_mgmt(cmd, op, sector); default: - return BLK_STS_OK; + return null_process_cmd(cmd, op, sector, nr_sectors); } } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 1e0a6b19ae0d..67d65ac785e9 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3754,11 +3754,7 @@ static int __rbd_notify_op_lock(struct rbd_device *rbd_dev, static void rbd_notify_op_lock(struct rbd_device *rbd_dev, enum rbd_notify_op notify_op) { - struct page **reply_pages; - size_t reply_len; - - __rbd_notify_op_lock(rbd_dev, notify_op, &reply_pages, &reply_len); - ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len)); + __rbd_notify_op_lock(rbd_dev, notify_op, NULL, NULL); } static void rbd_notify_acquired_lock(struct work_struct *work) @@ -4527,6 +4523,10 @@ static void cancel_tasks_sync(struct rbd_device *rbd_dev) cancel_work_sync(&rbd_dev->unlock_work); } +/* + * header_rwsem must not be held to avoid a deadlock with + * rbd_dev_refresh() when flushing notifies. + */ static void rbd_unregister_watch(struct rbd_device *rbd_dev) { cancel_tasks_sync(rbd_dev); @@ -6894,9 +6894,10 @@ static void rbd_print_dne(struct rbd_device *rbd_dev, bool is_snap) static void rbd_dev_image_release(struct rbd_device *rbd_dev) { - rbd_dev_unprobe(rbd_dev); - if (rbd_dev->opts) + if (!rbd_is_ro(rbd_dev)) rbd_unregister_watch(rbd_dev); + + rbd_dev_unprobe(rbd_dev); rbd_dev->image_format = 0; kfree(rbd_dev->spec->image_id); rbd_dev->spec->image_id = NULL; @@ -6907,6 +6908,9 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev) * device. If this image is the one being mapped (i.e., not a * parent), initiate a watch on its header object before using that * object to get detailed information about the rbd image. + * + * On success, returns with header_rwsem held for write if called + * with @depth == 0. */ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) { @@ -6936,11 +6940,14 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) } } + if (!depth) + down_write(&rbd_dev->header_rwsem); + ret = rbd_dev_header_info(rbd_dev); if (ret) { if (ret == -ENOENT && !need_watch) rbd_print_dne(rbd_dev, false); - goto err_out_watch; + goto err_out_probe; } /* @@ -6985,10 +6992,11 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) return 0; err_out_probe: - rbd_dev_unprobe(rbd_dev); -err_out_watch: + if (!depth) + up_write(&rbd_dev->header_rwsem); if (need_watch) rbd_unregister_watch(rbd_dev); + rbd_dev_unprobe(rbd_dev); err_out_format: rbd_dev->image_format = 0; kfree(rbd_dev->spec->image_id); @@ -7050,12 +7058,9 @@ static ssize_t do_rbd_add(struct bus_type *bus, goto err_out_rbd_dev; } - down_write(&rbd_dev->header_rwsem); rc = rbd_dev_image_probe(rbd_dev, 0); - if (rc < 0) { - up_write(&rbd_dev->header_rwsem); + if (rc < 0) goto err_out_rbd_dev; - } if (rbd_dev->opts->alloc_size > rbd_dev->layout.object_size) { rbd_warn(rbd_dev, "alloc_size adjusted to %u", diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index f9b1e70f1b31..93468b7c6701 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -15,6 +15,7 @@ #include <linux/blk-mq.h> #include <linux/blk-mq-virtio.h> #include <linux/numa.h> +#include <uapi/linux/virtio_ring.h> #define PART_BITS 4 #define VQ_NAME_LEN 16 diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index a16845c0751d..3ea866d44568 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -32,7 +32,7 @@ int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version, * VSE event. WCN3991 sends version command response as a payload to * command complete event. */ - if (soc_type == QCA_WCN3991) { + if (soc_type >= QCA_WCN3991) { event_type = 0; rlen += 1; rtype = EDL_PATCH_VER_REQ_CMD; @@ -69,7 +69,7 @@ int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version, goto out; } - if (soc_type == QCA_WCN3991) + if (soc_type >= QCA_WCN3991) memmove(&edl->data, &edl->data[1], sizeof(*ver)); ver = (struct qca_btsoc_version *)(edl->data); @@ -217,7 +217,7 @@ static void qca_tlv_check_data(struct qca_fw_config *config, tlv_nvm->data[0] |= 0x80; /* UART Baud Rate */ - if (soc_type == QCA_WCN3991) + if (soc_type >= QCA_WCN3991) tlv_nvm->data[1] = nvm_baud_rate; else tlv_nvm->data[2] = nvm_baud_rate; @@ -268,7 +268,7 @@ static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, * VSE event. WCN3991 sends version command response as a payload to * command complete event. */ - if (soc_type == QCA_WCN3991) { + if (soc_type >= QCA_WCN3991) { event_type = 0; rlen = sizeof(*edl); rtype = EDL_PATCH_TLV_REQ_CMD; @@ -301,7 +301,7 @@ static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, err = -EIO; } - if (soc_type == QCA_WCN3991) + if (soc_type >= QCA_WCN3991) goto out; tlv_resp = (struct tlv_seg_resp *)(edl->data); @@ -442,6 +442,11 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, (soc_ver & 0x0000000f); snprintf(config.fwname, sizeof(config.fwname), "qca/crbtfw%02x.tlv", rom_ver); + } else if (soc_type == QCA_QCA6390) { + rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | + (soc_ver & 0x0000000f); + snprintf(config.fwname, sizeof(config.fwname), + "qca/htbtfw%02x.tlv", rom_ver); } else { snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin", soc_ver); @@ -464,6 +469,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, else if (qca_is_wcn399x(soc_type)) snprintf(config.fwname, sizeof(config.fwname), "qca/crnv%02x.bin", rom_ver); + else if (soc_type == QCA_QCA6390) + snprintf(config.fwname, sizeof(config.fwname), + "qca/htnv%02x.bin", rom_ver); else snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin", soc_ver); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index e16a4d650597..6e1e62dd4b95 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -125,8 +125,9 @@ enum qca_btsoc_type { QCA_AR3002, QCA_ROME, QCA_WCN3990, - QCA_WCN3991, QCA_WCN3998, + QCA_WCN3991, + QCA_QCA6390, }; #if IS_ENABLED(CONFIG_BT_QCA) diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 67f4bc21e7c5..3a9afc905f24 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -130,12 +130,19 @@ static const struct id_table ic_id_table[] = { .cfg_name = "rtl_bt/rtl8821c_config" }, /* 8761A */ - { IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0, + { IC_INFO(RTL_ROM_LMP_8761A, 0xa), .config_needed = false, .has_rom_version = true, .fw_name = "rtl_bt/rtl8761a_fw.bin", .cfg_name = "rtl_bt/rtl8761a_config" }, + /* 8761B */ + { IC_INFO(RTL_ROM_LMP_8761A, 0xb), + .config_needed = false, + .has_rom_version = true, + .fw_name = "rtl_bt/rtl8761b_fw.bin", + .cfg_name = "rtl_bt/rtl8761b_config" }, + /* 8822C with UART interface */ { .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV | IC_MATCH_FL_HCIBUS, @@ -267,6 +274,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, { RTL_ROM_LMP_8723B, 9 }, /* 8723D */ { RTL_ROM_LMP_8821A, 10 }, /* 8821C */ { RTL_ROM_LMP_8822B, 13 }, /* 8822C */ + { RTL_ROM_LMP_8761A, 14 }, /* 8761B */ }; min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 3bdec42c9612..871162790a0e 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -492,6 +492,8 @@ struct btusb_data { __u8 cmdreq; unsigned int sco_num; + unsigned int air_mode; + bool usb_alt6_packet_flow; int isoc_altsetting; int suspend_count; @@ -983,6 +985,42 @@ static void btusb_isoc_complete(struct urb *urb) } } +static inline void __fill_isoc_descriptor_msbc(struct urb *urb, int len, + int mtu, struct btusb_data *data) +{ + int i, offset = 0; + unsigned int interval; + + BT_DBG("len %d mtu %d", len, mtu); + + /* For mSBC ALT 6 setting the host will send the packet at continuous + * flow. As per core spec 5, vol 4, part B, table 2.1. For ALT setting + * 6 the HCI PACKET INTERVAL should be 7.5ms for every usb packets. + * To maintain the rate we send 63bytes of usb packets alternatively for + * 7ms and 8ms to maintain the rate as 7.5ms. + */ + if (data->usb_alt6_packet_flow) { + interval = 7; + data->usb_alt6_packet_flow = false; + } else { + interval = 6; + data->usb_alt6_packet_flow = true; + } + + for (i = 0; i < interval; i++) { + urb->iso_frame_desc[i].offset = offset; + urb->iso_frame_desc[i].length = offset; + } + + if (len && i < BTUSB_MAX_ISOC_FRAMES) { + urb->iso_frame_desc[i].offset = offset; + urb->iso_frame_desc[i].length = len; + i++; + } + + urb->number_of_packets = i; +} + static inline void __fill_isoc_descriptor(struct urb *urb, int len, int mtu) { int i, offset = 0; @@ -1386,9 +1424,13 @@ static struct urb *alloc_isoc_urb(struct hci_dev *hdev, struct sk_buff *skb) urb->transfer_flags = URB_ISO_ASAP; - __fill_isoc_descriptor(urb, skb->len, - le16_to_cpu(data->isoc_tx_ep->wMaxPacketSize)); - + if (data->isoc_altsetting == 6) + __fill_isoc_descriptor_msbc(urb, skb->len, + le16_to_cpu(data->isoc_tx_ep->wMaxPacketSize), + data); + else + __fill_isoc_descriptor(urb, skb->len, + le16_to_cpu(data->isoc_tx_ep->wMaxPacketSize)); skb->dev = (void *)hdev; return urb; @@ -1484,6 +1526,7 @@ static void btusb_notify(struct hci_dev *hdev, unsigned int evt) if (hci_conn_num(hdev, SCO_LINK) != data->sco_num) { data->sco_num = hci_conn_num(hdev, SCO_LINK); + data->air_mode = evt; schedule_work(&data->work); } } @@ -1531,11 +1574,70 @@ static inline int __set_isoc_interface(struct hci_dev *hdev, int altsetting) return 0; } +static int btusb_switch_alt_setting(struct hci_dev *hdev, int new_alts) +{ + struct btusb_data *data = hci_get_drvdata(hdev); + int err; + + if (data->isoc_altsetting != new_alts) { + unsigned long flags; + + clear_bit(BTUSB_ISOC_RUNNING, &data->flags); + usb_kill_anchored_urbs(&data->isoc_anchor); + + /* When isochronous alternate setting needs to be + * changed, because SCO connection has been added + * or removed, a packet fragment may be left in the + * reassembling state. This could lead to wrongly + * assembled fragments. + * + * Clear outstanding fragment when selecting a new + * alternate setting. + */ + spin_lock_irqsave(&data->rxlock, flags); + kfree_skb(data->sco_skb); + data->sco_skb = NULL; + spin_unlock_irqrestore(&data->rxlock, flags); + + err = __set_isoc_interface(hdev, new_alts); + if (err < 0) + return err; + } + + if (!test_and_set_bit(BTUSB_ISOC_RUNNING, &data->flags)) { + if (btusb_submit_isoc_urb(hdev, GFP_KERNEL) < 0) + clear_bit(BTUSB_ISOC_RUNNING, &data->flags); + else + btusb_submit_isoc_urb(hdev, GFP_KERNEL); + } + + return 0; +} + +static struct usb_host_interface *btusb_find_altsetting(struct btusb_data *data, + int alt) +{ + struct usb_interface *intf = data->isoc; + int i; + + BT_DBG("Looking for Alt no :%d", alt); + + if (!intf) + return NULL; + + for (i = 0; i < intf->num_altsetting; i++) { + if (intf->altsetting[i].desc.bAlternateSetting == alt) + return &intf->altsetting[i]; + } + + return NULL; +} + static void btusb_work(struct work_struct *work) { struct btusb_data *data = container_of(work, struct btusb_data, work); struct hci_dev *hdev = data->hdev; - int new_alts; + int new_alts = 0; int err; if (data->sco_num > 0) { @@ -1550,44 +1652,27 @@ static void btusb_work(struct work_struct *work) set_bit(BTUSB_DID_ISO_RESUME, &data->flags); } - if (hdev->voice_setting & 0x0020) { - static const int alts[3] = { 2, 4, 5 }; + if (data->air_mode == HCI_NOTIFY_ENABLE_SCO_CVSD) { + if (hdev->voice_setting & 0x0020) { + static const int alts[3] = { 2, 4, 5 }; - new_alts = alts[data->sco_num - 1]; - } else { - new_alts = data->sco_num; - } - - if (data->isoc_altsetting != new_alts) { - unsigned long flags; - - clear_bit(BTUSB_ISOC_RUNNING, &data->flags); - usb_kill_anchored_urbs(&data->isoc_anchor); - - /* When isochronous alternate setting needs to be - * changed, because SCO connection has been added - * or removed, a packet fragment may be left in the - * reassembling state. This could lead to wrongly - * assembled fragments. - * - * Clear outstanding fragment when selecting a new - * alternate setting. - */ - spin_lock_irqsave(&data->rxlock, flags); - kfree_skb(data->sco_skb); - data->sco_skb = NULL; - spin_unlock_irqrestore(&data->rxlock, flags); + new_alts = alts[data->sco_num - 1]; + } else { + new_alts = data->sco_num; + } + } else if (data->air_mode == HCI_NOTIFY_ENABLE_SCO_TRANSP) { - if (__set_isoc_interface(hdev, new_alts) < 0) - return; - } + data->usb_alt6_packet_flow = true; - if (!test_and_set_bit(BTUSB_ISOC_RUNNING, &data->flags)) { - if (btusb_submit_isoc_urb(hdev, GFP_KERNEL) < 0) - clear_bit(BTUSB_ISOC_RUNNING, &data->flags); + /* Check if Alt 6 is supported for Transparent audio */ + if (btusb_find_altsetting(data, 6)) + new_alts = 6; else - btusb_submit_isoc_urb(hdev, GFP_KERNEL); + bt_dev_err(hdev, "Device does not support ALT setting 6"); } + + if (btusb_switch_alt_setting(hdev, new_alts) < 0) + bt_dev_err(hdev, "set USB alt:(%d) failed!", new_alts); } else { clear_bit(BTUSB_ISOC_RUNNING, &data->flags); usb_kill_anchored_urbs(&data->isoc_anchor); @@ -2252,7 +2337,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) if (ver.fw_variant == 0x23) { clear_bit(BTUSB_BOOTLOADER, &data->flags); btintel_check_bdaddr(hdev); - return 0; + goto finish; } /* If the device is not in bootloader mode, then the only possible @@ -2452,6 +2537,23 @@ done: */ btintel_load_ddc_config(hdev, fwname); + /* Read the Intel version information after loading the FW */ + err = btintel_read_version(hdev, &ver); + if (err) + return err; + + btintel_version_info(hdev, &ver); + +finish: + /* All Intel controllers that support the Microsoft vendor + * extension are using 0xFC1E for VsMsftOpCode. + */ + switch (ver.hw_variant) { + case 0x12: /* ThP */ + hci_set_msft_opcode(hdev, 0xFC1E); + break; + } + /* Set the event mask for Intel specific vendor events. This enables * a few extra events that are useful during general operation. It * does not enable any debugging related events. @@ -2461,13 +2563,6 @@ done: */ btintel_set_event_mask(hdev, false); - /* Read the Intel version information after loading the FW */ - err = btintel_read_version(hdev, &ver); - if (err) - return err; - - btintel_version_info(hdev, &ver); - return 0; } diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index b236cb11c0dc..19e4587f366c 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -118,6 +118,7 @@ struct bcm_device { u32 oper_speed; int irq; bool irq_active_low; + bool irq_acquired; #ifdef CONFIG_PM struct hci_uart *hu; @@ -333,6 +334,8 @@ static int bcm_request_irq(struct bcm_data *bcm) goto unlock; } + bdev->irq_acquired = true; + device_init_wakeup(bdev->dev, true); pm_runtime_set_autosuspend_delay(bdev->dev, @@ -514,7 +517,7 @@ static int bcm_close(struct hci_uart *hu) } if (bdev) { - if (IS_ENABLED(CONFIG_PM) && bdev->irq > 0) { + if (IS_ENABLED(CONFIG_PM) && bdev->irq_acquired) { devm_free_irq(bdev->dev, bdev->irq, bdev); device_init_wakeup(bdev->dev, false); pm_runtime_disable(bdev->dev); @@ -1153,7 +1156,8 @@ static int bcm_of_probe(struct bcm_device *bdev) device_property_read_u8_array(bdev->dev, "brcm,bt-pcm-int-params", bdev->pcm_int_params, 5); bdev->irq = of_irq_get_byname(bdev->dev->of_node, "host-wakeup"); - + bdev->irq_active_low = irq_get_trigger_type(bdev->irq) + & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_LEVEL_LOW); return 0; } diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 439392b1c043..d0ac554584a4 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -26,6 +26,7 @@ #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/of_device.h> +#include <linux/acpi.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> #include <linux/serdev.h> @@ -1596,7 +1597,7 @@ static int qca_setup(struct hci_uart *hu) set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); bt_dev_info(hdev, "setting up %s", - qca_is_wcn399x(soc_type) ? "wcn399x" : "ROME"); + qca_is_wcn399x(soc_type) ? "wcn399x" : "ROME/QCA6390"); retry: ret = qca_power_on(hdev); @@ -1665,10 +1666,10 @@ retry: } /* Setup bdaddr */ - if (qca_is_wcn399x(soc_type)) - hu->hdev->set_bdaddr = qca_set_bdaddr; - else + if (soc_type == QCA_ROME) hu->hdev->set_bdaddr = qca_set_bdaddr_rome; + else + hu->hdev->set_bdaddr = qca_set_bdaddr; return ret; } @@ -1721,6 +1722,11 @@ static const struct qca_vreg_data qca_soc_data_wcn3998 = { .num_vregs = 4, }; +static const struct qca_vreg_data qca_soc_data_qca6390 = { + .soc_type = QCA_QCA6390, + .num_vregs = 0, +}; + static void qca_power_shutdown(struct hci_uart *hu) { struct qca_serdev *qcadev; @@ -1764,7 +1770,7 @@ static int qca_power_off(struct hci_dev *hdev) enum qca_btsoc_type soc_type = qca_soc_type(hu); /* Stop sending shutdown command if soc crashes. */ - if (qca_is_wcn399x(soc_type) + if (soc_type != QCA_ROME && qca->memdump_state == QCA_MEMDUMP_IDLE) { qca_send_pre_shutdown_cmd(hdev); usleep_range(8000, 10000); @@ -1900,7 +1906,11 @@ static int qca_serdev_probe(struct serdev_device *serdev) return err; } } else { - qcadev->btsoc_type = QCA_ROME; + if (data) + qcadev->btsoc_type = data->soc_type; + else + qcadev->btsoc_type = QCA_ROME; + qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); if (!qcadev->bt_en) { @@ -2044,21 +2054,37 @@ static int __maybe_unused qca_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(qca_pm_ops, qca_suspend, qca_resume); +#ifdef CONFIG_OF static const struct of_device_id qca_bluetooth_of_match[] = { { .compatible = "qcom,qca6174-bt" }, + { .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390}, { .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990}, { .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991}, { .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); +#endif + +#ifdef CONFIG_ACPI +static const struct acpi_device_id qca_bluetooth_acpi_match[] = { + { "QCOM6390", (kernel_ulong_t)&qca_soc_data_qca6390 }, + { "DLA16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, + { "DLB16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, + { "DLB26390", (kernel_ulong_t)&qca_soc_data_qca6390 }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, qca_bluetooth_acpi_match); +#endif + static struct serdev_device_driver qca_serdev_driver = { .probe = qca_serdev_probe, .remove = qca_serdev_remove, .driver = { .name = "hci_uart_qca", - .of_match_table = qca_bluetooth_of_match, + .of_match_table = of_match_ptr(qca_bluetooth_of_match), + .acpi_match_table = ACPI_PTR(qca_bluetooth_acpi_match), .pm = &qca_pm_ops, }, }; diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 718d8c087650..79a6e47b5fbc 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -11,6 +11,7 @@ #include <linux/virtio.h> #include <linux/virtio_rng.h> #include <linux/module.h> +#include <linux/slab.h> static DEFINE_IDA(rng_index_ida); diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index a438b1206fcb..1621ce818705 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -323,7 +323,7 @@ int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, for (i = 0; i < chip->nr_allocated_banks; i++) { if (digests[i].alg_id != chip->allocated_banks[i].alg_id) { - rc = EINVAL; + rc = -EINVAL; goto out; } } diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 76f67b155bd5..eff1f12d981a 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -681,6 +681,7 @@ out: rc = -ENODEV; return rc; } +EXPORT_SYMBOL_GPL(tpm2_get_cc_attrs_tbl); /** * tpm2_startup - turn on the TPM diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index 1a49db9e108e..09fe45246b8c 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2012 IBM Corporation + * Copyright (C) 2012-2020 IBM Corporation * * Author: Ashley Lai <ashleydlai@gmail.com> * @@ -135,6 +135,64 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count) } /** + * ibmvtpm_crq_send_init - Send a CRQ initialize message + * @ibmvtpm: vtpm device struct + * + * Return: + * 0 on success. + * Non-zero on failure. + */ +static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm) +{ + int rc; + + rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD); + if (rc != H_SUCCESS) + dev_err(ibmvtpm->dev, + "%s failed rc=%d\n", __func__, rc); + + return rc; +} + +/** + * tpm_ibmvtpm_resume - Resume from suspend + * + * @dev: device struct + * + * Return: Always 0. + */ +static int tpm_ibmvtpm_resume(struct device *dev) +{ + struct tpm_chip *chip = dev_get_drvdata(dev); + struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); + int rc = 0; + + do { + if (rc) + msleep(100); + rc = plpar_hcall_norets(H_ENABLE_CRQ, + ibmvtpm->vdev->unit_address); + } while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc)); + + if (rc) { + dev_err(dev, "Error enabling ibmvtpm rc=%d\n", rc); + return rc; + } + + rc = vio_enable_interrupts(ibmvtpm->vdev); + if (rc) { + dev_err(dev, "Error vio_enable_interrupts rc=%d\n", rc); + return rc; + } + + rc = ibmvtpm_crq_send_init(ibmvtpm); + if (rc) + dev_err(dev, "Error send_init rc=%d\n", rc); + + return rc; +} + +/** * tpm_ibmvtpm_send() - Send a TPM command * @chip: tpm chip struct * @buf: buffer contains data to send @@ -147,6 +205,7 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count) static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) { struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); + bool retry = true; int rc, sig; if (!ibmvtpm->rtce_buf) { @@ -180,18 +239,27 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) */ ibmvtpm->tpm_processing_cmd = true; +again: rc = ibmvtpm_send_crq(ibmvtpm->vdev, IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND, count, ibmvtpm->rtce_dma_handle); if (rc != H_SUCCESS) { + /* + * H_CLOSED can be returned after LPM resume. Call + * tpm_ibmvtpm_resume() to re-enable the CRQ then retry + * ibmvtpm_send_crq() once before failing. + */ + if (rc == H_CLOSED && retry) { + tpm_ibmvtpm_resume(ibmvtpm->dev); + retry = false; + goto again; + } dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc); - rc = 0; ibmvtpm->tpm_processing_cmd = false; - } else - rc = 0; + } spin_unlock(&ibmvtpm->rtce_lock); - return rc; + return 0; } static void tpm_ibmvtpm_cancel(struct tpm_chip *chip) @@ -270,26 +338,6 @@ static int ibmvtpm_crq_send_init_complete(struct ibmvtpm_dev *ibmvtpm) } /** - * ibmvtpm_crq_send_init - Send a CRQ initialize message - * @ibmvtpm: vtpm device struct - * - * Return: - * 0 on success. - * Non-zero on failure. - */ -static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm) -{ - int rc; - - rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD); - if (rc != H_SUCCESS) - dev_err(ibmvtpm->dev, - "ibmvtpm_crq_send_init failed rc=%d\n", rc); - - return rc; -} - -/** * tpm_ibmvtpm_remove - ibm vtpm remove entry point * @vdev: vio device struct * @@ -401,44 +449,6 @@ static int ibmvtpm_reset_crq(struct ibmvtpm_dev *ibmvtpm) ibmvtpm->crq_dma_handle, CRQ_RES_BUF_SIZE); } -/** - * tpm_ibmvtpm_resume - Resume from suspend - * - * @dev: device struct - * - * Return: Always 0. - */ -static int tpm_ibmvtpm_resume(struct device *dev) -{ - struct tpm_chip *chip = dev_get_drvdata(dev); - struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); - int rc = 0; - - do { - if (rc) - msleep(100); - rc = plpar_hcall_norets(H_ENABLE_CRQ, - ibmvtpm->vdev->unit_address); - } while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc)); - - if (rc) { - dev_err(dev, "Error enabling ibmvtpm rc=%d\n", rc); - return rc; - } - - rc = vio_enable_interrupts(ibmvtpm->vdev); - if (rc) { - dev_err(dev, "Error vio_enable_interrupts rc=%d\n", rc); - return rc; - } - - rc = ibmvtpm_crq_send_init(ibmvtpm); - if (rc) - dev_err(dev, "Error send_init rc=%d\n", rc); - - return rc; -} - static bool tpm_ibmvtpm_req_canceled(struct tpm_chip *chip, u8 status) { return (status == 0); diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 27c6ca031e23..2435216bd10a 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -433,6 +433,9 @@ static void disable_interrupts(struct tpm_chip *chip) u32 intmask; int rc; + if (priv->irq == 0) + return; + rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask); if (rc < 0) intmask = 0; @@ -1062,9 +1065,12 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, if (irq) { tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED, irq); - if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) + if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { dev_err(&chip->dev, FW_BUG "TPM interrupt not working, polling instead\n"); + + disable_interrupts(chip); + } } else { tpm_tis_probe_irq(chip, intmask); } diff --git a/drivers/clk/clk-asm9260.c b/drivers/clk/clk-asm9260.c index 536b59aabd2c..bacebd457e6f 100644 --- a/drivers/clk/clk-asm9260.c +++ b/drivers/clk/clk-asm9260.c @@ -276,7 +276,7 @@ static void __init asm9260_acc_init(struct device_node *np) /* TODO: Convert to DT parent scheme */ ref_clk = of_clk_get_parent_name(np, 0); - hw = __clk_hw_register_fixed_rate_with_accuracy(NULL, NULL, pll_clk, + hw = __clk_hw_register_fixed_rate(NULL, NULL, pll_clk, ref_clk, NULL, NULL, 0, rate, 0, CLK_FIXED_RATE_PARENT_ACCURACY); diff --git a/drivers/clk/mmp/clk-pll.c b/drivers/clk/mmp/clk-pll.c index 7077be293871..962014cfdc44 100644 --- a/drivers/clk/mmp/clk-pll.c +++ b/drivers/clk/mmp/clk-pll.c @@ -97,7 +97,7 @@ static const struct clk_ops mmp_clk_pll_ops = { .recalc_rate = mmp_clk_pll_recalc_rate, }; -struct clk *mmp_clk_register_pll(char *name, +static struct clk *mmp_clk_register_pll(char *name, unsigned long default_rate, void __iomem *enable_reg, u32 enable, void __iomem *reg, u8 shift, @@ -137,3 +137,34 @@ struct clk *mmp_clk_register_pll(char *name, return clk; } + +void mmp_register_pll_clks(struct mmp_clk_unit *unit, + struct mmp_param_pll_clk *clks, + void __iomem *base, int size) +{ + struct clk *clk; + int i; + + for (i = 0; i < size; i++) { + void __iomem *reg = NULL; + + if (clks[i].offset) + reg = base + clks[i].offset; + + clk = mmp_clk_register_pll(clks[i].name, + clks[i].default_rate, + base + clks[i].enable_offset, + clks[i].enable, + reg, clks[i].shift, + clks[i].input_rate, + base + clks[i].postdiv_offset, + clks[i].postdiv_shift); + if (IS_ERR(clk)) { + pr_err("%s: failed to register clock %s\n", + __func__, clks[i].name); + continue; + } + if (clks[i].id) + unit->clk_table[clks[i].id] = clk; + } +} diff --git a/drivers/clk/mmp/clk.c b/drivers/clk/mmp/clk.c index 317123641d1e..ca7d37e2c7be 100644 --- a/drivers/clk/mmp/clk.c +++ b/drivers/clk/mmp/clk.c @@ -176,37 +176,6 @@ void mmp_register_div_clks(struct mmp_clk_unit *unit, } } -void mmp_register_pll_clks(struct mmp_clk_unit *unit, - struct mmp_param_pll_clk *clks, - void __iomem *base, int size) -{ - struct clk *clk; - int i; - - for (i = 0; i < size; i++) { - void __iomem *reg = NULL; - - if (clks[i].offset) - reg = base + clks[i].offset; - - clk = mmp_clk_register_pll(clks[i].name, - clks[i].default_rate, - base + clks[i].enable_offset, - clks[i].enable, - reg, clks[i].shift, - clks[i].input_rate, - base + clks[i].postdiv_offset, - clks[i].postdiv_shift); - if (IS_ERR(clk)) { - pr_err("%s: failed to register clock %s\n", - __func__, clks[i].name); - continue; - } - if (clks[i].id) - unit->clk_table[clks[i].id] = clk; - } -} - void mmp_clk_add(struct mmp_clk_unit *unit, unsigned int id, struct clk *clk) { diff --git a/drivers/clk/mmp/clk.h b/drivers/clk/mmp/clk.h index 971b4d6d992f..20dc1e5dd756 100644 --- a/drivers/clk/mmp/clk.h +++ b/drivers/clk/mmp/clk.h @@ -238,13 +238,6 @@ void mmp_register_pll_clks(struct mmp_clk_unit *unit, struct mmp_param_pll_clk *clks, void __iomem *base, int size); -extern struct clk *mmp_clk_register_pll(char *name, - unsigned long default_rate, - void __iomem *enable_reg, u32 enable, - void __iomem *reg, u8 shift, - unsigned long input_rate, - void __iomem *postdiv_reg, u8 postdiv_shift); - #define DEFINE_MIX_REG_INFO(w_d, s_d, w_m, s_m, fc) \ { \ .width_div = (w_d), \ diff --git a/drivers/clk/sprd/sc9863a-clk.c b/drivers/clk/sprd/sc9863a-clk.c index a0631f7756cf..2e2dfb2d48ff 100644 --- a/drivers/clk/sprd/sc9863a-clk.c +++ b/drivers/clk/sprd/sc9863a-clk.c @@ -1641,8 +1641,9 @@ static SPRD_SC_GATE_CLK_FW_NAME(i2c4_eb, "i2c4-eb", "ext-26m", 0x0, 0x1000, BIT(12), 0, 0); static SPRD_SC_GATE_CLK_FW_NAME(uart0_eb, "uart0-eb", "ext-26m", 0x0, 0x1000, BIT(13), 0, 0); +/* uart1_eb is for console, don't gate even if unused */ static SPRD_SC_GATE_CLK_FW_NAME(uart1_eb, "uart1-eb", "ext-26m", 0x0, - 0x1000, BIT(14), 0, 0); + 0x1000, BIT(14), CLK_IGNORE_UNUSED, 0); static SPRD_SC_GATE_CLK_FW_NAME(uart2_eb, "uart2-eb", "ext-26m", 0x0, 0x1000, BIT(15), 0, 0); static SPRD_SC_GATE_CLK_FW_NAME(uart3_eb, "uart3-eb", "ext-26m", 0x0, diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c index cd1769ecdc1c..e92b352fb0ad 100644 --- a/drivers/crypto/chelsio/chcr_ktls.c +++ b/drivers/crypto/chelsio/chcr_ktls.c @@ -120,12 +120,10 @@ out: static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info, int new_state) { - unsigned long flags; - /* This function can be called from both rx (interrupt context) and tx * queue contexts. */ - spin_lock_irqsave(&tx_info->lock, flags); + spin_lock_bh(&tx_info->lock); switch (tx_info->connection_state) { case KTLS_CONN_CLOSED: tx_info->connection_state = new_state; @@ -169,7 +167,7 @@ static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info, pr_err("unknown KTLS connection state\n"); break; } - spin_unlock_irqrestore(&tx_info->lock, flags); + spin_unlock_bh(&tx_info->lock); return tx_info->connection_state; } diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index b1af0de2e100..9d2512913d25 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -101,7 +101,7 @@ void cper_print_bits(const char *pfx, unsigned int bits, if (!len) len = snprintf(buf, sizeof(buf), "%s%s", pfx, str); else - len += snprintf(buf+len, sizeof(buf)-len, ", %s", str); + len += scnprintf(buf+len, sizeof(buf)-len, ", %s", str); } if (len) printk("%s\n", buf); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index cc90a748bcf0..67d26949fd26 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -25,7 +25,7 @@ #define EFI_ALLOC_ALIGN EFI_PAGE_SIZE #endif -#ifdef CONFIG_ARM +#if defined(CONFIG_ARM) || defined(CONFIG_X86) #define __efistub_global __section(.data) #else #define __efistub_global diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c index d4c7e5f59d2c..ea66b1f16a79 100644 --- a/drivers/firmware/efi/libstub/file.c +++ b/drivers/firmware/efi/libstub/file.c @@ -29,30 +29,31 @@ */ #define EFI_READ_CHUNK_SIZE SZ_1M +struct finfo { + efi_file_info_t info; + efi_char16_t filename[MAX_FILENAME_SIZE]; +}; + static efi_status_t efi_open_file(efi_file_protocol_t *volume, - efi_char16_t *filename_16, + struct finfo *fi, efi_file_protocol_t **handle, unsigned long *file_size) { - struct { - efi_file_info_t info; - efi_char16_t filename[MAX_FILENAME_SIZE]; - } finfo; efi_guid_t info_guid = EFI_FILE_INFO_ID; efi_file_protocol_t *fh; unsigned long info_sz; efi_status_t status; - status = volume->open(volume, &fh, filename_16, EFI_FILE_MODE_READ, 0); + status = volume->open(volume, &fh, fi->filename, EFI_FILE_MODE_READ, 0); if (status != EFI_SUCCESS) { pr_efi_err("Failed to open file: "); - efi_char16_printk(filename_16); + efi_char16_printk(fi->filename); efi_printk("\n"); return status; } - info_sz = sizeof(finfo); - status = fh->get_info(fh, &info_guid, &info_sz, &finfo); + info_sz = sizeof(struct finfo); + status = fh->get_info(fh, &info_guid, &info_sz, fi); if (status != EFI_SUCCESS) { pr_efi_err("Failed to get file info\n"); fh->close(fh); @@ -60,7 +61,7 @@ static efi_status_t efi_open_file(efi_file_protocol_t *volume, } *handle = fh; - *file_size = finfo.info.file_size; + *file_size = fi->info.file_size; return EFI_SUCCESS; } @@ -146,13 +147,13 @@ static efi_status_t handle_cmdline_files(efi_loaded_image_t *image, alloc_addr = alloc_size = 0; do { - efi_char16_t filename[MAX_FILENAME_SIZE]; + struct finfo fi; unsigned long size; void *addr; offset = find_file_option(cmdline, cmdline_len, optstr, optstr_size, - filename, ARRAY_SIZE(filename)); + fi.filename, ARRAY_SIZE(fi.filename)); if (!offset) break; @@ -166,7 +167,7 @@ static efi_status_t handle_cmdline_files(efi_loaded_image_t *image, return status; } - status = efi_open_file(volume, filename, &file, &size); + status = efi_open_file(volume, &fi, &file, &size); if (status != EFI_SUCCESS) goto err_close_volume; diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 8d3a707789de..05ccb229fb45 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -20,7 +20,7 @@ /* Maximum physical address for 64-bit kernel with 4-level paging */ #define MAXMEM_X86_64_4LEVEL (1ull << 46) -static efi_system_table_t *sys_table; +static efi_system_table_t *sys_table __efistub_global; extern const bool efi_is64; extern u32 image_offset; @@ -392,8 +392,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, image_base = efi_table_attr(image, image_base); image_offset = (void *)startup_32 - image_base; - hdr = &((struct boot_params *)image_base)->hdr; - status = efi_allocate_pages(0x4000, (unsigned long *)&boot_params, ULONG_MAX); if (status != EFI_SUCCESS) { efi_printk("Failed to allocate lowmem for boot params\n"); @@ -742,8 +740,15 @@ unsigned long efi_main(efi_handle_t handle, * now use KERNEL_IMAGE_SIZE, which will be 512MiB, the same as what * KASLR uses. * - * Also relocate it if image_offset is zero, i.e. we weren't loaded by - * LoadImage, but we are not aligned correctly. + * Also relocate it if image_offset is zero, i.e. the kernel wasn't + * loaded by LoadImage, but rather by a bootloader that called the + * handover entry. The reason we must always relocate in this case is + * to handle the case of systemd-boot booting a unified kernel image, + * which is a PE executable that contains the bzImage and an initrd as + * COFF sections. The initrd section is placed after the bzImage + * without ensuring that there are at least init_size bytes available + * for the bzImage, and thus the compressed kernel's startup code may + * overwrite the initrd unless it is moved out of the way. */ buffer_start = ALIGN(bzimage_addr - image_offset, @@ -753,8 +758,7 @@ unsigned long efi_main(efi_handle_t handle, if ((buffer_start < LOAD_PHYSICAL_ADDR) || (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE) || (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) || - (image_offset == 0 && !IS_ALIGNED(bzimage_addr, - hdr->kernel_alignment))) { + (image_offset == 0)) { status = efi_relocate_kernel(&bzimage_addr, hdr->init_size, hdr->init_size, hdr->pref_address, diff --git a/drivers/firmware/xilinx/zynqmp-debug.c b/drivers/firmware/xilinx/zynqmp-debug.c index c6d0724da4db..43bc6cfdab45 100644 --- a/drivers/firmware/xilinx/zynqmp-debug.c +++ b/drivers/firmware/xilinx/zynqmp-debug.c @@ -35,7 +35,7 @@ static struct pm_api_info pm_api_list[] = { PM_API(PM_QUERY_DATA), }; -struct dentry *firmware_debugfs_root; +static struct dentry *firmware_debugfs_root; /** * zynqmp_pm_argument_value() - Extract argument value from a PM-API request diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 559dc24ef436..f84f9e35a73b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2008,8 +2008,24 @@ static void amdgpu_device_fill_reset_magic(struct amdgpu_device *adev) */ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev) { - return !!memcmp(adev->gart.ptr, adev->reset_magic, - AMDGPU_RESET_MAGIC_NUM); + if (memcmp(adev->gart.ptr, adev->reset_magic, + AMDGPU_RESET_MAGIC_NUM)) + return true; + + if (!adev->in_gpu_reset) + return false; + + /* + * For all ASICs with baco/mode1 reset, the VRAM is + * always assumed to be lost. + */ + switch (amdgpu_asic_reset_method(adev)) { + case AMD_RESET_METHOD_BACO: + case AMD_RESET_METHOD_MODE1: + return true; + default: + return false; + } } /** @@ -2340,6 +2356,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 006f21ef7ddf..62635e58e45e 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1358,8 +1358,6 @@ static int cik_asic_reset(struct amdgpu_device *adev) int r; if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); r = amdgpu_dpm_baco_reset(adev); } else { r = cik_asic_pci_config_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index d78059fd2c72..f92c158d89a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -279,7 +279,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2_nv12[] = #define DEFAULT_SH_MEM_CONFIG \ ((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \ - (SH_MEM_ALIGNMENT_MODE_DWORD << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ + (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ (SH_MEM_RETRY_MODE_ALL << SH_MEM_CONFIG__RETRY_MODE__SHIFT) | \ (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index e6b113ed2f40..0c390485bc10 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1234,6 +1234,8 @@ struct amdgpu_gfxoff_quirk { static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { /* https://bugzilla.kernel.org/show_bug.cgi?id=204689 */ { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */ + { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 033cbbca2072..52318b03c424 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -351,8 +351,6 @@ static int nv_asic_reset(struct amdgpu_device *adev) struct smu_context *smu = &adev->smu; if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); ret = smu_baco_enter(smu); if (ret) return ret; @@ -360,8 +358,6 @@ static int nv_asic_reset(struct amdgpu_device *adev) if (ret) return ret; } else { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); ret = nv_asic_mode1_reset(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index a40499d51c93..d42a8d8a0dea 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -569,14 +569,10 @@ static int soc15_asic_reset(struct amdgpu_device *adev) switch (soc15_asic_reset_method(adev)) { case AMD_RESET_METHOD_BACO: - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); return soc15_asic_baco_reset(adev); case AMD_RESET_METHOD_MODE2: return amdgpu_dpm_mode2_reset(adev); default: - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); return soc15_asic_mode1_reset(adev); } } diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 78b35901643b..3ce10e05d0d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -765,8 +765,6 @@ static int vi_asic_reset(struct amdgpu_device *adev) int r; if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) { - if (!adev->in_suspend) - amdgpu_inc_vram_lost(adev); r = amdgpu_dpm_baco_reset(adev); } else { r = vi_asic_pci_config_reset(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f7c5cdc10a70..c5ba5d46a148 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4664,6 +4664,7 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) i2c_del_adapter(&aconnector->i2c->base); kfree(aconnector->i2c); } + kfree(aconnector->dm_dp_aux.aux.name); kfree(connector); } @@ -4723,10 +4724,19 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector) static int amdgpu_dm_connector_late_register(struct drm_connector *connector) { -#if defined(CONFIG_DEBUG_FS) struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); + int r; + if ((connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) || + (connector->connector_type == DRM_MODE_CONNECTOR_eDP)) { + amdgpu_dm_connector->dm_dp_aux.aux.dev = connector->kdev; + r = drm_dp_aux_register(&amdgpu_dm_connector->dm_dp_aux.aux); + if (r) + return r; + } + +#if defined(CONFIG_DEBUG_FS) connector_debugfs_init(amdgpu_dm_connector); #endif @@ -6092,7 +6102,7 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm, if (connector_type == DRM_MODE_CONNECTOR_DisplayPort || connector_type == DRM_MODE_CONNECTOR_eDP) - amdgpu_dm_initialize_dp_connector(dm, aconnector); + amdgpu_dm_initialize_dp_connector(dm, aconnector, link->link_index); out_free: if (res) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index fabbe78d5aef..d2917759b7ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -156,16 +156,16 @@ amdgpu_dm_mst_connector_late_register(struct drm_connector *connector) to_amdgpu_dm_connector(connector); int r; - amdgpu_dm_connector->dm_dp_aux.aux.dev = connector->kdev; - r = drm_dp_aux_register(&amdgpu_dm_connector->dm_dp_aux.aux); - if (r) + r = drm_dp_mst_connector_late_register(connector, + amdgpu_dm_connector->port); + if (r < 0) return r; #if defined(CONFIG_DEBUG_FS) connector_debugfs_init(amdgpu_dm_connector); #endif - return r; + return 0; } static void @@ -472,9 +472,12 @@ static const struct drm_dp_mst_topology_cbs dm_mst_cbs = { }; void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, - struct amdgpu_dm_connector *aconnector) + struct amdgpu_dm_connector *aconnector, + int link_index) { - aconnector->dm_dp_aux.aux.name = "dmdc"; + aconnector->dm_dp_aux.aux.name = + kasprintf(GFP_KERNEL, "AMDGPU DM aux hw bus %d", + link_index); aconnector->dm_dp_aux.aux.transfer = dm_dp_aux_transfer; aconnector->dm_dp_aux.ddc_service = aconnector->dc_link->ddc; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index d6813ce67bbd..d2c56579a2cc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -32,7 +32,8 @@ struct amdgpu_dm_connector; int dm_mst_get_pbn_divider(struct dc_link *link); void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, - struct amdgpu_dm_connector *aconnector); + struct amdgpu_dm_connector *aconnector, + int link_index); #if defined(CONFIG_DRM_AMD_DC_DCN) bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c index 77c14671866c..719597c5d27d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c @@ -984,6 +984,32 @@ static int init_thermal_controller( struct pp_hwmgr *hwmgr, const ATOM_PPLIB_POWERPLAYTABLE *powerplay_table) { + hwmgr->thermal_controller.ucType = + powerplay_table->sThermalController.ucType; + hwmgr->thermal_controller.ucI2cLine = + powerplay_table->sThermalController.ucI2cLine; + hwmgr->thermal_controller.ucI2cAddress = + powerplay_table->sThermalController.ucI2cAddress; + + hwmgr->thermal_controller.fanInfo.bNoFan = + (0 != (powerplay_table->sThermalController.ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN)); + + hwmgr->thermal_controller.fanInfo.ucTachometerPulsesPerRevolution = + powerplay_table->sThermalController.ucFanParameters & + ATOM_PP_FANPARAMETERS_TACHOMETER_PULSES_PER_REVOLUTION_MASK; + + hwmgr->thermal_controller.fanInfo.ulMinRPM + = powerplay_table->sThermalController.ucFanMinRPM * 100UL; + hwmgr->thermal_controller.fanInfo.ulMaxRPM + = powerplay_table->sThermalController.ucFanMaxRPM * 100UL; + + set_hw_cap(hwmgr, + ATOM_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType, + PHM_PlatformCaps_ThermalController); + + hwmgr->thermal_controller.use_hw_fan_control = 1; + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 7740488999df..4795eb66b2b2 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3804,9 +3804,12 @@ static int smu7_trim_single_dpm_states(struct pp_hwmgr *hwmgr, { uint32_t i; + /* force the trim if mclk_switching is disabled to prevent flicker */ + bool force_trim = (low_limit == high_limit); for (i = 0; i < dpm_table->count; i++) { /*skip the trim if od is enabled*/ - if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit + if ((!hwmgr->od_enabled || force_trim) + && (dpm_table->dpm_levels[i].value < low_limit || dpm_table->dpm_levels[i].value > high_limit)) dpm_table->dpm_levels[i].enabled = false; else diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index ff73a735b888..b0ed1b3fe79a 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -895,12 +895,17 @@ static int renoir_read_sensor(struct smu_context *smu, static bool renoir_is_dpm_running(struct smu_context *smu) { + struct amdgpu_device *adev = smu->adev; + /* * Util now, the pmfw hasn't exported the interface of SMU * feature mask to APU SKU so just force on all the feature * at early initial stage. */ - return true; + if (adev->in_suspend) + return false; + else + return true; } diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 541c932a6005..655ba4fb05dc 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -1718,6 +1718,12 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) if (ret) goto out; + if (ras && ras->supported) { + ret = smu_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + if (ret) + goto out; + } + /* clear vbios scratch 6 and 7 for coming asic reinit */ WREG32(adev->bios_scratch_reg_offset + 6, 0); WREG32(adev->bios_scratch_reg_offset + 7, 0); diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c index 2bc6e4f85171..9af39ec958db 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c @@ -485,6 +485,9 @@ static int anx6345_get_modes(struct drm_connector *connector) num_modes += drm_add_edid_modes(connector, anx6345->edid); + /* Driver currently supports only 6bpc */ + connector->display_info.bpc = 6; + unlock: if (power_off) anx6345_poweroff(anx6345); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 70c4b7afed12..283615e44838 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -4295,6 +4295,7 @@ int drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, if (pos->vcpi) { drm_dp_mst_put_port_malloc(port); pos->vcpi = 0; + pos->pbn = 0; } return 0; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 2c617c98db3a..52db7852827b 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3141,9 +3141,6 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder, intel_dp_set_link_params(intel_dp, crtc_state->port_clock, crtc_state->lane_count, is_mst); - intel_dp->regs.dp_tp_ctl = DP_TP_CTL(port); - intel_dp->regs.dp_tp_status = DP_TP_STATUS(port); - intel_edp_panel_on(intel_dp); intel_ddi_clk_select(encoder, crtc_state); @@ -3848,12 +3845,18 @@ void intel_ddi_get_config(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc); enum transcoder cpu_transcoder = pipe_config->cpu_transcoder; + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); u32 temp, flags = 0; /* XXX: DSI transcoder paranoia */ if (drm_WARN_ON(&dev_priv->drm, transcoder_is_dsi(cpu_transcoder))) return; + if (INTEL_GEN(dev_priv) >= 12) { + intel_dp->regs.dp_tp_ctl = TGL_DP_TP_CTL(cpu_transcoder); + intel_dp->regs.dp_tp_status = TGL_DP_TP_STATUS(cpu_transcoder); + } + intel_dsc_get_config(encoder, pipe_config); temp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); @@ -4173,6 +4176,7 @@ static const struct drm_encoder_funcs intel_ddi_funcs = { static struct intel_connector * intel_ddi_init_dp_connector(struct intel_digital_port *intel_dig_port) { + struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev); struct intel_connector *connector; enum port port = intel_dig_port->base.port; @@ -4183,6 +4187,10 @@ intel_ddi_init_dp_connector(struct intel_digital_port *intel_dig_port) intel_dig_port->dp.output_reg = DDI_BUF_CTL(port); intel_dig_port->dp.prepare_link_retrain = intel_ddi_prepare_link_retrain; + if (INTEL_GEN(dev_priv) < 12) { + intel_dig_port->dp.regs.dp_tp_ctl = DP_TP_CTL(port); + intel_dig_port->dp.regs.dp_tp_status = DP_TP_STATUS(port); + } if (!intel_dp_init_connector(intel_dig_port, connector)) { kfree(connector); diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 246e406bb385..84ecf8e58523 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4140,7 +4140,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX D TBT1", .domains = TGL_AUX_D_TBT1_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4151,7 +4151,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX E TBT2", .domains = TGL_AUX_E_TBT2_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4162,7 +4162,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX F TBT3", .domains = TGL_AUX_F_TBT3_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4173,7 +4173,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX G TBT4", .domains = TGL_AUX_G_TBT4_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4184,7 +4184,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX H TBT5", .domains = TGL_AUX_H_TBT5_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, @@ -4195,7 +4195,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = { { .name = "AUX I TBT6", .domains = TGL_AUX_I_TBT6_IO_POWER_DOMAINS, - .ops = &hsw_power_well_ops, + .ops = &icl_tc_phy_aux_power_well_ops, .id = DISP_PW_ID_NONE, { .hsw.regs = &icl_aux_power_well_regs, diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 804b1d966f66..a2fafd4499f2 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2517,9 +2517,6 @@ static void intel_dp_prepare(struct intel_encoder *encoder, intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST)); - intel_dp->regs.dp_tp_ctl = DP_TP_CTL(port); - intel_dp->regs.dp_tp_status = DP_TP_STATUS(port); - /* * There are four kinds of DP registers: * @@ -7836,6 +7833,8 @@ bool intel_dp_init(struct drm_i915_private *dev_priv, intel_dig_port->dp.output_reg = output_reg; intel_dig_port->max_lanes = 4; + intel_dig_port->dp.regs.dp_tp_ctl = DP_TP_CTL(port); + intel_dig_port->dp.regs.dp_tp_status = DP_TP_STATUS(port); intel_encoder->type = INTEL_OUTPUT_DP; intel_encoder->power_domain = intel_port_to_power_domain(port); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 3e706bb850a8..dbfa6895795b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -342,6 +342,7 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector) */ if (dev_priv->vbt.backlight.type != INTEL_BACKLIGHT_VESA_EDP_AUX_INTERFACE && + i915_modparams.enable_dpcd_backlight != 1 && !drm_dp_has_quirk(&intel_dp->desc, intel_dp->edid_quirks, DP_QUIRK_FORCE_DPCD_BACKLIGHT)) { DRM_DEV_INFO(dev->dev, diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 39930232b253..821411b93dac 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1536,7 +1536,8 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port) intel_de_write(i915, HDCP_RPRIME(i915, cpu_transcoder, port), ri.reg); /* Wait for Ri prime match */ - if (wait_for(intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) & + if (wait_for((intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) & + (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC)) == (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) { DRM_ERROR("Ri' mismatch detected, link check failed (%x)\n", intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port))); diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c index deda351719db..33d886141138 100644 --- a/drivers/gpu/drm/i915/display/intel_sprite.c +++ b/drivers/gpu/drm/i915/display/intel_sprite.c @@ -2817,19 +2817,25 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane, } } -static bool gen12_plane_supports_mc_ccs(enum plane_id plane_id) +static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv, + enum plane_id plane_id) { + /* Wa_14010477008:tgl[a0..c0] */ + if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0)) + return false; + return plane_id < PLANE_SPRITE4; } static bool gen12_plane_format_mod_supported(struct drm_plane *_plane, u32 format, u64 modifier) { + struct drm_i915_private *dev_priv = to_i915(_plane->dev); struct intel_plane *plane = to_intel_plane(_plane); switch (modifier) { case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS: - if (!gen12_plane_supports_mc_ccs(plane->id)) + if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id)) return false; /* fall through */ case DRM_FORMAT_MOD_LINEAR: @@ -2998,9 +3004,10 @@ static const u32 *icl_get_plane_formats(struct drm_i915_private *dev_priv, } } -static const u64 *gen12_get_plane_modifiers(enum plane_id plane_id) +static const u64 *gen12_get_plane_modifiers(struct drm_i915_private *dev_priv, + enum plane_id plane_id) { - if (gen12_plane_supports_mc_ccs(plane_id)) + if (gen12_plane_supports_mc_ccs(dev_priv, plane_id)) return gen12_plane_format_modifiers_mc_ccs; else return gen12_plane_format_modifiers_rc_ccs; @@ -3070,7 +3077,7 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv, plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id); if (INTEL_GEN(dev_priv) >= 12) { - modifiers = gen12_get_plane_modifiers(plane_id); + modifiers = gen12_get_plane_modifiers(dev_priv, plane_id); plane_funcs = &gen12_plane_funcs; } else { if (plane->has_ccs) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index cfaf141bac4d..19542fd9e207 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -81,13 +81,14 @@ static void rps_enable_interrupts(struct intel_rps *rps) events = (GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT); - WRITE_ONCE(rps->pm_events, events); + spin_lock_irq(>->irq_lock); gen6_gt_pm_enable_irq(gt, rps->pm_events); spin_unlock_irq(>->irq_lock); - set(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->cur_freq)); + intel_uncore_write(gt->uncore, + GEN6_PMINTRMSK, rps_pm_mask(rps, rps->last_freq)); } static void gen6_rps_reset_interrupts(struct intel_rps *rps) @@ -120,7 +121,9 @@ static void rps_disable_interrupts(struct intel_rps *rps) struct intel_gt *gt = rps_to_gt(rps); WRITE_ONCE(rps->pm_events, 0); - set(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u)); + + intel_uncore_write(gt->uncore, + GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u)); spin_lock_irq(>->irq_lock); gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 074c4efb58eb..eee530453aa6 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -131,6 +131,7 @@ struct kvmgt_vdev { struct work_struct release_work; atomic_t released; struct vfio_device *vfio_device; + struct vfio_group *vfio_group; }; static inline struct kvmgt_vdev *kvmgt_vdev(struct intel_vgpu *vgpu) @@ -151,6 +152,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size) { struct drm_i915_private *i915 = vgpu->gvt->gt->i915; + struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu); int total_pages; int npage; int ret; @@ -160,7 +162,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, for (npage = 0; npage < total_pages; npage++) { unsigned long cur_gfn = gfn + npage; - ret = vfio_unpin_pages(mdev_dev(kvmgt_vdev(vgpu)->mdev), &cur_gfn, 1); + ret = vfio_group_unpin_pages(vdev->vfio_group, &cur_gfn, 1); drm_WARN_ON(&i915->drm, ret != 1); } } @@ -169,6 +171,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size, struct page **page) { + struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu); unsigned long base_pfn = 0; int total_pages; int npage; @@ -183,8 +186,8 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, unsigned long cur_gfn = gfn + npage; unsigned long pfn; - ret = vfio_pin_pages(mdev_dev(kvmgt_vdev(vgpu)->mdev), &cur_gfn, 1, - IOMMU_READ | IOMMU_WRITE, &pfn); + ret = vfio_group_pin_pages(vdev->vfio_group, &cur_gfn, 1, + IOMMU_READ | IOMMU_WRITE, &pfn); if (ret != 1) { gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n", cur_gfn, ret); @@ -792,6 +795,7 @@ static int intel_vgpu_open(struct mdev_device *mdev) struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu); unsigned long events; int ret; + struct vfio_group *vfio_group; vdev->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier; vdev->group_notifier.notifier_call = intel_vgpu_group_notifier; @@ -814,6 +818,14 @@ static int intel_vgpu_open(struct mdev_device *mdev) goto undo_iommu; } + vfio_group = vfio_group_get_external_user_from_dev(mdev_dev(mdev)); + if (IS_ERR_OR_NULL(vfio_group)) { + ret = !vfio_group ? -EFAULT : PTR_ERR(vfio_group); + gvt_vgpu_err("vfio_group_get_external_user_from_dev failed\n"); + goto undo_register; + } + vdev->vfio_group = vfio_group; + /* Take a module reference as mdev core doesn't take * a reference for vendor driver. */ @@ -830,6 +842,10 @@ static int intel_vgpu_open(struct mdev_device *mdev) return ret; undo_group: + vfio_group_put_external_user(vdev->vfio_group); + vdev->vfio_group = NULL; + +undo_register: vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY, &vdev->group_notifier); @@ -884,6 +900,7 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu) kvmgt_guest_exit(info); intel_vgpu_release_msi_eventfd_ctx(vgpu); + vfio_group_put_external_user(vdev->vfio_group); vdev->kvm = NULL; vgpu->handle = 0; @@ -2035,33 +2052,14 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, void *buf, unsigned long len, bool write) { struct kvmgt_guest_info *info; - struct kvm *kvm; - int idx, ret; - bool kthread = current->mm == NULL; if (!handle_valid(handle)) return -ESRCH; info = (struct kvmgt_guest_info *)handle; - kvm = info->kvm; - - if (kthread) { - if (!mmget_not_zero(kvm->mm)) - return -EFAULT; - use_mm(kvm->mm); - } - - idx = srcu_read_lock(&kvm->srcu); - ret = write ? kvm_write_guest(kvm, gpa, buf, len) : - kvm_read_guest(kvm, gpa, buf, len); - srcu_read_unlock(&kvm->srcu, idx); - - if (kthread) { - unuse_mm(kvm->mm); - mmput(kvm->mm); - } - return ret; + return vfio_dma_rw(kvmgt_vdev(info->vgpu)->vfio_group, + gpa, buf, len, write); } static int kvmgt_read_gpa(unsigned long handle, unsigned long gpa, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 1f5b9a584f71..62b901ffabf9 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1507,6 +1507,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, (IS_ICELAKE(p) && IS_REVID(p, since, until)) #define TGL_REVID_A0 0x0 +#define TGL_REVID_B0 0x1 +#define TGL_REVID_C0 0x2 #define IS_TGL_REVID(p, since, until) \ (IS_TIGERLAKE(p) && IS_REVID(p, since, until)) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 551be589d6f4..66a46e41d5ef 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2941,49 +2941,6 @@ void i915_oa_init_reg_state(const struct intel_context *ce, } /** - * i915_perf_read_locked - &i915_perf_stream_ops->read with error normalisation - * @stream: An i915 perf stream - * @file: An i915 perf stream file - * @buf: destination buffer given by userspace - * @count: the number of bytes userspace wants to read - * @ppos: (inout) file seek position (unused) - * - * Besides wrapping &i915_perf_stream_ops->read this provides a common place to - * ensure that if we've successfully copied any data then reporting that takes - * precedence over any internal error status, so the data isn't lost. - * - * For example ret will be -ENOSPC whenever there is more buffered data than - * can be copied to userspace, but that's only interesting if we weren't able - * to copy some data because it implies the userspace buffer is too small to - * receive a single record (and we never split records). - * - * Another case with ret == -EFAULT is more of a grey area since it would seem - * like bad form for userspace to ask us to overrun its buffer, but the user - * knows best: - * - * http://yarchive.net/comp/linux/partial_reads_writes.html - * - * Returns: The number of bytes copied or a negative error code on failure. - */ -static ssize_t i915_perf_read_locked(struct i915_perf_stream *stream, - struct file *file, - char __user *buf, - size_t count, - loff_t *ppos) -{ - /* Note we keep the offset (aka bytes read) separate from any - * error status so that the final check for whether we return - * the bytes read with a higher precedence than any error (see - * comment below) doesn't need to be handled/duplicated in - * stream->ops->read() implementations. - */ - size_t offset = 0; - int ret = stream->ops->read(stream, buf, count, &offset); - - return offset ?: (ret ?: -EAGAIN); -} - -/** * i915_perf_read - handles read() FOP for i915 perf stream FDs * @file: An i915 perf stream file * @buf: destination buffer given by userspace @@ -3008,7 +2965,8 @@ static ssize_t i915_perf_read(struct file *file, { struct i915_perf_stream *stream = file->private_data; struct i915_perf *perf = stream->perf; - ssize_t ret; + size_t offset = 0; + int ret; /* To ensure it's handled consistently we simply treat all reads of a * disabled stream as an error. In particular it might otherwise lead @@ -3031,13 +2989,12 @@ static ssize_t i915_perf_read(struct file *file, return ret; mutex_lock(&perf->lock); - ret = i915_perf_read_locked(stream, file, - buf, count, ppos); + ret = stream->ops->read(stream, buf, count, &offset); mutex_unlock(&perf->lock); - } while (ret == -EAGAIN); + } while (!offset && !ret); } else { mutex_lock(&perf->lock); - ret = i915_perf_read_locked(stream, file, buf, count, ppos); + ret = stream->ops->read(stream, buf, count, &offset); mutex_unlock(&perf->lock); } @@ -3048,15 +3005,15 @@ static ssize_t i915_perf_read(struct file *file, * and read() returning -EAGAIN. Clearing the oa.pollin state here * effectively ensures we back off until the next hrtimer callback * before reporting another EPOLLIN event. + * The exception to this is if ops->read() returned -ENOSPC which means + * that more OA data is available than could fit in the user provided + * buffer. In this case we want the next poll() call to not block. */ - if (ret >= 0 || ret == -EAGAIN) { - /* Maybe make ->pollin per-stream state if we support multiple - * concurrent streams in the future. - */ + if (ret != -ENOSPC) stream->pollin = false; - } - return ret; + /* Possible values for ret are 0, -EFAULT, -ENOSPC, -EIO, ... */ + return offset ?: (ret ?: -EAGAIN); } static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 59e64acc2c56..e0c6021fdaf9 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -34,8 +34,8 @@ * Follow the style described here for new macros, and while changing existing * macros. Do **not** mass change existing definitions just to update the style. * - * Layout - * ~~~~~~ + * File Layout + * ~~~~~~~~~~~ * * Keep helper macros near the top. For example, _PIPE() and friends. * diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index e8c94915a4fc..64cb6ba4bc42 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -1034,10 +1034,8 @@ static int meson_dw_hdmi_bind(struct device *dev, struct device *master, return PTR_ERR(dw_plat_data->regm); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "Failed to get hdmi top irq\n"); + if (irq < 0) return irq; - } ret = devm_request_threaded_irq(dev, irq, dw_hdmi_top_irq, dw_hdmi_top_thread_irq, IRQF_SHARED, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c index 232a9d7c51e5..e770c9497871 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c @@ -25,6 +25,9 @@ MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin"); MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin"); MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/gv100/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/gv100/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/gv100/sec2/sig.bin"); static const struct nvkm_sec2_fwif gp108_sec2_fwif[] = { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c index b6ebd95c9ba1..a8295653ceab 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c @@ -56,6 +56,22 @@ tu102_sec2_nofw(struct nvkm_sec2 *sec2, int ver, return 0; } +MODULE_FIRMWARE("nvidia/tu102/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu102/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu102/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu104/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu104/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu104/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu106/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu106/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu106/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu116/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu116/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu116/sec2/sig.bin"); +MODULE_FIRMWARE("nvidia/tu117/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/tu117/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/tu117/sec2/sig.bin"); + static const struct nvkm_sec2_fwif tu102_sec2_fwif[] = { { 0, gp102_sec2_load, &tu102_sec2, &gp102_sec2_acr_1 }, diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 8e731ed0d9d9..2f319102ae9f 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -676,7 +676,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) */ if ((sched->timeout != MAX_SCHEDULE_TIMEOUT && !cancel_delayed_work(&sched->work_tdr)) || - __kthread_should_park(sched->thread)) + kthread_should_park()) return NULL; spin_lock(&sched->job_list_lock); diff --git a/drivers/gpu/drm/tidss/tidss_crtc.c b/drivers/gpu/drm/tidss/tidss_crtc.c index d4ce9bab8c7e..3221a707e073 100644 --- a/drivers/gpu/drm/tidss/tidss_crtc.c +++ b/drivers/gpu/drm/tidss/tidss_crtc.c @@ -379,9 +379,17 @@ static struct drm_crtc_state *tidss_crtc_duplicate_state(struct drm_crtc *crtc) return &state->base; } +static void tidss_crtc_destroy(struct drm_crtc *crtc) +{ + struct tidss_crtc *tcrtc = to_tidss_crtc(crtc); + + drm_crtc_cleanup(crtc); + kfree(tcrtc); +} + static const struct drm_crtc_funcs tidss_crtc_funcs = { .reset = tidss_crtc_reset, - .destroy = drm_crtc_cleanup, + .destroy = tidss_crtc_destroy, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, .atomic_duplicate_state = tidss_crtc_duplicate_state, @@ -400,7 +408,7 @@ struct tidss_crtc *tidss_crtc_create(struct tidss_device *tidss, bool has_ctm = tidss->feat->vp_feat.color.has_ctm; int ret; - tcrtc = devm_kzalloc(tidss->dev, sizeof(*tcrtc), GFP_KERNEL); + tcrtc = kzalloc(sizeof(*tcrtc), GFP_KERNEL); if (!tcrtc) return ERR_PTR(-ENOMEM); @@ -411,8 +419,10 @@ struct tidss_crtc *tidss_crtc_create(struct tidss_device *tidss, ret = drm_crtc_init_with_planes(&tidss->ddev, crtc, primary, NULL, &tidss_crtc_funcs, NULL); - if (ret < 0) + if (ret < 0) { + kfree(tcrtc); return ERR_PTR(ret); + } drm_crtc_helper_add(crtc, &tidss_crtc_helper_funcs); diff --git a/drivers/gpu/drm/tidss/tidss_encoder.c b/drivers/gpu/drm/tidss/tidss_encoder.c index 83785b0a66a9..30bf2a65949c 100644 --- a/drivers/gpu/drm/tidss/tidss_encoder.c +++ b/drivers/gpu/drm/tidss/tidss_encoder.c @@ -55,12 +55,18 @@ static int tidss_encoder_atomic_check(struct drm_encoder *encoder, return 0; } +static void tidss_encoder_destroy(struct drm_encoder *encoder) +{ + drm_encoder_cleanup(encoder); + kfree(encoder); +} + static const struct drm_encoder_helper_funcs encoder_helper_funcs = { .atomic_check = tidss_encoder_atomic_check, }; static const struct drm_encoder_funcs encoder_funcs = { - .destroy = drm_encoder_cleanup, + .destroy = tidss_encoder_destroy, }; struct drm_encoder *tidss_encoder_create(struct tidss_device *tidss, @@ -69,7 +75,7 @@ struct drm_encoder *tidss_encoder_create(struct tidss_device *tidss, struct drm_encoder *enc; int ret; - enc = devm_kzalloc(tidss->dev, sizeof(*enc), GFP_KERNEL); + enc = kzalloc(sizeof(*enc), GFP_KERNEL); if (!enc) return ERR_PTR(-ENOMEM); @@ -77,8 +83,10 @@ struct drm_encoder *tidss_encoder_create(struct tidss_device *tidss, ret = drm_encoder_init(&tidss->ddev, enc, &encoder_funcs, encoder_type, NULL); - if (ret < 0) + if (ret < 0) { + kfree(enc); return ERR_PTR(ret); + } drm_encoder_helper_add(enc, &encoder_helper_funcs); diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c index ff99b2dd4a17..798488948fc5 100644 --- a/drivers/gpu/drm/tidss/tidss_plane.c +++ b/drivers/gpu/drm/tidss/tidss_plane.c @@ -141,6 +141,14 @@ static void tidss_plane_atomic_disable(struct drm_plane *plane, dispc_plane_enable(tidss->dispc, tplane->hw_plane_id, false); } +static void drm_plane_destroy(struct drm_plane *plane) +{ + struct tidss_plane *tplane = to_tidss_plane(plane); + + drm_plane_cleanup(plane); + kfree(tplane); +} + static const struct drm_plane_helper_funcs tidss_plane_helper_funcs = { .atomic_check = tidss_plane_atomic_check, .atomic_update = tidss_plane_atomic_update, @@ -151,7 +159,7 @@ static const struct drm_plane_funcs tidss_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .reset = drm_atomic_helper_plane_reset, - .destroy = drm_plane_cleanup, + .destroy = drm_plane_destroy, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; @@ -175,7 +183,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, BIT(DRM_MODE_BLEND_COVERAGE)); int ret; - tplane = devm_kzalloc(tidss->dev, sizeof(*tplane), GFP_KERNEL); + tplane = kzalloc(sizeof(*tplane), GFP_KERNEL); if (!tplane) return ERR_PTR(-ENOMEM); @@ -190,7 +198,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, formats, num_formats, NULL, type, NULL); if (ret < 0) - return ERR_PTR(ret); + goto err; drm_plane_helper_add(&tplane->plane, &tidss_plane_helper_funcs); @@ -203,15 +211,19 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, default_encoding, default_range); if (ret) - return ERR_PTR(ret); + goto err; ret = drm_plane_create_alpha_property(&tplane->plane); if (ret) - return ERR_PTR(ret); + goto err; ret = drm_plane_create_blend_mode_property(&tplane->plane, blend_modes); if (ret) - return ERR_PTR(ret); + goto err; return tplane; + +err: + kfree(tplane); + return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 336cc9143205..3f60bf2fe05a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -27,6 +27,7 @@ #include <linux/file.h> #include <linux/sync_file.h> +#include <linux/uaccess.h> #include <drm/drm_file.h> #include <drm/virtgpu_drm.h> diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 023a030ca7b9..f4ea4cef5e23 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -25,6 +25,7 @@ #include <linux/virtio.h> #include <linux/virtio_config.h> +#include <linux/virtio_ring.h> #include <drm/drm_file.h> diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 0370364169c4..501c43c5851d 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash) { struct vmbus_channel_message_header hdr; + if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED) + return; + /* Pre-Win2012R2 hosts don't support reconnect */ if (vmbus_proto_version < VERSION_WIN8_1) return; diff --git a/drivers/hv/hv_debugfs.c b/drivers/hv/hv_debugfs.c index 8a2878573582..ccf752b6659a 100644 --- a/drivers/hv/hv_debugfs.c +++ b/drivers/hv/hv_debugfs.c @@ -11,7 +11,7 @@ #include "hyperv_vmbus.h" -struct dentry *hv_debug_root; +static struct dentry *hv_debug_root; static int hv_debugfs_delay_get(void *data, u64 *val) { diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index f5fa3b3c9baf..70b30e223a57 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -292,7 +292,7 @@ struct vmbus_msginfo { struct list_head msglist_entry; /* The message itself */ - unsigned char msg[0]; + unsigned char msg[]; }; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 029378c27421..a68bce4d0ddb 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -31,6 +31,7 @@ #include <linux/kdebug.h> #include <linux/efi.h> #include <linux/random.h> +#include <linux/kernel.h> #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> #include "hyperv_vmbus.h" @@ -48,14 +49,35 @@ static int hyperv_cpuhp_online; static void *hv_panic_page; +/* + * Boolean to control whether to report panic messages over Hyper-V. + * + * It can be set via /proc/sys/kernel/hyperv/record_panic_msg + */ +static int sysctl_record_panic_msg = 1; + +static int hyperv_report_reg(void) +{ + return !sysctl_record_panic_msg || !hv_panic_page; +} + static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, void *args) { struct pt_regs *regs; - regs = current_pt_regs(); + vmbus_initiate_unload(true); - hyperv_report_panic(regs, val); + /* + * Hyper-V should be notified only once about a panic. If we will be + * doing hyperv_report_panic_msg() later with kmsg data, don't do + * the notification here. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE + && hyperv_report_reg()) { + regs = current_pt_regs(); + hyperv_report_panic(regs, val, false); + } return NOTIFY_DONE; } @@ -65,7 +87,13 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, struct die_args *die = (struct die_args *)args; struct pt_regs *regs = die->regs; - hyperv_report_panic(regs, val); + /* + * Hyper-V should be notified only once about a panic. If we will be + * doing hyperv_report_panic_msg() later with kmsg data, don't do + * the notification here. + */ + if (hyperv_report_reg()) + hyperv_report_panic(regs, val, true); return NOTIFY_DONE; } @@ -1253,13 +1281,6 @@ static void vmbus_isr(void) } /* - * Boolean to control whether to report panic messages over Hyper-V. - * - * It can be set via /proc/sys/kernel/hyperv/record_panic_msg - */ -static int sysctl_record_panic_msg = 1; - -/* * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg * buffer and call into Hyper-V to transfer the data. */ @@ -1382,19 +1403,29 @@ static int vmbus_bus_init(void) hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page(); if (hv_panic_page) { ret = kmsg_dump_register(&hv_kmsg_dumper); - if (ret) + if (ret) { pr_err("Hyper-V: kmsg dump register " "error 0x%x\n", ret); + hv_free_hyperv_page( + (unsigned long)hv_panic_page); + hv_panic_page = NULL; + } } else pr_err("Hyper-V: panic message page memory " "allocation failed"); } register_die_notifier(&hyperv_die_block); - atomic_notifier_chain_register(&panic_notifier_list, - &hyperv_panic_block); } + /* + * Always register the panic notifier because we need to unload + * the VMbus channel connection to prevent any VMbus + * activity after the VM panics. + */ + atomic_notifier_chain_register(&panic_notifier_list, + &hyperv_panic_block); + vmbus_request_offers(); return 0; @@ -1407,7 +1438,6 @@ err_alloc: hv_remove_vmbus_irq(); bus_unregister(&hv_bus); - hv_free_hyperv_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; return ret; @@ -2204,8 +2234,6 @@ static int vmbus_bus_suspend(struct device *dev) vmbus_initiate_unload(false); - vmbus_connection.conn_state = DISCONNECTED; - /* Reset the event for the next resume. */ reinit_completion(&vmbus_connection.ready_for_resume_event); @@ -2289,7 +2317,6 @@ static void hv_kexec_handler(void) { hv_stimer_global_cleanup(); vmbus_initiate_unload(false); - vmbus_connection.conn_state = DISCONNECTED; /* Make sure conn_state is set as hv_synic_cleanup checks for it */ mb(); cpuhp_remove_state(hyperv_cpuhp_online); @@ -2306,7 +2333,6 @@ static void hv_crash_handler(struct pt_regs *regs) * doing the cleanup for current CPU only. This should be sufficient * for kdump. */ - vmbus_connection.conn_state = DISCONNECTED; cpu = smp_processor_id(); hv_stimer_cleanup(cpu); hv_synic_disable_regs(cpu); diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 05a30832c6ba..4c62f900bf7e 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -412,7 +412,7 @@ config SENSORS_DRIVETEMP hard disk drives. This driver can also be built as a module. If so, the module - will be called satatemp. + will be called drivetemp. config SENSORS_DS620 tristate "Dallas Semiconductor DS620" diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 370d0c74eb01..9179460c2d9d 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -264,12 +264,18 @@ static int drivetemp_get_scttemp(struct drivetemp_data *st, u32 attr, long *val) return err; switch (attr) { case hwmon_temp_input: + if (!temp_is_valid(buf[SCT_STATUS_TEMP])) + return -ENODATA; *val = temp_from_sct(buf[SCT_STATUS_TEMP]); break; case hwmon_temp_lowest: + if (!temp_is_valid(buf[SCT_STATUS_TEMP_LOWEST])) + return -ENODATA; *val = temp_from_sct(buf[SCT_STATUS_TEMP_LOWEST]); break; case hwmon_temp_highest: + if (!temp_is_valid(buf[SCT_STATUS_TEMP_HIGHEST])) + return -ENODATA; *val = temp_from_sct(buf[SCT_STATUS_TEMP_HIGHEST]); break; default: diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index f2d81b0558e5..e3f1ebee7130 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -506,7 +506,7 @@ static int jc42_probe(struct i2c_client *client, const struct i2c_device_id *id) } data->config = config; - hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, + hwmon_dev = devm_hwmon_device_register_with_info(dev, "jc42", data, &jc42_chip_info, NULL); return PTR_ERR_OR_ZERO(hwmon_dev); diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 3f37d5d81fe4..9915578533bb 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -186,7 +186,7 @@ static long get_raw_temp(struct k10temp_data *data) return temp; } -const char *k10temp_temp_label[] = { +static const char *k10temp_temp_label[] = { "Tctl", "Tdie", "Tccd1", @@ -199,12 +199,12 @@ const char *k10temp_temp_label[] = { "Tccd8", }; -const char *k10temp_in_label[] = { +static const char *k10temp_in_label[] = { "Vcore", "Vsoc", }; -const char *k10temp_curr_label[] = { +static const char *k10temp_curr_label[] = { "Icore", "Isoc", }; diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index 4d2315208bb5..0c622711ef7e 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -21,8 +21,50 @@ #define ISL68137_VOUT_AVS 0x30 #define RAA_DMPVR2_READ_VMON 0xc8 -enum versions { +enum chips { isl68137, + isl68220, + isl68221, + isl68222, + isl68223, + isl68224, + isl68225, + isl68226, + isl68227, + isl68229, + isl68233, + isl68239, + isl69222, + isl69223, + isl69224, + isl69225, + isl69227, + isl69228, + isl69234, + isl69236, + isl69239, + isl69242, + isl69243, + isl69247, + isl69248, + isl69254, + isl69255, + isl69256, + isl69259, + isl69260, + isl69268, + isl69269, + isl69298, + raa228000, + raa228004, + raa228006, + raa228228, + raa229001, + raa229004, +}; + +enum variants { + raa_dmpvr1_2rail, raa_dmpvr2_1rail, raa_dmpvr2_2rail, raa_dmpvr2_3rail, @@ -186,7 +228,7 @@ static int isl68137_probe(struct i2c_client *client, memcpy(info, &raa_dmpvr_info, sizeof(*info)); switch (id->driver_data) { - case isl68137: + case raa_dmpvr1_2rail: info->pages = 2; info->R[PSC_VOLTAGE_IN] = 3; info->func[0] &= ~PMBUS_HAVE_VMON; @@ -224,11 +266,47 @@ static int isl68137_probe(struct i2c_client *client, } static const struct i2c_device_id raa_dmpvr_id[] = { - {"isl68137", isl68137}, - {"raa_dmpvr2_1rail", raa_dmpvr2_1rail}, - {"raa_dmpvr2_2rail", raa_dmpvr2_2rail}, - {"raa_dmpvr2_3rail", raa_dmpvr2_3rail}, - {"raa_dmpvr2_hv", raa_dmpvr2_hv}, + {"isl68137", raa_dmpvr1_2rail}, + {"isl68220", raa_dmpvr2_2rail}, + {"isl68221", raa_dmpvr2_3rail}, + {"isl68222", raa_dmpvr2_2rail}, + {"isl68223", raa_dmpvr2_2rail}, + {"isl68224", raa_dmpvr2_3rail}, + {"isl68225", raa_dmpvr2_2rail}, + {"isl68226", raa_dmpvr2_3rail}, + {"isl68227", raa_dmpvr2_1rail}, + {"isl68229", raa_dmpvr2_3rail}, + {"isl68233", raa_dmpvr2_2rail}, + {"isl68239", raa_dmpvr2_3rail}, + + {"isl69222", raa_dmpvr2_2rail}, + {"isl69223", raa_dmpvr2_3rail}, + {"isl69224", raa_dmpvr2_2rail}, + {"isl69225", raa_dmpvr2_2rail}, + {"isl69227", raa_dmpvr2_3rail}, + {"isl69228", raa_dmpvr2_3rail}, + {"isl69234", raa_dmpvr2_2rail}, + {"isl69236", raa_dmpvr2_2rail}, + {"isl69239", raa_dmpvr2_3rail}, + {"isl69242", raa_dmpvr2_2rail}, + {"isl69243", raa_dmpvr2_1rail}, + {"isl69247", raa_dmpvr2_2rail}, + {"isl69248", raa_dmpvr2_2rail}, + {"isl69254", raa_dmpvr2_2rail}, + {"isl69255", raa_dmpvr2_2rail}, + {"isl69256", raa_dmpvr2_2rail}, + {"isl69259", raa_dmpvr2_2rail}, + {"isl69260", raa_dmpvr2_2rail}, + {"isl69268", raa_dmpvr2_2rail}, + {"isl69269", raa_dmpvr2_3rail}, + {"isl69298", raa_dmpvr2_2rail}, + + {"raa228000", raa_dmpvr2_hv}, + {"raa228004", raa_dmpvr2_hv}, + {"raa228006", raa_dmpvr2_hv}, + {"raa228228", raa_dmpvr2_2rail}, + {"raa229001", raa_dmpvr2_2rail}, + {"raa229004", raa_dmpvr2_2rail}, {} }; diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c index 20ef63820c77..f5c00f903df3 100644 --- a/drivers/i2c/busses/i2c-altera.c +++ b/drivers/i2c/busses/i2c-altera.c @@ -384,7 +384,6 @@ static int altr_i2c_probe(struct platform_device *pdev) struct altr_i2c_dev *idev = NULL; struct resource *res; int irq, ret; - u32 val; idev = devm_kzalloc(&pdev->dev, sizeof(*idev), GFP_KERNEL); if (!idev) @@ -411,17 +410,17 @@ static int altr_i2c_probe(struct platform_device *pdev) init_completion(&idev->msg_complete); spin_lock_init(&idev->lock); - val = device_property_read_u32(idev->dev, "fifo-size", + ret = device_property_read_u32(idev->dev, "fifo-size", &idev->fifo_size); - if (val) { + if (ret) { dev_err(&pdev->dev, "FIFO size set to default of %d\n", ALTR_I2C_DFLT_FIFO_SZ); idev->fifo_size = ALTR_I2C_DFLT_FIFO_SZ; } - val = device_property_read_u32(idev->dev, "clock-frequency", + ret = device_property_read_u32(idev->dev, "clock-frequency", &idev->bus_clk_rate); - if (val) { + if (ret) { dev_err(&pdev->dev, "Default to 100kHz\n"); idev->bus_clk_rate = I2C_MAX_STANDARD_MODE_FREQ; /* default clock rate */ } diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index c98befe2a92e..5536673060cc 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -354,10 +354,16 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) adap->dev.of_node = pdev->dev.of_node; adap->nr = -1; - dev_pm_set_driver_flags(&pdev->dev, - DPM_FLAG_SMART_PREPARE | - DPM_FLAG_SMART_SUSPEND | - DPM_FLAG_LEAVE_SUSPENDED); + if (dev->flags & ACCESS_NO_IRQ_SUSPEND) { + dev_pm_set_driver_flags(&pdev->dev, + DPM_FLAG_SMART_PREPARE | + DPM_FLAG_LEAVE_SUSPENDED); + } else { + dev_pm_set_driver_flags(&pdev->dev, + DPM_FLAG_SMART_PREPARE | + DPM_FLAG_SMART_SUSPEND | + DPM_FLAG_LEAVE_SUSPENDED); + } /* The code below assumes runtime PM to be disabled. */ WARN_ON(pm_runtime_enabled(&pdev->dev)); diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 4c4d17ddc96b..8280ac7cc1b7 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -996,14 +996,13 @@ tegra_i2c_poll_completion_timeout(struct tegra_i2c_dev *i2c_dev, do { u32 status = i2c_readl(i2c_dev, I2C_INT_STATUS); - if (status) { + if (status) tegra_i2c_isr(i2c_dev->irq, i2c_dev); - if (completion_done(complete)) { - s64 delta = ktime_ms_delta(ktimeout, ktime); + if (completion_done(complete)) { + s64 delta = ktime_ms_delta(ktimeout, ktime); - return msecs_to_jiffies(delta) ?: 1; - } + return msecs_to_jiffies(delta) ?: 1; } ktime = ktime_get(); @@ -1030,14 +1029,18 @@ tegra_i2c_wait_completion_timeout(struct tegra_i2c_dev *i2c_dev, disable_irq(i2c_dev->irq); /* - * There is a chance that completion may happen after IRQ - * synchronization, which is done by disable_irq(). + * Under some rare circumstances (like running KASAN + + * NFS root) CPU, which handles interrupt, may stuck in + * uninterruptible state for a significant time. In this + * case we will get timeout if I2C transfer is running on + * a sibling CPU, despite of IRQ being raised. + * + * In order to handle this rare condition, the IRQ status + * needs to be checked after timeout. */ - if (ret == 0 && completion_done(complete)) { - dev_warn(i2c_dev->dev, - "completion done after timeout\n"); - ret = 1; - } + if (ret == 0) + ret = tegra_i2c_poll_completion_timeout(i2c_dev, + complete, 0); } return ret; @@ -1216,6 +1219,15 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, time_left = tegra_i2c_wait_completion_timeout( i2c_dev, &i2c_dev->dma_complete, xfer_time); + /* + * Synchronize DMA first, since dmaengine_terminate_sync() + * performs synchronization after the transfer's termination + * and we want to get a completion if transfer succeeded. + */ + dmaengine_synchronize(i2c_dev->msg_read ? + i2c_dev->rx_dma_chan : + i2c_dev->tx_dma_chan); + dmaengine_terminate_sync(i2c_dev->msg_read ? i2c_dev->rx_dma_chan : i2c_dev->tx_dma_chan); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 5cc0b0ec5570..a66912782064 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2273,19 +2273,6 @@ i2c_new_scanned_device(struct i2c_adapter *adap, } EXPORT_SYMBOL_GPL(i2c_new_scanned_device); -struct i2c_client * -i2c_new_probed_device(struct i2c_adapter *adap, - struct i2c_board_info *info, - unsigned short const *addr_list, - int (*probe)(struct i2c_adapter *adap, unsigned short addr)) -{ - struct i2c_client *client; - - client = i2c_new_scanned_device(adap, info, addr_list, probe); - return IS_ERR(client) ? NULL : client; -} -EXPORT_SYMBOL_GPL(i2c_new_probed_device); - struct i2c_adapter *i2c_get_adapter(int nr) { struct i2c_adapter *adapter; diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index eb9bce93cd05..fd7c537fb42a 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -416,7 +416,7 @@ static const struct irq_domain_ops bcm7038_l1_domain_ops = { .map = bcm7038_l1_map, }; -int __init bcm7038_l1_of_init(struct device_node *dn, +static int __init bcm7038_l1_of_init(struct device_node *dn, struct device_node *parent) { struct bcm7038_l1_chip *intc; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 54d142ccc63a..124251b0ccba 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -14,6 +14,7 @@ #include <linux/dma-iommu.h> #include <linux/efi.h> #include <linux/interrupt.h> +#include <linux/iopoll.h> #include <linux/irqdomain.h> #include <linux/list.h> #include <linux/log2.h> @@ -3672,6 +3673,20 @@ out: return IRQ_SET_MASK_OK_DONE; } +static void its_wait_vpt_parse_complete(void) +{ + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + u64 val; + + if (!gic_rdists->has_vpend_valid_dirty) + return; + + WARN_ON_ONCE(readq_relaxed_poll_timeout(vlpi_base + GICR_VPENDBASER, + val, + !(val & GICR_VPENDBASER_Dirty), + 10, 500)); +} + static void its_vpe_schedule(struct its_vpe *vpe) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); @@ -3702,6 +3717,8 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0; val |= GICR_VPENDBASER_Valid; gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + its_wait_vpt_parse_complete(); } static void its_vpe_deschedule(struct its_vpe *vpe) @@ -3910,6 +3927,8 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe, val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id); gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + its_wait_vpt_parse_complete(); } static void its_vpe_4_1_deschedule(struct its_vpe *vpe, @@ -4035,6 +4054,7 @@ static int its_sgi_set_affinity(struct irq_data *d, * not on the host (since they can only be targetting a vPE). * Tell the kernel we've done whatever it asked for. */ + irq_data_update_effective_affinity(d, mask_val); return IRQ_SET_MASK_OK; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 9dbc81b6f62e..d7006ef18a0d 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -873,6 +873,7 @@ static int __gic_update_rdist_properties(struct redist_region *region, gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | gic_data.rdists.has_rvpeid); + gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); /* Detect non-sensical configurations */ if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) { @@ -893,10 +894,11 @@ static void gic_update_rdist_properties(void) if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; pr_info("%d PPIs implemented\n", gic_data.ppi_nr); - pr_info("%sVLPI support, %sdirect LPI support, %sRVPEID support\n", - !gic_data.rdists.has_vlpis ? "no " : "", - !gic_data.rdists.has_direct_lpi ? "no " : "", - !gic_data.rdists.has_rvpeid ? "no " : ""); + if (gic_data.rdists.has_vlpis) + pr_info("GICv4 features: %s%s%s\n", + gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", + gic_data.rdists.has_rvpeid ? "RVPEID " : "", + gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : ""); } /* Check whether it's single security state view */ @@ -1620,6 +1622,7 @@ static int __init gic_init_bases(void __iomem *dist_base, gic_data.rdists.has_rvpeid = true; gic_data.rdists.has_vlpis = true; gic_data.rdists.has_direct_lpi = true; + gic_data.rdists.has_vpend_valid_dirty = true; if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { err = -ENOMEM; diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index 6b566bba263b..ff7627b57772 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -220,10 +220,16 @@ static int mbigen_irq_domain_alloc(struct irq_domain *domain, return 0; } +static void mbigen_irq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + platform_msi_domain_free(domain, virq, nr_irqs); +} + static const struct irq_domain_ops mbigen_domain_ops = { .translate = mbigen_domain_translate, .alloc = mbigen_irq_domain_alloc, - .free = irq_domain_free_irqs_common, + .free = mbigen_irq_domain_free, }; static int mbigen_of_create_domain(struct platform_device *pdev, diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index ccc7f823911b..bc7aebcc96e9 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -144,12 +144,17 @@ struct meson_gpio_irq_controller { static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl, unsigned int reg, u32 mask, u32 val) { + unsigned long flags; u32 tmp; + spin_lock_irqsave(&ctl->lock, flags); + tmp = readl_relaxed(ctl->base + reg); tmp &= ~mask; tmp |= val; writel_relaxed(tmp, ctl->base + reg); + + spin_unlock_irqrestore(&ctl->lock, flags); } static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl) @@ -196,14 +201,15 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, unsigned long hwirq, u32 **channel_hwirq) { + unsigned long flags; unsigned int idx; - spin_lock(&ctl->lock); + spin_lock_irqsave(&ctl->lock, flags); /* Find a free channel */ idx = find_first_zero_bit(ctl->channel_map, NUM_CHANNEL); if (idx >= NUM_CHANNEL) { - spin_unlock(&ctl->lock); + spin_unlock_irqrestore(&ctl->lock, flags); pr_err("No channel available\n"); return -ENOSPC; } @@ -211,6 +217,8 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, /* Mark the channel as used */ set_bit(idx, ctl->channel_map); + spin_unlock_irqrestore(&ctl->lock, flags); + /* * Setup the mux of the channel to route the signal of the pad * to the appropriate input of the GIC @@ -225,8 +233,6 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, */ *channel_hwirq = &(ctl->channel_irqs[idx]); - spin_unlock(&ctl->lock); - pr_debug("hwirq %lu assigned to channel %d - irq %u\n", hwirq, idx, **channel_hwirq); @@ -287,13 +293,9 @@ static int meson_gpio_irq_type_setup(struct meson_gpio_irq_controller *ctl, val |= REG_EDGE_POL_LOW(params, idx); } - spin_lock(&ctl->lock); - meson_gpio_irq_update_bits(ctl, REG_EDGE_POL, REG_EDGE_POL_MASK(params, idx), val); - spin_unlock(&ctl->lock); - return 0; } diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c index 547045d89c4b..91adf771f185 100644 --- a/drivers/irqchip/irq-mvebu-icu.c +++ b/drivers/irqchip/irq-mvebu-icu.c @@ -66,7 +66,7 @@ struct mvebu_icu_irq_data { unsigned int type; }; -DEFINE_STATIC_KEY_FALSE(legacy_bindings); +static DEFINE_STATIC_KEY_FALSE(legacy_bindings); static void mvebu_icu_init(struct mvebu_icu *icu, struct mvebu_icu_msi_data *msi_data, diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index c34fb3ae0ff8..d0a71febdadc 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -56,7 +56,7 @@ #define CONTEXT_THRESHOLD 0x00 #define CONTEXT_CLAIM 0x04 -#define PLIC_DISABLE_THRESHOLD 0xf +#define PLIC_DISABLE_THRESHOLD 0x7 #define PLIC_ENABLE_THRESHOLD 0 struct plic_priv { diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index 8f6e6b08eadf..7e3ebf6ed2cd 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -37,6 +37,7 @@ #define VINT_ENABLE_SET_OFFSET 0x0 #define VINT_ENABLE_CLR_OFFSET 0x8 #define VINT_STATUS_OFFSET 0x18 +#define VINT_STATUS_MASKED_OFFSET 0x20 /** * struct ti_sci_inta_event_desc - Description of an event coming to @@ -116,7 +117,7 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc) chained_irq_enter(irq_desc_get_chip(desc), desc); val = readq_relaxed(inta->base + vint_desc->vint_id * 0x1000 + - VINT_STATUS_OFFSET); + VINT_STATUS_MASKED_OFFSET); for_each_set_bit(bit, &val, MAX_EVENTS_PER_VINT) { virq = irq_find_mapping(domain, vint_desc->events[bit].hwirq); diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c index e325e87c0593..11e8c7d8b6e8 100644 --- a/drivers/isdn/hardware/mISDN/mISDNisar.c +++ b/drivers/isdn/hardware/mISDN/mISDNisar.c @@ -743,10 +743,10 @@ check_send(struct isar_hw *isar, u8 rdm) } } -const char *dmril[] = {"NO SPEED", "1200/75", "NODEF2", "75/1200", "NODEF4", +static const char *dmril[] = {"NO SPEED", "1200/75", "NODEF2", "75/1200", "NODEF4", "300", "600", "1200", "2400", "4800", "7200", "9600nt", "9600t", "12000", "14400", "WRONG"}; -const char *dmrim[] = {"NO MOD", "NO DEF", "V32/V32b", "V22", "V21", +static const char *dmrim[] = {"NO MOD", "NO DEF", "V32/V32b", "V22", "V21", "Bell103", "V23", "Bell202", "V17", "V29", "V27ter"}; static void diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 0f3417d161b8..069c42f22a8c 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -103,6 +103,8 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_peek_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + case BPF_FUNC_ktime_get_boot_ns: + return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_prandom_u32: diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig index 8f201d019f5a..3bfe72c59864 100644 --- a/drivers/misc/mic/Kconfig +++ b/drivers/misc/mic/Kconfig @@ -116,7 +116,7 @@ config MIC_COSM config VOP tristate "VOP Driver" - depends on VOP_BUS + depends on VOP_BUS && VHOST_DPN select VHOST_RING select VIRTIO help diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile index 7ddb742de1fe..653923896205 100644 --- a/drivers/mtd/spi-nor/Makefile +++ b/drivers/mtd/spi-nor/Makefile @@ -18,3 +18,5 @@ spi-nor-objs += winbond.o spi-nor-objs += xilinx.o spi-nor-objs += xmc.o obj-$(CONFIG_MTD_SPI_NOR) += spi-nor.o + +obj-$(CONFIG_MTD_SPI_NOR) += controllers/ diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h index 45b77bc8c7b3..48cdf3a49a7d 100644 --- a/drivers/net/bonding/bonding_priv.h +++ b/drivers/net/bonding/bonding_priv.h @@ -14,7 +14,7 @@ #ifndef _BONDING_PRIV_H #define _BONDING_PRIV_H -#include <linux/vermagic.h> +#include <generated/utsrelease.h> #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig index 9db0570c5beb..661c25eb1c46 100644 --- a/drivers/net/caif/Kconfig +++ b/drivers/net/caif/Kconfig @@ -50,7 +50,7 @@ config CAIF_HSI config CAIF_VIRTIO tristate "CAIF virtio transport driver" - depends on CAIF && HAS_DMA + depends on CAIF && HAS_DMA && VHOST_DPN select VHOST_RING select VIRTIO select GENERIC_ALLOCATOR diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 68e2381694b9..c283593bef17 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1474,6 +1474,10 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op) reg |= ARLTBL_RW; else reg &= ~ARLTBL_RW; + if (dev->vlan_enabled) + reg &= ~ARLTBL_IVL_SVL_SELECT; + else + reg |= ARLTBL_IVL_SVL_SELECT; b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg); return b53_arl_op_wait(dev); @@ -1483,6 +1487,7 @@ static int b53_arl_read(struct b53_device *dev, u64 mac, u16 vid, struct b53_arl_entry *ent, u8 *idx, bool is_valid) { + DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES); unsigned int i; int ret; @@ -1490,6 +1495,8 @@ static int b53_arl_read(struct b53_device *dev, u64 mac, if (ret) return ret; + bitmap_zero(free_bins, dev->num_arl_entries); + /* Read the bins */ for (i = 0; i < dev->num_arl_entries; i++) { u64 mac_vid; @@ -1501,13 +1508,24 @@ static int b53_arl_read(struct b53_device *dev, u64 mac, B53_ARLTBL_DATA_ENTRY(i), &fwd_entry); b53_arl_to_entry(ent, mac_vid, fwd_entry); - if (!(fwd_entry & ARLTBL_VALID)) + if (!(fwd_entry & ARLTBL_VALID)) { + set_bit(i, free_bins); continue; + } if ((mac_vid & ARLTBL_MAC_MASK) != mac) continue; + if (dev->vlan_enabled && + ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid) + continue; *idx = i; + return 0; } + if (bitmap_weight(free_bins, dev->num_arl_entries) == 0) + return -ENOSPC; + + *idx = find_first_bit(free_bins, dev->num_arl_entries); + return -ENOENT; } @@ -1537,10 +1555,21 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, if (op) return ret; - /* We could not find a matching MAC, so reset to a new entry */ - if (ret) { + switch (ret) { + case -ENOSPC: + dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n", + addr, vid); + return is_valid ? ret : 0; + case -ENOENT: + /* We could not find a matching MAC, so reset to a new entry */ + dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n", + addr, vid, idx); fwd_entry = 0; - idx = 1; + break; + default: + dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n", + addr, vid, idx); + break; } /* For multicast address, the port is a bitmask and the validity @@ -1558,7 +1587,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, ent.is_valid = !!(ent.port); } - ent.is_valid = is_valid; ent.vid = vid; ent.is_static = true; ent.is_age = false; diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 2a9f421680aa..c90985c294a2 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -292,6 +292,7 @@ /* ARL Table Read/Write Register (8 bit) */ #define B53_ARLTBL_RW_CTRL 0x00 #define ARLTBL_RW BIT(0) +#define ARLTBL_IVL_SVL_SELECT BIT(6) #define ARLTBL_START_DONE BIT(7) /* MAC Address Index Register (48 bit) */ @@ -304,7 +305,7 @@ * * BCM5325 and BCM5365 share most definitions below */ -#define B53_ARLTBL_MAC_VID_ENTRY(n) (0x10 * (n)) +#define B53_ARLTBL_MAC_VID_ENTRY(n) ((0x10 * (n)) + 0x10) #define ARLTBL_MAC_MASK 0xffffffffffffULL #define ARLTBL_VID_S 48 #define ARLTBL_VID_MASK_25 0xff @@ -316,13 +317,16 @@ #define ARLTBL_VALID_25 BIT(63) /* ARL Table Data Entry N Registers (32 bit) */ -#define B53_ARLTBL_DATA_ENTRY(n) ((0x10 * (n)) + 0x08) +#define B53_ARLTBL_DATA_ENTRY(n) ((0x10 * (n)) + 0x18) #define ARLTBL_DATA_PORT_ID_MASK 0x1ff #define ARLTBL_TC(tc) ((3 & tc) << 11) #define ARLTBL_AGE BIT(14) #define ARLTBL_STATIC BIT(15) #define ARLTBL_VALID BIT(16) +/* Maximum number of bin entries in the ARL for all switches */ +#define B53_ARLTBL_MAX_BIN_ENTRIES 4 + /* ARL Search Control Register (8 bit) */ #define B53_ARL_SRCH_CTL 0x50 #define B53_ARL_SRCH_CTL_25 0x20 diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 0a1be5259be0..1207c3095027 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -524,7 +524,7 @@ static void b53_srab_prepare_irq(struct platform_device *pdev) port->num = i; port->dev = dev; - port->irq = platform_get_irq_byname(pdev, name); + port->irq = platform_get_irq_byname_optional(pdev, name); kfree(name); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 2d0d91db0ddb..5c444cd722bd 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -67,58 +67,6 @@ static const struct mt7530_mib_desc mt7530_mib[] = { }; static int -mt7623_trgmii_write(struct mt7530_priv *priv, u32 reg, u32 val) -{ - int ret; - - ret = regmap_write(priv->ethernet, TRGMII_BASE(reg), val); - if (ret < 0) - dev_err(priv->dev, - "failed to priv write register\n"); - return ret; -} - -static u32 -mt7623_trgmii_read(struct mt7530_priv *priv, u32 reg) -{ - int ret; - u32 val; - - ret = regmap_read(priv->ethernet, TRGMII_BASE(reg), &val); - if (ret < 0) { - dev_err(priv->dev, - "failed to priv read register\n"); - return ret; - } - - return val; -} - -static void -mt7623_trgmii_rmw(struct mt7530_priv *priv, u32 reg, - u32 mask, u32 set) -{ - u32 val; - - val = mt7623_trgmii_read(priv, reg); - val &= ~mask; - val |= set; - mt7623_trgmii_write(priv, reg, val); -} - -static void -mt7623_trgmii_set(struct mt7530_priv *priv, u32 reg, u32 val) -{ - mt7623_trgmii_rmw(priv, reg, 0, val); -} - -static void -mt7623_trgmii_clear(struct mt7530_priv *priv, u32 reg, u32 val) -{ - mt7623_trgmii_rmw(priv, reg, val, 0); -} - -static int core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad) { struct mii_bus *bus = priv->bus; @@ -530,27 +478,6 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, int mode) for (i = 0 ; i < NUM_TRGMII_CTRL; i++) mt7530_rmw(priv, MT7530_TRGMII_RD(i), RD_TAP_MASK, RD_TAP(16)); - else - if (priv->id != ID_MT7621) - mt7623_trgmii_set(priv, GSW_INTF_MODE, - INTF_MODE_TRGMII); - - return 0; -} - -static int -mt7623_pad_clk_setup(struct dsa_switch *ds) -{ - struct mt7530_priv *priv = ds->priv; - int i; - - for (i = 0 ; i < NUM_TRGMII_CTRL; i++) - mt7623_trgmii_write(priv, GSW_TRGMII_TD_ODT(i), - TD_DM_DRVP(8) | TD_DM_DRVN(8)); - - mt7623_trgmii_set(priv, GSW_TRGMII_RCK_CTRL, RX_RST | RXC_DQSISEL); - mt7623_trgmii_clear(priv, GSW_TRGMII_RCK_CTRL, RX_RST); - return 0; } @@ -846,8 +773,9 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) */ mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK, MT7530_PORT_MATRIX_MODE); - mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK, - VLAN_ATTR(MT7530_VLAN_TRANSPARENT)); + mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK, + VLAN_ATTR(MT7530_VLAN_TRANSPARENT) | + PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); for (i = 0; i < MT7530_NUM_PORTS; i++) { if (dsa_is_user_port(ds, i) && @@ -863,8 +791,8 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) if (all_user_ports_removed) { mt7530_write(priv, MT7530_PCR_P(MT7530_CPU_PORT), PCR_MATRIX(dsa_user_ports(priv->ds))); - mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), - PORT_SPEC_TAG); + mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), PORT_SPEC_TAG + | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } } @@ -890,8 +818,9 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) /* Set the port as a user port which is to be able to recognize VID * from incoming packets before fetching entry within the VLAN table. */ - mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK, - VLAN_ATTR(MT7530_VLAN_USER)); + mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK, + VLAN_ATTR(MT7530_VLAN_USER) | + PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); } static void @@ -1303,10 +1232,6 @@ mt7530_setup(struct dsa_switch *ds) dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent; if (priv->id == ID_MT7530) { - priv->ethernet = syscon_node_to_regmap(dn); - if (IS_ERR(priv->ethernet)) - return PTR_ERR(priv->ethernet); - regulator_set_voltage(priv->core_pwr, 1000000, 1000000); ret = regulator_enable(priv->core_pwr); if (ret < 0) { @@ -1380,6 +1305,10 @@ mt7530_setup(struct dsa_switch *ds) mt7530_cpu_port_enable(priv, i); else mt7530_port_disable(ds, i); + + /* Enable consistent egress tag */ + mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK, + PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } /* Setup port 5 */ @@ -1468,14 +1397,6 @@ static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port, /* Setup TX circuit incluing relevant PAD and driving */ mt7530_pad_clk_setup(ds, state->interface); - if (priv->id == ID_MT7530) { - /* Setup RX circuit, relevant PAD and driving on the - * host which must be placed after the setup on the - * device side is all finished. - */ - mt7623_pad_clk_setup(ds); - } - priv->p6_interface = state->interface; break; default: diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index ef9b52f3152b..979bb6374678 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -172,9 +172,16 @@ enum mt7530_port_mode { /* Register for port vlan control */ #define MT7530_PVC_P(x) (0x2010 + ((x) * 0x100)) #define PORT_SPEC_TAG BIT(5) +#define PVC_EG_TAG(x) (((x) & 0x7) << 8) +#define PVC_EG_TAG_MASK PVC_EG_TAG(7) #define VLAN_ATTR(x) (((x) & 0x3) << 6) #define VLAN_ATTR_MASK VLAN_ATTR(3) +enum mt7530_vlan_port_eg_tag { + MT7530_VLAN_EG_DISABLED = 0, + MT7530_VLAN_EG_CONSISTENT = 1, +}; + enum mt7530_vlan_port_attr { MT7530_VLAN_USER = 0, MT7530_VLAN_TRANSPARENT = 3, @@ -277,7 +284,6 @@ enum mt7530_vlan_port_attr { /* Registers for TRGMII on the both side */ #define MT7530_TRGMII_RCK_CTRL 0x7a00 -#define GSW_TRGMII_RCK_CTRL 0x300 #define RX_RST BIT(31) #define RXC_DQSISEL BIT(30) #define DQSI1_TAP_MASK (0x7f << 8) @@ -286,31 +292,24 @@ enum mt7530_vlan_port_attr { #define DQSI0_TAP(x) ((x) & 0x7f) #define MT7530_TRGMII_RCK_RTT 0x7a04 -#define GSW_TRGMII_RCK_RTT 0x304 #define DQS1_GATE BIT(31) #define DQS0_GATE BIT(30) #define MT7530_TRGMII_RD(x) (0x7a10 + (x) * 8) -#define GSW_TRGMII_RD(x) (0x310 + (x) * 8) #define BSLIP_EN BIT(31) #define EDGE_CHK BIT(30) #define RD_TAP_MASK 0x7f #define RD_TAP(x) ((x) & 0x7f) -#define GSW_TRGMII_TXCTRL 0x340 #define MT7530_TRGMII_TXCTRL 0x7a40 #define TRAIN_TXEN BIT(31) #define TXC_INV BIT(30) #define TX_RST BIT(28) #define MT7530_TRGMII_TD_ODT(i) (0x7a54 + 8 * (i)) -#define GSW_TRGMII_TD_ODT(i) (0x354 + 8 * (i)) #define TD_DM_DRVP(x) ((x) & 0xf) #define TD_DM_DRVN(x) (((x) & 0xf) << 4) -#define GSW_INTF_MODE 0x390 -#define INTF_MODE_TRGMII BIT(1) - #define MT7530_TRGMII_TCK_CTRL 0x7a78 #define TCK_TAP(x) (((x) & 0xf) << 8) @@ -443,7 +442,6 @@ static const char *p5_intf_modes(unsigned int p5_interface) * @ds: The pointer to the dsa core structure * @bus: The bus used for the device and built-in PHY * @rstc: The pointer to reset control used by MCM - * @ethernet: The regmap used for access TRGMII-based registers * @core_pwr: The power supplied into the core * @io_pwr: The power supplied into the I/O * @reset: The descriptor for GPIO line tied to its reset pin @@ -460,7 +458,6 @@ struct mt7530_priv { struct dsa_switch *ds; struct mii_bus *bus; struct reset_control *rstc; - struct regmap *ethernet; struct regulator *core_pwr; struct regulator *io_pwr; struct gpio_desc *reset; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 221593261e8f..dd8a5666a584 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -709,7 +709,8 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, ops = chip->info->ops; mv88e6xxx_reg_lock(chip); - if (!mv88e6xxx_port_ppu_updates(chip, port) && ops->port_set_link) + if ((!mv88e6xxx_port_ppu_updates(chip, port) || + mode == MLO_AN_FIXED) && ops->port_set_link) err = ops->port_set_link(chip, port, LINK_FORCED_DOWN); mv88e6xxx_reg_unlock(chip); @@ -731,7 +732,7 @@ static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, ops = chip->info->ops; mv88e6xxx_reg_lock(chip); - if (!mv88e6xxx_port_ppu_updates(chip, port)) { + if (!mv88e6xxx_port_ppu_updates(chip, port) || mode == MLO_AN_FIXED) { /* FIXME: for an automedia port, should we force the link * down here - what if the link comes up due to "other" media * while we're bringing the port up, how is the exclusivity diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 79ca3aadb864..8a633ddce6c5 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -7,6 +7,7 @@ #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot_dev.h> #include <soc/mscc/ocelot_ana.h> +#include <soc/mscc/ocelot_ptp.h> #include <soc/mscc/ocelot.h> #include <linux/packing.h> #include <linux/module.h> @@ -46,11 +47,8 @@ static int felix_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { struct ocelot *ocelot = ds->priv; - bool vlan_aware; - vlan_aware = dsa_port_is_vlan_filtering(dsa_to_port(ds, port)); - - return ocelot_fdb_add(ocelot, port, addr, vid, vlan_aware); + return ocelot_fdb_add(ocelot, port, addr, vid); } static int felix_fdb_del(struct dsa_switch *ds, int port, @@ -497,6 +495,23 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return 0; } +static struct ptp_clock_info ocelot_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "felix ptp", + .max_adj = 0x7fffffff, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = OCELOT_PTP_PINS_NUM, + .n_pins = OCELOT_PTP_PINS_NUM, + .pps = 0, + .gettime64 = ocelot_ptp_gettime64, + .settime64 = ocelot_ptp_settime64, + .adjtime = ocelot_ptp_adjtime, + .adjfine = ocelot_ptp_adjfine, + .verify = ocelot_ptp_verify, + .enable = ocelot_ptp_enable, +}; + /* 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 @@ -507,12 +522,21 @@ static int felix_setup(struct dsa_switch *ds) struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); int port, err; + int tc; err = felix_init_structs(felix, ds->num_ports); if (err) return err; ocelot_init(ocelot); + if (ocelot->ptp) { + err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info); + if (err) { + dev_err(ocelot->dev, + "Timestamp initialization failed\n"); + ocelot->ptp = 0; + } + } for (port = 0; port < ds->num_ports; port++) { ocelot_init_port(ocelot, port); @@ -532,6 +556,12 @@ static int felix_setup(struct dsa_switch *ds) ocelot_write_rix(ocelot, ANA_PGID_PGID_PGID(GENMASK(ocelot->num_phys_ports, 0)), ANA_PGID_PGID, PGID_UC); + /* Setup the per-traffic class flooding PGIDs */ + for (tc = 0; tc < FELIX_NUM_TC; tc++) + ocelot_write_rix(ocelot, ANA_FLOODING_FLD_MULTICAST(PGID_MC) | + ANA_FLOODING_FLD_BROADCAST(PGID_MC) | + ANA_FLOODING_FLD_UNICAST(PGID_UC), + ANA_FLOODING, tc); ds->mtu_enforcement_ingress = true; /* It looks like the MAC/PCS interrupt register - PM0_IEVENT (0x8040) @@ -551,6 +581,7 @@ static void felix_teardown(struct dsa_switch *ds) if (felix->info->mdio_bus_free) felix->info->mdio_bus_free(ocelot); + ocelot_deinit_timestamp(ocelot); /* stop workqueue thread */ ocelot_deinit(ocelot); } diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 82d46f260041..2ad793c0e1df 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -5,6 +5,7 @@ #define _MSCC_FELIX_H #define ocelot_to_felix(o) container_of((o), struct felix, ocelot) +#define FELIX_NUM_TC 8 /* Platform-specific information */ struct felix_info { diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index b4078f3c5c38..4fe707ef54b8 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -313,6 +313,8 @@ static const u32 vsc9959_ptp_regmap[] = { REG(PTP_PIN_TOD_SEC_MSB, 0x000004), REG(PTP_PIN_TOD_SEC_LSB, 0x000008), REG(PTP_PIN_TOD_NSEC, 0x00000c), + REG(PTP_PIN_WF_HIGH_PERIOD, 0x000014), + REG(PTP_PIN_WF_LOW_PERIOD, 0x000018), REG(PTP_CFG_MISC, 0x0000a0), REG(PTP_CLK_CFG_ADJ_CFG, 0x0000a4), REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 8b60dbd567f2..2f62942692ec 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -49,6 +49,7 @@ struct sja1105_regs { u64 ptpschtm; u64 ptpegr_ts[SJA1105_NUM_PORTS]; u64 pad_mii_tx[SJA1105_NUM_PORTS]; + u64 pad_mii_rx[SJA1105_NUM_PORTS]; u64 pad_mii_id[SJA1105_NUM_PORTS]; u64 cgu_idiv[SJA1105_NUM_PORTS]; u64 mii_tx_clk[SJA1105_NUM_PORTS]; diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c index 0fdc2d55fff6..2a9b8a6a5306 100644 --- a/drivers/net/dsa/sja1105/sja1105_clocking.c +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -7,12 +7,16 @@ #define SJA1105_SIZE_CGU_CMD 4 -struct sja1105_cfg_pad_mii_tx { +/* Common structure for CFG_PAD_MIIx_RX and CFG_PAD_MIIx_TX */ +struct sja1105_cfg_pad_mii { u64 d32_os; + u64 d32_ih; u64 d32_ipud; + u64 d10_ih; u64 d10_os; u64 d10_ipud; u64 ctrl_os; + u64 ctrl_ih; u64 ctrl_ipud; u64 clk_os; u64 clk_ih; @@ -338,16 +342,19 @@ static int sja1105_cgu_rgmii_tx_clk_config(struct sja1105_private *priv, /* AGU */ static void -sja1105_cfg_pad_mii_tx_packing(void *buf, struct sja1105_cfg_pad_mii_tx *cmd, - enum packing_op op) +sja1105_cfg_pad_mii_packing(void *buf, struct sja1105_cfg_pad_mii *cmd, + enum packing_op op) { const int size = 4; sja1105_packing(buf, &cmd->d32_os, 28, 27, size, op); + sja1105_packing(buf, &cmd->d32_ih, 26, 26, size, op); sja1105_packing(buf, &cmd->d32_ipud, 25, 24, size, op); sja1105_packing(buf, &cmd->d10_os, 20, 19, size, op); + sja1105_packing(buf, &cmd->d10_ih, 18, 18, size, op); sja1105_packing(buf, &cmd->d10_ipud, 17, 16, size, op); sja1105_packing(buf, &cmd->ctrl_os, 12, 11, size, op); + sja1105_packing(buf, &cmd->ctrl_ih, 10, 10, size, op); sja1105_packing(buf, &cmd->ctrl_ipud, 9, 8, size, op); sja1105_packing(buf, &cmd->clk_os, 4, 3, size, op); sja1105_packing(buf, &cmd->clk_ih, 2, 2, size, op); @@ -358,7 +365,7 @@ static int sja1105_rgmii_cfg_pad_tx_config(struct sja1105_private *priv, int port) { const struct sja1105_regs *regs = priv->info->regs; - struct sja1105_cfg_pad_mii_tx pad_mii_tx; + struct sja1105_cfg_pad_mii pad_mii_tx = {0}; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; /* Payload */ @@ -375,12 +382,45 @@ static int sja1105_rgmii_cfg_pad_tx_config(struct sja1105_private *priv, pad_mii_tx.clk_os = 3; /* TX_CLK output stage */ pad_mii_tx.clk_ih = 0; /* TX_CLK input hysteresis (default) */ pad_mii_tx.clk_ipud = 2; /* TX_CLK input stage (default) */ - sja1105_cfg_pad_mii_tx_packing(packed_buf, &pad_mii_tx, PACK); + sja1105_cfg_pad_mii_packing(packed_buf, &pad_mii_tx, PACK); return sja1105_xfer_buf(priv, SPI_WRITE, regs->pad_mii_tx[port], packed_buf, SJA1105_SIZE_CGU_CMD); } +static int sja1105_cfg_pad_rx_config(struct sja1105_private *priv, int port) +{ + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cfg_pad_mii pad_mii_rx = {0}; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + + /* Payload */ + pad_mii_rx.d32_ih = 0; /* RXD[3:2] input stage hysteresis: */ + /* non-Schmitt (default) */ + pad_mii_rx.d32_ipud = 2; /* RXD[3:2] input weak pull-up/down */ + /* plain input (default) */ + pad_mii_rx.d10_ih = 0; /* RXD[1:0] input stage hysteresis: */ + /* non-Schmitt (default) */ + pad_mii_rx.d10_ipud = 2; /* RXD[1:0] input weak pull-up/down */ + /* plain input (default) */ + pad_mii_rx.ctrl_ih = 0; /* RX_DV/CRS_DV/RX_CTL and RX_ER */ + /* input stage hysteresis: */ + /* non-Schmitt (default) */ + pad_mii_rx.ctrl_ipud = 3; /* RX_DV/CRS_DV/RX_CTL and RX_ER */ + /* input stage weak pull-up/down: */ + /* pull-down */ + pad_mii_rx.clk_os = 2; /* RX_CLK/RXC output stage: */ + /* medium noise/fast speed (default) */ + pad_mii_rx.clk_ih = 0; /* RX_CLK/RXC input hysteresis: */ + /* non-Schmitt (default) */ + pad_mii_rx.clk_ipud = 2; /* RX_CLK/RXC input pull-up/down: */ + /* plain input (default) */ + sja1105_cfg_pad_mii_packing(packed_buf, &pad_mii_rx, PACK); + + return sja1105_xfer_buf(priv, SPI_WRITE, regs->pad_mii_rx[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + static void sja1105_cfg_pad_mii_id_packing(void *buf, struct sja1105_cfg_pad_mii_id *cmd, enum packing_op op) @@ -669,10 +709,14 @@ int sja1105_clocking_setup_port(struct sja1105_private *priv, int port) phy_mode); return -EINVAL; } - if (rc) + if (rc) { dev_err(dev, "Clocking setup for port %d failed: %d\n", port, rc); - return rc; + return rc; + } + + /* Internally pull down the RX_DV/CRS_DV/RX_CTL and RX_ER inputs */ + return sja1105_cfg_pad_rx_config(priv, port); } int sja1105_clocking_setup(struct sja1105_private *priv) diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index 04bdb72ae6b6..43f14a5c2718 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -443,6 +443,7 @@ static struct sja1105_regs sja1105et_regs = { .rgu = 0x100440, /* UM10944.pdf, Table 86, ACU Register overview */ .pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, + .pad_mii_rx = {0x100801, 0x100803, 0x100805, 0x100807, 0x100809}, .rmii_pll1 = 0x10000A, .cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F}, .mac = {0x200, 0x202, 0x204, 0x206, 0x208}, @@ -475,6 +476,7 @@ static struct sja1105_regs sja1105pqrs_regs = { .rgu = 0x100440, /* UM10944.pdf, Table 86, ACU Register overview */ .pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, + .pad_mii_rx = {0x100801, 0x100803, 0x100805, 0x100807, 0x100809}, .pad_mii_id = {0x100810, 0x100811, 0x100812, 0x100813, 0x100814}, .sgmii = 0x1F0000, .rmii_pll1 = 0x10000A, diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index b762176a1406..139d0120f511 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -85,7 +85,6 @@ #include <linux/device.h> #include <linux/eisa.h> #include <linux/bitops.h> -#include <linux/vermagic.h> #include <linux/uaccess.h> #include <asm/io.h> diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 90312fcd6319..47b4215bb93b 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -22,7 +22,6 @@ */ -#include <linux/vermagic.h> #define DRV_NAME "3c515" #define CORKSCREW 1 diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 2db42211329f..a64191fc2af9 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -45,7 +45,6 @@ #include <asm/processor.h> /* Processor type for cache alignment. */ #include <linux/uaccess.h> #include <asm/io.h> -#include <linux/vermagic.h> /* * The current frame processor firmware fails to checksum a fragment diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index b71f9b04a51e..a87264f95f1a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -514,7 +514,7 @@ static void xgbe_isr_task(unsigned long data) xgbe_disable_rx_tx_ints(pdata); /* Turn on polling */ - __napi_schedule_irqoff(&pdata->napi); + __napi_schedule(&pdata->napi); } } else { /* Don't clear Rx/Tx status if doing per channel DMA diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c index 0b3e234a54aa..91870ceaf3fe 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c @@ -401,7 +401,7 @@ static u32 aq_sc_idx_max(const enum aq_macsec_sc_sa sc_sa) break; default: break; - }; + } return result; } @@ -417,7 +417,7 @@ static u32 aq_to_hw_sc_idx(const u32 sc_idx, const enum aq_macsec_sc_sa sc_sa) return sc_idx; default: WARN_ONCE(true, "Invalid sc_sa"); - }; + } return sc_idx; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index af7ce5c5488c..b25356e21a1e 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -664,7 +664,8 @@ static struct sk_buff *bcm_sysport_rx_refill(struct bcm_sysport_priv *priv, dma_addr_t mapping; /* Allocate a new SKB for a new packet */ - skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH); + skb = __netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH, + GFP_ATOMIC | __GFP_NOWARN); if (!skb) { priv->mib.alloc_rx_buff_failed++; netif_err(priv, rx_err, ndev, "SKB alloc failed\n"); @@ -2475,7 +2476,6 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->wol_irq = platform_get_irq(pdev, 1); } if (priv->irq0 <= 0 || (priv->irq1 <= 0 && !priv->is_lite)) { - dev_err(&pdev->dev, "invalid interrupts\n"); ret = -EINVAL; goto err_free_netdev; } diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index c46c1b1416f7..a5d1a6cb9ce3 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -172,7 +172,6 @@ static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct bgmac *bgmac; - struct resource *regs; const u8 *mac_addr; bgmac = bgmac_alloc(&pdev->dev); @@ -202,31 +201,21 @@ static int bgmac_probe(struct platform_device *pdev) if (bgmac->irq < 0) return bgmac->irq; - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "amac_base"); - if (!regs) { - dev_err(&pdev->dev, "Unable to obtain base resource\n"); - return -EINVAL; - } - - bgmac->plat.base = devm_ioremap_resource(&pdev->dev, regs); + bgmac->plat.base = + devm_platform_ioremap_resource_byname(pdev, "amac_base"); if (IS_ERR(bgmac->plat.base)) return PTR_ERR(bgmac->plat.base); - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); - if (regs) { - bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; - } + bgmac->plat.idm_base = + devm_platform_ioremap_resource_byname(pdev, "idm_base"); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); - if (regs) { - bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, - regs); - if (IS_ERR(bgmac->plat.nicpm_base)) - return PTR_ERR(bgmac->plat.nicpm_base); - } + bgmac->plat.nicpm_base = + devm_platform_ioremap_resource_byname(pdev, "nicpm_base"); + if (IS_ERR(bgmac->plat.nicpm_base)) + return PTR_ERR(bgmac->plat.nicpm_base); bgmac->read = platform_bgmac_read; bgmac->write = platform_bgmac_write; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index d975338bf78d..351d0282f199 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -23,11 +23,6 @@ #include <linux/dma-mapping.h> #include <linux/pm.h> #include <linux/clk.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/of_net.h> -#include <linux/of_platform.h> #include <net/arp.h> #include <linux/mii.h> @@ -934,6 +929,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev, if (netif_running(dev)) bcmgenet_update_mib_counters(priv); + dev->netdev_ops->ndo_get_stats(dev); + for (i = 0; i < BCMGENET_STATS_LEN; i++) { const struct bcmgenet_stats *s; char *p; @@ -1622,7 +1619,8 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv, dma_addr_t mapping; /* Allocate a new Rx skb */ - skb = netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT); + skb = __netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT, + GFP_ATOMIC | __GFP_NOWARN); if (!skb) { priv->mib.alloc_rx_buff_failed++; netif_err(priv, rx_err, priv->dev, @@ -2707,9 +2705,8 @@ static void bcmgenet_umac_reset(struct bcmgenet_priv *priv) static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, unsigned char *addr) { - bcmgenet_umac_writel(priv, (addr[0] << 24) | (addr[1] << 16) | - (addr[2] << 8) | addr[3], UMAC_MAC0); - bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1); + bcmgenet_umac_writel(priv, get_unaligned_be32(&addr[0]), UMAC_MAC0); + bcmgenet_umac_writel(priv, get_unaligned_be16(&addr[4]), UMAC_MAC1); } static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, @@ -2718,13 +2715,9 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, u32 addr_tmp; addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC0); - addr[0] = addr_tmp >> 24; - addr[1] = (addr_tmp >> 16) & 0xff; - addr[2] = (addr_tmp >> 8) & 0xff; - addr[3] = addr_tmp & 0xff; + put_unaligned_be32(addr_tmp, &addr[0]); addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC1); - addr[4] = (addr_tmp >> 8) & 0xff; - addr[5] = addr_tmp & 0xff; + put_unaligned_be16(addr_tmp, &addr[4]); } /* Returns a reusable dma control register value */ @@ -3156,6 +3149,7 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev) dev->stats.rx_packets = rx_packets; dev->stats.rx_errors = rx_errors; dev->stats.rx_missed_errors = rx_errors; + dev->stats.rx_dropped = rx_dropped; return &dev->stats; } @@ -3417,8 +3411,6 @@ MODULE_DEVICE_TABLE(of, bcmgenet_match); static int bcmgenet_probe(struct platform_device *pdev) { struct bcmgenet_platform_data *pd = pdev->dev.platform_data; - struct device_node *dn = pdev->dev.of_node; - const struct of_device_id *of_id = NULL; const struct bcmgenet_plat_data *pdata; struct bcmgenet_priv *priv; struct net_device *dev; @@ -3433,12 +3425,6 @@ static int bcmgenet_probe(struct platform_device *pdev) return -ENOMEM; } - if (dn) { - of_id = of_match_node(bcmgenet_match, dn); - if (!of_id) - return -EINVAL; - } - priv = netdev_priv(dev); priv->irq0 = platform_get_irq(pdev, 0); if (priv->irq0 < 0) { @@ -3500,13 +3486,16 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->dma_max_burst_length = DMA_MAX_BURST_LENGTH; } - priv->clk = devm_clk_get(&priv->pdev->dev, "enet"); + priv->clk = devm_clk_get_optional(&priv->pdev->dev, "enet"); if (IS_ERR(priv->clk)) { dev_dbg(&priv->pdev->dev, "failed to get enet clock\n"); - priv->clk = NULL; + err = PTR_ERR(priv->clk); + goto err; } - clk_prepare_enable(priv->clk); + err = clk_prepare_enable(priv->clk); + if (err) + goto err; bcmgenet_set_hw_params(priv); @@ -3524,16 +3513,18 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->rx_buf_len = RX_BUF_LENGTH; INIT_WORK(&priv->bcmgenet_irq_work, bcmgenet_irq_task); - priv->clk_wol = devm_clk_get(&priv->pdev->dev, "enet-wol"); + priv->clk_wol = devm_clk_get_optional(&priv->pdev->dev, "enet-wol"); if (IS_ERR(priv->clk_wol)) { dev_dbg(&priv->pdev->dev, "failed to get enet-wol clock\n"); - priv->clk_wol = NULL; + err = PTR_ERR(priv->clk_wol); + goto err; } - priv->clk_eee = devm_clk_get(&priv->pdev->dev, "enet-eee"); + priv->clk_eee = devm_clk_get_optional(&priv->pdev->dev, "enet-eee"); if (IS_ERR(priv->clk_eee)) { dev_dbg(&priv->pdev->dev, "failed to get enet-eee clock\n"); - priv->clk_eee = NULL; + err = PTR_ERR(priv->clk_eee); + goto err; } /* If this is an internal GPHY, power it on now, before UniMAC is @@ -3542,7 +3533,7 @@ static int bcmgenet_probe(struct platform_device *pdev) if (device_get_phy_mode(&pdev->dev) == PHY_INTERFACE_MODE_INTERNAL) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - if ((pd) && (!IS_ERR_OR_NULL(pd->mac_address))) + if (pd && !IS_ERR_OR_NULL(pd->mac_address)) ether_addr_copy(dev->dev_addr, pd->mac_address); else if (!device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) @@ -3740,7 +3731,7 @@ static struct platform_driver bcmgenet_driver = { .name = "bcmgenet", .of_match_table = bcmgenet_match, .pm = &bcmgenet_pm_ops, - .acpi_match_table = ACPI_PTR(genet_acpi_match), + .acpi_match_table = genet_acpi_match, }, }; module_platform_driver(bcmgenet_driver); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index 3d01d3602d8f..fb380b4f3e02 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -712,18 +712,6 @@ struct octeon_device *lio_get_device(u32 octeon_id); */ int lio_get_device_id(void *dev); -static inline u16 OCTEON_MAJOR_REV(struct octeon_device *oct) -{ - u16 rev = (oct->rev_id & 0xC) >> 2; - - return (rev == 0) ? 1 : rev; -} - -static inline u16 OCTEON_MINOR_REV(struct octeon_device *oct) -{ - return oct->rev_id & 0x3; -} - /** Read windowed register. * @param oct - pointer to the Octeon device. * @param addr - Address of the register to read. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 19c11568113a..7b9cd69f9844 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -1049,9 +1049,9 @@ static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init, } } -static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init, - struct cudbg_error *cudbg_err, - u8 mem_type) +static int cudbg_mem_region_size(struct cudbg_init *pdbg_init, + struct cudbg_error *cudbg_err, + u8 mem_type, unsigned long *region_size) { struct adapter *padap = pdbg_init->adap; struct cudbg_meminfo mem_info; @@ -1060,15 +1060,23 @@ static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init, memset(&mem_info, 0, sizeof(struct cudbg_meminfo)); rc = cudbg_fill_meminfo(padap, &mem_info); - if (rc) + if (rc) { + cudbg_err->sys_err = rc; return rc; + } cudbg_t4_fwcache(pdbg_init, cudbg_err); rc = cudbg_meminfo_get_mem_index(padap, &mem_info, mem_type, &mc_idx); - if (rc) + if (rc) { + cudbg_err->sys_err = rc; return rc; + } + + if (region_size) + *region_size = mem_info.avail[mc_idx].limit - + mem_info.avail[mc_idx].base; - return mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base; + return 0; } static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init, @@ -1076,7 +1084,12 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init, struct cudbg_error *cudbg_err, u8 mem_type) { - unsigned long size = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type); + unsigned long size = 0; + int rc; + + rc = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type, &size); + if (rc) + return rc; return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size, cudbg_err); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index af1f40cbccc8..f5bc996ac77d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -311,32 +311,17 @@ static int cxgb4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) */ static int cxgb4_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { - struct adapter *adapter = (struct adapter *)container_of(ptp, - struct adapter, ptp_clock_info); - struct fw_ptp_cmd c; + struct adapter *adapter = container_of(ptp, struct adapter, + ptp_clock_info); u64 ns; - int err; - - memset(&c, 0, sizeof(c)); - c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) | - FW_CMD_REQUEST_F | - FW_CMD_READ_F | - FW_PTP_CMD_PORTID_V(0)); - c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16)); - c.u.ts.sc = FW_PTP_SC_GET_TIME; - err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), &c); - if (err < 0) { - dev_err(adapter->pdev_dev, - "PTP: %s error %d\n", __func__, -err); - return err; - } + ns = t4_read_reg(adapter, T5_PORT_REG(0, MAC_PORT_PTP_SUM_LO_A)); + ns |= (u64)t4_read_reg(adapter, + T5_PORT_REG(0, MAC_PORT_PTP_SUM_HI_A)) << 32; /* convert to timespec*/ - ns = be64_to_cpu(c.u.ts.tm); *ts = ns_to_timespec64(ns); - - return err; + return 0; } /** diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 239f678a94ed..2a3480fc1d91 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3742,7 +3742,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver) FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_VERSION)); ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val); - if (ret < 0) + if (ret) return ret; *phy_fw_ver = val; return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index bb20e50ddb84..4a9fcd6c226c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -1906,6 +1906,9 @@ #define MAC_PORT_CFG2_A 0x818 +#define MAC_PORT_PTP_SUM_LO_A 0x990 +#define MAC_PORT_PTP_SUM_HI_A 0x994 + #define MPS_CMN_CTL_A 0x9000 #define COUNTPAUSEMCRX_S 5 diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 48ea658aa1a6..15efc294f513 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1277,7 +1277,7 @@ static const struct net_device_ops tulip_netdev_ops = { #endif }; -const struct pci_device_id early_486_chipsets[] = { +static const struct pci_device_id early_486_chipsets[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82424) }, { PCI_DEVICE(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_496) }, { }, diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 057a508dd6e2..db98274501a0 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -776,8 +776,7 @@ static int dnet_probe(struct platform_device *pdev) spin_lock_init(&bp->lock); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - bp->regs = devm_ioremap_resource(&pdev->dev, res); + bp->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(bp->regs)) { err = PTR_ERR(bp->regs); goto err_out_free_dev; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c index a9afe46b837f..80291afff3ea 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c @@ -127,16 +127,19 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset) int i; seq_printf(file, "Channel stats for %s:\n", priv->net_dev->name); - seq_printf(file, "%s%16s%16s%16s%16s\n", - "CHID", "CPU", "Deq busy", "CDANs", "Buf count"); + seq_printf(file, "%s%16s%16s%16s%16s%16s%16s\n", + "CHID", "CPU", "Deq busy", "Frames", "CDANs", + "Avg Frm/CDAN", "Buf count"); for (i = 0; i < priv->num_channels; i++) { ch = priv->channel[i]; - seq_printf(file, "%4d%16d%16llu%16llu%16d\n", + seq_printf(file, "%4d%16d%16llu%16llu%16llu%16llu%16d\n", ch->ch_id, ch->nctx.desired_cpu, ch->stats.dequeue_portal_busy, + ch->stats.frames, ch->stats.cdan, + ch->stats.frames / ch->stats.cdan, ch->buf_count); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b6c46639aa4c..8ec435ba7d27 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2014-2016 Freescale Semiconductor Inc. - * Copyright 2016-2019 NXP + * Copyright 2016-2020 NXP */ #include <linux/init.h> #include <linux/module.h> @@ -268,7 +268,7 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd, fq = &priv->fq[queue_id]; for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { - err = priv->enqueue(priv, fq, fd, 0); + err = priv->enqueue(priv, fq, fd, 0, 1, NULL); if (err != -EBUSY) break; } @@ -493,6 +493,7 @@ static int consume_frames(struct dpaa2_eth_channel *ch, return 0; fq->stats.frames += cleaned; + ch->stats.frames += cleaned; /* A dequeue operation only pulls frames from a single queue * into the store. Return the frame queue as an out param. @@ -847,7 +848,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) * the Tx confirmation callback for this frame */ for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { - err = priv->enqueue(priv, fq, &fd, prio); + err = priv->enqueue(priv, fq, &fd, prio, 1, NULL); if (err != -EBUSY) break; } @@ -1880,20 +1881,16 @@ static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp) return 0; } -static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev, - struct xdp_frame *xdpf) +static int dpaa2_eth_xdp_create_fd(struct net_device *net_dev, + struct xdp_frame *xdpf, + struct dpaa2_fd *fd) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct device *dev = net_dev->dev.parent; - struct rtnl_link_stats64 *percpu_stats; - struct dpaa2_eth_drv_stats *percpu_extras; unsigned int needed_headroom; struct dpaa2_eth_swa *swa; - struct dpaa2_eth_fq *fq; - struct dpaa2_fd fd; void *buffer_start, *aligned_start; dma_addr_t addr; - int err, i; /* We require a minimum headroom to be able to transmit the frame. * Otherwise return an error and let the original net_device handle it @@ -1902,11 +1899,8 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev, if (xdpf->headroom < needed_headroom) return -EINVAL; - percpu_stats = this_cpu_ptr(priv->percpu_stats); - percpu_extras = this_cpu_ptr(priv->percpu_extras); - /* Setup the FD fields */ - memset(&fd, 0, sizeof(fd)); + memset(fd, 0, sizeof(*fd)); /* Align FD address, if possible */ buffer_start = xdpf->data - needed_headroom; @@ -1924,32 +1918,14 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev, addr = dma_map_single(dev, buffer_start, swa->xdp.dma_size, DMA_BIDIRECTIONAL); - if (unlikely(dma_mapping_error(dev, addr))) { - percpu_stats->tx_dropped++; + if (unlikely(dma_mapping_error(dev, addr))) return -ENOMEM; - } - - dpaa2_fd_set_addr(&fd, addr); - dpaa2_fd_set_offset(&fd, xdpf->data - buffer_start); - dpaa2_fd_set_len(&fd, xdpf->len); - dpaa2_fd_set_format(&fd, dpaa2_fd_single); - dpaa2_fd_set_ctrl(&fd, FD_CTRL_PTA); - fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)]; - for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { - err = priv->enqueue(priv, fq, &fd, 0); - if (err != -EBUSY) - break; - } - percpu_extras->tx_portal_busy += i; - if (unlikely(err < 0)) { - percpu_stats->tx_errors++; - /* let the Rx device handle the cleanup */ - return err; - } - - percpu_stats->tx_packets++; - percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd); + dpaa2_fd_set_addr(fd, addr); + dpaa2_fd_set_offset(fd, xdpf->data - buffer_start); + dpaa2_fd_set_len(fd, xdpf->len); + dpaa2_fd_set_format(fd, dpaa2_fd_single); + dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA); return 0; } @@ -1957,8 +1933,13 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev, static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n, struct xdp_frame **frames, u32 flags) { - int drops = 0; - int i, err; + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + int total_enqueued = 0, retries = 0, enqueued; + struct dpaa2_eth_drv_stats *percpu_extras; + struct rtnl_link_stats64 *percpu_stats; + int num_fds, i, err, max_retries; + struct dpaa2_eth_fq *fq; + struct dpaa2_fd *fds; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; @@ -1966,17 +1947,40 @@ static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n, if (!netif_running(net_dev)) return -ENETDOWN; + fq = &priv->fq[smp_processor_id()]; + fds = fq->xdp_fds; + + percpu_stats = this_cpu_ptr(priv->percpu_stats); + percpu_extras = this_cpu_ptr(priv->percpu_extras); + + /* create a FD for each xdp_frame in the list received */ for (i = 0; i < n; i++) { - struct xdp_frame *xdpf = frames[i]; + err = dpaa2_eth_xdp_create_fd(net_dev, frames[i], &fds[i]); + if (err) + break; + } + num_fds = i; - err = dpaa2_eth_xdp_xmit_frame(net_dev, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; + /* try to enqueue all the FDs until the max number of retries is hit */ + max_retries = num_fds * DPAA2_ETH_ENQUEUE_RETRIES; + while (total_enqueued < num_fds && retries < max_retries) { + err = priv->enqueue(priv, fq, &fds[total_enqueued], + 0, num_fds - total_enqueued, &enqueued); + if (err == -EBUSY) { + percpu_extras->tx_portal_busy += ++retries; + continue; } + total_enqueued += enqueued; } - return n - drops; + /* update statistics */ + percpu_stats->tx_packets += total_enqueued; + for (i = 0; i < total_enqueued; i++) + percpu_stats->tx_bytes += dpaa2_fd_get_len(&fds[i]); + for (i = total_enqueued; i < n; i++) + xdp_return_frame_rx_napi(frames[i]); + + return total_enqueued; } static int update_xps(struct dpaa2_eth_priv *priv) @@ -2018,7 +2022,7 @@ static int dpaa2_eth_setup_tc(struct net_device *net_dev, int i; if (type != TC_SETUP_QDISC_MQPRIO) - return -EINVAL; + return -EOPNOTSUPP; mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; num_queues = dpaa2_eth_queue_count(priv); @@ -2030,7 +2034,7 @@ static int dpaa2_eth_setup_tc(struct net_device *net_dev, if (num_tc > dpaa2_eth_tc_count(priv)) { netdev_err(net_dev, "Max %d traffic classes supported\n", dpaa2_eth_tc_count(priv)); - return -EINVAL; + return -EOPNOTSUPP; } if (!num_tc) { @@ -2523,19 +2527,38 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv, struct dpaa2_eth_fq *fq, - struct dpaa2_fd *fd, u8 prio) + struct dpaa2_fd *fd, u8 prio, + u32 num_frames __always_unused, + int *frames_enqueued) { - return dpaa2_io_service_enqueue_qd(fq->channel->dpio, - priv->tx_qdid, prio, - fq->tx_qdbin, fd); + int err; + + err = dpaa2_io_service_enqueue_qd(fq->channel->dpio, + priv->tx_qdid, prio, + fq->tx_qdbin, fd); + if (!err && frames_enqueued) + *frames_enqueued = 1; + return err; } -static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_fq *fq, - struct dpaa2_fd *fd, u8 prio) +static inline int dpaa2_eth_enqueue_fq_multiple(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq, + struct dpaa2_fd *fd, + u8 prio, u32 num_frames, + int *frames_enqueued) { - return dpaa2_io_service_enqueue_fq(fq->channel->dpio, - fq->tx_fqid[prio], fd); + int err; + + err = dpaa2_io_service_enqueue_multiple_fq(fq->channel->dpio, + fq->tx_fqid[prio], + fd, num_frames); + + if (err == 0) + return -EBUSY; + + if (frames_enqueued) + *frames_enqueued = err; + return 0; } static void set_enqueue_mode(struct dpaa2_eth_priv *priv) @@ -2544,7 +2567,7 @@ static void set_enqueue_mode(struct dpaa2_eth_priv *priv) DPNI_ENQUEUE_FQID_VER_MINOR) < 0) priv->enqueue = dpaa2_eth_enqueue_qd; else - priv->enqueue = dpaa2_eth_enqueue_fq; + priv->enqueue = dpaa2_eth_enqueue_fq_multiple; } static int set_pause(struct dpaa2_eth_priv *priv) @@ -2605,7 +2628,7 @@ static void update_tx_fqids(struct dpaa2_eth_priv *priv) } } - priv->enqueue = dpaa2_eth_enqueue_fq; + priv->enqueue = dpaa2_eth_enqueue_fq_multiple; return; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 7635db3ef903..43cd8409f2e9 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ /* Copyright 2014-2016 Freescale Semiconductor Inc. - * Copyright 2016 NXP + * Copyright 2016-2020 NXP */ #ifndef __DPAA2_ETH_H @@ -288,6 +288,8 @@ struct dpaa2_eth_ch_stats { __u64 xdp_tx; __u64 xdp_tx_err; __u64 xdp_redirect; + /* Must be last, does not show up in ethtool stats */ + __u64 frames; }; /* Maximum number of queues associated with a DPNI */ @@ -325,6 +327,8 @@ struct dpaa2_eth_fq { const struct dpaa2_fd *fd, struct dpaa2_eth_fq *fq); struct dpaa2_eth_fq_stats stats; + + struct dpaa2_fd xdp_fds[DEV_MAP_BULK_SIZE]; }; struct dpaa2_eth_ch_xdp { @@ -371,7 +375,9 @@ struct dpaa2_eth_priv { struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES]; int (*enqueue)(struct dpaa2_eth_priv *priv, struct dpaa2_eth_fq *fq, - struct dpaa2_fd *fd, u8 prio); + struct dpaa2_fd *fd, u8 prio, + u32 num_frames, + int *frames_enqueued); u8 num_channels; struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS]; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 94347c695233..bd13ee48d623 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -277,7 +277,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, /* Per-channel stats */ for (k = 0; k < priv->num_channels; k++) { ch_stats = &priv->channel[k]->stats; - for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64); j++) + for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++) *((__u64 *)data + i + j) += *((__u64 *)ch_stats + j); } i += j; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 85e2b741df41..de1ad4975074 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -50,21 +50,6 @@ static void enetc_set_vlan_promisc(struct enetc_hw *hw, char si_map) enetc_port_wr(hw, ENETC_PSIPVMR, ENETC_PSIPVMR_SET_VP(si_map) | val); } -static bool enetc_si_vlan_promisc_is_on(struct enetc_pf *pf, int si_idx) -{ - return pf->vlan_promisc_simap & BIT(si_idx); -} - -static bool enetc_vlan_filter_is_on(struct enetc_pf *pf) -{ - int i; - - for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) - return true; - - return false; -} - static void enetc_enable_si_vlan_promisc(struct enetc_pf *pf, int si_idx) { pf->vlan_promisc_simap |= BIT(si_idx); @@ -204,6 +189,7 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_pf *pf = enetc_si_priv(priv->si); + char vlan_promisc_simap = pf->vlan_promisc_simap; struct enetc_hw *hw = &priv->si->hw; bool uprom = false, mprom = false; struct enetc_mac_filter *filter; @@ -216,16 +202,16 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev) psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0); uprom = true; mprom = true; - /* enable VLAN promisc mode for SI0 */ - if (!enetc_si_vlan_promisc_is_on(pf, 0)) - enetc_enable_si_vlan_promisc(pf, 0); - + /* Enable VLAN promiscuous mode for SI0 (PF) */ + vlan_promisc_simap |= BIT(0); } else if (ndev->flags & IFF_ALLMULTI) { /* enable multi cast promisc mode for SI0 (PF) */ psipmr = ENETC_PSIPMR_SET_MP(0); mprom = true; } + enetc_set_vlan_promisc(&pf->si->hw, vlan_promisc_simap); + /* first 2 filter entries belong to PF */ if (!uprom) { /* Update unicast filters */ @@ -306,9 +292,6 @@ static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid) struct enetc_pf *pf = enetc_si_priv(priv->si); int idx; - if (enetc_si_vlan_promisc_is_on(pf, 0)) - enetc_disable_si_vlan_promisc(pf, 0); - __set_bit(vid, pf->active_vlans); idx = enetc_vid_hash_idx(vid); @@ -326,9 +309,6 @@ static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid) __clear_bit(vid, pf->active_vlans); enetc_sync_vlan_ht_filter(pf, true); - if (!enetc_vlan_filter_is_on(pf)) - enetc_enable_si_vlan_promisc(pf, 0); - return 0; } @@ -677,6 +657,15 @@ static int enetc_pf_set_features(struct net_device *ndev, enetc_enable_txvlan(&priv->si->hw, 0, !!(features & NETIF_F_HW_VLAN_CTAG_TX)); + if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { + struct enetc_pf *pf = enetc_si_priv(priv->si); + + if (!!(features & NETIF_F_HW_VLAN_CTAG_FILTER)) + enetc_disable_si_vlan_promisc(pf, 0); + else + enetc_enable_si_vlan_promisc(pf, 0); + } + if (changed & NETIF_F_LOOPBACK) enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK)); @@ -719,12 +708,11 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_LOOPBACK; + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK; ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_RX; if (si->num_rss) ndev->hw_features |= NETIF_F_RXHASH; diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index bd898f5b4da5..a6cdd5b61921 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -376,8 +376,7 @@ struct bufdesc_ex { #define FEC_ENET_TS_AVAIL ((uint)0x00010000) #define FEC_ENET_TS_TIMER ((uint)0x00008000) -#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII) -#define FEC_NAPI_IMASK FEC_ENET_MII +#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF) #define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF)) /* ENET interrupt coalescing macro define */ @@ -488,6 +487,12 @@ struct fec_enet_priv_rx_q { struct sk_buff *rx_skbuff[RX_RING_SIZE]; }; +struct fec_stop_mode_gpr { + struct regmap *gpr; + u8 reg; + u8 bit; +}; + /* The FEC buffer descriptors track the ring buffers. The rx_bd_base and * tx_bd_base always point to the base of the buffer descriptors. The * cur_rx and cur_tx point to the currently available buffer. @@ -537,7 +542,6 @@ struct fec_enet_private { int link; int full_duplex; int speed; - struct completion mdio_done; int irq[FEC_IRQ_NUM]; bool bufdesc_ex; int pause_flag; @@ -562,6 +566,7 @@ struct fec_enet_private { int hwts_tx_en; struct delayed_work time_keep; struct regulator *reg_phy; + struct fec_stop_mode_gpr stop_gpr; unsigned int tx_align; unsigned int rx_align; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index c1c267b61647..1ae075a246a3 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -62,6 +62,8 @@ #include <linux/if_vlan.h> #include <linux/pinctrl/consumer.h> #include <linux/prefetch.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> #include <soc/imx/cpuidle.h> #include <asm/cacheflush.h> @@ -84,6 +86,56 @@ static void fec_enet_itr_coal_init(struct net_device *ndev); #define FEC_ENET_OPD_V 0xFFF0 #define FEC_MDIO_PM_TIMEOUT 100 /* ms */ +struct fec_devinfo { + u32 quirks; + u8 stop_gpr_reg; + u8 stop_gpr_bit; +}; + +static const struct fec_devinfo fec_imx25_info = { + .quirks = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR | + FEC_QUIRK_HAS_FRREG, +}; + +static const struct fec_devinfo fec_imx27_info = { + .quirks = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG, +}; + +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, +}; + +static const struct fec_devinfo fec_imx6q_info = { + .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | + FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | + FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 | + FEC_QUIRK_HAS_RACC, + .stop_gpr_reg = 0x34, + .stop_gpr_bit = 27, +}; + +static const struct fec_devinfo fec_mvf600_info = { + .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC, +}; + +static const struct fec_devinfo fec_imx6x_info = { + .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | + FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | + FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | + FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | + FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE, +}; + +static const struct fec_devinfo fec_imx6ul_info = { + .quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | + FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | + FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 | + FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | + FEC_QUIRK_HAS_COALESCE, +}; + static struct platform_device_id fec_devtype[] = { { /* keep it for coldfire */ @@ -91,39 +143,25 @@ static struct platform_device_id fec_devtype[] = { .driver_data = 0, }, { .name = "imx25-fec", - .driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR | - FEC_QUIRK_HAS_FRREG, + .driver_data = (kernel_ulong_t)&fec_imx25_info, }, { .name = "imx27-fec", - .driver_data = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG, + .driver_data = (kernel_ulong_t)&fec_imx27_info, }, { .name = "imx28-fec", - .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME | - FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_FRREG, + .driver_data = (kernel_ulong_t)&fec_imx28_info, }, { .name = "imx6q-fec", - .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | - FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | - FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 | - FEC_QUIRK_HAS_RACC, + .driver_data = (kernel_ulong_t)&fec_imx6q_info, }, { .name = "mvf600-fec", - .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC, + .driver_data = (kernel_ulong_t)&fec_mvf600_info, }, { .name = "imx6sx-fec", - .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | - FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | - FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | - FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | - FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE, + .driver_data = (kernel_ulong_t)&fec_imx6x_info, }, { .name = "imx6ul-fec", - .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | - FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM | - FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 | - FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | - FEC_QUIRK_HAS_COALESCE, + .driver_data = (kernel_ulong_t)&fec_imx6ul_info, }, { /* sentinel */ } @@ -938,8 +976,8 @@ fec_restart(struct net_device *ndev) writel((__force u32)cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH); - /* Clear any outstanding interrupt. */ - writel(0xffffffff, fep->hwp + FEC_IEVENT); + /* Clear any outstanding interrupt, except MDIO. */ + writel((0xffffffff & ~FEC_ENET_MII), fep->hwp + FEC_IEVENT); fec_enet_bd_init(ndev); @@ -1085,18 +1123,35 @@ fec_restart(struct net_device *ndev) if (fep->link) writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); else - writel(FEC_ENET_MII, fep->hwp + FEC_IMASK); + writel(0, fep->hwp + FEC_IMASK); /* Init the interrupt coalescing */ fec_enet_itr_coal_init(ndev); } +static void fec_enet_stop_mode(struct fec_enet_private *fep, bool enabled) +{ + struct fec_platform_data *pdata = fep->pdev->dev.platform_data; + struct fec_stop_mode_gpr *stop_gpr = &fep->stop_gpr; + + if (stop_gpr->gpr) { + if (enabled) + regmap_update_bits(stop_gpr->gpr, stop_gpr->reg, + BIT(stop_gpr->bit), + BIT(stop_gpr->bit)); + else + regmap_update_bits(stop_gpr->gpr, stop_gpr->reg, + BIT(stop_gpr->bit), 0); + } else if (pdata && pdata->sleep_mode_enable) { + pdata->sleep_mode_enable(enabled); + } +} + static void fec_stop(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); - struct fec_platform_data *pdata = fep->pdev->dev.platform_data; u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8); u32 val; @@ -1125,9 +1180,7 @@ fec_stop(struct net_device *ndev) val = readl(fep->hwp + FEC_ECNTRL); val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP); writel(val, fep->hwp + FEC_ECNTRL); - - if (pdata && pdata->sleep_mode_enable) - pdata->sleep_mode_enable(true); + fec_enet_stop_mode(fep, true); } writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); @@ -1599,6 +1652,10 @@ fec_enet_interrupt(int irq, void *dev_id) irqreturn_t ret = IRQ_NONE; int_events = readl(fep->hwp + FEC_IEVENT); + + /* Don't clear MDIO events, we poll for those */ + int_events &= ~FEC_ENET_MII; + writel(int_events, fep->hwp + FEC_IEVENT); fec_enet_collect_events(fep, int_events); @@ -1606,16 +1663,12 @@ fec_enet_interrupt(int irq, void *dev_id) ret = IRQ_HANDLED; if (napi_schedule_prep(&fep->napi)) { - /* Disable the NAPI interrupts */ - writel(FEC_NAPI_IMASK, fep->hwp + FEC_IMASK); + /* Disable interrupts */ + writel(0, fep->hwp + FEC_IMASK); __napi_schedule(&fep->napi); } } - if (int_events & FEC_ENET_MII) { - ret = IRQ_HANDLED; - complete(&fep->mdio_done); - } return ret; } @@ -1765,11 +1818,24 @@ static void fec_enet_adjust_link(struct net_device *ndev) phy_print_status(phy_dev); } +static int fec_enet_mdio_wait(struct fec_enet_private *fep) +{ + uint ievent; + int ret; + + ret = readl_poll_timeout_atomic(fep->hwp + FEC_IEVENT, ievent, + ievent & FEC_ENET_MII, 2, 30000); + + if (!ret) + writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT); + + return ret; +} + static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) { struct fec_enet_private *fep = bus->priv; struct device *dev = &fep->pdev->dev; - unsigned long time_left; int ret = 0, frame_start, frame_addr, frame_op; bool is_c45 = !!(regnum & MII_ADDR_C45); @@ -1777,8 +1843,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) if (ret < 0) return ret; - reinit_completion(&fep->mdio_done); - if (is_c45) { frame_start = FEC_MMFR_ST_C45; @@ -1790,11 +1854,9 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ - time_left = wait_for_completion_timeout(&fep->mdio_done, - usecs_to_jiffies(FEC_MII_TIMEOUT)); - if (time_left == 0) { + ret = fec_enet_mdio_wait(fep); + if (ret) { netdev_err(fep->netdev, "MDIO address write timeout\n"); - ret = -ETIMEDOUT; goto out; } @@ -1813,11 +1875,9 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) FEC_MMFR_TA, fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ - time_left = wait_for_completion_timeout(&fep->mdio_done, - usecs_to_jiffies(FEC_MII_TIMEOUT)); - if (time_left == 0) { + ret = fec_enet_mdio_wait(fep); + if (ret) { netdev_err(fep->netdev, "MDIO read timeout\n"); - ret = -ETIMEDOUT; goto out; } @@ -1835,7 +1895,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, { struct fec_enet_private *fep = bus->priv; struct device *dev = &fep->pdev->dev; - unsigned long time_left; int ret, frame_start, frame_addr; bool is_c45 = !!(regnum & MII_ADDR_C45); @@ -1845,8 +1904,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, else ret = 0; - reinit_completion(&fep->mdio_done); - if (is_c45) { frame_start = FEC_MMFR_ST_C45; @@ -1858,11 +1915,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ - time_left = wait_for_completion_timeout(&fep->mdio_done, - usecs_to_jiffies(FEC_MII_TIMEOUT)); - if (time_left == 0) { + ret = fec_enet_mdio_wait(fep); + if (ret) { netdev_err(fep->netdev, "MDIO address write timeout\n"); - ret = -ETIMEDOUT; goto out; } } else { @@ -1878,12 +1933,9 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ - time_left = wait_for_completion_timeout(&fep->mdio_done, - usecs_to_jiffies(FEC_MII_TIMEOUT)); - if (time_left == 0) { + ret = fec_enet_mdio_wait(fep); + if (ret) netdev_err(fep->netdev, "MDIO write timeout\n"); - ret = -ETIMEDOUT; - } out: pm_runtime_mark_last_busy(dev); @@ -2012,9 +2064,11 @@ static int fec_enet_mii_init(struct platform_device *pdev) static struct mii_bus *fec0_mii_bus; struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + bool suppress_preamble = false; struct device_node *node; int err = -ENXIO; u32 mii_speed, holdtime; + u32 bus_freq; /* * The i.MX28 dual fec interfaces are not equal. @@ -2042,15 +2096,23 @@ static int fec_enet_mii_init(struct platform_device *pdev) return -ENOENT; } + bus_freq = 2500000; /* 2.5MHz by default */ + node = of_get_child_by_name(pdev->dev.of_node, "mdio"); + if (node) { + of_property_read_u32(node, "clock-frequency", &bus_freq); + suppress_preamble = of_property_read_bool(node, + "suppress-preamble"); + } + /* - * Set MII speed to 2.5 MHz (= clk_get_rate() / 2 * phy_speed) + * Set MII speed (= clk_get_rate() / 2 * phy_speed) * * The formula for FEC MDC is 'ref_freq / (MII_SPEED x 2)' while * for ENET-MAC is 'ref_freq / ((MII_SPEED + 1) x 2)'. The i.MX28 * Reference Manual has an error on this, and gets fixed on i.MX6Q * document. */ - mii_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 5000000); + mii_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), bus_freq * 2); if (fep->quirks & FEC_QUIRK_ENET_MAC) mii_speed--; if (mii_speed > 63) { @@ -2077,8 +2139,14 @@ static int fec_enet_mii_init(struct platform_device *pdev) fep->phy_speed = mii_speed << 1 | holdtime << 8; + if (suppress_preamble) + fep->phy_speed |= BIT(7); + writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); + /* Clear any pending transaction complete indication */ + writel(FEC_ENET_MII, fep->hwp + FEC_IEVENT); + fep->mii_bus = mdiobus_alloc(); if (fep->mii_bus == NULL) { err = -ENOMEM; @@ -2093,7 +2161,6 @@ static int fec_enet_mii_init(struct platform_device *pdev) fep->mii_bus->priv = fep; fep->mii_bus->parent = &pdev->dev; - node = of_get_child_by_name(pdev->dev.of_node, "mdio"); err = of_mdiobus_register(fep->mii_bus, node); of_node_put(node); if (err) @@ -3398,6 +3465,37 @@ static int fec_enet_get_irq_cnt(struct platform_device *pdev) return irq_cnt; } +static int fec_enet_init_stop_mode(struct fec_enet_private *fep, + struct fec_devinfo *dev_info, + struct device_node *np) +{ + struct device_node *gpr_np; + int ret = 0; + + if (!dev_info) + return 0; + + gpr_np = of_parse_phandle(np, "gpr", 0); + if (!gpr_np) + return 0; + + fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np); + if (IS_ERR(fep->stop_gpr.gpr)) { + dev_err(&fep->pdev->dev, "could not find gpr regmap\n"); + ret = PTR_ERR(fep->stop_gpr.gpr); + fep->stop_gpr.gpr = NULL; + goto out; + } + + fep->stop_gpr.reg = dev_info->stop_gpr_reg; + fep->stop_gpr.bit = dev_info->stop_gpr_bit; + +out: + of_node_put(gpr_np); + + return ret; +} + static int fec_probe(struct platform_device *pdev) { @@ -3413,6 +3511,7 @@ fec_probe(struct platform_device *pdev) int num_rx_qs; char irq_name[8]; int irq_cnt; + struct fec_devinfo *dev_info; fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs); @@ -3430,7 +3529,9 @@ fec_probe(struct platform_device *pdev) of_id = of_match_device(fec_dt_ids, &pdev->dev); if (of_id) pdev->id_entry = of_id->data; - fep->quirks = pdev->id_entry->driver_data; + dev_info = (struct fec_devinfo *)pdev->id_entry->driver_data; + if (dev_info) + fep->quirks = dev_info->quirks; fep->netdev = ndev; fep->num_rx_queues = num_rx_qs; @@ -3464,6 +3565,10 @@ fec_probe(struct platform_device *pdev) if (of_get_property(np, "fsl,magic-packet", NULL)) fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET; + ret = fec_enet_init_stop_mode(fep, dev_info, np); + if (ret) + goto failed_stop_mode; + phy_node = of_parse_phandle(np, "phy-handle", 0); if (!phy_node && of_phy_is_fixed_link(np)) { ret = of_phy_register_fixed_link(np); @@ -3583,7 +3688,6 @@ fec_probe(struct platform_device *pdev) fep->irq[i] = irq; } - init_completion(&fep->mdio_done); ret = fec_enet_mii_init(pdev); if (ret) goto failed_mii_init; @@ -3632,6 +3736,7 @@ failed_clk: if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(phy_node); +failed_stop_mode: failed_phy: dev_id--; failed_ioremap: @@ -3709,7 +3814,6 @@ static int __maybe_unused fec_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); - struct fec_platform_data *pdata = fep->pdev->dev.platform_data; int ret; int val; @@ -3727,8 +3831,8 @@ static int __maybe_unused fec_resume(struct device *dev) goto failed_clk; } if (fep->wol_flag & FEC_WOL_FLAG_ENABLE) { - if (pdata && pdata->sleep_mode_enable) - pdata->sleep_mode_enable(false); + fec_enet_stop_mode(fep, false); + val = readl(fep->hwp + FEC_ECNTRL); val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP); writel(val, fep->hwp + FEC_ECNTRL); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 8aace2de0cc9..9a907947ba19 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -697,9 +697,9 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb, return rc; if (!strcmp(phy_type, phy_modes(PHY_INTERFACE_MODE_XGMII))) - is_c45 = 1; + is_c45 = true; else if (!strcmp(phy_type, phy_modes(PHY_INTERFACE_MODE_SGMII))) - is_c45 = 0; + is_c45 = false; else return -ENODATA; diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 948e67ef30fd..21a736174fda 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -45,6 +45,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_PUSH_PROMISC_INFO, /* (PF -> VF) push vf promisc info */ HCLGE_MBX_VF_UNINIT, /* (VF -> PF) vf is unintializing */ + HCLGE_MBX_HANDLE_VF_TBL, /* (VF -> PF) store/clear hw table */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf flr status */ HCLGE_MBX_PUSH_LINK_STATUS, /* (M7 -> PF) get port link status */ @@ -70,6 +71,10 @@ enum hclge_mbx_vlan_cfg_subcode { HCLGE_MBX_GET_PORT_BASE_VLAN_STATE, /* get port based vlan state */ }; +enum hclge_mbx_tbl_cfg_subcode { + HCLGE_MBX_VPORT_LIST_CLEAR, +}; + #define HCLGE_MBX_MAX_MSG_SIZE 14 #define HCLGE_MBX_MAX_RESP_DATA_SIZE 8U #define HCLGE_MBX_MAX_RING_CHAIN_PARAM_NUM 4 diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 5587605d6deb..6291aa9f06b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -233,7 +233,6 @@ struct hnae3_ae_dev { struct list_head node; u32 flag; unsigned long hw_err_reset_req; - enum hnae3_reset_type reset_type; void *priv; }; @@ -270,6 +269,8 @@ struct hnae3_ae_dev { * Set loopback * set_promisc_mode * Set promisc mode + * request_update_promisc_mode + * request to hclge(vf) to update promisc mode * set_mtu() * set mtu * get_pauseparam() @@ -354,8 +355,6 @@ struct hnae3_ae_dev { * Set vlan filter config of Ports * set_vf_vlan_filter() * Set vlan filter config of vf - * restore_vlan_table() - * Restore vlan filter entries after reset * enable_hw_strip_rxvtag() * Enable/disable hardware strip vlan tag of packets received * set_gro_en @@ -408,6 +407,7 @@ struct hnae3_ae_ops { int (*set_promisc_mode)(struct hnae3_handle *handle, bool en_uc_pmc, bool en_mc_pmc); + void (*request_update_promisc_mode)(struct hnae3_handle *handle); int (*set_mtu)(struct hnae3_handle *handle, int new_mtu); void (*get_pauseparam)(struct hnae3_handle *handle, @@ -525,7 +525,6 @@ struct hnae3_ae_ops { struct ethtool_rxnfc *cmd); int (*get_fd_all_rules)(struct hnae3_handle *handle, struct ethtool_rxnfc *cmd, u32 *rule_locs); - int (*restore_fd_rules)(struct hnae3_handle *handle); void (*enable_fd)(struct hnae3_handle *handle, bool enable); int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id, u16 flow_id, struct flow_keys *fkeys); @@ -539,7 +538,6 @@ struct hnae3_ae_ops { void (*set_timer_task)(struct hnae3_handle *handle, bool enable); int (*mac_connect_phy)(struct hnae3_handle *handle); void (*mac_disconnect_phy)(struct hnae3_handle *handle); - void (*restore_vlan_table)(struct hnae3_handle *handle); int (*get_vf_config)(struct hnae3_handle *handle, int vf, struct ifla_vf_info *ivf); int (*set_vf_link_state)(struct hnae3_handle *handle, int vf, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index e1d88095a77e..fe7fb565da19 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -262,6 +262,8 @@ static void hns3_dbg_help(struct hnae3_handle *h) dev_info(&h->pdev->dev, "dump mac tnl status\n"); dev_info(&h->pdev->dev, "dump loopback\n"); dev_info(&h->pdev->dev, "dump qs shaper [qs id]\n"); + dev_info(&h->pdev->dev, "dump uc mac list <func id>\n"); + dev_info(&h->pdev->dev, "dump mc mac list <func id>\n"); memset(printf_buf, 0, HNS3_DBG_BUF_LEN); strncat(printf_buf, "dump reg [[bios common] [ssu <port_id>]", @@ -270,7 +272,7 @@ static void hns3_dbg_help(struct hnae3_handle *h) " [igu egu <port_id>] [rpu <tc_queue_num>]", HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); strncat(printf_buf + strlen(printf_buf), - " [rtc] [ppp] [rcb] [tqp <queue_num>]]\n", + " [rtc] [ppp] [rcb] [tqp <queue_num>] [mac]]\n", HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); dev_info(&h->pdev->dev, "%s", printf_buf); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index da98fd7c8eca..c79d6a391105 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -15,7 +15,6 @@ #include <linux/aer.h> #include <linux/skbuff.h> #include <linux/sctp.h> -#include <linux/vermagic.h> #include <net/gre.h> #include <net/ip6_checksum.h> #include <net/pkt_cls.h> @@ -41,10 +40,8 @@ } while (0) static void hns3_clear_all_ring(struct hnae3_handle *h, bool force); -static void hns3_remove_hw_addr(struct net_device *netdev); static const char hns3_driver_name[] = "hns3"; -const char hns3_driver_version[] = VERMAGIC_STRING; static const char hns3_driver_string[] = "Hisilicon Ethernet Network Driver for Hip08 Family"; static const char hns3_copyright[] = "Copyright (c) 2017 Huawei Corporation."; @@ -550,6 +547,13 @@ static int hns3_nic_uc_unsync(struct net_device *netdev, { struct hnae3_handle *h = hns3_get_handle(netdev); + /* need ignore the request of removing device address, because + * we store the device address and other addresses of uc list + * in the function's mac filter list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + if (h->ae_algo->ops->rm_uc_addr) return h->ae_algo->ops->rm_uc_addr(h, addr); @@ -597,34 +601,25 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev) { struct hnae3_handle *h = hns3_get_handle(netdev); u8 new_flags; - int ret; new_flags = hns3_get_netdev_flags(netdev); - ret = __dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync); - if (ret) { - netdev_err(netdev, "sync uc address fail\n"); - if (ret == -ENOSPC) - new_flags |= HNAE3_OVERFLOW_UPE; - } - - if (netdev->flags & IFF_MULTICAST) { - ret = __dev_mc_sync(netdev, hns3_nic_mc_sync, - hns3_nic_mc_unsync); - if (ret) { - netdev_err(netdev, "sync mc address fail\n"); - if (ret == -ENOSPC) - new_flags |= HNAE3_OVERFLOW_MPE; - } - } + __dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync); + __dev_mc_sync(netdev, hns3_nic_mc_sync, hns3_nic_mc_unsync); /* User mode Promisc mode enable and vlan filtering is disabled to - * let all packets in. MAC-VLAN Table overflow Promisc enabled and - * vlan fitering is enabled + * let all packets in. */ - hns3_enable_vlan_filter(netdev, new_flags & HNAE3_VLAN_FLTR); h->netdev_flags = new_flags; - hns3_update_promisc_mode(netdev, new_flags); + hns3_request_update_promisc_mode(h); +} + +void hns3_request_update_promisc_mode(struct hnae3_handle *handle) +{ + const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + + if (ops->request_update_promisc_mode) + ops->request_update_promisc_mode(handle); } int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags) @@ -2107,7 +2102,6 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ae_dev->pdev = pdev; ae_dev->flag = ent->driver_data; - ae_dev->reset_type = HNAE3_NONE_RESET; hns3_get_dev_capability(pdev, ae_dev); pci_set_drvdata(pdev, ae_dev); @@ -3909,9 +3903,11 @@ static int hns3_init_mac_addr(struct net_device *netdev) eth_hw_addr_random(netdev); dev_warn(priv->dev, "using random MAC address %pM\n", netdev->dev_addr); - } else { + } else if (!ether_addr_equal(netdev->dev_addr, mac_addr_temp)) { ether_addr_copy(netdev->dev_addr, mac_addr_temp); ether_addr_copy(netdev->perm_addr, mac_addr_temp); + } else { + return 0; } if (h->ae_algo->ops->set_mac_addr) @@ -3939,17 +3935,6 @@ static void hns3_uninit_phy(struct net_device *netdev) h->ae_algo->ops->mac_disconnect_phy(h); } -static int hns3_restore_fd_rules(struct net_device *netdev) -{ - struct hnae3_handle *h = hns3_get_handle(netdev); - int ret = 0; - - if (h->ae_algo->ops->restore_fd_rules) - ret = h->ae_algo->ops->restore_fd_rules(h); - - return ret; -} - static void hns3_del_all_fd_rules(struct net_device *netdev, bool clear_list) { struct hnae3_handle *h = hns3_get_handle(netdev); @@ -4121,8 +4106,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) struct hns3_nic_priv *priv = netdev_priv(netdev); int ret; - hns3_remove_hw_addr(netdev); - if (netdev->reg_state != NETREG_UNINITIALIZED) unregister_netdev(netdev); @@ -4193,56 +4176,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc) return hns3_nic_set_real_num_queue(ndev); } -static int hns3_recover_hw_addr(struct net_device *ndev) -{ - struct netdev_hw_addr_list *list; - struct netdev_hw_addr *ha, *tmp; - int ret = 0; - - netif_addr_lock_bh(ndev); - /* go through and sync uc_addr entries to the device */ - list = &ndev->uc; - list_for_each_entry_safe(ha, tmp, &list->list, list) { - ret = hns3_nic_uc_sync(ndev, ha->addr); - if (ret) - goto out; - } - - /* go through and sync mc_addr entries to the device */ - list = &ndev->mc; - list_for_each_entry_safe(ha, tmp, &list->list, list) { - ret = hns3_nic_mc_sync(ndev, ha->addr); - if (ret) - goto out; - } - -out: - netif_addr_unlock_bh(ndev); - return ret; -} - -static void hns3_remove_hw_addr(struct net_device *netdev) -{ - struct netdev_hw_addr_list *list; - struct netdev_hw_addr *ha, *tmp; - - hns3_nic_uc_unsync(netdev, netdev->dev_addr); - - netif_addr_lock_bh(netdev); - /* go through and unsync uc_addr entries to the device */ - list = &netdev->uc; - list_for_each_entry_safe(ha, tmp, &list->list, list) - hns3_nic_uc_unsync(netdev, ha->addr); - - /* go through and unsync mc_addr entries to the device */ - list = &netdev->mc; - list_for_each_entry_safe(ha, tmp, &list->list, list) - if (ha->refcount > 1) - hns3_nic_mc_unsync(netdev, ha->addr); - - netif_addr_unlock_bh(netdev); -} - static void hns3_clear_tx_ring(struct hns3_enet_ring *ring) { while (ring->next_to_clean != ring->next_to_use) { @@ -4401,7 +4334,6 @@ static void hns3_restore_coal(struct hns3_nic_priv *priv) static int hns3_reset_notify_down_enet(struct hnae3_handle *handle) { - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev); struct hnae3_knic_private_info *kinfo = &handle->kinfo; struct net_device *ndev = kinfo->netdev; struct hns3_nic_priv *priv = netdev_priv(ndev); @@ -4409,15 +4341,6 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle) if (test_and_set_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) return 0; - /* it is cumbersome for hardware to pick-and-choose entries for deletion - * from table space. Hence, for function reset software intervention is - * required to delete the entries - */ - if (hns3_dev_ongoing_func_reset(ae_dev)) { - hns3_remove_hw_addr(ndev); - hns3_del_all_fd_rules(ndev, false); - } - if (!netif_running(ndev)) return 0; @@ -4484,6 +4407,9 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) goto err_init_irq_fail; } + if (!hns3_is_phys_func(handle->pdev)) + hns3_init_mac_addr(netdev); + ret = hns3_client_start(handle); if (ret) { dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret); @@ -4509,33 +4435,6 @@ err_put_ring: return ret; } -static int hns3_reset_notify_restore_enet(struct hnae3_handle *handle) -{ - struct net_device *netdev = handle->kinfo.netdev; - bool vlan_filter_enable; - int ret; - - ret = hns3_init_mac_addr(netdev); - if (ret) - return ret; - - ret = hns3_recover_hw_addr(netdev); - if (ret) - return ret; - - ret = hns3_update_promisc_mode(netdev, handle->netdev_flags); - if (ret) - return ret; - - vlan_filter_enable = netdev->flags & IFF_PROMISC ? false : true; - hns3_enable_vlan_filter(netdev, vlan_filter_enable); - - if (handle->ae_algo->ops->restore_vlan_table) - handle->ae_algo->ops->restore_vlan_table(handle); - - return hns3_restore_fd_rules(netdev); -} - static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) { struct net_device *netdev = handle->kinfo.netdev; @@ -4585,9 +4484,6 @@ static int hns3_reset_notify(struct hnae3_handle *handle, case HNAE3_UNINIT_CLIENT: ret = hns3_reset_notify_uninit_enet(handle); break; - case HNAE3_RESTORE_CLIENT: - ret = hns3_reset_notify_restore_enet(handle); - break; default: break; } @@ -4765,4 +4661,3 @@ MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet Driver"); MODULE_AUTHOR("Huawei Tech. Co., Ltd."); MODULE_LICENSE("GPL"); MODULE_ALIAS("pci:hns-nic"); -MODULE_VERSION(HNS3_MOD_VERSION); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index abefd7a179f7..240ba06cd0eb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -8,10 +8,6 @@ #include "hnae3.h" -#define HNS3_MOD_VERSION "1.0" - -extern const char hns3_driver_version[]; - enum hns3_nic_state { HNS3_NIC_STATE_TESTING, HNS3_NIC_STATE_RESETTING, @@ -580,15 +576,6 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) writel(value, reg_addr + reg); } -static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev) -{ - return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET || - ae_dev->reset_type == HNAE3_FLR_RESET || - ae_dev->reset_type == HNAE3_VF_FUNC_RESET || - ae_dev->reset_type == HNAE3_VF_FULL_RESET || - ae_dev->reset_type == HNAE3_VF_PF_FUNC_RESET)); -} - #define hns3_read_dev(a, reg) \ hns3_read_reg((a)->io_base, (reg)) @@ -662,6 +649,7 @@ void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector, void hns3_enable_vlan_filter(struct net_device *netdev, bool enable); int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags); +void hns3_request_update_promisc_mode(struct hnae3_handle *handle); #ifdef CONFIG_HNS3_DCB void hns3_dcbnl_setup(struct hnae3_handle *handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 28b81f24afa1..4d9c85f049dc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -99,7 +99,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) h->ae_algo->ops->set_promisc_mode(h, true, true); } else { /* recover promisc mode before loopback test */ - hns3_update_promisc_mode(ndev, h->netdev_flags); + hns3_request_update_promisc_mode(h); vlan_filter_enable = ndev->flags & IFF_PROMISC ? false : true; hns3_enable_vlan_filter(ndev, vlan_filter_enable); } @@ -546,10 +546,6 @@ static void hns3_get_drvinfo(struct net_device *netdev, return; } - strncpy(drvinfo->version, hns3_driver_version, - sizeof(drvinfo->version)); - drvinfo->version[sizeof(drvinfo->version) - 1] = '\0'; - strncpy(drvinfo->driver, h->pdev->driver->name, sizeof(drvinfo->driver)); drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile index 0fb61d440d3b..6c28c8f6292c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -4,6 +4,7 @@ # ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 +ccflags-y += -I $(srctree)/$(src) obj-$(CONFIG_HNS3_HCLGE) += hclge.o hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 96498d9b4754..90e422efe590 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -733,31 +733,6 @@ struct hclge_mac_mgr_tbl_entry_cmd { u8 rsv3[2]; }; -struct hclge_mac_vlan_add_cmd { - __le16 flags; - __le16 mac_addr_hi16; - __le32 mac_addr_lo32; - __le32 mac_addr_msk_hi32; - __le16 mac_addr_msk_lo16; - __le16 vlan_tag; - __le16 ingress_port; - __le16 egress_port; - u8 rsv[4]; -}; - -#define HNS3_MAC_VLAN_CFG_FLAG_BIT 0 -struct hclge_mac_vlan_remove_cmd { - __le16 flags; - __le16 mac_addr_hi16; - __le32 mac_addr_lo32; - __le32 mac_addr_msk_hi32; - __le16 mac_addr_msk_lo16; - __le16 vlan_tag; - __le16 ingress_port; - __le16 egress_port; - u8 rsv[4]; -}; - struct hclge_vlan_filter_ctrl_cmd { u8 vlan_type; u8 vlan_fe; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 17228288d4df..6cfa8253eefc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -143,7 +143,7 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev, return; } - buf_len = sizeof(struct hclge_desc) * bd_num; + buf_len = sizeof(struct hclge_desc) * bd_num; desc_src = kzalloc(buf_len, GFP_KERNEL); if (!desc_src) return; @@ -173,6 +173,114 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev, kfree(desc_src); } +static void hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev) +{ + struct hclge_config_mac_mode_cmd *req; + struct hclge_desc desc; + u32 loop_en; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump mac enable status, ret = %d\n", ret); + return; + } + + req = (struct hclge_config_mac_mode_cmd *)desc.data; + loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en); + + dev_info(&hdev->pdev->dev, "config_mac_trans_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_TX_EN_B)); + dev_info(&hdev->pdev->dev, "config_mac_rcv_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_EN_B)); + dev_info(&hdev->pdev->dev, "config_pad_trans_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_PAD_TX_B)); + dev_info(&hdev->pdev->dev, "config_pad_rcv_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_PAD_RX_B)); + dev_info(&hdev->pdev->dev, "config_1588_trans_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_1588_TX_B)); + dev_info(&hdev->pdev->dev, "config_1588_rcv_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_1588_RX_B)); + dev_info(&hdev->pdev->dev, "config_mac_app_loop_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_APP_LP_B)); + dev_info(&hdev->pdev->dev, "config_mac_line_loop_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_LINE_LP_B)); + dev_info(&hdev->pdev->dev, "config_mac_fcs_tx_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_FCS_TX_B)); + dev_info(&hdev->pdev->dev, "config_mac_rx_oversize_truncate_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B)); + dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_strip_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B)); + dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_B)); + dev_info(&hdev->pdev->dev, "config_mac_tx_under_min_err_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B)); + dev_info(&hdev->pdev->dev, "config_mac_tx_oversize_truncate_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B)); +} + +static void hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev) +{ + struct hclge_config_max_frm_size_cmd *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, true); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump mac frame size, ret = %d\n", ret); + return; + } + + req = (struct hclge_config_max_frm_size_cmd *)desc.data; + + dev_info(&hdev->pdev->dev, "max_frame_size: %u\n", + le16_to_cpu(req->max_frm_size)); + dev_info(&hdev->pdev->dev, "min_frame_size: %u\n", req->min_frm_size); +} + +static void hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev) +{ +#define HCLGE_MAC_SPEED_SHIFT 0 +#define HCLGE_MAC_SPEED_MASK GENMASK(5, 0) +#define HCLGE_MAC_DUPLEX_SHIFT 7 + + struct hclge_config_mac_speed_dup_cmd *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, true); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump mac speed duplex, ret = %d\n", ret); + return; + } + + req = (struct hclge_config_mac_speed_dup_cmd *)desc.data; + + dev_info(&hdev->pdev->dev, "speed: %#lx\n", + hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK, + HCLGE_MAC_SPEED_SHIFT)); + dev_info(&hdev->pdev->dev, "duplex: %#x\n", + hnae3_get_bit(req->speed_dup, HCLGE_MAC_DUPLEX_SHIFT)); +} + +static void hclge_dbg_dump_mac(struct hclge_dev *hdev) +{ + hclge_dbg_dump_mac_enable_status(hdev); + + hclge_dbg_dump_mac_frame_size(hdev); + + hclge_dbg_dump_mac_speed_duplex(hdev); +} + static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, const char *cmd_buf) { struct device *dev = &hdev->pdev->dev; @@ -304,6 +412,11 @@ static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf) } } + if (strncmp(cmd_buf, "mac", strlen("mac")) == 0) { + hclge_dbg_dump_mac(hdev); + has_dump = true; + } + if (strncmp(cmd_buf, "dcb", 3) == 0) { hclge_dbg_dump_dcb(hdev, &cmd_buf[sizeof("dcb")]); has_dump = true; @@ -1328,6 +1441,49 @@ static void hclge_dbg_dump_qs_shaper(struct hclge_dev *hdev, hclge_dbg_dump_qs_shaper_single(hdev, qsid); } +static int hclge_dbg_dump_mac_list(struct hclge_dev *hdev, const char *cmd_buf, + bool is_unicast) +{ + struct hclge_mac_node *mac_node, *tmp; + struct hclge_vport *vport; + struct list_head *list; + u32 func_id; + int ret; + + ret = kstrtouint(cmd_buf, 0, &func_id); + if (ret < 0) { + dev_err(&hdev->pdev->dev, + "dump mac list: bad command string, ret = %d\n", ret); + return -EINVAL; + } + + if (func_id >= hdev->num_alloc_vport) { + dev_err(&hdev->pdev->dev, + "function id(%u) is out of range(0-%u)\n", func_id, + hdev->num_alloc_vport - 1); + return -EINVAL; + } + + vport = &hdev->vport[func_id]; + + list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list; + + dev_info(&hdev->pdev->dev, "vport %u %s mac list:\n", + func_id, is_unicast ? "uc" : "mc"); + dev_info(&hdev->pdev->dev, "mac address state\n"); + + spin_lock_bh(&vport->mac_list_lock); + + list_for_each_entry_safe(mac_node, tmp, list, node) { + dev_info(&hdev->pdev->dev, "%pM %d\n", + mac_node->mac_addr, mac_node->state); + } + + spin_unlock_bh(&vport->mac_list_lock); + + return 0; +} + int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) { #define DUMP_REG "dump reg" @@ -1372,6 +1528,14 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) } else if (strncmp(cmd_buf, "dump qs shaper", 14) == 0) { hclge_dbg_dump_qs_shaper(hdev, &cmd_buf[sizeof("dump qs shaper")]); + } else if (strncmp(cmd_buf, "dump uc mac list", 16) == 0) { + hclge_dbg_dump_mac_list(hdev, + &cmd_buf[sizeof("dump uc mac list")], + true); + } else if (strncmp(cmd_buf, "dump mc mac list", 16) == 0) { + hclge_dbg_dump_mac_list(hdev, + &cmd_buf[sizeof("dump mc mac list")], + false); } else { dev_info(&hdev->pdev->dev, "unknown command\n"); 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 a758f9ae32be..e2fec832fdf0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -62,14 +62,16 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev); static void hclge_sync_vlan_filter(struct hclge_dev *hdev); static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev); static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle); -static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, - u16 *allocated_size, bool is_alloc); static void hclge_rfs_filter_expire(struct hclge_dev *hdev); static void hclge_clear_arfs_rules(struct hnae3_handle *handle); static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev, unsigned long *addr); static int hclge_set_default_loopback(struct hclge_dev *hdev); +static void hclge_sync_mac_table(struct hclge_dev *hdev); +static void hclge_restore_hw_table(struct hclge_dev *hdev); +static void hclge_sync_promisc_mode(struct hclge_dev *hdev); + static struct hnae3_ae_algo ae_algo; static struct workqueue_struct *hclge_wq; @@ -1687,6 +1689,7 @@ static int hclge_alloc_vport(struct hclge_dev *hdev) INIT_LIST_HEAD(&vport->vlan_list); INIT_LIST_HEAD(&vport->uc_mac_list); INIT_LIST_HEAD(&vport->mc_mac_list); + spin_lock_init(&vport->mac_list_lock); if (i == 0) ret = hclge_vport_setup(vport, tqp_main_vport); @@ -3729,22 +3732,13 @@ static int hclge_reset_stack(struct hclge_dev *hdev) if (ret) return ret; - ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT); - if (ret) - return ret; - - return hclge_notify_client(hdev, HNAE3_RESTORE_CLIENT); + return hclge_notify_client(hdev, HNAE3_INIT_CLIENT); } static int hclge_reset_prepare(struct hclge_dev *hdev) { - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); int ret; - /* Initialize ae_dev reset status as well, in case enet layer wants to - * know if device is undergoing reset - */ - ae_dev->reset_type = hdev->reset_type; hdev->rst_stats.reset_cnt++; /* perform reset of the stack & ae device for a client */ ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT); @@ -3806,7 +3800,6 @@ static int hclge_reset_rebuild(struct hclge_dev *hdev) hdev->last_reset_time = jiffies; hdev->rst_stats.reset_fail_cnt = 0; hdev->rst_stats.reset_done_cnt++; - ae_dev->reset_type = HNAE3_NONE_RESET; clear_bit(HCLGE_STATE_RST_FAIL, &hdev->state); /* if default_reset_request has a higher level reset request, @@ -3973,6 +3966,8 @@ static void hclge_periodic_service_task(struct hclge_dev *hdev) * updated when it is triggered by mbx. */ hclge_update_link_status(hdev); + hclge_sync_mac_table(hdev); + hclge_sync_promisc_mode(hdev); if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) { delta = jiffies - hdev->last_serv_processed; @@ -4722,7 +4717,8 @@ static int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) dev_err(&hdev->pdev->dev, - "Set promisc mode fail, status is %d.\n", ret); + "failed to set vport %d promisc mode, ret = %d.\n", + param->vf_id, ret); return ret; } @@ -4772,6 +4768,14 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, en_bc_pmc); } +static void hclge_request_update_promisc_mode(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); +} + static int hclge_get_fd_mode(struct hclge_dev *hdev, u8 *fd_mode) { struct hclge_get_fd_mode_cmd *req; @@ -4822,7 +4826,8 @@ static int hclge_get_fd_allocation(struct hclge_dev *hdev, return ret; } -static int hclge_set_fd_key_config(struct hclge_dev *hdev, int stage_num) +static int hclge_set_fd_key_config(struct hclge_dev *hdev, + enum HCLGE_FD_STAGE stage_num) { struct hclge_set_fd_key_config_cmd *req; struct hclge_fd_key_cfg *stage; @@ -4876,9 +4881,6 @@ static int hclge_init_fd_config(struct hclge_dev *hdev) return -EOPNOTSUPP; } - hdev->fd_cfg.proto_support = - TCP_V4_FLOW | UDP_V4_FLOW | SCTP_V4_FLOW | TCP_V6_FLOW | - UDP_V6_FLOW | SCTP_V6_FLOW | IPV4_USER_FLOW | IPV6_USER_FLOW; key_cfg = &hdev->fd_cfg.key_cfg[HCLGE_FD_STAGE_1]; key_cfg->key_sel = HCLGE_FD_KEY_BASE_ON_TUPLE, key_cfg->inner_sipv6_word_en = LOW_2_WORDS; @@ -4892,11 +4894,9 @@ static int hclge_init_fd_config(struct hclge_dev *hdev) BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT); /* If use max 400bit key, we can support tuples for ether type */ - if (hdev->fd_cfg.max_key_length == MAX_KEY_LENGTH) { - hdev->fd_cfg.proto_support |= ETHER_FLOW; + if (hdev->fd_cfg.fd_mode == HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1) key_cfg->tuple_active |= BIT(INNER_DST_MAC) | BIT(INNER_SRC_MAC); - } /* roce_type is used to filter roce frames * dst_vport is used to specify the rule @@ -5006,8 +5006,6 @@ static bool hclge_fd_convert_tuple(u32 tuple_bit, u8 *key_x, u8 *key_y, return true; switch (tuple_bit) { - case 0: - return false; case BIT(INNER_DST_MAC): for (i = 0; i < ETH_ALEN; i++) { calc_x(key_x[ETH_ALEN - 1 - i], rule->tuples.dst_mac[i], @@ -5165,9 +5163,10 @@ static int hclge_config_key(struct hclge_dev *hdev, u8 stage, struct hclge_fd_key_cfg *key_cfg = &hdev->fd_cfg.key_cfg[stage]; u8 key_x[MAX_KEY_BYTES], key_y[MAX_KEY_BYTES]; u8 *cur_key_x, *cur_key_y; - unsigned int i; - int ret, tuple_size; u8 meta_data_region; + u8 tuple_size; + int ret; + u32 i; memset(key_x, 0, sizeof(key_x)); memset(key_y, 0, sizeof(key_y)); @@ -5244,172 +5243,255 @@ static int hclge_config_action(struct hclge_dev *hdev, u8 stage, return hclge_fd_ad_config(hdev, stage, ad_data.ad_id, &ad_data); } -static int hclge_fd_check_spec(struct hclge_dev *hdev, - struct ethtool_rx_flow_spec *fs, u32 *unused) +static int hclge_fd_check_tcpip4_tuple(struct ethtool_tcpip4_spec *spec, + u32 *unused_tuple) { - struct ethtool_tcpip4_spec *tcp_ip4_spec; - struct ethtool_usrip4_spec *usr_ip4_spec; - struct ethtool_tcpip6_spec *tcp_ip6_spec; - struct ethtool_usrip6_spec *usr_ip6_spec; - struct ethhdr *ether_spec; - - if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) + if (!spec || !unused_tuple) return -EINVAL; - if (!(fs->flow_type & hdev->fd_cfg.proto_support)) - return -EOPNOTSUPP; - - if ((fs->flow_type & FLOW_EXT) && - (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) { - dev_err(&hdev->pdev->dev, "user-def bytes are not supported\n"); - return -EOPNOTSUPP; - } + *unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC); - switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { - case SCTP_V4_FLOW: - case TCP_V4_FLOW: - case UDP_V4_FLOW: - tcp_ip4_spec = &fs->h_u.tcp_ip4_spec; - *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC); + if (!spec->ip4src) + *unused_tuple |= BIT(INNER_SRC_IP); - if (!tcp_ip4_spec->ip4src) - *unused |= BIT(INNER_SRC_IP); + if (!spec->ip4dst) + *unused_tuple |= BIT(INNER_DST_IP); - if (!tcp_ip4_spec->ip4dst) - *unused |= BIT(INNER_DST_IP); + if (!spec->psrc) + *unused_tuple |= BIT(INNER_SRC_PORT); - if (!tcp_ip4_spec->psrc) - *unused |= BIT(INNER_SRC_PORT); + if (!spec->pdst) + *unused_tuple |= BIT(INNER_DST_PORT); - if (!tcp_ip4_spec->pdst) - *unused |= BIT(INNER_DST_PORT); + if (!spec->tos) + *unused_tuple |= BIT(INNER_IP_TOS); - if (!tcp_ip4_spec->tos) - *unused |= BIT(INNER_IP_TOS); + return 0; +} - break; - case IP_USER_FLOW: - usr_ip4_spec = &fs->h_u.usr_ip4_spec; - *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | - BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT); +static int hclge_fd_check_ip4_tuple(struct ethtool_usrip4_spec *spec, + u32 *unused_tuple) +{ + if (!spec || !unused_tuple) + return -EINVAL; - if (!usr_ip4_spec->ip4src) - *unused |= BIT(INNER_SRC_IP); + *unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | + BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT); - if (!usr_ip4_spec->ip4dst) - *unused |= BIT(INNER_DST_IP); + if (!spec->ip4src) + *unused_tuple |= BIT(INNER_SRC_IP); - if (!usr_ip4_spec->tos) - *unused |= BIT(INNER_IP_TOS); + if (!spec->ip4dst) + *unused_tuple |= BIT(INNER_DST_IP); - if (!usr_ip4_spec->proto) - *unused |= BIT(INNER_IP_PROTO); + if (!spec->tos) + *unused_tuple |= BIT(INNER_IP_TOS); - if (usr_ip4_spec->l4_4_bytes) - return -EOPNOTSUPP; + if (!spec->proto) + *unused_tuple |= BIT(INNER_IP_PROTO); - if (usr_ip4_spec->ip_ver != ETH_RX_NFC_IP4) - return -EOPNOTSUPP; + if (spec->l4_4_bytes) + return -EOPNOTSUPP; - break; - case SCTP_V6_FLOW: - case TCP_V6_FLOW: - case UDP_V6_FLOW: - tcp_ip6_spec = &fs->h_u.tcp_ip6_spec; - *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | - BIT(INNER_IP_TOS); + if (spec->ip_ver != ETH_RX_NFC_IP4) + return -EOPNOTSUPP; - /* check whether src/dst ip address used */ - if (!tcp_ip6_spec->ip6src[0] && !tcp_ip6_spec->ip6src[1] && - !tcp_ip6_spec->ip6src[2] && !tcp_ip6_spec->ip6src[3]) - *unused |= BIT(INNER_SRC_IP); + return 0; +} - if (!tcp_ip6_spec->ip6dst[0] && !tcp_ip6_spec->ip6dst[1] && - !tcp_ip6_spec->ip6dst[2] && !tcp_ip6_spec->ip6dst[3]) - *unused |= BIT(INNER_DST_IP); +static int hclge_fd_check_tcpip6_tuple(struct ethtool_tcpip6_spec *spec, + u32 *unused_tuple) +{ + if (!spec || !unused_tuple) + return -EINVAL; - if (!tcp_ip6_spec->psrc) - *unused |= BIT(INNER_SRC_PORT); + *unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | + BIT(INNER_IP_TOS); - if (!tcp_ip6_spec->pdst) - *unused |= BIT(INNER_DST_PORT); + /* check whether src/dst ip address used */ + if (!spec->ip6src[0] && !spec->ip6src[1] && + !spec->ip6src[2] && !spec->ip6src[3]) + *unused_tuple |= BIT(INNER_SRC_IP); - if (tcp_ip6_spec->tclass) - return -EOPNOTSUPP; + if (!spec->ip6dst[0] && !spec->ip6dst[1] && + !spec->ip6dst[2] && !spec->ip6dst[3]) + *unused_tuple |= BIT(INNER_DST_IP); - break; - case IPV6_USER_FLOW: - usr_ip6_spec = &fs->h_u.usr_ip6_spec; - *unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | - BIT(INNER_IP_TOS) | BIT(INNER_SRC_PORT) | - BIT(INNER_DST_PORT); + if (!spec->psrc) + *unused_tuple |= BIT(INNER_SRC_PORT); - /* check whether src/dst ip address used */ - if (!usr_ip6_spec->ip6src[0] && !usr_ip6_spec->ip6src[1] && - !usr_ip6_spec->ip6src[2] && !usr_ip6_spec->ip6src[3]) - *unused |= BIT(INNER_SRC_IP); + if (!spec->pdst) + *unused_tuple |= BIT(INNER_DST_PORT); - if (!usr_ip6_spec->ip6dst[0] && !usr_ip6_spec->ip6dst[1] && - !usr_ip6_spec->ip6dst[2] && !usr_ip6_spec->ip6dst[3]) - *unused |= BIT(INNER_DST_IP); + if (spec->tclass) + return -EOPNOTSUPP; - if (!usr_ip6_spec->l4_proto) - *unused |= BIT(INNER_IP_PROTO); + return 0; +} - if (usr_ip6_spec->tclass) - return -EOPNOTSUPP; +static int hclge_fd_check_ip6_tuple(struct ethtool_usrip6_spec *spec, + u32 *unused_tuple) +{ + if (!spec || !unused_tuple) + return -EINVAL; - if (usr_ip6_spec->l4_4_bytes) - return -EOPNOTSUPP; + *unused_tuple |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) | + BIT(INNER_IP_TOS) | BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT); - break; - case ETHER_FLOW: - ether_spec = &fs->h_u.ether_spec; - *unused |= BIT(INNER_SRC_IP) | BIT(INNER_DST_IP) | - BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT) | - BIT(INNER_IP_TOS) | BIT(INNER_IP_PROTO); + /* check whether src/dst ip address used */ + if (!spec->ip6src[0] && !spec->ip6src[1] && + !spec->ip6src[2] && !spec->ip6src[3]) + *unused_tuple |= BIT(INNER_SRC_IP); - if (is_zero_ether_addr(ether_spec->h_source)) - *unused |= BIT(INNER_SRC_MAC); + if (!spec->ip6dst[0] && !spec->ip6dst[1] && + !spec->ip6dst[2] && !spec->ip6dst[3]) + *unused_tuple |= BIT(INNER_DST_IP); - if (is_zero_ether_addr(ether_spec->h_dest)) - *unused |= BIT(INNER_DST_MAC); + if (!spec->l4_proto) + *unused_tuple |= BIT(INNER_IP_PROTO); - if (!ether_spec->h_proto) - *unused |= BIT(INNER_ETH_TYPE); + if (spec->tclass) + return -EOPNOTSUPP; - break; - default: + if (spec->l4_4_bytes) return -EOPNOTSUPP; - } - if ((fs->flow_type & FLOW_EXT)) { - if (fs->h_ext.vlan_etype) + return 0; +} + +static int hclge_fd_check_ether_tuple(struct ethhdr *spec, u32 *unused_tuple) +{ + if (!spec || !unused_tuple) + return -EINVAL; + + *unused_tuple |= BIT(INNER_SRC_IP) | BIT(INNER_DST_IP) | + BIT(INNER_SRC_PORT) | BIT(INNER_DST_PORT) | + BIT(INNER_IP_TOS) | BIT(INNER_IP_PROTO); + + if (is_zero_ether_addr(spec->h_source)) + *unused_tuple |= BIT(INNER_SRC_MAC); + + if (is_zero_ether_addr(spec->h_dest)) + *unused_tuple |= BIT(INNER_DST_MAC); + + if (!spec->h_proto) + *unused_tuple |= BIT(INNER_ETH_TYPE); + + return 0; +} + +static int hclge_fd_check_ext_tuple(struct hclge_dev *hdev, + struct ethtool_rx_flow_spec *fs, + u32 *unused_tuple) +{ + if (fs->flow_type & FLOW_EXT) { + if (fs->h_ext.vlan_etype) { + dev_err(&hdev->pdev->dev, "vlan-etype is not supported!\n"); return -EOPNOTSUPP; + } + if (!fs->h_ext.vlan_tci) - *unused |= BIT(INNER_VLAN_TAG_FST); + *unused_tuple |= BIT(INNER_VLAN_TAG_FST); - if (fs->m_ext.vlan_tci) { - if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID) - return -EINVAL; + if (fs->m_ext.vlan_tci && + be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID) { + dev_err(&hdev->pdev->dev, + "failed to config vlan_tci, invalid vlan_tci: %u, max is %u.\n", + ntohs(fs->h_ext.vlan_tci), VLAN_N_VID - 1); + return -EINVAL; } } else { - *unused |= BIT(INNER_VLAN_TAG_FST); + *unused_tuple |= BIT(INNER_VLAN_TAG_FST); } if (fs->flow_type & FLOW_MAC_EXT) { - if (!(hdev->fd_cfg.proto_support & ETHER_FLOW)) + if (hdev->fd_cfg.fd_mode != + HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1) { + dev_err(&hdev->pdev->dev, + "FLOW_MAC_EXT is not supported in current fd mode!\n"); return -EOPNOTSUPP; + } if (is_zero_ether_addr(fs->h_ext.h_dest)) - *unused |= BIT(INNER_DST_MAC); + *unused_tuple |= BIT(INNER_DST_MAC); else - *unused &= ~(BIT(INNER_DST_MAC)); + *unused_tuple &= ~BIT(INNER_DST_MAC); } return 0; } +static int hclge_fd_check_spec(struct hclge_dev *hdev, + struct ethtool_rx_flow_spec *fs, + u32 *unused_tuple) +{ + u32 flow_type; + int ret; + + if (fs->location >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) { + dev_err(&hdev->pdev->dev, + "failed to config fd rules, invalid rule location: %u, max is %u\n.", + fs->location, + hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1] - 1); + return -EINVAL; + } + + if ((fs->flow_type & FLOW_EXT) && + (fs->h_ext.data[0] != 0 || fs->h_ext.data[1] != 0)) { + dev_err(&hdev->pdev->dev, "user-def bytes are not supported\n"); + return -EOPNOTSUPP; + } + + flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT); + switch (flow_type) { + case SCTP_V4_FLOW: + case TCP_V4_FLOW: + case UDP_V4_FLOW: + ret = hclge_fd_check_tcpip4_tuple(&fs->h_u.tcp_ip4_spec, + unused_tuple); + break; + case IP_USER_FLOW: + ret = hclge_fd_check_ip4_tuple(&fs->h_u.usr_ip4_spec, + unused_tuple); + break; + case SCTP_V6_FLOW: + case TCP_V6_FLOW: + case UDP_V6_FLOW: + ret = hclge_fd_check_tcpip6_tuple(&fs->h_u.tcp_ip6_spec, + unused_tuple); + break; + case IPV6_USER_FLOW: + ret = hclge_fd_check_ip6_tuple(&fs->h_u.usr_ip6_spec, + unused_tuple); + break; + case ETHER_FLOW: + if (hdev->fd_cfg.fd_mode != + HCLGE_FD_MODE_DEPTH_2K_WIDTH_400B_STAGE_1) { + dev_err(&hdev->pdev->dev, + "ETHER_FLOW is not supported in current fd mode!\n"); + return -EOPNOTSUPP; + } + + ret = hclge_fd_check_ether_tuple(&fs->h_u.ether_spec, + unused_tuple); + break; + default: + dev_err(&hdev->pdev->dev, + "unsupported protocol type, protocol type = %#x\n", + flow_type); + return -EOPNOTSUPP; + } + + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to check flow union tuple, ret = %d\n", + ret); + return ret; + } + + return hclge_fd_check_ext_tuple(hdev, fs, unused_tuple); +} + static bool hclge_fd_rule_exist(struct hclge_dev *hdev, u16 location) { struct hclge_fd_rule *rule = NULL; @@ -5618,7 +5700,7 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev, break; } - if ((fs->flow_type & FLOW_EXT)) { + if (fs->flow_type & FLOW_EXT) { rule->tuples.vlan_tag1 = be16_to_cpu(fs->h_ext.vlan_tci); rule->tuples_mask.vlan_tag1 = be16_to_cpu(fs->m_ext.vlan_tci); } @@ -5673,22 +5755,23 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle, u8 action; int ret; - if (!hnae3_dev_fd_supported(hdev)) + if (!hnae3_dev_fd_supported(hdev)) { + dev_err(&hdev->pdev->dev, + "flow table director is not supported\n"); return -EOPNOTSUPP; + } if (!hdev->fd_en) { - dev_warn(&hdev->pdev->dev, - "Please enable flow director first\n"); + dev_err(&hdev->pdev->dev, + "please enable flow director first\n"); return -EOPNOTSUPP; } fs = (struct ethtool_rx_flow_spec *)&cmd->fs; ret = hclge_fd_check_spec(hdev, fs, &unused); - if (ret) { - dev_err(&hdev->pdev->dev, "Check fd spec failed\n"); + if (ret) return ret; - } if (fs->ring_cookie == RX_CLS_FLOW_DISC) { action = HCLGE_FD_ACTION_DROP_PACKET; @@ -5729,7 +5812,6 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle, } rule->flow_type = fs->flow_type; - rule->location = fs->location; rule->unused_tuple = unused; rule->vf_id = dst_vport_id; @@ -5877,6 +5959,149 @@ static int hclge_get_fd_rule_cnt(struct hnae3_handle *handle, return 0; } +static void hclge_fd_get_tcpip4_info(struct hclge_fd_rule *rule, + struct ethtool_tcpip4_spec *spec, + struct ethtool_tcpip4_spec *spec_mask) +{ + spec->ip4src = cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]); + spec_mask->ip4src = rule->unused_tuple & BIT(INNER_SRC_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]); + + spec->ip4dst = cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]); + spec_mask->ip4dst = rule->unused_tuple & BIT(INNER_DST_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]); + + spec->psrc = cpu_to_be16(rule->tuples.src_port); + spec_mask->psrc = rule->unused_tuple & BIT(INNER_SRC_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.src_port); + + spec->pdst = cpu_to_be16(rule->tuples.dst_port); + spec_mask->pdst = rule->unused_tuple & BIT(INNER_DST_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.dst_port); + + spec->tos = rule->tuples.ip_tos; + spec_mask->tos = rule->unused_tuple & BIT(INNER_IP_TOS) ? + 0 : rule->tuples_mask.ip_tos; +} + +static void hclge_fd_get_ip4_info(struct hclge_fd_rule *rule, + struct ethtool_usrip4_spec *spec, + struct ethtool_usrip4_spec *spec_mask) +{ + spec->ip4src = cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]); + spec_mask->ip4src = rule->unused_tuple & BIT(INNER_SRC_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]); + + spec->ip4dst = cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]); + spec_mask->ip4dst = rule->unused_tuple & BIT(INNER_DST_IP) ? + 0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]); + + spec->tos = rule->tuples.ip_tos; + spec_mask->tos = rule->unused_tuple & BIT(INNER_IP_TOS) ? + 0 : rule->tuples_mask.ip_tos; + + spec->proto = rule->tuples.ip_proto; + spec_mask->proto = rule->unused_tuple & BIT(INNER_IP_PROTO) ? + 0 : rule->tuples_mask.ip_proto; + + spec->ip_ver = ETH_RX_NFC_IP4; +} + +static void hclge_fd_get_tcpip6_info(struct hclge_fd_rule *rule, + struct ethtool_tcpip6_spec *spec, + struct ethtool_tcpip6_spec *spec_mask) +{ + cpu_to_be32_array(spec->ip6src, + rule->tuples.src_ip, IPV6_SIZE); + cpu_to_be32_array(spec->ip6dst, + rule->tuples.dst_ip, IPV6_SIZE); + if (rule->unused_tuple & BIT(INNER_SRC_IP)) + memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src)); + else + cpu_to_be32_array(spec_mask->ip6src, rule->tuples_mask.src_ip, + IPV6_SIZE); + + if (rule->unused_tuple & BIT(INNER_DST_IP)) + memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst)); + else + cpu_to_be32_array(spec_mask->ip6dst, rule->tuples_mask.dst_ip, + IPV6_SIZE); + + spec->psrc = cpu_to_be16(rule->tuples.src_port); + spec_mask->psrc = rule->unused_tuple & BIT(INNER_SRC_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.src_port); + + spec->pdst = cpu_to_be16(rule->tuples.dst_port); + spec_mask->pdst = rule->unused_tuple & BIT(INNER_DST_PORT) ? + 0 : cpu_to_be16(rule->tuples_mask.dst_port); +} + +static void hclge_fd_get_ip6_info(struct hclge_fd_rule *rule, + struct ethtool_usrip6_spec *spec, + struct ethtool_usrip6_spec *spec_mask) +{ + cpu_to_be32_array(spec->ip6src, rule->tuples.src_ip, IPV6_SIZE); + cpu_to_be32_array(spec->ip6dst, rule->tuples.dst_ip, IPV6_SIZE); + if (rule->unused_tuple & BIT(INNER_SRC_IP)) + memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src)); + else + cpu_to_be32_array(spec_mask->ip6src, + rule->tuples_mask.src_ip, IPV6_SIZE); + + if (rule->unused_tuple & BIT(INNER_DST_IP)) + memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst)); + else + cpu_to_be32_array(spec_mask->ip6dst, + rule->tuples_mask.dst_ip, IPV6_SIZE); + + spec->l4_proto = rule->tuples.ip_proto; + spec_mask->l4_proto = rule->unused_tuple & BIT(INNER_IP_PROTO) ? + 0 : rule->tuples_mask.ip_proto; +} + +static void hclge_fd_get_ether_info(struct hclge_fd_rule *rule, + struct ethhdr *spec, + struct ethhdr *spec_mask) +{ + ether_addr_copy(spec->h_source, rule->tuples.src_mac); + ether_addr_copy(spec->h_dest, rule->tuples.dst_mac); + + if (rule->unused_tuple & BIT(INNER_SRC_MAC)) + eth_zero_addr(spec_mask->h_source); + else + ether_addr_copy(spec_mask->h_source, rule->tuples_mask.src_mac); + + if (rule->unused_tuple & BIT(INNER_DST_MAC)) + eth_zero_addr(spec_mask->h_dest); + else + ether_addr_copy(spec_mask->h_dest, rule->tuples_mask.dst_mac); + + spec->h_proto = cpu_to_be16(rule->tuples.ether_proto); + spec_mask->h_proto = rule->unused_tuple & BIT(INNER_ETH_TYPE) ? + 0 : cpu_to_be16(rule->tuples_mask.ether_proto); +} + +static void hclge_fd_get_ext_info(struct ethtool_rx_flow_spec *fs, + struct hclge_fd_rule *rule) +{ + if (fs->flow_type & FLOW_EXT) { + fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1); + fs->m_ext.vlan_tci = + rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ? + cpu_to_be16(VLAN_VID_MASK) : + cpu_to_be16(rule->tuples_mask.vlan_tag1); + } + + if (fs->flow_type & FLOW_MAC_EXT) { + ether_addr_copy(fs->h_ext.h_dest, rule->tuples.dst_mac); + if (rule->unused_tuple & BIT(INNER_DST_MAC)) + eth_zero_addr(fs->m_u.ether_spec.h_dest); + else + ether_addr_copy(fs->m_u.ether_spec.h_dest, + rule->tuples_mask.dst_mac); + } +} + static int hclge_get_fd_rule_info(struct hnae3_handle *handle, struct ethtool_rxnfc *cmd) { @@ -5909,162 +6134,34 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle, case SCTP_V4_FLOW: case TCP_V4_FLOW: case UDP_V4_FLOW: - fs->h_u.tcp_ip4_spec.ip4src = - cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]); - fs->m_u.tcp_ip4_spec.ip4src = - rule->unused_tuple & BIT(INNER_SRC_IP) ? - 0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]); - - fs->h_u.tcp_ip4_spec.ip4dst = - cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]); - fs->m_u.tcp_ip4_spec.ip4dst = - rule->unused_tuple & BIT(INNER_DST_IP) ? - 0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]); - - fs->h_u.tcp_ip4_spec.psrc = cpu_to_be16(rule->tuples.src_port); - fs->m_u.tcp_ip4_spec.psrc = - rule->unused_tuple & BIT(INNER_SRC_PORT) ? - 0 : cpu_to_be16(rule->tuples_mask.src_port); - - fs->h_u.tcp_ip4_spec.pdst = cpu_to_be16(rule->tuples.dst_port); - fs->m_u.tcp_ip4_spec.pdst = - rule->unused_tuple & BIT(INNER_DST_PORT) ? - 0 : cpu_to_be16(rule->tuples_mask.dst_port); - - fs->h_u.tcp_ip4_spec.tos = rule->tuples.ip_tos; - fs->m_u.tcp_ip4_spec.tos = - rule->unused_tuple & BIT(INNER_IP_TOS) ? - 0 : rule->tuples_mask.ip_tos; - + hclge_fd_get_tcpip4_info(rule, &fs->h_u.tcp_ip4_spec, + &fs->m_u.tcp_ip4_spec); break; case IP_USER_FLOW: - fs->h_u.usr_ip4_spec.ip4src = - cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]); - fs->m_u.tcp_ip4_spec.ip4src = - rule->unused_tuple & BIT(INNER_SRC_IP) ? - 0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]); - - fs->h_u.usr_ip4_spec.ip4dst = - cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]); - fs->m_u.usr_ip4_spec.ip4dst = - rule->unused_tuple & BIT(INNER_DST_IP) ? - 0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]); - - fs->h_u.usr_ip4_spec.tos = rule->tuples.ip_tos; - fs->m_u.usr_ip4_spec.tos = - rule->unused_tuple & BIT(INNER_IP_TOS) ? - 0 : rule->tuples_mask.ip_tos; - - fs->h_u.usr_ip4_spec.proto = rule->tuples.ip_proto; - fs->m_u.usr_ip4_spec.proto = - rule->unused_tuple & BIT(INNER_IP_PROTO) ? - 0 : rule->tuples_mask.ip_proto; - - fs->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; - + hclge_fd_get_ip4_info(rule, &fs->h_u.usr_ip4_spec, + &fs->m_u.usr_ip4_spec); break; case SCTP_V6_FLOW: case TCP_V6_FLOW: case UDP_V6_FLOW: - cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6src, - rule->tuples.src_ip, IPV6_SIZE); - if (rule->unused_tuple & BIT(INNER_SRC_IP)) - memset(fs->m_u.tcp_ip6_spec.ip6src, 0, - sizeof(int) * IPV6_SIZE); - else - cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6src, - rule->tuples_mask.src_ip, IPV6_SIZE); - - cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6dst, - rule->tuples.dst_ip, IPV6_SIZE); - if (rule->unused_tuple & BIT(INNER_DST_IP)) - memset(fs->m_u.tcp_ip6_spec.ip6dst, 0, - sizeof(int) * IPV6_SIZE); - else - cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6dst, - rule->tuples_mask.dst_ip, IPV6_SIZE); - - fs->h_u.tcp_ip6_spec.psrc = cpu_to_be16(rule->tuples.src_port); - fs->m_u.tcp_ip6_spec.psrc = - rule->unused_tuple & BIT(INNER_SRC_PORT) ? - 0 : cpu_to_be16(rule->tuples_mask.src_port); - - fs->h_u.tcp_ip6_spec.pdst = cpu_to_be16(rule->tuples.dst_port); - fs->m_u.tcp_ip6_spec.pdst = - rule->unused_tuple & BIT(INNER_DST_PORT) ? - 0 : cpu_to_be16(rule->tuples_mask.dst_port); - + hclge_fd_get_tcpip6_info(rule, &fs->h_u.tcp_ip6_spec, + &fs->m_u.tcp_ip6_spec); break; case IPV6_USER_FLOW: - cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6src, - rule->tuples.src_ip, IPV6_SIZE); - if (rule->unused_tuple & BIT(INNER_SRC_IP)) - memset(fs->m_u.usr_ip6_spec.ip6src, 0, - sizeof(int) * IPV6_SIZE); - else - cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6src, - rule->tuples_mask.src_ip, IPV6_SIZE); - - cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6dst, - rule->tuples.dst_ip, IPV6_SIZE); - if (rule->unused_tuple & BIT(INNER_DST_IP)) - memset(fs->m_u.usr_ip6_spec.ip6dst, 0, - sizeof(int) * IPV6_SIZE); - else - cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6dst, - rule->tuples_mask.dst_ip, IPV6_SIZE); - - fs->h_u.usr_ip6_spec.l4_proto = rule->tuples.ip_proto; - fs->m_u.usr_ip6_spec.l4_proto = - rule->unused_tuple & BIT(INNER_IP_PROTO) ? - 0 : rule->tuples_mask.ip_proto; - - break; - case ETHER_FLOW: - ether_addr_copy(fs->h_u.ether_spec.h_source, - rule->tuples.src_mac); - if (rule->unused_tuple & BIT(INNER_SRC_MAC)) - eth_zero_addr(fs->m_u.ether_spec.h_source); - else - ether_addr_copy(fs->m_u.ether_spec.h_source, - rule->tuples_mask.src_mac); - - ether_addr_copy(fs->h_u.ether_spec.h_dest, - rule->tuples.dst_mac); - if (rule->unused_tuple & BIT(INNER_DST_MAC)) - eth_zero_addr(fs->m_u.ether_spec.h_dest); - else - ether_addr_copy(fs->m_u.ether_spec.h_dest, - rule->tuples_mask.dst_mac); - - fs->h_u.ether_spec.h_proto = - cpu_to_be16(rule->tuples.ether_proto); - fs->m_u.ether_spec.h_proto = - rule->unused_tuple & BIT(INNER_ETH_TYPE) ? - 0 : cpu_to_be16(rule->tuples_mask.ether_proto); - + hclge_fd_get_ip6_info(rule, &fs->h_u.usr_ip6_spec, + &fs->m_u.usr_ip6_spec); break; + /* The flow type of fd rule has been checked before adding in to rule + * list. As other flow types have been handled, it must be ETHER_FLOW + * for the default case + */ default: - spin_unlock_bh(&hdev->fd_rule_lock); - return -EOPNOTSUPP; + hclge_fd_get_ether_info(rule, &fs->h_u.ether_spec, + &fs->m_u.ether_spec); + break; } - if (fs->flow_type & FLOW_EXT) { - fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1); - fs->m_ext.vlan_tci = - rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ? - cpu_to_be16(VLAN_VID_MASK) : - cpu_to_be16(rule->tuples_mask.vlan_tag1); - } - - if (fs->flow_type & FLOW_MAC_EXT) { - ether_addr_copy(fs->h_ext.h_dest, rule->tuples.dst_mac); - if (rule->unused_tuple & BIT(INNER_DST_MAC)) - eth_zero_addr(fs->m_u.ether_spec.h_dest); - else - ether_addr_copy(fs->m_u.ether_spec.h_dest, - rule->tuples_mask.dst_mac); - } + hclge_fd_get_ext_info(fs, rule); if (rule->action == HCLGE_FD_ACTION_DROP_PACKET) { fs->ring_cookie = RX_CLS_FLOW_DISC; @@ -6202,7 +6299,6 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, */ if (hdev->fd_active_type == HCLGE_FD_EP_ACTIVE) { spin_unlock_bh(&hdev->fd_rule_lock); - return -EOPNOTSUPP; } @@ -6216,14 +6312,12 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, bit_id = find_first_zero_bit(hdev->fd_bmap, MAX_FD_FILTER_NUM); if (bit_id >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) { spin_unlock_bh(&hdev->fd_rule_lock); - return -ENOSPC; } rule = kzalloc(sizeof(*rule), GFP_ATOMIC); if (!rule) { spin_unlock_bh(&hdev->fd_rule_lock); - return -ENOMEM; } @@ -6834,8 +6928,22 @@ static void hclge_ae_stop(struct hnae3_handle *handle) int hclge_vport_start(struct hclge_vport *vport) { + struct hclge_dev *hdev = vport->back; + set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state); vport->last_active_jiffies = jiffies; + + if (test_bit(vport->vport_id, hdev->vport_config_block)) { + if (vport->vport_id) { + hclge_restore_mac_table_common(vport); + hclge_restore_vport_vlan_table(vport); + } else { + hclge_restore_hw_table(hdev); + } + } + + clear_bit(vport->vport_id, hdev->vport_config_block); + return 0; } @@ -6872,17 +6980,11 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport, } if (op == HCLGE_MAC_VLAN_ADD) { - if ((!resp_code) || (resp_code == 1)) { + if (!resp_code || resp_code == 1) return 0; - } else if (resp_code == HCLGE_ADD_UC_OVERFLOW) { - dev_err(&hdev->pdev->dev, - "add mac addr failed for uc_overflow.\n"); + else if (resp_code == HCLGE_ADD_UC_OVERFLOW || + resp_code == HCLGE_ADD_MC_OVERFLOW) return -ENOSPC; - } else if (resp_code == HCLGE_ADD_MC_OVERFLOW) { - dev_err(&hdev->pdev->dev, - "add mac addr failed for mc_overflow.\n"); - return -ENOSPC; - } dev_err(&hdev->pdev->dev, "add mac addr failed for undefined, code=%u.\n", @@ -7106,52 +7208,8 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, return cfg_status; } -static int hclge_init_umv_space(struct hclge_dev *hdev) -{ - u16 allocated_size = 0; - int ret; - - ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size, - true); - if (ret) - return ret; - - if (allocated_size < hdev->wanted_umv_size) - dev_warn(&hdev->pdev->dev, - "Alloc umv space failed, want %u, get %u\n", - hdev->wanted_umv_size, allocated_size); - - mutex_init(&hdev->umv_mutex); - hdev->max_umv_size = allocated_size; - /* divide max_umv_size by (hdev->num_req_vfs + 2), in order to - * preserve some unicast mac vlan table entries shared by pf - * and its vfs. - */ - hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_req_vfs + 2); - hdev->share_umv_size = hdev->priv_umv_size + - hdev->max_umv_size % (hdev->num_req_vfs + 2); - - return 0; -} - -static int hclge_uninit_umv_space(struct hclge_dev *hdev) -{ - int ret; - - if (hdev->max_umv_size > 0) { - ret = hclge_set_umv_space(hdev, hdev->max_umv_size, NULL, - false); - if (ret) - return ret; - hdev->max_umv_size = 0; - } - mutex_destroy(&hdev->umv_mutex); - - return 0; -} - static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, - u16 *allocated_size, bool is_alloc) + u16 *allocated_size) { struct hclge_umv_spc_alc_cmd *req; struct hclge_desc desc; @@ -7159,21 +7217,39 @@ static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, req = (struct hclge_umv_spc_alc_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ALLOCATE, false); - if (!is_alloc) - hnae3_set_bit(req->allocate, HCLGE_UMV_SPC_ALC_B, 1); req->space_size = cpu_to_le32(space_size); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { - dev_err(&hdev->pdev->dev, - "%s umv space failed for cmd_send, ret =%d\n", - is_alloc ? "allocate" : "free", ret); + dev_err(&hdev->pdev->dev, "failed to set umv space, ret = %d\n", + ret); return ret; } - if (is_alloc && allocated_size) - *allocated_size = le32_to_cpu(desc.data[1]); + *allocated_size = le32_to_cpu(desc.data[1]); + + return 0; +} + +static int hclge_init_umv_space(struct hclge_dev *hdev) +{ + u16 allocated_size = 0; + int ret; + + ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size); + if (ret) + return ret; + + if (allocated_size < hdev->wanted_umv_size) + dev_warn(&hdev->pdev->dev, + "failed to alloc umv space, want %u, get %u\n", + hdev->wanted_umv_size, allocated_size); + + hdev->max_umv_size = allocated_size; + hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_alloc_vport + 1); + hdev->share_umv_size = hdev->priv_umv_size + + hdev->max_umv_size % (hdev->num_alloc_vport + 1); return 0; } @@ -7188,21 +7264,25 @@ static void hclge_reset_umv_space(struct hclge_dev *hdev) vport->used_umv_num = 0; } - mutex_lock(&hdev->umv_mutex); + mutex_lock(&hdev->vport_lock); hdev->share_umv_size = hdev->priv_umv_size + - hdev->max_umv_size % (hdev->num_req_vfs + 2); - mutex_unlock(&hdev->umv_mutex); + hdev->max_umv_size % (hdev->num_alloc_vport + 1); + mutex_unlock(&hdev->vport_lock); } -static bool hclge_is_umv_space_full(struct hclge_vport *vport) +static bool hclge_is_umv_space_full(struct hclge_vport *vport, bool need_lock) { struct hclge_dev *hdev = vport->back; bool is_full; - mutex_lock(&hdev->umv_mutex); + if (need_lock) + mutex_lock(&hdev->vport_lock); + is_full = (vport->used_umv_num >= hdev->priv_umv_size && hdev->share_umv_size == 0); - mutex_unlock(&hdev->umv_mutex); + + if (need_lock) + mutex_unlock(&hdev->vport_lock); return is_full; } @@ -7211,7 +7291,6 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free) { struct hclge_dev *hdev = vport->back; - mutex_lock(&hdev->umv_mutex); if (is_free) { if (vport->used_umv_num > hdev->priv_umv_size) hdev->share_umv_size++; @@ -7224,7 +7303,99 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free) hdev->share_umv_size--; vport->used_umv_num++; } - mutex_unlock(&hdev->umv_mutex); +} + +static struct hclge_mac_node *hclge_find_mac_node(struct list_head *list, + const u8 *mac_addr) +{ + struct hclge_mac_node *mac_node, *tmp; + + list_for_each_entry_safe(mac_node, tmp, list, node) + if (ether_addr_equal(mac_addr, mac_node->mac_addr)) + return mac_node; + + return NULL; +} + +static void hclge_update_mac_node(struct hclge_mac_node *mac_node, + enum HCLGE_MAC_NODE_STATE state) +{ + switch (state) { + /* from set_rx_mode or tmp_add_list */ + case HCLGE_MAC_TO_ADD: + if (mac_node->state == HCLGE_MAC_TO_DEL) + mac_node->state = HCLGE_MAC_ACTIVE; + break; + /* only from set_rx_mode */ + case HCLGE_MAC_TO_DEL: + if (mac_node->state == HCLGE_MAC_TO_ADD) { + list_del(&mac_node->node); + kfree(mac_node); + } else { + mac_node->state = HCLGE_MAC_TO_DEL; + } + break; + /* only from tmp_add_list, the mac_node->state won't be + * ACTIVE. + */ + case HCLGE_MAC_ACTIVE: + if (mac_node->state == HCLGE_MAC_TO_ADD) + mac_node->state = HCLGE_MAC_ACTIVE; + + break; + } +} + +int hclge_update_mac_list(struct hclge_vport *vport, + enum HCLGE_MAC_NODE_STATE state, + enum HCLGE_MAC_ADDR_TYPE mac_type, + const unsigned char *addr) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_mac_node *mac_node; + struct list_head *list; + + list = (mac_type == HCLGE_MAC_ADDR_UC) ? + &vport->uc_mac_list : &vport->mc_mac_list; + + spin_lock_bh(&vport->mac_list_lock); + + /* if the mac addr is already in the mac list, no need to add a new + * one into it, just check the mac addr state, convert it to a new + * new state, or just remove it, or do nothing. + */ + mac_node = hclge_find_mac_node(list, addr); + if (mac_node) { + hclge_update_mac_node(mac_node, state); + spin_unlock_bh(&vport->mac_list_lock); + set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state); + return 0; + } + + /* if this address is never added, unnecessary to delete */ + if (state == HCLGE_MAC_TO_DEL) { + spin_unlock_bh(&vport->mac_list_lock); + dev_err(&hdev->pdev->dev, + "failed to delete address %pM from mac list\n", + addr); + return -ENOENT; + } + + mac_node = kzalloc(sizeof(*mac_node), GFP_ATOMIC); + if (!mac_node) { + spin_unlock_bh(&vport->mac_list_lock); + return -ENOMEM; + } + + set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state); + + mac_node->state = state; + ether_addr_copy(mac_node->mac_addr, addr); + list_add_tail(&mac_node->node, list); + + spin_unlock_bh(&vport->mac_list_lock); + + return 0; } static int hclge_add_uc_addr(struct hnae3_handle *handle, @@ -7232,7 +7403,8 @@ static int hclge_add_uc_addr(struct hnae3_handle *handle, { struct hclge_vport *vport = hclge_get_vport(handle); - return hclge_add_uc_addr_common(vport, addr); + return hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD, HCLGE_MAC_ADDR_UC, + addr); } int hclge_add_uc_addr_common(struct hclge_vport *vport, @@ -7271,15 +7443,19 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, */ ret = hclge_lookup_mac_vlan_tbl(vport, &req, &desc, false); if (ret == -ENOENT) { - if (!hclge_is_umv_space_full(vport)) { + mutex_lock(&hdev->vport_lock); + if (!hclge_is_umv_space_full(vport, false)) { ret = hclge_add_mac_vlan_tbl(vport, &req, NULL); if (!ret) hclge_update_umv_space(vport, false); + mutex_unlock(&hdev->vport_lock); return ret; } + mutex_unlock(&hdev->vport_lock); - dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n", - hdev->priv_umv_size); + if (!(vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE)) + dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n", + hdev->priv_umv_size); return -ENOSPC; } @@ -7303,7 +7479,8 @@ static int hclge_rm_uc_addr(struct hnae3_handle *handle, { struct hclge_vport *vport = hclge_get_vport(handle); - return hclge_rm_uc_addr_common(vport, addr); + return hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL, HCLGE_MAC_ADDR_UC, + addr); } int hclge_rm_uc_addr_common(struct hclge_vport *vport, @@ -7326,8 +7503,13 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hclge_prepare_mac_addr(&req, addr, false); ret = hclge_remove_mac_vlan_tbl(vport, &req); - if (!ret) + if (!ret) { + mutex_lock(&hdev->vport_lock); hclge_update_umv_space(vport, true); + mutex_unlock(&hdev->vport_lock); + } else if (ret == -ENOENT) { + ret = 0; + } return ret; } @@ -7337,7 +7519,8 @@ static int hclge_add_mc_addr(struct hnae3_handle *handle, { struct hclge_vport *vport = hclge_get_vport(handle); - return hclge_add_mc_addr_common(vport, addr); + return hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD, HCLGE_MAC_ADDR_MC, + addr); } int hclge_add_mc_addr_common(struct hclge_vport *vport, @@ -7369,7 +7552,9 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, return status; status = hclge_add_mac_vlan_tbl(vport, &req, desc); - if (status == -ENOSPC) + /* if already overflow, not to print each time */ + if (status == -ENOSPC && + !(vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE)) dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n"); return status; @@ -7380,7 +7565,8 @@ static int hclge_rm_mc_addr(struct hnae3_handle *handle, { struct hclge_vport *vport = hclge_get_vport(handle); - return hclge_rm_mc_addr_common(vport, addr); + return hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL, HCLGE_MAC_ADDR_MC, + addr); } int hclge_rm_mc_addr_common(struct hclge_vport *vport, @@ -7415,111 +7601,354 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, /* Not all the vfid is zero, update the vfid */ status = hclge_add_mac_vlan_tbl(vport, &req, desc); - } else { - /* Maybe this mac address is in mta table, but it cannot be - * deleted here because an entry of mta represents an address - * range rather than a specific address. the delete action to - * all entries will take effect in update_mta_status called by - * hns3_nic_set_rx_mode. - */ + } else if (status == -ENOENT) { status = 0; } return status; } -void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, - enum HCLGE_MAC_ADDR_TYPE mac_type) +static void hclge_sync_vport_mac_list(struct hclge_vport *vport, + struct list_head *list, + int (*sync)(struct hclge_vport *, + const unsigned char *)) { - struct hclge_vport_mac_addr_cfg *mac_cfg; - struct list_head *list; + struct hclge_mac_node *mac_node, *tmp; + int ret; - if (!vport->vport_id) - return; + list_for_each_entry_safe(mac_node, tmp, list, node) { + ret = sync(vport, mac_node->mac_addr); + if (!ret) { + mac_node->state = HCLGE_MAC_ACTIVE; + } else { + set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, + &vport->state); + break; + } + } +} - mac_cfg = kzalloc(sizeof(*mac_cfg), GFP_KERNEL); - if (!mac_cfg) - return; +static void hclge_unsync_vport_mac_list(struct hclge_vport *vport, + struct list_head *list, + int (*unsync)(struct hclge_vport *, + const unsigned char *)) +{ + struct hclge_mac_node *mac_node, *tmp; + int ret; + + list_for_each_entry_safe(mac_node, tmp, list, node) { + ret = unsync(vport, mac_node->mac_addr); + if (!ret || ret == -ENOENT) { + list_del(&mac_node->node); + kfree(mac_node); + } else { + set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, + &vport->state); + break; + } + } +} - mac_cfg->hd_tbl_status = true; - memcpy(mac_cfg->mac_addr, mac_addr, ETH_ALEN); +static bool hclge_sync_from_add_list(struct list_head *add_list, + struct list_head *mac_list) +{ + struct hclge_mac_node *mac_node, *tmp, *new_node; + bool all_added = true; - list = (mac_type == HCLGE_MAC_ADDR_UC) ? - &vport->uc_mac_list : &vport->mc_mac_list; + list_for_each_entry_safe(mac_node, tmp, add_list, node) { + if (mac_node->state == HCLGE_MAC_TO_ADD) + all_added = false; - list_add_tail(&mac_cfg->node, list); + /* if the mac address from tmp_add_list is not in the + * uc/mc_mac_list, it means have received a TO_DEL request + * during the time window of adding the mac address into mac + * table. if mac_node state is ACTIVE, then change it to TO_DEL, + * then it will be removed at next time. else it must be TO_ADD, + * this address hasn't been added into mac table, + * so just remove the mac node. + */ + new_node = hclge_find_mac_node(mac_list, mac_node->mac_addr); + if (new_node) { + hclge_update_mac_node(new_node, mac_node->state); + list_del(&mac_node->node); + kfree(mac_node); + } else if (mac_node->state == HCLGE_MAC_ACTIVE) { + mac_node->state = HCLGE_MAC_TO_DEL; + list_del(&mac_node->node); + list_add_tail(&mac_node->node, mac_list); + } else { + list_del(&mac_node->node); + kfree(mac_node); + } + } + + return all_added; } -void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, - bool is_write_tbl, - enum HCLGE_MAC_ADDR_TYPE mac_type) +static void hclge_sync_from_del_list(struct list_head *del_list, + struct list_head *mac_list) { - struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp; - struct list_head *list; - bool uc_flag, mc_flag; + struct hclge_mac_node *mac_node, *tmp, *new_node; - list = (mac_type == HCLGE_MAC_ADDR_UC) ? - &vport->uc_mac_list : &vport->mc_mac_list; + list_for_each_entry_safe(mac_node, tmp, del_list, node) { + new_node = hclge_find_mac_node(mac_list, mac_node->mac_addr); + if (new_node) { + /* If the mac addr exists in the mac list, it means + * received a new TO_ADD request during the time window + * of configuring the mac address. For the mac node + * state is TO_ADD, and the address is already in the + * in the hardware(due to delete fail), so we just need + * to change the mac node state to ACTIVE. + */ + new_node->state = HCLGE_MAC_ACTIVE; + list_del(&mac_node->node); + kfree(mac_node); + } else { + list_del(&mac_node->node); + list_add_tail(&mac_node->node, mac_list); + } + } +} + +static void hclge_update_overflow_flags(struct hclge_vport *vport, + enum HCLGE_MAC_ADDR_TYPE mac_type, + bool is_all_added) +{ + if (mac_type == HCLGE_MAC_ADDR_UC) { + if (is_all_added) + vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_UPE; + else + vport->overflow_promisc_flags |= HNAE3_OVERFLOW_UPE; + } else { + if (is_all_added) + vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_MPE; + else + vport->overflow_promisc_flags |= HNAE3_OVERFLOW_MPE; + } +} - uc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_UC; - mc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_MC; +static void hclge_sync_vport_mac_table(struct hclge_vport *vport, + enum HCLGE_MAC_ADDR_TYPE mac_type) +{ + struct hclge_mac_node *mac_node, *tmp, *new_node; + struct list_head tmp_add_list, tmp_del_list; + struct list_head *list; + bool all_added; - list_for_each_entry_safe(mac_cfg, tmp, list, node) { - if (ether_addr_equal(mac_cfg->mac_addr, mac_addr)) { - if (uc_flag && mac_cfg->hd_tbl_status) - hclge_rm_uc_addr_common(vport, mac_addr); + INIT_LIST_HEAD(&tmp_add_list); + INIT_LIST_HEAD(&tmp_del_list); - if (mc_flag && mac_cfg->hd_tbl_status) - hclge_rm_mc_addr_common(vport, mac_addr); + /* move the mac addr to the tmp_add_list and tmp_del_list, then + * we can add/delete these mac addr outside the spin lock + */ + list = (mac_type == HCLGE_MAC_ADDR_UC) ? + &vport->uc_mac_list : &vport->mc_mac_list; - list_del(&mac_cfg->node); - kfree(mac_cfg); + spin_lock_bh(&vport->mac_list_lock); + + list_for_each_entry_safe(mac_node, tmp, list, node) { + switch (mac_node->state) { + case HCLGE_MAC_TO_DEL: + list_del(&mac_node->node); + list_add_tail(&mac_node->node, &tmp_del_list); + break; + case HCLGE_MAC_TO_ADD: + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) + goto stop_traverse; + ether_addr_copy(new_node->mac_addr, mac_node->mac_addr); + new_node->state = mac_node->state; + list_add_tail(&new_node->node, &tmp_add_list); + break; + default: break; } } + +stop_traverse: + spin_unlock_bh(&vport->mac_list_lock); + + /* delete first, in order to get max mac table space for adding */ + if (mac_type == HCLGE_MAC_ADDR_UC) { + hclge_unsync_vport_mac_list(vport, &tmp_del_list, + hclge_rm_uc_addr_common); + hclge_sync_vport_mac_list(vport, &tmp_add_list, + hclge_add_uc_addr_common); + } else { + hclge_unsync_vport_mac_list(vport, &tmp_del_list, + hclge_rm_mc_addr_common); + hclge_sync_vport_mac_list(vport, &tmp_add_list, + hclge_add_mc_addr_common); + } + + /* if some mac addresses were added/deleted fail, move back to the + * mac_list, and retry at next time. + */ + spin_lock_bh(&vport->mac_list_lock); + + hclge_sync_from_del_list(&tmp_del_list, list); + all_added = hclge_sync_from_add_list(&tmp_add_list, list); + + spin_unlock_bh(&vport->mac_list_lock); + + hclge_update_overflow_flags(vport, mac_type, all_added); +} + +static bool hclge_need_sync_mac_table(struct hclge_vport *vport) +{ + struct hclge_dev *hdev = vport->back; + + if (test_bit(vport->vport_id, hdev->vport_config_block)) + return false; + + if (test_and_clear_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state)) + return true; + + return false; +} + +static void hclge_sync_mac_table(struct hclge_dev *hdev) +{ + int i; + + for (i = 0; i < hdev->num_alloc_vport; i++) { + struct hclge_vport *vport = &hdev->vport[i]; + + if (!hclge_need_sync_mac_table(vport)) + continue; + + hclge_sync_vport_mac_table(vport, HCLGE_MAC_ADDR_UC); + hclge_sync_vport_mac_table(vport, HCLGE_MAC_ADDR_MC); + } } void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list, enum HCLGE_MAC_ADDR_TYPE mac_type) { - struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp; - struct list_head *list; + int (*unsync)(struct hclge_vport *vport, const unsigned char *addr); + struct hclge_mac_node *mac_cfg, *tmp; + struct hclge_dev *hdev = vport->back; + struct list_head tmp_del_list, *list; + int ret; - list = (mac_type == HCLGE_MAC_ADDR_UC) ? - &vport->uc_mac_list : &vport->mc_mac_list; + if (mac_type == HCLGE_MAC_ADDR_UC) { + list = &vport->uc_mac_list; + unsync = hclge_rm_uc_addr_common; + } else { + list = &vport->mc_mac_list; + unsync = hclge_rm_mc_addr_common; + } - list_for_each_entry_safe(mac_cfg, tmp, list, node) { - if (mac_type == HCLGE_MAC_ADDR_UC && mac_cfg->hd_tbl_status) - hclge_rm_uc_addr_common(vport, mac_cfg->mac_addr); + INIT_LIST_HEAD(&tmp_del_list); - if (mac_type == HCLGE_MAC_ADDR_MC && mac_cfg->hd_tbl_status) - hclge_rm_mc_addr_common(vport, mac_cfg->mac_addr); + if (!is_del_list) + set_bit(vport->vport_id, hdev->vport_config_block); - mac_cfg->hd_tbl_status = false; - if (is_del_list) { + spin_lock_bh(&vport->mac_list_lock); + + list_for_each_entry_safe(mac_cfg, tmp, list, node) { + switch (mac_cfg->state) { + case HCLGE_MAC_TO_DEL: + case HCLGE_MAC_ACTIVE: list_del(&mac_cfg->node); - kfree(mac_cfg); + list_add_tail(&mac_cfg->node, &tmp_del_list); + break; + case HCLGE_MAC_TO_ADD: + if (is_del_list) { + list_del(&mac_cfg->node); + kfree(mac_cfg); + } + break; + } + } + + spin_unlock_bh(&vport->mac_list_lock); + + list_for_each_entry_safe(mac_cfg, tmp, &tmp_del_list, node) { + ret = unsync(vport, mac_cfg->mac_addr); + if (!ret || ret == -ENOENT) { + /* clear all mac addr from hardware, but remain these + * mac addr in the mac list, and restore them after + * vf reset finished. + */ + if (!is_del_list && + mac_cfg->state == HCLGE_MAC_ACTIVE) { + mac_cfg->state = HCLGE_MAC_TO_ADD; + } else { + list_del(&mac_cfg->node); + kfree(mac_cfg); + } + } else if (is_del_list) { + mac_cfg->state = HCLGE_MAC_TO_DEL; } } + + spin_lock_bh(&vport->mac_list_lock); + + hclge_sync_from_del_list(&tmp_del_list, list); + + spin_unlock_bh(&vport->mac_list_lock); } -void hclge_uninit_vport_mac_table(struct hclge_dev *hdev) +/* remove all mac address when uninitailize */ +static void hclge_uninit_vport_mac_list(struct hclge_vport *vport, + enum HCLGE_MAC_ADDR_TYPE mac_type) +{ + struct hclge_mac_node *mac_node, *tmp; + struct hclge_dev *hdev = vport->back; + struct list_head tmp_del_list, *list; + + INIT_LIST_HEAD(&tmp_del_list); + + list = (mac_type == HCLGE_MAC_ADDR_UC) ? + &vport->uc_mac_list : &vport->mc_mac_list; + + spin_lock_bh(&vport->mac_list_lock); + + list_for_each_entry_safe(mac_node, tmp, list, node) { + switch (mac_node->state) { + case HCLGE_MAC_TO_DEL: + case HCLGE_MAC_ACTIVE: + list_del(&mac_node->node); + list_add_tail(&mac_node->node, &tmp_del_list); + break; + case HCLGE_MAC_TO_ADD: + list_del(&mac_node->node); + kfree(mac_node); + break; + } + } + + spin_unlock_bh(&vport->mac_list_lock); + + if (mac_type == HCLGE_MAC_ADDR_UC) + hclge_unsync_vport_mac_list(vport, &tmp_del_list, + hclge_rm_uc_addr_common); + else + hclge_unsync_vport_mac_list(vport, &tmp_del_list, + hclge_rm_mc_addr_common); + + if (!list_empty(&tmp_del_list)) + dev_warn(&hdev->pdev->dev, + "uninit %s mac list for vport %u not completely.\n", + mac_type == HCLGE_MAC_ADDR_UC ? "uc" : "mc", + vport->vport_id); + + list_for_each_entry_safe(mac_node, tmp, &tmp_del_list, node) { + list_del(&mac_node->node); + kfree(mac_node); + } +} + +static void hclge_uninit_mac_table(struct hclge_dev *hdev) { - struct hclge_vport_mac_addr_cfg *mac, *tmp; struct hclge_vport *vport; int i; for (i = 0; i < hdev->num_alloc_vport; i++) { vport = &hdev->vport[i]; - list_for_each_entry_safe(mac, tmp, &vport->uc_mac_list, node) { - list_del(&mac->node); - kfree(mac); - } - - list_for_each_entry_safe(mac, tmp, &vport->mc_mac_list, node) { - list_del(&mac->node); - kfree(mac); - } + hclge_uninit_vport_mac_list(vport, HCLGE_MAC_ADDR_UC); + hclge_uninit_vport_mac_list(vport, HCLGE_MAC_ADDR_MC); } } @@ -7683,12 +8112,57 @@ static void hclge_get_mac_addr(struct hnae3_handle *handle, u8 *p) ether_addr_copy(p, hdev->hw.mac.mac_addr); } +int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport, + const u8 *old_addr, const u8 *new_addr) +{ + struct list_head *list = &vport->uc_mac_list; + struct hclge_mac_node *old_node, *new_node; + + new_node = hclge_find_mac_node(list, new_addr); + if (!new_node) { + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) + return -ENOMEM; + + new_node->state = HCLGE_MAC_TO_ADD; + ether_addr_copy(new_node->mac_addr, new_addr); + list_add(&new_node->node, list); + } else { + if (new_node->state == HCLGE_MAC_TO_DEL) + new_node->state = HCLGE_MAC_ACTIVE; + + /* make sure the new addr is in the list head, avoid dev + * addr may be not re-added into mac table for the umv space + * limitation after global/imp reset which will clear mac + * table by hardware. + */ + list_move(&new_node->node, list); + } + + if (old_addr && !ether_addr_equal(old_addr, new_addr)) { + old_node = hclge_find_mac_node(list, old_addr); + if (old_node) { + if (old_node->state == HCLGE_MAC_TO_ADD) { + list_del(&old_node->node); + kfree(old_node); + } else { + old_node->state = HCLGE_MAC_TO_DEL; + } + } + } + + set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state); + + return 0; +} + static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, bool is_first) { const unsigned char *new_addr = (const unsigned char *)p; struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; + unsigned char *old_addr = NULL; int ret; /* mac addr check */ @@ -7696,39 +8170,42 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, is_broadcast_ether_addr(new_addr) || is_multicast_ether_addr(new_addr)) { dev_err(&hdev->pdev->dev, - "Change uc mac err! invalid mac:%pM.\n", + "change uc mac err! invalid mac: %pM.\n", new_addr); return -EINVAL; } - if ((!is_first || is_kdump_kernel()) && - hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr)) - dev_warn(&hdev->pdev->dev, - "remove old uc mac address fail.\n"); - - ret = hclge_add_uc_addr(handle, new_addr); + ret = hclge_pause_addr_cfg(hdev, new_addr); if (ret) { dev_err(&hdev->pdev->dev, - "add uc mac address fail, ret =%d.\n", + "failed to configure mac pause address, ret = %d\n", ret); - - if (!is_first && - hclge_add_uc_addr(handle, hdev->hw.mac.mac_addr)) - dev_err(&hdev->pdev->dev, - "restore uc mac address fail.\n"); - - return -EIO; + return ret; } - ret = hclge_pause_addr_cfg(hdev, new_addr); + if (!is_first) + old_addr = hdev->hw.mac.mac_addr; + + spin_lock_bh(&vport->mac_list_lock); + ret = hclge_update_mac_node_for_dev_addr(vport, old_addr, new_addr); if (ret) { dev_err(&hdev->pdev->dev, - "configure mac pause address fail, ret =%d.\n", - ret); - return -EIO; - } + "failed to change the mac addr:%pM, ret = %d\n", + new_addr, ret); + spin_unlock_bh(&vport->mac_list_lock); + + if (!is_first) + hclge_pause_addr_cfg(hdev, old_addr); + return ret; + } + /* we must update dev addr with spin lock protect, preventing dev addr + * being removed by set_rx_mode path. + */ ether_addr_copy(hdev->hw.mac.mac_addr, new_addr); + spin_unlock_bh(&vport->mac_list_lock); + + hclge_task_schedule(hdev, 0); return 0; } @@ -8308,42 +8785,80 @@ void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev) } } -static void hclge_restore_vlan_table(struct hnae3_handle *handle) +void hclge_restore_vport_vlan_table(struct hclge_vport *vport) { - struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_vport_vlan_cfg *vlan, *tmp; struct hclge_dev *hdev = vport->back; u16 vlan_proto; - u16 state, vlan_id; - int i; + u16 vlan_id; + u16 state; + int ret; - for (i = 0; i < hdev->num_alloc_vport; i++) { - vport = &hdev->vport[i]; - vlan_proto = vport->port_base_vlan_cfg.vlan_info.vlan_proto; - vlan_id = vport->port_base_vlan_cfg.vlan_info.vlan_tag; - state = vport->port_base_vlan_cfg.state; + vlan_proto = vport->port_base_vlan_cfg.vlan_info.vlan_proto; + vlan_id = vport->port_base_vlan_cfg.vlan_info.vlan_tag; + state = vport->port_base_vlan_cfg.state; - if (state != HNAE3_PORT_BASE_VLAN_DISABLE) { - hclge_set_vlan_filter_hw(hdev, htons(vlan_proto), - vport->vport_id, vlan_id, - false); - continue; - } + if (state != HNAE3_PORT_BASE_VLAN_DISABLE) { + clear_bit(vport->vport_id, hdev->vlan_table[vlan_id]); + hclge_set_vlan_filter_hw(hdev, htons(vlan_proto), + vport->vport_id, vlan_id, + false); + return; + } - list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { - int ret; + list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { + ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), + vport->vport_id, + vlan->vlan_id, false); + if (ret) + break; + vlan->hd_tbl_status = true; + } +} - if (!vlan->hd_tbl_status) - continue; - ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), - vport->vport_id, - vlan->vlan_id, false); - if (ret) - break; +/* For global reset and imp reset, hardware will clear the mac table, + * so we change the mac address state from ACTIVE to TO_ADD, then they + * can be restored in the service task after reset complete. Furtherly, + * the mac addresses with state TO_DEL or DEL_FAIL are unnecessary to + * be restored after reset, so just remove these mac nodes from mac_list. + */ +static void hclge_mac_node_convert_for_reset(struct list_head *list) +{ + struct hclge_mac_node *mac_node, *tmp; + + list_for_each_entry_safe(mac_node, tmp, list, node) { + if (mac_node->state == HCLGE_MAC_ACTIVE) { + mac_node->state = HCLGE_MAC_TO_ADD; + } else if (mac_node->state == HCLGE_MAC_TO_DEL) { + list_del(&mac_node->node); + kfree(mac_node); } } } +void hclge_restore_mac_table_common(struct hclge_vport *vport) +{ + spin_lock_bh(&vport->mac_list_lock); + + hclge_mac_node_convert_for_reset(&vport->uc_mac_list); + hclge_mac_node_convert_for_reset(&vport->mc_mac_list); + set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state); + + spin_unlock_bh(&vport->mac_list_lock); +} + +static void hclge_restore_hw_table(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = &hdev->vport[0]; + struct hnae3_handle *handle = &vport->nic; + + hclge_restore_mac_table_common(vport); + hclge_restore_vport_vlan_table(vport); + set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); + + hclge_restore_fd_entries(handle); +} + int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -9658,7 +10173,7 @@ static int hclge_set_vf_spoofchk(struct hnae3_handle *handle, int vf, dev_warn(&hdev->pdev->dev, "vf %d vlan table is full, enable spoof check may cause its packet send fail\n", vf); - else if (enable && hclge_is_umv_space_full(vport)) + else if (enable && hclge_is_umv_space_full(vport, true)) dev_warn(&hdev->pdev->dev, "vf %d mac table is full, enable spoof check may cause its packet send fail\n", vf); @@ -9835,8 +10350,16 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) set_bit(HCLGE_STATE_DOWN, &hdev->state); hclge_stats_clear(hdev); - memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table)); - memset(hdev->vf_vlan_full, 0, sizeof(hdev->vf_vlan_full)); + /* NOTE: pf reset needn't to clear or restore pf and vf table entry. + * so here should not clean table in memory. + */ + if (hdev->reset_type == HNAE3_IMP_RESET || + hdev->reset_type == HNAE3_GLOBAL_RESET) { + memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table)); + memset(hdev->vf_vlan_full, 0, sizeof(hdev->vf_vlan_full)); + bitmap_set(hdev->vport_config_block, 0, hdev->num_alloc_vport); + hclge_reset_umv_space(hdev); + } ret = hclge_cmd_init(hdev); if (ret) { @@ -9850,8 +10373,6 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } - hclge_reset_umv_space(hdev); - ret = hclge_mac_init(hdev); if (ret) { dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); @@ -9947,12 +10468,11 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_clear_vf_vlan(hdev); hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); + hclge_uninit_mac_table(hdev); if (mac->phydev) mdiobus_unregister(mac->mdio_bus); - hclge_uninit_umv_space(hdev); - /* Disable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, false); synchronize_irq(hdev->misc_vector.vector_irq); @@ -9966,7 +10486,6 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_misc_irq_uninit(hdev); hclge_pci_uninit(hdev); mutex_destroy(&hdev->vport_lock); - hclge_uninit_vport_mac_table(hdev); hclge_uninit_vport_vlan_table(hdev); ae_dev->priv = NULL; } @@ -10576,6 +11095,30 @@ static int hclge_gro_en(struct hnae3_handle *handle, bool enable) return hclge_config_gro(hdev, enable); } +static void hclge_sync_promisc_mode(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = &hdev->vport[0]; + struct hnae3_handle *handle = &vport->nic; + u8 tmp_flags = 0; + int ret; + + if (vport->last_promisc_flags != vport->overflow_promisc_flags) { + set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); + vport->last_promisc_flags = vport->overflow_promisc_flags; + } + + if (test_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state)) { + tmp_flags = handle->netdev_flags | vport->last_promisc_flags; + ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE, + tmp_flags & HNAE3_MPE); + if (!ret) { + clear_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); + hclge_enable_vlan_filter(handle, + tmp_flags & HNAE3_VLAN_FLTR); + } + } +} + static const struct hnae3_ae_ops hclge_ops = { .init_ae_dev = hclge_init_ae_dev, .uninit_ae_dev = hclge_uninit_ae_dev, @@ -10588,6 +11131,7 @@ static const struct hnae3_ae_ops hclge_ops = { .get_vector = hclge_get_vector, .put_vector = hclge_put_vector, .set_promisc_mode = hclge_set_promisc_mode, + .request_update_promisc_mode = hclge_request_update_promisc_mode, .set_loopback = hclge_set_loopback, .start = hclge_ae_start, .stop = hclge_ae_stop, @@ -10649,7 +11193,6 @@ static const struct hnae3_ae_ops hclge_ops = { .get_fd_rule_cnt = hclge_get_fd_rule_cnt, .get_fd_rule_info = hclge_get_fd_rule_info, .get_fd_all_rules = hclge_get_all_rules, - .restore_fd_rules = hclge_restore_fd_entries, .enable_fd = hclge_enable_fd, .add_arfs_entry = hclge_add_fd_entry_by_arfs, .dbg_run_cmd = hclge_dbg_run_cmd, @@ -10662,7 +11205,6 @@ static const struct hnae3_ae_ops hclge_ops = { .set_timer_task = hclge_set_timer_task, .mac_connect_phy = hclge_mac_connect_phy, .mac_disconnect_phy = hclge_mac_disconnect_phy, - .restore_vlan_table = hclge_restore_vlan_table, .get_vf_config = hclge_get_vf_config, .set_vf_link_state = hclge_set_vf_link_state, .set_vf_spoofchk = hclge_set_vf_spoofchk, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 71df23d5f1b4..913c4f677404 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -217,6 +217,7 @@ enum HCLGE_DEV_STATE { HCLGE_STATE_STATISTICS_UPDATING, HCLGE_STATE_CMD_DISABLE, HCLGE_STATE_LINK_UPDATING, + HCLGE_STATE_PROMISC_CHANGED, HCLGE_STATE_RST_FAIL, HCLGE_STATE_MAX }; @@ -580,7 +581,6 @@ struct hclge_fd_key_cfg { struct hclge_fd_cfg { u8 fd_mode; u16 max_key_length; /* use bit as unit */ - u32 proto_support; u32 rule_num[MAX_STAGE_NUM]; /* rule entry number */ u16 cnt_num[MAX_STAGE_NUM]; /* rule hit counter number */ struct hclge_fd_key_cfg key_cfg[MAX_STAGE_NUM]; @@ -631,9 +631,15 @@ struct hclge_fd_ad_data { u16 rule_id; }; -struct hclge_vport_mac_addr_cfg { +enum HCLGE_MAC_NODE_STATE { + HCLGE_MAC_TO_ADD, + HCLGE_MAC_TO_DEL, + HCLGE_MAC_ACTIVE +}; + +struct hclge_mac_node { struct list_head node; - int hd_tbl_status; + enum HCLGE_MAC_NODE_STATE state; u8 mac_addr[ETH_ALEN]; }; @@ -806,6 +812,8 @@ struct hclge_dev { unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)]; unsigned long vf_vlan_full[BITS_TO_LONGS(HCLGE_VPORT_NUM)]; + unsigned long vport_config_block[BITS_TO_LONGS(HCLGE_VPORT_NUM)]; + struct hclge_fd_cfg fd_cfg; struct hlist_head fd_rule_list; spinlock_t fd_rule_lock; /* protect fd_rule_list and fd_bmap */ @@ -823,7 +831,6 @@ struct hclge_dev { u16 priv_umv_size; /* unicast mac vlan space shared by PF and its VFs */ u16 share_umv_size; - struct mutex umv_mutex; /* protect share_umv_size */ DECLARE_KFIFO(mac_tnl_log, struct hclge_mac_tnl_stats, HCLGE_MAC_TNL_LOG_SIZE); @@ -867,6 +874,7 @@ struct hclge_rss_tuple_cfg { enum HCLGE_VPORT_STATE { HCLGE_VPORT_STATE_ALIVE, + HCLGE_VPORT_STATE_MAC_TBL_CHANGE, HCLGE_VPORT_STATE_MAX }; @@ -923,6 +931,10 @@ struct hclge_vport { u32 mps; /* Max packet size */ struct hclge_vf_info vf_info; + u8 overflow_promisc_flags; + u8 last_promisc_flags; + + spinlock_t mac_list_lock; /* protect mac address need to add/detele */ struct list_head uc_mac_list; /* Store VF unicast table */ struct list_head mc_mac_list; /* Store VF multicast table */ struct list_head vlan_list; /* Store VF vlan table */ @@ -978,16 +990,18 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf); 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); -void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, - enum HCLGE_MAC_ADDR_TYPE mac_type); -void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr, - bool is_write_tbl, - enum HCLGE_MAC_ADDR_TYPE mac_type); +int hclge_update_mac_list(struct hclge_vport *vport, + enum HCLGE_MAC_NODE_STATE state, + enum HCLGE_MAC_ADDR_TYPE mac_type, + const unsigned char *addr); +int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport, + const u8 *old_addr, const u8 *new_addr); void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list, enum HCLGE_MAC_ADDR_TYPE mac_type); -void hclge_uninit_vport_mac_table(struct hclge_dev *hdev); void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list); void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev); +void hclge_restore_mac_table_common(struct hclge_vport *vport); +void hclge_restore_vport_vlan_table(struct hclge_vport *vport); int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, struct hclge_vlan_info *vlan_info); int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 7f24fcb4f96a..ac70fafd15d5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -5,6 +5,9 @@ #include "hclge_mbx.h" #include "hnae3.h" +#define CREATE_TRACE_POINTS +#include "hclge_trace.h" + static u16 hclge_errno_to_resp(int errno) { return abs(errno); @@ -90,6 +93,8 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, memcpy(&resp_pf_to_vf->msg.vf_mbx_msg_code, msg, msg_len); + trace_hclge_pf_mbx_send(hdev, resp_pf_to_vf); + status = hclge_cmd_send(&hdev->hw, &desc, 1); if (status) dev_err(&hdev->pdev->dev, @@ -270,26 +275,17 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport, if (!is_valid_ether_addr(mac_addr)) return -EINVAL; - hclge_rm_uc_addr_common(vport, old_addr); - status = hclge_add_uc_addr_common(vport, mac_addr); - if (status) { - hclge_add_uc_addr_common(vport, old_addr); - } else { - hclge_rm_vport_mac_table(vport, mac_addr, - false, HCLGE_MAC_ADDR_UC); - hclge_add_vport_mac_table(vport, mac_addr, - HCLGE_MAC_ADDR_UC); - } + spin_lock_bh(&vport->mac_list_lock); + status = hclge_update_mac_node_for_dev_addr(vport, old_addr, + mac_addr); + spin_unlock_bh(&vport->mac_list_lock); + hclge_task_schedule(hdev, 0); } else if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_UC_ADD) { - status = hclge_add_uc_addr_common(vport, mac_addr); - if (!status) - hclge_add_vport_mac_table(vport, mac_addr, - HCLGE_MAC_ADDR_UC); + status = hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD, + HCLGE_MAC_ADDR_UC, mac_addr); } else if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_UC_REMOVE) { - status = hclge_rm_uc_addr_common(vport, mac_addr); - if (!status) - hclge_rm_vport_mac_table(vport, mac_addr, - false, HCLGE_MAC_ADDR_UC); + status = hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL, + HCLGE_MAC_ADDR_UC, mac_addr); } else { dev_err(&hdev->pdev->dev, "failed to set unicast mac addr, unknown subcode %u\n", @@ -305,18 +301,13 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, { const u8 *mac_addr = (const u8 *)(mbx_req->msg.data); struct hclge_dev *hdev = vport->back; - int status; if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_MC_ADD) { - status = hclge_add_mc_addr_common(vport, mac_addr); - if (!status) - hclge_add_vport_mac_table(vport, mac_addr, - HCLGE_MAC_ADDR_MC); + hclge_update_mac_list(vport, HCLGE_MAC_TO_ADD, + HCLGE_MAC_ADDR_MC, mac_addr); } else if (mbx_req->msg.subcode == HCLGE_MBX_MAC_VLAN_MC_REMOVE) { - status = hclge_rm_mc_addr_common(vport, mac_addr); - if (!status) - hclge_rm_vport_mac_table(vport, mac_addr, - false, HCLGE_MAC_ADDR_MC); + hclge_update_mac_list(vport, HCLGE_MAC_TO_DEL, + HCLGE_MAC_ADDR_MC, mac_addr); } else { dev_err(&hdev->pdev->dev, "failed to set mcast mac addr, unknown subcode %u\n", @@ -324,7 +315,7 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, return -EIO; } - return status; + return 0; } int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, @@ -638,6 +629,23 @@ static void hclge_handle_ncsi_error(struct hclge_dev *hdev) ae_dev->ops->reset_event(hdev->pdev, NULL); } +static void hclge_handle_vf_tbl(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_vf_vlan_cfg *msg_cmd; + + msg_cmd = (struct hclge_vf_vlan_cfg *)&mbx_req->msg; + if (msg_cmd->subcode == HCLGE_MBX_VPORT_LIST_CLEAR) { + hclge_rm_vport_all_mac_table(vport, true, HCLGE_MAC_ADDR_UC); + hclge_rm_vport_all_mac_table(vport, true, HCLGE_MAC_ADDR_MC); + hclge_rm_vport_all_vlan_table(vport, true); + } else { + dev_warn(&hdev->pdev->dev, "Invalid cmd(%u)\n", + msg_cmd->subcode); + } +} + void hclge_mbx_handler(struct hclge_dev *hdev) { struct hclge_cmq_ring *crq = &hdev->hw.cmq.crq; @@ -645,6 +653,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev) struct hclge_mbx_vf_to_pf_cmd *req; struct hclge_vport *vport; struct hclge_desc *desc; + bool is_del = false; unsigned int flag; int ret = 0; @@ -674,6 +683,8 @@ void hclge_mbx_handler(struct hclge_dev *hdev) vport = &hdev->vport[req->mbx_src_vfid]; + trace_hclge_pf_mbx_get(hdev, req); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, @@ -760,11 +771,12 @@ void hclge_mbx_handler(struct hclge_dev *hdev) break; case HCLGE_MBX_GET_VF_FLR_STATUS: case HCLGE_MBX_VF_UNINIT: - hclge_rm_vport_all_mac_table(vport, true, + is_del = req->msg.code == HCLGE_MBX_VF_UNINIT; + hclge_rm_vport_all_mac_table(vport, is_del, HCLGE_MAC_ADDR_UC); - hclge_rm_vport_all_mac_table(vport, true, + hclge_rm_vport_all_mac_table(vport, is_del, HCLGE_MAC_ADDR_MC); - hclge_rm_vport_all_vlan_table(vport, true); + hclge_rm_vport_all_vlan_table(vport, is_del); break; case HCLGE_MBX_GET_MEDIA_TYPE: hclge_get_vf_media_type(vport, &resp_msg); @@ -778,6 +790,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) case HCLGE_MBX_NCSI_ERROR: hclge_handle_ncsi_error(hdev); break; + case HCLGE_MBX_HANDLE_VF_TBL: + hclge_handle_vf_tbl(vport, req); + break; default: dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %u\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h new file mode 100644 index 000000000000..5b0b71bd6120 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2018-2020 Hisilicon Limited. */ + +/* This must be outside ifdef _HCLGE_TRACE_H */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hns3 + +#if !defined(_HCLGE_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _HCLGE_TRACE_H_ + +#include <linux/tracepoint.h> + +#define PF_GET_MBX_LEN (sizeof(struct hclge_mbx_vf_to_pf_cmd) / sizeof(u32)) +#define PF_SEND_MBX_LEN (sizeof(struct hclge_mbx_pf_to_vf_cmd) / sizeof(u32)) + +TRACE_EVENT(hclge_pf_mbx_get, + TP_PROTO( + struct hclge_dev *hdev, + struct hclge_mbx_vf_to_pf_cmd *req), + TP_ARGS(hdev, req), + + TP_STRUCT__entry( + __field(u8, vfid) + __field(u8, code) + __field(u8, subcode) + __string(pciname, pci_name(hdev->pdev)) + __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __array(u32, mbx_data, PF_GET_MBX_LEN) + ), + + TP_fast_assign( + __entry->vfid = req->mbx_src_vfid; + __entry->code = req->msg.code; + __entry->subcode = req->msg.subcode; + __assign_str(pciname, pci_name(hdev->pdev)); + __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + memcpy(__entry->mbx_data, req, + sizeof(struct hclge_mbx_vf_to_pf_cmd)); + ), + + TP_printk( + "%s %s vfid:%u code:%u subcode:%u data:%s", + __get_str(pciname), __get_str(devname), __entry->vfid, + __entry->code, __entry->subcode, + __print_array(__entry->mbx_data, PF_GET_MBX_LEN, sizeof(u32)) + ) +); + +TRACE_EVENT(hclge_pf_mbx_send, + TP_PROTO( + struct hclge_dev *hdev, + struct hclge_mbx_pf_to_vf_cmd *req), + TP_ARGS(hdev, req), + + TP_STRUCT__entry( + __field(u8, vfid) + __field(u16, code) + __string(pciname, pci_name(hdev->pdev)) + __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __array(u32, mbx_data, PF_SEND_MBX_LEN) + ), + + TP_fast_assign( + __entry->vfid = req->dest_vfid; + __entry->code = req->msg.code; + __assign_str(pciname, pci_name(hdev->pdev)); + __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + memcpy(__entry->mbx_data, req, + sizeof(struct hclge_mbx_pf_to_vf_cmd)); + ), + + TP_printk( + "%s %s vfid:%u code:%u data:%s", + __get_str(pciname), __get_str(devname), __entry->vfid, + __entry->code, + __print_array(__entry->mbx_data, PF_SEND_MBX_LEN, sizeof(u32)) + ) +); + +#endif /* _HCLGE_TRACE_H_ */ + +/* This must be outside ifdef _HCLGE_TRACE_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE hclge_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile index 53804d95ea90..2c26ea607a53 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile @@ -4,6 +4,7 @@ # ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 +ccflags-y += -I $(srctree)/$(src) obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index e02d427131ee..32341dcaa6c1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1164,6 +1164,27 @@ static int hclgevf_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, en_bc_pmc); } +static void hclgevf_request_update_promisc_mode(struct hnae3_handle *handle) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + + set_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state); +} + +static void hclgevf_sync_promisc_mode(struct hclgevf_dev *hdev) +{ + struct hnae3_handle *handle = &hdev->nic; + bool en_uc_pmc = handle->netdev_flags & HNAE3_UPE; + bool en_mc_pmc = handle->netdev_flags & HNAE3_MPE; + int ret; + + if (test_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state)) { + ret = hclgevf_set_promisc_mode(handle, en_uc_pmc, en_mc_pmc); + if (!ret) + clear_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state); + } +} + static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, unsigned int tqp_id, int stream_id, bool enable) { @@ -1245,10 +1266,12 @@ static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p, int status; hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_UNICAST, 0); - send_msg.subcode = is_first ? HCLGE_MBX_MAC_VLAN_UC_ADD : - HCLGE_MBX_MAC_VLAN_UC_MODIFY; + send_msg.subcode = HCLGE_MBX_MAC_VLAN_UC_MODIFY; ether_addr_copy(send_msg.data, new_mac_addr); - ether_addr_copy(&send_msg.data[ETH_ALEN], old_mac_addr); + if (is_first && !hdev->has_pf_mac) + eth_zero_addr(&send_msg.data[ETH_ALEN]); + else + ether_addr_copy(&send_msg.data[ETH_ALEN], old_mac_addr); status = hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0); if (!status) ether_addr_copy(hdev->hw.mac.mac_addr, new_mac_addr); @@ -1256,54 +1279,302 @@ static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p, return status; } -static int hclgevf_add_uc_addr(struct hnae3_handle *handle, - const unsigned char *addr) +static struct hclgevf_mac_addr_node * +hclgevf_find_mac_node(struct list_head *list, const u8 *mac_addr) +{ + struct hclgevf_mac_addr_node *mac_node, *tmp; + + list_for_each_entry_safe(mac_node, tmp, list, node) + if (ether_addr_equal(mac_addr, mac_node->mac_addr)) + return mac_node; + + return NULL; +} + +static void hclgevf_update_mac_node(struct hclgevf_mac_addr_node *mac_node, + enum HCLGEVF_MAC_NODE_STATE state) +{ + switch (state) { + /* from set_rx_mode or tmp_add_list */ + case HCLGEVF_MAC_TO_ADD: + if (mac_node->state == HCLGEVF_MAC_TO_DEL) + mac_node->state = HCLGEVF_MAC_ACTIVE; + break; + /* only from set_rx_mode */ + case HCLGEVF_MAC_TO_DEL: + if (mac_node->state == HCLGEVF_MAC_TO_ADD) { + list_del(&mac_node->node); + kfree(mac_node); + } else { + mac_node->state = HCLGEVF_MAC_TO_DEL; + } + break; + /* only from tmp_add_list, the mac_node->state won't be + * HCLGEVF_MAC_ACTIVE + */ + case HCLGEVF_MAC_ACTIVE: + if (mac_node->state == HCLGEVF_MAC_TO_ADD) + mac_node->state = HCLGEVF_MAC_ACTIVE; + break; + } +} + +static int hclgevf_update_mac_list(struct hnae3_handle *handle, + enum HCLGEVF_MAC_NODE_STATE state, + enum HCLGEVF_MAC_ADDR_TYPE mac_type, + const unsigned char *addr) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct hclge_vf_to_pf_msg send_msg; + struct hclgevf_mac_addr_node *mac_node; + struct list_head *list; - hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_UNICAST, - HCLGE_MBX_MAC_VLAN_UC_ADD); - ether_addr_copy(send_msg.data, addr); - return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); + list = (mac_type == HCLGEVF_MAC_ADDR_UC) ? + &hdev->mac_table.uc_mac_list : &hdev->mac_table.mc_mac_list; + + spin_lock_bh(&hdev->mac_table.mac_list_lock); + + /* if the mac addr is already in the mac list, no need to add a new + * one into it, just check the mac addr state, convert it to a new + * new state, or just remove it, or do nothing. + */ + mac_node = hclgevf_find_mac_node(list, addr); + if (mac_node) { + hclgevf_update_mac_node(mac_node, state); + spin_unlock_bh(&hdev->mac_table.mac_list_lock); + return 0; + } + /* if this address is never added, unnecessary to delete */ + if (state == HCLGEVF_MAC_TO_DEL) { + spin_unlock_bh(&hdev->mac_table.mac_list_lock); + return -ENOENT; + } + + mac_node = kzalloc(sizeof(*mac_node), GFP_ATOMIC); + if (!mac_node) { + spin_unlock_bh(&hdev->mac_table.mac_list_lock); + return -ENOMEM; + } + + mac_node->state = state; + ether_addr_copy(mac_node->mac_addr, addr); + list_add_tail(&mac_node->node, list); + + spin_unlock_bh(&hdev->mac_table.mac_list_lock); + return 0; +} + +static int hclgevf_add_uc_addr(struct hnae3_handle *handle, + const unsigned char *addr) +{ + return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_ADD, + HCLGEVF_MAC_ADDR_UC, addr); } static int hclgevf_rm_uc_addr(struct hnae3_handle *handle, const unsigned char *addr) { - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct hclge_vf_to_pf_msg send_msg; - - hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_UNICAST, - HCLGE_MBX_MAC_VLAN_UC_REMOVE); - ether_addr_copy(send_msg.data, addr); - return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); + return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_DEL, + HCLGEVF_MAC_ADDR_UC, addr); } static int hclgevf_add_mc_addr(struct hnae3_handle *handle, const unsigned char *addr) { - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct hclge_vf_to_pf_msg send_msg; - - hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_MULTICAST, - HCLGE_MBX_MAC_VLAN_MC_ADD); - ether_addr_copy(send_msg.data, addr); - return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); + return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_ADD, + HCLGEVF_MAC_ADDR_MC, addr); } static int hclgevf_rm_mc_addr(struct hnae3_handle *handle, const unsigned char *addr) { - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + return hclgevf_update_mac_list(handle, HCLGEVF_MAC_TO_DEL, + HCLGEVF_MAC_ADDR_MC, addr); +} + +static int hclgevf_add_del_mac_addr(struct hclgevf_dev *hdev, + struct hclgevf_mac_addr_node *mac_node, + enum HCLGEVF_MAC_ADDR_TYPE mac_type) +{ struct hclge_vf_to_pf_msg send_msg; + u8 code, subcode; - hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_MULTICAST, - HCLGE_MBX_MAC_VLAN_MC_REMOVE); - ether_addr_copy(send_msg.data, addr); + if (mac_type == HCLGEVF_MAC_ADDR_UC) { + code = HCLGE_MBX_SET_UNICAST; + if (mac_node->state == HCLGEVF_MAC_TO_ADD) + subcode = HCLGE_MBX_MAC_VLAN_UC_ADD; + else + subcode = HCLGE_MBX_MAC_VLAN_UC_REMOVE; + } else { + code = HCLGE_MBX_SET_MULTICAST; + if (mac_node->state == HCLGEVF_MAC_TO_ADD) + subcode = HCLGE_MBX_MAC_VLAN_MC_ADD; + else + subcode = HCLGE_MBX_MAC_VLAN_MC_REMOVE; + } + + hclgevf_build_send_msg(&send_msg, code, subcode); + ether_addr_copy(send_msg.data, mac_node->mac_addr); return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); } +static void hclgevf_config_mac_list(struct hclgevf_dev *hdev, + struct list_head *list, + enum HCLGEVF_MAC_ADDR_TYPE mac_type) +{ + struct hclgevf_mac_addr_node *mac_node, *tmp; + int ret; + + list_for_each_entry_safe(mac_node, tmp, list, node) { + ret = hclgevf_add_del_mac_addr(hdev, mac_node, mac_type); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to configure mac %pM, state = %d, ret = %d\n", + mac_node->mac_addr, mac_node->state, ret); + return; + } + if (mac_node->state == HCLGEVF_MAC_TO_ADD) { + mac_node->state = HCLGEVF_MAC_ACTIVE; + } else { + list_del(&mac_node->node); + kfree(mac_node); + } + } +} + +static void hclgevf_sync_from_add_list(struct list_head *add_list, + struct list_head *mac_list) +{ + struct hclgevf_mac_addr_node *mac_node, *tmp, *new_node; + + list_for_each_entry_safe(mac_node, tmp, add_list, node) { + /* if the mac address from tmp_add_list is not in the + * uc/mc_mac_list, it means have received a TO_DEL request + * during the time window of sending mac config request to PF + * If mac_node state is ACTIVE, then change its state to TO_DEL, + * then it will be removed at next time. If is TO_ADD, it means + * send TO_ADD request failed, so just remove the mac node. + */ + new_node = hclgevf_find_mac_node(mac_list, mac_node->mac_addr); + if (new_node) { + hclgevf_update_mac_node(new_node, mac_node->state); + list_del(&mac_node->node); + kfree(mac_node); + } else if (mac_node->state == HCLGEVF_MAC_ACTIVE) { + mac_node->state = HCLGEVF_MAC_TO_DEL; + list_del(&mac_node->node); + list_add_tail(&mac_node->node, mac_list); + } else { + list_del(&mac_node->node); + kfree(mac_node); + } + } +} + +static void hclgevf_sync_from_del_list(struct list_head *del_list, + struct list_head *mac_list) +{ + struct hclgevf_mac_addr_node *mac_node, *tmp, *new_node; + + list_for_each_entry_safe(mac_node, tmp, del_list, node) { + new_node = hclgevf_find_mac_node(mac_list, mac_node->mac_addr); + if (new_node) { + /* If the mac addr is exist in the mac list, it means + * received a new request TO_ADD during the time window + * of sending mac addr configurrequest to PF, so just + * change the mac state to ACTIVE. + */ + new_node->state = HCLGEVF_MAC_ACTIVE; + list_del(&mac_node->node); + kfree(mac_node); + } else { + list_del(&mac_node->node); + list_add_tail(&mac_node->node, mac_list); + } + } +} + +static void hclgevf_clear_list(struct list_head *list) +{ + struct hclgevf_mac_addr_node *mac_node, *tmp; + + list_for_each_entry_safe(mac_node, tmp, list, node) { + list_del(&mac_node->node); + kfree(mac_node); + } +} + +static void hclgevf_sync_mac_list(struct hclgevf_dev *hdev, + enum HCLGEVF_MAC_ADDR_TYPE mac_type) +{ + struct hclgevf_mac_addr_node *mac_node, *tmp, *new_node; + struct list_head tmp_add_list, tmp_del_list; + struct list_head *list; + + INIT_LIST_HEAD(&tmp_add_list); + INIT_LIST_HEAD(&tmp_del_list); + + /* move the mac addr to the tmp_add_list and tmp_del_list, then + * we can add/delete these mac addr outside the spin lock + */ + list = (mac_type == HCLGEVF_MAC_ADDR_UC) ? + &hdev->mac_table.uc_mac_list : &hdev->mac_table.mc_mac_list; + + spin_lock_bh(&hdev->mac_table.mac_list_lock); + + list_for_each_entry_safe(mac_node, tmp, list, node) { + switch (mac_node->state) { + case HCLGEVF_MAC_TO_DEL: + list_del(&mac_node->node); + list_add_tail(&mac_node->node, &tmp_del_list); + break; + case HCLGEVF_MAC_TO_ADD: + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) + goto stop_traverse; + + ether_addr_copy(new_node->mac_addr, mac_node->mac_addr); + new_node->state = mac_node->state; + list_add_tail(&new_node->node, &tmp_add_list); + break; + default: + break; + } + } + +stop_traverse: + spin_unlock_bh(&hdev->mac_table.mac_list_lock); + + /* delete first, in order to get max mac table space for adding */ + hclgevf_config_mac_list(hdev, &tmp_del_list, mac_type); + hclgevf_config_mac_list(hdev, &tmp_add_list, mac_type); + + /* if some mac addresses were added/deleted fail, move back to the + * mac_list, and retry at next time. + */ + spin_lock_bh(&hdev->mac_table.mac_list_lock); + + hclgevf_sync_from_del_list(&tmp_del_list, list); + hclgevf_sync_from_add_list(&tmp_add_list, list); + + spin_unlock_bh(&hdev->mac_table.mac_list_lock); +} + +static void hclgevf_sync_mac_table(struct hclgevf_dev *hdev) +{ + hclgevf_sync_mac_list(hdev, HCLGEVF_MAC_ADDR_UC); + hclgevf_sync_mac_list(hdev, HCLGEVF_MAC_ADDR_MC); +} + +static void hclgevf_uninit_mac_list(struct hclgevf_dev *hdev) +{ + spin_lock_bh(&hdev->mac_table.mac_list_lock); + + hclgevf_clear_list(&hdev->mac_table.uc_mac_list); + hclgevf_clear_list(&hdev->mac_table.mc_mac_list); + + spin_unlock_bh(&hdev->mac_table.mac_list_lock); +} + static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, u16 vlan_id, bool is_kill) @@ -1506,10 +1777,6 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev) if (ret) return ret; - ret = hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT); - if (ret) - return ret; - /* clear handshake status with IMP */ hclgevf_reset_handshake(hdev, false); @@ -1589,13 +1856,8 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) static int hclgevf_reset_prepare(struct hclgevf_dev *hdev) { - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); int ret; - /* Initialize ae_dev reset status as well, in case enet layer wants to - * know if device is undergoing reset - */ - ae_dev->reset_type = hdev->reset_type; hdev->rst_stats.rst_cnt++; rtnl_lock(); @@ -1610,7 +1872,6 @@ static int hclgevf_reset_prepare(struct hclgevf_dev *hdev) static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev) { - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); int ret; hdev->rst_stats.hw_rst_done_cnt++; @@ -1625,7 +1886,6 @@ static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev) } hdev->last_reset_time = jiffies; - ae_dev->reset_type = HNAE3_NONE_RESET; hdev->rst_stats.rst_done_cnt++; hdev->rst_stats.rst_fail_cnt = 0; clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state); @@ -1951,6 +2211,10 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev) hclgevf_sync_vlan_filter(hdev); + hclgevf_sync_mac_table(hdev); + + hclgevf_sync_promisc_mode(hdev); + hdev->last_serv_processed = jiffies; out: @@ -2313,6 +2577,10 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev) mutex_init(&hdev->mbx_resp.mbx_mutex); sema_init(&hdev->reset_sem, 1); + spin_lock_init(&hdev->mac_table.mac_list_lock); + INIT_LIST_HEAD(&hdev->mac_table.uc_mac_list); + INIT_LIST_HEAD(&hdev->mac_table.mc_mac_list); + /* bring the device down */ set_bit(HCLGEVF_STATE_DOWN, &hdev->state); } @@ -2695,6 +2963,15 @@ static int hclgevf_pci_reset(struct hclgevf_dev *hdev) return ret; } +static int hclgevf_clear_vport_list(struct hclgevf_dev *hdev) +{ + struct hclge_vf_to_pf_msg send_msg; + + hclgevf_build_send_msg(&send_msg, HCLGE_MBX_HANDLE_VF_TBL, + HCLGE_MBX_VPORT_LIST_CLEAR); + return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); +} + static int hclgevf_reset_hdev(struct hclgevf_dev *hdev) { struct pci_dev *pdev = hdev->pdev; @@ -2730,6 +3007,8 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev) return ret; } + set_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state); + dev_info(&hdev->pdev->dev, "Reset done\n"); return 0; @@ -2802,6 +3081,15 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) goto err_config; } + /* ensure vf tbl list as empty before init*/ + ret = hclgevf_clear_vport_list(hdev); + if (ret) { + dev_err(&pdev->dev, + "failed to clear tbl list configuration, ret = %d.\n", + ret); + goto err_config; + } + ret = hclgevf_init_vlan_config(hdev); if (ret) { dev_err(&hdev->pdev->dev, @@ -2846,6 +3134,7 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev) hclgevf_pci_uninit(hdev); hclgevf_cmd_uninit(hdev); + hclgevf_uninit_mac_list(hdev); } static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev) @@ -3213,6 +3502,7 @@ static const struct hnae3_ae_ops hclgevf_ops = { .set_timer_task = hclgevf_set_timer_task, .get_link_mode = hclgevf_get_link_mode, .set_promisc_mode = hclgevf_set_promisc_mode, + .request_update_promisc_mode = hclgevf_request_update_promisc_mode, }; static struct hnae3_ae_algo ae_algovf = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 3b88d866facc..f19583c4bc9b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -148,6 +148,7 @@ enum hclgevf_states { HCLGEVF_STATE_MBX_HANDLING, HCLGEVF_STATE_CMD_DISABLE, HCLGEVF_STATE_LINK_UPDATING, + HCLGEVF_STATE_PROMISC_CHANGED, HCLGEVF_STATE_RST_FAIL, }; @@ -234,6 +235,29 @@ struct hclgevf_rst_stats { u32 rst_fail_cnt; /* the number of VF reset fail */ }; +enum HCLGEVF_MAC_ADDR_TYPE { + HCLGEVF_MAC_ADDR_UC, + HCLGEVF_MAC_ADDR_MC +}; + +enum HCLGEVF_MAC_NODE_STATE { + HCLGEVF_MAC_TO_ADD, + HCLGEVF_MAC_TO_DEL, + HCLGEVF_MAC_ACTIVE +}; + +struct hclgevf_mac_addr_node { + struct list_head node; + enum HCLGEVF_MAC_NODE_STATE state; + u8 mac_addr[ETH_ALEN]; +}; + +struct hclgevf_mac_table_cfg { + spinlock_t mac_list_lock; /* protect mac address need to add/detele */ + struct list_head uc_mac_list; + struct list_head mc_mac_list; +}; + struct hclgevf_dev { struct pci_dev *pdev; struct hnae3_ae_dev *ae_dev; @@ -282,6 +306,8 @@ struct hclgevf_dev { unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)]; + struct hclgevf_mac_table_cfg mac_table; + bool mbx_event_pending; struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */ struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index 9b8154955f91..5b2dcd97c107 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -5,6 +5,9 @@ #include "hclgevf_main.h" #include "hnae3.h" +#define CREATE_TRACE_POINTS +#include "hclgevf_trace.h" + static int hclgevf_resp_to_errno(u16 resp_code) { return resp_code ? -resp_code : 0; @@ -106,6 +109,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg)); + trace_hclge_vf_mbx_send(hdev, req); + /* synchronous send */ if (need_resp) { mutex_lock(&hdev->mbx_resp.mbx_mutex); @@ -179,6 +184,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) continue; } + trace_hclge_vf_mbx_get(hdev, req); + /* synchronous messages are time critical and need preferential * treatment. Therefore, we need to acknowledge all the sync * responses as quickly as possible so that waiting tasks do not diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h new file mode 100644 index 000000000000..e4bfb6191fef --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2018-2019 Hisilicon Limited. */ + +/* This must be outside ifdef _HCLGEVF_TRACE_H */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hns3 + +#if !defined(_HCLGEVF_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _HCLGEVF_TRACE_H_ + +#include <linux/tracepoint.h> + +#define VF_GET_MBX_LEN (sizeof(struct hclge_mbx_pf_to_vf_cmd) / sizeof(u32)) +#define VF_SEND_MBX_LEN (sizeof(struct hclge_mbx_vf_to_pf_cmd) / sizeof(u32)) + +TRACE_EVENT(hclge_vf_mbx_get, + TP_PROTO( + struct hclgevf_dev *hdev, + struct hclge_mbx_pf_to_vf_cmd *req), + TP_ARGS(hdev, req), + + TP_STRUCT__entry( + __field(u8, vfid) + __field(u16, code) + __string(pciname, pci_name(hdev->pdev)) + __string(devname, &hdev->nic.kinfo.netdev->name) + __array(u32, mbx_data, VF_GET_MBX_LEN) + ), + + TP_fast_assign( + __entry->vfid = req->dest_vfid; + __entry->code = req->msg.code; + __assign_str(pciname, pci_name(hdev->pdev)); + __assign_str(devname, &hdev->nic.kinfo.netdev->name); + memcpy(__entry->mbx_data, req, + sizeof(struct hclge_mbx_pf_to_vf_cmd)); + ), + + TP_printk( + "%s %s vfid:%u code:%u data:%s", + __get_str(pciname), __get_str(devname), __entry->vfid, + __entry->code, + __print_array(__entry->mbx_data, VF_GET_MBX_LEN, sizeof(u32)) + ) +); + +TRACE_EVENT(hclge_vf_mbx_send, + TP_PROTO( + struct hclgevf_dev *hdev, + struct hclge_mbx_vf_to_pf_cmd *req), + TP_ARGS(hdev, req), + + TP_STRUCT__entry( + __field(u8, vfid) + __field(u8, code) + __field(u8, subcode) + __string(pciname, pci_name(hdev->pdev)) + __string(devname, &hdev->nic.kinfo.netdev->name) + __array(u32, mbx_data, VF_SEND_MBX_LEN) + ), + + TP_fast_assign( + __entry->vfid = req->mbx_src_vfid; + __entry->code = req->msg.code; + __entry->subcode = req->msg.subcode; + __assign_str(pciname, pci_name(hdev->pdev)); + __assign_str(devname, &hdev->nic.kinfo.netdev->name); + memcpy(__entry->mbx_data, req, + sizeof(struct hclge_mbx_vf_to_pf_cmd)); + ), + + TP_printk( + "%s %s vfid:%u code:%u subcode:%u data:%s", + __get_str(pciname), __get_str(devname), __entry->vfid, + __entry->code, __entry->subcode, + __print_array(__entry->mbx_data, VF_SEND_MBX_LEN, sizeof(u32)) + ) +); + +#endif /* _HCLGEVF_TRACE_H_ */ + +/* This must be outside ifdef _HCLGEVF_TRACE_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE hclgevf_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile index fe88ab88cacc..32a011ca44c3 100644 --- a/drivers/net/ethernet/huawei/hinic/Makefile +++ b/drivers/net/ethernet/huawei/hinic/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_HINIC) += hinic.o hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \ hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \ hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \ - hinic_common.o hinic_ethtool.o + hinic_common.o hinic_ethtool.o hinic_hw_mbox.o hinic_sriov.o diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h index a209b14160cc..a621ebbf7610 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -16,6 +16,7 @@ #include "hinic_hw_dev.h" #include "hinic_tx.h" #include "hinic_rx.h" +#include "hinic_sriov.h" #define HINIC_DRV_NAME "hinic" @@ -23,6 +24,7 @@ enum hinic_flags { HINIC_LINK_UP = BIT(0), HINIC_INTF_UP = BIT(1), HINIC_RSS_ENABLE = BIT(2), + HINIC_LINK_DOWN = BIT(3), }; struct hinic_rx_mode_work { @@ -78,6 +80,7 @@ struct hinic_dev { struct hinic_rss_type rss_type; u8 *rss_hkey_user; s32 *rss_indir_user; + struct hinic_sriov_info sriov_info; }; #endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c index 5f2d57d1b2d3..33c5333657c1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c @@ -64,7 +64,7 @@ #define CMDQ_WQE_SIZE 64 #define CMDQ_DEPTH SZ_4K -#define CMDQ_WQ_PAGE_SIZE SZ_4K +#define CMDQ_WQ_PAGE_SIZE SZ_256K #define WQE_LCMD_SIZE 64 #define WQE_SCMD_SIZE 64 @@ -705,7 +705,7 @@ static void cmdq_init_queue_ctxt(struct hinic_cmdq_ctxt *cmdq_ctxt, /* The data in the HW is in Big Endian Format */ wq_first_page_paddr = be64_to_cpu(*wq->block_vaddr); - pfn = CMDQ_PFN(wq_first_page_paddr, wq->wq_page_size); + pfn = CMDQ_PFN(wq_first_page_paddr, SZ_4K); ctxt_info->curr_wqe_page_pfn = HINIC_CMDQ_CTXT_PAGE_INFO_SET(pfn, CURR_WQE_PAGE_PFN) | @@ -714,16 +714,19 @@ static void cmdq_init_queue_ctxt(struct hinic_cmdq_ctxt *cmdq_ctxt, HINIC_CMDQ_CTXT_PAGE_INFO_SET(1, CEQ_EN) | HINIC_CMDQ_CTXT_PAGE_INFO_SET(cmdq->wrapped, WRAPPED); - /* block PFN - Read Modify Write */ - cmdq_first_block_paddr = cmdq_pages->page_paddr; + if (wq->num_q_pages != 1) { + /* block PFN - Read Modify Write */ + cmdq_first_block_paddr = cmdq_pages->page_paddr; - pfn = CMDQ_PFN(cmdq_first_block_paddr, wq->wq_page_size); + pfn = CMDQ_PFN(cmdq_first_block_paddr, wq->wq_page_size); + } ctxt_info->wq_block_pfn = HINIC_CMDQ_CTXT_BLOCK_INFO_SET(pfn, WQ_BLOCK_PFN) | HINIC_CMDQ_CTXT_BLOCK_INFO_SET(atomic_read(&wq->cons_idx), CI); cmdq_ctxt->func_idx = HINIC_HWIF_FUNC_IDX(cmdqs->hwif); + cmdq_ctxt->ppf_idx = HINIC_HWIF_PPF_IDX(cmdqs->hwif); cmdq_ctxt->cmdq_type = cmdq->cmdq_type; } @@ -795,11 +798,6 @@ static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev, size_t cmdq_ctxts_size; int err; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI function type\n"); - return -EINVAL; - } - cmdq_ctxts_size = HINIC_MAX_CMDQ_TYPES * sizeof(*cmdq_ctxts); cmdq_ctxts = devm_kzalloc(&pdev->dev, cmdq_ctxts_size, GFP_KERNEL); if (!cmdq_ctxts) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h index 7a434b653faa..3e4b0aef9fe6 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h @@ -122,7 +122,7 @@ struct hinic_cmdq_ctxt { u16 func_idx; u8 cmdq_type; - u8 rsvd1[1]; + u8 ppf_idx; u8 rsvd2[4]; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h index cdec1d0a3962..7e84e4e33fff 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h @@ -10,7 +10,7 @@ /* HW interface registers */ #define HINIC_CSR_FUNC_ATTR0_ADDR 0x0 #define HINIC_CSR_FUNC_ATTR1_ADDR 0x4 - +#define HINIC_CSR_FUNC_ATTR2_ADDR 0x8 #define HINIC_CSR_FUNC_ATTR4_ADDR 0x10 #define HINIC_CSR_FUNC_ATTR5_ADDR 0x14 diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index c7c75b772a86..e5cab58e4ddd 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -15,7 +15,9 @@ #include <linux/jiffies.h> #include <linux/log2.h> #include <linux/err.h> +#include <linux/netdevice.h> +#include "hinic_sriov.h" #include "hinic_hw_if.h" #include "hinic_hw_eqs.h" #include "hinic_hw_mgmt.h" @@ -46,20 +48,6 @@ enum hw_ioctxt_set_cmdq_depth { HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT, }; -/* HW struct */ -struct hinic_dev_cap { - u8 status; - u8 version; - u8 rsvd0[6]; - - u8 rsvd1[5]; - u8 intr_type; - u8 rsvd2[66]; - u16 max_sqs; - u16 max_rqs; - u8 rsvd3[208]; -}; - /** * get_capability - convert device capabilities to NIC capabilities * @hwdev: the HW device to set and convert device capabilities for @@ -67,16 +55,13 @@ struct hinic_dev_cap { * * Return 0 - Success, negative - Failure **/ -static int get_capability(struct hinic_hwdev *hwdev, - struct hinic_dev_cap *dev_cap) +static int parse_capability(struct hinic_hwdev *hwdev, + struct hinic_dev_cap *dev_cap) { struct hinic_cap *nic_cap = &hwdev->nic_cap; int num_aeqs, num_ceqs, num_irqs; - if (!HINIC_IS_PF(hwdev->hwif) && !HINIC_IS_PPF(hwdev->hwif)) - return -EINVAL; - - if (dev_cap->intr_type != INTR_MSIX_TYPE) + if (!HINIC_IS_VF(hwdev->hwif) && dev_cap->intr_type != INTR_MSIX_TYPE) return -EFAULT; num_aeqs = HINIC_HWIF_NUM_AEQS(hwdev->hwif); @@ -89,13 +74,19 @@ static int get_capability(struct hinic_hwdev *hwdev, if (nic_cap->num_qps > HINIC_Q_CTXT_MAX) nic_cap->num_qps = HINIC_Q_CTXT_MAX; - nic_cap->max_qps = dev_cap->max_sqs + 1; - if (nic_cap->max_qps != (dev_cap->max_rqs + 1)) - return -EFAULT; + if (!HINIC_IS_VF(hwdev->hwif)) + nic_cap->max_qps = dev_cap->max_sqs + 1; + else + nic_cap->max_qps = dev_cap->max_sqs; if (nic_cap->num_qps > nic_cap->max_qps) nic_cap->num_qps = nic_cap->max_qps; + if (!HINIC_IS_VF(hwdev->hwif)) { + nic_cap->max_vf = dev_cap->max_vf; + nic_cap->max_vf_qps = dev_cap->max_vf_sqs + 1; + } + return 0; } @@ -105,27 +96,26 @@ static int get_capability(struct hinic_hwdev *hwdev, * * Return 0 - Success, negative - Failure **/ -static int get_cap_from_fw(struct hinic_pfhwdev *pfhwdev) +static int get_capability(struct hinic_pfhwdev *pfhwdev) { struct hinic_hwdev *hwdev = &pfhwdev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; struct hinic_dev_cap dev_cap; - u16 in_len, out_len; + u16 out_len; int err; - in_len = 0; out_len = sizeof(dev_cap); err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_CFGM, - HINIC_CFG_NIC_CAP, &dev_cap, in_len, &dev_cap, - &out_len, HINIC_MGMT_MSG_SYNC); + HINIC_CFG_NIC_CAP, &dev_cap, sizeof(dev_cap), + &dev_cap, &out_len, HINIC_MGMT_MSG_SYNC); if (err) { dev_err(&pdev->dev, "Failed to get capability from FW\n"); return err; } - return get_capability(hwdev, &dev_cap); + return parse_capability(hwdev, &dev_cap); } /** @@ -144,15 +134,14 @@ static int get_dev_cap(struct hinic_hwdev *hwdev) switch (HINIC_FUNC_TYPE(hwif)) { case HINIC_PPF: case HINIC_PF: + case HINIC_VF: pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); - - err = get_cap_from_fw(pfhwdev); + err = get_capability(pfhwdev); if (err) { - dev_err(&pdev->dev, "Failed to get capability from FW\n"); + dev_err(&pdev->dev, "Failed to get capability\n"); return err; } break; - default: dev_err(&pdev->dev, "Unsupported PCI Function type\n"); return -EINVAL; @@ -225,15 +214,8 @@ static void disable_msix(struct hinic_hwdev *hwdev) int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd, void *buf_in, u16 in_size, void *buf_out, u16 *out_size) { - struct hinic_hwif *hwif = hwdev->hwif; - struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "unsupported PCI Function type\n"); - return -EINVAL; - } - pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, cmd, @@ -252,14 +234,9 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev) struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; struct hinic_cmd_fw_ctxt fw_ctxt; - u16 out_size; + u16 out_size = sizeof(fw_ctxt); int err; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI Function type\n"); - return -EINVAL; - } - fw_ctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); fw_ctxt.rx_buf_sz = HINIC_RX_BUF_SZ; @@ -288,14 +265,8 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth, { struct hinic_hwif *hwif = hwdev->hwif; struct hinic_cmd_hw_ioctxt hw_ioctxt; - struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI Function type\n"); - return -EINVAL; - } - hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif); @@ -374,11 +345,6 @@ static int clear_io_resources(struct hinic_hwdev *hwdev) struct hinic_pfhwdev *pfhwdev; int err; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI Function type\n"); - return -EINVAL; - } - /* sleep 100ms to wait for firmware stopping I/O */ msleep(100); @@ -410,14 +376,8 @@ static int set_resources_state(struct hinic_hwdev *hwdev, { struct hinic_cmd_set_res_state res_state; struct hinic_hwif *hwif = hwdev->hwif; - struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI Function type\n"); - return -EINVAL; - } - res_state.func_idx = HINIC_HWIF_FUNC_IDX(hwif); res_state.state = state; @@ -441,8 +401,8 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn) { struct hinic_cmd_base_qpn cmd_base_qpn; struct hinic_hwif *hwif = hwdev->hwif; + u16 out_size = sizeof(cmd_base_qpn); struct pci_dev *pdev = hwif->pdev; - u16 out_size; int err; cmd_base_qpn.func_idx = HINIC_HWIF_FUNC_IDX(hwif); @@ -488,7 +448,7 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev) num_ceqs = HINIC_HWIF_NUM_CEQS(hwif); ceq_msix_entries = &hwdev->msix_entries[num_aeqs]; - + func_to_io->hwdev = hwdev; err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, num_ceqs, ceq_msix_entries); if (err) { @@ -558,17 +518,10 @@ void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev, u16 in_size, void *buf_out, u16 *out_size)) { - struct hinic_hwif *hwif = hwdev->hwif; - struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; struct hinic_nic_cb *nic_cb; u8 cmd_cb; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "unsupported PCI Function type\n"); - return; - } - pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE; @@ -588,15 +541,12 @@ void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev, enum hinic_mgmt_msg_cmd cmd) { struct hinic_hwif *hwif = hwdev->hwif; - struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; struct hinic_nic_cb *nic_cb; u8 cmd_cb; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "unsupported PCI Function type\n"); + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) return; - } pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); @@ -676,10 +626,23 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev) return err; } - hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, - pfhwdev, nic_mgmt_msg_handler); + err = hinic_func_to_func_init(hwdev); + if (err) { + dev_err(&hwif->pdev->dev, "Failed to init mailbox\n"); + hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); + return err; + } + + if (!HINIC_IS_VF(hwif)) + hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, + HINIC_MOD_L2NIC, pfhwdev, + nic_mgmt_msg_handler); + else + hinic_register_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC, + nic_mgmt_msg_handler); hinic_set_pf_action(hwif, HINIC_PF_MGMT_ACTIVE); + return 0; } @@ -693,7 +656,13 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev) hinic_set_pf_action(hwdev->hwif, HINIC_PF_MGMT_INIT); - hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC); + if (!HINIC_IS_VF(hwdev->hwif)) + hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, + HINIC_MOD_L2NIC); + else + hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC); + + hinic_func_to_func_free(hwdev); hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); } @@ -723,12 +692,6 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev) return ERR_PTR(err); } - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI Function type\n"); - err = -EFAULT; - goto err_func_type; - } - pfhwdev = devm_kzalloc(&pdev->dev, sizeof(*pfhwdev), GFP_KERNEL); if (!pfhwdev) { err = -ENOMEM; @@ -772,6 +735,12 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev) goto err_dev_cap; } + err = hinic_vf_func_init(hwdev); + if (err) { + dev_err(&pdev->dev, "Failed to init nic mbox\n"); + goto err_vf_func_init; + } + err = init_fw_ctxt(hwdev); if (err) { dev_err(&pdev->dev, "Failed to init function table\n"); @@ -788,6 +757,8 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev) err_resources_state: err_init_fw_ctxt: + hinic_vf_func_free(hwdev); +err_vf_func_init: err_dev_cap: free_pfhwdev(pfhwdev); @@ -799,7 +770,6 @@ err_aeqs_init: err_init_msix: err_pfhwdev_alloc: -err_func_type: hinic_free_hwif(hwif); return ERR_PTR(err); } @@ -930,15 +900,9 @@ int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq, { struct hinic_qp *qp = container_of(sq, struct hinic_qp, sq); struct hinic_hwif *hwif = hwdev->hwif; - struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; struct hinic_cmd_hw_ci hw_ci; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "Unsupported PCI Function type\n"); - return -EINVAL; - } - hw_ci.dma_attr_off = 0; hw_ci.pending_limit = pending_limit; hw_ci.coalesc_timer = coalesc_timer; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index 66fd2340d447..531d1072e0df 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -16,18 +16,27 @@ #include "hinic_hw_mgmt.h" #include "hinic_hw_qp.h" #include "hinic_hw_io.h" +#include "hinic_hw_mbox.h" #define HINIC_MAX_QPS 32 #define HINIC_MGMT_NUM_MSG_CMD (HINIC_MGMT_MSG_CMD_MAX - \ HINIC_MGMT_MSG_CMD_BASE) +#define HINIC_PF_SET_VF_ALREADY 0x4 +#define HINIC_MGMT_STATUS_EXIST 0x6 + struct hinic_cap { u16 max_qps; u16 num_qps; + u8 max_vf; + u16 max_vf_qps; }; enum hinic_port_cmd { + HINIC_PORT_CMD_VF_REGISTER = 0x0, + HINIC_PORT_CMD_VF_UNREGISTER = 0x1, + HINIC_PORT_CMD_CHANGE_MTU = 2, HINIC_PORT_CMD_ADD_VLAN = 3, @@ -83,10 +92,18 @@ enum hinic_port_cmd { HINIC_PORT_CMD_GET_GLOBAL_QPN = 102, + HINIC_PORT_CMD_SET_VF_VLAN = 106, + + HINIC_PORT_CMD_CLR_VF_VLAN, + HINIC_PORT_CMD_SET_TSO = 112, HINIC_PORT_CMD_SET_RQ_IQ_MAP = 115, + HINIC_PORT_CMD_LINK_STATUS_REPORT = 160, + + HINIC_PORT_CMD_UPDATE_MAC = 164, + HINIC_PORT_CMD_GET_CAP = 170, HINIC_PORT_CMD_SET_LRO_TIMER = 244, @@ -191,6 +208,17 @@ struct hinic_cmd_set_res_state { u32 rsvd2; }; +struct hinic_ceq_ctrl_reg { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_id; + u16 q_id; + u32 ctrl0; + u32 ctrl1; +}; + struct hinic_cmd_base_qpn { u8 status; u8 version; @@ -225,6 +253,7 @@ struct hinic_hwdev { struct hinic_aeqs aeqs; struct hinic_func_to_io func_to_io; + struct hinic_mbox_func_to_func *func_to_func; struct hinic_cap nic_cap; }; @@ -246,6 +275,25 @@ struct hinic_pfhwdev { struct hinic_nic_cb nic_cb[HINIC_MGMT_NUM_MSG_CMD]; }; +struct hinic_dev_cap { + u8 status; + u8 version; + u8 rsvd0[6]; + + u8 rsvd1[5]; + u8 intr_type; + u8 max_cos_id; + u8 er_id; + u8 port_id; + u8 max_vf; + u8 rsvd2[62]; + u16 max_sqs; + u16 max_rqs; + u16 max_vf_sqs; + u16 max_vf_rqs; + u8 rsvd3[204]; +}; + void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev, enum hinic_mgmt_msg_cmd cmd, void *handle, void (*handler)(void *handle, void *buf_in, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c index c0b6bcb067cd..397936cac304 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c @@ -17,6 +17,7 @@ #include <asm/byteorder.h> #include <asm/barrier.h> +#include "hinic_hw_dev.h" #include "hinic_hw_csr.h" #include "hinic_hw_if.h" #include "hinic_hw_eqs.h" @@ -416,11 +417,11 @@ static irqreturn_t ceq_interrupt(int irq, void *data) return IRQ_HANDLED; } -static void set_ctrl0(struct hinic_eq *eq) +static u32 get_ctrl0_val(struct hinic_eq *eq, u32 addr) { struct msix_entry *msix_entry = &eq->msix_entry; enum hinic_eq_type type = eq->type; - u32 addr, val, ctrl0; + u32 val, ctrl0; if (type == HINIC_AEQ) { /* RMW Ctrl0 */ @@ -440,9 +441,7 @@ static void set_ctrl0(struct hinic_eq *eq) HINIC_AEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INT_MODE); val |= ctrl0; - - hinic_hwif_write_reg(eq->hwif, addr, val); - } else if (type == HINIC_CEQ) { + } else { /* RMW Ctrl0 */ addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id); @@ -462,16 +461,28 @@ static void set_ctrl0(struct hinic_eq *eq) HINIC_CEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INTR_MODE); val |= ctrl0; - - hinic_hwif_write_reg(eq->hwif, addr, val); } + return val; } -static void set_ctrl1(struct hinic_eq *eq) +static void set_ctrl0(struct hinic_eq *eq) { + u32 val, addr; + + if (eq->type == HINIC_AEQ) + addr = HINIC_CSR_AEQ_CTRL_0_ADDR(eq->q_id); + else + addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id); + + val = get_ctrl0_val(eq, addr); + + hinic_hwif_write_reg(eq->hwif, addr, val); +} + +static u32 get_ctrl1_val(struct hinic_eq *eq, u32 addr) +{ + u32 page_size_val, elem_size, val, ctrl1; enum hinic_eq_type type = eq->type; - u32 page_size_val, elem_size; - u32 addr, val, ctrl1; if (type == HINIC_AEQ) { /* RMW Ctrl1 */ @@ -491,9 +502,7 @@ static void set_ctrl1(struct hinic_eq *eq) HINIC_AEQ_CTRL_1_SET(page_size_val, PAGE_SIZE); val |= ctrl1; - - hinic_hwif_write_reg(eq->hwif, addr, val); - } else if (type == HINIC_CEQ) { + } else { /* RMW Ctrl1 */ addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id); @@ -508,19 +517,70 @@ static void set_ctrl1(struct hinic_eq *eq) HINIC_CEQ_CTRL_1_SET(page_size_val, PAGE_SIZE); val |= ctrl1; + } + return val; +} - hinic_hwif_write_reg(eq->hwif, addr, val); +static void set_ctrl1(struct hinic_eq *eq) +{ + u32 addr, val; + + if (eq->type == HINIC_AEQ) + addr = HINIC_CSR_AEQ_CTRL_1_ADDR(eq->q_id); + else + addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id); + + val = get_ctrl1_val(eq, addr); + + hinic_hwif_write_reg(eq->hwif, addr, val); +} + +static int set_ceq_ctrl_reg(struct hinic_eq *eq) +{ + struct hinic_ceq_ctrl_reg ceq_ctrl = {0}; + struct hinic_hwdev *hwdev = eq->hwdev; + u16 out_size = sizeof(ceq_ctrl); + u16 in_size = sizeof(ceq_ctrl); + struct hinic_pfhwdev *pfhwdev; + u32 addr; + int err; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id); + ceq_ctrl.ctrl0 = get_ctrl0_val(eq, addr); + addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id); + ceq_ctrl.ctrl1 = get_ctrl1_val(eq, addr); + + ceq_ctrl.func_id = HINIC_HWIF_FUNC_IDX(hwdev->hwif); + ceq_ctrl.q_id = eq->q_id; + + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + HINIC_COMM_CMD_CEQ_CTRL_REG_WR_BY_UP, + &ceq_ctrl, in_size, + &ceq_ctrl, &out_size, HINIC_MGMT_MSG_SYNC); + if (err || !out_size || ceq_ctrl.status) { + dev_err(&hwdev->hwif->pdev->dev, + "Failed to set ceq %d ctrl reg, err: %d status: 0x%x, out_size: 0x%x\n", + eq->q_id, err, ceq_ctrl.status, out_size); + return -EFAULT; } + + return 0; } /** * set_eq_ctrls - setting eq's ctrl registers * @eq: the Event Queue for setting **/ -static void set_eq_ctrls(struct hinic_eq *eq) +static int set_eq_ctrls(struct hinic_eq *eq) { + if (HINIC_IS_VF(eq->hwif) && eq->type == HINIC_CEQ) + return set_ceq_ctrl_reg(eq); + set_ctrl0(eq); set_ctrl1(eq); + return 0; } /** @@ -703,7 +763,12 @@ static int init_eq(struct hinic_eq *eq, struct hinic_hwif *hwif, return -EINVAL; } - set_eq_ctrls(eq); + err = set_eq_ctrls(eq); + if (err) { + dev_err(&pdev->dev, "Failed to set eq ctrls\n"); + return err; + } + eq_update_ci(eq, EQ_ARMED); err = alloc_eq_pages(eq); @@ -859,6 +924,7 @@ int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif, ceqs->num_ceqs = num_ceqs; for (q_id = 0; q_id < num_ceqs; q_id++) { + ceqs->ceq[q_id].hwdev = ceqs->hwdev; err = init_eq(&ceqs->ceq[q_id], hwif, HINIC_CEQ, q_id, q_len, page_size, msix_entries[q_id]); if (err) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h index d35f2068ee0c..74b9ff90640c 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h @@ -143,8 +143,9 @@ enum hinic_eq_type { }; enum hinic_aeq_type { + HINIC_MBX_FROM_FUNC = 1, HINIC_MSG_FROM_MGMT_CPU = 2, - + HINIC_MBX_SEND_RSLT = 5, HINIC_MAX_AEQ_EVENTS, }; @@ -171,7 +172,7 @@ struct hinic_eq_work { struct hinic_eq { struct hinic_hwif *hwif; - + struct hinic_hwdev *hwdev; enum hinic_eq_type type; int q_id; u32 q_len; @@ -219,7 +220,7 @@ struct hinic_ceq_cb { struct hinic_ceqs { struct hinic_hwif *hwif; - + struct hinic_hwdev *hwdev; struct hinic_eq ceq[HINIC_MAX_CEQS]; int num_ceqs; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c index 07bbfbf68577..3fbd2eb80582 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c @@ -115,8 +115,12 @@ int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index) **/ void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action) { - u32 attr5 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR); + u32 attr5; + if (HINIC_IS_VF(hwif)) + return; + + attr5 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR); attr5 = HINIC_FA5_CLEAR(attr5, PF_ACTION); attr5 |= HINIC_FA5_SET(action, PF_ACTION); @@ -203,7 +207,8 @@ static int hwif_ready(struct hinic_hwif *hwif) * @attr0: the first attribute that was read from the hw * @attr1: the second attribute that was read from the hw **/ -static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1) +static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1, + u32 attr2) { hwif->attr.func_idx = HINIC_FA0_GET(attr0, FUNC_IDX); hwif->attr.pf_idx = HINIC_FA0_GET(attr0, PF_IDX); @@ -214,6 +219,8 @@ static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1) hwif->attr.num_ceqs = BIT(HINIC_FA1_GET(attr1, CEQS_PER_FUNC)); hwif->attr.num_irqs = BIT(HINIC_FA1_GET(attr1, IRQS_PER_FUNC)); hwif->attr.num_dma_attr = BIT(HINIC_FA1_GET(attr1, DMA_ATTR_PER_FUNC)); + hwif->attr.global_vf_id_of_pf = HINIC_FA2_GET(attr2, + GLOBAL_VF_ID_OF_PF); } /** @@ -222,7 +229,7 @@ static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1) **/ static void read_hwif_attr(struct hinic_hwif *hwif) { - u32 addr, attr0, attr1; + u32 addr, attr0, attr1, attr2; addr = HINIC_CSR_FUNC_ATTR0_ADDR; attr0 = hinic_hwif_read_reg(hwif, addr); @@ -230,7 +237,10 @@ static void read_hwif_attr(struct hinic_hwif *hwif) addr = HINIC_CSR_FUNC_ATTR1_ADDR; attr1 = hinic_hwif_read_reg(hwif, addr); - set_hwif_attr(hwif, attr0, attr1); + addr = HINIC_CSR_FUNC_ATTR2_ADDR; + attr2 = hinic_hwif_read_reg(hwif, addr); + + set_hwif_attr(hwif, attr0, attr1, attr2); } /** @@ -309,6 +319,34 @@ static void dma_attr_init(struct hinic_hwif *hwif) HINIC_PCIE_SNOOP, HINIC_PCIE_TPH_DISABLE); } +u16 hinic_glb_pf_vf_offset(struct hinic_hwif *hwif) +{ + if (!hwif) + return 0; + + return hwif->attr.global_vf_id_of_pf; +} + +u16 hinic_global_func_id_hw(struct hinic_hwif *hwif) +{ + u32 addr, attr0; + + addr = HINIC_CSR_FUNC_ATTR0_ADDR; + attr0 = hinic_hwif_read_reg(hwif, addr); + + return HINIC_FA0_GET(attr0, FUNC_IDX); +} + +u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif) +{ + u32 addr, attr0; + + addr = HINIC_CSR_FUNC_ATTR0_ADDR; + attr0 = hinic_hwif_read_reg(hwif, addr); + + return HINIC_FA0_GET(attr0, PF_IDX); +} + /** * hinic_init_hwif - initialize the hw interface * @hwif: the HW interface of a pci function device diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h index c7bb9ceca72c..53bb89c1dd26 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -35,6 +35,7 @@ #define HINIC_FA0_FUNC_IDX_SHIFT 0 #define HINIC_FA0_PF_IDX_SHIFT 10 #define HINIC_FA0_PCI_INTF_IDX_SHIFT 14 +#define HINIC_FA0_VF_IN_PF_SHIFT 16 /* reserved members - off 16 */ #define HINIC_FA0_FUNC_TYPE_SHIFT 24 @@ -42,6 +43,7 @@ #define HINIC_FA0_PF_IDX_MASK 0xF #define HINIC_FA0_PCI_INTF_IDX_MASK 0x3 #define HINIC_FA0_FUNC_TYPE_MASK 0x1 +#define HINIC_FA0_VF_IN_PF_MASK 0xFF #define HINIC_FA0_GET(val, member) \ (((val) >> HINIC_FA0_##member##_SHIFT) & HINIC_FA0_##member##_MASK) @@ -64,6 +66,12 @@ #define HINIC_FA1_GET(val, member) \ (((val) >> HINIC_FA1_##member##_SHIFT) & HINIC_FA1_##member##_MASK) +#define HINIC_FA2_GLOBAL_VF_ID_OF_PF_SHIFT 16 +#define HINIC_FA2_GLOBAL_VF_ID_OF_PF_MASK 0x3FF + +#define HINIC_FA2_GET(val, member) \ + (((val) >> HINIC_FA2_##member##_SHIFT) & HINIC_FA2_##member##_MASK) + #define HINIC_FA4_OUTBOUND_STATE_SHIFT 0 #define HINIC_FA4_DB_STATE_SHIFT 1 @@ -140,6 +148,7 @@ #define HINIC_HWIF_PPF_IDX(hwif) ((hwif)->attr.ppf_idx) #define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type) +#define HINIC_IS_VF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_VF) #define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF) #define HINIC_IS_PPF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PPF) @@ -173,6 +182,7 @@ enum hinic_pcie_tph { enum hinic_func_type { HINIC_PF = 0, + HINIC_VF = 1, HINIC_PPF = 2, }; @@ -223,6 +233,8 @@ struct hinic_func_attr { u8 num_ceqs; u8 num_dma_attr; + + u16 global_vf_id_of_pf; }; struct hinic_hwif { @@ -271,6 +283,12 @@ enum hinic_db_state hinic_db_state_get(struct hinic_hwif *hwif); void hinic_db_state_set(struct hinic_hwif *hwif, enum hinic_db_state db_state); +u16 hinic_glb_pf_vf_offset(struct hinic_hwif *hwif); + +u16 hinic_global_func_id_hw(struct hinic_hwif *hwif); + +u16 hinic_pf_id_of_vf_hw(struct hinic_hwif *hwif); + int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev); void hinic_free_hwif(struct hinic_hwif *hwif); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c index d66f86fa3f46..a4581c988a63 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c @@ -15,6 +15,7 @@ #include <linux/io.h> #include <linux/err.h> +#include "hinic_hw_dev.h" #include "hinic_hw_if.h" #include "hinic_hw_eqs.h" #include "hinic_hw_wqe.h" @@ -34,6 +35,8 @@ #define DB_IDX(db, db_base) \ (((unsigned long)(db) - (unsigned long)(db_base)) / HINIC_DB_PAGE_SIZE) +#define HINIC_PAGE_SIZE_HW(pg_size) ((u8)ilog2((u32)((pg_size) >> 12))) + enum io_cmd { IO_CMD_MODIFY_QUEUE_CTXT = 0, IO_CMD_CLEAN_QUEUE_CTXT, @@ -484,6 +487,33 @@ void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io, int num_qps) devm_kfree(&pdev->dev, func_to_io->qps); } +int hinic_set_wq_page_size(struct hinic_hwdev *hwdev, u16 func_idx, + u32 page_size) +{ + struct hinic_wq_page_size page_size_info = {0}; + u16 out_size = sizeof(page_size_info); + struct hinic_pfhwdev *pfhwdev; + int err; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + page_size_info.func_idx = func_idx; + page_size_info.ppf_idx = HINIC_HWIF_PPF_IDX(hwdev->hwif); + page_size_info.page_size = HINIC_PAGE_SIZE_HW(page_size); + + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + HINIC_COMM_CMD_PAGESIZE_SET, &page_size_info, + sizeof(page_size_info), &page_size_info, + &out_size, HINIC_MGMT_MSG_SYNC); + if (err || !out_size || page_size_info.status) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to set wq page size, err: %d, status: 0x%x, out_size: 0x%0x\n", + err, page_size_info.status, out_size); + return -EFAULT; + } + + return 0; +} + /** * hinic_io_init - Initialize the IO components * @func_to_io: func to io channel that holds the IO components @@ -506,6 +536,7 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io, func_to_io->hwif = hwif; func_to_io->qps = NULL; func_to_io->max_qps = max_qps; + func_to_io->ceqs.hwdev = func_to_io->hwdev; err = hinic_ceqs_init(&func_to_io->ceqs, hwif, num_ceqs, HINIC_DEFAULT_CEQ_LEN, HINIC_EQ_PAGE_SIZE, @@ -541,6 +572,14 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io, func_to_io->cmdq_db_area[cmdq] = db_area; } + err = hinic_set_wq_page_size(func_to_io->hwdev, + HINIC_HWIF_FUNC_IDX(hwif), + HINIC_DEFAULT_WQ_PAGE_SIZE); + if (err) { + dev_err(&func_to_io->hwif->pdev->dev, "Failed to set wq page size\n"); + goto init_wq_pg_size_err; + } + err = hinic_init_cmdqs(&func_to_io->cmdqs, hwif, func_to_io->cmdq_db_area); if (err) { @@ -551,6 +590,11 @@ int hinic_io_init(struct hinic_func_to_io *func_to_io, return 0; err_init_cmdqs: + if (!HINIC_IS_VF(func_to_io->hwif)) + hinic_set_wq_page_size(func_to_io->hwdev, + HINIC_HWIF_FUNC_IDX(hwif), + HINIC_HW_WQ_PAGE_SIZE); +init_wq_pg_size_err: err_db_area: for (type = HINIC_CMDQ_SYNC; type < cmdq; type++) return_db_area(func_to_io, func_to_io->cmdq_db_area[type]); @@ -575,6 +619,11 @@ void hinic_io_free(struct hinic_func_to_io *func_to_io) hinic_free_cmdqs(&func_to_io->cmdqs); + if (!HINIC_IS_VF(func_to_io->hwif)) + hinic_set_wq_page_size(func_to_io->hwdev, + HINIC_HWIF_FUNC_IDX(func_to_io->hwif), + HINIC_HW_WQ_PAGE_SIZE); + for (cmdq = HINIC_CMDQ_SYNC; cmdq < HINIC_MAX_CMDQ_TYPES; cmdq++) return_db_area(func_to_io, func_to_io->cmdq_db_area[cmdq]); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h index cac2b722e7dc..28c0594f636d 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h @@ -20,6 +20,8 @@ #define HINIC_DB_PAGE_SIZE SZ_4K #define HINIC_DB_SIZE SZ_4M +#define HINIC_HW_WQ_PAGE_SIZE SZ_4K +#define HINIC_DEFAULT_WQ_PAGE_SIZE SZ_256K #define HINIC_DB_MAX_AREAS (HINIC_DB_SIZE / HINIC_DB_PAGE_SIZE) @@ -47,7 +49,7 @@ struct hinic_free_db_area { struct hinic_func_to_io { struct hinic_hwif *hwif; - + struct hinic_hwdev *hwdev; struct hinic_ceqs ceqs; struct hinic_wqs wqs; @@ -69,8 +71,27 @@ struct hinic_func_to_io { void __iomem *cmdq_db_area[HINIC_MAX_CMDQ_TYPES]; struct hinic_cmdqs cmdqs; + + u16 max_vfs; + struct vf_data_storage *vf_infos; + u8 link_status; }; +struct hinic_wq_page_size { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 ppf_idx; + u8 page_size; + + u32 rsvd1; +}; + +int hinic_set_wq_page_size(struct hinic_hwdev *hwdev, u16 func_idx, + u32 page_size); + int hinic_io_create_qps(struct hinic_func_to_io *func_to_io, u16 base_qpn, int num_qps, struct msix_entry *sq_msix_entries, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c new file mode 100644 index 000000000000..f8626dfd192e --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.c @@ -0,0 +1,1213 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/types.h> +#include <linux/completion.h> +#include <linux/semaphore.h> +#include <linux/spinlock.h> +#include <linux/workqueue.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_mgmt.h" +#include "hinic_hw_csr.h" +#include "hinic_hw_dev.h" +#include "hinic_hw_mbox.h" + +#define HINIC_MBOX_INT_DST_FUNC_SHIFT 0 +#define HINIC_MBOX_INT_DST_AEQN_SHIFT 10 +#define HINIC_MBOX_INT_SRC_RESP_AEQN_SHIFT 12 +#define HINIC_MBOX_INT_STAT_DMA_SHIFT 14 +/* The size of data to be sended (unit of 4 bytes) */ +#define HINIC_MBOX_INT_TX_SIZE_SHIFT 20 +/* SO_RO(strong order, relax order) */ +#define HINIC_MBOX_INT_STAT_DMA_SO_RO_SHIFT 25 +#define HINIC_MBOX_INT_WB_EN_SHIFT 28 + +#define HINIC_MBOX_INT_DST_FUNC_MASK 0x3FF +#define HINIC_MBOX_INT_DST_AEQN_MASK 0x3 +#define HINIC_MBOX_INT_SRC_RESP_AEQN_MASK 0x3 +#define HINIC_MBOX_INT_STAT_DMA_MASK 0x3F +#define HINIC_MBOX_INT_TX_SIZE_MASK 0x1F +#define HINIC_MBOX_INT_STAT_DMA_SO_RO_MASK 0x3 +#define HINIC_MBOX_INT_WB_EN_MASK 0x1 + +#define HINIC_MBOX_INT_SET(val, field) \ + (((val) & HINIC_MBOX_INT_##field##_MASK) << \ + HINIC_MBOX_INT_##field##_SHIFT) + +enum hinic_mbox_tx_status { + TX_NOT_DONE = 1, +}; + +#define HINIC_MBOX_CTRL_TRIGGER_AEQE_SHIFT 0 + +/* specifies the issue request for the message data. + * 0 - Tx request is done; + * 1 - Tx request is in process. + */ +#define HINIC_MBOX_CTRL_TX_STATUS_SHIFT 1 + +#define HINIC_MBOX_CTRL_TRIGGER_AEQE_MASK 0x1 +#define HINIC_MBOX_CTRL_TX_STATUS_MASK 0x1 + +#define HINIC_MBOX_CTRL_SET(val, field) \ + (((val) & HINIC_MBOX_CTRL_##field##_MASK) << \ + HINIC_MBOX_CTRL_##field##_SHIFT) + +#define HINIC_MBOX_HEADER_MSG_LEN_SHIFT 0 +#define HINIC_MBOX_HEADER_MODULE_SHIFT 11 +#define HINIC_MBOX_HEADER_SEG_LEN_SHIFT 16 +#define HINIC_MBOX_HEADER_NO_ACK_SHIFT 22 +#define HINIC_MBOX_HEADER_SEQID_SHIFT 24 +#define HINIC_MBOX_HEADER_LAST_SHIFT 30 + +/* specifies the mailbox message direction + * 0 - send + * 1 - receive + */ +#define HINIC_MBOX_HEADER_DIRECTION_SHIFT 31 +#define HINIC_MBOX_HEADER_CMD_SHIFT 32 +#define HINIC_MBOX_HEADER_MSG_ID_SHIFT 40 +#define HINIC_MBOX_HEADER_STATUS_SHIFT 48 +#define HINIC_MBOX_HEADER_SRC_GLB_FUNC_IDX_SHIFT 54 + +#define HINIC_MBOX_HEADER_MSG_LEN_MASK 0x7FF +#define HINIC_MBOX_HEADER_MODULE_MASK 0x1F +#define HINIC_MBOX_HEADER_SEG_LEN_MASK 0x3F +#define HINIC_MBOX_HEADER_NO_ACK_MASK 0x1 +#define HINIC_MBOX_HEADER_SEQID_MASK 0x3F +#define HINIC_MBOX_HEADER_LAST_MASK 0x1 +#define HINIC_MBOX_HEADER_DIRECTION_MASK 0x1 +#define HINIC_MBOX_HEADER_CMD_MASK 0xFF +#define HINIC_MBOX_HEADER_MSG_ID_MASK 0xFF +#define HINIC_MBOX_HEADER_STATUS_MASK 0x3F +#define HINIC_MBOX_HEADER_SRC_GLB_FUNC_IDX_MASK 0x3FF + +#define HINIC_MBOX_HEADER_GET(val, field) \ + (((val) >> HINIC_MBOX_HEADER_##field##_SHIFT) & \ + HINIC_MBOX_HEADER_##field##_MASK) +#define HINIC_MBOX_HEADER_SET(val, field) \ + ((u64)((val) & HINIC_MBOX_HEADER_##field##_MASK) << \ + HINIC_MBOX_HEADER_##field##_SHIFT) + +#define MBOX_SEGLEN_MASK \ + HINIC_MBOX_HEADER_SET(HINIC_MBOX_HEADER_SEG_LEN_MASK, SEG_LEN) + +#define HINIC_MBOX_SEG_LEN 48 +#define HINIC_MBOX_COMP_TIME 8000U +#define MBOX_MSG_POLLING_TIMEOUT 8000 + +#define HINIC_MBOX_DATA_SIZE 2040 + +#define MBOX_MAX_BUF_SZ 2048UL +#define MBOX_HEADER_SZ 8 + +#define MBOX_INFO_SZ 4 + +/* MBOX size is 64B, 8B for mbox_header, 4B reserved */ +#define MBOX_SEG_LEN 48 +#define MBOX_SEG_LEN_ALIGN 4 +#define MBOX_WB_STATUS_LEN 16UL + +/* mbox write back status is 16B, only first 4B is used */ +#define MBOX_WB_STATUS_ERRCODE_MASK 0xFFFF +#define MBOX_WB_STATUS_MASK 0xFF +#define MBOX_WB_ERROR_CODE_MASK 0xFF00 +#define MBOX_WB_STATUS_FINISHED_SUCCESS 0xFF +#define MBOX_WB_STATUS_FINISHED_WITH_ERR 0xFE +#define MBOX_WB_STATUS_NOT_FINISHED 0x00 + +#define MBOX_STATUS_FINISHED(wb) \ + (((wb) & MBOX_WB_STATUS_MASK) != MBOX_WB_STATUS_NOT_FINISHED) +#define MBOX_STATUS_SUCCESS(wb) \ + (((wb) & MBOX_WB_STATUS_MASK) == MBOX_WB_STATUS_FINISHED_SUCCESS) +#define MBOX_STATUS_ERRCODE(wb) \ + ((wb) & MBOX_WB_ERROR_CODE_MASK) + +#define SEQ_ID_START_VAL 0 +#define SEQ_ID_MAX_VAL 42 + +#define DST_AEQ_IDX_DEFAULT_VAL 0 +#define SRC_AEQ_IDX_DEFAULT_VAL 0 +#define NO_DMA_ATTRIBUTE_VAL 0 + +#define HINIC_MGMT_RSP_AEQN 0 +#define HINIC_MBOX_RSP_AEQN 2 +#define HINIC_MBOX_RECV_AEQN 0 + +#define MBOX_MSG_NO_DATA_LEN 1 + +#define MBOX_BODY_FROM_HDR(header) ((u8 *)(header) + MBOX_HEADER_SZ) +#define MBOX_AREA(hwif) \ + ((hwif)->cfg_regs_bar + HINIC_FUNC_CSR_MAILBOX_DATA_OFF) + +#define IS_PF_OR_PPF_SRC(src_func_idx) ((src_func_idx) < HINIC_MAX_PF_FUNCS) + +#define MBOX_RESPONSE_ERROR 0x1 +#define MBOX_MSG_ID_MASK 0xFF +#define MBOX_MSG_ID(func_to_func) ((func_to_func)->send_msg_id) +#define MBOX_MSG_ID_INC(func_to_func_mbox) (MBOX_MSG_ID(func_to_func_mbox) = \ + (MBOX_MSG_ID(func_to_func_mbox) + 1) & MBOX_MSG_ID_MASK) + +#define FUNC_ID_OFF_SET_8B 8 +#define FUNC_ID_OFF_SET_10B 10 + +/* max message counter wait to process for one function */ +#define HINIC_MAX_MSG_CNT_TO_PROCESS 10 + +#define HINIC_QUEUE_MIN_DEPTH 6 +#define HINIC_QUEUE_MAX_DEPTH 12 +#define HINIC_MAX_RX_BUFFER_SIZE 15 + +enum hinic_hwif_direction_type { + HINIC_HWIF_DIRECT_SEND = 0, + HINIC_HWIF_RESPONSE = 1, +}; + +enum mbox_send_mod { + MBOX_SEND_MSG_INT, +}; + +enum mbox_seg_type { + NOT_LAST_SEG, + LAST_SEG, +}; + +enum mbox_ordering_type { + STRONG_ORDER, +}; + +enum mbox_write_back_type { + WRITE_BACK = 1, +}; + +enum mbox_aeq_trig_type { + NOT_TRIGGER, + TRIGGER, +}; + +/** + * hinic_register_pf_mbox_cb - register mbox callback for pf + * @hwdev: the pointer to hw device + * @mod: specific mod that the callback will handle + * @callback: callback function + * Return: 0 - success, negative - failure + */ +int hinic_register_pf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, + hinic_pf_mbox_cb callback) +{ + struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func; + + if (mod >= HINIC_MOD_MAX) + return -EFAULT; + + func_to_func->pf_mbox_cb[mod] = callback; + + set_bit(HINIC_PF_MBOX_CB_REG, &func_to_func->pf_mbox_cb_state[mod]); + + return 0; +} + +/** + * hinic_register_vf_mbox_cb - register mbox callback for vf + * @hwdev: the pointer to hw device + * @mod: specific mod that the callback will handle + * @callback: callback function + * Return: 0 - success, negative - failure + */ +int hinic_register_vf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, + hinic_vf_mbox_cb callback) +{ + struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func; + + if (mod >= HINIC_MOD_MAX) + return -EFAULT; + + func_to_func->vf_mbox_cb[mod] = callback; + + set_bit(HINIC_VF_MBOX_CB_REG, &func_to_func->vf_mbox_cb_state[mod]); + + return 0; +} + +/** + * hinic_unregister_pf_mbox_cb - unregister the mbox callback for pf + * @hwdev: the pointer to hw device + * @mod: specific mod that the callback will handle + */ +void hinic_unregister_pf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod) +{ + struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func; + + clear_bit(HINIC_PF_MBOX_CB_REG, &func_to_func->pf_mbox_cb_state[mod]); + + while (test_bit(HINIC_PF_MBOX_CB_RUNNING, + &func_to_func->pf_mbox_cb_state[mod])) + usleep_range(900, 1000); + + func_to_func->pf_mbox_cb[mod] = NULL; +} + +/** + * hinic_unregister_vf_mbox_cb - unregister the mbox callback for vf + * @hwdev: the pointer to hw device + * @mod: specific mod that the callback will handle + */ +void hinic_unregister_vf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod) +{ + struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func; + + clear_bit(HINIC_VF_MBOX_CB_REG, &func_to_func->vf_mbox_cb_state[mod]); + + while (test_bit(HINIC_VF_MBOX_CB_RUNNING, + &func_to_func->vf_mbox_cb_state[mod])) + usleep_range(900, 1000); + + func_to_func->vf_mbox_cb[mod] = NULL; +} + +static int recv_vf_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *recv_mbox, + void *buf_out, u16 *out_size) +{ + hinic_vf_mbox_cb cb; + int ret = 0; + + if (recv_mbox->mod >= HINIC_MOD_MAX) { + dev_err(&func_to_func->hwif->pdev->dev, "Receive illegal mbox message, mod = %d\n", + recv_mbox->mod); + return -EINVAL; + } + + set_bit(HINIC_VF_MBOX_CB_RUNNING, + &func_to_func->vf_mbox_cb_state[recv_mbox->mod]); + + cb = func_to_func->vf_mbox_cb[recv_mbox->mod]; + if (cb && test_bit(HINIC_VF_MBOX_CB_REG, + &func_to_func->vf_mbox_cb_state[recv_mbox->mod])) { + cb(func_to_func->hwdev, recv_mbox->cmd, recv_mbox->mbox, + recv_mbox->mbox_len, buf_out, out_size); + } else { + dev_err(&func_to_func->hwif->pdev->dev, "VF mbox cb is not registered\n"); + ret = -EINVAL; + } + + clear_bit(HINIC_VF_MBOX_CB_RUNNING, + &func_to_func->vf_mbox_cb_state[recv_mbox->mod]); + + return ret; +} + +static int +recv_pf_from_vf_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *recv_mbox, + u16 src_func_idx, void *buf_out, + u16 *out_size) +{ + hinic_pf_mbox_cb cb; + u16 vf_id = 0; + int ret; + + if (recv_mbox->mod >= HINIC_MOD_MAX) { + dev_err(&func_to_func->hwif->pdev->dev, "Receive illegal mbox message, mod = %d\n", + recv_mbox->mod); + return -EINVAL; + } + + set_bit(HINIC_PF_MBOX_CB_RUNNING, + &func_to_func->pf_mbox_cb_state[recv_mbox->mod]); + + cb = func_to_func->pf_mbox_cb[recv_mbox->mod]; + if (cb && test_bit(HINIC_PF_MBOX_CB_REG, + &func_to_func->pf_mbox_cb_state[recv_mbox->mod])) { + vf_id = src_func_idx - + hinic_glb_pf_vf_offset(func_to_func->hwif); + ret = cb(func_to_func->hwdev, vf_id, recv_mbox->cmd, + recv_mbox->mbox, recv_mbox->mbox_len, + buf_out, out_size); + } else { + dev_err(&func_to_func->hwif->pdev->dev, "PF mbox mod(0x%x) cb is not registered\n", + recv_mbox->mod); + ret = -EINVAL; + } + + clear_bit(HINIC_PF_MBOX_CB_RUNNING, + &func_to_func->pf_mbox_cb_state[recv_mbox->mod]); + + return ret; +} + +static bool check_mbox_seq_id_and_seg_len(struct hinic_recv_mbox *recv_mbox, + u8 seq_id, u8 seg_len) +{ + if (seq_id > SEQ_ID_MAX_VAL || seg_len > MBOX_SEG_LEN) + return false; + + if (seq_id == 0) { + recv_mbox->seq_id = seq_id; + } else { + if (seq_id != recv_mbox->seq_id + 1) + return false; + + recv_mbox->seq_id = seq_id; + } + + return true; +} + +static void resp_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *recv_mbox) +{ + spin_lock(&func_to_func->mbox_lock); + if (recv_mbox->msg_info.msg_id == func_to_func->send_msg_id && + func_to_func->event_flag == EVENT_START) + complete(&recv_mbox->recv_done); + else + dev_err(&func_to_func->hwif->pdev->dev, + "Mbox response timeout, current send msg id(0x%x), recv msg id(0x%x), status(0x%x)\n", + func_to_func->send_msg_id, recv_mbox->msg_info.msg_id, + recv_mbox->msg_info.status); + spin_unlock(&func_to_func->mbox_lock); +} + +static void recv_func_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *recv_mbox, + u16 src_func_idx); + +static void recv_func_mbox_work_handler(struct work_struct *work) +{ + struct hinic_mbox_work *mbox_work = + container_of(work, struct hinic_mbox_work, work); + struct hinic_recv_mbox *recv_mbox; + + recv_func_mbox_handler(mbox_work->func_to_func, mbox_work->recv_mbox, + mbox_work->src_func_idx); + + recv_mbox = + &mbox_work->func_to_func->mbox_send[mbox_work->src_func_idx]; + + atomic_dec(&recv_mbox->msg_cnt); + + kfree(mbox_work); +} + +static void recv_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, + void *header, struct hinic_recv_mbox *recv_mbox) +{ + void *mbox_body = MBOX_BODY_FROM_HDR(header); + struct hinic_recv_mbox *rcv_mbox_temp = NULL; + u64 mbox_header = *((u64 *)header); + struct hinic_mbox_work *mbox_work; + u8 seq_id, seg_len; + u16 src_func_idx; + int pos; + + seq_id = HINIC_MBOX_HEADER_GET(mbox_header, SEQID); + seg_len = HINIC_MBOX_HEADER_GET(mbox_header, SEG_LEN); + src_func_idx = HINIC_MBOX_HEADER_GET(mbox_header, SRC_GLB_FUNC_IDX); + + if (!check_mbox_seq_id_and_seg_len(recv_mbox, seq_id, seg_len)) { + dev_err(&func_to_func->hwif->pdev->dev, + "Mailbox sequence and segment check fail, src func id: 0x%x, front id: 0x%x, current id: 0x%x, seg len: 0x%x\n", + src_func_idx, recv_mbox->seq_id, seq_id, seg_len); + recv_mbox->seq_id = SEQ_ID_MAX_VAL; + return; + } + + pos = seq_id * MBOX_SEG_LEN; + memcpy((u8 *)recv_mbox->mbox + pos, mbox_body, + HINIC_MBOX_HEADER_GET(mbox_header, SEG_LEN)); + + if (!HINIC_MBOX_HEADER_GET(mbox_header, LAST)) + return; + + recv_mbox->cmd = HINIC_MBOX_HEADER_GET(mbox_header, CMD); + recv_mbox->mod = HINIC_MBOX_HEADER_GET(mbox_header, MODULE); + recv_mbox->mbox_len = HINIC_MBOX_HEADER_GET(mbox_header, MSG_LEN); + recv_mbox->ack_type = HINIC_MBOX_HEADER_GET(mbox_header, NO_ACK); + recv_mbox->msg_info.msg_id = HINIC_MBOX_HEADER_GET(mbox_header, MSG_ID); + recv_mbox->msg_info.status = HINIC_MBOX_HEADER_GET(mbox_header, STATUS); + recv_mbox->seq_id = SEQ_ID_MAX_VAL; + + if (HINIC_MBOX_HEADER_GET(mbox_header, DIRECTION) == + HINIC_HWIF_RESPONSE) { + resp_mbox_handler(func_to_func, recv_mbox); + return; + } + + if (atomic_read(&recv_mbox->msg_cnt) > HINIC_MAX_MSG_CNT_TO_PROCESS) { + dev_warn(&func_to_func->hwif->pdev->dev, + "This function(%u) have %d message wait to process,can't add to work queue\n", + src_func_idx, atomic_read(&recv_mbox->msg_cnt)); + return; + } + + rcv_mbox_temp = kzalloc(sizeof(*rcv_mbox_temp), GFP_KERNEL); + if (!rcv_mbox_temp) + return; + + memcpy(rcv_mbox_temp, recv_mbox, sizeof(*rcv_mbox_temp)); + + rcv_mbox_temp->mbox = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL); + if (!rcv_mbox_temp->mbox) + goto err_alloc_rcv_mbox_msg; + + memcpy(rcv_mbox_temp->mbox, recv_mbox->mbox, MBOX_MAX_BUF_SZ); + + rcv_mbox_temp->buf_out = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL); + if (!rcv_mbox_temp->buf_out) + goto err_alloc_rcv_mbox_buf; + + mbox_work = kzalloc(sizeof(*mbox_work), GFP_KERNEL); + if (!mbox_work) + goto err_alloc_mbox_work; + + mbox_work->func_to_func = func_to_func; + mbox_work->recv_mbox = rcv_mbox_temp; + mbox_work->src_func_idx = src_func_idx; + + atomic_inc(&recv_mbox->msg_cnt); + INIT_WORK(&mbox_work->work, recv_func_mbox_work_handler); + queue_work(func_to_func->workq, &mbox_work->work); + + return; + +err_alloc_mbox_work: + kfree(rcv_mbox_temp->buf_out); + +err_alloc_rcv_mbox_buf: + kfree(rcv_mbox_temp->mbox); + +err_alloc_rcv_mbox_msg: + kfree(rcv_mbox_temp); +} + +void hinic_mbox_func_aeqe_handler(void *handle, void *header, u8 size) +{ + struct hinic_mbox_func_to_func *func_to_func; + u64 mbox_header = *((u64 *)header); + struct hinic_recv_mbox *recv_mbox; + u64 src, dir; + + func_to_func = ((struct hinic_hwdev *)handle)->func_to_func; + + dir = HINIC_MBOX_HEADER_GET(mbox_header, DIRECTION); + src = HINIC_MBOX_HEADER_GET(mbox_header, SRC_GLB_FUNC_IDX); + + if (src >= HINIC_MAX_FUNCTIONS) { + dev_err(&func_to_func->hwif->pdev->dev, + "Mailbox source function id:%u is invalid\n", (u32)src); + return; + } + + recv_mbox = (dir == HINIC_HWIF_DIRECT_SEND) ? + &func_to_func->mbox_send[src] : + &func_to_func->mbox_resp[src]; + + recv_mbox_handler(func_to_func, (u64 *)header, recv_mbox); +} + +void hinic_mbox_self_aeqe_handler(void *handle, void *header, u8 size) +{ + struct hinic_mbox_func_to_func *func_to_func; + struct hinic_send_mbox *send_mbox; + + func_to_func = ((struct hinic_hwdev *)handle)->func_to_func; + send_mbox = &func_to_func->send_mbox; + + complete(&send_mbox->send_done); +} + +static void clear_mbox_status(struct hinic_send_mbox *mbox) +{ + *mbox->wb_status = 0; + + /* clear mailbox write back status */ + wmb(); +} + +static void mbox_copy_header(struct hinic_hwdev *hwdev, + struct hinic_send_mbox *mbox, u64 *header) +{ + u32 i, idx_max = MBOX_HEADER_SZ / sizeof(u32); + u32 *data = (u32 *)header; + + for (i = 0; i < idx_max; i++) + __raw_writel(*(data + i), mbox->data + i * sizeof(u32)); +} + +static void mbox_copy_send_data(struct hinic_hwdev *hwdev, + struct hinic_send_mbox *mbox, void *seg, + u16 seg_len) +{ + u8 mbox_max_buf[MBOX_SEG_LEN] = {0}; + u32 data_len, chk_sz = sizeof(u32); + u32 *data = seg; + u32 i, idx_max; + + /* The mbox message should be aligned in 4 bytes. */ + if (seg_len % chk_sz) { + memcpy(mbox_max_buf, seg, seg_len); + data = (u32 *)mbox_max_buf; + } + + data_len = seg_len; + idx_max = ALIGN(data_len, chk_sz) / chk_sz; + + for (i = 0; i < idx_max; i++) + __raw_writel(*(data + i), + mbox->data + MBOX_HEADER_SZ + i * sizeof(u32)); +} + +static void write_mbox_msg_attr(struct hinic_mbox_func_to_func *func_to_func, + u16 dst_func, u16 dst_aeqn, u16 seg_len, + int poll) +{ + u16 rsp_aeq = (dst_aeqn == 0) ? 0 : HINIC_MBOX_RSP_AEQN; + u32 mbox_int, mbox_ctrl; + + mbox_int = HINIC_MBOX_INT_SET(dst_func, DST_FUNC) | + HINIC_MBOX_INT_SET(dst_aeqn, DST_AEQN) | + HINIC_MBOX_INT_SET(rsp_aeq, SRC_RESP_AEQN) | + HINIC_MBOX_INT_SET(NO_DMA_ATTRIBUTE_VAL, STAT_DMA) | + HINIC_MBOX_INT_SET(ALIGN(MBOX_SEG_LEN + MBOX_HEADER_SZ + + MBOX_INFO_SZ, MBOX_SEG_LEN_ALIGN) >> 2, + TX_SIZE) | + HINIC_MBOX_INT_SET(STRONG_ORDER, STAT_DMA_SO_RO) | + HINIC_MBOX_INT_SET(WRITE_BACK, WB_EN); + + hinic_hwif_write_reg(func_to_func->hwif, + HINIC_FUNC_CSR_MAILBOX_INT_OFFSET_OFF, mbox_int); + + wmb(); /* writing the mbox int attributes */ + mbox_ctrl = HINIC_MBOX_CTRL_SET(TX_NOT_DONE, TX_STATUS); + + if (poll) + mbox_ctrl |= HINIC_MBOX_CTRL_SET(NOT_TRIGGER, TRIGGER_AEQE); + else + mbox_ctrl |= HINIC_MBOX_CTRL_SET(TRIGGER, TRIGGER_AEQE); + + hinic_hwif_write_reg(func_to_func->hwif, + HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF, mbox_ctrl); +} + +void dump_mox_reg(struct hinic_hwdev *hwdev) +{ + u32 val; + + val = hinic_hwif_read_reg(hwdev->hwif, + HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF); + dev_err(&hwdev->hwif->pdev->dev, "Mailbox control reg: 0x%x\n", val); + + val = hinic_hwif_read_reg(hwdev->hwif, + HINIC_FUNC_CSR_MAILBOX_INT_OFFSET_OFF); + dev_err(&hwdev->hwif->pdev->dev, "Mailbox interrupt offset: 0x%x\n", + val); +} + +static u16 get_mbox_status(struct hinic_send_mbox *mbox) +{ + /* write back is 16B, but only use first 4B */ + u64 wb_val = be64_to_cpu(*mbox->wb_status); + + rmb(); /* verify reading before check */ + + return (u16)(wb_val & MBOX_WB_STATUS_ERRCODE_MASK); +} + +static int +wait_for_mbox_seg_completion(struct hinic_mbox_func_to_func *func_to_func, + int poll, u16 *wb_status) +{ + struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox; + struct hinic_hwdev *hwdev = func_to_func->hwdev; + struct completion *done = &send_mbox->send_done; + u32 cnt = 0; + ulong jif; + + if (poll) { + while (cnt < MBOX_MSG_POLLING_TIMEOUT) { + *wb_status = get_mbox_status(send_mbox); + if (MBOX_STATUS_FINISHED(*wb_status)) + break; + + usleep_range(900, 1000); + cnt++; + } + + if (cnt == MBOX_MSG_POLLING_TIMEOUT) { + dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment timeout, wb status: 0x%x\n", + *wb_status); + dump_mox_reg(hwdev); + return -ETIMEDOUT; + } + } else { + jif = msecs_to_jiffies(HINIC_MBOX_COMP_TIME); + if (!wait_for_completion_timeout(done, jif)) { + dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment timeout\n"); + dump_mox_reg(hwdev); + return -ETIMEDOUT; + } + + *wb_status = get_mbox_status(send_mbox); + } + + return 0; +} + +static int send_mbox_seg(struct hinic_mbox_func_to_func *func_to_func, + u64 header, u16 dst_func, void *seg, u16 seg_len, + int poll, void *msg_info) +{ + struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox; + u16 seq_dir = HINIC_MBOX_HEADER_GET(header, DIRECTION); + struct hinic_hwdev *hwdev = func_to_func->hwdev; + struct completion *done = &send_mbox->send_done; + u8 num_aeqs = hwdev->hwif->attr.num_aeqs; + u16 dst_aeqn, wb_status = 0, errcode; + + if (num_aeqs >= 4) + dst_aeqn = (seq_dir == HINIC_HWIF_DIRECT_SEND) ? + HINIC_MBOX_RECV_AEQN : HINIC_MBOX_RSP_AEQN; + else + dst_aeqn = 0; + + if (!poll) + init_completion(done); + + clear_mbox_status(send_mbox); + + mbox_copy_header(hwdev, send_mbox, &header); + + mbox_copy_send_data(hwdev, send_mbox, seg, seg_len); + + write_mbox_msg_attr(func_to_func, dst_func, dst_aeqn, seg_len, poll); + + wmb(); /* writing the mbox msg attributes */ + + if (wait_for_mbox_seg_completion(func_to_func, poll, &wb_status)) + return -ETIMEDOUT; + + if (!MBOX_STATUS_SUCCESS(wb_status)) { + dev_err(&hwdev->hwif->pdev->dev, "Send mailbox segment to function %d error, wb status: 0x%x\n", + dst_func, wb_status); + errcode = MBOX_STATUS_ERRCODE(wb_status); + return errcode ? errcode : -EFAULT; + } + + return 0; +} + +static int send_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func, + enum hinic_mod_type mod, u16 cmd, void *msg, + u16 msg_len, u16 dst_func, + enum hinic_hwif_direction_type direction, + enum hinic_mbox_ack_type ack_type, + struct mbox_msg_info *msg_info) +{ + struct hinic_hwdev *hwdev = func_to_func->hwdev; + u16 seg_len = MBOX_SEG_LEN; + u8 *msg_seg = (u8 *)msg; + u16 left = msg_len; + u32 seq_id = 0; + u64 header = 0; + int err = 0; + + down(&func_to_func->msg_send_sem); + + header = HINIC_MBOX_HEADER_SET(msg_len, MSG_LEN) | + HINIC_MBOX_HEADER_SET(mod, MODULE) | + HINIC_MBOX_HEADER_SET(seg_len, SEG_LEN) | + HINIC_MBOX_HEADER_SET(ack_type, NO_ACK) | + HINIC_MBOX_HEADER_SET(SEQ_ID_START_VAL, SEQID) | + HINIC_MBOX_HEADER_SET(NOT_LAST_SEG, LAST) | + HINIC_MBOX_HEADER_SET(direction, DIRECTION) | + HINIC_MBOX_HEADER_SET(cmd, CMD) | + /* The vf's offset to it's associated pf */ + HINIC_MBOX_HEADER_SET(msg_info->msg_id, MSG_ID) | + HINIC_MBOX_HEADER_SET(msg_info->status, STATUS) | + HINIC_MBOX_HEADER_SET(hinic_global_func_id_hw(hwdev->hwif), + SRC_GLB_FUNC_IDX); + + while (!(HINIC_MBOX_HEADER_GET(header, LAST))) { + if (left <= HINIC_MBOX_SEG_LEN) { + header &= ~MBOX_SEGLEN_MASK; + header |= HINIC_MBOX_HEADER_SET(left, SEG_LEN); + header |= HINIC_MBOX_HEADER_SET(LAST_SEG, LAST); + + seg_len = left; + } + + err = send_mbox_seg(func_to_func, header, dst_func, msg_seg, + seg_len, MBOX_SEND_MSG_INT, msg_info); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to send mbox seg, seq_id=0x%llx\n", + HINIC_MBOX_HEADER_GET(header, SEQID)); + goto err_send_mbox_seg; + } + + left -= HINIC_MBOX_SEG_LEN; + msg_seg += HINIC_MBOX_SEG_LEN; + + seq_id++; + header &= ~(HINIC_MBOX_HEADER_SET(HINIC_MBOX_HEADER_SEQID_MASK, + SEQID)); + header |= HINIC_MBOX_HEADER_SET(seq_id, SEQID); + } + +err_send_mbox_seg: + up(&func_to_func->msg_send_sem); + + return err; +} + +static void +response_for_recv_func_mbox(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *recv_mbox, int err, + u16 out_size, u16 src_func_idx) +{ + struct mbox_msg_info msg_info = {0}; + + if (recv_mbox->ack_type == MBOX_ACK) { + msg_info.msg_id = recv_mbox->msg_info.msg_id; + if (err == HINIC_MBOX_PF_BUSY_ACTIVE_FW) + msg_info.status = HINIC_MBOX_PF_BUSY_ACTIVE_FW; + else if (err == HINIC_MBOX_VF_CMD_ERROR) + msg_info.status = HINIC_MBOX_VF_CMD_ERROR; + else if (err) + msg_info.status = HINIC_MBOX_PF_SEND_ERR; + + /* if no data needs to response, set out_size to 1 */ + if (!out_size || err) + out_size = MBOX_MSG_NO_DATA_LEN; + + send_mbox_to_func(func_to_func, recv_mbox->mod, recv_mbox->cmd, + recv_mbox->buf_out, out_size, src_func_idx, + HINIC_HWIF_RESPONSE, MBOX_ACK, + &msg_info); + } +} + +static void recv_func_mbox_handler(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *recv_mbox, + u16 src_func_idx) +{ + void *buf_out = recv_mbox->buf_out; + u16 out_size = MBOX_MAX_BUF_SZ; + int err = 0; + + if (HINIC_IS_VF(func_to_func->hwif)) { + err = recv_vf_mbox_handler(func_to_func, recv_mbox, buf_out, + &out_size); + } else { + if (IS_PF_OR_PPF_SRC(src_func_idx)) + dev_warn(&func_to_func->hwif->pdev->dev, + "Unsupported pf2pf mbox msg\n"); + else + err = recv_pf_from_vf_mbox_handler(func_to_func, + recv_mbox, + src_func_idx, + buf_out, &out_size); + } + + response_for_recv_func_mbox(func_to_func, recv_mbox, err, out_size, + src_func_idx); + kfree(recv_mbox->buf_out); + kfree(recv_mbox->mbox); + kfree(recv_mbox); +} + +static void set_mbox_to_func_event(struct hinic_mbox_func_to_func *func_to_func, + enum mbox_event_state event_flag) +{ + spin_lock(&func_to_func->mbox_lock); + func_to_func->event_flag = event_flag; + spin_unlock(&func_to_func->mbox_lock); +} + +static int mbox_resp_info_handler(struct hinic_mbox_func_to_func *func_to_func, + struct hinic_recv_mbox *mbox_for_resp, + enum hinic_mod_type mod, u16 cmd, + void *buf_out, u16 *out_size) +{ + int err; + + if (mbox_for_resp->msg_info.status) { + err = mbox_for_resp->msg_info.status; + if (err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) + dev_err(&func_to_func->hwif->pdev->dev, "Mbox response error(0x%x)\n", + mbox_for_resp->msg_info.status); + return err; + } + + if (buf_out && out_size) { + if (*out_size < mbox_for_resp->mbox_len) { + dev_err(&func_to_func->hwif->pdev->dev, + "Invalid response mbox message length: %d for mod %d cmd %d, should less than: %d\n", + mbox_for_resp->mbox_len, mod, cmd, *out_size); + return -EFAULT; + } + + if (mbox_for_resp->mbox_len) + memcpy(buf_out, mbox_for_resp->mbox, + mbox_for_resp->mbox_len); + + *out_size = mbox_for_resp->mbox_len; + } + + return 0; +} + +int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func, + enum hinic_mod_type mod, u16 cmd, u16 dst_func, + void *buf_in, u16 in_size, void *buf_out, + u16 *out_size, u32 timeout) +{ + struct hinic_recv_mbox *mbox_for_resp; + struct mbox_msg_info msg_info = {0}; + ulong timeo; + int err; + + mbox_for_resp = &func_to_func->mbox_resp[dst_func]; + + down(&func_to_func->mbox_send_sem); + + init_completion(&mbox_for_resp->recv_done); + + msg_info.msg_id = MBOX_MSG_ID_INC(func_to_func); + + set_mbox_to_func_event(func_to_func, EVENT_START); + + err = send_mbox_to_func(func_to_func, mod, cmd, buf_in, in_size, + dst_func, HINIC_HWIF_DIRECT_SEND, MBOX_ACK, + &msg_info); + if (err) { + dev_err(&func_to_func->hwif->pdev->dev, "Send mailbox failed, msg_id: %d\n", + msg_info.msg_id); + set_mbox_to_func_event(func_to_func, EVENT_FAIL); + goto err_send_mbox; + } + + timeo = msecs_to_jiffies(timeout ? timeout : HINIC_MBOX_COMP_TIME); + if (!wait_for_completion_timeout(&mbox_for_resp->recv_done, timeo)) { + set_mbox_to_func_event(func_to_func, EVENT_TIMEOUT); + dev_err(&func_to_func->hwif->pdev->dev, + "Send mbox msg timeout, msg_id: %d\n", msg_info.msg_id); + err = -ETIMEDOUT; + goto err_send_mbox; + } + + set_mbox_to_func_event(func_to_func, EVENT_END); + + err = mbox_resp_info_handler(func_to_func, mbox_for_resp, mod, cmd, + buf_out, out_size); + +err_send_mbox: + up(&func_to_func->mbox_send_sem); + + return err; +} + +static int mbox_func_params_valid(struct hinic_mbox_func_to_func *func_to_func, + void *buf_in, u16 in_size) +{ + if (in_size > HINIC_MBOX_DATA_SIZE) { + dev_err(&func_to_func->hwif->pdev->dev, + "Mbox msg len(%d) exceed limit(%d)\n", + in_size, HINIC_MBOX_DATA_SIZE); + return -EINVAL; + } + + return 0; +} + +int hinic_mbox_to_pf(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size, u32 timeout) +{ + struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func; + int err = mbox_func_params_valid(func_to_func, buf_in, in_size); + + if (err) + return err; + + if (!HINIC_IS_VF(hwdev->hwif)) { + dev_err(&hwdev->hwif->pdev->dev, "Params error, func_type: %d\n", + HINIC_FUNC_TYPE(hwdev->hwif)); + return -EINVAL; + } + + return hinic_mbox_to_func(func_to_func, mod, cmd, + hinic_pf_id_of_vf_hw(hwdev->hwif), buf_in, + in_size, buf_out, out_size, timeout); +} + +int hinic_mbox_to_vf(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, u16 vf_id, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size, u32 timeout) +{ + struct hinic_mbox_func_to_func *func_to_func; + u16 dst_func_idx; + int err; + + if (!hwdev) + return -EINVAL; + + func_to_func = hwdev->func_to_func; + err = mbox_func_params_valid(func_to_func, buf_in, in_size); + if (err) + return err; + + if (HINIC_IS_VF(hwdev->hwif)) { + dev_err(&hwdev->hwif->pdev->dev, "Params error, func_type: %d\n", + HINIC_FUNC_TYPE(hwdev->hwif)); + return -EINVAL; + } + + if (!vf_id) { + dev_err(&hwdev->hwif->pdev->dev, + "VF id(%d) error!\n", vf_id); + return -EINVAL; + } + + /* vf_offset_to_pf + vf_id is the vf's global function id of vf in + * this pf + */ + dst_func_idx = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id; + + return hinic_mbox_to_func(func_to_func, mod, cmd, dst_func_idx, buf_in, + in_size, buf_out, out_size, timeout); +} + +static int init_mbox_info(struct hinic_recv_mbox *mbox_info) +{ + int err; + + mbox_info->seq_id = SEQ_ID_MAX_VAL; + + mbox_info->mbox = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL); + if (!mbox_info->mbox) + return -ENOMEM; + + mbox_info->buf_out = kzalloc(MBOX_MAX_BUF_SZ, GFP_KERNEL); + if (!mbox_info->buf_out) { + err = -ENOMEM; + goto err_alloc_buf_out; + } + + atomic_set(&mbox_info->msg_cnt, 0); + + return 0; + +err_alloc_buf_out: + kfree(mbox_info->mbox); + + return err; +} + +static void clean_mbox_info(struct hinic_recv_mbox *mbox_info) +{ + kfree(mbox_info->buf_out); + kfree(mbox_info->mbox); +} + +static int alloc_mbox_info(struct hinic_hwdev *hwdev, + struct hinic_recv_mbox *mbox_info) +{ + u16 func_idx, i; + int err; + + for (func_idx = 0; func_idx < HINIC_MAX_FUNCTIONS; func_idx++) { + err = init_mbox_info(&mbox_info[func_idx]); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to init function %d mbox info\n", + func_idx); + goto err_init_mbox_info; + } + } + + return 0; + +err_init_mbox_info: + for (i = 0; i < func_idx; i++) + clean_mbox_info(&mbox_info[i]); + + return err; +} + +static void free_mbox_info(struct hinic_recv_mbox *mbox_info) +{ + u16 func_idx; + + for (func_idx = 0; func_idx < HINIC_MAX_FUNCTIONS; func_idx++) + clean_mbox_info(&mbox_info[func_idx]); +} + +static void prepare_send_mbox(struct hinic_mbox_func_to_func *func_to_func) +{ + struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox; + + send_mbox->data = MBOX_AREA(func_to_func->hwif); +} + +static int alloc_mbox_wb_status(struct hinic_mbox_func_to_func *func_to_func) +{ + struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox; + struct hinic_hwdev *hwdev = func_to_func->hwdev; + u32 addr_h, addr_l; + + send_mbox->wb_vaddr = dma_alloc_coherent(&hwdev->hwif->pdev->dev, + MBOX_WB_STATUS_LEN, + &send_mbox->wb_paddr, + GFP_KERNEL); + if (!send_mbox->wb_vaddr) + return -ENOMEM; + + send_mbox->wb_status = send_mbox->wb_vaddr; + + addr_h = upper_32_bits(send_mbox->wb_paddr); + addr_l = lower_32_bits(send_mbox->wb_paddr); + + hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_H_OFF, + addr_h); + hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_L_OFF, + addr_l); + + return 0; +} + +static void free_mbox_wb_status(struct hinic_mbox_func_to_func *func_to_func) +{ + struct hinic_send_mbox *send_mbox = &func_to_func->send_mbox; + struct hinic_hwdev *hwdev = func_to_func->hwdev; + + hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_H_OFF, + 0); + hinic_hwif_write_reg(hwdev->hwif, HINIC_FUNC_CSR_MAILBOX_RESULT_L_OFF, + 0); + + dma_free_coherent(&hwdev->hwif->pdev->dev, MBOX_WB_STATUS_LEN, + send_mbox->wb_vaddr, + send_mbox->wb_paddr); +} + +static int comm_pf_mbox_handler(void *handle, u16 vf_id, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size) +{ + struct hinic_hwdev *hwdev = handle; + struct hinic_pfhwdev *pfhwdev; + int err = 0; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + if (cmd == HINIC_COMM_CMD_START_FLR) { + *out_size = 0; + } else { + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + cmd, buf_in, in_size, buf_out, out_size, + HINIC_MGMT_MSG_SYNC); + if (err && err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) + dev_err(&hwdev->hwif->pdev->dev, + "PF mbox common callback handler err: %d\n", + err); + } + + return err; +} + +int hinic_func_to_func_init(struct hinic_hwdev *hwdev) +{ + struct hinic_mbox_func_to_func *func_to_func; + struct hinic_pfhwdev *pfhwdev; + int err; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + func_to_func = kzalloc(sizeof(*func_to_func), GFP_KERNEL); + if (!func_to_func) + return -ENOMEM; + + hwdev->func_to_func = func_to_func; + func_to_func->hwdev = hwdev; + func_to_func->hwif = hwdev->hwif; + sema_init(&func_to_func->mbox_send_sem, 1); + sema_init(&func_to_func->msg_send_sem, 1); + spin_lock_init(&func_to_func->mbox_lock); + func_to_func->workq = create_singlethread_workqueue(HINIC_MBOX_WQ_NAME); + if (!func_to_func->workq) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to initialize MBOX workqueue\n"); + err = -ENOMEM; + goto err_create_mbox_workq; + } + + err = alloc_mbox_info(hwdev, func_to_func->mbox_send); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to alloc mem for mbox_active\n"); + goto err_alloc_mbox_for_send; + } + + err = alloc_mbox_info(hwdev, func_to_func->mbox_resp); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to alloc mem for mbox_passive\n"); + goto err_alloc_mbox_for_resp; + } + + err = alloc_mbox_wb_status(func_to_func); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to alloc mbox write back status\n"); + goto err_alloc_wb_status; + } + + prepare_send_mbox(func_to_func); + + hinic_aeq_register_hw_cb(&hwdev->aeqs, HINIC_MBX_FROM_FUNC, + &pfhwdev->hwdev, hinic_mbox_func_aeqe_handler); + hinic_aeq_register_hw_cb(&hwdev->aeqs, HINIC_MBX_SEND_RSLT, + &pfhwdev->hwdev, hinic_mbox_self_aeqe_handler); + + if (!HINIC_IS_VF(hwdev->hwif)) + hinic_register_pf_mbox_cb(hwdev, HINIC_MOD_COMM, + comm_pf_mbox_handler); + + return 0; + +err_alloc_wb_status: + free_mbox_info(func_to_func->mbox_resp); + +err_alloc_mbox_for_resp: + free_mbox_info(func_to_func->mbox_send); + +err_alloc_mbox_for_send: + destroy_workqueue(func_to_func->workq); + +err_create_mbox_workq: + kfree(func_to_func); + + return err; +} + +void hinic_func_to_func_free(struct hinic_hwdev *hwdev) +{ + struct hinic_mbox_func_to_func *func_to_func = hwdev->func_to_func; + + hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MBX_FROM_FUNC); + hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MBX_SEND_RSLT); + + hinic_unregister_pf_mbox_cb(hwdev, HINIC_MOD_COMM); + /* destroy workqueue before free related mbox resources in case of + * illegal resource access + */ + destroy_workqueue(func_to_func->workq); + + free_mbox_wb_status(func_to_func); + free_mbox_info(func_to_func->mbox_resp); + free_mbox_info(func_to_func->mbox_send); + + kfree(func_to_func); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h new file mode 100644 index 000000000000..7b18559bfe80 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mbox.h @@ -0,0 +1,154 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#ifndef HINIC_MBOX_H_ +#define HINIC_MBOX_H_ + +#define HINIC_MBOX_PF_SEND_ERR 0x1 +#define HINIC_MBOX_PF_BUSY_ACTIVE_FW 0x2 +#define HINIC_MBOX_VF_CMD_ERROR 0x3 + +#define HINIC_MAX_FUNCTIONS 512 + +#define HINIC_MAX_PF_FUNCS 16 + +#define HINIC_MBOX_WQ_NAME "hinic_mbox" + +#define HINIC_FUNC_CSR_MAILBOX_DATA_OFF 0x80 +#define HINIC_FUNC_CSR_MAILBOX_CONTROL_OFF 0x0100 +#define HINIC_FUNC_CSR_MAILBOX_INT_OFFSET_OFF 0x0104 +#define HINIC_FUNC_CSR_MAILBOX_RESULT_H_OFF 0x0108 +#define HINIC_FUNC_CSR_MAILBOX_RESULT_L_OFF 0x010C + +enum hinic_mbox_ack_type { + MBOX_ACK, + MBOX_NO_ACK, +}; + +struct mbox_msg_info { + u8 msg_id; + u8 status; +}; + +struct hinic_recv_mbox { + struct completion recv_done; + void *mbox; + u8 cmd; + enum hinic_mod_type mod; + u16 mbox_len; + void *buf_out; + enum hinic_mbox_ack_type ack_type; + struct mbox_msg_info msg_info; + u8 seq_id; + atomic_t msg_cnt; +}; + +struct hinic_send_mbox { + struct completion send_done; + u8 *data; + + u64 *wb_status; + void *wb_vaddr; + dma_addr_t wb_paddr; +}; + +typedef void (*hinic_vf_mbox_cb)(void *handle, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size); +typedef int (*hinic_pf_mbox_cb)(void *handle, u16 vf_id, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size); + +enum mbox_event_state { + EVENT_START = 0, + EVENT_FAIL, + EVENT_TIMEOUT, + EVENT_END, +}; + +enum hinic_mbox_cb_state { + HINIC_VF_MBOX_CB_REG = 0, + HINIC_VF_MBOX_CB_RUNNING, + HINIC_PF_MBOX_CB_REG, + HINIC_PF_MBOX_CB_RUNNING, + HINIC_PPF_MBOX_CB_REG, + HINIC_PPF_MBOX_CB_RUNNING, + HINIC_PPF_TO_PF_MBOX_CB_REG, + HINIC_PPF_TO_PF_MBOX_CB_RUNNIG, +}; + +struct hinic_mbox_func_to_func { + struct hinic_hwdev *hwdev; + struct hinic_hwif *hwif; + + struct semaphore mbox_send_sem; + struct semaphore msg_send_sem; + struct hinic_send_mbox send_mbox; + + struct workqueue_struct *workq; + + struct hinic_recv_mbox mbox_resp[HINIC_MAX_FUNCTIONS]; + struct hinic_recv_mbox mbox_send[HINIC_MAX_FUNCTIONS]; + + hinic_vf_mbox_cb vf_mbox_cb[HINIC_MOD_MAX]; + hinic_pf_mbox_cb pf_mbox_cb[HINIC_MOD_MAX]; + unsigned long pf_mbox_cb_state[HINIC_MOD_MAX]; + unsigned long vf_mbox_cb_state[HINIC_MOD_MAX]; + + u8 send_msg_id; + enum mbox_event_state event_flag; + + /* lock for mbox event flag */ + spinlock_t mbox_lock; +}; + +struct hinic_mbox_work { + struct work_struct work; + u16 src_func_idx; + struct hinic_mbox_func_to_func *func_to_func; + struct hinic_recv_mbox *recv_mbox; +}; + +struct vf_cmd_msg_handle { + u8 cmd; + int (*cmd_msg_handler)(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size); +}; + +int hinic_register_pf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, + hinic_pf_mbox_cb callback); + +int hinic_register_vf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, + hinic_vf_mbox_cb callback); + +void hinic_unregister_pf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod); + +void hinic_unregister_vf_mbox_cb(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod); + +void hinic_mbox_func_aeqe_handler(void *handle, void *header, u8 size); + +void hinic_mbox_self_aeqe_handler(void *handle, void *header, u8 size); + +int hinic_func_to_func_init(struct hinic_hwdev *hwdev); + +void hinic_func_to_func_free(struct hinic_hwdev *hwdev); + +int hinic_mbox_to_pf(struct hinic_hwdev *hwdev, enum hinic_mod_type mod, + u8 cmd, void *buf_in, u16 in_size, void *buf_out, + u16 *out_size, u32 timeout); + +int hinic_mbox_to_func(struct hinic_mbox_func_to_func *func_to_func, + enum hinic_mod_type mod, u16 cmd, u16 dst_func, + void *buf_in, u16 in_size, void *buf_out, + u16 *out_size, u32 timeout); + +int hinic_mbox_to_vf(struct hinic_hwdev *hwdev, + enum hinic_mod_type mod, u16 vf_id, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size, u32 timeout); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index 8995e32dd1c0..eef855f11a01 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -353,7 +353,11 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, return -EINVAL; } - return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, + if (HINIC_IS_VF(hwif)) + return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in, + in_size, buf_out, out_size, 0); + else + return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, buf_out, out_size, MGMT_DIRECT_SEND, MSG_NOT_RESP); } @@ -390,8 +394,8 @@ static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt, recv_msg->msg, recv_msg->msg_len, buf_out, &out_size); else - dev_err(&pdev->dev, "No MGMT msg handler, mod = %d\n", - recv_msg->mod); + dev_err(&pdev->dev, "No MGMT msg handler, mod: %d, cmd: %d\n", + recv_msg->mod, recv_msg->cmd); mgmt_cb->state &= ~HINIC_MGMT_CB_RUNNING; @@ -553,6 +557,10 @@ int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt, int err; pf_to_mgmt->hwif = hwif; + pf_to_mgmt->hwdev = hwdev; + + if (HINIC_IS_VF(hwif)) + return 0; sema_init(&pf_to_mgmt->sync_msg_lock, 1); pf_to_mgmt->sync_msg_id = 0; @@ -584,6 +592,9 @@ void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt) struct hinic_pfhwdev *pfhwdev = mgmt_to_pfhwdev(pf_to_mgmt); struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + if (HINIC_IS_VF(hwdev->hwif)) + return; + hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU); hinic_api_cmd_free(pf_to_mgmt->cmd_chain); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h index 182fba17b643..c2b142c08b0e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h @@ -60,7 +60,9 @@ enum hinic_cfg_cmd { }; enum hinic_comm_cmd { + HINIC_COMM_CMD_START_FLR = 0x1, HINIC_COMM_CMD_IO_STATUS_GET = 0x3, + HINIC_COMM_CMD_DMA_ATTR_SET = 0x4, HINIC_COMM_CMD_CMDQ_CTXT_SET = 0x10, HINIC_COMM_CMD_CMDQ_CTXT_GET = 0x11, @@ -74,7 +76,13 @@ enum hinic_comm_cmd { HINIC_COMM_CMD_IO_RES_CLEAR = 0x29, - HINIC_COMM_CMD_MAX = 0x32, + HINIC_COMM_CMD_CEQ_CTRL_REG_WR_BY_UP = 0x33, + + HINIC_COMM_CMD_L2NIC_RESET = 0x4b, + + HINIC_COMM_CMD_PAGESIZE_SET = 0x50, + + HINIC_COMM_CMD_MAX = 0x51, }; enum hinic_mgmt_cb_state { @@ -107,7 +115,7 @@ struct hinic_mgmt_cb { struct hinic_pf_to_mgmt { struct hinic_hwif *hwif; - + struct hinic_hwdev *hwdev; struct semaphore sync_msg_lock; u16 sync_msg_id; u8 *sync_msg_buf; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c index be364b7a7019..20c5c8ea452e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c @@ -108,7 +108,12 @@ void hinic_sq_prepare_ctxt(struct hinic_sq_ctxt *sq_ctxt, wq_page_pfn_hi = upper_32_bits(wq_page_pfn); wq_page_pfn_lo = lower_32_bits(wq_page_pfn); - wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq->block_paddr); + /* If only one page, use 0-level CLA */ + if (wq->num_q_pages == 1) + wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq_page_addr); + else + wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq->block_paddr); + wq_block_pfn_hi = upper_32_bits(wq_block_pfn); wq_block_pfn_lo = lower_32_bits(wq_block_pfn); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index 79091e131418..c30d092e48d5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -38,8 +38,8 @@ #define HINIC_SQ_WQEBB_SIZE 64 #define HINIC_RQ_WQEBB_SIZE 32 -#define HINIC_SQ_PAGE_SIZE SZ_4K -#define HINIC_RQ_PAGE_SIZE SZ_4K +#define HINIC_SQ_PAGE_SIZE SZ_256K +#define HINIC_RQ_PAGE_SIZE SZ_256K #define HINIC_SQ_DEPTH SZ_4K #define HINIC_RQ_DEPTH SZ_4K diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c index 03363216ff59..5dc3743f8091 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c @@ -503,7 +503,7 @@ err_alloc_wq_pages: * Return 0 - Success, negative - Failure **/ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq, - u16 wqebb_size, u16 wq_page_size, u16 q_depth, + u16 wqebb_size, u32 wq_page_size, u16 q_depth, u16 max_wqe_size) { struct hinic_hwif *hwif = wqs->hwif; @@ -600,7 +600,7 @@ void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq) **/ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages, struct hinic_wq *wq, struct hinic_hwif *hwif, - int cmdq_blocks, u16 wqebb_size, u16 wq_page_size, + int cmdq_blocks, u16 wqebb_size, u32 wq_page_size, u16 q_depth, u16 max_wqe_size) { struct pci_dev *pdev = hwif->pdev; @@ -768,7 +768,10 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size, *prod_idx = curr_prod_idx; - if (curr_pg != end_pg) { + /* If we only have one page, still need to get shadown wqe when + * wqe rolling-over page + */ + if (curr_pg != end_pg || MASKED_WQE_IDX(wq, end_prod_idx) < *prod_idx) { void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *prod_idx); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h index 811eef744140..b06f8c0255de 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h @@ -26,7 +26,7 @@ struct hinic_wq { int block_idx; u16 wqebb_size; - u16 wq_page_size; + u32 wq_page_size; u16 q_depth; u16 max_wqe_size; u16 num_wqebbs_per_page; @@ -76,7 +76,7 @@ struct hinic_cmdq_pages { int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages, struct hinic_wq *wq, struct hinic_hwif *hwif, - int cmdq_blocks, u16 wqebb_size, u16 wq_page_size, + int cmdq_blocks, u16 wqebb_size, u32 wq_page_size, u16 q_depth, u16 max_wqe_size); void hinic_wqs_cmdq_free(struct hinic_cmdq_pages *cmdq_pages, @@ -88,7 +88,7 @@ int hinic_wqs_alloc(struct hinic_wqs *wqs, int num_wqs, void hinic_wqs_free(struct hinic_wqs *wqs); int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq, - u16 wqebb_size, u16 wq_page_size, u16 q_depth, + u16 wqebb_size, u32 wq_page_size, u16 q_depth, u16 max_wqe_size); void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 13560975c103..b66bb86cff96 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -29,6 +29,7 @@ #include "hinic_tx.h" #include "hinic_rx.h" #include "hinic_dev.h" +#include "hinic_sriov.h" MODULE_AUTHOR("Huawei Technologies CO., Ltd"); MODULE_DESCRIPTION("Huawei Intelligent NIC driver"); @@ -46,6 +47,7 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)"); #define HINIC_DEV_ID_DUAL_PORT_100GE 0x0200 #define HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ 0x0205 #define HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ 0x0210 +#define HINIC_DEV_ID_VF 0x375e #define HINIC_WQ_NAME "hinic_dev" @@ -65,6 +67,8 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)"); #define rx_mode_work_to_nic_dev(rx_mode_work) \ container_of(rx_mode_work, struct hinic_dev, rx_mode_work) +#define HINIC_WAIT_SRIOV_CFG_TIMEOUT 15000 + static int change_mac_addr(struct net_device *netdev, const u8 *addr); static int set_features(struct hinic_dev *nic_dev, @@ -423,8 +427,9 @@ static int hinic_open(struct net_device *netdev) goto err_func_port_state; } - /* Wait up to 3 sec between port enable to link state */ - msleep(3000); + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + /* Wait up to 3 sec between port enable to link state */ + msleep(3000); down(&nic_dev->mgmt_lock); @@ -434,6 +439,9 @@ static int hinic_open(struct net_device *netdev) goto err_port_link; } + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + hinic_notify_all_vfs_link_changed(nic_dev->hwdev, link_state); + if (link_state == HINIC_LINK_STATE_UP) nic_dev->flags |= HINIC_LINK_UP; @@ -497,6 +505,9 @@ static int hinic_close(struct net_device *netdev) up(&nic_dev->mgmt_lock); + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + hinic_notify_all_vfs_link_changed(nic_dev->hwdev, 0); + err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); if (err) { netif_err(nic_dev, drv, netdev, @@ -685,7 +696,7 @@ static int hinic_vlan_rx_add_vid(struct net_device *netdev, } err = hinic_port_add_mac(nic_dev, netdev->dev_addr, vid); - if (err) { + if (err && err != HINIC_PF_SET_VF_ALREADY) { netif_err(nic_dev, drv, netdev, "Failed to set mac\n"); goto err_add_mac; } @@ -737,8 +748,6 @@ static void set_rx_mode(struct work_struct *work) struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work); struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work); - netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n"); - hinic_port_set_rx_mode(nic_dev, rx_mode_work->rx_mode); __dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr); @@ -770,8 +779,26 @@ static void hinic_set_rx_mode(struct net_device *netdev) static void hinic_tx_timeout(struct net_device *netdev, unsigned int txqueue) { struct hinic_dev *nic_dev = netdev_priv(netdev); + u16 sw_pi, hw_ci, sw_ci; + struct hinic_sq *sq; + u16 num_sqs, q_id; + + num_sqs = hinic_hwdev_num_qps(nic_dev->hwdev); netif_err(nic_dev, drv, netdev, "Tx timeout\n"); + + for (q_id = 0; q_id < num_sqs; q_id++) { + if (!netif_xmit_stopped(netdev_get_tx_queue(netdev, q_id))) + continue; + + sq = hinic_hwdev_get_sq(nic_dev->hwdev, q_id); + sw_pi = atomic_read(&sq->wq->prod_idx) & sq->wq->mask; + hw_ci = be16_to_cpu(*(u16 *)(sq->hw_ci_addr)) & sq->wq->mask; + sw_ci = atomic_read(&sq->wq->cons_idx) & sq->wq->mask; + netif_err(nic_dev, drv, netdev, "Txq%d: sw_pi: %d, hw_ci: %d, sw_ci: %d, napi->state: 0x%lx\n", + q_id, sw_pi, hw_ci, sw_ci, + nic_dev->txqs[q_id].napi.state); + } } static void hinic_get_stats64(struct net_device *netdev, @@ -837,6 +864,26 @@ static const struct net_device_ops hinic_netdev_ops = { .ndo_get_stats64 = hinic_get_stats64, .ndo_fix_features = hinic_fix_features, .ndo_set_features = hinic_set_features, + .ndo_set_vf_mac = hinic_ndo_set_vf_mac, + .ndo_set_vf_vlan = hinic_ndo_set_vf_vlan, + .ndo_get_vf_config = hinic_ndo_get_vf_config, + .ndo_set_vf_trust = hinic_ndo_set_vf_trust, +}; + +static const struct net_device_ops hinicvf_netdev_ops = { + .ndo_open = hinic_open, + .ndo_stop = hinic_close, + .ndo_change_mtu = hinic_change_mtu, + .ndo_set_mac_address = hinic_set_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_vlan_rx_add_vid = hinic_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = hinic_vlan_rx_kill_vid, + .ndo_set_rx_mode = hinic_set_rx_mode, + .ndo_start_xmit = hinic_xmit_frame, + .ndo_tx_timeout = hinic_tx_timeout, + .ndo_get_stats64 = hinic_get_stats64, + .ndo_fix_features = hinic_fix_features, + .ndo_set_features = hinic_set_features, }; static void netdev_features_init(struct net_device *netdev) @@ -896,6 +943,10 @@ static void link_status_event_handler(void *handle, void *buf_in, u16 in_size, netif_info(nic_dev, drv, nic_dev->netdev, "HINIC_Link is DOWN\n"); } + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + hinic_notify_all_vfs_link_changed(nic_dev->hwdev, + link_status->link); + ret_link_status = buf_out; ret_link_status->status = 0; @@ -969,7 +1020,12 @@ static int nic_dev_init(struct pci_dev *pdev) } hinic_set_ethtool_ops(netdev); - netdev->netdev_ops = &hinic_netdev_ops; + + if (!HINIC_IS_VF(hwdev->hwif)) + netdev->netdev_ops = &hinic_netdev_ops; + else + netdev->netdev_ops = &hinicvf_netdev_ops; + netdev->max_mtu = ETH_MAX_MTU; nic_dev = netdev_priv(netdev); @@ -981,6 +1037,8 @@ static int nic_dev_init(struct pci_dev *pdev) nic_dev->rxqs = NULL; nic_dev->tx_weight = tx_weight; nic_dev->rx_weight = rx_weight; + nic_dev->sriov_info.hwdev = hwdev; + nic_dev->sriov_info.pdev = pdev; sema_init(&nic_dev->mgmt_lock, 1); @@ -1007,11 +1065,25 @@ static int nic_dev_init(struct pci_dev *pdev) pci_set_drvdata(pdev, netdev); err = hinic_port_get_mac(nic_dev, netdev->dev_addr); - if (err) - dev_warn(&pdev->dev, "Failed to get mac address\n"); + if (err) { + dev_err(&pdev->dev, "Failed to get mac address\n"); + goto err_get_mac; + } + + if (!is_valid_ether_addr(netdev->dev_addr)) { + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) { + dev_err(&pdev->dev, "Invalid MAC address\n"); + err = -EIO; + goto err_add_mac; + } + + dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", + netdev->dev_addr); + eth_hw_addr_random(netdev); + } err = hinic_port_add_mac(nic_dev, netdev->dev_addr, 0); - if (err) { + if (err && err != HINIC_PF_SET_VF_ALREADY) { dev_err(&pdev->dev, "Failed to add mac\n"); goto err_add_mac; } @@ -1053,6 +1125,7 @@ err_set_features: cancel_work_sync(&rx_mode_work->work); err_set_mtu: +err_get_mac: err_add_mac: pci_set_drvdata(pdev, NULL); destroy_workqueue(nic_dev->workq); @@ -1126,12 +1199,37 @@ err_pci_regions: return err; } +#define HINIC_WAIT_SRIOV_CFG_TIMEOUT 15000 + +static void wait_sriov_cfg_complete(struct hinic_dev *nic_dev) +{ + struct hinic_sriov_info *sriov_info = &nic_dev->sriov_info; + u32 loop_cnt = 0; + + set_bit(HINIC_FUNC_REMOVE, &sriov_info->state); + usleep_range(9900, 10000); + + while (loop_cnt < HINIC_WAIT_SRIOV_CFG_TIMEOUT) { + if (!test_bit(HINIC_SRIOV_ENABLE, &sriov_info->state) && + !test_bit(HINIC_SRIOV_DISABLE, &sriov_info->state)) + return; + + usleep_range(9900, 10000); + loop_cnt++; + } +} + static void hinic_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct hinic_dev *nic_dev = netdev_priv(netdev); struct hinic_rx_mode_work *rx_mode_work; + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) { + wait_sriov_cfg_complete(nic_dev); + hinic_pci_sriov_disable(pdev); + } + unregister_netdev(netdev); hinic_hwdev_cb_unregister(nic_dev->hwdev, @@ -1144,6 +1242,8 @@ static void hinic_remove(struct pci_dev *pdev) destroy_workqueue(nic_dev->workq); + hinic_vf_func_free(nic_dev->hwdev); + hinic_free_hwdev(nic_dev->hwdev); free_netdev(netdev); @@ -1164,6 +1264,7 @@ static const struct pci_device_id hinic_pci_table[] = { { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0}, { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ), 0}, { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ), 0}, + { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_VF), 0}, { 0, 0} }; MODULE_DEVICE_TABLE(pci, hinic_pci_table); @@ -1174,6 +1275,7 @@ static struct pci_driver hinic_driver = { .probe = hinic_probe, .remove = hinic_remove, .shutdown = hinic_shutdown, + .sriov_configure = hinic_pci_sriov_configure, }; module_pci_driver(hinic_driver); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index 1e389a004e50..b7fe0adcc29a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -37,20 +37,14 @@ enum mac_op { static int change_mac(struct hinic_dev *nic_dev, const u8 *addr, u16 vlan_id, enum mac_op op) { - struct net_device *netdev = nic_dev->netdev; struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_port_mac_cmd port_mac_cmd; struct hinic_hwif *hwif = hwdev->hwif; + u16 out_size = sizeof(port_mac_cmd); struct pci_dev *pdev = hwif->pdev; enum hinic_port_cmd cmd; - u16 out_size; int err; - if (vlan_id >= VLAN_N_VID) { - netif_err(nic_dev, drv, netdev, "Invalid VLAN number\n"); - return -EINVAL; - } - if (op == MAC_SET) cmd = HINIC_PORT_CMD_SET_MAC; else @@ -63,12 +57,25 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr, err = hinic_port_msg_cmd(hwdev, cmd, &port_mac_cmd, sizeof(port_mac_cmd), &port_mac_cmd, &out_size); - if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) { + if (err || out_size != sizeof(port_mac_cmd) || + (port_mac_cmd.status && + port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY && + port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) { dev_err(&pdev->dev, "Failed to change MAC, ret = %d\n", port_mac_cmd.status); return -EFAULT; } + if (cmd == HINIC_PORT_CMD_SET_MAC && port_mac_cmd.status == + HINIC_PF_SET_VF_ALREADY) { + dev_warn(&pdev->dev, "PF has already set VF mac, Ignore set operation\n"); + return HINIC_PF_SET_VF_ALREADY; + } + + if (cmd == HINIC_PORT_CMD_SET_MAC && port_mac_cmd.status == + HINIC_MGMT_STATUS_EXIST) + dev_warn(&pdev->dev, "MAC is repeated. Ignore set operation\n"); + return 0; } @@ -112,8 +119,8 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr) struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_port_mac_cmd port_mac_cmd; struct hinic_hwif *hwif = hwdev->hwif; + u16 out_size = sizeof(port_mac_cmd); struct pci_dev *pdev = hwif->pdev; - u16 out_size; int err; port_mac_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); @@ -144,9 +151,9 @@ int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu) struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_port_mtu_cmd port_mtu_cmd; struct hinic_hwif *hwif = hwdev->hwif; + u16 out_size = sizeof(port_mtu_cmd); struct pci_dev *pdev = hwif->pdev; int err, max_frame; - u16 out_size; if (new_mtu < HINIC_MIN_MTU_SIZE) { netif_err(nic_dev, drv, netdev, "mtu < MIN MTU size"); @@ -248,14 +255,9 @@ int hinic_port_link_state(struct hinic_dev *nic_dev, struct hinic_hwif *hwif = hwdev->hwif; struct hinic_port_link_cmd link_cmd; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(link_cmd); int err; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "unsupported PCI Function type\n"); - return -EINVAL; - } - link_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_STATE, @@ -284,13 +286,11 @@ int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state) struct hinic_port_state_cmd port_state; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(port_state); int err; - if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { - dev_err(&pdev->dev, "unsupported PCI Function type\n"); - return -EINVAL; - } + if (HINIC_IS_VF(hwdev->hwif)) + return 0; port_state.state = state; @@ -320,7 +320,7 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev, struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(func_state); int err; func_state.func_idx = HINIC_HWIF_FUNC_IDX(hwif); @@ -351,7 +351,7 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev, struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(*port_cap); int err; port_cap->func_idx = HINIC_HWIF_FUNC_IDX(hwif); @@ -382,7 +382,7 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state) struct hinic_hwif *hwif = hwdev->hwif; struct hinic_tso_config tso_cfg = {0}; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(tso_cfg); int err; tso_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -405,9 +405,9 @@ int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en) { struct hinic_checksum_offload rx_csum_cfg = {0}; struct hinic_hwdev *hwdev = nic_dev->hwdev; + u16 out_size = sizeof(rx_csum_cfg); struct hinic_hwif *hwif; struct pci_dev *pdev; - u16 out_size; int err; if (!hwdev) @@ -443,6 +443,7 @@ int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en) if (!hwdev) return -EINVAL; + out_size = sizeof(vlan_cfg); hwif = hwdev->hwif; pdev = hwif->pdev; vlan_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -465,8 +466,8 @@ int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs) { struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; - struct pci_dev *pdev = hwif->pdev; struct hinic_rq_num rq_num = { 0 }; + struct pci_dev *pdev = hwif->pdev; u16 out_size = sizeof(rq_num); int err; @@ -491,8 +492,8 @@ static int hinic_set_rx_lro(struct hinic_dev *nic_dev, u8 ipv4_en, u8 ipv6_en, u8 max_wqe_num) { struct hinic_hwdev *hwdev = nic_dev->hwdev; - struct hinic_hwif *hwif = hwdev->hwif; struct hinic_lro_config lro_cfg = { 0 }; + struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; u16 out_size = sizeof(lro_cfg); int err; @@ -568,6 +569,9 @@ int hinic_set_rx_lro_state(struct hinic_dev *nic_dev, u8 lro_en, if (err) return err; + if (HINIC_IS_VF(nic_dev->hwdev->hwif)) + return 0; + err = hinic_set_rx_lro_timer(nic_dev, lro_timer); if (err) return err; @@ -741,9 +745,9 @@ int hinic_get_rss_type(struct hinic_dev *nic_dev, u32 tmpl_idx, { struct hinic_rss_context_table ctx_tbl = { 0 }; struct hinic_hwdev *hwdev = nic_dev->hwdev; + u16 out_size = sizeof(ctx_tbl); struct hinic_hwif *hwif; struct pci_dev *pdev; - u16 out_size = sizeof(ctx_tbl); int err; if (!hwdev || !rss_type) @@ -784,7 +788,7 @@ int hinic_rss_set_template_tbl(struct hinic_dev *nic_dev, u32 template_id, struct hinic_hwif *hwif = hwdev->hwif; struct hinic_rss_key rss_key = { 0 }; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(rss_key); int err; rss_key.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -809,9 +813,9 @@ int hinic_rss_get_template_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx, { struct hinic_rss_template_key temp_key = { 0 }; struct hinic_hwdev *hwdev = nic_dev->hwdev; + u16 out_size = sizeof(temp_key); struct hinic_hwif *hwif; struct pci_dev *pdev; - u16 out_size = sizeof(temp_key); int err; if (!hwdev || !temp) @@ -844,7 +848,7 @@ int hinic_rss_set_hash_engine(struct hinic_dev *nic_dev, u8 template_id, struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(rss_engine); int err; rss_engine.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -868,9 +872,9 @@ int hinic_rss_get_hash_engine(struct hinic_dev *nic_dev, u8 tmpl_idx, u8 *type) { struct hinic_rss_engine_type hash_type = { 0 }; struct hinic_hwdev *hwdev = nic_dev->hwdev; + u16 out_size = sizeof(hash_type); struct hinic_hwif *hwif; struct pci_dev *pdev; - u16 out_size = sizeof(hash_type); int err; if (!hwdev || !type) @@ -901,7 +905,7 @@ int hinic_rss_cfg(struct hinic_dev *nic_dev, u8 rss_en, u8 template_id) struct hinic_rss_config rss_cfg = { 0 }; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - u16 out_size; + u16 out_size = sizeof(rss_cfg); int err; rss_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -927,8 +931,8 @@ int hinic_rss_template_alloc(struct hinic_dev *nic_dev, u8 *tmpl_idx) struct hinic_rss_template_mgmt template_mgmt = { 0 }; struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; + u16 out_size = sizeof(template_mgmt); struct pci_dev *pdev = hwif->pdev; - u16 out_size; int err; template_mgmt.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -953,8 +957,8 @@ int hinic_rss_template_free(struct hinic_dev *nic_dev, u8 tmpl_idx) struct hinic_rss_template_mgmt template_mgmt = { 0 }; struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; + u16 out_size = sizeof(template_mgmt); struct pci_dev *pdev = hwif->pdev; - u16 out_size; int err; template_mgmt.func_id = HINIC_HWIF_FUNC_IDX(hwif); @@ -1043,9 +1047,9 @@ int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver) { struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_version_info up_ver = {0}; + u16 out_size = sizeof(up_ver); struct hinic_hwif *hwif; struct pci_dev *pdev; - u16 out_size; int err; if (!hwdev) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h index 44772fd47fc1..5ad04fb6722a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h @@ -148,9 +148,9 @@ struct hinic_port_link_status { u8 version; u8 rsvd0[6]; - u16 rsvd1; + u16 func_id; u8 link; - u8 rsvd2; + u8 port_id; }; struct hinic_port_func_state_cmd { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 815649e37cb1..af20d0dd6de7 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -432,9 +432,11 @@ static int rx_poll(struct napi_struct *napi, int budget) return budget; napi_complete(napi); - hinic_hwdev_set_msix_state(nic_dev->hwdev, - rq->msix_entry, - HINIC_MSIX_ENABLE); + + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + hinic_hwdev_set_msix_state(nic_dev->hwdev, + rq->msix_entry, + HINIC_MSIX_ENABLE); return pkts; } @@ -461,9 +463,10 @@ static irqreturn_t rx_irq(int irq, void *data) /* Disable the interrupt until napi will be completed */ nic_dev = netdev_priv(rxq->netdev); - hinic_hwdev_set_msix_state(nic_dev->hwdev, - rq->msix_entry, - HINIC_MSIX_DISABLE); + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + hinic_hwdev_set_msix_state(nic_dev->hwdev, + rq->msix_entry, + HINIC_MSIX_DISABLE); nic_dev = netdev_priv(rxq->netdev); hinic_hwdev_msix_cnt_set(nic_dev->hwdev, rq->msix_entry); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c new file mode 100644 index 000000000000..b24788e9733c --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -0,0 +1,1016 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#include <linux/pci.h> +#include <linux/if_vlan.h> +#include <linux/interrupt.h> +#include <linux/etherdevice.h> +#include <linux/netdevice.h> + +#include "hinic_hw_dev.h" +#include "hinic_dev.h" +#include "hinic_hw_mbox.h" +#include "hinic_hw_cmdq.h" +#include "hinic_port.h" +#include "hinic_sriov.h" + +static unsigned char set_vf_link_state; +module_param(set_vf_link_state, byte, 0444); +MODULE_PARM_DESC(set_vf_link_state, "Set vf link state, 0 represents link auto, 1 represents link always up, 2 represents link always down. - default is 0."); + +#define HINIC_VLAN_PRIORITY_SHIFT 13 +#define HINIC_ADD_VLAN_IN_MAC 0x8000 + +int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id, + u16 func_id) +{ + struct hinic_port_mac_cmd mac_info = {0}; + u16 out_size = sizeof(mac_info); + int err; + + mac_info.func_idx = func_id; + mac_info.vlan_id = vlan_id; + memcpy(mac_info.mac, mac_addr, ETH_ALEN); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_MAC, &mac_info, + sizeof(mac_info), &mac_info, &out_size); + if (err || out_size != sizeof(mac_info) || + (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY && + mac_info.status != HINIC_MGMT_STATUS_EXIST)) { + dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to change MAC, ret = %d\n", + mac_info.status); + return -EFAULT; + } + + return 0; +} + +static void hinic_notify_vf_link_status(struct hinic_hwdev *hwdev, u16 vf_id, + u8 link_status) +{ + struct vf_data_storage *vf_infos = hwdev->func_to_io.vf_infos; + struct hinic_port_link_status link = {0}; + u16 out_size = sizeof(link); + int err; + + if (vf_infos[HW_VF_ID_TO_OS(vf_id)].registered) { + link.link = link_status; + link.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id; + err = hinic_mbox_to_vf(hwdev, HINIC_MOD_L2NIC, + vf_id, HINIC_PORT_CMD_LINK_STATUS_REPORT, + &link, sizeof(link), + &link, &out_size, 0); + if (err || !out_size || link.status) + dev_err(&hwdev->hwif->pdev->dev, + "Send link change event to VF %d failed, err: %d, status: 0x%x, out_size: 0x%x\n", + HW_VF_ID_TO_OS(vf_id), err, + link.status, out_size); + } +} + +/* send link change event mbox msg to active vfs under the pf */ +void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev, + u8 link_status) +{ + struct hinic_func_to_io *nic_io = &hwdev->func_to_io; + u16 i; + + nic_io->link_status = link_status; + for (i = 1; i <= nic_io->max_vfs; i++) { + if (!nic_io->vf_infos[HW_VF_ID_TO_OS(i)].link_forced) + hinic_notify_vf_link_status(hwdev, i, link_status); + } +} + +u16 hinic_vf_info_vlanprio(struct hinic_hwdev *hwdev, int vf_id) +{ + struct hinic_func_to_io *nic_io = &hwdev->func_to_io; + u16 pf_vlan, vlanprio; + u8 pf_qos; + + pf_vlan = nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan; + pf_qos = nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos; + vlanprio = pf_vlan | pf_qos << HINIC_VLAN_PRIORITY_SHIFT; + + return vlanprio; +} + +int hinic_set_vf_vlan(struct hinic_hwdev *hwdev, bool add, u16 vid, + u8 qos, int vf_id) +{ + struct hinic_vf_vlan_config vf_vlan = {0}; + u16 out_size = sizeof(vf_vlan); + int err; + u8 cmd; + + /* VLAN 0 is a special case, don't allow it to be removed */ + if (!vid && !add) + return 0; + + vf_vlan.func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id; + vf_vlan.vlan_id = vid; + vf_vlan.qos = qos; + + if (add) + cmd = HINIC_PORT_CMD_SET_VF_VLAN; + else + cmd = HINIC_PORT_CMD_CLR_VF_VLAN; + + err = hinic_port_msg_cmd(hwdev, cmd, &vf_vlan, + sizeof(vf_vlan), &vf_vlan, &out_size); + if (err || !out_size || vf_vlan.status) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to set VF %d vlan, err: %d, status: 0x%x, out size: 0x%x\n", + HW_VF_ID_TO_OS(vf_id), err, vf_vlan.status, out_size); + return -EFAULT; + } + + return 0; +} + +static int hinic_init_vf_config(struct hinic_hwdev *hwdev, u16 vf_id) +{ + struct vf_data_storage *vf_info; + u16 func_id, vlan_id; + int err = 0; + + vf_info = hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id); + if (vf_info->pf_set_mac) { + func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf_id; + + vlan_id = 0; + + err = hinic_set_mac(hwdev, vf_info->vf_mac_addr, vlan_id, + func_id); + if (err) { + dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set VF %d MAC\n", + HW_VF_ID_TO_OS(vf_id)); + return err; + } + } + + if (hinic_vf_info_vlanprio(hwdev, vf_id)) { + err = hinic_set_vf_vlan(hwdev, true, vf_info->pf_vlan, + vf_info->pf_qos, vf_id); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, "Failed to add VF %d VLAN_QOS\n", + HW_VF_ID_TO_OS(vf_id)); + return err; + } + } + + return 0; +} + +int hinic_register_vf_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_register_vf *register_info = buf_out; + struct hinic_hwdev *hw_dev = hwdev; + struct hinic_func_to_io *nic_io; + int err; + + nic_io = &hw_dev->func_to_io; + if (vf_id > nic_io->max_vfs) { + dev_err(&hw_dev->hwif->pdev->dev, "Register VF id %d exceed limit[0-%d]\n", + HW_VF_ID_TO_OS(vf_id), HW_VF_ID_TO_OS(nic_io->max_vfs)); + register_info->status = EFAULT; + return -EFAULT; + } + + *out_size = sizeof(*register_info); + err = hinic_init_vf_config(hw_dev, vf_id); + if (err) { + register_info->status = EFAULT; + return err; + } + + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].registered = true; + + return 0; +} + +int hinic_unregister_vf_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_hwdev *hw_dev = hwdev; + struct hinic_func_to_io *nic_io; + + nic_io = &hw_dev->func_to_io; + *out_size = 0; + if (vf_id > nic_io->max_vfs) + return 0; + + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].registered = false; + + return 0; +} + +int hinic_change_vf_mtu_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_hwdev *hw_dev = hwdev; + int err; + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_CHANGE_MTU, buf_in, + in_size, buf_out, out_size); + if (err) { + dev_err(&hw_dev->hwif->pdev->dev, "Failed to set VF %u mtu\n", + vf_id); + return err; + } + + return 0; +} + +int hinic_get_vf_mac_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_port_mac_cmd *mac_info = buf_out; + struct hinic_hwdev *dev = hwdev; + struct hinic_func_to_io *nic_io; + struct vf_data_storage *vf_info; + + nic_io = &dev->func_to_io; + vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id); + + memcpy(mac_info->mac, vf_info->vf_mac_addr, ETH_ALEN); + mac_info->status = 0; + *out_size = sizeof(*mac_info); + + return 0; +} + +int hinic_set_vf_mac_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_port_mac_cmd *mac_out = buf_out; + struct hinic_port_mac_cmd *mac_in = buf_in; + struct hinic_hwdev *hw_dev = hwdev; + struct hinic_func_to_io *nic_io; + struct vf_data_storage *vf_info; + int err; + + nic_io = &hw_dev->func_to_io; + vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id); + if (vf_info->pf_set_mac && !(vf_info->trust) && + is_valid_ether_addr(mac_in->mac)) { + dev_warn(&hw_dev->hwif->pdev->dev, "PF has already set VF %d MAC address\n", + HW_VF_ID_TO_OS(vf_id)); + mac_out->status = HINIC_PF_SET_VF_ALREADY; + *out_size = sizeof(*mac_out); + return 0; + } + + err = hinic_port_msg_cmd(hw_dev, HINIC_PORT_CMD_SET_MAC, buf_in, + in_size, buf_out, out_size); + if ((err && err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) || !(*out_size)) { + dev_err(&hw_dev->hwif->pdev->dev, + "Failed to set VF %d MAC address, err: %d, status: 0x%x, out size: 0x%x\n", + HW_VF_ID_TO_OS(vf_id), err, mac_out->status, *out_size); + return -EFAULT; + } + + return err; +} + +int hinic_del_vf_mac_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_port_mac_cmd *mac_out = buf_out; + struct hinic_port_mac_cmd *mac_in = buf_in; + struct hinic_hwdev *hw_dev = hwdev; + struct hinic_func_to_io *nic_io; + struct vf_data_storage *vf_info; + int err; + + nic_io = &hw_dev->func_to_io; + vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf_id); + if (vf_info->pf_set_mac && is_valid_ether_addr(mac_in->mac) && + !memcmp(vf_info->vf_mac_addr, mac_in->mac, ETH_ALEN)) { + dev_warn(&hw_dev->hwif->pdev->dev, "PF has already set VF mac.\n"); + mac_out->status = HINIC_PF_SET_VF_ALREADY; + *out_size = sizeof(*mac_out); + return 0; + } + + err = hinic_port_msg_cmd(hw_dev, HINIC_PORT_CMD_DEL_MAC, buf_in, + in_size, buf_out, out_size); + if ((err && err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) || !(*out_size)) { + dev_err(&hw_dev->hwif->pdev->dev, "Failed to delete VF %d MAC, err: %d, status: 0x%x, out size: 0x%x\n", + HW_VF_ID_TO_OS(vf_id), err, mac_out->status, *out_size); + return -EFAULT; + } + + return err; +} + +int hinic_get_vf_link_status_msg_handler(void *hwdev, u16 vf_id, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_port_link_cmd *get_link = buf_out; + struct hinic_hwdev *hw_dev = hwdev; + struct vf_data_storage *vf_infos; + struct hinic_func_to_io *nic_io; + bool link_forced, link_up; + + nic_io = &hw_dev->func_to_io; + vf_infos = nic_io->vf_infos; + link_forced = vf_infos[HW_VF_ID_TO_OS(vf_id)].link_forced; + link_up = vf_infos[HW_VF_ID_TO_OS(vf_id)].link_up; + + if (link_forced) + get_link->state = link_up ? + HINIC_LINK_STATE_UP : HINIC_LINK_STATE_DOWN; + else + get_link->state = nic_io->link_status; + + get_link->status = 0; + *out_size = sizeof(*get_link); + + return 0; +} + +struct vf_cmd_msg_handle nic_vf_cmd_msg_handler[] = { + {HINIC_PORT_CMD_VF_REGISTER, hinic_register_vf_msg_handler}, + {HINIC_PORT_CMD_VF_UNREGISTER, hinic_unregister_vf_msg_handler}, + {HINIC_PORT_CMD_CHANGE_MTU, hinic_change_vf_mtu_msg_handler}, + {HINIC_PORT_CMD_GET_MAC, hinic_get_vf_mac_msg_handler}, + {HINIC_PORT_CMD_SET_MAC, hinic_set_vf_mac_msg_handler}, + {HINIC_PORT_CMD_DEL_MAC, hinic_del_vf_mac_msg_handler}, + {HINIC_PORT_CMD_GET_LINK_STATE, hinic_get_vf_link_status_msg_handler}, +}; + +#define CHECK_IPSU_15BIT 0X8000 + +struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct hinic_dev *nic_dev = netdev_priv(netdev); + + return &nic_dev->sriov_info; +} + +static int hinic_check_mac_info(u8 status, u16 vlan_id) +{ + if ((status && status != HINIC_MGMT_STATUS_EXIST && + status != HINIC_PF_SET_VF_ALREADY) || + (vlan_id & CHECK_IPSU_15BIT && + status == HINIC_MGMT_STATUS_EXIST)) + return -EINVAL; + + return 0; +} + +#define HINIC_VLAN_ID_MASK 0x7FFF + +int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac, u8 *new_mac, + u16 vlan_id, u16 func_id) +{ + struct hinic_port_mac_update mac_info = {0}; + u16 out_size = sizeof(mac_info); + int err; + + if (!hwdev || !old_mac || !new_mac) + return -EINVAL; + + if ((vlan_id & HINIC_VLAN_ID_MASK) >= VLAN_N_VID) { + dev_err(&hwdev->hwif->pdev->dev, "Invalid VLAN number: %d\n", + (vlan_id & HINIC_VLAN_ID_MASK)); + return -EINVAL; + } + + mac_info.func_id = func_id; + mac_info.vlan_id = vlan_id; + memcpy(mac_info.old_mac, old_mac, ETH_ALEN); + memcpy(mac_info.new_mac, new_mac, ETH_ALEN); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_UPDATE_MAC, &mac_info, + sizeof(mac_info), &mac_info, &out_size); + + if (err || !out_size || + hinic_check_mac_info(mac_info.status, mac_info.vlan_id)) { + dev_err(&hwdev->hwif->pdev->dev, + "Failed to update MAC, err: %d, status: 0x%x, out size: 0x%x\n", + err, mac_info.status, out_size); + return -EINVAL; + } + + if (mac_info.status == HINIC_PF_SET_VF_ALREADY) { + dev_warn(&hwdev->hwif->pdev->dev, + "PF has already set VF MAC. Ignore update operation\n"); + return HINIC_PF_SET_VF_ALREADY; + } + + if (mac_info.status == HINIC_MGMT_STATUS_EXIST) + dev_warn(&hwdev->hwif->pdev->dev, "MAC is repeated. Ignore update operation\n"); + + return 0; +} + +void hinic_get_vf_config(struct hinic_hwdev *hwdev, u16 vf_id, + struct ifla_vf_info *ivi) +{ + struct vf_data_storage *vfinfo; + + vfinfo = hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id); + + ivi->vf = HW_VF_ID_TO_OS(vf_id); + memcpy(ivi->mac, vfinfo->vf_mac_addr, ETH_ALEN); + ivi->vlan = vfinfo->pf_vlan; + ivi->qos = vfinfo->pf_qos; + ivi->spoofchk = vfinfo->spoofchk; + ivi->trusted = vfinfo->trust; + ivi->max_tx_rate = vfinfo->max_rate; + ivi->min_tx_rate = vfinfo->min_rate; + + if (!vfinfo->link_forced) + ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; + else if (vfinfo->link_up) + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + else + ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; +} + +int hinic_ndo_get_vf_config(struct net_device *netdev, + int vf, struct ifla_vf_info *ivi) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_sriov_info *sriov_info; + + sriov_info = &nic_dev->sriov_info; + if (vf >= sriov_info->num_vfs) + return -EINVAL; + + hinic_get_vf_config(sriov_info->hwdev, OS_VF_ID_TO_HW(vf), ivi); + + return 0; +} + +int hinic_set_vf_mac(struct hinic_hwdev *hwdev, int vf, unsigned char *mac_addr) +{ + struct hinic_func_to_io *nic_io = &hwdev->func_to_io; + struct vf_data_storage *vf_info; + u16 func_id; + int err; + + vf_info = nic_io->vf_infos + HW_VF_ID_TO_OS(vf); + + /* duplicate request, so just return success */ + if (vf_info->pf_set_mac && + !memcmp(vf_info->vf_mac_addr, mac_addr, ETH_ALEN)) + return 0; + + vf_info->pf_set_mac = true; + + func_id = hinic_glb_pf_vf_offset(hwdev->hwif) + vf; + err = hinic_update_mac(hwdev, vf_info->vf_mac_addr, + mac_addr, 0, func_id); + if (err) { + vf_info->pf_set_mac = false; + return err; + } + + memcpy(vf_info->vf_mac_addr, mac_addr, ETH_ALEN); + + return 0; +} + +int hinic_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_sriov_info *sriov_info; + int err; + + sriov_info = &nic_dev->sriov_info; + if (!is_valid_ether_addr(mac) || vf >= sriov_info->num_vfs) + return -EINVAL; + + err = hinic_set_vf_mac(sriov_info->hwdev, OS_VF_ID_TO_HW(vf), mac); + if (err) + return err; + + netif_info(nic_dev, drv, netdev, "Setting MAC %pM on VF %d\n", mac, vf); + netif_info(nic_dev, drv, netdev, "Reload the VF driver to make this change effective."); + + return 0; +} + +int hinic_add_vf_vlan(struct hinic_hwdev *hwdev, int vf_id, u16 vlan, u8 qos) +{ + struct hinic_func_to_io *nic_io = &hwdev->func_to_io; + int err; + + err = hinic_set_vf_vlan(hwdev, true, vlan, qos, vf_id); + if (err) + return err; + + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan = vlan; + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos = qos; + + dev_info(&hwdev->hwif->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n", + vlan, qos, HW_VF_ID_TO_OS(vf_id)); + return 0; +} + +int hinic_kill_vf_vlan(struct hinic_hwdev *hwdev, int vf_id) +{ + struct hinic_func_to_io *nic_io = &hwdev->func_to_io; + int err; + + err = hinic_set_vf_vlan(hwdev, false, + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan, + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos, + vf_id); + if (err) + return err; + + dev_info(&hwdev->hwif->pdev->dev, "Remove VLAN %d on VF %d\n", + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan, + HW_VF_ID_TO_OS(vf_id)); + + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_vlan = 0; + nic_io->vf_infos[HW_VF_ID_TO_OS(vf_id)].pf_qos = 0; + + return 0; +} + +int hinic_update_mac_vlan(struct hinic_dev *nic_dev, u16 old_vlan, u16 new_vlan, + int vf_id) +{ + struct vf_data_storage *vf_info; + u16 vlan_id; + int err; + + if (!nic_dev || old_vlan >= VLAN_N_VID || new_vlan >= VLAN_N_VID) + return -EINVAL; + + vf_info = nic_dev->hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id); + if (!vf_info->pf_set_mac) + return 0; + + vlan_id = old_vlan; + if (vlan_id) + vlan_id |= HINIC_ADD_VLAN_IN_MAC; + + err = hinic_port_del_mac(nic_dev, vf_info->vf_mac_addr, vlan_id); + if (err) { + dev_err(&nic_dev->hwdev->hwif->pdev->dev, "Failed to delete VF %d MAC %pM vlan %d\n", + HW_VF_ID_TO_OS(vf_id), vf_info->vf_mac_addr, old_vlan); + return err; + } + + vlan_id = new_vlan; + if (vlan_id) + vlan_id |= HINIC_ADD_VLAN_IN_MAC; + + err = hinic_port_add_mac(nic_dev, vf_info->vf_mac_addr, vlan_id); + if (err) { + dev_err(&nic_dev->hwdev->hwif->pdev->dev, "Failed to add VF %d MAC %pM vlan %d\n", + HW_VF_ID_TO_OS(vf_id), vf_info->vf_mac_addr, new_vlan); + goto out; + } + + return 0; + +out: + vlan_id = old_vlan; + if (vlan_id) + vlan_id |= HINIC_ADD_VLAN_IN_MAC; + hinic_port_add_mac(nic_dev, vf_info->vf_mac_addr, vlan_id); + + return err; +} + +static int set_hw_vf_vlan(struct hinic_dev *nic_dev, + u16 cur_vlanprio, int vf, u16 vlan, u8 qos) +{ + u16 old_vlan = cur_vlanprio & VLAN_VID_MASK; + int err = 0; + + if (vlan || qos) { + if (cur_vlanprio) { + err = hinic_kill_vf_vlan(nic_dev->hwdev, + OS_VF_ID_TO_HW(vf)); + if (err) { + dev_err(&nic_dev->sriov_info.pdev->dev, "Failed to delete vf %d old vlan %d\n", + vf, old_vlan); + goto out; + } + } + err = hinic_add_vf_vlan(nic_dev->hwdev, + OS_VF_ID_TO_HW(vf), vlan, qos); + if (err) { + dev_err(&nic_dev->sriov_info.pdev->dev, "Failed to add vf %d new vlan %d\n", + vf, vlan); + goto out; + } + } else { + err = hinic_kill_vf_vlan(nic_dev->hwdev, OS_VF_ID_TO_HW(vf)); + if (err) { + dev_err(&nic_dev->sriov_info.pdev->dev, "Failed to delete vf %d vlan %d\n", + vf, old_vlan); + goto out; + } + } + + err = hinic_update_mac_vlan(nic_dev, old_vlan, vlan, + OS_VF_ID_TO_HW(vf)); + +out: + return err; +} + +int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_sriov_info *sriov_info; + u16 vlanprio, cur_vlanprio; + + sriov_info = &nic_dev->sriov_info; + if (vf >= sriov_info->num_vfs || vlan > 4095 || qos > 7) + return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + vlanprio = vlan | qos << HINIC_VLAN_PRIORITY_SHIFT; + cur_vlanprio = hinic_vf_info_vlanprio(nic_dev->hwdev, + OS_VF_ID_TO_HW(vf)); + /* duplicate request, so just return success */ + if (vlanprio == cur_vlanprio) + return 0; + + return set_hw_vf_vlan(nic_dev, cur_vlanprio, vf, vlan, qos); +} + +int hinic_set_vf_trust(struct hinic_hwdev *hwdev, u16 vf_id, bool trust) +{ + struct vf_data_storage *vf_infos; + struct hinic_func_to_io *nic_io; + + if (!hwdev) + return -EINVAL; + + nic_io = &hwdev->func_to_io; + vf_infos = nic_io->vf_infos; + vf_infos[vf_id].trust = trust; + + return 0; +} + +int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting) +{ + struct hinic_dev *adapter = netdev_priv(netdev); + struct hinic_sriov_info *sriov_info; + struct hinic_func_to_io *nic_io; + bool cur_trust; + int err; + + sriov_info = &adapter->sriov_info; + nic_io = &adapter->hwdev->func_to_io; + + if (vf >= sriov_info->num_vfs) + return -EINVAL; + + cur_trust = nic_io->vf_infos[vf].trust; + /* same request, so just return success */ + if ((setting && cur_trust) || (!setting && !cur_trust)) + return 0; + + err = hinic_set_vf_trust(adapter->hwdev, vf, setting); + if (!err) + dev_info(&sriov_info->pdev->dev, "Set VF %d trusted %s succeed\n", + vf, setting ? "on" : "off"); + else + dev_err(&sriov_info->pdev->dev, "Failed set VF %d trusted %s\n", + vf, setting ? "on" : "off"); + + return err; +} + +/* pf receive message from vf */ +int nic_pf_mbox_handler(void *hwdev, u16 vf_id, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size) +{ + struct vf_cmd_msg_handle *vf_msg_handle; + struct hinic_hwdev *dev = hwdev; + struct hinic_func_to_io *nic_io; + struct hinic_pfhwdev *pfhwdev; + u32 i, cmd_number; + int err = 0; + + if (!hwdev) + return -EFAULT; + + cmd_number = sizeof(nic_vf_cmd_msg_handler) / + sizeof(struct vf_cmd_msg_handle); + pfhwdev = container_of(dev, struct hinic_pfhwdev, hwdev); + nic_io = &dev->func_to_io; + for (i = 0; i < cmd_number; i++) { + vf_msg_handle = &nic_vf_cmd_msg_handler[i]; + if (cmd == vf_msg_handle->cmd && + vf_msg_handle->cmd_msg_handler) { + err = vf_msg_handle->cmd_msg_handler(hwdev, vf_id, + buf_in, in_size, + buf_out, + out_size); + break; + } + } + if (i == cmd_number) + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, + cmd, buf_in, in_size, buf_out, + out_size, HINIC_MGMT_MSG_SYNC); + + if (err && err != HINIC_MBOX_PF_BUSY_ACTIVE_FW) + dev_err(&nic_io->hwif->pdev->dev, "PF receive VF L2NIC cmd: %d process error, err:%d\n", + cmd, err); + return err; +} + +static int cfg_mbx_pf_proc_vf_msg(void *hwdev, u16 vf_id, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size) +{ + struct hinic_dev_cap *dev_cap = buf_out; + struct hinic_hwdev *dev = hwdev; + struct hinic_cap *cap; + + cap = &dev->nic_cap; + memset(dev_cap, 0, sizeof(*dev_cap)); + + dev_cap->max_vf = cap->max_vf; + dev_cap->max_sqs = cap->max_vf_qps; + dev_cap->max_rqs = cap->max_vf_qps; + + *out_size = sizeof(*dev_cap); + + return 0; +} + +static int hinic_init_vf_infos(struct hinic_func_to_io *nic_io, u16 vf_id) +{ + struct vf_data_storage *vf_infos = nic_io->vf_infos; + + if (set_vf_link_state > HINIC_IFLA_VF_LINK_STATE_DISABLE) { + dev_warn(&nic_io->hwif->pdev->dev, "Module Parameter set_vf_link_state value %d is out of range, resetting to %d\n", + set_vf_link_state, HINIC_IFLA_VF_LINK_STATE_AUTO); + set_vf_link_state = HINIC_IFLA_VF_LINK_STATE_AUTO; + } + + switch (set_vf_link_state) { + case HINIC_IFLA_VF_LINK_STATE_AUTO: + vf_infos[vf_id].link_forced = false; + break; + case HINIC_IFLA_VF_LINK_STATE_ENABLE: + vf_infos[vf_id].link_forced = true; + vf_infos[vf_id].link_up = true; + break; + case HINIC_IFLA_VF_LINK_STATE_DISABLE: + vf_infos[vf_id].link_forced = true; + vf_infos[vf_id].link_up = false; + break; + default: + dev_err(&nic_io->hwif->pdev->dev, "Invalid input parameter set_vf_link_state: %d\n", + set_vf_link_state); + return -EINVAL; + } + + return 0; +} + +void hinic_clear_vf_infos(struct hinic_dev *nic_dev, u16 vf_id) +{ + struct vf_data_storage *vf_infos; + u16 func_id; + + func_id = hinic_glb_pf_vf_offset(nic_dev->hwdev->hwif) + vf_id; + vf_infos = nic_dev->hwdev->func_to_io.vf_infos + HW_VF_ID_TO_OS(vf_id); + if (vf_infos->pf_set_mac) + hinic_port_del_mac(nic_dev, vf_infos->vf_mac_addr, 0); + + if (hinic_vf_info_vlanprio(nic_dev->hwdev, vf_id)) + hinic_kill_vf_vlan(nic_dev->hwdev, vf_id); + + if (vf_infos->trust) + hinic_set_vf_trust(nic_dev->hwdev, vf_id, false); + + memset(vf_infos, 0, sizeof(*vf_infos)); + /* set vf_infos to default */ + hinic_init_vf_infos(&nic_dev->hwdev->func_to_io, HW_VF_ID_TO_OS(vf_id)); +} + +int hinic_deinit_vf_hw(struct hinic_sriov_info *sriov_info, u16 start_vf_id, + u16 end_vf_id) +{ + struct hinic_dev *nic_dev; + u16 func_idx, idx; + + nic_dev = container_of(sriov_info, struct hinic_dev, sriov_info); + + for (idx = start_vf_id; idx <= end_vf_id; idx++) { + func_idx = hinic_glb_pf_vf_offset(nic_dev->hwdev->hwif) + idx; + hinic_set_wq_page_size(nic_dev->hwdev, func_idx, + HINIC_HW_WQ_PAGE_SIZE); + hinic_clear_vf_infos(nic_dev, idx); + } + + return 0; +} + +int hinic_vf_func_init(struct hinic_hwdev *hwdev) +{ + struct hinic_register_vf register_info = {0}; + u16 out_size = sizeof(register_info); + struct hinic_func_to_io *nic_io; + int err = 0; + u32 size, i; + + nic_io = &hwdev->func_to_io; + + if (HINIC_IS_VF(hwdev->hwif)) { + err = hinic_mbox_to_pf(hwdev, HINIC_MOD_L2NIC, + HINIC_PORT_CMD_VF_REGISTER, + ®ister_info, sizeof(register_info), + ®ister_info, &out_size, 0); + if (err || register_info.status || !out_size) { + dev_err(&hwdev->hwif->pdev->dev, + "Failed to register VF, err: %d, status: 0x%x, out size: 0x%x\n", + err, register_info.status, out_size); + hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC); + return -EIO; + } + } else { + err = hinic_register_pf_mbox_cb(hwdev, HINIC_MOD_CFGM, + cfg_mbx_pf_proc_vf_msg); + if (err) { + dev_err(&hwdev->hwif->pdev->dev, + "Register PF mailbox callback failed\n"); + return err; + } + nic_io->max_vfs = hwdev->nic_cap.max_vf; + size = sizeof(*nic_io->vf_infos) * nic_io->max_vfs; + if (size != 0) { + nic_io->vf_infos = kzalloc(size, GFP_KERNEL); + if (!nic_io->vf_infos) { + err = -ENOMEM; + goto out_free_nic_io; + } + + for (i = 0; i < nic_io->max_vfs; i++) { + err = hinic_init_vf_infos(nic_io, i); + if (err) + goto err_init_vf_infos; + } + + err = hinic_register_pf_mbox_cb(hwdev, HINIC_MOD_L2NIC, + nic_pf_mbox_handler); + if (err) + goto err_register_pf_mbox_cb; + } + } + + return 0; + +err_register_pf_mbox_cb: +err_init_vf_infos: + kfree(nic_io->vf_infos); +out_free_nic_io: + return err; +} + +void hinic_vf_func_free(struct hinic_hwdev *hwdev) +{ + struct hinic_register_vf unregister = {0}; + u16 out_size = sizeof(unregister); + int err; + + if (HINIC_IS_VF(hwdev->hwif)) { + err = hinic_mbox_to_pf(hwdev, HINIC_MOD_L2NIC, + HINIC_PORT_CMD_VF_UNREGISTER, + &unregister, sizeof(unregister), + &unregister, &out_size, 0); + if (err || !out_size || unregister.status) + dev_err(&hwdev->hwif->pdev->dev, "Failed to unregister VF, err: %d, status: 0x%x, out_size: 0x%x\n", + err, unregister.status, out_size); + } else { + if (hwdev->func_to_io.vf_infos) { + hinic_unregister_pf_mbox_cb(hwdev, HINIC_MOD_L2NIC); + kfree(hwdev->func_to_io.vf_infos); + } + } +} + +int hinic_init_vf_hw(struct hinic_hwdev *hwdev, u16 start_vf_id, u16 end_vf_id) +{ + u16 i, func_idx; + int err; + + /* vf use 256K as default wq page size, and can't change it */ + for (i = start_vf_id; i <= end_vf_id; i++) { + func_idx = hinic_glb_pf_vf_offset(hwdev->hwif) + i; + err = hinic_set_wq_page_size(hwdev, func_idx, + HINIC_DEFAULT_WQ_PAGE_SIZE); + if (err) + return err; + } + + return 0; +} + +int hinic_pci_sriov_disable(struct pci_dev *pdev) +{ + struct hinic_sriov_info *sriov_info; + u16 tmp_vfs; + + sriov_info = hinic_get_sriov_info_by_pcidev(pdev); + /* if SR-IOV is already disabled then nothing will be done */ + if (!sriov_info->sriov_enabled) + return 0; + + set_bit(HINIC_SRIOV_DISABLE, &sriov_info->state); + + /* If our VFs are assigned we cannot shut down SR-IOV + * without causing issues, so just leave the hardware + * available but disabled + */ + if (pci_vfs_assigned(sriov_info->pdev)) { + clear_bit(HINIC_SRIOV_DISABLE, &sriov_info->state); + dev_warn(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n"); + return -EPERM; + } + sriov_info->sriov_enabled = false; + + /* disable iov and allow time for transactions to clear */ + pci_disable_sriov(sriov_info->pdev); + + tmp_vfs = (u16)sriov_info->num_vfs; + sriov_info->num_vfs = 0; + hinic_deinit_vf_hw(sriov_info, OS_VF_ID_TO_HW(0), + OS_VF_ID_TO_HW(tmp_vfs - 1)); + + clear_bit(HINIC_SRIOV_DISABLE, &sriov_info->state); + + return 0; +} + +int hinic_pci_sriov_enable(struct pci_dev *pdev, int num_vfs) +{ + struct hinic_sriov_info *sriov_info; + int err; + + sriov_info = hinic_get_sriov_info_by_pcidev(pdev); + + if (test_and_set_bit(HINIC_SRIOV_ENABLE, &sriov_info->state)) { + dev_err(&pdev->dev, + "SR-IOV enable in process, please wait, num_vfs %d\n", + num_vfs); + return -EPERM; + } + + err = hinic_init_vf_hw(sriov_info->hwdev, OS_VF_ID_TO_HW(0), + OS_VF_ID_TO_HW((u16)num_vfs - 1)); + if (err) { + dev_err(&sriov_info->pdev->dev, + "Failed to init vf in hardware before enable sriov, error %d\n", + err); + clear_bit(HINIC_SRIOV_ENABLE, &sriov_info->state); + return err; + } + + err = pci_enable_sriov(sriov_info->pdev, num_vfs); + if (err) { + dev_err(&pdev->dev, + "Failed to enable SR-IOV, error %d\n", err); + clear_bit(HINIC_SRIOV_ENABLE, &sriov_info->state); + return err; + } + + sriov_info->sriov_enabled = true; + sriov_info->num_vfs = num_vfs; + clear_bit(HINIC_SRIOV_ENABLE, &sriov_info->state); + + return num_vfs; +} + +int hinic_pci_sriov_configure(struct pci_dev *dev, int num_vfs) +{ + struct hinic_sriov_info *sriov_info; + + sriov_info = hinic_get_sriov_info_by_pcidev(dev); + + if (test_bit(HINIC_FUNC_REMOVE, &sriov_info->state)) + return -EBUSY; + + if (!num_vfs) + return hinic_pci_sriov_disable(dev); + else + return hinic_pci_sriov_enable(dev, num_vfs); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.h b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h new file mode 100644 index 000000000000..64affc7474b5 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#ifndef HINIC_SRIOV_H +#define HINIC_SRIOV_H + +#include "hinic_hw_dev.h" + +#define OS_VF_ID_TO_HW(os_vf_id) ((os_vf_id) + 1) +#define HW_VF_ID_TO_OS(hw_vf_id) ((hw_vf_id) - 1) + +enum hinic_sriov_state { + HINIC_SRIOV_DISABLE, + HINIC_SRIOV_ENABLE, + HINIC_FUNC_REMOVE, +}; + +enum { + HINIC_IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + HINIC_IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + HINIC_IFLA_VF_LINK_STATE_DISABLE, /* link always down */ +}; + +struct hinic_sriov_info { + struct pci_dev *pdev; + struct hinic_hwdev *hwdev; + bool sriov_enabled; + unsigned int num_vfs; + unsigned long state; +}; + +struct vf_data_storage { + u8 vf_mac_addr[ETH_ALEN]; + bool registered; + bool pf_set_mac; + u16 pf_vlan; + u8 pf_qos; + u32 max_rate; + u32 min_rate; + + bool link_forced; + bool link_up; /* only valid if VF link is forced */ + bool spoofchk; + bool trust; +}; + +struct hinic_register_vf { + u8 status; + u8 version; + u8 rsvd0[6]; +}; + +struct hinic_port_mac_update { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_id; + u16 vlan_id; + u16 rsvd1; + u8 old_mac[ETH_ALEN]; + u16 rsvd2; + u8 new_mac[ETH_ALEN]; +}; + +struct hinic_vf_vlan_config { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_id; + u16 vlan_id; + u8 qos; + u8 rsvd1[7]; +}; + +int hinic_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); + +int hinic_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto); + +int hinic_ndo_get_vf_config(struct net_device *netdev, + int vf, struct ifla_vf_info *ivi); + +int hinic_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting); + +void hinic_notify_all_vfs_link_changed(struct hinic_hwdev *hwdev, + u8 link_status); + +int hinic_pci_sriov_disable(struct pci_dev *dev); + +int hinic_pci_sriov_enable(struct pci_dev *dev, int num_vfs); + +int hinic_vf_func_init(struct hinic_hwdev *hwdev); + +void hinic_vf_func_free(struct hinic_hwdev *hwdev); + +int hinic_pci_sriov_configure(struct pci_dev *dev, int num_vfs); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 365016450bdb..4c66a0bc1b28 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -673,9 +673,11 @@ static int free_tx_poll(struct napi_struct *napi, int budget) if (pkts < budget) { napi_complete(napi); - hinic_hwdev_set_msix_state(nic_dev->hwdev, - sq->msix_entry, - HINIC_MSIX_ENABLE); + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + hinic_hwdev_set_msix_state(nic_dev->hwdev, + sq->msix_entry, + HINIC_MSIX_ENABLE); + return pkts; } @@ -701,10 +703,11 @@ static irqreturn_t tx_irq(int irq, void *data) nic_dev = netdev_priv(txq->netdev); - /* Disable the interrupt until napi will be completed */ - hinic_hwdev_set_msix_state(nic_dev->hwdev, - txq->sq->msix_entry, - HINIC_MSIX_DISABLE); + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + /* Disable the interrupt until napi will be completed */ + hinic_hwdev_set_msix_state(nic_dev->hwdev, + txq->sq->msix_entry, + HINIC_MSIX_DISABLE); hinic_hwdev_msix_cnt_set(nic_dev->hwdev, txq->sq->msix_entry); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index f7103356ef56..05bc6e216bca 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1476,7 +1476,7 @@ static bool e1000_check_64k_bound(struct e1000_adapter *adapter, void *start, if (hw->mac_type == e1000_82545 || hw->mac_type == e1000_ce4100 || hw->mac_type == e1000_82546) { - return ((begin ^ (end - 1)) >> 16) != 0 ? false : true; + return ((begin ^ (end - 1)) >> 16) == 0; } return true; @@ -3136,8 +3136,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); if (skb->data_len && hdr_len == len) { switch (hw->mac_type) { + case e1000_82544: { unsigned int pull_size; - case e1000_82544: + /* Make sure we have room to chop off 4 bytes, * and that the end alignment will work out to * this hardware's requirements @@ -3158,6 +3159,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, } len = skb_headlen(skb); break; + } default: /* do nothing */ break; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 177c6da80c57..e0b074820b47 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6404,6 +6404,31 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) mac_data |= BIT(3); ew32(CTRL_EXT, mac_data); + /* Disable disconnected cable conditioning for Power Gating */ + mac_data = er32(DPGFR); + mac_data |= BIT(2); + ew32(DPGFR, mac_data); + + /* Don't wake from dynamic Power Gating with clock request */ + mac_data = er32(FEXTNVM12); + mac_data |= BIT(12); + ew32(FEXTNVM12, mac_data); + + /* Ungate PGCB clock */ + mac_data = er32(FEXTNVM9); + mac_data |= BIT(28); + ew32(FEXTNVM9, mac_data); + + /* Enable K1 off to enable mPHY Power Gating */ + mac_data = er32(FEXTNVM6); + mac_data |= BIT(31); + ew32(FEXTNVM12, mac_data); + + /* Enable mPHY power gating for any link and speed */ + mac_data = er32(FEXTNVM8); + mac_data |= BIT(9); + ew32(FEXTNVM8, mac_data); + /* Enable the Dynamic Clock Gating in the DMA and MAC */ mac_data = er32(CTRL_EXT); mac_data |= E1000_CTRL_EXT_DMA_DYN_CLK_EN; @@ -6433,6 +6458,35 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data |= BIT(0); ew32(FEXTNVM7, mac_data); + /* Disable mPHY power gating for any link and speed */ + mac_data = er32(FEXTNVM8); + mac_data &= ~BIT(9); + ew32(FEXTNVM8, mac_data); + + /* Disable K1 off */ + mac_data = er32(FEXTNVM6); + mac_data &= ~BIT(31); + ew32(FEXTNVM12, mac_data); + + /* Disable Ungate PGCB clock */ + mac_data = er32(FEXTNVM9); + mac_data &= ~BIT(28); + ew32(FEXTNVM9, mac_data); + + /* Cancel not waking from dynamic + * Power Gating with clock request + */ + mac_data = er32(FEXTNVM12); + mac_data &= ~BIT(12); + ew32(FEXTNVM12, mac_data); + + /* Cancel disable disconnected cable conditioning + * for Power Gating + */ + mac_data = er32(DPGFR); + mac_data &= ~BIT(2); + ew32(DPGFR, mac_data); + /* Disable Dynamic Power Gating */ mac_data = er32(CTRL_EXT); mac_data &= 0xFFFFFFF7; diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h index df59fd1d660c..8165ba2619a4 100644 --- a/drivers/net/ethernet/intel/e1000e/regs.h +++ b/drivers/net/ethernet/intel/e1000e/regs.h @@ -21,9 +21,12 @@ #define E1000_FEXTNVM5 0x00014 /* Future Extended NVM 5 - RW */ #define E1000_FEXTNVM6 0x00010 /* Future Extended NVM 6 - RW */ #define E1000_FEXTNVM7 0x000E4 /* Future Extended NVM 7 - RW */ +#define E1000_FEXTNVM8 0x5BB0 /* Future Extended NVM 8 - RW */ #define E1000_FEXTNVM9 0x5BB4 /* Future Extended NVM 9 - RW */ #define E1000_FEXTNVM11 0x5BBC /* Future Extended NVM 11 - RW */ +#define E1000_FEXTNVM12 0x5BC0 /* Future Extended NVM 12 - RW */ #define E1000_PCIEANACFG 0x00F18 /* PCIE Analog Config */ +#define E1000_DPGFR 0x00FAC /* Dynamic Power Gate Force Control Register */ #define E1000_FCT 0x00030 /* Flow Control Type - RW */ #define E1000_VET 0x00038 /* VLAN Ether Type - RW */ #define E1000_ICR 0x000C0 /* Interrupt Cause Read - R/clr */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8c3e753bfb9d..2a037ec244b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1611,7 +1611,7 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, } } if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + bool pf_lut = vsi->type == I40E_VSI_MAIN; ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); if (ret) { @@ -11436,7 +11436,7 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, } if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + bool pf_lut = vsi->type == I40E_VSI_MAIN; ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); if (ret) { diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile index e3c164c12e10..3652f211f351 100644 --- a/drivers/net/ethernet/intel/igc/Makefile +++ b/drivers/net/ethernet/intel/igc/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_IGC) += igc.o igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ -igc_ethtool.o igc_ptp.o igc_dump.o +igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index a1f845a2aa80..8ddc39482a8e 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -19,8 +19,199 @@ /* forward declaration */ void igc_set_ethtool_ops(struct net_device *); -struct igc_adapter; -struct igc_ring; +/* Transmit and receive queues */ +#define IGC_MAX_RX_QUEUES 4 +#define IGC_MAX_TX_QUEUES 4 + +#define MAX_Q_VECTORS 8 +#define MAX_STD_JUMBO_FRAME_SIZE 9216 + +#define MAX_ETYPE_FILTER (4 - 1) +#define IGC_RETA_SIZE 128 + +struct igc_tx_queue_stats { + u64 packets; + u64 bytes; + u64 restart_queue; + u64 restart_queue2; +}; + +struct igc_rx_queue_stats { + u64 packets; + u64 bytes; + u64 drops; + u64 csum_err; + u64 alloc_failed; +}; + +struct igc_rx_packet_stats { + u64 ipv4_packets; /* IPv4 headers processed */ + u64 ipv4e_packets; /* IPv4E headers with extensions processed */ + u64 ipv6_packets; /* IPv6 headers processed */ + u64 ipv6e_packets; /* IPv6E headers with extensions processed */ + u64 tcp_packets; /* TCP headers processed */ + u64 udp_packets; /* UDP headers processed */ + u64 sctp_packets; /* SCTP headers processed */ + u64 nfs_packets; /* NFS headers processe */ + u64 other_packets; +}; + +struct igc_ring_container { + struct igc_ring *ring; /* pointer to linked list of rings */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u16 work_limit; /* total work allowed per interrupt */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +struct igc_ring { + struct igc_q_vector *q_vector; /* backlink to q_vector */ + struct net_device *netdev; /* back pointer to net_device */ + struct device *dev; /* device for dma mapping */ + union { /* array of buffer info structs */ + struct igc_tx_buffer *tx_buffer_info; + struct igc_rx_buffer *rx_buffer_info; + }; + void *desc; /* descriptor ring memory */ + unsigned long flags; /* ring specific flags */ + void __iomem *tail; /* pointer to ring tail register */ + dma_addr_t dma; /* phys address of the ring */ + unsigned int size; /* length of desc. ring in bytes */ + + u16 count; /* number of desc. in the ring */ + u8 queue_index; /* logical index of the ring*/ + u8 reg_idx; /* physical index of the ring */ + bool launchtime_enable; /* true if LaunchTime is enabled */ + + u32 start_time; + u32 end_time; + + /* everything past this point are written often */ + u16 next_to_clean; + u16 next_to_use; + u16 next_to_alloc; + + union { + /* TX */ + struct { + struct igc_tx_queue_stats tx_stats; + struct u64_stats_sync tx_syncp; + struct u64_stats_sync tx_syncp2; + }; + /* RX */ + struct { + struct igc_rx_queue_stats rx_stats; + struct igc_rx_packet_stats pkt_stats; + struct u64_stats_sync rx_syncp; + struct sk_buff *skb; + }; + }; +} ____cacheline_internodealigned_in_smp; + +/* Board specific private data structure */ +struct igc_adapter { + struct net_device *netdev; + + unsigned long state; + unsigned int flags; + unsigned int num_q_vectors; + + struct msix_entry *msix_entries; + + /* TX */ + u16 tx_work_limit; + u32 tx_timeout_count; + int num_tx_queues; + struct igc_ring *tx_ring[IGC_MAX_TX_QUEUES]; + + /* RX */ + int num_rx_queues; + struct igc_ring *rx_ring[IGC_MAX_RX_QUEUES]; + + struct timer_list watchdog_timer; + struct timer_list dma_err_timer; + struct timer_list phy_info_timer; + + u32 wol; + u32 en_mng_pt; + u16 link_speed; + u16 link_duplex; + + u8 port_num; + + u8 __iomem *io_addr; + /* Interrupt Throttle Rate */ + u32 rx_itr_setting; + u32 tx_itr_setting; + + struct work_struct reset_task; + struct work_struct watchdog_task; + struct work_struct dma_err_task; + bool fc_autoneg; + + u8 tx_timeout_factor; + + int msg_enable; + u32 max_frame_size; + u32 min_frame_size; + + ktime_t base_time; + ktime_t cycle_time; + + /* OS defined structs */ + struct pci_dev *pdev; + /* lock for statistics */ + spinlock_t stats64_lock; + struct rtnl_link_stats64 stats64; + + /* structs defined in igc_hw.h */ + struct igc_hw hw; + struct igc_hw_stats stats; + + struct igc_q_vector *q_vector[MAX_Q_VECTORS]; + u32 eims_enable_mask; + u32 eims_other; + + u16 tx_ring_count; + u16 rx_ring_count; + + u32 tx_hwtstamp_timeouts; + u32 tx_hwtstamp_skipped; + u32 rx_hwtstamp_cleared; + + u32 rss_queues; + u32 rss_indir_tbl_init; + + /* RX network flow classification support */ + struct hlist_head nfc_filter_list; + unsigned int nfc_filter_count; + + /* lock for RX network flow classification filter */ + spinlock_t nfc_lock; + bool etype_bitmap[MAX_ETYPE_FILTER]; + + struct igc_mac_addr *mac_table; + + u8 rss_indir_tbl[IGC_RETA_SIZE]; + + unsigned long link_check_timeout; + struct igc_info ei; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_caps; + struct work_struct ptp_tx_work; + struct sk_buff *ptp_tx_skb; + struct hwtstamp_config tstamp_config; + unsigned long ptp_tx_start; + unsigned long last_rx_ptp_check; + unsigned long last_rx_timestamp; + unsigned int ptp_flags; + /* System time value lock */ + spinlock_t tmreg_lock; + struct cyclecounter cc; + struct timecounter tc; +}; void igc_up(struct igc_adapter *adapter); void igc_down(struct igc_adapter *adapter); @@ -36,10 +227,10 @@ void igc_write_rss_indir_tbl(struct igc_adapter *adapter); bool igc_has_link(struct igc_adapter *adapter); void igc_reset(struct igc_adapter *adapter); int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx); -int igc_add_mac_steering_filter(struct igc_adapter *adapter, - const u8 *addr, u8 queue, u8 flags); -int igc_del_mac_steering_filter(struct igc_adapter *adapter, - const u8 *addr, u8 queue, u8 flags); +int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr, + const s8 queue, const u8 flags); +int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr, + const u8 flags); void igc_update_stats(struct igc_adapter *adapter); /* igc_dump declarations */ @@ -50,14 +241,10 @@ extern char igc_driver_name[]; extern char igc_driver_version[]; #define IGC_REGS_LEN 740 -#define IGC_RETA_SIZE 128 /* flags controlling PTP/1588 function */ #define IGC_PTP_ENABLED BIT(0) -/* Interrupt defines */ -#define IGC_START_ITR 648 /* ~6000 ints/sec */ - /* Flags definitions */ #define IGC_FLAG_HAS_MSI BIT(0) #define IGC_FLAG_QUEUE_PAIRS BIT(3) @@ -70,6 +257,7 @@ extern char igc_driver_version[]; #define IGC_FLAG_HAS_MSIX BIT(13) #define IGC_FLAG_VLAN_PROMISC BIT(15) #define IGC_FLAG_RX_LEGACY BIT(16) +#define IGC_FLAG_TSN_QBV_ENABLED BIT(17) #define IGC_FLAG_RSS_FIELD_IPV4_UDP BIT(6) #define IGC_FLAG_RSS_FIELD_IPV6_UDP BIT(7) @@ -78,6 +266,7 @@ extern char igc_driver_version[]; #define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 #define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +/* Interrupt defines */ #define IGC_START_ITR 648 /* ~6000 ints/sec */ #define IGC_4K_ITR 980 #define IGC_20K_ITR 196 @@ -99,13 +288,6 @@ extern char igc_driver_version[]; #define IGC_MIN_RXD 80 #define IGC_MAX_RXD 4096 -/* Transmit and receive queues */ -#define IGC_MAX_RX_QUEUES 4 -#define IGC_MAX_TX_QUEUES 4 - -#define MAX_Q_VECTORS 8 -#define MAX_STD_JUMBO_FRAME_SIZE 9216 - /* Supported Rx Buffer Sizes */ #define IGC_RXBUFFER_256 256 #define IGC_RXBUFFER_2048 2048 @@ -232,83 +414,6 @@ struct igc_rx_buffer { __u16 pagecnt_bias; }; -struct igc_tx_queue_stats { - u64 packets; - u64 bytes; - u64 restart_queue; - u64 restart_queue2; -}; - -struct igc_rx_queue_stats { - u64 packets; - u64 bytes; - u64 drops; - u64 csum_err; - u64 alloc_failed; -}; - -struct igc_rx_packet_stats { - u64 ipv4_packets; /* IPv4 headers processed */ - u64 ipv4e_packets; /* IPv4E headers with extensions processed */ - u64 ipv6_packets; /* IPv6 headers processed */ - u64 ipv6e_packets; /* IPv6E headers with extensions processed */ - u64 tcp_packets; /* TCP headers processed */ - u64 udp_packets; /* UDP headers processed */ - u64 sctp_packets; /* SCTP headers processed */ - u64 nfs_packets; /* NFS headers processe */ - u64 other_packets; -}; - -struct igc_ring_container { - struct igc_ring *ring; /* pointer to linked list of rings */ - unsigned int total_bytes; /* total bytes processed this int */ - unsigned int total_packets; /* total packets processed this int */ - u16 work_limit; /* total work allowed per interrupt */ - u8 count; /* total number of rings in vector */ - u8 itr; /* current ITR setting for ring */ -}; - -struct igc_ring { - struct igc_q_vector *q_vector; /* backlink to q_vector */ - struct net_device *netdev; /* back pointer to net_device */ - struct device *dev; /* device for dma mapping */ - union { /* array of buffer info structs */ - struct igc_tx_buffer *tx_buffer_info; - struct igc_rx_buffer *rx_buffer_info; - }; - void *desc; /* descriptor ring memory */ - unsigned long flags; /* ring specific flags */ - void __iomem *tail; /* pointer to ring tail register */ - dma_addr_t dma; /* phys address of the ring */ - unsigned int size; /* length of desc. ring in bytes */ - - u16 count; /* number of desc. in the ring */ - u8 queue_index; /* logical index of the ring*/ - u8 reg_idx; /* physical index of the ring */ - bool launchtime_enable; /* true if LaunchTime is enabled */ - - /* everything past this point are written often */ - u16 next_to_clean; - u16 next_to_use; - u16 next_to_alloc; - - union { - /* TX */ - struct { - struct igc_tx_queue_stats tx_stats; - struct u64_stats_sync tx_syncp; - struct u64_stats_sync tx_syncp2; - }; - /* RX */ - struct { - struct igc_rx_queue_stats rx_stats; - struct igc_rx_packet_stats pkt_stats; - struct u64_stats_sync rx_syncp; - struct sk_buff *skb; - }; - }; -} ____cacheline_internodealigned_in_smp; - struct igc_q_vector { struct igc_adapter *adapter; /* backlink */ void __iomem *itr_register; @@ -329,8 +434,6 @@ struct igc_q_vector { struct igc_ring ring[] ____cacheline_internodealigned_in_smp; }; -#define MAX_ETYPE_FILTER (4 - 1) - enum igc_filter_match_flags { IGC_FILTER_FLAG_ETHER_TYPE = 0x1, IGC_FILTER_FLAG_VLAN_TCI = 0x2, @@ -363,119 +466,16 @@ struct igc_nfc_filter { struct igc_mac_addr { u8 addr[ETH_ALEN]; - u8 queue; + s8 queue; u8 state; /* bitmask */ }; #define IGC_MAC_STATE_DEFAULT 0x1 #define IGC_MAC_STATE_IN_USE 0x2 #define IGC_MAC_STATE_SRC_ADDR 0x4 -#define IGC_MAC_STATE_QUEUE_STEERING 0x8 #define IGC_MAX_RXNFC_FILTERS 16 -/* Board specific private data structure */ -struct igc_adapter { - struct net_device *netdev; - - unsigned long state; - unsigned int flags; - unsigned int num_q_vectors; - - struct msix_entry *msix_entries; - - /* TX */ - u16 tx_work_limit; - u32 tx_timeout_count; - int num_tx_queues; - struct igc_ring *tx_ring[IGC_MAX_TX_QUEUES]; - - /* RX */ - int num_rx_queues; - struct igc_ring *rx_ring[IGC_MAX_RX_QUEUES]; - - struct timer_list watchdog_timer; - struct timer_list dma_err_timer; - struct timer_list phy_info_timer; - - u32 wol; - u32 en_mng_pt; - u16 link_speed; - u16 link_duplex; - - u8 port_num; - - u8 __iomem *io_addr; - /* Interrupt Throttle Rate */ - u32 rx_itr_setting; - u32 tx_itr_setting; - - struct work_struct reset_task; - struct work_struct watchdog_task; - struct work_struct dma_err_task; - bool fc_autoneg; - - u8 tx_timeout_factor; - - int msg_enable; - u32 max_frame_size; - u32 min_frame_size; - - /* OS defined structs */ - struct pci_dev *pdev; - /* lock for statistics */ - spinlock_t stats64_lock; - struct rtnl_link_stats64 stats64; - - /* structs defined in igc_hw.h */ - struct igc_hw hw; - struct igc_hw_stats stats; - - struct igc_q_vector *q_vector[MAX_Q_VECTORS]; - u32 eims_enable_mask; - u32 eims_other; - - u16 tx_ring_count; - u16 rx_ring_count; - - u32 tx_hwtstamp_timeouts; - u32 tx_hwtstamp_skipped; - u32 rx_hwtstamp_cleared; - - u32 rss_queues; - u32 rss_indir_tbl_init; - - /* RX network flow classification support */ - struct hlist_head nfc_filter_list; - struct hlist_head cls_flower_list; - unsigned int nfc_filter_count; - - /* lock for RX network flow classification filter */ - spinlock_t nfc_lock; - bool etype_bitmap[MAX_ETYPE_FILTER]; - - struct igc_mac_addr *mac_table; - - u8 rss_indir_tbl[IGC_RETA_SIZE]; - - unsigned long link_check_timeout; - struct igc_info ei; - - struct ptp_clock *ptp_clock; - struct ptp_clock_info ptp_caps; - struct work_struct ptp_tx_work; - struct sk_buff *ptp_tx_skb; - struct hwtstamp_config tstamp_config; - unsigned long ptp_tx_start; - unsigned long last_rx_ptp_check; - unsigned long last_rx_timestamp; - unsigned int ptp_flags; - /* System time value lock */ - spinlock_t tmreg_lock; - struct cyclecounter cc; - struct timecounter tc; -}; - /* igc_desc_unused - calculate if we have unused descriptors */ static inline u16 igc_desc_unused(const struct igc_ring *ring) { diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 5a506440560a..f7fb18d8d8f5 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -212,6 +212,9 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) case IGC_DEV_ID_I225_I: case IGC_DEV_ID_I220_V: case IGC_DEV_ID_I225_K: + case IGC_DEV_ID_I225_K2: + case IGC_DEV_ID_I225_LMVP: + case IGC_DEV_ID_I225_IT: case IGC_DEV_ID_I225_BLANK_NVM: mac->type = igc_i225; break; diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 4ddccccf42cc..af0c03d77a39 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -44,9 +44,6 @@ /* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */ #define IGC_WUPM_BYTES 128 -/* Physical Func Reset Done Indication */ -#define IGC_CTRL_EXT_LINK_MODE_MASK 0x00C00000 - /* Loop limit on how long we wait for auto-negotiation to complete */ #define COPPER_LINK_UP_LIMIT 10 #define PHY_AUTO_NEG_LIMIT 45 @@ -66,8 +63,11 @@ * (RAR[15]) for our directed address used by controllers with * manageability enabled, allowing us room for 15 multicast addresses. */ +#define IGC_RAH_QSEL_MASK 0x000C0000 +#define IGC_RAH_QSEL_SHIFT 18 +#define IGC_RAH_QSEL_ENABLE BIT(28) #define IGC_RAH_AV 0x80000000 /* Receive descriptor valid */ -#define IGC_RAH_POOL_1 0x00040000 + #define IGC_RAL_MAC_ADDR_LEN 4 #define IGC_RAH_MAC_ADDR_LEN 2 @@ -94,8 +94,6 @@ #define IGC_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */ #define IGC_CTRL_TFCE 0x10000000 /* Transmit flow control enable */ -#define IGC_CONNSW_AUTOSENSE_EN 0x1 - /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */ #define MAX_JUMBO_FRAME_SIZE 0x2600 @@ -377,6 +375,11 @@ #define I225_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ #define IGC_RXPBS_CFG_TS_EN 0x80000000 /* Timestamp in Rx buffer */ +#define IGC_TXPBSIZE_TSN 0x04145145 /* 5k bytes buffer for each queue */ + +#define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ +#define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ + /* Time Sync Interrupt Causes */ #define IGC_TSICR_SYS_WRAP BIT(0) /* SYSTIM Wrap around. */ #define IGC_TSICR_TXTS BIT(1) /* Transmit Timestamp. */ @@ -431,6 +434,14 @@ #define IGC_TSYNCTXCTL_START_SYNC 0x80000000 /* initiate sync */ #define IGC_TSYNCTXCTL_TXSYNSIG 0x00000020 /* Sample TX tstamp in PHY sop */ +/* Transmit Scheduling */ +#define IGC_TQAVCTRL_TRANSMIT_MODE_TSN 0x00000001 +#define IGC_TQAVCTRL_ENHANCED_QAV 0x00000008 + +#define IGC_TXQCTL_QUEUE_MODE_LAUNCHT 0x00000001 +#define IGC_TXQCTL_STRICT_CYCLE 0x00000002 +#define IGC_TXQCTL_STRICT_END 0x00000004 + /* Receive Checksum Control */ #define IGC_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */ #define IGC_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ @@ -497,7 +508,6 @@ #define IGC_MDIC_READY 0x10000000 #define IGC_MDIC_INT_EN 0x20000000 #define IGC_MDIC_ERROR 0x40000000 -#define IGC_MDIC_DEST 0x80000000 #define IGC_N0_QUEUE -1 diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index f530fc29b074..0a8c4a7412a4 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -153,7 +153,7 @@ static void igc_get_regs(struct net_device *netdev, memset(p, 0, IGC_REGS_LEN * sizeof(u32)); - regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id; + regs->version = (2u << 24) | (hw->revision_id << 16) | hw->device_id; /* General Registers */ regs_buff[0] = rd32(IGC_CTRL); @@ -306,6 +306,15 @@ static void igc_get_regs(struct net_device *netdev, regs_buff[164 + i] = rd32(IGC_TDT(i)); for (i = 0; i < 4; i++) regs_buff[168 + i] = rd32(IGC_TXDCTL(i)); + + /* XXX: Due to a bug few lines above, RAL and RAH registers are + * overwritten. To preserve the ABI, we write these registers again in + * regs_buff. + */ + for (i = 0; i < 16; i++) + regs_buff[172 + i] = rd32(IGC_RAL(i)); + for (i = 0; i < 16; i++) + regs_buff[188 + i] = rd32(IGC_RAH(i)); } static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) @@ -1257,20 +1266,16 @@ int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input) } if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) { - err = igc_add_mac_steering_filter(adapter, - input->filter.dst_addr, - input->action, 0); - err = min_t(int, err, 0); + err = igc_add_mac_filter(adapter, input->filter.dst_addr, + input->action, 0); if (err) return err; } if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) { - err = igc_add_mac_steering_filter(adapter, - input->filter.src_addr, - input->action, - IGC_MAC_STATE_SRC_ADDR); - err = min_t(int, err, 0); + err = igc_add_mac_filter(adapter, input->filter.src_addr, + input->action, + IGC_MAC_STATE_SRC_ADDR); if (err) return err; } @@ -1324,13 +1329,11 @@ int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input) ntohs(input->filter.vlan_tci)); if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) - igc_del_mac_steering_filter(adapter, input->filter.src_addr, - input->action, - IGC_MAC_STATE_SRC_ADDR); + igc_del_mac_filter(adapter, input->filter.src_addr, + IGC_MAC_STATE_SRC_ADDR); if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) - igc_del_mac_steering_filter(adapter, input->filter.dst_addr, - input->action, 0); + igc_del_mac_filter(adapter, input->filter.dst_addr, 0); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index 90ac0e0144d8..af34ae310327 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -21,6 +21,9 @@ #define IGC_DEV_ID_I225_I 0x15F8 #define IGC_DEV_ID_I220_V 0x15F7 #define IGC_DEV_ID_I225_K 0x3100 +#define IGC_DEV_ID_I225_K2 0x3101 +#define IGC_DEV_ID_I225_LMVP 0x5502 +#define IGC_DEV_ID_I225_IT 0x0D9F #define IGC_DEV_ID_I225_BLANK_NVM 0x15FD /* Function pointers for the MAC. */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 69fa1ce1f927..9d5f8287c704 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -9,11 +9,13 @@ #include <linux/udp.h> #include <linux/ip.h> #include <linux/pm_runtime.h> +#include <net/pkt_sched.h> #include <net/ipv6.h> #include "igc.h" #include "igc_hw.h" +#include "igc_tsn.h" #define DRV_VERSION "0.0.1-k" #define DRV_SUMMARY "Intel(R) 2.5G Ethernet Linux Driver" @@ -45,6 +47,9 @@ static const struct pci_device_id igc_pci_tbl[] = { { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_I), board_base }, { PCI_VDEVICE(INTEL, IGC_DEV_ID_I220_V), board_base }, { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K2), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LMVP), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_IT), board_base }, { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_BLANK_NVM), board_base }, /* required last entry */ {0, } @@ -106,6 +111,9 @@ void igc_reset(struct igc_adapter *adapter) /* Re-enable PTP, where applicable. */ igc_ptp_reset(adapter); + /* Re-enable TSN offloading, where applicable. */ + igc_tsn_offload_apply(adapter); + igc_get_phy_info(hw); } @@ -757,48 +765,74 @@ static void igc_setup_tctl(struct igc_adapter *adapter) } /** - * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table - * @adapter: address of board private structure - * @index: Index of the RAR entry which need to be synced with MAC table + * igc_set_mac_filter_hw() - Set MAC address filter in hardware + * @adapter: Pointer to adapter where the filter should be set + * @index: Filter index + * @addr: Destination MAC address + * @queue: If non-negative, queue assignment feature is enabled and frames + * matching the filter are enqueued onto 'queue'. Otherwise, queue + * assignment is disabled. */ -static void igc_rar_set_index(struct igc_adapter *adapter, u32 index) +static void igc_set_mac_filter_hw(struct igc_adapter *adapter, int index, + const u8 *addr, int queue) { - u8 *addr = adapter->mac_table[index].addr; + struct net_device *dev = adapter->netdev; struct igc_hw *hw = &adapter->hw; - u32 rar_low, rar_high; + u32 ral, rah; - /* HW expects these to be in network order when they are plugged - * into the registers which are little endian. In order to guarantee - * that ordering we need to do an leXX_to_cpup here in order to be - * ready for the byteswap that occurs with writel - */ - rar_low = le32_to_cpup((__le32 *)(addr)); - rar_high = le16_to_cpup((__le16 *)(addr + 4)); + if (WARN_ON(index >= hw->mac.rar_entry_count)) + return; - /* Indicate to hardware the Address is Valid. */ - if (adapter->mac_table[index].state & IGC_MAC_STATE_IN_USE) { - if (is_valid_ether_addr(addr)) - rar_high |= IGC_RAH_AV; + ral = le32_to_cpup((__le32 *)(addr)); + rah = le16_to_cpup((__le16 *)(addr + 4)); - rar_high |= IGC_RAH_POOL_1 << - adapter->mac_table[index].queue; + if (queue >= 0) { + rah &= ~IGC_RAH_QSEL_MASK; + rah |= (queue << IGC_RAH_QSEL_SHIFT); + rah |= IGC_RAH_QSEL_ENABLE; } - wr32(IGC_RAL(index), rar_low); - wrfl(); - wr32(IGC_RAH(index), rar_high); - wrfl(); + rah |= IGC_RAH_AV; + + wr32(IGC_RAL(index), ral); + wr32(IGC_RAH(index), rah); + + netdev_dbg(dev, "MAC address filter set in HW: index %d", index); +} + +/** + * igc_clear_mac_filter_hw() - Clear MAC address filter in hardware + * @adapter: Pointer to adapter where the filter should be cleared + * @index: Filter index + */ +static void igc_clear_mac_filter_hw(struct igc_adapter *adapter, int index) +{ + struct net_device *dev = adapter->netdev; + struct igc_hw *hw = &adapter->hw; + + if (WARN_ON(index >= hw->mac.rar_entry_count)) + return; + + wr32(IGC_RAL(index), 0); + wr32(IGC_RAH(index), 0); + + netdev_dbg(dev, "MAC address filter cleared in HW: index %d", index); } /* Set default MAC address for the PF in the first RAR entry */ static void igc_set_default_mac_filter(struct igc_adapter *adapter) { struct igc_mac_addr *mac_table = &adapter->mac_table[0]; + struct net_device *dev = adapter->netdev; + u8 *addr = adapter->hw.mac.addr; - ether_addr_copy(mac_table->addr, adapter->hw.mac.addr); + netdev_dbg(dev, "Set default MAC address filter: address %pM", addr); + + ether_addr_copy(mac_table->addr, addr); mac_table->state = IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE; + mac_table->queue = -1; - igc_rar_set_index(adapter, 0); + igc_set_mac_filter_hw(adapter, 0, addr, mac_table->queue); } /** @@ -864,6 +898,23 @@ static int igc_write_mc_addr_list(struct net_device *netdev) return netdev_mc_count(netdev); } +static __le32 igc_tx_launchtime(struct igc_adapter *adapter, ktime_t txtime) +{ + ktime_t cycle_time = adapter->cycle_time; + ktime_t base_time = adapter->base_time; + u32 launchtime; + + /* FIXME: when using ETF together with taprio, we may have a + * case where 'delta' is larger than the cycle_time, this may + * cause problems if we don't read the current value of + * IGC_BASET, as the value writen into the launchtime + * descriptor field may be misinterpreted. + */ + div_s64_rem(ktime_sub_ns(txtime, base_time), cycle_time, &launchtime); + + return cpu_to_le32(launchtime); +} + static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, struct igc_tx_buffer *first, u32 vlan_macip_lens, u32 type_tucmd, @@ -871,7 +922,6 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, { struct igc_adv_tx_context_desc *context_desc; u16 i = tx_ring->next_to_use; - struct timespec64 ts; context_desc = IGC_TX_CTXTDESC(tx_ring, i); @@ -893,9 +943,12 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, * should have been handled by the upper layers. */ if (tx_ring->launchtime_enable) { - ts = ktime_to_timespec64(first->skb->tstamp); + struct igc_adapter *adapter = netdev_priv(tx_ring->netdev); + ktime_t txtime = first->skb->tstamp; + first->skb->tstamp = ktime_set(0, 0); - context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32); + context_desc->launch_time = igc_tx_launchtime(adapter, + txtime); } else { context_desc->launch_time = 0; } @@ -2133,129 +2186,148 @@ static void igc_nfc_filter_restore(struct igc_adapter *adapter) spin_unlock(&adapter->nfc_lock); } -/* If the filter to be added and an already existing filter express - * the same address and address type, it should be possible to only - * override the other configurations, for example the queue to steer - * traffic. - */ -static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry, - const u8 *addr, const u8 flags) +static int igc_find_mac_filter(struct igc_adapter *adapter, const u8 *addr, + u8 flags) { - if (!(entry->state & IGC_MAC_STATE_IN_USE)) - return true; + int max_entries = adapter->hw.mac.rar_entry_count; + struct igc_mac_addr *entry; + int i; - if ((entry->state & IGC_MAC_STATE_SRC_ADDR) != - (flags & IGC_MAC_STATE_SRC_ADDR)) - return false; + for (i = 0; i < max_entries; i++) { + entry = &adapter->mac_table[i]; - if (!ether_addr_equal(addr, entry->addr)) - return false; + if (!(entry->state & IGC_MAC_STATE_IN_USE)) + continue; + if (!ether_addr_equal(addr, entry->addr)) + continue; + if ((entry->state & IGC_MAC_STATE_SRC_ADDR) != + (flags & IGC_MAC_STATE_SRC_ADDR)) + continue; - return true; + return i; + } + + return -1; } -/* Add a MAC filter for 'addr' directing matching traffic to 'queue', - * 'flags' is used to indicate what kind of match is made, match is by - * default for the destination address, if matching by source address - * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used. - */ -static int igc_add_mac_filter(struct igc_adapter *adapter, - const u8 *addr, const u8 queue) +static int igc_get_avail_mac_filter_slot(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; - int rar_entries = hw->mac.rar_entry_count; + int max_entries = adapter->hw.mac.rar_entry_count; + struct igc_mac_addr *entry; int i; - if (is_zero_ether_addr(addr)) + for (i = 0; i < max_entries; i++) { + entry = &adapter->mac_table[i]; + + if (!(entry->state & IGC_MAC_STATE_IN_USE)) + return i; + } + + return -1; +} + +/** + * igc_add_mac_filter() - Add MAC address filter + * @adapter: Pointer to adapter where the filter should be added + * @addr: MAC address + * @queue: If non-negative, queue assignment feature is enabled and frames + * matching the filter are enqueued onto 'queue'. Otherwise, queue + * assignment is disabled. + * @flags: Set IGC_MAC_STATE_SRC_ADDR bit to indicate @address is a source + * address + * + * Return: 0 in case of success, negative errno code otherwise. + */ +int igc_add_mac_filter(struct igc_adapter *adapter, const u8 *addr, + const s8 queue, const u8 flags) +{ + struct net_device *dev = adapter->netdev; + int index; + + if (!is_valid_ether_addr(addr)) return -EINVAL; + if (flags & IGC_MAC_STATE_SRC_ADDR) + return -ENOTSUPP; - /* Search for the first empty entry in the MAC table. - * Do not touch entries at the end of the table reserved for the VF MAC - * addresses. - */ - for (i = 0; i < rar_entries; i++) { - if (!igc_mac_entry_can_be_used(&adapter->mac_table[i], - addr, 0)) - continue; + index = igc_find_mac_filter(adapter, addr, flags); + if (index >= 0) + goto update_queue_assignment; - ether_addr_copy(adapter->mac_table[i].addr, addr); - adapter->mac_table[i].queue = queue; - adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE; + index = igc_get_avail_mac_filter_slot(adapter); + if (index < 0) + return -ENOSPC; - igc_rar_set_index(adapter, i); - return i; - } + netdev_dbg(dev, "Add MAC address filter: index %d address %pM queue %d", + index, addr, queue); + + ether_addr_copy(adapter->mac_table[index].addr, addr); + adapter->mac_table[index].state |= IGC_MAC_STATE_IN_USE | flags; +update_queue_assignment: + adapter->mac_table[index].queue = queue; - return -ENOSPC; + igc_set_mac_filter_hw(adapter, index, addr, queue); + return 0; } -/* Remove a MAC filter for 'addr' directing matching traffic to - * 'queue', 'flags' is used to indicate what kind of match need to be - * removed, match is by default for the destination address, if - * matching by source address is to be removed the flag - * IGC_MAC_STATE_SRC_ADDR can be used. +/** + * igc_del_mac_filter() - Delete MAC address filter + * @adapter: Pointer to adapter where the filter should be deleted from + * @addr: MAC address + * @flags: Set IGC_MAC_STATE_SRC_ADDR bit to indicate @address is a source + * address + * + * Return: 0 in case of success, negative errno code otherwise. */ -static int igc_del_mac_filter(struct igc_adapter *adapter, - const u8 *addr, const u8 queue) +int igc_del_mac_filter(struct igc_adapter *adapter, const u8 *addr, + const u8 flags) { - struct igc_hw *hw = &adapter->hw; - int rar_entries = hw->mac.rar_entry_count; - int i; + struct net_device *dev = adapter->netdev; + struct igc_mac_addr *entry; + int index; - if (is_zero_ether_addr(addr)) + if (!is_valid_ether_addr(addr)) return -EINVAL; - /* Search for matching entry in the MAC table based on given address - * and queue. Do not touch entries at the end of the table reserved - * for the VF MAC addresses. - */ - for (i = 0; i < rar_entries; i++) { - if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE)) - continue; - if (adapter->mac_table[i].state != 0) - continue; - if (adapter->mac_table[i].queue != queue) - continue; - if (!ether_addr_equal(adapter->mac_table[i].addr, addr)) - continue; + index = igc_find_mac_filter(adapter, addr, flags); + if (index < 0) + return -ENOENT; - /* When a filter for the default address is "deleted", - * we return it to its initial configuration + entry = &adapter->mac_table[index]; + + if (entry->state & IGC_MAC_STATE_DEFAULT) { + /* If this is the default filter, we don't actually delete it. + * We just reset to its default value i.e. disable queue + * assignment. */ - if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) { - adapter->mac_table[i].state = - IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE; - adapter->mac_table[i].queue = 0; - } else { - adapter->mac_table[i].state = 0; - adapter->mac_table[i].queue = 0; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); - } + netdev_dbg(dev, "Disable default MAC filter queue assignment"); - igc_rar_set_index(adapter, i); - return 0; + entry->queue = -1; + igc_set_mac_filter_hw(adapter, 0, addr, entry->queue); + } else { + netdev_dbg(dev, "Delete MAC address filter: index %d address %pM", + index, addr); + + entry->state = 0; + entry->queue = -1; + memset(entry->addr, 0, ETH_ALEN); + igc_clear_mac_filter_hw(adapter, index); } - return -ENOENT; + return 0; } static int igc_uc_sync(struct net_device *netdev, const unsigned char *addr) { struct igc_adapter *adapter = netdev_priv(netdev); - int ret; - - ret = igc_add_mac_filter(adapter, addr, adapter->num_rx_queues); - return min_t(int, ret, 0); + return igc_add_mac_filter(adapter, addr, -1, 0); } static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr) { struct igc_adapter *adapter = netdev_priv(netdev); - igc_del_mac_filter(adapter, addr, adapter->num_rx_queues); - - return 0; + return igc_del_mac_filter(adapter, addr, 0); } /** @@ -2325,7 +2397,9 @@ static void igc_configure(struct igc_adapter *adapter) igc_setup_mrqc(adapter); igc_setup_rctl(adapter); + igc_set_default_mac_filter(adapter); igc_nfc_filter_restore(adapter); + igc_configure_tx(adapter); igc_configure_rx(adapter); @@ -3458,9 +3532,6 @@ static void igc_nfc_filter_exit(struct igc_adapter *adapter) hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) igc_erase_filter(adapter, rule); - hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node) - igc_erase_filter(adapter, rule); - spin_unlock(&adapter->nfc_lock); } @@ -3689,106 +3760,6 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, return features; } -/* Add a MAC filter for 'addr' directing matching traffic to 'queue', - * 'flags' is used to indicate what kind of match is made, match is by - * default for the destination address, if matching by source address - * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used. - */ -static int igc_add_mac_filter_flags(struct igc_adapter *adapter, - const u8 *addr, const u8 queue, - const u8 flags) -{ - struct igc_hw *hw = &adapter->hw; - int rar_entries = hw->mac.rar_entry_count; - int i; - - if (is_zero_ether_addr(addr)) - return -EINVAL; - - /* Search for the first empty entry in the MAC table. - * Do not touch entries at the end of the table reserved for the VF MAC - * addresses. - */ - for (i = 0; i < rar_entries; i++) { - if (!igc_mac_entry_can_be_used(&adapter->mac_table[i], - addr, flags)) - continue; - - ether_addr_copy(adapter->mac_table[i].addr, addr); - adapter->mac_table[i].queue = queue; - adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags; - - igc_rar_set_index(adapter, i); - return i; - } - - return -ENOSPC; -} - -int igc_add_mac_steering_filter(struct igc_adapter *adapter, - const u8 *addr, u8 queue, u8 flags) -{ - return igc_add_mac_filter_flags(adapter, addr, queue, - IGC_MAC_STATE_QUEUE_STEERING | flags); -} - -/* Remove a MAC filter for 'addr' directing matching traffic to - * 'queue', 'flags' is used to indicate what kind of match need to be - * removed, match is by default for the destination address, if - * matching by source address is to be removed the flag - * IGC_MAC_STATE_SRC_ADDR can be used. - */ -static int igc_del_mac_filter_flags(struct igc_adapter *adapter, - const u8 *addr, const u8 queue, - const u8 flags) -{ - struct igc_hw *hw = &adapter->hw; - int rar_entries = hw->mac.rar_entry_count; - int i; - - if (is_zero_ether_addr(addr)) - return -EINVAL; - - /* Search for matching entry in the MAC table based on given address - * and queue. Do not touch entries at the end of the table reserved - * for the VF MAC addresses. - */ - for (i = 0; i < rar_entries; i++) { - if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE)) - continue; - if ((adapter->mac_table[i].state & flags) != flags) - continue; - if (adapter->mac_table[i].queue != queue) - continue; - if (!ether_addr_equal(adapter->mac_table[i].addr, addr)) - continue; - - /* When a filter for the default address is "deleted", - * we return it to its initial configuration - */ - if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) { - adapter->mac_table[i].state = - IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE; - } else { - adapter->mac_table[i].state = 0; - adapter->mac_table[i].queue = 0; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); - } - - igc_rar_set_index(adapter, i); - return 0; - } - - return -ENOENT; -} - -int igc_del_mac_steering_filter(struct igc_adapter *adapter, - const u8 *addr, u8 queue, u8 flags) -{ - return igc_del_mac_filter_flags(adapter, addr, queue, - IGC_MAC_STATE_QUEUE_STEERING | flags); -} - static void igc_tsync_interrupt(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -4009,7 +3980,6 @@ static void igc_watchdog_task(struct work_struct *work) struct igc_hw *hw = &adapter->hw; struct igc_phy_info *phy = &hw->phy; u16 phy_data, retry_count = 20; - u32 connsw; u32 link; int i; @@ -4022,14 +3992,6 @@ static void igc_watchdog_task(struct work_struct *work) link = false; } - /* Force link down if we have fiber to swap to */ - if (adapter->flags & IGC_FLAG_MAS_ENABLE) { - if (hw->phy.media_type == igc_media_type_copper) { - connsw = rd32(IGC_CONNSW); - if (!(connsw & IGC_CONNSW_AUTOSENSE_EN)) - link = 0; - } - } if (link) { /* Cancel scheduled suspend requests. */ pm_runtime_resume(netdev->dev.parent); @@ -4491,6 +4453,158 @@ static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) } } +static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue, + bool enable) +{ + struct igc_ring *ring; + int i; + + if (queue < 0 || queue >= adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[queue]; + ring->launchtime_enable = enable; + + if (adapter->base_time) + return 0; + + adapter->cycle_time = NSEC_PER_SEC; + + for (i = 0; i < adapter->num_tx_queues; i++) { + ring = adapter->tx_ring[i]; + ring->start_time = 0; + ring->end_time = NSEC_PER_SEC; + } + + return 0; +} + +static bool validate_schedule(const struct tc_taprio_qopt_offload *qopt) +{ + int queue_uses[IGC_MAX_TX_QUEUES] = { }; + size_t n; + + if (qopt->cycle_time_extension) + return false; + + for (n = 0; n < qopt->num_entries; n++) { + const struct tc_taprio_sched_entry *e; + int i; + + e = &qopt->entries[n]; + + /* i225 only supports "global" frame preemption + * settings. + */ + if (e->command != TC_TAPRIO_CMD_SET_GATES) + return false; + + for (i = 0; i < IGC_MAX_TX_QUEUES; i++) { + if (e->gate_mask & BIT(i)) + queue_uses[i]++; + + if (queue_uses[i] > 1) + return false; + } + } + + return true; +} + +static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, + struct tc_etf_qopt_offload *qopt) +{ + struct igc_hw *hw = &adapter->hw; + int err; + + if (hw->mac.type != igc_i225) + return -EOPNOTSUPP; + + err = igc_save_launchtime_params(adapter, qopt->queue, qopt->enable); + if (err) + return err; + + return igc_tsn_offload_apply(adapter); +} + +static int igc_save_qbv_schedule(struct igc_adapter *adapter, + struct tc_taprio_qopt_offload *qopt) +{ + u32 start_time = 0, end_time = 0; + size_t n; + + if (!qopt->enable) { + adapter->base_time = 0; + return 0; + } + + if (adapter->base_time) + return -EALREADY; + + if (!validate_schedule(qopt)) + return -EINVAL; + + adapter->cycle_time = qopt->cycle_time; + adapter->base_time = qopt->base_time; + + /* FIXME: be a little smarter about cases when the gate for a + * queue stays open for more than one entry. + */ + for (n = 0; n < qopt->num_entries; n++) { + struct tc_taprio_sched_entry *e = &qopt->entries[n]; + int i; + + end_time += e->interval; + + for (i = 0; i < IGC_MAX_TX_QUEUES; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + + if (!(e->gate_mask & BIT(i))) + continue; + + ring->start_time = start_time; + ring->end_time = end_time; + } + + start_time += e->interval; + } + + return 0; +} + +static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, + struct tc_taprio_qopt_offload *qopt) +{ + struct igc_hw *hw = &adapter->hw; + int err; + + if (hw->mac.type != igc_i225) + return -EOPNOTSUPP; + + err = igc_save_qbv_schedule(adapter, qopt); + if (err) + return err; + + return igc_tsn_offload_apply(adapter); +} + +static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct igc_adapter *adapter = netdev_priv(dev); + + switch (type) { + case TC_SETUP_QDISC_TAPRIO: + return igc_tsn_enable_qbv_scheduling(adapter, type_data); + + case TC_SETUP_QDISC_ETF: + return igc_tsn_enable_launchtime(adapter, type_data); + + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops igc_netdev_ops = { .ndo_open = igc_open, .ndo_stop = igc_close, @@ -4503,6 +4617,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, .ndo_do_ioctl = igc_ioctl, + .ndo_setup_tc = igc_setup_tc, }; /* PCIe configuration access */ @@ -4726,6 +4841,17 @@ static int igc_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_RXCSUM; netdev->features |= NETIF_F_HW_CSUM; netdev->features |= NETIF_F_SCTP_CRC; + netdev->features |= NETIF_F_HW_TC; + +#define IGC_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ + NETIF_F_GSO_GRE_CSUM | \ + NETIF_F_GSO_IPXIP4 | \ + NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_TUNNEL | \ + NETIF_F_GSO_UDP_TUNNEL_CSUM) + + netdev->gso_partial_features = IGC_GSO_PARTIAL_FEATURES; + netdev->features |= NETIF_F_GSO_PARTIAL | IGC_GSO_PARTIAL_FEATURES; /* setup the private structure */ err = igc_sw_init(adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index d4af53a80f11..6093cde2351c 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -231,6 +231,18 @@ #define IGC_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */ +/* Transmit Scheduling Registers */ +#define IGC_TQAVCTRL 0x3570 +#define IGC_TXQCTL(_n) (0x3344 + 0x4 * (_n)) +#define IGC_BASET_L 0x3314 +#define IGC_BASET_H 0x3318 +#define IGC_QBVCYCLET 0x331C +#define IGC_QBVCYCLET_S 0x3320 + +#define IGC_STQT(_n) (0x3324 + 0x4 * (_n)) +#define IGC_ENDQT(_n) (0x3334 + 0x4 * (_n)) +#define IGC_DTXMXPKTSZ 0x355C + /* System Time Registers */ #define IGC_SYSTIML 0x0B600 /* System time register Low - RO */ #define IGC_SYSTIMH 0x0B604 /* System time register High - RO */ diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c new file mode 100644 index 000000000000..174103c4bea6 --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Intel Corporation */ + +#include "igc.h" +#include "igc_tsn.h" + +static bool is_any_launchtime(struct igc_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + + if (ring->launchtime_enable) + return true; + } + + return false; +} + +/* Returns the TSN specific registers to their default values after + * TSN offloading is disabled. + */ +static int igc_tsn_disable_offload(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 tqavctrl; + int i; + + if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED)) + return 0; + + adapter->cycle_time = 0; + + wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); + wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + + tqavctrl = rd32(IGC_TQAVCTRL); + tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | + IGC_TQAVCTRL_ENHANCED_QAV); + wr32(IGC_TQAVCTRL, tqavctrl); + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + + ring->start_time = 0; + ring->end_time = 0; + ring->launchtime_enable = false; + + wr32(IGC_TXQCTL(i), 0); + wr32(IGC_STQT(i), 0); + wr32(IGC_ENDQT(i), NSEC_PER_SEC); + } + + wr32(IGC_QBVCYCLET_S, NSEC_PER_SEC); + wr32(IGC_QBVCYCLET, NSEC_PER_SEC); + + adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED; + + return 0; +} + +static int igc_tsn_enable_offload(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 tqavctrl, baset_l, baset_h; + u32 sec, nsec, cycle; + ktime_t base_time, systim; + int i; + + if (adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) + return 0; + + cycle = adapter->cycle_time; + base_time = adapter->base_time; + + wr32(IGC_TSAUXC, 0); + wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); + wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + + tqavctrl = rd32(IGC_TQAVCTRL); + tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; + wr32(IGC_TQAVCTRL, tqavctrl); + + wr32(IGC_QBVCYCLET_S, cycle); + wr32(IGC_QBVCYCLET, cycle); + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + u32 txqctl = 0; + + wr32(IGC_STQT(i), ring->start_time); + wr32(IGC_ENDQT(i), ring->end_time); + + if (adapter->base_time) { + /* If we have a base_time we are in "taprio" + * mode and we need to be strict about the + * cycles: only transmit a packet if it can be + * completed during that cycle. + */ + txqctl |= IGC_TXQCTL_STRICT_CYCLE | + IGC_TXQCTL_STRICT_END; + } + + if (ring->launchtime_enable) + txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT; + + wr32(IGC_TXQCTL(i), txqctl); + } + + nsec = rd32(IGC_SYSTIML); + sec = rd32(IGC_SYSTIMH); + + systim = ktime_set(sec, nsec); + + if (ktime_compare(systim, base_time) > 0) { + s64 n; + + n = div64_s64(ktime_sub_ns(systim, base_time), cycle); + base_time = ktime_add_ns(base_time, (n + 1) * cycle); + } + + baset_h = div_s64_rem(base_time, NSEC_PER_SEC, &baset_l); + + wr32(IGC_BASET_H, baset_h); + wr32(IGC_BASET_L, baset_l); + + adapter->flags |= IGC_FLAG_TSN_QBV_ENABLED; + + return 0; +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + bool is_any_enabled = adapter->base_time || is_any_launchtime(adapter); + + if (!(adapter->flags & IGC_FLAG_TSN_QBV_ENABLED) && !is_any_enabled) + return 0; + + if (!is_any_enabled) { + int err = igc_tsn_disable_offload(adapter); + + if (err < 0) + return err; + + /* The BASET registers aren't cleared when writing + * into them, force a reset if the interface is + * running. + */ + if (netif_running(adapter->netdev)) + schedule_work(&adapter->reset_task); + + return 0; + } + + return igc_tsn_enable_offload(adapter); +} diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h new file mode 100644 index 000000000000..f76bc86ddccd --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Intel Corporation */ + +#ifndef _IGC_TSN_H_ +#define _IGC_TSN_H_ + +int igc_tsn_offload_apply(struct igc_adapter *adapter); + +#endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5be61f73b6ab..51889770958d 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -5383,7 +5383,7 @@ static int __init mvneta_driver_init(void) { int ret; - ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/mvmeta:online", + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/mvneta:online", mvneta_cpu_online, mvneta_cpu_down_prepare); if (ret < 0) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 018c283a0ac4..0b1c653b3449 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -309,7 +309,7 @@ static inline void __iomem *otx2_get_regaddr(struct otx2_nic *nic, u64 offset) default: blkaddr = BLKADDR_RVUM; break; - }; + } offset &= ~(RVU_FUNC_BLKADDR_MASK << RVU_FUNC_BLKADDR_SHIFT); offset |= (blkaddr << RVU_FUNC_BLKADDR_SHIFT); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8d28f90acfe7..09047109d0da 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -65,6 +65,17 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg) return __raw_readl(eth->base + reg); } +u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg) +{ + u32 val; + + val = mtk_r32(eth, reg); + val &= ~mask; + val |= set; + mtk_w32(eth, val, reg); + return reg; +} + static int mtk_mdio_busy_wait(struct mtk_eth *eth) { unsigned long t_start = jiffies; @@ -193,7 +204,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, struct mtk_mac *mac = container_of(config, struct mtk_mac, phylink_config); struct mtk_eth *eth = mac->hw; - u32 mcr_cur, mcr_new, sid; + u32 mcr_cur, mcr_new, sid, i; int val, ge_mode, err; /* MT76x8 has no hardware settings between for the MAC */ @@ -255,6 +266,17 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, PHY_INTERFACE_MODE_TRGMII) mtk_gmac0_rgmii_adjust(mac->hw, state->speed); + + /* mt7623_pad_clk_setup */ + for (i = 0 ; i < NUM_TRGMII_CTRL; i++) + mtk_w32(mac->hw, + TD_DM_DRVP(8) | TD_DM_DRVN(8), + TRGMII_TD_ODT(i)); + + /* Assert/release MT7623 RXC reset */ + mtk_m32(mac->hw, 0, RXC_RST | RXC_DQSISEL, + TRGMII_RCK_CTRL); + mtk_m32(mac->hw, RXC_RST, 0, TRGMII_RCK_CTRL); } } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 85830fe14a1b..454cfcd465fd 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -352,10 +352,13 @@ #define DQSI0(x) ((x << 0) & GENMASK(6, 0)) #define DQSI1(x) ((x << 8) & GENMASK(14, 8)) #define RXCTL_DMWTLAT(x) ((x << 16) & GENMASK(18, 16)) +#define RXC_RST BIT(31) #define RXC_DQSISEL BIT(30) #define RCK_CTRL_RGMII_1000 (RXC_DQSISEL | RXCTL_DMWTLAT(2) | DQSI1(16)) #define RCK_CTRL_RGMII_10_100 RXCTL_DMWTLAT(2) +#define NUM_TRGMII_CTRL 5 + /* TRGMII RXC control register */ #define TRGMII_TCK_CTRL 0x10340 #define TXCTL_DMWTLAT(x) ((x << 16) & GENMASK(18, 16)) @@ -363,6 +366,11 @@ #define TCK_CTRL_RGMII_1000 TXCTL_DMWTLAT(2) #define TCK_CTRL_RGMII_10_100 (TXC_INV | TXCTL_DMWTLAT(2)) +/* TRGMII TX Drive Strength */ +#define TRGMII_TD_ODT(i) (0x10354 + 8 * (i)) +#define TD_DM_DRVP(x) ((x) & 0xf) +#define TD_DM_DRVN(x) (((x) & 0xf) << 4) + /* TRGMII Interface mode register */ #define INTF_MODE 0x10390 #define TRGMII_INTF_DIS BIT(0) diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c index 73eae80e1cb7..ac5468b77488 100644 --- a/drivers/net/ethernet/mellanox/mlx4/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -197,6 +197,7 @@ int mlx4_crdump_collect(struct mlx4_dev *dev) err = devlink_region_snapshot_id_get(devlink, &id); if (err) { mlx4_err(dev, "crdump: devlink get snapshot id err %d\n", err); + iounmap(cr_space); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index db3552f2d087..787139219813 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -946,7 +946,7 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget) xdp_tx_cq = priv->tx_cq[TX_XDP][cq->ring]; if (xdp_tx_cq->xdp_busy) { clean_complete = mlx4_en_process_tx_cq(dev, xdp_tx_cq, - budget); + budget) < budget; xdp_tx_cq->xdp_busy = !clean_complete; } } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 4d5ca302c067..9dff7b086c9f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -43,6 +43,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/moduleparam.h> +#include <linux/indirect_call_wrapper.h> #include "mlx4_en.h" @@ -261,6 +262,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv, } } +INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u64 timestamp, + int napi_mode)); u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, @@ -329,6 +334,11 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, return tx_info->nr_txbb; } +INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, + int index, u64 timestamp, + int napi_mode)); + u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, int index, u64 timestamp, @@ -382,8 +392,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) return cnt; } -bool mlx4_en_process_tx_cq(struct net_device *dev, - struct mlx4_en_cq *cq, int napi_budget) +int mlx4_en_process_tx_cq(struct net_device *dev, + struct mlx4_en_cq *cq, int napi_budget) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_cq *mcq = &cq->mcq; @@ -405,7 +415,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, u32 ring_cons; if (unlikely(!priv->port_up)) - return true; + return 0; netdev_txq_bql_complete_prefetchw(ring->tx_queue); @@ -449,7 +459,9 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, timestamp = mlx4_en_get_cqe_ts(cqe); /* free next descriptor */ - last_nr_txbb = ring->free_tx_desc( + last_nr_txbb = INDIRECT_CALL_2(ring->free_tx_desc, + mlx4_en_free_tx_desc, + mlx4_en_recycle_tx_desc, priv, ring, ring_index, timestamp, napi_budget); @@ -480,7 +492,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, WRITE_ONCE(ring->cons, ring_cons + txbbs_skipped); if (cq->type == TX_XDP) - return done < budget; + return done; netdev_tx_completed_queue(ring->tx_queue, packets, bytes); @@ -492,7 +504,7 @@ bool mlx4_en_process_tx_cq(struct net_device *dev, ring->wake_queue++; } - return done < budget; + return done; } void mlx4_en_tx_irq(struct mlx4_cq *mcq) @@ -512,14 +524,14 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget) struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi); struct net_device *dev = cq->dev; struct mlx4_en_priv *priv = netdev_priv(dev); - bool clean_complete; + int work_done; - clean_complete = mlx4_en_process_tx_cq(dev, cq, budget); - if (!clean_complete) + work_done = mlx4_en_process_tx_cq(dev, cq, budget); + if (work_done >= budget) return budget; - napi_complete(napi); - mlx4_en_arm_cq(priv, cq); + if (napi_complete_done(napi, work_done)) + mlx4_en_arm_cq(priv, cq); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 630f15977f09..9f5603612960 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -737,8 +737,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, int budget); int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget); int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget); -bool mlx4_en_process_tx_cq(struct net_device *dev, - struct mlx4_en_cq *cq, int napi_budget); +int mlx4_en_process_tx_cq(struct net_device *dev, + struct mlx4_en_cq *cq, int napi_budget); u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, int index, u64 timestamp, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 312e0a1ad43d..7d69a3061f17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -7,10 +7,10 @@ config MLX5_CORE tristate "Mellanox 5th generation network adapters (ConnectX series) core driver" depends on PCI select NET_DEVLINK - imply PTP_1588_CLOCK - imply VXLAN - imply MLXFW - imply PCI_HYPERV_INTERFACE + depends on VXLAN || !VXLAN + depends on MLXFW || !MLXFW + depends on PTP_1588_CLOCK || !PTP_1588_CLOCK + depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE default n ---help--- Core driver for low level functionality of the ConnectX-4 and diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c index eddc34e4a762..8a4985d8cbfe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c @@ -58,12 +58,21 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters, void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev, struct mlx5_accel_esp_xfrm *xfrm, - const __be32 saddr[4], - const __be32 daddr[4], - const __be32 spi, bool is_ipv6) + u32 *sa_handle) { - return mlx5_fpga_ipsec_create_sa_ctx(mdev, xfrm, saddr, daddr, - spi, is_ipv6); + __be32 saddr[4] = {}, daddr[4] = {}; + + if (!xfrm->attrs.is_ipv6) { + saddr[3] = xfrm->attrs.saddr.a4; + daddr[3] = xfrm->attrs.daddr.a4; + } else { + memcpy(saddr, xfrm->attrs.saddr.a6, sizeof(saddr)); + memcpy(daddr, xfrm->attrs.daddr.a6, sizeof(daddr)); + } + + return mlx5_fpga_ipsec_create_sa_ctx(mdev, xfrm, saddr, + daddr, xfrm->attrs.spi, + xfrm->attrs.is_ipv6, sa_handle); } void mlx5_accel_esp_free_hw_context(void *context) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h index 530e428d46ab..e89747674712 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h @@ -48,9 +48,7 @@ int mlx5_accel_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters, void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev, struct mlx5_accel_esp_xfrm *xfrm, - const __be32 saddr[4], - const __be32 daddr[4], - const __be32 spi, bool is_ipv6); + u32 *sa_handle); void mlx5_accel_esp_free_hw_context(void *context); int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev); @@ -64,9 +62,7 @@ void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev); static inline void * mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev, struct mlx5_accel_esp_xfrm *xfrm, - const __be32 saddr[4], - const __be32 daddr[4], - const __be32 spi, bool is_ipv6) + u32 *sa_handle) { return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index bdeb291f6b67..e94f0c4d74a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -23,7 +23,10 @@ static int mlx5_devlink_flash_update(struct devlink *devlink, if (err) return err; - return mlx5_firmware_flash(dev, fw, extack); + err = mlx5_firmware_flash(dev, fw, extack); + release_firmware(fw); + + return err; } static u8 mlx5_fw_ver_major(u32 version) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index c9c9b479bda5..a7551274be58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -684,7 +684,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work) get_block_timestamp(tracer, &tmp_trace_block[TRACES_PER_BLOCK - 1]); while (block_timestamp > tracer->last_timestamp) { - /* Check block override if its not the first block */ + /* Check block override if it's not the first block */ if (!tracer->last_timestamp) { u64 *ts_event; /* To avoid block override be the HW in case of buffer @@ -935,7 +935,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) return NULL; } - tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); + tracer = kvzalloc(sizeof(*tracer), GFP_KERNEL); if (!tracer) return ERR_PTR(-ENOMEM); @@ -982,7 +982,7 @@ destroy_workqueue: tracer->dev = NULL; destroy_workqueue(tracer->work_queue); free_tracer: - kfree(tracer); + kvfree(tracer); return ERR_PTR(err); } @@ -1061,7 +1061,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_destroy_log_buf(tracer); flush_workqueue(tracer->work_queue); destroy_workqueue(tracer->work_queue); - kfree(tracer); + kvfree(tracer); } static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 12a61bf82c14..23701c0e36ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -367,6 +367,7 @@ enum { MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, + MLX5E_SQ_STATE_PENDING_XSK_TX, }; struct mlx5e_sq_wqe_info { @@ -960,7 +961,7 @@ void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); -void mlx5e_poll_ico_cq(struct mlx5e_cq *cq); +int mlx5e_poll_ico_cq(struct mlx5e_cq *cq); bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq); void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix); void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix); 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 ad3e3a65d403..a172c5e39710 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -12,6 +12,7 @@ #include <net/flow_offload.h> #include <net/netfilter/nf_flow_table.h> #include <linux/workqueue.h> +#include <linux/xarray.h> #include "esw/chains.h" #include "en/tc_ct.h" @@ -35,7 +36,7 @@ struct mlx5_tc_ct_priv { struct mlx5_eswitch *esw; const struct net_device *netdev; struct idr fte_ids; - struct idr tuple_ids; + struct xarray tuple_ids; struct rhashtable zone_ht; struct mlx5_flow_table *ct; struct mlx5_flow_table *ct_nat; @@ -67,11 +68,9 @@ struct mlx5_ct_ft { struct nf_flowtable *nf_ft; struct mlx5_tc_ct_priv *ct_priv; struct rhashtable ct_entries_ht; - struct list_head ct_entries_list; }; struct mlx5_ct_entry { - struct list_head list; u16 zone; struct rhash_head node; struct flow_rule *flow_rule; @@ -240,7 +239,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv, mlx5_eswitch_del_offloaded_rule(esw, zone_rule->rule, attr); mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr); - idr_remove(&ct_priv->tuple_ids, zone_rule->tupleid); + xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid); } static void @@ -485,7 +484,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_esw_flow_attr *attr = &zone_rule->attr; struct mlx5_eswitch *esw = ct_priv->esw; struct mlx5_flow_spec *spec = NULL; - u32 tupleid = 1; + u32 tupleid; int err; zone_rule->nat = nat; @@ -495,12 +494,12 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, return -ENOMEM; /* Get tuple unique id */ - err = idr_alloc_u32(&ct_priv->tuple_ids, zone_rule, &tupleid, - TUPLE_ID_MAX, GFP_KERNEL); + err = xa_alloc(&ct_priv->tuple_ids, &tupleid, zone_rule, + XA_LIMIT(1, TUPLE_ID_MAX), GFP_KERNEL); if (err) { netdev_warn(ct_priv->netdev, "Failed to allocate tuple id, err: %d\n", err); - goto err_idr_alloc; + goto err_xa_alloc; } zone_rule->tupleid = tupleid; @@ -541,8 +540,8 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr); err_mod_hdr: - idr_remove(&ct_priv->tuple_ids, zone_rule->tupleid); -err_idr_alloc: + xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid); +err_xa_alloc: kfree(spec); return err; } @@ -617,8 +616,6 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, if (err) goto err_insert; - list_add(&entry->list, &ft->ct_entries_list); - return 0; err_insert: @@ -646,7 +643,6 @@ mlx5_tc_ct_block_flow_offload_del(struct mlx5_ct_ft *ft, WARN_ON(rhashtable_remove_fast(&ft->ct_entries_ht, &entry->node, cts_ht_params)); - list_del(&entry->list); kfree(entry); return 0; @@ -818,7 +814,6 @@ mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone, ft->zone = zone; ft->nf_ft = nf_ft; ft->ct_priv = ct_priv; - INIT_LIST_HEAD(&ft->ct_entries_list); refcount_set(&ft->refcount, 1); err = rhashtable_init(&ft->ct_entries_ht, &cts_ht_params); @@ -847,12 +842,12 @@ err_init: } static void -mlx5_tc_ct_flush_ft(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) +mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg) { - struct mlx5_ct_entry *entry; + struct mlx5_tc_ct_priv *ct_priv = arg; + struct mlx5_ct_entry *entry = ptr; - list_for_each_entry(entry, &ft->ct_entries_list, list) - mlx5_tc_ct_entry_del_rules(ft->ct_priv, entry); + mlx5_tc_ct_entry_del_rules(ct_priv, entry); } static void @@ -863,9 +858,10 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) nf_flow_table_offload_del_cb(ft->nf_ft, mlx5_tc_ct_block_flow_offload, ft); - mlx5_tc_ct_flush_ft(ct_priv, ft); rhashtable_remove_fast(&ct_priv->zone_ht, &ft->node, zone_params); - rhashtable_destroy(&ft->ct_entries_ht); + rhashtable_free_and_destroy(&ft->ct_entries_ht, + mlx5_tc_ct_flush_ft_entry, + ct_priv); kfree(ft); } @@ -1304,7 +1300,7 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv) } idr_init(&ct_priv->fte_ids); - idr_init(&ct_priv->tuple_ids); + xa_init_flags(&ct_priv->tuple_ids, XA_FLAGS_ALLOC1); mutex_init(&ct_priv->control_lock); rhashtable_init(&ct_priv->zone_ht, &zone_params); @@ -1339,7 +1335,7 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) rhashtable_destroy(&ct_priv->zone_ht); mutex_destroy(&ct_priv->control_lock); - idr_destroy(&ct_priv->tuple_ids); + xa_destroy(&ct_priv->tuple_ids); idr_destroy(&ct_priv->fte_ids); kfree(ct_priv); @@ -1357,7 +1353,7 @@ mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv, if (!ct_priv || !tupleid) return true; - zone_rule = idr_find(&ct_priv->tuple_ids, tupleid); + zone_rule = xa_load(&ct_priv->tuple_ids, tupleid); if (!zone_rule) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index f07b1399744e..9f6967d76053 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -102,7 +102,7 @@ static inline void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map, struct mlx5_wqe_ctrl_seg *ctrl) { - ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; + ctrl->fm_ce_se |= MLX5_WQE_CTRL_CQ_UPDATE; /* ensure wqe is visible to device before updating doorbell record */ dma_wmb(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index fe2d596cb361..3bcdb5b2fc20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -33,6 +33,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &c->xskicosq.state))) return 0; + if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->xskicosq.state)) + return 0; + spin_lock(&c->xskicosq_lock); mlx5e_trigger_irq(&c->xskicosq); spin_unlock(&c->xskicosq_lock); 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 3022463f2284..a6f65d4b2f36 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 @@ -42,6 +42,8 @@ #include "en/txrx.h" #if IS_ENABLED(CONFIG_GENEVE) +#include <net/geneve.h> + static inline bool mlx5_geneve_tx_allowed(struct mlx5_core_dev *mdev) { return mlx5_tx_swp_supported(mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 29626c6c9c25..92eb3bad4acd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -75,18 +75,23 @@ struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *ipsec, return ret; } -static int mlx5e_ipsec_sadb_rx_add(struct mlx5e_ipsec_sa_entry *sa_entry) +static int mlx5e_ipsec_sadb_rx_add(struct mlx5e_ipsec_sa_entry *sa_entry, + unsigned int handle) { struct mlx5e_ipsec *ipsec = sa_entry->ipsec; + struct mlx5e_ipsec_sa_entry *_sa_entry; unsigned long flags; - int ret; - ret = ida_simple_get(&ipsec->halloc, 1, 0, GFP_KERNEL); - if (ret < 0) - return ret; + rcu_read_lock(); + hash_for_each_possible_rcu(ipsec->sadb_rx, _sa_entry, hlist, handle) + if (_sa_entry->handle == handle) { + rcu_read_unlock(); + return -EEXIST; + } + rcu_read_unlock(); spin_lock_irqsave(&ipsec->sadb_rx_lock, flags); - sa_entry->handle = ret; + sa_entry->handle = handle; hash_add_rcu(ipsec->sadb_rx, &sa_entry->hlist, sa_entry->handle); spin_unlock_irqrestore(&ipsec->sadb_rx_lock, flags); @@ -103,15 +108,6 @@ static void mlx5e_ipsec_sadb_rx_del(struct mlx5e_ipsec_sa_entry *sa_entry) spin_unlock_irqrestore(&ipsec->sadb_rx_lock, flags); } -static void mlx5e_ipsec_sadb_rx_free(struct mlx5e_ipsec_sa_entry *sa_entry) -{ - struct mlx5e_ipsec *ipsec = sa_entry->ipsec; - - /* xfrm already doing sync rcu between del and free callbacks */ - - ida_simple_remove(&ipsec->halloc, sa_entry->handle); -} - static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) { struct xfrm_replay_state_esn *replay_esn; @@ -199,6 +195,14 @@ mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->flags |= (x->props.mode == XFRM_MODE_TRANSPORT) ? MLX5_ACCEL_ESP_FLAGS_TRANSPORT : MLX5_ACCEL_ESP_FLAGS_TUNNEL; + + /* spi */ + attrs->spi = x->id.spi; + + /* source , destination ips */ + memcpy(&attrs->saddr, x->props.saddr.a6, sizeof(attrs->saddr)); + memcpy(&attrs->daddr, x->id.daddr.a6, sizeof(attrs->daddr)); + attrs->is_ipv6 = (x->props.family != AF_INET); } static inline int mlx5e_xfrm_validate_state(struct xfrm_state *x) @@ -284,8 +288,7 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) struct net_device *netdev = x->xso.dev; struct mlx5_accel_esp_xfrm_attrs attrs; struct mlx5e_priv *priv; - __be32 saddr[4] = {0}, daddr[4] = {0}, spi; - bool is_ipv6 = false; + unsigned int sa_handle; int err; priv = netdev_priv(netdev); @@ -303,20 +306,6 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) sa_entry->x = x; sa_entry->ipsec = priv->ipsec; - /* Add the SA to handle processed incoming packets before the add SA - * completion was received - */ - if (x->xso.flags & XFRM_OFFLOAD_INBOUND) { - err = mlx5e_ipsec_sadb_rx_add(sa_entry); - if (err) { - netdev_info(netdev, "Failed adding to SADB_RX: %d\n", err); - goto err_entry; - } - } else { - sa_entry->set_iv_op = (x->props.flags & XFRM_STATE_ESN) ? - mlx5e_ipsec_set_iv_esn : mlx5e_ipsec_set_iv; - } - /* check esn */ mlx5e_ipsec_update_esn_state(sa_entry); @@ -327,41 +316,38 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x) MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA); if (IS_ERR(sa_entry->xfrm)) { err = PTR_ERR(sa_entry->xfrm); - goto err_sadb_rx; + goto err_sa_entry; } /* create hw context */ - if (x->props.family == AF_INET) { - saddr[3] = x->props.saddr.a4; - daddr[3] = x->id.daddr.a4; - } else { - memcpy(saddr, x->props.saddr.a6, sizeof(saddr)); - memcpy(daddr, x->id.daddr.a6, sizeof(daddr)); - is_ipv6 = true; - } - spi = x->id.spi; sa_entry->hw_context = mlx5_accel_esp_create_hw_context(priv->mdev, sa_entry->xfrm, - saddr, daddr, spi, - is_ipv6); + &sa_handle); if (IS_ERR(sa_entry->hw_context)) { err = PTR_ERR(sa_entry->hw_context); goto err_xfrm; } + if (x->xso.flags & XFRM_OFFLOAD_INBOUND) { + err = mlx5e_ipsec_sadb_rx_add(sa_entry, sa_handle); + if (err) + goto err_hw_ctx; + } else { + sa_entry->set_iv_op = (x->props.flags & XFRM_STATE_ESN) ? + mlx5e_ipsec_set_iv_esn : mlx5e_ipsec_set_iv; + } + x->xso.offload_handle = (unsigned long)sa_entry; goto out; +err_hw_ctx: + mlx5_accel_esp_free_hw_context(sa_entry->hw_context); err_xfrm: mlx5_accel_esp_destroy_xfrm(sa_entry->xfrm); -err_sadb_rx: - if (x->xso.flags & XFRM_OFFLOAD_INBOUND) { - mlx5e_ipsec_sadb_rx_del(sa_entry); - mlx5e_ipsec_sadb_rx_free(sa_entry); - } -err_entry: +err_sa_entry: kfree(sa_entry); + out: return err; } @@ -390,9 +376,6 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x) mlx5_accel_esp_destroy_xfrm(sa_entry->xfrm); } - if (x->xso.flags & XFRM_OFFLOAD_INBOUND) - mlx5e_ipsec_sadb_rx_free(sa_entry); - kfree(sa_entry); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 93bf10e6508c..c85151a1e008 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -109,11 +109,6 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv); void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv); void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv); -int mlx5e_ipsec_get_count(struct mlx5e_priv *priv); -int mlx5e_ipsec_get_strings(struct mlx5e_priv *priv, uint8_t *data); -void mlx5e_ipsec_update_stats(struct mlx5e_priv *priv); -int mlx5e_ipsec_get_stats(struct mlx5e_priv *priv, u64 *data); - struct xfrm_state *mlx5e_ipsec_sadb_rx_lookup(struct mlx5e_ipsec *dev, unsigned int handle); @@ -136,26 +131,6 @@ static inline void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) { } -static inline int mlx5e_ipsec_get_count(struct mlx5e_priv *priv) -{ - return 0; -} - -static inline int mlx5e_ipsec_get_strings(struct mlx5e_priv *priv, - uint8_t *data) -{ - return 0; -} - -static inline void mlx5e_ipsec_update_stats(struct mlx5e_priv *priv) -{ -} - -static inline int mlx5e_ipsec_get_stats(struct mlx5e_priv *priv, u64 *data) -{ - return 0; -} - #endif #endif /* __MLX5E_IPSEC_H__ */ 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 6fea59223dc4..6c5c54bcd9be 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 @@ -38,6 +38,7 @@ #include "accel/ipsec.h" #include "fpga/sdk.h" #include "en_accel/ipsec.h" +#include "fpga/ipsec.h" static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_ipsec_stats, ipsec_dec_in_packets) }, @@ -73,61 +74,74 @@ static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = { #define NUM_IPSEC_HW_COUNTERS ARRAY_SIZE(mlx5e_ipsec_hw_stats_desc) #define NUM_IPSEC_SW_COUNTERS ARRAY_SIZE(mlx5e_ipsec_sw_stats_desc) -#define NUM_IPSEC_COUNTERS (NUM_IPSEC_HW_COUNTERS + NUM_IPSEC_SW_COUNTERS) - -int mlx5e_ipsec_get_count(struct mlx5e_priv *priv) +static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_sw) { - if (!priv->ipsec) - return 0; - - return NUM_IPSEC_COUNTERS; + return NUM_IPSEC_SW_COUNTERS; } -int mlx5e_ipsec_get_strings(struct mlx5e_priv *priv, uint8_t *data) -{ - unsigned int i, idx = 0; +static inline MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_sw) {} - if (!priv->ipsec) - return 0; +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_sw) +{ + unsigned int i; - for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, - mlx5e_ipsec_hw_stats_desc[i].format); + if (priv->ipsec) + for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + mlx5e_ipsec_sw_stats_desc[i].format); + return idx; +} - for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, - mlx5e_ipsec_sw_stats_desc[i].format); +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_sw) +{ + int i; - return NUM_IPSEC_COUNTERS; + if (priv->ipsec) + for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++) + data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->sw_stats, + mlx5e_ipsec_sw_stats_desc, i); + return idx; } -void mlx5e_ipsec_update_stats(struct mlx5e_priv *priv) +static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec_hw) { - int ret; + return (mlx5_fpga_ipsec_device_caps(priv->mdev)) ? NUM_IPSEC_HW_COUNTERS : 0; +} - if (!priv->ipsec) - return; +static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec_hw) +{ + int ret = 0; - ret = mlx5_accel_ipsec_counters_read(priv->mdev, (u64 *)&priv->ipsec->stats, - NUM_IPSEC_HW_COUNTERS); + if (priv->ipsec) + ret = mlx5_accel_ipsec_counters_read(priv->mdev, (u64 *)&priv->ipsec->stats, + NUM_IPSEC_HW_COUNTERS); if (ret) memset(&priv->ipsec->stats, 0, sizeof(priv->ipsec->stats)); } -int mlx5e_ipsec_get_stats(struct mlx5e_priv *priv, u64 *data) +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec_hw) { - int i, idx = 0; - - if (!priv->ipsec) - return 0; + unsigned int i; - for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++) - data[idx++] = MLX5E_READ_CTR64_CPU(&priv->ipsec->stats, - mlx5e_ipsec_hw_stats_desc, i); + if (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev)) + for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + mlx5e_ipsec_hw_stats_desc[i].format); - for (i = 0; i < NUM_IPSEC_SW_COUNTERS; i++) - data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->ipsec->sw_stats, - mlx5e_ipsec_sw_stats_desc, i); + return idx; +} - return NUM_IPSEC_COUNTERS; +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec_hw) +{ + int i; + + if (priv->ipsec && mlx5_fpga_ipsec_device_caps(priv->mdev)) + for (i = 0; i < NUM_IPSEC_HW_COUNTERS; i++) + data[idx++] = MLX5E_READ_CTR64_CPU(&priv->ipsec->stats, + mlx5e_ipsec_hw_stats_desc, + i); + return idx; } + +MLX5E_DEFINE_STATS_GRP(ipsec_sw, 0); +MLX5E_DEFINE_STATS_GRP(ipsec_hw, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 6d703ddee4e2..4ab78b5c2393 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -432,7 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { *cur_params = new_channels.params; - mlx5e_num_channels_changed(priv); + err = mlx5e_num_channels_changed(priv); 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 dd7f338425eb..47396f1b02f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2839,11 +2839,8 @@ void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv) ETH_MAX_MTU); } -static void mlx5e_netdev_set_tcs(struct net_device *netdev) +static void mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc) { - struct mlx5e_priv *priv = netdev_priv(netdev); - int nch = priv->channels.params.num_channels; - int ntc = priv->channels.params.num_tc; int tc; netdev_reset_tc(netdev); @@ -2860,15 +2857,47 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) netdev_set_tc_queue(netdev, tc, nch, 0); } -static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv, u16 count) +static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) { - int num_txqs = count * priv->channels.params.num_tc; - int num_rxqs = count * priv->profile->rq_groups; struct net_device *netdev = priv->netdev; + int num_txqs, num_rxqs, nch, ntc; + int old_num_txqs, old_ntc; + int err; + + old_num_txqs = netdev->real_num_tx_queues; + old_ntc = netdev->num_tc; + + nch = priv->channels.params.num_channels; + ntc = priv->channels.params.num_tc; + num_txqs = nch * ntc; + num_rxqs = nch * priv->profile->rq_groups; + + mlx5e_netdev_set_tcs(netdev, nch, ntc); + + err = netif_set_real_num_tx_queues(netdev, num_txqs); + if (err) { + netdev_warn(netdev, "netif_set_real_num_tx_queues failed, %d\n", err); + goto err_tcs; + } + err = netif_set_real_num_rx_queues(netdev, num_rxqs); + if (err) { + netdev_warn(netdev, "netif_set_real_num_rx_queues failed, %d\n", err); + goto err_txqs; + } + + return 0; - mlx5e_netdev_set_tcs(netdev); - netif_set_real_num_tx_queues(netdev, num_txqs); - netif_set_real_num_rx_queues(netdev, num_rxqs); +err_txqs: + /* netif_set_real_num_rx_queues could fail only when nch increased. Only + * one of nch and ntc is changed in this function. That means, the call + * to netif_set_real_num_tx_queues below should not fail, because it + * decreases the number of TX queues. + */ + WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs)); + +err_tcs: + mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc); + return err; } static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, @@ -2895,8 +2924,12 @@ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, int mlx5e_num_channels_changed(struct mlx5e_priv *priv) { u16 count = priv->channels.params.num_channels; + int err; + + err = mlx5e_update_netdev_queues(priv); + if (err) + return err; - mlx5e_update_netdev_queues(priv, count); mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params); if (!netif_is_rxfh_configured(priv->netdev)) @@ -3583,7 +3616,12 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; - if (!mlx5e_monitor_counter_supported(priv)) { + /* In switchdev mode, monitor counters doesn't monitor + * rx/tx stats of 802_3. The update stats mechanism + * should keep the 802_3 layout counters updated + */ + if (!mlx5e_monitor_counter_supported(priv) || + mlx5e_is_uplink_rep(priv)) { /* update HW stats in background for next time */ mlx5e_queue_update_stats(priv); } @@ -5358,9 +5396,11 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) */ if (take_rtnl) rtnl_lock(); - mlx5e_num_channels_changed(priv); + err = mlx5e_num_channels_changed(priv); if (take_rtnl) rtnl_unlock(); + if (err) + goto out; err = profile->init_tx(priv); if (err) @@ -5526,8 +5566,8 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_delete_app(priv); #endif - mlx5e_devlink_port_unregister(priv); unregister_netdev(priv->netdev); + mlx5e_devlink_port_unregister(priv); mlx5e_detach(mdev, vpriv); mlx5e_destroy_netdev(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 2a0243e4af75..55457f268495 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -2050,29 +2050,30 @@ static int register_devlink_port(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep = rpriv->rep; struct netdev_phys_item_id ppid = {}; unsigned int dl_port_index = 0; + u16 pfnum; if (!is_devlink_port_supported(dev, rpriv)) return 0; mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); + pfnum = PCI_FUNC(dev->pdev->devfn); if (rep->vport == MLX5_VPORT_UPLINK) { devlink_port_attrs_set(&rpriv->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - PCI_FUNC(dev->pdev->devfn), false, 0, + pfnum, false, 0, &ppid.id[0], ppid.id_len); dl_port_index = vport_to_devlink_port_index(dev, rep->vport); } else if (rep->vport == MLX5_VPORT_PF) { devlink_port_attrs_pci_pf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, - dev->pdev->devfn); + pfnum); dl_port_index = rep->vport; } else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) { devlink_port_attrs_pci_vf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, - dev->pdev->devfn, - rep->vport - 1); + pfnum, rep->vport - 1); dl_port_index = vport_to_devlink_port_index(dev, rep->vport); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 6173faf542b0..e2beb89c1832 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -589,7 +589,7 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) return !!err; } -void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) +int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) { struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); struct mlx5_cqe64 *cqe; @@ -597,11 +597,11 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) int i; if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return; + return 0; cqe = mlx5_cqwq_get_cqe(&cq->wq); if (likely(!cqe)) - return; + return 0; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), * otherwise a cq overrun may occur @@ -650,6 +650,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) sq->cc = sqcc; mlx5_cqwq_update_db_record(&cq->wq); + + return i; } bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 30b216d9284c..6eb0e8236bbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -32,8 +32,8 @@ #include "lib/mlx5.h" #include "en.h" -#include "en_accel/ipsec.h" #include "en_accel/tls.h" +#include "en_accel/en_accel.h" static unsigned int stats_grps_num(struct mlx5e_priv *priv) { @@ -1424,27 +1424,6 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pme) static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pme) { return; } -static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(ipsec) -{ - return mlx5e_ipsec_get_count(priv); -} - -static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ipsec) -{ - return idx + mlx5e_ipsec_get_strings(priv, - data + idx * ETH_GSTRING_LEN); -} - -static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(ipsec) -{ - return idx + mlx5e_ipsec_get_stats(priv, data + idx); -} - -static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ipsec) -{ - mlx5e_ipsec_update_stats(priv); -} - static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(tls) { return mlx5e_tls_get_count(priv); @@ -1714,7 +1693,6 @@ MLX5E_DEFINE_STATS_GRP(pme, 0); MLX5E_DEFINE_STATS_GRP(channels, 0); MLX5E_DEFINE_STATS_GRP(per_port_buff_congest, 0); MLX5E_DEFINE_STATS_GRP(eth_ext, 0); -static MLX5E_DEFINE_STATS_GRP(ipsec, 0); static MLX5E_DEFINE_STATS_GRP(tls, 0); /* The stats groups order is opposite to the update_stats() order calls */ @@ -1731,7 +1709,10 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = { &MLX5E_STATS_GRP(pcie), &MLX5E_STATS_GRP(per_prio), &MLX5E_STATS_GRP(pme), - &MLX5E_STATS_GRP(ipsec), +#ifdef CONFIG_MLX5_EN_IPSEC + &MLX5E_STATS_GRP(ipsec_sw), + &MLX5E_STATS_GRP(ipsec_hw), +#endif &MLX5E_STATS_GRP(tls), &MLX5E_STATS_GRP(channels), &MLX5E_STATS_GRP(per_port_buff_congest), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 092b39ffa32a..2b83ba990714 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -390,5 +390,7 @@ extern MLX5E_DECLARE_STATS_GRP(per_prio); extern MLX5E_DECLARE_STATS_GRP(pme); extern MLX5E_DECLARE_STATS_GRP(channels); extern MLX5E_DECLARE_STATS_GRP(per_port_buff_congest); +extern MLX5E_DECLARE_STATS_GRP(ipsec_hw); +extern MLX5E_DECLARE_STATS_GRP(ipsec_sw); #endif /* __MLX5_EN_STATS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 438128dde187..7d2b05576f44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -171,6 +171,11 @@ struct tunnel_match_key { int filter_ifindex; }; +struct tunnel_match_enc_opts { + struct flow_dissector_key_enc_opts key; + struct flow_dissector_key_enc_opts mask; +}; + /* Tunnel_id mapping is TUNNEL_INFO_BITS + ENC_OPTS_BITS. * Upper TUNNEL_INFO_BITS for general tunnel info. * Lower ENC_OPTS_BITS bits for enc_opts. @@ -1343,7 +1348,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (err) return err; - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + !(attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR)) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); if (err) @@ -1823,9 +1829,7 @@ enc_opts_is_dont_care_or_full_match(struct mlx5e_priv *priv, *dont_care = false; if (opt->opt_class != U16_MAX || - opt->type != U8_MAX || - memchr_inv(opt->opt_data, 0xFF, - opt->length * 4)) { + opt->type != U8_MAX) { NL_SET_ERR_MSG(extack, "Partial match of tunnel options in chain > 0 isn't supported"); netdev_warn(priv->netdev, @@ -1862,6 +1866,7 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts; struct flow_match_enc_opts enc_opts_match; + struct tunnel_match_enc_opts tun_enc_opts; struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; struct tunnel_match_key tunnel_key; @@ -1904,8 +1909,14 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv, goto err_enc_opts; if (!enc_opts_is_dont_care) { + memset(&tun_enc_opts, 0, sizeof(tun_enc_opts)); + memcpy(&tun_enc_opts.key, enc_opts_match.key, + sizeof(*enc_opts_match.key)); + memcpy(&tun_enc_opts.mask, enc_opts_match.mask, + sizeof(*enc_opts_match.mask)); + err = mapping_add(uplink_priv->tunnel_enc_opts_mapping, - enc_opts_match.key, &enc_opts_id); + &tun_enc_opts, &enc_opts_id); if (err) goto err_enc_opts; } @@ -3558,12 +3569,13 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr, u32 *action) { - int nest_level = attr->parse_attr->filter_dev->lower_level; struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, }; - int err = 0; + int nest_level, err = 0; + nest_level = attr->parse_attr->filter_dev->lower_level - + priv->netdev->lower_level; while (nest_level--) { err = parse_tc_vlan_action(priv, &vlan_act, attr, action); if (err) @@ -4705,7 +4717,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) int mlx5e_tc_esw_init(struct rhashtable *tc_ht) { - const size_t sz_enc_opts = sizeof(struct flow_dissector_key_enc_opts); + const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts); struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *priv; struct mapping_ctx *mapping; @@ -4800,7 +4812,7 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, u32 tunnel_id) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct flow_dissector_key_enc_opts enc_opts = {}; + struct tunnel_match_enc_opts enc_opts = {}; struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; struct metadata_dst *tun_dst; @@ -4838,7 +4850,7 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, } } - tun_dst = tun_rx_dst(enc_opts.len); + tun_dst = tun_rx_dst(enc_opts.key.len); if (!tun_dst) { WARN_ON_ONCE(true); return false; @@ -4852,9 +4864,11 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, key32_to_tunnel_id(key.enc_key_id.keyid), TUNNEL_KEY); - if (enc_opts.len) - ip_tunnel_info_opts_set(&tun_dst->u.tun_info, enc_opts.data, - enc_opts.len, enc_opts.dst_opt_type); + if (enc_opts.key.len) + ip_tunnel_info_opts_set(&tun_dst->u.tun_info, + enc_opts.key.data, + enc_opts.key.len, + enc_opts.key.dst_opt_type); skb_dst_set(skb, (struct dst_entry *)tun_dst); dev = dev_get_by_index(&init_net, key.filter_ifindex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 87c49e7a164c..acb20215a33b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -152,7 +152,11 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_post_rx_wqes, rq); if (xsk_open) { - mlx5e_poll_ico_cq(&c->xskicosq.cq); + if (mlx5e_poll_ico_cq(&c->xskicosq.cq)) + /* Don't clear the flag if nothing was polled to prevent + * queueing more WQEs and overflowing XSKICOSQ. + */ + clear_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->xskicosq.state); busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); busy_xsk |= mlx5e_napi_xsk_post(xsksq, xskrq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 39f42f985fbd..c1848b57f61c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -403,7 +403,6 @@ enum { MLX5_ESW_ATTR_FLAG_VLAN_HANDLED = BIT(0), MLX5_ESW_ATTR_FLAG_SLOW_PATH = BIT(1), MLX5_ESW_ATTR_FLAG_NO_IN_PORT = BIT(2), - MLX5_ESW_ATTR_FLAG_HAIRPIN = BIT(3), }; struct mlx5_esw_flow_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f171eb2234b0..b2e38e0cde97 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -300,7 +300,6 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, bool split = !!(attr->split_count); struct mlx5_flow_handle *rule; struct mlx5_flow_table *fdb; - bool hairpin = false; int j, i = 0; if (esw->mode != MLX5_ESWITCH_OFFLOADS) @@ -398,21 +397,16 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, goto err_esw_get; } - if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) { + if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr, &flow_act, dest, i); - hairpin = true; - } else { + else rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i); - } if (IS_ERR(rule)) goto err_add_rule; else atomic64_inc(&esw->offloads.num_flows); - if (hairpin) - attr->flags |= MLX5_ESW_ATTR_FLAG_HAIRPIN; - return rule; err_add_rule: @@ -501,7 +495,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, mlx5_del_flow_rules(rule); - if (attr->flags & MLX5_ESW_ATTR_FLAG_HAIRPIN) { + if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) { /* unref the term table */ for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) { if (attr->dests[i].termtbl) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index b794888fa3ba..0604216eb94f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -65,6 +65,7 @@ struct mlx5_fpga_esp_xfrm; struct mlx5_fpga_ipsec_sa_ctx { struct rhash_head hash; struct mlx5_ifc_fpga_ipsec_sa hw_sa; + u32 sa_handle; struct mlx5_core_dev *dev; struct mlx5_fpga_esp_xfrm *fpga_xfrm; }; @@ -119,6 +120,8 @@ struct mlx5_fpga_ipsec { */ struct rb_root rules_rb; struct mutex rules_rb_lock; /* rules lock */ + + struct ida halloc; }; static bool mlx5_fpga_is_ipsec_device(struct mlx5_core_dev *mdev) @@ -602,7 +605,7 @@ static bool mlx5_is_fpga_ipsec_rule(struct mlx5_core_dev *dev, const u32 *match_c, const u32 *match_v) { - u32 ipsec_dev_caps = mlx5_accel_ipsec_device_caps(dev); + u32 ipsec_dev_caps = mlx5_fpga_ipsec_device_caps(dev); bool ipv6_flow; ipv6_flow = mlx5_fs_is_outer_ipv6_flow(dev, match_c, match_v); @@ -666,7 +669,8 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev, struct mlx5_accel_esp_xfrm *accel_xfrm, const __be32 saddr[4], const __be32 daddr[4], - const __be32 spi, bool is_ipv6) + const __be32 spi, bool is_ipv6, + u32 *sa_handle) { struct mlx5_fpga_ipsec_sa_ctx *sa_ctx; struct mlx5_fpga_esp_xfrm *fpga_xfrm = @@ -704,6 +708,17 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev, goto exists; } + if (accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT) { + err = ida_simple_get(&fipsec->halloc, 1, 0, GFP_KERNEL); + if (err < 0) { + context = ERR_PTR(err); + goto exists; + } + + sa_ctx->sa_handle = err; + if (sa_handle) + *sa_handle = sa_ctx->sa_handle; + } /* This is unbounded fpga_xfrm, try to add to hash */ mutex_lock(&fipsec->sa_hash_lock); @@ -744,7 +759,8 @@ delete_hash: rhash_sa)); unlock_hash: mutex_unlock(&fipsec->sa_hash_lock); - + if (accel_xfrm->attrs.action & MLX5_ACCEL_ESP_ACTION_DECRYPT) + ida_simple_remove(&fipsec->halloc, sa_ctx->sa_handle); exists: mutex_unlock(&fpga_xfrm->lock); kfree(sa_ctx); @@ -816,7 +832,7 @@ mlx5_fpga_ipsec_fs_create_sa_ctx(struct mlx5_core_dev *mdev, /* create */ return mlx5_fpga_ipsec_create_sa_ctx(mdev, accel_xfrm, saddr, daddr, - spi, is_ipv6); + spi, is_ipv6, NULL); } static void @@ -836,6 +852,10 @@ mlx5_fpga_ipsec_release_sa_ctx(struct mlx5_fpga_ipsec_sa_ctx *sa_ctx) return; } + if (sa_ctx->fpga_xfrm->accel_xfrm.attrs.action & + MLX5_ACCEL_ESP_ACTION_DECRYPT) + ida_simple_remove(&fipsec->halloc, sa_ctx->sa_handle); + mutex_lock(&fipsec->sa_hash_lock); WARN_ON(rhashtable_remove_fast(&fipsec->sa_hash, &sa_ctx->hash, rhash_sa)); @@ -1299,6 +1319,8 @@ int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev) goto err_destroy_hash; } + ida_init(&fdev->ipsec->halloc); + return 0; err_destroy_hash: @@ -1331,6 +1353,7 @@ void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev) if (!mlx5_fpga_is_ipsec_device(mdev)) return; + ida_destroy(&fdev->ipsec->halloc); destroy_rules_rb(&fdev->ipsec->rules_rb); rhashtable_destroy(&fdev->ipsec->sa_hash); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h index 382985e65b48..9ba637f0f0f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h @@ -37,6 +37,7 @@ #include "accel/ipsec.h" #include "fs_cmd.h" +#ifdef CONFIG_MLX5_FPGA_IPSEC u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev); unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev); int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters, @@ -46,7 +47,8 @@ void *mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev, struct mlx5_accel_esp_xfrm *accel_xfrm, const __be32 saddr[4], const __be32 daddr[4], - const __be32 spi, bool is_ipv6); + const __be32 spi, bool is_ipv6, + u32 *sa_handle); void mlx5_fpga_ipsec_delete_sa_ctx(void *context); int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev); @@ -63,5 +65,17 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_flow_cmds * mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type); +#else +static inline u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev) +{ + return 0; +} -#endif /* __MLX5_FPGA_SADB_H__ */ +static inline const struct mlx5_flow_cmds * +mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type) +{ + return mlx5_fs_cmd_get_default(type); +} + +#endif /* CONFIG_MLX5_FPGA_IPSEC */ +#endif /* __MLX5_FPGA_IPSEC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d5defe09339a..2da45e9b9b6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2359,7 +2359,7 @@ static struct mlx5_flow_root_namespace struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_namespace *ns; - if (mlx5_accel_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE && + if (mlx5_fpga_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE && (table_type == FS_FT_NIC_RX || table_type == FS_FT_NIC_TX)) cmds = mlx5_fs_cmd_get_default_ipsec_fpga_cmds(table_type); @@ -2943,7 +2943,8 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) { + if (mlx5_fpga_ipsec_device_caps(steering->dev) & MLX5_ACCEL_IPSEC_CAP_DEVICE || + MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) { err = init_egress_root_ns(steering); if (err) goto err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index fa1665caac46..f99e1752d4e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -243,7 +243,7 @@ recover_from_sw_reset: if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) break; - cond_resched(); + msleep(20); } while (!time_after(jiffies, end)); if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 7af4210c1b96..5a97e98e937c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -782,7 +782,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); - + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); return 0; err_clr_master: @@ -1180,7 +1180,6 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) { int err = 0; - dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { mlx5_core_warn(dev, "interface is up, NOP\n"); diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 046a0cb82ed8..7a04c626a2aa 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -76,7 +76,7 @@ static int mlxfw_fsm_state_err(struct mlxfw_dev *mlxfw_dev, case MLXFW_FSM_STATE_ERR_MAX: MLXFW_ERR_MSG(mlxfw_dev, extack, "unknown error", err); break; - }; + } return mlxfw_fsm_state_errno[fsm_state_err]; }; @@ -159,7 +159,7 @@ mlxfw_fsm_reactivate_err(struct mlxfw_dev *mlxfw_dev, case MLXFW_FSM_REACTIVATE_STATUS_MAX: MLXFW_REACT_ERR("unexpected error", err); break; - }; + } return -EREMOTEIO; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 70a104e728f6..c3d04319ff44 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -380,7 +380,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa) block = kzalloc(sizeof(*block), GFP_KERNEL); if (!block) - return NULL; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&block->resource_list); block->afa = mlxsw_afa; @@ -408,7 +408,7 @@ err_second_set_create: mlxsw_afa_set_destroy(block->first_set); err_first_set_create: kfree(block); - return NULL; + return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(mlxsw_afa_block_create); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 9b39b8e70519..3c3db1c874b6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3203,7 +3203,7 @@ MLXSW_ITEM32_INDEXED(reg, iedr, rec_type, MLXSW_REG_IEDR_BASE_LEN, 24, 8, * Size of entries do be deleted. The unit is 1 entry, regardless of entry type. * Access: OP */ -MLXSW_ITEM32_INDEXED(reg, iedr, rec_size, MLXSW_REG_IEDR_BASE_LEN, 0, 11, +MLXSW_ITEM32_INDEXED(reg, iedr, rec_size, MLXSW_REG_IEDR_BASE_LEN, 0, 13, MLXSW_REG_IEDR_REC_LEN, 0x00, false); /* reg_iedr_rec_index_start diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c index 6c66a0f1b79e..ad69913f19c1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c @@ -88,8 +88,8 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, * to be written using PEFA register to all indexes for all regions. */ afa_block = mlxsw_afa_block_create(mlxsw_sp->afa); - if (!afa_block) { - err = -ENOMEM; + if (IS_ERR(afa_block)) { + err = PTR_ERR(afa_block); goto err_afa_block; } err = mlxsw_afa_block_continue(afa_block); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 67ee880a8727..01cff711bbd2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -464,7 +464,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl, rulei = kzalloc(sizeof(*rulei), GFP_KERNEL); if (!rulei) - return NULL; + return ERR_PTR(-ENOMEM); if (afa_block) { rulei->act_block = afa_block; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c index 346f4a5fe053..221aa6a474eb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c @@ -199,8 +199,8 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp, int err; afa_block = mlxsw_afa_block_create(mlxsw_sp->afa); - if (!afa_block) - return ERR_PTR(-ENOMEM); + if (IS_ERR(afa_block)) + return afa_block; err = mlxsw_afa_block_append_allocated_counter(afa_block, counter_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index d5bca1be3ef5..71aee4914619 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2999,6 +2999,7 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed); + val ^= jhash(&nh->gw_addr, sizeof(nh->gw_addr), seed); } return jhash(&val, sizeof(val), seed); default: @@ -3012,11 +3013,14 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) { unsigned int val = fib6_entry->nrt6; struct mlxsw_sp_rt6 *mlxsw_sp_rt6; - struct net_device *dev; list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { - dev = mlxsw_sp_rt6->rt->fib6_nh->fib_nh_dev; + struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh; + struct net_device *dev = fib6_nh->fib_nh_dev; + struct in6_addr *gw = &fib6_nh->fib_nh_gw6; + val ^= jhash(&dev->ifindex, sizeof(dev->ifindex), seed); + val ^= jhash(gw, sizeof(*gw), seed); } return jhash(&val, sizeof(val), seed); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 9fb2e9d93929..ae3c8a1e9a43 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -3,6 +3,7 @@ #include <linux/if_bridge.h> #include <linux/list.h> +#include <linux/refcount.h> #include <linux/rtnetlink.h> #include <linux/workqueue.h> #include <net/arp.h> @@ -21,7 +22,7 @@ struct mlxsw_sp_span { struct mlxsw_sp *mlxsw_sp; atomic_t active_entries_count; int entries_count; - struct mlxsw_sp_span_entry entries[0]; + struct mlxsw_sp_span_entry entries[]; }; static void mlxsw_sp_span_respin_work(struct work_struct *work); @@ -130,7 +131,7 @@ 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 = { .can_handle = mlxsw_sp_port_dev_check, - .parms = mlxsw_sp_span_entry_phys_parms, + .parms_set = mlxsw_sp_span_entry_phys_parms, .configure = mlxsw_sp_span_entry_phys_configure, .deconfigure = mlxsw_sp_span_entry_phys_deconfigure, }; @@ -418,7 +419,7 @@ mlxsw_sp_span_entry_gretap4_deconfigure(struct mlxsw_sp_span_entry *span_entry) static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap4 = { .can_handle = netif_is_gretap, - .parms = mlxsw_sp_span_entry_gretap4_parms, + .parms_set = mlxsw_sp_span_entry_gretap4_parms, .configure = mlxsw_sp_span_entry_gretap4_configure, .deconfigure = mlxsw_sp_span_entry_gretap4_deconfigure, }; @@ -519,7 +520,7 @@ mlxsw_sp_span_entry_gretap6_deconfigure(struct mlxsw_sp_span_entry *span_entry) static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = { .can_handle = netif_is_ip6gretap, - .parms = mlxsw_sp_span_entry_gretap6_parms, + .parms_set = mlxsw_sp_span_entry_gretap6_parms, .configure = mlxsw_sp_span_entry_gretap6_configure, .deconfigure = mlxsw_sp_span_entry_gretap6_deconfigure, }; @@ -575,7 +576,7 @@ mlxsw_sp_span_entry_vlan_deconfigure(struct mlxsw_sp_span_entry *span_entry) static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_vlan = { .can_handle = mlxsw_sp_span_vlan_can_handle, - .parms = mlxsw_sp_span_entry_vlan_parms, + .parms_set = mlxsw_sp_span_entry_vlan_parms, .configure = mlxsw_sp_span_entry_vlan_configure, .deconfigure = mlxsw_sp_span_entry_vlan_deconfigure, }; @@ -612,7 +613,7 @@ mlxsw_sp_span_entry_nop_deconfigure(struct mlxsw_sp_span_entry *span_entry) } static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_nop = { - .parms = mlxsw_sp_span_entry_nop_parms, + .parms_set = mlxsw_sp_span_entry_nop_parms, .configure = mlxsw_sp_span_entry_nop_configure, .deconfigure = mlxsw_sp_span_entry_nop_deconfigure, }; @@ -622,18 +623,27 @@ mlxsw_sp_span_entry_configure(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_span_entry *span_entry, struct mlxsw_sp_span_parms sparms) { - if (sparms.dest_port) { - if (sparms.dest_port->mlxsw_sp != mlxsw_sp) { - netdev_err(span_entry->to_dev, "Cannot mirror to %s, which belongs to a different mlxsw instance", - sparms.dest_port->dev->name); - sparms.dest_port = NULL; - } else if (span_entry->ops->configure(span_entry, sparms)) { - netdev_err(span_entry->to_dev, "Failed to offload mirror to %s", - sparms.dest_port->dev->name); - sparms.dest_port = NULL; - } + int err; + + if (!sparms.dest_port) + goto set_parms; + + if (sparms.dest_port->mlxsw_sp != mlxsw_sp) { + netdev_err(span_entry->to_dev, "Cannot mirror to %s, which belongs to a different mlxsw instance", + sparms.dest_port->dev->name); + sparms.dest_port = NULL; + goto set_parms; } + err = span_entry->ops->configure(span_entry, sparms); + if (err) { + netdev_err(span_entry->to_dev, "Failed to offload mirror to %s", + sparms.dest_port->dev->name); + sparms.dest_port = NULL; + goto set_parms; + } + +set_parms: span_entry->parms = sparms; } @@ -655,7 +665,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp, /* find a free entry to use */ for (i = 0; i < mlxsw_sp->span->entries_count; i++) { - if (!mlxsw_sp->span->entries[i].ref_count) { + if (!refcount_read(&mlxsw_sp->span->entries[i].ref_count)) { span_entry = &mlxsw_sp->span->entries[i]; break; } @@ -665,7 +675,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp, atomic_inc(&mlxsw_sp->span->active_entries_count); span_entry->ops = ops; - span_entry->ref_count = 1; + refcount_set(&span_entry->ref_count, 1); span_entry->to_dev = to_dev; mlxsw_sp_span_entry_configure(mlxsw_sp, span_entry, sparms); @@ -688,7 +698,7 @@ mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < mlxsw_sp->span->entries_count; i++) { struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; - if (curr->ref_count && curr->to_dev == to_dev) + if (refcount_read(&curr->ref_count) && curr->to_dev == to_dev) return curr; } return NULL; @@ -709,7 +719,7 @@ mlxsw_sp_span_entry_find_by_id(struct mlxsw_sp *mlxsw_sp, int span_id) for (i = 0; i < mlxsw_sp->span->entries_count; i++) { struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; - if (curr->ref_count && curr->id == span_id) + if (refcount_read(&curr->ref_count) && curr->id == span_id) return curr; } return NULL; @@ -726,7 +736,7 @@ mlxsw_sp_span_entry_get(struct mlxsw_sp *mlxsw_sp, span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, to_dev); if (span_entry) { /* Already exists, just take a reference */ - span_entry->ref_count++; + refcount_inc(&span_entry->ref_count); return span_entry; } @@ -736,8 +746,7 @@ mlxsw_sp_span_entry_get(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_span_entry *span_entry) { - WARN_ON(!span_entry->ref_count); - if (--span_entry->ref_count == 0) + if (refcount_dec_and_test(&span_entry->ref_count)) mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); return 0; } @@ -961,7 +970,7 @@ int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, return -EOPNOTSUPP; } - err = ops->parms(to_dev, &sparms); + err = ops->parms_set(to_dev, &sparms); if (err) return err; @@ -969,9 +978,6 @@ int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, if (!span_entry) return -ENOBUFS; - netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", - span_entry->id); - err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind); if (err) goto err_port_bind; @@ -995,8 +1001,6 @@ void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id, return; } - netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", - span_entry->id); mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind); } @@ -1014,10 +1018,10 @@ static void mlxsw_sp_span_respin_work(struct work_struct *work) struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; struct mlxsw_sp_span_parms sparms = {NULL}; - if (!curr->ref_count) + if (!refcount_read(&curr->ref_count)) continue; - err = curr->ops->parms(curr->to_dev, &sparms); + err = curr->ops->parms_set(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 59724335525f..d23abdf957fa 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/if_ether.h> +#include <linux/refcount.h> #include "spectrum_router.h" @@ -43,14 +44,14 @@ struct mlxsw_sp_span_entry { const struct mlxsw_sp_span_entry_ops *ops; struct mlxsw_sp_span_parms parms; struct list_head bound_ports_list; - int ref_count; + refcount_t ref_count; int id; }; struct mlxsw_sp_span_entry_ops { bool (*can_handle)(const struct net_device *to_dev); - int (*parms)(const struct net_device *to_dev, - struct mlxsw_sp_span_parms *sparmsp); + int (*parms_set)(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp); int (*configure)(struct mlxsw_sp_span_entry *span_entry, struct mlxsw_sp_span_parms sparms); void (*deconfigure)(struct mlxsw_sp_span_entry *span_entry); diff --git a/drivers/net/ethernet/mscc/Makefile b/drivers/net/ethernet/mscc/Makefile index 9a36c26095c8..91b33b55054e 100644 --- a/drivers/net/ethernet/mscc/Makefile +++ b/drivers/net/ethernet/mscc/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: (GPL-2.0 OR MIT) obj-$(CONFIG_MSCC_OCELOT_SWITCH) += mscc_ocelot_common.o mscc_ocelot_common-y := ocelot.o ocelot_io.o -mscc_ocelot_common-y += ocelot_regs.o ocelot_tc.o ocelot_police.o ocelot_ace.o ocelot_flower.o +mscc_ocelot_common-y += ocelot_regs.o ocelot_tc.o ocelot_police.o ocelot_ace.o ocelot_flower.o ocelot_ptp.o obj-$(CONFIG_MSCC_OCELOT_SWITCH_OCELOT) += ocelot_board.o diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index b4731df186f4..a2b9b85612a4 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/phy.h> -#include <linux/ptp_clock_kernel.h> #include <linux/skbuff.h> #include <linux/iopoll.h> #include <net/arp.h> @@ -183,44 +182,47 @@ static void ocelot_vlan_mode(struct ocelot *ocelot, int port, ocelot_write(ocelot, val, ANA_VLANMASK); } -void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, - bool vlan_aware) +static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port, + u16 vid) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - u32 val; + u32 val = 0; - if (vlan_aware) - val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | - ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1); - else - val = 0; - ocelot_rmw_gix(ocelot, val, - ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | - ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, - ANA_PORT_VLAN_CFG, port); + if (ocelot_port->vid != vid) { + /* Always permit deleting the native VLAN (vid = 0) */ + if (ocelot_port->vid && vid) { + dev_err(ocelot->dev, + "Port already has a native VLAN: %d\n", + ocelot_port->vid); + return -EBUSY; + } + ocelot_port->vid = vid; + } - if (vlan_aware && !ocelot_port->vid) + ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid), + REW_PORT_VLAN_CFG_PORT_VID_M, + REW_PORT_VLAN_CFG, port); + + if (ocelot_port->vlan_aware && !ocelot_port->vid) /* If port is vlan-aware and tagged, drop untagged and priority * tagged frames. */ val = ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA | ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; - else - val = 0; ocelot_rmw_gix(ocelot, val, ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA | ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, ANA_PORT_DROP_CFG, port); - if (vlan_aware) { + if (ocelot_port->vlan_aware) { if (ocelot_port->vid) /* Tag all frames except when VID == DEFAULT_VLAN */ - val |= REW_TAG_CFG_TAG_CFG(1); + val = REW_TAG_CFG_TAG_CFG(1); else /* Tag all frames */ - val |= REW_TAG_CFG_TAG_CFG(3); + val = REW_TAG_CFG_TAG_CFG(3); } else { /* Port tagging disabled. */ val = REW_TAG_CFG_TAG_CFG(0); @@ -228,31 +230,31 @@ void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ocelot_rmw_gix(ocelot, val, REW_TAG_CFG_TAG_CFG_M, REW_TAG_CFG, port); + + return 0; } -EXPORT_SYMBOL(ocelot_port_vlan_filtering); -static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port, - u16 vid) +void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, + bool vlan_aware) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + u32 val; - if (ocelot_port->vid != vid) { - /* Always permit deleting the native VLAN (vid = 0) */ - if (ocelot_port->vid && vid) { - dev_err(ocelot->dev, - "Port already has a native VLAN: %d\n", - ocelot_port->vid); - return -EBUSY; - } - ocelot_port->vid = vid; - } + ocelot_port->vlan_aware = vlan_aware; - ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid), - REW_PORT_VLAN_CFG_PORT_VID_M, - REW_PORT_VLAN_CFG, port); + if (vlan_aware) + val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | + ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1); + else + val = 0; + ocelot_rmw_gix(ocelot, val, + ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA | + ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, + ANA_PORT_VLAN_CFG, port); - return 0; + ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid); } +EXPORT_SYMBOL(ocelot_port_vlan_filtering); /* Default vlan to clasify for untagged frames (may be zero) */ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, u16 pvid) @@ -873,12 +875,12 @@ static void ocelot_get_stats64(struct net_device *dev, } int ocelot_fdb_add(struct ocelot *ocelot, int port, - const unsigned char *addr, u16 vid, bool vlan_aware) + const unsigned char *addr, u16 vid) { struct ocelot_port *ocelot_port = ocelot->ports[port]; if (!vid) { - if (!vlan_aware) + if (!ocelot_port->vlan_aware) /* If the bridge is not VLAN aware and no VID was * provided, set it to pvid to ensure the MAC entry * matches incoming untagged packets @@ -905,7 +907,7 @@ static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct ocelot *ocelot = priv->port.ocelot; int port = priv->chip_port; - return ocelot_fdb_add(ocelot, port, addr, vid, priv->vlan_aware); + return ocelot_fdb_add(ocelot, port, addr, vid); } int ocelot_fdb_del(struct ocelot *ocelot, int port, @@ -1347,6 +1349,12 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, { info->phc_index = ocelot->ptp_clock ? ptp_clock_index(ocelot->ptp_clock) : -1; + if (info->phc_index == -1) { + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + return 0; + } info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE | @@ -1496,8 +1504,8 @@ static int ocelot_port_attr_set(struct net_device *dev, ocelot_port_attr_ageing_set(ocelot, port, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: - priv->vlan_aware = attr->u.vlan_filtering; - ocelot_port_vlan_filtering(ocelot, port, priv->vlan_aware); + ocelot_port_vlan_filtering(ocelot, port, + attr->u.vlan_filtering); break; case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED: ocelot_port_attr_mc_set(ocelot, port, !attr->u.mc_disabled); @@ -1868,7 +1876,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev, } else { err = ocelot_port_bridge_leave(ocelot, port, info->upper_dev); - priv->vlan_aware = false; } } if (netif_is_lag_master(info->upper_dev)) { @@ -1989,200 +1996,6 @@ struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = { }; EXPORT_SYMBOL(ocelot_switchdev_blocking_nb); -int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) -{ - struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); - unsigned long flags; - time64_t s; - u32 val; - s64 ns; - - spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); - - val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); - val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); - val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE); - ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); - - s = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN) & 0xffff; - s <<= 32; - s += ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); - ns = ocelot_read_rix(ocelot, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); - - spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); - - /* Deal with negative values */ - if (ns >= 0x3ffffff0 && ns <= 0x3fffffff) { - s--; - ns &= 0xf; - ns += 999999984; - } - - set_normalized_timespec64(ts, s, ns); - return 0; -} -EXPORT_SYMBOL(ocelot_ptp_gettime64); - -static int ocelot_ptp_settime64(struct ptp_clock_info *ptp, - const struct timespec64 *ts) -{ - struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); - unsigned long flags; - u32 val; - - spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); - - val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); - val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); - val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); - - ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); - - ocelot_write_rix(ocelot, lower_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_LSB, - TOD_ACC_PIN); - ocelot_write_rix(ocelot, upper_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_MSB, - TOD_ACC_PIN); - ocelot_write_rix(ocelot, ts->tv_nsec, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); - - val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); - val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); - val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_LOAD); - - ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); - - spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); - return 0; -} - -static int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) -{ - if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) { - struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); - unsigned long flags; - u32 val; - - spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); - - val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); - val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); - val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); - - ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); - - ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); - ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN); - ocelot_write_rix(ocelot, delta, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); - - val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); - val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); - val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_DELTA); - - ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); - - spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); - } else { - /* Fall back using ocelot_ptp_settime64 which is not exact. */ - struct timespec64 ts; - u64 now; - - ocelot_ptp_gettime64(ptp, &ts); - - now = ktime_to_ns(timespec64_to_ktime(ts)); - ts = ns_to_timespec64(now + delta); - - ocelot_ptp_settime64(ptp, &ts); - } - return 0; -} - -static int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) -{ - struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); - u32 unit = 0, direction = 0; - unsigned long flags; - u64 adj = 0; - - spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); - - if (!scaled_ppm) - goto disable_adj; - - if (scaled_ppm < 0) { - direction = PTP_CFG_CLK_ADJ_CFG_DIR; - scaled_ppm = -scaled_ppm; - } - - adj = PSEC_PER_SEC << 16; - do_div(adj, scaled_ppm); - do_div(adj, 1000); - - /* If the adjustment value is too large, use ns instead */ - if (adj >= (1L << 30)) { - unit = PTP_CFG_CLK_ADJ_FREQ_NS; - do_div(adj, 1000); - } - - /* Still too big */ - if (adj >= (1L << 30)) - goto disable_adj; - - ocelot_write(ocelot, unit | adj, PTP_CLK_CFG_ADJ_FREQ); - ocelot_write(ocelot, PTP_CFG_CLK_ADJ_CFG_ENA | direction, - PTP_CLK_CFG_ADJ_CFG); - - spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); - return 0; - -disable_adj: - ocelot_write(ocelot, 0, PTP_CLK_CFG_ADJ_CFG); - - spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); - return 0; -} - -static struct ptp_clock_info ocelot_ptp_clock_info = { - .owner = THIS_MODULE, - .name = "ocelot ptp", - .max_adj = 0x7fffffff, - .n_alarm = 0, - .n_ext_ts = 0, - .n_per_out = 0, - .n_pins = 0, - .pps = 0, - .gettime64 = ocelot_ptp_gettime64, - .settime64 = ocelot_ptp_settime64, - .adjtime = ocelot_ptp_adjtime, - .adjfine = ocelot_ptp_adjfine, -}; - -static int ocelot_init_timestamp(struct ocelot *ocelot) -{ - struct ptp_clock *ptp_clock; - - ocelot->ptp_info = ocelot_ptp_clock_info; - ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev); - if (IS_ERR(ptp_clock)) - return PTR_ERR(ptp_clock); - /* Check if PHC support is missing at the configuration level */ - if (!ptp_clock) - return 0; - - ocelot->ptp_clock = ptp_clock; - - ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG); - ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW); - ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH); - - ocelot_write(ocelot, PTP_CFG_MISC_PTP_EN, PTP_CFG_MISC); - - /* There is no device reconfiguration, PTP Rx stamping is always - * enabled. - */ - ocelot->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; - - return 0; -} - /* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu. * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG. * In the special case that it's the NPI port that we're configuring, the @@ -2528,15 +2341,6 @@ int ocelot_init(struct ocelot *ocelot) queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); - if (ocelot->ptp) { - ret = ocelot_init_timestamp(ocelot); - if (ret) { - dev_err(ocelot->dev, - "Timestamp initialization failed\n"); - return ret; - } - } - return 0; } EXPORT_SYMBOL(ocelot_init); @@ -2549,8 +2353,6 @@ void ocelot_deinit(struct ocelot *ocelot) cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); - if (ocelot->ptp_clock) - ptp_clock_unregister(ocelot->ptp_clock); for (i = 0; i < ocelot->num_phys_ports; i++) { port = ocelot->ports[i]; diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index e34ef8380eb3..f0a15aa187f2 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -15,18 +15,17 @@ #include <linux/phy.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> -#include <linux/ptp_clock_kernel.h> #include <linux/regmap.h> #include <soc/mscc/ocelot_qsys.h> #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot_dev.h> #include <soc/mscc/ocelot_ana.h> +#include <soc/mscc/ocelot_ptp.h> #include <soc/mscc/ocelot.h> #include "ocelot_rew.h" #include "ocelot_qs.h" #include "ocelot_tc.h" -#include "ocelot_ptp.h" #define OCELOT_BUFFER_CELL_SZ 60 @@ -56,8 +55,6 @@ struct ocelot_port_private { struct phy_device *phy; u8 chip_port; - u8 vlan_aware; - struct phy *serdes; struct ocelot_port_tc tc; diff --git a/drivers/net/ethernet/mscc/ocelot_ace.c b/drivers/net/ethernet/mscc/ocelot_ace.c index 3bd286044480..dfd82a3baab2 100644 --- a/drivers/net/ethernet/mscc/ocelot_ace.c +++ b/drivers/net/ethernet/mscc/ocelot_ace.c @@ -706,13 +706,124 @@ ocelot_ace_rule_get_rule_index(struct ocelot_acl_block *block, int index) return NULL; } +/* 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 + * information. The only frame types to match on keys containing MAC addresses + * in this case are non-SNAP, non-ARP, non-IP and non-OAM frames. + * + * If @on=true, then the above frame types (SNAP, ARP, IP and OAM) will match + * on MAC_ETYPE keys such as destination and source MAC on this ingress port. + * However the setting has the side effect of making these frames not matching + * on any _other_ keys than MAC_ETYPE ones. + */ +static void ocelot_match_all_as_mac_etype(struct ocelot *ocelot, int port, + bool on) +{ + u32 val = 0; + + if (on) + val = ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS(3) | + ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS(3) | + ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS(3) | + ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS(3) | + ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS(3); + + ocelot_rmw_gix(ocelot, val, + ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS_M | + ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS_M | + ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS_M | + ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS_M | + ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS_M, + ANA_PORT_VCAP_S2_CFG, port); +} + +static bool ocelot_ace_is_problematic_mac_etype(struct ocelot_ace_rule *ace) +{ + u16 proto, mask; + + if (ace->type != OCELOT_ACE_TYPE_ETYPE) + return false; + + proto = ntohs(*(u16 *)ace->frame.etype.etype.value); + mask = ntohs(*(u16 *)ace->frame.etype.etype.mask); + + /* ETH_P_ALL match, so all protocols below are included */ + if (mask == 0) + return true; + if (proto == ETH_P_ARP) + return true; + if (proto == ETH_P_IP) + return true; + if (proto == ETH_P_IPV6) + return true; + + return false; +} + +static bool ocelot_ace_is_problematic_non_mac_etype(struct ocelot_ace_rule *ace) +{ + if (ace->type == OCELOT_ACE_TYPE_SNAP) + return true; + if (ace->type == OCELOT_ACE_TYPE_ARP) + return true; + if (ace->type == OCELOT_ACE_TYPE_IPV4) + return true; + if (ace->type == OCELOT_ACE_TYPE_IPV6) + return true; + return false; +} + +static bool ocelot_exclusive_mac_etype_ace_rules(struct ocelot *ocelot, + struct ocelot_ace_rule *ace) +{ + struct ocelot_acl_block *block = &ocelot->acl_block; + struct ocelot_ace_rule *tmp; + unsigned long port; + int i; + + if (ocelot_ace_is_problematic_mac_etype(ace)) { + /* Search for any non-MAC_ETYPE rules on the port */ + for (i = 0; i < block->count; i++) { + tmp = ocelot_ace_rule_get_rule_index(block, i); + if (tmp->ingress_port_mask & ace->ingress_port_mask && + ocelot_ace_is_problematic_non_mac_etype(tmp)) + return false; + } + + for_each_set_bit(port, &ace->ingress_port_mask, + ocelot->num_phys_ports) + ocelot_match_all_as_mac_etype(ocelot, port, true); + } else if (ocelot_ace_is_problematic_non_mac_etype(ace)) { + /* Search for any MAC_ETYPE rules on the port */ + for (i = 0; i < block->count; i++) { + tmp = ocelot_ace_rule_get_rule_index(block, i); + if (tmp->ingress_port_mask & ace->ingress_port_mask && + ocelot_ace_is_problematic_mac_etype(tmp)) + return false; + } + + for_each_set_bit(port, &ace->ingress_port_mask, + ocelot->num_phys_ports) + ocelot_match_all_as_mac_etype(ocelot, port, false); + } + + return true; +} + int ocelot_ace_rule_offload_add(struct ocelot *ocelot, - struct ocelot_ace_rule *rule) + struct ocelot_ace_rule *rule, + struct netlink_ext_ack *extack) { struct ocelot_acl_block *block = &ocelot->acl_block; struct ocelot_ace_rule *ace; int i, index; + if (!ocelot_exclusive_mac_etype_ace_rules(ocelot, rule)) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot mix MAC_ETYPE with non-MAC_ETYPE rules"); + return -EBUSY; + } + /* Add rule to the linked list */ ocelot_ace_rule_add(ocelot, block, rule); diff --git a/drivers/net/ethernet/mscc/ocelot_ace.h b/drivers/net/ethernet/mscc/ocelot_ace.h index 29d22c566786..099e177f2617 100644 --- a/drivers/net/ethernet/mscc/ocelot_ace.h +++ b/drivers/net/ethernet/mscc/ocelot_ace.h @@ -194,7 +194,7 @@ struct ocelot_ace_rule { enum ocelot_ace_action action; struct ocelot_ace_stats stats; - u16 ingress_port_mask; + unsigned long ingress_port_mask; enum ocelot_vcap_bit dmac_mc; enum ocelot_vcap_bit dmac_bc; @@ -215,7 +215,8 @@ struct ocelot_ace_rule { }; int ocelot_ace_rule_offload_add(struct ocelot *ocelot, - struct ocelot_ace_rule *rule); + struct ocelot_ace_rule *rule, + struct netlink_ext_ack *extack); int ocelot_ace_rule_offload_del(struct ocelot *ocelot, struct ocelot_ace_rule *rule); int ocelot_ace_rule_stats_update(struct ocelot *ocelot, diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 0ac9fbf77a01..67a8d61c926a 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -366,6 +366,23 @@ static const struct vcap_props vsc7514_vcap_props[] = { }, }; +static struct ptp_clock_info ocelot_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "ocelot ptp", + .max_adj = 0x7fffffff, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = OCELOT_PTP_PINS_NUM, + .n_pins = OCELOT_PTP_PINS_NUM, + .pps = 0, + .gettime64 = ocelot_ptp_gettime64, + .settime64 = ocelot_ptp_settime64, + .adjtime = ocelot_ptp_adjtime, + .adjfine = ocelot_ptp_adjfine, + .verify = ocelot_ptp_verify, + .enable = ocelot_ptp_enable, +}; + static int mscc_ocelot_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; @@ -469,6 +486,15 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ocelot->vcap = vsc7514_vcap_props; ocelot_init(ocelot); + if (ocelot->ptp) { + err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info); + if (err) { + dev_err(ocelot->dev, + "Timestamp initialization failed\n"); + ocelot->ptp = 0; + } + } + /* No NPI port */ ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE, OCELOT_TAG_PREFIX_NONE); @@ -574,6 +600,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev) { struct ocelot *ocelot = platform_get_drvdata(pdev); + ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); unregister_switchdev_notifier(&ocelot_switchdev_nb); diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 341923311fec..5ce172e22b43 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -51,6 +51,8 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, { struct flow_rule *rule = flow_cls_offload_flow_rule(f); struct flow_dissector *dissector = rule->match.dissector; + u16 proto = ntohs(f->common.protocol); + bool match_protocol = true; if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | @@ -71,7 +73,6 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; - u16 proto = ntohs(f->common.protocol); /* The hw support mac matches only for MAC_ETYPE key, * therefore if other matches(port, tcp flags, etc) are added @@ -86,11 +87,6 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, BIT(FLOW_DISSECTOR_KEY_CONTROL))) return -EOPNOTSUPP; - if (proto == ETH_P_IP || - proto == ETH_P_IPV6 || - proto == ETH_P_ARP) - return -EOPNOTSUPP; - flow_rule_match_eth_addrs(rule, &match); ace->type = OCELOT_ACE_TYPE_ETYPE; ether_addr_copy(ace->frame.etype.dmac.value, @@ -114,6 +110,7 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, match.key->ip_proto; ace->frame.ipv4.proto.mask[0] = match.mask->ip_proto; + match_protocol = false; } if (ntohs(match.key->n_proto) == ETH_P_IPV6) { ace->type = OCELOT_ACE_TYPE_IPV6; @@ -121,11 +118,12 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, match.key->ip_proto; ace->frame.ipv6.proto.mask[0] = match.mask->ip_proto; + match_protocol = false; } } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) && - ntohs(f->common.protocol) == ETH_P_IP) { + proto == ETH_P_IP) { struct flow_match_ipv4_addrs match; u8 *tmp; @@ -141,10 +139,11 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, tmp = &ace->frame.ipv4.dip.mask.addr[0]; memcpy(tmp, &match.mask->dst, 4); + match_protocol = false; } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) && - ntohs(f->common.protocol) == ETH_P_IPV6) { + proto == ETH_P_IPV6) { return -EOPNOTSUPP; } @@ -156,6 +155,7 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, ace->frame.ipv4.sport.mask = ntohs(match.mask->src); ace->frame.ipv4.dport.value = ntohs(match.key->dst); ace->frame.ipv4.dport.mask = ntohs(match.mask->dst); + match_protocol = false; } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { @@ -167,9 +167,20 @@ static int ocelot_flower_parse(struct flow_cls_offload *f, ace->vlan.vid.mask = match.mask->vlan_id; ace->vlan.pcp.value[0] = match.key->vlan_priority; ace->vlan.pcp.mask[0] = match.mask->vlan_priority; + match_protocol = false; } finished_key_parsing: + if (match_protocol && proto != ETH_P_ALL) { + /* TODO: support SNAP, LLC etc */ + if (proto < ETH_P_802_3_MIN) + return -EOPNOTSUPP; + ace->type = OCELOT_ACE_TYPE_ETYPE; + *(u16 *)ace->frame.etype.etype.value = htons(proto); + *(u16 *)ace->frame.etype.etype.mask = 0xffff; + } + /* else, a rule of type OCELOT_ACE_TYPE_ANY is implicitly added */ + ace->prio = f->common.prio; ace->id = f->cookie; return ocelot_flower_parse_action(f, ace); @@ -205,7 +216,7 @@ int ocelot_cls_flower_replace(struct ocelot *ocelot, int port, return ret; } - return ocelot_ace_rule_offload_add(ocelot, ace); + return ocelot_ace_rule_offload_add(ocelot, ace, f->common.extack); } EXPORT_SYMBOL_GPL(ocelot_cls_flower_replace); diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c new file mode 100644 index 000000000000..a3088a1676ed --- /dev/null +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Microsemi Ocelot PTP clock driver + * + * Copyright (c) 2017 Microsemi Corporation + * Copyright 2020 NXP + */ +#include <soc/mscc/ocelot_ptp.h> +#include <soc/mscc/ocelot_sys.h> +#include <soc/mscc/ocelot.h> + +int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + time64_t s; + u32 val; + s64 ns; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + s = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN) & 0xffff; + s <<= 32; + s += ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + ns = ocelot_read_rix(ocelot, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + + /* Deal with negative values */ + if (ns >= 0x3ffffff0 && ns <= 0x3fffffff) { + s--; + ns &= 0xf; + ns += 999999984; + } + + set_normalized_timespec64(ts, s, ns); + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_gettime64); + +int ocelot_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + ocelot_write_rix(ocelot, lower_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_LSB, + TOD_ACC_PIN); + ocelot_write_rix(ocelot, upper_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_MSB, + TOD_ACC_PIN); + ocelot_write_rix(ocelot, ts->tv_nsec, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_LOAD); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_settime64); + +int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) { + struct ocelot *ocelot = container_of(ptp, struct ocelot, + ptp_info); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | + PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN); + ocelot_write_rix(ocelot, delta, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | + PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_DELTA); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + } else { + /* Fall back using ocelot_ptp_settime64 which is not exact. */ + struct timespec64 ts; + u64 now; + + ocelot_ptp_gettime64(ptp, &ts); + + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + + ocelot_ptp_settime64(ptp, &ts); + } + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_adjtime); + +int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + u32 unit = 0, direction = 0; + unsigned long flags; + u64 adj = 0; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + if (!scaled_ppm) + goto disable_adj; + + if (scaled_ppm < 0) { + direction = PTP_CFG_CLK_ADJ_CFG_DIR; + scaled_ppm = -scaled_ppm; + } + + adj = PSEC_PER_SEC << 16; + do_div(adj, scaled_ppm); + do_div(adj, 1000); + + /* If the adjustment value is too large, use ns instead */ + if (adj >= (1L << 30)) { + unit = PTP_CFG_CLK_ADJ_FREQ_NS; + do_div(adj, 1000); + } + + /* Still too big */ + if (adj >= (1L << 30)) + goto disable_adj; + + ocelot_write(ocelot, unit | adj, PTP_CLK_CFG_ADJ_FREQ); + ocelot_write(ocelot, PTP_CFG_CLK_ADJ_CFG_ENA | direction, + PTP_CLK_CFG_ADJ_CFG); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; + +disable_adj: + ocelot_write(ocelot, 0, PTP_CLK_CFG_ADJ_CFG); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_adjfine); + +int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_PEROUT: + break; + case PTP_PF_EXTTS: + case PTP_PF_PHYSYNC: + return -1; + } + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_verify); + +int ocelot_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + struct timespec64 ts_start, ts_period; + enum ocelot_ptp_pins ptp_pin; + unsigned long flags; + bool pps = false; + int pin = -1; + u32 val; + s64 ns; + + switch (rq->type) { + case PTP_CLK_REQ_PEROUT: + /* Reject requests with unsupported flags */ + if (rq->perout.flags) + return -EOPNOTSUPP; + + pin = ptp_find_pin(ocelot->ptp_clock, PTP_PF_PEROUT, + rq->perout.index); + if (pin == 0) + ptp_pin = PTP_PIN_0; + else if (pin == 1) + ptp_pin = PTP_PIN_1; + else if (pin == 2) + ptp_pin = PTP_PIN_2; + else if (pin == 3) + ptp_pin = PTP_PIN_3; + else + return -EBUSY; + + ts_start.tv_sec = rq->perout.start.sec; + ts_start.tv_nsec = rq->perout.start.nsec; + ts_period.tv_sec = rq->perout.period.sec; + ts_period.tv_nsec = rq->perout.period.nsec; + + if (ts_period.tv_sec == 1 && ts_period.tv_nsec == 0) + pps = true; + + if (ts_start.tv_sec || (ts_start.tv_nsec && !pps)) { + dev_warn(ocelot->dev, + "Absolute start time not supported!\n"); + dev_warn(ocelot->dev, + "Accept nsec for PPS phase adjustment, otherwise start time should be 0 0.\n"); + return -EINVAL; + } + + /* Handle turning off */ + if (!on) { + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + val = PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, ptp_pin); + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + break; + } + + /* Handle PPS request */ + if (pps) { + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + /* Pulse generated perout.start.nsec after TOD has + * increased seconds. + * Pulse width is set to 1us. + */ + ocelot_write_rix(ocelot, ts_start.tv_nsec, + PTP_PIN_WF_LOW_PERIOD, ptp_pin); + ocelot_write_rix(ocelot, 1000, + PTP_PIN_WF_HIGH_PERIOD, ptp_pin); + val = PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_CLOCK); + val |= PTP_PIN_CFG_SYNC; + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, ptp_pin); + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + break; + } + + /* Handle periodic clock */ + ns = timespec64_to_ns(&ts_period); + ns = ns >> 1; + if (ns > 0x3fffffff || ns <= 0x6) + return -EINVAL; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + ocelot_write_rix(ocelot, ns, PTP_PIN_WF_LOW_PERIOD, ptp_pin); + ocelot_write_rix(ocelot, ns, PTP_PIN_WF_HIGH_PERIOD, ptp_pin); + val = PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_CLOCK); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, ptp_pin); + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + break; + default: + return -EOPNOTSUPP; + } + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_enable); + +int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info) +{ + struct ptp_clock *ptp_clock; + int i; + + ocelot->ptp_info = *info; + + for (i = 0; i < OCELOT_PTP_PINS_NUM; i++) { + struct ptp_pin_desc *p = &ocelot->ptp_pins[i]; + + snprintf(p->name, sizeof(p->name), "switch_1588_dat%d", i); + p->index = i; + p->func = PTP_PF_NONE; + } + + ocelot->ptp_info.pin_config = &ocelot->ptp_pins[0]; + + ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev); + if (IS_ERR(ptp_clock)) + return PTR_ERR(ptp_clock); + /* Check if PHC support is missing at the configuration level */ + if (!ptp_clock) + return 0; + + ocelot->ptp_clock = ptp_clock; + + ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG); + ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW); + ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH); + + ocelot_write(ocelot, PTP_CFG_MISC_PTP_EN, PTP_CFG_MISC); + + /* There is no device reconfiguration, PTP Rx stamping is always + * enabled. + */ + ocelot->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + + return 0; +} +EXPORT_SYMBOL(ocelot_init_timestamp); + +int ocelot_deinit_timestamp(struct ocelot *ocelot) +{ + if (ocelot->ptp_clock) + ptp_clock_unregister(ocelot->ptp_clock); + return 0; +} +EXPORT_SYMBOL(ocelot_deinit_timestamp); diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index b88b5899b227..ed4dd01a41ad 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -239,6 +239,8 @@ static const u32 ocelot_ptp_regmap[] = { REG(PTP_PIN_TOD_SEC_MSB, 0x000004), REG(PTP_PIN_TOD_SEC_LSB, 0x000008), REG(PTP_PIN_TOD_NSEC, 0x00000c), + REG(PTP_PIN_WF_HIGH_PERIOD, 0x000014), + REG(PTP_PIN_WF_LOW_PERIOD, 0x000018), REG(PTP_CFG_MISC, 0x0000a0), REG(PTP_CLK_CFG_ADJ_CFG, 0x0000a4), REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 0ec6b8e8b549..67e62603fe3b 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5155,7 +5155,7 @@ static int do_s2io_delete_unicast_mc(struct s2io_nic *sp, u64 addr) /* read mac entries from CAM */ static u64 do_s2io_read_unicast_mc(struct s2io_nic *sp, int offset) { - u64 tmp64 = 0xffffffffffff0000ULL, val64; + u64 tmp64, val64; struct XENA_dev_config __iomem *bar0 = sp->bar0; /* read mac addr */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 4d282fc56009..7ff2ccbd43b0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -14,7 +14,6 @@ #include <linux/mutex.h> #include <linux/pci.h> #include <linux/firmware.h> -#include <linux/vermagic.h> #include <linux/vmalloc.h> #include <net/devlink.h> @@ -31,7 +30,6 @@ #include "nfp_net.h" static const char nfp_driver_name[] = "nfp"; -const char nfp_driver_version[] = VERMAGIC_STRING; static const struct pci_device_id nfp_pci_device_ids[] = { { PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP6000, @@ -920,4 +918,3 @@ MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_1x10_1x25.nffw"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("The Netronome Flow Processor (NFP) driver."); -MODULE_VERSION(UTS_RELEASE); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 2779f1526d1e..a5aa3219d112 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -203,8 +203,6 @@ nfp_get_drvinfo(struct nfp_app *app, struct pci_dev *pdev, char nsp_version[ETHTOOL_FWVERS_LEN] = {}; strlcpy(drvinfo->driver, pdev->driver->name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, nfp_driver_version, sizeof(drvinfo->version)); - nfp_net_get_nspinfo(app, nsp_version); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%s %s %s %s", vnic_version, nsp_version, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 4b8a76098ca3..5acf4f46c268 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2127,6 +2127,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) if (lif->registered) ionic_lif_set_netdev_info(lif); + ionic_rx_filter_replay(lif); + if (netif_running(lif->netdev)) { err = ionic_txrx_alloc(lif); if (err) @@ -2206,9 +2208,9 @@ static void ionic_lif_deinit(struct ionic_lif *lif) if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { cancel_work_sync(&lif->deferred.work); cancel_work_sync(&lif->tx_timeout_work); + ionic_rx_filters_deinit(lif); } - ionic_rx_filters_deinit(lif); if (lif->netdev->features & NETIF_F_RXHASH) ionic_lif_rss_deinit(lif); @@ -2339,24 +2341,30 @@ static int ionic_station_set(struct ionic_lif *lif) err = ionic_adminq_post_wait(lif, &ctx); if (err) return err; - + netdev_dbg(lif->netdev, "found initial MAC addr %pM\n", + ctx.comp.lif_getattr.mac); if (is_zero_ether_addr(ctx.comp.lif_getattr.mac)) return 0; - memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); - addr.sa_family = AF_INET; - err = eth_prepare_mac_addr_change(netdev, &addr); - if (err) { - netdev_warn(lif->netdev, "ignoring bad MAC addr from NIC %pM - err %d\n", - addr.sa_data, err); - return 0; - } + if (!ether_addr_equal(ctx.comp.lif_getattr.mac, netdev->dev_addr)) { + memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); + addr.sa_family = AF_INET; + err = eth_prepare_mac_addr_change(netdev, &addr); + if (err) { + netdev_warn(lif->netdev, "ignoring bad MAC addr from NIC %pM - err %d\n", + addr.sa_data, err); + return 0; + } - netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", - netdev->dev_addr); - ionic_lif_addr(lif, netdev->dev_addr, false); + if (!is_zero_ether_addr(netdev->dev_addr)) { + netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", + netdev->dev_addr); + ionic_lif_addr(lif, netdev->dev_addr, false); + } + + eth_commit_mac_addr_change(netdev, &addr); + } - eth_commit_mac_addr_change(netdev, &addr); netdev_dbg(lif->netdev, "adding station MAC addr %pM\n", netdev->dev_addr); ionic_lif_addr(lif, netdev->dev_addr, true); @@ -2421,9 +2429,11 @@ static int ionic_lif_init(struct ionic_lif *lif) if (err) goto err_out_notifyq_deinit; - err = ionic_rx_filters_init(lif); - if (err) - goto err_out_notifyq_deinit; + if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { + err = ionic_rx_filters_init(lif); + if (err) + goto err_out_notifyq_deinit; + } err = ionic_station_set(lif); if (err) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 588c62e9add7..3ed150512091 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -6,7 +6,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/utsname.h> -#include <linux/vermagic.h> +#include <generated/utsrelease.h> #include "ionic.h" #include "ionic_bus.h" diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index 7a093f148ee5..80eeb7696e01 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -2,6 +2,7 @@ /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ #include <linux/netdevice.h> +#include <linux/dynamic_debug.h> #include <linux/etherdevice.h> #include "ionic.h" @@ -17,17 +18,49 @@ void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f) devm_kfree(dev, f); } -int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f) +void ionic_rx_filter_replay(struct ionic_lif *lif) { - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_del = { - .opcode = IONIC_CMD_RX_FILTER_DEL, - .filter_id = cpu_to_le32(f->filter_id), - }, - }; - - return ionic_adminq_post_wait(lif, &ctx); + struct ionic_rx_filter_add_cmd *ac; + struct ionic_admin_ctx ctx; + struct ionic_rx_filter *f; + struct hlist_head *head; + struct hlist_node *tmp; + unsigned int i; + int err; + + ac = &ctx.cmd.rx_filter_add; + + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + head = &lif->rx_filters.by_id[i]; + hlist_for_each_entry_safe(f, tmp, head, by_id) { + ctx.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work); + memcpy(ac, &f->cmd, sizeof(f->cmd)); + dev_dbg(&lif->netdev->dev, "replay filter command:\n"); + dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1, + &ctx.cmd, sizeof(ctx.cmd), true); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) { + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_info(lif->netdev, "Replay failed - %d: vlan %d\n", + err, + le16_to_cpu(ac->vlan.vlan)); + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_info(lif->netdev, "Replay failed - %d: mac %pM\n", + err, ac->mac.addr); + break; + case IONIC_RX_FILTER_MATCH_MAC_VLAN: + netdev_info(lif->netdev, "Replay failed - %d: vlan %d mac %pM\n", + err, + le16_to_cpu(ac->vlan.vlan), + ac->mac.addr); + break; + } + } + } + } } int ionic_rx_filters_init(struct ionic_lif *lif) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h index b6aec9c19918..cf8f4c0a961c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h @@ -24,7 +24,7 @@ struct ionic_rx_filters { }; void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f); -int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f); +void ionic_rx_filter_replay(struct ionic_lif *lif); int ionic_rx_filters_init(struct ionic_lif *lif); void ionic_rx_filters_deinit(struct ionic_lif *lif); int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 38a65b984e47..7119a18af19e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1972,7 +1972,7 @@ static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn) return 0; if (QED_IS_ROCE_PERSONALITY(p_hwfn)) { - p_hwfn->hw_info.multi_tc_roce_en = 0; + p_hwfn->hw_info.multi_tc_roce_en = false; DP_NOTICE(p_hwfn, "multi-tc roce was disabled to reduce requested amount of pqs\n"); if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ)) @@ -4392,7 +4392,7 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, } if (QED_IS_ROCE_PERSONALITY(p_hwfn)) - p_hwfn->hw_info.multi_tc_roce_en = 1; + p_hwfn->hw_info.multi_tc_roce_en = true; p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2; p_hwfn->hw_info.num_active_tc = 1; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 037e5978787e..4afd8572ada6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2331,7 +2331,7 @@ static void qed_ll2_register_cb_ops(struct qed_dev *cdev, cdev->ll2->cb_cookie = cookie; } -struct qed_ll2_cbs ll2_cbs = { +static struct qed_ll2_cbs ll2_cbs = { .rx_comp_cb = &qed_ll2b_complete_rx_packet, .rx_release_cb = &qed_ll2b_release_rx_packet, .tx_comp_cb = &qed_ll2b_complete_tx_packet, diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 96356e897c80..38a1d26ca9db 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -49,6 +49,7 @@ #include <linux/qed/qed_if.h> #include <linux/qed/qed_ll2_if.h> #include <net/devlink.h> +#include <linux/aer.h> #include "qed.h" #include "qed_sriov.h" @@ -129,6 +130,8 @@ static void qed_free_pci(struct qed_dev *cdev) { struct pci_dev *pdev = cdev->pdev; + pci_disable_pcie_error_reporting(pdev); + if (cdev->doorbells && cdev->db_size) iounmap(cdev->doorbells); if (cdev->regview) @@ -231,6 +234,12 @@ static int qed_init_pci(struct qed_dev *cdev, struct pci_dev *pdev) return -ENOMEM; } + /* AER (Advanced Error reporting) configuration */ + rc = pci_enable_pcie_error_reporting(pdev); + if (rc) + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "Failed to configure PCIe AER [%d]\n", rc); + return 0; err2: diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 37e70562a964..475b89903f46 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -736,9 +736,9 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, p_ramrod = &p_ent->ramrod.roce_destroy_qp_resp; - p_ramrod_res = (struct roce_destroy_qp_resp_output_params *) - dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, sizeof(*p_ramrod_res), - &ramrod_res_phys, GFP_KERNEL); + p_ramrod_res = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, + sizeof(*p_ramrod_res), + &ramrod_res_phys, GFP_KERNEL); if (!p_ramrod_res) { rc = -ENOMEM; @@ -872,10 +872,10 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn, } /* Send a query responder ramrod to FW to get RQ-PSN and state */ - p_resp_ramrod_res = (struct roce_query_qp_resp_output_params *) - dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, - sizeof(*p_resp_ramrod_res), - &resp_ramrod_res_phys, GFP_KERNEL); + p_resp_ramrod_res = + dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, + sizeof(*p_resp_ramrod_res), + &resp_ramrod_res_phys, GFP_KERNEL); if (!p_resp_ramrod_res) { DP_NOTICE(p_hwfn, "qed query qp failed: cannot allocate memory (ramrod)\n"); @@ -920,8 +920,7 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn, } /* Send a query requester ramrod to FW to get SQ-PSN and state */ - p_req_ramrod_res = (struct roce_query_qp_req_output_params *) - dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, + p_req_ramrod_res = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, sizeof(*p_req_ramrod_res), &req_ramrod_res_phys, GFP_KERNEL); diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 234c6f30effb..1a708f95ce94 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -485,6 +485,7 @@ struct qede_fastpath { #define QEDE_SP_RECOVERY 0 #define QEDE_SP_RX_MODE 1 +#define QEDE_SP_AER 7 #ifdef CONFIG_RFS_ACCEL int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 34fa3917eb33..9b456198cb50 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -60,6 +60,7 @@ #include <net/ip6_checksum.h> #include <linux/bitops.h> #include <linux/vmalloc.h> +#include <linux/aer.h> #include "qede.h" #include "qede_ptp.h" @@ -124,6 +125,8 @@ static const struct pci_device_id qede_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, qede_pci_tbl); static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id); +static pci_ers_result_t +qede_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state); #define TX_TIMEOUT (5 * HZ) @@ -203,6 +206,10 @@ static int qede_sriov_configure(struct pci_dev *pdev, int num_vfs_param) } #endif +static const struct pci_error_handlers qede_err_handler = { + .error_detected = qede_io_error_detected, +}; + static struct pci_driver qede_pci_driver = { .name = "qede", .id_table = qede_pci_tbl, @@ -212,6 +219,7 @@ static struct pci_driver qede_pci_driver = { #ifdef CONFIG_QED_SRIOV .sriov_configure = qede_sriov_configure, #endif + .err_handler = &qede_err_handler, }; static struct qed_eth_cb_ops qede_ll_ops = { @@ -974,7 +982,8 @@ static void qede_sp_task(struct work_struct *work) /* SRIOV must be disabled outside the lock to avoid a deadlock. * The recovery of the active VFs is currently not supported. */ - qede_sriov_configure(edev->pdev, 0); + if (pci_num_vf(edev->pdev)) + qede_sriov_configure(edev->pdev, 0); #endif qede_lock(edev); qede_recovery_handler(edev); @@ -994,6 +1003,17 @@ static void qede_sp_task(struct work_struct *work) } #endif __qede_unlock(edev); + + if (test_and_clear_bit(QEDE_SP_AER, &edev->sp_flags)) { +#ifdef CONFIG_QED_SRIOV + /* SRIOV must be disabled outside the lock to avoid a deadlock. + * The recovery of the active VFs is currently not supported. + */ + if (pci_num_vf(edev->pdev)) + qede_sriov_configure(edev->pdev, 0); +#endif + edev->ops->common->recovery_process(edev->cdev); + } } static void qede_update_pf_params(struct qed_dev *cdev) @@ -2579,3 +2599,49 @@ static void qede_get_eth_tlv_data(void *dev, void *data) etlv->num_txqs_full_set = true; etlv->num_rxqs_full_set = true; } + +/** + * qede_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t +qede_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) +{ + struct net_device *dev = pci_get_drvdata(pdev); + struct qede_dev *edev = netdev_priv(dev); + + if (!edev) + return PCI_ERS_RESULT_NONE; + + DP_NOTICE(edev, "IO error detected [%d]\n", state); + + __qede_lock(edev); + if (edev->state == QEDE_STATE_RECOVERY) { + DP_NOTICE(edev, "Device already in the recovery state\n"); + __qede_unlock(edev); + return PCI_ERS_RESULT_NONE; + } + + /* PF handles the recovery of its VFs */ + if (IS_VF(edev)) { + DP_VERBOSE(edev, QED_MSG_IOV, + "VF recovery is handled by its PF\n"); + __qede_unlock(edev); + return PCI_ERS_RESULT_RECOVERED; + } + + /* Close OS Tx */ + netif_tx_disable(edev->ndev); + netif_carrier_off(edev->ndev); + + set_bit(QEDE_SP_AER, &edev->sp_flags); + schedule_delayed_work(&edev->sp_task, 0); + + __qede_unlock(edev); + + return PCI_ERS_RESULT_CAN_RECOVER; +} diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 134611aa2c9a..d838774af5a6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1880,12 +1880,6 @@ static inline void qlcnic_write_crb(struct qlcnic_adapter *adapter, char *buf, adapter->ahw->hw_ops->write_crb(adapter, buf, offset, size); } -static inline int qlcnic_hw_write_wx_2M(struct qlcnic_adapter *adapter, - ulong off, u32 data) -{ - return adapter->ahw->hw_ops->write_reg(adapter, off, data); -} - static inline int qlcnic_get_mac_address(struct qlcnic_adapter *adapter, u8 *mac, u8 function) { diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bf5bf05970a2..4c616701856a 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -75,6 +75,8 @@ #define R8169_TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc)) #define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc)) +#define OCP_STD_PHY_BASE 0xa400 + #define RTL_CFG_NO_GBIT 1 /* write/read MMIO register */ @@ -847,8 +849,6 @@ static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); } -#define OCP_STD_PHY_BASE 0xa400 - static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) { if (reg == 0x1f) { @@ -2391,12 +2391,12 @@ static void rtl_pll_power_up(struct rtl8169_private *tp) } phy_resume(tp->phydev); - /* give MAC/PHY some time to resume */ - msleep(20); } static void rtl_init_rxcfg(struct rtl8169_private *tp) { + u32 vlan; + switch (tp->mac_version) { case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17: @@ -2411,8 +2411,9 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) 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_61: - RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_VLAN_8125 | - RX_DMA_BURST); + /* VLAN flags are controlled by NETIF_F_HW_VLAN_CTAG_RX */ + vlan = RTL_R32(tp, RxConfig) & RX_VLAN_8125; + RTL_W32(tp, RxConfig, vlan | RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; default: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); @@ -3881,12 +3882,6 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) return 0; } -static inline void rtl8169_make_unusable_by_asic(struct RxDesc *desc) -{ - desc->addr = cpu_to_le64(0x0badbadbadbadbadull); - desc->opts1 &= ~cpu_to_le32(DescOwn | RsvdMask); -} - static inline void rtl8169_mark_to_asic(struct RxDesc *desc) { u32 eor = le32_to_cpu(desc->opts1) & RingEnd; @@ -3934,15 +3929,11 @@ static void rtl8169_rx_clear(struct rtl8169_private *tp) R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); __free_pages(tp->Rx_databuff[i], get_order(R8169_RX_BUF_SIZE)); tp->Rx_databuff[i] = NULL; - rtl8169_make_unusable_by_asic(tp->RxDescArray + i); + tp->RxDescArray[i].addr = 0; + tp->RxDescArray[i].opts1 = 0; } } -static inline void rtl8169_mark_as_last_descriptor(struct RxDesc *desc) -{ - desc->opts1 |= cpu_to_le32(RingEnd); -} - static int rtl8169_rx_fill(struct rtl8169_private *tp) { unsigned int i; @@ -3958,7 +3949,8 @@ static int rtl8169_rx_fill(struct rtl8169_private *tp) tp->Rx_databuff[i] = data; } - rtl8169_mark_as_last_descriptor(tp->RxDescArray + NUM_RX_DESC - 1); + /* mark as last descriptor in the ring */ + tp->RxDescArray[NUM_RX_DESC - 1].opts1 |= cpu_to_le32(RingEnd); return 0; } @@ -4124,25 +4116,20 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, struct sk_buff *skb, u32 *opts) { u32 transport_offset = (u32)skb_transport_offset(skb); - u32 mss = skb_shinfo(skb)->gso_size; + struct skb_shared_info *shinfo = skb_shinfo(skb); + u32 mss = shinfo->gso_size; if (mss) { - switch (vlan_get_protocol(skb)) { - case htons(ETH_P_IP): + if (shinfo->gso_type & SKB_GSO_TCPV4) { opts[0] |= TD1_GTSENV4; - break; - - case htons(ETH_P_IPV6): + } else if (shinfo->gso_type & SKB_GSO_TCPV6) { if (skb_cow_head(skb, 0)) return false; tcp_v6_gso_csum_prep(skb); opts[0] |= TD1_GTSENV6; - break; - - default: + } else { WARN_ON_ONCE(1); - break; } opts[0] |= transport_offset << GTTCPHO_SHIFT; @@ -4262,8 +4249,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd_first->opts1 |= cpu_to_le32(DescOwn | FirstFrag); - /* Force all memory writes to complete before notifying device */ - wmb(); + /* rtl_tx needs to see descriptor changes before updated tp->cur_tx */ + smp_wmb(); tp->cur_tx += frags + 1; @@ -4308,6 +4295,37 @@ err_stop_0: return NETDEV_TX_BUSY; } +static unsigned int rtl_last_frag_len(struct sk_buff *skb) +{ + struct skb_shared_info *info = skb_shinfo(skb); + unsigned int nr_frags = info->nr_frags; + + if (!nr_frags) + return UINT_MAX; + + return skb_frag_size(info->frags + nr_frags - 1); +} + +/* Workaround for hw issues with TSO on RTL8168evl */ +static netdev_features_t rtl8168evl_fix_tso(struct sk_buff *skb, + netdev_features_t features) +{ + /* IPv4 header has options field */ + if (vlan_get_protocol(skb) == htons(ETH_P_IP) && + ip_hdrlen(skb) > sizeof(struct iphdr)) + features &= ~NETIF_F_ALL_TSO; + + /* IPv4 TCP header has options field */ + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 && + tcp_hdrlen(skb) > sizeof(struct tcphdr)) + features &= ~NETIF_F_ALL_TSO; + + else if (rtl_last_frag_len(skb) <= 6) + features &= ~NETIF_F_ALL_TSO; + + return features; +} + static netdev_features_t rtl8169_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) @@ -4316,6 +4334,9 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb, struct rtl8169_private *tp = netdev_priv(dev); if (skb_is_gso(skb)) { + if (tp->mac_version == RTL_GIGA_MAC_VER_34) + features = rtl8168evl_fix_tso(skb, features); + if (transport_offset > GTTCPHO_MAX && rtl_chip_supports_csum_v2(tp)) features &= ~NETIF_F_ALL_TSO; @@ -5164,20 +5185,18 @@ static int r8169_mdio_register(struct rtl8169_private *tp) new_bus->read = r8169_mdio_read_reg; new_bus->write = r8169_mdio_write_reg; - ret = mdiobus_register(new_bus); + ret = devm_mdiobus_register(new_bus); if (ret) return ret; tp->phydev = mdiobus_get_phy(new_bus, 0); if (!tp->phydev) { - mdiobus_unregister(new_bus); return -ENODEV; } else if (!tp->phydev->drv) { /* Most chip versions fail with the genphy driver. * Therefore ensure that the dedicated PHY driver is loaded. */ dev_err(&pdev->dev, "realtek.ko not loaded, maybe it needs to be added to initramfs?\n"); - mdiobus_unregister(new_bus); return -EUNATCH; } @@ -5189,8 +5208,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp) static void rtl_hw_init_8168g(struct rtl8169_private *tp) { - tp->ocp_base = OCP_STD_PHY_BASE; - RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); if (!rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42)) @@ -5215,8 +5232,6 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp) static void rtl_hw_init_8125(struct rtl8169_private *tp) { - tp->ocp_base = OCP_STD_PHY_BASE; - RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); if (!rtl_udelay_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42)) @@ -5353,6 +5368,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT); tp->supports_gmii = ent->driver_data == RTL_CFG_NO_GBIT ? 0 : 1; tp->eee_adv = -1; + tp->ocp_base = OCP_STD_PHY_BASE; /* Get the *optional* external "ether_clk" used on some boards */ rc = rtl_get_ether_clk(tp); @@ -5443,14 +5459,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; - dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | - NETIF_F_HIGHDMA; + dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - tp->cp_cmd |= RxChkSum; - /* RTL8125 uses register RxConfig for VLAN offloading config */ - if (!rtl_is_8125(tp)) - tp->cp_cmd |= RxVlan; /* * Pretend we are using VLANs; This bypasses a nasty bug where * Interrupts stop flowing on high load on 8110SCd controllers. @@ -5482,6 +5493,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->hw_features |= NETIF_F_RXALL; dev->hw_features |= NETIF_F_RXFCS; + /* configure chip for default features */ + rtl8169_set_features(dev, dev->features); + jumbo_max = rtl_jumbo_max(tp); if (jumbo_max) dev->max_mtu = jumbo_max; @@ -5507,7 +5521,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc = register_netdev(dev); if (rc) - goto err_mdio_unregister; + return rc; netif_info(tp, probe, dev, "%s, %pM, XID %03x, IRQ %d\n", rtl_chip_infos[chipset].name, dev->dev_addr, xid, @@ -5526,10 +5540,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pm_runtime_put_sync(&pdev->dev); return 0; - -err_mdio_unregister: - mdiobus_unregister(tp->phydev->mdio.bus); - return rc; } static struct pci_driver rtl8169_pci_driver = { diff --git a/drivers/net/ethernet/sgi/meth.h b/drivers/net/ethernet/sgi/meth.h index 5b145c6bad60..2ba15c263e8b 100644 --- a/drivers/net/ethernet/sgi/meth.h +++ b/drivers/net/ethernet/sgi/meth.h @@ -1,19 +1,3 @@ - -/* - * snull.h -- definitions for the network module - * - * Copyright (C) 2001 Alessandro Rubini and Jonathan Corbet - * Copyright (C) 2001 O'Reilly & Associates - * - * The source code in this file can be freely used, adapted, - * and redistributed in source or binary form, so long as an - * acknowledgment appears in derived source files. The citation - * should list that the code comes from the book "Linux Device - * Drivers" by Alessandro Rubini and Jonathan Corbet, published - * by O'Reilly & Associates. No warranty is attached; - * we cannot take responsibility for errors or fitness for use. - */ - /* version dependencies have been confined to a separate file */ /* Tunable parameters */ diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 6208a68a331d..127f75862962 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -473,6 +473,7 @@ struct mac_device_info { unsigned int xlgmac; unsigned int num_vlan; u32 vlan_filter[32]; + unsigned int promisc; }; struct stmmac_rx_routing { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 5419d4e478c0..2e4aaedb93f5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -5,8 +5,13 @@ #include <linux/clk-provider.h> #include <linux/pci.h> #include <linux/dmi.h> +#include "dwmac-intel.h" #include "stmmac.h" +struct intel_priv_data { + int mdio_adhoc_addr; /* mdio address for serdes & etc */ +}; + /* This struct is used to associate PCI Function of MAC controller on a board, * discovered via DMI, with the address of PHY connected to the MAC. The * negative value of the address means that MAC controller is not connected @@ -49,6 +54,172 @@ static int stmmac_pci_find_phy_addr(struct pci_dev *pdev, return -ENODEV; } +static int serdes_status_poll(struct stmmac_priv *priv, int phyaddr, + int phyreg, u32 mask, u32 val) +{ + unsigned int retries = 10; + int val_rd; + + do { + val_rd = mdiobus_read(priv->mii, phyaddr, phyreg); + if ((val_rd & mask) == (val & mask)) + return 0; + udelay(POLL_DELAY_US); + } while (--retries); + + return -ETIMEDOUT; +} + +static int intel_serdes_powerup(struct net_device *ndev, void *priv_data) +{ + struct intel_priv_data *intel_priv = priv_data; + struct stmmac_priv *priv = netdev_priv(ndev); + int serdes_phy_addr = 0; + u32 data = 0; + + if (!intel_priv->mdio_adhoc_addr) + return 0; + + serdes_phy_addr = intel_priv->mdio_adhoc_addr; + + /* assert clk_req */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data |= SERDES_PLL_CLK; + + mdiobus_write(priv->mii, serdes_phy_addr, + SERDES_GCR0, data); + + /* check for clk_ack assertion */ + data = serdes_status_poll(priv, serdes_phy_addr, + SERDES_GSR0, + SERDES_PLL_CLK, + SERDES_PLL_CLK); + + if (data) { + dev_err(priv->device, "Serdes PLL clk request timeout\n"); + return data; + } + + /* assert lane reset */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data |= SERDES_RST; + + mdiobus_write(priv->mii, serdes_phy_addr, + SERDES_GCR0, data); + + /* check for assert lane reset reflection */ + data = serdes_status_poll(priv, serdes_phy_addr, + SERDES_GSR0, + SERDES_RST, + SERDES_RST); + + if (data) { + dev_err(priv->device, "Serdes assert lane reset timeout\n"); + return data; + } + + /* move power state to P0 */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data &= ~SERDES_PWR_ST_MASK; + data |= SERDES_PWR_ST_P0 << SERDES_PWR_ST_SHIFT; + + mdiobus_write(priv->mii, serdes_phy_addr, + SERDES_GCR0, data); + + /* Check for P0 state */ + data = serdes_status_poll(priv, serdes_phy_addr, + SERDES_GSR0, + SERDES_PWR_ST_MASK, + SERDES_PWR_ST_P0 << SERDES_PWR_ST_SHIFT); + + if (data) { + dev_err(priv->device, "Serdes power state P0 timeout.\n"); + return data; + } + + return 0; +} + +static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data) +{ + struct intel_priv_data *intel_priv = intel_data; + struct stmmac_priv *priv = netdev_priv(ndev); + int serdes_phy_addr = 0; + u32 data = 0; + + if (!intel_priv->mdio_adhoc_addr) + return; + + serdes_phy_addr = intel_priv->mdio_adhoc_addr; + + /* move power state to P3 */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data &= ~SERDES_PWR_ST_MASK; + data |= SERDES_PWR_ST_P3 << SERDES_PWR_ST_SHIFT; + + mdiobus_write(priv->mii, serdes_phy_addr, + SERDES_GCR0, data); + + /* Check for P3 state */ + data = serdes_status_poll(priv, serdes_phy_addr, + SERDES_GSR0, + SERDES_PWR_ST_MASK, + SERDES_PWR_ST_P3 << SERDES_PWR_ST_SHIFT); + + if (data) { + dev_err(priv->device, "Serdes power state P3 timeout\n"); + return; + } + + /* de-assert clk_req */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data &= ~SERDES_PLL_CLK; + + mdiobus_write(priv->mii, serdes_phy_addr, + SERDES_GCR0, data); + + /* check for clk_ack de-assert */ + data = serdes_status_poll(priv, serdes_phy_addr, + SERDES_GSR0, + SERDES_PLL_CLK, + (u32)~SERDES_PLL_CLK); + + if (data) { + dev_err(priv->device, "Serdes PLL clk de-assert timeout\n"); + return; + } + + /* de-assert lane reset */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data &= ~SERDES_RST; + + mdiobus_write(priv->mii, serdes_phy_addr, + SERDES_GCR0, data); + + /* check for de-assert lane reset reflection */ + data = serdes_status_poll(priv, serdes_phy_addr, + SERDES_GSR0, + SERDES_RST, + (u32)~SERDES_RST); + + if (data) { + dev_err(priv->device, "Serdes de-assert lane reset timeout\n"); + return; + } +} + static void common_default_data(struct plat_stmmacenet_data *plat) { plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ @@ -189,6 +360,9 @@ static int ehl_sgmii_data(struct pci_dev *pdev, plat->phy_addr = 0; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->serdes_powerup = intel_serdes_powerup; + plat->serdes_powerdown = intel_serdes_powerdown; + return ehl_common_data(pdev, plat); } @@ -233,6 +407,8 @@ static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->serdes_powerup = intel_serdes_powerup; + plat->serdes_powerdown = intel_serdes_powerdown; return ehl_pse0_common_data(pdev, plat); } @@ -263,6 +439,8 @@ static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->serdes_powerup = intel_serdes_powerup; + plat->serdes_powerdown = intel_serdes_powerdown; return ehl_pse1_common_data(pdev, plat); } @@ -291,6 +469,8 @@ static int tgl_sgmii_data(struct pci_dev *pdev, plat->bus_id = 1; plat->phy_addr = 0; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->serdes_powerup = intel_serdes_powerup; + plat->serdes_powerdown = intel_serdes_powerdown; return tgl_common_data(pdev, plat); } @@ -417,11 +597,17 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct stmmac_pci_info *info = (struct stmmac_pci_info *)id->driver_data; + struct intel_priv_data *intel_priv; struct plat_stmmacenet_data *plat; struct stmmac_resources res; int i; int ret; + intel_priv = devm_kzalloc(&pdev->dev, sizeof(*intel_priv), + GFP_KERNEL); + if (!intel_priv) + return -ENOMEM; + plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) return -ENOMEM; @@ -457,6 +643,9 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, pci_set_master(pdev); + plat->bsp_priv = intel_priv; + intel_priv->mdio_adhoc_addr = 0x15; + ret = info->setup(pdev, plat); if (ret) return ret; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h new file mode 100644 index 000000000000..e723096c0b15 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020, Intel Corporation + * DWMAC Intel header file + */ + +#ifndef __DWMAC_INTEL_H__ +#define __DWMAC_INTEL_H__ + +#define POLL_DELAY_US 8 + +/* SERDES Register */ +#define SERDES_GSR0 0x5 /* Global Status Reg0 */ +#define SERDES_GCR0 0xb /* Global Configuration Reg0 */ + +/* SERDES defines */ +#define SERDES_PLL_CLK BIT(0) /* PLL clk valid signal */ +#define SERDES_RST BIT(2) /* Serdes Reset */ +#define SERDES_PWR_ST_MASK GENMASK(6, 4) /* Serdes Power state*/ +#define SERDES_PWR_ST_SHIFT 4 +#define SERDES_PWR_ST_P0 0x0 +#define SERDES_PWR_ST_P3 0x3 + +#endif /* __DWMAC_INTEL_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 0e2fa14f1423..a3934ca6a043 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -119,6 +119,7 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) { .div = 5, .val = 5, }, { .div = 6, .val = 6, }, { .div = 7, .val = 7, }, + { /* end of array */ } }; clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index e0212d2fc2a1..70d41783329d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -241,6 +241,8 @@ static int socfpga_set_phy_mode_common(int phymode, u32 *val) switch (phymode) { case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: *val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII; break; case PHY_INTERFACE_MODE_MII: @@ -289,16 +291,19 @@ static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac) phymode == PHY_INTERFACE_MODE_MII || phymode == PHY_INTERFACE_MODE_GMII || phymode == PHY_INTERFACE_MODE_SGMII) { - ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2); regmap_read(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG, &module); module |= (SYSMGR_FPGAGRP_MODULE_EMAC << (reg_shift / 2)); regmap_write(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG, module); - } else { - ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2)); } + if (dwmac->f2h_ptp_ref_clk) + ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2); + else + ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << + (reg_shift / 2)); + regmap_write(sys_mgr_base_addr, reg_offset, ctrl); /* Deassert reset for the phy configuration to be sampled by diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 7d40760e9ba8..0e1ca2cba3c7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -150,6 +150,8 @@ static int sun7i_gmac_probe(struct platform_device *pdev) plat_dat->init = sun7i_gmac_init; plat_dat->exit = sun7i_gmac_exit; plat_dat->fix_mac_speed = sun7i_fix_speed; + plat_dat->tx_fifo_size = 4096; + plat_dat->rx_fifo_size = 16384; ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 28cac28253b8..61f3249bd724 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -90,6 +90,7 @@ #define GMAC_VLAN_CSVL BIT(19) #define GMAC_VLAN_VLC GENMASK(17, 16) #define GMAC_VLAN_VLC_SHIFT 16 +#define GMAC_VLAN_VLHT GENMASK(15, 0) /* MAC VLAN Tag */ #define GMAC_VLAN_TAG_VID GENMASK(15, 0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 39692d15d80c..ecd834e0e121 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -450,6 +450,12 @@ static int dwmac4_add_hw_vlan_rx_fltr(struct net_device *dev, if (vid > 4095) return -EINVAL; + if (hw->promisc) { + netdev_err(dev, + "Adding VLAN in promisc mode not supported\n"); + return -EPERM; + } + /* Single Rx VLAN Filter */ if (hw->num_vlan == 1) { /* For single VLAN filter, VID 0 means VLAN promiscuous */ @@ -499,6 +505,12 @@ static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev, { int i, ret = 0; + if (hw->promisc) { + netdev_err(dev, + "Deleting VLAN in promisc mode not supported\n"); + return -EPERM; + } + /* Single Rx VLAN Filter */ if (hw->num_vlan == 1) { if ((hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) == vid) { @@ -523,9 +535,45 @@ static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev, return ret; } +static void dwmac4_vlan_promisc_enable(struct net_device *dev, + struct mac_device_info *hw) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + u32 hash; + u32 val; + int i; + + /* Single Rx VLAN Filter */ + if (hw->num_vlan == 1) { + dwmac4_write_single_vlan(dev, 0); + return; + } + + /* Extended Rx VLAN Filter Enable */ + for (i = 0; i < hw->num_vlan; i++) { + if (hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN) { + val = hw->vlan_filter[i] & ~GMAC_VLAN_TAG_DATA_VEN; + dwmac4_write_vlan_filter(dev, hw, i, val); + } + } + + hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE); + if (hash & GMAC_VLAN_VLHT) { + value = readl(ioaddr + GMAC_VLAN_TAG); + if (value & GMAC_VLAN_VTHM) { + value &= ~GMAC_VLAN_VTHM; + writel(value, ioaddr + GMAC_VLAN_TAG); + } + } +} + static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev, struct mac_device_info *hw) { + void __iomem *ioaddr = hw->pcsr; + u32 value; + u32 hash; u32 val; int i; @@ -542,6 +590,13 @@ static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev, dwmac4_write_vlan_filter(dev, hw, i, val); } } + + hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE); + if (hash & GMAC_VLAN_VLHT) { + value = readl(ioaddr + GMAC_VLAN_TAG); + value |= GMAC_VLAN_VTHM; + writel(value, ioaddr + GMAC_VLAN_TAG); + } } static void dwmac4_set_filter(struct mac_device_info *hw, @@ -624,6 +679,18 @@ static void dwmac4_set_filter(struct mac_device_info *hw, value |= GMAC_PACKET_FILTER_VTFE; writel(value, ioaddr + GMAC_PACKET_FILTER); + + if (dev->flags & IFF_PROMISC) { + if (!hw->promisc) { + hw->promisc = 1; + dwmac4_vlan_promisc_enable(dev, hw); + } + } else { + if (hw->promisc) { + hw->promisc = 0; + dwmac4_restore_hw_vlan_rx_fltr(dev, hw); + } + } } static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index fcf080243a0f..d291612eeafb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -27,12 +27,16 @@ static void config_sub_second_increment(void __iomem *ioaddr, unsigned long data; u32 reg_value; - /* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second - * formula = (1/ptp_clock) * 1000000000 - * where ptp_clock is 50MHz if fine method is used to update system + /* For GMAC3.x, 4.x versions, in "fine adjustement mode" set sub-second + * increment to twice the number of nanoseconds of a clock cycle. + * The calculation of the default_addend value by the caller will set it + * to mid-range = 2^31 when the remainder of this division is zero, + * which will make the accumulator overflow once every 2 ptp_clock + * cycles, adding twice the number of nanoseconds of a clock cycle : + * 2000000000ULL / ptp_clock. */ if (value & PTP_TCR_TSCFUPDT) - data = (1000000000ULL / 50000000); + data = (2000000000ULL / ptp_clock); else data = (1000000000ULL / ptp_clock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e6898fd5223f..565da6498c84 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4986,6 +4986,14 @@ int stmmac_dvr_probe(struct device *device, goto error_netdev_register; } + if (priv->plat->serdes_powerup) { + ret = priv->plat->serdes_powerup(ndev, + priv->plat->bsp_priv); + + if (ret < 0) + return ret; + } + #ifdef CONFIG_DEBUG_FS stmmac_init_fs(ndev); #endif @@ -5029,6 +5037,9 @@ int stmmac_dvr_remove(struct device *dev) stmmac_stop_all_dma(priv); + if (priv->plat->serdes_powerdown) + priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv); + stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); @@ -5081,6 +5092,9 @@ int stmmac_suspend(struct device *dev) /* Stop TX/RX DMA */ stmmac_stop_all_dma(priv); + if (priv->plat->serdes_powerdown) + priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv); + /* Enable Power down mode by programming the PMT regs */ if (device_may_wakeup(priv->device)) { stmmac_pmt(priv, priv->hw, priv->wolopts); @@ -5143,6 +5157,7 @@ int stmmac_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); + int ret; if (!netif_running(ndev)) return 0; @@ -5170,6 +5185,14 @@ int stmmac_resume(struct device *dev) stmmac_mdio_reset(priv->mii); } + if (priv->plat->serdes_powerup) { + ret = priv->plat->serdes_powerup(ndev, + priv->plat->bsp_priv); + + if (ret < 0) + return ret; + } + netif_device_attach(ndev); mutex_lock(&priv->lock); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index e6d1aa882fa5..3ee6ab104cb9 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -5059,7 +5059,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (cp->cas_flags & CAS_FLAG_SATURN) cas_saturn_firmware_init(cp); - cp->init_block = (struct cas_init_block *) + cp->init_block = pci_alloc_consistent(pdev, sizeof(struct cas_init_block), &cp->block_dvma); if (!cp->init_block) { diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index f71c15c39492..2bf56733ba94 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1372,7 +1372,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) err: i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common); if (i) { - dev_err(dev, "failed to add free_tx_chns action %d", i); + dev_err(dev, "Failed to add free_tx_chns action %d\n", i); return i; } @@ -1481,7 +1481,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) err: i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common); if (i) { - dev_err(dev, "failed to add free_rx_chns action %d", i); + dev_err(dev, "Failed to add free_rx_chns action %d\n", i); return i; } @@ -1691,7 +1691,7 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common) ret = devm_add_action_or_reset(dev, am65_cpsw_pcpu_stats_free, ndev_priv->stats); if (ret) { - dev_err(dev, "failed to add percpu stat free action %d", ret); + dev_err(dev, "Failed to add percpu stat free action %d\n", ret); return ret; } diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index c2c5bf87da01..09f98fa2fb4e 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1569,6 +1569,12 @@ static int cpsw_probe(struct platform_device *pdev) return irq; cpsw->irqs_table[1] = irq; + /* get misc irq*/ + irq = platform_get_irq(pdev, 3); + if (irq <= 0) + return irq; + cpsw->misc_irq = irq; + /* * This may be required here for child devices. */ @@ -1703,6 +1709,21 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_unregister_netdev_ret; } + if (!cpsw->cpts) + goto skip_cpts; + + ret = devm_request_irq(&pdev->dev, cpsw->misc_irq, cpsw_misc_interrupt, + 0, dev_name(&pdev->dev), cpsw); + if (ret < 0) { + dev_err(dev, "error attaching misc irq (%d)\n", ret); + goto clean_unregister_netdev_ret; + } + + /* Enable misc CPTS evnt_pend IRQ */ + cpts_set_irqpoll(cpsw->cpts, false); + writel(0x10, &cpsw->wr_regs->misc_en); + +skip_cpts: cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d, pool size %d)\n", &ss_res->start, cpsw->irqs_table[0], descs_pool_size); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 9209e613257d..33c8dd686206 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1896,6 +1896,11 @@ static int cpsw_probe(struct platform_device *pdev) return irq; cpsw->irqs_table[1] = irq; + irq = platform_get_irq_byname(pdev, "misc"); + if (irq <= 0) + return irq; + cpsw->misc_irq = irq; + platform_set_drvdata(pdev, cpsw); /* This may be required here for child devices. */ pm_runtime_enable(dev); @@ -1975,6 +1980,21 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_unregister_netdev; } + if (!cpsw->cpts) + goto skip_cpts; + + ret = devm_request_irq(dev, cpsw->misc_irq, cpsw_misc_interrupt, + 0, dev_name(&pdev->dev), cpsw); + if (ret < 0) { + dev_err(dev, "error attaching misc irq (%d)\n", ret); + goto clean_unregister_netdev; + } + + /* Enable misc CPTS evnt_pend IRQ */ + cpts_set_irqpoll(cpsw->cpts, false); + writel(0x10, &cpsw->wr_regs->misc_en); + +skip_cpts: ret = cpsw_register_notifiers(cpsw); if (ret) goto clean_unregister_netdev; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 97a058ca60ac..9d098c802c6d 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -28,6 +28,8 @@ #include "cpsw_sl.h" #include "davinci_cpdma.h" +#define CPTS_N_ETX_TS 4 + int (*cpsw_slave_index)(struct cpsw_common *cpsw, struct cpsw_priv *priv); void cpsw_intr_enable(struct cpsw_common *cpsw) @@ -112,6 +114,18 @@ irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +irqreturn_t cpsw_misc_interrupt(int irq, void *dev_id) +{ + struct cpsw_common *cpsw = dev_id; + + writel(0, &cpsw->wr_regs->misc_en); + cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_MISC); + cpts_misc_interrupt(cpsw->cpts); + writel(0x10, &cpsw->wr_regs->misc_en); + + return IRQ_HANDLED; +} + int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget) { struct cpsw_common *cpsw = napi_to_cpsw(napi_tx); @@ -522,7 +536,8 @@ int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs, if (!cpts_node) cpts_node = cpsw->dev->of_node; - cpsw->cpts = cpts_create(cpsw->dev, cpts_regs, cpts_node); + cpsw->cpts = cpts_create(cpsw->dev, cpts_regs, cpts_node, + CPTS_N_ETX_TS); if (IS_ERR(cpsw->cpts)) { ret = PTR_ERR(cpsw->cpts); cpdma_ctlr_destroy(cpsw->dma); diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index b8d7b924ee3d..bf4e179b4ca4 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -350,6 +350,7 @@ struct cpsw_common { bool rx_irq_disabled; bool tx_irq_disabled; u32 irqs_table[IRQ_NUM]; + int misc_irq; struct cpts *cpts; struct devlink *devlink; int rx_ch_num, tx_ch_num; @@ -442,6 +443,7 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, struct page *page, int port); irqreturn_t cpsw_tx_interrupt(int irq, void *dev_id); irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id); +irqreturn_t cpsw_misc_interrupt(int irq, void *dev_id); int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget); int cpsw_tx_poll(struct napi_struct *napi_tx, int budget); int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget); diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 729ce09dded9..7c55d395de2c 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -21,16 +21,21 @@ #include "cpts.h" #define CPTS_SKB_TX_WORK_TIMEOUT 1 /* jiffies */ +#define CPTS_SKB_RX_TX_TMO 100 /*ms */ +#define CPTS_EVENT_RX_TX_TIMEOUT (100) /* ms */ struct cpts_skb_cb_data { + u32 skb_mtype_seqid; unsigned long tmo; }; #define cpts_read32(c, r) readl_relaxed(&c->reg->r) #define cpts_write32(c, v, r) writel_relaxed(v, &c->reg->r) -static int cpts_match(struct sk_buff *skb, unsigned int ptp_class, - u16 ts_seqid, u8 ts_msgtype); +static int cpts_event_port(struct cpts_event *event) +{ + return (event->high >> PORT_NUMBER_SHIFT) & PORT_NUMBER_MASK; +} static int event_expired(struct cpts_event *event) { @@ -71,7 +76,7 @@ static int cpts_purge_events(struct cpts *cpts) } if (removed) - pr_debug("cpts: event pool cleaned up %d\n", removed); + dev_dbg(cpts->dev, "cpts: event pool cleaned up %d\n", removed); return removed ? 0 : -1; } @@ -94,132 +99,126 @@ static void cpts_purge_txq(struct cpts *cpts) dev_dbg(cpts->dev, "txq cleaned up %d\n", removed); } -static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event) -{ - struct sk_buff *skb, *tmp; - u16 seqid; - u8 mtype; - bool found = false; - - mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK; - seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK; - - /* no need to grab txq.lock as access is always done under cpts->lock */ - skb_queue_walk_safe(&cpts->txq, skb, tmp) { - struct skb_shared_hwtstamps ssh; - unsigned int class = ptp_classify_raw(skb); - struct cpts_skb_cb_data *skb_cb = - (struct cpts_skb_cb_data *)skb->cb; - - if (cpts_match(skb, class, seqid, mtype)) { - u64 ns = timecounter_cyc2time(&cpts->tc, event->low); - - memset(&ssh, 0, sizeof(ssh)); - ssh.hwtstamp = ns_to_ktime(ns); - skb_tstamp_tx(skb, &ssh); - found = true; - __skb_unlink(skb, &cpts->txq); - dev_consume_skb_any(skb); - dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n", - mtype, seqid); - break; - } - - if (time_after(jiffies, skb_cb->tmo)) { - /* timeout any expired skbs over 1s */ - dev_dbg(cpts->dev, "expiring tx timestamp from txq\n"); - __skb_unlink(skb, &cpts->txq); - dev_consume_skb_any(skb); - } - } - - return found; -} - /* * Returns zero if matching event type was found. */ static int cpts_fifo_read(struct cpts *cpts, int match) { + struct ptp_clock_event pevent; + bool need_schedule = false; + struct cpts_event *event; + unsigned long flags; int i, type = -1; u32 hi, lo; - struct cpts_event *event; + + spin_lock_irqsave(&cpts->lock, flags); for (i = 0; i < CPTS_FIFO_DEPTH; i++) { if (cpts_fifo_pop(cpts, &hi, &lo)) break; if (list_empty(&cpts->pool) && cpts_purge_events(cpts)) { - pr_err("cpts: event pool empty\n"); - return -1; + dev_warn(cpts->dev, "cpts: event pool empty\n"); + break; } event = list_first_entry(&cpts->pool, struct cpts_event, list); - event->tmo = jiffies + 2; event->high = hi; event->low = lo; + event->timestamp = timecounter_cyc2time(&cpts->tc, event->low); type = event_type(event); + + dev_dbg(cpts->dev, "CPTS_EV: %d high:%08X low:%08x\n", + type, event->high, event->low); switch (type) { - case CPTS_EV_TX: - if (cpts_match_tx_ts(cpts, event)) { - /* if the new event matches an existing skb, - * then don't queue it - */ - break; - } - /* fall through */ case CPTS_EV_PUSH: + WRITE_ONCE(cpts->cur_timestamp, lo); + timecounter_read(&cpts->tc); + if (cpts->mult_new) { + cpts->cc.mult = cpts->mult_new; + cpts->mult_new = 0; + } + if (!cpts->irq_poll) + complete(&cpts->ts_push_complete); + break; + case CPTS_EV_TX: case CPTS_EV_RX: + event->tmo = jiffies + + msecs_to_jiffies(CPTS_EVENT_RX_TX_TIMEOUT); + list_del_init(&event->list); list_add_tail(&event->list, &cpts->events); + need_schedule = true; break; case CPTS_EV_ROLL: case CPTS_EV_HALF: + break; case CPTS_EV_HW: + pevent.timestamp = event->timestamp; + pevent.type = PTP_CLOCK_EXTTS; + pevent.index = cpts_event_port(event) - 1; + ptp_clock_event(cpts->clock, &pevent); break; default: - pr_err("cpts: unknown event type\n"); + dev_err(cpts->dev, "cpts: unknown event type\n"); break; } if (type == match) break; } + + spin_unlock_irqrestore(&cpts->lock, flags); + + if (!cpts->irq_poll && need_schedule) + ptp_schedule_worker(cpts->clock, 0); + return type == match ? 0 : -1; } +void cpts_misc_interrupt(struct cpts *cpts) +{ + cpts_fifo_read(cpts, -1); +} +EXPORT_SYMBOL_GPL(cpts_misc_interrupt); + static u64 cpts_systim_read(const struct cyclecounter *cc) { - u64 val = 0; - struct cpts_event *event; - struct list_head *this, *next; struct cpts *cpts = container_of(cc, struct cpts, cc); + return READ_ONCE(cpts->cur_timestamp); +} + +static void cpts_update_cur_time(struct cpts *cpts, int match, + struct ptp_system_timestamp *sts) +{ + unsigned long flags; + + reinit_completion(&cpts->ts_push_complete); + + /* use spin_lock_irqsave() here as it has to run very fast */ + spin_lock_irqsave(&cpts->lock, flags); + ptp_read_system_prets(sts); cpts_write32(cpts, TS_PUSH, ts_push); - if (cpts_fifo_read(cpts, CPTS_EV_PUSH)) - pr_err("cpts: unable to obtain a time stamp\n"); + cpts_read32(cpts, ts_push); + ptp_read_system_postts(sts); + spin_unlock_irqrestore(&cpts->lock, flags); - list_for_each_safe(this, next, &cpts->events) { - event = list_entry(this, struct cpts_event, list); - if (event_type(event) == CPTS_EV_PUSH) { - list_del_init(&event->list); - list_add(&event->list, &cpts->pool); - val = event->low; - break; - } - } + if (cpts->irq_poll && cpts_fifo_read(cpts, match) && match != -1) + dev_err(cpts->dev, "cpts: unable to obtain a time stamp\n"); - return val; + if (!cpts->irq_poll && + !wait_for_completion_timeout(&cpts->ts_push_complete, HZ)) + dev_err(cpts->dev, "cpts: obtain a time stamp timeout\n"); } /* PTP clock operations */ static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) { - u64 adj; - u32 diff, mult; - int neg_adj = 0; - unsigned long flags; struct cpts *cpts = container_of(ptp, struct cpts, info); + int neg_adj = 0; + u32 diff, mult; + u64 adj; if (ppb < 0) { neg_adj = 1; @@ -230,38 +229,40 @@ static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) adj *= ppb; diff = div_u64(adj, 1000000000ULL); - spin_lock_irqsave(&cpts->lock, flags); + mutex_lock(&cpts->ptp_clk_mutex); - timecounter_read(&cpts->tc); + cpts->mult_new = neg_adj ? mult - diff : mult + diff; - cpts->cc.mult = neg_adj ? mult - diff : mult + diff; - - spin_unlock_irqrestore(&cpts->lock, flags); + cpts_update_cur_time(cpts, CPTS_EV_PUSH, NULL); + mutex_unlock(&cpts->ptp_clk_mutex); return 0; } static int cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { - unsigned long flags; struct cpts *cpts = container_of(ptp, struct cpts, info); - spin_lock_irqsave(&cpts->lock, flags); + mutex_lock(&cpts->ptp_clk_mutex); timecounter_adjtime(&cpts->tc, delta); - spin_unlock_irqrestore(&cpts->lock, flags); + mutex_unlock(&cpts->ptp_clk_mutex); return 0; } -static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +static int cpts_ptp_gettimeex(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) { - u64 ns; - unsigned long flags; struct cpts *cpts = container_of(ptp, struct cpts, info); + u64 ns; + + mutex_lock(&cpts->ptp_clk_mutex); + + cpts_update_cur_time(cpts, CPTS_EV_PUSH, sts); - spin_lock_irqsave(&cpts->lock, flags); ns = timecounter_read(&cpts->tc); - spin_unlock_irqrestore(&cpts->lock, flags); + mutex_unlock(&cpts->ptp_clk_mutex); *ts = ns_to_timespec64(ns); @@ -271,15 +272,38 @@ static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) static int cpts_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts) { - u64 ns; - unsigned long flags; struct cpts *cpts = container_of(ptp, struct cpts, info); + u64 ns; ns = timespec64_to_ns(ts); - spin_lock_irqsave(&cpts->lock, flags); + mutex_lock(&cpts->ptp_clk_mutex); timecounter_init(&cpts->tc, &cpts->cc, ns); - spin_unlock_irqrestore(&cpts->lock, flags); + mutex_unlock(&cpts->ptp_clk_mutex); + + return 0; +} + +static int cpts_extts_enable(struct cpts *cpts, u32 index, int on) +{ + u32 v; + + if (((cpts->hw_ts_enable & BIT(index)) >> index) == on) + return 0; + + mutex_lock(&cpts->ptp_clk_mutex); + + v = cpts_read32(cpts, control); + if (on) { + v |= BIT(8 + index); + cpts->hw_ts_enable |= BIT(index); + } else { + v &= ~BIT(8 + index); + cpts->hw_ts_enable &= ~BIT(index); + } + cpts_write32(cpts, v, control); + + mutex_unlock(&cpts->ptp_clk_mutex); return 0; } @@ -287,28 +311,120 @@ static int cpts_ptp_settime(struct ptp_clock_info *ptp, static int cpts_ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { + struct cpts *cpts = container_of(ptp, struct cpts, info); + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + return cpts_extts_enable(cpts, rq->extts.index, on); + default: + break; + } + return -EOPNOTSUPP; } +static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event) +{ + struct sk_buff_head txq_list; + struct sk_buff *skb, *tmp; + unsigned long flags; + bool found = false; + u32 mtype_seqid; + + mtype_seqid = event->high & + ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) | + (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) | + (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT)); + + __skb_queue_head_init(&txq_list); + + spin_lock_irqsave(&cpts->txq.lock, flags); + skb_queue_splice_init(&cpts->txq, &txq_list); + spin_unlock_irqrestore(&cpts->txq.lock, flags); + + skb_queue_walk_safe(&txq_list, skb, tmp) { + struct skb_shared_hwtstamps ssh; + struct cpts_skb_cb_data *skb_cb = + (struct cpts_skb_cb_data *)skb->cb; + + if (mtype_seqid == skb_cb->skb_mtype_seqid) { + memset(&ssh, 0, sizeof(ssh)); + ssh.hwtstamp = ns_to_ktime(event->timestamp); + skb_tstamp_tx(skb, &ssh); + found = true; + __skb_unlink(skb, &txq_list); + dev_consume_skb_any(skb); + dev_dbg(cpts->dev, "match tx timestamp mtype_seqid %08x\n", + mtype_seqid); + break; + } + + if (time_after(jiffies, skb_cb->tmo)) { + /* timeout any expired skbs over 1s */ + dev_dbg(cpts->dev, "expiring tx timestamp from txq\n"); + __skb_unlink(skb, &txq_list); + dev_consume_skb_any(skb); + } + } + + spin_lock_irqsave(&cpts->txq.lock, flags); + skb_queue_splice(&txq_list, &cpts->txq); + spin_unlock_irqrestore(&cpts->txq.lock, flags); + + return found; +} + +static void cpts_process_events(struct cpts *cpts) +{ + struct list_head *this, *next; + struct cpts_event *event; + LIST_HEAD(events_free); + unsigned long flags; + LIST_HEAD(events); + + spin_lock_irqsave(&cpts->lock, flags); + list_splice_init(&cpts->events, &events); + spin_unlock_irqrestore(&cpts->lock, flags); + + list_for_each_safe(this, next, &events) { + event = list_entry(this, struct cpts_event, list); + if (cpts_match_tx_ts(cpts, event) || + time_after(jiffies, event->tmo)) { + list_del_init(&event->list); + list_add(&event->list, &events_free); + } + } + + spin_lock_irqsave(&cpts->lock, flags); + list_splice_tail(&events, &cpts->events); + list_splice_tail(&events_free, &cpts->pool); + spin_unlock_irqrestore(&cpts->lock, flags); +} + static long cpts_overflow_check(struct ptp_clock_info *ptp) { struct cpts *cpts = container_of(ptp, struct cpts, info); unsigned long delay = cpts->ov_check_period; - struct timespec64 ts; unsigned long flags; + u64 ns; - spin_lock_irqsave(&cpts->lock, flags); - ts = ns_to_timespec64(timecounter_read(&cpts->tc)); + mutex_lock(&cpts->ptp_clk_mutex); + + cpts_update_cur_time(cpts, -1, NULL); + ns = timecounter_read(&cpts->tc); + + cpts_process_events(cpts); + spin_lock_irqsave(&cpts->txq.lock, flags); if (!skb_queue_empty(&cpts->txq)) { cpts_purge_txq(cpts); if (!skb_queue_empty(&cpts->txq)) delay = CPTS_SKB_TX_WORK_TIMEOUT; } - spin_unlock_irqrestore(&cpts->lock, flags); + spin_unlock_irqrestore(&cpts->txq.lock, flags); - pr_debug("cpts overflow check at %lld.%09ld\n", - (long long)ts.tv_sec, ts.tv_nsec); + dev_dbg(cpts->dev, "cpts overflow check at %lld\n", ns); + mutex_unlock(&cpts->ptp_clk_mutex); return (long)delay; } @@ -321,18 +437,21 @@ static const struct ptp_clock_info cpts_info = { .pps = 0, .adjfreq = cpts_ptp_adjfreq, .adjtime = cpts_ptp_adjtime, - .gettime64 = cpts_ptp_gettime, + .gettimex64 = cpts_ptp_gettimeex, .settime64 = cpts_ptp_settime, .enable = cpts_ptp_enable, .do_aux_work = cpts_overflow_check, }; -static int cpts_match(struct sk_buff *skb, unsigned int ptp_class, - u16 ts_seqid, u8 ts_msgtype) +static int cpts_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) { - u16 *seqid; - unsigned int offset = 0; + unsigned int ptp_class = ptp_classify_raw(skb); u8 *msgtype, *data = skb->data; + unsigned int offset = 0; + u16 *seqid; + + if (ptp_class == PTP_CLASS_NONE) + return 0; if (ptp_class & PTP_CLASS_VLAN) offset += VLAN_HLEN; @@ -360,25 +479,23 @@ static int cpts_match(struct sk_buff *skb, unsigned int ptp_class, msgtype = data + offset; seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID); + *mtype_seqid = (*msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT; + *mtype_seqid |= (ntohs(*seqid) & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT; - return (ts_msgtype == (*msgtype & 0xf) && ts_seqid == ntohs(*seqid)); + return 1; } -static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type) +static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, + int ev_type, u32 skb_mtype_seqid) { - u64 ns = 0; - struct cpts_event *event; struct list_head *this, *next; - unsigned int class = ptp_classify_raw(skb); + struct cpts_event *event; unsigned long flags; - u16 seqid; - u8 mtype; - - if (class == PTP_CLASS_NONE) - return 0; + u32 mtype_seqid; + u64 ns = 0; - spin_lock_irqsave(&cpts->lock, flags); cpts_fifo_read(cpts, -1); + spin_lock_irqsave(&cpts->lock, flags); list_for_each_safe(this, next, &cpts->events) { event = list_entry(this, struct cpts_event, list); if (event_expired(event)) { @@ -386,29 +503,19 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type) list_add(&event->list, &cpts->pool); continue; } - mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK; - seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK; - if (ev_type == event_type(event) && - cpts_match(skb, class, seqid, mtype)) { - ns = timecounter_cyc2time(&cpts->tc, event->low); + + mtype_seqid = event->high & + ((MESSAGE_TYPE_MASK << MESSAGE_TYPE_SHIFT) | + (SEQUENCE_ID_MASK << SEQUENCE_ID_SHIFT) | + (EVENT_TYPE_MASK << EVENT_TYPE_SHIFT)); + + if (mtype_seqid == skb_mtype_seqid) { + ns = event->timestamp; list_del_init(&event->list); list_add(&event->list, &cpts->pool); break; } } - - if (ev_type == CPTS_EV_TX && !ns) { - struct cpts_skb_cb_data *skb_cb = - (struct cpts_skb_cb_data *)skb->cb; - /* Not found, add frame to queue for processing later. - * The periodic FIFO check will handle this. - */ - skb_get(skb); - /* get the timestamp for timeouts */ - skb_cb->tmo = jiffies + msecs_to_jiffies(100); - __skb_queue_tail(&cpts->txq, skb); - ptp_schedule_worker(cpts->clock, 0); - } spin_unlock_irqrestore(&cpts->lock, flags); return ns; @@ -416,10 +523,21 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type) void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb) { - u64 ns; + struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb; struct skb_shared_hwtstamps *ssh; + int ret; + u64 ns; - ns = cpts_find_ts(cpts, skb, CPTS_EV_RX); + ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid); + if (!ret) + return; + + skb_cb->skb_mtype_seqid |= (CPTS_EV_RX << EVENT_TYPE_SHIFT); + + dev_dbg(cpts->dev, "%s mtype seqid %08x\n", + __func__, skb_cb->skb_mtype_seqid); + + ns = cpts_find_ts(cpts, skb, CPTS_EV_RX, skb_cb->skb_mtype_seqid); if (!ns) return; ssh = skb_hwtstamps(skb); @@ -430,17 +548,27 @@ EXPORT_SYMBOL_GPL(cpts_rx_timestamp); void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb) { - u64 ns; - struct skb_shared_hwtstamps ssh; + struct cpts_skb_cb_data *skb_cb = (struct cpts_skb_cb_data *)skb->cb; + int ret; if (!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) return; - ns = cpts_find_ts(cpts, skb, CPTS_EV_TX); - if (!ns) + + ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid); + if (!ret) return; - memset(&ssh, 0, sizeof(ssh)); - ssh.hwtstamp = ns_to_ktime(ns); - skb_tstamp_tx(skb, &ssh); + + skb_cb->skb_mtype_seqid |= (CPTS_EV_TX << EVENT_TYPE_SHIFT); + + dev_dbg(cpts->dev, "%s mtype seqid %08x\n", + __func__, skb_cb->skb_mtype_seqid); + + /* Always defer TX TS processing to PTP worker */ + skb_get(skb); + /* get the timestamp for timeouts */ + skb_cb->tmo = jiffies + msecs_to_jiffies(CPTS_SKB_RX_TX_TMO); + skb_queue_tail(&cpts->txq, skb); + ptp_schedule_worker(cpts->clock, 0); } EXPORT_SYMBOL_GPL(cpts_tx_timestamp); @@ -632,7 +760,7 @@ of_error: } struct cpts *cpts_create(struct device *dev, void __iomem *regs, - struct device_node *node) + struct device_node *node, u32 n_ext_ts) { struct cpts *cpts; int ret; @@ -643,7 +771,10 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, cpts->dev = dev; cpts->reg = (struct cpsw_cpts __iomem *)regs; + cpts->irq_poll = true; spin_lock_init(&cpts->lock); + mutex_init(&cpts->ptp_clk_mutex); + init_completion(&cpts->ts_push_complete); ret = cpts_of_parse(cpts, node); if (ret) @@ -668,6 +799,9 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, cpts->cc.mask = CLOCKSOURCE_MASK(32); cpts->info = cpts_info; + if (n_ext_ts) + cpts->info.n_ext_ts = n_ext_ts; + cpts_calc_mult_shift(cpts); /* save cc.mult original value as it can be modified * by cpts_ptp_adjfreq(). diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h index bb997c11ee15..07222f651d2e 100644 --- a/drivers/net/ethernet/ti/cpts.h +++ b/drivers/net/ethernet/ti/cpts.h @@ -94,6 +94,7 @@ struct cpts_event { unsigned long tmo; u32 high; u32 low; + u64 timestamp; }; struct cpts { @@ -103,7 +104,7 @@ struct cpts { int rx_enable; struct ptp_clock_info info; struct ptp_clock *clock; - spinlock_t lock; /* protects time registers */ + spinlock_t lock; /* protects fifo/events */ u32 cc_mult; /* for the nominal frequency */ struct cyclecounter cc; struct timecounter tc; @@ -114,6 +115,12 @@ struct cpts { struct cpts_event pool_data[CPTS_MAX_EVENTS]; unsigned long ov_check_period; struct sk_buff_head txq; + u64 cur_timestamp; + u32 mult_new; + struct mutex ptp_clk_mutex; /* sync PTP interface and worker */ + bool irq_poll; + struct completion ts_push_complete; + u32 hw_ts_enable; }; void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb); @@ -121,8 +128,9 @@ void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb); int cpts_register(struct cpts *cpts); void cpts_unregister(struct cpts *cpts); struct cpts *cpts_create(struct device *dev, void __iomem *regs, - struct device_node *node); + struct device_node *node, u32 n_ext_ts); void cpts_release(struct cpts *cpts); +void cpts_misc_interrupt(struct cpts *cpts); static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb) { @@ -134,6 +142,11 @@ static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb) return true; } +static inline void cpts_set_irqpoll(struct cpts *cpts, bool en) +{ + cpts->irq_poll = en; +} + #else struct cpts; @@ -146,7 +159,7 @@ static inline void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb) static inline struct cpts *cpts_create(struct device *dev, void __iomem *regs, - struct device_node *node) + struct device_node *node, u32 n_ext_ts) { return NULL; } @@ -169,6 +182,14 @@ static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb) { return false; } + +static inline void cpts_misc_interrupt(struct cpts *cpts) +{ +} + +static inline void cpts_set_irqpoll(struct cpts *cpts, bool en) +{ +} #endif diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index fb36115e9c51..9d6e27fb710e 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -3716,7 +3716,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, if (!cpts_node) cpts_node = of_node_get(node); - gbe_dev->cpts = cpts_create(gbe_dev->dev, gbe_dev->cpts_reg, cpts_node); + gbe_dev->cpts = cpts_create(gbe_dev->dev, gbe_dev->cpts_reg, + cpts_node, 0); of_node_put(cpts_node); if (IS_ENABLED(CONFIG_TI_CPTS) && IS_ERR(gbe_dev->cpts)) { ret = PTR_ERR(gbe_dev->cpts); diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 269596c15133..2e5202923510 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -1387,6 +1387,8 @@ static int ixp4xx_eth_probe(struct platform_device *pdev) return -ENODEV; regs_phys = res->start; port->regs = devm_ioremap_resource(dev, res); + if (IS_ERR(port->regs)) + return PTR_ERR(port->regs); switch (port->id) { case IXP4XX_ETH_NPEA: diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 09f279c0182b..6b461be1820b 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1207,7 +1207,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]); if (df < 0 || df > GENEVE_DF_MAX) { - NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF], + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF], "Invalid DF attribute"); return -EINVAL; } diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index 55c9329a4b1d..ed10818dd99f 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -297,14 +297,13 @@ static void ipa_modem_crashed(struct ipa *ipa) ret = ipa_endpoint_modem_exception_reset_all(ipa); if (ret) - dev_err(dev, "error %d resetting exception endpoint", - ret); + dev_err(dev, "error %d resetting exception endpoint\n", ret); ipa_endpoint_modem_pause_all(ipa, false); ret = ipa_modem_stop(ipa); if (ret) - dev_err(dev, "error %d stopping modem", ret); + dev_err(dev, "error %d stopping modem\n", ret); /* Now prepare for the next modem boot */ ret = ipa_mem_zero_modem(ipa); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 0d580d81d910..758baf7cb8a1 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3809,7 +3809,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); - struct macsec_tx_sa tx_sc; + struct macsec_tx_sc tx_sc; struct macsec_secy secy; int ret; @@ -4002,11 +4002,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); + rx_handler_func_t *rx_handler; + u8 icv_len = DEFAULT_ICV_LEN; struct net_device *real_dev; - int err; + int err, mtu; sci_t sci; - u8 icv_len = DEFAULT_ICV_LEN; - rx_handler_func_t *rx_handler; if (!tb[IFLA_LINK]) return -EINVAL; @@ -4033,7 +4033,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (data && data[IFLA_MACSEC_ICV_LEN]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); - dev->mtu = real_dev->mtu - icv_len - macsec_extra_len(true); + mtu = real_dev->mtu - icv_len - macsec_extra_len(true); + if (mtu < 0) + dev->mtu = 0; + else + dev->mtu = mtu; rx_handler = rtnl_dereference(real_dev->rx_handler); if (rx_handler && rx_handler != macsec_handle_frame) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index e7289d67268f..d45600e0a38c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -123,7 +123,8 @@ static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, struct macvlan_dev *vlan; u32 idx = macvlan_eth_hash(addr); - hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist) { + hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist, + lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } @@ -1704,7 +1705,7 @@ static int macvlan_device_event(struct notifier_block *unused, struct macvlan_dev, list); - if (macvlan_sync_address(vlan->dev, dev->dev_addr)) + if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr)) return NOTIFY_BAD; break; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 3fa33d27eeba..bacfee41b564 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -346,6 +346,17 @@ config BROADCOM_PHY Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, BCM5481, BCM54810 and BCM5482 PHYs. +config BCM54140_PHY + tristate "Broadcom BCM54140 PHY" + depends on PHYLIB + depends on HWMON || HWMON=n + select BCM_NET_PHYLIB + help + Support the Broadcom BCM54140 Quad SGMII/QSGMII PHY. + + This driver also supports the hardware monitoring of this PHY and + exposes voltage and temperature sensors. + config BCM84881_PHY tristate "Broadcom BCM84881 PHY" depends on PHYLIB diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 2f5c7093a65b..cd345b75d127 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -68,6 +68,7 @@ obj-$(CONFIG_BCM87XX_PHY) += bcm87xx.o obj-$(CONFIG_BCM_CYGNUS_PHY) += bcm-cygnus.o obj-$(CONFIG_BCM_NET_PHYLIB) += bcm-phy-lib.o obj-$(CONFIG_BROADCOM_PHY) += broadcom.o +obj-$(CONFIG_BCM54140_PHY) += bcm54140.o obj-$(CONFIG_BCM84881_PHY) += bcm84881.o obj-$(CONFIG_CICADA_PHY) += cicada.o obj-$(CONFIG_CORTINA_PHY) += cortina.o diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 31f731e6df72..31b6edcc1fd1 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -106,6 +106,7 @@ #define ATH9331_PHY_ID 0x004dd041 #define ATH8030_PHY_ID 0x004dd076 #define ATH8031_PHY_ID 0x004dd074 +#define ATH8032_PHY_ID 0x004dd023 #define ATH8035_PHY_ID 0x004dd072 #define AT803X_PHY_ID_MASK 0xffffffef @@ -763,6 +764,21 @@ static struct phy_driver at803x_driver[] = { .ack_interrupt = &at803x_ack_interrupt, .config_intr = &at803x_config_intr, }, { + /* Qualcomm Atheros AR8032 */ + PHY_ID_MATCH_EXACT(ATH8032_PHY_ID), + .name = "Qualcomm Atheros AR8032", + .probe = at803x_probe, + .remove = at803x_remove, + .config_init = at803x_config_init, + .link_change_notify = at803x_link_change_notify, + .set_wol = at803x_set_wol, + .get_wol = at803x_get_wol, + .suspend = at803x_suspend, + .resume = at803x_resume, + /* PHY_BASIC_FEATURES */ + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, +}, { /* ATHEROS AR9331 */ PHY_ID_MATCH_EXACT(ATH9331_PHY_ID), .name = "Qualcomm Atheros AR9331 built-in PHY", @@ -778,6 +794,7 @@ module_phy_driver(at803x_driver); static struct mdio_device_id __maybe_unused atheros_tbl[] = { { ATH8030_PHY_ID, AT803X_PHY_ID_MASK }, { ATH8031_PHY_ID, AT803X_PHY_ID_MASK }, + { PHY_ID_MATCH_EXACT(ATH8032_PHY_ID) }, { ATH8035_PHY_ID, AT803X_PHY_ID_MASK }, { PHY_ID_MATCH_EXACT(ATH9331_PHY_ID) }, { } diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index e77b274a09fd..d5f9a2701989 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -155,6 +155,86 @@ int bcm_phy_write_shadow(struct phy_device *phydev, u16 shadow, } EXPORT_SYMBOL_GPL(bcm_phy_write_shadow); +int __bcm_phy_read_rdb(struct phy_device *phydev, u16 rdb) +{ + int val; + + val = __phy_write(phydev, MII_BCM54XX_RDB_ADDR, rdb); + if (val < 0) + return val; + + return __phy_read(phydev, MII_BCM54XX_RDB_DATA); +} +EXPORT_SYMBOL_GPL(__bcm_phy_read_rdb); + +int bcm_phy_read_rdb(struct phy_device *phydev, u16 rdb) +{ + int ret; + + phy_lock_mdio_bus(phydev); + ret = __bcm_phy_read_rdb(phydev, rdb); + phy_unlock_mdio_bus(phydev); + + return ret; +} +EXPORT_SYMBOL_GPL(bcm_phy_read_rdb); + +int __bcm_phy_write_rdb(struct phy_device *phydev, u16 rdb, u16 val) +{ + int ret; + + ret = __phy_write(phydev, MII_BCM54XX_RDB_ADDR, rdb); + if (ret < 0) + return ret; + + return __phy_write(phydev, MII_BCM54XX_RDB_DATA, val); +} +EXPORT_SYMBOL_GPL(__bcm_phy_write_rdb); + +int bcm_phy_write_rdb(struct phy_device *phydev, u16 rdb, u16 val) +{ + int ret; + + phy_lock_mdio_bus(phydev); + ret = __bcm_phy_write_rdb(phydev, rdb, val); + phy_unlock_mdio_bus(phydev); + + return ret; +} +EXPORT_SYMBOL_GPL(bcm_phy_write_rdb); + +int __bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask, u16 set) +{ + int new, ret; + + ret = __phy_write(phydev, MII_BCM54XX_RDB_ADDR, rdb); + if (ret < 0) + return ret; + + ret = __phy_read(phydev, MII_BCM54XX_RDB_DATA); + if (ret < 0) + return ret; + + new = (ret & ~mask) | set; + if (new == ret) + return 0; + + return __phy_write(phydev, MII_BCM54XX_RDB_DATA, new); +} +EXPORT_SYMBOL_GPL(__bcm_phy_modify_rdb); + +int bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask, u16 set) +{ + int ret; + + phy_lock_mdio_bus(phydev); + ret = __bcm_phy_modify_rdb(phydev, rdb, mask, set); + phy_unlock_mdio_bus(phydev); + + return ret; +} +EXPORT_SYMBOL_GPL(bcm_phy_modify_rdb); + int bcm_phy_enable_apd(struct phy_device *phydev, bool dll_pwr_down) { int val; diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h index 129df819be8c..4d3de91cda6c 100644 --- a/drivers/net/phy/bcm-phy-lib.h +++ b/drivers/net/phy/bcm-phy-lib.h @@ -48,6 +48,15 @@ int bcm_phy_write_shadow(struct phy_device *phydev, u16 shadow, u16 val); int bcm_phy_read_shadow(struct phy_device *phydev, u16 shadow); +int __bcm_phy_write_rdb(struct phy_device *phydev, u16 rdb, u16 val); +int bcm_phy_write_rdb(struct phy_device *phydev, u16 rdb, u16 val); +int __bcm_phy_read_rdb(struct phy_device *phydev, u16 rdb); +int bcm_phy_read_rdb(struct phy_device *phydev, u16 rdb); +int __bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask, + u16 set); +int bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask, + u16 set); + int bcm_phy_ack_intr(struct phy_device *phydev); int bcm_phy_config_intr(struct phy_device *phydev); diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c new file mode 100644 index 000000000000..7341f0126cc4 --- /dev/null +++ b/drivers/net/phy/bcm54140.c @@ -0,0 +1,879 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Broadcom BCM54140 Quad SGMII/QSGMII Copper/Fiber Gigabit PHY + * + * Copyright (c) 2020 Michael Walle <michael@walle.cc> + */ + +#include <linux/bitfield.h> +#include <linux/brcmphy.h> +#include <linux/hwmon.h> +#include <linux/module.h> +#include <linux/phy.h> + +#include "bcm-phy-lib.h" + +/* RDB per-port registers + */ +#define BCM54140_RDB_ISR 0x00a /* interrupt status */ +#define BCM54140_RDB_IMR 0x00b /* interrupt mask */ +#define BCM54140_RDB_INT_LINK BIT(1) /* link status changed */ +#define BCM54140_RDB_INT_SPEED BIT(2) /* link speed change */ +#define BCM54140_RDB_INT_DUPLEX BIT(3) /* duplex mode changed */ +#define BCM54140_RDB_SPARE1 0x012 /* spare control 1 */ +#define BCM54140_RDB_SPARE1_LSLM BIT(2) /* link speed LED mode */ +#define BCM54140_RDB_SPARE2 0x014 /* spare control 2 */ +#define BCM54140_RDB_SPARE2_WS_RTRY_DIS BIT(8) /* wirespeed retry disable */ +#define BCM54140_RDB_SPARE2_WS_RTRY_LIMIT GENMASK(4, 2) /* retry limit */ +#define BCM54140_RDB_SPARE3 0x015 /* spare control 3 */ +#define BCM54140_RDB_SPARE3_BIT0 BIT(0) +#define BCM54140_RDB_LED_CTRL 0x019 /* LED control */ +#define BCM54140_RDB_LED_CTRL_ACTLINK0 BIT(4) +#define BCM54140_RDB_LED_CTRL_ACTLINK1 BIT(8) +#define BCM54140_RDB_C_APWR 0x01a /* auto power down control */ +#define BCM54140_RDB_C_APWR_SINGLE_PULSE BIT(8) /* single pulse */ +#define BCM54140_RDB_C_APWR_APD_MODE_DIS 0 /* ADP disable */ +#define BCM54140_RDB_C_APWR_APD_MODE_EN 1 /* ADP enable */ +#define BCM54140_RDB_C_APWR_APD_MODE_DIS2 2 /* ADP disable */ +#define BCM54140_RDB_C_APWR_APD_MODE_EN_ANEG 3 /* ADP enable w/ aneg */ +#define BCM54140_RDB_C_APWR_APD_MODE_MASK GENMASK(6, 5) +#define BCM54140_RDB_C_APWR_SLP_TIM_MASK BIT(4)/* sleep timer */ +#define BCM54140_RDB_C_APWR_SLP_TIM_2_7 0 /* 2.7s */ +#define BCM54140_RDB_C_APWR_SLP_TIM_5_4 1 /* 5.4s */ +#define BCM54140_RDB_C_PWR 0x02a /* copper power control */ +#define BCM54140_RDB_C_PWR_ISOLATE BIT(5) /* super isolate mode */ +#define BCM54140_RDB_C_MISC_CTRL 0x02f /* misc copper control */ +#define BCM54140_RDB_C_MISC_CTRL_WS_EN BIT(4) /* wirespeed enable */ + +/* RDB global registers + */ +#define BCM54140_RDB_TOP_IMR 0x82d /* interrupt mask */ +#define BCM54140_RDB_TOP_IMR_PORT0 BIT(4) +#define BCM54140_RDB_TOP_IMR_PORT1 BIT(5) +#define BCM54140_RDB_TOP_IMR_PORT2 BIT(6) +#define BCM54140_RDB_TOP_IMR_PORT3 BIT(7) +#define BCM54140_RDB_MON_CTRL 0x831 /* monitor control */ +#define BCM54140_RDB_MON_CTRL_V_MODE BIT(3) /* voltage mode */ +#define BCM54140_RDB_MON_CTRL_SEL_MASK GENMASK(2, 1) +#define BCM54140_RDB_MON_CTRL_SEL_TEMP 0 /* meassure temperature */ +#define BCM54140_RDB_MON_CTRL_SEL_1V0 1 /* meassure AVDDL 1.0V */ +#define BCM54140_RDB_MON_CTRL_SEL_3V3 2 /* meassure AVDDH 3.3V */ +#define BCM54140_RDB_MON_CTRL_SEL_RR 3 /* meassure all round-robin */ +#define BCM54140_RDB_MON_CTRL_PWR_DOWN BIT(0) /* power-down monitor */ +#define BCM54140_RDB_MON_TEMP_VAL 0x832 /* temperature value */ +#define BCM54140_RDB_MON_TEMP_MAX 0x833 /* temperature high thresh */ +#define BCM54140_RDB_MON_TEMP_MIN 0x834 /* temperature low thresh */ +#define BCM54140_RDB_MON_TEMP_DATA_MASK GENMASK(9, 0) +#define BCM54140_RDB_MON_1V0_VAL 0x835 /* AVDDL 1.0V value */ +#define BCM54140_RDB_MON_1V0_MAX 0x836 /* AVDDL 1.0V high thresh */ +#define BCM54140_RDB_MON_1V0_MIN 0x837 /* AVDDL 1.0V low thresh */ +#define BCM54140_RDB_MON_1V0_DATA_MASK GENMASK(10, 0) +#define BCM54140_RDB_MON_3V3_VAL 0x838 /* AVDDH 3.3V value */ +#define BCM54140_RDB_MON_3V3_MAX 0x839 /* AVDDH 3.3V high thresh */ +#define BCM54140_RDB_MON_3V3_MIN 0x83a /* AVDDH 3.3V low thresh */ +#define BCM54140_RDB_MON_3V3_DATA_MASK GENMASK(11, 0) +#define BCM54140_RDB_MON_ISR 0x83b /* interrupt status */ +#define BCM54140_RDB_MON_ISR_3V3 BIT(2) /* AVDDH 3.3V alarm */ +#define BCM54140_RDB_MON_ISR_1V0 BIT(1) /* AVDDL 1.0V alarm */ +#define BCM54140_RDB_MON_ISR_TEMP BIT(0) /* temperature alarm */ + +/* According to the datasheet the formula is: + * T = 413.35 - (0.49055 * bits[9:0]) + */ +#define BCM54140_HWMON_TO_TEMP(v) (413350L - (v) * 491) +#define BCM54140_HWMON_FROM_TEMP(v) DIV_ROUND_CLOSEST_ULL(413350L - (v), 491) + +/* According to the datasheet the formula is: + * U = bits[11:0] / 1024 * 220 / 0.2 + * + * Normalized: + * U = bits[11:0] / 4096 * 2514 + */ +#define BCM54140_HWMON_TO_IN_1V0(v) ((v) * 2514 >> 11) +#define BCM54140_HWMON_FROM_IN_1V0(v) DIV_ROUND_CLOSEST_ULL(((v) << 11), 2514) + +/* According to the datasheet the formula is: + * U = bits[10:0] / 1024 * 880 / 0.7 + * + * Normalized: + * U = bits[10:0] / 2048 * 4400 + */ +#define BCM54140_HWMON_TO_IN_3V3(v) ((v) * 4400 >> 12) +#define BCM54140_HWMON_FROM_IN_3V3(v) DIV_ROUND_CLOSEST_ULL(((v) << 12), 4400) + +#define BCM54140_HWMON_TO_IN(ch, v) ((ch) ? BCM54140_HWMON_TO_IN_3V3(v) \ + : BCM54140_HWMON_TO_IN_1V0(v)) +#define BCM54140_HWMON_FROM_IN(ch, v) ((ch) ? BCM54140_HWMON_FROM_IN_3V3(v) \ + : BCM54140_HWMON_FROM_IN_1V0(v)) +#define BCM54140_HWMON_IN_MASK(ch) ((ch) ? BCM54140_RDB_MON_3V3_DATA_MASK \ + : BCM54140_RDB_MON_1V0_DATA_MASK) +#define BCM54140_HWMON_IN_VAL_REG(ch) ((ch) ? BCM54140_RDB_MON_3V3_VAL \ + : BCM54140_RDB_MON_1V0_VAL) +#define BCM54140_HWMON_IN_MIN_REG(ch) ((ch) ? BCM54140_RDB_MON_3V3_MIN \ + : BCM54140_RDB_MON_1V0_MIN) +#define BCM54140_HWMON_IN_MAX_REG(ch) ((ch) ? BCM54140_RDB_MON_3V3_MAX \ + : BCM54140_RDB_MON_1V0_MAX) +#define BCM54140_HWMON_IN_ALARM_BIT(ch) ((ch) ? BCM54140_RDB_MON_ISR_3V3 \ + : BCM54140_RDB_MON_ISR_1V0) + +#define BCM54140_DEFAULT_DOWNSHIFT 5 +#define BCM54140_MAX_DOWNSHIFT 9 + +struct bcm54140_priv { + int port; + int base_addr; +#if IS_ENABLED(CONFIG_HWMON) + bool pkg_init; + /* protect the alarm bits */ + struct mutex alarm_lock; + u16 alarm; +#endif +}; + +#if IS_ENABLED(CONFIG_HWMON) +static umode_t bcm54140_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + switch (type) { + case hwmon_in: + switch (attr) { + case hwmon_in_min: + case hwmon_in_max: + return 0644; + case hwmon_in_label: + case hwmon_in_input: + case hwmon_in_alarm: + return 0444; + default: + return 0; + } + case hwmon_temp: + switch (attr) { + case hwmon_temp_min: + case hwmon_temp_max: + return 0644; + case hwmon_temp_input: + case hwmon_temp_alarm: + return 0444; + default: + return 0; + } + default: + return 0; + } +} + +static int bcm54140_hwmon_read_alarm(struct device *dev, unsigned int bit, + long *val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + struct bcm54140_priv *priv = phydev->priv; + int tmp, ret = 0; + + mutex_lock(&priv->alarm_lock); + + /* latch any alarm bits */ + tmp = bcm_phy_read_rdb(phydev, BCM54140_RDB_MON_ISR); + if (tmp < 0) { + ret = tmp; + goto out; + } + priv->alarm |= tmp; + + *val = !!(priv->alarm & bit); + priv->alarm &= ~bit; + +out: + mutex_unlock(&priv->alarm_lock); + return ret; +} + +static int bcm54140_hwmon_read_temp(struct device *dev, u32 attr, long *val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + u16 reg; + int tmp; + + switch (attr) { + case hwmon_temp_input: + reg = BCM54140_RDB_MON_TEMP_VAL; + break; + case hwmon_temp_min: + reg = BCM54140_RDB_MON_TEMP_MIN; + break; + case hwmon_temp_max: + reg = BCM54140_RDB_MON_TEMP_MAX; + break; + case hwmon_temp_alarm: + return bcm54140_hwmon_read_alarm(dev, + BCM54140_RDB_MON_ISR_TEMP, + val); + default: + return -EOPNOTSUPP; + } + + tmp = bcm_phy_read_rdb(phydev, reg); + if (tmp < 0) + return tmp; + + *val = BCM54140_HWMON_TO_TEMP(tmp & BCM54140_RDB_MON_TEMP_DATA_MASK); + + return 0; +} + +static int bcm54140_hwmon_read_in(struct device *dev, u32 attr, + int channel, long *val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + u16 bit, reg; + int tmp; + + switch (attr) { + case hwmon_in_input: + reg = BCM54140_HWMON_IN_VAL_REG(channel); + break; + case hwmon_in_min: + reg = BCM54140_HWMON_IN_MIN_REG(channel); + break; + case hwmon_in_max: + reg = BCM54140_HWMON_IN_MAX_REG(channel); + break; + case hwmon_in_alarm: + bit = BCM54140_HWMON_IN_ALARM_BIT(channel); + return bcm54140_hwmon_read_alarm(dev, bit, val); + default: + return -EOPNOTSUPP; + } + + tmp = bcm_phy_read_rdb(phydev, reg); + if (tmp < 0) + return tmp; + + tmp &= BCM54140_HWMON_IN_MASK(channel); + *val = BCM54140_HWMON_TO_IN(channel, tmp); + + return 0; +} + +static int bcm54140_hwmon_read(struct device *dev, + enum hwmon_sensor_types type, u32 attr, + int channel, long *val) +{ + switch (type) { + case hwmon_temp: + return bcm54140_hwmon_read_temp(dev, attr, val); + case hwmon_in: + return bcm54140_hwmon_read_in(dev, attr, channel, val); + default: + return -EOPNOTSUPP; + } +} + +static const char *const bcm54140_hwmon_in_labels[] = { + "AVDDL", + "AVDDH", +}; + +static int bcm54140_hwmon_read_string(struct device *dev, + enum hwmon_sensor_types type, u32 attr, + int channel, const char **str) +{ + switch (type) { + case hwmon_in: + switch (attr) { + case hwmon_in_label: + *str = bcm54140_hwmon_in_labels[channel]; + return 0; + default: + return -EOPNOTSUPP; + } + default: + return -EOPNOTSUPP; + } +} + +static int bcm54140_hwmon_write_temp(struct device *dev, u32 attr, + int channel, long val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + u16 mask = BCM54140_RDB_MON_TEMP_DATA_MASK; + u16 reg; + + val = clamp_val(val, BCM54140_HWMON_TO_TEMP(mask), + BCM54140_HWMON_TO_TEMP(0)); + + switch (attr) { + case hwmon_temp_min: + reg = BCM54140_RDB_MON_TEMP_MIN; + break; + case hwmon_temp_max: + reg = BCM54140_RDB_MON_TEMP_MAX; + break; + default: + return -EOPNOTSUPP; + } + + return bcm_phy_modify_rdb(phydev, reg, mask, + BCM54140_HWMON_FROM_TEMP(val)); +} + +static int bcm54140_hwmon_write_in(struct device *dev, u32 attr, + int channel, long val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + u16 mask = BCM54140_HWMON_IN_MASK(channel); + u16 reg; + + val = clamp_val(val, 0, BCM54140_HWMON_TO_IN(channel, mask)); + + switch (attr) { + case hwmon_in_min: + reg = BCM54140_HWMON_IN_MIN_REG(channel); + break; + case hwmon_in_max: + reg = BCM54140_HWMON_IN_MAX_REG(channel); + break; + default: + return -EOPNOTSUPP; + } + + return bcm_phy_modify_rdb(phydev, reg, mask, + BCM54140_HWMON_FROM_IN(channel, val)); +} + +static int bcm54140_hwmon_write(struct device *dev, + enum hwmon_sensor_types type, u32 attr, + int channel, long val) +{ + switch (type) { + case hwmon_temp: + return bcm54140_hwmon_write_temp(dev, attr, channel, val); + case hwmon_in: + return bcm54140_hwmon_write_in(dev, attr, channel, val); + default: + return -EOPNOTSUPP; + } +} + +static const struct hwmon_channel_info *bcm54140_hwmon_info[] = { + HWMON_CHANNEL_INFO(temp, + HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX | + HWMON_T_ALARM), + HWMON_CHANNEL_INFO(in, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | + HWMON_I_ALARM | HWMON_I_LABEL, + HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | + HWMON_I_ALARM | HWMON_I_LABEL), + NULL +}; + +static const struct hwmon_ops bcm54140_hwmon_ops = { + .is_visible = bcm54140_hwmon_is_visible, + .read = bcm54140_hwmon_read, + .read_string = bcm54140_hwmon_read_string, + .write = bcm54140_hwmon_write, +}; + +static const struct hwmon_chip_info bcm54140_chip_info = { + .ops = &bcm54140_hwmon_ops, + .info = bcm54140_hwmon_info, +}; + +static int bcm54140_enable_monitoring(struct phy_device *phydev) +{ + u16 mask, set; + + /* 3.3V voltage mode */ + set = BCM54140_RDB_MON_CTRL_V_MODE; + + /* select round-robin */ + mask = BCM54140_RDB_MON_CTRL_SEL_MASK; + set |= FIELD_PREP(BCM54140_RDB_MON_CTRL_SEL_MASK, + BCM54140_RDB_MON_CTRL_SEL_RR); + + /* remove power-down bit */ + mask |= BCM54140_RDB_MON_CTRL_PWR_DOWN; + + return bcm_phy_modify_rdb(phydev, BCM54140_RDB_MON_CTRL, mask, set); +} + +/* Check if one PHY has already done the init of the parts common to all PHYs + * in the Quad PHY package. + */ +static bool bcm54140_is_pkg_init(struct phy_device *phydev) +{ + struct bcm54140_priv *priv = phydev->priv; + struct mii_bus *bus = phydev->mdio.bus; + int base_addr = priv->base_addr; + struct phy_device *phy; + int i; + + /* Quad PHY */ + for (i = 0; i < 4; i++) { + phy = mdiobus_get_phy(bus, base_addr + i); + if (!phy) + continue; + + if ((phy->phy_id & phydev->drv->phy_id_mask) != + (phydev->drv->phy_id & phydev->drv->phy_id_mask)) + continue; + + priv = phy->priv; + + if (priv && priv->pkg_init) + return true; + } + + return false; +} + +static int bcm54140_probe_once(struct phy_device *phydev) +{ + struct device *hwmon; + int ret; + + /* enable hardware monitoring */ + ret = bcm54140_enable_monitoring(phydev); + if (ret) + return ret; + + hwmon = devm_hwmon_device_register_with_info(&phydev->mdio.dev, + "BCM54140", phydev, + &bcm54140_chip_info, + NULL); + return PTR_ERR_OR_ZERO(hwmon); +} +#endif + +static int bcm54140_base_read_rdb(struct phy_device *phydev, u16 rdb) +{ + struct bcm54140_priv *priv = phydev->priv; + struct mii_bus *bus = phydev->mdio.bus; + int ret; + + mutex_lock(&bus->mdio_lock); + ret = __mdiobus_write(bus, priv->base_addr, MII_BCM54XX_RDB_ADDR, rdb); + if (ret < 0) + goto out; + + ret = __mdiobus_read(bus, priv->base_addr, MII_BCM54XX_RDB_DATA); + +out: + mutex_unlock(&bus->mdio_lock); + return ret; +} + +static int bcm54140_base_write_rdb(struct phy_device *phydev, + u16 rdb, u16 val) +{ + struct bcm54140_priv *priv = phydev->priv; + struct mii_bus *bus = phydev->mdio.bus; + int ret; + + mutex_lock(&bus->mdio_lock); + ret = __mdiobus_write(bus, priv->base_addr, MII_BCM54XX_RDB_ADDR, rdb); + if (ret < 0) + goto out; + + ret = __mdiobus_write(bus, priv->base_addr, MII_BCM54XX_RDB_DATA, val); + +out: + mutex_unlock(&bus->mdio_lock); + return ret; +} + +/* Under some circumstances a core PLL may not lock, this will then prevent + * a successful link establishment. Restart the PLL after the voltages are + * stable to workaround this issue. + */ +static int bcm54140_b0_workaround(struct phy_device *phydev) +{ + int spare3; + int ret; + + spare3 = bcm_phy_read_rdb(phydev, BCM54140_RDB_SPARE3); + if (spare3 < 0) + return spare3; + + spare3 &= ~BCM54140_RDB_SPARE3_BIT0; + + ret = bcm_phy_write_rdb(phydev, BCM54140_RDB_SPARE3, spare3); + if (ret) + return ret; + + ret = phy_modify(phydev, MII_BMCR, 0, BMCR_PDOWN); + if (ret) + return ret; + + ret = phy_modify(phydev, MII_BMCR, BMCR_PDOWN, 0); + if (ret) + return ret; + + spare3 |= BCM54140_RDB_SPARE3_BIT0; + + return bcm_phy_write_rdb(phydev, BCM54140_RDB_SPARE3, spare3); +} + +/* The BCM54140 is a quad PHY where only the first port has access to the + * global register. Thus we need to find out its PHY address. + * + */ +static int bcm54140_get_base_addr_and_port(struct phy_device *phydev) +{ + struct bcm54140_priv *priv = phydev->priv; + struct mii_bus *bus = phydev->mdio.bus; + int addr, min_addr, max_addr; + int step = 1; + u32 phy_id; + int tmp; + + min_addr = phydev->mdio.addr; + max_addr = phydev->mdio.addr; + addr = phydev->mdio.addr; + + /* We scan forward and backwards and look for PHYs which have the + * same phy_id like we do. Step 1 will scan forward, step 2 + * backwards. Once we are finished, we have a min_addr and + * max_addr which resembles the range of PHY addresses of the same + * type of PHY. There is one caveat; there may be many PHYs of + * the same type, but we know that each PHY takes exactly 4 + * consecutive addresses. Therefore we can deduce our offset + * to the base address of this quad PHY. + */ + + while (1) { + if (step == 3) { + break; + } else if (step == 1) { + max_addr = addr; + addr++; + } else { + min_addr = addr; + addr--; + } + + if (addr < 0 || addr >= PHY_MAX_ADDR) { + addr = phydev->mdio.addr; + step++; + continue; + } + + /* read the PHY id */ + tmp = mdiobus_read(bus, addr, MII_PHYSID1); + if (tmp < 0) + return tmp; + phy_id = tmp << 16; + tmp = mdiobus_read(bus, addr, MII_PHYSID2); + if (tmp < 0) + return tmp; + phy_id |= tmp; + + /* see if it is still the same PHY */ + if ((phy_id & phydev->drv->phy_id_mask) != + (phydev->drv->phy_id & phydev->drv->phy_id_mask)) { + addr = phydev->mdio.addr; + step++; + } + } + + /* The range we get should be a multiple of four. Please note that both + * the min_addr and max_addr are inclusive. So we have to add one if we + * subtract them. + */ + if ((max_addr - min_addr + 1) % 4) { + dev_err(&phydev->mdio.dev, + "Detected Quad PHY IDs %d..%d doesn't make sense.\n", + min_addr, max_addr); + return -EINVAL; + } + + priv->port = (phydev->mdio.addr - min_addr) % 4; + priv->base_addr = phydev->mdio.addr - priv->port; + + return 0; +} + +static int bcm54140_probe(struct phy_device *phydev) +{ + struct bcm54140_priv *priv; + int ret; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + ret = bcm54140_get_base_addr_and_port(phydev); + if (ret) + return ret; + +#if IS_ENABLED(CONFIG_HWMON) + mutex_init(&priv->alarm_lock); + + if (!bcm54140_is_pkg_init(phydev)) { + ret = bcm54140_probe_once(phydev); + if (ret) + return ret; + } + + priv->pkg_init = true; +#endif + + phydev_dbg(phydev, "probed (port %d, base PHY address %d)\n", + priv->port, priv->base_addr); + + return 0; +} + +static int bcm54140_config_init(struct phy_device *phydev) +{ + u16 reg = 0xffff; + int ret; + + /* Apply hardware errata */ + ret = bcm54140_b0_workaround(phydev); + if (ret) + return ret; + + /* Unmask events we are interested in. */ + reg &= ~(BCM54140_RDB_INT_DUPLEX | + BCM54140_RDB_INT_SPEED | + BCM54140_RDB_INT_LINK); + ret = bcm_phy_write_rdb(phydev, BCM54140_RDB_IMR, reg); + if (ret) + return ret; + + /* LED1=LINKSPD[1], LED2=LINKSPD[2], LED3=LINK/ACTIVITY */ + ret = bcm_phy_modify_rdb(phydev, BCM54140_RDB_SPARE1, + 0, BCM54140_RDB_SPARE1_LSLM); + if (ret) + return ret; + + ret = bcm_phy_modify_rdb(phydev, BCM54140_RDB_LED_CTRL, + 0, BCM54140_RDB_LED_CTRL_ACTLINK0); + if (ret) + return ret; + + /* disable super isolate mode */ + return bcm_phy_modify_rdb(phydev, BCM54140_RDB_C_PWR, + BCM54140_RDB_C_PWR_ISOLATE, 0); +} + +int bcm54140_did_interrupt(struct phy_device *phydev) +{ + int ret; + + ret = bcm_phy_read_rdb(phydev, BCM54140_RDB_ISR); + + return (ret < 0) ? 0 : ret; +} + +int bcm54140_ack_intr(struct phy_device *phydev) +{ + int reg; + + /* clear pending interrupts */ + reg = bcm_phy_read_rdb(phydev, BCM54140_RDB_ISR); + if (reg < 0) + return reg; + + return 0; +} + +int bcm54140_config_intr(struct phy_device *phydev) +{ + struct bcm54140_priv *priv = phydev->priv; + static const u16 port_to_imr_bit[] = { + BCM54140_RDB_TOP_IMR_PORT0, BCM54140_RDB_TOP_IMR_PORT1, + BCM54140_RDB_TOP_IMR_PORT2, BCM54140_RDB_TOP_IMR_PORT3, + }; + int reg; + + if (priv->port >= ARRAY_SIZE(port_to_imr_bit)) + return -EINVAL; + + reg = bcm54140_base_read_rdb(phydev, BCM54140_RDB_TOP_IMR); + if (reg < 0) + return reg; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + reg &= ~port_to_imr_bit[priv->port]; + else + reg |= port_to_imr_bit[priv->port]; + + return bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg); +} + +static int bcm54140_get_downshift(struct phy_device *phydev, u8 *data) +{ + int val; + + val = bcm_phy_read_rdb(phydev, BCM54140_RDB_C_MISC_CTRL); + if (val < 0) + return val; + + if (!(val & BCM54140_RDB_C_MISC_CTRL_WS_EN)) { + *data = DOWNSHIFT_DEV_DISABLE; + return 0; + } + + val = bcm_phy_read_rdb(phydev, BCM54140_RDB_SPARE2); + if (val < 0) + return val; + + if (val & BCM54140_RDB_SPARE2_WS_RTRY_DIS) + *data = 1; + else + *data = FIELD_GET(BCM54140_RDB_SPARE2_WS_RTRY_LIMIT, val) + 2; + + return 0; +} + +static int bcm54140_set_downshift(struct phy_device *phydev, u8 cnt) +{ + u16 mask, set; + int ret; + + if (cnt > BCM54140_MAX_DOWNSHIFT && cnt != DOWNSHIFT_DEV_DEFAULT_COUNT) + return -EINVAL; + + if (!cnt) + return bcm_phy_modify_rdb(phydev, BCM54140_RDB_C_MISC_CTRL, + BCM54140_RDB_C_MISC_CTRL_WS_EN, 0); + + if (cnt == DOWNSHIFT_DEV_DEFAULT_COUNT) + cnt = BCM54140_DEFAULT_DOWNSHIFT; + + if (cnt == 1) { + mask = 0; + set = BCM54140_RDB_SPARE2_WS_RTRY_DIS; + } else { + mask = BCM54140_RDB_SPARE2_WS_RTRY_DIS; + mask |= BCM54140_RDB_SPARE2_WS_RTRY_LIMIT; + set = FIELD_PREP(BCM54140_RDB_SPARE2_WS_RTRY_LIMIT, cnt - 2); + } + ret = bcm_phy_modify_rdb(phydev, BCM54140_RDB_SPARE2, + mask, set); + if (ret) + return ret; + + return bcm_phy_modify_rdb(phydev, BCM54140_RDB_C_MISC_CTRL, + 0, BCM54140_RDB_C_MISC_CTRL_WS_EN); +} + +static int bcm54140_get_edpd(struct phy_device *phydev, u16 *tx_interval) +{ + int val; + + val = bcm_phy_read_rdb(phydev, BCM54140_RDB_C_APWR); + if (val < 0) + return val; + + switch (FIELD_GET(BCM54140_RDB_C_APWR_APD_MODE_MASK, val)) { + case BCM54140_RDB_C_APWR_APD_MODE_DIS: + case BCM54140_RDB_C_APWR_APD_MODE_DIS2: + *tx_interval = ETHTOOL_PHY_EDPD_DISABLE; + break; + case BCM54140_RDB_C_APWR_APD_MODE_EN: + case BCM54140_RDB_C_APWR_APD_MODE_EN_ANEG: + switch (FIELD_GET(BCM54140_RDB_C_APWR_SLP_TIM_MASK, val)) { + case BCM54140_RDB_C_APWR_SLP_TIM_2_7: + *tx_interval = 2700; + break; + case BCM54140_RDB_C_APWR_SLP_TIM_5_4: + *tx_interval = 5400; + break; + } + } + + return 0; +} + +static int bcm54140_set_edpd(struct phy_device *phydev, u16 tx_interval) +{ + u16 mask, set; + + mask = BCM54140_RDB_C_APWR_APD_MODE_MASK; + if (tx_interval == ETHTOOL_PHY_EDPD_DISABLE) + set = FIELD_PREP(BCM54140_RDB_C_APWR_APD_MODE_MASK, + BCM54140_RDB_C_APWR_APD_MODE_DIS); + else + set = FIELD_PREP(BCM54140_RDB_C_APWR_APD_MODE_MASK, + BCM54140_RDB_C_APWR_APD_MODE_EN_ANEG); + + /* enable single pulse mode */ + set |= BCM54140_RDB_C_APWR_SINGLE_PULSE; + + /* set sleep timer */ + mask |= BCM54140_RDB_C_APWR_SLP_TIM_MASK; + switch (tx_interval) { + case ETHTOOL_PHY_EDPD_DFLT_TX_MSECS: + case ETHTOOL_PHY_EDPD_DISABLE: + case 2700: + set |= BCM54140_RDB_C_APWR_SLP_TIM_2_7; + break; + case 5400: + set |= BCM54140_RDB_C_APWR_SLP_TIM_5_4; + break; + default: + return -EINVAL; + } + + return bcm_phy_modify_rdb(phydev, BCM54140_RDB_C_APWR, mask, set); +} + +static int bcm54140_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return bcm54140_get_downshift(phydev, data); + case ETHTOOL_PHY_EDPD: + return bcm54140_get_edpd(phydev, data); + default: + return -EOPNOTSUPP; + } +} + +static int bcm54140_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return bcm54140_set_downshift(phydev, *(const u8 *)data); + case ETHTOOL_PHY_EDPD: + return bcm54140_set_edpd(phydev, *(const u16 *)data); + default: + return -EOPNOTSUPP; + } +} + +static struct phy_driver bcm54140_drivers[] = { + { + .phy_id = PHY_ID_BCM54140, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM54140", + .features = PHY_GBIT_FEATURES, + .config_init = bcm54140_config_init, + .did_interrupt = bcm54140_did_interrupt, + .ack_interrupt = bcm54140_ack_intr, + .config_intr = bcm54140_config_intr, + .probe = bcm54140_probe, + .suspend = genphy_suspend, + .resume = genphy_resume, + .get_tunable = bcm54140_get_tunable, + .set_tunable = bcm54140_set_tunable, + }, +}; +module_phy_driver(bcm54140_drivers); + +static struct mdio_device_id __maybe_unused bcm54140_tbl[] = { + { PHY_ID_BCM54140, 0xfffffff0 }, + { } +}; + +MODULE_AUTHOR("Michael Walle"); +MODULE_DESCRIPTION("Broadcom BCM54140 PHY driver"); +MODULE_DEVICE_TABLE(mdio, bcm54140_tbl); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c index 3840d2adbbb9..9717a1626f3f 100644 --- a/drivers/net/phy/bcm84881.c +++ b/drivers/net/phy/bcm84881.c @@ -155,9 +155,6 @@ static int bcm84881_read_status(struct phy_device *phydev) if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete) phydev->link = false; - if (!phydev->link) - return 0; - linkmode_zero(phydev->lp_advertising); phydev->speed = SPEED_UNKNOWN; phydev->duplex = DUPLEX_UNKNOWN; @@ -165,6 +162,9 @@ static int bcm84881_read_status(struct phy_device *phydev) phydev->asym_pause = 0; phydev->mdix = 0; + if (!phydev->link) + return 0; + if (phydev->autoneg_complete) { val = genphy_c45_read_lpa(phydev); if (val < 0) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ae4873f2f86e..97201d5cf007 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -782,6 +782,19 @@ static struct phy_driver broadcom_drivers[] = { .get_stats = bcm53xx_phy_get_stats, .probe = bcm53xx_phy_probe, }, { + .phy_id = PHY_ID_BCM53125, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM53125", + .flags = PHY_IS_INTERNAL, + /* PHY_GBIT_FEATURES */ + .get_sset_count = bcm_phy_get_sset_count, + .get_strings = bcm_phy_get_strings, + .get_stats = bcm53xx_phy_get_stats, + .probe = bcm53xx_phy_probe, + .config_init = bcm54xx_config_init, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, +}, { .phy_id = PHY_ID_BCM89610, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM89610", @@ -810,6 +823,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = { { PHY_ID_BCMAC131, 0xfffffff0 }, { PHY_ID_BCM5241, 0xfffffff0 }, { PHY_ID_BCM5395, 0xfffffff0 }, + { PHY_ID_BCM53125, 0xfffffff0 }, { PHY_ID_BCM89610, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/cortina.c b/drivers/net/phy/cortina.c index 856cdc36aacd..aac51362c0fe 100644 --- a/drivers/net/phy/cortina.c +++ b/drivers/net/phy/cortina.c @@ -82,7 +82,6 @@ static struct phy_driver cortina_driver[] = { .features = PHY_10GBIT_FEATURES, .config_aneg = gen10g_config_aneg, .read_status = cortina_read_status, - .soft_reset = genphy_no_soft_reset, .probe = cortina_probe, }, }; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index b55e3c0403ed..4017ae1692d8 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -365,7 +365,7 @@ static int dp83867_get_downshift(struct phy_device *phydev, u8 *data) break; default: return -EINVAL; - }; + } *data = enable ? count : DOWNSHIFT_DEV_DISABLE; @@ -400,7 +400,7 @@ static int dp83867_set_downshift(struct phy_device *phydev, u8 cnt) phydev_err(phydev, "Downshift count must be 1, 2, 4 or 8\n"); return -EINVAL; - }; + } val = DP83867_DOWNSHIFT_EN; val |= FIELD_PREP(DP83867_DOWNSHIFT_ATTEMPT_MASK, count); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 4714ca0e0d4b..7fc8e10c5f33 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1263,6 +1263,30 @@ static int marvell_read_status_page_an(struct phy_device *phydev, int lpa; int err; + if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) { + phydev->link = 0; + return 0; + } + + if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + + switch (status & MII_M1011_PHY_STATUS_SPD_MASK) { + case MII_M1011_PHY_STATUS_1000: + phydev->speed = SPEED_1000; + break; + + case MII_M1011_PHY_STATUS_100: + phydev->speed = SPEED_100; + break; + + default: + phydev->speed = SPEED_10; + break; + } + if (!fiber) { err = genphy_read_lpa(phydev); if (err < 0) @@ -1291,28 +1315,6 @@ static int marvell_read_status_page_an(struct phy_device *phydev, } } - if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) - return 0; - - if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) - phydev->duplex = DUPLEX_FULL; - else - phydev->duplex = DUPLEX_HALF; - - switch (status & MII_M1011_PHY_STATUS_SPD_MASK) { - case MII_M1011_PHY_STATUS_1000: - phydev->speed = SPEED_1000; - break; - - case MII_M1011_PHY_STATUS_100: - phydev->speed = SPEED_100; - break; - - default: - phydev->speed = SPEED_10; - break; - } - return 0; } diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 7621badae64d..8352c09004c7 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -33,6 +33,8 @@ #define MV_PHY_ALASKA_NBT_QUIRK_REV (MARVELL_PHY_ID_88X3310 | 0xa) enum { + MV_PMA_FW_VER0 = 0xc011, + MV_PMA_FW_VER1 = 0xc012, MV_PMA_BOOT = 0xc050, MV_PMA_BOOT_FATAL = BIT(0), @@ -73,7 +75,8 @@ enum { /* Vendor2 MMD registers */ MV_V2_PORT_CTRL = 0xf001, - MV_V2_PORT_CTRL_PWRDOWN = 0x0800, + MV_V2_PORT_CTRL_SWRST = BIT(15), + MV_V2_PORT_CTRL_PWRDOWN = BIT(11), MV_V2_TEMP_CTRL = 0xf08a, MV_V2_TEMP_CTRL_MASK = 0xc000, MV_V2_TEMP_CTRL_SAMPLE = 0x0000, @@ -83,6 +86,8 @@ enum { }; struct mv3310_priv { + u32 firmware_ver; + struct device *hwmon_dev; char *hwmon_name; }; @@ -235,8 +240,18 @@ static int mv3310_power_down(struct phy_device *phydev) static int mv3310_power_up(struct phy_device *phydev) { - return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL, - MV_V2_PORT_CTRL_PWRDOWN); + struct mv3310_priv *priv = dev_get_drvdata(&phydev->mdio.dev); + int ret; + + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL, + MV_V2_PORT_CTRL_PWRDOWN); + + if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310 || + priv->firmware_ver < 0x00030000) + return ret; + + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL, + MV_V2_PORT_CTRL_SWRST); } static int mv3310_reset(struct phy_device *phydev, u32 unit) @@ -355,6 +370,22 @@ static int mv3310_probe(struct phy_device *phydev) dev_set_drvdata(&phydev->mdio.dev, priv); + ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MV_PMA_FW_VER0); + if (ret < 0) + return ret; + + priv->firmware_ver = ret << 16; + + ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MV_PMA_FW_VER1); + if (ret < 0) + return ret; + + priv->firmware_ver |= ret; + + phydev_info(phydev, "Firmware version %u.%u.%u.%u\n", + priv->firmware_ver >> 24, (priv->firmware_ver >> 16) & 255, + (priv->firmware_ver >> 8) & 255, priv->firmware_ver & 255); + /* Powering down the port when not in use saves about 600mW */ ret = mv3310_power_down(phydev); if (ret) @@ -697,7 +728,6 @@ static struct phy_driver mv3310_drivers[] = { .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "mv88x3310", .get_features = mv3310_get_features, - .soft_reset = genphy_no_soft_reset, .config_init = mv3310_config_init, .probe = mv3310_probe, .suspend = mv3310_suspend, @@ -715,7 +745,6 @@ static struct phy_driver mv3310_drivers[] = { .probe = mv3310_probe, .suspend = mv3310_suspend, .resume = mv3310_resume, - .soft_reset = genphy_no_soft_reset, .config_init = mv3310_config_init, .config_aneg = mv3310_config_aneg, .aneg_done = mv3310_aneg_done, diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index f1ded03f0229..38bf40e0d673 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -159,7 +159,7 @@ static int iproc_mdio_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); - dev_info(&pdev->dev, "Broadcom iProc MDIO bus at 0x%p\n", priv->base); + dev_info(&pdev->dev, "Broadcom iProc MDIO bus registered\n"); return 0; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 522760c8bca6..3e79b96fa344 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -42,14 +42,11 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev) { - int error; - /* Deassert the optional reset signal */ mdiodev->reset_gpio = gpiod_get_optional(&mdiodev->dev, "reset", GPIOD_OUT_LOW); - error = PTR_ERR_OR_ZERO(mdiodev->reset_gpio); - if (error) - return error; + if (IS_ERR(mdiodev->reset_gpio)) + return PTR_ERR(mdiodev->reset_gpio); if (mdiodev->reset_gpio) gpiod_set_consumer_name(mdiodev->reset_gpio, "PHY reset"); @@ -170,7 +167,12 @@ EXPORT_SYMBOL(mdiobus_alloc_size); static void _devm_mdiobus_free(struct device *dev, void *res) { - mdiobus_free(*(struct mii_bus **)res); + struct mii_bus *bus = *(struct mii_bus **)res; + + if (bus->is_managed_registered && bus->state == MDIOBUS_REGISTERED) + mdiobus_unregister(bus); + + mdiobus_free(bus); } static int devm_mdiobus_match(struct device *dev, void *res, void *data) @@ -210,6 +212,7 @@ struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv) if (bus) { *ptr = bus; devres_add(dev, ptr); + bus->is_managed = 1; } else { devres_free(ptr); } @@ -464,7 +467,7 @@ static struct class mdio_bus_class = { /** * mdio_find_bus - Given the name of a mdiobus, find the mii_bus. - * @mdio_bus_np: Pointer to the mii_bus. + * @mdio_name: The name of a mdiobus. * * Returns a reference to the mii_bus, or NULL if none found. The * embedded struct device will have its reference count incremented, @@ -627,8 +630,11 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) gpiod_set_value_cansleep(gpiod, 0); } - if (bus->reset) - bus->reset(bus); + if (bus->reset) { + err = bus->reset(bus); + if (err) + goto error_reset_gpiod; + } for (i = 0; i < PHY_MAX_ADDR; i++) { if ((bus->phy_mask & (1 << i)) == 0) { @@ -657,7 +663,7 @@ error: mdiodev->device_remove(mdiodev); mdiodev->device_free(mdiodev); } - +error_reset_gpiod: /* Put PHYs in RESET to save power */ if (bus->reset_gpiod) gpiod_set_value_cansleep(bus->reset_gpiod, 1); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 05d20343b816..3fe552675dd2 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -19,6 +19,7 @@ * ksz9477 */ +#include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/phy.h> @@ -490,9 +491,50 @@ static int ksz9021_config_init(struct phy_device *phydev) /* MMD Address 0x2 */ #define MII_KSZ9031RN_CONTROL_PAD_SKEW 4 +#define MII_KSZ9031RN_RX_CTL_M GENMASK(7, 4) +#define MII_KSZ9031RN_TX_CTL_M GENMASK(3, 0) + #define MII_KSZ9031RN_RX_DATA_PAD_SKEW 5 +#define MII_KSZ9031RN_RXD3 GENMASK(15, 12) +#define MII_KSZ9031RN_RXD2 GENMASK(11, 8) +#define MII_KSZ9031RN_RXD1 GENMASK(7, 4) +#define MII_KSZ9031RN_RXD0 GENMASK(3, 0) + #define MII_KSZ9031RN_TX_DATA_PAD_SKEW 6 +#define MII_KSZ9031RN_TXD3 GENMASK(15, 12) +#define MII_KSZ9031RN_TXD2 GENMASK(11, 8) +#define MII_KSZ9031RN_TXD1 GENMASK(7, 4) +#define MII_KSZ9031RN_TXD0 GENMASK(3, 0) + #define MII_KSZ9031RN_CLK_PAD_SKEW 8 +#define MII_KSZ9031RN_GTX_CLK GENMASK(9, 5) +#define MII_KSZ9031RN_RX_CLK GENMASK(4, 0) + +/* KSZ9031 has internal RGMII_IDRX = 1.2ns and RGMII_IDTX = 0ns. To + * provide different RGMII options we need to configure delay offset + * for each pad relative to build in delay. + */ +/* keep rx as "No delay adjustment" and set rx_clk to +0.60ns to get delays of + * 1.80ns + */ +#define RX_ID 0x7 +#define RX_CLK_ID 0x19 + +/* set rx to +0.30ns and rx_clk to -0.90ns to compensate the + * internal 1.2ns delay. + */ +#define RX_ND 0xc +#define RX_CLK_ND 0x0 + +/* set tx to -0.42ns and tx_clk to +0.96ns to get 1.38ns delay */ +#define TX_ID 0x0 +#define TX_CLK_ID 0x1f + +/* set tx and tx_clk to "No delay adjustment" to keep 0ns + * dealy + */ +#define TX_ND 0x7 +#define TX_CLK_ND 0xf /* MMD Address 0x1C */ #define MII_KSZ9031RN_EDPD 0x23 @@ -501,7 +543,8 @@ static int ksz9021_config_init(struct phy_device *phydev) static int ksz9031_of_load_skew_values(struct phy_device *phydev, const struct device_node *of_node, u16 reg, size_t field_sz, - const char *field[], u8 numfields) + const char *field[], u8 numfields, + bool *update) { int val[4] = {-1, -2, -3, -4}; int matches = 0; @@ -517,6 +560,8 @@ static int ksz9031_of_load_skew_values(struct phy_device *phydev, if (!matches) return 0; + *update |= true; + if (matches < numfields) newval = phy_read_mmd(phydev, 2, reg); else @@ -565,6 +610,67 @@ static int ksz9031_enable_edpd(struct phy_device *phydev) reg | MII_KSZ9031RN_EDPD_ENABLE); } +static int ksz9031_config_rgmii_delay(struct phy_device *phydev) +{ + u16 rx, tx, rx_clk, tx_clk; + int ret; + + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + tx = TX_ND; + tx_clk = TX_CLK_ND; + rx = RX_ND; + rx_clk = RX_CLK_ND; + break; + case PHY_INTERFACE_MODE_RGMII_ID: + tx = TX_ID; + tx_clk = TX_CLK_ID; + rx = RX_ID; + rx_clk = RX_CLK_ID; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + tx = TX_ND; + tx_clk = TX_CLK_ND; + rx = RX_ID; + rx_clk = RX_CLK_ID; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + tx = TX_ID; + tx_clk = TX_CLK_ID; + rx = RX_ND; + rx_clk = RX_CLK_ND; + break; + default: + return 0; + } + + ret = phy_write_mmd(phydev, 2, MII_KSZ9031RN_CONTROL_PAD_SKEW, + FIELD_PREP(MII_KSZ9031RN_RX_CTL_M, rx) | + FIELD_PREP(MII_KSZ9031RN_TX_CTL_M, tx)); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, 2, MII_KSZ9031RN_RX_DATA_PAD_SKEW, + FIELD_PREP(MII_KSZ9031RN_RXD3, rx) | + FIELD_PREP(MII_KSZ9031RN_RXD2, rx) | + FIELD_PREP(MII_KSZ9031RN_RXD1, rx) | + FIELD_PREP(MII_KSZ9031RN_RXD0, rx)); + if (ret < 0) + return ret; + + ret = phy_write_mmd(phydev, 2, MII_KSZ9031RN_TX_DATA_PAD_SKEW, + FIELD_PREP(MII_KSZ9031RN_TXD3, tx) | + FIELD_PREP(MII_KSZ9031RN_TXD2, tx) | + FIELD_PREP(MII_KSZ9031RN_TXD1, tx) | + FIELD_PREP(MII_KSZ9031RN_TXD0, tx)); + if (ret < 0) + return ret; + + return phy_write_mmd(phydev, 2, MII_KSZ9031RN_CLK_PAD_SKEW, + FIELD_PREP(MII_KSZ9031RN_GTX_CLK, tx_clk) | + FIELD_PREP(MII_KSZ9031RN_RX_CLK, rx_clk)); +} + static int ksz9031_config_init(struct phy_device *phydev) { const struct device *dev = &phydev->mdio.dev; @@ -597,21 +703,33 @@ static int ksz9031_config_init(struct phy_device *phydev) } while (!of_node && dev_walker); if (of_node) { + bool update = false; + + if (phy_interface_is_rgmii(phydev)) { + result = ksz9031_config_rgmii_delay(phydev); + if (result < 0) + return result; + } + ksz9031_of_load_skew_values(phydev, of_node, MII_KSZ9031RN_CLK_PAD_SKEW, 5, - clk_skews, 2); + clk_skews, 2, &update); ksz9031_of_load_skew_values(phydev, of_node, MII_KSZ9031RN_CONTROL_PAD_SKEW, 4, - control_skews, 2); + control_skews, 2, &update); ksz9031_of_load_skew_values(phydev, of_node, MII_KSZ9031RN_RX_DATA_PAD_SKEW, 4, - rx_data_skews, 4); + rx_data_skews, 4, &update); ksz9031_of_load_skew_values(phydev, of_node, MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4, - tx_data_skews, 4); + tx_data_skews, 4, &update); + + if (update && phydev->interface != PHY_INTERFACE_MODE_RGMII) + phydev_warn(phydev, + "*-skew-ps values should be used only with phy-mode = \"rgmii\"\n"); /* Silicon Errata Sheet (DS80000691D or DS80000692D): * When the device links in the 1000BASE-T slave mode only, @@ -1204,7 +1322,7 @@ static struct phy_driver ksphy_driver[] = { .driver_data = &ksz9021_type, .probe = kszphy_probe, .config_init = ksz9131_config_init, - .read_status = ksz9031_read_status, + .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .get_sset_count = kszphy_get_sset_count, diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 001def4509c2..fed3e395f18e 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -3,9 +3,21 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/delay.h> #include <linux/mii.h> #include <linux/phy.h> +/* External Register Control Register */ +#define LAN87XX_EXT_REG_CTL (0x14) +#define LAN87XX_EXT_REG_CTL_RD_CTL (0x1000) +#define LAN87XX_EXT_REG_CTL_WR_CTL (0x0800) + +/* External Register Read Data Register */ +#define LAN87XX_EXT_REG_RD_DATA (0x15) + +/* External Register Write Data Register */ +#define LAN87XX_EXT_REG_WR_DATA (0x16) + /* Interrupt Source Register */ #define LAN87XX_INTERRUPT_SOURCE (0x18) @@ -14,9 +26,160 @@ #define LAN87XX_MASK_LINK_UP (0x0004) #define LAN87XX_MASK_LINK_DOWN (0x0002) +/* phyaccess nested types */ +#define PHYACC_ATTR_MODE_READ 0 +#define PHYACC_ATTR_MODE_WRITE 1 +#define PHYACC_ATTR_MODE_MODIFY 2 + +#define PHYACC_ATTR_BANK_SMI 0 +#define PHYACC_ATTR_BANK_MISC 1 +#define PHYACC_ATTR_BANK_PCS 2 +#define PHYACC_ATTR_BANK_AFE 3 +#define PHYACC_ATTR_BANK_MAX 7 + #define DRIVER_AUTHOR "Nisar Sayed <nisar.sayed@microchip.com>" #define DRIVER_DESC "Microchip LAN87XX T1 PHY driver" +struct access_ereg_val { + u8 mode; + u8 bank; + u8 offset; + u16 val; + u16 mask; +}; + +static int access_ereg(struct phy_device *phydev, u8 mode, u8 bank, + u8 offset, u16 val) +{ + u16 ereg = 0; + int rc = 0; + + if (mode > PHYACC_ATTR_MODE_WRITE || bank > PHYACC_ATTR_BANK_MAX) + return -EINVAL; + + if (bank == PHYACC_ATTR_BANK_SMI) { + if (mode == PHYACC_ATTR_MODE_WRITE) + rc = phy_write(phydev, offset, val); + else + rc = phy_read(phydev, offset); + return rc; + } + + if (mode == PHYACC_ATTR_MODE_WRITE) { + ereg = LAN87XX_EXT_REG_CTL_WR_CTL; + rc = phy_write(phydev, LAN87XX_EXT_REG_WR_DATA, val); + if (rc < 0) + return rc; + } else { + ereg = LAN87XX_EXT_REG_CTL_RD_CTL; + } + + ereg |= (bank << 8) | offset; + + rc = phy_write(phydev, LAN87XX_EXT_REG_CTL, ereg); + if (rc < 0) + return rc; + + if (mode == PHYACC_ATTR_MODE_READ) + rc = phy_read(phydev, LAN87XX_EXT_REG_RD_DATA); + + return rc; +} + +static int access_ereg_modify_changed(struct phy_device *phydev, + u8 bank, u8 offset, u16 val, u16 mask) +{ + int new = 0, rc = 0; + + if (bank > PHYACC_ATTR_BANK_MAX) + return -EINVAL; + + rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, bank, offset, val); + if (rc < 0) + return rc; + + new = val | (rc & (mask ^ 0xFFFF)); + rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, bank, offset, new); + + return rc; +} + +static int lan87xx_phy_init(struct phy_device *phydev) +{ + static const struct access_ereg_val init[] = { + /* TX Amplitude = 5 */ + {PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_AFE, 0x0B, + 0x000A, 0x001E}, + /* Clear SMI interrupts */ + {PHYACC_ATTR_MODE_READ, PHYACC_ATTR_BANK_SMI, 0x18, + 0, 0}, + /* Clear MISC interrupts */ + {PHYACC_ATTR_MODE_READ, PHYACC_ATTR_BANK_MISC, 0x08, + 0, 0}, + /* Turn on TC10 Ring Oscillator (ROSC) */ + {PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_MISC, 0x20, + 0x0020, 0x0020}, + /* WUR Detect Length to 1.2uS, LPC Detect Length to 1.09uS */ + {PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_PCS, 0x20, + 0x283C, 0}, + /* Wake_In Debounce Length to 39uS, Wake_Out Length to 79uS */ + {PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x21, + 0x274F, 0}, + /* Enable Auto Wake Forward to Wake_Out, ROSC on, Sleep, + * and Wake_In to wake PHY + */ + {PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x20, + 0x80A7, 0}, + /* Enable WUP Auto Fwd, Enable Wake on MDI, Wakeup Debouncer + * to 128 uS + */ + {PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x24, + 0xF110, 0}, + /* Enable HW Init */ + {PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_SMI, 0x1A, + 0x0100, 0x0100}, + }; + int rc, i; + + /* Start manual initialization procedures in Managed Mode */ + rc = access_ereg_modify_changed(phydev, PHYACC_ATTR_BANK_SMI, + 0x1a, 0x0000, 0x0100); + if (rc < 0) + return rc; + + /* Soft Reset the SMI block */ + rc = access_ereg_modify_changed(phydev, PHYACC_ATTR_BANK_SMI, + 0x00, 0x8000, 0x8000); + if (rc < 0) + return rc; + + /* Check to see if the self-clearing bit is cleared */ + usleep_range(1000, 2000); + rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, + PHYACC_ATTR_BANK_SMI, 0x00, 0); + if (rc < 0) + return rc; + if ((rc & 0x8000) != 0) + return -ETIMEDOUT; + + /* PHY Initialization */ + for (i = 0; i < ARRAY_SIZE(init); i++) { + if (init[i].mode == PHYACC_ATTR_MODE_MODIFY) { + rc = access_ereg_modify_changed(phydev, init[i].bank, + init[i].offset, + init[i].val, + init[i].mask); + } else { + rc = access_ereg(phydev, init[i].mode, init[i].bank, + init[i].offset, init[i].val); + } + if (rc < 0) + return rc; + } + + return 0; +} + static int lan87xx_phy_config_intr(struct phy_device *phydev) { int rc, val = 0; @@ -40,6 +203,13 @@ static int lan87xx_phy_ack_interrupt(struct phy_device *phydev) return rc < 0 ? rc : 0; } +static int lan87xx_config_init(struct phy_device *phydev) +{ + int rc = lan87xx_phy_init(phydev); + + return rc < 0 ? rc : 0; +} + static struct phy_driver microchip_t1_phy_driver[] = { { .phy_id = 0x0007c150, @@ -48,6 +218,7 @@ static struct phy_driver microchip_t1_phy_driver[] = { .features = PHY_BASIC_T1_FEATURES, + .config_init = lan87xx_config_init, .config_aneg = genphy_config_aneg, .ack_interrupt = lan87xx_phy_ack_interrupt, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index acddef79f4e8..5391acdece05 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -1292,7 +1292,7 @@ out: */ static bool vsc8584_is_pkg_init(struct phy_device *phydev, bool reversed) { - struct mdio_device **map = phydev->mdio.bus->mdio_map; + struct mii_bus *bus = phydev->mdio.bus; struct vsc8531_private *vsc8531; struct phy_device *phy; int i, addr; @@ -1306,11 +1306,10 @@ static bool vsc8584_is_pkg_init(struct phy_device *phydev, bool reversed) else addr = vsc8531->base_addr + i; - if (!map[addr]) + phy = mdiobus_get_phy(bus, addr); + if (!phy) continue; - phy = container_of(map[addr], struct phy_device, mdio); - if ((phy->phy_id & phydev->drv->phy_id_mask) != (phydev->drv->phy_id & phydev->drv->phy_id_mask)) continue; diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c index 47caae770ffc..cc766b2d4136 100644 --- a/drivers/net/phy/nxp-tja11xx.c +++ b/drivers/net/phy/nxp-tja11xx.c @@ -6,15 +6,19 @@ #include <linux/delay.h> #include <linux/ethtool.h> #include <linux/kernel.h> +#include <linux/mdio.h> #include <linux/mii.h> #include <linux/module.h> #include <linux/phy.h> #include <linux/hwmon.h> #include <linux/bitfield.h> +#include <linux/of_mdio.h> +#include <linux/of_irq.h> #define PHY_ID_MASK 0xfffffff0 #define PHY_ID_TJA1100 0x0180dc40 #define PHY_ID_TJA1101 0x0180dd00 +#define PHY_ID_TJA1102 0x0180dc80 #define MII_ECTRL 17 #define MII_ECTRL_LINK_CONTROL BIT(15) @@ -40,6 +44,10 @@ #define MII_INTSRC_TEMP_ERR BIT(1) #define MII_INTSRC_UV_ERR BIT(3) +#define MII_INTEN 22 +#define MII_INTEN_LINK_FAIL BIT(10) +#define MII_INTEN_LINK_UP BIT(9) + #define MII_COMMSTAT 23 #define MII_COMMSTAT_LINK_UP BIT(15) @@ -52,6 +60,8 @@ struct tja11xx_priv { char *hwmon_name; struct device *hwmon_dev; + struct phy_device *phydev; + struct work_struct phy_register_work; }; struct tja11xx_phy_stats { @@ -180,6 +190,7 @@ static int tja11xx_config_init(struct phy_device *phydev) return ret; break; case PHY_ID_TJA1101: + case PHY_ID_TJA1102: ret = phy_set_bits(phydev, MII_COMMCFG, MII_COMMCFG_AUTO_OP); if (ret) return ret; @@ -317,16 +328,12 @@ static const struct hwmon_chip_info tja11xx_hwmon_chip_info = { .info = tja11xx_hwmon_info, }; -static int tja11xx_probe(struct phy_device *phydev) +static int tja11xx_hwmon_register(struct phy_device *phydev, + struct tja11xx_priv *priv) { struct device *dev = &phydev->mdio.dev; - struct tja11xx_priv *priv; int i; - priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - priv->hwmon_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL); if (!priv->hwmon_name) return -ENOMEM; @@ -344,6 +351,152 @@ static int tja11xx_probe(struct phy_device *phydev) return PTR_ERR_OR_ZERO(priv->hwmon_dev); } +static int tja11xx_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct tja11xx_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->phydev = phydev; + + return tja11xx_hwmon_register(phydev, priv); +} + +static void tja1102_p1_register(struct work_struct *work) +{ + struct tja11xx_priv *priv = container_of(work, struct tja11xx_priv, + phy_register_work); + struct phy_device *phydev_phy0 = priv->phydev; + struct mii_bus *bus = phydev_phy0->mdio.bus; + struct device *dev = &phydev_phy0->mdio.dev; + struct device_node *np = dev->of_node; + struct device_node *child; + int ret; + + for_each_available_child_of_node(np, child) { + struct phy_device *phy; + int addr; + + addr = of_mdio_parse_addr(dev, child); + if (addr < 0) { + dev_err(dev, "Can't parse addr\n"); + continue; + } else if (addr != phydev_phy0->mdio.addr + 1) { + /* Currently we care only about double PHY chip TJA1102. + * If some day NXP will decide to bring chips with more + * PHYs, this logic should be reworked. + */ + dev_err(dev, "Unexpected address. Should be: %i\n", + phydev_phy0->mdio.addr + 1); + continue; + } + + if (mdiobus_is_registered_device(bus, addr)) { + dev_err(dev, "device is already registered\n"); + continue; + } + + /* Real PHY ID of Port 1 is 0 */ + phy = phy_device_create(bus, addr, PHY_ID_TJA1102, false, NULL); + if (IS_ERR(phy)) { + dev_err(dev, "Can't create PHY device for Port 1: %i\n", + addr); + continue; + } + + /* Overwrite parent device. phy_device_create() set parent to + * the mii_bus->dev, which is not correct in case. + */ + phy->mdio.dev.parent = dev; + + ret = of_mdiobus_phy_device_register(bus, phy, child, addr); + if (ret) { + /* All resources needed for Port 1 should be already + * available for Port 0. Both ports use the same + * interrupt line, so -EPROBE_DEFER would make no sense + * here. + */ + dev_err(dev, "Can't register Port 1. Unexpected error: %i\n", + ret); + phy_device_free(phy); + } + } +} + +static int tja1102_p0_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct tja11xx_priv *priv; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->phydev = phydev; + INIT_WORK(&priv->phy_register_work, tja1102_p1_register); + + ret = tja11xx_hwmon_register(phydev, priv); + if (ret) + return ret; + + schedule_work(&priv->phy_register_work); + + return 0; +} + +static int tja1102_match_phy_device(struct phy_device *phydev, bool port0) +{ + int ret; + + if ((phydev->phy_id & PHY_ID_MASK) != PHY_ID_TJA1102) + return 0; + + ret = phy_read(phydev, MII_PHYSID2); + if (ret < 0) + return ret; + + /* TJA1102 Port 1 has phyid 0 and doesn't support temperature + * and undervoltage alarms. + */ + if (port0) + return ret ? 1 : 0; + + return !ret; +} + +static int tja1102_p0_match_phy_device(struct phy_device *phydev) +{ + return tja1102_match_phy_device(phydev, true); +} + +static int tja1102_p1_match_phy_device(struct phy_device *phydev) +{ + return tja1102_match_phy_device(phydev, false); +} + +static int tja11xx_ack_interrupt(struct phy_device *phydev) +{ + int ret; + + ret = phy_read(phydev, MII_INTSRC); + + return (ret < 0) ? ret : 0; +} + +static int tja11xx_config_intr(struct phy_device *phydev) +{ + int value = 0; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + value = MII_INTEN_LINK_FAIL | MII_INTEN_LINK_UP; + + return phy_write(phydev, MII_INTEN, value); +} + static struct phy_driver tja11xx_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA1100), @@ -375,6 +528,41 @@ static struct phy_driver tja11xx_driver[] = { .get_sset_count = tja11xx_get_sset_count, .get_strings = tja11xx_get_strings, .get_stats = tja11xx_get_stats, + }, { + .name = "NXP TJA1102 Port 0", + .features = PHY_BASIC_T1_FEATURES, + .probe = tja1102_p0_probe, + .soft_reset = tja11xx_soft_reset, + .config_init = tja11xx_config_init, + .read_status = tja11xx_read_status, + .match_phy_device = tja1102_p0_match_phy_device, + .suspend = genphy_suspend, + .resume = genphy_resume, + .set_loopback = genphy_loopback, + /* Statistics */ + .get_sset_count = tja11xx_get_sset_count, + .get_strings = tja11xx_get_strings, + .get_stats = tja11xx_get_stats, + .ack_interrupt = tja11xx_ack_interrupt, + .config_intr = tja11xx_config_intr, + + }, { + .name = "NXP TJA1102 Port 1", + .features = PHY_BASIC_T1_FEATURES, + /* currently no probe for Port 1 is need */ + .soft_reset = tja11xx_soft_reset, + .config_init = tja11xx_config_init, + .read_status = tja11xx_read_status, + .match_phy_device = tja1102_p1_match_phy_device, + .suspend = genphy_suspend, + .resume = genphy_resume, + .set_loopback = genphy_loopback, + /* Statistics */ + .get_sset_count = tja11xx_get_sset_count, + .get_strings = tja11xx_get_strings, + .get_stats = tja11xx_get_stats, + .ack_interrupt = tja11xx_ack_interrupt, + .config_intr = tja11xx_config_intr, } }; @@ -383,6 +571,7 @@ module_phy_driver(tja11xx_driver); static struct mdio_device_id __maybe_unused tja11xx_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA1100) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA1101) }, + { PHY_ID_MATCH_MODEL(PHY_ID_TJA1102) }, { } }; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 67ba47ae5284..defe09d94422 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -564,6 +564,5 @@ struct phy_driver genphy_c45_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic Clause 45 PHY", - .soft_reset = genphy_no_soft_reset, .read_status = genphy_c45_read_status, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index ac2784192472..7e1ddd5745d2 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1082,8 +1082,12 @@ int phy_init_hw(struct phy_device *phydev) if (!phydev->drv) return 0; - if (phydev->drv->soft_reset) + if (phydev->drv->soft_reset) { ret = phydev->drv->soft_reset(phydev); + /* see comment in genphy_soft_reset for an explanation */ + if (!ret) + phydev->suspended = 0; + } if (ret < 0) return ret; @@ -1524,6 +1528,9 @@ int phy_suspend(struct phy_device *phydev) struct phy_driver *phydrv = phydev->drv; int ret; + if (phydev->suspended) + return 0; + /* If the device has WOL enabled, we cannot suspend the PHY */ phy_ethtool_get_wol(phydev, &wol); if (wol.wolopts || (netdev && netdev->wol_enabled)) @@ -2154,6 +2161,12 @@ int genphy_soft_reset(struct phy_device *phydev) if (ret < 0) return ret; + /* Clause 22 states that setting bit BMCR_RESET sets control registers + * to their default value. Therefore the POWER DOWN bit is supposed to + * be cleared after soft reset. + */ + phydev->suspended = 0; + ret = phy_poll_reset(phydev); if (ret) return ret; @@ -2627,7 +2640,6 @@ static struct phy_driver genphy_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic PHY", - .soft_reset = genphy_no_soft_reset, .get_features = genphy_read_abilities, .suspend = genphy_suspend, .resume = genphy_resume, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 34ca12aec61b..0f23bec431c1 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -480,8 +480,8 @@ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_state *state) { *state = pl->link_config; - if (pl->get_fixed_state) - pl->get_fixed_state(pl->netdev, state); + if (pl->config->get_fixed_state) + pl->config->get_fixed_state(pl->config, state); else if (pl->link_gpio) state->link = !!gpiod_get_value_cansleep(pl->link_gpio); @@ -1045,32 +1045,6 @@ void phylink_disconnect_phy(struct phylink *pl) EXPORT_SYMBOL_GPL(phylink_disconnect_phy); /** - * phylink_fixed_state_cb() - allow setting a fixed link callback - * @pl: a pointer to a &struct phylink returned from phylink_create() - * @cb: callback to execute to determine the fixed link state. - * - * The MAC driver should call this driver when the state of its link - * can be determined through e.g: an out of band MMIO register. - */ -int phylink_fixed_state_cb(struct phylink *pl, - void (*cb)(struct net_device *dev, - struct phylink_link_state *state)) -{ - /* It does not make sense to let the link be overriden unless we use - * MLO_AN_FIXED - */ - if (pl->cfg_link_an_mode != MLO_AN_FIXED) - return -EINVAL; - - mutex_lock(&pl->state_mutex); - pl->get_fixed_state = cb; - mutex_unlock(&pl->state_mutex); - - return 0; -} -EXPORT_SYMBOL_GPL(phylink_fixed_state_cb); - -/** * phylink_mac_change() - notify phylink of a change in MAC state * @pl: a pointer to a &struct phylink returned from phylink_create() * @up: indicates whether the link is currently up. @@ -1106,6 +1080,8 @@ static irqreturn_t phylink_link_handler(int irq, void *data) */ void phylink_start(struct phylink *pl) { + bool poll = false; + ASSERT_RTNL(); phylink_info(pl, "configuring for %s/%s link mode\n", @@ -1142,10 +1118,18 @@ void phylink_start(struct phylink *pl) irq = 0; } if (irq <= 0) - mod_timer(&pl->link_poll, jiffies + HZ); + poll = true; + } + + switch (pl->cfg_link_an_mode) { + case MLO_AN_FIXED: + poll |= pl->config->poll_fixed_state; + break; + case MLO_AN_INBAND: + poll |= pl->config->pcs_poll; + break; } - if ((pl->cfg_link_an_mode == MLO_AN_FIXED && pl->get_fixed_state) || - pl->config->pcs_poll) + if (poll) mod_timer(&pl->link_poll, jiffies + HZ); if (pl->phydev) phy_start(pl->phydev); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 2d99e9de6ee1..c7229d022a27 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -11,6 +11,7 @@ #include <linux/bitops.h> #include <linux/phy.h> #include <linux/module.h> +#include <linux/delay.h> #define RTL821x_PHYSR 0x11 #define RTL821x_PHYSR_DUPLEX BIT(13) @@ -526,6 +527,16 @@ static int rtl8125_match_phy_device(struct phy_device *phydev) rtlgen_supports_2_5gbps(phydev); } +static int rtlgen_resume(struct phy_device *phydev) +{ + int ret = genphy_resume(phydev); + + /* Internal PHY's from RTL8168h up may not be instantly ready */ + msleep(20); + + return ret; +} + static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), @@ -609,7 +620,7 @@ static struct phy_driver realtek_drvs[] = { .match_phy_device = rtlgen_match_phy_device, .read_status = rtlgen_read_status, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = rtlgen_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, .read_mmd = rtlgen_read_mmd, @@ -621,7 +632,7 @@ static struct phy_driver realtek_drvs[] = { .config_aneg = rtl8125_config_aneg, .read_status = rtl8125_read_status, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = rtlgen_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, .read_mmd = rtl8125_read_mmd, diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c index beb054b931ee..8057ea8dbc21 100644 --- a/drivers/net/phy/teranetics.c +++ b/drivers/net/phy/teranetics.c @@ -78,7 +78,6 @@ static struct phy_driver teranetics_driver[] = { .phy_id_mask = 0xffffffff, .name = "Teranetics TN2020", .features = PHY_10GBIT_FEATURES, - .soft_reset = genphy_no_soft_reset, .aneg_done = teranetics_aneg_done, .config_aneg = gen10g_config_aneg, .read_status = teranetics_read_status, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 4004f98e50d9..04845a4017f9 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -468,6 +468,9 @@ static const struct team_mode *team_mode_get(const char *kind) struct team_mode_item *mitem; const struct team_mode *mode = NULL; + if (!try_module_get(THIS_MODULE)) + return NULL; + spin_lock(&mode_list_lock); mitem = __find_mode(kind); if (!mitem) { @@ -483,6 +486,7 @@ static const struct team_mode *team_mode_get(const char *kind) } spin_unlock(&mode_list_lock); + module_put(THIS_MODULE); return mode; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 07476c6510f2..44889eba1dbc 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1888,6 +1888,7 @@ drop: skb_reset_network_header(skb); skb_probe_transport_header(skb); + skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { struct bpf_prog *xdp_prog; @@ -2459,6 +2460,7 @@ build: skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); skb_probe_transport_header(skb); + skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { err = do_xdp_generic(xdp_prog, skb); @@ -2470,7 +2472,6 @@ build: !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); - skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); /* No need for get_cpu_ptr() here since this function is diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 66e00ddc0d42..56f8aab46f89 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -188,8 +188,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, fl6.flowi6_proto = iph->nexthdr; fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; - dst = ip6_route_output(net, NULL, &fl6); - if (dst == dst_null) + dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst) || dst == dst_null) goto err; skb_dst_drop(skb); @@ -474,7 +474,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; - if (qdisc_tx_is_default(vrf_dev)) + if (qdisc_tx_is_default(vrf_dev) || + IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); return vrf_ip6_out_redirect(vrf_dev, skb); @@ -686,7 +687,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; - if (qdisc_tx_is_default(vrf_dev)) + if (qdisc_tx_is_default(vrf_dev) || + IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); return vrf_ip_out_redirect(vrf_dev, skb); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 45308b3350cf..a5b415fed11e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3144,7 +3144,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); if (id >= VXLAN_N_VID) { - NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], "VXLAN ID must be lower than 16777216"); return -ERANGE; } @@ -3155,7 +3155,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], = nla_data(data[IFLA_VXLAN_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { - NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], "Invalid source port range"); return -EINVAL; } @@ -3165,7 +3165,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); if (df < 0 || df > VXLAN_DF_MAX) { - NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF], + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], "Invalid DF attribute"); return -EINVAL; } diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c index 529ebca1e9e1..1f7709d24f35 100644 --- a/drivers/net/wimax/i2400m/usb-fw.c +++ b/drivers/net/wimax/i2400m/usb-fw.c @@ -354,6 +354,7 @@ out: usb_autopm_put_interface(i2400mu->usb_iface); d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n", i2400m, ack, ack_size, (long) result); + usb_put_urb(¬if_urb); return result; error_exceeded: diff --git a/drivers/net/wireless/ath/ath11k/thermal.h b/drivers/net/wireless/ath/ath11k/thermal.h index 459b8d49c184..f9af55f3682d 100644 --- a/drivers/net/wireless/ath/ath11k/thermal.h +++ b/drivers/net/wireless/ath/ath11k/thermal.h @@ -36,12 +36,13 @@ static inline int ath11k_thermal_register(struct ath11k_base *sc) return 0; } -static inline void ath11k_thermal_unregister(struct ath11k *ar) +static inline void ath11k_thermal_unregister(struct ath11k_base *sc) { } static inline int ath11k_thermal_set_throttling(struct ath11k *ar, u32 throttle_state) { + return 0; } static inline void ath11k_thermal_event_temperature(struct ath11k *ar, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index 23627c953a5e..436f501be937 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -729,9 +729,18 @@ static int brcmf_net_mon_stop(struct net_device *ndev) return err; } +static netdev_tx_t brcmf_net_mon_start_xmit(struct sk_buff *skb, + struct net_device *ndev) +{ + dev_kfree_skb_any(skb); + + return NETDEV_TX_OK; +} + static const struct net_device_ops brcmf_netdev_ops_mon = { .ndo_open = brcmf_net_mon_open, .ndo_stop = brcmf_net_mon_stop, + .ndo_start_xmit = brcmf_net_mon_start_xmit, }; int brcmf_net_mon_attach(struct brcmf_if *ifp) diff --git a/drivers/net/wireless/intel/iwlegacy/3945-rs.c b/drivers/net/wireless/intel/iwlegacy/3945-rs.c index 6209f85a71dd..0af9e997c9f6 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945-rs.c +++ b/drivers/net/wireless/intel/iwlegacy/3945-rs.c @@ -374,7 +374,7 @@ out: } static void * -il3945_rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +il3945_rs_alloc(struct ieee80211_hw *hw) { return hw->priv; } diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c index 7c6e2c863497..0a02d8aca320 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c @@ -2474,7 +2474,7 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta, } static void * -il4965_rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +il4965_rs_alloc(struct ieee80211_hw *hw) { return hw->priv; } diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c index 226165db7dfd..dac809df7f1d 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c @@ -3019,7 +3019,7 @@ static void rs_fill_link_cmd(struct iwl_priv *priv, cpu_to_le16(priv->lib->bt_params->agg_time_limit); } -static void *rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +static void *rs_alloc(struct ieee80211_hw *hw) { return hw->priv; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index ba2aff3af0fe..e3a33388be70 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -296,9 +296,14 @@ int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt, if (!prof->enabled) { IWL_DEBUG_RADIO(fwrt, "SAR profile %d is disabled.\n", profs[i]); - /* if one of the profiles is disabled, we fail all */ - return -ENOENT; + /* + * if one of the profiles is disabled, we + * ignore all of them and return 1 to + * differentiate disabled from other failures. + */ + return 1; } + IWL_DEBUG_INFO(fwrt, "SAR EWRD: chain %d profile index %d\n", i, profs[i]); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h index 73196cbc7fbe..75d958bab0e3 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h @@ -8,7 +8,7 @@ * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2019 Intel Corporation + * Copyright(c) 2019 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2019 Intel Corporation + * Copyright(c) 2019 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -99,7 +99,7 @@ enum iwl_mvm_dqa_txq { IWL_MVM_DQA_MAX_MGMT_QUEUE = 8, IWL_MVM_DQA_AP_PROBE_RESP_QUEUE = 9, IWL_MVM_DQA_MIN_DATA_QUEUE = 10, - IWL_MVM_DQA_MAX_DATA_QUEUE = 31, + IWL_MVM_DQA_MAX_DATA_QUEUE = 30, }; enum iwl_mvm_tx_fifo { diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index ff52e69c1c80..eeb750bdbda1 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1467,7 +1467,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) kmemdup(pieces->dbg_conf_tlv[i], pieces->dbg_conf_tlv_len[i], GFP_KERNEL); - if (!pieces->dbg_conf_tlv[i]) + if (!drv->fw.dbg.conf_tlv[i]) goto out_free_fw; } } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 9e9810d2b262..ccf0bc16465d 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -532,8 +532,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = - IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP | - IEEE80211_HE_MAC_CAP2_ACK_EN, + IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, @@ -617,8 +616,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = - IEEE80211_HE_MAC_CAP2_BSR | - IEEE80211_HE_MAC_CAP2_ACK_EN, + IEEE80211_HE_MAC_CAP2_BSR, .mac_cap_info[3] = IEEE80211_HE_MAC_CAP3_OMI_CONTROL | IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index a4038f289ab3..e67c452fa92c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -727,6 +727,7 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) struct iwl_dev_tx_power_cmd_v4 v4; } cmd; + int ret; u16 len = 0; cmd.v5.v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS); @@ -741,9 +742,14 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) len = sizeof(cmd.v4.v3); - if (iwl_sar_select_profile(&mvm->fwrt, cmd.v5.v3.per_chain_restriction, - prof_a, prof_b)) - return -ENOENT; + ret = iwl_sar_select_profile(&mvm->fwrt, + cmd.v5.v3.per_chain_restriction, + prof_a, prof_b); + + /* return on error or if the profile is disabled (positive number) */ + if (ret) + return ret; + IWL_DEBUG_RADIO(mvm, "Sending REDUCE_TX_POWER_CMD per chain\n"); return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd); } @@ -1034,16 +1040,7 @@ static int iwl_mvm_sar_init(struct iwl_mvm *mvm) "EWRD SAR BIOS table invalid or unavailable. (%d)\n", ret); - ret = iwl_mvm_sar_select_profile(mvm, 1, 1); - /* - * If we don't have profile 0 from BIOS, just skip it. This - * means that SAR Geo will not be enabled either, even if we - * have other valid profiles. - */ - if (ret == -ENOENT) - return 1; - - return ret; + return iwl_mvm_sar_select_profile(mvm, 1, 1); } static int iwl_mvm_load_rt_fw(struct iwl_mvm *mvm) @@ -1272,7 +1269,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm) ret = iwl_mvm_sar_init(mvm); if (ret == 0) { ret = iwl_mvm_sar_geo_init(mvm); - } else if (ret > 0 && !iwl_sar_get_wgds_table(&mvm->fwrt)) { + } else if (ret == -ENOENT && !iwl_sar_get_wgds_table(&mvm->fwrt)) { /* * If basic SAR is not available, we check for WGDS, * which should *not* be available either. If it is diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index c1aba2bf73cf..00e7fdbaeb7f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -3665,7 +3665,7 @@ static void rs_fill_lq_cmd(struct iwl_mvm *mvm, cpu_to_le16(iwl_mvm_coex_agg_time_limit(mvm, sta)); } -static void *rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +static void *rs_alloc(struct ieee80211_hw *hw) { return hw->priv; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 5ee33c8ae9d2..77b8def26edb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -8,7 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2018 - 2020 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 - 2019 Intel Corporation + * Copyright(c) 2018 - 2020 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -566,6 +566,7 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_mvm_stat_data { struct iwl_mvm *mvm; + __le32 flags; __le32 mac_id; u8 beacon_filter_average_energy; void *general; @@ -606,6 +607,13 @@ static void iwl_mvm_stat_iterator(void *_data, u8 *mac, -general->beacon_average_energy[vif_id]; } + /* make sure that beacon statistics don't go backwards with TCM + * request to clear statistics + */ + if (le32_to_cpu(data->flags) & IWL_STATISTICS_REPLY_FLG_CLEAR) + mvmvif->beacon_stats.accu_num_beacons += + mvmvif->beacon_stats.num_beacons; + if (mvmvif->id != id) return; @@ -763,6 +771,7 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm, flags = stats->flag; } + data.flags = flags; iwl_mvm_rx_stats_check_trigger(mvm, pkt); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 64ef3f3ba23b..56ae72debb96 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -722,6 +722,11 @@ static int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id, lockdep_assert_held(&mvm->mutex); + if (WARN(maxq >= mvm->trans->trans_cfg->base_params->num_of_queues, + "max queue %d >= num_of_queues (%d)", maxq, + mvm->trans->trans_cfg->base_params->num_of_queues)) + maxq = mvm->trans->trans_cfg->base_params->num_of_queues - 1; + /* This should not be hit with new TX path */ if (WARN_ON(iwl_mvm_has_new_tx_api(mvm))) return -ENOSPC; @@ -1164,9 +1169,9 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta) inactive_tid_bitmap, &unshare_queues, &changetid_queues); - if (ret >= 0 && free_queue < 0) { + if (ret && free_queue < 0) { queue_owner = sta; - free_queue = ret; + free_queue = i; } /* only unlock sta lock - we still need the queue info lock */ spin_unlock_bh(&mvmsta->lock); 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 01f248ba8fec..9d5b1e51b50d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -129,6 +129,18 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, int cmdq_size = max_t(u32, IWL_CMD_QUEUE_SIZE, trans->cfg->min_txq_size); + switch (trans_pcie->rx_buf_size) { + case IWL_AMSDU_DEF: + return -EINVAL; + case IWL_AMSDU_2K: + break; + case IWL_AMSDU_4K: + case IWL_AMSDU_8K: + case IWL_AMSDU_12K: + control_flags |= IWL_PRPH_SCRATCH_RB_SIZE_4K; + break; + } + /* Allocate prph scratch */ prph_scratch = dma_alloc_coherent(trans->dev, sizeof(*prph_scratch), &trans_pcie->prph_scratch_dma_addr, @@ -143,10 +155,8 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV)); prph_sc_ctrl->version.size = cpu_to_le16(sizeof(*prph_scratch) / 4); - control_flags = IWL_PRPH_SCRATCH_RB_SIZE_4K | - IWL_PRPH_SCRATCH_MTR_MODE | - (IWL_PRPH_MTR_FORMAT_256B & - IWL_PRPH_SCRATCH_MTR_FORMAT); + control_flags |= IWL_PRPH_SCRATCH_MTR_MODE; + control_flags |= IWL_PRPH_MTR_FORMAT_256B & IWL_PRPH_SCRATCH_MTR_FORMAT; /* initialize RX default queue */ prph_sc_ctrl->rbd_cfg.free_rbd_addr = diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 86fc00167817..9664dbc70ef1 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -1418,6 +1418,9 @@ void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue) iwl_pcie_gen2_txq_unmap(trans, queue); + iwl_pcie_gen2_txq_free_memory(trans, trans_pcie->txq[queue]); + trans_pcie->txq[queue] = NULL; + IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue); } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 7fe8207db6ae..0528d4cb4d37 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3669,9 +3669,9 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) } if (info->attrs[HWSIM_ATTR_RADIO_NAME]) { - hwname = kasprintf(GFP_KERNEL, "%.*s", - nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), - (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME])); + hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]), + nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), + GFP_KERNEL); if (!hwname) return -ENOMEM; param.hwname = hwname; @@ -3691,9 +3691,9 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_RADIO_ID]) { idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]); } else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) { - hwname = kasprintf(GFP_KERNEL, "%.*s", - nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), - (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME])); + hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]), + nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]), + GFP_KERNEL); if (!hwname) return -ENOMEM; } else @@ -4068,7 +4068,7 @@ static void hwsim_virtio_rx_work(struct work_struct *work) } vq = hwsim_vqs[HWSIM_VQ_RX]; sg_init_one(sg, skb->head, skb_end_offset(skb)); - err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL); + err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_ATOMIC); if (WARN(err, "virtqueue_add_inbuf returned %d\n", err)) nlmsg_free(skb); else diff --git a/drivers/net/wireless/realtek/rtlwifi/rc.c b/drivers/net/wireless/realtek/rtlwifi/rc.c index 0c7d74902d33..4b5ea0ec9109 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rc.c +++ b/drivers/net/wireless/realtek/rtlwifi/rc.c @@ -261,7 +261,7 @@ static void rtl_rate_update(void *ppriv, { } -static void *rtl_rate_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +static void *rtl_rate_alloc(struct ieee80211_hw *hw) { struct rtl_priv *rtlpriv = rtl_priv(hw); return rtlpriv; diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c index e37c71495c0d..1af87eb2e53a 100644 --- a/drivers/net/wireless/realtek/rtw88/pci.c +++ b/drivers/net/wireless/realtek/rtw88/pci.c @@ -1338,22 +1338,17 @@ static void rtw_pci_phy_cfg(struct rtw_dev *rtwdev) rtw_pci_link_cfg(rtwdev); } -#ifdef CONFIG_PM -static int rtw_pci_suspend(struct device *dev) +static int __maybe_unused rtw_pci_suspend(struct device *dev) { return 0; } -static int rtw_pci_resume(struct device *dev) +static int __maybe_unused rtw_pci_resume(struct device *dev) { return 0; } static SIMPLE_DEV_PM_OPS(rtw_pm_ops, rtw_pci_suspend, rtw_pci_resume); -#define RTW_PM_OPS (&rtw_pm_ops) -#else -#define RTW_PM_OPS NULL -#endif static int rtw_pci_claim(struct rtw_dev *rtwdev, struct pci_dev *pdev) { @@ -1582,7 +1577,7 @@ static struct pci_driver rtw_pci_driver = { .id_table = rtw_pci_id_table, .probe = rtw_pci_probe, .remove = rtw_pci_remove, - .driver.pm = RTW_PM_OPS, + .driver.pm = &rtw_pm_ops, }; module_pci_driver(rtw_pci_driver); diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 9f982c0627a0..a04afe79529c 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -60,39 +60,15 @@ static struct mii_timestamper *of_find_mii_timestamper(struct device_node *node) return register_mii_timestamper(arg.np, arg.args[0]); } -static int of_mdiobus_register_phy(struct mii_bus *mdio, - struct device_node *child, u32 addr) +int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, + struct device_node *child, u32 addr) { - struct mii_timestamper *mii_ts; - struct phy_device *phy; - bool is_c45; int rc; - u32 phy_id; - - mii_ts = of_find_mii_timestamper(child); - if (IS_ERR(mii_ts)) - return PTR_ERR(mii_ts); - - is_c45 = of_device_is_compatible(child, - "ethernet-phy-ieee802.3-c45"); - - if (!is_c45 && !of_get_phy_id(child, &phy_id)) - phy = phy_device_create(mdio, addr, phy_id, 0, NULL); - else - phy = get_phy_device(mdio, addr, is_c45); - if (IS_ERR(phy)) { - if (mii_ts) - unregister_mii_timestamper(mii_ts); - return PTR_ERR(phy); - } rc = of_irq_get(child, 0); - if (rc == -EPROBE_DEFER) { - if (mii_ts) - unregister_mii_timestamper(mii_ts); - phy_device_free(phy); + if (rc == -EPROBE_DEFER) return rc; - } + if (rc > 0) { phy->irq = rc; mdio->irq[addr] = rc; @@ -118,10 +94,47 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, * register it */ rc = phy_device_register(phy); if (rc) { + of_node_put(child); + return rc; + } + + dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n", + child, addr); + return 0; +} +EXPORT_SYMBOL(of_mdiobus_phy_device_register); + +static int of_mdiobus_register_phy(struct mii_bus *mdio, + struct device_node *child, u32 addr) +{ + struct mii_timestamper *mii_ts; + struct phy_device *phy; + bool is_c45; + int rc; + u32 phy_id; + + mii_ts = of_find_mii_timestamper(child); + if (IS_ERR(mii_ts)) + return PTR_ERR(mii_ts); + + is_c45 = of_device_is_compatible(child, + "ethernet-phy-ieee802.3-c45"); + + if (!is_c45 && !of_get_phy_id(child, &phy_id)) + phy = phy_device_create(mdio, addr, phy_id, 0, NULL); + else + phy = get_phy_device(mdio, addr, is_c45); + if (IS_ERR(phy)) { + if (mii_ts) + unregister_mii_timestamper(mii_ts); + return PTR_ERR(phy); + } + + rc = of_mdiobus_phy_device_register(mdio, phy, child, addr); + if (rc) { if (mii_ts) unregister_mii_timestamper(mii_ts); phy_device_free(phy); - of_node_put(child); return rc; } @@ -132,8 +145,6 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, if (mii_ts) phy->mii_ts = mii_ts; - dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n", - child, addr); return 0; } diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index c9219fddf44b..50bbe0edf538 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -261,6 +261,8 @@ static struct property *dup_and_fixup_symbol_prop( of_property_set_flag(new_prop, OF_DYNAMIC); + kfree(target_path); + return new_prop; err_free_new_prop: diff --git a/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts b/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts index c190da54f175..6327d1ffb963 100644 --- a/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts +++ b/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts @@ -3,22 +3,37 @@ /plugin/; /* - * &electric_1/motor-1 and &spin_ctrl_1 are the same node: - * /testcase-data-2/substation@100/motor-1 + * &electric_1/motor-1/electric and &spin_ctrl_1/electric are the same node: + * /testcase-data-2/substation@100/motor-1/electric * * Thus the property "rpm_avail" in each fragment will * result in an attempt to update the same property twice. * This will result in an error and the overlay apply * will fail. + * + * The previous version of this test did not include the extra + * level of node 'electric'. That resulted in the 'rpm_avail' + * property being located in the pre-existing node 'motor-1'. + * Modifying a property results in a WARNING that a memory leak + * will occur if the overlay is removed. Since the overlay apply + * fails, the memory leak does actually occur, and kmemleak will + * further report the memory leak if CONFIG_DEBUG_KMEMLEAK is + * enabled. Adding the overlay node 'electric' avoids the + * memory leak and thus people who use kmemleak will not + * have to debug this non-problem again. */ &electric_1 { motor-1 { - rpm_avail = < 100 >; + electric { + rpm_avail = < 100 >; + }; }; }; &spin_ctrl_1 { - rpm_avail = < 100 200 >; + electric { + rpm_avail = < 100 200 >; + }; }; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 7e27670c3616..398de04fd19c 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -861,6 +861,10 @@ static void __init of_unittest_changeset(void) unittest(!of_changeset_revert(&chgset), "revert failed\n"); of_changeset_destroy(&chgset); + + of_node_put(n1); + of_node_put(n2); + of_node_put(n21); #endif } @@ -1243,10 +1247,13 @@ static void __init of_unittest_platform_populate(void) of_platform_populate(np, match, NULL, &test_bus->dev); for_each_child_of_node(np, child) { - for_each_child_of_node(child, grandchild) - unittest(of_find_device_by_node(grandchild), + for_each_child_of_node(child, grandchild) { + pdev = of_find_device_by_node(grandchild); + unittest(pdev, "Could not create device for node '%pOFn'\n", grandchild); + of_dev_put(pdev); + } } of_platform_depopulate(&test_bus->dev); @@ -3087,8 +3094,11 @@ static __init void of_unittest_overlay_high_level(void) goto err_unlock; } if (__of_add_property(of_symbols, new_prop)) { + kfree(new_prop->name); + kfree(new_prop->value); + kfree(new_prop); /* "name" auto-generated by unflatten */ - if (!strcmp(new_prop->name, "name")) + if (!strcmp(prop->name, "name")) continue; unittest(0, "duplicate property '%s' in overlay_base node __symbols__", prop->name); @@ -3171,21 +3181,21 @@ static __init void of_unittest_overlay_high_level(void) "OF: overlay: ERROR: multiple fragments add and/or delete node /testcase-data-2/substation@100/motor-1/controller"); EXPECT_BEGIN(KERN_ERR, - "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail"); + "OF: overlay: ERROR: multiple fragments add and/or delete node /testcase-data-2/substation@100/motor-1/electric"); EXPECT_BEGIN(KERN_ERR, - "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail"); + "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/rpm_avail"); EXPECT_BEGIN(KERN_ERR, - "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/rpm_avail"); + "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/name"); unittest(overlay_data_apply("overlay_bad_add_dup_prop", NULL), "Adding overlay 'overlay_bad_add_dup_prop' failed\n"); EXPECT_END(KERN_ERR, - "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/rpm_avail"); + "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/name"); EXPECT_END(KERN_ERR, - "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail"); + "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/rpm_avail"); EXPECT_END(KERN_ERR, - "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail"); + "OF: overlay: ERROR: multiple fragments add and/or delete node /testcase-data-2/substation@100/motor-1/electric"); unittest(overlay_data_apply("overlay_bad_phandle", NULL), "Adding overlay 'overlay_bad_phandle' failed\n"); diff --git a/drivers/opp/core.c b/drivers/opp/core.c index ba43e6a3dc0a..e4f01e7771a2 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -819,6 +819,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) if (unlikely(!target_freq)) { if (opp_table->required_opp_tables) { ret = _set_required_opps(dev, opp_table, NULL); + } else if (!_get_opp_count(opp_table)) { + return 0; } else { dev_err(dev, "target frequency can't be 0\n"); ret = -EINVAL; @@ -849,6 +851,18 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) goto put_opp_table; } + /* + * For IO devices which require an OPP on some platforms/SoCs + * while just needing to scale the clock on some others + * we look for empty OPP tables with just a clock handle and + * scale only the clk. This makes dev_pm_opp_set_rate() + * equivalent to a clk_set_rate() + */ + if (!_get_opp_count(opp_table)) { + ret = _generic_set_opp_clk_only(dev, clk, freq); + goto put_opp_table; + } + temp_freq = old_freq; old_opp = _find_freq_ceil(opp_table, &temp_freq); if (IS_ERR(old_opp)) { diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 28c9a2409c50..ca9ed5774eb1 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5567,3 +5567,10 @@ static void pci_fixup_no_d0_pme(struct pci_dev *dev) dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x2142, pci_fixup_no_d0_pme); + +static void apex_pci_fixup_class(struct pci_dev *pdev) +{ + pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class; +} +DECLARE_PCI_FIXUP_CLASS_HEADER(0x1ac1, 0x089a, + PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class); diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index 230e6cf3da2f..c48e5b38a441 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -40,7 +40,7 @@ cros_sensorhub_send_sample(struct cros_ec_sensorhub *sensorhub, int id = sample->sensor_id; struct iio_dev *indio_dev; - if (id > sensorhub->sensor_num) + if (id >= sensorhub->sensor_num) return -EINVAL; cb = sensorhub->push_data[id].push_data_cb; @@ -820,7 +820,7 @@ static void cros_ec_sensorhub_ring_handler(struct cros_ec_sensorhub *sensorhub) if (fifo_info->count > sensorhub->fifo_size || fifo_info->size != sensorhub->fifo_size) { dev_warn(sensorhub->dev, - "Mismatch EC data: count %d, size %d - expected %d", + "Mismatch EC data: count %d, size %d - expected %d\n", fifo_info->count, fifo_info->size, sensorhub->fifo_size); goto error; @@ -851,14 +851,14 @@ static void cros_ec_sensorhub_ring_handler(struct cros_ec_sensorhub *sensorhub) } if (number_data > fifo_info->count - i) { dev_warn(sensorhub->dev, - "Invalid EC data: too many entry received: %d, expected %d", + "Invalid EC data: too many entry received: %d, expected %d\n", number_data, fifo_info->count - i); break; } if (out + number_data > sensorhub->ring + fifo_info->count) { dev_warn(sensorhub->dev, - "Too many samples: %d (%zd data) to %d entries for expected %d entries", + "Too many samples: %d (%zd data) to %d entries for expected %d entries\n", i, out - sensorhub->ring, i + number_data, fifo_info->count); break; diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c index 65c23ef6408d..b3c05ff05783 100644 --- a/drivers/power/supply/test_power.c +++ b/drivers/power/supply/test_power.c @@ -16,7 +16,7 @@ #include <linux/power_supply.h> #include <linux/errno.h> #include <linux/delay.h> -#include <linux/vermagic.h> +#include <generated/utsrelease.h> enum test_power_id { TEST_AC, diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 032e112c3dd9..a3f608832660 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -780,7 +780,7 @@ static int idtcm_load_firmware(struct idtcm *idtcm, /* Page size 128, last 4 bytes of page skipped */ if (((loaddr > 0x7b) && (loaddr <= 0x7f)) - || ((loaddr > 0xfb) && (loaddr <= 0xff))) + || loaddr > 0xfb) continue; err = idtcm_write(idtcm, regaddr, 0, &val, sizeof(val)); diff --git a/drivers/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c index b63ac240308b..179f6c472e50 100644 --- a/drivers/ptp/ptp_idt82p33.c +++ b/drivers/ptp/ptp_idt82p33.c @@ -23,12 +23,12 @@ MODULE_VERSION("1.0"); MODULE_LICENSE("GPL"); /* Module Parameters */ -u32 sync_tod_timeout = SYNC_TOD_TIMEOUT_SEC; +static u32 sync_tod_timeout = SYNC_TOD_TIMEOUT_SEC; module_param(sync_tod_timeout, uint, 0); MODULE_PARM_DESC(sync_tod_timeout, "duration in second to keep SYNC_TOD on (set to 0 to keep it always on)"); -u32 phase_snap_threshold = SNAP_THRESHOLD_NS; +static u32 phase_snap_threshold = SNAP_THRESHOLD_NS; module_param(phase_snap_threshold, uint, 0); MODULE_PARM_DESC(phase_snap_threshold, "threshold (150000ns by default) below which adjtime would ignore"); @@ -881,7 +881,7 @@ static int idt82p33_load_firmware(struct idt82p33 *idt82p33) /* Page size 128, last 4 bytes of page skipped */ if (((loaddr > 0x7b) && (loaddr <= 0x7f)) - || ((loaddr > 0xfb) && (loaddr <= 0xff))) + || loaddr > 0xfb) continue; err = idt82p33_write(idt82p33, _ADDR(page, loaddr), diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c index dfda54cbd866..52d77db39829 100644 --- a/drivers/ptp/ptp_ines.c +++ b/drivers/ptp/ptp_ines.c @@ -400,8 +400,8 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) ines_write32(port, ts_stat_rx, ts_stat_rx); ines_write32(port, ts_stat_tx, ts_stat_tx); - port->rxts_enabled = ts_stat_rx == TS_ENABLE ? true : false; - port->txts_enabled = ts_stat_tx == TS_ENABLE ? true : false; + port->rxts_enabled = ts_stat_rx == TS_ENABLE; + port->txts_enabled = ts_stat_tx == TS_ENABLE; spin_unlock_irqrestore(&port->lock, flags); diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c index fc7d0b77e118..658d33fc3195 100644 --- a/drivers/ptp/ptp_kvm.c +++ b/drivers/ptp/ptp_kvm.c @@ -22,7 +22,7 @@ struct kvm_ptp_clock { struct ptp_clock_info caps; }; -DEFINE_SPINLOCK(kvm_ptp_lock); +static DEFINE_SPINLOCK(kvm_ptp_lock); static struct pvclock_vsyscall_time_info *hv_clock; diff --git a/drivers/remoteproc/mtk_common.h b/drivers/remoteproc/mtk_common.h index deb20096146a..0066c83636d0 100644 --- a/drivers/remoteproc/mtk_common.h +++ b/drivers/remoteproc/mtk_common.h @@ -68,7 +68,7 @@ struct mtk_scp { wait_queue_head_t ack_wq; void __iomem *cpu_addr; - phys_addr_t phys_addr; + dma_addr_t dma_addr; size_t dram_size; struct rproc_subdev *rpmsg_subdev; diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index ea3743e7e794..2bead57c9cf9 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -330,7 +330,7 @@ static void *scp_da_to_va(struct rproc *rproc, u64 da, size_t len) if (offset >= 0 && (offset + len) < scp->sram_size) return (void __force *)scp->sram_base + offset; } else { - offset = da - scp->phys_addr; + offset = da - scp->dma_addr; if (offset >= 0 && (offset + len) < scp->dram_size) return (void __force *)scp->cpu_addr + offset; } @@ -451,7 +451,7 @@ static int scp_map_memory_region(struct mtk_scp *scp) /* Reserved SCP code size */ scp->dram_size = MAX_CODE_SIZE; scp->cpu_addr = dma_alloc_coherent(scp->dev, scp->dram_size, - &scp->phys_addr, GFP_KERNEL); + &scp->dma_addr, GFP_KERNEL); if (!scp->cpu_addr) return -ENOMEM; @@ -461,7 +461,7 @@ static int scp_map_memory_region(struct mtk_scp *scp) static void scp_unmap_memory_region(struct mtk_scp *scp) { dma_free_coherent(scp->dev, scp->dram_size, scp->cpu_addr, - scp->phys_addr); + scp->dma_addr); of_reserved_mem_device_release(scp->dev); } diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index ce49c3236ff7..5475d4f808a8 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -367,7 +367,7 @@ unroll_pd_votes: } return ret; -}; +} static void q6v5_pds_disable(struct q6v5 *qproc, struct device **pds, size_t pd_count) @@ -1527,7 +1527,7 @@ unroll_attach: dev_pm_domain_detach(devs[i], false); return ret; -}; +} static void q6v5_pds_detach(struct q6v5 *qproc, struct device **pds, size_t pd_count) @@ -1675,7 +1675,7 @@ static int q6v5_probe(struct platform_device *pdev) ret = of_property_read_string_index(pdev->dev.of_node, "firmware-name", 1, &qproc->hexagon_mdt_image); if (ret < 0 && ret != -EINVAL) - return ret; + goto free_rproc; platform_set_drvdata(pdev, qproc); @@ -1766,17 +1766,23 @@ static int q6v5_probe(struct platform_device *pdev) qproc->sysmon = qcom_add_sysmon_subdev(rproc, "modem", 0x12); if (IS_ERR(qproc->sysmon)) { ret = PTR_ERR(qproc->sysmon); - goto detach_proxy_pds; + goto remove_subdevs; } ret = rproc_add(rproc); if (ret) - goto detach_proxy_pds; + goto remove_sysmon_subdev; return 0; -detach_proxy_pds: +remove_sysmon_subdev: + qcom_remove_sysmon_subdev(qproc->sysmon); +remove_subdevs: qcom_remove_ipa_notify_subdev(qproc->rproc, &qproc->ipa_notify_subdev); + qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev); + qcom_remove_smd_subdev(rproc, &qproc->smd_subdev); + qcom_remove_glink_subdev(rproc, &qproc->glink_subdev); +detach_proxy_pds: q6v5_pds_detach(qproc, qproc->proxy_pds, qproc->proxy_pd_count); detach_active_pds: q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count); @@ -1789,19 +1795,20 @@ free_rproc: static int q6v5_remove(struct platform_device *pdev) { struct q6v5 *qproc = platform_get_drvdata(pdev); + struct rproc *rproc = qproc->rproc; - rproc_del(qproc->rproc); + rproc_del(rproc); qcom_remove_sysmon_subdev(qproc->sysmon); - qcom_remove_ipa_notify_subdev(qproc->rproc, &qproc->ipa_notify_subdev); - qcom_remove_glink_subdev(qproc->rproc, &qproc->glink_subdev); - qcom_remove_smd_subdev(qproc->rproc, &qproc->smd_subdev); - qcom_remove_ssr_subdev(qproc->rproc, &qproc->ssr_subdev); + qcom_remove_ipa_notify_subdev(rproc, &qproc->ipa_notify_subdev); + qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev); + qcom_remove_smd_subdev(rproc, &qproc->smd_subdev); + qcom_remove_glink_subdev(rproc, &qproc->glink_subdev); - q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count); q6v5_pds_detach(qproc, qproc->proxy_pds, qproc->proxy_pd_count); + q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count); - rproc_free(qproc->rproc); + rproc_free(rproc); return 0; } diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c index 7f8536b73295..52b871327b55 100644 --- a/drivers/remoteproc/remoteproc_sysfs.c +++ b/drivers/remoteproc/remoteproc_sysfs.c @@ -4,6 +4,7 @@ */ #include <linux/remoteproc.h> +#include <linux/slab.h> #include "remoteproc_internal.h" diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 6a66dbf2df40..0bdd56f02f18 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -19,6 +19,7 @@ #include <linux/regmap.h> #include <linux/remoteproc.h> #include <linux/reset.h> +#include <linux/slab.h> #include <linux/workqueue.h> #include "remoteproc_internal.h" diff --git a/drivers/rpmsg/mtk_rpmsg.c b/drivers/rpmsg/mtk_rpmsg.c index 232aa4e40133..83f2b8804ee9 100644 --- a/drivers/rpmsg/mtk_rpmsg.c +++ b/drivers/rpmsg/mtk_rpmsg.c @@ -8,6 +8,7 @@ #include <linux/platform_device.h> #include <linux/remoteproc.h> #include <linux/rpmsg/mtk_rpmsg.h> +#include <linux/slab.h> #include <linux/workqueue.h> #include "rpmsg_internal.h" diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index a8682f69effc..376f1efbbb86 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -26,7 +26,6 @@ config DASD def_tristate y prompt "Support for DASD devices" depends on CCW && BLOCK - select IOSCHED_DEADLINE help Enable this option if you want to access DASDs directly utilizing S/390s channel subsystem commands. This is necessary for running diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 17feff174f57..2017c43dac1b 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -127,7 +127,7 @@ config CHR_DEV_SG For scanners, look at SANE (<http://www.sane-project.org/>). For CD writer software look at Cdrtools - (<http://cdrecord.berlios.de/private/cdrecord.html>) + (<http://cdrtools.sourceforge.net/>) and for burning a "disk at once": CDRDAO (<http://cdrdao.sourceforge.net/>). Cdparanoia is a high quality digital reader of audio CDs (<http://www.xiph.org/paranoia/>). diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig index 90a17452a50d..13ed9073fc72 100644 --- a/drivers/scsi/hisi_sas/Kconfig +++ b/drivers/scsi/hisi_sas/Kconfig @@ -6,6 +6,7 @@ config SCSI_HISI_SAS select SCSI_SAS_LIBSAS select BLK_DEV_INTEGRITY depends on ATA + select SATA_HOST help This driver supports HiSilicon's SAS HBA, including support based on platform device diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index f301a8048b2f..bf1e98f11990 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -2539,7 +2539,6 @@ ql_dbg(uint level, scsi_qla_host_t *vha, uint id, const char *fmt, ...) { va_list va; struct va_format vaf; - char pbuf[64]; va_start(va, fmt); @@ -2547,6 +2546,8 @@ ql_dbg(uint level, scsi_qla_host_t *vha, uint id, const char *fmt, ...) vaf.va = &va; if (!ql_mask_match(level)) { + char pbuf[64]; + if (vha != NULL) { const struct pci_dev *pdev = vha->hw->pdev; /* <module-name> <msg-id>:<host> Message */ diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 5b2deaa730bf..caa6b840e459 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -3611,8 +3611,6 @@ qla24xx_detect_sfp(scsi_qla_host_t *vha) ha->lr_distance = LR_DISTANCE_5K; } - if (!vha->flags.init_done) - rc = QLA_SUCCESS; out: ql_dbg(ql_dbg_async, vha, 0x507b, "SFP detect: %s-Range SFP %s (nvr=%x ll=%x lr=%x lrd=%x).\n", diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 8d7a905f6247..8a78d395bbc8 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -87,7 +87,6 @@ qla24xx_process_abts(struct scsi_qla_host *vha, void *pkt) } /* terminate exchange */ - memset(rsp_els, 0, sizeof(*rsp_els)); rsp_els->entry_type = ELS_IOCB_TYPE; rsp_els->entry_count = 1; rsp_els->nport_handle = ~0; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 9fd83d1bffe0..4ed90437e8c4 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -4894,8 +4894,6 @@ qla25xx_set_els_cmds_supported(scsi_qla_host_t *vha) return QLA_MEMORY_ALLOC_FAILED; } - memset(els_cmd_map, 0, ELS_CMD_MAP_SIZE); - els_cmd_map[index] |= 1 << bit; mcp->mb[0] = MBC_SET_RNID_PARAMS; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 4e6af592f018..20472aaaf630 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -685,8 +685,10 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos) hp->flags = input_size; /* structure abuse ... */ hp->pack_id = old_hdr.pack_id; hp->usr_ptr = NULL; - if (copy_from_user(cmnd, buf, cmd_size)) + if (copy_from_user(cmnd, buf, cmd_size)) { + sg_remove_request(sfp, srp); return -EFAULT; + } /* * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV, * but is is possible that the app intended SG_DXFER_TO_DEV, because there @@ -793,8 +795,10 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, "sg_common_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) cmnd[0], (int) hp->cmd_len)); - if (hp->dxfer_len >= SZ_256M) + if (hp->dxfer_len >= SZ_256M) { + sg_remove_request(sfp, srp); return -EINVAL; + } k = sg_start_req(srp, cmnd); if (k) { diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index cd4f6410e8c2..bcdcd3e7d7f1 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -478,12 +478,18 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d, const struct dpaa2_fd *fd, int nb) { - int i; - struct qbman_eq_desc ed[32]; + struct qbman_eq_desc *ed; + int i, ret; + + ed = kcalloc(sizeof(struct qbman_eq_desc), 32, GFP_KERNEL); + if (!ed) + return -ENOMEM; d = service_select(d); - if (!d) - return -ENODEV; + if (!d) { + ret = -ENODEV; + goto out; + } for (i = 0; i < nb; i++) { qbman_eq_desc_clear(&ed[i]); @@ -491,7 +497,10 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d, qbman_eq_desc_set_fq(&ed[i], fqid[i]); } - return qbman_swp_enqueue_multiple_desc(d->swp, &ed[0], fd, nb); + ret = qbman_swp_enqueue_multiple_desc(d->swp, &ed[0], fd, nb); +out: + kfree(ed); + return ret; } EXPORT_SYMBOL(dpaa2_io_service_enqueue_multiple_desc_fq); diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c index d1f49caa5b13..804b8ba9bf5c 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.c +++ b/drivers/soc/fsl/dpio/qbman-portal.c @@ -753,7 +753,7 @@ int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s, if (!s->eqcr.available) { eqcr_ci = s->eqcr.ci; p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK; - s->eqcr.ci = __raw_readl(p) & full_mask; + s->eqcr.ci = *p & full_mask; s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size, eqcr_ci, s->eqcr.ci); if (!s->eqcr.available) { @@ -823,7 +823,6 @@ int qbman_swp_enqueue_multiple_desc_direct(struct qbman_swp *s, const uint32_t *cl; uint32_t eqcr_ci, eqcr_pi, half_mask, full_mask; int i, num_enqueued = 0; - uint64_t addr_cena; half_mask = (s->eqcr.pi_ci_mask>>1); full_mask = s->eqcr.pi_ci_mask; @@ -867,7 +866,6 @@ int qbman_swp_enqueue_multiple_desc_direct(struct qbman_swp *s, /* Flush all the cacheline without load/store in between */ eqcr_pi = s->eqcr.pi; - addr_cena = (uint64_t)s->addr_cena; for (i = 0; i < num_enqueued; i++) eqcr_pi++; s->eqcr.pi = eqcr_pi & full_mask; @@ -901,7 +899,7 @@ int qbman_swp_enqueue_multiple_desc_mem_back(struct qbman_swp *s, if (!s->eqcr.available) { eqcr_ci = s->eqcr.ci; p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK; - s->eqcr.ci = __raw_readl(p) & full_mask; + s->eqcr.ci = *p & full_mask; s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size, eqcr_ci, s->eqcr.ci); if (!s->eqcr.available) diff --git a/drivers/soc/imx/Kconfig b/drivers/soc/imx/Kconfig index 67aa94b2481b..d515d2cc20ed 100644 --- a/drivers/soc/imx/Kconfig +++ b/drivers/soc/imx/Kconfig @@ -21,6 +21,7 @@ config SOC_IMX8M bool "i.MX8M SoC family support" depends on ARCH_MXC || COMPILE_TEST default ARCH_MXC && ARM64 + select SOC_BUS 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/xilinx/Kconfig b/drivers/soc/xilinx/Kconfig index 223f1f9d0922..646512d7276f 100644 --- a/drivers/soc/xilinx/Kconfig +++ b/drivers/soc/xilinx/Kconfig @@ -19,7 +19,7 @@ config XILINX_VCU config ZYNQMP_POWER bool "Enable Xilinx Zynq MPSoC Power Management driver" - depends on PM && ARCH_ZYNQMP + depends on PM && ZYNQMP_FIRMWARE default y select MAILBOX select ZYNQMP_IPI_MBOX @@ -35,7 +35,7 @@ config ZYNQMP_POWER config ZYNQMP_PM_DOMAINS bool "Enable Zynq MPSoC generic PM domains" default y - depends on PM && ARCH_ZYNQMP && ZYNQMP_FIRMWARE + depends on PM && ZYNQMP_FIRMWARE select PM_GENERIC_DOMAINS help Say yes to enable device power management through PM domains diff --git a/drivers/staging/gasket/apex_driver.c b/drivers/staging/gasket/apex_driver.c index 46199c8ca441..f12f81c8dd2f 100644 --- a/drivers/staging/gasket/apex_driver.c +++ b/drivers/staging/gasket/apex_driver.c @@ -570,13 +570,6 @@ static const struct pci_device_id apex_pci_ids[] = { { PCI_DEVICE(APEX_PCI_VENDOR_ID, APEX_PCI_DEVICE_ID) }, { 0 } }; -static void apex_pci_fixup_class(struct pci_dev *pdev) -{ - pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class; -} -DECLARE_PCI_FIXUP_CLASS_HEADER(APEX_PCI_VENDOR_ID, APEX_PCI_DEVICE_ID, - PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class); - static int apex_pci_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) { diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index 6b4b354c88aa..1e031d81e59e 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -63,7 +63,7 @@ static int fc_get_pr_transport_id( * encoded TransportID. */ ptr = &se_nacl->initiatorname[0]; - for (i = 0; i < 24; ) { + for (i = 0; i < 23; ) { if (!strncmp(&ptr[i], ":", 1)) { i++; continue; @@ -341,7 +341,8 @@ static char *iscsi_parse_pr_out_transport_id( *p = tolower(*p); p++; } - } + } else + *port_nexus_ptr = NULL; return &buf[4]; } diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 0b9dfa6b17bc..f769bb1e3735 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -2073,6 +2073,7 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level) mb->cmd_tail = 0; mb->cmd_head = 0; tcmu_flush_dcache_range(mb, sizeof(*mb)); + clear_bit(TCMU_DEV_BIT_BROKEN, &udev->flags); del_timer(&udev->cmd_timer); diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 7db1460104b7..e8140065c8a5 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -1,21 +1,16 @@ # SPDX-License-Identifier: GPL-2.0-only -config VDPA - tristate +menuconfig VDPA + tristate "vDPA drivers" help Enable this module to support vDPA device that uses a datapath which complies with virtio specifications with vendor specific control path. -menuconfig VDPA_MENU - bool "VDPA drivers" - default n - -if VDPA_MENU +if VDPA config VDPA_SIM tristate "vDPA device simulator" - depends on RUNTIME_TESTING_MENU - select VDPA + depends on RUNTIME_TESTING_MENU && HAS_DMA && VHOST_DPN select VHOST_RING default n help @@ -24,9 +19,8 @@ config VDPA_SIM development of vDPA. config IFCVF - tristate "Intel IFC VF VDPA driver" + tristate "Intel IFC VF vDPA driver" depends on PCI_MSI - select VDPA default n help This kernel module can drive Intel IFC VF NIC to offload @@ -34,4 +28,4 @@ config IFCVF To compile this driver as a module, choose M here: the module will be called ifcvf. -endif # VDPA_MENU +endif # VDPA diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c index b61b06ea26d3..e24371d644b5 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.c +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -301,12 +301,10 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num) static int ifcvf_hw_enable(struct ifcvf_hw *hw) { - struct ifcvf_lm_cfg __iomem *ifcvf_lm; struct virtio_pci_common_cfg __iomem *cfg; struct ifcvf_adapter *ifcvf; u32 i; - ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg; ifcvf = vf_to_adapter(hw); cfg = hw->common_cfg; ifc_iowrite16(IFCVF_MSI_CONFIG_OFF, &cfg->msix_config); diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 8d54dc5b08d2..abf6a061cab6 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -31,11 +31,9 @@ static irqreturn_t ifcvf_intr_handler(int irq, void *arg) static int ifcvf_start_datapath(void *private) { struct ifcvf_hw *vf = ifcvf_private_to_vf(private); - struct ifcvf_adapter *ifcvf; u8 status; int ret; - ifcvf = vf_to_adapter(vf); vf->nr_vring = IFCVF_MAX_QUEUE_PAIRS * 2; ret = ifcvf_start_hw(vf); if (ret < 0) { @@ -228,7 +226,7 @@ static u32 ifcvf_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev) return IFCVF_SUBSYS_VENDOR_ID; } -static u16 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev) +static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev) { return IFCVF_QUEUE_ALIGNMENT; } diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index e9ed6a2b635b..ff6562f602e0 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -116,7 +116,7 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device); /** * vdpa_register_device - register a vDPA device - * Callers must have a succeed call of vdpa_init_device() before. + * Callers must have a succeed call of vdpa_alloc_device() before. * @vdev: the vdpa device to be registered to vDPA bus * * Returns an error when fail to add to vDPA bus diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 6e8a0cf2fdeb..7957d2d41fc4 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -435,7 +435,7 @@ static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx) return vrh->last_avail_idx; } -static u16 vdpasim_get_vq_align(struct vdpa_device *vdpa) +static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa) { return VDPASIM_QUEUE_ALIGN; } @@ -488,7 +488,7 @@ static u8 vdpasim_get_status(struct vdpa_device *vdpa) status = vdpasim->status; spin_unlock(&vdpasim->lock); - return vdpasim->status; + return status; } static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index 362b832f5338..c4f273793595 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -3,6 +3,8 @@ config VHOST_IOTLB tristate help Generic IOTLB implementation for vhost and vringh. + This option is selected by any driver which needs to support + an IOMMU in software. config VHOST_RING tristate @@ -11,6 +13,15 @@ config VHOST_RING This option is selected by any driver which needs to access the host side of a virtio ring. +config VHOST_DPN + bool + depends on !ARM || AEABI + default y + help + Anything selecting VHOST or VHOST_RING must depend on VHOST_DPN. + This excludes the deprecated ARM ABI since that forces a 4 byte + alignment on all structs - incompatible with virtio spec requirements. + config VHOST tristate select VHOST_IOTLB @@ -26,7 +37,7 @@ if VHOST_MENU config VHOST_NET tristate "Host kernel accelerator for virtio net" - depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP) + depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP) && VHOST_DPN select VHOST ---help--- This kernel module can be loaded in host kernel to accelerate @@ -38,7 +49,7 @@ config VHOST_NET config VHOST_SCSI tristate "VHOST_SCSI TCM fabric driver" - depends on TARGET_CORE && EVENTFD + depends on TARGET_CORE && EVENTFD && VHOST_DPN select VHOST default n ---help--- @@ -47,7 +58,7 @@ config VHOST_SCSI config VHOST_VSOCK tristate "vhost virtio-vsock driver" - depends on VSOCKETS && EVENTFD + depends on VSOCKETS && EVENTFD && VHOST_DPN select VHOST select VIRTIO_VSOCKETS_COMMON default n @@ -61,9 +72,9 @@ config VHOST_VSOCK config VHOST_VDPA tristate "Vhost driver for vDPA-based backend" - depends on EVENTFD + depends on EVENTFD && VHOST_DPN select VHOST - select VDPA + depends on VDPA help This kernel module can be loaded in host kernel to accelerate guest virtio devices with the vDPA-based backends. diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 87469d67ede8..2927f02cc7e1 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -424,7 +424,7 @@ static void vhost_net_disable_vq(struct vhost_net *n, struct vhost_net_virtqueue *nvq = container_of(vq, struct vhost_net_virtqueue, vq); struct vhost_poll *poll = n->poll + (nvq - n->vqs); - if (!vq->private_data) + if (!vhost_vq_get_backend(vq)) return; vhost_poll_stop(poll); } @@ -437,7 +437,7 @@ static int vhost_net_enable_vq(struct vhost_net *n, struct vhost_poll *poll = n->poll + (nvq - n->vqs); struct socket *sock; - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); if (!sock) return 0; @@ -524,7 +524,7 @@ static void vhost_net_busy_poll(struct vhost_net *net, return; vhost_disable_notify(&net->dev, vq); - sock = rvq->private_data; + sock = vhost_vq_get_backend(rvq); busyloop_timeout = poll_rx ? rvq->busyloop_timeout: tvq->busyloop_timeout; @@ -570,8 +570,10 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net, if (r == tvq->num && tvq->busyloop_timeout) { /* Flush batched packets first */ - if (!vhost_sock_zcopy(tvq->private_data)) - vhost_tx_batch(net, tnvq, tvq->private_data, msghdr); + if (!vhost_sock_zcopy(vhost_vq_get_backend(tvq))) + vhost_tx_batch(net, tnvq, + vhost_vq_get_backend(tvq), + msghdr); vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false); @@ -685,7 +687,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct vhost_virtqueue *vq = &nvq->vq; struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); - struct socket *sock = vq->private_data; + struct socket *sock = vhost_vq_get_backend(vq); struct page_frag *alloc_frag = &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; @@ -952,7 +954,7 @@ static void handle_tx(struct vhost_net *net) struct socket *sock; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX); - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); if (!sock) goto out; @@ -1121,7 +1123,7 @@ static void handle_rx(struct vhost_net *net) int recv_pkts = 0; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX); - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); if (!sock) goto out; @@ -1345,9 +1347,9 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n, container_of(vq, struct vhost_net_virtqueue, vq); mutex_lock(&vq->mutex); - sock = vq->private_data; + sock = vhost_vq_get_backend(vq); vhost_net_disable_vq(n, vq); - vq->private_data = NULL; + vhost_vq_set_backend(vq, NULL); vhost_net_buf_unproduce(nvq); nvq->rx_ring = NULL; mutex_unlock(&vq->mutex); @@ -1521,7 +1523,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) } /* start polling new socket */ - oldsock = vq->private_data; + oldsock = vhost_vq_get_backend(vq); if (sock != oldsock) { ubufs = vhost_net_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock)); @@ -1531,7 +1533,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) } vhost_net_disable_vq(n, vq); - vq->private_data = sock; + vhost_vq_set_backend(vq, sock); vhost_net_buf_unproduce(nvq); r = vhost_vq_init_access(vq); if (r) @@ -1568,7 +1570,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) return 0; err_used: - vq->private_data = oldsock; + vhost_vq_set_backend(vq, oldsock); vhost_net_enable_vq(n, vq); if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 7653667a8cdc..c39952243fd3 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -452,7 +452,7 @@ vhost_scsi_do_evt_work(struct vhost_scsi *vs, struct vhost_scsi_evt *evt) unsigned out, in; int head, ret; - if (!vq->private_data) { + if (!vhost_vq_get_backend(vq)) { vs->vs_events_missed = true; return; } @@ -892,7 +892,7 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, } else { struct vhost_scsi_tpg **vs_tpg, *tpg; - vs_tpg = vq->private_data; /* validated at handler entry */ + vs_tpg = vhost_vq_get_backend(vq); /* validated at handler entry */ tpg = READ_ONCE(vs_tpg[*vc->target]); if (unlikely(!tpg)) { @@ -929,7 +929,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) * We can handle the vq only after the endpoint is setup by calling the * VHOST_SCSI_SET_ENDPOINT ioctl. */ - vs_tpg = vq->private_data; + vs_tpg = vhost_vq_get_backend(vq); if (!vs_tpg) goto out; @@ -1184,7 +1184,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) * We can handle the vq only after the endpoint is setup by calling the * VHOST_SCSI_SET_ENDPOINT ioctl. */ - if (!vq->private_data) + if (!vhost_vq_get_backend(vq)) goto out; memset(&vc, 0, sizeof(vc)); @@ -1322,7 +1322,7 @@ static void vhost_scsi_evt_handle_kick(struct vhost_work *work) struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev); mutex_lock(&vq->mutex); - if (!vq->private_data) + if (!vhost_vq_get_backend(vq)) goto out; if (vs->vs_events_missed) @@ -1460,7 +1460,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { vq = &vs->vqs[i].vq; mutex_lock(&vq->mutex); - vq->private_data = vs_tpg; + vhost_vq_set_backend(vq, vs_tpg); vhost_vq_init_access(vq); mutex_unlock(&vq->mutex); } @@ -1547,7 +1547,7 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { vq = &vs->vqs[i].vq; mutex_lock(&vq->mutex); - vq->private_data = NULL; + vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } } diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index e37c92d4d7ad..9a3a09005e03 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -49,7 +49,7 @@ static void handle_vq(struct vhost_test *n) void *private; mutex_lock(&vq->mutex); - private = vq->private_data; + private = vhost_vq_get_backend(vq); if (!private) { mutex_unlock(&vq->mutex); return; @@ -120,7 +120,7 @@ static int vhost_test_open(struct inode *inode, struct file *f) vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ]; n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick; vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV, - VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT); + VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT, NULL); f->private_data = n; @@ -133,8 +133,8 @@ static void *vhost_test_stop_vq(struct vhost_test *n, void *private; mutex_lock(&vq->mutex); - private = vq->private_data; - vq->private_data = NULL; + private = vhost_vq_get_backend(vq); + vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); return private; } @@ -198,8 +198,8 @@ static long vhost_test_run(struct vhost_test *n, int test) priv = test ? n : NULL; /* start polling new socket */ - oldpriv = vq->private_data; - vq->private_data = priv; + oldpriv = vhost_vq_get_backend(vq); + vhost_vq_set_backend(vq, priv); r = vhost_vq_init_access(&n->vqs[index]); @@ -225,7 +225,7 @@ static long vhost_test_reset_owner(struct vhost_test *n) { void *priv = NULL; long err; - struct vhost_umem *umem; + struct vhost_iotlb *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 421f02a8530a..0968361e3b77 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -296,7 +296,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, struct vdpa_callback cb; struct vhost_virtqueue *vq; struct vhost_vring_state s; - u8 status; u32 idx; long r; @@ -310,8 +309,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, idx = array_index_nospec(idx, v->nvqs); vq = &v->vqs[idx]; - status = ops->get_status(vdpa); - if (cmd == VHOST_VDPA_SET_VRING_ENABLE) { if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; @@ -678,8 +675,6 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) int nvqs, i, r, opened; v = container_of(inode->i_cdev, struct vhost_vdpa, cdev); - if (!v) - return -ENODEV; opened = atomic_cmpxchg(&v->opened, 0, 1); if (opened) diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 181382185bbc..f8403bd46b85 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -231,6 +231,33 @@ enum { (1ULL << VIRTIO_F_VERSION_1) }; +/** + * vhost_vq_set_backend - Set backend. + * + * @vq Virtqueue. + * @private_data The private data. + * + * Context: Need to call with vq->mutex acquired. + */ +static inline void vhost_vq_set_backend(struct vhost_virtqueue *vq, + void *private_data) +{ + vq->private_data = private_data; +} + +/** + * vhost_vq_get_backend - Get backend. + * + * @vq Virtqueue. + * + * Context: Need to call with vq->mutex acquired. + * Return: Private data previously set with vhost_vq_set_backend. + */ +static inline void *vhost_vq_get_backend(struct vhost_virtqueue *vq) +{ + return vq->private_data; +} + static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) { return vq->acked_features & (1ULL << bit); diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index ee0491f579ac..ba8e0d6cfd97 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -13,9 +13,11 @@ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/export.h> +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) #include <linux/bvec.h> #include <linux/highmem.h> #include <linux/vhost_iotlb.h> +#endif #include <uapi/linux/virtio_config.h> static __printf(1,2) __cold void vringh_bad(const char *fmt, ...) @@ -1059,6 +1061,8 @@ int vringh_need_notify_kern(struct vringh *vrh) } EXPORT_SYMBOL(vringh_need_notify_kern); +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) + static int iotlb_translate(const struct vringh *vrh, u64 addr, u64 len, struct bio_vec iov[], int iov_size, u32 perm) @@ -1416,5 +1420,6 @@ int vringh_need_notify_iotlb(struct vringh *vrh) } EXPORT_SYMBOL(vringh_need_notify_iotlb); +#endif MODULE_LICENSE("GPL"); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 97669484a3f6..e36aaf9ba7bd 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -91,7 +91,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, mutex_lock(&vq->mutex); - if (!vq->private_data) + if (!vhost_vq_get_backend(vq)) goto out; /* Avoid further vmexits, we're already processing the virtqueue */ @@ -440,7 +440,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) mutex_lock(&vq->mutex); - if (!vq->private_data) + if (!vhost_vq_get_backend(vq)) goto out; vhost_disable_notify(&vsock->dev, vq); @@ -533,8 +533,8 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) goto err_vq; } - if (!vq->private_data) { - vq->private_data = vsock; + if (!vhost_vq_get_backend(vq)) { + vhost_vq_set_backend(vq, vsock); ret = vhost_vq_init_access(vq); if (ret) goto err_vq; @@ -547,14 +547,14 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) return 0; err_vq: - vq->private_data = NULL; + vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); - vq->private_data = NULL; + vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: @@ -577,7 +577,7 @@ static int vhost_vsock_stop(struct vhost_vsock *vsock) struct vhost_virtqueue *vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); - vq->private_data = NULL; + vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 2bbf94b15bba..69a32dfc318a 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -45,7 +45,7 @@ config VIRTIO_PCI_LEGACY config VIRTIO_VDPA tristate "vDPA driver for virtio devices" - select VDPA + depends on VDPA select VIRTIO help This driver provides support for virtio based paravirtual diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 0ef16566c3f3..51086a5afdd4 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -165,7 +165,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) } -int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info, +static int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info, struct scatterlist *sg, unsigned int nents) { struct virtio_balloon *vb = @@ -580,7 +580,7 @@ static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, &vb->config_read_bitmap)) virtio_cread(vb->vdev, struct virtio_balloon_config, - free_page_report_cmd_id, + free_page_hint_cmd_id, &vb->cmd_id_received_cache); return vb->cmd_id_received_cache; diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index 5ae529671b3d..efaf65b0f42d 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -3,6 +3,7 @@ #include <linux/virtio.h> #include <linux/virtio_config.h> #include <linux/input.h> +#include <linux/slab.h> #include <uapi/linux/virtio_ids.h> #include <uapi/linux/virtio_input.h> diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index 53e04926a7b2..190d26e2e75f 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -137,10 +137,14 @@ wdt_restart(struct watchdog_device *wdd, unsigned long mode, void *cmd) { struct sp805_wdt *wdt = watchdog_get_drvdata(wdd); + writel_relaxed(UNLOCK, wdt->base + WDTLOCK); writel_relaxed(0, wdt->base + WDTCONTROL); writel_relaxed(0, wdt->base + WDTLOAD); writel_relaxed(INT_ENABLE | RESET_ENABLE, wdt->base + WDTCONTROL); + /* Flush posted writes. */ + readl_relaxed(wdt->base + WDTLOCK); + return 0; } diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 385843256865..040d2a43e8e3 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -448,7 +448,14 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn); int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr) { - return ring_ops->map(dev, gnt_refs, nr_grefs, vaddr); + int err; + + err = ring_ops->map(dev, gnt_refs, nr_grefs, vaddr); + /* Some hypervisors are buggy and can return 1. */ + if (err > 0) + err = GNTST_general_error; + + return err; } EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc); diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 6765949b3aab..380ad5ace7cf 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -169,7 +169,7 @@ static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server) spin_lock(&server->probe_lock); - if (!test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) { + if (!test_and_set_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) { server->cm_epoch = call->epoch; server->probe.cm_epoch = call->epoch; goto out; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 5c794f4b051a..d1e1caa23c8b 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1032,7 +1032,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) struct dentry *parent; struct inode *inode; struct key *key; - afs_dataversion_t dir_version; + afs_dataversion_t dir_version, invalid_before; long de_version; int ret; @@ -1084,8 +1084,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (de_version == (long)dir_version) goto out_valid_noupdate; - dir_version = dir->invalid_before; - if (de_version - (long)dir_version >= 0) + invalid_before = dir->invalid_before; + if (de_version - (long)invalid_before >= 0) goto out_valid; _debug("dir modified"); @@ -1275,6 +1275,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct afs_fs_cursor fc; struct afs_vnode *dvnode = AFS_FS_I(dir); struct key *key; + afs_dataversion_t data_version; int ret; mode |= S_IFDIR; @@ -1295,7 +1296,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t data_version = dvnode->status.data_version + 1; + data_version = dvnode->status.data_version + 1; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); @@ -1316,10 +1317,14 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto error_key; } - if (ret == 0 && - test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, - afs_edit_dir_for_create); + if (ret == 0) { + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == data_version) + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, + afs_edit_dir_for_create); + up_write(&dvnode->validate_lock); + } key_put(key); kfree(scb); @@ -1360,6 +1365,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) struct afs_fs_cursor fc; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; struct key *key; + afs_dataversion_t data_version; int ret; _enter("{%llx:%llu},{%pd}", @@ -1391,7 +1397,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t data_version = dvnode->status.data_version + 1; + data_version = dvnode->status.data_version + 1; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); @@ -1404,9 +1410,12 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) ret = afs_end_vnode_operation(&fc); if (ret == 0) { afs_dir_remove_subdir(dentry); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == data_version) afs_edit_dir_remove(dvnode, &dentry->d_name, afs_edit_dir_for_rmdir); + up_write(&dvnode->validate_lock); } } @@ -1544,10 +1553,15 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) ret = afs_end_vnode_operation(&fc); if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) ret = afs_dir_remove_link(dvnode, dentry, key); - if (ret == 0 && - test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_remove(dvnode, &dentry->d_name, - afs_edit_dir_for_unlink); + + if (ret == 0) { + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == data_version) + afs_edit_dir_remove(dvnode, &dentry->d_name, + afs_edit_dir_for_unlink); + up_write(&dvnode->validate_lock); + } } if (need_rehash && ret < 0 && ret != -ENOENT) @@ -1573,6 +1587,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir); struct key *key; + afs_dataversion_t data_version; int ret; mode |= S_IFREG; @@ -1597,7 +1612,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t data_version = dvnode->status.data_version + 1; + data_version = dvnode->status.data_version + 1; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); @@ -1618,9 +1633,12 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, goto error_key; } - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == data_version) afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_create); + up_write(&dvnode->validate_lock); kfree(scb); key_put(key); @@ -1648,6 +1666,7 @@ static int afs_link(struct dentry *from, struct inode *dir, struct afs_vnode *dvnode = AFS_FS_I(dir); struct afs_vnode *vnode = AFS_FS_I(d_inode(from)); struct key *key; + afs_dataversion_t data_version; int ret; _enter("{%llx:%llu},{%llx:%llu},{%pd}", @@ -1672,7 +1691,7 @@ static int afs_link(struct dentry *from, struct inode *dir, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t data_version = dvnode->status.data_version + 1; + data_version = dvnode->status.data_version + 1; if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); @@ -1702,9 +1721,12 @@ static int afs_link(struct dentry *from, struct inode *dir, goto error_key; } - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == data_version) afs_edit_dir_add(dvnode, &dentry->d_name, &vnode->fid, afs_edit_dir_for_link); + up_write(&dvnode->validate_lock); key_put(key); kfree(scb); @@ -1732,6 +1754,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir); struct key *key; + afs_dataversion_t data_version; int ret; _enter("{%llx:%llu},{%pd},%s", @@ -1759,7 +1782,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t data_version = dvnode->status.data_version + 1; + data_version = dvnode->status.data_version + 1; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); @@ -1780,9 +1803,12 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, goto error_key; } - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == data_version) afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_symlink); + up_write(&dvnode->validate_lock); key_put(key); kfree(scb); @@ -1812,6 +1838,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, struct dentry *tmp = NULL, *rehash = NULL; struct inode *new_inode; struct key *key; + afs_dataversion_t orig_data_version; + afs_dataversion_t new_data_version; bool new_negative = d_is_negative(new_dentry); int ret; @@ -1890,10 +1918,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { - afs_dataversion_t orig_data_version; - afs_dataversion_t new_data_version; - struct afs_status_cb *new_scb = &scb[1]; - orig_data_version = orig_dvnode->status.data_version + 1; if (orig_dvnode != new_dvnode) { @@ -1904,7 +1928,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, new_data_version = new_dvnode->status.data_version + 1; } else { new_data_version = orig_data_version; - new_scb = &scb[0]; } while (afs_select_fileserver(&fc)) { @@ -1912,7 +1935,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode); afs_fs_rename(&fc, old_dentry->d_name.name, new_dvnode, new_dentry->d_name.name, - &scb[0], new_scb); + &scb[0], &scb[1]); } afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break, @@ -1930,18 +1953,25 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, if (ret == 0) { if (rehash) d_rehash(rehash); - if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags)) - afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name, - afs_edit_dir_for_rename_0); + down_write(&orig_dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) && + orig_dvnode->status.data_version == orig_data_version) + afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name, + afs_edit_dir_for_rename_0); + if (orig_dvnode != new_dvnode) { + up_write(&orig_dvnode->validate_lock); - if (!new_negative && - test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags)) - afs_edit_dir_remove(new_dvnode, &new_dentry->d_name, - afs_edit_dir_for_rename_1); + down_write(&new_dvnode->validate_lock); + } + if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags) && + orig_dvnode->status.data_version == new_data_version) { + if (!new_negative) + afs_edit_dir_remove(new_dvnode, &new_dentry->d_name, + afs_edit_dir_for_rename_1); - if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags)) afs_edit_dir_add(new_dvnode, &new_dentry->d_name, &vnode->fid, afs_edit_dir_for_rename_2); + } new_inode = d_inode(new_dentry); if (new_inode) { @@ -1957,14 +1987,10 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, * Note that if we ever implement RENAME_EXCHANGE, we'll have * to update both dentries with opposing dir versions. */ - if (new_dvnode != orig_dvnode) { - afs_update_dentry_version(&fc, old_dentry, &scb[1]); - afs_update_dentry_version(&fc, new_dentry, &scb[1]); - } else { - afs_update_dentry_version(&fc, old_dentry, &scb[0]); - afs_update_dentry_version(&fc, new_dentry, &scb[0]); - } + afs_update_dentry_version(&fc, old_dentry, &scb[1]); + afs_update_dentry_version(&fc, new_dentry, &scb[1]); d_move(old_dentry, new_dentry); + up_write(&new_dvnode->validate_lock); goto error_tmp; } diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index 361088a5edb9..d94e2b7cddff 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -21,6 +21,7 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode { struct afs_fs_cursor fc; struct afs_status_cb *scb; + afs_dataversion_t dir_data_version; int ret = -ERESTARTSYS; _enter("%pd,%pd", old, new); @@ -31,7 +32,7 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode trace_afs_silly_rename(vnode, false); if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { - afs_dataversion_t dir_data_version = dvnode->status.data_version + 1; + dir_data_version = dvnode->status.data_version + 1; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); @@ -54,12 +55,15 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode dvnode->silly_key = key_get(key); } - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dir_data_version) { afs_edit_dir_remove(dvnode, &old->d_name, afs_edit_dir_for_silly_0); - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_edit_dir_add(dvnode, &new->d_name, &vnode->fid, afs_edit_dir_for_silly_1); + } + up_write(&dvnode->validate_lock); } kfree(scb); @@ -181,10 +185,14 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); } } - if (ret == 0 && - test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_remove(dvnode, &dentry->d_name, - afs_edit_dir_for_unlink); + if (ret == 0) { + down_write(&dvnode->validate_lock); + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) && + dvnode->status.data_version == dir_data_version) + afs_edit_dir_remove(dvnode, &dentry->d_name, + afs_edit_dir_for_unlink); + up_write(&dvnode->validate_lock); + } } kfree(scb); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index e1b9ed679045..a587767b6ae1 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -117,11 +117,8 @@ out: (unsigned int)rtt, ret); have_result |= afs_fs_probe_done(server); - if (have_result) { - server->probe.have_result = true; - wake_up_var(&server->probe.have_result); + if (have_result) wake_up_all(&server->probe_wq); - } } /* diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 1f9c5d8e6fe5..68fc46634346 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -65,6 +65,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus); u64 data_version, size; u32 type, abort_code; + int ret; abort_code = ntohl(xdr->abort_code); @@ -78,7 +79,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, */ status->abort_code = abort_code; scb->have_error = true; - return 0; + goto good; } pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version)); @@ -87,7 +88,8 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, if (abort_code != 0 && inline_error) { status->abort_code = abort_code; - return 0; + scb->have_error = true; + goto good; } type = ntohl(xdr->type); @@ -123,13 +125,16 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp, data_version |= (u64)ntohl(xdr->data_version_hi) << 32; status->data_version = data_version; scb->have_status = true; - +good: + ret = 0; +advance: *_bp = (const void *)*_bp + sizeof(*xdr); - return 0; + return ret; bad: xdr_dump_bad(*_bp); - return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + goto advance; } static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) @@ -981,16 +986,16 @@ static int afs_deliver_fs_rename(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ + /* If the two dirs are the same, we have two copies of the same status + * report, so we just decode it twice. + */ bp = call->buffer; ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - if (call->out_dir_scb != call->out_scb) { - ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - } + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index ef732dd4e7ef..80255513e230 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -533,12 +533,10 @@ struct afs_server { u32 abort_code; u32 cm_epoch; short error; - bool have_result; bool responded:1; bool is_yfs:1; bool not_yfs:1; bool local_failure:1; - bool no_epoch:1; bool cm_probed:1; bool said_rebooted:1; bool said_inconsistent:1; @@ -1335,7 +1333,7 @@ extern struct afs_volume *afs_create_volume(struct afs_fs_context *); extern void afs_activate_volume(struct afs_volume *); extern void afs_deactivate_volume(struct afs_volume *); extern void afs_put_volume(struct afs_cell *, struct afs_volume *); -extern int afs_check_volume_status(struct afs_volume *, struct key *); +extern int afs_check_volume_status(struct afs_volume *, struct afs_fs_cursor *); /* * write.c diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 172ba569cd60..2a3305e42b14 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -192,7 +192,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) write_unlock(&vnode->volume->servers_lock); set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags); - error = afs_check_volume_status(vnode->volume, fc->key); + error = afs_check_volume_status(vnode->volume, fc); if (error < 0) goto failed_set_error; @@ -281,7 +281,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags); set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags); - error = afs_check_volume_status(vnode->volume, fc->key); + error = afs_check_volume_status(vnode->volume, fc); if (error < 0) goto failed_set_error; @@ -341,7 +341,7 @@ start: /* See if we need to do an update of the volume record. Note that the * volume may have moved or even have been deleted. */ - error = afs_check_volume_status(vnode->volume, fc->key); + error = afs_check_volume_status(vnode->volume, fc); if (error < 0) goto failed_set_error; diff --git a/fs/afs/server.c b/fs/afs/server.c index b7f3cb2130ca..11b90ac7ea30 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -594,12 +594,9 @@ retry: } ret = wait_on_bit(&server->flags, AFS_SERVER_FL_UPDATING, - TASK_INTERRUPTIBLE); + (fc->flags & AFS_FS_CURSOR_INTR) ? + TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); if (ret == -ERESTARTSYS) { - if (!(fc->flags & AFS_FS_CURSOR_INTR) && server->addresses) { - _leave(" = t [intr]"); - return true; - } fc->error = ret; _leave(" = f [intr]"); return false; diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index 9a5ce9687779..72eacc14e6e1 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -302,8 +302,8 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc) pr_notice("VC: - nr=%u/%u/%u pf=%u\n", a->nr_ipv4, a->nr_addrs, a->max_addrs, a->preferred); - pr_notice("VC: - pr=%lx R=%lx F=%lx\n", - a->probed, a->responded, a->failed); + pr_notice("VC: - R=%lx F=%lx\n", + a->responded, a->failed); if (a == vc->ac.alist) pr_notice("VC: - current\n"); } diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 92ca5e27573b..4310336b9bb8 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -281,7 +281,7 @@ error: /* * Make sure the volume record is up to date. */ -int afs_check_volume_status(struct afs_volume *volume, struct key *key) +int afs_check_volume_status(struct afs_volume *volume, struct afs_fs_cursor *fc) { time64_t now = ktime_get_real_seconds(); int ret, retries = 0; @@ -299,7 +299,7 @@ retry: } if (!test_and_set_bit_lock(AFS_VOLUME_UPDATING, &volume->flags)) { - ret = afs_update_volume_status(volume, key); + ret = afs_update_volume_status(volume, fc->key); clear_bit_unlock(AFS_VOLUME_WAIT, &volume->flags); clear_bit_unlock(AFS_VOLUME_UPDATING, &volume->flags); wake_up_bit(&volume->flags, AFS_VOLUME_WAIT); @@ -312,7 +312,9 @@ retry: return 0; } - ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, TASK_INTERRUPTIBLE); + ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, + (fc->flags & AFS_FS_CURSOR_INTR) ? + TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); if (ret == -ERESTARTSYS) { _leave(" = %d", ret); return ret; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index a26126ac7bf1..b5b45c57e1b1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -165,15 +165,15 @@ static void xdr_dump_bad(const __be32 *bp) int i; pr_notice("YFS XDR: Bad status record\n"); - for (i = 0; i < 5 * 4 * 4; i += 16) { + for (i = 0; i < 6 * 4 * 4; i += 16) { memcpy(x, bp, 16); bp += 4; pr_notice("%03x: %08x %08x %08x %08x\n", i, ntohl(x[0]), ntohl(x[1]), ntohl(x[2]), ntohl(x[3])); } - memcpy(x, bp, 4); - pr_notice("0x50: %08x\n", ntohl(x[0])); + memcpy(x, bp, 8); + pr_notice("0x60: %08x %08x\n", ntohl(x[0]), ntohl(x[1])); } /* @@ -186,13 +186,14 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp, const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp; struct afs_file_status *status = &scb->status; u32 type; + int ret; status->abort_code = ntohl(xdr->abort_code); if (status->abort_code != 0) { if (status->abort_code == VNOVNODE) status->nlink = 0; scb->have_error = true; - return 0; + goto good; } type = ntohl(xdr->type); @@ -220,13 +221,16 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp, status->size = xdr_to_u64(xdr->size); status->data_version = xdr_to_u64(xdr->data_version); scb->have_status = true; - +good: + ret = 0; +advance: *_bp += xdr_size(xdr); - return 0; + return ret; bad: xdr_dump_bad(*_bp); - return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); + goto advance; } /* @@ -1153,11 +1157,9 @@ static int yfs_deliver_fs_rename(struct afs_call *call) ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - if (call->out_dir_scb != call->out_scb) { - ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); - if (ret < 0) - return ret; - } + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); diff --git a/fs/block_dev.c b/fs/block_dev.c index 52b6f646cdbd..93672c3f1c78 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -19,7 +19,6 @@ #include <linux/module.h> #include <linux/blkpg.h> #include <linux/magic.h> -#include <linux/dax.h> #include <linux/buffer_head.h> #include <linux/swap.h> #include <linux/pagevec.h> @@ -1893,6 +1892,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) struct gendisk *disk = bdev->bd_disk; struct block_device *victim = NULL; + /* + * Sync early if it looks like we're the last one. If someone else + * opens the block device between now and the decrement of bd_openers + * then we did a sync that we didn't need to, but that's not the end + * of the world and we want to avoid long (could be several minute) + * syncs while holding the mutex. + */ + if (bdev->bd_openers == 1) + sync_blockdev(bdev); + mutex_lock_nested(&bdev->bd_mutex, for_part); if (for_part) bdev->bd_part_count--; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 786849fcc319..47f66c6a7d7f 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3370,6 +3370,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) space_info->bytes_reserved > 0 || space_info->bytes_may_use > 0)) btrfs_dump_space_info(info, space_info, 0, 0); + WARN_ON(space_info->reclaim_size > 0); list_del(&space_info->list); btrfs_sysfs_remove_space_info(space_info); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 8a144f9cb7ac..719e68ab552c 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2098,6 +2098,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges and races between logging and + * completion of ordered extents for adjancent ranges - both races + * could lead to file extent items in the log with overlapping ranges. + * Do this while holding the inode lock, to avoid races with other + * tasks. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * Before we acquired the inode's lock, someone may have dirtied more * pages in the target range. We need to make sure that writeback for * any such pages does not start while we are logging the inode, because diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index d1973141d3bb..040009d1cc31 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -264,6 +264,7 @@ copy_inline_extent: size); inode_add_bytes(dst, datal); set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags); + ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end); out: if (!ret && !trans) { /* diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index f65595602aa8..d35936c934ab 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -611,8 +611,8 @@ static int should_ignore_root(struct btrfs_root *root) if (!reloc_root) return 0; - if (btrfs_root_last_snapshot(&reloc_root->root_item) == - root->fs_info->running_transaction->transid - 1) + if (btrfs_header_generation(reloc_root->commit_root) == + root->fs_info->running_transaction->transid) return 0; /* * if there is reloc tree and it was created in previous @@ -1527,8 +1527,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, int clear_rsv = 0; int ret; - if (!rc || !rc->create_reloc_tree || - root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) + if (!rc) return 0; /* @@ -1538,12 +1537,28 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, if (reloc_root_is_dead(root)) return 0; + /* + * This is subtle but important. We do not do + * record_root_in_transaction for reloc roots, instead we record their + * corresponding fs root, and then here we update the last trans for the + * reloc root. This means that we have to do this for the entire life + * of the reloc root, regardless of which stage of the relocation we are + * in. + */ if (root->reloc_root) { reloc_root = root->reloc_root; reloc_root->last_trans = trans->transid; return 0; } + /* + * We are merging reloc roots, we do not need new reloc trees. Also + * reloc trees never need their own reloc tree. + */ + if (!rc->create_reloc_tree || + root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) + return 0; + if (!trans->reloc_reserved) { rsv = trans->block_rsv; trans->block_rsv = rc->block_rsv; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 8b0fe053a25d..ff17a4420358 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -361,6 +361,16 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, return 0; } +static void remove_ticket(struct btrfs_space_info *space_info, + struct reserve_ticket *ticket) +{ + if (!list_empty(&ticket->list)) { + list_del_init(&ticket->list); + ASSERT(space_info->reclaim_size >= ticket->bytes); + space_info->reclaim_size -= ticket->bytes; + } +} + /* * This is for space we already have accounted in space_info->bytes_may_use, so * basically when we're returning space from block_rsv's. @@ -388,9 +398,7 @@ again: btrfs_space_info_update_bytes_may_use(fs_info, space_info, ticket->bytes); - list_del_init(&ticket->list); - ASSERT(space_info->reclaim_size >= ticket->bytes); - space_info->reclaim_size -= ticket->bytes; + remove_ticket(space_info, ticket); ticket->bytes = 0; space_info->tickets_id++; wake_up(&ticket->wait); @@ -899,7 +907,7 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info, btrfs_info(fs_info, "failing ticket with %llu bytes", ticket->bytes); - list_del_init(&ticket->list); + remove_ticket(space_info, ticket); ticket->error = -ENOSPC; wake_up(&ticket->wait); @@ -1063,7 +1071,7 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, * despite getting an error, resulting in a space leak * (bytes_may_use counter of our space_info). */ - list_del_init(&ticket->list); + remove_ticket(space_info, ticket); ticket->error = -EINTR; break; } @@ -1121,7 +1129,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, * either the async reclaim job deletes the ticket from the list * or we delete it ourselves at wait_reserve_ticket(). */ - list_del_init(&ticket->list); + remove_ticket(space_info, ticket); if (!ret) ret = -ENOSPC; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 58c111474ba5..ec36a7c6ba3d 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -96,8 +96,8 @@ enum { static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_inode *inode, int inode_only, - u64 start, - u64 end, + const loff_t start, + const loff_t end, struct btrfs_log_ctx *ctx); static int link_to_fixup_dir(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -4533,15 +4533,13 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, static int btrfs_log_holes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_inode *inode, - struct btrfs_path *path, - const u64 start, - const u64 end) + struct btrfs_path *path) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; const u64 ino = btrfs_ino(inode); const u64 i_size = i_size_read(&inode->vfs_inode); - u64 prev_extent_end = start; + u64 prev_extent_end = 0; int ret; if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0) @@ -4549,21 +4547,14 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans, key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = start; + key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; - if (ret > 0 && path->slots[0] > 0) { - btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); - if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) - path->slots[0]--; - } - while (true) { struct extent_buffer *leaf = path->nodes[0]; - u64 extent_end; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); @@ -4580,18 +4571,9 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans, if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) break; - extent_end = btrfs_file_extent_end(path); - if (extent_end <= start) - goto next_slot; - /* We have a hole, log it. */ if (prev_extent_end < key.offset) { - u64 hole_len; - - if (key.offset >= end) - hole_len = end - prev_extent_end; - else - hole_len = key.offset - prev_extent_end; + const u64 hole_len = key.offset - prev_extent_end; /* * Release the path to avoid deadlocks with other code @@ -4621,20 +4603,16 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans, leaf = path->nodes[0]; } - prev_extent_end = min(extent_end, end); - if (extent_end >= end) - break; -next_slot: + prev_extent_end = btrfs_file_extent_end(path); path->slots[0]++; cond_resched(); } - if (prev_extent_end < end && prev_extent_end < i_size) { + if (prev_extent_end < i_size) { u64 hole_len; btrfs_release_path(path); - hole_len = min(ALIGN(i_size, fs_info->sectorsize), end); - hole_len -= prev_extent_end; + hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize); ret = btrfs_insert_file_extent(trans, root->log_root, ino, prev_extent_end, 0, 0, hole_len, 0, hole_len, @@ -4971,8 +4949,6 @@ static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, const u64 logged_isize, const bool recursive_logging, const int inode_only, - const u64 start, - const u64 end, struct btrfs_log_ctx *ctx, bool *need_log_inode_item) { @@ -4981,21 +4957,6 @@ static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, int ins_nr = 0; int ret; - /* - * We must make sure we don't copy extent items that are entirely out of - * the range [start, end - 1]. This is not just an optimization to avoid - * copying but also needed to avoid a corruption where we end up with - * file extent items in the log tree that have overlapping ranges - this - * can happen if we race with ordered extent completion for ranges that - * are outside our target range. For example we copy an extent item and - * when we move to the next leaf, that extent was trimmed and a new one - * covering a subrange of it, but with a higher key, was inserted - we - * would then copy this other extent too, resulting in a log tree with - * 2 extent items that represent overlapping ranges. - * - * We can copy the entire extents at the range bondaries however, even - * if they cover an area outside the target range. That's ok. - */ while (1) { ret = btrfs_search_forward(root, min_key, path, trans->transid); if (ret < 0) @@ -5063,29 +5024,6 @@ again: goto next_slot; } - if (min_key->type == BTRFS_EXTENT_DATA_KEY) { - const u64 extent_end = btrfs_file_extent_end(path); - - if (extent_end <= start) { - if (ins_nr > 0) { - ret = copy_items(trans, inode, dst_path, - path, ins_start_slot, - ins_nr, inode_only, - logged_isize); - if (ret < 0) - return ret; - ins_nr = 0; - } - goto next_slot; - } - if (extent_end >= end) { - ins_nr++; - if (ins_nr == 1) - ins_start_slot = path->slots[0]; - break; - } - } - if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { ins_nr++; goto next_slot; @@ -5151,8 +5089,8 @@ next_key: static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_inode *inode, int inode_only, - u64 start, - u64 end, + const loff_t start, + const loff_t end, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -5180,9 +5118,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, return -ENOMEM; } - start = ALIGN_DOWN(start, fs_info->sectorsize); - end = ALIGN(end, fs_info->sectorsize); - min_key.objectid = ino; min_key.type = BTRFS_INODE_ITEM_KEY; min_key.offset = 0; @@ -5298,8 +5233,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, err = copy_inode_items_to_log(trans, inode, &min_key, &max_key, path, dst_path, logged_isize, - recursive_logging, inode_only, - start, end, ctx, &need_log_inode_item); + recursive_logging, inode_only, ctx, + &need_log_inode_item); if (err) goto out_unlock; @@ -5312,7 +5247,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) { btrfs_release_path(path); btrfs_release_path(dst_path); - err = btrfs_log_holes(trans, root, inode, path, start, end); + err = btrfs_log_holes(trans, root, inode, path); if (err) goto out_unlock; } diff --git a/fs/buffer.c b/fs/buffer.c index f73276d746bb..a60f60396cfa 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -967,7 +967,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, struct page *page; struct buffer_head *bh; sector_t end_block; - int ret = 0; /* Will call free_more_memory() */ + int ret = 0; gfp_t gfp_mask; gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; @@ -1371,6 +1371,17 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) } EXPORT_SYMBOL(__breadahead); +void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size, + gfp_t gfp) +{ + struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); + if (likely(bh)) { + ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); + brelse(bh); + } +} +EXPORT_SYMBOL(__breadahead_gfp); + /** * __bread_gfp() - reads a specified block and returns the bh * @bdev: the block_device to read from diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index d594c2627430..4c4202c93b71 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1051,8 +1051,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, /* If op failed, mark everyone involved for errors */ if (result) { - int pathlen; - u64 base; + int pathlen = 0; + u64 base = 0; char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, &base, 0); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4a5ccbb7e808..afdfca965a7f 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -527,8 +527,8 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, if (result) { struct dentry *dentry = req->r_dentry; - int pathlen; - u64 base; + int pathlen = 0; + u64 base = 0; char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, &base, 0); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 4e5be79bf080..903d9edfd4bf 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -521,7 +521,7 @@ extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); static inline void ceph_mdsc_free_path(char *path, int len) { - if (path) + if (!IS_ERR_OR_NULL(path)) __putname(path - (PATH_MAX - 1 - len)); } diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 140efc1a9374..182b864b3075 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -594,6 +594,8 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr) cifs_max_pending); set_credits(server, server->maxReq); server->maxBuf = le16_to_cpu(rsp->MaxBufSize); + /* set up max_read for readpages check */ + server->max_read = server->maxBuf; /* even though we do not use raw we might as well set this accurately, in case we ever find a need for it */ if ((le16_to_cpu(rsp->RawMode) & RAW_ENABLE) == RAW_ENABLE) { @@ -755,6 +757,8 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) set_credits(server, server->maxReq); /* probably no need to store and check maxvcs */ server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize); + /* set up max_read for readpages check */ + server->max_read = server->maxBuf; server->max_rw = le32_to_cpu(pSMBr->MaxRawSize); cifs_dbg(NOISY, "Max buf = %d\n", ses->server->maxBuf); server->capabilities = le32_to_cpu(pSMBr->Capabilities); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 8fbbdcdad8ff..390d2b15ef6e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -61,7 +61,7 @@ static void cifs_set_ops(struct inode *inode) } /* check if server can support readpages */ - if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf < + if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read < PAGE_SIZE + MAX_CIFS_HDR_SIZE) inode->i_data.a_ops = &cifs_addr_ops_smallbuf; else diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 47d3e382ecaa..b30aa3cdd845 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1552,6 +1552,21 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data) } rc = SMB2_sess_establish_session(sess_data); +#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS + if (ses->server->dialect < SMB30_PROT_ID) { + cifs_dbg(VFS, "%s: dumping generated SMB2 session keys\n", __func__); + /* + * The session id is opaque in terms of endianness, so we can't + * print it as a long long. we dump it as we got it on the wire + */ + cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid), + &ses->Suid); + cifs_dbg(VFS, "Session Key %*ph\n", + SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); + cifs_dbg(VFS, "Signing Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->auth_key.response); + } +#endif out: kfree(ntlmssp_blob); SMB2_sess_free_buffer(sess_data); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 1a6c227ada8f..c0348e3b1695 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -660,8 +660,8 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE)) { - dump_stack(); - cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n", shdr->Command, shdr->MessageId); + cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n", + shdr->Command, shdr->MessageId); return -EACCES; } else return 0; diff --git a/fs/coredump.c b/fs/coredump.c index f8296a82d01d..408418e6aa13 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -211,6 +211,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, return -ENOMEM; (*argv)[(*argc)++] = 0; ++pat_ptr; + if (!(*pat_ptr)) + return -ENOMEM; } /* Repeat as long as we have more pattern to process and more output diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 6a04cc02565a..6774a5a6ded8 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -91,7 +91,6 @@ static int exfat_allocate_bitmap(struct super_block *sb, } } - sbi->pbr_bh = NULL; return 0; } @@ -137,8 +136,6 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi) { int i; - brelse(sbi->pbr_bh); - for (i = 0; i < sbi->map_sectors; i++) __brelse(sbi->vol_amap[i]); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 67d4e46fb810..d67fb8a6f770 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -507,6 +507,7 @@ void exfat_msg(struct super_block *sb, const char *lv, const char *fmt, ...) __printf(3, 4) __cold; void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 tz, __le16 time, __le16 date, u8 time_ms); +void exfat_truncate_atime(struct timespec64 *ts); void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 *tz, __le16 *time, __le16 *date, u8 *time_ms); unsigned short exfat_calc_chksum_2byte(void *data, int len, diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 483f683757aa..4f76764165cf 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -273,6 +273,7 @@ int exfat_getattr(const struct path *path, struct kstat *stat, struct exfat_inode_info *ei = EXFAT_I(inode); generic_fillattr(inode, stat); + exfat_truncate_atime(&stat->atime); stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = ei->i_crtime.tv_sec; stat->btime.tv_nsec = ei->i_crtime.tv_nsec; @@ -339,6 +340,7 @@ int exfat_setattr(struct dentry *dentry, struct iattr *attr) } setattr_copy(inode, attr); + exfat_truncate_atime(&inode->i_atime); mark_inode_dirty(inode); out: diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c index 14a3300848f6..ebd2cbe3cbc1 100644 --- a/fs/exfat/misc.c +++ b/fs/exfat/misc.c @@ -88,7 +88,8 @@ void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, if (time_ms) { ts->tv_sec += time_ms / 100; ts->tv_nsec = (time_ms % 100) * 10 * NSEC_PER_MSEC; - } + } else + ts->tv_nsec = 0; if (tz & EXFAT_TZ_VALID) /* Adjust timezone to UTC0. */ @@ -124,6 +125,17 @@ void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, *tz = EXFAT_TZ_VALID; } +/* + * The timestamp for access_time has double seconds granularity. + * (There is no 10msIncrement field for access_time unlike create/modify_time) + * atime also has only a 2-second resolution. + */ +void exfat_truncate_atime(struct timespec64 *ts) +{ + ts->tv_sec = round_down(ts->tv_sec, 2); + ts->tv_nsec = 0; +} + unsigned short exfat_calc_chksum_2byte(void *data, int len, unsigned short chksum, int type) { diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index a8681d91f569..b72d782568b8 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -595,6 +595,7 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, inode_inc_iversion(inode); inode->i_mtime = inode->i_atime = inode->i_ctime = EXFAT_I(inode)->i_crtime = current_time(inode); + exfat_truncate_atime(&inode->i_atime); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); @@ -854,6 +855,7 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) inode_inc_iversion(dir); dir->i_mtime = dir->i_atime = current_time(dir); + exfat_truncate_atime(&dir->i_atime); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else @@ -861,6 +863,7 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) clear_nlink(inode); inode->i_mtime = inode->i_atime = current_time(inode); + exfat_truncate_atime(&inode->i_atime); exfat_unhash_inode(inode); exfat_d_version_set(dentry, inode_query_iversion(dir)); unlock: @@ -903,6 +906,7 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode_inc_iversion(inode); inode->i_mtime = inode->i_atime = inode->i_ctime = EXFAT_I(inode)->i_crtime = current_time(inode); + exfat_truncate_atime(&inode->i_atime); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); @@ -1019,6 +1023,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) inode_inc_iversion(dir); dir->i_mtime = dir->i_atime = current_time(dir); + exfat_truncate_atime(&dir->i_atime); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else @@ -1027,6 +1032,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) clear_nlink(inode); inode->i_mtime = inode->i_atime = current_time(inode); + exfat_truncate_atime(&inode->i_atime); exfat_unhash_inode(inode); exfat_d_version_set(dentry, inode_query_iversion(dir)); unlock: @@ -1387,6 +1393,7 @@ static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry, inode_inc_iversion(new_dir); new_dir->i_ctime = new_dir->i_mtime = new_dir->i_atime = EXFAT_I(new_dir)->i_crtime = current_time(new_dir); + exfat_truncate_atime(&new_dir->i_atime); if (IS_DIRSYNC(new_dir)) exfat_sync_inode(new_dir); else diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 16ed202ef527..0565d5539d57 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -49,6 +49,7 @@ static void exfat_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); exfat_set_vol_flags(sb, VOL_CLEAN); exfat_free_bitmap(sbi); + brelse(sbi->pbr_bh); mutex_unlock(&sbi->s_lock); call_rcu(&sbi->rcu, exfat_delayed_free); @@ -100,7 +101,7 @@ static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf) int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag) { struct exfat_sb_info *sbi = EXFAT_SB(sb); - struct pbr64 *bpb; + struct pbr64 *bpb = (struct pbr64 *)sbi->pbr_bh->b_data; bool sync = 0; /* flags are not changed */ @@ -115,15 +116,6 @@ int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag) if (sb_rdonly(sb)) return 0; - if (!sbi->pbr_bh) { - sbi->pbr_bh = sb_bread(sb, 0); - if (!sbi->pbr_bh) { - exfat_msg(sb, KERN_ERR, "failed to read boot sector"); - return -ENOMEM; - } - } - - bpb = (struct pbr64 *)sbi->pbr_bh->b_data; bpb->bsx.vol_flags = cpu_to_le16(new_flag); if (new_flag == VOL_DIRTY && !buffer_dirty(sbi->pbr_bh)) @@ -159,7 +151,6 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",iocharset=utf8"); else if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); - seq_printf(m, ",bps=%ld", sb->s_blocksize); if (opts->errors == EXFAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == EXFAT_ERRORS_PANIC) @@ -351,14 +342,15 @@ static int exfat_read_root(struct inode *inode) exfat_save_attr(inode, ATTR_SUBDIR); inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = current_time(inode); + exfat_truncate_atime(&inode->i_atime); exfat_cache_init_inode(inode); return 0; } -static struct pbr *exfat_read_pbr_with_logical_sector(struct super_block *sb, - struct buffer_head **prev_bh) +static struct pbr *exfat_read_pbr_with_logical_sector(struct super_block *sb) { - struct pbr *p_pbr = (struct pbr *) (*prev_bh)->b_data; + struct exfat_sb_info *sbi = EXFAT_SB(sb); + struct pbr *p_pbr = (struct pbr *) (sbi->pbr_bh)->b_data; unsigned short logical_sect = 0; logical_sect = 1 << p_pbr->bsx.f64.sect_size_bits; @@ -378,26 +370,23 @@ static struct pbr *exfat_read_pbr_with_logical_sector(struct super_block *sb, } if (logical_sect > sb->s_blocksize) { - struct buffer_head *bh = NULL; - - __brelse(*prev_bh); - *prev_bh = NULL; + brelse(sbi->pbr_bh); + sbi->pbr_bh = NULL; if (!sb_set_blocksize(sb, logical_sect)) { exfat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sect); return NULL; } - bh = sb_bread(sb, 0); - if (!bh) { + sbi->pbr_bh = sb_bread(sb, 0); + if (!sbi->pbr_bh) { exfat_msg(sb, KERN_ERR, "unable to read boot sector (logical sector size = %lu)", sb->s_blocksize); return NULL; } - *prev_bh = bh; - p_pbr = (struct pbr *) bh->b_data; + p_pbr = (struct pbr *)sbi->pbr_bh->b_data; } return p_pbr; } @@ -408,21 +397,20 @@ static int __exfat_fill_super(struct super_block *sb) int ret; struct pbr *p_pbr; struct pbr64 *p_bpb; - struct buffer_head *bh; struct exfat_sb_info *sbi = EXFAT_SB(sb); /* set block size to read super block */ sb_min_blocksize(sb, 512); /* read boot sector */ - bh = sb_bread(sb, 0); - if (!bh) { + sbi->pbr_bh = sb_bread(sb, 0); + if (!sbi->pbr_bh) { exfat_msg(sb, KERN_ERR, "unable to read boot sector"); return -EIO; } /* PRB is read */ - p_pbr = (struct pbr *)bh->b_data; + p_pbr = (struct pbr *)sbi->pbr_bh->b_data; /* check the validity of PBR */ if (le16_to_cpu((p_pbr->signature)) != PBR_SIGNATURE) { @@ -433,7 +421,7 @@ static int __exfat_fill_super(struct super_block *sb) /* check logical sector size */ - p_pbr = exfat_read_pbr_with_logical_sector(sb, &bh); + p_pbr = exfat_read_pbr_with_logical_sector(sb); if (!p_pbr) { ret = -EIO; goto free_bh; @@ -514,7 +502,7 @@ free_alloc_bitmap: free_upcase_table: exfat_free_upcase_table(sbi); free_bh: - brelse(bh); + brelse(sbi->pbr_bh); return ret; } @@ -531,17 +519,18 @@ static int exfat_fill_super(struct super_block *sb, struct fs_context *fc) if (opts->discard) { struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) + if (!blk_queue_discard(q)) { exfat_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); - opts->discard = 0; + opts->discard = 0; + } } sb->s_flags |= SB_NODIRATIME; sb->s_magic = EXFAT_SUPER_MAGIC; sb->s_op = &exfat_sops; - sb->s_time_gran = 1; + sb->s_time_gran = 10 * NSEC_PER_MSEC; sb->s_time_min = EXFAT_MIN_TIMESTAMP_SECS; sb->s_time_max = EXFAT_MAX_TIMESTAMP_SECS; @@ -605,6 +594,7 @@ put_inode: free_table: exfat_free_upcase_table(sbi); exfat_free_bitmap(sbi); + brelse(sbi->pbr_bh); check_nls_io: unload_nls(sbi->nls_io); @@ -717,6 +707,7 @@ static void __exit exit_exfat_fs(void) module_init(init_exfat_fs); module_exit(exit_exfat_fs); +MODULE_ALIAS_FS("exfat"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("exFAT filesystem support"); MODULE_AUTHOR("Samsung Electronics Co., Ltd."); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 0e0a4d6209c7..a32e5f7b5385 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -410,7 +410,7 @@ verified: * Read the bitmap for a given block_group,and validate the * bits for block/inode/inode tables are set in the bitmaps * - * Return buffer_head on success or NULL in case of failure. + * Return buffer_head on success or an ERR_PTR in case of failure. */ struct buffer_head * ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) @@ -502,7 +502,7 @@ out: return ERR_PTR(err); } -/* Returns 0 on success, 1 on error */ +/* Returns 0 on success, -errno on error */ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh) { diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 7f16e1af8d5c..0c76cdd44d90 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -338,9 +338,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, if (inode && inode_needs_sync(inode)) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) { - struct ext4_super_block *es; - - es = EXT4_SB(inode->i_sb)->s_es; ext4_error_inode_err(inode, where, line, bh->b_blocknr, EIO, "IO error syncing itable block"); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 031752cfb6f7..f2b577b315a0 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3374,8 +3374,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); - eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> - inode->i_sb->s_blocksize_bits; + eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) + >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; @@ -3627,8 +3627,8 @@ static int ext4_split_convert_extents(handle_t *handle, __func__, inode->i_ino, (unsigned long long)map->m_lblk, map->m_len); - eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> - inode->i_sb->s_blocksize_bits; + eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) + >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; /* diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b420c9dc444d..4b8c9a9bdf0c 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -113,7 +113,7 @@ verified: * Read the inode allocation bitmap for a given block_group, reading * into the specified slot in the superblock's bitmap cache. * - * Return buffer_head of bitmap on success or NULL. + * Return buffer_head of bitmap on success, or an ERR_PTR on error. */ static struct buffer_head * ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) @@ -662,7 +662,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent, * block has been written back to disk. (Yes, these values are * somewhat arbitrary...) */ -#define RECENTCY_MIN 5 +#define RECENTCY_MIN 60 #define RECENTCY_DIRTY 300 static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e416096fc081..2a4aae6acdcb 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1973,7 +1973,7 @@ static int ext4_writepage(struct page *page, bool keep_towrite = false; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { - ext4_invalidatepage(page, 0, PAGE_SIZE); + inode->i_mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); return -EIO; } @@ -4364,7 +4364,7 @@ make_io: if (end > table) end = table; while (b <= end) - sb_breadahead(sb, b++); + sb_breadahead_unmovable(sb, b++); } /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 87c85be4c12e..30d5d97548c4 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1943,7 +1943,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, int free; free = e4b->bd_info->bb_free; - BUG_ON(free <= 0); + if (WARN_ON(free <= 0)) + return; i = e4b->bd_info->bb_first_free; @@ -1966,7 +1967,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, } mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); - BUG_ON(ex.fe_len <= 0); + if (WARN_ON(ex.fe_len <= 0)) + break; if (free < ex.fe_len) { ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9728e7b0e84f..bf5fcb477f66 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -596,7 +596,6 @@ void __ext4_error_file(struct file *file, const char *function, { va_list args; struct va_format vaf; - struct ext4_super_block *es; struct inode *inode = file_inode(file); char pathname[80], *path; @@ -604,7 +603,6 @@ void __ext4_error_file(struct file *file, const char *function, return; trace_ext4_error(inode->i_sb, function, line); - es = EXT4_SB(inode->i_sb)->s_es; if (ext4_error_ratelimit(inode->i_sb)) { path = file_path(file, pathname, sizeof(pathname)); if (IS_ERR(path)) @@ -4340,7 +4338,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Pre-read the descriptors into the buffer cache */ for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logical_sb_block, i); - sb_breadahead(sb, block); + sb_breadahead_unmovable(sb, block); } for (i = 0; i < db_count; i++) { diff --git a/fs/io_uring.c b/fs/io_uring.c index 5190bfb6a665..c687f57fb651 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -357,7 +357,6 @@ struct io_timeout_data { struct hrtimer timer; struct timespec64 ts; enum hrtimer_mode mode; - u32 seq_offset; }; struct io_accept { @@ -385,7 +384,7 @@ struct io_timeout { struct file *file; u64 addr; int flags; - unsigned count; + u32 count; }; struct io_rw { @@ -508,6 +507,7 @@ enum { REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, + REQ_F_LINK_HEAD_BIT, REQ_F_LINK_NEXT_BIT, REQ_F_FAIL_LINK_BIT, REQ_F_INFLIGHT_BIT, @@ -543,6 +543,8 @@ enum { /* IOSQE_BUFFER_SELECT */ REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), + /* head of a link */ + REQ_F_LINK_HEAD = BIT(REQ_F_LINK_HEAD_BIT), /* already grabbed next link */ REQ_F_LINK_NEXT = BIT(REQ_F_LINK_NEXT_BIT), /* fail rest of links */ @@ -955,8 +957,8 @@ static inline bool __req_need_defer(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped - + atomic_read(&ctx->cached_cq_overflow); + return req->sequence != ctx->cached_cq_tail + + atomic_read(&ctx->cached_cq_overflow); } static inline bool req_need_defer(struct io_kiocb *req) @@ -1437,7 +1439,7 @@ static bool io_link_cancel_timeout(struct io_kiocb *req) if (ret != -1) { io_cqring_fill_event(req, -ECANCELED); io_commit_cqring(ctx); - req->flags &= ~REQ_F_LINK; + req->flags &= ~REQ_F_LINK_HEAD; io_put_req(req); return true; } @@ -1473,7 +1475,7 @@ static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr) list_del_init(&req->link_list); if (!list_empty(&nxt->link_list)) - nxt->flags |= REQ_F_LINK; + nxt->flags |= REQ_F_LINK_HEAD; *nxtptr = nxt; break; } @@ -1484,7 +1486,7 @@ static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr) } /* - * Called if REQ_F_LINK is set, and we fail the head request + * Called if REQ_F_LINK_HEAD is set, and we fail the head request */ static void io_fail_links(struct io_kiocb *req) { @@ -1517,7 +1519,7 @@ static void io_fail_links(struct io_kiocb *req) static void io_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt) { - if (likely(!(req->flags & REQ_F_LINK))) + if (likely(!(req->flags & REQ_F_LINK_HEAD))) return; /* @@ -1669,7 +1671,7 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req) { - if ((req->flags & REQ_F_LINK) || io_is_fallback_req(req)) + if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req)) return false; if (!(req->flags & REQ_F_FIXED_FILE) || req->io) @@ -2562,7 +2564,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock) req->result = 0; io_size = ret; - if (req->flags & REQ_F_LINK) + if (req->flags & REQ_F_LINK_HEAD) req->result = io_size; /* @@ -2653,7 +2655,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock) req->result = 0; io_size = ret; - if (req->flags & REQ_F_LINK) + if (req->flags & REQ_F_LINK_HEAD) req->result = io_size; /* @@ -2760,7 +2762,7 @@ static bool io_splice_punt(struct file *file) return false; if (!io_file_supports_async(file)) return true; - return !(file->f_mode & O_NONBLOCK); + return !(file->f_flags & O_NONBLOCK); } static int io_splice(struct io_kiocb *req, bool force_nonblock) @@ -4153,25 +4155,62 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, return 1; } +static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll) + __acquires(&req->ctx->completion_lock) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (!req->result && !READ_ONCE(poll->canceled)) { + struct poll_table_struct pt = { ._key = poll->events }; + + req->result = vfs_poll(req->file, &pt) & poll->events; + } + + spin_lock_irq(&ctx->completion_lock); + if (!req->result && !READ_ONCE(poll->canceled)) { + add_wait_queue(poll->head, &poll->wait); + return true; + } + + return false; +} + static void io_async_task_func(struct callback_head *cb) { struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); struct async_poll *apoll = req->apoll; struct io_ring_ctx *ctx = req->ctx; + bool canceled; trace_io_uring_task_run(req->ctx, req->opcode, req->user_data); - WARN_ON_ONCE(!list_empty(&req->apoll->poll.wait.entry)); + if (io_poll_rewait(req, &apoll->poll)) { + spin_unlock_irq(&ctx->completion_lock); + return; + } - if (hash_hashed(&req->hash_node)) { - spin_lock_irq(&ctx->completion_lock); + if (hash_hashed(&req->hash_node)) hash_del(&req->hash_node); - spin_unlock_irq(&ctx->completion_lock); + + canceled = READ_ONCE(apoll->poll.canceled); + if (canceled) { + io_cqring_fill_event(req, -ECANCELED); + io_commit_cqring(ctx); } + spin_unlock_irq(&ctx->completion_lock); + /* restore ->work in case we need to retry again */ memcpy(&req->work, &apoll->work, sizeof(req->work)); + if (canceled) { + kfree(apoll); + io_cqring_ev_posted(ctx); + req_set_fail_links(req); + io_double_put_req(req); + return; + } + __set_current_state(TASK_RUNNING); mutex_lock(&ctx->uring_lock); __io_queue_sqe(req, NULL); @@ -4315,11 +4354,13 @@ static bool __io_poll_remove_one(struct io_kiocb *req, static bool io_poll_remove_one(struct io_kiocb *req) { + struct async_poll *apoll = NULL; bool do_complete; if (req->opcode == IORING_OP_POLL_ADD) { do_complete = __io_poll_remove_one(req, &req->poll); } else { + apoll = req->apoll; /* non-poll requests have submit ref still */ do_complete = __io_poll_remove_one(req, &req->apoll->poll); if (do_complete) @@ -4328,6 +4369,14 @@ static bool io_poll_remove_one(struct io_kiocb *req) hash_del(&req->hash_node); + if (do_complete && apoll) { + /* + * restore ->work because we need to call io_req_work_drop_env. + */ + memcpy(&req->work, &apoll->work, sizeof(req->work)); + kfree(apoll); + } + if (do_complete) { io_cqring_fill_event(req, -ECANCELED); io_commit_cqring(req->ctx); @@ -4342,7 +4391,7 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx) { struct hlist_node *tmp; struct io_kiocb *req; - int i; + int posted = 0, i; spin_lock_irq(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { @@ -4350,11 +4399,12 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx) list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) - io_poll_remove_one(req); + posted += io_poll_remove_one(req); } spin_unlock_irq(&ctx->completion_lock); - io_cqring_ev_posted(ctx); + if (posted) + io_cqring_ev_posted(ctx); } static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) @@ -4423,18 +4473,11 @@ static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt) struct io_ring_ctx *ctx = req->ctx; struct io_poll_iocb *poll = &req->poll; - if (!req->result && !READ_ONCE(poll->canceled)) { - struct poll_table_struct pt = { ._key = poll->events }; - - req->result = vfs_poll(req->file, &pt) & poll->events; - } - - spin_lock_irq(&ctx->completion_lock); - if (!req->result && !READ_ONCE(poll->canceled)) { - add_wait_queue(poll->head, &poll->wait); + if (io_poll_rewait(req, poll)) { spin_unlock_irq(&ctx->completion_lock); return; } + hash_del(&req->hash_node); io_poll_complete(req, req->result, 0); req->flags |= REQ_F_COMP_LOCKED; @@ -4665,11 +4708,12 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, static int io_timeout(struct io_kiocb *req) { - unsigned count; struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data; struct list_head *entry; unsigned span = 0; + u32 count = req->timeout.count; + u32 seq = req->sequence; data = &req->io->timeout; @@ -4678,7 +4722,6 @@ static int io_timeout(struct io_kiocb *req) * timeout event to be satisfied. If it isn't set, then this is * a pure timeout request, sequence isn't used. */ - count = req->timeout.count; if (!count) { req->flags |= REQ_F_TIMEOUT_NOSEQ; spin_lock_irq(&ctx->completion_lock); @@ -4686,8 +4729,7 @@ static int io_timeout(struct io_kiocb *req) goto add; } - req->sequence = ctx->cached_sq_head + count - 1; - data->seq_offset = count; + req->sequence = seq + count; /* * Insertion sort, ensuring the first entry in the list is always @@ -4696,26 +4738,26 @@ static int io_timeout(struct io_kiocb *req) spin_lock_irq(&ctx->completion_lock); list_for_each_prev(entry, &ctx->timeout_list) { struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list); - unsigned nxt_sq_head; + unsigned nxt_seq; long long tmp, tmp_nxt; - u32 nxt_offset = nxt->io->timeout.seq_offset; + u32 nxt_offset = nxt->timeout.count; if (nxt->flags & REQ_F_TIMEOUT_NOSEQ) continue; /* - * Since cached_sq_head + count - 1 can overflow, use type long + * Since seq + count can overflow, use type long * long to store it. */ - tmp = (long long)ctx->cached_sq_head + count - 1; - nxt_sq_head = nxt->sequence - nxt_offset + 1; - tmp_nxt = (long long)nxt_sq_head + nxt_offset - 1; + tmp = (long long)seq + count; + nxt_seq = nxt->sequence - nxt_offset; + tmp_nxt = (long long)nxt_seq + nxt_offset; /* * cached_sq_head may overflow, and it will never overflow twice * once there is some timeout req still be valid. */ - if (ctx->cached_sq_head < nxt_sq_head) + if (seq < nxt_seq) tmp += UINT_MAX; if (tmp > tmp_nxt) @@ -5476,7 +5518,7 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) { struct io_kiocb *nxt; - if (!(req->flags & REQ_F_LINK)) + if (!(req->flags & REQ_F_LINK_HEAD)) return NULL; /* for polled retry, if flag is set, we already went through here */ if (req->flags & REQ_F_POLLED) @@ -5604,54 +5646,11 @@ static inline void io_queue_link_head(struct io_kiocb *req) io_queue_sqe(req, NULL); } -#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ - IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ - IOSQE_BUFFER_SELECT) - -static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, +static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_submit_state *state, struct io_kiocb **link) { struct io_ring_ctx *ctx = req->ctx; - unsigned int sqe_flags; - int ret, id, fd; - - sqe_flags = READ_ONCE(sqe->flags); - - /* enforce forwards compatibility on users */ - if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) { - ret = -EINVAL; - goto err_req; - } - - if ((sqe_flags & IOSQE_BUFFER_SELECT) && - !io_op_defs[req->opcode].buffer_select) { - ret = -EOPNOTSUPP; - goto err_req; - } - - id = READ_ONCE(sqe->personality); - if (id) { - req->work.creds = idr_find(&ctx->personality_idr, id); - if (unlikely(!req->work.creds)) { - ret = -EINVAL; - goto err_req; - } - get_cred(req->work.creds); - } - - /* same numerical values with corresponding REQ_F_*, safe to copy */ - req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK | - IOSQE_ASYNC | IOSQE_FIXED_FILE | - IOSQE_BUFFER_SELECT); - - fd = READ_ONCE(sqe->fd); - ret = io_req_set_file(state, req, fd, sqe_flags); - if (unlikely(ret)) { -err_req: - io_cqring_add_event(req, ret); - io_double_put_req(req); - return false; - } + int ret; /* * If we already have a head request, queue this one for async @@ -5670,42 +5669,39 @@ err_req: * next after the link request. The last one is done via * drain_next flag to persist the effect across calls. */ - if (sqe_flags & IOSQE_IO_DRAIN) { + if (req->flags & REQ_F_IO_DRAIN) { head->flags |= REQ_F_IO_DRAIN; ctx->drain_next = 1; } - if (io_alloc_async_ctx(req)) { - ret = -EAGAIN; - goto err_req; - } + if (io_alloc_async_ctx(req)) + return -EAGAIN; ret = io_req_defer_prep(req, sqe); if (ret) { /* fail even hard links since we don't submit */ head->flags |= REQ_F_FAIL_LINK; - goto err_req; + return ret; } trace_io_uring_link(ctx, req, head); list_add_tail(&req->link_list, &head->link_list); /* last request of a link, enqueue the link */ - if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK))) { + if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { io_queue_link_head(head); *link = NULL; } } else { if (unlikely(ctx->drain_next)) { req->flags |= REQ_F_IO_DRAIN; - req->ctx->drain_next = 0; + ctx->drain_next = 0; } - if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) { - req->flags |= REQ_F_LINK; + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + req->flags |= REQ_F_LINK_HEAD; INIT_LIST_HEAD(&req->link_list); - if (io_alloc_async_ctx(req)) { - ret = -EAGAIN; - goto err_req; - } + if (io_alloc_async_ctx(req)) + return -EAGAIN; + ret = io_req_defer_prep(req, sqe); if (ret) req->flags |= REQ_F_FAIL_LINK; @@ -5715,7 +5711,7 @@ err_req: } } - return true; + return 0; } /* @@ -5789,15 +5785,23 @@ static inline void io_consume_sqe(struct io_ring_ctx *ctx) ctx->cached_sq_head++; } -static void io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe) +#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ + IOSQE_BUFFER_SELECT) + +static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe, + struct io_submit_state *state, bool async) { + unsigned int sqe_flags; + int id, fd; + /* * All io need record the previous position, if LINK vs DARIN, * it can be used to mark the position of the first IO in the * link list. */ - req->sequence = ctx->cached_sq_head; + req->sequence = ctx->cached_sq_head - ctx->cached_sq_dropped; req->opcode = READ_ONCE(sqe->opcode); req->user_data = READ_ONCE(sqe->user_data); req->io = NULL; @@ -5808,17 +5812,50 @@ static void io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, refcount_set(&req->refs, 2); req->task = NULL; req->result = 0; + req->needs_fixed_file = async; INIT_IO_WORK(&req->work, io_wq_submit_work); + + if (unlikely(req->opcode >= IORING_OP_LAST)) + return -EINVAL; + + if (io_op_defs[req->opcode].needs_mm && !current->mm) { + if (unlikely(!mmget_not_zero(ctx->sqo_mm))) + return -EFAULT; + use_mm(ctx->sqo_mm); + } + + sqe_flags = READ_ONCE(sqe->flags); + /* enforce forwards compatibility on users */ + if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) + return -EINVAL; + + if ((sqe_flags & IOSQE_BUFFER_SELECT) && + !io_op_defs[req->opcode].buffer_select) + return -EOPNOTSUPP; + + id = READ_ONCE(sqe->personality); + if (id) { + req->work.creds = idr_find(&ctx->personality_idr, id); + if (unlikely(!req->work.creds)) + return -EINVAL; + get_cred(req->work.creds); + } + + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK | + IOSQE_ASYNC | IOSQE_FIXED_FILE | + IOSQE_BUFFER_SELECT | IOSQE_IO_LINK); + + fd = READ_ONCE(sqe->fd); + return io_req_set_file(state, req, fd, sqe_flags); } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, - struct file *ring_file, int ring_fd, - struct mm_struct **mm, bool async) + struct file *ring_file, int ring_fd, bool async) { struct io_submit_state state, *statep = NULL; struct io_kiocb *link = NULL; int i, submitted = 0; - bool mm_fault = false; /* if we have a backlog and couldn't flush it all, return BUSY */ if (test_bit(0, &ctx->sq_check_overflow)) { @@ -5858,34 +5895,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, break; } - io_init_req(ctx, req, sqe); + err = io_init_req(ctx, req, sqe, statep, async); io_consume_sqe(ctx); /* will complete beyond this point, count as submitted */ submitted++; - if (unlikely(req->opcode >= IORING_OP_LAST)) { - err = -EINVAL; + if (unlikely(err)) { fail_req: io_cqring_add_event(req, err); io_double_put_req(req); break; } - if (io_op_defs[req->opcode].needs_mm && !*mm) { - mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm); - if (unlikely(mm_fault)) { - err = -EFAULT; - goto fail_req; - } - use_mm(ctx->sqo_mm); - *mm = ctx->sqo_mm; - } - - req->needs_fixed_file = async; trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, true, async); - if (!io_submit_sqe(req, sqe, statep, &link)) - break; + err = io_submit_sqe(req, sqe, statep, &link); + if (err) + goto fail_req; } if (unlikely(submitted != nr)) { @@ -5904,10 +5930,19 @@ fail_req: return submitted; } +static inline void io_sq_thread_drop_mm(struct io_ring_ctx *ctx) +{ + struct mm_struct *mm = current->mm; + + if (mm) { + unuse_mm(mm); + mmput(mm); + } +} + static int io_sq_thread(void *data) { struct io_ring_ctx *ctx = data; - struct mm_struct *cur_mm = NULL; const struct cred *old_cred; mm_segment_t old_fs; DEFINE_WAIT(wait); @@ -5948,11 +5983,7 @@ static int io_sq_thread(void *data) * adding ourselves to the waitqueue, as the unuse/drop * may sleep. */ - if (cur_mm) { - unuse_mm(cur_mm); - mmput(cur_mm); - cur_mm = NULL; - } + io_sq_thread_drop_mm(ctx); /* * We're polling. If we're within the defined idle @@ -6016,7 +6047,7 @@ static int io_sq_thread(void *data) } mutex_lock(&ctx->uring_lock); - ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true); + ret = io_submit_sqes(ctx, to_submit, NULL, -1, true); mutex_unlock(&ctx->uring_lock); timeout = jiffies + ctx->sq_thread_idle; } @@ -6025,10 +6056,7 @@ static int io_sq_thread(void *data) task_work_run(); set_fs(old_fs); - if (cur_mm) { - unuse_mm(cur_mm); - mmput(cur_mm); - } + io_sq_thread_drop_mm(ctx); revert_creds(old_cred); kthread_parkme(); @@ -7509,13 +7537,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, wake_up(&ctx->sqo_wait); submitted = to_submit; } else if (to_submit) { - struct mm_struct *cur_mm; - mutex_lock(&ctx->uring_lock); - /* already have mm, so io_submit_sqes() won't try to grab it */ - cur_mm = ctx->sqo_mm; - submitted = io_submit_sqes(ctx, to_submit, f.file, fd, - &cur_mm, false); + submitted = io_submit_sqes(ctx, to_submit, f.file, fd, false); mutex_unlock(&ctx->uring_lock); if (submitted != to_submit) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index f2dc35c22964..b8d78f393365 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2023,6 +2023,7 @@ lookup_again: goto lookup_again; } + spin_unlock(&ino->i_lock); first = true; status = nfs4_select_rw_stateid(ctx->state, iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ, @@ -2032,12 +2033,12 @@ lookup_again: trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_INVALID_OPEN); - spin_unlock(&ino->i_lock); nfs4_schedule_stateid_recovery(server, ctx->state); pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); goto lookup_again; } + spin_lock(&ino->i_lock); } else { nfs4_stateid_copy(&stateid, &lo->plh_stateid); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index c3b11a715082..5cf91322de0f 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1312,6 +1312,7 @@ nfsd4_run_cb_work(struct work_struct *work) container_of(work, struct nfsd4_callback, cb_work); struct nfs4_client *clp = cb->cb_clp; struct rpc_clnt *clnt; + int flags; if (cb->cb_need_restart) { cb->cb_need_restart = false; @@ -1340,7 +1341,8 @@ nfsd4_run_cb_work(struct work_struct *work) } cb->cb_msg.rpc_cred = clp->cl_cb_cred; - rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN, + flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN; + rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags, cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index e32ecedece0f..c107caa56525 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -267,6 +267,8 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, if (!nbl) { nbl= kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { + INIT_LIST_HEAD(&nbl->nbl_list); + INIT_LIST_HEAD(&nbl->nbl_lru); fh_copy_shallow(&nbl->nbl_fh, fh); locks_init_lock(&nbl->nbl_lock); nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client, diff --git a/fs/proc/base.c b/fs/proc/base.c index 6042b646ab27..eb2255e95f62 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1573,6 +1573,7 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf, noffsets = 0; for (pos = kbuf; pos; pos = next_line) { struct proc_timens_offset *off = &offsets[noffsets]; + char clock[10]; int err; /* Find the end of line and ensure we don't look past it */ @@ -1584,10 +1585,21 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf, next_line = NULL; } - err = sscanf(pos, "%u %lld %lu", &off->clockid, + err = sscanf(pos, "%9s %lld %lu", clock, &off->val.tv_sec, &off->val.tv_nsec); if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC) goto out; + + clock[sizeof(clock) - 1] = 0; + if (strcmp(clock, "monotonic") == 0 || + strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0) + off->clockid = CLOCK_MONOTONIC; + else if (strcmp(clock, "boottime") == 0 || + strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0) + off->clockid = CLOCK_BOOTTIME; + else + goto out; + noffsets++; if (noffsets == ARRAY_SIZE(offsets)) { if (next_line) @@ -3274,7 +3286,6 @@ static const struct inode_operations proc_tgid_base_inode_operations = { void proc_flush_pid(struct pid *pid) { proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); - put_pid(pid); } static struct dentry *proc_pid_instantiate(struct dentry * dentry, diff --git a/fs/proc/root.c b/fs/proc/root.c index 2633f10446c3..cdbe9293ea55 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -196,6 +196,13 @@ static void proc_kill_sb(struct super_block *sb) if (ns->proc_thread_self) dput(ns->proc_thread_self); kill_anon_super(sb); + + /* Make the pid namespace safe for the next mount of proc */ + ns->proc_self = NULL; + ns->proc_thread_self = NULL; + ns->pid_gid = GLOBAL_ROOT_GID; + ns->hide_pid = 0; + put_pid_ns(ns); } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 7dc800cce354..c663202da8de 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -266,7 +266,8 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst, if (start < offset + dump->size) { tsz = min(offset + (u64)dump->size - start, (u64)size); buf = dump->buf + start - offset; - if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) { + if (remap_vmalloc_range_partial(vma, dst, buf, 0, + tsz)) { ret = -EFAULT; goto out_unlock; } @@ -624,7 +625,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size); kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz; if (remap_vmalloc_range_partial(vma, vma->vm_start + len, - kaddr, tsz)) + kaddr, 0, tsz)) goto fail; size -= tsz; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index a7be7a9e5c1a..8bf1d15be3f6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -911,7 +911,12 @@ xfs_eofblocks_worker( { struct xfs_mount *mp = container_of(to_delayed_work(work), struct xfs_mount, m_eofblocks_work); + + if (!sb_start_write_trylock(mp->m_super)) + return; xfs_icache_free_eofblocks(mp, NULL); + sb_end_write(mp->m_super); + xfs_queue_eofblocks(mp); } @@ -938,7 +943,12 @@ xfs_cowblocks_worker( { struct xfs_mount *mp = container_of(to_delayed_work(work), struct xfs_mount, m_cowblocks_work); + + if (!sb_start_write_trylock(mp->m_super)) + return; xfs_icache_free_cowblocks(mp, NULL); + sb_end_write(mp->m_super); + xfs_queue_cowblocks(mp); } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index cdfb3cd9a25b..309958186d33 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -2363,7 +2363,10 @@ xfs_file_ioctl( if (error) return error; - return xfs_icache_free_eofblocks(mp, &keofb); + sb_start_write(mp->m_super); + error = xfs_icache_free_eofblocks(mp, &keofb); + sb_end_write(mp->m_super); + return error; } default: diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 50c43422fa17..b2e4598fdf7d 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -167,8 +167,12 @@ typedef struct xfs_mount { struct xfs_kobj m_error_meta_kobj; struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX]; struct xstats m_stats; /* per-fs stats */ - struct ratelimit_state m_flush_inodes_ratelimit; + /* + * Workqueue item so that we can coalesce multiple inode flush attempts + * into a single flush. + */ + struct work_struct m_flush_inodes_work; struct workqueue_struct *m_buf_workqueue; struct workqueue_struct *m_unwritten_workqueue; struct workqueue_struct *m_cil_workqueue; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index b0ce04ffd3cd..107bf2a2f344 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1051,6 +1051,7 @@ xfs_reflink_remap_extent( uirec.br_startblock = irec->br_startblock + rlen; uirec.br_startoff = irec->br_startoff + rlen; uirec.br_blockcount = unmap_len - rlen; + uirec.br_state = irec->br_state; unmap_len = rlen; /* If this isn't a real mapping, we're done. */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index abf06bf9c3f3..424bb9a2d532 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -516,6 +516,20 @@ xfs_destroy_mount_workqueues( destroy_workqueue(mp->m_buf_workqueue); } +static void +xfs_flush_inodes_worker( + struct work_struct *work) +{ + struct xfs_mount *mp = container_of(work, struct xfs_mount, + m_flush_inodes_work); + struct super_block *sb = mp->m_super; + + if (down_read_trylock(&sb->s_umount)) { + sync_inodes_sb(sb); + up_read(&sb->s_umount); + } +} + /* * Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK * or a page lock. We use sync_inodes_sb() here to ensure we block while waiting @@ -526,15 +540,15 @@ void xfs_flush_inodes( struct xfs_mount *mp) { - struct super_block *sb = mp->m_super; - - if (!__ratelimit(&mp->m_flush_inodes_ratelimit)) + /* + * If flush_work() returns true then that means we waited for a flush + * which was already in progress. Don't bother running another scan. + */ + if (flush_work(&mp->m_flush_inodes_work)) return; - if (down_read_trylock(&sb->s_umount)) { - sync_inodes_sb(sb); - up_read(&sb->s_umount); - } + queue_work(mp->m_sync_workqueue, &mp->m_flush_inodes_work); + flush_work(&mp->m_flush_inodes_work); } /* Catch misguided souls that try to use this interface on XFS */ @@ -1369,17 +1383,6 @@ xfs_fc_fill_super( if (error) goto out_free_names; - /* - * Cap the number of invocations of xfs_flush_inodes to 16 for every - * quarter of a second. The magic numbers here were determined by - * observation neither to cause stalls in writeback when there are a - * lot of IO threads and the fs is near ENOSPC, nor cause any fstest - * regressions. YMMV. - */ - ratelimit_state_init(&mp->m_flush_inodes_ratelimit, HZ / 4, 16); - ratelimit_set_flags(&mp->m_flush_inodes_ratelimit, - RATELIMIT_MSG_ON_RELEASE); - error = xfs_init_mount_workqueues(mp); if (error) goto out_close_devices; @@ -1752,6 +1755,7 @@ static int xfs_init_fs_context( spin_lock_init(&mp->m_perag_lock); mutex_init(&mp->m_growlock); atomic_set(&mp->m_active_trans, 0); + INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker); INIT_DELAYED_WORK(&mp->m_cowblocks_work, xfs_cowblocks_worker); diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 36341dfded70..44ec80e70518 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -56,6 +56,7 @@ mandatory-y += topology.h mandatory-y += trace_clock.h mandatory-y += uaccess.h mandatory-y += unaligned.h +mandatory-y += vermagic.h mandatory-y += vga.h mandatory-y += word-at-a-time.h mandatory-y += xor.h diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index b3f1082cc435..1c4fd950f091 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -163,7 +163,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } -void hyperv_report_panic(struct pt_regs *regs, long err); +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); void hyperv_report_panic_msg(phys_addr_t pa, size_t size); bool hv_is_hyperv_initialized(void); bool hv_is_hibernation_supported(void); diff --git a/include/asm-generic/vermagic.h b/include/asm-generic/vermagic.h new file mode 100644 index 000000000000..084274a1219e --- /dev/null +++ b/include/asm-generic/vermagic.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_GENERIC_VERMAGIC_H +#define _ASM_GENERIC_VERMAGIC_H + +#define MODULE_ARCH_VERMAGIC "" + +#endif /* _ASM_GENERIC_VERMAGIC_H */ diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 4fc87dee005a..ee577a83cfe6 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -54,7 +54,6 @@ enum wb_reason { WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, - WB_REASON_FREE_MORE_MEM, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done diff --git a/include/linux/bio.h b/include/linux/bio.h index c1c0f9ea4e63..a0ee494a6329 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -319,7 +319,7 @@ struct bio_integrity_payload { struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; - struct bio_vec bip_inline_vecs[0];/* embedded bvec array */ + struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; #if defined(CONFIG_BLK_DEV_INTEGRITY) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index f389d7c724bd..b45148ba3291 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -173,7 +173,7 @@ struct blk_mq_hw_ctx { * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also * blk_mq_hw_ctx_size(). */ - struct srcu_struct srcu[0]; + struct srcu_struct srcu[]; }; /** diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 70254ae11769..31eb92876be7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -198,7 +198,7 @@ struct bio { * double allocations for a small number of bio_vecs. This member * MUST obviously be kept at the very end of the bio. */ - struct bio_vec bi_inline_vecs[0]; + struct bio_vec bi_inline_vecs[]; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fd2b2322412d..10960cfabea4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1215,6 +1215,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, struct bpf_prog *bpf_prog_by_id(u32 id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1365,6 +1366,12 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } + +static inline const struct bpf_func_proto * +bpf_base_func_proto(enum bpf_func_id func_id) +{ + return NULL; +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -1502,6 +1509,7 @@ extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; +extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; @@ -1523,6 +1531,7 @@ extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; +extern const struct bpf_func_proto bpf_event_output_data_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -1530,6 +1539,7 @@ const struct bpf_func_proto *bpf_tracing_func_proto( /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6462c5447872..8be150e69c7c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -15,6 +15,7 @@ #define PHY_ID_BCMAC131 0x0143bc70 #define PHY_ID_BCM5481 0x0143bca0 #define PHY_ID_BCM5395 0x0143bcf0 +#define PHY_ID_BCM53125 0x03625f20 #define PHY_ID_BCM54810 0x03625d00 #define PHY_ID_BCM5482 0x0143bcb0 #define PHY_ID_BCM5411 0x00206070 @@ -24,6 +25,7 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 +#define PHY_ID_BCM54140 0xae025019 #define PHY_ID_BCM57780 0x03625d90 #define PHY_ID_BCM89610 0x03625cd0 @@ -114,6 +116,9 @@ #define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10) #define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0) +#define MII_BCM54XX_RDB_ADDR 0x1e +#define MII_BCM54XX_RDB_DATA 0x1f + /* * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) */ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index e0b020eaf32e..15b765a181b8 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -189,6 +189,8 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); +void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, + gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); @@ -319,6 +321,12 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } +static inline void +sb_breadahead_unmovable(struct super_block *sb, sector_t block) +{ + __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); +} + static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h index 511a37302fea..5fd627e9da19 100644 --- a/include/linux/can/dev/peak_canfd.h +++ b/include/linux/can/dev/peak_canfd.h @@ -189,7 +189,7 @@ struct __packed pucan_rx_msg { u8 client; __le16 flags; __le32 can_id; - u8 d[0]; + u8 d[]; }; /* uCAN error types */ @@ -266,7 +266,7 @@ struct __packed pucan_tx_msg { u8 client; __le16 flags; __le32 can_id; - u8 d[0]; + u8 d[]; }; /* build the cmd opcode_channel field with respect to the correct endianness */ diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index 02edeafcb2bf..be8aea04d023 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -28,7 +28,7 @@ struct cpu_rmap { struct { u16 index; u16 dist; - } near[0]; + } near[]; }; #define CPU_RMAP_DIST_INF 0xffff diff --git a/include/linux/digsig.h b/include/linux/digsig.h index 594fc66a395a..2ace69e41088 100644 --- a/include/linux/digsig.h +++ b/include/linux/digsig.h @@ -29,7 +29,7 @@ struct pubkey_hdr { uint32_t timestamp; /* key made, always 0 for now */ uint8_t algo; uint8_t nmpi; - char mpi[0]; + char mpi[]; } __packed; struct signature_hdr { @@ -39,7 +39,7 @@ struct signature_hdr { uint8_t hash; uint8_t keyid[8]; uint8_t nmpi; - char mpi[0]; + char mpi[]; } __packed; #if defined(CONFIG_SIGNATURE) || defined(CONFIG_SIGNATURE_MODULE) diff --git a/include/linux/dirent.h b/include/linux/dirent.h index fc61f3cff72f..99002220cd45 100644 --- a/include/linux/dirent.h +++ b/include/linux/dirent.h @@ -7,7 +7,7 @@ struct linux_dirent64 { s64 d_off; unsigned short d_reclen; unsigned char d_type; - char d_name[0]; + char d_name[]; }; #endif diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 564e96f625ff..1c630e2c2756 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -101,7 +101,7 @@ struct enclosure_device { struct device edev; struct enclosure_component_callbacks *cb; int components; - struct enclosure_component component[0]; + struct enclosure_component component[]; }; static inline struct enclosure_device * diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index d249b88a4d5a..ade6486a3382 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -36,7 +36,7 @@ struct em_cap_state { struct em_perf_domain { struct em_cap_state *table; int nr_cap_states; - unsigned long cpus[0]; + unsigned long cpus[]; }; #ifdef CONFIG_ENERGY_MODEL diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c1d379bf6ee1..a23b26eab479 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -35,7 +35,7 @@ struct compat_ethtool_rxnfc { compat_u64 data; struct compat_ethtool_rx_flow_spec fs; u32 rule_cnt; - u32 rule_locs[0]; + u32 rule_locs[]; }; #endif /* CONFIG_COMPAT */ @@ -462,7 +462,7 @@ int ethtool_check_ops(const struct ethtool_ops *ops); struct ethtool_rx_flow_rule { struct flow_rule *rule; - unsigned long priv[0]; + unsigned long priv[]; }; struct ethtool_rx_flow_spec_input { diff --git a/include/linux/filter.h b/include/linux/filter.h index 9b5aa5c483cc..af37318bb1c5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -863,8 +863,6 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); -const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 5b14a0f38124..0bd581003cd5 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -76,7 +76,7 @@ struct gen_pool_chunk { void *owner; /* private data to retrieve at alloc time */ unsigned long start_addr; /* start address of memory chunk */ unsigned long end_addr; /* end address of memory chunk (inclusive) */ - unsigned long bits[0]; /* bitmap for allocating memory chunk */ + unsigned long bits[]; /* bitmap for allocating memory chunk */ }; /* diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 456fc17ecb1c..45d36ba4826b 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -461,12 +461,6 @@ i2c_new_scanned_device(struct i2c_adapter *adap, unsigned short const *addr_list, int (*probe)(struct i2c_adapter *adap, unsigned short addr)); -struct i2c_client * -i2c_new_probed_device(struct i2c_adapter *adap, - struct i2c_board_info *info, - unsigned short const *addr_list, - int (*probe)(struct i2c_adapter *adap, unsigned short addr)); - /* Common custom probe functions */ int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 463047d0190b..faa6586a5783 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -38,7 +38,7 @@ struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; - __be32 sl_addr[0]; + __be32 sl_addr[]; }; #define IP_SFLSIZE(count) (sizeof(struct ip_sf_socklist) + \ diff --git a/include/linux/ihex.h b/include/linux/ihex.h index 98cb5ce0b0a0..b824877e6d1b 100644 --- a/include/linux/ihex.h +++ b/include/linux/ihex.h @@ -18,7 +18,7 @@ struct ihex_binrec { __be32 addr; __be16 len; - uint8_t data[0]; + uint8_t data[]; } __attribute__((packed)); static inline uint16_t ihex_binrec_size(const struct ihex_binrec *p) diff --git a/include/linux/irq.h b/include/linux/irq.h index 9315fbb87db3..8d5bc2c237d7 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -573,8 +573,6 @@ enum { #define IRQ_DEFAULT_INIT_FLAGS ARCH_IRQ_INIT_FLAGS struct irqaction; -extern int setup_irq(unsigned int irq, struct irqaction *new); -extern void remove_irq(unsigned int irq, struct irqaction *act); extern int setup_percpu_irq(unsigned int irq, struct irqaction *new); extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); @@ -1043,7 +1041,7 @@ struct irq_chip_generic { unsigned long unused; struct irq_domain *domain; struct list_head list; - struct irq_chip_type chip_types[0]; + struct irq_chip_type chip_types[]; }; /** @@ -1079,7 +1077,7 @@ struct irq_domain_chip_generic { unsigned int irq_flags_to_clear; unsigned int irq_flags_to_set; enum irq_gc_flags gc_flags; - struct irq_chip_generic *gc[0]; + struct irq_chip_generic *gc[]; }; /* Generic chip callback functions */ diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 765d9b769b69..6c36b6cc3edf 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -243,6 +243,7 @@ #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) +#define GICR_TYPER_DIRTY (1U << 2) #define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) #define GICR_TYPER_RVPEID (1U << 7) @@ -686,6 +687,7 @@ struct rdists { bool has_vlpis; bool has_rvpeid; bool has_direct_lpi; + bool has_vpend_valid_dirty; }; struct irq_domain; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6d58beb65454..01276e3d01b9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1048,7 +1048,7 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn) start = slot + 1; } - if (gfn >= memslots[start].base_gfn && + if (start < slots->used_slots && gfn >= memslots[start].base_gfn && gfn < memslots[start].base_gfn + memslots[start].npages) { atomic_set(&slots->lru_slot, start); return &memslots[start]; diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index d5ceb2839a2d..9dcaa3e582c9 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -34,7 +34,7 @@ struct list_lru_one { struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_one *lru[0]; + struct list_lru_one *lru[]; }; struct list_lru_node { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1b4150ff64be..d275c72c4f8e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -106,7 +106,7 @@ struct lruvec_stat { */ struct memcg_shrinker_map { struct rcu_head rcu; - unsigned long map[0]; + unsigned long map[]; }; /* @@ -148,7 +148,7 @@ struct mem_cgroup_threshold_ary { /* Size of entries[] */ unsigned int size; /* Array of thresholds */ - struct mem_cgroup_threshold entries[0]; + struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 5613e677a5f9..b919d143a9a6 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -92,6 +92,18 @@ struct mlx5_accel_esp_xfrm_attrs { union { struct aes_gcm_keymat aes_gcm; } keymat; + + union { + __be32 a4; + __be32 a6[4]; + } saddr; + + union { + __be32 a4; + __be32 a6[4]; + } daddr; + + u8 is_ipv6; }; struct mlx5_accel_esp_xfrm { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 130a668049ab..5a8d40f1ffe2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -288,6 +288,7 @@ enum netdev_state_t { __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, + __LINK_STATE_TESTING, }; @@ -328,6 +329,7 @@ struct napi_struct { unsigned long state; int weight; + int defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL @@ -1994,6 +1996,7 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; + int napi_defer_hard_irqs; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -3908,6 +3911,46 @@ static inline bool netif_dormant(const struct net_device *dev) /** + * netif_testing_on - mark device as under test. + * @dev: network device + * + * Mark device as under test (as per RFC2863). + * + * The testing state indicates that some test(s) must be performed on + * the interface. After completion, of the test, the interface state + * will change to up, dormant, or down, as appropriate. + */ +static inline void netif_testing_on(struct net_device *dev) +{ + if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing_off - set device as not under test. + * @dev: network device + * + * Device is not in testing state. + */ +static inline void netif_testing_off(struct net_device *dev) +{ + if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) + linkwatch_fire_event(dev); +} + +/** + * netif_testing - test if device is under test + * @dev: network device + * + * Check if device is under test + */ +static inline bool netif_testing(const struct net_device *dev) +{ + return test_bit(__LINK_STATE_TESTING, &dev->state); +} + + +/** * netif_oper_up - test if device is operational * @dev: network device * diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 491a2b7e77c1..0f61a4ac6bcf 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -30,7 +30,9 @@ extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_phy_register_fixed_link(struct device_node *np); extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); - +extern int of_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct device_node *child, u32 addr); static inline int of_mdio_parse_addr(struct device *dev, const struct device_node *np) @@ -118,6 +120,13 @@ static inline bool of_phy_is_fixed_link(struct device_node *np) { return false; } + +static inline int of_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct device_node *child, u32 addr) +{ + return -ENOSYS; +} #endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 2432ca463ddc..e2bfb9240587 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -241,6 +241,9 @@ struct mii_bus { int (*reset)(struct mii_bus *bus); struct mdio_bus_stats stats[PHY_MAX_ADDR]; + unsigned int is_managed:1; /* is device-managed */ + unsigned int is_managed_registered:1; + /* * A lock to ensure that only one thing can read/write * the MDIO bus at a time @@ -286,6 +289,20 @@ static inline struct mii_bus *mdiobus_alloc(void) int __mdiobus_register(struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) +static inline int devm_mdiobus_register(struct mii_bus *bus) +{ + int ret; + + if (!bus->is_managed) + return -EPERM; + + ret = mdiobus_register(bus); + if (!ret) + bus->is_managed_registered = 1; + + return ret; +} + void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); @@ -1234,10 +1251,6 @@ static inline int genphy_config_aneg(struct phy_device *phydev) return __genphy_config_aneg(phydev, false); } -static inline int genphy_no_soft_reset(struct phy_device *phydev) -{ - return 0; -} static inline int genphy_no_ack_interrupt(struct phy_device *phydev) { return 0; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 3f8d37ec5503..cc5b452a184e 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -67,6 +67,9 @@ struct phylink_config { struct device *dev; enum phylink_op_type type; bool pcs_poll; + bool poll_fixed_state; + void (*get_fixed_state)(struct phylink_config *config, + struct phylink_link_state *state); }; /** @@ -366,9 +369,6 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); void phylink_disconnect_phy(struct phylink *); -int phylink_fixed_state_cb(struct phylink *, - void (*cb)(struct net_device *dev, - struct phylink_link_state *)); void phylink_mac_change(struct phylink *, bool up); diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h index 25f46a939637..3e268e636b5b 100644 --- a/include/linux/platform_data/wilco-ec.h +++ b/include/linux/platform_data/wilco-ec.h @@ -83,7 +83,7 @@ struct wilco_ec_response { u16 result; u16 data_size; u8 reserved[2]; - u8 data[0]; + u8 data[]; } __packed; /** diff --git a/include/linux/pnp.h b/include/linux/pnp.h index b18dca67253d..c2a7cfbca713 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -220,10 +220,8 @@ struct pnp_card { #define global_to_pnp_card(n) list_entry(n, struct pnp_card, global_list) #define protocol_to_pnp_card(n) list_entry(n, struct pnp_card, protocol_list) #define to_pnp_card(n) container_of(n, struct pnp_card, dev) -#define pnp_for_each_card(card) \ - for((card) = global_to_pnp_card(pnp_cards.next); \ - (card) != global_to_pnp_card(&pnp_cards); \ - (card) = global_to_pnp_card((card)->global_list.next)) +#define pnp_for_each_card(card) \ + list_for_each_entry(card, &pnp_cards, global_list) struct pnp_card_link { struct pnp_card *card; @@ -276,14 +274,9 @@ struct pnp_dev { #define card_to_pnp_dev(n) list_entry(n, struct pnp_dev, card_list) #define protocol_to_pnp_dev(n) list_entry(n, struct pnp_dev, protocol_list) #define to_pnp_dev(n) container_of(n, struct pnp_dev, dev) -#define pnp_for_each_dev(dev) \ - for((dev) = global_to_pnp_dev(pnp_global.next); \ - (dev) != global_to_pnp_dev(&pnp_global); \ - (dev) = global_to_pnp_dev((dev)->global_list.next)) -#define card_for_each_dev(card,dev) \ - for((dev) = card_to_pnp_dev((card)->devices.next); \ - (dev) != card_to_pnp_dev(&(card)->devices); \ - (dev) = card_to_pnp_dev((dev)->card_list.next)) +#define pnp_for_each_dev(dev) list_for_each_entry(dev, &pnp_global, global_list) +#define card_for_each_dev(card, dev) \ + list_for_each_entry(dev, &(card)->devices, card_list) #define pnp_dev_name(dev) (dev)->name static inline void *pnp_get_drvdata(struct pnp_dev *pdev) @@ -437,14 +430,10 @@ struct pnp_protocol { }; #define to_pnp_protocol(n) list_entry(n, struct pnp_protocol, protocol_list) -#define protocol_for_each_card(protocol,card) \ - for((card) = protocol_to_pnp_card((protocol)->cards.next); \ - (card) != protocol_to_pnp_card(&(protocol)->cards); \ - (card) = protocol_to_pnp_card((card)->protocol_list.next)) -#define protocol_for_each_dev(protocol,dev) \ - for((dev) = protocol_to_pnp_dev((protocol)->devices.next); \ - (dev) != protocol_to_pnp_dev(&(protocol)->devices); \ - (dev) = protocol_to_pnp_dev((dev)->protocol_list.next)) +#define protocol_for_each_card(protocol, card) \ + list_for_each_entry(card, &(protocol)->cards, protocol_list) +#define protocol_for_each_dev(protocol, dev) \ + list_for_each_entry(dev, &(protocol)->devices, protocol_list) extern struct bus_type pnp_bus_type; diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 540595a321a7..90797f1b421d 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -28,7 +28,7 @@ struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; - struct posix_acl_entry a_entries[0]; + struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ diff --git a/include/linux/rio.h b/include/linux/rio.h index 317bace5ac64..2cd637268b4f 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -100,7 +100,7 @@ struct rio_switch { u32 port_ok; struct rio_switch_ops *ops; spinlock_t lock; - struct rio_dev *nextdev[0]; + struct rio_dev *nextdev[]; }; /** @@ -201,7 +201,7 @@ struct rio_dev { u8 hopcount; struct rio_dev *prev; atomic_t state; - struct rio_switch rswitch[0]; /* RIO switch info */ + struct rio_switch rswitch[]; /* RIO switch info */ }; #define rio_dev_g(n) list_entry(n, struct rio_dev, global_list) diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 5974cedd008c..238bb85243d3 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -54,7 +54,7 @@ struct rs_codec { */ struct rs_control { struct rs_codec *codec; - uint16_t buffers[0]; + uint16_t buffers[]; }; /* General purpose RS codec, 8-bit data width, symbol width 1-15 bit */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index af9319e4cfb9..95253ad792b0 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -142,7 +142,7 @@ struct sched_domain { * by attaching extra space to the end of the structure, * depending on how many CPUs the kernel has booted up with) */ - unsigned long span[0]; + unsigned long span[]; }; static inline struct cpumask *sched_domain_span(struct sched_domain *sd) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3a2ac7072dbb..3000c526f552 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4162,7 +4162,7 @@ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ - char data[0] __aligned(8); + char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(void); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fbafb353e9be..bd964c31d333 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -177,6 +177,8 @@ struct plat_stmmacenet_data { struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*fix_mac_speed)(void *priv, unsigned int speed); + int (*serdes_powerup)(struct net_device *ndev, void *priv); + void (*serdes_powerdown)(struct net_device *ndev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); struct mac_device_info *(*setup)(void *priv); diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 78fe2ac6dc6c..cbcfbd0521e3 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -170,6 +170,7 @@ extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma); extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); +extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/swap.h b/include/linux/swap.h index b835d8dbea0e..e1bbf7a16b27 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -275,7 +275,7 @@ struct swap_info_struct { */ struct work_struct discard_work; /* discard worker */ struct swap_cluster_list discard_clusters; /* discard clusters list */ - struct plist_node avail_lists[0]; /* + struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index eb6cbdf10e50..44a7f9169ac6 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -295,7 +295,7 @@ struct bts_header { u32 magic; u32 version; u8 future[24]; - u8 actions[0]; + u8 actions[]; } __attribute__ ((packed)); /** @@ -305,7 +305,7 @@ struct bts_header { struct bts_action { u16 type; u16 size; - u8 data[0]; + u8 data[]; } __attribute__ ((packed)); struct bts_action_send { @@ -315,7 +315,7 @@ struct bts_action_send { struct bts_action_wait { u32 msec; u32 size; - u8 data[0]; + u8 data[]; } __attribute__ ((packed)); struct bts_action_delay { diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 131ea1bad458..c253461b1c4e 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -28,7 +28,7 @@ struct tcpa_event { u32 event_type; u8 pcr_value[20]; /* SHA1 */ u32 event_size; - u8 event_data[0]; + u8 event_data[]; }; enum tcpa_event_types { @@ -55,7 +55,7 @@ enum tcpa_event_types { struct tcpa_pc_event { u32 event_id; u32 event_size; - u8 event_data[0]; + u8 event_data[]; }; enum tcpa_pc_event_ids { @@ -102,7 +102,7 @@ struct tcg_pcr_event { struct tcg_event_field { u32 event_size; - u8 event[0]; + u8 event[]; } __packed; struct tcg_pcr_event2_head { diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 1fb11daa5c53..a1fecf311621 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -156,8 +156,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * Note, the proto and args passed in includes "__data" as the first parameter. * The reason for this is to handle the "void" prototype. If a tracepoint * has a "void" prototype, then it is invalid to declare a function - * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just - * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". + * as "(void *, void)". */ #define __DO_TRACE(tp, proto, args, cond, rcuidle) \ do { \ @@ -373,25 +372,6 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) # define __tracepoint_string #endif -/* - * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype - * (void). "void" is a special value in a function prototype and can - * not be combined with other arguments. Since the DECLARE_TRACE() - * macro adds a data element at the beginning of the prototype, - * we need a way to differentiate "(void *data, proto)" from - * "(void *data, void)". The second prototype is invalid. - * - * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype - * and "void *__data" as the callback prototype. - * - * DECLARE_TRACE() passes "proto" as the tracepoint protoype and - * "void *__data, proto" as the callback prototype. - */ -#define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , \ - cpu_online(raw_smp_processor_id()), \ - void *__data, __data) - #define DECLARE_TRACE(name, proto, args) \ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ cpu_online(raw_smp_processor_id()), \ diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 733acfb7ef84..5453af87a33e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -164,7 +164,7 @@ struct vdpa_config_ops { u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); /* Device ops */ - u16 (*get_vq_align)(struct vdpa_device *vdev); + u32 (*get_vq_align)(struct vdpa_device *vdev); u64 (*get_features)(struct vdpa_device *vdev); int (*set_features)(struct vdpa_device *vdev, u64 features); void (*set_config_cb)(struct vdpa_device *vdev, diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 9aced11e9000..1eaaa93c37bf 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -1,5 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VERMAGIC_H +#define _LINUX_VERMAGIC_H + +#ifndef INCLUDE_VERMAGIC +#error "This header can be included from kernel/module.c or *.mod.c only" +#endif + #include <generated/utsrelease.h> +#include <asm/vermagic.h> /* Simply sanity version stamp for modules. */ #ifdef CONFIG_SMP @@ -24,9 +32,6 @@ #else #define MODULE_VERMAGIC_MODVERSIONS "" #endif -#ifndef MODULE_ARCH_VERMAGIC -#define MODULE_ARCH_VERMAGIC "" -#endif #ifdef RANDSTRUCT_PLUGIN #include <generated/randomize_layout_hash.h> #define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED @@ -41,3 +46,4 @@ MODULE_ARCH_VERMAGIC \ MODULE_RANDSTRUCT_PLUGIN +#endif /* _LINUX_VERMAGIC_H */ diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 15f906e4a748..a493eac08393 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -9,7 +9,6 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> #include <linux/gfp.h> -#include <linux/vringh.h> /** * virtqueue - a queue to register buffers for sending or receiving. diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0507a162ccd0..a95d3cc74d79 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -137,7 +137,7 @@ extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, - unsigned long size); + unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); diff --git a/include/linux/vringh.h b/include/linux/vringh.h index bd0503ca6f8f..9e2763d7c159 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -14,8 +14,10 @@ #include <linux/virtio_byteorder.h> #include <linux/uio.h> #include <linux/slab.h> +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) #include <linux/dma-direction.h> #include <linux/vhost_iotlb.h> +#endif #include <asm/barrier.h> /* virtio_ring with information needed for host access. */ @@ -254,6 +256,8 @@ static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) return __cpu_to_virtio64(vringh_is_little_endian(vrh), val); } +#if IS_REACHABLE(CONFIG_VHOST_IOTLB) + void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb); int vringh_init_iotlb(struct vringh *vrh, u64 features, @@ -284,4 +288,6 @@ void vringh_notify_disable_iotlb(struct vringh *vrh); int vringh_need_notify_iotlb(struct vringh *vrh); +#endif /* CONFIG_VHOST_IOTLB */ + #endif /* _LINUX_VRINGH_H */ diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 4cf6e11f4a3c..47eaa34f8761 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -73,7 +73,7 @@ struct simple_xattr { struct list_head list; char *name; size_t size; - char value[0]; + char value[]; }; /* diff --git a/include/net/addrconf.h b/include/net/addrconf.h index e0eabe58aa8b..fdb07105384c 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -6,8 +6,6 @@ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ -#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ - #define TEMP_VALID_LIFETIME (7*86400) #define TEMP_PREFERRED_LIFETIME (86400) #define REGEN_MAX_RETRY (3) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 1576353a2773..3fa7b1e3c5d9 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -139,6 +139,14 @@ struct bt_voice { #define BT_PHY_LE_CODED_TX 0x00002000 #define BT_PHY_LE_CODED_RX 0x00004000 +#define BT_MODE 15 + +#define BT_MODE_BASIC 0x00 +#define BT_MODE_ERTM 0x01 +#define BT_MODE_STREAMING 0x02 +#define BT_MODE_LE_FLOWCTL 0x03 +#define BT_MODE_EXT_FLOWCTL 0x04 + __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5f60e135aeb6..1da8cec8e210 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -53,6 +53,9 @@ #define HCI_NOTIFY_CONN_ADD 1 #define HCI_NOTIFY_CONN_DEL 2 #define HCI_NOTIFY_VOICE_SETTING 3 +#define HCI_NOTIFY_ENABLE_SCO_CVSD 4 +#define HCI_NOTIFY_ENABLE_SCO_TRANSP 5 +#define HCI_NOTIFY_DISABLE_SCO 6 /* HCI bus types */ #define HCI_VIRTUAL 0 @@ -65,6 +68,7 @@ #define HCI_SPI 7 #define HCI_I2C 8 #define HCI_SMD 9 +#define HCI_VIRTIO 10 /* HCI controller types */ #define HCI_PRIMARY 0x00 @@ -294,6 +298,7 @@ enum { HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, HCI_CMD_PENDING, + HCI_FORCE_NO_MITM, __HCI_NUM_FLAGS, }; @@ -455,12 +460,11 @@ enum { #define HCI_LE_SLAVE_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 -#define HCI_LE_PHY_2M 0x01 -#define HCI_LE_PHY_CODED 0x08 -#define HCI_LE_EXT_ADV 0x10 +#define HCI_LE_LL_PRIVACY 0x40 #define HCI_LE_EXT_SCAN_POLICY 0x80 #define HCI_LE_PHY_2M 0x01 #define HCI_LE_PHY_CODED 0x08 +#define HCI_LE_EXT_ADV 0x10 #define HCI_LE_CHAN_SEL_ALG2 0x40 #define HCI_LE_CIS_MASTER 0x10 #define HCI_LE_CIS_SLAVE 0x20 @@ -1272,6 +1276,13 @@ struct hci_rp_read_data_block_size { #define HCI_OP_READ_LOCAL_CODECS 0x100b +#define HCI_OP_READ_LOCAL_PAIRING_OPTS 0x100c +struct hci_rp_read_local_pairing_opts { + __u8 status; + __u8 pairing_opts; + __u8 max_key_size; +} __packed; + #define HCI_OP_READ_PAGE_SCAN_ACTIVITY 0x0c1b struct hci_rp_read_page_scan_activity { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d4e28773d378..239ab72f16c6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -312,6 +312,8 @@ struct hci_dev { __u16 conn_info_max_age; __u16 auth_payload_timeout; __u8 min_enc_key_size; + __u8 max_enc_key_size; + __u8 pairing_opts; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; @@ -484,6 +486,11 @@ struct hci_dev { struct led_trigger *power_led; #endif +#if IS_ENABLED(CONFIG_BT_MSFTEXT) + __u16 msft_opcode; + void *msft_data; +#endif + int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); @@ -638,6 +645,7 @@ extern struct mutex hci_cb_list_lock; do { \ hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ hci_dev_clear_flag(hdev, HCI_LE_ADV); \ + hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\ hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ } while (0) @@ -1116,6 +1124,14 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); __printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); __printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); + +static inline void hci_set_msft_opcode(struct hci_dev *hdev, __u16 opcode) +{ +#if IS_ENABLED(CONFIG_BT_MSFTEXT) + hdev->msft_opcode = opcode; +#endif +} + int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index f41cd87550dc..65dd6fd1fff3 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -674,6 +674,13 @@ struct mgmt_cp_set_blocked_keys { #define MGMT_OP_SET_WIDEBAND_SPEECH 0x0047 +#define MGMT_OP_READ_SECURITY_INFO 0x0048 +#define MGMT_READ_SECURITY_INFO_SIZE 0 +struct mgmt_rp_read_security_info { + __le16 sec_len; + __u8 sec[0]; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c78bd4ff9e33..70e48f66dac8 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -905,6 +905,8 @@ struct survey_info { * protocol frames. * @control_port_over_nl80211: TRUE if userspace expects to exchange control * port frames over NL80211 instead of the network interface. + * @control_port_no_preauth: disables pre-auth rx over the nl80211 control + * port for mac80211 * @wep_keys: static WEP keys, if not NULL points to an array of * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key @@ -1222,6 +1224,7 @@ struct sta_txpwr { * @he_capa: HE capabilities of station * @he_capa_len: the length of the HE capabilities * @airtime_weight: airtime scheduler weight for this station + * @txpwr: transmit power for an associated station */ struct station_parameters { const u8 *supported_rates; @@ -4666,6 +4669,9 @@ struct wiphy_iftype_akm_suites { * @txq_memory_limit: configuration internal TX queue memory limit * @txq_quantum: configuration of internal TX queue scheduler quantum * + * @tx_queue_len: allow setting transmit queue len for drivers not using + * wake_tx_queue + * * @support_mbssid: can HW support association with nontransmitted AP * @support_only_he_mbssid: don't parse MBSSID elements if it is not * HE AP, in order to avoid compatibility issues. @@ -4681,6 +4687,10 @@ struct wiphy_iftype_akm_suites { * supported by the driver for each peer * @tid_config_support.max_retry: maximum supported retry count for * long/short retry configuration + * + * @max_data_retry_count: maximum supported per TID retry count for + * configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and + * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes */ struct wiphy { /* assign these fields before you register the wiphy */ diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f7543c095b33..9947eb1e9eb6 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -254,6 +254,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && + !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) && ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 1bf8065fe871..955badd1e8ff 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -908,7 +908,6 @@ static inline int ip6_default_np_autolabel(struct net *net) } } #else -static inline void ip6_set_txhash(struct sock *sk) { } static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b6b4de0e4b5e..97fec4d310ac 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6007,7 +6007,9 @@ enum rate_control_capabilities { struct rate_control_ops { unsigned long capa; const char *name; - void *(*alloc)(struct ieee80211_hw *hw, struct dentry *debugfsdir); + void *(*alloc)(struct ieee80211_hw *hw); + void (*add_debugfs)(struct ieee80211_hw *hw, void *priv, + struct dentry *debugfsdir); void (*free)(void *priv); void *(*alloc_sta)(void *priv, struct ieee80211_sta *sta, gfp_t gfp); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0e7c5471010b..5288fba56e55 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -68,6 +68,8 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) return tcp_rsk(req)->is_mptcp; } +void mptcp_space(const struct sock *ssk, int *space, int *full_space); + void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, int opsize, struct tcp_options_received *opt_rx); bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, @@ -197,6 +199,7 @@ static inline bool mptcp_sk_is_subflow(const struct sock *sk) return false; } +static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { } static inline void mptcp_seq_show(struct seq_file *seq) { } #endif /* CONFIG_MPTCP */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 7d107113f988..9205a76d967a 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -41,7 +41,7 @@ enum { ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ - ND_OPT_PREF64 = 38, /* RFC-ietf-6man-ra-pref64-09 */ + ND_OPT_PREF64 = 38, /* RFC8781 */ __ND_OPT_MAX }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 6eb627b3c99b..4ff7c81e6717 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -901,7 +901,7 @@ static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, { struct nft_expr *expr; - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) { + if (__nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) { expr = nft_set_ext_expr(ext); expr->ops->eval(expr, regs, pkt); } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 25d2ec4c8f00..1862bf5a105b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -710,11 +710,6 @@ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) } } -static inline void qdisc_reset_all_tx(struct net_device *dev) -{ - qdisc_reset_all_tx_gt(dev, 0); -} - /* Are all TX queues of the device empty? */ static inline bool qdisc_all_tx_empty(const struct net_device *dev) { diff --git a/include/net/sock.h b/include/net/sock.h index 6d84784d33fa..3e8c6d4b4b59 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2553,9 +2553,9 @@ sk_is_refcounted(struct sock *sk) } /** - * skb_steal_sock - * @skb to steal the socket from - * @refcounted is set to true if the socket is reference-counted + * skb_steal_sock - steal a socket from an sk_buff + * @skb: sk_buff to steal the socket from + * @refcounted: is set to true if the socket is reference-counted */ static inline struct sock * skb_steal_sock(struct sk_buff *skb, bool *refcounted) diff --git a/include/net/tcp.h b/include/net/tcp.h index 5fa9eacd965a..dcf9a72eeaa6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -51,7 +51,7 @@ extern struct inet_hashinfo tcp_hashinfo; extern struct percpu_counter tcp_orphan_count; void tcp_time_wait(struct sock *sk, int state, int timeo); -#define MAX_TCP_HEADER (128 + MAX_HEADER) +#define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE) diff --git a/include/net/xdp.h b/include/net/xdp.h index 40c6d3398458..3cc6d5d84aa4 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -181,4 +181,6 @@ bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); +#define DEV_MAP_BULK_SIZE 16 + #endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ebffcb36a7e3..a025fb798164 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -92,6 +92,8 @@ #define OCELOT_SPEED_100 2 #define OCELOT_SPEED_10 3 +#define OCELOT_PTP_PINS_NUM 4 + #define TARGET_OFFSET 24 #define REG_MASK GENMASK(TARGET_OFFSET - 1, 0) #define REG(reg, offset) [reg & REG_MASK] = offset @@ -385,6 +387,8 @@ enum ocelot_reg { PTP_PIN_TOD_SEC_MSB, PTP_PIN_TOD_SEC_LSB, PTP_PIN_TOD_NSEC, + PTP_PIN_WF_HIGH_PERIOD, + PTP_PIN_WF_LOW_PERIOD, PTP_CFG_MISC, PTP_CLK_CFG_ADJ_CFG, PTP_CLK_CFG_ADJ_FREQ, @@ -440,10 +444,11 @@ enum ocelot_regfield { REGFIELD_MAX }; -enum ocelot_clk_pins { - ALT_PPS_PIN = 1, - EXT_CLK_PIN, - ALT_LDST_PIN, +enum ocelot_ptp_pins { + PTP_PIN_0, + PTP_PIN_1, + PTP_PIN_2, + PTP_PIN_3, TOD_ACC_PIN }; @@ -476,6 +481,8 @@ struct ocelot_port { void __iomem *regs; + bool vlan_aware; + /* Ingress default VLAN (pvid) */ u16 pvid; @@ -547,6 +554,7 @@ struct ocelot { struct mutex ptp_lock; /* Protects the PTP clock */ spinlock_t ptp_clock_lock; + struct ptp_pin_desc ptp_pins[OCELOT_PTP_PINS_NUM]; }; struct ocelot_policer { @@ -610,7 +618,7 @@ int ocelot_port_bridge_leave(struct ocelot *ocelot, int port, int ocelot_fdb_dump(struct ocelot *ocelot, int port, dsa_fdb_dump_cb_t *cb, void *data); int ocelot_fdb_add(struct ocelot *ocelot, int port, - const unsigned char *addr, u16 vid, bool vlan_aware); + const unsigned char *addr, u16 vid); int ocelot_fdb_del(struct ocelot *ocelot, int port, const unsigned char *addr, u16 vid); int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, @@ -618,7 +626,6 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid); int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr); -int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port, struct sk_buff *skb); void ocelot_get_txtstamp(struct ocelot *ocelot); diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h index 9ede14a12573..4a6b2f71b6b2 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.h +++ b/include/soc/mscc/ocelot_ptp.h @@ -4,15 +4,21 @@ * * License: Dual MIT/GPL * Copyright (c) 2017 Microsemi Corporation + * Copyright 2020 NXP */ #ifndef _MSCC_OCELOT_PTP_H_ #define _MSCC_OCELOT_PTP_H_ +#include <linux/ptp_clock_kernel.h> +#include <soc/mscc/ocelot.h> + #define PTP_PIN_CFG_RSZ 0x20 #define PTP_PIN_TOD_SEC_MSB_RSZ PTP_PIN_CFG_RSZ #define PTP_PIN_TOD_SEC_LSB_RSZ PTP_PIN_CFG_RSZ #define PTP_PIN_TOD_NSEC_RSZ PTP_PIN_CFG_RSZ +#define PTP_PIN_WF_HIGH_PERIOD_RSZ PTP_PIN_CFG_RSZ +#define PTP_PIN_WF_LOW_PERIOD_RSZ PTP_PIN_CFG_RSZ #define PTP_PIN_CFG_DOM BIT(0) #define PTP_PIN_CFG_SYNC BIT(2) @@ -38,4 +44,15 @@ enum { #define PTP_CFG_CLK_ADJ_FREQ_NS BIT(30) +int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); +int ocelot_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts); +int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta); +int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm); +int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan); +int ocelot_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on); +int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info); +int ocelot_deinit_timestamp(struct ocelot *ocelot); #endif diff --git a/include/soc/tegra/pmc.h b/include/soc/tegra/pmc.h index 0dd52b0a5c1b..361cb64246f7 100644 --- a/include/soc/tegra/pmc.h +++ b/include/soc/tegra/pmc.h @@ -168,7 +168,6 @@ int tegra_io_pad_power_disable(enum tegra_io_pad id); int tegra_io_rail_power_on(unsigned int id); int tegra_io_rail_power_off(unsigned int id); -enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void); void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode); void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode); @@ -220,11 +219,6 @@ static inline int tegra_io_rail_power_off(unsigned int id) return -ENOSYS; } -static inline enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void) -{ - return TEGRA_SUSPEND_NONE; -} - static inline void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode) { } @@ -235,4 +229,13 @@ static inline void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode) #endif /* CONFIG_SOC_TEGRA_PMC */ +#if defined(CONFIG_SOC_TEGRA_PMC) && defined(CONFIG_PM_SLEEP) +enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void); +#else +static inline enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void) +{ + return TEGRA_SUSPEND_NONE; +} +#endif + #endif /* __SOC_TEGRA_PMC_H__ */ diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 3ee8036f5436..225154a4f2ed 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -494,6 +494,11 @@ void snd_hda_update_power_acct(struct hda_codec *codec); static inline void snd_hda_set_power_save(struct hda_bus *bus, int delay) {} #endif +static inline bool hda_codec_need_resume(struct hda_codec *codec) +{ + return !codec->relaxed_resume && codec->jacktbl.used; +} + #ifdef CONFIG_SND_HDA_PATCH_LOADER /* * patch firmware diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index d4825b82c7a3..b33abe93b905 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -351,7 +351,6 @@ struct snd_soc_dai { /* bit field */ unsigned int probed:1; - unsigned int started[SNDRV_PCM_STREAM_LAST + 1]; }; static inline struct snd_soc_pcm_stream * diff --git a/include/sound/soc.h b/include/sound/soc.h index 13458e4fbb13..946f88a6c63d 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -790,6 +790,9 @@ struct snd_soc_dai_link { const struct snd_soc_pcm_stream *params; unsigned int num_params; + struct snd_soc_dapm_widget *playback_widget; + struct snd_soc_dapm_widget *capture_widget; + unsigned int dai_fmt; /* format to set on init */ enum snd_soc_dpcm_trigger trigger[2]; /* trigger type for DPCM */ diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index 7ecaa65b7106..c2f580fd371b 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -130,7 +130,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset, TRACE_EVENT(iocost_ioc_vrate_adj, - TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 (*missed_ppm)[2], + TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 *missed_ppm, u32 rq_wait_pct, int nr_lagging, int nr_shortages, int nr_surpluses), @@ -155,8 +155,8 @@ TRACE_EVENT(iocost_ioc_vrate_adj, __entry->old_vrate = atomic64_read(&ioc->vtime_rate);; __entry->new_vrate = new_vrate; __entry->busy_level = ioc->busy_level; - __entry->read_missed_ppm = (*missed_ppm)[READ]; - __entry->write_missed_ppm = (*missed_ppm)[WRITE]; + __entry->read_missed_ppm = missed_ppm[READ]; + __entry->write_missed_ppm = missed_ppm[WRITE]; __entry->rq_wait_pct = rq_wait_pct; __entry->nr_lagging = nr_lagging; __entry->nr_shortages = nr_shortages; diff --git a/include/trace/events/qrtr.h b/include/trace/events/qrtr.h new file mode 100644 index 000000000000..b1de14c3bb93 --- /dev/null +++ b/include/trace/events/qrtr.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM qrtr + +#if !defined(_TRACE_QRTR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_QRTR_H + +#include <linux/qrtr.h> +#include <linux/tracepoint.h> + +TRACE_EVENT(qrtr_ns_service_announce_new, + + TP_PROTO(__le32 service, __le32 instance, __le32 node, __le32 port), + + TP_ARGS(service, instance, node, port), + + TP_STRUCT__entry( + __field(__le32, service) + __field(__le32, instance) + __field(__le32, node) + __field(__le32, port) + ), + + TP_fast_assign( + __entry->service = service; + __entry->instance = instance; + __entry->node = node; + __entry->port = port; + ), + + TP_printk("advertising new server [%d:%x]@[%d:%d]", + __entry->service, __entry->instance, __entry->node, + __entry->port + ) +); + +TRACE_EVENT(qrtr_ns_service_announce_del, + + TP_PROTO(__le32 service, __le32 instance, __le32 node, __le32 port), + + TP_ARGS(service, instance, node, port), + + TP_STRUCT__entry( + __field(__le32, service) + __field(__le32, instance) + __field(__le32, node) + __field(__le32, port) + ), + + TP_fast_assign( + __entry->service = service; + __entry->instance = instance; + __entry->node = node; + __entry->port = port; + ), + + TP_printk("advertising removal of server [%d:%x]@[%d:%d]", + __entry->service, __entry->instance, __entry->node, + __entry->port + ) +); + +TRACE_EVENT(qrtr_ns_server_add, + + TP_PROTO(__le32 service, __le32 instance, __le32 node, __le32 port), + + TP_ARGS(service, instance, node, port), + + TP_STRUCT__entry( + __field(__le32, service) + __field(__le32, instance) + __field(__le32, node) + __field(__le32, port) + ), + + TP_fast_assign( + __entry->service = service; + __entry->instance = instance; + __entry->node = node; + __entry->port = port; + ), + + TP_printk("add server [%d:%x]@[%d:%d]", + __entry->service, __entry->instance, __entry->node, + __entry->port + ) +); + +TRACE_EVENT(qrtr_ns_message, + + TP_PROTO(const char * const ctrl_pkt_str, __u32 sq_node, __u32 sq_port), + + TP_ARGS(ctrl_pkt_str, sq_node, sq_port), + + TP_STRUCT__entry( + __string(ctrl_pkt_str, ctrl_pkt_str) + __field(__u32, sq_node) + __field(__u32, sq_port) + ), + + TP_fast_assign( + __assign_str(ctrl_pkt_str, ctrl_pkt_str); + __entry->sq_node = sq_node; + __entry->sq_port = sq_port; + ), + + TP_printk("%s from %d:%d", + __get_str(ctrl_pkt_str), __entry->sq_node, __entry->sq_port + ) +); + +#endif /* _TRACE_QRTR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 051f26fedc4d..596e0a803477 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1695,17 +1695,15 @@ DECLARE_EVENT_CLASS(svcrdma_sendcomp_event, TRACE_EVENT(svcrdma_post_send, TP_PROTO( - const struct ib_send_wr *wr, - int status + const struct ib_send_wr *wr ), - TP_ARGS(wr, status), + TP_ARGS(wr), TP_STRUCT__entry( __field(const void *, cqe) __field(unsigned int, num_sge) __field(u32, inv_rkey) - __field(int, status) ), TP_fast_assign( @@ -1713,12 +1711,11 @@ TRACE_EVENT(svcrdma_post_send, __entry->num_sge = wr->num_sge; __entry->inv_rkey = (wr->opcode == IB_WR_SEND_WITH_INV) ? wr->ex.invalidate_rkey : 0; - __entry->status = status; ), - TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x status=%d", + TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x", __entry->cqe, __entry->num_sge, - __entry->inv_rkey, __entry->status + __entry->inv_rkey ) ); @@ -1783,26 +1780,23 @@ TRACE_EVENT(svcrdma_wc_receive, TRACE_EVENT(svcrdma_post_rw, TP_PROTO( const void *cqe, - int sqecount, - int status + int sqecount ), - TP_ARGS(cqe, sqecount, status), + TP_ARGS(cqe, sqecount), TP_STRUCT__entry( __field(const void *, cqe) __field(int, sqecount) - __field(int, status) ), TP_fast_assign( __entry->cqe = cqe; __entry->sqecount = sqecount; - __entry->status = status; ), - TP_printk("cqe=%p sqecount=%d status=%d", - __entry->cqe, __entry->sqecount, __entry->status + TP_printk("cqe=%p sqecount=%d", + __entry->cqe, __entry->sqecount ) ); @@ -1870,6 +1864,34 @@ DECLARE_EVENT_CLASS(svcrdma_sendqueue_event, DEFINE_SQ_EVENT(full); DEFINE_SQ_EVENT(retry); +TRACE_EVENT(svcrdma_sq_post_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + int status + ), + + TP_ARGS(rdma, status), + + TP_STRUCT__entry( + __field(int, avail) + __field(int, depth) + __field(int, status) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->avail = atomic_read(&rdma->sc_sq_avail); + __entry->depth = rdma->sc_sq_depth; + __entry->status = status; + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s sc_sq_avail=%d/%d status=%d", + __get_str(addr), __entry->avail, __entry->depth, + __entry->status + ) +); + #endif /* _TRACE_RPCRDMA_H */ #include <trace/define_trace.h> diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index 37342a13c9cb..784814160197 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -46,7 +46,7 @@ TRACE_EVENT(wbt_stat, ), TP_printk("%s: rmean=%llu, rmin=%llu, rmax=%llu, rsamples=%llu, " - "wmean=%llu, wmin=%llu, wmax=%llu, wsamples=%llu\n", + "wmean=%llu, wmin=%llu, wmax=%llu, wsamples=%llu", __entry->name, __entry->rmean, __entry->rmin, __entry->rmax, __entry->rnr_samples, __entry->wmean, __entry->wmin, __entry->wmax, __entry->wnr_samples) @@ -73,7 +73,7 @@ TRACE_EVENT(wbt_lat, __entry->lat = div_u64(lat, 1000); ), - TP_printk("%s: latency %lluus\n", __entry->name, + TP_printk("%s: latency %lluus", __entry->name, (unsigned long long) __entry->lat) ); @@ -115,7 +115,7 @@ TRACE_EVENT(wbt_step, __entry->max = max; ), - TP_printk("%s: %s: step=%d, window=%luus, background=%u, normal=%u, max=%u\n", + TP_printk("%s: %s: step=%d, window=%luus, background=%u, normal=%u, max=%u", __entry->name, __entry->msg, __entry->step, __entry->window, __entry->bg, __entry->normal, __entry->max) ); @@ -148,7 +148,7 @@ TRACE_EVENT(wbt_timer, __entry->inflight = inflight; ), - TP_printk("%s: status=%u, step=%d, inflight=%u\n", __entry->name, + TP_printk("%s: status=%u, step=%d, inflight=%u", __entry->name, __entry->status, __entry->step, __entry->inflight) ); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index d94def25e4dc..85a33bea76f1 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -36,7 +36,6 @@ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ - EM( WB_REASON_FREE_MORE_MEM, "free_more_memory") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EMe(WB_REASON_FORKER_THREAD, "forker_thread") diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2e29a671d67e..4a6c47f3febe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -652,6 +652,8 @@ union bpf_attr { * u64 bpf_ktime_get_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: clock_gettime(CLOCK_MONOTONIC) * Return * Current *ktime*. * @@ -1642,7 +1644,7 @@ union bpf_attr { * ifindex, but doesn't require a map to do so. * Return * **XDP_REDIRECT** on success, or the value of the two lower bits - * of the **flags* argument on error. + * of the *flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description @@ -3025,6 +3027,14 @@ union bpf_attr { * * **-EOPNOTSUPP** Unsupported operation, for example a * call from outside of TC ingress. * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: clock_gettime(CLOCK_BOOTTIME) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3151,7 +3161,8 @@ union bpf_attr { FN(xdp_output), \ FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), + FN(sk_assign), \ + FN(ktime_get_boot_ns), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 8134924cfc17..e6b6cb0f8bc6 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -36,12 +36,10 @@ struct btrfs_ioctl_vol_args { #define BTRFS_DEVICE_PATH_NAME_MAX 1024 #define BTRFS_SUBVOL_NAME_MAX 4039 -/* - * Deprecated since 5.7: - * - * BTRFS_SUBVOL_CREATE_ASYNC (1ULL << 0) - */ - +#ifndef __KERNEL__ +/* Deprecated since 5.7 */ +# define BTRFS_SUBVOL_CREATE_ASYNC (1ULL << 0) +#endif #define BTRFS_SUBVOL_RDONLY (1ULL << 1) #define BTRFS_SUBVOL_QGROUP_INHERIT (1ULL << 2) diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index f880d2831160..e83954c69fff 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[0]; + char name[]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[0]; + char name[]; }; struct dlm_purge_params { diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 8c0bc24d5d95..7a900b2377b6 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -34,7 +34,7 @@ struct fiemap { __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; - struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ + struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ }; #define FIEMAP_MAX_OFFSET (~0ULL) diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index be714cd8c826..797ba2c1562a 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -178,6 +178,7 @@ enum { enum { IF_LINK_MODE_DEFAULT, IF_LINK_MODE_DORMANT, /* limit upward transition to dormant */ + IF_LINK_MODE_TESTING, /* limit upward transition to testing */ }; /* diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 30f2a87270dc..4565456c0ef4 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -276,6 +276,7 @@ enum nft_rule_compat_attributes { * @NFT_SET_TIMEOUT: set uses timeouts * @NFT_SET_EVAL: set can be updated from the evaluation path * @NFT_SET_OBJECT: set contains stateful objects + * @NFT_SET_CONCAT: set contains a concatenation */ enum nft_set_flags { NFT_SET_ANONYMOUS = 0x1, @@ -285,6 +286,7 @@ enum nft_set_flags { NFT_SET_TIMEOUT = 0x10, NFT_SET_EVAL = 0x20, NFT_SET_OBJECT = 0x40, + NFT_SET_CONCAT = 0x80, }; /** diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h index 434e6506abaa..49ddcdc61c09 100644 --- a/include/uapi/linux/netfilter/xt_IDLETIMER.h +++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h @@ -48,6 +48,7 @@ struct idletimer_tg_info_v1 { char label[MAX_IDLETIMER_LABEL_SIZE]; + __u8 send_nl_msg; /* unused: for compatibility with Android */ __u8 timer_type; /* for kernel module internal use only */ diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index 19974392d324..dc3e656470dd 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -48,8 +48,15 @@ struct virtio_balloon_config { __u32 num_pages; /* Number of pages we've actually got in balloon. */ __u32 actual; - /* Free page report command id, readonly by guest */ - __u32 free_page_report_cmd_id; + /* + * Free page hint command id, readonly by guest. + * Was previously named free_page_report_cmd_id so we + * need to carry that name for legacy support. + */ + union { + __u32 free_page_hint_cmd_id; + __u32 free_page_report_cmd_id; /* deprecated */ + }; /* Stores PAGE_POISON if page poisoning is in use */ __u32 poison_val; }; diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index 5cbc9fcbfd45..7955c56d6b3c 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -73,8 +73,8 @@ struct vdso_timestamp { * * @offset is used by the special time namespace VVAR pages which are * installed instead of the real VVAR page. These namespace pages must set - * @seq to 1 and @clock_mode to VLOCK_TIMENS to force the code into the - * time namespace slow path. The namespace aware functions retrieve the + * @seq to 1 and @clock_mode to VDSO_CLOCKMODE_TIMENS to force the code into + * the time namespace slow path. The namespace aware functions retrieve the * real system wide VVAR page, read host time and add the per clock offset. * For clocks which are not affected by time namespace adjustment the * offset must be zero. diff --git a/kernel/audit.c b/kernel/audit.c index b69c8b460341..87f31bf1f0a0 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1326,6 +1326,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; + /* exit early if there isn't at least one character to print */ + if (data_len < 2) + return -EINVAL; err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index f02504640e18..6b12f06ee18c 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -30,7 +30,7 @@ struct bpf_lru_node { struct bpf_lru_list { struct list_head lists[NR_BPF_LRU_LIST_T]; unsigned int counts[NR_BPF_LRU_LIST_COUNT]; - /* The next inacitve list rotation starts from here */ + /* The next inactive list rotation starts from here */ struct list_head *next_inactive_rotation; raw_spinlock_t lock ____cacheline_aligned_in_smp; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 977bc69bb1c5..bf634959885c 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1054,36 +1054,21 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, return !allow; } -EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission); static const struct bpf_func_proto * cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { - case BPF_FUNC_map_lookup_elem: - return &bpf_map_lookup_elem_proto; - case BPF_FUNC_map_update_elem: - return &bpf_map_update_elem_proto; - case BPF_FUNC_map_delete_elem: - return &bpf_map_delete_elem_proto; - case BPF_FUNC_map_push_elem: - return &bpf_map_push_elem_proto; - case BPF_FUNC_map_pop_elem: - return &bpf_map_pop_elem_proto; - case BPF_FUNC_map_peek_elem: - return &bpf_map_peek_elem_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; - case BPF_FUNC_trace_printk: - if (capable(CAP_SYS_ADMIN)) - return bpf_get_trace_printk_proto(); - /* fall through */ + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; default: - return NULL; + return bpf_base_func_proto(func_id); } } @@ -1210,7 +1195,6 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, return ret == 1 ? 0 : -EPERM; } -EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); #ifdef CONFIG_NET static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, @@ -1315,7 +1299,6 @@ out: sockopt_free_buf(&ctx); return ret; } -EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt); int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int optname, char __user *optval, @@ -1402,7 +1385,6 @@ out: sockopt_free_buf(&ctx); return ret; } -EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt); #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 916f5132a984..6aa11de67315 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2136,6 +2136,11 @@ BPF_CALL_0(bpf_user_rnd_u32) return res; } +BPF_CALL_0(bpf_get_raw_cpu_id) +{ + return raw_smp_processor_id(); +} + /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; @@ -2151,6 +2156,7 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 70f71b154fa5..3fe0b006d2d2 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -469,7 +469,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, return -EOVERFLOW; /* Make sure CPU is a valid possible cpu */ - if (!cpu_possible(key_cpu)) + if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu)) return -ENODEV; if (qsize == 0) { diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 58bdca5d978a..a51d9fb7a359 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -52,7 +52,6 @@ #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) -#define DEV_MAP_BULK_SIZE 16 struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bafc53ddd350..5c0290e0696e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -151,7 +151,19 @@ BPF_CALL_0(bpf_ktime_get_ns) const struct bpf_func_proto bpf_ktime_get_ns_proto = { .func = bpf_ktime_get_ns, - .gpl_only = true, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_0(bpf_ktime_get_boot_ns) +{ + /* NMI safe access to clock boottime */ + return ktime_get_boot_fast_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { + .func = bpf_ktime_get_boot_ns, + .gpl_only = false, .ret_type = RET_INTEGER, }; @@ -562,3 +574,78 @@ const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = { .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; + +static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = { + .func = bpf_get_raw_cpu_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, + u64, flags, void *, data, u64, size) +{ + if (unlikely(flags & ~(BPF_F_INDEX_MASK))) + return -EINVAL; + + return bpf_event_output(map, flags, data, size, NULL, 0, NULL); +} + +const struct bpf_func_proto bpf_event_output_data_proto = { + .func = bpf_event_output_data, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, +}; + +const struct bpf_func_proto * +bpf_base_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; + case BPF_FUNC_get_prandom_u32: + return &bpf_get_prandom_u32_proto; + case BPF_FUNC_get_smp_processor_id: + return &bpf_get_raw_smp_processor_id_proto; + case BPF_FUNC_get_numa_node_id: + return &bpf_get_numa_node_id_proto; + case BPF_FUNC_tail_call: + return &bpf_tail_call_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; + case BPF_FUNC_ktime_get_boot_ns: + return &bpf_ktime_get_boot_ns_proto; + default: + break; + } + + if (!capable(CAP_SYS_ADMIN)) + return NULL; + + switch (func_id) { + case BPF_FUNC_spin_lock: + return &bpf_spin_lock_proto; + case BPF_FUNC_spin_unlock: + return &bpf_spin_unlock_proto; + case BPF_FUNC_trace_printk: + return bpf_get_trace_printk_proto(); + case BPF_FUNC_jiffies64: + return &bpf_jiffies64_proto; + default: + return NULL; + } +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 64783da34202..7626b8024471 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -586,9 +586,7 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - bpf_map_inc_with_uref(map); - - if (vma->vm_flags & VM_WRITE) { + if (vma->vm_flags & VM_MAYWRITE) { mutex_lock(&map->freeze_mutex); map->writecnt++; mutex_unlock(&map->freeze_mutex); @@ -600,13 +598,11 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_WRITE) { + if (vma->vm_flags & VM_MAYWRITE) { mutex_lock(&map->freeze_mutex); map->writecnt--; mutex_unlock(&map->freeze_mutex); } - - bpf_map_put_with_uref(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -635,14 +631,16 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; + vma->vm_flags &= ~VM_MAYEXEC; + if (!(vma->vm_flags & VM_WRITE)) + /* disallow re-mapping with PROT_WRITE */ + vma->vm_flags &= ~VM_MAYWRITE; err = map->ops->map_mmap(map, vma); if (err) goto out; - bpf_map_inc_with_uref(map); - - if (vma->vm_flags & VM_WRITE) + if (vma->vm_flags & VM_MAYWRITE) map->writecnt++; out: mutex_unlock(&map->freeze_mutex); @@ -2285,7 +2283,7 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -const struct file_operations bpf_link_fops = { +static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif @@ -3630,8 +3628,10 @@ static int link_update(union bpf_attr *attr) return PTR_ERR(link); new_prog = bpf_prog_get(attr->link_update.new_prog_fd); - if (IS_ERR(new_prog)) - return PTR_ERR(new_prog); + if (IS_ERR(new_prog)) { + ret = PTR_ERR(new_prog); + goto out_put_link; + } if (flags & BPF_F_REPLACE) { old_prog = bpf_prog_get(attr->link_update.old_prog_fd); @@ -3640,6 +3640,9 @@ static int link_update(union bpf_attr *attr) old_prog = NULL; goto out_put_progs; } + } else if (attr->link_update.old_prog_fd) { + ret = -EINVAL; + goto out_put_progs; } #ifdef CONFIG_CGROUP_BPF @@ -3655,6 +3658,8 @@ out_put_progs: bpf_prog_put(old_prog); if (ret) bpf_prog_put(new_prog); +out_put_link: + bpf_link_put(link); return ret; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 04c6630cc18f..91728e0f27eb 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -168,6 +168,8 @@ struct bpf_verifier_stack_elem { int insn_idx; int prev_insn_idx; struct bpf_verifier_stack_elem *next; + /* length of verifier log at the time this state was pushed on stack */ + u32 log_pos; }; #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 @@ -283,6 +285,18 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, log->ubuf = NULL; } +static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos) +{ + char zero = 0; + + if (!bpf_verifier_log_needed(log)) + return; + + log->len_used = new_pos; + if (put_user(zero, log->ubuf + new_pos)) + log->ubuf = NULL; +} + /* log_level controls verbosity level of eBPF verifier. * bpf_verifier_log_write() is used to dump the verification trace to the log, * so the user can figure out what's wrong with the program @@ -846,7 +860,7 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, - int *insn_idx) + int *insn_idx, bool pop_log) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem, *head = env->head; @@ -860,6 +874,8 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, if (err) return err; } + if (pop_log) + bpf_vlog_reset(&env->log, head->log_pos); if (insn_idx) *insn_idx = head->insn_idx; if (prev_insn_idx) @@ -887,6 +903,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; + elem->log_pos = env->log.len_used; env->head = elem; env->stack_size++; err = copy_verifier_state(&elem->st, cur); @@ -915,7 +932,7 @@ err: free_verifier_state(env->cur_state, true); env->cur_state = NULL; /* pop all elements and return */ - while (!pop_stack(env, NULL, NULL)); + while (!pop_stack(env, NULL, NULL, false)); return NULL; } @@ -1255,8 +1272,7 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env, reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; - reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? - true : false; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks; __mark_reg_unbounded(reg); } @@ -2119,6 +2135,15 @@ static bool register_is_const(struct bpf_reg_state *reg) return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); } +static bool __is_pointer_value(bool allow_ptr_leaks, + const struct bpf_reg_state *reg) +{ + if (allow_ptr_leaks) + return false; + + return reg->type != SCALAR_VALUE; +} + static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg) { @@ -2309,6 +2334,16 @@ static int check_stack_read(struct bpf_verifier_env *env, * which resets stack/reg liveness for state transitions */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; + } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { + /* If value_regno==-1, the caller is asking us whether + * it is acceptable to use this value as a SCALAR_VALUE + * (e.g. for XADD). + * We must not allow unprivileged callers to do that + * with spilled pointers. + */ + verbose(env, "leaking pointer from stack off %d\n", + off); + return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { @@ -2674,15 +2709,6 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, return -EACCES; } -static bool __is_pointer_value(bool allow_ptr_leaks, - const struct bpf_reg_state *reg) -{ - if (allow_ptr_leaks) - return false; - - return reg->type != SCALAR_VALUE; -} - static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) { return cur_regs(env) + regno; @@ -3090,7 +3116,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; - if (atype == BPF_READ) { + if (atype == BPF_READ && value_regno >= 0) { if (ret == SCALAR_VALUE) { mark_reg_unknown(env, regs, value_regno); return 0; @@ -5600,7 +5626,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); - bool src_known, dst_known; + bool src_known; s64 smin_val, smax_val; u64 umin_val, umax_val; s32 s32_min_val, s32_max_val; @@ -5622,7 +5648,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, if (alu32) { src_known = tnum_subreg_is_const(src_reg.var_off); - dst_known = tnum_subreg_is_const(dst_reg->var_off); if ((src_known && (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || s32_min_val > s32_max_val || u32_min_val > u32_max_val) { @@ -5634,7 +5659,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, } } else { src_known = tnum_is_const(src_reg.var_off); - dst_known = tnum_is_const(dst_reg->var_off); if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { @@ -8400,6 +8424,7 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) static int do_check(struct bpf_verifier_env *env) { + bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; @@ -8676,7 +8701,7 @@ static int do_check(struct bpf_verifier_env *env) process_bpf_exit: update_branch_counts(env, env->cur_state); err = pop_stack(env, &prev_insn_idx, - &env->insn_idx); + &env->insn_idx, pop_log); if (err < 0) { if (err != -ENOENT) return err; @@ -10199,6 +10224,7 @@ static void sanitize_insn_aux_data(struct bpf_verifier_env *env) static int do_check_common(struct bpf_verifier_env *env, int subprog) { + bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; @@ -10261,7 +10287,9 @@ out: free_verifier_state(env->cur_state, true); env->cur_state = NULL; } - while (!pop_stack(env, NULL, NULL)); + while (!pop_stack(env, NULL, NULL, false)); + if (!ret && pop_log) + bpf_vlog_reset(&env->log, 0); free_states(env); if (ret) /* clean aux data in case subprog was rejected */ @@ -10488,6 +10516,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; } env->ops = bpf_verifier_ops[tgt_prog->type]; + prog->expected_attach_type = tgt_prog->expected_attach_type; } if (!tgt_prog->jited) { verbose(env, "Can attach to only JITed progs\n"); @@ -10832,6 +10861,13 @@ err_release_maps: * them now. Otherwise free_used_maps() will release them. */ release_maps(env); + + /* extension progs temporarily inherit the attach_type of their targets + for verification purposes, so set it back to zero before returning + */ + if (env->prog->type == BPF_PROG_TYPE_EXT) + env->prog->expected_attach_type = 0; + *prog = env->prog; err_unlock: if (!is_priv) diff --git a/kernel/events/core.c b/kernel/events/core.c index f86d46f2c4d9..468139611e06 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7489,10 +7489,17 @@ static void perf_event_task_output(struct perf_event *event, goto out; task_event->event_id.pid = perf_event_pid(event, task); - task_event->event_id.ppid = perf_event_pid(event, current); - task_event->event_id.tid = perf_event_tid(event, task); - task_event->event_id.ptid = perf_event_tid(event, current); + + if (task_event->event_id.header.type == PERF_RECORD_EXIT) { + task_event->event_id.ppid = perf_event_pid(event, + task->real_parent); + task_event->event_id.ptid = perf_event_pid(event, + task->real_parent); + } else { /* PERF_RECORD_FORK */ + task_event->event_id.ppid = perf_event_pid(event, current); + task_event->event_id.ptid = perf_event_tid(event, current); + } task_event->event_id.time = perf_event_clock(event); diff --git a/kernel/exit.c b/kernel/exit.c index 389a88cb3081..ce2a75bc0ade 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -219,6 +219,7 @@ repeat: write_unlock_irq(&tasklist_lock); proc_flush_pid(thread_pid); + put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); diff --git a/kernel/fork.c b/kernel/fork.c index 4385f3d639f2..8c700f881d92 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2605,6 +2605,14 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args args; pid_t *kset_tid = kargs->set_tid; + BUILD_BUG_ON(offsetofend(struct clone_args, tls) != + CLONE_ARGS_SIZE_VER0); + BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != + CLONE_ARGS_SIZE_VER1); + BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != + CLONE_ARGS_SIZE_VER2); + BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); + if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) @@ -2631,7 +2639,8 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, !valid_signal(args.exit_signal))) return -EINVAL; - if ((args.flags & CLONE_INTO_CGROUP) && args.cgroup < 0) + if ((args.flags & CLONE_INTO_CGROUP) && + (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index fe40c658f86f..453a8a0f4804 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1690,34 +1690,6 @@ out_mput: return ret; } -/** - * setup_irq - setup an interrupt - * @irq: Interrupt line to setup - * @act: irqaction for the interrupt - * - * Used to statically setup interrupts in the early boot process. - */ -int setup_irq(unsigned int irq, struct irqaction *act) -{ - int retval; - struct irq_desc *desc = irq_to_desc(irq); - - if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) - return -EINVAL; - - retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) - return retval; - - retval = __setup_irq(irq, desc, act); - - if (retval) - irq_chip_pm_put(&desc->irq_data); - - return retval; -} -EXPORT_SYMBOL_GPL(setup_irq); - /* * Internal function to unregister an irqaction - used to free * regular and special interrupts that are part of the architecture. @@ -1859,22 +1831,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) } /** - * remove_irq - free an interrupt - * @irq: Interrupt line to free - * @act: irqaction for the interrupt - * - * Used to remove interrupts statically setup by the early boot process. - */ -void remove_irq(unsigned int irq, struct irqaction *act) -{ - struct irq_desc *desc = irq_to_desc(irq); - - if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc))) - __free_irq(desc, act->dev_id); -} -EXPORT_SYMBOL_GPL(remove_irq); - -/** * free_irq - free an interrupt allocated with request_irq * @irq: Interrupt line to free * @dev_id: Device identity to free diff --git a/kernel/module.c b/kernel/module.c index 646f1e2330d2..8833e848b73c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4,6 +4,9 @@ Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM. */ + +#define INCLUDE_VERMAGIC + #include <linux/export.h> #include <linux/extable.h> #include <linux/moduleloader.h> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 06548e2ebb72..d9a49cd6065a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -825,7 +825,7 @@ static __always_inline void rcu_nmi_enter_common(bool irq) rcu_cleanup_after_idle(); incby = 1; - } else if (tick_nohz_full_cpu(rdp->cpu) && + } else if (irq && tick_nohz_full_cpu(rdp->cpu) && rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE && READ_ONCE(rdp->rcu_urgent_qs) && !READ_ONCE(rdp->rcu_forced_tick)) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5c589a2e4d19..3e89a042a48f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1231,13 +1231,8 @@ static void uclamp_fork(struct task_struct *p) return; for_each_clamp_id(clamp_id) { - unsigned int clamp_value = uclamp_none(clamp_id); - - /* By default, RT tasks always get 100% boost */ - if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) - clamp_value = uclamp_none(UCLAMP_MAX); - - uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false); + uclamp_se_set(&p->uclamp_req[clamp_id], + uclamp_none(clamp_id), false); } } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index dac9104d126f..ff9435dee1df 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -1003,12 +1003,12 @@ u64 kcpustat_field(struct kernel_cpustat *kcpustat, enum cpu_usage_stat usage, int cpu) { u64 *cpustat = kcpustat->cpustat; + u64 val = cpustat[usage]; struct rq *rq; - u64 val; int err; if (!vtime_accounting_enabled_cpu(cpu)) - return cpustat[usage]; + return val; rq = cpu_rq(cpu); diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 008d6ac2342b..808244f3ddd9 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -149,6 +149,9 @@ __setup("nohz_full=", housekeeping_nohz_full_setup); static int __init housekeeping_isolcpus_setup(char *str) { unsigned int flags = 0; + bool illegal = false; + char *par; + int len; while (isalpha(*str)) { if (!strncmp(str, "nohz,", 5)) { @@ -169,8 +172,22 @@ static int __init housekeeping_isolcpus_setup(char *str) continue; } - pr_warn("isolcpus: Error, unknown flag\n"); - return 0; + /* + * Skip unknown sub-parameter and validate that it is not + * containing an invalid character. + */ + for (par = str, len = 0; *str && *str != ','; str++, len++) { + if (!isalpha(*str) && *str != '_') + illegal = true; + } + + if (illegal) { + pr_warn("isolcpus: Invalid flag %.*s\n", len, par); + return 0; + } + + pr_info("isolcpus: Skipped unknown flag %.*s\n", len, par); + str++; } /* Default behaviour for isolcpus without flags */ diff --git a/kernel/signal.c b/kernel/signal.c index e58a6c619824..284fc1600063 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1510,15 +1510,15 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, unsigned long flags; int ret = -EINVAL; + if (!valid_signal(sig)) + return ret; + clear_siginfo(&info); info.si_signo = sig; info.si_errno = errno; info.si_code = SI_ASYNCIO; *((sigval_t *)&info.si_pid) = addr; - if (!valid_signal(sig)) - return ret; - rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (!p) { @@ -1557,12 +1557,8 @@ static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid) { int ret; - if (pid > 0) { - rcu_read_lock(); - ret = kill_pid_info(sig, info, find_vpid(pid)); - rcu_read_unlock(); - return ret; - } + if (pid > 0) + return kill_proc_info(sig, info, pid); /* -INT_MIN is undefined. Exclude this case to avoid a UBSAN warning */ if (pid == INT_MIN) @@ -1993,8 +1989,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig) if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) sig = 0; } + /* + * Send with __send_signal as si_pid and si_uid are in the + * parent's namespaces. + */ if (valid_signal(sig) && sig) - __group_send_sig_info(sig, &info, tsk->parent); + __send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false); __wake_up_parent(tsk, tsk->parent); spin_unlock_irqrestore(&psig->siglock, flags); diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c index 3b30288793fe..53bce347cd50 100644 --- a/kernel/time/namespace.c +++ b/kernel/time/namespace.c @@ -338,7 +338,20 @@ static struct user_namespace *timens_owner(struct ns_common *ns) static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts) { - seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec); + char *clock; + + switch (clockid) { + case CLOCK_BOOTTIME: + clock = "boottime"; + break; + case CLOCK_MONOTONIC: + clock = "monotonic"; + break; + default: + clock = "unknown"; + break; + } + seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ca1796747a77..e875c95d3ced 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -797,6 +797,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_peek_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + case BPF_FUNC_ktime_get_boot_ns: + return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 041694a1eb74..bd030b1b9514 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5165,6 +5165,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) list_del_rcu(&direct->next); synchronize_rcu_tasks(); kfree(direct); + kfree(entry); ftrace_direct_func_count--; } } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5f6834a2bf41..fcab11cc6833 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3320,6 +3320,9 @@ static void __destroy_hist_field(struct hist_field *hist_field) kfree(hist_field->name); kfree(hist_field->type); + kfree(hist_field->system); + kfree(hist_field->event_name); + kfree(hist_field); } @@ -4382,6 +4385,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data, goto out; } + var->ref = 1; var->flags = HIST_FIELD_FL_VAR; var->var.idx = idx; var->var.hist_data = var->hist_data = hist_data; @@ -5011,6 +5015,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data) for (i = 0; i < hist_data->n_field_vars; i++) destroy_field_var(hist_data->field_vars[i]); + + for (i = 0; i < hist_data->n_save_vars; i++) + destroy_field_var(hist_data->save_vars[i]); } static void save_field_var(struct hist_trigger_data *hist_data, diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index dd34a1b46a86..3a74736da363 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1088,14 +1088,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data, struct trace_event_file *file) { - int ret = register_trigger(glob, ops, data, file); - - if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) { - unregister_trigger(glob, ops, data, file); - ret = 0; - } + if (tracing_alloc_snapshot_instance(file->tr) != 0) + return 0; - return ret; + return register_trigger(glob, ops, data, file); } static int diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9e31bfc818ff..74738c9856f1 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -283,7 +283,7 @@ int tracing_map_add_key_field(struct tracing_map *map, return idx; } -void tracing_map_array_clear(struct tracing_map_array *a) +static void tracing_map_array_clear(struct tracing_map_array *a) { unsigned int i; @@ -294,7 +294,7 @@ void tracing_map_array_clear(struct tracing_map_array *a) memset(a->pages[i], 0, PAGE_SIZE); } -void tracing_map_array_free(struct tracing_map_array *a) +static void tracing_map_array_free(struct tracing_map_array *a) { unsigned int i; @@ -316,7 +316,7 @@ void tracing_map_array_free(struct tracing_map_array *a) kfree(a); } -struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, +static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, unsigned int entry_size) { struct tracing_map_array *a; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 50c1f5f08e6f..21d9c5f6e7ec 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -242,6 +242,8 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_BTF bool "Generate BTF typeinfo" depends on DEBUG_INFO + depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED + depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST help Generate deduplicated BTF type information from DWARF debug info. Turning this on expects presence of pahole tool, which will convert @@ -1088,7 +1088,7 @@ retry: * potentially allocating memory. */ if (fatal_signal_pending(current)) { - ret = -ERESTARTSYS; + ret = -EINTR; goto out; } cond_resched(); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2277c5728b1f..f9a97320e1de 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5364,8 +5364,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm, { pgd_t *pgd; p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; + pud_t *pud, pud_entry; + pmd_t *pmd, pmd_entry; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) @@ -5375,17 +5375,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return NULL; pud = pud_offset(p4d, addr); - if (sz != PUD_SIZE && pud_none(*pud)) + pud_entry = READ_ONCE(*pud); + if (sz != PUD_SIZE && pud_none(pud_entry)) return NULL; /* hugepage or swap? */ - if (pud_huge(*pud) || !pud_present(*pud)) + if (pud_huge(pud_entry) || !pud_present(pud_entry)) return (pte_t *)pud; pmd = pmd_offset(pud, addr); - if (sz != PMD_SIZE && pmd_none(*pmd)) + pmd_entry = READ_ONCE(*pmd); + if (sz != PMD_SIZE && pmd_none(pmd_entry)) return NULL; /* hugepage or swap? */ - if (pmd_huge(*pmd) || !pmd_present(*pmd)) + if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry)) return (pte_t *)pmd; return NULL; @@ -2112,8 +2112,16 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) down_read(&mm->mmap_sem); vma = find_mergeable_vma(mm, rmap_item->address); - err = try_to_merge_one_page(vma, page, - ZERO_PAGE(rmap_item->address)); + if (vma) { + err = try_to_merge_one_page(vma, page, + ZERO_PAGE(rmap_item->address)); + } else { + /* + * If the vma is out of date, we do not need to + * continue. + */ + err = 0; + } up_read(&mm->mmap_sem); /* * In case of failure, the page was not really empty, so we diff --git a/mm/madvise.c b/mm/madvise.c index 4bb30ed6c8d2..8cbd8c1bfe15 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -27,6 +27,7 @@ #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> +#include <linux/sched/mm.h> #include <asm/tlb.h> @@ -1090,6 +1091,23 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) if (write) { if (down_write_killable(¤t->mm->mmap_sem)) return -EINTR; + + /* + * We may have stolen the mm from another process + * that is undergoing core dumping. + * + * Right now that's io_ring, in the future it may + * be remote process management and not "current" + * at all. + * + * We need to fix core dumping to not do this, + * but for now we have the mmget_still_valid() + * model. + */ + if (!mmget_still_valid(current->mm)) { + up_write(¤t->mm->mmap_sem); + return -EINTR; + } } else { down_read(¤t->mm->mmap_sem); } diff --git a/mm/mremap.c b/mm/mremap.c index a7e282ead438..c881abeba0bf 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -413,9 +413,20 @@ static unsigned long move_vma(struct vm_area_struct *vma, /* Always put back VM_ACCOUNT since we won't unmap */ vma->vm_flags |= VM_ACCOUNT; - vm_acct_memory(vma_pages(new_vma)); + vm_acct_memory(new_len >> PAGE_SHIFT); } + /* + * VMAs can actually be merged back together in copy_vma + * calling merge_vma. This can happen with anonymous vmas + * which have not yet been faulted, so if we were to consider + * this VMA split we'll end up adding VM_ACCOUNT on the + * next VMA, which is completely unrelated if this VMA + * was re-merged. + */ + if (split && new_vma == vma) + split = 0; + /* We always clear VM_LOCKED[ONFAULT] on the old vma */ vma->vm_flags &= VM_LOCKED_CLEAR_MASK; diff --git a/mm/shmem.c b/mm/shmem.c index d722eb830317..bd8840082c94 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -952,7 +952,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, VM_BUG_ON_PAGE(PageWriteback(page), page); if (shmem_punch_compound(page, start, end)) truncate_inode_page(mapping, page); - else { + else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Wipe the page and don't get stuck */ clear_highpage(page); flush_dcache_page(page); @@ -2179,7 +2179,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; - spin_lock_irq(&info->lock); + /* + * What serializes the accesses to info->flags? + * ipc_lock_object() when called from shmctl_do_lock(), + * no serialization needed when called from shm_destroy(). + */ if (lock && !(info->flags & VM_LOCKED)) { if (!user_shm_lock(inode->i_size, user)) goto out_nomem; @@ -2194,7 +2198,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) retval = 0; out_nomem: - spin_unlock_irq(&info->lock); return retval; } @@ -2399,11 +2402,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, lru_cache_add_anon(page); - spin_lock(&info->lock); + spin_lock_irq(&info->lock); info->alloced++; inode->i_blocks += BLOCKS_PER_PAGE; shmem_recalc_inode(inode); - spin_unlock(&info->lock); + spin_unlock_irq(&info->lock); inc_mm_counter(dst_mm, mm_counter_file(page)); page_add_file_rmap(page, false); diff --git a/mm/slub.c b/mm/slub.c index 332d4b459a90..9bf44955c4f1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3533,6 +3533,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) { slab_flags_t flags = s->flags; unsigned int size = s->object_size; + unsigned int freepointer_area; unsigned int order; /* @@ -3541,6 +3542,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * the possible location of the free pointer. */ size = ALIGN(size, sizeof(void *)); + /* + * This is the area of the object where a freepointer can be + * safely written. If redzoning adds more to the inuse size, we + * can't use that portion for writing the freepointer, so + * s->offset must be limited within this for the general case. + */ + freepointer_area = size; #ifdef CONFIG_SLUB_DEBUG /* @@ -3582,13 +3590,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) */ s->offset = size; size += sizeof(void *); - } else if (size > sizeof(void *)) { + } else if (freepointer_area > sizeof(void *)) { /* * Store freelist pointer near middle of object to keep * it away from the edges of the object to avoid small * sized over/underflows from neighboring allocations. */ - s->offset = ALIGN(size / 2, sizeof(void *)); + s->offset = ALIGN(freepointer_area / 2, sizeof(void *)); } #ifdef CONFIG_SLUB_DEBUG diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 399f219544f7..9a8227afa073 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -34,6 +34,7 @@ #include <linux/llist.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> +#include <linux/overflow.h> #include <linux/uaccess.h> #include <asm/tlbflush.h> @@ -3054,6 +3055,7 @@ finished: * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory + * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure @@ -3066,9 +3068,15 @@ finished: * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, - void *kaddr, unsigned long size) + void *kaddr, unsigned long pgoff, + unsigned long size) { struct vm_struct *area; + unsigned long off; + unsigned long end_index; + + if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) + return -EINVAL; size = PAGE_ALIGN(size); @@ -3082,8 +3090,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) return -EINVAL; - if (kaddr + size > area->addr + get_vm_area_size(area)) + if (check_add_overflow(size, off, &end_index) || + end_index > get_vm_area_size(area)) return -EINVAL; + kaddr += off; do { struct page *page = vmalloc_to_page(kaddr); @@ -3122,7 +3132,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, - addr + (pgoff << PAGE_SHIFT), + addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 165148c7c4ce..9e25c6570170 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -93,6 +93,21 @@ config BT_LEDS This option selects a few LED triggers for different Bluetooth events. +config BT_MSFTEXT + bool "Enable Microsoft extensions" + depends on BT + help + This options enables support for the Microsoft defined HCI + vendor extensions. + +config BT_DEBUGFS + bool "Export Bluetooth internals in debugfs" + depends on BT && DEBUG_FS + default y + help + Provide extensive information about internal Bluetooth states + in debugfs. + config BT_SELFTEST bool "Bluetooth self testing support" depends on BT && DEBUG_KERNEL @@ -120,12 +135,4 @@ config BT_SELFTEST_SMP Run test cases for SMP cryptographic functionality, including both legacy SMP as well as the Secure Connections features. -config BT_DEBUGFS - bool "Export Bluetooth internals in debugfs" - depends on BT && DEBUG_FS - default y - help - Provide extensive information about internal Bluetooth states - in debugfs. - source "drivers/bluetooth/Kconfig" diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index fda41c0b4781..41dd541a44a5 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -19,5 +19,6 @@ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ bluetooth-$(CONFIG_BT_BREDR) += sco.o bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o bluetooth-$(CONFIG_BT_LEDS) += leds.o +bluetooth-$(CONFIG_BT_MSFTEXT) += msft.o bluetooth-$(CONFIG_BT_DEBUGFS) += hci_debugfs.o bluetooth-$(CONFIG_BT_SELFTEST) += selftest.o diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index e245bc155cc2..07c34c55fc50 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -122,8 +122,18 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_conn_hash_del(hdev, conn); - if (hdev->notify) - hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); + if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { + switch (conn->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_CVSD: + case SCO_AIRMODE_TRANSP: + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_DISABLE_SCO); + break; + } + } else { + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); + } hci_conn_del_sysfs(conn); @@ -577,8 +587,15 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, hci_dev_hold(hdev); hci_conn_hash_add(hdev, conn); - if (hdev->notify) - hdev->notify(hdev, HCI_NOTIFY_CONN_ADD); + + /* The SCO and eSCO connections will only be notified when their + * setup has been completed. This is different to ACL links which + * can be notified right away. + */ + if (conn->type != SCO_LINK && conn->type != ESCO_LINK) { + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_CONN_ADD); + } hci_conn_init_sysfs(conn); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2e7bc2da8371..51d399273276 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -44,6 +44,7 @@ #include "hci_debugfs.h" #include "smp.h" #include "leds.h" +#include "msft.h" static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); @@ -637,6 +638,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) events[0] |= 0x40; /* LE Data Length Change */ + /* If the controller supports LL Privacy feature, enable + * the corresponding event. + */ + if (hdev->le_features[0] & HCI_LE_LL_PRIVACY) + events[1] |= 0x02; /* LE Enhanced Connection + * Complete + */ + /* If the controller supports Extended Scanner Filter * Policies, enable the correspondig event. */ @@ -710,14 +719,6 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) * Report */ - /* If the controller supports the LE Extended Create Connection - * command, enable the corresponding event. - */ - if (use_ext_conn(hdev)) - events[1] |= 0x02; /* LE Enhanced Connection - * Complete - */ - /* If the controller supports the LE Extended Advertising * command, enable the corresponding event. */ @@ -826,6 +827,10 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) if (hdev->commands[29] & 0x20) hci_req_add(req, HCI_OP_READ_LOCAL_CODECS, 0, NULL); + /* Read local pairing options if the HCI command is supported */ + if (hdev->commands[41] & 0x08) + hci_req_add(req, HCI_OP_READ_LOCAL_PAIRING_OPTS, 0, NULL); + /* Get MWS transport configuration if the HCI command is supported */ if (hdev->commands[30] & 0x08) hci_req_add(req, HCI_OP_GET_MWS_TRANSPORT_CONFIG, 0, NULL); @@ -1563,6 +1568,8 @@ setup_failed: hci_dev_test_flag(hdev, HCI_VENDOR_DIAG) && hdev->set_diag) ret = hdev->set_diag(hdev, true); + msft_do_open(hdev); + clear_bit(HCI_INIT, &hdev->flags); if (!ret) { @@ -1758,6 +1765,8 @@ int hci_dev_do_close(struct hci_dev *hdev) hci_sock_dev_event(hdev, HCI_DEV_DOWN); + msft_do_close(hdev); + if (hdev->flush) hdev->flush(hdev); @@ -4240,6 +4249,54 @@ static void __check_timeout(struct hci_dev *hdev, unsigned int cnt) } } +/* Schedule SCO */ +static void hci_sched_sco(struct hci_dev *hdev) +{ + struct hci_conn *conn; + struct sk_buff *skb; + int quote; + + BT_DBG("%s", hdev->name); + + if (!hci_conn_num(hdev, SCO_LINK)) + return; + + while (hdev->sco_cnt && (conn = hci_low_sent(hdev, SCO_LINK, "e))) { + while (quote-- && (skb = skb_dequeue(&conn->data_q))) { + BT_DBG("skb %p len %d", skb, skb->len); + hci_send_frame(hdev, skb); + + conn->sent++; + if (conn->sent == ~0) + conn->sent = 0; + } + } +} + +static void hci_sched_esco(struct hci_dev *hdev) +{ + struct hci_conn *conn; + struct sk_buff *skb; + int quote; + + BT_DBG("%s", hdev->name); + + if (!hci_conn_num(hdev, ESCO_LINK)) + return; + + while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, + "e))) { + while (quote-- && (skb = skb_dequeue(&conn->data_q))) { + BT_DBG("skb %p len %d", skb, skb->len); + hci_send_frame(hdev, skb); + + conn->sent++; + if (conn->sent == ~0) + conn->sent = 0; + } + } +} + static void hci_sched_acl_pkt(struct hci_dev *hdev) { unsigned int cnt = hdev->acl_cnt; @@ -4271,6 +4328,10 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev) hdev->acl_cnt--; chan->sent++; chan->conn->sent++; + + /* Send pending SCO packets right away */ + hci_sched_sco(hdev); + hci_sched_esco(hdev); } } @@ -4355,54 +4416,6 @@ static void hci_sched_acl(struct hci_dev *hdev) } } -/* Schedule SCO */ -static void hci_sched_sco(struct hci_dev *hdev) -{ - struct hci_conn *conn; - struct sk_buff *skb; - int quote; - - BT_DBG("%s", hdev->name); - - if (!hci_conn_num(hdev, SCO_LINK)) - return; - - while (hdev->sco_cnt && (conn = hci_low_sent(hdev, SCO_LINK, "e))) { - while (quote-- && (skb = skb_dequeue(&conn->data_q))) { - BT_DBG("skb %p len %d", skb, skb->len); - hci_send_frame(hdev, skb); - - conn->sent++; - if (conn->sent == ~0) - conn->sent = 0; - } - } -} - -static void hci_sched_esco(struct hci_dev *hdev) -{ - struct hci_conn *conn; - struct sk_buff *skb; - int quote; - - BT_DBG("%s", hdev->name); - - if (!hci_conn_num(hdev, ESCO_LINK)) - return; - - while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, - "e))) { - while (quote-- && (skb = skb_dequeue(&conn->data_q))) { - BT_DBG("skb %p len %d", skb, skb->len); - hci_send_frame(hdev, skb); - - conn->sent++; - if (conn->sent == ~0) - conn->sent = 0; - } - } -} - static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; @@ -4437,6 +4450,10 @@ static void hci_sched_le(struct hci_dev *hdev) cnt--; chan->sent++; chan->conn->sent++; + + /* Send pending SCO packets right away */ + hci_sched_sco(hdev); + hci_sched_esco(hdev); } } @@ -4459,9 +4476,9 @@ static void hci_tx_work(struct work_struct *work) if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { /* Schedule queues and send stuff to HCI driver */ - hci_sched_acl(hdev); hci_sched_sco(hdev); hci_sched_esco(hdev); + hci_sched_acl(hdev); hci_sched_le(hdev); } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 6b1314c738b8..5e8af2658e44 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -1075,6 +1075,50 @@ DEFINE_SIMPLE_ATTRIBUTE(auth_payload_timeout_fops, auth_payload_timeout_get, auth_payload_timeout_set, "%llu\n"); +static ssize_t force_no_mitm_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = hci_dev_test_flag(hdev, HCI_FORCE_NO_MITM) ? 'Y' : 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t force_no_mitm_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf) - 1)); + bool enable; + + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + if (strtobool(buf, &enable)) + return -EINVAL; + + if (enable == hci_dev_test_flag(hdev, HCI_FORCE_NO_MITM)) + return -EALREADY; + + hci_dev_change_flag(hdev, HCI_FORCE_NO_MITM); + + return count; +} + +static const struct file_operations force_no_mitm_fops = { + .open = simple_open, + .read = force_no_mitm_read, + .write = force_no_mitm_write, + .llseek = default_llseek, +}; + DEFINE_QUIRK_ATTRIBUTE(quirk_strict_duplicate_filter, HCI_QUIRK_STRICT_DUPLICATE_FILTER); DEFINE_QUIRK_ATTRIBUTE(quirk_simultaneous_discovery, @@ -1134,6 +1178,8 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &max_key_size_fops); debugfs_create_file("auth_payload_timeout", 0644, hdev->debugfs, hdev, &auth_payload_timeout_fops); + debugfs_create_file("force_no_mitm", 0644, hdev->debugfs, hdev, + &force_no_mitm_fops); debugfs_create_file("quirk_strict_duplicate_filter", 0644, hdev->debugfs, hdev, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0a591be8b0ae..966fc543c01d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -35,6 +35,7 @@ #include "a2mp.h" #include "amp.h" #include "smp.h" +#include "msft.h" #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" @@ -746,6 +747,23 @@ static void hci_cc_read_bd_addr(struct hci_dev *hdev, struct sk_buff *skb) bacpy(&hdev->setup_addr, &rp->bdaddr); } +static void hci_cc_read_local_pairing_opts(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_read_local_pairing_opts *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + return; + + if (hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG)) { + hdev->pairing_opts = rp->pairing_opts; + hdev->max_enc_key_size = rp->max_key_size; + } +} + static void hci_cc_read_page_scan_activity(struct hci_dev *hdev, struct sk_buff *skb) { @@ -2607,8 +2625,16 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (ev->status) { hci_connect_cfm(conn, ev->status); hci_conn_del(conn); - } else if (ev->link_type != ACL_LINK) + } else if (ev->link_type == SCO_LINK) { + switch (conn->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_CVSD: + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_CVSD); + break; + } + hci_connect_cfm(conn, ev->status); + } unlock: hci_dev_unlock(hdev); @@ -3334,6 +3360,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_read_bd_addr(hdev, skb); break; + case HCI_OP_READ_LOCAL_PAIRING_OPTS: + hci_cc_read_local_pairing_opts(hdev, skb); + break; + case HCI_OP_READ_PAGE_SCAN_ACTIVITY: hci_cc_read_page_scan_activity(hdev, skb); break; @@ -4307,6 +4337,19 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, break; } + bt_dev_dbg(hdev, "SCO connected with air mode: %02x", ev->air_mode); + + switch (conn->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_CVSD: + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_CVSD); + break; + case SCO_AIRMODE_TRANSP: + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_TRANSP); + break; + } + hci_connect_cfm(conn, ev->status); if (ev->status) hci_conn_del(conn); @@ -5269,7 +5312,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, case HCI_AUTO_CONN_ALWAYS: /* Devices advertising with ADV_IND or ADV_DIRECT_IND * are triggering a connection attempt. This means - * that incoming connectioms from slave device are + * that incoming connections from slave device are * accepted and also outgoing connections to slave * devices are established when found. */ @@ -5353,7 +5396,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* Adjust for actual length */ if (len != real_len) { - bt_dev_err_ratelimited(hdev, "advertising data len corrected"); + bt_dev_err_ratelimited(hdev, "advertising data len corrected %u -> %u", + len, real_len); len = real_len; } @@ -6145,6 +6189,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_num_comp_blocks_evt(hdev, skb); break; + case HCI_EV_VENDOR: + msft_vendor_evt(hdev, skb); + break; + default: BT_DBG("%s event 0x%2.2x", hdev->name, event); break; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 649e1e5ed446..9ea40106ef17 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -2723,6 +2723,8 @@ static int active_scan(struct hci_request *req, unsigned long opt) uint16_t interval = opt; struct hci_dev *hdev = req->hdev; u8 own_addr_type; + /* White list is not used for discovery */ + u8 filter_policy = 0x00; int err; BT_DBG("%s", hdev->name); @@ -2744,7 +2746,7 @@ static int active_scan(struct hci_request *req, unsigned long opt) own_addr_type = ADDR_LE_DEV_PUBLIC; hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, DISCOV_LE_SCAN_WIN, - own_addr_type, 0); + own_addr_type, filter_policy); return 0; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 117ba20ea194..1cea42ee1e92 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -395,6 +395,24 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, return sizeof(struct sockaddr_l2); } +static int l2cap_get_mode(struct l2cap_chan *chan) +{ + switch (chan->mode) { + case L2CAP_MODE_BASIC: + return BT_MODE_BASIC; + case L2CAP_MODE_ERTM: + return BT_MODE_ERTM; + case L2CAP_MODE_STREAMING: + return BT_MODE_STREAMING; + case L2CAP_MODE_LE_FLOWCTL: + return BT_MODE_LE_FLOWCTL; + case L2CAP_MODE_EXT_FLOWCTL: + return BT_MODE_EXT_FLOWCTL; + } + + return -EINVAL; +} + static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) { @@ -424,6 +442,20 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, break; } + /* Only BR/EDR modes are supported here */ + switch (chan->mode) { + case L2CAP_MODE_BASIC: + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + break; + default: + err = -EINVAL; + break; + } + + if (err < 0) + break; + memset(&opts, 0, sizeof(opts)); opts.imtu = chan->imtu; opts.omtu = chan->omtu; @@ -508,7 +540,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, struct bt_security sec; struct bt_power pwr; u32 phys; - int len, err = 0; + int len, mode, err = 0; BT_DBG("sk %p", sk); @@ -624,6 +656,27 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, err = -EFAULT; break; + case BT_MODE: + if (!enable_ecred) { + err = -ENOPROTOOPT; + break; + } + + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { + err = -EINVAL; + break; + } + + mode = l2cap_get_mode(chan); + if (mode < 0) { + err = mode; + break; + } + + if (put_user(mode, (u8 __user *) optval)) + err = -EFAULT; + break; + default: err = -ENOPROTOOPT; break; @@ -698,10 +751,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; } - chan->mode = opts.mode; - switch (chan->mode) { - case L2CAP_MODE_LE_FLOWCTL: - break; + /* Only BR/EDR modes are supported here */ + switch (opts.mode) { case L2CAP_MODE_BASIC: clear_bit(CONF_STATE2_DEVICE, &chan->conf_state); break; @@ -715,6 +766,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; } + if (err < 0) + break; + + chan->mode = opts.mode; + BT_DBG("mode 0x%2.2x", chan->mode); chan->imtu = opts.imtu; @@ -763,6 +819,45 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, return err; } +static int l2cap_set_mode(struct l2cap_chan *chan, u8 mode) +{ + switch (mode) { + case BT_MODE_BASIC: + if (bdaddr_type_is_le(chan->src_type)) + return -EINVAL; + mode = L2CAP_MODE_BASIC; + clear_bit(CONF_STATE2_DEVICE, &chan->conf_state); + break; + case BT_MODE_ERTM: + if (!disable_ertm || bdaddr_type_is_le(chan->src_type)) + return -EINVAL; + mode = L2CAP_MODE_ERTM; + break; + case BT_MODE_STREAMING: + if (!disable_ertm || bdaddr_type_is_le(chan->src_type)) + return -EINVAL; + mode = L2CAP_MODE_STREAMING; + break; + case BT_MODE_LE_FLOWCTL: + if (!bdaddr_type_is_le(chan->src_type)) + return -EINVAL; + mode = L2CAP_MODE_LE_FLOWCTL; + break; + case BT_MODE_EXT_FLOWCTL: + /* TODO: Add support for ECRED PDUs to BR/EDR */ + if (!bdaddr_type_is_le(chan->src_type)) + return -EINVAL; + mode = L2CAP_MODE_EXT_FLOWCTL; + break; + default: + return -EINVAL; + } + + chan->mode = mode; + + return 0; +} + static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -968,6 +1063,39 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; + case BT_MODE: + if (!enable_ecred) { + err = -ENOPROTOOPT; + break; + } + + BT_DBG("sk->sk_state %u", sk->sk_state); + + if (sk->sk_state != BT_BOUND) { + err = -EINVAL; + break; + } + + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { + err = -EINVAL; + break; + } + + if (get_user(opt, (u8 __user *) optval)) { + err = -EFAULT; + break; + } + + BT_DBG("opt %u", opt); + + err = l2cap_set_mode(chan, opt); + if (err) + break; + + BT_DBG("mode 0x%2.2x", chan->mode); + + break; + default: err = -ENOPROTOOPT; break; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 6552003a170e..f8c0a4fc8090 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -38,7 +38,7 @@ #include "mgmt_util.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 16 +#define MGMT_REVISION 17 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -108,6 +108,7 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_APPEARANCE, MGMT_OP_SET_BLOCKED_KEYS, MGMT_OP_SET_WIDEBAND_SPEECH, + MGMT_OP_READ_SECURITY_INFO, }; static const u16 mgmt_events[] = { @@ -155,6 +156,7 @@ static const u16 mgmt_untrusted_commands[] = { MGMT_OP_READ_CONFIG_INFO, MGMT_OP_READ_EXT_INDEX_LIST, MGMT_OP_READ_EXT_INFO, + MGMT_OP_READ_SECURITY_INFO, }; static const u16 mgmt_untrusted_events[] = { @@ -3659,6 +3661,55 @@ unlock: return err; } +static int read_security_info(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + char buf[16]; + struct mgmt_rp_read_security_info *rp = (void *)buf; + u16 sec_len = 0; + u8 flags = 0; + + bt_dev_dbg(hdev, "sock %p", sk); + + memset(&buf, 0, sizeof(buf)); + + hci_dev_lock(hdev); + + /* When the Read Simple Pairing Options command is supported, then + * the remote public key validation is supported. + */ + if (hdev->commands[41] & 0x08) + flags |= 0x01; /* Remote public key validation (BR/EDR) */ + + flags |= 0x02; /* Remote public key validation (LE) */ + + /* When the Read Encryption Key Size command is supported, then the + * encryption key size is enforced. + */ + if (hdev->commands[20] & 0x10) + flags |= 0x04; /* Encryption key size enforcement (BR/EDR) */ + + flags |= 0x08; /* Encryption key size enforcement (LE) */ + + sec_len = eir_append_data(rp->sec, sec_len, 0x01, &flags, 1); + + /* When the Read Simple Pairing Options command is supported, then + * also max encryption key size information is provided. + */ + if (hdev->commands[41] & 0x08) + sec_len = eir_append_le16(rp->sec, sec_len, 0x02, + hdev->max_enc_key_size); + + sec_len = eir_append_le16(rp->sec, sec_len, 0x03, SMP_MAX_ENC_KEY_SIZE); + + rp->sec_len = cpu_to_le16(sec_len); + + hci_dev_unlock(hdev); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_SECURITY_INFO, 0, + rp, sizeof(*rp) + sec_len); +} + static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -7099,6 +7150,8 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { set_blocked_keys, MGMT_OP_SET_BLOCKED_KEYS_SIZE, HCI_MGMT_VAR_LEN }, { set_wideband_speech, MGMT_SETTING_SIZE }, + { read_security_info, MGMT_READ_SECURITY_INFO_SIZE, + HCI_MGMT_UNTRUSTED }, }; void mgmt_index_added(struct hci_dev *hdev) diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c new file mode 100644 index 000000000000..d6c4e6b5ae77 --- /dev/null +++ b/net/bluetooth/msft.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google Corporation + */ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> + +#include "msft.h" + +#define MSFT_OP_READ_SUPPORTED_FEATURES 0x00 +struct msft_cp_read_supported_features { + __u8 sub_opcode; +} __packed; +struct msft_rp_read_supported_features { + __u8 status; + __u8 sub_opcode; + __le64 features; + __u8 evt_prefix_len; + __u8 evt_prefix[0]; +} __packed; + +struct msft_data { + __u64 features; + __u8 evt_prefix_len; + __u8 *evt_prefix; +}; + +static bool read_supported_features(struct hci_dev *hdev, + struct msft_data *msft) +{ + struct msft_cp_read_supported_features cp; + struct msft_rp_read_supported_features *rp; + struct sk_buff *skb; + + cp.sub_opcode = MSFT_OP_READ_SUPPORTED_FEATURES; + + skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, + HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Failed to read MSFT supported features (%ld)", + PTR_ERR(skb)); + return false; + } + + if (skb->len < sizeof(*rp)) { + bt_dev_err(hdev, "MSFT supported features length mismatch"); + goto failed; + } + + rp = (struct msft_rp_read_supported_features *)skb->data; + + if (rp->sub_opcode != MSFT_OP_READ_SUPPORTED_FEATURES) + goto failed; + + if (rp->evt_prefix_len > 0) { + msft->evt_prefix = kmemdup(rp->evt_prefix, rp->evt_prefix_len, + GFP_KERNEL); + if (!msft->evt_prefix) + goto failed; + } + + msft->evt_prefix_len = rp->evt_prefix_len; + msft->features = __le64_to_cpu(rp->features); + + kfree_skb(skb); + return true; + +failed: + kfree_skb(skb); + return false; +} + +void msft_do_open(struct hci_dev *hdev) +{ + struct msft_data *msft; + + if (hdev->msft_opcode == HCI_OP_NOP) + return; + + bt_dev_dbg(hdev, "Initialize MSFT extension"); + + msft = kzalloc(sizeof(*msft), GFP_KERNEL); + if (!msft) + return; + + if (!read_supported_features(hdev, msft)) { + kfree(msft); + return; + } + + hdev->msft_data = msft; +} + +void msft_do_close(struct hci_dev *hdev) +{ + struct msft_data *msft = hdev->msft_data; + + if (!msft) + return; + + bt_dev_dbg(hdev, "Cleanup of MSFT extension"); + + hdev->msft_data = NULL; + + kfree(msft->evt_prefix); + kfree(msft); +} + +void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct msft_data *msft = hdev->msft_data; + u8 event; + + if (!msft) + return; + + /* When the extension has defined an event prefix, check that it + * matches, and otherwise just return. + */ + if (msft->evt_prefix_len > 0) { + if (skb->len < msft->evt_prefix_len) + return; + + if (memcmp(skb->data, msft->evt_prefix, msft->evt_prefix_len)) + return; + + skb_pull(skb, msft->evt_prefix_len); + } + + /* Every event starts at least with an event code and the rest of + * the data is variable and depends on the event code. + */ + if (skb->len < 1) + return; + + event = *skb->data; + skb_pull(skb, 1); + + bt_dev_dbg(hdev, "MSFT vendor event %u", event); +} diff --git a/net/bluetooth/msft.h b/net/bluetooth/msft.h new file mode 100644 index 000000000000..5aa9130e1f8a --- /dev/null +++ b/net/bluetooth/msft.h @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google Corporation + */ + +#if IS_ENABLED(CONFIG_BT_MSFTEXT) + +void msft_do_open(struct hci_dev *hdev); +void msft_do_close(struct hci_dev *hdev); +void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb); + +#else + +static inline void msft_do_open(struct hci_dev *hdev) {} +static inline void msft_do_close(struct hci_dev *hdev) {} +static inline void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb) {} + +#endif diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1476a91ce935..df22cbf94693 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -854,7 +854,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, struct l2cap_chan *chan = conn->smp; struct smp_chan *smp = chan->data; u32 passkey = 0; - int ret = 0; + int ret; /* Initialize key for JUST WORKS */ memset(smp->tk, 0, sizeof(smp->tk)); @@ -883,9 +883,16 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT) smp->method = JUST_WORKS; - /* If Just Works, Continue with Zero TK */ + /* If Just Works, Continue with Zero TK and ask user-space for + * confirmation */ if (smp->method == JUST_WORKS) { - set_bit(SMP_FLAG_TK_VALID, &smp->flags); + ret = mgmt_user_confirm_request(hcon->hdev, &hcon->dst, + hcon->type, + hcon->dst_type, + passkey, 1); + if (ret) + return ret; + set_bit(SMP_FLAG_WAIT_USER, &smp->flags); return 0; } @@ -2194,7 +2201,7 @@ mackey_and_ltk: if (err) return SMP_UNSPECIFIED; - if (smp->method == JUST_WORKS || smp->method == REQ_OOB) { + if (smp->method == REQ_OOB) { if (hcon->out) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2209,6 +2216,9 @@ mackey_and_ltk: confirm_hint = 0; confirm: + if (smp->method == JUST_WORKS) + confirm_hint = 1; + err = mgmt_user_confirm_request(hcon->hdev, &hcon->dst, hcon->type, hcon->dst_type, passkey, confirm_hint); if (err) @@ -2385,12 +2395,17 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_CT2; } - /* Require MITM if IO Capability allows or the security level - * requires it. + /* Don't attempt to set MITM if setting is overridden by debugfs + * Needed to pass certification test SM/MAS/PKE/BV-01-C */ - if (hcon->io_capability != HCI_IO_NO_INPUT_OUTPUT || - hcon->pending_sec_level > BT_SECURITY_MEDIUM) - authreq |= SMP_AUTH_MITM; + if (!hci_dev_test_flag(hcon->hdev, HCI_FORCE_NO_MITM)) { + /* Require MITM if IO Capability allows or the security level + * requires it. + */ + if (hcon->io_capability != HCI_IO_NO_INPUT_OUTPUT || + hcon->pending_sec_level > BT_SECURITY_MEDIUM) + authreq |= SMP_AUTH_MITM; + } if (hcon->role == HCI_ROLE_MASTER) { struct smp_cmd_pairing cp; diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 195d2d67be8a..c10e5a55758d 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -142,7 +142,7 @@ static void caif_flow_cb(struct sk_buff *skb) spin_lock_bh(&caifd->flow_lock); send_xoff = caifd->xoff; - caifd->xoff = 0; + caifd->xoff = false; dtor = caifd->xoff_skb_dtor; if (WARN_ON(caifd->xoff_skb != skb)) @@ -220,7 +220,7 @@ static int transmit(struct cflayer *layer, struct cfpkt *pkt) pr_debug("queue has stopped(%d) or is full (%d > %d)\n", netif_queue_stopped(caifd->netdev), qlen, high); - caifd->xoff = 1; + caifd->xoff = true; caifd->xoff_skb = skb; caifd->xoff_skb_dtor = skb->destructor; skb->destructor = caif_flow_cb; @@ -407,7 +407,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, break; } - caifd->xoff = 0; + caifd->xoff = false; cfcnfg_set_phy_state(cfg, &caifd->layer, true); rcu_read_unlock(); @@ -442,7 +442,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, if (caifd->xoff_skb_dtor != NULL && caifd->xoff_skb != NULL) caifd->xoff_skb->destructor = caifd->xoff_skb_dtor; - caifd->xoff = 0; + caifd->xoff = false; caifd->xoff_skb_dtor = NULL; caifd->xoff_skb = NULL; diff --git a/net/core/dev.c b/net/core/dev.c index 9c9e763bfe0e..afff16849c26 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4140,7 +4140,8 @@ EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -unsigned int __read_mostly netdev_budget_usecs = 2000; +/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ +unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ @@ -6226,7 +6227,8 @@ EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { - unsigned long flags, val, new; + unsigned long flags, val, new, timeout = 0; + bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list @@ -6238,20 +6240,23 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + if (work_done) { + if (n->gro_bitmask) + timeout = READ_ONCE(n->dev->gro_flush_timeout); + n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs); + } + if (n->defer_hard_irqs_count > 0) { + n->defer_hard_irqs_count--; + timeout = READ_ONCE(n->dev->gro_flush_timeout); + if (timeout) + ret = false; + } if (n->gro_bitmask) { - unsigned long timeout = 0; - - if (work_done) - timeout = n->dev->gro_flush_timeout; - /* When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer */ napi_gro_flush(n, !!timeout); - if (timeout) - hrtimer_start(&n->timer, ns_to_ktime(timeout), - HRTIMER_MODE_REL_PINNED); } gro_normal_list(n); @@ -6283,7 +6288,10 @@ bool napi_complete_done(struct napi_struct *n, int work_done) return false; } - return true; + if (timeout) + hrtimer_start(&n->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); + return ret; } EXPORT_SYMBOL(napi_complete_done); @@ -6463,7 +6471,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_bitmask && !napi_disable_pending(napi) && + if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); @@ -8666,8 +8674,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, const struct net_device_ops *ops = dev->netdev_ops; enum bpf_netdev_command query; u32 prog_id, expected_id = 0; - struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; + struct bpf_prog *prog; bool offload; int err; @@ -8733,6 +8741,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, } else { if (!prog_id) return 0; + prog = NULL; } err = dev_xdp_install(dev, bpf_op, extack, flags, prog); @@ -9134,6 +9143,11 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, else netif_dormant_off(dev); + if (rootdev->operstate == IF_OPER_TESTING) + netif_testing_on(dev); + else + netif_testing_off(dev); + if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else diff --git a/net/core/filter.c b/net/core/filter.c index 7628b947dbc3..da3b7a72c37c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -256,17 +256,6 @@ BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, offset); } -BPF_CALL_0(bpf_get_raw_cpu_id) -{ - return raw_smp_processor_id(); -} - -static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = { - .func = bpf_get_raw_cpu_id, - .gpl_only = false, - .ret_type = RET_INTEGER, -}; - static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { @@ -4205,26 +4194,6 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, u64, flags, - void *, data, u64, size) -{ - if (unlikely(flags & ~(BPF_F_INDEX_MASK))) - return -EINVAL; - - return bpf_event_output(map, flags, data, size, NULL, 0, NULL); -} - -static const struct bpf_func_proto bpf_event_output_data_proto = { - .func = bpf_event_output_data, - .gpl_only = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, - .arg5_type = ARG_CONST_SIZE_OR_ZERO, -}; - BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { @@ -5925,7 +5894,7 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; - if (unlikely(sk->sk_reuseport)) + if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) return -ESOCKTNOSUPPORT; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) @@ -5983,52 +5952,7 @@ bool bpf_helper_changes_pkt_data(void *func) return false; } -const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) -{ - switch (func_id) { - case BPF_FUNC_map_lookup_elem: - return &bpf_map_lookup_elem_proto; - case BPF_FUNC_map_update_elem: - return &bpf_map_update_elem_proto; - case BPF_FUNC_map_delete_elem: - return &bpf_map_delete_elem_proto; - case BPF_FUNC_map_push_elem: - return &bpf_map_push_elem_proto; - case BPF_FUNC_map_pop_elem: - return &bpf_map_pop_elem_proto; - case BPF_FUNC_map_peek_elem: - return &bpf_map_peek_elem_proto; - case BPF_FUNC_get_prandom_u32: - return &bpf_get_prandom_u32_proto; - case BPF_FUNC_get_smp_processor_id: - return &bpf_get_raw_smp_processor_id_proto; - case BPF_FUNC_get_numa_node_id: - return &bpf_get_numa_node_id_proto; - case BPF_FUNC_tail_call: - return &bpf_tail_call_proto; - case BPF_FUNC_ktime_get_ns: - return &bpf_ktime_get_ns_proto; - default: - break; - } - - if (!capable(CAP_SYS_ADMIN)) - return NULL; - - switch (func_id) { - case BPF_FUNC_spin_lock: - return &bpf_spin_lock_proto; - case BPF_FUNC_spin_unlock: - return &bpf_spin_unlock_proto; - case BPF_FUNC_trace_printk: - return bpf_get_trace_printk_proto(); - case BPF_FUNC_jiffies64: - return &bpf_jiffies64_proto; - default: - return NULL; - } -} +const struct bpf_func_proto bpf_event_output_data_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) @@ -6213,6 +6137,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; + case BPF_FUNC_skb_change_head: + return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: diff --git a/net/core/link_watch.c b/net/core/link_watch.c index f153e0601838..75431ca9300f 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -34,6 +34,9 @@ static DEFINE_SPINLOCK(lweventlist_lock); static unsigned char default_operstate(const struct net_device *dev) { + if (netif_testing(dev)) + return IF_OPER_TESTING; + if (!netif_carrier_ok(dev)) return (dev->ifindex != dev_get_iflink(dev) ? IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN); @@ -55,11 +58,15 @@ static void rfc2863_policy(struct net_device *dev) write_lock_bh(&dev_base_lock); switch(dev->link_mode) { + case IF_LINK_MODE_TESTING: + if (operstate == IF_OPER_UP) + operstate = IF_OPER_TESTING; + break; + case IF_LINK_MODE_DORMANT: if (operstate == IF_OPER_UP) operstate = IF_OPER_DORMANT; break; - case IF_LINK_MODE_DEFAULT: default: break; @@ -74,7 +81,8 @@ static void rfc2863_policy(struct net_device *dev) void linkwatch_init_dev(struct net_device *dev) { /* Handle pre-registration link state changes */ - if (!netif_carrier_ok(dev) || netif_dormant(dev)) + if (!netif_carrier_ok(dev) || netif_dormant(dev) || + netif_testing(dev)) rfc2863_policy(dev); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index cf0215734ceb..880e89c894f6 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -80,7 +80,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; - int ret = -EINVAL; + int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -243,6 +243,18 @@ static ssize_t duplex_show(struct device *dev, } static DEVICE_ATTR_RO(duplex); +static ssize_t testing_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + + if (netif_running(netdev)) + return sprintf(buf, fmt_dec, !!netif_testing(netdev)); + + return -EINVAL; +} +static DEVICE_ATTR_RO(testing); + static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -260,7 +272,7 @@ static const char *const operstates[] = { "notpresent", /* currently unused */ "down", "lowerlayerdown", - "testing", /* currently unused */ + "testing", "dormant", "up" }; @@ -355,7 +367,7 @@ NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { - dev->gro_flush_timeout = val; + WRITE_ONCE(dev->gro_flush_timeout, val); return 0; } @@ -370,6 +382,23 @@ static ssize_t gro_flush_timeout_store(struct device *dev, } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); +static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) +{ + WRITE_ONCE(dev->napi_defer_hard_irqs, val); + return 0; +} + +static ssize_t napi_defer_hard_irqs_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); +} +NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec); + static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -524,6 +553,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_speed.attr, &dev_attr_duplex.attr, &dev_attr_dormant.attr, + &dev_attr_testing.attr, &dev_attr_operstate.attr, &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, @@ -532,6 +562,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, + &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index b4c87fe31be2..41b24cd31562 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -127,10 +127,8 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, cs->classid = (u32)value; css_task_iter_start(css, 0, &it); - while ((p = css_task_iter_next(&it))) { + while ((p = css_task_iter_next(&it))) update_classid_task(p, cs->classid); - cond_resched(); - } css_task_iter_end(&it); return 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 709ebbf8ab5b..d6f4f4a9e8ba 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -829,11 +829,18 @@ static void set_operstate(struct net_device *dev, unsigned char transition) switch (transition) { case IF_OPER_UP: if ((operstate == IF_OPER_DORMANT || + operstate == IF_OPER_TESTING || operstate == IF_OPER_UNKNOWN) && - !netif_dormant(dev)) + !netif_dormant(dev) && !netif_testing(dev)) operstate = IF_OPER_UP; break; + case IF_OPER_TESTING: + if (operstate == IF_OPER_UP || + operstate == IF_OPER_UNKNOWN) + operstate = IF_OPER_TESTING; + break; + case IF_OPER_DORMANT: if (operstate == IF_OPER_UP || operstate == IF_OPER_UNKNOWN) diff --git a/net/core/sock.c b/net/core/sock.c index ce1d8dce9b7a..90509c37d291 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1872,7 +1872,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) - RCU_INIT_POINTER(newsk->sk_user_data, NULL); + newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9c3b27c257bb..7dce4f6c7025 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -108,11 +108,6 @@ extern int sysctl_dccp_sync_ratelimit; #define ADD48(a, b) (((a) + (b)) & UINT48_MAX) #define SUB48(a, b) ADD48((a), COMPLEMENT48(b)) -static inline void dccp_set_seqno(u64 *seqno, u64 value) -{ - *seqno = value & UINT48_MAX; -} - static inline void dccp_inc_seqno(u64 *seqno) { *seqno = ADD48(*seqno, 1); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 92663dcb3aa2..739613070d07 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,6 +9,7 @@ menuconfig NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n + select GRO_CELLS select NET_SWITCHDEV select PHYLINK select NET_DEVLINK diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index ee2610c4d46a..0384a911779e 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -234,7 +234,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (dsa_skb_defer_rx_timestamp(p, skb)) return 0; - netif_receive_skb(skb); + gro_cells_receive(&p->gcells, skb); return 0; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 904cc7c9b882..6d9a1ef65fa0 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/netpoll.h> #include <net/dsa.h> +#include <net/gro_cells.h> enum { DSA_NOTIFIER_AGEING_TIME, @@ -77,6 +78,8 @@ struct dsa_slave_priv { struct pcpu_sw_netstats *stats64; + struct gro_cells gcells; + /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; diff --git a/net/dsa/port.c b/net/dsa/port.c index 231b2d494f1c..a58fdd362574 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -670,11 +670,16 @@ int dsa_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; struct device_node *phy_np; + int port = dp->index; if (!ds->ops->adjust_link) { phy_np = of_parse_phandle(dp->dn, "phy-handle", 0); - if (of_phy_is_fixed_link(dp->dn) || phy_np) + if (of_phy_is_fixed_link(dp->dn) || phy_np) { + if (ds->ops->phylink_mac_link_down) + ds->ops->phylink_mac_link_down(ds, port, + MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); return dsa_port_phylink_register(dp); + } return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index e94eb1aac602..ba8bf90dc0cc 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1590,10 +1590,10 @@ void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); -static void dsa_slave_phylink_fixed_state(struct net_device *dev, +static void dsa_slave_phylink_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; /* No need to check that this operation is valid, the callback would @@ -1633,6 +1633,15 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) dp->pl_config.dev = &slave_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; + /* The get_fixed_state callback takes precedence over polling the + * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set + * this if the switch provides such a callback. + */ + if (ds->ops->phylink_fixed_state) { + dp->pl_config.get_fixed_state = dsa_slave_phylink_fixed_state; + dp->pl_config.poll_fixed_state = true; + } + dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn), mode, &dsa_port_phylink_mac_ops); if (IS_ERR(dp->pl)) { @@ -1641,13 +1650,6 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return PTR_ERR(dp->pl); } - /* Register only if the switch provides such a callback, since this - * callback takes precedence over polling the link GPIO in PHYLINK - * (see phylink_get_fixed_state). - */ - if (ds->ops->phylink_fixed_state) - phylink_fixed_state_cb(dp->pl, dsa_slave_phylink_fixed_state); - if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); @@ -1762,6 +1764,11 @@ int dsa_slave_create(struct dsa_port *port) free_netdev(slave_dev); return -ENOMEM; } + + ret = gro_cells_init(&p->gcells, slave_dev); + if (ret) + goto out_free; + p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); p->xmit = cpu_dp->tag_ops->xmit; @@ -1770,18 +1777,16 @@ int dsa_slave_create(struct dsa_port *port) rtnl_lock(); ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); rtnl_unlock(); - if (ret && ret != -EOPNOTSUPP) { - dev_err(ds->dev, "error %d setting MTU on port %d\n", - ret, port->index); - goto out_free; - } + if (ret) + dev_warn(ds->dev, "nonfatal error %d setting MTU on port %d\n", + ret, port->index); netif_carrier_off(slave_dev); ret = dsa_slave_phy_setup(slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); - goto out_free; + goto out_gcells; } dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); @@ -1800,6 +1805,8 @@ out_phy: phylink_disconnect_phy(p->dp->pl); rtnl_unlock(); phylink_destroy(p->dp->pl); +out_gcells: + gro_cells_destroy(&p->gcells); out_free: free_percpu(p->stats64); free_netdev(slave_dev); @@ -1820,6 +1827,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); phylink_destroy(dp->pl); + gro_cells_destroy(&p->gcells); free_percpu(p->stats64); free_netdev(slave_dev); } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 89d0b1827aaf..226d5ecdd567 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -17,7 +17,6 @@ #include <linux/phy.h> #include <linux/bitops.h> #include <linux/uaccess.h> -#include <linux/vermagic.h> #include <linux/vmalloc.h> #include <linux/sfp.h> #include <linux/slab.h> @@ -28,7 +27,7 @@ #include <net/xdp_sock.h> #include <net/flow_offload.h> #include <linux/ethtool_netlink.h> - +#include <generated/utsrelease.h> #include "common.h" /* @@ -1746,7 +1745,9 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) if (!data) return -ENOMEM; + netif_testing_on(dev); ops->self_test(dev, &test, data); + netif_testing_off(dev); ret = -EFAULT; if (copy_to_user(useraddr, &test, sizeof(test))) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index fc7027314ad8..cd99f548e440 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -125,13 +125,11 @@ int hsr_get_max_mtu(struct hsr_priv *hsr) static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; - struct hsr_port *master; hsr = netdev_priv(dev); - master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (new_mtu > hsr_get_max_mtu(hsr)) { - netdev_info(master->dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", + netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 5465a395da04..1decb25f6764 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -69,10 +69,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, else multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]); - if (!data[IFLA_HSR_VERSION]) + if (!data[IFLA_HSR_VERSION]) { hsr_version = 0; - else + } else { hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]); + if (hsr_version > 1) { + NL_SET_ERR_MSG_MOD(extack, + "Only versions 0..1 are supported"); + return -EINVAL; + } + } return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index cf58e29cf746..c618e242490f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1914,7 +1914,7 @@ static int __init inet_init(void) { struct inet_protosw *q; struct list_head *r; - int rc = -EINVAL; + int rc; sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a118978d222c..fc94f82f82c7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -614,12 +614,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, return NULL; } -static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) +static int ip_mc_autojoin_config(struct net *net, bool join, + const struct in_ifaddr *ifa) { +#if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; + struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL(); @@ -632,6 +635,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) release_sock(sk); return ret; +#else + return -EOPNOTSUPP; +#endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -675,7 +681,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, continue; if (ipv4_is_multicast(ifa->ifa_address)) - ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa); + ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -940,8 +946,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { - int ret = ip_mc_config(net->ipv4.mc_autojoin_sk, - true, ifa); + int ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { inet_free_ifa(ifa); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 6ed8c9317179..55ca2e521828 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2014,7 +2014,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; - struct fib_nh *nh; + struct fib_nh_common *nhc; if (fa->fa_slen != slen) continue; @@ -2037,8 +2037,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) fa->fa_type != RTN_UNICAST) continue; - nh = fib_info_nh(next_fi, 0); - if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK) + nhc = fib_info_nhc(next_fi, 0); + if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK) continue; fib_alias_accessed(fa); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2f45cde168c4..ba4482130f08 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2772,8 +2772,12 @@ u32 __tcp_select_window(struct sock *sk) int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); int allowed_space = tcp_full_space(sk); - int full_space = min_t(int, tp->window_clamp, allowed_space); - int window; + int full_space, window; + + if (sk_is_mptcp(sk)) + mptcp_space(sk, &free_space, &allowed_space); + + full_space = min_t(int, tp->window_clamp, allowed_space); if (unlikely(mss > full_space)) { mss = full_space; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 89ba7c87de5d..30ddb9dc9398 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb) { memset(IPCB(skb), 0, sizeof(*IPCB(skb))); -#ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; -#endif return xfrm_output(sk, skb); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9d0e89bccb90..bad198e6b863 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2564,7 +2564,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, __u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1); - int create = 0, update_lft = 0; + int create = 0; if (!ifp && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; @@ -2608,32 +2608,19 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, unsigned long now; u32 stored_lft; - /* update lifetime (RFC2462 5.5.3 e) */ + /* Update lifetime (RFC4862 5.5.3 e) + * We deviate from RFC4862 by honoring all Valid Lifetimes to + * improve the reaction of SLAAC to renumbering events + * (draft-gont-6man-slaac-renum-06, Section 4.2) + */ spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!create && stored_lft) { - const u32 minimum_lft = min_t(u32, - stored_lft, MIN_VALID_LIFETIME); - valid_lft = max(valid_lft, minimum_lft); - - /* RFC4862 Section 5.5.3e: - * "Note that the preferred lifetime of the - * corresponding address is always reset to - * the Preferred Lifetime in the received - * Prefix Information option, regardless of - * whether the valid lifetime is also reset or - * ignored." - * - * So we should always update prefered_lft here. - */ - update_lft = 1; - } - if (update_lft) { + if (!create && stored_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; ifp->tstamp = now; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 2688f3e82165..fc5000370030 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -229,6 +229,25 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, return res; } +static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, + struct flowi6 *fl6) +{ + struct net *net = sock_net(sk); + struct dst_entry *dst; + bool res = false; + + dst = ip6_route_output(net, sk, fl6); + if (!dst->error) { + struct rt6_info *rt = (struct rt6_info *)dst; + struct in6_addr prefsrc; + + rt6_get_prefsrc(rt, &prefsrc); + res = !ipv6_addr_any(&prefsrc); + } + dst_release(dst); + return res; +} + /* * an inline helper for the "simple" if statement below * checks if parameter problem report is caused by an @@ -527,7 +546,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, saddr = force_saddr; if (saddr) { fl6.saddr = *saddr; - } else { + } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) { /* select a more meaningful saddr from input if */ struct net_device *in_netdev; diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 5fc1f4e0c0cf..a1ac0e3d8c60 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -601,8 +601,6 @@ out_ret: return ret; } -#define ILA_HASH_TABLE_SIZE 1024 - int ila_xlat_init_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index debdaeba5d8c..18d05403d3b5 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,15 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol == IPPROTO_TCP) { - if (sk->sk_prot != &tcpv6_prot) { - retv = -EBUSY; - break; - } - break; - } else { + } + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; break; } + if (sk->sk_protocol != IPPROTO_TCP) + break; if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index d38b476fc7f2..307f336b5353 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -8,6 +8,7 @@ #include <net/rpl.h> #define IPV6_PFXTAIL_LEN(x) (sizeof(struct in6_addr) - (x)) +#define IPV6_RPL_BEST_ADDR_COMPRESSION 15 static void ipv6_rpl_addr_decompress(struct in6_addr *dst, const struct in6_addr *daddr, @@ -73,7 +74,7 @@ static unsigned char ipv6_rpl_srh_calc_cmpri(const struct ipv6_rpl_sr_hdr *inhdr } } - return plen; + return IPV6_RPL_BEST_ADDR_COMPRESSION; } static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr, @@ -83,10 +84,10 @@ static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr, for (plen = 0; plen < sizeof(*daddr); plen++) { if (daddr->s6_addr[plen] != last_segment->s6_addr[plen]) - break; + return plen; } - return plen; + return IPV6_RPL_BEST_ADDR_COMPRESSION; } void ipv6_rpl_srh_compress(struct ipv6_rpl_sr_hdr *outhdr, diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 75421a472d25..4c7e0a27fa9c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -434,7 +434,7 @@ static struct genl_family seg6_genl_family __ro_after_init = { int __init seg6_init(void) { - int err = -ENOMEM; + int err; err = genl_register_family(&seg6_genl_family); if (err) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index fbe51d40bd7e..e34167f790e6 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -111,9 +111,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) { memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); -#ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; -#endif return xfrm_output(sk, skb); } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f5a9bdc4980c..ebb381c3f1b9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = { .cmd = L2TP_CMD_TUNNEL_CREATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_create, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_delete, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_MODIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_modify, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_get, .dumpit = l2tp_nl_cmd_tunnel_dump, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_CREATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_create, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_delete, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_MODIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_modify, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_get, .dumpit = l2tp_nl_cmd_session_dump, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, }; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 8345926193de..6423173bb87e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1069,7 +1069,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC; if (hw->max_signal <= 0) { result = -EINVAL; - goto fail_wiphy_register; + goto fail_workqueue; } } @@ -1135,7 +1135,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) result = ieee80211_init_cipher_suites(local); if (result < 0) - goto fail_wiphy_register; + goto fail_workqueue; if (!local->ops->remain_on_channel) local->hw.wiphy->max_remain_on_channel_duration = 5000; @@ -1161,10 +1161,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; - result = wiphy_register(local->hw.wiphy); - if (result < 0) - goto fail_wiphy_register; - /* * We use the number of queues for feature tests (QoS, HT) internally * so restrict them appropriately. @@ -1187,8 +1183,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->tx_headroom = max_t(unsigned int , local->hw.extra_tx_headroom, IEEE80211_TX_STATUS_HEADROOM); - debugfs_hw_add(local); - /* * if the driver doesn't specify a max listen interval we * use 5 which should be a safe default @@ -1217,9 +1211,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_flows; rtnl_lock(); - result = ieee80211_init_rate_ctrl_alg(local, hw->rate_control_algorithm); + rtnl_unlock(); if (result < 0) { wiphy_debug(local->hw.wiphy, "Failed to initialize rate control algorithm\n"); @@ -1273,6 +1267,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->sband_allocated |= BIT(band); } + result = wiphy_register(local->hw.wiphy); + if (result < 0) + goto fail_wiphy_register; + + debugfs_hw_add(local); + rate_control_add_debugfs(local); + + rtnl_lock(); + /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !ieee80211_hw_check(hw, NO_AUTO_VIF)) { @@ -1312,17 +1315,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) #if defined(CONFIG_INET) || defined(CONFIG_IPV6) fail_ifa: #endif + wiphy_unregister(local->hw.wiphy); + fail_wiphy_register: rtnl_lock(); rate_control_deinitialize(local); ieee80211_remove_interfaces(local); - fail_rate: rtnl_unlock(); + fail_rate: fail_flows: ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - wiphy_unregister(local->hw.wiphy); - fail_wiphy_register: if (local->wiphy_ciphers_allocated) kfree(local->hw.wiphy->cipher_suites); kfree(local->int_scan_req); @@ -1372,8 +1375,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); + destroy_workqueue(local->workqueue); ieee80211_led_exit(local); kfree(local->int_scan_req); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index d09b3c789314..36978a0e5000 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1257,15 +1257,15 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal) mesh_neighbour_update(sdata, mgmt->sa, &elems, rx_status); + + if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && + !sdata->vif.csa_active) + ieee80211_mesh_process_chnswitch(sdata, &elems, true); } if (ifmsh->sync_ops) ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, &elems, rx_status); - - if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && - !sdata->vif.csa_active) - ieee80211_mesh_process_chnswitch(sdata, &elems, true); } int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata) @@ -1373,6 +1373,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(pos, len - baselen, true, &elems, mgmt->bssid, NULL); + if (!mesh_matches_local(sdata, &elems)) + return; + ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl; if (!--ifmsh->chsw_ttl) fwd_csa = false; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index a1e9fc7878aa..b051f125d3af 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -214,17 +214,16 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf, ref->ops->name, len); } -static const struct file_operations rcname_ops = { +const struct file_operations rcname_ops = { .read = rcname_read, .open = simple_open, .llseek = default_llseek, }; #endif -static struct rate_control_ref *rate_control_alloc(const char *name, - struct ieee80211_local *local) +static struct rate_control_ref * +rate_control_alloc(const char *name, struct ieee80211_local *local) { - struct dentry *debugfsdir = NULL; struct rate_control_ref *ref; ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL); @@ -234,13 +233,7 @@ static struct rate_control_ref *rate_control_alloc(const char *name, if (!ref->ops) goto free; -#ifdef CONFIG_MAC80211_DEBUGFS - debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); - local->debugfs.rcdir = debugfsdir; - debugfs_create_file("name", 0400, debugfsdir, ref, &rcname_ops); -#endif - - ref->priv = ref->ops->alloc(&local->hw, debugfsdir); + ref->priv = ref->ops->alloc(&local->hw); if (!ref->priv) goto free; return ref; diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 5397c6dad056..79b44d3db171 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -60,6 +60,29 @@ static inline void rate_control_add_sta_debugfs(struct sta_info *sta) #endif } +extern const struct file_operations rcname_ops; + +static inline void rate_control_add_debugfs(struct ieee80211_local *local) +{ +#ifdef CONFIG_MAC80211_DEBUGFS + struct dentry *debugfsdir; + + if (!local->rate_ctrl) + return; + + if (!local->rate_ctrl->ops->add_debugfs) + return; + + debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); + local->debugfs.rcdir = debugfsdir; + debugfs_create_file("name", 0400, debugfsdir, + local->rate_ctrl, &rcname_ops); + + local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv, + debugfsdir); +#endif +} + void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata); /* Get a reference to the rate control algorithm. If `name' is NULL, get the diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 694a31978a04..5dc3e5bc4e64 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1635,7 +1635,7 @@ minstrel_ht_init_cck_rates(struct minstrel_priv *mp) } static void * -minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +minstrel_ht_alloc(struct ieee80211_hw *hw) { struct minstrel_priv *mp; @@ -1673,7 +1673,17 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) mp->update_interval = HZ / 10; mp->new_avg = true; + minstrel_ht_init_cck_rates(mp); + + return mp; +} + #ifdef CONFIG_MAC80211_DEBUGFS +static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv, + struct dentry *debugfsdir) +{ + struct minstrel_priv *mp = priv; + mp->fixed_rate_idx = (u32) -1; debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir, &mp->fixed_rate_idx); @@ -1681,12 +1691,8 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) &mp->sample_switch); debugfs_create_bool("new_avg", S_IRUGO | S_IWUSR, debugfsdir, &mp->new_avg); -#endif - - minstrel_ht_init_cck_rates(mp); - - return mp; } +#endif static void minstrel_ht_free(void *priv) @@ -1725,6 +1731,7 @@ static const struct rate_control_ops mac80211_minstrel_ht = { .alloc = minstrel_ht_alloc, .free = minstrel_ht_free, #ifdef CONFIG_MAC80211_DEBUGFS + .add_debugfs = minstrel_ht_add_debugfs, .add_sta_debugfs = minstrel_ht_add_sta_debugfs, #endif .get_expected_throughput = minstrel_ht_get_expected_throughput, diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f8d5c2515829..cd8487bc6fc2 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -231,7 +231,8 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; int i = 0; - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry_rcu(sta, &local->sta_list, list, + lockdep_is_held(&local->sta_mtx)) { if (sdata != sta->sdata) continue; if (i < idx) { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index faf57585b892..4a7c467b99db 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -876,12 +876,11 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, mpext->data_seq = mp_opt->data_seq; mpext->subflow_seq = mp_opt->subflow_seq; mpext->dsn64 = mp_opt->dsn64; + mpext->data_fin = mp_opt->data_fin; } mpext->data_len = mp_opt->data_len; mpext->use_map = 1; } - - mpext->data_fin = mp_opt->data_fin; } void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 86d61ab34c7c..b78edf237ba0 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -599,12 +599,14 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb, nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex)) goto nla_put_failure; - if (addr->family == AF_INET) - nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4, - addr->addr.s_addr); + if (addr->family == AF_INET && + nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4, + addr->addr.s_addr)) + goto nla_put_failure; #if IS_ENABLED(CONFIG_MPTCP_IPV6) - else if (addr->family == AF_INET6) - nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6); + else if (addr->family == AF_INET6 && + nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6)) + goto nla_put_failure; #endif nla_nest_end(skb, attr); return 0; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 939a5045181a..b22a63ba2348 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -97,12 +97,7 @@ static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk) if (likely(!__mptcp_needs_tcp_fallback(msk))) return NULL; - if (msk->subflow) { - release_sock((struct sock *)msk); - return msk->subflow; - } - - return NULL; + return msk->subflow; } static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk) @@ -734,9 +729,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out; } +fallback: ssock = __mptcp_tcp_fallback(msk); if (unlikely(ssock)) { -fallback: + release_sock(sk); pr_debug("fallback passthrough"); ret = sock_sendmsg(ssock, msg); return ret >= 0 ? ret + copied : (copied ? copied : ret); @@ -769,8 +765,14 @@ fallback: if (ret < 0) break; if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) { + /* Can happen for passive sockets: + * 3WHS negotiated MPTCP, but first packet after is + * plain TCP (e.g. due to middlebox filtering unknown + * options). + * + * Fall back to TCP. + */ release_sock(ssk); - ssock = __mptcp_tcp_fallback(msk); goto fallback; } @@ -883,6 +885,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, ssock = __mptcp_tcp_fallback(msk); if (unlikely(ssock)) { fallback: + release_sock(sk); pr_debug("fallback-read subflow=%p", mptcp_subflow_ctx(ssock->sk)); copied = sock_recvmsg(ssock, msg, flags); @@ -1329,7 +1332,9 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req) +struct sock *mptcp_sk_clone(const struct sock *sk, + const struct tcp_options_received *opt_rx, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -1352,26 +1357,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req) msk->subflow = NULL; if (unlikely(mptcp_token_new_accept(subflow_req->token, nsk))) { + nsk->sk_state = TCP_CLOSE; bh_unlock_sock(nsk); /* we can't call into mptcp_close() here - possible BH context - * free the sock directly + * free the sock directly. + * sk_clone_lock() sets nsk refcnt to two, hence call sk_free() + * too. */ - nsk->sk_prot->destroy(nsk); + sk_common_release(nsk); sk_free(nsk); return NULL; } msk->write_seq = subflow_req->idsn + 1; atomic64_set(&msk->snd_una, msk->write_seq); - if (subflow_req->remote_key_valid) { + if (opt_rx->mptcp.mp_capable) { msk->can_ack = true; - msk->remote_key = subflow_req->remote_key; + msk->remote_key = opt_rx->mptcp.sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; msk->ack_seq = ack_seq; } + sock_reset_flag(nsk, SOCK_RCU_FREE); /* will be fully established after successful MPC subflow creation */ inet_sk_state_store(nsk, TCP_SYN_RECV); bh_unlock_sock(nsk); @@ -1428,6 +1437,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, newsk = new_mptcp_sock; mptcp_copy_inaddrs(newsk, ssk); list_add(&subflow->node, &msk->conn_list); + inet_sk_state_store(newsk, TCP_ESTABLISHED); bh_unlock_sock(new_mptcp_sock); @@ -1467,12 +1477,11 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, */ lock_sock(sk); ssock = __mptcp_tcp_fallback(msk); + release_sock(sk); if (ssock) return tcp_setsockopt(ssock->sk, level, optname, optval, optlen); - release_sock(sk); - return -EOPNOTSUPP; } @@ -1492,12 +1501,11 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, */ lock_sock(sk); ssock = __mptcp_tcp_fallback(msk); + release_sock(sk); if (ssock) return tcp_getsockopt(ssock->sk, level, optname, optval, option); - release_sock(sk); - return -EOPNOTSUPP; } @@ -1774,6 +1782,8 @@ static int mptcp_listen(struct socket *sock, int backlog) goto unlock; } + sock_set_flag(sock->sk, SOCK_RCU_FREE); + err = ssock->ops->listen(ssock, backlog); inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); if (!err) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67448002a2d7..a2b3048037d0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -206,12 +206,10 @@ struct mptcp_subflow_request_sock { struct tcp_request_sock sk; u16 mp_capable : 1, mp_join : 1, - backup : 1, - remote_key_valid : 1; + backup : 1; u8 local_id; u8 remote_id; u64 local_key; - u64 remote_key; u64 idsn; u32 token; u32 ssn_offset; @@ -332,7 +330,9 @@ void mptcp_proto_init(void); int mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req); +struct sock *mptcp_sk_clone(const struct sock *sk, + const struct tcp_options_received *opt_rx, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 50a8bea987c6..87c094702d63 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -133,7 +133,6 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 0; subflow_req->mp_join = 0; - subflow_req->remote_key_valid = 0; #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -347,6 +346,46 @@ static bool subflow_hmac_valid(const struct request_sock *req, return ret; } +static void mptcp_sock_destruct(struct sock *sk) +{ + /* if new mptcp socket isn't accepted, it is free'd + * from the tcp listener sockets request queue, linked + * from req->sk. The tcp socket is released. + * This calls the ULP release function which will + * also remove the mptcp socket, via + * sock_put(ctx->conn). + * + * Problem is that the mptcp socket will not be in + * SYN_RECV state and doesn't have SOCK_DEAD flag. + * Both result in warnings from inet_sock_destruct. + */ + + if (sk->sk_state == TCP_SYN_RECV) { + sk->sk_state = TCP_CLOSE; + WARN_ON_ONCE(sk->sk_socket); + sock_orphan(sk); + } + + inet_sock_destruct(sk); +} + +static void mptcp_force_close(struct sock *sk) +{ + inet_sk_state_store(sk, TCP_CLOSE); + sk_common_release(sk); +} + +static void subflow_ulp_fallback(struct sock *sk, + struct mptcp_subflow_context *old_ctx) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + mptcp_subflow_tcp_fallback(sk, old_ctx); + icsk->icsk_ulp_ops = NULL; + rcu_assign_pointer(icsk->icsk_ulp_data, NULL); + tcp_sk(sk)->is_mptcp = 0; +} + static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -359,10 +398,12 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct tcp_options_received opt_rx; bool fallback_is_fatal = false; struct sock *new_msk = NULL; + bool fallback = false; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); + opt_rx.mptcp.mp_capable = 0; if (tcp_rsk(req)->is_mptcp == 0) goto create_child; @@ -377,20 +418,16 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, goto create_msk; } - opt_rx.mptcp.mp_capable = 0; mptcp_get_options(skb, &opt_rx); - if (opt_rx.mptcp.mp_capable) { - subflow_req->remote_key = opt_rx.mptcp.sndr_key; - subflow_req->remote_key_valid = 1; - } else { - subflow_req->mp_capable = 0; + if (!opt_rx.mptcp.mp_capable) { + fallback = true; goto create_child; } create_msk: - new_msk = mptcp_sk_clone(listener->conn, req); + new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req); if (!new_msk) - subflow_req->mp_capable = 0; + fallback = true; } else if (subflow_req->mp_join) { fallback_is_fatal = true; opt_rx.mptcp.mp_join = 0; @@ -409,12 +446,18 @@ create_child: if (child && *own_req) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child); - /* we have null ctx on TCP fallback, which is fatal on - * MPJ handshake + /* we need to fallback on ctx allocation failure and on pre-reqs + * checking above. In the latter scenario we additionally need + * to reset the context to non MPTCP status. */ - if (!ctx) { + if (!ctx || fallback) { if (fallback_is_fatal) goto close_child; + + if (ctx) { + subflow_ulp_fallback(child, ctx); + kfree_rcu(ctx, rcu); + } goto out; } @@ -422,10 +465,17 @@ create_child: /* new mpc subflow takes ownership of the newly * created mptcp socket */ - inet_sk_state_store(new_msk, TCP_ESTABLISHED); + new_msk->sk_destruct = mptcp_sock_destruct; mptcp_pm_new_connection(mptcp_sk(new_msk), 1); ctx->conn = new_msk; new_msk = NULL; + + /* with OoO packets we can reach here without ingress + * mpc option + */ + ctx->remote_key = opt_rx.mptcp.sndr_key; + ctx->fully_established = opt_rx.mptcp.mp_capable; + ctx->can_ack = opt_rx.mptcp.mp_capable; } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -444,7 +494,14 @@ create_child: out: /* dispose of the left over mptcp master, if any */ if (unlikely(new_msk)) - sock_put(new_msk); + mptcp_force_close(new_msk); + + /* check for expected invariant - should never trigger, just help + * catching eariler subtle bugs + */ + WARN_ON_ONCE(*own_req && child && tcp_sk(child)->is_mptcp && + (!mptcp_subflow_ctx(child) || + !mptcp_subflow_ctx(child)->conn)); return child; close_child: @@ -764,6 +821,24 @@ bool mptcp_subflow_data_available(struct sock *sk) return subflow->data_avail; } +/* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy, + * not the ssk one. + * + * In mptcp, rwin is about the mptcp-level connection data. + * + * Data that is still on the ssk rx queue can thus be ignored, + * as far as mptcp peer is concerened that data is still inflight. + * DSS ACK is updated when skb is moved to the mptcp rx queue. + */ +void mptcp_space(const struct sock *ssk, int *space, int *full_space) +{ + const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + const struct sock *sk = subflow->conn; + + *space = tcp_space(sk); + *full_space = tcp_full_space(sk); +} + static void subflow_data_ready(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -1047,17 +1122,6 @@ static void subflow_ulp_release(struct sock *sk) kfree_rcu(ctx, rcu); } -static void subflow_ulp_fallback(struct sock *sk, - struct mptcp_subflow_context *old_ctx) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - mptcp_subflow_tcp_fallback(sk, old_ctx); - icsk->icsk_ulp_ops = NULL; - rcu_assign_pointer(icsk->icsk_ulp_data, NULL); - tcp_sk(sk)->is_mptcp = 0; -} - static void subflow_ulp_clone(const struct request_sock *req, struct sock *newsk, const gfp_t priority) @@ -1091,9 +1155,6 @@ static void subflow_ulp_clone(const struct request_sock *req, * is fully established only after we receive the remote key */ new_ctx->mp_capable = 1; - new_ctx->fully_established = subflow_req->remote_key_valid; - new_ctx->can_ack = subflow_req->remote_key_valid; - new_ctx->remote_key = subflow_req->remote_key; new_ctx->local_key = subflow_req->local_key; new_ctx->token = subflow_req->token; new_ctx->ssn_offset = subflow_req->ssn_offset; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 8dd17589217d..340cb955af25 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -86,7 +86,8 @@ find_set_type(const char *name, u8 family, u8 revision) { struct ip_set_type *type; - list_for_each_entry_rcu(type, &ip_set_type_list, list) + list_for_each_entry_rcu(type, &ip_set_type_list, list, + lockdep_is_held(&ip_set_type_mutex)) if (STRNCMP(type->name, name) && (type->family == family || type->family == NFPROTO_UNSPEC) && diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index c0cb79495c35..4344e572b7f9 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -421,10 +421,12 @@ void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, down_write(&flow_table->flow_block_lock); block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) + if (block_cb) { list_del(&block_cb->list); - else + flow_block_cb_free(block_cb); + } else { WARN_ON(true); + } up_write(&flow_table->flow_block_lock); } EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb); diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 64eedc17037a..3d816a1e5442 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -1035,8 +1035,8 @@ int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) - nf_nat_ipv6_unregister_fn(net, ops); - + nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, + ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4471393da6d8..9780bd93b7e4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3542,6 +3542,7 @@ cont: continue; if (!strcmp(set->name, i->name)) { kfree(set->name); + set->name = NULL; return -ENFILE; } } @@ -3961,8 +3962,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | - NFT_SET_OBJECT)) - return -EINVAL; + NFT_SET_OBJECT | NFT_SET_CONCAT)) + return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == (NFT_SET_MAP | NFT_SET_OBJECT)) @@ -4000,7 +4001,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); if (objtype == NFT_OBJECT_UNSPEC || objtype > NFT_OBJECT_MAX) - return -EINVAL; + return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 1e70359d633c..f1363b8aabba 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -29,7 +29,7 @@ void nft_lookup_eval(const struct nft_expr *expr, { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; - const struct nft_set_ext *ext; + const struct nft_set_ext *ext = NULL; bool found; found = set->ops->lookup(nft_net(pkt), set, ®s->data[priv->sreg], @@ -39,11 +39,13 @@ void nft_lookup_eval(const struct nft_expr *expr, return; } - if (set->flags & NFT_SET_MAP) - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), set->dlen); + if (ext) { + if (set->flags & NFT_SET_MAP) + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), set->dlen); - nft_set_elem_update_expr(ext, regs, pkt); + nft_set_elem_update_expr(ext, regs, pkt); + } } static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 32f0fc8be3a4..2a81ea421819 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -81,7 +81,6 @@ static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, u32 idx, off; nft_bitmap_location(set, key, &idx, &off); - *ext = NULL; return nft_bitmap_active(priv->bitmap, idx, off, genmask); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3a5552e14f75..3ffef454d469 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -218,27 +218,26 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* Detect overlaps as we descend the tree. Set the flag in these cases: * - * a1. |__ _ _? >|__ _ _ (insert start after existing start) - * a2. _ _ __>| ?_ _ __| (insert end before existing end) - * a3. _ _ ___| ?_ _ _>| (insert end after existing end) - * a4. >|__ _ _ _ _ __| (insert start before existing end) + * a1. _ _ __>| ?_ _ __| (insert end before existing end) + * a2. _ _ ___| ?_ _ _>| (insert end after existing end) + * a3. _ _ ___? >|_ _ __| (insert start before existing end) * * and clear it later on, as we eventually reach the points indicated by * '?' above, in the cases described below. We'll always meet these * later, locally, due to tree ordering, and overlaps for the intervals * that are the closest together are always evaluated last. * - * b1. |__ _ _! >|__ _ _ (insert start after existing end) - * b2. _ _ __>| !_ _ __| (insert end before existing start) - * b3. !_____>| (insert end after existing start) + * b1. _ _ __>| !_ _ __| (insert end before existing start) + * b2. _ _ ___| !_ _ _>| (insert end after existing start) + * b3. _ _ ___! >|_ _ __| (insert start after existing end) * - * Case a4. resolves to b1.: + * Case a3. resolves to b3.: * - if the inserted start element is the leftmost, because the '0' * element in the tree serves as end element * - otherwise, if an existing end is found. Note that end elements are * always inserted after corresponding start elements. * - * For a new, rightmost pair of elements, we'll hit cases b1. and b3., + * For a new, rightmost pair of elements, we'll hit cases b3. and b2., * in that order. * * The flag is also cleared in two special cases: @@ -262,9 +261,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, p = &parent->rb_left; if (nft_rbtree_interval_start(new)) { - overlap = nft_rbtree_interval_start(rbe) && - nft_set_elem_active(&rbe->ext, - genmask); + if (nft_rbtree_interval_end(rbe) && + nft_set_elem_active(&rbe->ext, genmask)) + overlap = false; } else { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 75bd0e5dd312..7b2f359bfce4 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -346,6 +346,9 @@ static int idletimer_tg_checkentry_v1(const struct xt_tgchk_param *par) pr_debug("checkentry targinfo%s\n", info->label); + if (info->send_nl_msg) + return -EOPNOTSUPP; + ret = idletimer_tg_helper((struct idletimer_tg_info *)info); if(ret < 0) { diff --git a/net/netlabel/Kconfig b/net/netlabel/Kconfig index 64280a1d3906..07b03c306f28 100644 --- a/net/netlabel/Kconfig +++ b/net/netlabel/Kconfig @@ -14,6 +14,6 @@ config NETLABEL Documentation/netlabel as well as the NetLabel SourceForge project for configuration tools and additional documentation. - * http://netlabel.sf.net + * https://github.com/netlabel/netlabel_tools If you are unsure, say N. diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 79f12d8c7b86..0891ee02ca4f 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, /* refcount initialized at 1 */ spin_unlock_bh(&nr_node_list_lock); + nr_neigh_put(nr_neigh); return 0; } nr_node_lock(nr_node); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e726159cfcfa..4340f25fe390 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1895,7 +1895,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node) + hlist_for_each_entry_rcu(ct_limit, head, hlist_node, + lockdep_ovsl_is_held()) kfree_rcu(ct_limit, rcu); } kfree(ovs_net->ct_limit_info->limits); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d8ae541d22a8..94b024534987 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2466,8 +2466,10 @@ static void __net_exit ovs_exit_net(struct net *dnet) struct net *net; LIST_HEAD(head); - ovs_ct_exit(dnet); ovs_lock(); + + ovs_ct_exit(dnet); + list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index e239a46c2f94..2016dd107939 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -82,7 +82,7 @@ struct datapath { u32 max_headroom; /* Switch meters. */ - struct hlist_head *meters; + struct dp_meter_table meter_tbl; }; /** diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 5010d1ddd4bd..3d3d8e094546 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -12,6 +12,7 @@ #include <linux/openvswitch.h> #include <linux/netlink.h> #include <linux/rculist.h> +#include <linux/swap.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -19,8 +20,6 @@ #include "datapath.h" #include "meter.h" -#define METER_HASH_BUCKETS 1024 - static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = { [OVS_METER_ATTR_ID] = { .type = NLA_U32, }, [OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG }, @@ -39,6 +38,11 @@ static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = { [OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, }; +static u32 meter_hash(struct dp_meter_instance *ti, u32 id) +{ + return id % ti->n_meters; +} + static void ovs_meter_free(struct dp_meter *meter) { if (!meter) @@ -47,40 +51,162 @@ static void ovs_meter_free(struct dp_meter *meter) kfree_rcu(meter, rcu); } -static struct hlist_head *meter_hash_bucket(const struct datapath *dp, - u32 meter_id) -{ - return &dp->meters[meter_id & (METER_HASH_BUCKETS - 1)]; -} - /* Call with ovs_mutex or RCU read lock. */ -static struct dp_meter *lookup_meter(const struct datapath *dp, +static struct dp_meter *lookup_meter(const struct dp_meter_table *tbl, u32 meter_id) { + struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); + u32 hash = meter_hash(ti, meter_id); struct dp_meter *meter; - struct hlist_head *head; - head = meter_hash_bucket(dp, meter_id); - hlist_for_each_entry_rcu(meter, head, dp_hash_node, - lockdep_ovsl_is_held()) { - if (meter->id == meter_id) - return meter; - } + meter = rcu_dereference_ovsl(ti->dp_meters[hash]); + if (meter && likely(meter->id == meter_id)) + return meter; + return NULL; } -static void attach_meter(struct datapath *dp, struct dp_meter *meter) +static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size) +{ + struct dp_meter_instance *ti; + + ti = kvzalloc(sizeof(*ti) + + sizeof(struct dp_meter *) * size, + GFP_KERNEL); + if (!ti) + return NULL; + + ti->n_meters = size; + + return ti; +} + +static void dp_meter_instance_free(struct dp_meter_instance *ti) +{ + kvfree(ti); +} + +static void dp_meter_instance_free_rcu(struct rcu_head *rcu) { - struct hlist_head *head = meter_hash_bucket(dp, meter->id); + struct dp_meter_instance *ti; - hlist_add_head_rcu(&meter->dp_hash_node, head); + ti = container_of(rcu, struct dp_meter_instance, rcu); + kvfree(ti); } -static void detach_meter(struct dp_meter *meter) +static int +dp_meter_instance_realloc(struct dp_meter_table *tbl, u32 size) +{ + struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); + int n_meters = min(size, ti->n_meters); + struct dp_meter_instance *new_ti; + int i; + + new_ti = dp_meter_instance_alloc(size); + if (!new_ti) + return -ENOMEM; + + for (i = 0; i < n_meters; i++) + if (rcu_dereference_ovsl(ti->dp_meters[i])) + new_ti->dp_meters[i] = ti->dp_meters[i]; + + rcu_assign_pointer(tbl->ti, new_ti); + call_rcu(&ti->rcu, dp_meter_instance_free_rcu); + + return 0; +} + +static void dp_meter_instance_insert(struct dp_meter_instance *ti, + struct dp_meter *meter) +{ + u32 hash; + + hash = meter_hash(ti, meter->id); + rcu_assign_pointer(ti->dp_meters[hash], meter); +} + +static void dp_meter_instance_remove(struct dp_meter_instance *ti, + struct dp_meter *meter) { + u32 hash; + + hash = meter_hash(ti, meter->id); + RCU_INIT_POINTER(ti->dp_meters[hash], NULL); +} + +static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) +{ + struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); + u32 hash = meter_hash(ti, meter->id); + int err; + + /* In generally, slots selected should be empty, because + * OvS uses id-pool to fetch a available id. + */ + if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash]))) + return -EBUSY; + + dp_meter_instance_insert(ti, meter); + + /* That function is thread-safe. */ + tbl->count++; + if (tbl->count >= tbl->max_meters_allowed) { + err = -EFBIG; + goto attach_err; + } + + if (tbl->count >= ti->n_meters && + dp_meter_instance_realloc(tbl, ti->n_meters * 2)) { + err = -ENOMEM; + goto attach_err; + } + + return 0; + +attach_err: + dp_meter_instance_remove(ti, meter); + tbl->count--; + return err; +} + +static int detach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) +{ + struct dp_meter_instance *ti; + ASSERT_OVSL(); - if (meter) - hlist_del_rcu(&meter->dp_hash_node); + if (!meter) + return 0; + + ti = rcu_dereference_ovsl(tbl->ti); + dp_meter_instance_remove(ti, meter); + + tbl->count--; + + /* Shrink the meter array if necessary. */ + if (ti->n_meters > DP_METER_ARRAY_SIZE_MIN && + tbl->count <= (ti->n_meters / 4)) { + int half_size = ti->n_meters / 2; + int i; + + /* Avoid hash collision, don't move slots to other place. + * Make sure there are no references of meters in array + * which will be released. + */ + for (i = half_size; i < ti->n_meters; i++) + if (rcu_dereference_ovsl(ti->dp_meters[i])) + goto out; + + if (dp_meter_instance_realloc(tbl, half_size)) + goto shrink_err; + } + +out: + return 0; + +shrink_err: + dp_meter_instance_insert(ti, meter); + tbl->count++; + return -ENOMEM; } static struct sk_buff * @@ -116,12 +242,11 @@ static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id, if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id)) goto error; - if (!meter) - return 0; - if (nla_put(reply, OVS_METER_ATTR_STATS, - sizeof(struct ovs_flow_stats), &meter->stats) || - nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used, + sizeof(struct ovs_flow_stats), &meter->stats)) + goto error; + + if (nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used, OVS_METER_ATTR_PAD)) goto error; @@ -150,18 +275,32 @@ error: static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) { - struct sk_buff *reply; + struct ovs_header *ovs_header = info->userhdr; struct ovs_header *ovs_reply_header; struct nlattr *nla, *band_nla; - int err; + struct sk_buff *reply; + struct datapath *dp; + int err = -EMSGSIZE; reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); - if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, U32_MAX) || - nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS)) + ovs_lock(); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (!dp) { + err = -ENODEV; + goto exit_unlock; + } + + if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, + dp->meter_tbl.max_meters_allowed)) + goto exit_unlock; + + ovs_unlock(); + + if (nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS)) goto nla_put_failure; nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); @@ -180,9 +319,10 @@ static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); +exit_unlock: + ovs_unlock(); nla_put_failure: nlmsg_free(reply); - err = -EMSGSIZE; return err; } @@ -252,8 +392,8 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) * * Start with a full bucket. */ - band->bucket = (band->burst_size + band->rate) * 1000; - band_max_delta_t = band->bucket / band->rate; + band->bucket = (band->burst_size + band->rate) * 1000ULL; + band_max_delta_t = div_u64(band->bucket, band->rate); if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; @@ -273,14 +413,14 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_header *ovs_header = info->userhdr; + struct dp_meter_table *meter_tbl; struct datapath *dp; int err; u32 meter_id; bool failed; - if (!a[OVS_METER_ATTR_ID]) { - return -ENODEV; - } + if (!a[OVS_METER_ATTR_ID]) + return -EINVAL; meter = dp_meter_create(a); if (IS_ERR_OR_NULL(meter)) @@ -300,12 +440,18 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } + meter_tbl = &dp->meter_tbl; meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); - /* Cannot fail after this. */ - old_meter = lookup_meter(dp, meter_id); - detach_meter(old_meter); - attach_meter(dp, meter); + old_meter = lookup_meter(meter_tbl, meter_id); + err = detach_meter(meter_tbl, old_meter); + if (err) + goto exit_unlock; + + err = attach_meter(meter_tbl, meter); + if (err) + goto exit_unlock; + ovs_unlock(); /* Build response with the meter_id and stats from @@ -337,14 +483,14 @@ exit_free_meter: static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) { - struct nlattr **a = info->attrs; - u32 meter_id; struct ovs_header *ovs_header = info->userhdr; struct ovs_header *ovs_reply_header; + struct nlattr **a = info->attrs; + struct dp_meter *meter; + struct sk_buff *reply; struct datapath *dp; + u32 meter_id; int err; - struct sk_buff *reply; - struct dp_meter *meter; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; @@ -365,7 +511,7 @@ static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) } /* Locate meter, copy stats. */ - meter = lookup_meter(dp, meter_id); + meter = lookup_meter(&dp->meter_tbl, meter_id); if (!meter) { err = -ENOENT; goto exit_unlock; @@ -390,18 +536,17 @@ exit_unlock: static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) { - struct nlattr **a = info->attrs; - u32 meter_id; struct ovs_header *ovs_header = info->userhdr; struct ovs_header *ovs_reply_header; + struct nlattr **a = info->attrs; + struct dp_meter *old_meter; + struct sk_buff *reply; struct datapath *dp; + u32 meter_id; int err; - struct sk_buff *reply; - struct dp_meter *old_meter; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; - meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL, &ovs_reply_header); @@ -416,14 +561,19 @@ static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - old_meter = lookup_meter(dp, meter_id); + meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); + old_meter = lookup_meter(&dp->meter_tbl, meter_id); if (old_meter) { spin_lock_bh(&old_meter->lock); err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter); WARN_ON(err); spin_unlock_bh(&old_meter->lock); - detach_meter(old_meter); + + err = detach_meter(&dp->meter_tbl, old_meter); + if (err) + goto exit_unlock; } + ovs_unlock(); ovs_meter_free(old_meter); genlmsg_end(reply, ovs_reply_header); @@ -443,16 +593,16 @@ exit_unlock: bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, u32 meter_id) { - struct dp_meter *meter; - struct dp_meter_band *band; long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000); long long int long_delta_ms; - u32 delta_ms; - u32 cost; + struct dp_meter_band *band; + struct dp_meter *meter; int i, band_exceeded_max = -1; u32 band_exceeded_rate = 0; + u32 delta_ms; + u32 cost; - meter = lookup_meter(dp, meter_id); + meter = lookup_meter(&dp->meter_tbl, meter_id); /* Do not drop the packet when there is no meter. */ if (!meter) return false; @@ -570,32 +720,39 @@ struct genl_family dp_meter_genl_family __ro_after_init = { int ovs_meters_init(struct datapath *dp) { - int i; - - dp->meters = kmalloc_array(METER_HASH_BUCKETS, - sizeof(struct hlist_head), GFP_KERNEL); + struct dp_meter_table *tbl = &dp->meter_tbl; + struct dp_meter_instance *ti; + unsigned long free_mem_bytes; - if (!dp->meters) + ti = dp_meter_instance_alloc(DP_METER_ARRAY_SIZE_MIN); + if (!ti) return -ENOMEM; - for (i = 0; i < METER_HASH_BUCKETS; i++) - INIT_HLIST_HEAD(&dp->meters[i]); + /* Allow meters in a datapath to use ~3.12% of physical memory. */ + free_mem_bytes = nr_free_buffer_pages() * (PAGE_SIZE >> 5); + tbl->max_meters_allowed = min(free_mem_bytes / sizeof(struct dp_meter), + DP_METER_NUM_MAX); + if (!tbl->max_meters_allowed) + goto out_err; + + rcu_assign_pointer(tbl->ti, ti); + tbl->count = 0; return 0; + +out_err: + dp_meter_instance_free(ti); + return -ENOMEM; } void ovs_meters_exit(struct datapath *dp) { + struct dp_meter_table *tbl = &dp->meter_tbl; + struct dp_meter_instance *ti = rcu_dereference_raw(tbl->ti); int i; - for (i = 0; i < METER_HASH_BUCKETS; i++) { - struct hlist_head *head = &dp->meters[i]; - struct dp_meter *meter; - struct hlist_node *n; - - hlist_for_each_entry_safe(meter, n, head, dp_hash_node) - kfree(meter); - } + for (i = 0; i < ti->n_meters; i++) + ovs_meter_free(rcu_dereference_raw(ti->dp_meters[i])); - kfree(dp->meters); + dp_meter_instance_free(ti); } diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h index f645913870bd..0c33889a8515 100644 --- a/net/openvswitch/meter.h +++ b/net/openvswitch/meter.h @@ -13,26 +13,26 @@ #include <linux/openvswitch.h> #include <linux/genetlink.h> #include <linux/skbuff.h> +#include <linux/bits.h> #include "flow.h" struct datapath; #define DP_MAX_BANDS 1 +#define DP_METER_ARRAY_SIZE_MIN BIT_ULL(10) +#define DP_METER_NUM_MAX (200000UL) struct dp_meter_band { u32 type; u32 rate; u32 burst_size; - u32 bucket; /* 1/1000 packets, or in bits */ + u64 bucket; /* 1/1000 packets, or in bits */ struct ovs_flow_stats stats; }; struct dp_meter { spinlock_t lock; /* Per meter lock */ struct rcu_head rcu; - struct hlist_node dp_hash_node; /*Element in datapath->meters - * hash table. - */ u32 id; u16 kbps:1, keep_stats:1; u16 n_bands; @@ -42,6 +42,18 @@ struct dp_meter { struct dp_meter_band bands[]; }; +struct dp_meter_instance { + struct rcu_head rcu; + u32 n_meters; + struct dp_meter __rcu *dp_meters[]; +}; + +struct dp_meter_table { + struct dp_meter_instance __rcu *ti; + u32 count; + u32 max_meters_allowed; +}; + extern struct genl_family dp_meter_genl_family; int ovs_meters_init(struct datapath *dp); void ovs_meters_exit(struct datapath *dp); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index e7d0fe3f4330..3ca196fc7f9b 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -12,6 +12,9 @@ #include "qrtr.h" +#define CREATE_TRACE_POINTS +#include <trace/events/qrtr.h> + static RADIX_TREE(nodes, GFP_KERNEL); static struct { @@ -105,8 +108,8 @@ static int service_announce_new(struct sockaddr_qrtr *dest, struct msghdr msg = { }; struct kvec iv; - trace_printk("advertising new server [%d:%x]@[%d:%d]\n", - srv->service, srv->instance, srv->node, srv->port); + trace_qrtr_ns_service_announce_new(srv->service, srv->instance, + srv->node, srv->port); iv.iov_base = &pkt; iv.iov_len = sizeof(pkt); @@ -132,8 +135,8 @@ static int service_announce_del(struct sockaddr_qrtr *dest, struct kvec iv; int ret; - trace_printk("advertising removal of server [%d:%x]@[%d:%d]\n", - srv->service, srv->instance, srv->node, srv->port); + trace_qrtr_ns_service_announce_del(srv->service, srv->instance, + srv->node, srv->port); iv.iov_base = &pkt; iv.iov_len = sizeof(pkt); @@ -244,8 +247,8 @@ static struct qrtr_server *server_add(unsigned int service, radix_tree_insert(&node->servers, port, srv); - trace_printk("add server [%d:%x]@[%d:%d]\n", srv->service, - srv->instance, srv->node, srv->port); + trace_qrtr_ns_server_add(srv->service, srv->instance, + srv->node, srv->port); return srv; @@ -633,9 +636,8 @@ static void qrtr_ns_worker(struct work_struct *work) cmd = le32_to_cpu(pkt->cmd); if (cmd < ARRAY_SIZE(qrtr_ctrl_pkt_strings) && qrtr_ctrl_pkt_strings[cmd]) - trace_printk("%s from %d:%d\n", - qrtr_ctrl_pkt_strings[cmd], sq.sq_node, - sq.sq_port); + trace_qrtr_ns_message(qrtr_ctrl_pkt_strings[cmd], + sq.sq_node, sq.sq_port); ret = 0; switch (cmd) { diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e22092e4a783..7ed31b5e77e4 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -906,20 +906,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) node = NULL; if (addr->sq_node == QRTR_NODE_BCAST) { - enqueue_fn = qrtr_bcast_enqueue; - if (addr->sq_port != QRTR_PORT_CTRL) { + if (addr->sq_port != QRTR_PORT_CTRL && + qrtr_local_nid != QRTR_NODE_BCAST) { release_sock(sk); return -ENOTCONN; } + enqueue_fn = qrtr_bcast_enqueue; } else if (addr->sq_node == ipc->us.sq_node) { enqueue_fn = qrtr_local_enqueue; } else { - enqueue_fn = qrtr_node_enqueue; node = qrtr_node_lookup(addr->sq_node); if (!node) { release_sock(sk); return -ECONNRESET; } + enqueue_fn = qrtr_node_enqueue; } plen = (len + 3) & ~3; diff --git a/net/rds/message.c b/net/rds/message.c index 50f13f1d4ae0..071a261fdaab 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -162,12 +162,12 @@ static void rds_message_purge(struct rds_message *rm) if (rm->rdma.op_active) rds_rdma_free_op(&rm->rdma); if (rm->rdma.op_rdma_mr) - rds_mr_put(rm->rdma.op_rdma_mr); + kref_put(&rm->rdma.op_rdma_mr->r_kref, __rds_put_mr_final); if (rm->atomic.op_active) rds_atomic_free_op(&rm->atomic); if (rm->atomic.op_rdma_mr) - rds_mr_put(rm->atomic.op_rdma_mr); + kref_put(&rm->atomic.op_rdma_mr->r_kref, __rds_put_mr_final); } void rds_message_put(struct rds_message *rm) @@ -308,26 +308,20 @@ out: /* * RDS ops use this to grab SG entries from the rm's sg pool. */ -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret) +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; - if (WARN_ON(!ret)) - return NULL; - if (nents <= 0) { pr_warn("rds: alloc sgs failed! nents <= 0\n"); - *ret = -EINVAL; - return NULL; + return ERR_PTR(-EINVAL); } if (rm->m_used_sgs + nents > rm->m_total_sgs) { pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", rm->m_total_sgs, rm->m_used_sgs, nents); - *ret = -ENOMEM; - return NULL; + return ERR_PTR(-ENOMEM); } sg_ret = &sg_first[rm->m_used_sgs]; @@ -343,7 +337,6 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in unsigned int i; int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); - int ret; rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) @@ -352,10 +345,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) { + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { rds_message_put(rm); - return ERR_PTR(ret); + return ERR_CAST(rm->data.op_sg); } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 585e6b3b69ce..a7ae11846cd7 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2007, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -84,7 +84,7 @@ static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); - refcount_inc(&insert->r_refcount); + kref_get(&insert->r_kref); } return NULL; } @@ -99,10 +99,7 @@ static void rds_destroy_mr(struct rds_mr *mr) unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", - mr->r_key, refcount_read(&mr->r_refcount)); - - if (test_and_set_bit(RDS_MR_DEAD, &mr->r_state)) - return; + mr->r_key, kref_read(&mr->r_kref)); spin_lock_irqsave(&rs->rs_rdma_lock, flags); if (!RB_EMPTY_NODE(&mr->r_rb_node)) @@ -115,8 +112,10 @@ static void rds_destroy_mr(struct rds_mr *mr) mr->r_trans->free_mr(trans_private, mr->r_invalidate); } -void __rds_put_mr_final(struct rds_mr *mr) +void __rds_put_mr_final(struct kref *kref) { + struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref); + rds_destroy_mr(mr); kfree(mr); } @@ -140,8 +139,7 @@ void rds_rdma_drop_keys(struct rds_sock *rs) rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); - rds_destroy_mr(mr); - rds_mr_put(mr); + kref_put(&mr->r_kref, __rds_put_mr_final); spin_lock_irqsave(&rs->rs_rdma_lock, flags); } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); @@ -242,7 +240,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } - refcount_set(&mr->r_refcount, 1); + kref_init(&mr->r_kref); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; @@ -343,7 +341,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { - refcount_inc(&mr->r_refcount); + kref_get(&mr->r_kref); *mr_ret = mr; } @@ -351,7 +349,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, out: kfree(pages); if (mr) - rds_mr_put(mr); + kref_put(&mr->r_kref, __rds_put_mr_final); return ret; } @@ -434,13 +432,7 @@ int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen) if (!mr) return -EINVAL; - /* - * call rds_destroy_mr() ourselves so that we're sure it's done by the time - * we return. If we let rds_mr_put() do it it might not happen until - * someone else drops their ref. - */ - rds_destroy_mr(mr); - rds_mr_put(mr); + kref_put(&mr->r_kref, __rds_put_mr_final); return 0; } @@ -464,6 +456,14 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) return; } + /* Get a reference so that the MR won't go away before calling + * sync_mr() below. + */ + kref_get(&mr->r_kref); + + /* If it is going to be freed, remove it from the tree now so + * that no other thread can find it and free it. + */ if (mr->r_use_once || force) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); @@ -477,12 +477,13 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) if (mr->r_trans->sync_mr) mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE); + /* Release the reference held above. */ + kref_put(&mr->r_kref, __rds_put_mr_final); + /* If the MR was marked as invalidate, this will * trigger an async flush. */ - if (zot_me) { - rds_destroy_mr(mr); - rds_mr_put(mr); - } + if (zot_me) + kref_put(&mr->r_kref, __rds_put_mr_final); } void rds_rdma_free_op(struct rm_rdma_op *ro) @@ -490,7 +491,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) unsigned int i; if (ro->op_odp_mr) { - rds_mr_put(ro->op_odp_mr); + kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final); } else { for (i = 0; i < ro->op_nents; i++) { struct page *page = sg_page(&ro->op_sg[i]); @@ -664,9 +665,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_odp_mr = NULL; WARN_ON(!nr_pages); - op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); - if (!op->op_sg) + op->op_sg = rds_message_alloc_sgs(rm, nr_pages); + if (IS_ERR(op->op_sg)) { + ret = PTR_ERR(op->op_sg); goto out_pages; + } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -730,7 +733,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_pages; } RB_CLEAR_NODE(&local_odp_mr->r_rb_node); - refcount_set(&local_odp_mr->r_refcount, 1); + kref_init(&local_odp_mr->r_kref); local_odp_mr->r_trans = rs->rs_transport; local_odp_mr->r_sock = rs; local_odp_mr->r_trans_private = @@ -827,7 +830,7 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, if (!mr) err = -EINVAL; /* invalid r_key */ else - refcount_inc(&mr->r_refcount); + kref_get(&mr->r_kref); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { @@ -905,9 +908,11 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; - rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret); - if (!rm->atomic.op_sg) + rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); + if (IS_ERR(rm->atomic.op_sg)) { + ret = PTR_ERR(rm->atomic.op_sg); goto err; + } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/rds.h b/net/rds/rds.h index e4a603523083..6019b0c004a9 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -291,7 +291,7 @@ struct rds_incoming { struct rds_mr { struct rb_node r_rb_node; - refcount_t r_refcount; + struct kref r_kref; u32 r_key; /* A copy of the creation flags */ @@ -299,19 +299,11 @@ struct rds_mr { unsigned int r_invalidate:1; unsigned int r_write:1; - /* This is for RDS_MR_DEAD. - * It would be nice & consistent to make this part of the above - * bit field here, but we need to use test_and_set_bit. - */ - unsigned long r_state; struct rds_sock *r_sock; /* back pointer to the socket that owns us */ struct rds_transport *r_trans; void *r_trans_private; }; -/* Flags for mr->r_state */ -#define RDS_MR_DEAD 0 - static inline rds_rdma_cookie_t rds_rdma_make_cookie(u32 r_key, u32 offset) { return r_key | (((u64) offset) << 32); @@ -852,8 +844,7 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret); +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); @@ -946,12 +937,7 @@ void rds_atomic_send_complete(struct rds_message *rm, int wc_status); int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); -void __rds_put_mr_final(struct rds_mr *mr); -static inline void rds_mr_put(struct rds_mr *mr) -{ - if (refcount_dec_and_test(&mr->r_refcount)) - __rds_put_mr_final(mr); -} +void __rds_put_mr_final(struct kref *kref); static inline bool rds_destroy_pending(struct rds_connection *conn) { diff --git a/net/rds/send.c b/net/rds/send.c index 82dcd8b84fe7..68e2bdb08fd0 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1274,9 +1274,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { + ret = PTR_ERR(rm->data.op_sg); goto out; + } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a6c1349e965d..01135e54d95d 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -165,15 +165,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) goto error; } - /* we want to set the don't fragment bit */ - opt = IPV6_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } - /* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket. */ diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index bad3d2420344..90e263c6aa69 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -474,41 +474,21 @@ send_fragmentable: skb->tstamp = ktime_get_real(); switch (conn->params.local->srx.transport.family) { + case AF_INET6: case AF_INET: opt = IP_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IP, IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IP_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, SOL_IP, - IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - opt = IPV6_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IPV6_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + ret = kernel_sendmsg(conn->params.local->socket, &msg, + iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_seconds(); + + opt = IP_PMTUDISC_DO; + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); break; -#endif default: BUG(); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 1a766393be62..9adff83b523b 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -30,6 +30,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <uapi/linux/netfilter/nf_nat.h> @@ -536,6 +537,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, flow_offload_refresh(nf_ft, flow); nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); + nf_ct_acct_update(ct, dir, skb->len); return true; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index f6a3b969ead0..11b683c45c28 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -735,8 +735,11 @@ static int tcf_block_offload_cmd(struct tcf_block *block, INIT_LIST_HEAD(&bo.cb_list); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); - if (err < 0) + if (err < 0) { + if (err != -EOPNOTSUPP) + NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); return err; + } return tcf_block_setup(block, &bo); } @@ -1667,6 +1670,7 @@ int tcf_classify_ingress(struct sk_buff *skb, skb_ext_del(skb, TC_SKB_EXT); tp = rcu_dereference_bh(fchain->filter_chain); + last_executed_chain = fchain->index; } ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c index eecfe072c508..18755d29fd15 100644 --- a/net/sched/em_ipt.c +++ b/net/sched/em_ipt.c @@ -199,7 +199,7 @@ static void em_ipt_destroy(struct tcf_ematch *em) im->match->destroy(&par); } module_put(im->match->me); - kfree((void *)im); + kfree(im); } static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index b1da5589a0c6..c48f91075b5c 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -82,7 +82,7 @@ static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb) if (q->skip_sock_check) goto skip; - if (!sk) + if (!sk || !sk_fullsock(sk)) return false; if (!sock_flag(sk, SOCK_TXTIME)) @@ -137,8 +137,9 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) struct sock_exterr_skb *serr; struct sk_buff *clone; ktime_t txtime = skb->tstamp; + struct sock *sk = skb->sk; - if (!skb->sk || !(skb->sk->sk_txtime_report_errors)) + if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors)) return; clone = skb_clone(skb, GFP_ATOMIC); @@ -154,7 +155,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */ serr->ee.ee_info = txtime; /* low part of tstamp */ - if (sock_queue_err_skb(skb->sk, clone)) + if (sock_queue_err_skb(sk, clone)) kfree_skb(clone); } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 09050c1d5517..f7cb0b7faec2 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -858,7 +858,11 @@ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, struct sctp_chunk *retval; __u32 ctsn; - ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); + if (chunk && chunk->asoc) + ctsn = sctp_tsnmap_get_ctsn(&chunk->asoc->peer.tsn_map); + else + ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); + shut.cum_tsn_ack = htonl(ctsn); retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 6a16af4b1ef6..26788f4a3b9e 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1865,7 +1865,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( */ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, - SCTP_ST_CHUNK(0), NULL, + SCTP_ST_CHUNK(0), repl, commands); } else { sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -5470,7 +5470,7 @@ enum sctp_disposition sctp_sf_do_9_2_start_shutdown( * in the Cumulative TSN Ack field the last sequential TSN it * has received from the peer. */ - reply = sctp_make_shutdown(asoc, NULL); + reply = sctp_make_shutdown(asoc, arg); if (!reply) goto nomem; @@ -6068,7 +6068,7 @@ enum sctp_disposition sctp_sf_autoclose_timer_expire( disposition = SCTP_DISPOSITION_CONSUME; if (sctp_outq_is_empty(&asoc->outqueue)) { disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, - arg, commands); + NULL, commands); } return disposition; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index af0ddd28b081..baef5ee43dbb 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -529,7 +529,6 @@ void cache_purge(struct cache_detail *detail) { struct cache_head *ch = NULL; struct hlist_head *head = NULL; - struct hlist_node *tmp = NULL; int i = 0; spin_lock(&detail->hash_lock); @@ -541,7 +540,9 @@ void cache_purge(struct cache_detail *detail) dprintk("RPC: %d entries in %s cache\n", detail->entries, detail->name); for (i = 0; i < detail->hash_size; i++) { head = &detail->hash_table[i]; - hlist_for_each_entry_safe(ch, tmp, head, cache_list) { + while (!hlist_empty(head)) { + ch = hlist_entry(head->first, struct cache_head, + cache_list); sunrpc_begin_cache_remove_entry(ch, detail); spin_unlock(&detail->hash_lock); sunrpc_end_cache_remove_entry(ch, detail); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index e27e3532ec75..2284ff038dad 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -908,9 +908,6 @@ int svc_send(struct svc_rqst *rqstp) if (!xprt) goto out; - /* release the receive skb before sending the reply */ - xprt->xpt_ops->xpo_release_rqst(rqstp); - /* calculate over-all length */ xb = &rqstp->rq_res; xb->len = xb->head[0].iov_len + @@ -1040,6 +1037,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt) dprintk("svc: svc_delete_xprt(%p)\n", xprt); xprt->xpt_ops->xpo_detach(xprt); + if (xprt->xpt_bc_xprt) + xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt); spin_lock_bh(&serv->sv_lock); list_del_init(&xprt->xpt_list); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 519cf9c4f8fd..023514e392b3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -527,6 +527,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int uninitialized_var(sent); int err; + svc_release_udp_skb(rqstp); + svc_set_cmsg_data(rqstp, cmh); err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); @@ -1076,6 +1078,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int uninitialized_var(sent); int err; + svc_release_skb(rqstp); + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); if (err < 0 || sent != (xdr->len + sizeof(marker))) diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index d510a3a15d4b..af7eb8d202ae 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -244,6 +244,8 @@ static void xprt_rdma_bc_close(struct rpc_xprt *xprt) { dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); + + xprt_disconnect_done(xprt); xprt->cwnd = RPC_CWNDSHIFT; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 54469b72b25f..efa5fcb5793f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -223,6 +223,26 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, svc_rdma_recv_ctxt_destroy(rdma, ctxt); } +/** + * svc_rdma_release_rqst - Release transport-specific per-rqst resources + * @rqstp: svc_rqst being released + * + * Ensure that the recv_ctxt is released whether or not a Reply + * was sent. For example, the client could close the connection, + * or svc_process could drop an RPC, before the Reply is sent. + */ +void svc_rdma_release_rqst(struct svc_rqst *rqstp) +{ + struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; + struct svc_xprt *xprt = rqstp->rq_xprt; + struct svcxprt_rdma *rdma = + container_of(xprt, struct svcxprt_rdma, sc_xprt); + + rqstp->rq_xprt_ctxt = NULL; + if (ctxt) + svc_rdma_recv_ctxt_put(rdma, ctxt); +} + static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt) { @@ -820,6 +840,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) __be32 *p; int ret; + rqstp->rq_xprt_ctxt = NULL; + spin_lock(&rdma_xprt->sc_rq_dto_lock); ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q); if (ctxt) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index bd7c195d872e..23c2d3ce0dc9 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -323,8 +323,6 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) if (atomic_sub_return(cc->cc_sqecount, &rdma->sc_sq_avail) > 0) { ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr); - trace_svcrdma_post_rw(&cc->cc_cqe, - cc->cc_sqecount, ret); if (ret) break; return 0; @@ -337,6 +335,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) trace_svcrdma_sq_retry(rdma); } while (1); + trace_svcrdma_sq_post_err(rdma, ret); set_bit(XPT_CLOSE, &xprt->xpt_flags); /* If even one was posted, there will be a completion. */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 90cba3058f04..b6c8643867f2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -322,15 +322,17 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr) } svc_xprt_get(&rdma->sc_xprt); + trace_svcrdma_post_send(wr); ret = ib_post_send(rdma->sc_qp, wr, NULL); - trace_svcrdma_post_send(wr, ret); - if (ret) { - set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); - svc_xprt_put(&rdma->sc_xprt); - wake_up(&rdma->sc_send_wait); - } - break; + if (ret) + break; + return 0; } + + trace_svcrdma_sq_post_err(rdma, ret); + set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); + svc_xprt_put(&rdma->sc_xprt); + wake_up(&rdma->sc_send_wait); return ret; } @@ -924,12 +926,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp); if (ret < 0) goto err1; - ret = 0; - -out: - rqstp->rq_xprt_ctxt = NULL; - svc_rdma_recv_ctxt_put(rdma, rctxt); - return ret; + return 0; err2: if (ret != -E2BIG && ret != -EINVAL) @@ -938,16 +935,14 @@ out: ret = svc_rdma_send_error_msg(rdma, sctxt, rqstp); if (ret < 0) goto err1; - ret = 0; - goto out; + return 0; err1: svc_rdma_send_ctxt_put(rdma, sctxt); err0: trace_svcrdma_send_failed(rqstp, ret); set_bit(XPT_CLOSE, &xprt->xpt_flags); - ret = -ENOTCONN; - goto out; + return -ENOTCONN; } /** diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 8bb99980ae85..ea54785db4f8 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -71,7 +71,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, struct sockaddr *sa, int salen, int flags); static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt); -static void svc_rdma_release_rqst(struct svc_rqst *); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); @@ -552,10 +551,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) return NULL; } -static void svc_rdma_release_rqst(struct svc_rqst *rqstp) -{ -} - /* * When connected, an svc_xprt has at least two references: * diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0bda8a73e8a8..845d0be805ec 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2584,6 +2584,7 @@ static int bc_send_request(struct rpc_rqst *req) static void bc_close(struct rpc_xprt *xprt) { + xprt_disconnect_done(xprt); } /* diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c8c47fc72653..8c47ded2edb6 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1712,6 +1712,7 @@ exit: case -EBUSY: this_cpu_inc(stats->stat[STAT_ASYNC]); *skb = NULL; + tipc_aead_put(aead); return rc; default: this_cpu_inc(stats->stat[STAT_NOK]); diff --git a/net/tipc/link.c b/net/tipc/link.c index 467c53a1fb5c..d4675e922a8f 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1065,7 +1065,7 @@ static void tipc_link_update_cwin(struct tipc_link *l, int released, /* Enter fast recovery */ if (unlikely(retransmitted)) { l->ssthresh = max_t(u16, l->window / 2, 300); - l->window = l->ssthresh; + l->window = min_t(u16, l->ssthresh, l->window); return; } /* Enter slow start */ diff --git a/net/tipc/node.c b/net/tipc/node.c index 10292c942384..803a3a6d0f50 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2038,6 +2038,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) n = tipc_node_find_by_id(net, ehdr->id); } tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b); + tipc_node_put(n); if (!skb) return; @@ -2090,7 +2091,7 @@ rcv: /* Check/update node state before receiving */ if (unlikely(skb)) { if (unlikely(skb_linearize(skb))) - goto discard; + goto out_node_put; tipc_node_write_lock(n); if (tipc_node_check_state(n, skb, bearer_id, &xmitq)) { if (le->link) { @@ -2119,6 +2120,7 @@ rcv: if (!skb_queue_empty(&xmitq)) tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n); +out_node_put: tipc_node_put(n); discard: kfree_skb(skb); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 156efce50dbd..0e989005bdc2 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -56,9 +56,9 @@ enum { TLS_NUM_PROTS, }; -static struct proto *saved_tcpv6_prot; +static const struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); -static struct proto *saved_tcpv4_prot; +static const struct proto *saved_tcpv4_prot; static DEFINE_MUTEX(tcpv4_prot_mutex); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_sw_proto_ops; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5fa402144cda..692bcd35f809 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -644,10 +644,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, .len = NL80211_HE_MAX_CAPABILITY_LEN }, - [NL80211_ATTR_FTM_RESPONDER] = { - .type = NLA_NESTED, - .validation_data = nl80211_ftm_responder_policy, - }, + [NL80211_ATTR_FTM_RESPONDER] = + NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 00e782335cb0..25bf72ee6cad 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -115,8 +115,10 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, goto drop; } - if (!pskb_may_pull(skb, 1)) + if (!pskb_may_pull(skb, 1)) { + x25_neigh_put(nb); return 0; + } switch (skb->data[0]) { diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index fa7bb5e060d0..ed7a6060f73c 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -343,7 +343,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) u32 chunk_size = mr->chunk_size, headroom = mr->headroom; unsigned int chunks, chunks_per_page; u64 addr = mr->addr, size = mr->len; - int size_chk, err; + int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: @@ -382,8 +382,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; - if (size_chk < 0) + if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; umem->address = (unsigned long)addr; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 356f90e4522b..f6e6609f70a3 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -131,8 +131,9 @@ static void __xsk_rcv_memcpy(struct xdp_umem *umem, u64 addr, void *from_buf, u64 page_start = addr & ~(PAGE_SIZE - 1); u64 first_len = PAGE_SIZE - (addr - page_start); - memcpy(to_buf, from_buf, first_len + metalen); - memcpy(next_pg_addr, from_buf + first_len, len - first_len); + memcpy(to_buf, from_buf, first_len); + memcpy(next_pg_addr, from_buf + first_len, + len + metalen - first_len); return; } @@ -321,7 +322,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) if (!xskq_cons_peek_desc(xs->tx, desc, umem)) continue; - /* This is the backpreassure mechanism for the Tx path. + /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. @@ -405,7 +406,7 @@ static int xsk_generic_xmit(struct sock *sk) addr = desc.addr; buffer = xdp_umem_get_data(xs->umem, addr); err = skb_store_bits(skb, 0, buffer, len); - /* This is the backpreassure mechanism for the Tx path. + /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c index cc86bf6566e4..9894693f3be1 100644 --- a/samples/vfio-mdev/mdpy.c +++ b/samples/vfio-mdev/mdpy.c @@ -418,7 +418,7 @@ static int mdpy_mmap(struct mdev_device *mdev, struct vm_area_struct *vma) return -EINVAL; return remap_vmalloc_range_partial(vma, vma->vm_start, - mdev_state->memblk, + mdev_state->memblk, 0, vma->vm_end - vma->vm_start); } diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 97547108ee7f..4b799737722c 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -309,7 +309,7 @@ define rule_dtc endef $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_rule,dtc) + $(call if_changed_rule,dtc,yaml) dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index d64c67b67e3c..eac40f0abd56 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -479,7 +479,7 @@ our $allocFunctions = qr{(?x: (?:kv|k|v)[czm]alloc(?:_node|_array)? | kstrdup(?:_const)? | kmemdup(?:_nul)?) | - (?:\w+)?alloc_skb(?:ip_align)? | + (?:\w+)?alloc_skb(?:_ip_align)? | # dev_alloc_skb/netdev_alloc_skb, et al dma_alloc_coherent )}; diff --git a/scripts/config b/scripts/config index e0e39826dae9..eee5b7f3a092 100755 --- a/scripts/config +++ b/scripts/config @@ -7,6 +7,9 @@ myname=${0##*/} # If no prefix forced, use the default CONFIG_ CONFIG_="${CONFIG_-CONFIG_}" +# We use an uncommon delimiter for sed substitutions +SED_DELIM=$(echo -en "\001") + usage() { cat >&2 <<EOL Manipulate options in a .config file from the command line. @@ -83,7 +86,7 @@ txt_subst() { local infile="$3" local tmpfile="$infile.swp" - sed -e "s:$before:$after:" "$infile" >"$tmpfile" + sed -e "s$SED_DELIM$before$SED_DELIM$after$SED_DELIM" "$infile" >"$tmpfile" # replace original file with the edited one mv "$tmpfile" "$infile" } diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check index 9a8cc10cffd0..c71832b2312b 100755 --- a/scripts/documentation-file-ref-check +++ b/scripts/documentation-file-ref-check @@ -25,7 +25,7 @@ my $fix = 0; my $warn = 0; if (! -d ".git") { - printf "Warning: can't check if file exists, as this is not a git tree"; + printf "Warning: can't check if file exists, as this is not a git tree\n"; exit 0; } diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile index 2f3c3a7e1620..ef85f8b7d4a7 100644 --- a/scripts/dtc/Makefile +++ b/scripts/dtc/Makefile @@ -13,7 +13,7 @@ dtc-objs += dtc-lexer.lex.o dtc-parser.tab.o HOST_EXTRACFLAGS := -I $(srctree)/$(src)/libfdt ifeq ($(shell pkg-config --exists yaml-0.1 2>/dev/null && echo yes),) -ifneq ($(CHECK_DTBS),) +ifneq ($(CHECK_DT_BINDING)$(CHECK_DTBS),) $(error dtc needs libyaml for DT schema validation support. \ Install the necessary libyaml development package.) endif diff --git a/scripts/kernel-doc b/scripts/kernel-doc index f2d73f04e71d..f746ca8fa403 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -853,7 +853,7 @@ sub output_function_rst(%) { if ($type =~ m/([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)/) { # pointer-to-function - print $1 . $parameter . ") (" . $2; + print $1 . $parameter . ") (" . $2 . ")"; } else { print $type . " " . $parameter; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 5c3c50c5ec52..7f7d4ee7b652 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2251,6 +2251,7 @@ static void add_header(struct buffer *b, struct module *mod) * Include build-salt.h after module.h in order to * inherit the definitions. */ + buf_printf(b, "#define INCLUDE_VERMAGIC\n"); buf_printf(b, "#include <linux/build-salt.h>\n"); buf_printf(b, "#include <linux/vermagic.h>\n"); buf_printf(b, "#include <linux/compiler.h>\n"); diff --git a/security/keys/proc.c b/security/keys/proc.c index 415f3f1c2da0..d0cde6685627 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -139,6 +139,8 @@ static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos) n = key_serial_next(p, v); if (n) *_pos = key_node_serial(n); + else + (*_pos)++; return n; } diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 70ecdc78efbd..c21b922e5ebe 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -1035,14 +1035,14 @@ static int str_read(char **strp, gfp_t flags, void *fp, u32 len) if (!str) return -ENOMEM; - /* it's expected the caller should free the str */ - *strp = str; - rc = next_entry(str, fp, len); - if (rc) + if (rc) { + kfree(str); return rc; + } str[len] = '\0'; + *strp = str; return 0; } diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig index 4ca6b09056f3..3bc9224d5e4f 100644 --- a/sound/hda/Kconfig +++ b/sound/hda/Kconfig @@ -21,16 +21,17 @@ config SND_HDA_EXT_CORE select SND_HDA_CORE config SND_HDA_PREALLOC_SIZE - int "Pre-allocated buffer size for HD-audio driver" if !SND_DMA_SGBUF + int "Pre-allocated buffer size for HD-audio driver" range 0 32768 - default 0 if SND_DMA_SGBUF + default 2048 if SND_DMA_SGBUF default 64 if !SND_DMA_SGBUF help Specifies the default pre-allocated buffer-size in kB for the HD-audio driver. A larger buffer (e.g. 2048) is preferred for systems using PulseAudio. The default 64 is chosen just for compatibility reasons. - On x86 systems, the default is zero as we need no preallocation. + On x86 systems, the default is 2048 as a reasonable value for + most of modern systems. Note that the pre-allocation size can be changed dynamically via a proc file (/proc/asound/card*/pcm*/sub*/prealloc), too. diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c index 6e3177bcc709..015c0d676897 100644 --- a/sound/pci/ctxfi/cthw20k1.c +++ b/sound/pci/ctxfi/cthw20k1.c @@ -168,7 +168,7 @@ static int src_get_rsc_ctrl_blk(void **rblk) static int src_put_rsc_ctrl_blk(void *blk) { - kfree((struct src_rsc_ctrl_blk *)blk); + kfree(blk); return 0; } @@ -494,7 +494,7 @@ static int src_mgr_get_ctrl_blk(void **rblk) static int src_mgr_put_ctrl_blk(void *blk) { - kfree((struct src_mgr_ctrl_blk *)blk); + kfree(blk); return 0; } @@ -515,7 +515,7 @@ static int srcimp_mgr_get_ctrl_blk(void **rblk) static int srcimp_mgr_put_ctrl_blk(void *blk) { - kfree((struct srcimp_mgr_ctrl_blk *)blk); + kfree(blk); return 0; } @@ -702,7 +702,7 @@ static int amixer_rsc_get_ctrl_blk(void **rblk) static int amixer_rsc_put_ctrl_blk(void *blk) { - kfree((struct amixer_rsc_ctrl_blk *)blk); + kfree(blk); return 0; } @@ -909,7 +909,7 @@ static int dai_get_ctrl_blk(void **rblk) static int dai_put_ctrl_blk(void *blk) { - kfree((struct dai_ctrl_blk *)blk); + kfree(blk); return 0; } @@ -958,7 +958,7 @@ static int dao_get_ctrl_blk(void **rblk) static int dao_put_ctrl_blk(void *blk) { - kfree((struct dao_ctrl_blk *)blk); + kfree(blk); return 0; } @@ -1156,7 +1156,7 @@ static int daio_mgr_get_ctrl_blk(struct hw *hw, void **rblk) static int daio_mgr_put_ctrl_blk(void *blk) { - kfree((struct daio_mgr_ctrl_blk *)blk); + kfree(blk); return 0; } diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index a34a2c9f4bcf..7e3ae4534df9 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -641,8 +641,18 @@ static void hda_jackpoll_work(struct work_struct *work) struct hda_codec *codec = container_of(work, struct hda_codec, jackpoll_work.work); - snd_hda_jack_set_dirty_all(codec); - snd_hda_jack_poll_all(codec); + /* for non-polling trigger: we need nothing if already powered on */ + if (!codec->jackpoll_interval && snd_hdac_is_power_on(&codec->core)) + return; + + /* the power-up/down sequence triggers the runtime resume */ + snd_hda_power_up_pm(codec); + /* update jacks manually if polling is required, too */ + if (codec->jackpoll_interval) { + snd_hda_jack_set_dirty_all(codec); + snd_hda_jack_poll_all(codec); + } + snd_hda_power_down_pm(codec); if (!codec->jackpoll_interval) return; @@ -2951,18 +2961,14 @@ static int hda_codec_runtime_resume(struct device *dev) static int hda_codec_force_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); - bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used; int ret; - /* The get/put pair below enforces the runtime resume even if the - * device hasn't been used at suspend time. This trick is needed to - * update the jack state change during the sleep. - */ - if (forced_resume) - pm_runtime_get_noresume(dev); ret = pm_runtime_force_resume(dev); - if (forced_resume) - pm_runtime_put(dev); + /* schedule jackpoll work for jack detection update */ + if (codec->jackpoll_interval || + (pm_runtime_suspended(dev) && hda_codec_need_resume(codec))) + schedule_delayed_work(&codec->jackpoll_work, + codec->jackpoll_interval); return ret; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index bd093593f8fb..457a2c065485 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1004,7 +1004,8 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt) if (status && from_rt) { list_for_each_codec(codec, &chip->bus) - if (status & (1 << codec->addr)) + if (!codec->relaxed_resume && + (status & (1 << codec->addr))) schedule_delayed_work(&codec->jackpoll_work, codec->jackpoll_interval); } @@ -1027,7 +1028,7 @@ static int azx_suspend(struct device *dev) chip = card->private_data; bus = azx_bus(chip); snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); - __azx_runtime_suspend(chip); + pm_runtime_force_suspend(dev); if (bus->irq >= 0) { free_irq(bus->irq, chip); bus->irq = -1; @@ -1055,7 +1056,8 @@ static int azx_resume(struct device *dev) chip->msi = 0; if (azx_acquire_irq(chip, 1) < 0) return -EIO; - __azx_runtime_resume(chip, false); + + pm_runtime_force_resume(dev); snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); @@ -1071,6 +1073,8 @@ static int azx_freeze_noirq(struct device *dev) struct azx *chip = card->private_data; struct pci_dev *pci = to_pci_dev(dev); + if (!azx_is_pm_ready(card)) + return 0; if (chip->driver_type == AZX_DRIVER_SKL) pci_set_power_state(pci, PCI_D3hot); @@ -1083,6 +1087,8 @@ static int azx_thaw_noirq(struct device *dev) struct azx *chip = card->private_data; struct pci_dev *pci = to_pci_dev(dev); + if (!azx_is_pm_ready(card)) + return 0; if (chip->driver_type == AZX_DRIVER_SKL) pci_set_power_state(pci, PCI_D0); @@ -1098,12 +1104,12 @@ static int azx_runtime_suspend(struct device *dev) if (!azx_is_pm_ready(card)) return 0; chip = card->private_data; - if (!azx_has_pm_runtime(chip)) - return 0; /* enable controller wake up event */ - azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | - STATESTS_INT_MASK); + if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) { + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | + STATESTS_INT_MASK); + } __azx_runtime_suspend(chip); trace_azx_runtime_suspend(chip); @@ -1114,17 +1120,18 @@ static int azx_runtime_resume(struct device *dev) { struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; + bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0; if (!azx_is_pm_ready(card)) return 0; chip = card->private_data; - if (!azx_has_pm_runtime(chip)) - return 0; - __azx_runtime_resume(chip, true); + __azx_runtime_resume(chip, from_rt); /* disable controller Wake Up event*/ - azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & - ~STATESTS_INT_MASK); + if (from_rt) { + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & + ~STATESTS_INT_MASK); + } trace_azx_runtime_resume(chip); return 0; @@ -1199,10 +1206,8 @@ static void azx_vs_set_state(struct pci_dev *pci, if (!disabled) { dev_info(chip->card->dev, "Start delayed initialization\n"); - if (azx_probe_continue(chip) < 0) { + if (azx_probe_continue(chip) < 0) dev_err(chip->card->dev, "initialization error\n"); - hda->init_failed = true; - } } } else { dev_info(chip->card->dev, "%s via vga_switcheroo\n", @@ -1335,12 +1340,15 @@ static int register_vga_switcheroo(struct azx *chip) /* * destructor */ -static int azx_free(struct azx *chip) +static void azx_free(struct azx *chip) { struct pci_dev *pci = chip->pci; struct hda_intel *hda = container_of(chip, struct hda_intel, chip); struct hdac_bus *bus = azx_bus(chip); + if (hda->freed) + return; + if (azx_has_pm_runtime(chip) && chip->running) pm_runtime_get_noresume(&pci->dev); chip->running = 0; @@ -1384,9 +1392,8 @@ static int azx_free(struct azx *chip) if (chip->driver_caps & AZX_DCAPS_I915_COMPONENT) snd_hdac_i915_exit(bus); - kfree(hda); - return 0; + hda->freed = 1; } static int azx_dev_disconnect(struct snd_device *device) @@ -1402,7 +1409,8 @@ static int azx_dev_disconnect(struct snd_device *device) static int azx_dev_free(struct snd_device *device) { - return azx_free(device->device_data); + azx_free(device->device_data); + return 0; } #ifdef SUPPORT_VGA_SWITCHEROO @@ -1769,7 +1777,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci, if (err < 0) return err; - hda = kzalloc(sizeof(*hda), GFP_KERNEL); + hda = devm_kzalloc(&pci->dev, sizeof(*hda), GFP_KERNEL); if (!hda) { pci_disable_device(pci); return -ENOMEM; @@ -1810,7 +1818,6 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci, err = azx_bus_init(chip, model[dev]); if (err < 0) { - kfree(hda); pci_disable_device(pci); return err; } @@ -2005,7 +2012,7 @@ static int azx_first_init(struct azx *chip) /* codec detection */ if (!azx_bus(chip)->codec_mask) { dev_err(card->dev, "no codecs found!\n"); - return -ENODEV; + /* keep running the rest for the runtime PM */ } if (azx_acquire_irq(chip, 0) < 0) @@ -2027,24 +2034,15 @@ static void azx_firmware_cb(const struct firmware *fw, void *context) { struct snd_card *card = context; struct azx *chip = card->private_data; - struct pci_dev *pci = chip->pci; - - if (!fw) { - dev_err(card->dev, "Cannot load firmware, aborting\n"); - goto error; - } - chip->fw = fw; + if (fw) + chip->fw = fw; + else + dev_err(card->dev, "Cannot load firmware, continue without patching\n"); if (!chip->disabled) { /* continue probing */ - if (azx_probe_continue(chip)) - goto error; + azx_probe_continue(chip); } - return; /* OK */ - - error: - snd_card_free(card); - pci_set_drvdata(pci, NULL); } #endif @@ -2081,7 +2079,6 @@ static void pcm_mmap_prepare(struct snd_pcm_substream *substream, * should be ignored from the beginning. */ static const struct snd_pci_quirk driver_blacklist[] = { - SND_PCI_QUIRK(0x1043, 0x874f, "ASUS ROG Zenith II / Strix", 0), SND_PCI_QUIRK(0x1462, 0xcb59, "MSI TRX40 Creator", 0), SND_PCI_QUIRK(0x1462, 0xcb60, "MSI TRX40", 0), {} @@ -2308,9 +2305,11 @@ static int azx_probe_continue(struct azx *chip) #endif /* create codec instances */ - err = azx_probe_codecs(chip, azx_max_codecs[chip->driver_type]); - if (err < 0) - goto out_free; + if (bus->codec_mask) { + err = azx_probe_codecs(chip, azx_max_codecs[chip->driver_type]); + if (err < 0) + goto out_free; + } #ifdef CONFIG_SND_HDA_PATCH_LOADER if (chip->fw) { @@ -2324,7 +2323,7 @@ static int azx_probe_continue(struct azx *chip) #endif } #endif - if ((probe_only[dev] & 1) == 0) { + if (bus->codec_mask && !(probe_only[dev] & 1)) { err = azx_codec_configure(chip); if (err < 0) goto out_free; @@ -2341,17 +2340,23 @@ static int azx_probe_continue(struct azx *chip) set_default_power_save(chip); - if (azx_has_pm_runtime(chip)) + if (azx_has_pm_runtime(chip)) { + pm_runtime_use_autosuspend(&pci->dev); + pm_runtime_allow(&pci->dev); pm_runtime_put_autosuspend(&pci->dev); + } out_free: - if (err < 0 || !hda->need_i915_power) + if (err < 0) { + azx_free(chip); + return err; + } + + if (!hda->need_i915_power) display_power(chip, false); - if (err < 0) - hda->init_failed = 1; complete_all(&hda->probe_wait); to_hda_bus(bus)->bus_probing = 0; - return err; + return 0; } static void azx_remove(struct pci_dev *pci) diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h index 2acfff3da1a0..3fb119f09040 100644 --- a/sound/pci/hda/hda_intel.h +++ b/sound/pci/hda/hda_intel.h @@ -27,6 +27,7 @@ struct hda_intel { unsigned int use_vga_switcheroo:1; unsigned int vga_switcheroo_registered:1; unsigned int init_failed:1; /* delayed init failed */ + unsigned int freed:1; /* resources already released */ bool need_i915_power:1; /* the hda controller needs i915 power */ }; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index bb287a916dae..4eff16053bd5 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -38,6 +38,10 @@ static bool static_hdmi_pcm; module_param(static_hdmi_pcm, bool, 0644); MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); +static bool enable_acomp = true; +module_param(enable_acomp, bool, 0444); +MODULE_PARM_DESC(enable_acomp, "Enable audio component binding (default=yes)"); + struct hdmi_spec_per_cvt { hda_nid_t cvt_nid; int assigned; @@ -2505,6 +2509,11 @@ static void generic_acomp_init(struct hda_codec *codec, { struct hdmi_spec *spec = codec->spec; + if (!enable_acomp) { + codec_info(codec, "audio component disabled by module option\n"); + return; + } + spec->port2pin = port2pin; setup_drm_audio_ops(codec, ops); if (!snd_hdac_acomp_init(&codec->bus->core, &spec->drm_audio_ops, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index de2826f90d34..c1a85c8f7b69 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -377,6 +377,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0233: case 0x10ec0235: case 0x10ec0236: + case 0x10ec0245: case 0x10ec0255: case 0x10ec0256: case 0x10ec0257: @@ -797,9 +798,11 @@ static void alc_ssid_check(struct hda_codec *codec, const hda_nid_t *ports) { if (!alc_subsystem_id(codec, ports)) { struct alc_spec *spec = codec->spec; - codec_dbg(codec, - "realtek: Enable default setup for auto mode as fallback\n"); - spec->init_amp = ALC_INIT_DEFAULT; + if (spec->init_amp == ALC_INIT_UNDEFINED) { + codec_dbg(codec, + "realtek: Enable default setup for auto mode as fallback\n"); + spec->init_amp = ALC_INIT_DEFAULT; + } } } @@ -7378,6 +7381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), 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, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), @@ -8195,6 +8199,7 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; break; case 0x10ec0215: + case 0x10ec0245: case 0x10ec0285: case 0x10ec0289: spec->codec_variant = ALC269_TYPE_ALC215; @@ -9456,6 +9461,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0234, "ALC234", patch_alc269), HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269), HDA_CODEC_ENTRY(0x10ec0236, "ALC236", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0245, "ALC245", patch_alc269), HDA_CODEC_ENTRY(0x10ec0255, "ALC255", patch_alc269), HDA_CODEC_ENTRY(0x10ec0256, "ALC256", patch_alc269), HDA_CODEC_ENTRY(0x10ec0257, "ALC257", patch_alc269), diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c index 024a7ee54cd5..e499c00e0c66 100644 --- a/sound/soc/amd/acp3x-rt5682-max9836.c +++ b/sound/soc/amd/acp3x-rt5682-max9836.c @@ -89,9 +89,9 @@ static int acp3x_5682_init(struct snd_soc_pcm_runtime *rtd) } snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_0, KEY_PLAYPAUSE); - snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_1, KEY_VOLUMEUP); - snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN); - snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_3, KEY_VOICECOMMAND); + snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_1, KEY_VOICECOMMAND); + snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_2, KEY_VOLUMEUP); + snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN); ret = snd_soc_component_set_jack(component, &pco_jack, NULL); if (ret) { diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index e6a0c5d05fa5..e60e0b6a689c 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1525,6 +1525,7 @@ config SND_SOC_WM8804_SPI config SND_SOC_WM8900 tristate + depends on SND_SOC_I2C_AND_SPI config SND_SOC_WM8903 tristate "Wolfson Microelectronics WM8903 CODEC" @@ -1576,6 +1577,7 @@ config SND_SOC_WM8985 config SND_SOC_WM8988 tristate + depends on SND_SOC_I2C_AND_SPI config SND_SOC_WM8990 tristate @@ -1594,6 +1596,7 @@ config SND_SOC_WM8994 config SND_SOC_WM8995 tristate + depends on SND_SOC_I2C_AND_SPI config SND_SOC_WM8996 tristate diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index fba9b749839d..f26b77faed59 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -142,14 +142,14 @@ static struct hdac_hdmi_pcm * hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi, struct hdac_hdmi_cvt *cvt) { - struct hdac_hdmi_pcm *pcm = NULL; + struct hdac_hdmi_pcm *pcm; list_for_each_entry(pcm, &hdmi->pcm_list, head) { if (pcm->cvt == cvt) - break; + return pcm; } - return pcm; + return NULL; } static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm, diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c index 40de9d7811d1..a448d2a2918a 100644 --- a/sound/soc/codecs/madera.c +++ b/sound/soc/codecs/madera.c @@ -1903,7 +1903,6 @@ const struct soc_enum madera_isrc_fsh[] = { MADERA_ISRC4_FSH_SHIFT, 0xf, MADERA_RATE_ENUM_SIZE, madera_rate_text, madera_rate_val), - }; EXPORT_SYMBOL_GPL(madera_isrc_fsh); @@ -1924,7 +1923,6 @@ const struct soc_enum madera_isrc_fsl[] = { MADERA_ISRC4_FSL_SHIFT, 0xf, MADERA_RATE_ENUM_SIZE, madera_rate_text, madera_rate_val), - }; EXPORT_SYMBOL_GPL(madera_isrc_fsl); @@ -1938,7 +1936,6 @@ const struct soc_enum madera_asrc1_rate[] = { MADERA_ASYNC_RATE_ENUM_SIZE, madera_rate_text + MADERA_SYNC_RATE_ENUM_SIZE, madera_rate_val + MADERA_SYNC_RATE_ENUM_SIZE), - }; EXPORT_SYMBOL_GPL(madera_asrc1_rate); @@ -1964,7 +1961,6 @@ const struct soc_enum madera_asrc2_rate[] = { MADERA_ASYNC_RATE_ENUM_SIZE, madera_rate_text + MADERA_SYNC_RATE_ENUM_SIZE, madera_rate_val + MADERA_SYNC_RATE_ENUM_SIZE), - }; EXPORT_SYMBOL_GPL(madera_asrc2_rate); diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index d5130193b4a2..e8a8bf7b4ffe 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1653,6 +1653,40 @@ static int sgtl5000_i2c_probe(struct i2c_client *client, dev_err(&client->dev, "Error %d initializing CHIP_CLK_CTRL\n", ret); + /* Mute everything to avoid pop from the following power-up */ + ret = regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_CTRL, + SGTL5000_CHIP_ANA_CTRL_DEFAULT); + if (ret) { + dev_err(&client->dev, + "Error %d muting outputs via CHIP_ANA_CTRL\n", ret); + goto disable_clk; + } + + /* + * If VAG is powered-on (e.g. from previous boot), it would be disabled + * by the write to ANA_POWER in later steps of the probe code. This + * may create a loud pop even with all outputs muted. The proper way + * to circumvent this is disabling the bit first and waiting the proper + * cool-down time. + */ + ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, &value); + if (ret) { + dev_err(&client->dev, "Failed to read ANA_POWER: %d\n", ret); + goto disable_clk; + } + if (value & SGTL5000_VAG_POWERUP) { + ret = regmap_update_bits(sgtl5000->regmap, + SGTL5000_CHIP_ANA_POWER, + SGTL5000_VAG_POWERUP, + 0); + if (ret) { + dev_err(&client->dev, "Error %d disabling VAG\n", ret); + goto disable_clk; + } + + msleep(SGTL5000_VAG_POWERDOWN_DELAY); + } + /* Follow section 2.2.1.1 of AN3663 */ ana_pwr = SGTL5000_ANA_POWER_DEFAULT; if (sgtl5000->num_supplies <= VDDD) { diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h index a4bf4bca95bf..56ec5863f250 100644 --- a/sound/soc/codecs/sgtl5000.h +++ b/sound/soc/codecs/sgtl5000.h @@ -233,6 +233,7 @@ /* * SGTL5000_CHIP_ANA_CTRL */ +#define SGTL5000_CHIP_ANA_CTRL_DEFAULT 0x0133 #define SGTL5000_LINE_OUT_MUTE 0x0100 #define SGTL5000_HP_SEL_MASK 0x0040 #define SGTL5000_HP_SEL_SHIFT 6 diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c index 1554631cb397..5b7f9fcf6cbf 100644 --- a/sound/soc/codecs/tas571x.c +++ b/sound/soc/codecs/tas571x.c @@ -820,8 +820,10 @@ static int tas571x_i2c_probe(struct i2c_client *client, priv->regmap = devm_regmap_init(dev, NULL, client, priv->chip->regmap_config); - if (IS_ERR(priv->regmap)) - return PTR_ERR(priv->regmap); + if (IS_ERR(priv->regmap)) { + ret = PTR_ERR(priv->regmap); + goto disable_regs; + } priv->pdn_gpio = devm_gpiod_get_optional(dev, "pdn", GPIOD_OUT_LOW); if (IS_ERR(priv->pdn_gpio)) { @@ -845,7 +847,7 @@ static int tas571x_i2c_probe(struct i2c_client *client, ret = regmap_write(priv->regmap, TAS571X_OSC_TRIM_REG, 0); if (ret) - return ret; + goto disable_regs; usleep_range(50000, 60000); @@ -861,12 +863,20 @@ static int tas571x_i2c_probe(struct i2c_client *client, */ ret = regmap_update_bits(priv->regmap, TAS571X_MVOL_REG, 1, 0); if (ret) - return ret; + goto disable_regs; } - return devm_snd_soc_register_component(&client->dev, + ret = devm_snd_soc_register_component(&client->dev, &priv->component_driver, &tas571x_dai, 1); + if (ret) + goto disable_regs; + + return ret; + +disable_regs: + regulator_bulk_disable(priv->chip->num_supply_names, priv->supplies); + return ret; } static int tas571x_i2c_remove(struct i2c_client *client) diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index 55112c1bba5e..6cf0f6612bda 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -860,8 +860,7 @@ static int wm8960_hw_params(struct snd_pcm_substream *substream, wm8960->is_stream_in_use[tx] = true; - if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_ON && - !wm8960->is_stream_in_use[!tx]) + if (!wm8960->is_stream_in_use[!tx]) return wm8960_configure_clocking(component); return 0; diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index f2d6f2f81f14..d39d479e2378 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -394,6 +394,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = { .min_ch = 1, .max_ch = 1, .simple_ch_prep_sm = true, + .read_only_wordlength = true, }, { /* COMP */ .num = 2, @@ -401,6 +402,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = { .min_ch = 1, .max_ch = 1, .simple_ch_prep_sm = true, + .read_only_wordlength = true, }, { /* BOOST */ .num = 3, @@ -408,6 +410,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = { .min_ch = 1, .max_ch = 1, .simple_ch_prep_sm = true, + .read_only_wordlength = true, }, { /* VISENSE */ .num = 4, @@ -415,6 +418,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = { .min_ch = 1, .max_ch = 1, .simple_ch_prep_sm = true, + .read_only_wordlength = true, } }; diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c index bcedec6c6117..7d85bd5aff9f 100644 --- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c @@ -113,14 +113,6 @@ static const struct snd_soc_acpi_adr_device rt1308_1_adr[] = { } }; -static const struct snd_soc_acpi_adr_device rt1308_2_adr[] = { - { - .adr = 0x000210025D130800, - .num_endpoints = 1, - .endpoints = &single_endpoint, - } -}; - static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = { { .adr = 0x000110025D130800, diff --git a/sound/soc/intel/common/soc-acpi-intel-icl-match.c b/sound/soc/intel/common/soc-acpi-intel-icl-match.c index ef8500349f2f..16ec9f382b0f 100644 --- a/sound/soc/intel/common/soc-acpi-intel-icl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-icl-match.c @@ -87,14 +87,6 @@ static const struct snd_soc_acpi_adr_device rt1308_1_adr[] = { } }; -static const struct snd_soc_acpi_adr_device rt1308_2_adr[] = { - { - .adr = 0x000210025D130800, - .num_endpoints = 1, - .endpoints = &single_endpoint, - } -}; - static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = { { .adr = 0x000110025D130800, diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c index af46845f4ef2..89f7f64747cd 100644 --- a/sound/soc/meson/axg-card.c +++ b/sound/soc/meson/axg-card.c @@ -338,8 +338,10 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np, if (axg_card_cpu_is_tdm_iface(dai_link->cpus->of_node)) ret = axg_card_parse_tdm(card, np, index); - else if (axg_card_cpu_is_codec(dai_link->cpus->of_node)) + else if (axg_card_cpu_is_codec(dai_link->cpus->of_node)) { dai_link->params = &codec_params; + dai_link->no_pcm = 0; /* link is not a DPCM BE */ + } return ret; } diff --git a/sound/soc/meson/gx-card.c b/sound/soc/meson/gx-card.c index 7b01dcb73e5e..4abf7efb7eac 100644 --- a/sound/soc/meson/gx-card.c +++ b/sound/soc/meson/gx-card.c @@ -108,8 +108,10 @@ static int gx_card_add_link(struct snd_soc_card *card, struct device_node *np, ret = gx_card_parse_i2s(card, np, index); /* Or apply codec to codec params if necessary */ - else if (gx_card_cpu_identify(dai_link->cpus, "CODEC CTRL")) + else if (gx_card_cpu_identify(dai_link->cpus, "CODEC CTRL")) { dai_link->params = &codec_params; + dai_link->no_pcm = 0; /* link is not a DPCM BE */ + } return ret; } diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c index d55e3ad96716..287ad2aa27f3 100644 --- a/sound/soc/qcom/apq8096.c +++ b/sound/soc/qcom/apq8096.c @@ -116,10 +116,8 @@ static int apq8096_platform_probe(struct platform_device *pdev) card->dev = dev; dev_set_drvdata(dev, card); ret = qcom_snd_parse_of(card); - if (ret) { - dev_err(dev, "Error parsing OF data\n"); + if (ret) goto err; - } apq8096_add_be_ops(card); ret = snd_soc_register_card(card); diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c index c1a7624eaf17..2a5302f1db98 100644 --- a/sound/soc/qcom/qdsp6/q6afe-dai.c +++ b/sound/soc/qcom/qdsp6/q6afe-dai.c @@ -902,6 +902,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -917,6 +919,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -931,6 +935,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { .rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -946,6 +952,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -960,6 +968,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { .rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -975,6 +985,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -989,6 +1001,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { .rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, @@ -1004,6 +1018,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = { SNDRV_PCM_RATE_16000, .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .channels_min = 1, + .channels_max = 8, .rate_min = 8000, .rate_max = 48000, }, diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index b2de65c7f95c..68e9388ff46f 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -559,10 +559,8 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev) card->dev = dev; dev_set_drvdata(dev, card); ret = qcom_snd_parse_of(card); - if (ret) { - dev_err(dev, "Error parsing OF data\n"); + if (ret) goto parse_dt_fail; - } data->card = card; snd_soc_card_set_drvdata(card, data); diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c index 358887848293..5e95c30fb2ba 100644 --- a/sound/soc/samsung/s3c-i2s-v2.c +++ b/sound/soc/samsung/s3c-i2s-v2.c @@ -656,60 +656,6 @@ void s3c_i2sv2_cleanup(struct snd_soc_dai *dai, } EXPORT_SYMBOL_GPL(s3c_i2sv2_cleanup); -#ifdef CONFIG_PM -static int s3c2412_i2s_suspend(struct snd_soc_dai *dai) -{ - struct s3c_i2sv2_info *i2s = to_info(dai); - u32 iismod; - - if (dai->active) { - i2s->suspend_iismod = readl(i2s->regs + S3C2412_IISMOD); - i2s->suspend_iiscon = readl(i2s->regs + S3C2412_IISCON); - i2s->suspend_iispsr = readl(i2s->regs + S3C2412_IISPSR); - - /* some basic suspend checks */ - - iismod = readl(i2s->regs + S3C2412_IISMOD); - - if (iismod & S3C2412_IISCON_RXDMA_ACTIVE) - pr_warn("%s: RXDMA active?\n", __func__); - - if (iismod & S3C2412_IISCON_TXDMA_ACTIVE) - pr_warn("%s: TXDMA active?\n", __func__); - - if (iismod & S3C2412_IISCON_IIS_ACTIVE) - pr_warn("%s: IIS active\n", __func__); - } - - return 0; -} - -static int s3c2412_i2s_resume(struct snd_soc_dai *dai) -{ - struct s3c_i2sv2_info *i2s = to_info(dai); - - pr_info("dai_active %d, IISMOD %08x, IISCON %08x\n", - dai->active, i2s->suspend_iismod, i2s->suspend_iiscon); - - if (dai->active) { - writel(i2s->suspend_iiscon, i2s->regs + S3C2412_IISCON); - writel(i2s->suspend_iismod, i2s->regs + S3C2412_IISMOD); - writel(i2s->suspend_iispsr, i2s->regs + S3C2412_IISPSR); - - writel(S3C2412_IISFIC_RXFLUSH | S3C2412_IISFIC_TXFLUSH, - i2s->regs + S3C2412_IISFIC); - - ndelay(250); - writel(0x0, i2s->regs + S3C2412_IISFIC); - } - - return 0; -} -#else -#define s3c2412_i2s_suspend NULL -#define s3c2412_i2s_resume NULL -#endif - int s3c_i2sv2_register_component(struct device *dev, int id, const struct snd_soc_component_driver *cmp_drv, struct snd_soc_dai_driver *dai_drv) @@ -727,9 +673,6 @@ int s3c_i2sv2_register_component(struct device *dev, int id, if (!ops->delay) ops->delay = s3c2412_i2s_delay; - dai_drv->suspend = s3c2412_i2s_suspend; - dai_drv->resume = s3c2412_i2s_resume; - return devm_snd_soc_register_component(dev, cmp_drv, dai_drv, 1); } EXPORT_SYMBOL_GPL(s3c_i2sv2_register_component); diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c index 787a3f6e9f24..b35d828c1cfe 100644 --- a/sound/soc/samsung/s3c2412-i2s.c +++ b/sound/soc/samsung/s3c2412-i2s.c @@ -117,6 +117,60 @@ static int s3c2412_i2s_hw_params(struct snd_pcm_substream *substream, return 0; } +#ifdef CONFIG_PM +static int s3c2412_i2s_suspend(struct snd_soc_component *component) +{ + struct s3c_i2sv2_info *i2s = snd_soc_component_get_drvdata(component); + u32 iismod; + + if (component->active) { + i2s->suspend_iismod = readl(i2s->regs + S3C2412_IISMOD); + i2s->suspend_iiscon = readl(i2s->regs + S3C2412_IISCON); + i2s->suspend_iispsr = readl(i2s->regs + S3C2412_IISPSR); + + /* some basic suspend checks */ + + iismod = readl(i2s->regs + S3C2412_IISMOD); + + if (iismod & S3C2412_IISCON_RXDMA_ACTIVE) + pr_warn("%s: RXDMA active?\n", __func__); + + if (iismod & S3C2412_IISCON_TXDMA_ACTIVE) + pr_warn("%s: TXDMA active?\n", __func__); + + if (iismod & S3C2412_IISCON_IIS_ACTIVE) + pr_warn("%s: IIS active\n", __func__); + } + + return 0; +} + +static int s3c2412_i2s_resume(struct snd_soc_component *component) +{ + struct s3c_i2sv2_info *i2s = snd_soc_component_get_drvdata(component); + + pr_info("component_active %d, IISMOD %08x, IISCON %08x\n", + component->active, i2s->suspend_iismod, i2s->suspend_iiscon); + + if (component->active) { + writel(i2s->suspend_iiscon, i2s->regs + S3C2412_IISCON); + writel(i2s->suspend_iismod, i2s->regs + S3C2412_IISMOD); + writel(i2s->suspend_iispsr, i2s->regs + S3C2412_IISPSR); + + writel(S3C2412_IISFIC_RXFLUSH | S3C2412_IISFIC_TXFLUSH, + i2s->regs + S3C2412_IISFIC); + + ndelay(250); + writel(0x0, i2s->regs + S3C2412_IISFIC); + } + + return 0; +} +#else +#define s3c2412_i2s_suspend NULL +#define s3c2412_i2s_resume NULL +#endif + #define S3C2412_I2S_RATES \ (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_11025 | SNDRV_PCM_RATE_16000 | \ SNDRV_PCM_RATE_22050 | SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 | \ @@ -146,6 +200,8 @@ static struct snd_soc_dai_driver s3c2412_i2s_dai = { static const struct snd_soc_component_driver s3c2412_i2s_component = { .name = "s3c2412-i2s", + .suspend = s3c2412_i2s_suspend, + .resume = s3c2412_i2s_resume, }; static int s3c2412_iis_dev_probe(struct platform_device *pdev) diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index fc5d089868df..4a7d3413917f 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -594,10 +594,16 @@ static int rsnd_ssi_stop(struct rsnd_mod *mod, * Capture: It might not receave data. Do nothing */ if (rsnd_io_is_play(io)) { - rsnd_mod_write(mod, SSICR, cr | EN); + rsnd_mod_write(mod, SSICR, cr | ssi->cr_en); rsnd_ssi_status_check(mod, DIRQ); } + /* In multi-SSI mode, stop is performed by setting ssi0129 in + * SSI_CONTROL to 0 (in rsnd_ssio_stop_gen2). Do nothing here. + */ + if (rsnd_ssi_multi_slaves_runtime(io)) + return 0; + /* * disable SSI, * and, wait idle state @@ -737,6 +743,9 @@ static void rsnd_ssi_parent_attach(struct rsnd_mod *mod, if (!rsnd_rdai_is_clk_master(rdai)) return; + if (rsnd_ssi_is_multi_slave(mod, io)) + return; + switch (rsnd_mod_id(mod)) { case 1: case 2: diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c index f35d88211887..9c7c3e7539c9 100644 --- a/sound/soc/sh/rcar/ssiu.c +++ b/sound/soc/sh/rcar/ssiu.c @@ -221,7 +221,7 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod, i; for_each_rsnd_mod_array(i, pos, io, rsnd_ssi_array) { - shift = (i * 4) + 16; + shift = (i * 4) + 20; val = (val & ~(0xF << shift)) | rsnd_mod_id(pos) << shift; } diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c index 8f3cad8db89a..31c41559034b 100644 --- a/sound/soc/soc-dai.c +++ b/sound/soc/soc-dai.c @@ -295,24 +295,17 @@ int snd_soc_dai_startup(struct snd_soc_dai *dai, { int ret = 0; - if (!dai->started[substream->stream] && - dai->driver->ops->startup) + if (dai->driver->ops->startup) ret = dai->driver->ops->startup(substream, dai); - if (ret == 0) - dai->started[substream->stream] = 1; - return ret; } void snd_soc_dai_shutdown(struct snd_soc_dai *dai, struct snd_pcm_substream *substream) { - if (dai->started[substream->stream] && - dai->driver->ops->shutdown) + if (dai->driver->ops->shutdown) dai->driver->ops->shutdown(substream, dai); - - dai->started[substream->stream] = 0; } int snd_soc_dai_prepare(struct snd_soc_dai *dai, diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 679ed60d850e..e2632841b321 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -423,7 +423,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget, memset(&template, 0, sizeof(template)); template.reg = e->reg; - template.mask = e->mask << e->shift_l; + template.mask = e->mask; template.shift = e->shift_l; template.off_val = snd_soc_enum_item_to_val(e, 0); template.on_val = template.off_val; @@ -546,8 +546,22 @@ static bool dapm_kcontrol_set_value(const struct snd_kcontrol *kcontrol, if (data->value == value) return false; - if (data->widget) - data->widget->on_val = value; + if (data->widget) { + switch (dapm_kcontrol_get_wlist(kcontrol)->widgets[0]->id) { + case snd_soc_dapm_switch: + case snd_soc_dapm_mixer: + case snd_soc_dapm_mixer_named_ctl: + data->widget->on_val = value & data->widget->mask; + break; + case snd_soc_dapm_demux: + case snd_soc_dapm_mux: + data->widget->on_val = value >> data->widget->shift; + break; + default: + data->widget->on_val = value; + break; + } + } data->value = value; @@ -4165,6 +4179,8 @@ snd_soc_dapm_new_dai(struct snd_soc_card *card, w = snd_soc_dapm_new_control_unlocked(&card->dapm, &template); if (IS_ERR(w)) { ret = PTR_ERR(w); + dev_err(rtd->dev, "ASoC: Failed to create %s widget: %d\n", + link_name, ret); goto outfree_kcontrol_news; } @@ -4283,52 +4299,58 @@ int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card) return 0; } -static void dapm_add_valid_dai_widget(struct snd_soc_card *card, - struct snd_soc_pcm_runtime *rtd, - struct snd_soc_dai *codec_dai, - struct snd_soc_dai *cpu_dai) +static void dapm_connect_dai_routes(struct snd_soc_dapm_context *dapm, + struct snd_soc_dai *src_dai, + struct snd_soc_dapm_widget *src, + struct snd_soc_dapm_widget *dai, + struct snd_soc_dai *sink_dai, + struct snd_soc_dapm_widget *sink) { - struct snd_soc_dapm_widget *playback = NULL, *capture = NULL; - struct snd_soc_dapm_widget *codec, *playback_cpu, *capture_cpu; + dev_dbg(dapm->dev, "connected DAI link %s:%s -> %s:%s\n", + src_dai->component->name, src->name, + sink_dai->component->name, sink->name); + + if (dai) { + snd_soc_dapm_add_path(dapm, src, dai, NULL, NULL); + src = dai; + } + + snd_soc_dapm_add_path(dapm, src, sink, NULL, NULL); +} + +static void dapm_connect_dai_pair(struct snd_soc_card *card, + struct snd_soc_pcm_runtime *rtd, + struct snd_soc_dai *codec_dai, + struct snd_soc_dai *cpu_dai) +{ + struct snd_soc_dai_link *dai_link = rtd->dai_link; + struct snd_soc_dapm_widget *dai, *codec, *playback_cpu, *capture_cpu; struct snd_pcm_substream *substream; struct snd_pcm_str *streams = rtd->pcm->streams; - if (rtd->dai_link->params) { + if (dai_link->params) { playback_cpu = cpu_dai->capture_widget; capture_cpu = cpu_dai->playback_widget; } else { - playback = cpu_dai->playback_widget; - capture = cpu_dai->capture_widget; - playback_cpu = playback; - capture_cpu = capture; + playback_cpu = cpu_dai->playback_widget; + capture_cpu = cpu_dai->capture_widget; } /* connect BE DAI playback if widgets are valid */ codec = codec_dai->playback_widget; if (playback_cpu && codec) { - if (!playback) { + if (dai_link->params && !dai_link->playback_widget) { substream = streams[SNDRV_PCM_STREAM_PLAYBACK].substream; - playback = snd_soc_dapm_new_dai(card, substream, - "playback"); - if (IS_ERR(playback)) { - dev_err(rtd->dev, - "ASoC: Failed to create DAI %s: %ld\n", - codec_dai->name, - PTR_ERR(playback)); + dai = snd_soc_dapm_new_dai(card, substream, "playback"); + if (IS_ERR(dai)) goto capture; - } - - snd_soc_dapm_add_path(&card->dapm, playback_cpu, - playback, NULL, NULL); + dai_link->playback_widget = dai; } - dev_dbg(rtd->dev, "connected DAI link %s:%s -> %s:%s\n", - cpu_dai->component->name, playback_cpu->name, - codec_dai->component->name, codec->name); - - snd_soc_dapm_add_path(&card->dapm, playback, codec, - NULL, NULL); + dapm_connect_dai_routes(&card->dapm, cpu_dai, playback_cpu, + dai_link->playback_widget, + codec_dai, codec); } capture: @@ -4336,50 +4358,18 @@ capture: codec = codec_dai->capture_widget; if (codec && capture_cpu) { - if (!capture) { + if (dai_link->params && !dai_link->capture_widget) { substream = streams[SNDRV_PCM_STREAM_CAPTURE].substream; - capture = snd_soc_dapm_new_dai(card, substream, - "capture"); - if (IS_ERR(capture)) { - dev_err(rtd->dev, - "ASoC: Failed to create DAI %s: %ld\n", - codec_dai->name, - PTR_ERR(capture)); + dai = snd_soc_dapm_new_dai(card, substream, "capture"); + if (IS_ERR(dai)) return; - } - - snd_soc_dapm_add_path(&card->dapm, capture, - capture_cpu, NULL, NULL); + dai_link->capture_widget = dai; } - dev_dbg(rtd->dev, "connected DAI link %s:%s -> %s:%s\n", - codec_dai->component->name, codec->name, - cpu_dai->component->name, capture_cpu->name); - - snd_soc_dapm_add_path(&card->dapm, codec, capture, - NULL, NULL); - } -} - -static void dapm_connect_dai_link_widgets(struct snd_soc_card *card, - struct snd_soc_pcm_runtime *rtd) -{ - struct snd_soc_dai *codec_dai; - int i; - - if (rtd->num_cpus == 1) { - for_each_rtd_codec_dais(rtd, i, codec_dai) - dapm_add_valid_dai_widget(card, rtd, codec_dai, - rtd->cpu_dais[0]); - } else if (rtd->num_codecs == rtd->num_cpus) { - for_each_rtd_codec_dais(rtd, i, codec_dai) - dapm_add_valid_dai_widget(card, rtd, codec_dai, - rtd->cpu_dais[i]); - } else { - dev_err(card->dev, - "N cpus to M codecs link is not supported yet\n"); + dapm_connect_dai_routes(&card->dapm, codec_dai, codec, + dai_link->capture_widget, + cpu_dai, capture_cpu); } - } static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream, @@ -4422,6 +4412,8 @@ static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream, void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card) { struct snd_soc_pcm_runtime *rtd; + struct snd_soc_dai *codec_dai; + int i; /* for each BE DAI link... */ for_each_card_rtds(card, rtd) { @@ -4432,7 +4424,18 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card) if (rtd->dai_link->dynamic) continue; - dapm_connect_dai_link_widgets(card, rtd); + if (rtd->num_cpus == 1) { + for_each_rtd_codec_dais(rtd, i, codec_dai) + dapm_connect_dai_pair(card, rtd, codec_dai, + rtd->cpu_dais[0]); + } else if (rtd->num_codecs == rtd->num_cpus) { + for_each_rtd_codec_dais(rtd, i, codec_dai) + dapm_connect_dai_pair(card, rtd, codec_dai, + rtd->cpu_dais[i]); + } else { + dev_err(card->dev, + "N cpus to M codecs link is not supported yet\n"); + } } } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 289aebc15529..1f302de44052 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2911,8 +2911,17 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num) int i; if (rtd->dai_link->dynamic || rtd->dai_link->no_pcm) { - playback = rtd->dai_link->dpcm_playback; - capture = rtd->dai_link->dpcm_capture; + cpu_dai = asoc_rtd_to_cpu(rtd, 0); + if (rtd->num_cpus > 1) { + dev_err(rtd->dev, + "DPCM doesn't support Multi CPU yet\n"); + return -EINVAL; + } + + playback = rtd->dai_link->dpcm_playback && + snd_soc_dai_stream_valid(cpu_dai, SNDRV_PCM_STREAM_PLAYBACK); + capture = rtd->dai_link->dpcm_capture && + snd_soc_dai_stream_valid(cpu_dai, SNDRV_PCM_STREAM_CAPTURE); } else { /* Adapt stream for codec2codec links */ int cpu_capture = rtd->dai_link->params ? diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 87f75edba3dc..6df3b0d12d87 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -894,7 +894,13 @@ static int soc_tplg_dmixer_create(struct soc_tplg *tplg, unsigned int count, } /* create any TLV data */ - soc_tplg_create_tlv(tplg, &kc, &mc->hdr); + err = soc_tplg_create_tlv(tplg, &kc, &mc->hdr); + if (err < 0) { + dev_err(tplg->dev, "ASoC: failed to create TLV %s\n", + mc->hdr.name); + kfree(sm); + continue; + } /* pass control to driver for optional further init */ err = soc_tplg_init_kcontrol(tplg, &kc, @@ -1118,6 +1124,7 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg, struct snd_soc_tplg_hdr *hdr) { struct snd_soc_tplg_ctl_hdr *control_hdr; + int ret; int i; if (tplg->pass != SOC_TPLG_PASS_MIXER) { @@ -1146,25 +1153,30 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg, case SND_SOC_TPLG_CTL_RANGE: case SND_SOC_TPLG_DAPM_CTL_VOLSW: case SND_SOC_TPLG_DAPM_CTL_PIN: - soc_tplg_dmixer_create(tplg, 1, - le32_to_cpu(hdr->payload_size)); + ret = soc_tplg_dmixer_create(tplg, 1, + le32_to_cpu(hdr->payload_size)); break; case SND_SOC_TPLG_CTL_ENUM: case SND_SOC_TPLG_CTL_ENUM_VALUE: case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE: case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT: case SND_SOC_TPLG_DAPM_CTL_ENUM_VALUE: - soc_tplg_denum_create(tplg, 1, - le32_to_cpu(hdr->payload_size)); + ret = soc_tplg_denum_create(tplg, 1, + le32_to_cpu(hdr->payload_size)); break; case SND_SOC_TPLG_CTL_BYTES: - soc_tplg_dbytes_create(tplg, 1, - le32_to_cpu(hdr->payload_size)); + ret = soc_tplg_dbytes_create(tplg, 1, + le32_to_cpu(hdr->payload_size)); break; default: soc_bind_err(tplg, control_hdr, i); return -EINVAL; } + if (ret < 0) { + dev_err(tplg->dev, "ASoC: invalid control\n"); + return ret; + } + } return 0; @@ -1272,7 +1284,9 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, routes[i]->dobj.index = tplg->index; list_add(&routes[i]->dobj.list, &tplg->comp->dobj_list); - soc_tplg_add_route(tplg, routes[i]); + ret = soc_tplg_add_route(tplg, routes[i]); + if (ret < 0) + break; /* add route, but keep going if some fail */ snd_soc_dapm_add_routes(dapm, routes[i], 1); @@ -1355,7 +1369,13 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create( } /* create any TLV data */ - soc_tplg_create_tlv(tplg, &kc[i], &mc->hdr); + err = soc_tplg_create_tlv(tplg, &kc[i], &mc->hdr); + if (err < 0) { + dev_err(tplg->dev, "ASoC: failed to create TLV %s\n", + mc->hdr.name); + kfree(sm); + continue; + } /* pass control to driver for optional further init */ err = soc_tplg_init_kcontrol(tplg, &kc[i], @@ -1766,10 +1786,13 @@ static int soc_tplg_dapm_complete(struct soc_tplg *tplg) return 0; } -static void set_stream_info(struct snd_soc_pcm_stream *stream, +static int set_stream_info(struct snd_soc_pcm_stream *stream, struct snd_soc_tplg_stream_caps *caps) { stream->stream_name = kstrdup(caps->name, GFP_KERNEL); + if (!stream->stream_name) + return -ENOMEM; + stream->channels_min = le32_to_cpu(caps->channels_min); stream->channels_max = le32_to_cpu(caps->channels_max); stream->rates = le32_to_cpu(caps->rates); @@ -1777,6 +1800,8 @@ static void set_stream_info(struct snd_soc_pcm_stream *stream, stream->rate_max = le32_to_cpu(caps->rate_max); stream->formats = le64_to_cpu(caps->formats); stream->sig_bits = le32_to_cpu(caps->sig_bits); + + return 0; } static void set_dai_flags(struct snd_soc_dai_driver *dai_drv, @@ -1812,20 +1837,29 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, if (dai_drv == NULL) return -ENOMEM; - if (strlen(pcm->dai_name)) + if (strlen(pcm->dai_name)) { dai_drv->name = kstrdup(pcm->dai_name, GFP_KERNEL); + if (!dai_drv->name) { + ret = -ENOMEM; + goto err; + } + } dai_drv->id = le32_to_cpu(pcm->dai_id); if (pcm->playback) { stream = &dai_drv->playback; caps = &pcm->caps[SND_SOC_TPLG_STREAM_PLAYBACK]; - set_stream_info(stream, caps); + ret = set_stream_info(stream, caps); + if (ret < 0) + goto err; } if (pcm->capture) { stream = &dai_drv->capture; caps = &pcm->caps[SND_SOC_TPLG_STREAM_CAPTURE]; - set_stream_info(stream, caps); + ret = set_stream_info(stream, caps); + if (ret < 0) + goto err; } if (pcm->compress) @@ -1835,11 +1869,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, ret = soc_tplg_dai_load(tplg, dai_drv, pcm, NULL); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n"); - kfree(dai_drv->playback.stream_name); - kfree(dai_drv->capture.stream_name); - kfree(dai_drv->name); - kfree(dai_drv); - return ret; + goto err; } dai_drv->dobj.index = tplg->index; @@ -1860,6 +1890,14 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg, return ret; } + return 0; + +err: + kfree(dai_drv->playback.stream_name); + kfree(dai_drv->capture.stream_name); + kfree(dai_drv->name); + kfree(dai_drv); + return ret; } @@ -1916,11 +1954,20 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg, if (strlen(pcm->pcm_name)) { link->name = kstrdup(pcm->pcm_name, GFP_KERNEL); link->stream_name = kstrdup(pcm->pcm_name, GFP_KERNEL); + if (!link->name || !link->stream_name) { + ret = -ENOMEM; + goto err; + } } link->id = le32_to_cpu(pcm->pcm_id); - if (strlen(pcm->dai_name)) + if (strlen(pcm->dai_name)) { link->cpus->dai_name = kstrdup(pcm->dai_name, GFP_KERNEL); + if (!link->cpus->dai_name) { + ret = -ENOMEM; + goto err; + } + } link->codecs->name = "snd-soc-dummy"; link->codecs->dai_name = "snd-soc-dummy-dai"; @@ -2088,7 +2135,9 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg, _pcm = pcm; } else { abi_match = false; - pcm_new_ver(tplg, pcm, &_pcm); + ret = pcm_new_ver(tplg, pcm, &_pcm); + if (ret < 0) + return ret; } /* create the FE DAIs and DAI links */ @@ -2436,13 +2485,17 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg, if (d->playback) { stream = &dai_drv->playback; caps = &d->caps[SND_SOC_TPLG_STREAM_PLAYBACK]; - set_stream_info(stream, caps); + ret = set_stream_info(stream, caps); + if (ret < 0) + goto err; } if (d->capture) { stream = &dai_drv->capture; caps = &d->caps[SND_SOC_TPLG_STREAM_CAPTURE]; - set_stream_info(stream, caps); + ret = set_stream_info(stream, caps); + if (ret < 0) + goto err; } if (d->flag_mask) @@ -2454,10 +2507,15 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg, ret = soc_tplg_dai_load(tplg, dai_drv, NULL, dai); if (ret < 0) { dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n"); - return ret; + goto err; } return 0; + +err: + kfree(dai_drv->playback.stream_name); + kfree(dai_drv->capture.stream_name); + return ret; } /* load physical DAI elements */ @@ -2466,7 +2524,7 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg, { struct snd_soc_tplg_dai *dai; int count; - int i; + int i, ret; count = le32_to_cpu(hdr->count); @@ -2481,7 +2539,12 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg, return -EINVAL; } - soc_tplg_dai_config(tplg, dai); + ret = soc_tplg_dai_config(tplg, dai); + if (ret < 0) { + dev_err(tplg->dev, "ASoC: failed to configure DAI\n"); + return ret; + } + tplg->pos += (sizeof(*dai) + le32_to_cpu(dai->priv.size)); } @@ -2589,7 +2652,7 @@ static int soc_valid_header(struct soc_tplg *tplg, } /* big endian firmware objects not supported atm */ - if (hdr->magic == SOC_TPLG_MAGIC_BIG_ENDIAN) { + if (le32_to_cpu(hdr->magic) == SOC_TPLG_MAGIC_BIG_ENDIAN) { dev_err(tplg->dev, "ASoC: pass %d big endian not supported header got %x at offset 0x%lx size 0x%zx.\n", tplg->pass, hdr->magic, diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c index 6c23c5769330..a32a3ef78ec5 100644 --- a/sound/soc/sof/intel/bdw.c +++ b/sound/soc/sof/intel/bdw.c @@ -567,9 +567,25 @@ static void bdw_set_mach_params(const struct snd_soc_acpi_mach *mach, static struct snd_soc_dai_driver bdw_dai[] = { { .name = "ssp0-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, { .name = "ssp1-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, }; diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c index f84391294f12..29fd1d86156c 100644 --- a/sound/soc/sof/intel/byt.c +++ b/sound/soc/sof/intel/byt.c @@ -459,21 +459,69 @@ static void byt_set_mach_params(const struct snd_soc_acpi_mach *mach, static struct snd_soc_dai_driver byt_dai[] = { { .name = "ssp0-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, { .name = "ssp1-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, { .name = "ssp2-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + } }, { .name = "ssp3-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, { .name = "ssp4-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, { .name = "ssp5-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, }; diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index 0d0c9afd8791..41f01c3e639e 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -837,7 +837,7 @@ static int stm32_sai_set_config(struct snd_soc_dai *cpu_dai, cr1 = SAI_XCR1_DS_SET(SAI_DATASIZE_32); break; default: - dev_err(cpu_dai->dev, "Data format not supported"); + dev_err(cpu_dai->dev, "Data format not supported\n"); return -EINVAL; } @@ -1547,6 +1547,9 @@ static int stm32_sai_sub_probe(struct platform_device *pdev) return ret; } + if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) + conf = &stm32_sai_pcm_config_spdif; + ret = snd_dmaengine_pcm_register(&pdev->dev, conf, 0); if (ret) { if (ret != -EPROBE_DEFER) @@ -1556,15 +1559,10 @@ static int stm32_sai_sub_probe(struct platform_device *pdev) ret = snd_soc_register_component(&pdev->dev, &stm32_component, &sai->cpu_dai_drv, 1); - if (ret) { + if (ret) snd_dmaengine_pcm_unregister(&pdev->dev); - return ret; - } - - if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) - conf = &stm32_sai_pcm_config_spdif; - return 0; + return ret; } static int stm32_sai_sub_remove(struct platform_device *pdev) diff --git a/sound/usb/format.c b/sound/usb/format.c index 50e1874c847c..5ffb457cc88c 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -278,6 +278,52 @@ static bool s1810c_valid_sample_rate(struct audioformat *fp, } /* + * Many Focusrite devices supports a limited set of sampling rates per + * altsetting. Maximum rate is exposed in the last 4 bytes of Format Type + * descriptor which has a non-standard bLength = 10. + */ +static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip, + struct audioformat *fp, + unsigned int rate) +{ + struct usb_interface *iface; + struct usb_host_interface *alts; + unsigned char *fmt; + unsigned int max_rate; + + iface = usb_ifnum_to_if(chip->dev, fp->iface); + if (!iface) + return true; + + alts = &iface->altsetting[fp->altset_idx]; + fmt = snd_usb_find_csint_desc(alts->extra, alts->extralen, + NULL, UAC_FORMAT_TYPE); + if (!fmt) + return true; + + if (fmt[0] == 10) { /* bLength */ + max_rate = combine_quad(&fmt[6]); + + /* Validate max rate */ + if (max_rate != 48000 && + max_rate != 96000 && + max_rate != 192000 && + max_rate != 384000) { + + usb_audio_info(chip, + "%u:%d : unexpected max rate: %u\n", + fp->iface, fp->altsetting, max_rate); + + return true; + } + + return rate <= max_rate; + } + + return true; +} + +/* * Helper function to walk the array of sample rate triplets reported by * the device. The problem is that we need to parse whole array first to * get to know how many sample rates we have to expect. @@ -319,6 +365,11 @@ static int parse_uac2_sample_rate_range(struct snd_usb_audio *chip, !s1810c_valid_sample_rate(fp, rate)) goto skip_rate; + /* Filter out invalid rates on Focusrite devices */ + if (USB_ID_VENDOR(chip->usb_id) == 0x1235 && + !focusrite_valid_sample_rate(chip, fp, rate)) + goto skip_rate; + if (fp->rate_table) fp->rate_table[nr_rates] = rate; if (!fp->rate_min || rate < fp->rate_min) diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 721d12130d0c..a88d7854513b 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1457,7 +1457,7 @@ error: usb_audio_err(chip, "cannot get connectors status: req = %#x, wValue = %#x, wIndex = %#x, type = %d\n", UAC_GET_CUR, validx, idx, cval->val_type); - return ret; + return filter_error(cval, ret); } ucontrol->value.integer.value[0] = val; @@ -1771,10 +1771,16 @@ static void get_connector_control_name(struct usb_mixer_interface *mixer, /* Build a mixer control for a UAC connector control (jack-detect) */ static void build_connector_control(struct usb_mixer_interface *mixer, + const struct usbmix_name_map *imap, struct usb_audio_term *term, bool is_input) { struct snd_kcontrol *kctl; struct usb_mixer_elem_info *cval; + const struct usbmix_name_map *map; + + map = find_map(imap, term->id, 0); + if (check_ignored_ctl(map)) + return; cval = kzalloc(sizeof(*cval), GFP_KERNEL); if (!cval) @@ -1805,8 +1811,12 @@ static void build_connector_control(struct usb_mixer_interface *mixer, usb_mixer_elem_info_free(cval); return; } - get_connector_control_name(mixer, term, is_input, kctl->id.name, - sizeof(kctl->id.name)); + + if (check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name))) + strlcat(kctl->id.name, " Jack", sizeof(kctl->id.name)); + else + get_connector_control_name(mixer, term, is_input, kctl->id.name, + sizeof(kctl->id.name)); kctl->private_free = snd_usb_mixer_elem_free; snd_usb_mixer_add_control(&cval->head, kctl); } @@ -2109,8 +2119,9 @@ static int parse_audio_input_terminal(struct mixer_build *state, int unitid, check_input_term(state, term_id, &iterm); /* Check for jack detection. */ - if (uac_v2v3_control_is_readable(bmctls, control)) - build_connector_control(state->mixer, &iterm, true); + if ((iterm.type & 0xff00) != 0x0100 && + uac_v2v3_control_is_readable(bmctls, control)) + build_connector_control(state->mixer, state->map, &iterm, true); return 0; } @@ -3071,13 +3082,13 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer, memset(&iterm, 0, sizeof(iterm)); iterm.id = UAC3_BADD_IT_ID4; iterm.type = UAC_BIDIR_TERMINAL_HEADSET; - build_connector_control(mixer, &iterm, true); + build_connector_control(mixer, map->map, &iterm, true); /* Output Term - Insertion control */ memset(&oterm, 0, sizeof(oterm)); oterm.id = UAC3_BADD_OT_ID3; oterm.type = UAC_BIDIR_TERMINAL_HEADSET; - build_connector_control(mixer, &oterm, false); + build_connector_control(mixer, map->map, &oterm, false); } return 0; @@ -3106,7 +3117,8 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer) if (map->id == state.chip->usb_id) { state.map = map->map; state.selector_map = map->selector_map; - mixer->ignore_ctl_error = map->ignore_ctl_error; + mixer->connector_map = map->connector_map; + mixer->ignore_ctl_error |= map->ignore_ctl_error; break; } } @@ -3149,10 +3161,11 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer) if (err < 0 && err != -EINVAL) return err; - if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls), + if ((state.oterm.type & 0xff00) != 0x0100 && + uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls), UAC2_TE_CONNECTOR)) { - build_connector_control(state.mixer, &state.oterm, - false); + build_connector_control(state.mixer, state.map, + &state.oterm, false); } } else { /* UAC_VERSION_3 */ struct uac3_output_terminal_descriptor *desc = p; @@ -3174,10 +3187,11 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer) if (err < 0 && err != -EINVAL) return err; - if (uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls), + if ((state.oterm.type & 0xff00) != 0x0100 && + uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls), UAC3_TE_INSERTION)) { - build_connector_control(state.mixer, &state.oterm, - false); + build_connector_control(state.mixer, state.map, + &state.oterm, false); } } } @@ -3185,10 +3199,32 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer) return 0; } +static int delegate_notify(struct usb_mixer_interface *mixer, int unitid, + u8 *control, u8 *channel) +{ + const struct usbmix_connector_map *map = mixer->connector_map; + + if (!map) + return unitid; + + for (; map->id; map++) { + if (map->id == unitid) { + if (control && map->control) + *control = map->control; + if (channel && map->channel) + *channel = map->channel; + return map->delegated_id; + } + } + return unitid; +} + void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid) { struct usb_mixer_elem_list *list; + unitid = delegate_notify(mixer, unitid, NULL, NULL); + for_each_mixer_elem(list, mixer, unitid) { struct usb_mixer_elem_info *info = mixer_elem_list_to_info(list); @@ -3258,6 +3294,8 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer, return; } + unitid = delegate_notify(mixer, unitid, &control, &channel); + for_each_mixer_elem(list, mixer, unitid) count++; diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 65d6d08c96f5..41ec9dc4139b 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -6,6 +6,13 @@ struct media_mixer_ctl; +struct usbmix_connector_map { + u8 id; + u8 delegated_id; + u8 control; + u8 channel; +}; + struct usb_mixer_interface { struct snd_usb_audio *chip; struct usb_host_interface *hostif; @@ -18,6 +25,9 @@ struct usb_mixer_interface { /* the usb audio specification version this interface complies to */ int protocol; + /* optional connector delegation map */ + const struct usbmix_connector_map *connector_map; + /* Sound Blaster remote control stuff */ const struct rc_config *rc_cfg; u32 rc_code; diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 72b575c34860..0260c750e156 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -27,6 +27,7 @@ struct usbmix_ctl_map { u32 id; const struct usbmix_name_map *map; const struct usbmix_selector_map *selector_map; + const struct usbmix_connector_map *connector_map; int ignore_ctl_error; }; @@ -360,13 +361,42 @@ static const struct usbmix_name_map corsair_virtuoso_map[] = { }; /* Some mobos shipped with a dummy HD-audio show the invalid GET_MIN/GET_MAX - * response for Input Gain Pad (id=19, control=12). Skip it. + * response for Input Gain Pad (id=19, control=12) and the connector status + * for SPDIF terminal (id=18). Skip them. */ static const struct usbmix_name_map asus_rog_map[] = { + { 18, NULL }, /* OT, connector control */ { 19, NULL, 12 }, /* FU, Input Gain Pad */ {} }; +/* TRX40 mobos with Realtek ALC1220-VB */ +static const struct usbmix_name_map trx40_mobo_map[] = { + { 18, NULL }, /* OT, IEC958 - broken response, disabled */ + { 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */ + { 16, "Speaker" }, /* OT */ + { 22, "Speaker Playback" }, /* FU */ + { 7, "Line" }, /* IT */ + { 19, "Line Capture" }, /* FU */ + { 17, "Front Headphone" }, /* OT */ + { 23, "Front Headphone Playback" }, /* FU */ + { 8, "Mic" }, /* IT */ + { 20, "Mic Capture" }, /* FU */ + { 9, "Front Mic" }, /* IT */ + { 21, "Front Mic Capture" }, /* FU */ + { 24, "IEC958 Playback" }, /* FU */ + {} +}; + +static const struct usbmix_connector_map trx40_mobo_connector_map[] = { + { 10, 16 }, /* (Back) Speaker */ + { 11, 17 }, /* Front Headphone */ + { 13, 7 }, /* Line */ + { 14, 8 }, /* Mic */ + { 15, 9 }, /* Front Mic */ + {} +}; + /* * Control map entries */ @@ -498,7 +528,8 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { }, { /* Gigabyte TRX40 Aorus Pro WiFi */ .id = USB_ID(0x0414, 0xa002), - .map = asus_rog_map, + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, }, { /* ASUS ROG Zenith II */ .id = USB_ID(0x0b05, 0x1916), @@ -510,11 +541,13 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { }, { /* MSI TRX40 Creator */ .id = USB_ID(0x0db0, 0x0d64), - .map = asus_rog_map, + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, }, { /* MSI TRX40 */ .id = USB_ID(0x0db0, 0x543d), - .map = asus_rog_map, + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, }, { 0 } /* terminator */ }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 02b036b2aefb..a5f65a9a0254 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -1509,11 +1509,15 @@ static int snd_microii_spdif_default_get(struct snd_kcontrol *kcontrol, /* use known values for that card: interface#1 altsetting#1 */ iface = usb_ifnum_to_if(chip->dev, 1); - if (!iface || iface->num_altsetting < 2) - return -EINVAL; + if (!iface || iface->num_altsetting < 2) { + err = -EINVAL; + goto end; + } alts = &iface->altsetting[1]; - if (get_iface_desc(alts)->bNumEndpoints < 1) - return -EINVAL; + if (get_iface_desc(alts)->bNumEndpoints < 1) { + err = -EINVAL; + goto end; + } ep = get_endpoint(alts, 0)->bEndpointAddress; err = snd_usb_ctl_msg(chip->dev, diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index e009d584e7d0..a1df4c5b4f8c 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2756,90 +2756,6 @@ YAMAHA_DEVICE(0x7010, "UB99"), .type = QUIRK_MIDI_NOVATION } }, -{ - /* - * Focusrite Scarlett Solo 2nd generation - * Reports that playback should use Synch: Synchronous - * while still providing a feedback endpoint. Synchronous causes - * snapping on some sample rates. - * Force it to use Synch: Asynchronous. - */ - USB_DEVICE(0x1235, 0x8205), - .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_COMPOSITE, - .data = (const struct snd_usb_audio_quirk[]) { - { - .ifnum = 1, - .type = QUIRK_AUDIO_FIXED_ENDPOINT, - .data = & (const struct audioformat) { - .formats = SNDRV_PCM_FMTBIT_S32_LE, - .channels = 2, - .iface = 1, - .altsetting = 1, - .altset_idx = 1, - .attributes = 0, - .endpoint = 0x01, - .ep_attr = USB_ENDPOINT_XFER_ISOC | - USB_ENDPOINT_SYNC_ASYNC, - .protocol = UAC_VERSION_2, - .rates = SNDRV_PCM_RATE_44100 | - SNDRV_PCM_RATE_48000 | - SNDRV_PCM_RATE_88200 | - SNDRV_PCM_RATE_96000 | - SNDRV_PCM_RATE_176400 | - SNDRV_PCM_RATE_192000, - .rate_min = 44100, - .rate_max = 192000, - .nr_rates = 6, - .rate_table = (unsigned int[]) { - 44100, 48000, 88200, - 96000, 176400, 192000 - }, - .clock = 41 - } - }, - { - .ifnum = 2, - .type = QUIRK_AUDIO_FIXED_ENDPOINT, - .data = & (const struct audioformat) { - .formats = SNDRV_PCM_FMTBIT_S32_LE, - .channels = 2, - .iface = 2, - .altsetting = 1, - .altset_idx = 1, - .attributes = 0, - .endpoint = 0x82, - .ep_attr = USB_ENDPOINT_XFER_ISOC | - USB_ENDPOINT_SYNC_ASYNC | - USB_ENDPOINT_USAGE_IMPLICIT_FB, - .protocol = UAC_VERSION_2, - .rates = SNDRV_PCM_RATE_44100 | - SNDRV_PCM_RATE_48000 | - SNDRV_PCM_RATE_88200 | - SNDRV_PCM_RATE_96000 | - SNDRV_PCM_RATE_176400 | - SNDRV_PCM_RATE_192000, - .rate_min = 44100, - .rate_max = 192000, - .nr_rates = 6, - .rate_table = (unsigned int[]) { - 44100, 48000, 88200, - 96000, 176400, 192000 - }, - .clock = 41 - } - }, - { - .ifnum = 3, - .type = QUIRK_IGNORE_INTERFACE - }, - { - .ifnum = -1 - } - } - } -}, /* Access Music devices */ { @@ -3635,4 +3551,18 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), } }, +#define ALC1220_VB_DESKTOP(vend, prod) { \ + USB_DEVICE(vend, prod), \ + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { \ + .vendor_name = "Realtek", \ + .product_name = "ALC1220-VB-DT", \ + .profile_name = "Realtek-ALC1220-VB-Desktop", \ + .ifnum = QUIRK_NO_INTERFACE \ + } \ +} +ALC1220_VB_DESKTOP(0x0414, 0xa002), /* Gigabyte TRX40 Aorus Pro WiFi */ +ALC1220_VB_DESKTOP(0x0db0, 0x0d64), /* MSI TRX40 Creator */ +ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */ +#undef ALC1220_VB_DESKTOP + #undef USB_DEVICE_VENDOR_SPEC diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index a8ece1701068..351ba214a9d3 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1806,6 +1806,20 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip, */ fp->attributes &= ~UAC_EP_CS_ATTR_FILL_MAX; break; + case USB_ID(0x1235, 0x8200): /* Focusrite Scarlett 2i4 2nd gen */ + case USB_ID(0x1235, 0x8202): /* Focusrite Scarlett 2i2 2nd gen */ + case USB_ID(0x1235, 0x8205): /* Focusrite Scarlett Solo 2nd gen */ + /* + * Reports that playback should use Synch: Synchronous + * while still providing a feedback endpoint. + * Synchronous causes snapping on some sample rates. + * Force it to use Synch: Asynchronous. + */ + if (stream == SNDRV_PCM_STREAM_PLAYBACK) { + fp->ep_attr &= ~USB_ENDPOINT_SYNCTYPE; + fp->ep_attr |= USB_ENDPOINT_SYNC_ASYNC; + } + break; } } diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c index 37d290fe9d43..ecaf41265dcd 100644 --- a/sound/usb/usx2y/usbusx2yaudio.c +++ b/sound/usb/usx2y/usbusx2yaudio.c @@ -681,6 +681,8 @@ static int usX2Y_rate_set(struct usX2Ydev *usX2Y, int rate) us->submitted = 2*NOOF_SETRATE_URBS; for (i = 0; i < NOOF_SETRATE_URBS; ++i) { struct urb *urb = us->urb[i]; + if (!urb) + continue; if (urb->status) { if (!err) err = -ENODEV; diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index f3327cb56edf..db189945e9b0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -217,7 +217,7 @@ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ #define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ @@ -285,6 +285,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -299,6 +300,7 @@ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ @@ -367,6 +369,7 @@ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index d5e517d1c3dd..12c9684d59ba 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -41,6 +41,10 @@ /* Intel MSRs. Some also available on other CPUs */ +#define MSR_TEST_CTRL 0x00000033 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) + #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS BIT(0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ @@ -70,6 +74,11 @@ */ #define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U) +/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */ +#define MSR_IA32_CORE_CAPS 0x000000cf +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT 5 +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT) + #define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) #define NHM_C1_AUTO_DEMOTE (1UL << 26) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index bcaf55b59498..41a1346934a1 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -15,7 +15,6 @@ #include <linux/hashtable.h> #include <sys/types.h> #include <sys/stat.h> -#include <unistd.h> #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index f8113b3646f5..0e5f0236cc76 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -17,7 +17,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> -#include <unistd.h> #include <bpf/btf.h> #include "bpf/libbpf_internal.h" diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index f7f5885aa3ba..e7e7eee9f172 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -15,7 +15,6 @@ #include <stdio.h> #include <stdarg.h> #include <stdint.h> -#include <stdio.h> #include <stdlib.h> #include <assert.h> #include <unistd.h> diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 2a7befbd11ad..e17738479edc 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -479,6 +479,7 @@ static int do_unregister(int argc, char **argv) static int do_register(int argc, char **argv) { + struct bpf_object_load_attr load_attr = {}; const struct bpf_map_def *def; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); @@ -499,7 +500,12 @@ static int do_register(int argc, char **argv) set_max_rlimit(); - if (bpf_object__load(obj)) { + load_attr.obj = obj; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + load_attr.log_level = 1 + 2 + 4; + + if (bpf_object__load_xattr(&load_attr)) { bpf_object__close(obj); return -1; } @@ -591,6 +597,8 @@ int do_struct_ops(int argc, char **argv) err = cmd_select(cmds, argc, argv, do_help); - btf__free(btf_vmlinux); + if (!IS_ERR(btf_vmlinux)) + btf__free(btf_vmlinux); + return err; } diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 39edd68afa8e..8a6f82e56a24 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -8,7 +8,7 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL) LIBBPF_SRC := $(abspath ../../lib/bpf) BPFOBJ := $(OUTPUT)/libbpf.a BPF_INCLUDE := $(OUTPUT) -INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib) +INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib) CFLAGS := -g -Wall # Try to detect best kernel BTF source diff --git a/tools/build/feature/test-sync-compare-and-swap.c b/tools/build/feature/test-sync-compare-and-swap.c index 1e38d1930a97..3bc6b0768a53 100644 --- a/tools/build/feature/test-sync-compare-and-swap.c +++ b/tools/build/feature/test-sync-compare-and-swap.c @@ -7,7 +7,7 @@ int main(int argc, char *argv[]) { uint64_t old, new = argc; - argv = argv; + (void)argv; do { old = __sync_val_compare_and_swap(&x, 0, 0); } while (!__sync_bool_compare_and_swap(&x, old, new)); diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 669d69441a62..4671fbf28842 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -3,9 +3,9 @@ #define __LINUX_BITS_H #include <linux/const.h> +#include <vdso/bits.h> #include <asm/bitsperlong.h> -#define BIT(nr) (UL(1) << (nr)) #define BIT_ULL(nr) (ULL(1) << (nr)) #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) @@ -18,12 +18,30 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#define GENMASK(h, l) \ +#if !defined(__ASSEMBLY__) && \ + (!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000) +#include <linux/build_bug.h> +#define GENMASK_INPUT_CHECK(h, l) \ + (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ + __builtin_constant_p((l) > (h)), (l) > (h), 0))) +#else +/* + * BUILD_BUG_ON_ZERO is not available in h files included from asm files, + * disable the input check if that is the case. + */ +#define GENMASK_INPUT_CHECK(h, l) 0 +#endif + +#define __GENMASK(h, l) \ (((~UL(0)) - (UL(1) << (l)) + 1) & \ (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define GENMASK(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l)) -#define GENMASK_ULL(h, l) \ +#define __GENMASK_ULL(h, l) \ (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define GENMASK_ULL(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) #endif /* __LINUX_BITS_H */ diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h new file mode 100644 index 000000000000..cc7070c7439b --- /dev/null +++ b/tools/include/linux/build_bug.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#include <linux/compiler.h> + +#ifdef __CHECKER__ +#define BUILD_BUG_ON_ZERO(e) (0) +#else /* __CHECKER__ */ +/* + * Force a compilation error if condition is true, but also produce a + * result (of value 0 and type int), so the expression can be used + * e.g. in a structure initializer (or where-ever else comma expressions + * aren't permitted). + */ +#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); }))) +#endif /* __CHECKER__ */ + +/* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + +/** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** + * BUILD_BUG_ON - break compile if a condition is true. + * @condition: the condition which the compiler should know is false. + * + * If you have some code which relies on certain constants being equal, or + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * detect if someone changes it. + */ +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) + +/** + * BUILD_BUG - break compile if used. + * + * If you have some code that you expect the compiler to eliminate at + * build time, you should use BUILD_BUG to detect if it is + * unexpectedly used. + */ +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") + +/** + * static_assert - check integer constant expression at build time + * + * static_assert() is a wrapper for the C11 _Static_assert, with a + * little macro magic to make the message optional (defaulting to the + * stringification of the tested expression). + * + * Contrary to BUILD_BUG_ON(), static_assert() can be used at global + * scope, but requires the expression to be an integer constant + * expression (i.e., it is not enough that __builtin_constant_p() is + * true for expr). + * + * Also note that BUILD_BUG_ON() fails the build if the condition is + * true, while static_assert() fails the build if the expression is + * false. + */ +#ifndef static_assert +#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr) +#define __static_assert(expr, msg, ...) _Static_assert(expr, msg) +#endif // static_assert + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 1827c2f973f9..180f7714a5f1 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -10,6 +10,32 @@ # define __compiletime_error(message) #endif +#ifdef __OPTIMIZE__ +# define __compiletime_assert(condition, msg, prefix, suffix) \ + do { \ + extern void prefix ## suffix(void) __compiletime_error(msg); \ + if (!(condition)) \ + prefix ## suffix(); \ + } while (0) +#else +# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) +#endif + +#define _compiletime_assert(condition, msg, prefix, suffix) \ + __compiletime_assert(condition, msg, prefix, suffix) + +/** + * compiletime_assert - break build and emit msg if condition is false + * @condition: a compile-time constant condition to check + * @msg: a message to emit if condition is false + * + * In tradition of POSIX assert, this macro will break the build if the + * supplied condition is *false*, emitting the supplied error message if the + * compiler has support to do so. + */ +#define compiletime_assert(condition, msg) \ + _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) + /* Optimization barrier */ /* The "volatile" is due to gcc bugs */ #define barrier() __asm__ __volatile__("": : :"memory") diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h index 7b55a55f5911..81b8aae5a855 100644 --- a/tools/include/linux/const.h +++ b/tools/include/linux/const.h @@ -1,9 +1,6 @@ #ifndef _LINUX_CONST_H #define _LINUX_CONST_H -#include <uapi/linux/const.h> - -#define UL(x) (_UL(x)) -#define ULL(x) (_ULL(x)) +#include <vdso/const.h> #endif /* _LINUX_CONST_H */ diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index cba226948a0c..a7e54a08fb54 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -5,6 +5,7 @@ #include <stdarg.h> #include <stddef.h> #include <assert.h> +#include <linux/build_bug.h> #include <linux/compiler.h> #include <endian.h> #include <byteswap.h> @@ -35,9 +36,6 @@ (type *)((char *)__mptr - offsetof(type, member)); }) #endif -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) - #ifndef max #define max(x, y) ({ \ typeof(x) _max1 = (x); \ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 868bf7996c0f..808b48a93330 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -948,6 +948,8 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) + /** * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 829c0a48577f..2813e579b480 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1619,6 +1619,27 @@ struct drm_i915_gem_context_param { * By default, new contexts allow persistence. */ #define I915_CONTEXT_PARAM_PERSISTENCE 0xb + +/* + * I915_CONTEXT_PARAM_RINGSIZE: + * + * Sets the size of the CS ringbuffer to use for logical ring contexts. This + * applies a limit of how many batches can be queued to HW before the caller + * is blocked due to lack of space for more commands. + * + * Only reliably possible to be set prior to first use, i.e. during + * construction. At any later point, the current execution must be flushed as + * the ring can only be changed while the context is idle. Note, the ringsize + * can be specified as a constructor property, see + * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required. + * + * Only applies to the current set of engine and lost when those engines + * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES). + * + * Must be between 4 - 512 KiB, in intervals of page size [4 KiB]. + * Default is 16 KiB. + */ +#define I915_CONTEXT_PARAM_RINGSIZE 0xc /* Must be kept compact -- no holes and well documented */ __u64 value; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2e29a671d67e..4a6c47f3febe 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -652,6 +652,8 @@ union bpf_attr { * u64 bpf_ktime_get_ns(void) * Description * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: clock_gettime(CLOCK_MONOTONIC) * Return * Current *ktime*. * @@ -1642,7 +1644,7 @@ union bpf_attr { * ifindex, but doesn't require a map to do so. * Return * **XDP_REDIRECT** on success, or the value of the two lower bits - * of the **flags* argument on error. + * of the *flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description @@ -3025,6 +3027,14 @@ union bpf_attr { * * **-EOPNOTSUPP** Unsupported operation, for example a * call from outside of TC ingress. * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: clock_gettime(CLOCK_BOOTTIME) + * Return + * Current *ktime*. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3151,7 +3161,8 @@ union bpf_attr { FN(xdp_output), \ FN(get_netns_cookie), \ FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), + FN(sk_assign), \ + FN(ktime_get_boot_ns), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 0d8a6f47711c..a10e3cdc2839 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -163,6 +163,7 @@ struct fscrypt_get_key_status_arg { #define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg) #define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS _IOWR('f', 25, struct fscrypt_remove_key_arg) #define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 26, struct fscrypt_get_key_status_arg) +#define FS_IOC_GET_ENCRYPTION_NONCE _IOR('f', 27, __u8[16]) /**********************************************************************/ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4b95f9a31a2f..428c7dde6b4b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -474,12 +474,17 @@ struct kvm_s390_mem_op { __u32 size; /* amount of bytes */ __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */ - __u8 ar; /* the access register number */ - __u8 reserved[31]; /* should be set to 0 */ + union { + __u8 ar; /* the access register number */ + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* should be set to 0 */ + }; }; /* types for kvm_s390_mem_op->op */ #define KVM_S390_MEMOP_LOGICAL_READ 0 #define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) @@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 #define KVM_CAP_S390_VCPU_RESETS 179 +#define KVM_CAP_S390_PROTECTED 180 +#define KVM_CAP_PPC_SECURE_GUEST 181 #ifdef KVM_CAP_IRQ_ROUTING @@ -1478,6 +1485,39 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +/* Available with KVM_CAP_S390_PROTECTED */ +#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd { #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) +#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) +#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index fc1a64c3447b..923cc162609c 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -5,8 +5,9 @@ #include <asm/mman.h> #include <asm-generic/hugetlb_encode.h> -#define MREMAP_MAYMOVE 1 -#define MREMAP_FIXED 2 +#define MREMAP_MAYMOVE 1 +#define MREMAP_FIXED 2 +#define MREMAP_DONTUNMAP 4 #define OVERCOMMIT_GUESS 0 #define OVERCOMMIT_ALWAYS 1 diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 2e3bc22c6f20..3bac0a8ceab2 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -35,6 +35,7 @@ /* Flags for the clone3() syscall. */ #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ +#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ /* * cloning flags intersect with CSIGNAL so can be used with unshare and clone3 @@ -81,6 +82,8 @@ * @set_tid_size: This defines the size of the array referenced * in @set_tid. This cannot be larger than the * kernel's limit of nested PID namespaces. + * @cgroup: If CLONE_INTO_CGROUP is specified set this to + * a file descriptor for the cgroup. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -97,11 +100,13 @@ struct clone_args { __aligned_u64 tls; __aligned_u64 set_tid; __aligned_u64 set_tid_size; + __aligned_u64 cgroup; }; #endif #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ #define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ +#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */ /* * Scheduling policies diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 40d028eed645..9fe72e4b1373 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -116,4 +116,28 @@ #define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64) #define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int) +/* VHOST_VDPA specific defines */ + +/* Get the device id. The device ids follow the same definition of + * the device id defined in virtio-spec. + */ +#define VHOST_VDPA_GET_DEVICE_ID _IOR(VHOST_VIRTIO, 0x70, __u32) +/* Get and set the status. The status bits follow the same definition + * of the device status defined in virtio-spec. + */ +#define VHOST_VDPA_GET_STATUS _IOR(VHOST_VIRTIO, 0x71, __u8) +#define VHOST_VDPA_SET_STATUS _IOW(VHOST_VIRTIO, 0x72, __u8) +/* Get and set the device config. The device config follows the same + * definition of the device config defined in virtio-spec. + */ +#define VHOST_VDPA_GET_CONFIG _IOR(VHOST_VIRTIO, 0x73, \ + struct vhost_vdpa_config) +#define VHOST_VDPA_SET_CONFIG _IOW(VHOST_VIRTIO, 0x74, \ + struct vhost_vdpa_config) +/* Enable/disable the ring. */ +#define VHOST_VDPA_SET_VRING_ENABLE _IOW(VHOST_VIRTIO, 0x75, \ + struct vhost_vring_state) +/* Get the max ring size. */ +#define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16) + #endif diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h new file mode 100644 index 000000000000..6d005a1f5d94 --- /dev/null +++ b/tools/include/vdso/bits.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_BITS_H +#define __VDSO_BITS_H + +#include <vdso/const.h> + +#define BIT(nr) (UL(1) << (nr)) + +#endif /* __VDSO_BITS_H */ diff --git a/tools/include/vdso/const.h b/tools/include/vdso/const.h new file mode 100644 index 000000000000..94b385ad438d --- /dev/null +++ b/tools/include/vdso/const.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_CONST_H +#define __VDSO_CONST_H + +#include <uapi/linux/const.h> + +#define UL(x) (_UL(x)) +#define ULL(x) (_ULL(x)) + +#endif /* __VDSO_CONST_H */ diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index f69cc208778a..60aad054eea1 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -2,6 +2,12 @@ #ifndef __BPF_HELPERS__ #define __BPF_HELPERS__ +/* + * Note that bpf programs need to include either + * vmlinux.h (auto-generated from BTF) or linux/types.h + * in advance since bpf_helper_defs.h uses such types + * as __u64. + */ #include "bpf_helper_defs.h" #define __uint(name, val) int (*name)[val] diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ff9174282a8c..8e1dc6980fac 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -178,6 +178,8 @@ struct bpf_capabilities { __u32 array_mmap:1; /* BTF_FUNC_GLOBAL is supported */ __u32 btf_func_global:1; + /* kernel support for expected_attach_type in BPF_PROG_LOAD */ + __u32 exp_attach_type:1; }; enum reloc_type { @@ -194,6 +196,22 @@ struct reloc_desc { int sym_off; }; +struct bpf_sec_def; + +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +struct bpf_sec_def { + const char *sec; + size_t len; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + bool is_exp_attach_type_optional; + bool is_attachable; + bool is_attach_btf; + attach_fn_t attach_fn; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -204,6 +222,7 @@ struct bpf_program { char *name; int prog_ifindex; char *section_name; + const struct bpf_sec_def *sec_def; /* section_name with / replaced by _; makes recursive pinning * in bpf_object__pin_programs easier */ @@ -3316,6 +3335,37 @@ static int bpf_object__probe_array_mmap(struct bpf_object *obj) } static int +bpf_object__probe_exp_attach_type(struct bpf_object *obj) +{ + struct bpf_load_program_attr attr; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd; + + memset(&attr, 0, sizeof(attr)); + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK; + attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; + attr.insns = insns; + attr.insns_cnt = ARRAY_SIZE(insns); + attr.license = "GPL"; + + fd = bpf_load_program_xattr(&attr, NULL, 0); + if (fd >= 0) { + obj->caps.exp_attach_type = 1; + close(fd); + return 1; + } + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { int (*probe_fn[])(struct bpf_object *obj) = { @@ -3325,6 +3375,7 @@ bpf_object__probe_caps(struct bpf_object *obj) bpf_object__probe_btf_func_global, bpf_object__probe_btf_datasec, bpf_object__probe_array_mmap, + bpf_object__probe_exp_attach_type, }; int i, ret; @@ -4861,7 +4912,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; - load_attr.expected_attach_type = prog->expected_attach_type; + /* old kernels might not support specifying expected_attach_type */ + if (!prog->caps->exp_attach_type && prog->sec_def && + prog->sec_def->is_exp_attach_type_optional) + load_attr.expected_attach_type = 0; + else + load_attr.expected_attach_type = prog->expected_attach_type; if (prog->caps->name) load_attr.name = prog->name; load_attr.insns = insns; @@ -5062,6 +5118,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } +static const struct bpf_sec_def *find_sec_def(const char *sec_name); + static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) @@ -5117,24 +5175,17 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, bpf_object__elf_finish(obj); bpf_object__for_each_program(prog, obj) { - enum bpf_prog_type prog_type; - enum bpf_attach_type attach_type; - - if (prog->type != BPF_PROG_TYPE_UNSPEC) - continue; - - err = libbpf_prog_type_by_name(prog->section_name, &prog_type, - &attach_type); - if (err == -ESRCH) + prog->sec_def = find_sec_def(prog->section_name); + if (!prog->sec_def) /* couldn't guess, but user might manually specify */ continue; - if (err) - goto out; - bpf_program__set_type(prog, prog_type); - bpf_program__set_expected_attach_type(prog, attach_type); - if (prog_type == BPF_PROG_TYPE_TRACING || - prog_type == BPF_PROG_TYPE_EXT) + bpf_program__set_type(prog, prog->sec_def->prog_type); + bpf_program__set_expected_attach_type(prog, + prog->sec_def->expected_attach_type); + + if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || + prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); } @@ -6223,23 +6274,32 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \ - { string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype } +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \ + attachable, attach_btf) \ + { \ + .sec = string, \ + .len = sizeof(string) - 1, \ + .prog_type = ptype, \ + .expected_attach_type = eatype, \ + .is_exp_attach_type_optional = eatype_optional, \ + .is_attachable = attachable, \ + .is_attach_btf = attach_btf, \ + } /* Programs that can NOT be attached. */ #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) /* Programs that can be attached. */ #define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype) + BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) /* Programs that must specify expected attach type at load time. */ #define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype) + BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0) /* Programs that use BTF to identify attach point */ #define BPF_PROG_BTF(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0) + BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) /* Programs that can be attached but attach type can't be identified by section * name. Kept for backward compatibility. @@ -6253,11 +6313,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, __VA_ARGS__ \ } -struct bpf_sec_def; - -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, - struct bpf_program *prog); - static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, struct bpf_program *prog); static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, @@ -6269,17 +6324,6 @@ static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, struct bpf_program *prog); -struct bpf_sec_def { - const char *sec; - size_t len; - enum bpf_prog_type prog_type; - enum bpf_attach_type expected_attach_type; - bool is_attachable; - bool is_attach_btf; - enum bpf_attach_type attach_type; - attach_fn_t attach_fn; -}; - static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), @@ -6713,7 +6757,7 @@ int libbpf_attach_type_by_name(const char *name, continue; if (!section_defs[i].is_attachable) return -EINVAL; - *attach_type = section_defs[i].attach_type; + *attach_type = section_defs[i].expected_attach_type; return 0; } pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); @@ -6962,7 +7006,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, err = bpf_object__load(obj); if (err) { bpf_object__close(obj); - return -EINVAL; + return err; } *pobj = obj; @@ -7542,7 +7586,6 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, struct bpf_link * bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) { - const struct bpf_sec_def *sec_def; enum bpf_attach_type attach_type; char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -7561,11 +7604,6 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) link->detach = &bpf_link__detach_fd; attach_type = bpf_program__get_expected_attach_type(prog); - if (!attach_type) { - sec_def = find_sec_def(bpf_program__title(prog, false)); - if (sec_def) - attach_type = sec_def->attach_type; - } link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL); if (link_fd < 0) { link_fd = -errno; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 44df1d3e7287..f1dacecb1619 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -458,7 +458,7 @@ struct xdp_link_info { struct bpf_xdp_set_link_opts { size_t sz; - __u32 old_fd; + int old_fd; }; #define bpf_xdp_set_link_opts__last_field old_fd diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 18b5319025e1..312f887570b2 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -142,7 +142,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, struct ifinfomsg ifinfo; char attrbuf[64]; } req; - __u32 nl_pid; + __u32 nl_pid = 0; sock = libbpf_netlink_open(&nl_pid); if (sock < 0) @@ -288,7 +288,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, { struct xdp_id_md xdp_id = {}; int sock, ret; - __u32 nl_pid; + __u32 nl_pid = 0; __u32 mask; if (flags & ~XDP_FLAGS_MASK || !info_size) @@ -321,7 +321,9 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) { - if (info->attach_mode != XDP_ATTACHED_MULTI) + flags &= XDP_FLAGS_MODES; + + if (info->attach_mode != XDP_ATTACHED_MULTI && !flags) return info->prog_id; if (flags & XDP_FLAGS_DRV_MODE) return info->drv_prog_id; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8dd01f986fbb..4b170fd08a28 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1050,10 +1050,7 @@ static struct rela *find_jump_table(struct objtool_file *file, * it. */ for (; - &insn->list != &file->insn_list && - insn->sec == func->sec && - insn->offset >= func->offset; - + &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func; insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) @@ -2008,8 +2005,8 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct } if (state->bp_scratch) { - WARN("%s uses BP as a scratch register", - func->name); + WARN_FUNC("BP used as a scratch register", + insn->sec, insn->offset); return 1; } @@ -2364,14 +2361,27 @@ static bool ignore_unreachable_insn(struct instruction *insn) !strcmp(insn->sec->name, ".altinstr_aux")) return true; + if (!insn->func) + return false; + + /* + * CONFIG_UBSAN_TRAP inserts a UD2 when it sees + * __builtin_unreachable(). The BUG() macro has an unreachable() after + * the UD2, which causes GCC's undefined trap logic to emit another UD2 + * (or occasionally a JMP to UD2). + */ + if (list_prev_entry(insn, list)->dead_end && + (insn->type == INSN_BUG || + (insn->type == INSN_JUMP_UNCONDITIONAL && + insn->jump_dest && insn->jump_dest->type == INSN_BUG))) + return true; + /* * Check if this (or a subsequent) instruction is related to * CONFIG_UBSAN or CONFIG_KASAN. * * End the search at 5 instructions to avoid going into the weeds. */ - if (!insn->func) - return false; for (i = 0; i < 5; i++) { if (is_kasan_insn(insn) || is_ubsan_insn(insn)) diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 09ddc8f1def3..c4857fa3f1d1 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -105,7 +105,7 @@ static int symbol_by_offset(const void *key, const struct rb_node *node) if (*o < s->offset) return -1; - if (*o > s->offset + s->len) + if (*o >= s->offset + s->len) return 1; return 0; diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index ebbb10c61e24..0b79c2353a21 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -99,7 +99,7 @@ static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) offset &= OFFSET_STRIDE_MASK; ol = offset; - oh = offset >> 32; + oh = (offset >> 16) >> 16; __jhash_mix(ol, oh, idx); diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 13ccf775a83a..ba4cbb1cdd63 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -66,7 +66,7 @@ int orc_dump(const char *_objname) char *name; size_t nr_sections; Elf64_Addr orc_ip_addr = 0; - size_t shstrtab_idx; + size_t shstrtab_idx, strtab_idx = 0; Elf *elf; Elf_Scn *scn; GElf_Shdr sh; @@ -127,6 +127,8 @@ int orc_dump(const char *_objname) if (!strcmp(name, ".symtab")) { symtab = data; + } else if (!strcmp(name, ".strtab")) { + strtab_idx = i; } else if (!strcmp(name, ".orc_unwind")) { orc = data->d_buf; orc_size = sh.sh_size; @@ -138,7 +140,7 @@ int orc_dump(const char *_objname) } } - if (!symtab || !orc || !orc_ip) + if (!symtab || !strtab_idx || !orc || !orc_ip) return 0; if (orc_size % sizeof(*orc) != 0) { @@ -159,21 +161,29 @@ int orc_dump(const char *_objname) return -1; } - scn = elf_getscn(elf, sym.st_shndx); - if (!scn) { - WARN_ELF("elf_getscn"); - return -1; - } - - if (!gelf_getshdr(scn, &sh)) { - WARN_ELF("gelf_getshdr"); - return -1; - } - - name = elf_strptr(elf, shstrtab_idx, sh.sh_name); - if (!name || !*name) { - WARN_ELF("elf_strptr"); - return -1; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) { + scn = elf_getscn(elf, sym.st_shndx); + if (!scn) { + WARN_ELF("elf_getscn"); + return -1; + } + + if (!gelf_getshdr(scn, &sh)) { + WARN_ELF("gelf_getshdr"); + return -1; + } + + name = elf_strptr(elf, shstrtab_idx, sh.sh_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } + } else { + name = elf_strptr(elf, strtab_idx, sym.st_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } } printf("%s+%llx:", name, (unsigned long long)rela.r_addend); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 41e4a2754da4..4c0dabd28000 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -88,11 +88,6 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti struct orc_entry *orc; struct rela *rela; - if (!insn_sec->sym) { - WARN("missing symbol for section %s", insn_sec->name); - return -1; - } - /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc)); @@ -105,8 +100,32 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti } memset(rela, 0, sizeof(*rela)); - rela->sym = insn_sec->sym; - rela->addend = insn_off; + if (insn_sec->sym) { + rela->sym = insn_sec->sym; + rela->addend = insn_off; + } else { + /* + * The Clang assembler doesn't produce section symbols, so we + * have to reference the function symbol instead: + */ + rela->sym = find_symbol_containing(insn_sec, insn_off); + if (!rela->sym) { + /* + * Hack alert. This happens when we need to reference + * the NOP pad insn immediately after the function. + */ + rela->sym = find_symbol_containing(insn_sec, + insn_off - 1); + } + if (!rela->sym) { + WARN("missing symbol for insn at offset 0x%lx\n", + insn_off); + return -1; + } + + rela->addend = insn_off - rela->sym->offset; + } + rela->type = R_X86_64_PC32; rela->offset = idx * sizeof(int); rela->sec = ip_relasec; diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 44d510bc9b78..37b844f839bc 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -8,357 +8,357 @@ # # The abi is "common", "64" or "x32" for this file. # -0 common read __x64_sys_read -1 common write __x64_sys_write -2 common open __x64_sys_open -3 common close __x64_sys_close -4 common stat __x64_sys_newstat -5 common fstat __x64_sys_newfstat -6 common lstat __x64_sys_newlstat -7 common poll __x64_sys_poll -8 common lseek __x64_sys_lseek -9 common mmap __x64_sys_mmap -10 common mprotect __x64_sys_mprotect -11 common munmap __x64_sys_munmap -12 common brk __x64_sys_brk -13 64 rt_sigaction __x64_sys_rt_sigaction -14 common rt_sigprocmask __x64_sys_rt_sigprocmask -15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs -16 64 ioctl __x64_sys_ioctl -17 common pread64 __x64_sys_pread64 -18 common pwrite64 __x64_sys_pwrite64 -19 64 readv __x64_sys_readv -20 64 writev __x64_sys_writev -21 common access __x64_sys_access -22 common pipe __x64_sys_pipe -23 common select __x64_sys_select -24 common sched_yield __x64_sys_sched_yield -25 common mremap __x64_sys_mremap -26 common msync __x64_sys_msync -27 common mincore __x64_sys_mincore -28 common madvise __x64_sys_madvise -29 common shmget __x64_sys_shmget -30 common shmat __x64_sys_shmat -31 common shmctl __x64_sys_shmctl -32 common dup __x64_sys_dup -33 common dup2 __x64_sys_dup2 -34 common pause __x64_sys_pause -35 common nanosleep __x64_sys_nanosleep -36 common getitimer __x64_sys_getitimer -37 common alarm __x64_sys_alarm -38 common setitimer __x64_sys_setitimer -39 common getpid __x64_sys_getpid -40 common sendfile __x64_sys_sendfile64 -41 common socket __x64_sys_socket -42 common connect __x64_sys_connect -43 common accept __x64_sys_accept -44 common sendto __x64_sys_sendto -45 64 recvfrom __x64_sys_recvfrom -46 64 sendmsg __x64_sys_sendmsg -47 64 recvmsg __x64_sys_recvmsg -48 common shutdown __x64_sys_shutdown -49 common bind __x64_sys_bind -50 common listen __x64_sys_listen -51 common getsockname __x64_sys_getsockname -52 common getpeername __x64_sys_getpeername -53 common socketpair __x64_sys_socketpair -54 64 setsockopt __x64_sys_setsockopt -55 64 getsockopt __x64_sys_getsockopt -56 common clone __x64_sys_clone/ptregs -57 common fork __x64_sys_fork/ptregs -58 common vfork __x64_sys_vfork/ptregs -59 64 execve __x64_sys_execve/ptregs -60 common exit __x64_sys_exit -61 common wait4 __x64_sys_wait4 -62 common kill __x64_sys_kill -63 common uname __x64_sys_newuname -64 common semget __x64_sys_semget -65 common semop __x64_sys_semop -66 common semctl __x64_sys_semctl -67 common shmdt __x64_sys_shmdt -68 common msgget __x64_sys_msgget -69 common msgsnd __x64_sys_msgsnd -70 common msgrcv __x64_sys_msgrcv -71 common msgctl __x64_sys_msgctl -72 common fcntl __x64_sys_fcntl -73 common flock __x64_sys_flock -74 common fsync __x64_sys_fsync -75 common fdatasync __x64_sys_fdatasync -76 common truncate __x64_sys_truncate -77 common ftruncate __x64_sys_ftruncate -78 common getdents __x64_sys_getdents -79 common getcwd __x64_sys_getcwd -80 common chdir __x64_sys_chdir -81 common fchdir __x64_sys_fchdir -82 common rename __x64_sys_rename -83 common mkdir __x64_sys_mkdir -84 common rmdir __x64_sys_rmdir -85 common creat __x64_sys_creat -86 common link __x64_sys_link -87 common unlink __x64_sys_unlink -88 common symlink __x64_sys_symlink -89 common readlink __x64_sys_readlink -90 common chmod __x64_sys_chmod -91 common fchmod __x64_sys_fchmod -92 common chown __x64_sys_chown -93 common fchown __x64_sys_fchown -94 common lchown __x64_sys_lchown -95 common umask __x64_sys_umask -96 common gettimeofday __x64_sys_gettimeofday -97 common getrlimit __x64_sys_getrlimit -98 common getrusage __x64_sys_getrusage -99 common sysinfo __x64_sys_sysinfo -100 common times __x64_sys_times -101 64 ptrace __x64_sys_ptrace -102 common getuid __x64_sys_getuid -103 common syslog __x64_sys_syslog -104 common getgid __x64_sys_getgid -105 common setuid __x64_sys_setuid -106 common setgid __x64_sys_setgid -107 common geteuid __x64_sys_geteuid -108 common getegid __x64_sys_getegid -109 common setpgid __x64_sys_setpgid -110 common getppid __x64_sys_getppid -111 common getpgrp __x64_sys_getpgrp -112 common setsid __x64_sys_setsid -113 common setreuid __x64_sys_setreuid -114 common setregid __x64_sys_setregid -115 common getgroups __x64_sys_getgroups -116 common setgroups __x64_sys_setgroups -117 common setresuid __x64_sys_setresuid -118 common getresuid __x64_sys_getresuid -119 common setresgid __x64_sys_setresgid -120 common getresgid __x64_sys_getresgid -121 common getpgid __x64_sys_getpgid -122 common setfsuid __x64_sys_setfsuid -123 common setfsgid __x64_sys_setfsgid -124 common getsid __x64_sys_getsid -125 common capget __x64_sys_capget -126 common capset __x64_sys_capset -127 64 rt_sigpending __x64_sys_rt_sigpending -128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait -129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo -130 common rt_sigsuspend __x64_sys_rt_sigsuspend -131 64 sigaltstack __x64_sys_sigaltstack -132 common utime __x64_sys_utime -133 common mknod __x64_sys_mknod +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 common rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn sys_rt_sigreturn +16 64 ioctl sys_ioctl +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt +56 common clone sys_clone +57 common fork sys_fork +58 common vfork sys_vfork +59 64 execve sys_execve +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times +101 64 ptrace sys_ptrace +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 common rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack sys_sigaltstack +132 common utime sys_utime +133 common mknod sys_mknod 134 64 uselib -135 common personality __x64_sys_personality -136 common ustat __x64_sys_ustat -137 common statfs __x64_sys_statfs -138 common fstatfs __x64_sys_fstatfs -139 common sysfs __x64_sys_sysfs -140 common getpriority __x64_sys_getpriority -141 common setpriority __x64_sys_setpriority -142 common sched_setparam __x64_sys_sched_setparam -143 common sched_getparam __x64_sys_sched_getparam -144 common sched_setscheduler __x64_sys_sched_setscheduler -145 common sched_getscheduler __x64_sys_sched_getscheduler -146 common sched_get_priority_max __x64_sys_sched_get_priority_max -147 common sched_get_priority_min __x64_sys_sched_get_priority_min -148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval -149 common mlock __x64_sys_mlock -150 common munlock __x64_sys_munlock -151 common mlockall __x64_sys_mlockall -152 common munlockall __x64_sys_munlockall -153 common vhangup __x64_sys_vhangup -154 common modify_ldt __x64_sys_modify_ldt -155 common pivot_root __x64_sys_pivot_root -156 64 _sysctl __x64_sys_sysctl -157 common prctl __x64_sys_prctl -158 common arch_prctl __x64_sys_arch_prctl -159 common adjtimex __x64_sys_adjtimex -160 common setrlimit __x64_sys_setrlimit -161 common chroot __x64_sys_chroot -162 common sync __x64_sys_sync -163 common acct __x64_sys_acct -164 common settimeofday __x64_sys_settimeofday -165 common mount __x64_sys_mount -166 common umount2 __x64_sys_umount -167 common swapon __x64_sys_swapon -168 common swapoff __x64_sys_swapoff -169 common reboot __x64_sys_reboot -170 common sethostname __x64_sys_sethostname -171 common setdomainname __x64_sys_setdomainname -172 common iopl __x64_sys_iopl/ptregs -173 common ioperm __x64_sys_ioperm +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl sys_iopl +173 common ioperm sys_ioperm 174 64 create_module -175 common init_module __x64_sys_init_module -176 common delete_module __x64_sys_delete_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module 177 64 get_kernel_syms 178 64 query_module -179 common quotactl __x64_sys_quotactl +179 common quotactl sys_quotactl 180 64 nfsservctl 181 common getpmsg 182 common putpmsg 183 common afs_syscall 184 common tuxcall 185 common security -186 common gettid __x64_sys_gettid -187 common readahead __x64_sys_readahead -188 common setxattr __x64_sys_setxattr -189 common lsetxattr __x64_sys_lsetxattr -190 common fsetxattr __x64_sys_fsetxattr -191 common getxattr __x64_sys_getxattr -192 common lgetxattr __x64_sys_lgetxattr -193 common fgetxattr __x64_sys_fgetxattr -194 common listxattr __x64_sys_listxattr -195 common llistxattr __x64_sys_llistxattr -196 common flistxattr __x64_sys_flistxattr -197 common removexattr __x64_sys_removexattr -198 common lremovexattr __x64_sys_lremovexattr -199 common fremovexattr __x64_sys_fremovexattr -200 common tkill __x64_sys_tkill -201 common time __x64_sys_time -202 common futex __x64_sys_futex -203 common sched_setaffinity __x64_sys_sched_setaffinity -204 common sched_getaffinity __x64_sys_sched_getaffinity +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 64 io_setup __x64_sys_io_setup -207 common io_destroy __x64_sys_io_destroy -208 common io_getevents __x64_sys_io_getevents -209 64 io_submit __x64_sys_io_submit -210 common io_cancel __x64_sys_io_cancel +206 64 io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 64 io_submit sys_io_submit +210 common io_cancel sys_io_cancel 211 64 get_thread_area -212 common lookup_dcookie __x64_sys_lookup_dcookie -213 common epoll_create __x64_sys_epoll_create +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create 214 64 epoll_ctl_old 215 64 epoll_wait_old -216 common remap_file_pages __x64_sys_remap_file_pages -217 common getdents64 __x64_sys_getdents64 -218 common set_tid_address __x64_sys_set_tid_address -219 common restart_syscall __x64_sys_restart_syscall -220 common semtimedop __x64_sys_semtimedop -221 common fadvise64 __x64_sys_fadvise64 -222 64 timer_create __x64_sys_timer_create -223 common timer_settime __x64_sys_timer_settime -224 common timer_gettime __x64_sys_timer_gettime -225 common timer_getoverrun __x64_sys_timer_getoverrun -226 common timer_delete __x64_sys_timer_delete -227 common clock_settime __x64_sys_clock_settime -228 common clock_gettime __x64_sys_clock_gettime -229 common clock_getres __x64_sys_clock_getres -230 common clock_nanosleep __x64_sys_clock_nanosleep -231 common exit_group __x64_sys_exit_group -232 common epoll_wait __x64_sys_epoll_wait -233 common epoll_ctl __x64_sys_epoll_ctl -234 common tgkill __x64_sys_tgkill -235 common utimes __x64_sys_utimes +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes 236 64 vserver -237 common mbind __x64_sys_mbind -238 common set_mempolicy __x64_sys_set_mempolicy -239 common get_mempolicy __x64_sys_get_mempolicy -240 common mq_open __x64_sys_mq_open -241 common mq_unlink __x64_sys_mq_unlink -242 common mq_timedsend __x64_sys_mq_timedsend -243 common mq_timedreceive __x64_sys_mq_timedreceive -244 64 mq_notify __x64_sys_mq_notify -245 common mq_getsetattr __x64_sys_mq_getsetattr -246 64 kexec_load __x64_sys_kexec_load -247 64 waitid __x64_sys_waitid -248 common add_key __x64_sys_add_key -249 common request_key __x64_sys_request_key -250 common keyctl __x64_sys_keyctl -251 common ioprio_set __x64_sys_ioprio_set -252 common ioprio_get __x64_sys_ioprio_get -253 common inotify_init __x64_sys_inotify_init -254 common inotify_add_watch __x64_sys_inotify_add_watch -255 common inotify_rm_watch __x64_sys_inotify_rm_watch -256 common migrate_pages __x64_sys_migrate_pages -257 common openat __x64_sys_openat -258 common mkdirat __x64_sys_mkdirat -259 common mknodat __x64_sys_mknodat -260 common fchownat __x64_sys_fchownat -261 common futimesat __x64_sys_futimesat -262 common newfstatat __x64_sys_newfstatat -263 common unlinkat __x64_sys_unlinkat -264 common renameat __x64_sys_renameat -265 common linkat __x64_sys_linkat -266 common symlinkat __x64_sys_symlinkat -267 common readlinkat __x64_sys_readlinkat -268 common fchmodat __x64_sys_fchmodat -269 common faccessat __x64_sys_faccessat -270 common pselect6 __x64_sys_pselect6 -271 common ppoll __x64_sys_ppoll -272 common unshare __x64_sys_unshare -273 64 set_robust_list __x64_sys_set_robust_list -274 64 get_robust_list __x64_sys_get_robust_list -275 common splice __x64_sys_splice -276 common tee __x64_sys_tee -277 common sync_file_range __x64_sys_sync_file_range -278 64 vmsplice __x64_sys_vmsplice -279 64 move_pages __x64_sys_move_pages -280 common utimensat __x64_sys_utimensat -281 common epoll_pwait __x64_sys_epoll_pwait -282 common signalfd __x64_sys_signalfd -283 common timerfd_create __x64_sys_timerfd_create -284 common eventfd __x64_sys_eventfd -285 common fallocate __x64_sys_fallocate -286 common timerfd_settime __x64_sys_timerfd_settime -287 common timerfd_gettime __x64_sys_timerfd_gettime -288 common accept4 __x64_sys_accept4 -289 common signalfd4 __x64_sys_signalfd4 -290 common eventfd2 __x64_sys_eventfd2 -291 common epoll_create1 __x64_sys_epoll_create1 -292 common dup3 __x64_sys_dup3 -293 common pipe2 __x64_sys_pipe2 -294 common inotify_init1 __x64_sys_inotify_init1 -295 64 preadv __x64_sys_preadv -296 64 pwritev __x64_sys_pwritev -297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo -298 common perf_event_open __x64_sys_perf_event_open -299 64 recvmmsg __x64_sys_recvmmsg -300 common fanotify_init __x64_sys_fanotify_init -301 common fanotify_mark __x64_sys_fanotify_mark -302 common prlimit64 __x64_sys_prlimit64 -303 common name_to_handle_at __x64_sys_name_to_handle_at -304 common open_by_handle_at __x64_sys_open_by_handle_at -305 common clock_adjtime __x64_sys_clock_adjtime -306 common syncfs __x64_sys_syncfs -307 64 sendmmsg __x64_sys_sendmmsg -308 common setns __x64_sys_setns -309 common getcpu __x64_sys_getcpu -310 64 process_vm_readv __x64_sys_process_vm_readv -311 64 process_vm_writev __x64_sys_process_vm_writev -312 common kcmp __x64_sys_kcmp -313 common finit_module __x64_sys_finit_module -314 common sched_setattr __x64_sys_sched_setattr -315 common sched_getattr __x64_sys_sched_getattr -316 common renameat2 __x64_sys_renameat2 -317 common seccomp __x64_sys_seccomp -318 common getrandom __x64_sys_getrandom -319 common memfd_create __x64_sys_memfd_create -320 common kexec_file_load __x64_sys_kexec_file_load -321 common bpf __x64_sys_bpf -322 64 execveat __x64_sys_execveat/ptregs -323 common userfaultfd __x64_sys_userfaultfd -324 common membarrier __x64_sys_membarrier -325 common mlock2 __x64_sys_mlock2 -326 common copy_file_range __x64_sys_copy_file_range -327 64 preadv2 __x64_sys_preadv2 -328 64 pwritev2 __x64_sys_pwritev2 -329 common pkey_mprotect __x64_sys_pkey_mprotect -330 common pkey_alloc __x64_sys_pkey_alloc -331 common pkey_free __x64_sys_pkey_free -332 common statx __x64_sys_statx -333 common io_pgetevents __x64_sys_io_pgetevents -334 common rseq __x64_sys_rseq +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 common mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 common perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 common setns sys_setns +309 common getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev +312 common kcmp sys_kcmp +313 common finit_module sys_finit_module +314 common sched_setattr sys_sched_setattr +315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 +317 common seccomp sys_seccomp +318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create +320 common kexec_file_load sys_kexec_file_load +321 common bpf sys_bpf +322 64 execveat sys_execveat +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range +327 64 preadv2 sys_preadv2 +328 64 pwritev2 sys_pwritev2 +329 common pkey_mprotect sys_pkey_mprotect +330 common pkey_alloc sys_pkey_alloc +331 common pkey_free sys_pkey_free +332 common statx sys_statx +333 common io_pgetevents sys_io_pgetevents +334 common rseq sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry -424 common pidfd_send_signal __x64_sys_pidfd_send_signal -425 common io_uring_setup __x64_sys_io_uring_setup -426 common io_uring_enter __x64_sys_io_uring_enter -427 common io_uring_register __x64_sys_io_uring_register -428 common open_tree __x64_sys_open_tree -429 common move_mount __x64_sys_move_mount -430 common fsopen __x64_sys_fsopen -431 common fsconfig __x64_sys_fsconfig -432 common fsmount __x64_sys_fsmount -433 common fspick __x64_sys_fspick -434 common pidfd_open __x64_sys_pidfd_open -435 common clone3 __x64_sys_clone3/ptregs -437 common openat2 __x64_sys_openat2 -438 common pidfd_getfd __x64_sys_pidfd_getfd +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd # # x32-specific system call numbers start at 512 to avoid cache impact @@ -366,39 +366,39 @@ # on-the-fly for compat_sys_*() compatibility system calls if X86_X32 # is defined. # -512 x32 rt_sigaction __x32_compat_sys_rt_sigaction -513 x32 rt_sigreturn sys32_x32_rt_sigreturn -514 x32 ioctl __x32_compat_sys_ioctl -515 x32 readv __x32_compat_sys_readv -516 x32 writev __x32_compat_sys_writev -517 x32 recvfrom __x32_compat_sys_recvfrom -518 x32 sendmsg __x32_compat_sys_sendmsg -519 x32 recvmsg __x32_compat_sys_recvmsg -520 x32 execve __x32_compat_sys_execve/ptregs -521 x32 ptrace __x32_compat_sys_ptrace -522 x32 rt_sigpending __x32_compat_sys_rt_sigpending -523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64 -524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo -525 x32 sigaltstack __x32_compat_sys_sigaltstack -526 x32 timer_create __x32_compat_sys_timer_create -527 x32 mq_notify __x32_compat_sys_mq_notify -528 x32 kexec_load __x32_compat_sys_kexec_load -529 x32 waitid __x32_compat_sys_waitid -530 x32 set_robust_list __x32_compat_sys_set_robust_list -531 x32 get_robust_list __x32_compat_sys_get_robust_list -532 x32 vmsplice __x32_compat_sys_vmsplice -533 x32 move_pages __x32_compat_sys_move_pages -534 x32 preadv __x32_compat_sys_preadv64 -535 x32 pwritev __x32_compat_sys_pwritev64 -536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64 -538 x32 sendmmsg __x32_compat_sys_sendmmsg -539 x32 process_vm_readv __x32_compat_sys_process_vm_readv -540 x32 process_vm_writev __x32_compat_sys_process_vm_writev -541 x32 setsockopt __x32_compat_sys_setsockopt -542 x32 getsockopt __x32_compat_sys_getsockopt -543 x32 io_setup __x32_compat_sys_io_setup -544 x32 io_submit __x32_compat_sys_io_submit -545 x32 execveat __x32_compat_sys_execveat/ptregs -546 x32 preadv2 __x32_compat_sys_preadv64v2 -547 x32 pwritev2 __x32_compat_sys_pwritev64v2 +512 x32 rt_sigaction compat_sys_rt_sigaction +513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve compat_sys_execve +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending compat_sys_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo +525 x32 sigaltstack compat_sys_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg_time64 +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit +545 x32 execveat compat_sys_execveat +546 x32 preadv2 compat_sys_preadv64v2 +547 x32 pwritev2 compat_sys_pwritev64v2 diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index bfb21d049e6c..cf147db4e5ca 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -22,7 +22,9 @@ include/uapi/linux/usbdevice_fs.h include/uapi/linux/vhost.h include/uapi/sound/asound.h include/linux/bits.h +include/vdso/bits.h include/linux/const.h +include/vdso/const.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h @@ -115,6 +117,7 @@ check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' +check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"' check include/linux/ctype.h '-I "isdigit("' check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B' check arch/x86/include/asm/inat.h '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"' diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c index 062ca849c8fd..f4db894e0af6 100644 --- a/tools/perf/trace/beauty/clone.c +++ b/tools/perf/trace/beauty/clone.c @@ -46,6 +46,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size, P_FLAG(NEWNET); P_FLAG(IO); P_FLAG(CLEAR_SIGHAND); + P_FLAG(INTO_CGROUP); #undef P_FLAG if (flags) diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index 9fa771a90d79..862c8331dded 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -69,6 +69,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, P_MREMAP_FLAG(MAYMOVE); P_MREMAP_FLAG(FIXED); + P_MREMAP_FLAG(DONTUNMAP); #undef P_MREMAP_FLAG if (flags) diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 347b2c0789e4..c5e3e9a68162 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -21,6 +21,8 @@ if cc_is_clang: vars[var] = sub("-fstack-clash-protection", "", vars[var]) if not clang_has_option("-fstack-protector-strong"): vars[var] = sub("-fstack-protector-strong", "", vars[var]) + if not clang_has_option("-fno-semantic-interposition"): + vars[var] = sub("-fno-semantic-interposition", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 0fd713d3674f..03ecb8cd0eec 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -803,8 +803,11 @@ static void generic_metric(struct perf_stat_config *config, out->force_header ? (metric_name ? metric_name : name) : "", 0); } - } else - print_metric(config, ctxp, NULL, NULL, "", 0); + } else { + print_metric(config, ctxp, NULL, NULL, + out->force_header ? + (metric_name ? metric_name : name) : "", 0); + } for (i = 1; i < pctx.num_ids; i++) zfree(&pctx.ids[i].name); diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile index 845541544570..b5310832c19c 100644 --- a/tools/power/pm-graph/Makefile +++ b/tools/power/pm-graph/Makefile @@ -41,6 +41,10 @@ uninstall : if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph/config ] ; then \ rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph/config; \ fi; + rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/__pycache__/* + if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph/__pycache__ ] ; then \ + rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph/__pycache__; \ + fi; rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/* if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph ] ; then \ rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph; \ diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README index 96259f6e5715..afe6beb40ad9 100644 --- a/tools/power/pm-graph/README +++ b/tools/power/pm-graph/README @@ -1,7 +1,12 @@ - p m - g r a p h + _ + _ __ _ __ ___ __ _ _ __ __ _ _ __ | |__ + | '_ \| '_ ` _ \ _____ / _` | '__/ _` | '_ \| '_ \ + | |_) | | | | | |_____| (_| | | | (_| | |_) | | | | + | .__/|_| |_| |_| \__, |_| \__,_| .__/|_| |_| + |_| |___/ |_| pm-graph: suspend/resume/boot timing analysis tools - Version: 5.5 + Version: 5.6 Author: Todd Brandt <todd.e.brandt@intel.com> Home Page: https://01.org/pm-graph @@ -18,10 +23,6 @@ - upstream version in git: https://github.com/intel/pm-graph/ - Requirements: - - runs with python2 or python3, choice is made by /usr/bin/python link - - python2 now requires python-configparser be installed - Table of Contents - Overview - Setup @@ -29,6 +30,8 @@ - Basic Usage - Dev Mode Usage - Proc Mode Usage + - Endurance Testing + - Usage Examples - Configuration Files - Usage Examples - Config File Options @@ -54,15 +57,18 @@ | SETUP | ------------------------------------------------------------------ - These packages are required to execute the scripts + Package Requirements + - runs with python2 or python3, choice is made by /usr/bin/python link - python - - python-requests + - python-configparser (for python2 sleepgraph) + - python-requests (for googlesheet.py) + - linux-tools-common (for turbostat usage in sleepgraph) Ubuntu: - sudo apt-get install python python-requests + sudo apt-get install python python-configparser python-requests linux-tools-common Fedora: - sudo dnf install python python-requests + sudo dnf install python python-configparser python-requests linux-tools-common The tools can most easily be installed via git clone and make install @@ -190,6 +196,104 @@ _______________ %> sudo ./sleepgraph.py -config config/suspend-proc.cfg +------------------------------------------------------------------ +| ENDURANCE TESTING | +------------------------------------------------------------------ + + The best way to gauge the health of a system is to run a series of + suspend/resumes over an extended period and analyze the behavior. This can be + accomplished with sleepgraph's -multi argument. You specify two numbers: the + number of tests to run OR the duration in days, hours, or minutes, and the + delay in seconds between them. For instance, -multi 20 5: execute 20 tests with + a 5 second delay between each, or -multi 24h 0: execute tests over a 24 hour + period with no delay between tests. You can include any other options you like + to generate the data you want. It's most useful to collect dev mode timelines + as the kprobes don't alter the performance much and you get more insight. + + On completion, the output folder contains a series of folders for the + individual test data and a set of summary pages in the root. The summary.html + file is a tabular list of the tests with relevant info and links. The + summary-issue.html and summary-devices.html files include data taken from + all tests on kernel issues and device performance. The folder looks like this: + + suspend-xN-{date}-{time}: + summary.html + summary-issues.html + summary-devices.html + suspend-{date}-{time} (1) + suspend-{date}-{time} (2) + ... + + These are the relevant arguments to use for testing: + + -m mode + Mode to initiate for suspend e.g. mem, freeze, standby (default: mem). + + -rtcwake t + Use rtcwake to autoresume after t seconds (default: 15). + + -gzip (optional) + Gzip the trace and dmesg logs to save space. The tool can also read in + gzipped logs for processing. This reduces the multitest folder size. + + -dev (optional) + Add kernel source calls and threads to the timeline (default: disabled). + + -multi n d + Execute n consecutive tests at d seconds intervals. The outputs will be + created in a new subdirectory: suspend-xN-{date}-{time}. When the multitest + run is done, the -summary command is called automatically to create summary + html files for all the data (unless you use -skiphtml). -skiphtml will + speed up the testing by not creating timelines or summary html files. You + can then run the tool again at a later time with -summary and -genhtml to + create the timelines. + + -skiphtml (optional) + Run the test and capture the trace logs, but skip the timeline and summary + html generation. This can greatly speed up overall testing. You can then + copy the data to a faster host machine and run -summary -genhtml to + generate the timelines and summary. + + These are the relevant commands to use after testing is complete: + + -summary indir + Generate or regenerate the summary for a -multi test run. Creates three + files: summary.html, summary-issues.html, and summary-devices.html in the + current folder. summary.html is a table of tests with relevant info sorted + by kernel/host/mode, and links to the test html files. summary-issues.html + is a list of kernel issues found in dmesg from all the tests. + summary-devices.html is a list of devices and times from all the tests. + + -genhtml + Used with -summary to regenerate any missing html timelines from their + dmesg and ftrace logs. This will require a significant amount of time if + there are thousands of tests. + +Usage Examples +_______________ + + A multitest is initiated like this: + + %> sudo ./sleepgraph.py -m mem -rtcwake 10 -dev -gzip -multi 2000 0 + + or you can skip timeline generation in order to speed things up + + %> sudo ./sleepgraph.py -m mem -rtcwake 10 -dev -gzip -multi 2000 0 -skiphtml + + The tool will produce an output folder with all the test subfolders inside. + Each test subfolder contains the dmesg/ftrace logs and/or the html timeline + depending on whether you used the -skiphtml option. The root folder contains + the summary.html files. + + The summary for an existing multitest is generated like this: + + %> cd suspend-x2000-{date}-{time} + %> sleepgraph.py -summary . + + or if you need to generate the html timelines you can use -genhtml + + %> cd suspend-xN-{date}-{time} + %> sleepgraph.py -summary . -genhtml ------------------------------------------------------------------ | CONFIGURATION FILES | diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py index d3b99a1e92d6..2823cd3122f7 100755 --- a/tools/power/pm-graph/bootgraph.py +++ b/tools/power/pm-graph/bootgraph.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0-only # # Tool for analyzing boot timing diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 index 43aee64316df..5126271de98a 100644 --- a/tools/power/pm-graph/sleepgraph.8 +++ b/tools/power/pm-graph/sleepgraph.8 @@ -74,8 +74,10 @@ after the test is complete. Switch the display to the requested mode for the test using the xset command. This helps maintain the consistency of test data for better comparison. .TP -\fB-skiphtml\fR -Run the test and capture the trace logs, but skip the timeline generation. +\fB-wifi\fR +If a wifi connection is available, check that it reconnects after resume. Include +the reconnect time in the total resume time calculation and treat wifi timeouts +as resume failures. .SS "advanced" .TP @@ -117,8 +119,24 @@ Include \fIt\fR ms delay before 1st suspend (default: 0 ms). Include \fIt\fR ms delay after last resume (default: 0 ms). .TP \fB-multi \fIn d\fR -Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will -be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}. +Used for endurance testing. If \fIn\fR is entirely numeric, it's treated as a count: +Execute \fIn\fR consecutive tests at \fId\fR second intervals. +If \fIn\fR is an integer followed by a "d", "h", or "m", it's treated as a duration: +Execute tests continuously over \fIn\fR days, hours, or minutes at \fId\fR second intervals. +The outputs will be created in a new subdirectory, for count: suspend-{date}-{time}-xN, +for duration: suspend-{date}-{time}-Nm. When the multitest run is done, the \fI-summary\fR +command is called automatically to create summary html files for all the data (unless you +use \fI-skiphtml\fR). \fI-skiphtml\fR will speed up the testing by not creating timelines +or summary html files. You can then run the tool again at a later time with \fI-summary\fR +and \fI-genhtml\fR to create the timelines. +.TP +\fB-maxfail \fIn\fR +Abort a -multi run after \fIn\fR consecutive fails. 0 means never abort (default = 0). +.TP +\fB-skiphtml\fR +Run the test and capture the trace logs, but skip the timeline generation. +You can generate the html timelines later with \fI-dmesg\fR & \fI-ftrace\fR, or +by running \fI-summary\fR and \fI-genhtml\fR. .SS "ftrace debug" .TP @@ -173,11 +191,20 @@ Set trace buffer size to N kilo-bytes (default: all of free memory up to 3GB) .SH COMMANDS .TP \fB-summary \fIindir\fR -Create a summary page of all tests in \fIindir\fR. Creates summary.html -in the current folder. The output page is a table of tests with -suspend and resume values sorted by suspend mode, host, and kernel. -Includes test averages by mode and links to the test html files. -Use -genhtml to include tests with missing html. +Create a set of summary pages for all tests in \fIindir\fR recursively. +Creates summary.html, summary-issues.html, and summary-devices.html in the current folder. +summary.html is a table of tests with relevant info sorted by kernel/host/mode, +and links to the test html files. It identifies the minimum, maximum, and median +suspend and resume times for you with highlights and links in the header. +summary-issues.html is a list of kernel issues found in dmesg from all the tests. +summary-devices.html is a list of devices and times from all the tests. + +Use \fI-genhtml\fR to regenerate any tests with missing html. +.TP +\fB-genhtml\fR +Used with \fI-summary\fR to regenerate any missing html timelines from their +dmesg and ftrace logs. This will require a significant amount of time if there +are thousands of tests. .TP \fB-modes\fR List available suspend modes. @@ -189,10 +216,7 @@ with any options you intend to use to see if they will work. \fB-fpdt\fR Print out the contents of the ACPI Firmware Performance Data Table. .TP -\fB-battery\fR -Print out battery status and current charge. -.TP -\fB-wifi\fR +\fB-wificheck\fR Print out wifi status and connection details. .TP \fB-xon/-xoff/-xstandby/-xsuspend\fR @@ -208,6 +232,9 @@ Print out system info extracted from BIOS. Reads /dev/mem directly instead of go \fB-devinfo\fR Print out the pm settings of all devices which support runtime suspend. .TP +\fB-cmdinfo\fR +Print out all the platform data collected from the system that makes it into the logs. +.TP \fB-flist\fR Print the list of ftrace functions currently being captured. Functions that are not available as symbols in the current kernel are shown in red. @@ -272,14 +299,20 @@ Run two suspends back to back, include a 500ms delay before, after, and in betwe .IP \f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR .PP +Execute a suspend using a custom command. +.IP +\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR +.PP + +.SS "endurance testing using -multi" +.PP Do a batch run of 10 freezes with 30 seconds delay between runs. .IP \f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR .PP -Execute a suspend using a custom command. +Do a batch run of freezes for 24 hours. .IP -\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR -.PP +\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 24h 0\fR .SS "adding callgraph data" Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger. diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index f7d1c1f62f86..9b0404d10768 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0-only # # Tool for analyzing suspend/resume timing @@ -58,7 +58,7 @@ import re import platform import signal import codecs -from datetime import datetime +from datetime import datetime, timedelta import struct import configparser import gzip @@ -81,12 +81,13 @@ def ascii(text): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.5' + version = '5.6' ansi = False rs = 0 display = '' gzip = False sync = False + wifi = False verbose = False testlog = True dmesglog = True @@ -97,7 +98,8 @@ class SystemValues: cgphase = '' cgtest = -1 cgskip = '' - multitest = {'run': False, 'count': 0, 'delay': 0} + maxfail = 0 + multitest = {'run': False, 'count': 1000000, 'delay': 0} max_graph_depth = 0 callloopmaxgap = 0.0001 callloopmaxlen = 0.005 @@ -148,7 +150,7 @@ class SystemValues: x2delay = 0 skiphtml = False usecallgraph = False - ftopfunc = 'suspend_devices_and_enter' + ftopfunc = 'pm_suspend' ftop = False usetraceevents = False usetracemarkers = True @@ -164,6 +166,8 @@ class SystemValues: predelay = 0 postdelay = 0 pmdebug = '' + tmstart = 'SUSPEND START %Y%m%d-%H:%M:%S.%f' + tmend = 'RESUME COMPLETE %Y%m%d-%H:%M:%S.%f' tracefuncs = { 'sys_sync': {}, 'ksys_sync': {}, @@ -183,9 +187,11 @@ class SystemValues: 'acpi_s2idle_sync': {}, 'acpi_s2idle_begin': {}, 'acpi_s2idle_prepare': {}, + 'acpi_s2idle_prepare_late': {}, 'acpi_s2idle_wake': {}, 'acpi_s2idle_wakeup': {}, 'acpi_s2idle_restore': {}, + 'acpi_s2idle_restore_early': {}, 'hibernate_preallocate_memory': {}, 'create_basic_memory_bitmaps': {}, 'swsusp_write': {}, @@ -270,12 +276,23 @@ class SystemValues: 'intel_opregion_init': {}, 'intel_fbdev_set_suspend': {}, } + infocmds = [ + [0, 'kparams', 'cat', '/proc/cmdline'], + [0, 'mcelog', 'mcelog'], + [0, 'pcidevices', 'lspci', '-tv'], + [0, 'usbdevices', 'lsusb', '-t'], + [1, 'interrupts', 'cat', '/proc/interrupts'], + [1, 'wakeups', 'cat', '/sys/kernel/debug/wakeup_sources'], + [2, 'gpecounts', 'sh', '-c', 'grep -v invalid /sys/firmware/acpi/interrupts/*'], + [2, 'suspendstats', 'sh', '-c', 'grep -v invalid /sys/power/suspend_stats/*'], + [2, 'cpuidle', 'sh', '-c', 'grep -v invalid /sys/devices/system/cpu/cpu*/cpuidle/state*/s2idle/*'], + [2, 'battery', 'sh', '-c', 'grep -v invalid /sys/class/power_supply/*/*'], + ] cgblacklist = [] kprobes = dict() timeformat = '%.3f' cmdline = '%s %s' % \ (os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:])) - kparams = '' sudouser = '' def __init__(self): self.archargs = 'args_'+platform.machine() @@ -295,6 +312,9 @@ class SystemValues: if os.getuid() == 0 and 'SUDO_USER' in os.environ and \ os.environ['SUDO_USER']: self.sudouser = os.environ['SUDO_USER'] + def resetlog(self): + self.logmsg = '' + self.platinfo = [] def vprint(self, msg): self.logmsg += msg+'\n' if self.verbose or msg.startswith('WARNING:'): @@ -304,11 +324,11 @@ class SystemValues: return signame = self.signames[signum] if signum in self.signames else 'UNKNOWN' msg = 'Signal %s caused a tool exit, line %d' % (signame, frame.f_lineno) - sysvals.outputResult({'error':msg}) + self.outputResult({'error':msg}) sys.exit(3) def signalHandlerInit(self): capture = ['BUS', 'SYS', 'XCPU', 'XFSZ', 'PWR', 'HUP', 'INT', 'QUIT', - 'ILL', 'ABRT', 'FPE', 'SEGV', 'TERM', 'TSTP'] + 'ILL', 'ABRT', 'FPE', 'SEGV', 'TERM'] self.signames = dict() for i in capture: s = 'SIG'+i @@ -336,6 +356,8 @@ class SystemValues: self.outputResult({'error':msg}) sys.exit(1) return False + def usable(self, file): + return (os.path.exists(file) and os.path.getsize(file) > 0) def getExec(self, cmd): try: fp = Popen(['which', cmd], stdout=PIPE, stderr=PIPE).stdout @@ -389,12 +411,6 @@ class SystemValues: r = info['bios-release-date'] if 'bios-release-date' in info else '' self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | biosdate:%s | numcpu:%d | memsz:%d | memfr:%d' % \ (m, p, c, b, r, self.cpucount, self.memtotal, self.memfree) - try: - kcmd = open('/proc/cmdline', 'r').read().strip() - except: - kcmd = '' - if kcmd: - self.sysstamp += '\n# kparams | %s' % kcmd def printSystemInfo(self, fatal=False): self.rootCheck(True) out = dmidecode(self.mempath, fatal) @@ -441,6 +457,7 @@ class SystemValues: self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html' if not os.path.isdir(self.testdir): os.makedirs(self.testdir) + self.sudoUserchown(self.testdir) def getValueList(self, value): out = [] for i in value.split(','): @@ -486,7 +503,7 @@ class SystemValues: fp.close() self.dmesgstart = float(ktime) def getdmesg(self, testdata): - op = self.writeDatafileHeader(sysvals.dmesgfile, testdata) + op = self.writeDatafileHeader(self.dmesgfile, testdata) # store all new dmesg lines since initdmesg was called fp = Popen('dmesg', stdout=PIPE).stdout for line in fp: @@ -716,9 +733,10 @@ class SystemValues: if name == f: return True return False - def initFtrace(self): - self.printSystemInfo(False) - pprint('INITIALIZING FTRACE...') + def initFtrace(self, quiet=False): + if not quiet: + sysvals.printSystemInfo(False) + pprint('INITIALIZING FTRACE...') # turn trace off self.fsetVal('0', 'tracing_on') self.cleanupFtrace() @@ -746,7 +764,7 @@ class SystemValues: if tgtsize < 65536: tgtsize = int(self.fgetVal('buffer_size_kb')) * cpus break - pprint('Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus)) + self.vprint('Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus)) # initialize the callgraph trace if(self.usecallgraph): # set trace type @@ -782,7 +800,8 @@ class SystemValues: if self.usedevsrc: for name in self.dev_tracefuncs: self.defaultKprobe(name, self.dev_tracefuncs[name]) - pprint('INITIALIZING KPROBES...') + if not quiet: + pprint('INITIALIZING KPROBES...') self.addKprobes(self.verbose) if(self.usetraceevents): # turn trace events on @@ -827,21 +846,10 @@ class SystemValues: fw = test['fw'] if(fw): fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1])) - if 'mcelog' in test: - fp.write('# mcelog %s\n' % test['mcelog']) if 'turbo' in test: fp.write('# turbostat %s\n' % test['turbo']) - if 'bat' in test: - (a1, c1), (a2, c2) = test['bat'] - fp.write('# battery %s %d %s %d\n' % (a1, c1, a2, c2)) if 'wifi' in test: - wstr = [] - for wifi in test['wifi']: - tmp = [] - for key in sorted(wifi): - tmp.append('%s:%s' % (key, wifi[key])) - wstr.append('|'.join(tmp)) - fp.write('# wifi %s\n' % (','.join(wstr))) + fp.write('# wifi %s\n' % test['wifi']) if test['error'] or len(testdata) > 1: fp.write('# enter_sleep_error %s\n' % test['error']) return fp @@ -901,23 +909,7 @@ class SystemValues: def b64zip(self, data): out = base64.b64encode(codecs.encode(data.encode(), 'zlib')).decode() return out - def mcelog(self, clear=False): - cmd = self.getExec('mcelog') - if not cmd: - return '' - if clear: - call(cmd+' > /dev/null 2>&1', shell=True) - return '' - try: - fp = Popen([cmd], stdout=PIPE, stderr=PIPE).stdout - out = ascii(fp.read()).strip() - fp.close() - except: - return '' - if not out: - return '' - return self.b64zip(out) - def platforminfo(self): + def platforminfo(self, cmdafter): # add platform info on to a completed ftrace file if not os.path.exists(self.ftracefile): return False @@ -1001,31 +993,76 @@ class SystemValues: footer += '# platform-devinfo: %s\n' % self.b64zip(out) # add a line for each of these commands with their outputs - cmds = [ - ['pcidevices', 'lspci', '-tv'], - ['interrupts', 'cat', '/proc/interrupts'], - ['gpecounts', 'sh', '-c', 'grep -v invalid /sys/firmware/acpi/interrupts/gpe*'], - ] - for cargs in cmds: - name = cargs[0] - cmdline = ' '.join(cargs[1:]) - cmdpath = self.getExec(cargs[1]) - if not cmdpath: + for name, cmdline, info in cmdafter: + footer += '# platform-%s: %s | %s\n' % (name, cmdline, self.b64zip(info)) + + with self.openlog(self.ftracefile, 'a') as fp: + fp.write(footer) + return True + def commonPrefix(self, list): + if len(list) < 2: + return '' + prefix = list[0] + for s in list[1:]: + while s[:len(prefix)] != prefix and prefix: + prefix = prefix[:len(prefix)-1] + if not prefix: + break + if '/' in prefix and prefix[-1] != '/': + prefix = prefix[0:prefix.rfind('/')+1] + return prefix + def dictify(self, text, format): + out = dict() + header = True if format == 1 else False + delim = ' ' if format == 1 else ':' + for line in text.split('\n'): + if header: + header, out['@'] = False, line + continue + line = line.strip() + if delim in line: + data = line.split(delim, 1) + num = re.search(r'[\d]+', data[1]) + if format == 2 and num: + out[data[0].strip()] = num.group() + else: + out[data[0].strip()] = data[1] + return out + def cmdinfo(self, begin, debug=False): + out = [] + if begin: + self.cmd1 = dict() + for cargs in self.infocmds: + delta, name = cargs[0], cargs[1] + cmdline, cmdpath = ' '.join(cargs[2:]), self.getExec(cargs[2]) + if not cmdpath or (begin and not delta): continue - cmd = [cmdpath] + cargs[2:] try: - fp = Popen(cmd, stdout=PIPE, stderr=PIPE).stdout + fp = Popen([cmdpath]+cargs[3:], stdout=PIPE, stderr=PIPE).stdout info = ascii(fp.read()).strip() fp.close() except: continue - if not info: - continue - footer += '# platform-%s: %s | %s\n' % (name, cmdline, self.b64zip(info)) - - with self.openlog(self.ftracefile, 'a') as fp: - fp.write(footer) - return True + if not debug and begin: + self.cmd1[name] = self.dictify(info, delta) + elif not debug and delta and name in self.cmd1: + before, after = self.cmd1[name], self.dictify(info, delta) + dinfo = ('\t%s\n' % before['@']) if '@' in before else '' + prefix = self.commonPrefix(list(before.keys())) + for key in sorted(before): + if key in after and before[key] != after[key]: + title = key.replace(prefix, '') + if delta == 2: + dinfo += '\t%s : %s -> %s\n' % \ + (title, before[key].strip(), after[key].strip()) + else: + dinfo += '%10s (start) : %s\n%10s (after) : %s\n' % \ + (title, before[key], title, after[key]) + dinfo = '\tnothing changed' if not dinfo else dinfo.rstrip() + out.append((name, cmdline, dinfo)) + else: + out.append((name, cmdline, '\tnothing' if not info else info)) + return out def haveTurbostat(self): if not self.tstat: return False @@ -1035,8 +1072,8 @@ class SystemValues: fp = Popen([cmd, '-v'], stdout=PIPE, stderr=PIPE).stderr out = ascii(fp.read()).strip() fp.close() - if re.match('turbostat version [0-9\.]* .*', out): - sysvals.vprint(out) + if re.match('turbostat version .*', out): + self.vprint(out) return True return False def turbostat(self): @@ -1056,11 +1093,11 @@ class SystemValues: fp.close() if not keyline or not valline or len(keyline) != len(valline): errmsg = 'unrecognized turbostat output:\n'+rawout.strip() - sysvals.vprint(errmsg) - if not sysvals.verbose: + self.vprint(errmsg) + if not self.verbose: pprint(errmsg) return '' - if sysvals.verbose: + if self.verbose: pprint(rawout.strip()) out = [] for key in keyline: @@ -1068,30 +1105,36 @@ class SystemValues: val = valline[idx] out.append('%s=%s' % (key, val)) return '|'.join(out) - def checkWifi(self): - out = dict() - iwcmd, ifcmd = self.getExec('iwconfig'), self.getExec('ifconfig') - if not iwcmd or not ifcmd: - return out - fp = Popen(iwcmd, stdout=PIPE, stderr=PIPE).stdout - for line in fp: - m = re.match('(?P<dev>\S*) .* ESSID:(?P<ess>\S*)', ascii(line)) - if not m: + def wifiDetails(self, dev): + try: + info = open('/sys/class/net/%s/device/uevent' % dev, 'r').read().strip() + except: + return dev + vals = [dev] + for prop in info.split('\n'): + if prop.startswith('DRIVER=') or prop.startswith('PCI_ID='): + vals.append(prop.split('=')[-1]) + return ':'.join(vals) + def checkWifi(self, dev=''): + try: + w = open('/proc/net/wireless', 'r').read().strip() + except: + return '' + for line in reversed(w.split('\n')): + m = re.match(' *(?P<dev>.*): (?P<stat>[0-9a-f]*) .*', w.split('\n')[-1]) + if not m or (dev and dev != m.group('dev')): continue - out['device'] = m.group('dev') - if '"' in m.group('ess'): - out['essid'] = m.group('ess').strip('"') - break - fp.close() - if 'device' in out: - fp = Popen([ifcmd, out['device']], stdout=PIPE, stderr=PIPE).stdout - for line in fp: - m = re.match('.* inet (?P<ip>[0-9\.]*)', ascii(line)) - if m: - out['ip'] = m.group('ip') - break - fp.close() - return out + return m.group('dev') + return '' + def pollWifi(self, dev, timeout=60): + start = time.time() + while (time.time() - start) < timeout: + w = self.checkWifi(dev) + if w: + return '%s reconnected %.2f' % \ + (self.wifiDetails(dev), max(0, time.time() - start)) + time.sleep(0.01) + return '%s timeout %d' % (self.wifiDetails(dev), timeout) def errorSummary(self, errinfo, msg): found = False for entry in errinfo: @@ -1113,8 +1156,9 @@ class SystemValues: arr[j] = arr[j]\ .replace('\\', '\\\\').replace(']', '\]').replace('[', '\[')\ .replace('.', '\.').replace('+', '\+').replace('*', '\*')\ - .replace('(', '\(').replace(')', '\)') - mstr = ' '.join(arr) + .replace('(', '\(').replace(')', '\)').replace('}', '\}')\ + .replace('{', '\{') + mstr = ' *'.join(arr) entry = { 'line': msg, 'match': mstr, @@ -1122,6 +1166,44 @@ class SystemValues: 'urls': {self.hostname: [self.htmlfile]} } errinfo.append(entry) + def multistat(self, start, idx, finish): + if 'time' in self.multitest: + id = '%d Duration=%dmin' % (idx+1, self.multitest['time']) + else: + id = '%d/%d' % (idx+1, self.multitest['count']) + t = time.time() + if 'start' not in self.multitest: + self.multitest['start'] = self.multitest['last'] = t + self.multitest['total'] = 0.0 + pprint('TEST (%s) START' % id) + return + dt = t - self.multitest['last'] + if not start: + if idx == 0 and self.multitest['delay'] > 0: + self.multitest['total'] += self.multitest['delay'] + pprint('TEST (%s) COMPLETE -- Duration %.1fs' % (id, dt)) + return + self.multitest['total'] += dt + self.multitest['last'] = t + avg = self.multitest['total'] / idx + if 'time' in self.multitest: + left = finish - datetime.now() + left -= timedelta(microseconds=left.microseconds) + else: + left = timedelta(seconds=((self.multitest['count'] - idx) * int(avg))) + pprint('TEST (%s) START - Avg Duration %.1fs, Time left %s' % \ + (id, avg, str(left))) + def multiinit(self, c, d): + sz, unit = 'count', 'm' + if c.endswith('d') or c.endswith('h') or c.endswith('m'): + sz, unit, c = 'time', c[-1], c[:-1] + self.multitest['run'] = True + self.multitest[sz] = getArgInt('multi: n d (exec count)', c, 1, 1000000, False) + self.multitest['delay'] = getArgInt('multi: n d (delay between tests)', d, 0, 3600, False) + if unit == 'd': + self.multitest[sz] *= 1440 + elif unit == 'h': + self.multitest[sz] *= 60 sysvals = SystemValues() switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0'] @@ -1210,25 +1292,30 @@ class Data: 'resume_complete': {'order': 9, 'color': '#FFFFCC'}, } errlist = { - 'HWERROR' : '.*\[ *Hardware Error *\].*', - 'FWBUG' : '.*\[ *Firmware Bug *\].*', - 'BUG' : '.*BUG.*', - 'ERROR' : '.*ERROR.*', - 'WARNING' : '.*WARNING.*', - 'IRQ' : '.*genirq: .*', - 'TASKFAIL': '.*Freezing of tasks *.*', - 'ACPI' : '.*ACPI *(?P<b>[A-Za-z]*) *Error[: ].*', - 'DEVFAIL' : '.* failed to (?P<b>[a-z]*) async: .*', - 'DISKFULL': '.*No space left on device.*', - 'USBERR' : '.*usb .*device .*, error [0-9-]*', - 'ATAERR' : ' *ata[0-9\.]*: .*failed.*', - 'MEIERR' : ' *mei.*: .*failed.*', - 'TPMERR' : '(?i) *tpm *tpm[0-9]*: .*error.*', + 'HWERROR' : r'.*\[ *Hardware Error *\].*', + 'FWBUG' : r'.*\[ *Firmware Bug *\].*', + 'BUG' : r'(?i).*\bBUG\b.*', + 'ERROR' : r'(?i).*\bERROR\b.*', + 'WARNING' : r'(?i).*\bWARNING\b.*', + 'FAULT' : r'(?i).*\bFAULT\b.*', + 'FAIL' : r'(?i).*\bFAILED\b.*', + 'INVALID' : r'(?i).*\bINVALID\b.*', + 'CRASH' : r'(?i).*\bCRASHED\b.*', + 'IRQ' : r'.*\bgenirq: .*', + 'TASKFAIL': r'.*Freezing of tasks *.*', + 'ACPI' : r'.*\bACPI *(?P<b>[A-Za-z]*) *Error[: ].*', + 'DISKFULL': r'.*\bNo space left on device.*', + 'USBERR' : r'.*usb .*device .*, error [0-9-]*', + 'ATAERR' : r' *ata[0-9\.]*: .*failed.*', + 'MEIERR' : r' *mei.*: .*failed.*', + 'TPMERR' : r'(?i) *tpm *tpm[0-9]*: .*error.*', } def __init__(self, num): idchar = 'abcdefghij' self.start = 0.0 # test start self.end = 0.0 # test end + self.hwstart = 0 # rtc test start + self.hwend = 0 # rtc test end self.tSuspended = 0.0 # low-level suspend start self.tResumed = 0.0 # low-level resume start self.tKernSus = 0.0 # kernel level suspend start @@ -1240,10 +1327,8 @@ class Data: self.stamp = 0 self.outfile = '' self.kerror = False - self.battery = 0 - self.wifi = 0 + self.wifi = dict() self.turbostat = 0 - self.mcelog = 0 self.enterfail = '' self.currphase = '' self.pstl = dict() # process timeline @@ -1308,6 +1393,8 @@ class Data: continue dir = 'suspend' if t < self.tSuspended else 'resume' msg = m.group('msg') + if re.match('capability: warning: .*', msg): + continue for err in self.errlist: if re.match(self.errlist[err], msg): list.append((msg, err, dir, t, i, i)) @@ -1316,17 +1403,26 @@ class Data: msglist = [] for msg, type, dir, t, idx1, idx2 in list: msglist.append(msg) - sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t)) self.errorinfo[dir].append((type, t, idx1, idx2)) if self.kerror: sysvals.dmesglog = True if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf.close() return msglist - def setStart(self, time): + def setStart(self, time, msg=''): self.start = time - def setEnd(self, time): + if msg: + try: + self.hwstart = datetime.strptime(msg, sysvals.tmstart) + except: + self.hwstart = 0 + def setEnd(self, time, msg=''): self.end = time + if msg: + try: + self.hwend = datetime.strptime(msg, sysvals.tmend) + except: + self.hwend = 0 def isTraceEventOutsideDeviceCalls(self, pid, time): for phase in self.sortedPhases(): list = self.dmesg[phase]['list'] @@ -1546,6 +1642,14 @@ class Data: self.trimTime(tS, tL, left) self.tLow.append('%.0f'%(tL*1000)) lp = phase + def getMemTime(self): + if not self.hwstart or not self.hwend: + return + stime = (self.tSuspended - self.start) * 1000000 + rtime = (self.end - self.tResumed) * 1000000 + hws = self.hwstart + timedelta(microseconds=stime) + hwr = self.hwend - timedelta(microseconds=rtime) + self.tLow.append('%.0f'%((hwr - hws).total_seconds() * 1000)) def getTimeValues(self): sktime = (self.tSuspended - self.tKernSus) * 1000 rktime = (self.tKernRes - self.tResumed) * 1000 @@ -1883,9 +1987,9 @@ class Data: c = self.addProcessUsageEvent(ps, tres) if c > 0: sysvals.vprint('%25s (res): %d' % (ps, c)) - def handleEndMarker(self, time): + def handleEndMarker(self, time, msg=''): dm = self.dmesg - self.setEnd(time) + self.setEnd(time, msg) self.initDevicegroups() # give suspend_prepare an end if needed if 'suspend_prepare' in dm and dm['suspend_prepare']['end'] < 0: @@ -2071,7 +2175,7 @@ class FTraceLine: if not self.fevent: return False if sysvals.usetracemarkers: - if(self.name == 'SUSPEND START'): + if(self.name.startswith('SUSPEND START')): return True return False else: @@ -2084,7 +2188,7 @@ class FTraceLine: if not self.fevent: return False if sysvals.usetracemarkers: - if(self.name == 'RESUME COMPLETE'): + if(self.name.startswith('RESUME COMPLETE')): return True return False else: @@ -2444,7 +2548,7 @@ class Timeline: def createHeader(self, sv, stamp): if(not stamp['time']): return - self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \ + self.html += '<div class="version"><a href="https://01.org/pm-graph">%s v%s</a></div>' \ % (sv.title, sv.version) if sv.logmsg and sv.testlog: self.html += '<button id="showtest" class="logbtn btnfmt">log</button>' @@ -2670,14 +2774,11 @@ class TestProps: stampfmt = '# [a-z]*-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\ '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\ ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$' - batteryfmt = '^# battery (?P<a1>\w*) (?P<c1>\d*) (?P<a2>\w*) (?P<c2>\d*)' - wififmt = '^# wifi (?P<w>.*)' + wififmt = '^# wifi *(?P<d>\S*) *(?P<s>\S*) *(?P<t>[0-9\.]+).*' tstatfmt = '^# turbostat (?P<t>\S*)' - mcelogfmt = '^# mcelog (?P<m>\S*)' testerrfmt = '^# enter_sleep_error (?P<e>.*)' sysinfofmt = '^# sysinfo .*' cmdlinefmt = '^# command \| (?P<cmd>.*)' - kparamsfmt = '^# kparams \| (?P<kp>.*)' devpropfmt = '# Device Properties: .*' pinfofmt = '# platform-(?P<val>[a-z,A-Z,0-9]*): (?P<info>.*)' tracertypefmt = '# tracer: (?P<t>.*)' @@ -2695,11 +2796,8 @@ class TestProps: self.stamp = '' self.sysinfo = '' self.cmdline = '' - self.kparams = '' self.testerror = [] - self.mcelog = [] self.turbostat = [] - self.battery = [] self.wifi = [] self.fwdata = [] self.ftrace_line_fmt = self.ftrace_line_fmt_nop @@ -2721,21 +2819,12 @@ class TestProps: elif re.match(self.sysinfofmt, line): self.sysinfo = line return True - elif re.match(self.kparamsfmt, line): - self.kparams = line - return True elif re.match(self.cmdlinefmt, line): self.cmdline = line return True - elif re.match(self.mcelogfmt, line): - self.mcelog.append(line) - return True elif re.match(self.tstatfmt, line): self.turbostat.append(line) return True - elif re.match(self.batteryfmt, line): - self.battery.append(line) - return True elif re.match(self.wififmt, line): self.wifi.append(line) return True @@ -2749,6 +2838,8 @@ class TestProps: def parseStamp(self, data, sv): # global test data m = re.match(self.stampfmt, self.stamp) + if not self.stamp or not m: + doError('data does not include the expected stamp') data.stamp = {'time': '', 'host': '', 'mode': ''} dt = datetime(int(m.group('y'))+2000, int(m.group('m')), int(m.group('d')), int(m.group('H')), int(m.group('M')), @@ -2780,10 +2871,6 @@ class TestProps: m = re.match(self.cmdlinefmt, self.cmdline) if m: sv.cmdline = m.group('cmd') - if self.kparams: - m = re.match(self.kparamsfmt, self.kparams) - if m: - sv.kparams = m.group('kp') if not sv.stamp: sv.stamp = data.stamp # firmware data @@ -2793,26 +2880,18 @@ class TestProps: data.fwSuspend, data.fwResume = int(m.group('s')), int(m.group('r')) if(data.fwSuspend > 0 or data.fwResume > 0): data.fwValid = True - # mcelog data - if len(self.mcelog) > data.testnumber: - m = re.match(self.mcelogfmt, self.mcelog[data.testnumber]) - if m: - data.mcelog = sv.b64unzip(m.group('m')) # turbostat data if len(self.turbostat) > data.testnumber: m = re.match(self.tstatfmt, self.turbostat[data.testnumber]) if m: data.turbostat = m.group('t') - # battery data - if len(self.battery) > data.testnumber: - m = re.match(self.batteryfmt, self.battery[data.testnumber]) - if m: - data.battery = m.groups() # wifi data if len(self.wifi) > data.testnumber: m = re.match(self.wififmt, self.wifi[data.testnumber]) if m: - data.wifi = m.group('w') + data.wifi = {'dev': m.group('d'), 'stat': m.group('s'), + 'time': float(m.group('t'))} + data.stamp['wifi'] = m.group('d') # sleep mode enter errors if len(self.testerror) > data.testnumber: m = re.match(self.testerrfmt, self.testerror[data.testnumber]) @@ -3012,13 +3091,13 @@ def appendIncompleteTraceLog(testruns): if(t.startMarker()): data = testrun[testidx].data tp.parseStamp(data, sysvals) - data.setStart(t.time) + data.setStart(t.time, t.name) continue if(not data): continue # find the end of resume if(t.endMarker()): - data.setEnd(t.time) + data.setEnd(t.time, t.name) testidx += 1 if(testidx >= testcnt): break @@ -3081,7 +3160,7 @@ def parseTraceLog(live=False): doError('%s does not exist' % sysvals.ftracefile) if not live: sysvals.setupAllKprobes() - ksuscalls = ['pm_prepare_console'] + ksuscalls = ['ksys_sync', 'pm_prepare_console'] krescalls = ['pm_restore_console'] tracewatch = ['irq_wakeup'] if sysvals.usekprobes: @@ -3094,7 +3173,7 @@ def parseTraceLog(live=False): testruns = [] testdata = [] testrun = 0 - data = 0 + data, limbo = 0, True tf = sysvals.openlog(sysvals.ftracefile, 'r') phase = 'suspend_prepare' for line in tf: @@ -3141,16 +3220,16 @@ def parseTraceLog(live=False): continue # find the start of suspend if(t.startMarker()): - data = Data(len(testdata)) + data, limbo = Data(len(testdata)), False testdata.append(data) testrun = TestRun(data) testruns.append(testrun) tp.parseStamp(data, sysvals) - data.setStart(t.time) + data.setStart(t.time, t.name) data.first_suspend_prepare = True phase = data.setPhase('suspend_prepare', t.time, True) continue - if(not data): + if(not data or limbo): continue # process cpu exec line if t.type == 'tracing_mark_write': @@ -3167,14 +3246,16 @@ def parseTraceLog(live=False): continue # find the end of resume if(t.endMarker()): - data.handleEndMarker(t.time) + if data.tKernRes == 0: + data.tKernRes = t.time + data.handleEndMarker(t.time, t.name) if(not sysvals.usetracemarkers): # no trace markers? then quit and be sure to finish recording # the event we used to trigger resume end if('thaw_processes' in testrun.ttemp and len(testrun.ttemp['thaw_processes']) > 0): # if an entry exists, assume this is its end testrun.ttemp['thaw_processes'][-1]['end'] = t.time - break + limbo = True continue # trace event processing if(t.fevent): @@ -3197,7 +3278,7 @@ def parseTraceLog(live=False): # -- phase changes -- # start of kernel suspend if(re.match('suspend_enter\[.*', t.name)): - if(isbegin): + if(isbegin and data.tKernSus == 0): data.tKernSus = t.time continue # suspend_prepare start @@ -3225,7 +3306,7 @@ def parseTraceLog(live=False): elif(re.match('machine_suspend\[.*', t.name)): if(isbegin): lp = data.lastPhase() - if lp == 'resume_machine': + if lp.startswith('resume_machine'): data.dmesg[lp]['end'] = t.time phase = data.setPhase('suspend_machine', data.dmesg[lp]['end'], True) data.setPhase(phase, t.time, False) @@ -3320,7 +3401,8 @@ def parseTraceLog(live=False): 'proc': m_proc, }) # start of kernel resume - if(phase == 'suspend_prepare' and kprobename in ksuscalls): + if(data.tKernSus == 0 and phase == 'suspend_prepare' \ + and kprobename in ksuscalls): data.tKernSus = t.time elif(t.freturn): if(key not in tp.ktemp) or len(tp.ktemp[key]) < 1: @@ -3355,7 +3437,7 @@ def parseTraceLog(live=False): sysvals.vprint('WARNING: ftrace start marker is missing') if data and not data.devicegroups: sysvals.vprint('WARNING: ftrace end marker is missing') - data.handleEndMarker(t.time) + data.handleEndMarker(t.time, t.name) if sysvals.suspendmode == 'command': for test in testruns: @@ -3476,6 +3558,10 @@ def parseTraceLog(live=False): data.fwValid = False sysvals.vprint('WARNING: phase "%s" is missing!' % p) lp = p + if not terr and 'dev' in data.wifi and data.wifi['stat'] == 'timeout': + terr = '%s%s failed in wifi_resume <i>(%s %.0fs timeout)</i>' % \ + (sysvals.suspendmode, tn, data.wifi['dev'], data.wifi['time']) + error.append(terr) if not terr and data.enterfail: pprint('test%s FAILED: enter %s failed with %s' % (tn, sysvals.suspendmode, data.enterfail)) terr = 'test%s failed to enter %s mode' % (tn, sysvals.suspendmode) @@ -3933,7 +4019,7 @@ def createHTMLSummarySimple(testruns, htmlfile, title): tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [dict(), dict()] iMin, iMed, iMax = [0, 0], [0, 0], [0, 0] num = 0 - useturbo = False + useturbo = usewifi = False lastmode = '' cnt = dict() for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])): @@ -3952,17 +4038,17 @@ def createHTMLSummarySimple(testruns, htmlfile, title): tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [dict(), dict()] iMin, iMed, iMax = [0, 0], [0, 0], [0, 0] num = 0 - pkgpc10 = syslpi = '' + pkgpc10 = syslpi = wifi = '' if 'pkgpc10' in data and 'syslpi' in data: - pkgpc10 = data['pkgpc10'] - syslpi = data['syslpi'] - useturbo = True + pkgpc10, syslpi, useturbo = data['pkgpc10'], data['syslpi'], True + if 'wifi' in data: + wifi, usewifi = data['wifi'], True res = data['result'] tVal = [float(data['suspend']), float(data['resume'])] list[mode]['data'].append([data['host'], data['kernel'], data['time'], tVal[0], tVal[1], data['url'], res, data['issues'], data['sus_worst'], data['sus_worsttime'], - data['res_worst'], data['res_worsttime'], pkgpc10, syslpi]) + data['res_worst'], data['res_worsttime'], pkgpc10, syslpi, wifi]) idx = len(list[mode]['data']) - 1 if res.startswith('fail in'): res = 'fail' @@ -4002,7 +4088,12 @@ def createHTMLSummarySimple(testruns, htmlfile, title): td = '\t<td>{0}</td>\n' tdh = '\t<td{1}>{0}</td>\n' tdlink = '\t<td><a href="{0}">html</a></td>\n' - colspan = '14' if useturbo else '12' + cols = 12 + if useturbo: + cols += 2 + if usewifi: + cols += 1 + colspan = '%d' % cols # table header html += '<table>\n<tr>\n' + th.format('#') +\ @@ -4013,6 +4104,8 @@ def createHTMLSummarySimple(testruns, htmlfile, title): th.format('Worst Resume Device') + th.format('RD Time') if useturbo: html += th.format('PkgPC10') + th.format('SysLPI') + if usewifi: + html += th.format('Wifi') html += th.format('Detail')+'</tr>\n' # export list into html head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\ @@ -4076,6 +4169,8 @@ def createHTMLSummarySimple(testruns, htmlfile, title): if useturbo: html += td.format(d[12]) # pkg_pc10 html += td.format(d[13]) # syslpi + if usewifi: + html += td.format(d[14]) # wifi html += tdlink.format(d[5]) if d[5] else td.format('') # url html += '</tr>\n' num += 1 @@ -4224,6 +4319,8 @@ def createHTML(testruns, testfail): kerror = True if(sysvals.suspendmode in ['freeze', 'standby']): data.trimFreezeTime(testruns[-1].tSuspended) + else: + data.getMemTime() # html function templates html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">{2}→</div>\n' @@ -4242,13 +4339,10 @@ def createHTML(testruns, testfail): '<td class="green">Execution Time: <b>{0} ms</b></td>'\ '<td class="yellow">Command: <b>{1}</b></td>'\ '</tr>\n</table>\n' - html_timegroups = '<table class="time2">\n<tr>'\ - '<td class="green" title="time from kernel enter_state({5}) to firmware mode [kernel time only]">{4}Kernel Suspend: {0} ms</td>'\ - '<td class="purple">{4}Firmware Suspend: {1} ms</td>'\ - '<td class="purple">{4}Firmware Resume: {2} ms</td>'\ - '<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\ - '</tr>\n</table>\n' html_fail = '<table class="testfail"><tr><td>{0}</td></tr></table>\n' + html_kdesc = '<td class="{3}" title="time spent in kernel execution">{0}Kernel {2}: {1} ms</td>' + html_fwdesc = '<td class="{3}" title="time spent in firmware">{0}Firmware {2}: {1} ms</td>' + html_wifdesc = '<td class="yellow" title="time for wifi to reconnect after resume complete ({2})">{0}Wifi Resume: {1}</td>' # html format variables scaleH = 20 @@ -4264,13 +4358,10 @@ def createHTML(testruns, testfail): # Generate the header for this timeline for data in testruns: tTotal = data.end - data.start - sktime, rktime = data.getTimeValues() if(tTotal == 0): doError('No timeline data') - if(len(data.tLow) > 0): - low_time = '+'.join(data.tLow) if sysvals.suspendmode == 'command': - run_time = '%.0f'%((data.end-data.start)*1000) + run_time = '%.0f' % (tTotal * 1000) if sysvals.testcommand: testdesc = sysvals.testcommand else: @@ -4279,43 +4370,55 @@ def createHTML(testruns, testfail): testdesc = ordinal(data.testnumber+1)+' '+testdesc thtml = html_timetotal3.format(run_time, testdesc) devtl.html += thtml - elif data.fwValid: - suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0)) - resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0)) - testdesc1 = 'Total' - testdesc2 = '' - stitle = 'time from kernel enter_state(%s) to low-power mode [kernel & firmware time]' % sysvals.suspendmode - rtitle = 'time from low-power mode to return from kernel enter_state(%s) [firmware & kernel time]' % sysvals.suspendmode - if(len(testruns) > 1): - testdesc1 = testdesc2 = ordinal(data.testnumber+1) - testdesc2 += ' ' - if(len(data.tLow) == 0): - thtml = html_timetotal.format(suspend_time, \ - resume_time, testdesc1, stitle, rtitle) - else: - thtml = html_timetotal2.format(suspend_time, low_time, \ - resume_time, testdesc1, stitle, rtitle) - devtl.html += thtml + continue + # typical full suspend/resume header + stot, rtot = sktime, rktime = data.getTimeValues() + ssrc, rsrc, testdesc, testdesc2 = ['kernel'], ['kernel'], 'Kernel', '' + if data.fwValid: + stot += (data.fwSuspend/1000000.0) + rtot += (data.fwResume/1000000.0) + ssrc.append('firmware') + rsrc.append('firmware') + testdesc = 'Total' + if 'time' in data.wifi and data.wifi['stat'] != 'timeout': + rtot += data.end - data.tKernRes + (data.wifi['time'] * 1000.0) + rsrc.append('wifi') + testdesc = 'Total' + suspend_time, resume_time = '%.3f' % stot, '%.3f' % rtot + stitle = 'time from kernel suspend start to %s mode [%s time]' % \ + (sysvals.suspendmode, ' & '.join(ssrc)) + rtitle = 'time from %s mode to kernel resume complete [%s time]' % \ + (sysvals.suspendmode, ' & '.join(rsrc)) + if(len(testruns) > 1): + testdesc = testdesc2 = ordinal(data.testnumber+1) + testdesc2 += ' ' + if(len(data.tLow) == 0): + thtml = html_timetotal.format(suspend_time, \ + resume_time, testdesc, stitle, rtitle) + else: + low_time = '+'.join(data.tLow) + thtml = html_timetotal2.format(suspend_time, low_time, \ + resume_time, testdesc, stitle, rtitle) + devtl.html += thtml + if not data.fwValid and 'dev' not in data.wifi: + continue + # extra detail when the times come from multiple sources + thtml = '<table class="time2">\n<tr>' + thtml += html_kdesc.format(testdesc2, '%.3f'%sktime, 'Suspend', 'green') + if data.fwValid: sftime = '%.3f'%(data.fwSuspend / 1000000.0) rftime = '%.3f'%(data.fwResume / 1000000.0) - devtl.html += html_timegroups.format('%.3f'%sktime, \ - sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode) - else: - suspend_time = '%.3f' % sktime - resume_time = '%.3f' % rktime - testdesc = 'Kernel' - stitle = 'time from kernel enter_state(%s) to firmware mode [kernel time only]' % sysvals.suspendmode - rtitle = 'time from firmware mode to return from kernel enter_state(%s) [kernel time only]' % sysvals.suspendmode - if(len(testruns) > 1): - testdesc = ordinal(data.testnumber+1)+' '+testdesc - if(len(data.tLow) == 0): - thtml = html_timetotal.format(suspend_time, \ - resume_time, testdesc, stitle, rtitle) + thtml += html_fwdesc.format(testdesc2, sftime, 'Suspend', 'green') + thtml += html_fwdesc.format(testdesc2, rftime, 'Resume', 'yellow') + thtml += html_kdesc.format(testdesc2, '%.3f'%rktime, 'Resume', 'yellow') + if 'time' in data.wifi: + if data.wifi['stat'] != 'timeout': + wtime = '%.0f ms'%(data.end - data.tKernRes + (data.wifi['time'] * 1000.0)) else: - thtml = html_timetotal2.format(suspend_time, low_time, \ - resume_time, testdesc, stitle, rtitle) - devtl.html += thtml - + wtime = 'TIMEOUT' + thtml += html_wifdesc.format(testdesc2, wtime, data.wifi['dev']) + thtml += '</tr>\n</table>\n' + devtl.html += thtml if testfail: devtl.html += html_fail.format(testfail) @@ -5082,28 +5185,32 @@ def setRuntimeSuspend(before=True): # Description: # Execute system suspend through the sysfs interface, then copy the output # dmesg and ftrace files to the test output directory. -def executeSuspend(): +def executeSuspend(quiet=False): pm = ProcessMonitor() tp = sysvals.tpath - wifi = sysvals.checkWifi() + if sysvals.wifi: + wifi = sysvals.checkWifi() testdata = [] - battery = True if getBattery() else False # run these commands to prepare the system for suspend if sysvals.display: - pprint('SET DISPLAY TO %s' % sysvals.display.upper()) + if not quiet: + pprint('SET DISPLAY TO %s' % sysvals.display.upper()) displayControl(sysvals.display) time.sleep(1) if sysvals.sync: - pprint('SYNCING FILESYSTEMS') + if not quiet: + pprint('SYNCING FILESYSTEMS') call('sync', shell=True) # mark the start point in the kernel ring buffer just as we start sysvals.initdmesg() # start ftrace if(sysvals.usecallgraph or sysvals.usetraceevents): - pprint('START TRACING') + if not quiet: + pprint('START TRACING') sysvals.fsetVal('1', 'tracing_on') if sysvals.useprocmon: pm.start() + sysvals.cmdinfo(True) # execute however many s/r runs requested for count in range(1,sysvals.execcount+1): # x2delay in between test runs @@ -5119,15 +5226,14 @@ def executeSuspend(): pprint('SUSPEND START') else: pprint('SUSPEND START (press a key to resume)') - sysvals.mcelog(True) - bat1 = getBattery() if battery else False # set rtcwake if(sysvals.rtcwake): - pprint('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime) + if not quiet: + pprint('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime) sysvals.rtcWakeAlarmOn() # start of suspend trace marker if(sysvals.usecallgraph or sysvals.usetraceevents): - sysvals.fsetVal('SUSPEND START', 'trace_marker') + sysvals.fsetVal(datetime.now().strftime(sysvals.tmstart), 'trace_marker') # predelay delay if(count == 1 and sysvals.predelay > 0): sysvals.fsetVal('WAIT %d' % sysvals.predelay, 'trace_marker') @@ -5174,37 +5280,33 @@ def executeSuspend(): # return from suspend pprint('RESUME COMPLETE') if(sysvals.usecallgraph or sysvals.usetraceevents): - sysvals.fsetVal('RESUME COMPLETE', 'trace_marker') + sysvals.fsetVal(datetime.now().strftime(sysvals.tmend), 'trace_marker') + if sysvals.wifi and wifi: + tdata['wifi'] = sysvals.pollWifi(wifi) if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'): tdata['fw'] = getFPDT(False) - mcelog = sysvals.mcelog() - if mcelog: - tdata['mcelog'] = mcelog - bat2 = getBattery() if battery else False - if battery and bat1 and bat2: - tdata['bat'] = (bat1, bat2) - if 'device' in wifi and 'ip' in wifi: - tdata['wifi'] = (wifi, sysvals.checkWifi()) testdata.append(tdata) + cmdafter = sysvals.cmdinfo(False) # stop ftrace if(sysvals.usecallgraph or sysvals.usetraceevents): if sysvals.useprocmon: pm.stop() sysvals.fsetVal('0', 'tracing_on') # grab a copy of the dmesg output - pprint('CAPTURING DMESG') + if not quiet: + pprint('CAPTURING DMESG') sysvals.getdmesg(testdata) # grab a copy of the ftrace output if(sysvals.usecallgraph or sysvals.usetraceevents): - pprint('CAPTURING TRACE') + if not quiet: + pprint('CAPTURING TRACE') op = sysvals.writeDatafileHeader(sysvals.ftracefile, testdata) fp = open(tp+'trace', 'r') for line in fp: op.write(line) op.close() sysvals.fsetVal('', 'trace') - sysvals.platforminfo() - return testdata + sysvals.platforminfo(cmdafter) def readFile(file): if os.path.islink(file): @@ -5447,25 +5549,6 @@ def dmidecode(mempath, fatal=False): count += 1 return out -def getBattery(): - p, charge, bat = '/sys/class/power_supply', 0, {} - if not os.path.exists(p): - return False - for d in os.listdir(p): - type = sysvals.getVal(os.path.join(p, d, 'type')).strip().lower() - if type != 'battery': - continue - for v in ['status', 'energy_now', 'capacity_now']: - bat[v] = sysvals.getVal(os.path.join(p, d, v)).strip().lower() - break - if 'status' not in bat: - return False - ac = False if 'discharging' in bat['status'] else True - for v in ['energy_now', 'capacity_now']: - if v in bat and bat[v]: - charge = int(bat[v]) - return (ac, charge) - def displayControl(cmd): xset, ret = 'timeout 10 xset -d :0.0 {0}', 0 if sysvals.sudouser: @@ -5715,6 +5798,17 @@ def statusCheck(probecheck=False): status = 'rtcwake is not properly supported' pprint(' is rtcwake supported: %s' % res) + # check info commands + pprint(' optional commands this tool may use for info:') + no = sysvals.colorText('MISSING') + yes = sysvals.colorText('FOUND', 32) + for c in ['turbostat', 'mcelog', 'lspci', 'lsusb']: + if c == 'turbostat': + res = yes if sysvals.haveTurbostat() else no + else: + res = yes if sysvals.getExec(c) else no + pprint(' %s: %s' % (c, res)) + if not probecheck: return status @@ -5780,8 +5874,9 @@ def getArgFloat(name, args, min, max, main=True): doError(name+': value should be between %f and %f' % (min, max), True) return val -def processData(live=False): - pprint('PROCESSING DATA') +def processData(live=False, quiet=False): + if not quiet: + pprint('PROCESSING DATA') sysvals.vprint('usetraceevents=%s, usetracemarkers=%s, usekprobes=%s' % \ (sysvals.usetraceevents, sysvals.usetracemarkers, sysvals.usekprobes)) error = '' @@ -5796,20 +5891,17 @@ def processData(live=False): parseKernelLog(data) if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)): appendIncompleteTraceLog(testruns) + if not sysvals.stamp: + pprint('ERROR: data does not include the expected stamp') + return (testruns, {'error': 'timeline generation failed'}) shown = ['bios', 'biosdate', 'cpu', 'host', 'kernel', 'man', 'memfr', - 'memsz', 'mode', 'numcpu', 'plat', 'time'] + 'memsz', 'mode', 'numcpu', 'plat', 'time', 'wifi'] sysvals.vprint('System Info:') for key in sorted(sysvals.stamp): if key in shown: sysvals.vprint(' %-8s : %s' % (key.upper(), sysvals.stamp[key])) - if sysvals.kparams: - sysvals.vprint('Kparams:\n %s' % sysvals.kparams) sysvals.vprint('Command:\n %s' % sysvals.cmdline) for data in testruns: - if data.mcelog: - sysvals.vprint('MCELOG Data:') - for line in data.mcelog.split('\n'): - sysvals.vprint(' %s' % line) if data.turbostat: idx, s = 0, 'Turbostat:\n ' for val in data.turbostat.split('|'): @@ -5819,23 +5911,13 @@ def processData(live=False): s += '\n ' s += val + ' ' sysvals.vprint(s) - if data.battery: - a1, c1, a2, c2 = data.battery - s = 'Battery:\n Before - AC: %s, Charge: %d\n After - AC: %s, Charge: %d' % \ - (a1, int(c1), a2, int(c2)) - sysvals.vprint(s) - if data.wifi: - w = data.wifi.replace('|', ' ').split(',') - s = 'Wifi:\n Before %s\n After %s' % \ - (w[0], w[1]) - sysvals.vprint(s) data.printDetails() - if len(sysvals.platinfo) > 0: - sysvals.vprint('\nPlatform Info:') - for info in sysvals.platinfo: - sysvals.vprint(info[0]+' - '+info[1]) - sysvals.vprint(info[2]) - sysvals.vprint('') + if len(sysvals.platinfo) > 0: + sysvals.vprint('\nPlatform Info:') + for info in sysvals.platinfo: + sysvals.vprint('[%s - %s]' % (info[0], info[1])) + sysvals.vprint(info[2]) + sysvals.vprint('') if sysvals.cgdump: for data in testruns: data.debugPrint() @@ -5845,7 +5927,8 @@ def processData(live=False): return (testruns, {'error': 'timeline generation failed'}) sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) createHTML(testruns, error) - pprint('DONE') + if not quiet: + pprint('DONE') data = testruns[0] stamp = data.stamp stamp['suspend'], stamp['resume'] = data.getTimeValues() @@ -5872,31 +5955,28 @@ def rerunTest(htmlfile=''): doError('a directory already exists with this name: %s' % sysvals.htmlfile) elif not os.access(sysvals.htmlfile, os.W_OK): doError('missing permission to write to %s' % sysvals.htmlfile) - testruns, stamp = processData(False) - sysvals.logmsg = '' + testruns, stamp = processData() + sysvals.resetlog() return stamp # Function: runTest # Description: # execute a suspend/resume, gather the logs, and generate the output -def runTest(n=0): +def runTest(n=0, quiet=False): # prepare for the test - sysvals.initFtrace() + sysvals.initFtrace(quiet) sysvals.initTestOutput('suspend') # execute the test - testdata = executeSuspend() + executeSuspend(quiet) sysvals.cleanupFtrace() if sysvals.skiphtml: + sysvals.outputResult({}, n) sysvals.sudoUserchown(sysvals.testdir) return - if not testdata[0]['error']: - testruns, stamp = processData(True) - for data in testruns: - del data - else: - stamp = testdata[0] - + testruns, stamp = processData(True, quiet) + for data in testruns: + del data sysvals.sudoUserchown(sysvals.testdir) sysvals.outputResult(stamp, n) if 'error' in stamp: @@ -5904,13 +5984,14 @@ def runTest(n=0): return 0 def find_in_html(html, start, end, firstonly=True): - n, out = 0, [] - while n < len(html): - m = re.search(start, html[n:]) + n, cnt, out = 0, len(html), [] + while n < cnt: + e = cnt if (n + 10000 > cnt or n == 0) else n + 10000 + m = re.search(start, html[n:e]) if not m: break i = m.end() - m = re.search(end, html[n+i:]) + m = re.search(end, html[n+i:e]) if not m: break j = m.start() @@ -5945,7 +6026,7 @@ def data_from_html(file, outpath, issues, fulldetail=False): tstr = dt.strftime('%Y/%m/%d %H:%M:%S') error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>') if error: - m = re.match('[a-z]* failed in (?P<p>[a-z0-9_]*) phase', error) + m = re.match('[a-z0-9]* failed in (?P<p>\S*).*', error) if m: result = 'fail in %s' % m.group('p') else: @@ -5974,6 +6055,9 @@ def data_from_html(file, outpath, issues, fulldetail=False): elist[err[0]] += 1 for i in elist: ilist.append('%sx%d' % (i, elist[i]) if elist[i] > 1 else i) + wifi = find_in_html(html, 'Wifi Resume: ', '</td>') + if wifi: + extra['wifi'] = wifi low = find_in_html(html, 'freeze time: <b>', ' ms</b>') if low and '|' in low: issue = 'FREEZEx%d' % len(low.split('|')) @@ -6048,13 +6132,15 @@ def genHtml(subdir, force=False): for dirname, dirnames, filenames in os.walk(subdir): sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = '' for filename in filenames: - if(re.match('.*_dmesg.txt', filename)): - sysvals.dmesgfile = os.path.join(dirname, filename) - elif(re.match('.*_ftrace.txt', filename)): - sysvals.ftracefile = os.path.join(dirname, filename) + file = os.path.join(dirname, filename) + if sysvals.usable(file): + if(re.match('.*_dmesg.txt', filename)): + sysvals.dmesgfile = file + elif(re.match('.*_ftrace.txt', filename)): + sysvals.ftracefile = file sysvals.setOutputFile() - if sysvals.ftracefile and sysvals.htmlfile and \ - (force or not os.path.exists(sysvals.htmlfile)): + if (sysvals.dmesgfile or sysvals.ftracefile) and sysvals.htmlfile and \ + (force or not sysvals.usable(sysvals.htmlfile)): pprint('FTRACE: %s' % sysvals.ftracefile) if sysvals.dmesgfile: pprint('DMESG : %s' % sysvals.dmesgfile) @@ -6169,9 +6255,9 @@ def configFromFile(file): sysvals.cgtest = getArgInt('cgtest', value, 0, 1, False) elif(option == 'cgphase'): d = Data(0) - if value not in d.sortedPhases(): + if value not in d.phasedef: doError('invalid phase --> (%s: %s), valid phases are %s'\ - % (option, value, d.sortedPhases()), True) + % (option, value, d.phasedef.keys()), True) sysvals.cgphase = value elif(option == 'fadd'): file = sysvals.configFile(value) @@ -6184,9 +6270,7 @@ def configFromFile(file): nums = value.split() if len(nums) != 2: doError('multi requires 2 integers (exec_count and delay)', True) - sysvals.multitest['run'] = True - sysvals.multitest['count'] = getArgInt('multi: n d (exec count)', nums[0], 2, 1000000, False) - sysvals.multitest['delay'] = getArgInt('multi: n d (delay between tests)', nums[1], 0, 3600, False) + sysvals.multiinit(nums[0], nums[1]) elif(option == 'devicefilter'): sysvals.setDeviceFilter(value) elif(option == 'expandcg'): @@ -6342,6 +6426,7 @@ def printHelp(): ' -srgap Add a visible gap in the timeline between sus/res (default: disabled)\n'\ ' -skiphtml Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\ ' -result fn Export a results table to a text file for parsing.\n'\ + ' -wifi If a wifi connection is available, check that it reconnects after resume.\n'\ ' [testprep]\n'\ ' -sync Sync the filesystems before starting the test\n'\ ' -rs on/off Enable/disable runtime suspend for all devices, restore all after test\n'\ @@ -6356,8 +6441,10 @@ def printHelp(): ' -predelay t Include t ms delay before 1st suspend (default: 0 ms)\n'\ ' -postdelay t Include t ms delay after last resume (default: 0 ms)\n'\ ' -mindev ms Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)\n'\ - ' -multi n d Execute <n> consecutive tests at <d> seconds intervals. The outputs will\n'\ - ' be created in a new subdirectory with a summary page.\n'\ + ' -multi n d Execute <n> consecutive tests at <d> seconds intervals. If <n> is followed\n'\ + ' by a "d", "h", or "m" execute for <n> days, hours, or mins instead.\n'\ + ' The outputs will be created in a new subdirectory with a summary page.\n'\ + ' -maxfail n Abort a -multi run after n consecutive fails (default is 0 = never abort)\n'\ ' [debug]\n'\ ' -f Use ftrace to create device callgraphs (default: disabled)\n'\ ' -ftop Use ftrace on the top level call: "%s" (default: disabled)\n'\ @@ -6379,11 +6466,11 @@ def printHelp(): ' -modes List available suspend modes\n'\ ' -status Test to see if the system is enabled to run this tool\n'\ ' -fpdt Print out the contents of the ACPI Firmware Performance Data Table\n'\ - ' -battery Print out battery info (if available)\n'\ - ' -wifi Print out wifi connection info (if wireless-tools and device exists)\n'\ + ' -wificheck Print out wifi connection info\n'\ ' -x<mode> Test xset by toggling the given mode (on/off/standby/suspend)\n'\ ' -sysinfo Print out system info extracted from BIOS\n'\ ' -devinfo Print out the pm settings of all devices which support runtime suspend\n'\ + ' -cmdinfo Print out all the platform info collected before and after suspend/resume\n'\ ' -flist Print the list of functions currently being captured in ftrace\n'\ ' -flistall Print all functions capable of being captured in ftrace\n'\ ' -summary dir Create a summary of tests in this dir [-genhtml builds missing html]\n'\ @@ -6399,8 +6486,8 @@ if __name__ == '__main__': genhtml = False cmd = '' simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', - '-devinfo', '-status', '-battery', '-xon', '-xoff', '-xstandby', - '-xsuspend', '-xinit', '-xreset', '-xstat', '-wifi'] + '-devinfo', '-status', '-xon', '-xoff', '-xstandby', '-xsuspend', + '-xinit', '-xreset', '-xstat', '-wificheck', '-cmdinfo'] if '-f' in sys.argv: sysvals.cgskip = sysvals.configFile('cgskip.txt') # loop through the command line arguments @@ -6462,8 +6549,15 @@ if __name__ == '__main__': sysvals.usedevsrc = True elif(arg == '-sync'): sysvals.sync = True + elif(arg == '-wifi'): + sysvals.wifi = True elif(arg == '-gzip'): sysvals.gzip = True + elif(arg == '-info'): + try: + val = next(args) + except: + doError('-info requires one string argument', True) elif(arg == '-rs'): try: val = next(args) @@ -6555,10 +6649,14 @@ if __name__ == '__main__': sysvals.cgexp = True elif(arg == '-srgap'): sysvals.srgap = 5 + elif(arg == '-maxfail'): + sysvals.maxfail = getArgInt('-maxfail', args, 0, 1000000) elif(arg == '-multi'): - sysvals.multitest['run'] = True - sysvals.multitest['count'] = getArgInt('-multi n d (exec count)', args, 2, 1000000) - sysvals.multitest['delay'] = getArgInt('-multi n d (delay between tests)', args, 0, 3600) + try: + c, d = next(args), next(args) + except: + doError('-multi requires two values', True) + sysvals.multiinit(c, d) elif(arg == '-o'): try: val = next(args) @@ -6655,13 +6753,6 @@ if __name__ == '__main__': elif(cmd == 'fpdt'): if not getFPDT(True): ret = 1 - elif(cmd == 'battery'): - out = getBattery() - if out: - pprint('AC Connect : %s\nBattery Charge: %d' % out) - else: - pprint('no battery found') - ret = 1 elif(cmd == 'sysinfo'): sysvals.printSystemInfo(True) elif(cmd == 'devinfo'): @@ -6679,13 +6770,15 @@ if __name__ == '__main__': ret = displayControl(cmd[1:]) elif(cmd == 'xstat'): pprint('Display Status: %s' % displayControl('stat').upper()) - elif(cmd == 'wifi'): - out = sysvals.checkWifi() - if 'device' not in out: - pprint('WIFI interface not found') + elif(cmd == 'wificheck'): + dev = sysvals.checkWifi() + if dev: + print('%s is connected' % sysvals.wifiDetails(dev)) else: - for key in sorted(out): - pprint('%6s: %s' % (key.upper(), out[key])) + print('No wifi connection found') + elif(cmd == 'cmdinfo'): + for out in sysvals.cmdinfo(False, True): + print('[%s - %s]\n%s\n' % out) sys.exit(ret) # if instructed, re-analyze existing data files @@ -6720,24 +6813,38 @@ if __name__ == '__main__': setRuntimeSuspend(True) if sysvals.display: displayControl('init') - ret = 0 + failcnt, ret = 0, 0 if sysvals.multitest['run']: # run multiple tests in a separate subdirectory if not sysvals.outdir: - s = 'suspend-x%d' % sysvals.multitest['count'] - sysvals.outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S') + if 'time' in sysvals.multitest: + s = '-%dm' % sysvals.multitest['time'] + else: + s = '-x%d' % sysvals.multitest['count'] + sysvals.outdir = datetime.now().strftime('suspend-%y%m%d-%H%M%S'+s) if not os.path.isdir(sysvals.outdir): os.makedirs(sysvals.outdir) + sysvals.sudoUserchown(sysvals.outdir) + finish = datetime.now() + if 'time' in sysvals.multitest: + finish += timedelta(minutes=sysvals.multitest['time']) for i in range(sysvals.multitest['count']): - if(i != 0): + sysvals.multistat(True, i, finish) + if i != 0 and sysvals.multitest['delay'] > 0: pprint('Waiting %d seconds...' % (sysvals.multitest['delay'])) time.sleep(sysvals.multitest['delay']) - pprint('TEST (%d/%d) START' % (i+1, sysvals.multitest['count'])) fmt = 'suspend-%y%m%d-%H%M%S' sysvals.testdir = os.path.join(sysvals.outdir, datetime.now().strftime(fmt)) - ret = runTest(i+1) - pprint('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count'])) - sysvals.logmsg = '' + ret = runTest(i+1, True) + failcnt = 0 if not ret else failcnt + 1 + if sysvals.maxfail > 0 and failcnt >= sysvals.maxfail: + pprint('Maximum fail count of %d reached, aborting multitest' % (sysvals.maxfail)) + break + time.sleep(5) + sysvals.resetlog() + sysvals.multistat(False, i, finish) + if 'time' in sysvals.multitest and datetime.now() >= finish: + break if not sysvals.skiphtml: runSummary(sysvals.outdir, False, False) sysvals.sudoUserchown(sysvals.outdir) diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c new file mode 100644 index 000000000000..f259085cca6a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2020 Cloudflare + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <string.h> + +#include <linux/pkt_cls.h> + +#include <test_progs.h> + +#include "progs/test_cls_redirect.h" +#include "test_cls_redirect.skel.h" + +#define ENCAP_IP INADDR_LOOPBACK +#define ENCAP_PORT (1234) + +struct addr_port { + in_port_t port; + union { + struct in_addr in_addr; + struct in6_addr in6_addr; + }; +}; + +struct tuple { + int family; + struct addr_port src; + struct addr_port dst; +}; + +static int start_server(const struct sockaddr *addr, socklen_t len, int type) +{ + int fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + return -1; + if (CHECK_FAIL(bind(fd, addr, len) == -1)) + goto err; + if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1)) + goto err; + + return fd; + +err: + close(fd); + return -1; +} + +static int connect_to_server(const struct sockaddr *addr, socklen_t len, + int type) +{ + int fd = socket(addr->sa_family, type, 0); + if (CHECK_FAIL(fd == -1)) + return -1; + if (CHECK_FAIL(connect(fd, addr, len))) + goto err; + + return fd; + +err: + close(fd); + return -1; +} + +static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap) +{ + const struct sockaddr_in6 *in6; + const struct sockaddr_in *in; + + switch (sa->sa_family) { + case AF_INET: + in = (const struct sockaddr_in *)sa; + ap->in_addr = in->sin_addr; + ap->port = in->sin_port; + return true; + + case AF_INET6: + in6 = (const struct sockaddr_in6 *)sa; + ap->in6_addr = in6->sin6_addr; + ap->port = in6->sin6_port; + return true; + + default: + return false; + } +} + +static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type, + int *server, int *conn, struct tuple *tuple) +{ + struct sockaddr_storage ss; + socklen_t slen = sizeof(ss); + struct sockaddr *sa = (struct sockaddr *)&ss; + + *server = start_server(addr, len, type); + if (*server < 0) + return false; + + if (CHECK_FAIL(getsockname(*server, sa, &slen))) + goto close_server; + + *conn = connect_to_server(sa, slen, type); + if (*conn < 0) + goto close_server; + + /* We want to simulate packets arriving at conn, so we have to + * swap src and dst. + */ + slen = sizeof(ss); + if (CHECK_FAIL(getsockname(*conn, sa, &slen))) + goto close_conn; + + if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst))) + goto close_conn; + + slen = sizeof(ss); + if (CHECK_FAIL(getpeername(*conn, sa, &slen))) + goto close_conn; + + if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src))) + goto close_conn; + + tuple->family = ss.ss_family; + return true; + +close_conn: + close(*conn); + *conn = -1; +close_server: + close(*server); + *server = -1; + return false; +} + +static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) +{ + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = family; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + return sizeof(*addr4); + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = family; + addr6->sin6_addr = in6addr_loopback; + return sizeof(*addr6); + default: + fprintf(stderr, "Invalid family %d", family); + return 0; + } +} + +static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr) +{ + return tattr->data_size_out < tattr->data_size_in; +} + +enum type { + UDP, + TCP, + __NR_KIND, +}; + +enum hops { + NO_HOPS, + ONE_HOP, +}; + +enum flags { + NONE, + SYN, + ACK, +}; + +enum conn { + KNOWN_CONN, + UNKNOWN_CONN, +}; + +enum result { + ACCEPT, + FORWARD, +}; + +struct test_cfg { + enum type type; + enum result result; + enum conn conn; + enum hops hops; + enum flags flags; +}; + +static int test_str(void *buf, size_t len, const struct test_cfg *test, + int family) +{ + const char *family_str, *type, *conn, *hops, *result, *flags; + + family_str = "IPv4"; + if (family == AF_INET6) + family_str = "IPv6"; + + type = "TCP"; + if (test->type == UDP) + type = "UDP"; + + conn = "known"; + if (test->conn == UNKNOWN_CONN) + conn = "unknown"; + + hops = "no hops"; + if (test->hops == ONE_HOP) + hops = "one hop"; + + result = "accept"; + if (test->result == FORWARD) + result = "forward"; + + flags = "none"; + if (test->flags == SYN) + flags = "SYN"; + else if (test->flags == ACK) + flags = "ACK"; + + return snprintf(buf, len, "%s %s %s %s (%s, flags: %s)", family_str, + type, result, conn, hops, flags); +} + +static struct test_cfg tests[] = { + { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, SYN }, + { TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, ACK }, + { TCP, FORWARD, UNKNOWN_CONN, ONE_HOP, ACK }, + { TCP, ACCEPT, KNOWN_CONN, ONE_HOP, ACK }, + { UDP, ACCEPT, UNKNOWN_CONN, NO_HOPS, NONE }, + { UDP, FORWARD, UNKNOWN_CONN, ONE_HOP, NONE }, + { UDP, ACCEPT, KNOWN_CONN, ONE_HOP, NONE }, +}; + +static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto) +{ + const uint8_t hlen = + (sizeof(struct guehdr) / sizeof(uint32_t)) + hop_count; + *encap = (encap_headers_t){ + .eth = { .h_proto = htons(ETH_P_IP) }, + .ip = { + .ihl = 5, + .version = 4, + .ttl = IPDEFTTL, + .protocol = IPPROTO_UDP, + .daddr = htonl(ENCAP_IP) + }, + .udp = { + .dest = htons(ENCAP_PORT), + }, + .gue = { + .hlen = hlen, + .proto_ctype = proto + }, + .unigue = { + .hop_count = hop_count + }, + }; +} + +static size_t build_input(const struct test_cfg *test, void *const buf, + const struct tuple *tuple) +{ + in_port_t sport = tuple->src.port; + encap_headers_t encap; + struct iphdr ip; + struct ipv6hdr ipv6; + struct tcphdr tcp; + struct udphdr udp; + struct in_addr next_hop; + uint8_t *p = buf; + int proto; + + proto = IPPROTO_IPIP; + if (tuple->family == AF_INET6) + proto = IPPROTO_IPV6; + + encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto); + p = mempcpy(p, &encap, sizeof(encap)); + + if (test->hops == ONE_HOP) { + next_hop = (struct in_addr){ .s_addr = htonl(0x7f000002) }; + p = mempcpy(p, &next_hop, sizeof(next_hop)); + } + + proto = IPPROTO_TCP; + if (test->type == UDP) + proto = IPPROTO_UDP; + + switch (tuple->family) { + case AF_INET: + ip = (struct iphdr){ + .ihl = 5, + .version = 4, + .ttl = IPDEFTTL, + .protocol = proto, + .saddr = tuple->src.in_addr.s_addr, + .daddr = tuple->dst.in_addr.s_addr, + }; + p = mempcpy(p, &ip, sizeof(ip)); + break; + case AF_INET6: + ipv6 = (struct ipv6hdr){ + .version = 6, + .hop_limit = IPDEFTTL, + .nexthdr = proto, + .saddr = tuple->src.in6_addr, + .daddr = tuple->dst.in6_addr, + }; + p = mempcpy(p, &ipv6, sizeof(ipv6)); + break; + default: + return 0; + } + + if (test->conn == UNKNOWN_CONN) + sport--; + + switch (test->type) { + case TCP: + tcp = (struct tcphdr){ + .source = sport, + .dest = tuple->dst.port, + }; + if (test->flags == SYN) + tcp.syn = true; + if (test->flags == ACK) + tcp.ack = true; + p = mempcpy(p, &tcp, sizeof(tcp)); + break; + case UDP: + udp = (struct udphdr){ + .source = sport, + .dest = tuple->dst.port, + }; + p = mempcpy(p, &udp, sizeof(udp)); + break; + default: + return 0; + } + + return (void *)p - buf; +} + +static void close_fds(int *fds, int n) +{ + int i; + + for (i = 0; i < n; i++) + if (fds[i] > 0) + close(fds[i]); +} + +void test_cls_redirect(void) +{ + struct test_cls_redirect *skel = NULL; + struct bpf_prog_test_run_attr tattr = {}; + int families[] = { AF_INET, AF_INET6 }; + struct sockaddr_storage ss; + struct sockaddr *addr; + socklen_t slen; + int i, j, err; + + int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; + int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; + struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; + + skel = test_cls_redirect__open(); + if (CHECK_FAIL(!skel)) + return; + + skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP); + skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT); + + if (CHECK_FAIL(test_cls_redirect__load(skel))) + goto cleanup; + + addr = (struct sockaddr *)&ss; + for (i = 0; i < ARRAY_SIZE(families); i++) { + slen = prepare_addr(&ss, families[i]); + if (CHECK_FAIL(!slen)) + goto cleanup; + + if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM, + &servers[UDP][i], &conns[UDP][i], + &tuples[UDP][i]))) + goto cleanup; + + if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM, + &servers[TCP][i], &conns[TCP][i], + &tuples[TCP][i]))) + goto cleanup; + } + + tattr.prog_fd = bpf_program__fd(skel->progs.cls_redirect); + for (i = 0; i < ARRAY_SIZE(tests); i++) { + struct test_cfg *test = &tests[i]; + + for (j = 0; j < ARRAY_SIZE(families); j++) { + struct tuple *tuple = &tuples[test->type][j]; + char input[256]; + char tmp[256]; + + test_str(tmp, sizeof(tmp), test, tuple->family); + if (!test__start_subtest(tmp)) + continue; + + tattr.data_out = tmp; + tattr.data_size_out = sizeof(tmp); + + tattr.data_in = input; + tattr.data_size_in = build_input(test, input, tuple); + if (CHECK_FAIL(!tattr.data_size_in)) + continue; + + err = bpf_prog_test_run_xattr(&tattr); + if (CHECK_FAIL(err)) + continue; + + if (tattr.retval != TC_ACT_REDIRECT) { + PRINT_FAIL("expected TC_ACT_REDIRECT, got %d\n", + tattr.retval); + continue; + } + + switch (test->result) { + case ACCEPT: + if (CHECK_FAIL(!was_decapsulated(&tattr))) + continue; + break; + case FORWARD: + if (CHECK_FAIL(was_decapsulated(&tattr))) + continue; + break; + default: + PRINT_FAIL("unknown result %d\n", test->result); + continue; + } + } + } + +cleanup: + test_cls_redirect__destroy(skel); + close_fds((int *)servers, sizeof(servers) / sizeof(servers[0][0])); + close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0])); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index cde463af7071..c2642517e1d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -5,7 +5,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, const char *target_obj_file, int prog_cnt, - const char **prog_name) + const char **prog_name, + bool run_prog) { struct bpf_object *obj = NULL, *pkt_obj; int err, pkt_fd, i; @@ -18,7 +19,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", + target_obj_file, err, errno)) return; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, .attach_prog_fd = pkt_fd, @@ -33,7 +35,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, obj = bpf_object__open_file(obj_file, &opts); if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", - "failed to open fexit_bpf2bpf: %ld\n", + "failed to open %s: %ld\n", obj_file, PTR_ERR(obj))) goto close_prog; @@ -49,6 +51,10 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) goto close_prog; } + + if (!run_prog) + goto close_prog; + data_map = bpf_object__find_map_by_name(obj, "fexit_bp.bss"); if (CHECK(!data_map, "find_data_map", "data map not found\n")) goto close_prog; @@ -89,7 +95,7 @@ static void test_target_no_callees(void) test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.o", "./test_pkt_md_access.o", ARRAY_SIZE(prog_name), - prog_name); + prog_name, true); } static void test_target_yes_callees(void) @@ -103,7 +109,7 @@ static void test_target_yes_callees(void) test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", "./test_pkt_access.o", ARRAY_SIZE(prog_name), - prog_name); + prog_name, true); } static void test_func_replace(void) @@ -120,7 +126,18 @@ static void test_func_replace(void) test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", "./test_pkt_access.o", ARRAY_SIZE(prog_name), - prog_name); + prog_name, true); +} + +static void test_func_replace_verify(void) +{ + const char *prog_name[] = { + "freplace/do_bind", + }; + test_fexit_bpf2bpf_common("./freplace_connect4.o", + "./connect4_prog.o", + ARRAY_SIZE(prog_name), + prog_name, false); } void test_fexit_bpf2bpf(void) @@ -128,4 +145,5 @@ void test_fexit_bpf2bpf(void) test_target_no_callees(); test_target_yes_callees(); test_func_replace(); + test_func_replace_verify(); } diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 16a814eb4d64..56d80adcf4bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -19,15 +19,16 @@ void test_mmap(void) const size_t map_sz = roundup_page(sizeof(struct map_data)); const int zero = 0, one = 1, two = 2, far = 1500; const long page_size = sysconf(_SC_PAGE_SIZE); - int err, duration = 0, i, data_map_fd; + int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd; struct bpf_map *data_map, *bss_map; void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; struct test_mmap__bss *bss_data; + struct bpf_map_info map_info; + __u32 map_info_sz = sizeof(map_info); struct map_data *map_data; struct test_mmap *skel; __u64 val = 0; - skel = test_mmap__open_and_load(); if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; @@ -36,6 +37,14 @@ void test_mmap(void) data_map = skel->maps.data_map; data_map_fd = bpf_map__fd(data_map); + /* get map's ID */ + memset(&map_info, 0, map_info_sz); + err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz); + if (CHECK(err, "map_get_info", "failed %d\n", errno)) + goto cleanup; + data_map_id = map_info.id; + + /* mmap BSS map */ bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED, bpf_map__fd(bss_map), 0); if (CHECK(bss_mmaped == MAP_FAILED, "bss_mmap", @@ -98,6 +107,10 @@ void test_mmap(void) "data_map freeze succeeded: err=%d, errno=%d\n", err, errno)) goto cleanup; + err = mprotect(map_mmaped, map_sz, PROT_READ); + if (CHECK(err, "mprotect_ro", "mprotect to r/o failed %d\n", errno)) + goto cleanup; + /* unmap R/W mapping */ err = munmap(map_mmaped, map_sz); map_mmaped = NULL; @@ -111,6 +124,12 @@ void test_mmap(void) map_mmaped = NULL; goto cleanup; } + err = mprotect(map_mmaped, map_sz, PROT_WRITE); + if (CHECK(!err, "mprotect_wr", "mprotect() succeeded unexpectedly!\n")) + goto cleanup; + err = mprotect(map_mmaped, map_sz, PROT_EXEC); + if (CHECK(!err, "mprotect_ex", "mprotect() succeeded unexpectedly!\n")) + goto cleanup; map_data = map_mmaped; /* map/unmap in a loop to test ref counting */ @@ -197,6 +216,45 @@ void test_mmap(void) CHECK_FAIL(map_data->val[far] != 3 * 321); munmap(tmp2, 4 * page_size); + + tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0); + if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno)) + goto cleanup; + + test_mmap__destroy(skel); + skel = NULL; + CHECK_FAIL(munmap(bss_mmaped, bss_sz)); + bss_mmaped = NULL; + CHECK_FAIL(munmap(map_mmaped, map_sz)); + map_mmaped = NULL; + + /* map should be still held by active mmap */ + tmp_fd = bpf_map_get_fd_by_id(data_map_id); + if (CHECK(tmp_fd < 0, "get_map_by_id", "failed %d\n", errno)) { + munmap(tmp1, map_sz); + goto cleanup; + } + close(tmp_fd); + + /* this should release data map finally */ + munmap(tmp1, map_sz); + + /* we need to wait for RCU grace period */ + for (i = 0; i < 10000; i++) { + __u32 id = data_map_id - 1; + if (bpf_map_get_next_id(id, &id) || id > data_map_id) + break; + usleep(1); + } + + /* should fail to get map FD by non-existing ID */ + tmp_fd = bpf_map_get_fd_by_id(data_map_id); + if (CHECK(tmp_fd >= 0, "get_map_by_id_after", + "unexpectedly succeeded %d\n", tmp_fd)) { + close(tmp_fd); + goto cleanup; + } + cleanup: if (bss_mmaped) CHECK_FAIL(munmap(bss_mmaped, bss_sz)); diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c index 9d9351dc2ded..713167449c98 100644 --- a/tools/testing/selftests/bpf/prog_tests/section_names.c +++ b/tools/testing/selftests/bpf/prog_tests/section_names.c @@ -43,18 +43,18 @@ static struct sec_name_test tests[] = { {"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} }, { "cgroup_skb/ingress", - {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, + {0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_INGRESS}, {0, BPF_CGROUP_INET_INGRESS}, }, { "cgroup_skb/egress", - {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, + {0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_EGRESS}, {0, BPF_CGROUP_INET_EGRESS}, }, {"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} }, { "cgroup/sock", - {0, BPF_PROG_TYPE_CGROUP_SOCK, 0}, + {0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE}, {0, BPF_CGROUP_INET_SOCK_CREATE}, }, { @@ -69,26 +69,38 @@ static struct sec_name_test tests[] = { }, { "cgroup/dev", - {0, BPF_PROG_TYPE_CGROUP_DEVICE, 0}, + {0, BPF_PROG_TYPE_CGROUP_DEVICE, BPF_CGROUP_DEVICE}, {0, BPF_CGROUP_DEVICE}, }, - {"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} }, + { + "sockops", + {0, BPF_PROG_TYPE_SOCK_OPS, BPF_CGROUP_SOCK_OPS}, + {0, BPF_CGROUP_SOCK_OPS}, + }, { "sk_skb/stream_parser", - {0, BPF_PROG_TYPE_SK_SKB, 0}, + {0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_PARSER}, {0, BPF_SK_SKB_STREAM_PARSER}, }, { "sk_skb/stream_verdict", - {0, BPF_PROG_TYPE_SK_SKB, 0}, + {0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_VERDICT}, {0, BPF_SK_SKB_STREAM_VERDICT}, }, {"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} }, - {"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} }, - {"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} }, + { + "sk_msg", + {0, BPF_PROG_TYPE_SK_MSG, BPF_SK_MSG_VERDICT}, + {0, BPF_SK_MSG_VERDICT}, + }, + { + "lirc_mode2", + {0, BPF_PROG_TYPE_LIRC_MODE2, BPF_LIRC_MODE2}, + {0, BPF_LIRC_MODE2}, + }, { "flow_dissector", - {0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0}, + {0, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_FLOW_DISSECTOR}, {0, BPF_FLOW_DISSECTOR}, }, { @@ -158,17 +170,17 @@ static void test_prog_type_by_name(const struct sec_name_test *test) &expected_attach_type); CHECK(rc != test->expected_load.rc, "check_code", - "prog: unexpected rc=%d for %s", rc, test->sec_name); + "prog: unexpected rc=%d for %s\n", rc, test->sec_name); if (rc) return; CHECK(prog_type != test->expected_load.prog_type, "check_prog_type", - "prog: unexpected prog_type=%d for %s", + "prog: unexpected prog_type=%d for %s\n", prog_type, test->sec_name); CHECK(expected_attach_type != test->expected_load.expected_attach_type, - "check_attach_type", "prog: unexpected expected_attach_type=%d for %s", + "check_attach_type", "prog: unexpected expected_attach_type=%d for %s\n", expected_attach_type, test->sec_name); } @@ -180,13 +192,13 @@ static void test_attach_type_by_name(const struct sec_name_test *test) rc = libbpf_attach_type_by_name(test->sec_name, &attach_type); CHECK(rc != test->expected_attach.rc, "check_ret", - "attach: unexpected rc=%d for %s", rc, test->sec_name); + "attach: unexpected rc=%d for %s\n", rc, test->sec_name); if (rc) return; CHECK(attach_type != test->expected_attach.attach_type, - "check_attach_type", "attach: unexpected attach_type=%d for %s", + "check_attach_type", "attach: unexpected attach_type=%d for %s\n", attach_type, test->sec_name); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index 1e4c258de09d..b17eb2045c1d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -15,7 +15,10 @@ char *CMD_ARGS[] = {"true", NULL}; -int heap_mprotect(void) +#define GET_PAGE_ADDR(ADDR, PAGE_SIZE) \ + (char *)(((unsigned long) (ADDR + PAGE_SIZE)) & ~(PAGE_SIZE-1)) + +int stack_mprotect(void) { void *buf; long sz; @@ -25,12 +28,9 @@ int heap_mprotect(void) if (sz < 0) return sz; - buf = memalign(sz, 2 * sz); - if (buf == NULL) - return -ENOMEM; - - ret = mprotect(buf, sz, PROT_READ | PROT_WRITE | PROT_EXEC); - free(buf); + buf = alloca(sz * 3); + ret = mprotect(GET_PAGE_ADDR(buf, sz), sz, + PROT_READ | PROT_WRITE | PROT_EXEC); return ret; } @@ -73,8 +73,8 @@ void test_test_lsm(void) skel->bss->monitored_pid = getpid(); - err = heap_mprotect(); - if (CHECK(errno != EPERM, "heap_mprotect", "want errno=EPERM, got %d\n", + err = stack_mprotect(); + if (CHECK(errno != EPERM, "stack_mprotect", "want err=EPERM, got %d\n", errno)) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index 05b294d6b923..15ef3531483e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -6,19 +6,34 @@ void test_xdp_attach(void) { + __u32 duration = 0, id1, id2, id0 = 0, len; struct bpf_object *obj1, *obj2, *obj3; const char *file = "./test_xdp.o"; + struct bpf_prog_info info = {}; int err, fd1, fd2, fd3; - __u32 duration = 0; DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); + len = sizeof(info); + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1); if (CHECK_FAIL(err)) return; + err = bpf_obj_get_info_by_fd(fd1, &info, &len); + if (CHECK_FAIL(err)) + goto out_1; + id1 = info.id; + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2); if (CHECK_FAIL(err)) goto out_1; + + memset(&info, 0, sizeof(info)); + err = bpf_obj_get_info_by_fd(fd2, &info, &len); + if (CHECK_FAIL(err)) + goto out_2; + id2 = info.id; + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3); if (CHECK_FAIL(err)) goto out_2; @@ -28,6 +43,11 @@ void test_xdp_attach(void) if (CHECK(err, "load_ok", "initial load failed")) goto out_close; + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id1, "id1_check", + "loaded prog id %u != id1 %u, err %d", id0, id1, err)) + goto out_close; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, &opts); if (CHECK(!err, "load_fail", "load with expected id didn't fail")) @@ -37,6 +57,10 @@ void test_xdp_attach(void) err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts); if (CHECK(err, "replace_ok", "replace valid old_fd failed")) goto out; + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id2, "id2_check", + "loaded prog id %u != id2 %u, err %d", id0, id2, err)) + goto out_close; err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts); if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail")) @@ -51,6 +75,10 @@ void test_xdp_attach(void) if (CHECK(err, "remove_ok", "remove valid old_fd failed")) goto out; + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != 0, "unload_check", + "loaded prog id %u != 0, err %d", id0, err)) + goto out_close; out: bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); out_close: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c new file mode 100644 index 000000000000..d2d7a283d72f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/if_link.h> +#include <test_progs.h> + +#define IFINDEX_LO 1 + +void test_xdp_info(void) +{ + __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id; + const char *file = "./xdp_dummy.o"; + struct bpf_prog_info info = {}; + struct bpf_object *obj; + int err, prog_fd; + + /* Get prog_id for XDP_ATTACHED_NONE mode */ + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + if (CHECK(err, "get_xdp_none", "errno=%d\n", errno)) + return; + if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id)) + return; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno)) + return; + if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n", + prog_id)) + return; + + /* Setup prog */ + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &len); + if (CHECK(err, "get_prog_info", "errno=%d\n", errno)) + goto out_close; + + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno)) + goto out_close; + + /* Get prog_id for single prog mode */ + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + if (CHECK(err, "get_xdp", "errno=%d\n", errno)) + goto out; + if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n")) + goto out; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno)) + goto out; + if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n")) + goto out; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE); + if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno)) + goto out; + if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) + goto out; + +out: + bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); +out_close: + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 75085119c5bb..ad3c498a8150 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -18,11 +18,25 @@ int _version SEC("version") = 1; +__attribute__ ((noinline)) +int do_bind(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + + sa.sin_family = AF_INET; + sa.sin_port = bpf_htons(0); + sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4); + + if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) + return 0; + + return 1; +} + SEC("cgroup/connect4") int connect_v4_prog(struct bpf_sock_addr *ctx) { struct bpf_sock_tuple tuple = {}; - struct sockaddr_in sa; struct bpf_sock *sk; /* Verify that new destination is available. */ @@ -56,17 +70,7 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); ctx->user_port = bpf_htons(DST_REWRITE_PORT4); - /* Rewrite source. */ - memset(&sa, 0, sizeof(sa)); - - sa.sin_family = AF_INET; - sa.sin_port = bpf_htons(0); - sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4); - - if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0) - return 0; - - return 1; + return do_bind(ctx) ? 1 : 0; } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/freplace_connect4.c b/tools/testing/selftests/bpf/progs/freplace_connect4.c new file mode 100644 index 000000000000..a0ae84230699 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_connect4.c @@ -0,0 +1,18 @@ +#include <linux/stddef.h> +#include <linux/ipv6.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <sys/socket.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +SEC("freplace/do_bind") +int new_do_bind(struct bpf_sock_addr *ctx) +{ + struct sockaddr_in sa = {}; + + bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index a4e3c223028d..b4598d4bc4f7 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -23,12 +23,12 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma, return ret; __u32 pid = bpf_get_current_pid_tgid() >> 32; - int is_heap = 0; + int is_stack = 0; - is_heap = (vma->vm_start >= vma->vm_mm->start_brk && - vma->vm_end <= vma->vm_mm->brk); + is_stack = (vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack); - if (is_heap && monitored_pid == pid) { + if (is_stack && monitored_pid == pid) { mprotect_count++; ret = -EPERM; } diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 88b0566da13d..31538c9ed193 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -20,20 +20,12 @@ struct bpf_map_def SEC("maps") btf_map = { BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); -struct dummy_tracepoint_args { - unsigned long long pad; - struct sock *sock; -}; - __attribute__((noinline)) -int test_long_fname_2(struct dummy_tracepoint_args *arg) +int test_long_fname_2(void) { struct ipv_counts *counts; int key = 0; - if (!arg->sock) - return 0; - counts = bpf_map_lookup_elem(&btf_map, &key); if (!counts) return 0; @@ -44,15 +36,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg) } __attribute__((noinline)) -int test_long_fname_1(struct dummy_tracepoint_args *arg) +int test_long_fname_1(void) { - return test_long_fname_2(arg); + return test_long_fname_2(); } SEC("dummy_tracepoint") -int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +int _dummy_tracepoint(void *arg) { - return test_long_fname_1(arg); + return test_long_fname_1(); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index a924e53c8e9d..6c5560162746 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -28,20 +28,12 @@ struct { __type(value, struct ipv_counts); } btf_map SEC(".maps"); -struct dummy_tracepoint_args { - unsigned long long pad; - struct sock *sock; -}; - __attribute__((noinline)) -int test_long_fname_2(struct dummy_tracepoint_args *arg) +int test_long_fname_2(void) { struct ipv_counts *counts; int key = 0; - if (!arg->sock) - return 0; - counts = bpf_map_lookup_elem(&btf_map, &key); if (!counts) return 0; @@ -57,15 +49,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg) } __attribute__((noinline)) -int test_long_fname_1(struct dummy_tracepoint_args *arg) +int test_long_fname_1(void) { - return test_long_fname_2(arg); + return test_long_fname_2(); } SEC("dummy_tracepoint") -int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +int _dummy_tracepoint(void *arg) { - return test_long_fname_1(arg); + return test_long_fname_1(); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 983aedd1c072..506da7fd2da2 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -17,20 +17,12 @@ struct bpf_map_def SEC("maps") btf_map = { .max_entries = 4, }; -struct dummy_tracepoint_args { - unsigned long long pad; - struct sock *sock; -}; - __attribute__((noinline)) -int test_long_fname_2(struct dummy_tracepoint_args *arg) +int test_long_fname_2(void) { struct ipv_counts *counts; int key = 0; - if (!arg->sock) - return 0; - counts = bpf_map_lookup_elem(&btf_map, &key); if (!counts) return 0; @@ -41,15 +33,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg) } __attribute__((noinline)) -int test_long_fname_1(struct dummy_tracepoint_args *arg) +int test_long_fname_1(void) { - return test_long_fname_2(arg); + return test_long_fname_2(); } SEC("dummy_tracepoint") -int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +int _dummy_tracepoint(void *arg) { - return test_long_fname_1(arg); + return test_long_fname_1(); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c new file mode 100644 index 000000000000..1668b993eb86 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -0,0 +1,1058 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// Copyright (c) 2019, 2020 Cloudflare + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/pkt_cls.h> +#include <linux/tcp.h> +#include <linux/udp.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "test_cls_redirect.h" + +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) + +#define IP_OFFSET_MASK (0x1FFF) +#define IP_MF (0x2000) + +char _license[] SEC("license") = "Dual BSD/GPL"; + +/** + * Destination port and IP used for UDP encapsulation. + */ +static volatile const __be16 ENCAPSULATION_PORT; +static volatile const __be32 ENCAPSULATION_IP; + +typedef struct { + uint64_t processed_packets_total; + uint64_t l3_protocol_packets_total_ipv4; + uint64_t l3_protocol_packets_total_ipv6; + uint64_t l4_protocol_packets_total_tcp; + uint64_t l4_protocol_packets_total_udp; + uint64_t accepted_packets_total_syn; + uint64_t accepted_packets_total_syn_cookies; + uint64_t accepted_packets_total_last_hop; + uint64_t accepted_packets_total_icmp_echo_request; + uint64_t accepted_packets_total_established; + uint64_t forwarded_packets_total_gue; + uint64_t forwarded_packets_total_gre; + + uint64_t errors_total_unknown_l3_proto; + uint64_t errors_total_unknown_l4_proto; + uint64_t errors_total_malformed_ip; + uint64_t errors_total_fragmented_ip; + uint64_t errors_total_malformed_icmp; + uint64_t errors_total_unwanted_icmp; + uint64_t errors_total_malformed_icmp_pkt_too_big; + uint64_t errors_total_malformed_tcp; + uint64_t errors_total_malformed_udp; + uint64_t errors_total_icmp_echo_replies; + uint64_t errors_total_malformed_encapsulation; + uint64_t errors_total_encap_adjust_failed; + uint64_t errors_total_encap_buffer_too_small; + uint64_t errors_total_redirect_loop; +} metrics_t; + +typedef enum { + INVALID = 0, + UNKNOWN, + ECHO_REQUEST, + SYN, + SYN_COOKIE, + ESTABLISHED, +} verdict_t; + +typedef struct { + uint16_t src, dst; +} flow_ports_t; + +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv4.dport) - + offsetof(struct bpf_sock_tuple, ipv4.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); +_Static_assert( + sizeof(flow_ports_t) != + offsetofend(struct bpf_sock_tuple, ipv6.dport) - + offsetof(struct bpf_sock_tuple, ipv6.sport) - 1, + "flow_ports_t must match sport and dport in struct bpf_sock_tuple"); + +typedef int ret_t; + +/* This is a bit of a hack. We need a return value which allows us to + * indicate that the regular flow of the program should continue, + * while allowing functions to use XDP_PASS and XDP_DROP, etc. + */ +static const ret_t CONTINUE_PROCESSING = -1; + +/* Convenience macro to call functions which return ret_t. + */ +#define MAYBE_RETURN(x) \ + do { \ + ret_t __ret = x; \ + if (__ret != CONTINUE_PROCESSING) \ + return __ret; \ + } while (0) + +/* Linux packet pointers are either aligned to NET_IP_ALIGN (aka 2 bytes), + * or not aligned if the arch supports efficient unaligned access. + * + * Since the verifier ensures that eBPF packet accesses follow these rules, + * we can tell LLVM to emit code as if we always had a larger alignment. + * It will yell at us if we end up on a platform where this is not valid. + */ +typedef uint8_t *net_ptr __attribute__((align_value(8))); + +typedef struct buf { + struct __sk_buff *skb; + net_ptr head; + /* NB: tail musn't have alignment other than 1, otherwise + * LLVM will go and eliminate code, e.g. when checking packet lengths. + */ + uint8_t *const tail; +} buf_t; + +static size_t buf_off(const buf_t *buf) +{ + /* Clang seems to optimize constructs like + * a - b + c + * if c is known: + * r? = c + * r? -= b + * r? += a + * + * This is a problem if a and b are packet pointers, + * since the verifier allows subtracting two pointers to + * get a scalar, but not a scalar and a pointer. + * + * Use inline asm to break this optimization. + */ + size_t off = (size_t)buf->head; + asm("%0 -= %1" : "+r"(off) : "r"(buf->skb->data)); + return off; +} + +static bool buf_copy(buf_t *buf, void *dst, size_t len) +{ + if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) { + return false; + } + + buf->head += len; + return true; +} + +static bool buf_skip(buf_t *buf, const size_t len) +{ + /* Check whether off + len is valid in the non-linear part. */ + if (buf_off(buf) + len > buf->skb->len) { + return false; + } + + buf->head += len; + return true; +} + +/* Returns a pointer to the start of buf, or NULL if len is + * larger than the remaining data. Consumes len bytes on a successful + * call. + * + * If scratch is not NULL, the function will attempt to load non-linear + * data via bpf_skb_load_bytes. On success, scratch is returned. + */ +static void *buf_assign(buf_t *buf, const size_t len, void *scratch) +{ + if (buf->head + len > buf->tail) { + if (scratch == NULL) { + return NULL; + } + + return buf_copy(buf, scratch, len) ? scratch : NULL; + } + + void *ptr = buf->head; + buf->head += len; + return ptr; +} + +static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4) +{ + if (ipv4->ihl <= 5) { + return true; + } + + return buf_skip(buf, (ipv4->ihl - 5) * 4); +} + +static bool ipv4_is_fragment(const struct iphdr *ip) +{ + uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK); + return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0; +} + +static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch) +{ + struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch); + if (ipv4 == NULL) { + return NULL; + } + + if (ipv4->ihl < 5) { + return NULL; + } + + if (!pkt_skip_ipv4_options(pkt, ipv4)) { + return NULL; + } + + return ipv4; +} + +/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */ +static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports) +{ + if (!buf_copy(pkt, ports, sizeof(*ports))) { + return false; + } + + /* Ports in the L4 headers are reversed, since we are parsing an ICMP + * payload which is going towards the eyeball. + */ + uint16_t dst = ports->src; + ports->src = ports->dst; + ports->dst = dst; + return true; +} + +static uint16_t pkt_checksum_fold(uint32_t csum) +{ + /* The highest reasonable value for an IPv4 header + * checksum requires two folds, so we just do that always. + */ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + return (uint16_t)~csum; +} + +static void pkt_ipv4_checksum(struct iphdr *iph) +{ + iph->check = 0; + + /* An IP header without options is 20 bytes. Two of those + * are the checksum, which we always set to zero. Hence, + * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7, + * which fits in 32 bit. + */ + _Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes"); + uint32_t acc = 0; + uint16_t *ipw = (uint16_t *)iph; + +#pragma clang loop unroll(full) + for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) { + acc += ipw[i]; + } + + iph->check = pkt_checksum_fold(acc); +} + +static bool pkt_skip_ipv6_extension_headers(buf_t *pkt, + const struct ipv6hdr *ipv6, + uint8_t *upper_proto, + bool *is_fragment) +{ + /* We understand five extension headers. + * https://tools.ietf.org/html/rfc8200#section-4.1 states that all + * headers should occur once, except Destination Options, which may + * occur twice. Hence we give up after 6 headers. + */ + struct { + uint8_t next; + uint8_t len; + } exthdr = { + .next = ipv6->nexthdr, + }; + *is_fragment = false; + +#pragma clang loop unroll(full) + for (int i = 0; i < 6; i++) { + switch (exthdr.next) { + case IPPROTO_FRAGMENT: + *is_fragment = true; + /* NB: We don't check that hdrlen == 0 as per spec. */ + /* fallthrough; */ + + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: + case IPPROTO_MH: + if (!buf_copy(pkt, &exthdr, sizeof(exthdr))) { + return false; + } + + /* hdrlen is in 8-octet units, and excludes the first 8 octets. */ + if (!buf_skip(pkt, + (exthdr.len + 1) * 8 - sizeof(exthdr))) { + return false; + } + + /* Decode next header */ + break; + + default: + /* The next header is not one of the known extension + * headers, treat it as the upper layer header. + * + * This handles IPPROTO_NONE. + * + * Encapsulating Security Payload (50) and Authentication + * Header (51) also end up here (and will trigger an + * unknown proto error later). They have a custom header + * format and seem too esoteric to care about. + */ + *upper_proto = exthdr.next; + return true; + } + } + + /* We never found an upper layer header. */ + return false; +} + +/* This function has to be inlined, because the verifier otherwise rejects it + * due to returning a pointer to the stack. This is technically correct, since + * scratch is allocated on the stack. However, this usage should be safe since + * it's the callers stack after all. + */ +static inline __attribute__((__always_inline__)) struct ipv6hdr * +pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto, + bool *is_fragment) +{ + struct ipv6hdr *ipv6 = buf_assign(pkt, sizeof(*ipv6), scratch); + if (ipv6 == NULL) { + return NULL; + } + + if (!pkt_skip_ipv6_extension_headers(pkt, ipv6, proto, is_fragment)) { + return NULL; + } + + return ipv6; +} + +/* Global metrics, per CPU + */ +struct bpf_map_def metrics_map SEC("maps") = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(unsigned int), + .value_size = sizeof(metrics_t), + .max_entries = 1, +}; + +static metrics_t *get_global_metrics(void) +{ + uint64_t key = 0; + return bpf_map_lookup_elem(&metrics_map, &key); +} + +static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap) +{ + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = payload_off - sizeof(struct ethhdr); + + // Changing the ethertype if the encapsulated packet is ipv6 + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + encap->eth.h_proto = bpf_htons(ETH_P_IPV6); + } + + if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC, + BPF_F_ADJ_ROOM_FIXED_GSO)) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, BPF_F_INGRESS); +} + +static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + metrics->forwarded_packets_total_gre++; + + const int payload_off = + sizeof(*encap) + + sizeof(struct in_addr) * encap->unigue.hop_count; + int32_t encap_overhead = + payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr); + int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead; + uint16_t proto = ETH_P_IP; + + /* Loop protection: the inner packet's TTL is decremented as a safeguard + * against any forwarding loop. As the only interesting field is the TTL + * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes + * as they handle the split packets if needed (no need for the data to be + * in the linear section). + */ + if (encap->gue.proto_ctype == IPPROTO_IPV6) { + proto = ETH_P_IPV6; + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct ipv6hdr, hop_limit), + &ttl, 1, 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } else { + uint8_t ttl; + int rc; + + rc = bpf_skb_load_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, + 1); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (ttl == 0) { + metrics->errors_total_redirect_loop++; + return TC_ACT_SHOT; + } + + /* IPv4 also has a checksum to patch. While the TTL is only one byte, + * this function only works for 2 and 4 bytes arguments (the result is + * the same). + */ + rc = bpf_l3_csum_replace( + skb, payload_off + offsetof(struct iphdr, check), ttl, + ttl - 1, 2); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + ttl--; + rc = bpf_skb_store_bytes( + skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1, + 0); + if (rc != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + } + + if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET, + BPF_F_ADJ_ROOM_FIXED_GSO)) { + metrics->errors_total_encap_adjust_failed++; + return TC_ACT_SHOT; + } + + if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap_gre_t *encap_gre = buf_assign(&pkt, sizeof(encap_gre_t), NULL); + if (encap_gre == NULL) { + metrics->errors_total_encap_buffer_too_small++; + return TC_ACT_SHOT; + } + + encap_gre->ip.protocol = IPPROTO_GRE; + encap_gre->ip.daddr = next_hop->s_addr; + encap_gre->ip.saddr = ENCAPSULATION_IP; + encap_gre->ip.tot_len = + bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta); + encap_gre->gre.flags = 0; + encap_gre->gre.protocol = bpf_htons(proto); + pkt_ipv4_checksum((void *)&encap_gre->ip); + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap, + struct in_addr *next_hop, metrics_t *metrics) +{ + /* swap L2 addresses */ + /* This assumes that packets are received from a router. + * So just swapping the MAC addresses here will make the packet go back to + * the router, which will send it to the appropriate machine. + */ + unsigned char temp[ETH_ALEN]; + memcpy(temp, encap->eth.h_dest, sizeof(temp)); + memcpy(encap->eth.h_dest, encap->eth.h_source, + sizeof(encap->eth.h_dest)); + memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source)); + + if (encap->unigue.next_hop == encap->unigue.hop_count - 1 && + encap->unigue.last_hop_gre) { + return forward_with_gre(skb, encap, next_hop, metrics); + } + + metrics->forwarded_packets_total_gue++; + uint32_t old_saddr = encap->ip.saddr; + encap->ip.saddr = encap->ip.daddr; + encap->ip.daddr = next_hop->s_addr; + if (encap->unigue.next_hop < encap->unigue.hop_count) { + encap->unigue.next_hop++; + } + + /* Remove ip->saddr, add next_hop->s_addr */ + const uint64_t off = offsetof(typeof(*encap), ip.check); + int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4); + if (ret < 0) { + return TC_ACT_SHOT; + } + + return bpf_redirect(skb->ifindex, 0); +} + +static ret_t skip_next_hops(buf_t *pkt, int n) +{ + switch (n) { + case 1: + if (!buf_skip(pkt, sizeof(struct in_addr))) + return TC_ACT_SHOT; + case 0: + return CONTINUE_PROCESSING; + + default: + return TC_ACT_SHOT; + } +} + +/* Get the next hop from the GLB header. + * + * Sets next_hop->s_addr to 0 if there are no more hops left. + * pkt is positioned just after the variable length GLB header + * iff the call is successful. + */ +static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap, + struct in_addr *next_hop) +{ + if (encap->unigue.next_hop > encap->unigue.hop_count) { + return TC_ACT_SHOT; + } + + /* Skip "used" next hops. */ + MAYBE_RETURN(skip_next_hops(pkt, encap->unigue.next_hop)); + + if (encap->unigue.next_hop == encap->unigue.hop_count) { + /* No more next hops, we are at the end of the GLB header. */ + next_hop->s_addr = 0; + return CONTINUE_PROCESSING; + } + + if (!buf_copy(pkt, next_hop, sizeof(*next_hop))) { + return TC_ACT_SHOT; + } + + /* Skip the remainig next hops (may be zero). */ + return skip_next_hops(pkt, encap->unigue.hop_count - + encap->unigue.next_hop - 1); +} + +/* Fill a bpf_sock_tuple to be used with the socket lookup functions. + * This is a kludge that let's us work around verifier limitations: + * + * fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321) + * + * clang will substitue a costant for sizeof, which allows the verifier + * to track it's value. Based on this, it can figure out the constant + * return value, and calling code works while still being "generic" to + * IPv4 and IPv6. + */ +static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph, + uint64_t iphlen, uint16_t sport, uint16_t dport) +{ + switch (iphlen) { + case sizeof(struct iphdr): { + struct iphdr *ipv4 = (struct iphdr *)iph; + tuple->ipv4.daddr = ipv4->daddr; + tuple->ipv4.saddr = ipv4->saddr; + tuple->ipv4.sport = sport; + tuple->ipv4.dport = dport; + return sizeof(tuple->ipv4); + } + + case sizeof(struct ipv6hdr): { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph; + memcpy(&tuple->ipv6.daddr, &ipv6->daddr, + sizeof(tuple->ipv6.daddr)); + memcpy(&tuple->ipv6.saddr, &ipv6->saddr, + sizeof(tuple->ipv6.saddr)); + tuple->ipv6.sport = sport; + tuple->ipv6.dport = dport; + return sizeof(tuple->ipv6); + } + + default: + return 0; + } +} + +static verdict_t classify_tcp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + void *iph, struct tcphdr *tcp) +{ + struct bpf_sock *sk = + bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state != BPF_TCP_LISTEN) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + if (iph != NULL && tcp != NULL) { + /* Kludge: we've run out of arguments, but need the length of the ip header. */ + uint64_t iphlen = sizeof(struct iphdr); + if (tuplen == sizeof(tuple->ipv6)) { + iphlen = sizeof(struct ipv6hdr); + } + + if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp, + sizeof(*tcp)) == 0) { + bpf_sk_release(sk); + return SYN_COOKIE; + } + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_udp(struct __sk_buff *skb, + struct bpf_sock_tuple *tuple, uint64_t tuplen) +{ + struct bpf_sock *sk = + bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0); + if (sk == NULL) { + return UNKNOWN; + } + + if (sk->state == BPF_TCP_ESTABLISHED) { + bpf_sk_release(sk); + return ESTABLISHED; + } + + bpf_sk_release(sk); + return UNKNOWN; +} + +static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto, + struct bpf_sock_tuple *tuple, uint64_t tuplen, + metrics_t *metrics) +{ + switch (proto) { + case IPPROTO_TCP: + return classify_tcp(skb, tuple, tuplen, NULL, NULL); + + case IPPROTO_UDP: + return classify_udp(skb, tuple, tuplen); + + default: + metrics->errors_total_malformed_icmp++; + return INVALID; + } +} + +static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics) +{ + struct icmphdr icmp; + if (!buf_copy(pkt, &icmp, sizeof(icmp))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp.type == ICMP_ECHOREPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp.type == ICMP_ECHO) { + return ECHO_REQUEST; + } + + if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + struct iphdr _ip4; + const struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + /* The source address in the outer IP header is from the entity that + * originated the ICMP message. Use the original IP header to restore + * the correct flow tuple. + */ + struct bpf_sock_tuple tuple; + tuple.ipv4.saddr = ipv4->daddr; + tuple.ipv4.daddr = ipv4->saddr; + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv4.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, ipv4->protocol, &tuple, + sizeof(tuple.ipv4), metrics); +} + +static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics) +{ + struct icmp6hdr icmp6; + if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) { + metrics->errors_total_malformed_icmp++; + return INVALID; + } + + /* We should never receive encapsulated echo replies. */ + if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) { + metrics->errors_total_icmp_echo_replies++; + return INVALID; + } + + if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) { + return ECHO_REQUEST; + } + + if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) { + metrics->errors_total_unwanted_icmp++; + return INVALID; + } + + bool is_fragment; + uint8_t l4_proto; + struct ipv6hdr _ipv6; + const struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + /* Swap source and dest addresses. */ + struct bpf_sock_tuple tuple; + memcpy(&tuple.ipv6.saddr, &ipv6->daddr, sizeof(tuple.ipv6.saddr)); + memcpy(&tuple.ipv6.daddr, &ipv6->saddr, sizeof(tuple.ipv6.daddr)); + + if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv6.sport)) { + metrics->errors_total_malformed_icmp_pkt_too_big++; + return INVALID; + } + + return classify_icmp(pkt->skb, l4_proto, &tuple, sizeof(tuple.ipv6), + metrics); +} + +static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_tcp++; + + struct tcphdr _tcp; + struct tcphdr *tcp = buf_assign(pkt, sizeof(_tcp), &_tcp); + if (tcp == NULL) { + metrics->errors_total_malformed_tcp++; + return INVALID; + } + + if (tcp->syn) { + return SYN; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, tcp->source, tcp->dest); + return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp); +} + +static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen, + metrics_t *metrics) +{ + metrics->l4_protocol_packets_total_udp++; + + struct udphdr _udp; + struct udphdr *udph = buf_assign(pkt, sizeof(_udp), &_udp); + if (udph == NULL) { + metrics->errors_total_malformed_udp++; + return INVALID; + } + + struct bpf_sock_tuple tuple; + uint64_t tuplen = + fill_tuple(&tuple, iph, iphlen, udph->source, udph->dest); + return classify_udp(pkt->skb, &tuple, tuplen); +} + +static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv4++; + + struct iphdr _ip4; + struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4); + if (ipv4 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4->version != 4) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv4_is_fragment(ipv4)) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (ipv4->protocol) { + case IPPROTO_ICMP: + return process_icmpv4(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv4, sizeof(*ipv4), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv4, sizeof(*ipv4), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +static verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) +{ + metrics->l3_protocol_packets_total_ipv6++; + + uint8_t l4_proto; + bool is_fragment; + struct ipv6hdr _ipv6; + struct ipv6hdr *ipv6 = + pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment); + if (ipv6 == NULL) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (ipv6->version != 6) { + metrics->errors_total_malformed_ip++; + return INVALID; + } + + if (is_fragment) { + metrics->errors_total_fragmented_ip++; + return INVALID; + } + + switch (l4_proto) { + case IPPROTO_ICMPV6: + return process_icmpv6(pkt, metrics); + + case IPPROTO_TCP: + return process_tcp(pkt, ipv6, sizeof(*ipv6), metrics); + + case IPPROTO_UDP: + return process_udp(pkt, ipv6, sizeof(*ipv6), metrics); + + default: + metrics->errors_total_unknown_l4_proto++; + return INVALID; + } +} + +SEC("classifier/cls_redirect") +int cls_redirect(struct __sk_buff *skb) +{ + metrics_t *metrics = get_global_metrics(); + if (metrics == NULL) { + return TC_ACT_SHOT; + } + + metrics->processed_packets_total++; + + /* Pass bogus packets as long as we're not sure they're + * destined for us. + */ + if (skb->protocol != bpf_htons(ETH_P_IP)) { + return TC_ACT_OK; + } + + encap_headers_t *encap; + + /* Make sure that all encapsulation headers are available in + * the linear portion of the skb. This makes it easy to manipulate them. + */ + if (bpf_skb_pull_data(skb, sizeof(*encap))) { + return TC_ACT_OK; + } + + buf_t pkt = { + .skb = skb, + .head = (uint8_t *)(long)skb->data, + .tail = (uint8_t *)(long)skb->data_end, + }; + + encap = buf_assign(&pkt, sizeof(*encap), NULL); + if (encap == NULL) { + return TC_ACT_OK; + } + + if (encap->ip.ihl != 5) { + /* We never have any options. */ + return TC_ACT_OK; + } + + if (encap->ip.daddr != ENCAPSULATION_IP || + encap->ip.protocol != IPPROTO_UDP) { + return TC_ACT_OK; + } + + /* TODO Check UDP length? */ + if (encap->udp.dest != ENCAPSULATION_PORT) { + return TC_ACT_OK; + } + + /* We now know that the packet is destined to us, we can + * drop bogus ones. + */ + if (ipv4_is_fragment((void *)&encap->ip)) { + metrics->errors_total_fragmented_ip++; + return TC_ACT_SHOT; + } + + if (encap->gue.variant != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.control != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.flags != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->gue.hlen != + sizeof(encap->unigue) / 4 + encap->unigue.hop_count) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.version != 0) { + metrics->errors_total_malformed_encapsulation++; + return TC_ACT_SHOT; + } + + if (encap->unigue.reserved != 0) { + return TC_ACT_SHOT; + } + + struct in_addr next_hop; + MAYBE_RETURN(get_next_hop(&pkt, encap, &next_hop)); + + if (next_hop.s_addr == 0) { + metrics->accepted_packets_total_last_hop++; + return accept_locally(skb, encap); + } + + verdict_t verdict; + switch (encap->gue.proto_ctype) { + case IPPROTO_IPIP: + verdict = process_ipv4(&pkt, metrics); + break; + + case IPPROTO_IPV6: + verdict = process_ipv6(&pkt, metrics); + break; + + default: + metrics->errors_total_unknown_l3_proto++; + return TC_ACT_SHOT; + } + + switch (verdict) { + case INVALID: + /* metrics have already been bumped */ + return TC_ACT_SHOT; + + case UNKNOWN: + return forward_to_next_hop(skb, encap, &next_hop, metrics); + + case ECHO_REQUEST: + metrics->accepted_packets_total_icmp_echo_request++; + break; + + case SYN: + if (encap->unigue.forward_syn) { + return forward_to_next_hop(skb, encap, &next_hop, + metrics); + } + + metrics->accepted_packets_total_syn++; + break; + + case SYN_COOKIE: + metrics->accepted_packets_total_syn_cookies++; + break; + + case ESTABLISHED: + metrics->accepted_packets_total_established++; + break; + } + + return accept_locally(skb, encap); +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h new file mode 100644 index 000000000000..76eab0aacba0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright 2019, 2020 Cloudflare */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <string.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> + +struct gre_base_hdr { + uint16_t flags; + uint16_t protocol; +} __attribute__((packed)); + +struct guehdr { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t hlen : 5, control : 1, variant : 2; +#else + uint8_t variant : 2, control : 1, hlen : 5; +#endif + uint8_t proto_ctype; + uint16_t flags; +}; + +struct unigue { +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + uint8_t _r : 2, last_hop_gre : 1, forward_syn : 1, version : 4; +#else + uint8_t version : 4, forward_syn : 1, last_hop_gre : 1, _r : 2; +#endif + uint8_t reserved; + uint8_t next_hop; + uint8_t hop_count; + // Next hops go here +} __attribute__((packed)); + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct gre_base_hdr gre; +} __attribute__((packed)) encap_gre_t; + +typedef struct { + struct ethhdr eth; + struct iphdr ip; + struct udphdr udp; + struct guehdr gue; + struct unigue unigue; +} __attribute__((packed)) encap_headers_t; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 8da77cda5f4a..305fae8f80a9 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -2854,7 +2854,7 @@ static struct btf_raw_test raw_tests[] = { .value_type_id = 1, .max_entries = 4, .btf_load_err = true, - .err_str = "vlen != 0", + .err_str = "Invalid func linkage", }, { diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index f4aff6b8284b..10188cc8e9e0 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -105,6 +105,13 @@ struct ipv6_packet { } __packed; extern struct ipv6_packet pkt_v6; +#define PRINT_FAIL(format...) \ + ({ \ + test__fail(); \ + fprintf(stdout, "%s:FAIL:%d ", __func__, __LINE__); \ + fprintf(stdout, ##format); \ + }) + #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ int __save_errno = errno; \ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 87eaa49609a0..ad6939c67c5e 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -943,7 +943,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv, attr.insns = prog; attr.insns_cnt = prog_len; attr.license = "GPL"; - attr.log_level = verbose || expected_ret == VERBOSE_ACCEPT ? 1 : 4; + if (verbose) + attr.log_level = 1; + else if (expected_ret == VERBOSE_ACCEPT) + attr.log_level = 2; + else + attr.log_level = 4; attr.prog_flags = pflags; fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 4d0d09574bf4..a253a064e6e0 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -501,7 +501,7 @@ .result = REJECT }, { - "bounds check mixed 32bit and 64bit arithmatic. test1", + "bounds check mixed 32bit and 64bit arithmetic. test1", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_1, -1), @@ -520,7 +520,7 @@ .result = ACCEPT }, { - "bounds check mixed 32bit and 64bit arithmatic. test2", + "bounds check mixed 32bit and 64bit arithmetic. test2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_1, -1), diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 130553e19eca..99f8f582c02b 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -92,3 +92,27 @@ .result = ACCEPT, .retval = 1, }, +{ + "perfevent for cgroup dev", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_DEVICE, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup sysctl", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup sockopt", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c index 7276620ef242..8bfeb77c60bd 100644 --- a/tools/testing/selftests/bpf/verifier/stack_ptr.c +++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c @@ -315,3 +315,43 @@ }, .result = ACCEPT, }, +{ + "store PTR_TO_STACK in R10 to array map using BPF_B", + .insns = { + /* Load pointer to map. */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + /* Copy R10 to R9. */ + BPF_MOV64_REG(BPF_REG_9, BPF_REG_10), + /* Pollute other registers with unaligned values. */ + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_MOV64_IMM(BPF_REG_3, -1), + BPF_MOV64_IMM(BPF_REG_4, -1), + BPF_MOV64_IMM(BPF_REG_5, -1), + BPF_MOV64_IMM(BPF_REG_6, -1), + BPF_MOV64_IMM(BPF_REG_7, -1), + BPF_MOV64_IMM(BPF_REG_8, -1), + /* Store both R9 and R10 with BPF_B and read back. */ + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_1, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_9, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_1, 0), + /* Should read back as same value. */ + BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 42, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c index 7f6c232cd842..ed1c2cea1dea 100644 --- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c +++ b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c @@ -88,6 +88,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 3 }, + .errstr_unpriv = "leaking pointer from stack off -8", .errstr = "R0 invalid mem access 'inv'", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config index c2c8de4fafff..e59d985eeff0 100644 --- a/tools/testing/selftests/ftrace/config +++ b/tools/testing/selftests/ftrace/config @@ -11,5 +11,6 @@ CONFIG_PREEMPTIRQ_DELAY_TEST=m CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_SAMPLES=y +CONFIG_SAMPLE_FTRACE_DIRECT=m CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_KALLSYMS_ALL=y diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index 4c156aeab6b8..5ec4d9e18806 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -137,7 +137,7 @@ int dump_queue(struct msgque_data *msgque) for (kern_id = 0; kern_id < 256; kern_id++) { ret = msgctl(kern_id, MSG_STAT, &ds); if (ret < 0) { - if (errno == -EINVAL) + if (errno == EINVAL) continue; printf("Failed to get stats for IPC queue with id %d\n", kern_id); diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index e84d901f8567..676b3a8b114d 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -33,7 +33,7 @@ tap_timeout() { # Make sure tests will time out if utility is available. if [ -x /usr/bin/timeout ] ; then - /usr/bin/timeout "$kselftest_timeout" "$1" + /usr/bin/timeout --foreground "$kselftest_timeout" "$1" else "$1" fi diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 2902f6a78f8a..2bb8c81fc0b4 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -705,7 +705,7 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) /* Sanity check handler execution environment. */ if (!t) { fprintf(TH_LOG_STREAM, - "no active test in SIGARLM handler!?\n"); + "no active test in SIGALRM handler!?\n"); abort(); } if (sig != SIGALRM || sig != info->si_signo) { @@ -731,7 +731,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &action, &saved_action)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to install SIGARLM handler\n", + "%s: unable to install SIGALRM handler\n", t->name); return; } @@ -743,7 +743,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &saved_action, NULL)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to uninstall SIGARLM handler\n", + "%s: unable to uninstall SIGALRM handler\n", t->name); return; } diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index 0a15f9e23431..187b14cad00c 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -4,8 +4,9 @@ CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ CFLAGS += -I../../../../usr/include/ -TEST_GEN_PROGS := memfd_test fuse_test fuse_mnt +TEST_GEN_PROGS := memfd_test TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh +TEST_GEN_FILES := fuse_test fuse_mnt fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3f386eb9e7d7..895ec992b2f1 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -16,6 +16,7 @@ TEST_PROGS += altnames.sh icmp_redirect.sh ip6_gre_headroom.sh TEST_PROGS += route_localnet.sh TEST_PROGS += reuseaddr_ports_exhausted.sh TEST_PROGS += txtimestamp.sh +TEST_PROGS += vrf-xfrm-tests.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 796670ebc65b..b785241127df 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -150,31 +150,31 @@ setup() $IP li add veth1 type veth peer name veth2 $IP li set veth1 up $IP addr add 172.16.1.1/24 dev veth1 - $IP -6 addr add 2001:db8:91::1/64 dev veth1 + $IP -6 addr add 2001:db8:91::1/64 dev veth1 nodad $IP li add veth3 type veth peer name veth4 $IP li set veth3 up $IP addr add 172.16.2.1/24 dev veth3 - $IP -6 addr add 2001:db8:92::1/64 dev veth3 + $IP -6 addr add 2001:db8:92::1/64 dev veth3 nodad $IP li set veth2 netns peer up ip -netns peer addr add 172.16.1.2/24 dev veth2 - ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 + ip -netns peer -6 addr add 2001:db8:91::2/64 dev veth2 nodad $IP li set veth4 netns peer up ip -netns peer addr add 172.16.2.2/24 dev veth4 - ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 + ip -netns peer -6 addr add 2001:db8:92::2/64 dev veth4 nodad ip -netns remote li add veth5 type veth peer name veth6 ip -netns remote li set veth5 up ip -netns remote addr add dev veth5 172.16.101.1/24 - ip -netns remote addr add dev veth5 2001:db8:101::1/64 + ip -netns remote -6 addr add dev veth5 2001:db8:101::1/64 nodad ip -netns remote ro add 172.16.0.0/22 via 172.16.101.2 ip -netns remote -6 ro add 2001:db8:90::/40 via 2001:db8:101::2 ip -netns remote li set veth6 netns peer up ip -netns peer addr add dev veth6 172.16.101.2/24 - ip -netns peer addr add dev veth6 2001:db8:101::2/64 + ip -netns peer -6 addr add dev veth6 2001:db8:101::2/64 nodad set +e } @@ -248,7 +248,7 @@ check_route6() local expected="$2" local out - out=$($IP -6 route ls match ${pfx} 2>/dev/null) + out=$($IP -6 route ls match ${pfx} 2>/dev/null | sed -e 's/pref medium//') check_output "${out}" "${expected}" } @@ -423,8 +423,6 @@ ipv6_fcnal_runtime() echo "IPv6 functional runtime" echo "-----------------------" - sleep 5 - # # IPv6 - the basics # @@ -481,12 +479,12 @@ ipv6_fcnal_runtime() run_cmd "$IP -6 nexthop add id 85 dev veth1" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 85" log_test $? 0 "IPv6 route with device only nexthop" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024 pref medium" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024" run_cmd "$IP nexthop add id 123 group 81/85" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 123" log_test $? 0 "IPv6 multipath route with nexthop mix - dev only + gw" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1 pref medium" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1" # # IPv6 route with v4 nexthop - not allowed @@ -749,6 +747,29 @@ ipv4_fcnal_runtime() run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" log_test $? 0 "Ping - multipath" + run_cmd "$IP ro delete 172.16.101.1/32 nhid 122" + + # + # multiple default routes + # - tests fib_select_default + run_cmd "$IP nexthop add id 501 via 172.16.1.2 dev veth1" + run_cmd "$IP ro add default nhid 501" + run_cmd "$IP ro add default via 172.16.1.3 dev veth1 metric 20" + run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" + log_test $? 0 "Ping - multiple default routes, nh first" + + # flip the order + run_cmd "$IP ro del default nhid 501" + run_cmd "$IP ro del default via 172.16.1.3 dev veth1 metric 20" + run_cmd "$IP ro add default via 172.16.1.2 dev veth1 metric 20" + run_cmd "$IP nexthop replace id 501 via 172.16.1.3 dev veth1" + run_cmd "$IP ro add default nhid 501 metric 20" + run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" + log_test $? 0 "Ping - multiple default routes, nh second" + + run_cmd "$IP nexthop delete nhid 501" + run_cmd "$IP ro del default" + # # IPv4 with blackhole nexthops # @@ -843,6 +864,11 @@ ipv4_fcnal_runtime() $IP neigh sh | grep 'dev veth1' fi + run_cmd "$IP ro del 172.16.101.1/32 via inet6 ${lladdr} dev veth1" + run_cmd "$IP -4 ro add default via inet6 ${lladdr} dev veth1" + run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" + log_test $? 0 "IPv4 default route with IPv6 gateway" + # # MPLS as an example of LWT encap # diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index b7616704b55e..84205c3a55eb 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -618,16 +618,22 @@ fib_nexthop_test() fib_suppress_test() { + echo + echo "FIB rule with suppress_prefixlength" + setup + $IP link add dummy1 type dummy $IP link set dummy1 up $IP -6 route add default dev dummy1 $IP -6 rule add table main suppress_prefixlength 0 - ping -f -c 1000 -W 1 1234::1 || true + ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1 $IP -6 rule del table main suppress_prefixlength 0 $IP link del dummy1 # If we got here without crashing, we're good. - return 0 + log_test 0 0 "FIB rule suppress test" + + cleanup } ################################################################################ diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh index b50081855913..1181d647f6a7 100755 --- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh +++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh @@ -20,10 +20,14 @@ ALL_TESTS=" ping_ipv4 + ping_ipv6 test_ip_dsfield test_ip_dscp test_ip_ecn test_ip_dscp_ecn + test_ip6_dsfield + test_ip6_dscp + test_ip6_ecn " NUM_NETIFS=4 @@ -107,6 +111,11 @@ ping_ipv4() ping_test $h1 192.0.2.2 } +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + do_test_pedit_dsfield_common() { local pedit_locus=$1; shift @@ -228,6 +237,63 @@ test_ip_dscp_ecn() do_test_ip_dscp_ecn "dev $swp2 egress" } +do_test_ip6_dsfield() +{ + local locus=$1; shift + local dsfield + + for dsfield in 0 1 2 3 128 252 253 254 255; do + do_test_pedit_dsfield "$locus" \ + "ip6 traffic_class set $dsfield" \ + ipv6 "ip_tos $dsfield" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" + done +} + +test_ip6_dsfield() +{ + do_test_ip6_dsfield "dev $swp1 ingress" + do_test_ip6_dsfield "dev $swp2 egress" +} + +do_test_ip6_dscp() +{ + local locus=$1; shift + local dscp + + for dscp in 0 1 2 3 32 61 62 63; do + do_test_pedit_dsfield "$locus" \ + "ip6 traffic_class set $((dscp << 2)) retain 0xfc" \ + ipv6 "ip_tos $(((dscp << 2) | 1))" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" + done +} + +test_ip6_dscp() +{ + do_test_ip6_dscp "dev $swp1 ingress" + do_test_ip6_dscp "dev $swp2 egress" +} + +do_test_ip6_ecn() +{ + local locus=$1; shift + local ecn + + for ecn in 0 1 2 3; do + do_test_pedit_dsfield "$locus" \ + "ip6 traffic_class set $ecn retain 0x3" \ + ipv6 "ip_tos $((124 | $ecn))" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" + done +} + +test_ip6_ecn() +{ + do_test_ip6_ecn "dev $swp1 ingress" + do_test_ip6_ecn "dev $swp2 egress" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 71a62e7e35b1..77c09cd339c3 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -67,6 +67,10 @@ # Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6 # encapsulation (GUE) over IPv4/IPv6, instead of VXLAN # +# - pmtu_ipv{4,6}_ipv{4,6}_exception +# Same as pmtu_ipv4_vxlan4, but using a IPv4/IPv6 tunnel over IPv4/IPv6, +# instead of VXLAN +# # - pmtu_vti4_exception # Set up vti tunnel on top of veth, with xfrm states and policies, in two # namespaces with matching endpoints. Check that route exception is not @@ -151,6 +155,10 @@ tests=" pmtu_ipv6_gue4_exception IPv6 over gue4: PMTU exceptions 1 pmtu_ipv4_gue6_exception IPv4 over gue6: PMTU exceptions 1 pmtu_ipv6_gue6_exception IPv6 over gue6: PMTU exceptions 1 + pmtu_ipv4_ipv4_exception IPv4 over IPv4: PMTU exceptions 1 + pmtu_ipv6_ipv4_exception IPv6 over IPv4: PMTU exceptions 1 + pmtu_ipv4_ipv6_exception IPv4 over IPv6: PMTU exceptions 1 + pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1 pmtu_vti6_exception vti6: PMTU exceptions 0 pmtu_vti4_exception vti4: PMTU exceptions 0 pmtu_vti4_default_mtu vti4: default MTU assignment 0 @@ -363,6 +371,62 @@ setup_gue66() { setup_fou_or_gue 6 6 gue } +setup_ipvX_over_ipvY() { + inner=${1} + outer=${2} + + if [ "${outer}" -eq 4 ]; then + a_addr="${prefix4}.${a_r1}.1" + b_addr="${prefix4}.${b_r1}.1" + if [ "${inner}" -eq 4 ]; then + type="ipip" + mode="ipip" + else + type="sit" + mode="ip6ip" + fi + else + a_addr="${prefix6}:${a_r1}::1" + b_addr="${prefix6}:${b_r1}::1" + type="ip6tnl" + if [ "${inner}" -eq 4 ]; then + mode="ipip6" + else + mode="ip6ip6" + fi + fi + + run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return 2 + run_cmd ${ns_b} ip link add ip_b type ${type} local ${b_addr} remote ${a_addr} mode ${mode} + + run_cmd ${ns_a} ip link set ip_a up + run_cmd ${ns_b} ip link set ip_b up + + if [ "${inner}" = "4" ]; then + run_cmd ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ip_a + run_cmd ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ip_b + else + run_cmd ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ip_a + run_cmd ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ip_b + fi +} + +setup_ip4ip4() { + setup_ipvX_over_ipvY 4 4 +} + +setup_ip6ip4() { + setup_ipvX_over_ipvY 6 4 +} + +setup_ip4ip6() { + setup_ipvX_over_ipvY 4 6 +} + +setup_ip6ip6() { + setup_ipvX_over_ipvY 6 6 +} + setup_namespaces() { for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do ip netns add ${n} || return 1 @@ -908,6 +972,64 @@ test_pmtu_ipv6_gue6_exception() { test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue } +test_pmtu_ipvX_over_ipvY_exception() { + inner=${1} + outer=${2} + ll_mtu=4000 + + setup namespaces routing ip${inner}ip${outer} || return 2 + + trace "${ns_a}" ip_a "${ns_b}" ip_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B + + if [ ${inner} -eq 4 ]; then + ping=ping + dst=${tunnel4_b_addr} + else + ping=${ping6} + dst=${tunnel6_b_addr} + fi + + if [ ${outer} -eq 4 ]; then + # IPv4 header + exp_mtu=$((${ll_mtu} - 20)) + else + # IPv6 header Option 4 + exp_mtu=$((${ll_mtu} - 40 - 8)) + fi + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ip_a $((${ll_mtu} + 1000)) || return + mtu "${ns_b}" ip_b $((${ll_mtu} + 1000)) || return + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} + + # Check that exception was created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ip${inner}ip${outer} interface" +} + +test_pmtu_ipv4_ipv4_exception() { + test_pmtu_ipvX_over_ipvY_exception 4 4 +} + +test_pmtu_ipv6_ipv4_exception() { + test_pmtu_ipvX_over_ipvY_exception 6 4 +} + +test_pmtu_ipv4_ipv6_exception() { + test_pmtu_ipvX_over_ipvY_exception 4 6 +} + +test_pmtu_ipv6_ipv6_exception() { + test_pmtu_ipvX_over_ipvY_exception 6 6 +} + test_pmtu_vti4_exception() { setup namespaces veth vti4 xfrm4 || return 2 trace "${ns_a}" veth_a "${ns_b}" veth_b \ diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh new file mode 100755 index 000000000000..184da81f554f --- /dev/null +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -0,0 +1,436 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Various combinations of VRF with xfrms and qdisc. + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +PAUSE_ON_FAIL=no +VERBOSE=0 +ret=0 + +HOST1_4=192.168.1.1 +HOST2_4=192.168.1.2 +HOST1_6=2001:db8:1::1 +HOST2_6=2001:db8:1::2 + +XFRM1_4=10.0.1.1 +XFRM2_4=10.0.1.2 +XFRM1_6=fc00:1000::1 +XFRM2_6=fc00:1000::2 +IF_ID=123 + +VRF=red +TABLE=300 + +AUTH_1=0xd94fcfea65fddf21dc6e0d24a0253508 +AUTH_2=0xdc6e0d24a0253508d94fcfea65fddf21 +ENC_1=0xfc46c20f8048be9725930ff3fb07ac2a91f0347dffeacf62 +ENC_2=0x3fb07ac2a91f0347dffeacf62fc46c20f8048be9725930ff +SPI_1=0x02122b77 +SPI_2=0x2b770212 + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +run_cmd_host1() +{ + local cmd="$*" + local out + local rc + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + fi + + out=$(eval ip netns exec host1 $cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" ]; then + if [ -n "$out" ]; then + echo + echo " $out" + fi + echo + fi + + return $rc +} + +################################################################################ +# create namespaces for hosts and sws + +create_vrf() +{ + local ns=$1 + local vrf=$2 + local table=$3 + + if [ -n "${ns}" ]; then + ns="-netns ${ns}" + fi + + ip ${ns} link add ${vrf} type vrf table ${table} + ip ${ns} link set ${vrf} up + ip ${ns} route add vrf ${vrf} unreachable default metric 8192 + ip ${ns} -6 route add vrf ${vrf} unreachable default metric 8192 + + ip ${ns} addr add 127.0.0.1/8 dev ${vrf} + ip ${ns} -6 addr add ::1 dev ${vrf} nodad + + ip ${ns} ru del pref 0 + ip ${ns} ru add pref 32765 from all lookup local + ip ${ns} -6 ru del pref 0 + ip ${ns} -6 ru add pref 32765 from all lookup local +} + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + [ -z "${addr}" ] && addr="-" + [ -z "${addr6}" ] && addr6="-" + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + local ns1arg + local ns2arg + + if [ -n "${ns1}" ]; then + ns1arg="-netns ${ns1}" + fi + if [ -n "${ns2}" ]; then + ns2arg="-netns ${ns2}" + fi + + ip ${ns1arg} li add ${ns1_dev} type veth peer name tmp + ip ${ns1arg} li set ${ns1_dev} up + ip ${ns1arg} li set tmp netns ${ns2} name ${ns2_dev} + ip ${ns2arg} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr} + ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip ${ns1arg} addr add dev ${ns1_dev} ${ns1_addr6} nodad + ip ${ns2arg} addr add dev ${ns2_dev} ${ns2_addr6} nodad + fi +} + +################################################################################ + +cleanup() +{ + ip netns del host1 + ip netns del host2 +} + +setup() +{ + create_ns "host1" + create_ns "host2" + + connect_ns "host1" eth0 ${HOST1_4}/24 ${HOST1_6}/64 \ + "host2" eth0 ${HOST2_4}/24 ${HOST2_6}/64 + + create_vrf "host1" ${VRF} ${TABLE} + ip -netns host1 link set dev eth0 master ${VRF} +} + +cleanup_xfrm() +{ + for ns in host1 host2 + do + for x in state policy + do + ip -netns ${ns} xfrm ${x} flush + ip -6 -netns ${ns} xfrm ${x} flush + done + done +} + +setup_xfrm() +{ + local h1_4=$1 + local h2_4=$2 + local h1_6=$3 + local h2_6=$4 + local devarg="$5" + + # + # policy + # + + # host1 - IPv4 out + ip -netns host1 xfrm policy add \ + src ${h1_4} dst ${h2_4} ${devarg} dir out \ + tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel + + # host2 - IPv4 in + ip -netns host2 xfrm policy add \ + src ${h1_4} dst ${h2_4} dir in \ + tmpl src ${HOST1_4} dst ${HOST2_4} proto esp mode tunnel + + # host1 - IPv4 in + ip -netns host1 xfrm policy add \ + src ${h2_4} dst ${h1_4} ${devarg} dir in \ + tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel + + # host2 - IPv4 out + ip -netns host2 xfrm policy add \ + src ${h2_4} dst ${h1_4} dir out \ + tmpl src ${HOST2_4} dst ${HOST1_4} proto esp mode tunnel + + + # host1 - IPv6 out + ip -6 -netns host1 xfrm policy add \ + src ${h1_6} dst ${h2_6} ${devarg} dir out \ + tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel + + # host2 - IPv6 in + ip -6 -netns host2 xfrm policy add \ + src ${h1_6} dst ${h2_6} dir in \ + tmpl src ${HOST1_6} dst ${HOST2_6} proto esp mode tunnel + + # host1 - IPv6 in + ip -6 -netns host1 xfrm policy add \ + src ${h2_6} dst ${h1_6} ${devarg} dir in \ + tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel + + # host2 - IPv6 out + ip -6 -netns host2 xfrm policy add \ + src ${h2_6} dst ${h1_6} dir out \ + tmpl src ${HOST2_6} dst ${HOST1_6} proto esp mode tunnel + + # + # state + # + ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_4} dst ${h2_4} ${devarg} + + ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_4} dst ${h2_4} + + + ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_4} dst ${h1_4} ${devarg} + + ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_4} dst ${h1_4} + + + ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_6} dst ${h2_6} ${devarg} + + ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ + proto esp spi ${SPI_1} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ + enc 'cbc(des3_ede)' ${ENC_1} \ + sel src ${h1_6} dst ${h2_6} + + + ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_6} dst ${h1_6} ${devarg} + + ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ + proto esp spi ${SPI_2} reqid 0 mode tunnel \ + replay-window 4 replay-oseq 0x4 \ + auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ + enc 'cbc(des3_ede)' ${ENC_2} \ + sel src ${h2_6} dst ${h1_6} +} + +cleanup_xfrm_dev() +{ + ip -netns host1 li del xfrm0 + ip -netns host2 addr del ${XFRM2_4}/24 dev eth0 + ip -netns host2 addr del ${XFRM2_6}/64 dev eth0 +} + +setup_xfrm_dev() +{ + local vrfarg="vrf ${VRF}" + + ip -netns host1 li add type xfrm dev eth0 if_id ${IF_ID} + ip -netns host1 li set xfrm0 ${vrfarg} up + ip -netns host1 addr add ${XFRM1_4}/24 dev xfrm0 + ip -netns host1 addr add ${XFRM1_6}/64 dev xfrm0 + + ip -netns host2 addr add ${XFRM2_4}/24 dev eth0 + ip -netns host2 addr add ${XFRM2_6}/64 dev eth0 + + setup_xfrm ${XFRM1_4} ${XFRM2_4} ${XFRM1_6} ${XFRM2_6} "if_id ${IF_ID}" +} + +run_tests() +{ + cleanup_xfrm + + # no IPsec + run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + log_test $? 0 "IPv4 no xfrm policy" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + log_test $? 0 "IPv6 no xfrm policy" + + # xfrm without VRF in sel + setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} + run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + log_test $? 0 "IPv4 xfrm policy based on address" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + log_test $? 0 "IPv6 xfrm policy based on address" + cleanup_xfrm + + # xfrm with VRF in sel + # Known failure: ipv4 resets the flow oif after the lookup. Fix is + # not straightforward. + # setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev ${VRF}" + # run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + # log_test $? 0 "IPv4 xfrm policy with VRF in selector" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + log_test $? 0 "IPv6 xfrm policy with VRF in selector" + cleanup_xfrm + + # xfrm with enslaved device in sel + # Known failures: combined with the above, __xfrm{4,6}_selector_match + # needs to consider both l3mdev and enslaved device index. + # setup_xfrm ${HOST1_4} ${HOST2_4} ${HOST1_6} ${HOST2_6} "dev eth0" + # run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${HOST2_4} + # log_test $? 0 "IPv4 xfrm policy with enslaved device in selector" + # run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${HOST2_6} + # log_test $? 0 "IPv6 xfrm policy with enslaved device in selector" + # cleanup_xfrm + + # xfrm device + setup_xfrm_dev + run_cmd_host1 ip vrf exec ${VRF} ping -c1 -w1 ${XFRM2_4} + log_test $? 0 "IPv4 xfrm policy with xfrm device" + run_cmd_host1 ip vrf exec ${VRF} ${ping6} -c1 -w1 ${XFRM2_6} + log_test $? 0 "IPv6 xfrm policy with xfrm device" + cleanup_xfrm_dev +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -p Pause on fail + -v verbose mode (show commands and output) + +done +EOF +} + +################################################################################ +# main + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +cleanup 2>/dev/null +setup + +echo +echo "No qdisc on VRF device" +run_tests + +run_cmd_host1 tc qdisc add dev ${VRF} root netem delay 100ms +echo +echo "netem qdisc on VRF device" +run_tests + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} + +exit $ret diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 89fb3e0b552e..c0aa46ce14f6 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -2803,12 +2803,13 @@ TEST(syscall_restart) offsetof(struct seccomp_data, nr)), #ifdef __NR_sigreturn - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 6, 0), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 7, 0), #endif - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 5, 0), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 4, 0), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 3, 0), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 4, 0), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 6, 0), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 5, 0), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 4, 0), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 5, 0), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_clock_nanosleep, 4, 0), BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_restart_syscall, 4, 0), /* Allow __NR_write for easy logging. */ @@ -2895,7 +2896,8 @@ TEST(syscall_restart) ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16)); ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg)); ASSERT_EQ(0x100, msg); - EXPECT_EQ(__NR_nanosleep, get_syscall(_metadata, child_pid)); + ret = get_syscall(_metadata, child_pid); + EXPECT_TRUE(ret == __NR_nanosleep || ret == __NR_clock_nanosleep); /* Might as well check siginfo for sanity while we're here. */ ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info)); diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json index f8ea6f5fa8e9..72cdc3c800a5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json @@ -1472,6 +1472,31 @@ ] }, { + "id": "94bb", + "name": "Add pedit action with LAYERED_OP ip6 traffic_class", + "category": [ + "actions", + "pedit", + "layered_op" + ], + "setup": [ + [ + "$TC actions flush action pedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pedit ex munge ip6 traffic_class set 0x40 continue", + "expExitCode": "0", + "verifyCmd": "$TC actions list action pedit", + "matchPattern": "ipv6\\+0: val 04000000 mask f00fffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action pedit" + ] + }, + { "id": "6f5e", "name": "Add pedit action with LAYERED_OP ip6 flow_lbl", "category": [ diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index e566c70e64a1..a3e43189d940 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -713,9 +713,8 @@ def set_operation_mode(pm, parser, args, remaining): exit(0) if args.list: - if args.list: - list_test_cases(alltests) - exit(0) + list_test_cases(alltests) + exit(0) if len(alltests): req_plugins = pm.get_required_plugins(alltests) diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index b630c7b5950a..8155c2ea7ccb 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -1,17 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -self.flags = flags -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - - -if [ -f /dev/tpm0 ] ; then - python -m unittest -v tpm2_tests.SmokeTest - python -m unittest -v tpm2_tests.AsyncTest -else - exit $ksft_skip -fi +python -m unittest -v tpm2_tests.SmokeTest +python -m unittest -v tpm2_tests.AsyncTest CLEAR_CMD=$(which tpm2_clear) if [ -n $CLEAR_CMD ]; then diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index 180b469c53b4..a6f5e346635e 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -1,11 +1,4 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - -if [ -f /dev/tpmrm0 ] ; then - python -m unittest -v tpm2_tests.SpaceTest -else - exit $ksft_skip -fi +python -m unittest -v tpm2_tests.SpaceTest diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index d31db052dff6..6998877f707e 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for vm selftests uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/') +MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/') CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) LDLIBS = -lrt @@ -20,7 +20,7 @@ TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd -ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) +ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index 665009ebfba4..76ca5e7a3951 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -59,7 +59,7 @@ else fi #filter 64bit architectures -ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64" +ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64" if [ -z $ARCH ]; then ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'` fi diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index f33f32f1d208..b587b9a7a124 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -4,7 +4,7 @@ test: virtio_test vringh_test virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o -CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE +CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h vpath %.c ../../drivers/virtio ../../drivers/vhost mod: ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V} @@ -22,7 +22,8 @@ OOT_CONFIGS=\ CONFIG_VHOST=m \ CONFIG_VHOST_NET=n \ CONFIG_VHOST_SCSI=n \ - CONFIG_VHOST_VSOCK=n + CONFIG_VHOST_VSOCK=n \ + CONFIG_VHOST_RING=n OOT_BUILD=KCFLAGS="-I "${OOT_VHOST} ${MAKE} -C ${OOT_KSRC} V=${V} oot-build: echo "UNSUPPORTED! Don't use the resulting modules in production!" diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index d0351f83aebe..04d563fc9b95 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <stdlib.h> #if defined(__i386__) || defined(__x86_64__) #define barrier() asm volatile("" ::: "memory") #define virt_mb() __sync_synchronize() diff --git a/tools/virtio/generated/autoconf.h b/tools/virtio/generated/autoconf.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/virtio/generated/autoconf.h diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h index 903dc9c4bd11..2c51bccb97bb 100644 --- a/tools/virtio/linux/compiler.h +++ b/tools/virtio/linux/compiler.h @@ -7,4 +7,5 @@ #define READ_ONCE(var) (*((volatile typeof(var) *)(&(var)))) +#define __aligned(x) __attribute((__aligned__(x))) #endif diff --git a/tools/vm/Makefile b/tools/vm/Makefile index 20f6cf04377f..9860622cbb15 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for vm tools # +include ../scripts/Makefile.include + TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api |